From 863580418bc82062083be854355f2213d3d804f5 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 1 Sep 2021 14:43:50 +0300 Subject: [PATCH 001/866] regulator: qcom-rpmh-regulator: fix pm8009-1 ldo7 resource name Fix a typo in the pm8009 LDO7 declaration, it uses resource name ldo%s6 instead of ldo%s7. Fixes: 951384cabc5d ("regulator: qcom-rpmh-regulator: add pm8009-1 chip revision") Signed-off-by: Dmitry Baryshkov Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210901114350.1106073-1-dmitry.baryshkov@linaro.org Signed-off-by: Mark Brown --- drivers/regulator/qcom-rpmh-regulator.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 6cca910a76de..7f458d510483 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -991,7 +991,7 @@ static const struct rpmh_vreg_init_data pm8009_1_vreg_data[] = { RPMH_VREG("ldo4", "ldo%s4", &pmic5_nldo, "vdd-l4"), RPMH_VREG("ldo5", "ldo%s5", &pmic5_pldo, "vdd-l5-l6"), RPMH_VREG("ldo6", "ldo%s6", &pmic5_pldo, "vdd-l5-l6"), - RPMH_VREG("ldo7", "ldo%s6", &pmic5_pldo_lv, "vdd-l7"), + RPMH_VREG("ldo7", "ldo%s7", &pmic5_pldo_lv, "vdd-l7"), {} }; From 49ca6153208f6efc409c1deb82dd5bcbb519d7e1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 24 Aug 2021 09:39:31 +0200 Subject: [PATCH 002/866] bpf: Relicense disassembler as GPL-2.0-only OR BSD-2-Clause Some time ago we dual-licensed both libbpf and bpftool through commits 1bc38b8ff6cc ("libbpf: relicense libbpf as LGPL-2.1 OR BSD-2-Clause") and 907b22365115 ("tools: bpftool: dual license all files"). The latter missed the disasm.{c,h} which we pull in via kernel/bpf/ such that we have a single source for verifier as well as bpftool asm dumping, see also f4ac7e0b5cc8 ("bpf: move instruction printing into a separate file"). It is currently GPL-2.0-only and missed the conversion in 907b22365115, therefore relicense the two as GPL-2.0-only OR BSD-2-Clause as well. Spotted-by: Quentin Monnet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Thomas Graf Acked-by: Brendan Jackman Acked-by: Jakub Kicinski Acked-by: Jiri Olsa Acked-by: Simon Horman Acked-by: Martin KaFai Lau Acked-by: Xu Kuohai Acked-by: Edward Cree --- kernel/bpf/disasm.c | 2 +- kernel/bpf/disasm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index ca3cd9aaa6ce..7b4afb7d96db 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h index e546b18d27da..a4b040793f44 100644 --- a/kernel/bpf/disasm.h +++ b/kernel/bpf/disasm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ From 1fd95c05d8f742abfe906620780aee4dbe1a2db0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 2 Sep 2021 11:36:01 -0400 Subject: [PATCH 003/866] ext4: add error checking to ext4_ext_replay_set_iblocks() If the call to ext4_map_blocks() fails due to an corrupted file system, ext4_ext_replay_set_iblocks() can get stuck in an infinite loop. This could be reproduced by running generic/526 with a file system that has inline_data and fast_commit enabled. The system will repeatedly log to the console: EXT4-fs warning (device dm-3): ext4_block_to_path:105: block 1074800922 > max in inode 131076 and the stack that it gets stuck in is: ext4_block_to_path+0xe3/0x130 ext4_ind_map_blocks+0x93/0x690 ext4_map_blocks+0x100/0x660 skip_hole+0x47/0x70 ext4_ext_replay_set_iblocks+0x223/0x440 ext4_fc_replay_inode+0x29e/0x3b0 ext4_fc_replay+0x278/0x550 do_one_pass+0x646/0xc10 jbd2_journal_recover+0x14a/0x270 jbd2_journal_load+0xc4/0x150 ext4_load_journal+0x1f3/0x490 ext4_fill_super+0x22d4/0x2c00 With this patch, generic/526 still fails, but system is no longer locking up in a tight loop. It's likely the root casue is that fast_commit replay is corrupting file systems with inline_data, and we probably need to add better error handling in the fast commit replay code path beyond what is done here, which essentially just breaks the infinite loop without reporting the to the higher levels of the code. Fixes: 8016E29F4362 ("ext4: fast commit recovery path") Cc: stable@kernel.org Cc: Harshad Shirwadkar Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index eb1dd4f024f2..e57019cc3601 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5913,7 +5913,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) } /* Check if *cur is a hole and if it is, skip it */ -static void skip_hole(struct inode *inode, ext4_lblk_t *cur) +static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; @@ -5922,9 +5922,12 @@ static void skip_hole(struct inode *inode, ext4_lblk_t *cur) map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; if (ret != 0) - return; + return 0; *cur = *cur + map.m_len; + return 0; } /* Count number of blocks used by this inode and update i_blocks */ @@ -5973,7 +5976,9 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) * iblocks by total number of differences found. */ cur = 0; - skip_hole(inode, &cur); + ret = skip_hole(inode, &cur); + if (ret < 0) + goto out; path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; @@ -5992,8 +5997,12 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); - skip_hole(inode, &cur); - + ret = skip_hole(inode, &cur); + if (ret < 0) { + ext4_ext_drop_refs(path); + kfree(path); + break; + } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { ext4_ext_drop_refs(path); From aeef8b5089b76852bd84889f2809e69a7cfb414e Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Wed, 11 Aug 2021 17:07:37 -0400 Subject: [PATCH 004/866] x86/pat: Pass valid address to sanitize_phys() The end address passed to memtype_reserve() is handed directly to sanitize_phys(). However, end is exclusive and sanitize_phys() expects an inclusive address. If end falls at the end of the physical address space, sanitize_phys() will return 0. This can result in drivers failing to load, and the following warning: WARNING: CPU: 26 PID: 749 at arch/x86/mm/pat.c:354 reserve_memtype+0x262/0x450 reserve_memtype failed: [mem 0x3ffffff00000-0xffffffffffffffff], req uncached-minus Call Trace: [] reserve_memtype+0x262/0x450 [] ioremap_nocache+0x1a/0x20 [] mpt3sas_base_map_resources+0x151/0xa60 [mpt3sas] [] mpt3sas_base_attach+0xf5/0xa50 [mpt3sas] ---[ end trace 6d6eea4438db89ef ]--- ioremap reserve_memtype failed -22 mpt3sas_cm0: unable to map adapter memory! or resource not found mpt3sas_cm0: failure at drivers/scsi/mpt3sas/mpt3sas_scsih.c:10597/_scsih_probe()! Fix this by passing the inclusive end address to sanitize_phys(). Fixes: 510ee090abc3 ("x86/mm/pat: Prepare {reserve, free}_memtype() for "decoy" addresses") Signed-off-by: Jeff Moyer Signed-off-by: Thomas Gleixner Reviewed-by: David Hildenbrand Reviewed-by: Dan Williams Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/x49o8a3pu5i.fsf@segfault.boston.devel.redhat.com --- arch/x86/mm/pat/memtype.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 3112ca7786ed..4ba2a3ee4bce 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type, int err = 0; start = sanitize_phys(start); - end = sanitize_phys(end); + + /* + * The end address passed into this function is exclusive, but + * sanitize_phys() expects an inclusive address. + */ + end = sanitize_phys(end - 1) + 1; if (start >= end) { WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__, start, end - 1, cattr_name(req_type)); From d7109fe3a0991a0f7b4ac099b78c908e3b619787 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 26 Aug 2021 18:03:17 +0300 Subject: [PATCH 005/866] x86/platform: Increase maximum GPIO number for X86_64 By default the 512 GPIOs is the maximum on any x86 platform. With, for example, Intel Tiger Lake-H the SoC based controller occupies up to 480 pins. This leaves only 32 available for GPIO expanders or other drivers, like PMIC. Hence, bump the maximum GPIO number to 1024 for X86_64 and leave 512 for X86_32. Signed-off-by: Andy Shevchenko Signed-off-by: Thomas Gleixner Reviewed-by: Linus Walleij Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20210826150317.29435-1-andriy.shevchenko@linux.intel.com --- arch/x86/Kconfig | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 421fa9e38c60..10163887c5eb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -340,6 +340,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK config ARCH_HIBERNATION_POSSIBLE def_bool y +config ARCH_NR_GPIO + int + default 1024 if X86_64 + default 512 + config ARCH_SUSPEND_POSSIBLE def_bool y From 0ddc5e55e6f1da1286fb2646f4248bf7da31a601 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 3 Sep 2021 09:29:07 +0100 Subject: [PATCH 006/866] Documentation: Fix irq-domain.rst build warning Correctly escape the * not to be used as emphasis. Also take this opportunity to clarify the fate of the rest of the legacy APIs. Reported-by: Stephen Rothwell Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210903085343.923036-1-maz@kernel.org --- Documentation/core-api/irq/irq-domain.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst index 6979b4af2c1f..9c0e8758037a 100644 --- a/Documentation/core-api/irq/irq-domain.rst +++ b/Documentation/core-api/irq/irq-domain.rst @@ -175,9 +175,10 @@ for IRQ numbers that are passed to struct device registrations. In that case the Linux IRQ numbers cannot be dynamically assigned and the legacy mapping should be used. -As the name implies, the *_legacy() functions are deprecated and only +As the name implies, the \*_legacy() functions are deprecated and only exist to ease the support of ancient platforms. No new users should be -added. +added. Same goes for the \*_simple() functions when their use results +in the legacy behaviour. The legacy map assumes a contiguous range of IRQ numbers has already been allocated for the controller and that the IRQ number can be From f1940d4e9cbe6208e7e77e433c587af108152a17 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 31 Aug 2021 16:39:16 +0200 Subject: [PATCH 007/866] Drivers: hv: vmbus: Fix kernel crash upon unbinding a device from uio_hv_generic driver The following crash happens when a never-used device is unbound from uio_hv_generic driver: kernel BUG at mm/slub.c:321! invalid opcode: 0000 [#1] SMP PTI CPU: 0 PID: 4001 Comm: bash Kdump: loaded Tainted: G X --------- --- 5.14.0-0.rc2.23.el9.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 12/07/2018 RIP: 0010:__slab_free+0x1d5/0x3d0 ... Call Trace: ? pick_next_task_fair+0x18e/0x3b0 ? __cond_resched+0x16/0x40 ? vunmap_pmd_range.isra.0+0x154/0x1c0 ? __vunmap+0x22d/0x290 ? hv_ringbuffer_cleanup+0x36/0x40 [hv_vmbus] kfree+0x331/0x380 ? hv_uio_remove+0x43/0x60 [uio_hv_generic] hv_ringbuffer_cleanup+0x36/0x40 [hv_vmbus] vmbus_free_ring+0x21/0x60 [hv_vmbus] hv_uio_remove+0x4f/0x60 [uio_hv_generic] vmbus_remove+0x23/0x30 [hv_vmbus] __device_release_driver+0x17a/0x230 device_driver_detach+0x3c/0xa0 unbind_store+0x113/0x130 ... The problem appears to be that we free 'ring_info->pkt_buffer' twice: first, when the device is unbound from in-kernel driver (netvsc in this case) and second from hv_uio_remove(). Normally, ring buffer is supposed to be re-initialized from hv_uio_open() but this happens when UIO device is being opened and this is not guaranteed to happen. Generally, it is OK to call hv_ringbuffer_cleanup() twice for the same channel (which is being handed over between in-kernel drivers and UIO) even if we didn't call hv_ringbuffer_init() in between. We, however, need to avoid kfree() call for an already freed pointer. Fixes: adae1e931acd ("Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer") Signed-off-by: Vitaly Kuznetsov Reviewed-by: Andrea Parri Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210831143916.144983-1-vkuznets@redhat.com Signed-off-by: Wei Liu --- drivers/hv/ring_buffer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 2aee356840a2..314015d9e912 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -245,6 +245,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) mutex_unlock(&ring_info->ring_buffer_mutex); kfree(ring_info->pkt_buffer); + ring_info->pkt_buffer = NULL; ring_info->pkt_buffer_size = 0; } From 5457773ef99f25fcc4b238ac76b68e28273250f4 Mon Sep 17 00:00:00 2001 From: Tobias Schramm Date: Fri, 27 Aug 2021 07:03:57 +0200 Subject: [PATCH 008/866] spi: rockchip: handle zero length transfers without timing out Previously zero length transfers submitted to the Rokchip SPI driver would time out in the SPI layer. This happens because the SPI peripheral does not trigger a transfer completion interrupt for zero length transfers. Fix that by completing zero length transfers immediately at start of transfer. Signed-off-by: Tobias Schramm Link: https://lore.kernel.org/r/20210827050357.165409-1-t.schramm@manjaro.org Signed-off-by: Mark Brown --- drivers/spi/spi-rockchip.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 540861ca2ba3..553b6b9d0222 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -600,6 +600,12 @@ static int rockchip_spi_transfer_one( int ret; bool use_dma; + /* Zero length transfers won't trigger an interrupt on completion */ + if (!xfer->len) { + spi_finalize_current_transfer(ctlr); + return 1; + } + WARN_ON(readl_relaxed(rs->regs + ROCKCHIP_SPI_SSIENR) && (readl_relaxed(rs->regs + ROCKCHIP_SPI_SR) & SR_BUSY)); From 4df031ff5876d94b48dd9ee486ba5522382a06b2 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 16 Jul 2021 20:20:21 +0800 Subject: [PATCH 009/866] ext4: check and update i_disksize properly After commit 3da40c7b0898 ("ext4: only call ext4_truncate when size <= isize"), i_disksize could always be updated to i_size in ext4_setattr(), and we could sure that i_disksize <= i_size since holding inode lock and if i_disksize < i_size there are delalloc writes pending in the range upto i_size. If the end of the current write is <= i_size, there's no need to touch i_disksize since writeback will push i_disksize upto i_size eventually. So we can switch to check i_size instead of i_disksize in ext4_da_write_end() when write to the end of the file. we also could remove ext4_mark_inode_dirty() together because we defer inode dirtying to generic_write_end() or ext4_da_write_inline_data_end(). Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210716122024.1105856-2-yi.zhang@huawei.com --- fs/ext4/inode.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2c33c795c4a7..76d9e25fe62c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3084,35 +3084,37 @@ static int ext4_da_write_end(struct file *file, end = start + copied - 1; /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range upto i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize upto i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block (ext4_da_should_update_i_disksize() + * check), we need to update i_disksize here as neither + * ext4_writepage() nor certain ext4_writepages() paths not + * allocating blocks update i_disksize. + * + * Note that we defer inode dirtying to generic_write_end() / + * ext4_da_write_inline_data_end(). */ new_i_size = pos + copied; - if (copied && new_i_size > EXT4_I(inode)->i_disksize) { + if (copied && new_i_size > inode->i_size) { if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) { + ext4_da_should_update_i_disksize(page, end)) ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ret = ext4_mark_inode_dirty(handle, inode); - } } if (write_mode != CONVERT_INLINE_DATA && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && ext4_has_inline_data(inode)) - ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, + ret = ext4_da_write_inline_data_end(inode, pos, len, copied, page); else - ret2 = generic_write_end(file, mapping, pos, len, copied, + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - copied = ret2; - if (ret2 < 0) - ret = ret2; + copied = ret; ret2 = ext4_journal_stop(handle); if (unlikely(ret2 && !ret)) ret = ret2; From 55ce2f649b9e88111270333a8127e23f4f8f42d7 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 16 Jul 2021 20:20:22 +0800 Subject: [PATCH 010/866] ext4: correct the error path of ext4_write_inline_data_end() Current error path of ext4_write_inline_data_end() is not correct. Firstly, it should pass out the error value if ext4_get_inode_loc() return fail, or else it could trigger infinite loop if we inject error here. And then it's better to add inode to orphan list if it return fail in ext4_journal_stop(), otherwise we could not restore inline xattr entry after power failure. Finally, we need to reset the 'ret' value if ext4_write_inline_data_end() return success in ext4_write_end() and ext4_journalled_write_end(), otherwise we could not get the error return value of ext4_journal_stop(). Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210716122024.1105856-3-yi.zhang@huawei.com --- fs/ext4/inline.c | 15 +++++---------- fs/ext4/inode.c | 7 +++++-- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 70cb64db33f7..28b666f25ac2 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -733,25 +733,20 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, void *kaddr; struct ext4_iloc iloc; - if (unlikely(copied < len)) { - if (!PageUptodate(page)) { - copied = 0; - goto out; - } - } + if (unlikely(copied < len) && !PageUptodate(page)) + return 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) { ext4_std_error(inode->i_sb, ret); - copied = 0; - goto out; + return ret; } ext4_write_lock_xattr(inode, &no_expand); BUG_ON(!ext4_has_inline_data(inode)); kaddr = kmap_atomic(page); - ext4_write_inline_data(inode, &iloc, kaddr, pos, len); + ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); kunmap_atomic(kaddr); SetPageUptodate(page); /* clear page dirty so that writepages wouldn't work for us. */ @@ -760,7 +755,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); mark_inode_dirty(inode); -out: + return copied; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 76d9e25fe62c..2baa17285096 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1295,6 +1295,7 @@ static int ext4_write_end(struct file *file, goto errout; } copied = ret; + ret = 0; } else copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -1321,13 +1322,14 @@ static int ext4_write_end(struct file *file, if (i_size_changed || inline_data) ret = ext4_mark_inode_dirty(handle, inode); +errout: if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); -errout: + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1410,6 +1412,7 @@ static int ext4_journalled_write_end(struct file *file, goto errout; } copied = ret; + ret = 0; } else if (unlikely(copied < len) && !PageUptodate(page)) { copied = 0; ext4_journalled_zero_new_buffers(handle, page, from, to); @@ -1439,6 +1442,7 @@ static int ext4_journalled_write_end(struct file *file, ret = ret2; } +errout: if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside @@ -1446,7 +1450,6 @@ static int ext4_journalled_write_end(struct file *file, */ ext4_orphan_add(handle, inode); -errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; From 6984aef59814fb5c47b0e30c56e101186b5ebf8c Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 16 Jul 2021 20:20:23 +0800 Subject: [PATCH 011/866] ext4: factor out write end code of inline file Now that the inline_data file write end procedure are falled into the common write end functions, it is not clear. Factor them out and do some cleanup. This patch also drop ext4_da_write_inline_data_end() and switch to use ext4_write_inline_data_end() instead because we also need to do the same error processing if we failed to write data into inline entry. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210716122024.1105856-4-yi.zhang@huawei.com --- fs/ext4/ext4.h | 3 -- fs/ext4/inline.c | 119 ++++++++++++++++++++++++----------------------- fs/ext4/inode.c | 73 +++++++++-------------------- 3 files changed, 85 insertions(+), 110 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d71dcac3b97f..ea6c0aae8f1b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3533,9 +3533,6 @@ extern int ext4_da_write_inline_data_begin(struct address_space *mapping, unsigned flags, struct page **pagep, void **fsdata); -extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 28b666f25ac2..d30709d42a27 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -729,34 +729,76 @@ convert: int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int ret, no_expand; + handle_t *handle = ext4_journal_current_handle(); + int no_expand; void *kaddr; struct ext4_iloc iloc; + int ret = 0, ret2; if (unlikely(copied < len) && !PageUptodate(page)) - return 0; + copied = 0; - ret = ext4_get_inode_loc(inode, &iloc); - if (ret) { - ext4_std_error(inode->i_sb, ret); - return ret; + if (likely(copied)) { + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) { + unlock_page(page); + put_page(page); + ext4_std_error(inode->i_sb, ret); + goto out; + } + ext4_write_lock_xattr(inode, &no_expand); + BUG_ON(!ext4_has_inline_data(inode)); + + kaddr = kmap_atomic(page); + ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); + kunmap_atomic(kaddr); + SetPageUptodate(page); + /* clear page dirty so that writepages wouldn't work for us. */ + ClearPageDirty(page); + + ext4_write_unlock_xattr(inode, &no_expand); + brelse(iloc.bh); + + /* + * It's important to update i_size while still holding page + * lock: page writeout could otherwise come in and zero + * beyond i_size. + */ + ext4_update_inode_size(inode, pos + copied); } + unlock_page(page); + put_page(page); - ext4_write_lock_xattr(inode, &no_expand); - BUG_ON(!ext4_has_inline_data(inode)); + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (likely(copied)) + mark_inode_dirty(inode); +out: + /* + * If we didn't copy as much data as expected, we need to trim back + * size of xattr containing inline data. + */ + if (pos + len > inode->i_size && ext4_can_truncate(inode)) + ext4_orphan_add(handle, inode); - kaddr = kmap_atomic(page); - ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); - kunmap_atomic(kaddr); - SetPageUptodate(page); - /* clear page dirty so that writepages wouldn't work for us. */ - ClearPageDirty(page); - - ext4_write_unlock_xattr(inode, &no_expand); - brelse(iloc.bh); - mark_inode_dirty(inode); - - return copied; + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + if (pos + len > inode->i_size) { + ext4_truncate_failed_write(inode); + /* + * If truncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + return ret ? ret : copied; } struct buffer_head * @@ -937,43 +979,6 @@ out: return ret; } -int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page) -{ - int ret; - - ret = ext4_write_inline_data_end(inode, pos, len, copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - return ret; - } - copied = ret; - - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. - * - * But it's important to update i_size while still holding page lock: - * page writeout could otherwise come in and zero beyond i_size. - */ - if (pos+copied > inode->i_size) - i_size_write(inode, pos+copied); - unlock_page(page); - put_page(page); - - /* - * Don't mark the inode dirty under page lock. First, it unnecessarily - * makes the holding time of page lock longer. Second, it forces lock - * ordering of page lock and transaction start for journaling - * filesystems. - */ - mark_inode_dirty(inode); - - return copied; -} - #ifdef INLINE_DIR_DEBUG void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2baa17285096..b80f15bba727 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1282,23 +1282,14 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - ret = 0; - } else - copied = block_write_end(file, mapping, pos, - len, copied, page, fsdata); + + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1319,10 +1310,9 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed || inline_data) + if (i_size_changed) ret = ext4_mark_inode_dirty(handle, inode); -errout: if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside @@ -1394,7 +1384,6 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); @@ -1403,17 +1392,10 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - ret = 0; - } else if (unlikely(copied < len) && !PageUptodate(page)) { + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + if (unlikely(copied < len) && !PageUptodate(page)) { copied = 0; ext4_journalled_zero_new_buffers(handle, page, from, to); } else { @@ -1436,13 +1418,12 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos && !verity) pagecache_isize_extended(inode, old_size, pos); - if (size_changed || inline_data) { + if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; } -errout: if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside @@ -3072,7 +3053,7 @@ static int ext4_da_write_end(struct file *file, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - int ret = 0, ret2; + int ret; handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; @@ -3083,6 +3064,12 @@ static int ext4_da_write_end(struct file *file, len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); + + if (write_mode != CONVERT_INLINE_DATA && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && + ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + start = pos & (PAGE_SIZE - 1); end = start + copied - 1; @@ -3102,26 +3089,12 @@ static int ext4_da_write_end(struct file *file, * ext4_da_write_inline_data_end(). */ new_i_size = pos + copied; - if (copied && new_i_size > inode->i_size) { - if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) - ext4_update_i_disksize(inode, new_i_size); - } - - if (write_mode != CONVERT_INLINE_DATA && - ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && - ext4_has_inline_data(inode)) - ret = ext4_da_write_inline_data_end(inode, pos, len, copied, - page); - else - ret = generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - - copied = ret; - ret2 = ext4_journal_stop(handle); - if (unlikely(ret2 && !ret)) - ret = ret2; + if (copied && new_i_size > inode->i_size && + ext4_da_should_update_i_disksize(page, end)) + ext4_update_i_disksize(inode, new_i_size); + copied = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + ret = ext4_journal_stop(handle); return ret ? ret : copied; } From cc883236b79297f6266ca6f4e7f24f3fd3c736c1 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 16 Jul 2021 20:20:24 +0800 Subject: [PATCH 012/866] ext4: drop unnecessary journal handle in delalloc write After we factor out the inline data write procedure from ext4_da_write_end(), we don't need to start journal handle for the cases of both buffer overwrite and append-write. If we need to update i_disksize, mark_inode_dirty() do start handle and update inode buffer. So we could just remove all the journal handle codes in the delalloc write procedure. After this patch, we could get a lot of performance improvement. Below is the Unixbench comparison data test on my machine with 'Intel Xeon Gold 5120' CPU and nvme SSD backend. Test cmd: ./Run -c 56 -i 3 fstime fsbuffer fsdisk Before this patch: System Benchmarks Partial Index BASELINE RESULT INDEX File Copy 1024 bufsize 2000 maxblocks 3960.0 422965.0 1068.1 File Copy 256 bufsize 500 maxblocks 1655.0 105077.0 634.9 File Copy 4096 bufsize 8000 maxblocks 5800.0 1429092.0 2464.0 ====== System Benchmarks Index Score (Partial Only) 1186.6 After this patch: System Benchmarks Partial Index BASELINE RESULT INDEX File Copy 1024 bufsize 2000 maxblocks 3960.0 732716.0 1850.3 File Copy 256 bufsize 500 maxblocks 1655.0 184940.0 1117.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 2427152.0 4184.7 ====== System Benchmarks Index Score (Partial Only) 2053.0 Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210716122024.1105856-5-yi.zhang@huawei.com --- fs/ext4/inode.c | 60 +++++-------------------------------------------- 1 file changed, 5 insertions(+), 55 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b80f15bba727..502f60621bad 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2910,19 +2910,6 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } -/* We always reserve for an inode update; the superblock could be there too */ -static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) -{ - if (likely(ext4_has_feature_large_file(inode->i_sb))) - return 1; - - if (pos + len <= 0x7fffffffULL) - return 1; - - /* We might need to update the superblock to set LARGE_FILE */ - return 2; -} - static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2931,7 +2918,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, struct page *page; pgoff_t index; struct inode *inode = mapping->host; - handle_t *handle; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; @@ -2957,41 +2943,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, return 0; } - /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page - * is being written back. So grab it first before we start - * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. - */ -retry_grab: +retry: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; - unlock_page(page); - /* - * With delayed allocation, we don't log the i_disksize update - * if there is delayed block allocation. But we still need - * to journalling the i_disksize update if writes to the end - * of file which has an already mapped buffer. - */ -retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_da_write_credits(inode, pos, len)); - if (IS_ERR(handle)) { - put_page(page); - return PTR_ERR(handle); - } - - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - put_page(page); - ext4_journal_stop(handle); - goto retry_grab; - } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); @@ -3003,20 +2959,18 @@ retry_journal: #endif if (ret < 0) { unlock_page(page); - ext4_journal_stop(handle); + put_page(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry_journal; - - put_page(page); + goto retry; return ret; } @@ -3053,8 +3007,6 @@ static int ext4_da_write_end(struct file *file, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - int ret; - handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; @@ -3093,9 +3045,7 @@ static int ext4_da_write_end(struct file *file, ext4_da_should_update_i_disksize(page, end)) ext4_update_i_disksize(inode, new_i_size); - copied = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - ret = ext4_journal_stop(handle); - return ret ? ret : copied; + return generic_write_end(file, mapping, pos, len, copied, page, fsdata); } /* From 31692ab9a9ef0119959f66838de74eeb37490c8d Mon Sep 17 00:00:00 2001 From: Jernej Skrabec Date: Thu, 5 Aug 2021 21:04:16 +0200 Subject: [PATCH 013/866] media: hantro: Fix check for single irq Some cores use only one interrupt and in such case interrupt name in DT is not needed. Driver supposedly accounted that, but due to the wrong field check it never worked. Fix that. Fixes: 18d6c8b7b4c9 ("media: hantro: add fallback handling for single irq/clk") Signed-off-by: Jernej Skrabec Reviewed-by: Ezequiel Garcia Reviewed-by: Emil Velikov Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/hantro/hantro_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c index 8a2edd67f2c6..20e508158871 100644 --- a/drivers/staging/media/hantro/hantro_drv.c +++ b/drivers/staging/media/hantro/hantro_drv.c @@ -919,7 +919,7 @@ static int hantro_probe(struct platform_device *pdev) if (!vpu->variant->irqs[i].handler) continue; - if (vpu->variant->num_clocks > 1) { + if (vpu->variant->num_irqs > 1) { irq_name = vpu->variant->irqs[i].name; irq = platform_get_irq_byname(vpu->pdev, irq_name); } else { From 132c88614f2b3548cd3c8979a434609019db4151 Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Thu, 19 Aug 2021 16:00:09 +0200 Subject: [PATCH 014/866] media: cedrus: Fix SUNXI tile size calculation Tiled formats requires full rows being allocated (even for Chroma planes). When the number of Luma tiles is odd, we need to round up to twice the tile width in order to roundup the number of Chroma tiles. This was notice with a crash running BA1_FT_C compliance test using sunxi tiles using GStreamer. Cedrus driver would allocate 9 rows for Luma, but only 4.5 rows for Chroma, causing userspace to crash. Signed-off-by: Nicolas Dufresne Fixes: 50e761516f2b8 ("media: platform: Add Cedrus VPU decoder driver") Reviewed-by: Jernej Skrabec Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/sunxi/cedrus/cedrus_video.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.c b/drivers/staging/media/sunxi/cedrus/cedrus_video.c index c589fe9dae70..825af5fd35e0 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_video.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.c @@ -135,7 +135,7 @@ void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt) sizeimage = bytesperline * height; /* Chroma plane size. */ - sizeimage += bytesperline * height / 2; + sizeimage += bytesperline * ALIGN(height, 64) / 2; break; From a61cb6017df0a9be072a35259e6e9ae7aa0ef6b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Sep 2021 14:40:00 +0200 Subject: [PATCH 015/866] dma-mapping: fix the kerneldoc for dma_map_sg_attrs Add the missing description for the nents parameter, and fix a trivial misalignment. Fixes: fffe3cc8c219 ("dma-mapping: allow map_sg() ops to return negative error codes") Reported-by: Stephen Rothwell Signed-off-by: Christoph Hellwig --- kernel/dma/mapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 7ee5284bff58..06fec5547e7c 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -206,7 +206,8 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, /** * dma_map_sg_attrs - Map the given buffer for DMA * @dev: The device for which to perform the DMA operation - * @sg: The sg_table object describing the buffer + * @sg: The sg_table object describing the buffer + * @nents: Number of entries to map * @dir: DMA direction * @attrs: Optional DMA attributes for the map operation * From 26391e49d5b0f0c33eb4b28a312d2ecc094d7489 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Wed, 25 Aug 2021 13:42:13 +0200 Subject: [PATCH 016/866] mmc: dw_mmc: Only inject fault before done/error The fault injection function can set EVENT_DATA_ERROR but skip the setting of ->data_status to an error status if it hits just after a data over interrupt. This confuses the tasklet which can later end up triggering the WARN_ON(host->cmd || ..) in dw_mci_request_end() since dw_mci_data_complete() would return success. Prevent the fault injection function from doing this since this is not a real case, and ensure that the fault injection doesn't race with a real error either. Signed-off-by: Vincent Whitchurch Reviewed-by: Jaehoon Chung Fixes: 2b8ac062f337 ("mmc: dw_mmc: Add data CRC error injection") Link: https://lore.kernel.org/r/20210825114213.7429-1-vincent.whitchurch@axis.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/dw_mmc.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 6578cc64ae9e..380f9aa56eb2 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1802,10 +1802,15 @@ static enum hrtimer_restart dw_mci_fault_timer(struct hrtimer *t) spin_lock_irqsave(&host->irq_lock, flags); - if (!host->data_status) + /* + * Only inject an error if we haven't already got an error or data over + * interrupt. + */ + if (!host->data_status) { host->data_status = SDMMC_INT_DCRC; - set_bit(EVENT_DATA_ERROR, &host->pending_events); - tasklet_schedule(&host->tasklet); + set_bit(EVENT_DATA_ERROR, &host->pending_events); + tasklet_schedule(&host->tasklet); + } spin_unlock_irqrestore(&host->irq_lock, flags); @@ -2721,12 +2726,16 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) } if (pending & DW_MCI_DATA_ERROR_FLAGS) { + spin_lock(&host->irq_lock); + /* if there is an error report DATA_ERROR */ mci_writel(host, RINTSTS, DW_MCI_DATA_ERROR_FLAGS); host->data_status = pending; smp_wmb(); /* drain writebuffer */ set_bit(EVENT_DATA_ERROR, &host->pending_events); tasklet_schedule(&host->tasklet); + + spin_unlock(&host->irq_lock); } if (pending & SDMMC_INT_DATA_OVER) { From b81bede4d138ce62f7342e27bf55ac93c8071818 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 26 Aug 2021 10:21:07 +0200 Subject: [PATCH 017/866] mmc: renesas_sdhi: fix regression with hard reset on old SDHIs Old SDHI instances have a default value for the reset register which keeps it in reset state by default. So, when applying a hard reset we need to manually leave the soft reset state as well. Later SDHI instances have a different default value, the one we write manually now. Fixes: b4d86f37eacb ("mmc: renesas_sdhi: do hard reset if possible") Signed-off-by: Wolfram Sang Tested-by: Geert Uytterhoeven Reported-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210826082107.47299-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/renesas_sdhi_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 6fc4cf3c9dce..a4407f391f66 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -561,6 +561,8 @@ static void renesas_sdhi_reset(struct tmio_mmc_host *host) /* Unknown why but without polling reset status, it will hang */ read_poll_timeout(reset_control_status, ret, ret == 0, 1, 100, false, priv->rstc); + /* At least SDHI_VER_GEN2_SDR50 needs manual release of reset */ + sd_ctrl_write16(host, CTL_RESET_SD, 0x0001); priv->needs_adjust_hs400 = false; renesas_sdhi_set_clock(host, host->clk_cache); } else if (priv->scc_ctl) { From 3ad02c27d89d72b3b49ac51899144b7d0942f05f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 7 Sep 2021 06:40:22 +0200 Subject: [PATCH 018/866] media: s5p-jpeg: rename JPEG marker constants to prevent build warnings The use of a macro named 'RST' conflicts with one of the same name in arch/mips/include/asm/mach-rc32434/rb.h. This causes build warnings on some MIPS builds. Change the names of the JPEG marker constants to be in their own namespace to fix these build warnings and to prevent other similar problems in the future. Fixes these build warnings: In file included from ../drivers/media/platform/s5p-jpeg/jpeg-hw-exynos3250.c:14: ../drivers/media/platform/s5p-jpeg/jpeg-core.h:43: warning: "RST" redefined 43 | #define RST 0xd0 | ../arch/mips/include/asm/mach-rc32434/rb.h:13: note: this is the location of the previous definition 13 | #define RST (1 << 15) In file included from ../drivers/media/platform/s5p-jpeg/jpeg-hw-s5p.c:13: ../drivers/media/platform/s5p-jpeg/jpeg-core.h:43: warning: "RST" redefined 43 | #define RST 0xd0 ../arch/mips/include/asm/mach-rc32434/rb.h:13: note: this is the location of the previous definition 13 | #define RST (1 << 15) In file included from ../drivers/media/platform/s5p-jpeg/jpeg-hw-exynos4.c:12: ../drivers/media/platform/s5p-jpeg/jpeg-core.h:43: warning: "RST" redefined 43 | #define RST 0xd0 ../arch/mips/include/asm/mach-rc32434/rb.h:13: note: this is the location of the previous definition 13 | #define RST (1 << 15) In file included from ../drivers/media/platform/s5p-jpeg/jpeg-core.c:31: ../drivers/media/platform/s5p-jpeg/jpeg-core.h:43: warning: "RST" redefined 43 | #define RST 0xd0 ../arch/mips/include/asm/mach-rc32434/rb.h:13: note: this is the location of the previous definition 13 | #define RST (1 << 15) Also update the kernel-doc so that the word "marker" is not repeated. Link: https://lore.kernel.org/linux-media/20210907044022.30602-1-rdunlap@infradead.org Fixes: bb677f3ac434 ("[media] Exynos4 JPEG codec v4l2 driver") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Andrzej Pietrasiewicz Cc: Jacek Anaszewski Cc: Sylwester Nawrocki Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/s5p-jpeg/jpeg-core.c | 18 ++++++------- drivers/media/platform/s5p-jpeg/jpeg-core.h | 28 ++++++++++----------- 2 files changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index d402e456f27d..7d0ab19c38bb 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -1140,8 +1140,8 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result, continue; length = 0; switch (c) { - /* SOF0: baseline JPEG */ - case SOF0: + /* JPEG_MARKER_SOF0: baseline JPEG */ + case JPEG_MARKER_SOF0: if (get_word_be(&jpeg_buffer, &word)) break; length = (long)word - 2; @@ -1172,7 +1172,7 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result, notfound = 0; break; - case DQT: + case JPEG_MARKER_DQT: if (get_word_be(&jpeg_buffer, &word)) break; length = (long)word - 2; @@ -1185,7 +1185,7 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result, skip(&jpeg_buffer, length); break; - case DHT: + case JPEG_MARKER_DHT: if (get_word_be(&jpeg_buffer, &word)) break; length = (long)word - 2; @@ -1198,15 +1198,15 @@ static bool s5p_jpeg_parse_hdr(struct s5p_jpeg_q_data *result, skip(&jpeg_buffer, length); break; - case SOS: + case JPEG_MARKER_SOS: sos = jpeg_buffer.curr - 2; /* 0xffda */ break; /* skip payload-less markers */ - case RST ... RST + 7: - case SOI: - case EOI: - case TEM: + case JPEG_MARKER_RST ... JPEG_MARKER_RST + 7: + case JPEG_MARKER_SOI: + case JPEG_MARKER_EOI: + case JPEG_MARKER_TEM: break; /* skip uninteresting payload markers */ diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.h b/drivers/media/platform/s5p-jpeg/jpeg-core.h index a77d93c098ce..8473a019bb5f 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.h +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.h @@ -37,15 +37,15 @@ #define EXYNOS3250_IRQ_TIMEOUT 0x10000000 /* a selection of JPEG markers */ -#define TEM 0x01 -#define SOF0 0xc0 -#define DHT 0xc4 -#define RST 0xd0 -#define SOI 0xd8 -#define EOI 0xd9 -#define SOS 0xda -#define DQT 0xdb -#define DHP 0xde +#define JPEG_MARKER_TEM 0x01 +#define JPEG_MARKER_SOF0 0xc0 +#define JPEG_MARKER_DHT 0xc4 +#define JPEG_MARKER_RST 0xd0 +#define JPEG_MARKER_SOI 0xd8 +#define JPEG_MARKER_EOI 0xd9 +#define JPEG_MARKER_SOS 0xda +#define JPEG_MARKER_DQT 0xdb +#define JPEG_MARKER_DHP 0xde /* Flags that indicate a format can be used for capture/output */ #define SJPEG_FMT_FLAG_ENC_CAPTURE (1 << 0) @@ -187,11 +187,11 @@ struct s5p_jpeg_marker { * @fmt: driver-specific format of this queue * @w: image width * @h: image height - * @sos: SOS marker's position relative to the buffer beginning - * @dht: DHT markers' positions relative to the buffer beginning - * @dqt: DQT markers' positions relative to the buffer beginning - * @sof: SOF0 marker's position relative to the buffer beginning - * @sof_len: SOF0 marker's payload length (without length field itself) + * @sos: JPEG_MARKER_SOS's position relative to the buffer beginning + * @dht: JPEG_MARKER_DHT' positions relative to the buffer beginning + * @dqt: JPEG_MARKER_DQT' positions relative to the buffer beginning + * @sof: JPEG_MARKER_SOF0's position relative to the buffer beginning + * @sof_len: JPEG_MARKER_SOF0's payload length (without length field itself) * @size: image buffer size in bytes */ struct s5p_jpeg_q_data { From 3a029e1f3d6e2ee809e85abecce619a48016bd4b Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 6 Sep 2021 17:36:38 +0100 Subject: [PATCH 019/866] selftests/bpf: Fix build of task_pt_regs test for arm64 struct pt_regs is not exported to userspace on all archs. arm64 and s390 export "user_pt_regs" instead, which causes build failure at the moment: progs/test_task_pt_regs.c:8:16: error: variable has incomplete type 'struct pt_regs' struct pt_regs current_regs = {}; Instead of using pt_regs from ptrace.h, use the larger kernel struct from vmlinux.h directly. Since the test runner task_pt_regs.c does not have access to the kernel struct definition, copy it into a char array. Fixes: 576d47bb1a92 ("bpf: selftests: Add bpf_task_pt_regs() selftest") Suggested-by: Andrii Nakryiko Signed-off-by: Jean-Philippe Brucker Signed-off-by: Daniel Borkmann Tested-by: Ilya Leoshkevich Acked-by: Ilya Leoshkevich Link: https://lore.kernel.org/bpf/20210906163635.302307-1-jean-philippe@linaro.org --- .../selftests/bpf/prog_tests/task_pt_regs.c | 1 - .../selftests/bpf/progs/test_task_pt_regs.c | 19 +++++++++++++------ 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 53f0e0fa1a53..37c20b5ffa70 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE #include -#include #include "test_task_pt_regs.skel.h" void test_task_pt_regs(void) diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c index 6c059f1cfa1b..e6cb09259408 100644 --- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c +++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c @@ -1,12 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include +#include "vmlinux.h" #include #include -struct pt_regs current_regs = {}; -struct pt_regs ctx_regs = {}; +#define PT_REGS_SIZE sizeof(struct pt_regs) + +/* + * The kernel struct pt_regs isn't exported in its entirety to userspace. + * Pass it as an array to task_pt_regs.c + */ +char current_regs[PT_REGS_SIZE] = {}; +char ctx_regs[PT_REGS_SIZE] = {}; int uprobe_res = 0; SEC("uprobe/trigger_func") @@ -17,8 +22,10 @@ int handle_uprobe(struct pt_regs *ctx) current = bpf_get_current_task_btf(); regs = (struct pt_regs *) bpf_task_pt_regs(current); - __builtin_memcpy(¤t_regs, regs, sizeof(*regs)); - __builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx)); + if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs)) + return 0; + if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx)) + return 0; /* Prove that uprobe was run */ uprobe_res = 1; From 8343268ec3cf4e097aa8b2071f0cd6779e2c4953 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 18 Aug 2021 14:19:13 +0300 Subject: [PATCH 020/866] net/mlx5: Bridge, fix uninitialized variable usage In some conditions variable 'err' is not assigned with value in mlx5_esw_bridge_port_obj_attr_set() and mlx5_esw_bridge_port_changeupper() functions after recent changes to support LAG. Initialize the variable with zero value in both cases. Reported-by: Colin King Reported-by: Tim Gardner Reported-by: Naresh Kamboju CC: linux-kernel@vger.kernel.org Fixes: ff9b7521468b ("net/mlx5: Bridge, support LAG") Signed-off-by: Vlad Buslov --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 0c38c2e319be..b5ddaa82755f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -137,7 +137,7 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr u16 vport_num, esw_owner_vhca_id; struct netlink_ext_ack *extack; int ifindex = upper->ifindex; - int err; + int err = 0; if (!netif_is_bridge_master(upper)) return 0; @@ -244,7 +244,7 @@ mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_attr_info->info); const struct switchdev_attr *attr = port_attr_info->attr; u16 vport_num, esw_owner_vhca_id; - int err; + int err = 0; if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, &esw_owner_vhca_id)) From 897ae4b40e80be7dcbf2b3079d85fa6339a6b751 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 17 Aug 2021 15:59:17 +0300 Subject: [PATCH 021/866] net/mlx5: Fix rdma aux device on devlink reload RDMA auxdev parameter registration was skipped for eswitch manager PCI PF. Due to this when devlink parameter is read, it reads as false in below code flow. $ devlink dev reload pci/0000:06:00.0 devlink_reload() mlx5_load_one() mlx5_attach_device() is_ib_enabled() devlink_param_driverinit_value_get() Due to this, is_ib_enabled() returns false for the RDMA auxiliary device. This results into a skipping RDMA auxiliary device creation on reload. There is no need to check for eswitch manager capability to support RDMA auxiliary device. Hence, fix it by skipping eswitch manager capability. Fixes: 87158cedf00e ("net/mlx5: Support enable_rdma devlink dev param") Signed-off-by: Parav Pandit Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index e84287ffc7ce..dcf9f27ba2ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -658,11 +658,10 @@ static const struct devlink_param enable_rdma_param = static int mlx5_devlink_rdma_param_register(struct devlink *devlink) { - struct mlx5_core_dev *dev = devlink_priv(devlink); union devlink_param_value value; int err; - if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return 0; err = devlink_param_register(devlink, &enable_rdma_param); @@ -679,9 +678,7 @@ static int mlx5_devlink_rdma_param_register(struct devlink *devlink) static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink) { - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return; devlink_param_unpublish(devlink, &enable_rdma_param); From da8252d5805d4a80120a0c2151277e5fb9e8aa9e Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 11 Aug 2021 16:40:16 +0300 Subject: [PATCH 022/866] net/mlx5: Lag, don't update lag if lag isn't supported In NICs that don't support LAG, the LAG control structure won't be allocated. If it wasn't allocated it means LAG doesn't exists and can be skipped. Fixes: cac1eb2cf2e3 ("net/mlx5: Lag, properly lock eswitch if needed") Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 49ca57c6d31d..ca5690b0a7ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -927,9 +927,12 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev) struct mlx5_core_dev *dev1; struct mlx5_lag *ldev; + ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + mlx5_dev_list_lock(); - ldev = mlx5_lag_dev(dev); dev0 = ldev->pf[MLX5_LAG_P1].dev; dev1 = ldev->pf[MLX5_LAG_P2].dev; @@ -946,8 +949,11 @@ void mlx5_lag_enable_change(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; - mlx5_dev_list_lock(); ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + + mlx5_dev_list_lock(); ldev->mode_changes_in_progress--; mlx5_dev_list_unlock(); mlx5_queue_bond_work(ldev, 0); From dfe6fd72b5f1878b16aa2c8603e031bbcd66b96d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 18 Aug 2021 13:09:26 -0700 Subject: [PATCH 023/866] net/mlx5: FWTrace, cancel work on alloc pd error flow Handle error flow on mlx5_core_alloc_pd() failure, read_fw_strings_work must be canceled. Fixes: c71ad41ccb0c ("net/mlx5: FW tracer, events handling") Reported-by: Pavel Machek (CIP) Suggested-by: Pavel Machek (CIP) Signed-off-by: Saeed Mahameed Reviewed-by: Aya Levin --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 3f8a98093f8c..f9cf9fb31547 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1007,7 +1007,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn); if (err) { mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err); - return err; + goto err_cancel_work; } err = mlx5_fw_tracer_create_mkey(tracer); @@ -1031,6 +1031,7 @@ err_notifier_unregister: mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); +err_cancel_work: cancel_work_sync(&tracer->read_fw_strings_work); return err; } From ee27e330a953595903979ffdb84926843595a9fe Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 1 Sep 2021 11:48:13 +0300 Subject: [PATCH 024/866] net/mlx5: Fix potential sleeping in atomic context Fixes the below flow of sleeping in atomic context by releasing the RCU lock before calling to free_match_list. build_match_list() <- disables preempt -> free_match_list() -> tree_put_node() -> down_write_ref_node() <- take write lock Fixes: 693c6883bbc4 ("net/mlx5: Add hash table for flow groups in flow table") Reported-by: Dan Carpenter Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9fe8e3c204d6..fe501ba88bea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1682,14 +1682,13 @@ static int build_match_list(struct match_list *match_head, curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { + rcu_read_unlock(); free_match_list(match_head, ft_locked); - err = -ENOMEM; - goto out; + return -ENOMEM; } curr_match->g = g; list_add_tail(&curr_match->list, &match_head->list); } -out: rcu_read_unlock(); return err; } From c91c1da72b47fc4c5e353cdd9099ba94ae07d2fa Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 15 Jul 2021 10:53:28 +0300 Subject: [PATCH 025/866] net/mlx5e: Fix mutual exclusion between CQE compression and HW TS Some profiles of the driver don't support a dedicated PTP-RQ, hence can't support HW TS and CQE compression simultaneously. When HW TS is enabled the COE compression is disabled, and should be restored when the HW TS is turned off. Add rx_filter as an input to modifying CQE compression to enforce this restriction. Fixes: 256f79d13c1d ("net/mlx5e: Fix HW TS with CQE compression according to profile") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 11 ++++++----- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- 3 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 669a75f3537a..7b8c8187543a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -922,7 +922,7 @@ void mlx5e_set_rx_mode_work(struct work_struct *work); int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); -int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val); +int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val, bool rx_filter); int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 2cfd12953909..306fb5d6a36d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1884,7 +1884,7 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable) return set_pflag_cqe_based_moder(netdev, enable, true); } -int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val) +int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val, bool rx_filter) { bool curr_val = MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS); struct mlx5e_params new_params; @@ -1896,8 +1896,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val if (curr_val == new_val) return 0; - if (new_val && !priv->profile->rx_ptp_support && - priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { + if (new_val && !priv->profile->rx_ptp_support && rx_filter) { netdev_err(priv->netdev, "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n"); return -EINVAL; @@ -1905,7 +1904,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val new_params = priv->channels.params; MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); - if (priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) + if (rx_filter) new_params.ptp_rx = new_val; if (new_params.ptp_rx == priv->channels.params.ptp_rx) @@ -1928,12 +1927,14 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + bool rx_filter; int err; if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + rx_filter = priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE; + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable, rx_filter); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 47efd858964d..3fd515e7bf30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3554,14 +3554,14 @@ static int mlx5e_hwstamp_config_no_ptp_rx(struct mlx5e_priv *priv, bool rx_filte if (!rx_filter) /* Reset CQE compression to Admin default */ - return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def); + return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def, false); if (!MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) return 0; /* Disable CQE compression */ netdev_warn(priv->netdev, "Disabling RX cqe compression\n"); - err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false, true); if (err) netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); From 8db6a54f3cae6a803b2cbf5390662bca641f7da8 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 29 Aug 2021 13:41:08 +0300 Subject: [PATCH 026/866] net/mlx5e: Fix condition when retrieving PTP-rqn When activating the PTP-RQ, redirect the RQT from drop-RQ to PTP-RQ. Use mlx5e_channels_get_ptp_rqn to retrieve the rqn. This helper returns a boolean (not status), hence caller should consider return value 0 as a fail. Change the caller interpretation of the return value. Fixes: 43ec0f41fa73 ("net/mlx5e: Hide all implementation details of mlx5e_rx_res") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index bf0313e2682b..13056cb9757d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -572,7 +572,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann if (res->features & MLX5E_RX_RES_FEATURE_PTP) { u32 rqn; - if (mlx5e_channels_get_ptp_rqn(chs, &rqn)) + if (!mlx5e_channels_get_ptp_rqn(chs, &rqn)) rqn = res->drop_rqn; err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); From 0f31ab217dc52a3044044d416be0248b1778c4da Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Tue, 7 Sep 2021 22:02:40 -0500 Subject: [PATCH 027/866] dt-bindings: net: sun8i-emac: Add compatible for D1 The D1 SoC contains EMAC hardware which is compatible with the A64 EMAC. Add the new compatible string, with the A64 as a fallback. Signed-off-by: Samuel Holland Acked-by: Maxime Ripard Signed-off-by: David S. Miller --- .../devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index 7f2578d48e3f..9eb4bb529ad5 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -19,7 +19,9 @@ properties: - const: allwinner,sun8i-v3s-emac - const: allwinner,sun50i-a64-emac - items: - - const: allwinner,sun50i-h6-emac + - enum: + - allwinner,sun20i-d1-emac + - allwinner,sun50i-h6-emac - const: allwinner,sun50i-a64-emac reg: From d9ea761fdd197351890418acd462c51f241014a7 Mon Sep 17 00:00:00 2001 From: "Lin, Zhenpeng" Date: Wed, 8 Sep 2021 03:40:59 +0000 Subject: [PATCH 028/866] dccp: don't duplicate ccid when cloning dccp sock Commit 2677d2067731 ("dccp: don't free ccid2_hc_tx_sock ...") fixed a UAF but reintroduced CVE-2017-6074. When the sock is cloned, two dccps_hc_tx_ccid will reference to the same ccid. So one can free the ccid object twice from two socks after cloning. This issue was found by "Hadar Manor" as well and assigned with CVE-2020-16119, which was fixed in Ubuntu's kernel. So here I port the patch from Ubuntu to fix it. The patch prevents cloned socks from referencing the same ccid. Fixes: 2677d2067731410 ("dccp: don't free ccid2_hc_tx_sock ...") Signed-off-by: Zhenpeng Lin Signed-off-by: David S. Miller --- net/dccp/minisocks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index c5c74a34d139..91e7a2202697 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -94,6 +94,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; newdp->dccps_service_list = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service = dreq->dreq_service; newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo; newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; From 581edcd0c8a076eba2ec9e20db50921ee80f5cbc Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Wed, 8 Sep 2021 12:13:10 +0800 Subject: [PATCH 029/866] mctp: perform route destruction under RCU read lock The kernel test robot reports: [ 843.509974][ T345] ============================= [ 843.524220][ T345] WARNING: suspicious RCU usage [ 843.538791][ T345] 5.14.0-rc2-00606-g889b7da23abf #1 Not tainted [ 843.553617][ T345] ----------------------------- [ 843.567412][ T345] net/mctp/route.c:310 RCU-list traversed in non-reader section!! - we're missing the rcu read lock acquire around the destruction path. This change adds the acquire/release - the path is already atomic, and we're using the _rcu list iterators. Reported-by: kernel test robot Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- net/mctp/route.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mctp/route.c b/net/mctp/route.c index 5265525011ad..5ca186d53cb0 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -1083,8 +1083,10 @@ static void __net_exit mctp_routes_net_exit(struct net *net) { struct mctp_route *rt; + rcu_read_lock(); list_for_each_entry_rcu(rt, &net->mctp.routes, list) mctp_route_release(rt); + rcu_read_unlock(); } static struct pernet_operations mctp_net_ops = { From d437f5aa23aa2b7bd07cd44b839d7546cc17166f Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Tue, 7 Sep 2021 22:07:03 -0700 Subject: [PATCH 030/866] ibmvnic: check failover_pending in login response If a failover occurs before a login response is received, the login response buffer maybe undefined. Check that there was no failover before accessing the login response buffer. Signed-off-by: Sukadev Bhattiprolu Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a775c69e4fd7..6aa6ff89a765 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4700,6 +4700,14 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, return 0; } + if (adapter->failover_pending) { + adapter->init_done_rc = -EAGAIN; + netdev_dbg(netdev, "Failover pending, ignoring login response\n"); + complete(&adapter->init_done); + /* login response buffer will be released on reset */ + return 0; + } + netdev->mtu = adapter->req_mtu - ETH_HLEN; netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); From d7e203ffd3ba5965e88952e7364a42ab32064408 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 7 Sep 2021 15:46:10 +0200 Subject: [PATCH 031/866] ne2000: fix unused function warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Geert noticed a warning on MIPS TX49xx, Atari and presuambly other platforms when the driver is built-in but NETDEV_LEGACY_INIT is disabled: drivers/net/ethernet/8390/ne.c:909:20: warning: ‘ne_add_devices’ defined but not used [-Wunused-function] Merge the two module init functions into a single one with an IS_ENABLED() check to replace the incorrect #ifdef. Fixes: 4228c3942821 ("make legacy ISA probe optional") Reported-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- drivers/net/ethernet/8390/ne.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 53660bc8d6ff..9afc712f5948 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -922,13 +922,16 @@ static void __init ne_add_devices(void) } } -#ifdef MODULE static int __init ne_init(void) { int retval; - ne_add_devices(); + + if (IS_MODULE(CONFIG_NE2000)) + ne_add_devices(); + retval = platform_driver_probe(&ne_driver, ne_drv_probe); - if (retval) { + + if (IS_MODULE(CONFIG_NE2000) && retval) { if (io[0] == 0) pr_notice("ne.c: You must supply \"io=0xNNN\"" " value(s) for ISA cards.\n"); @@ -941,18 +944,8 @@ static int __init ne_init(void) return retval; } module_init(ne_init); -#else /* MODULE */ -static int __init ne_init(void) -{ - int retval = platform_driver_probe(&ne_driver, ne_drv_probe); - /* Unregister unused platform_devices. */ - ne_loop_rm_unreg(0); - return retval; -} -module_init(ne_init); - -#ifdef CONFIG_NETDEV_LEGACY_INIT +#if !defined(MODULE) && defined(CONFIG_NETDEV_LEGACY_INIT) struct net_device * __init ne_probe(int unit) { int this_dev; @@ -994,7 +987,6 @@ struct net_device * __init ne_probe(int unit) return ERR_PTR(-ENODEV); } #endif -#endif /* MODULE */ static void __exit ne_exit(void) { From ea269a6f720782ed94171fb962b14ce07c372138 Mon Sep 17 00:00:00 2001 From: Nathan Rossi Date: Thu, 2 Sep 2021 05:14:49 +0000 Subject: [PATCH 032/866] net: phylink: Update SFP selected interface on advertising changes Currently changes to the advertising state via ethtool do not cause any reselection of the configured interface mode after the SFP is already inserted and initially configured. While it is not typical to change the advertised link modes for an interface using an SFP in certain use cases it is desirable. In the case of a SFP port that is capable of handling both SFP and SFP+ modules it will automatically select between 1G and 10G modes depending on the supported mode of the SFP. However if the SFP module is capable of working in multiple modes (e.g. a SFP+ DAC that can operate at 1G or 10G), one end of the cable may be attached to a SFP 1000base-x port thus the SFP+ end must be manually configured to the 1000base-x mode in order for the link to be established. This change causes the ethtool setting of advertised mode changes to reselect the interface mode so that the link can be established. Additionally when a module is inserted the advertising mode is reset to match the supported modes of the module. Signed-off-by: Nathan Rossi Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a1464b764d4d..0a0abe8e4be0 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1607,6 +1607,32 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, if (config.an_enabled && phylink_is_empty_linkmode(config.advertising)) return -EINVAL; + /* If this link is with an SFP, ensure that changes to advertised modes + * also cause the associated interface to be selected such that the + * link can be configured correctly. + */ + if (pl->sfp_port && pl->sfp_bus) { + config.interface = sfp_select_interface(pl->sfp_bus, + config.advertising); + if (config.interface == PHY_INTERFACE_MODE_NA) { + phylink_err(pl, + "selection of interface failed, advertisement %*pb\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, + config.advertising); + return -EINVAL; + } + + /* Revalidate with the selected interface */ + linkmode_copy(support, pl->supported); + if (phylink_validate(pl, support, &config)) { + phylink_err(pl, "validation of %s/%s with support %*pb failed\n", + phylink_an_mode_str(pl->cur_link_an_mode), + phy_modes(config.interface), + __ETHTOOL_LINK_MODE_MASK_NBITS, support); + return -EINVAL; + } + } + mutex_lock(&pl->state_mutex); pl->link_config.speed = config.speed; pl->link_config.duplex = config.duplex; @@ -2186,7 +2212,9 @@ static int phylink_sfp_config(struct phylink *pl, u8 mode, if (phy_interface_mode_is_8023z(iface) && pl->phydev) return -EINVAL; - changed = !linkmode_equal(pl->supported, support); + changed = !linkmode_equal(pl->supported, support) || + !linkmode_equal(pl->link_config.advertising, + config.advertising); if (changed) { linkmode_copy(pl->supported, support); linkmode_copy(pl->link_config.advertising, config.advertising); From b5c102238cea985d8126b173d06b9e1de88037ee Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 7 Sep 2021 12:05:54 -0500 Subject: [PATCH 033/866] net: ipa: initialize all filter table slots There is an off-by-one problem in ipa_table_init_add(), when initializing filter tables. In that function, the number of filter table entries is determined based on the number of set bits in the filter map. However that count does *not* include the extra "slot" in the filter table that holds the filter map itself. Meanwhile, ipa_table_addr() *does* include the filter map in the memory it returns, but because the count it's provided doesn't include it, it includes one too few table entries. Fix this by including the extra slot for the filter map in the count computed in ipa_table_init_add(). Note: ipa_filter_reset_table() does not have this problem; it resets filter table entries one by one, but does not overwrite the filter bitmap. Fixes: 2b9feef2b6c2 ("soc: qcom: ipa: filter and routing tables") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_table.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2324e1b93e37..1da334f54944 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -430,7 +430,8 @@ static void ipa_table_init_add(struct gsi_trans *trans, bool filter, * table region determines the number of entries it has. */ if (filter) { - count = hweight32(ipa->filter_map); + /* Include one extra "slot" to hold the filter map itself */ + count = 1 + hweight32(ipa->filter_map); hash_count = hash_mem->size ? count : 0; } else { count = mem->size / sizeof(__le64); From 276aae377206d60b9b7b7df4586cd9f2a813f5d0 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Wed, 8 Sep 2021 15:43:35 +0800 Subject: [PATCH 034/866] net: stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer, unfortunately, it only can resolve it for system reboot stress test. System hang also can be reproduced easily during system suspend/resume stess test when mount NFS on i.MX8MP EVK board. In stmmac driver, eee feature is combined to phylink framework. When do system suspend, phylink_stop() would queue delayed work, it invokes stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly. In above commit, try to fix issue by deactivating eee_ctrl_timer obviously, but it is not enough. Looking into eee_ctrl_timer expire callback stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always asserted. This interrupt has chance to be issued when LPI state entry/exit from the MAC, and at that time, clock could have been already disabled. The result is that system hang when driver try to touch register from interrupt handler. The reason why above commit can fix system hang issue in stmmac_release() is that, deactivate eee_ctrl_timer not just after napi disabled, further after irq freed. In conclusion, hardware would generate LPI interrupt when clock has been disabled during suspend or resume, since hardware is in eee mode and LPI interrupt enabled. Interrupts from MAC, MTL and DMA level are enabled and never been disabled when system suspend, so postpone clocks management from suspend stage to noirq suspend stage should be more safe. Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled") Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ------ .../ethernet/stmicro/stmmac/stmmac_platform.c | 44 +++++++++++++++++++ 2 files changed, 44 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ece02b35a6ce..246f84fedbc8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); u32 chan; - int ret; if (!ndev || !netif_running(ndev)) return 0; @@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev) } else { stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); - /* Disable clock in case of PWM is off */ - clk_disable_unprepare(priv->plat->clk_ptp_ref); - ret = pm_runtime_force_suspend(dev); - if (ret) { - mutex_unlock(&priv->lock); - return ret; - } } mutex_unlock(&priv->lock); @@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev) priv->irq_wake = 0; } else { pinctrl_pm_select_default_state(priv->device); - /* enable the clk previously disabled */ - ret = pm_runtime_force_resume(dev); - if (ret) - return ret; - if (priv->plat->clk_ptp_ref) - clk_prepare_enable(priv->plat->clk_ptp_ref); /* reset the phy so that it's ready */ if (priv->mii) stmmac_mdio_reset(priv->mii); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5ca710844cc1..4885f9ad1b1e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -9,6 +9,7 @@ *******************************************************************************/ #include +#include #include #include #include @@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev) return stmmac_bus_clks_config(priv, true); } +static int stmmac_pltfr_noirq_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + int ret; + + if (!netif_running(ndev)) + return 0; + + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + /* Disable clock in case of PWM is off */ + clk_disable_unprepare(priv->plat->clk_ptp_ref); + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + } + + return 0; +} + +static int stmmac_pltfr_noirq_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + int ret; + + if (!netif_running(ndev)) + return 0; + + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + /* enable the clk previously disabled */ + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + clk_prepare_enable(priv->plat->clk_ptp_ref); + } + + return 0; +} + const struct dev_pm_ops stmmac_pltfr_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume) SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume) }; EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops); From 34b1999da935a33be6239226bfa6cd4f704c5c88 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 19 Aug 2021 16:27:17 +0300 Subject: [PATCH 035/866] x86/mm: Fix kern_addr_valid() to cope with existing but not present entries Jiri Olsa reported a fault when running: # cat /proc/kallsyms | grep ksys_read ffffffff8136d580 T ksys_read # objdump -d --start-address=0xffffffff8136d580 --stop-address=0xffffffff8136d590 /proc/kcore /proc/kcore: file format elf64-x86-64 Segmentation fault general protection fault, probably for non-canonical address 0xf887ffcbff000: 0000 [#1] SMP PTI CPU: 12 PID: 1079 Comm: objdump Not tainted 5.14.0-rc5qemu+ #508 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:kern_addr_valid Call Trace: read_kcore ? rcu_read_lock_sched_held ? rcu_read_lock_sched_held ? rcu_read_lock_sched_held ? trace_hardirqs_on ? rcu_read_lock_sched_held ? lock_acquire ? lock_acquire ? rcu_read_lock_sched_held ? lock_acquire ? rcu_read_lock_sched_held ? rcu_read_lock_sched_held ? rcu_read_lock_sched_held ? lock_release ? _raw_spin_unlock ? __handle_mm_fault ? rcu_read_lock_sched_held ? lock_acquire ? rcu_read_lock_sched_held ? lock_release proc_reg_read ? vfs_read vfs_read ksys_read do_syscall_64 entry_SYSCALL_64_after_hwframe The fault happens because kern_addr_valid() dereferences existent but not present PMD in the high kernel mappings. Such PMDs are created when free_kernel_image_pages() frees regions larger than 2Mb. In this case, a part of the freed memory is mapped with PMDs and the set_memory_np_noalias() -> ... -> __change_page_attr() sequence will mark the PMD as not present rather than wipe it completely. Have kern_addr_valid() check whether higher level page table entries are present before trying to dereference them to fix this issue and to avoid similar issues in the future. Stable backporting note: ------------------------ Note that the stable marking is for all active stable branches because there could be cases where pagetable entries exist but are not valid - see 9a14aefc1d28 ("x86: cpa, fix lookup_address"), for example. So make sure to be on the safe side here and use pXY_present() accessors rather than pXY_none() which could #GP when accessing pages in the direct map. Also see: c40a56a7818c ("x86/mm/init: Remove freed kernel image areas from alias mapping") for more info. Reported-by: Jiri Olsa Signed-off-by: Mike Rapoport Signed-off-by: Borislav Petkov Reviewed-by: David Hildenbrand Acked-by: Dave Hansen Tested-by: Jiri Olsa Cc: # 4.4+ Link: https://lkml.kernel.org/r/20210819132717.19358-1-rppt@kernel.org --- arch/x86/mm/init_64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ddeaba947eb3..879886c6cc53 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1433,18 +1433,18 @@ int kern_addr_valid(unsigned long addr) return 0; p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) + if (!p4d_present(*p4d)) return 0; pud = pud_offset(p4d, addr); - if (pud_none(*pud)) + if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return pfn_valid(pud_pfn(*pud)); pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) + if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) From 3c4cea8fa7f71f00c5279547043a84bc2a4d8b8c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 8 Sep 2021 13:42:09 +0200 Subject: [PATCH 036/866] vhost_net: fix OoB on sendmsg() failure. If the sendmsg() call in vhost_tx_batch() fails, both the 'batched_xdp' and 'done_idx' indexes are left unchanged. If such failure happens when batched_xdp == VHOST_NET_BATCH, the next call to vhost_net_build_xdp() will access and write memory outside the xdp buffers area. Since sendmsg() can only error with EBADFD, this change addresses the issue explicitly freeing the XDP buffers batch on error. Fixes: 0a0be13b8fe2 ("vhost_net: batch submitting XDP buffers to underlayer sockets") Suggested-by: Jason Wang Signed-off-by: Paolo Abeni Acked-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 3a249ee7e144..28ef323882fb 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -467,7 +467,7 @@ static void vhost_tx_batch(struct vhost_net *net, .num = nvq->batched_xdp, .ptr = nvq->xdp, }; - int err; + int i, err; if (nvq->batched_xdp == 0) goto signal_used; @@ -476,6 +476,15 @@ static void vhost_tx_batch(struct vhost_net *net, err = sock->ops->sendmsg(sock, msghdr, 0); if (unlikely(err < 0)) { vq_err(&nvq->vq, "Fail to batch sending packets\n"); + + /* free pages owned by XDP; since this is an unlikely error path, + * keep it simple and avoid more complex bulk update for the + * used pages + */ + for (i = 0; i < nvq->batched_xdp; ++i) + put_page(virt_to_head_page(nvq->xdp[i].data)); + nvq->batched_xdp = 0; + nvq->done_idx = 0; return; } From 273c29e944bda9a20a30c26cfc34c9a3f363280b Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Wed, 8 Sep 2021 09:58:20 -0700 Subject: [PATCH 037/866] ibmvnic: check failover_pending in login response If a failover occurs before a login response is received, the login response buffer maybe undefined. Check that there was no failover before accessing the login response buffer. Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol") Signed-off-by: Sukadev Bhattiprolu Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 6aa6ff89a765..a4579b340120 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4708,6 +4708,14 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, return 0; } + if (adapter->failover_pending) { + adapter->init_done_rc = -EAGAIN; + netdev_dbg(netdev, "Failover pending, ignoring login response\n"); + complete(&adapter->init_done); + /* login response buffer will be released on reset */ + return 0; + } + netdev->mtu = adapter->req_mtu - ETH_HLEN; netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); From d82d5303c4c539db86588ffb5dc5b26c3f1513e8 Mon Sep 17 00:00:00 2001 From: Tong Zhang Date: Wed, 8 Sep 2021 12:02:32 -0700 Subject: [PATCH 038/866] net: macb: fix use after free on rmmod plat_dev->dev->platform_data is released by platform_device_unregister(), use of pclk and hclk is a use-after-free. Since device unregister won't need a clk device we adjust the function call sequence to fix this issue. [ 31.261225] BUG: KASAN: use-after-free in macb_remove+0x77/0xc6 [macb_pci] [ 31.275563] Freed by task 306: [ 30.276782] platform_device_release+0x25/0x80 Suggested-by: Nicolas Ferre Signed-off-by: Tong Zhang Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb_pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index 8b7b59908a1a..f66d22de5168 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -111,9 +111,9 @@ static void macb_remove(struct pci_dev *pdev) struct platform_device *plat_dev = pci_get_drvdata(pdev); struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev); - platform_device_unregister(plat_dev); clk_unregister(plat_data->pclk); clk_unregister(plat_data->hclk); + platform_device_unregister(plat_dev); } static const struct pci_device_id dev_id_table[] = { From 04f08eb44b5011493d77b602fdec29ff0f5c6cd5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Sep 2021 17:00:29 -0700 Subject: [PATCH 039/866] net/af_unix: fix a data-race in unix_dgram_poll syzbot reported another data-race in af_unix [1] Lets change __skb_insert() to use WRITE_ONCE() when changing skb head qlen. Also, change unix_dgram_poll() to use lockless version of unix_recvq_full() It is verry possible we can switch all/most unix_recvq_full() to the lockless version, this will be done in a future kernel version. [1] HEAD commit: 8596e589b787732c8346f0482919e83cc9362db1 BUG: KCSAN: data-race in skb_queue_tail / unix_dgram_poll write to 0xffff88814eeb24e0 of 4 bytes by task 25815 on cpu 0: __skb_insert include/linux/skbuff.h:1938 [inline] __skb_queue_before include/linux/skbuff.h:2043 [inline] __skb_queue_tail include/linux/skbuff.h:2076 [inline] skb_queue_tail+0x80/0xa0 net/core/skbuff.c:3264 unix_dgram_sendmsg+0xff2/0x1600 net/unix/af_unix.c:1850 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2532 __do_sys_sendmmsg net/socket.c:2561 [inline] __se_sys_sendmmsg net/socket.c:2558 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2558 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88814eeb24e0 of 4 bytes by task 25834 on cpu 1: skb_queue_len include/linux/skbuff.h:1869 [inline] unix_recvq_full net/unix/af_unix.c:194 [inline] unix_dgram_poll+0x2bc/0x3e0 net/unix/af_unix.c:2777 sock_poll+0x23e/0x260 net/socket.c:1288 vfs_poll include/linux/poll.h:90 [inline] ep_item_poll fs/eventpoll.c:846 [inline] ep_send_events fs/eventpoll.c:1683 [inline] ep_poll fs/eventpoll.c:1798 [inline] do_epoll_wait+0x6ad/0xf00 fs/eventpoll.c:2226 __do_sys_epoll_wait fs/eventpoll.c:2238 [inline] __se_sys_epoll_wait fs/eventpoll.c:2233 [inline] __x64_sys_epoll_wait+0xf6/0x120 fs/eventpoll.c:2233 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000001b -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 25834 Comm: syz-executor.1 Tainted: G W 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 86b18aaa2b5b ("skbuff: fix a data race in skb_queue_len()") Cc: Qian Cai Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/unix/af_unix.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdb0db3e825..841e2f0f5240 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk, WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); - list->qlen++; + WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index eb47b9de2380..92345c9bb60c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3073,7 +3073,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer(sk); if (other && unix_peer(other) != sk && - unix_recvq_full(other) && + unix_recvq_full_lockless(other) && unix_dgram_peer_wake_me(sk, other)) writable = 0; From 9b6ff7eb666415e1558f1ba8a742f5db6a9954de Mon Sep 17 00:00:00 2001 From: Xiyu Yang Date: Thu, 9 Sep 2021 12:32:00 +0800 Subject: [PATCH 040/866] net/l2tp: Fix reference count leak in l2tp_udp_recv_core The reference count leak issue may take place in an error handling path. If both conditions of tunnel->version == L2TP_HDR_VER_3 and the return value of l2tp_v3_ensure_opt_in_linear is nonzero, the function would directly jump to label invalid, without decrementing the reference count of the l2tp_session object session increased earlier by l2tp_tunnel_get_session(). This may result in refcount leaks. Fix this issue by decrease the reference count before jumping to the label invalid. Fixes: 4522a70db7aa ("l2tp: fix reading optional fields of L2TPv3") Signed-off-by: Xiyu Yang Signed-off-by: Xin Xiong Signed-off-by: Xin Tan Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 53486b162f01..93271a2632b8 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -869,8 +869,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) } if (tunnel->version == L2TP_HDR_VER_3 && - l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { + l2tp_session_dec_refcount(session); goto invalid; + } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); From 2a48d96fd58a666ae231c3dd6fe4a458798ac645 Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Thu, 9 Sep 2021 17:23:22 +0800 Subject: [PATCH 041/866] net: stmmac: platform: fix build warning when with !CONFIG_PM_SLEEP Use __maybe_unused for noirq_suspend()/noirq_resume() hooks to avoid build warning with !CONFIG_PM_SLEEP: >> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c:796:12: error: 'stmmac_pltfr_noirq_resume' defined but not used [-Werror=unused-function] 796 | static int stmmac_pltfr_noirq_resume(struct device *dev) | ^~~~~~~~~~~~~~~~~~~~~~~~~ >> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c:775:12: error: 'stmmac_pltfr_noirq_suspend' defined but not used [-Werror=unused-function] 775 | static int stmmac_pltfr_noirq_suspend(struct device *dev) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors Fixes: 276aae377206 ("net: stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume") Reported-by: kernel test robot Signed-off-by: Joakim Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 4885f9ad1b1e..62cec9bfcd33 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -772,7 +772,7 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev) return stmmac_bus_clks_config(priv, true); } -static int stmmac_pltfr_noirq_suspend(struct device *dev) +static int __maybe_unused stmmac_pltfr_noirq_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); @@ -793,7 +793,7 @@ static int stmmac_pltfr_noirq_suspend(struct device *dev) return 0; } -static int stmmac_pltfr_noirq_resume(struct device *dev) +static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); From 415446185b939dcdcd6a483e705c805ab961e54c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Thu, 9 Sep 2021 11:28:45 +0200 Subject: [PATCH 042/866] sfc: fallback for lack of xdp tx queues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If there are not enough resources to allocate one TX queue per core for XDP TX it was completely disabled. This patch implements a fallback solution for sharing the available queues using __netif_tx_lock for synchronization. In the normal case that there is one TX queue per CPU, no locking is done, as it was before. With this fallback solution, XDP TX will work in much more cases that were failing, specially in machines with many CPUs. It's hard for XDP users to know what features are supported across different NICs and configurations, so they will benefit on having wider support. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 54 ++++++++++++++++++++----- drivers/net/ethernet/sfc/net_driver.h | 8 ++++ drivers/net/ethernet/sfc/tx.c | 21 ++++++---- 3 files changed, 64 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index e5b0d795c301..e7849f1260a1 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -166,32 +166,46 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, * We need a channel per event queue, plus a VI per tx queue. * This may be more pessimistic than it needs to be. */ - if (n_channels + n_xdp_ev > max_channels) { + if (n_channels >= max_channels) { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DISABLED; netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", n_xdp_ev, n_channels, max_channels); netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface"); - efx->n_xdp_channels = 0; - efx->xdp_tx_per_channel = 0; - efx->xdp_tx_queue_count = 0; + "XDP_TX and XDP_REDIRECT will not work on this interface\n"); } else if (n_channels + n_xdp_tx > efx->max_vis) { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DISABLED; netif_err(efx, drv, efx->net_dev, "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", n_xdp_tx, n_channels, efx->max_vis); netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface"); - efx->n_xdp_channels = 0; - efx->xdp_tx_per_channel = 0; - efx->xdp_tx_queue_count = 0; + "XDP_TX and XDP_REDIRECT will not work on this interface\n"); + } else if (n_channels + n_xdp_ev > max_channels) { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_SHARED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", + n_xdp_ev, n_channels, max_channels); + + n_xdp_ev = max_channels - n_channels; + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will work with reduced performance (%d cpus/tx_queue)\n", + DIV_ROUND_UP(n_xdp_tx, tx_per_ev * n_xdp_ev)); } else { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DEDICATED; + } + + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DISABLED) { efx->n_xdp_channels = n_xdp_ev; efx->xdp_tx_per_channel = tx_per_ev; efx->xdp_tx_queue_count = n_xdp_tx; n_channels += n_xdp_ev; netif_dbg(efx, drv, efx->net_dev, "Allocating %d TX and %d event queues for XDP\n", - n_xdp_tx, n_xdp_ev); + n_xdp_ev * tx_per_ev, n_xdp_ev); + } else { + efx->n_xdp_channels = 0; + efx->xdp_tx_per_channel = 0; + efx->xdp_tx_queue_count = 0; } if (vec_count < n_channels) { @@ -921,7 +935,25 @@ int efx_set_channels(struct efx_nic *efx) } } } - WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have less XDP TX queues than CPUs, assign the already existing + * queues to the exceeding CPUs (this means that we will have to use + * locking when transmitting with XDP) + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + channel = tx_queue->channel; + netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", + channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + + efx->xdp_tx_queues[xdp_queue_number++] = tx_queue; + } rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9b4b25704271..e731c766f709 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -782,6 +782,12 @@ struct efx_async_filter_insertion { #define EFX_RPS_MAX_IN_FLIGHT 8 #endif /* CONFIG_RFS_ACCEL */ +enum efx_xdp_tx_queues_mode { + EFX_XDP_TX_QUEUES_DEDICATED, /* one queue per core, locking not needed */ + EFX_XDP_TX_QUEUES_SHARED, /* each queue used by more than 1 core */ + EFX_XDP_TX_QUEUES_DISABLED /* xdp tx not available */ +}; + /** * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) @@ -820,6 +826,7 @@ struct efx_async_filter_insertion { * should be allocated for this NIC * @xdp_tx_queue_count: Number of entries in %xdp_tx_queues. * @xdp_tx_queues: Array of pointers to tx queues used for XDP transmit. + * @xdp_txq_queues_mode: XDP TX queues sharing strategy. * @rxq_entries: Size of receive queues requested by user. * @txq_entries: Size of transmit queues requested by user. * @txq_stop_thresh: TX queue fill level at or above which we stop it. @@ -979,6 +986,7 @@ struct efx_nic { unsigned int xdp_tx_queue_count; struct efx_tx_queue **xdp_tx_queues; + enum efx_xdp_tx_queues_mode xdp_txq_queues_mode; unsigned rxq_entries; unsigned txq_entries; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 0c6650d2e239..c7afd6cda902 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -430,21 +430,23 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, int cpu; int i; - cpu = raw_smp_processor_id(); + if (unlikely(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DISABLED)) + return -EINVAL; + if (unlikely(n && !xdpfs)) + return -EINVAL; + if (unlikely(!n)) + return 0; - if (!efx->xdp_tx_queue_count || - unlikely(cpu >= efx->xdp_tx_queue_count)) + cpu = raw_smp_processor_id(); + if (unlikely(cpu >= efx->xdp_tx_queue_count)) return -EINVAL; tx_queue = efx->xdp_tx_queues[cpu]; if (unlikely(!tx_queue)) return -EINVAL; - if (unlikely(n && !xdpfs)) - return -EINVAL; - - if (!n) - return 0; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) + HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); /* Check for available space. We should never need multiple * descriptors per frame. @@ -484,6 +486,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (flush && i > 0) efx_nic_push_buffers(tx_queue); + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) + HARD_TX_UNLOCK(efx->net_dev, tx_queue->core_txq); + return i == 0 ? -EIO : i; } From 6215b608a8c4d4a478721e14a6faa0dc56e4a693 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Thu, 9 Sep 2021 11:28:46 +0200 Subject: [PATCH 043/866] sfc: last resort fallback for lack of xdp tx queues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Previous patch addressed the situation of having some free resources for xdp tx but not enough for one tx queue per CPU. This patch address the worst case of not having resources at all for xdp tx. Instead of using queues dedicated to xdp, normal queues used by network stack are shared for both cases, using __netif_tx_lock for synchronization. Also queue stop/restart must be considered in the xdp path to avoid freezing the queue. This is not the ideal situation we might want to be, and a performance penalty is expected both for normal and xdp traffic, but at least XDP will work in all possible situations (with a warning in the logs), improving a bit the pain of not knowing in what situations we can use it and in what situations we cannot. Signed-off-by: Íñigo Huguet Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_channels.c | 82 ++++++++++++++----------- drivers/net/ethernet/sfc/net_driver.h | 2 +- drivers/net/ethernet/sfc/tx.c | 14 ++++- 3 files changed, 58 insertions(+), 40 deletions(-) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index e7849f1260a1..3dbea028b325 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -167,19 +167,19 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, * This may be more pessimistic than it needs to be. */ if (n_channels >= max_channels) { - efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DISABLED; - netif_err(efx, drv, efx->net_dev, - "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", - n_xdp_ev, n_channels, max_channels); - netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface\n"); + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", + n_xdp_ev, n_channels, max_channels); + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT might decrease device's performance\n"); } else if (n_channels + n_xdp_tx > efx->max_vis) { - efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DISABLED; - netif_err(efx, drv, efx->net_dev, - "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", - n_xdp_tx, n_channels, efx->max_vis); - netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface\n"); + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", + n_xdp_tx, n_channels, efx->max_vis); + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT might decrease device's performance\n"); } else if (n_channels + n_xdp_ev > max_channels) { efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_SHARED; netif_warn(efx, drv, efx->net_dev, @@ -194,7 +194,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DEDICATED; } - if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DISABLED) { + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_BORROWED) { efx->n_xdp_channels = n_xdp_ev; efx->xdp_tx_per_channel = tx_per_ev; efx->xdp_tx_queue_count = n_xdp_tx; @@ -205,7 +205,7 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, } else { efx->n_xdp_channels = 0; efx->xdp_tx_per_channel = 0; - efx->xdp_tx_queue_count = 0; + efx->xdp_tx_queue_count = n_xdp_tx; } if (vec_count < n_channels) { @@ -872,6 +872,20 @@ rollback: goto out; } +static inline int +efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + int efx_set_channels(struct efx_nic *efx) { struct efx_tx_queue *tx_queue; @@ -910,20 +924,9 @@ int efx_set_channels(struct efx_nic *efx) if (efx_channel_is_xdp_tx(channel)) { efx_for_each_channel_tx_queue(tx_queue, channel) { tx_queue->queue = next_queue++; - - /* We may have a few left-over XDP TX - * queues owing to xdp_tx_queue_count - * not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL. - * We still allocate and probe those - * TXQs, but never use them. - */ - if (xdp_queue_number < efx->xdp_tx_queue_count) { - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) xdp_queue_number++; - } } } else { efx_for_each_channel_tx_queue(tx_queue, channel) { @@ -932,6 +935,17 @@ int efx_set_channels(struct efx_nic *efx) channel->channel, tx_queue->label, tx_queue->queue); } + + /* If XDP is borrowing queues from net stack, it must use the queue + * with no csum offload, which is the first one of the channel + * (note: channel->tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } } } } @@ -940,19 +954,15 @@ int efx_set_channels(struct efx_nic *efx) WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && xdp_queue_number > efx->xdp_tx_queue_count); - /* If we have less XDP TX queues than CPUs, assign the already existing - * queues to the exceeding CPUs (this means that we will have to use - * locking when transmitting with XDP) + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs */ next_queue = 0; while (xdp_queue_number < efx->xdp_tx_queue_count) { tx_queue = efx->xdp_tx_queues[next_queue++]; - channel = tx_queue->channel; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - - efx->xdp_tx_queues[xdp_queue_number++] = tx_queue; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; } rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index e731c766f709..f6981810039d 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -785,7 +785,7 @@ struct efx_async_filter_insertion { enum efx_xdp_tx_queues_mode { EFX_XDP_TX_QUEUES_DEDICATED, /* one queue per core, locking not needed */ EFX_XDP_TX_QUEUES_SHARED, /* each queue used by more than 1 core */ - EFX_XDP_TX_QUEUES_DISABLED /* xdp tx not available */ + EFX_XDP_TX_QUEUES_BORROWED /* queues borrowed from net stack */ }; /** diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index c7afd6cda902..d16e031e95f4 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -428,10 +428,8 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, unsigned int len; int space; int cpu; - int i; + int i = 0; - if (unlikely(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DISABLED)) - return -EINVAL; if (unlikely(n && !xdpfs)) return -EINVAL; if (unlikely(!n)) @@ -448,6 +446,15 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); + /* If we're borrowing net stack queues we have to handle stop-restart + * or we might block the queue and it will be considered as frozen + */ + if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { + if (netif_tx_queue_stopped(tx_queue->core_txq)) + goto unlock; + efx_tx_maybe_stop_queue(tx_queue); + } + /* Check for available space. We should never need multiple * descriptors per frame. */ @@ -486,6 +493,7 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (flush && i > 0) efx_nic_push_buffers(tx_queue); +unlock: if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_UNLOCK(efx->net_dev, tx_queue->core_txq); From e011912651bdf72840d88e8a8de3716bbcc4be99 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 8 Sep 2021 21:49:53 -0700 Subject: [PATCH 044/866] net: ni65: Avoid typecast of pointer to u32 Building alpha:allmodconfig results in the following error. drivers/net/ethernet/amd/ni65.c: In function 'ni65_stop_start': drivers/net/ethernet/amd/ni65.c:751:37: error: cast from pointer to integer of different size buffer[i] = (u32) isa_bus_to_virt(tmdp->u.buffer); 'buffer[]' is declared as unsigned long, so replace the typecast to u32 with a typecast to unsigned long to fix the problem. Cc: Arnd Bergmann Signed-off-by: Guenter Roeck Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/ni65.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index b5df7ad5a83f..032e8922b482 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -748,7 +748,7 @@ static void ni65_stop_start(struct net_device *dev,struct priv *p) #ifdef XMT_VIA_SKB skb_save[i] = p->tmd_skb[i]; #endif - buffer[i] = (u32) isa_bus_to_virt(tmdp->u.buffer); + buffer[i] = (unsigned long)isa_bus_to_virt(tmdp->u.buffer); blen[i] = tmdp->blen; tmdp->u.s.status = 0x0; } From 58eafe1ff52ee1ce255759fc15729519af180cbb Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 7 Sep 2021 13:44:36 -0500 Subject: [PATCH 045/866] ASoC: Intel: sof_sdw: tag SoundWire BEs as non-atomic The SoundWire BEs make use of 'stream' functions for .prepare and .trigger. These functions will in turn force a Bank Switch, which implies a wait operation. Mark SoundWire BEs as nonatomic for consistency, but keep all other types of BEs as is. The initialization of .nonatomic is done outside of the create_sdw_dailink helper to avoid adding more parameters to deal with a single exception to the rule that BEs are atomic. Suggested-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Ranjani Sridharan Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20210907184436.33152-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/intel/boards/sof_sdw.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 6602eda89e8e..6b06248a9327 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -929,6 +929,11 @@ static int create_sdw_dailink(struct snd_soc_card *card, cpus + *cpu_id, cpu_dai_num, codecs, codec_num, NULL, &sdw_ops); + /* + * SoundWire DAILINKs use 'stream' functions and Bank Switch operations + * based on wait_for_completion(), tag them as 'nonatomic'. + */ + dai_links[*be_index].nonatomic = true; ret = set_codec_init_func(card, link, dai_links + (*be_index)++, playback, group_id); From 5a80dea93191d55840f42252ed3e4565a125a514 Mon Sep 17 00:00:00 2001 From: Trevor Wu Date: Thu, 9 Sep 2021 14:55:33 +0800 Subject: [PATCH 046/866] ASoC: mediatek: add required config dependency Because SND_SOC_MT8195 depends on COMPILE_TEST, it's possible to build MT8195 driver in many different config combinations. Add all dependent config for SND_SOC_MT8195 in case some errors happen when COMPILE_TEST is enabled. Signed-off-by: Trevor Wu Reported-by: Randy Dunlap Link: https://lore.kernel.org/r/20210909065533.2114-1-trevor.wu@mediatek.com Signed-off-by: Mark Brown --- sound/soc/mediatek/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 5a2f4667d50b..81ad2dcee9eb 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config SND_SOC_MEDIATEK tristate + select REGMAP_MMIO config SND_SOC_MT2701 tristate "ASoC support for Mediatek MT2701 chip" @@ -188,7 +189,9 @@ config SND_SOC_MT8192_MT6359_RT1015_RT5682 config SND_SOC_MT8195 tristate "ASoC support for Mediatek MT8195 chip" depends on ARCH_MEDIATEK || COMPILE_TEST + depends on COMMON_CLK select SND_SOC_MEDIATEK + select MFD_SYSCON if SND_SOC_MT6359 help This adds ASoC platform driver support for Mediatek MT8195 chip that can be used with other codecs. From 2bab94090b01bc593d8bc25f68df41f198721173 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 6 Sep 2021 21:53:58 -0700 Subject: [PATCH 047/866] spi: tegra20-slink: Declare runtime suspend and resume functions conditionally The following build error is seen with CONFIG_PM=n. drivers/spi/spi-tegra20-slink.c:1188:12: error: 'tegra_slink_runtime_suspend' defined but not used drivers/spi/spi-tegra20-slink.c:1200:12: error: 'tegra_slink_runtime_resume' defined but not used Declare the functions only if PM is enabled. While at it, remove the unnecessary forward declarations. Signed-off-by: Guenter Roeck Reviewed-by: Geert Uytterhoeven Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20210907045358.2138282-1-linux@roeck-us.net Signed-off-by: Mark Brown --- drivers/spi/spi-tegra20-slink.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index ebd27f883033..8ce840c7ecc8 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -204,9 +204,6 @@ struct tegra_slink_data { struct dma_async_tx_descriptor *tx_dma_desc; }; -static int tegra_slink_runtime_suspend(struct device *dev); -static int tegra_slink_runtime_resume(struct device *dev); - static inline u32 tegra_slink_readl(struct tegra_slink_data *tspi, unsigned long reg) { @@ -1185,6 +1182,7 @@ static int tegra_slink_resume(struct device *dev) } #endif +#ifdef CONFIG_PM static int tegra_slink_runtime_suspend(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); @@ -1210,6 +1208,7 @@ static int tegra_slink_runtime_resume(struct device *dev) } return 0; } +#endif /* CONFIG_PM */ static const struct dev_pm_ops slink_pm_ops = { SET_RUNTIME_PM_OPS(tegra_slink_runtime_suspend, From 0add491df4e5e2c8cc6eeeaa6dbcca50f932090c Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 19 Aug 2021 10:49:26 -0400 Subject: [PATCH 048/866] ext4: remove extent cache entries when truncating inline data Conditionally remove all cached extents belonging to an inode when truncating its inline data. It's only necessary to attempt to remove cached extents when a conversion from inline to extent storage has been initiated (!EXT4_STATE_MAY_INLINE_DATA). This avoids unnecessary es lock overhead in the more common inline case. Signed-off-by: Eric Whitney Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210819144927.25163-2-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/inline.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 50a3031bf466..39a1ab129fdc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "ext4_jbd2.h" #include "ext4.h" @@ -1918,6 +1919,24 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) EXT4_I(inode)->i_disksize = i_size; if (i_size < inline_size) { + /* + * if there's inline data to truncate and this file was + * converted to extents after that inline data was written, + * the extent status cache must be cleared to avoid leaving + * behind stale delayed allocated extent entries + */ + if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { +retry: + err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); + if (err == -ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (err) + goto out_error; + } + /* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) From 948ca5f30e1df0c11eb5b0f410b9ceb97fa77ad9 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 19 Aug 2021 10:49:27 -0400 Subject: [PATCH 049/866] ext4: enforce buffer head state assertion in ext4_da_map_blocks Remove the code that re-initializes a buffer head with an invalid block number and BH_New and BH_Delay bits when a matching delayed and unwritten block has been found in the extent status cache. Replace it with assertions that verify the buffer head already has this state correctly set. The current code masked an inline data truncation bug that left stale entries in the extent status cache. With this change, generic/130 can be used to reproduce and detect that bug. Signed-off-by: Eric Whitney Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210819144927.25163-3-enwlinux@gmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8204176256c8..2a076d236ba1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1706,13 +1706,16 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, } /* - * Delayed extent could be allocated by fallocate. - * So we need to check it. + * the buffer head associated with a delayed and not unwritten + * block found in the extent status cache must contain an + * invalid block number and have its BH_New and BH_Delay bits + * set, reflecting the state assigned when the block was + * initially delayed allocated */ - if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); + if (ext4_es_is_delonly(&es)) { + BUG_ON(bh->b_blocknr != invalid_block); + BUG_ON(!buffer_new(bh)); + BUG_ON(!buffer_delay(bh)); return 0; } From 26be23af1866eead5a29f8501f9d774ac277d0bd Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Thu, 9 Sep 2021 16:54:49 +0200 Subject: [PATCH 050/866] MAINTAINERS: fix update references to stm32 audio bindings The 00d38fd8d2524 ("MAINTAINERS: update references to stm32 audio bindings") commit update the bindings reference, by removing bindings/sound/st,stm32-adfsdm.txt, to set the new reference to bindings/iio/adc/st,stm32-*.yaml. This leads to "get_maintainer finds" the match for the Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml, but also to the IIO bindings Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml And The commit fixes only a part of the problem: Documentation/devicetree/bindings/sound/st,stm32-*.txt file have been also moved to yaml. Update references to include all stm32 audio bindings file and exclude the st,stm32-adc.yaml bindings file. cc: Mauro Carvalho Chehab Fixes: 0d38fd8d2524 ("MAINTAINERS: update references to stm32 audio bindings") Signed-off-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20210909145449.24388-1-arnaud.pouliquen@foss.st.com Signed-off-by: Mark Brown --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index c6b8a720c0bc..33d99e9cf3e1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17718,7 +17718,8 @@ M: Olivier Moysan M: Arnaud Pouliquen L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml +F: Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml +F: Documentation/devicetree/bindings/sound/st,stm32-*.yaml F: sound/soc/stm/ STM32 TIMER/LPTIMER DRIVERS From bfe84435090a6c85271b02a42b1d83fef9ff7cc7 Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Thu, 9 Sep 2021 08:12:23 -0700 Subject: [PATCH 051/866] ice: Correctly deal with PFs that do not support RDMA There are two cases where the current PF does not support RDMA functionality. The first is if the NVM loaded on the device is set to not support RDMA (common_caps.rdma is false). The second is if the kernel bonding driver has included the current PF in an active link aggregate. When the driver has determined that this PF does not support RDMA, then auxiliary devices should not be created on the auxiliary bus. Without a device on the auxiliary bus, even if the irdma driver is present, there will be no RDMA activity attempted on this PF. Currently, in the reset flow, an attempt to create auxiliary devices is performed without regard to the ability of the PF. There needs to be a check in ice_aux_plug_dev (as the central point that creates auxiliary devices) to see if the PF is in a state to support the functionality. When disabling and re-enabling RDMA due to the inclusion/removal of the PF in a link aggregate, we also need to set/clear the bit which controls auxiliary device creation so that a reset recovery in a link aggregate situation doesn't try to create auxiliary devices when it shouldn't. Fixes: f9f5301e7e2d ("ice: Register auxiliary device to provide RDMA") Reported-by: Yongxin Liu Signed-off-by: Dave Ertman Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice.h | 2 ++ drivers/net/ethernet/intel/ice/ice_idc.c | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index eadcb9958346..3c4f08d20414 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -695,6 +695,7 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) { if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + set_bit(ICE_FLAG_AUX_ENA, pf->flags); ice_plug_aux_dev(pf); } } @@ -707,5 +708,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { ice_unplug_aux_dev(pf); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 1f2afdf6cd48..adcc9a251595 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -271,6 +271,12 @@ int ice_plug_aux_dev(struct ice_pf *pf) struct auxiliary_device *adev; int ret; + /* if this PF doesn't support a technology that requires auxiliary + * devices, then gracefully exit + */ + if (!ice_is_aux_ena(pf)) + return 0; + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); if (!iadev) return -ENOMEM; From e3f0cc1a945fcefec0c7c9d9dfd028a51daa1846 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 9 Sep 2021 10:33:28 -0700 Subject: [PATCH 052/866] r6040: Restore MDIO clock frequency after MAC reset A number of users have reported that they were not able to get the PHY to successfully link up, especially after commit c36757eb9dee ("net: phy: consider AN_RESTART status when reading link status") where we stopped reading just BMSR, but we also read BMCR to determine the link status. Andrius at NetBSD did a wonderful job at debugging the problem and found out that the MDIO bus clock frequency would be incorrectly set back to its default value which would prevent the MDIO bus controller from reading PHY registers properly. Back when we only read BMSR, if we read all 1s, we could falsely indicate a link status, though in general there is a cable plugged in, so this went unnoticed. After a second read of BMCR was added, a wrong read will lead to the inability to determine a link UP condition which is when it started to be visibly broken, even if it was long before that. The fix consists in restoring the value of the MD_CSR register that was set prior to the MAC reset. Link: http://gnats.netbsd.org/cgi-bin/query-pr-single.pl?number=53494 Fixes: 90f750a81a29 ("r6040: consolidate MAC reset to its own function") Reported-by: Andrius V Reported-by: Darek Strugacz Tested-by: Darek Strugacz Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/rdc/r6040.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 4b2eca5e08e2..01ef5efd7bc2 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -119,6 +119,8 @@ #define PHY_ST 0x8A /* PHY status register */ #define MAC_SM 0xAC /* MAC status machine */ #define MAC_SM_RST 0x0002 /* MAC status machine reset */ +#define MD_CSC 0xb6 /* MDC speed control register */ +#define MD_CSC_DEFAULT 0x0030 #define MAC_ID 0xBE /* Identifier register */ #define TX_DCNT 0x80 /* TX descriptor count */ @@ -355,8 +357,9 @@ static void r6040_reset_mac(struct r6040_private *lp) { void __iomem *ioaddr = lp->base; int limit = MAC_DEF_TIMEOUT; - u16 cmd; + u16 cmd, md_csc; + md_csc = ioread16(ioaddr + MD_CSC); iowrite16(MAC_RST, ioaddr + MCR1); while (limit--) { cmd = ioread16(ioaddr + MCR1); @@ -368,6 +371,10 @@ static void r6040_reset_mac(struct r6040_private *lp) iowrite16(MAC_SM_RST, ioaddr + MAC_SM); iowrite16(0, ioaddr + MAC_SM); mdelay(5); + + /* Restore MDIO clock frequency */ + if (md_csc != MD_CSC_DEFAULT) + iowrite16(md_csc, ioaddr + MD_CSC); } static void r6040_init_mac_regs(struct net_device *dev) From dc41c4a98a76640e7085815f937eadd1f336ba85 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 9 Sep 2021 20:49:47 +0300 Subject: [PATCH 053/866] net/packet: clarify source of pr_*() messages Add pr_fmt macro to spell out the source of messages in prefix. Before this patch: packet size is too long (1543 > 1518) With this patch: af_packet: packet size is too long (1543 > 1518) Signed-off-by: Baruch Siach Signed-off-by: David S. Miller --- net/packet/af_packet.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 543365f58e97..2a2bc64f75cf 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -46,6 +46,8 @@ * Copyright (C) 2011, */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include From 20e100f52730cd0db609e559799c1712b5f27582 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Fri, 10 Sep 2021 11:33:56 +0300 Subject: [PATCH 054/866] qed: Handle management FW error Handle MFW (management FW) error response in order to avoid a crash during recovery flows. Changes from v1: - Add "Fixes tag". Fixes: tag 5e7ba042fd05 ("qed: Fix reading stale configuration information") Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 6e5a6cc97d0e..24cd41567775 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3367,6 +3367,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, struct qed_nvm_image_att *p_image_att) { enum nvm_image_type type; + int rc; u32 i; /* Translate image_id into MFW definitions */ @@ -3395,7 +3396,10 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, return -EINVAL; } - qed_mcp_nvm_info_populate(p_hwfn); + rc = qed_mcp_nvm_info_populate(p_hwfn); + if (rc) + return rc; + for (i = 0; i < p_hwfn->nvm_info.num_images; i++) if (type == p_hwfn->nvm_info.image_att[i].image_type) break; From 666eb96d85dcbc93aacc186a037db2e05b92b9f5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 10 Sep 2021 12:15:11 +0100 Subject: [PATCH 055/866] qlcnic: Remove redundant initialization of variable ret The variable ret is being initialized with a value that is never read, it is being updated later on. The assignment is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 0a2f34fc8b24..27dffa299ca6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1354,10 +1354,10 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter) struct qlc_83xx_fw_info *fw_info = adapter->ahw->fw_info; const struct firmware *fw = fw_info->fw; u32 dest, *p_cache, *temp; - int i, ret = -EIO; __le32 *temp_le; u8 data[16]; size_t size; + int i, ret; u64 addr; temp = vzalloc(fw->size); From 9c3ad33b5a412d8bc0a377e7cd9baa53ed52f22d Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 3 Sep 2021 18:30:02 +0800 Subject: [PATCH 056/866] ASoC: fsl_sai: register platform component before registering cpu dai There is no defer probe when adding platform component to snd_soc_pcm_runtime(rtd), the code is in snd_soc_add_pcm_runtime() snd_soc_register_card() -> snd_soc_bind_card() -> snd_soc_add_pcm_runtime() -> adding cpu dai -> adding codec dai -> adding platform component. So if the platform component is not ready at that time, then the sound card still registered successfully, but platform component is empty, the sound card can't be used. As there is defer probe checking for cpu dai component, then register platform component before cpu dai to avoid such issue. Fixes: 435508214942 ("ASoC: Add SAI SoC Digital Audio Interface driver") Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1630665006-31437-2-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_sai.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 223fcd15bfcc..38f6362099d5 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -1152,11 +1152,10 @@ static int fsl_sai_probe(struct platform_device *pdev) if (ret < 0) goto err_pm_get_sync; - ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, - &sai->cpu_dai_drv, 1); - if (ret) - goto err_pm_get_sync; - + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ if (sai->soc_data->use_imx_pcm) { ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE); if (ret) @@ -1167,6 +1166,11 @@ static int fsl_sai_probe(struct platform_device *pdev) goto err_pm_get_sync; } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, + &sai->cpu_dai_drv, 1); + if (ret) + goto err_pm_get_sync; + return ret; err_pm_get_sync: From f12ce92e98b21c1fc669cd74e12c54a0fe3bc2eb Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 3 Sep 2021 18:30:03 +0800 Subject: [PATCH 057/866] ASoC: fsl_esai: register platform component before registering cpu dai There is no defer probe when adding platform component to snd_soc_pcm_runtime(rtd), the code is in snd_soc_add_pcm_runtime() snd_soc_register_card() -> snd_soc_bind_card() -> snd_soc_add_pcm_runtime() -> adding cpu dai -> adding codec dai -> adding platform component. So if the platform component is not ready at that time, then the sound card still registered successfully, but platform component is empty, the sound card can't be used. As there is defer probe checking for cpu dai component, then register platform component before cpu dai to avoid such issue. Fixes: 43d24e76b698 ("ASoC: fsl_esai: Add ESAI CPU DAI driver") Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1630665006-31437-3-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_esai.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index a961f837cd09..bda66b30e063 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -1073,6 +1073,16 @@ static int fsl_esai_probe(struct platform_device *pdev) if (ret < 0) goto err_pm_get_sync; + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE); + if (ret) { + dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret); + goto err_pm_get_sync; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) { @@ -1082,12 +1092,6 @@ static int fsl_esai_probe(struct platform_device *pdev) INIT_WORK(&esai_priv->work, fsl_esai_hw_reset); - ret = imx_pcm_dma_init(pdev, IMX_ESAI_DMABUF_SIZE); - if (ret) { - dev_err(&pdev->dev, "failed to init imx pcm dma: %d\n", ret); - goto err_pm_get_sync; - } - return ret; err_pm_get_sync: From 0adf292069dcca8bab76a603251fcaabf77468ca Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 3 Sep 2021 18:30:04 +0800 Subject: [PATCH 058/866] ASoC: fsl_micfil: register platform component before registering cpu dai There is no defer probe when adding platform component to snd_soc_pcm_runtime(rtd), the code is in snd_soc_add_pcm_runtime() snd_soc_register_card() -> snd_soc_bind_card() -> snd_soc_add_pcm_runtime() -> adding cpu dai -> adding codec dai -> adding platform component. So if the platform component is not ready at that time, then the sound card still registered successfully, but platform component is empty, the sound card can't be used. As there is defer probe checking for cpu dai component, then register platform component before cpu dai to avoid such issue. Fixes: 47a70e6fc9a8 ("ASoC: Add MICFIL SoC Digital Audio Interface driver.") Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1630665006-31437-4-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_micfil.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 8c0c75ce9490..9f90989ac59a 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -737,18 +737,23 @@ static int fsl_micfil_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); regcache_cache_only(micfil->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); + if (ret) { + dev_err(&pdev->dev, "failed to pcm register\n"); + return ret; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_micfil_component, &fsl_micfil_dai, 1); if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); - return ret; } - ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); - if (ret) - dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; } From ee8ccc2eb5840e34fce088bdb174fd5329153ef0 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 3 Sep 2021 18:30:05 +0800 Subject: [PATCH 059/866] ASoC: fsl_spdif: register platform component before registering cpu dai There is no defer probe when adding platform component to snd_soc_pcm_runtime(rtd), the code is in snd_soc_add_pcm_runtime() snd_soc_register_card() -> snd_soc_bind_card() -> snd_soc_add_pcm_runtime() -> adding cpu dai -> adding codec dai -> adding platform component. So if the platform component is not ready at that time, then the sound card still registered successfully, but platform component is empty, the sound card can't be used. As there is defer probe checking for cpu dai component, then register platform component before cpu dai to avoid such issue. Fixes: a2388a498ad2 ("ASoC: fsl: Add S/PDIF CPU DAI driver") Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1630665006-31437-5-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_spdif.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index 8ffb1a6048d6..1c53719bb61e 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1434,6 +1434,16 @@ static int fsl_spdif_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); regcache_cache_only(spdif_priv->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE); + if (ret) { + dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n"); + goto err_pm_disable; + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_spdif_component, &spdif_priv->cpu_dai_drv, 1); if (ret) { @@ -1441,12 +1451,6 @@ static int fsl_spdif_probe(struct platform_device *pdev) goto err_pm_disable; } - ret = imx_pcm_dma_init(pdev, IMX_SPDIF_DMABUF_SIZE); - if (ret) { - dev_err_probe(&pdev->dev, ret, "imx_pcm_dma_init failed\n"); - goto err_pm_disable; - } - return ret; err_pm_disable: From c590fa80b39287a91abeb487829f3190e7ae775f Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Fri, 3 Sep 2021 18:30:06 +0800 Subject: [PATCH 060/866] ASoC: fsl_xcvr: register platform component before registering cpu dai There is no defer probe when adding platform component to snd_soc_pcm_runtime(rtd), the code is in snd_soc_add_pcm_runtime() snd_soc_register_card() -> snd_soc_bind_card() -> snd_soc_add_pcm_runtime() -> adding cpu dai -> adding codec dai -> adding platform component. So if the platform component is not ready at that time, then the sound card still registered successfully, but platform component is empty, the sound card can't be used. As there is defer probe checking for cpu dai component, then register platform component before cpu dai to avoid such issue. Fixes: 28564486866f ("ASoC: fsl_xcvr: Add XCVR ASoC CPU DAI driver") Signed-off-by: Shengjiu Wang Link: https://lore.kernel.org/r/1630665006-31437-6-git-send-email-shengjiu.wang@nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_xcvr.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index 31c5ee641fe7..7ba2fd15132d 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -1215,18 +1215,23 @@ static int fsl_xcvr_probe(struct platform_device *pdev) pm_runtime_enable(dev); regcache_cache_only(xcvr->regmap, true); + /* + * Register platform component before registering cpu dai for there + * is not defer probe for platform component in snd_soc_add_pcm_runtime(). + */ + ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0); + if (ret) { + dev_err(dev, "failed to pcm register\n"); + return ret; + } + ret = devm_snd_soc_register_component(dev, &fsl_xcvr_comp, &fsl_xcvr_dai, 1); if (ret) { dev_err(dev, "failed to register component %s\n", fsl_xcvr_comp.name); - return ret; } - ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0); - if (ret) - dev_err(dev, "failed to pcm register\n"); - return ret; } From 1dd038522615b70f5f8945c5631e9e2fa5bd58b1 Mon Sep 17 00:00:00 2001 From: Trevor Wu Date: Fri, 10 Sep 2021 17:26:13 +0800 Subject: [PATCH 061/866] ASoC: mediatek: common: handle NULL case in suspend/resume function When memory allocation for afe->reg_back_up fails, reg_back_up can't be used. Keep the suspend/resume flow but skip register backup when afe->reg_back_up is NULL, in case illegal memory access happens. Fixes: 283b612429a2 ("ASoC: mediatek: implement mediatek common structure") Signed-off-by: Trevor Wu Reported-by: Dan Carpenter Link: https://lore.kernel.org/r/20210910092613.30188-1-trevor.wu@mediatek.com Signed-off-by: Mark Brown --- sound/soc/mediatek/common/mtk-afe-fe-dai.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/sound/soc/mediatek/common/mtk-afe-fe-dai.c b/sound/soc/mediatek/common/mtk-afe-fe-dai.c index baaa5881b1d4..e95c7c018e7d 100644 --- a/sound/soc/mediatek/common/mtk-afe-fe-dai.c +++ b/sound/soc/mediatek/common/mtk-afe-fe-dai.c @@ -334,9 +334,11 @@ int mtk_afe_suspend(struct snd_soc_component *component) devm_kcalloc(dev, afe->reg_back_up_list_num, sizeof(unsigned int), GFP_KERNEL); - for (i = 0; i < afe->reg_back_up_list_num; i++) - regmap_read(regmap, afe->reg_back_up_list[i], - &afe->reg_back_up[i]); + if (afe->reg_back_up) { + for (i = 0; i < afe->reg_back_up_list_num; i++) + regmap_read(regmap, afe->reg_back_up_list[i], + &afe->reg_back_up[i]); + } afe->suspended = true; afe->runtime_suspend(dev); @@ -356,12 +358,13 @@ int mtk_afe_resume(struct snd_soc_component *component) afe->runtime_resume(dev); - if (!afe->reg_back_up) + if (!afe->reg_back_up) { dev_dbg(dev, "%s no reg_backup\n", __func__); - - for (i = 0; i < afe->reg_back_up_list_num; i++) - mtk_regmap_write(regmap, afe->reg_back_up_list[i], - afe->reg_back_up[i]); + } else { + for (i = 0; i < afe->reg_back_up_list_num; i++) + mtk_regmap_write(regmap, afe->reg_back_up_list[i], + afe->reg_back_up[i]); + } afe->suspended = false; return 0; From 2f1aaf3ea666b737ad717b3d88667225aca23149 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 9 Sep 2021 08:49:59 -0700 Subject: [PATCH 062/866] bpf, mm: Fix lockdep warning triggered by stack_map_get_build_id_offset() Currently the bpf selftest "get_stack_raw_tp" triggered the warning: [ 1411.304463] WARNING: CPU: 3 PID: 140 at include/linux/mmap_lock.h:164 find_vma+0x47/0xa0 [ 1411.304469] Modules linked in: bpf_testmod(O) [last unloaded: bpf_testmod] [ 1411.304476] CPU: 3 PID: 140 Comm: systemd-journal Tainted: G W O 5.14.0+ #53 [ 1411.304479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 1411.304481] RIP: 0010:find_vma+0x47/0xa0 [ 1411.304484] Code: de 48 89 ef e8 ba f5 fe ff 48 85 c0 74 2e 48 83 c4 08 5b 5d c3 48 8d bf 28 01 00 00 be ff ff ff ff e8 2d 9f d8 00 85 c0 75 d4 <0f> 0b 48 89 de 48 8 [ 1411.304487] RSP: 0018:ffffabd440403db8 EFLAGS: 00010246 [ 1411.304490] RAX: 0000000000000000 RBX: 00007f00ad80a0e0 RCX: 0000000000000000 [ 1411.304492] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.304494] RBP: ffff9cf5c2f50000 R08: ffff9cf5c3eb25d8 R09: 00000000fffffffe [ 1411.304496] R10: 0000000000000001 R11: 00000000ef974e19 R12: ffff9cf5c39ae0e0 [ 1411.304498] R13: 0000000000000000 R14: 0000000000000000 R15: ffff9cf5c39ae0e0 [ 1411.304501] FS: 00007f00ae754780(0000) GS:ffff9cf5fba00000(0000) knlGS:0000000000000000 [ 1411.304504] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.304506] CR2: 000000003e34343c CR3: 0000000103a98005 CR4: 0000000000370ee0 [ 1411.304508] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.304510] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.304512] Call Trace: [ 1411.304517] stack_map_get_build_id_offset+0x17c/0x260 [ 1411.304528] __bpf_get_stack+0x18f/0x230 [ 1411.304541] bpf_get_stack_raw_tp+0x5a/0x70 [ 1411.305752] RAX: 0000000000000000 RBX: 5541f689495641d7 RCX: 0000000000000000 [ 1411.305756] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.305758] RBP: ffff9cf5c02b2f40 R08: ffff9cf5ca7606c0 R09: ffffcbd43ee02c04 [ 1411.306978] bpf_prog_32007c34f7726d29_bpf_prog1+0xaf/0xd9c [ 1411.307861] R10: 0000000000000001 R11: 0000000000000044 R12: ffff9cf5c2ef60e0 [ 1411.307865] R13: 0000000000000005 R14: 0000000000000000 R15: ffff9cf5c2ef6108 [ 1411.309074] bpf_trace_run2+0x8f/0x1a0 [ 1411.309891] FS: 00007ff485141700(0000) GS:ffff9cf5fae00000(0000) knlGS:0000000000000000 [ 1411.309896] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.311221] syscall_trace_enter.isra.20+0x161/0x1f0 [ 1411.311600] CR2: 00007ff48514d90e CR3: 0000000107114001 CR4: 0000000000370ef0 [ 1411.312291] do_syscall_64+0x15/0x80 [ 1411.312941] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.313803] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 1411.314223] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.315082] RIP: 0033:0x7f00ad80a0e0 [ 1411.315626] Call Trace: [ 1411.315632] stack_map_get_build_id_offset+0x17c/0x260 To reproduce, first build `test_progs` binary: make -C tools/testing/selftests/bpf -j60 and then run the binary at tools/testing/selftests/bpf directory: ./test_progs -t get_stack_raw_tp The warning is due to commit 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") which added mmap_assert_locked() in find_vma() function. The mmap_assert_locked() function asserts that mm->mmap_lock needs to be held. But this is not the case for bpf_get_stack() or bpf_get_stackid() helper (kernel/bpf/stackmap.c), which uses mmap_read_trylock_non_owner() instead. Since mm->mmap_lock is not held in bpf_get_stack[id]() use case, the above warning is emitted during test run. This patch fixed the issue by (1). using mmap_read_trylock() instead of mmap_read_trylock_non_owner() to satisfy lockdep checking in find_vma(), and (2). droping lockdep for mmap_lock right before the irq_work_queue(). The function mmap_read_trylock_non_owner() is also removed since after this patch nobody calls it any more. Fixes: 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") Suggested-by: Jason Gunthorpe Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Reviewed-by: Liam R. Howlett Cc: Luigi Rizzo Cc: Jason Gunthorpe Cc: linux-mm@kvack.org Link: https://lore.kernel.org/bpf/20210909155000.1610299-1-yhs@fb.com --- include/linux/mmap_lock.h | 9 --------- kernel/bpf/stackmap.c | 10 ++++++++-- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 0540f0156f58..3af8f7fb067d 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) __mmap_lock_trace_released(mm, false); } -static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) -{ - if (mmap_read_trylock(mm)) { - rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); - return true; - } - return false; -} - static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e8eefdf8cf3e..09a3fd97d329 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * with build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; @@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } if (!work) { - mmap_read_unlock_non_owner(current->mm); + mmap_read_unlock(current->mm); } else { work->mm = current->mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } From 345e1ae0c6ba54f6a4d32154e80cadc2ee2ef1af Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 27 Aug 2021 23:22:02 +0100 Subject: [PATCH 063/866] afs: Fix missing put on afs_read objects and missing get on the key therein The afs_read objects created by afs_req_issue_op() get leaked because afs_alloc_read() returns a ref and then afs_fetch_data() gets its own ref which is released when the operation completes, but the initial ref is never released. Fix this by discarding the initial ref at the end of afs_req_issue_op(). This leak also covered another bug whereby a ref isn't got on the key attached to the read record by afs_req_issue_op(). This isn't a problem as long as the afs_read req never goes away... Fix this by calling key_get() in afs_req_issue_op(). This was found by the generic/074 test. It leaks a bunch of kmalloc-192 objects each time it is run, which can be observed by watching /proc/slabinfo. Fixes: f7605fa869cf ("afs: Fix leak of afs_read objects") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-and-tested-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163010394740.3035676.8516846193899793357.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163111665914.283156.3038561975681836591.stgit@warthog.procyon.org.uk/ --- fs/afs/file.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/afs/file.c b/fs/afs/file.c index db035ae2a134..6688fff14b0b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -295,7 +295,7 @@ static void afs_req_issue_op(struct netfs_read_subrequest *subreq) fsreq->subreq = subreq; fsreq->pos = subreq->start + subreq->transferred; fsreq->len = subreq->len - subreq->transferred; - fsreq->key = subreq->rreq->netfs_priv; + fsreq->key = key_get(subreq->rreq->netfs_priv); fsreq->vnode = vnode; fsreq->iter = &fsreq->def_iter; @@ -304,6 +304,7 @@ static void afs_req_issue_op(struct netfs_read_subrequest *subreq) fsreq->pos, fsreq->len); afs_fetch_data(fsreq->vnode, fsreq); + afs_put_read(fsreq); } static int afs_symlink_readpage(struct page *page) From 581b2027af0018944ba301d68e7af45c6d1128b5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Sep 2021 09:15:21 +0100 Subject: [PATCH 064/866] afs: Fix page leak There's a loop in afs_extend_writeback() that adds extra pages to a write we want to make to improve the efficiency of the writeback by making it larger. This loop stops, however, if we hit a page we can't write back from immediately, but it doesn't get rid of the page ref we speculatively acquired. This was caused by the removal of the cleanup loop when the code switched from using find_get_pages_contig() to xarray scanning as the latter only gets a single page at a time, not a batch. Fix this by putting the page on a ref on an early break from the loop. Unfortunately, we can't just add that page to the pagevec we're employing as we'll go through that and add those pages to the RPC call. This was found by the generic/074 test. It leaks ~4GiB of RAM each time it is run - which can be observed with "top". Fixes: e87b03f5830e ("afs: Prepare for use of THPs") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-and-tested-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111666635.283156.177701903478910460.stgit@warthog.procyon.org.uk/ --- fs/afs/write.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/afs/write.c b/fs/afs/write.c index c0534697268e..66b235266893 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -471,13 +471,18 @@ static void afs_extend_writeback(struct address_space *mapping, } /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) + if (unlikely(page != xas_reload(&xas))) { + put_page(page); break; + } - if (!trylock_page(page)) + if (!trylock_page(page)) { + put_page(page); break; + } if (!PageDirty(page) || PageWriteback(page)) { unlock_page(page); + put_page(page); break; } @@ -487,6 +492,7 @@ static void afs_extend_writeback(struct address_space *mapping, t = afs_page_dirty_to(page, priv); if (f != 0 && !new_content) { unlock_page(page); + put_page(page); break; } From 08dad2f4d541fcfe5e7bfda72cc6314bbfd2802f Mon Sep 17 00:00:00 2001 From: Jesper Nilsson Date: Fri, 10 Sep 2021 21:55:34 +0200 Subject: [PATCH 065/866] net: stmmac: allow CSR clock of 300MHz The Synopsys Ethernet IP uses the CSR clock as a base clock for MDC. The divisor used is set in the MAC_MDIO_Address register field CR (Clock Rate) The divisor is there to change the CSR clock into a clock that falls below the IEEE 802.3 specified max frequency of 2.5MHz. If the CSR clock is 300MHz, the code falls back to using the reset value in the MAC_MDIO_Address register, as described in the comment above this code. However, 300MHz is actually an allowed value and the proper divider can be estimated quite easily (it's just 1Hz difference!) A CSR frequency of 300MHz with the maximum clock rate value of 0x5 (STMMAC_CSR_250_300M, a divisor of 124) gives somewhere around ~2.42MHz which is below the IEEE 802.3 specified maximum. For the ARTPEC-8 SoC, the CSR clock is this problematic 300MHz, and unfortunately, the reset-value of the MAC_MDIO_Address CR field is 0x0. This leads to a clock rate of zero and a divisor of 42, and gives an MDC frequency of ~7.14MHz. Allow CSR clock of 300MHz by making the comparison inclusive. Signed-off-by: Jesper Nilsson Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 246f84fedbc8..553c4403258a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -309,7 +309,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_100_150M; else if ((clk_rate >= CSR_F_150M) && (clk_rate < CSR_F_250M)) priv->clk_csr = STMMAC_CSR_150_250M; - else if ((clk_rate >= CSR_F_250M) && (clk_rate < CSR_F_300M)) + else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M)) priv->clk_csr = STMMAC_CSR_250_300M; } From 7ad9bb9d0f357dcab5eb9a0f28d1c8983c48434c Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Fri, 10 Sep 2021 18:57:13 +0000 Subject: [PATCH 066/866] asm-generic/hyperv: provide cpumask_to_vpset_noself This is a new variant which removes `self' cpu from the vpset. It will be used in Hyper-V enlightened IPI code. Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210910185714.299411-2-wei.liu@kernel.org --- include/asm-generic/mshyperv.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 9a000ba2bb75..9a134806f1d5 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -184,10 +184,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) return hv_vp_index[cpu_number]; } -static inline int cpumask_to_vpset(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int __cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool exclude_self) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + int this_cpu = smp_processor_id(); /* valid_bank_mask can represent up to 64 banks */ if (hv_max_vp_index / 64 >= 64) @@ -205,6 +207,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { + if (exclude_self && cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) return -1; @@ -219,6 +223,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +static inline int cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + return __cpumask_to_vpset(vpset, cpus, false); +} + +static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + WARN_ON_ONCE(preemptible()); + return __cpumask_to_vpset(vpset, cpus, true); +} + void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); From dfb5c1e12c28e35e4d4e5bc8022b0e9d585b89a7 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Fri, 10 Sep 2021 18:57:14 +0000 Subject: [PATCH 067/866] x86/hyperv: remove on-stack cpumask from hv_send_ipi_mask_allbutself It is not a good practice to allocate a cpumask on stack, given it may consume up to 1 kilobytes of stack space if the kernel is configured to have 8192 cpus. The internal helper functions __send_ipi_mask{,_ex} need to loop over the provided mask anyway, so it is not too difficult to skip `self' there. We can thus do away with the on-stack cpumask in hv_send_ipi_mask_allbutself. Adjust call sites of __send_ipi_mask as needed. Reported-by: Linus Torvalds Suggested-by: Michael Kelley Suggested-by: Linus Torvalds Fixes: 68bb7bfb7985d ("X86/Hyper-V: Enable IPI enlightenments") Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210910185714.299411-3-wei.liu@kernel.org --- arch/x86/hyperv/hv_apic.c | 43 +++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 90e682a92820..32a1ad356c18 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -99,7 +99,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) /* * IPI implementation on Hyper-V. */ -static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) +static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, + bool exclude_self) { struct hv_send_ipi_ex **arg; struct hv_send_ipi_ex *ipi_arg; @@ -123,7 +124,10 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) if (!cpumask_equal(mask, cpu_present_mask)) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); + if (exclude_self) + nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); + else + nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); } if (nr_bank < 0) goto ipi_mask_ex_done; @@ -138,15 +142,25 @@ ipi_mask_ex_done: return hv_result_success(status); } -static bool __send_ipi_mask(const struct cpumask *mask, int vector) +static bool __send_ipi_mask(const struct cpumask *mask, int vector, + bool exclude_self) { - int cur_cpu, vcpu; + int cur_cpu, vcpu, this_cpu = smp_processor_id(); struct hv_send_ipi ipi_arg; u64 status; + unsigned int weight; trace_hyperv_send_ipi_mask(mask, vector); - if (cpumask_empty(mask)) + weight = cpumask_weight(mask); + + /* + * Do nothing if + * 1. the mask is empty + * 2. the mask only contains self when exclude_self is true + */ + if (weight == 0 || + (exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask))) return true; if (!hv_hypercall_pg) @@ -172,6 +186,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) ipi_arg.cpu_mask = 0; for_each_cpu(cur_cpu, mask) { + if (exclude_self && cur_cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cur_cpu); if (vcpu == VP_INVAL) return false; @@ -191,7 +207,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector) return hv_result_success(status); do_ex_hypercall: - return __send_ipi_mask_ex(mask, vector); + return __send_ipi_mask_ex(mask, vector, exclude_self); } static bool __send_ipi_one(int cpu, int vector) @@ -208,7 +224,7 @@ static bool __send_ipi_one(int cpu, int vector) return false; if (vp >= 64) - return __send_ipi_mask_ex(cpumask_of(cpu), vector); + return __send_ipi_mask_ex(cpumask_of(cpu), vector, false); status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp)); return hv_result_success(status); @@ -222,20 +238,13 @@ static void hv_send_ipi(int cpu, int vector) static void hv_send_ipi_mask(const struct cpumask *mask, int vector) { - if (!__send_ipi_mask(mask, vector)) + if (!__send_ipi_mask(mask, vector, false)) orig_apic.send_IPI_mask(mask, vector); } static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { - unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; - const struct cpumask *local_mask; - - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; - if (!__send_ipi_mask(local_mask, vector)) + if (!__send_ipi_mask(mask, vector, true)) orig_apic.send_IPI_mask_allbutself(mask, vector); } @@ -246,7 +255,7 @@ static void hv_send_ipi_allbutself(int vector) static void hv_send_ipi_all(int vector) { - if (!__send_ipi_mask(cpu_online_mask, vector)) + if (!__send_ipi_mask(cpu_online_mask, vector, false)) orig_apic.send_IPI_all(vector); } From ce062a0adbfe933b1932235fdfd874c4c91d1bb0 Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Sat, 11 Sep 2021 17:50:09 +0200 Subject: [PATCH 068/866] net: dsa: qca8k: fix kernel panic with legacy mdio mapping When the mdio legacy mapping is used the mii_bus priv registered by DSA refer to the dsa switch struct instead of the qca8k_priv struct and causes a kernel panic. Create dedicated function when the internal dedicated mdio driver is used to properly handle the 2 different implementation. Fixes: 759bafb8a322 ("net: dsa: qca8k: add support for internal phy and internal mdio") Signed-off-by: Ansuel Smith Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 1f63f50f73f1..bda5a9bf4f52 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -643,10 +643,8 @@ qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask) } static int -qca8k_mdio_write(struct mii_bus *salve_bus, int phy, int regnum, u16 data) +qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) { - struct qca8k_priv *priv = salve_bus->priv; - struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -682,10 +680,8 @@ exit: } static int -qca8k_mdio_read(struct mii_bus *salve_bus, int phy, int regnum) +qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) { - struct qca8k_priv *priv = salve_bus->priv; - struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -726,6 +722,24 @@ exit: return ret; } +static int +qca8k_internal_mdio_write(struct mii_bus *slave_bus, int phy, int regnum, u16 data) +{ + struct qca8k_priv *priv = slave_bus->priv; + struct mii_bus *bus = priv->bus; + + return qca8k_mdio_write(bus, phy, regnum, data); +} + +static int +qca8k_internal_mdio_read(struct mii_bus *slave_bus, int phy, int regnum) +{ + struct qca8k_priv *priv = slave_bus->priv; + struct mii_bus *bus = priv->bus; + + return qca8k_mdio_read(bus, phy, regnum); +} + static int qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) { @@ -775,8 +789,8 @@ qca8k_mdio_register(struct qca8k_priv *priv, struct device_node *mdio) bus->priv = (void *)priv; bus->name = "qca8k slave mii"; - bus->read = qca8k_mdio_read; - bus->write = qca8k_mdio_write; + bus->read = qca8k_internal_mdio_read; + bus->write = qca8k_internal_mdio_write; snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d", ds->index); From 1b704b27beb11ce147d64b21c914e57afbfb5656 Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Sat, 11 Sep 2021 16:14:18 +0200 Subject: [PATCH 069/866] selftest: net: fix typo in altname test If altname deletion of the short alternative name fails, the error message printed is: "Failed to add short alternative name". This is obviously a typo, as we are testing altname deletion. Fix this using a proper error message. Fixes: f95e6c9c4617 ("selftest: net: add alternative names test") Signed-off-by: Andrea Claudi Signed-off-by: David S. Miller --- tools/testing/selftests/net/altnames.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/altnames.sh b/tools/testing/selftests/net/altnames.sh index 4254ddc3f70b..1ef9e4159bba 100755 --- a/tools/testing/selftests/net/altnames.sh +++ b/tools/testing/selftests/net/altnames.sh @@ -45,7 +45,7 @@ altnames_test() check_err $? "Got unexpected long alternative name from link show JSON" ip link property del $DUMMY_DEV altname $SHORT_NAME - check_err $? "Failed to add short alternative name" + check_err $? "Failed to delete short alternative name" ip -j -p link show $SHORT_NAME &>/dev/null check_fail $? "Unexpected success while trying to do link show with deleted short alternative name" From f11ee2ad25b22c2ee587045dd6999434375532f7 Mon Sep 17 00:00:00 2001 From: Len Baker Date: Sat, 11 Sep 2021 12:28:18 +0200 Subject: [PATCH 070/866] net: mana: Prefer struct_size over open coded arithmetic As noted in the "Deprecated Interfaces, Language Features, Attributes, and Conventions" documentation [1], size calculations (especially multiplication) should not be performed in memory allocator (or similar) function arguments due to the risk of them overflowing. This could lead to values wrapping around and a smaller allocation being made than the caller was expecting. Using those allocations could lead to linear overflows of heap memory and other misbehaviors. So, use the struct_size() helper to do the arithmetic instead of the argument "size + count * size" in the kzalloc() function. [1] https://www.kernel.org/doc/html/v5.14/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments Signed-off-by: Len Baker Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index c1310ea1c216..d5c485a6d284 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -398,9 +398,7 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth, int err; u16 i; - dma_buf = kzalloc(sizeof(*dma_buf) + - q_depth * sizeof(struct hwc_work_request), - GFP_KERNEL); + dma_buf = kzalloc(struct_size(dma_buf, reqs, q_depth), GFP_KERNEL); if (!dma_buf) return -ENOMEM; From 23c69b90365c8280b627aa969393d828ff47ac14 Mon Sep 17 00:00:00 2001 From: suma hegde Date: Thu, 2 Sep 2021 23:11:54 +0530 Subject: [PATCH 071/866] hwmon: (k10temp) Remove residues of current and voltage Commit id "b00647c46c9d7f6ee1ff6aaf335906101755e614", adds reporting current and voltage to k10temp.c The commit id "0a4e668b5d52eed8026f5d717196b02b55fb2dc6", removed reporting current and voltage from k10temp.c The curr and in(voltage) entries are not removed from "k10temp_info" structure. Removing those residue entries. while at it, update k10temp driver documentation Signed-off-by: suma hegde Cc: Guenter Roeck Link: https://lore.kernel.org/r/20210902174155.7365-2-nchatrad@amd.com Signed-off-by: Guenter Roeck --- Documentation/hwmon/k10temp.rst | 17 ----------------- drivers/hwmon/k10temp.c | 6 ------ 2 files changed, 23 deletions(-) diff --git a/Documentation/hwmon/k10temp.rst b/Documentation/hwmon/k10temp.rst index 8557e26281c3..91b99adc6c48 100644 --- a/Documentation/hwmon/k10temp.rst +++ b/Documentation/hwmon/k10temp.rst @@ -132,20 +132,3 @@ On Family 17h and Family 18h CPUs, additional temperature sensors may report Core Complex Die (CCD) temperatures. Up to 8 such temperatures are reported as temp{3..10}_input, labeled Tccd{1..8}. Actual support depends on the CPU variant. - -Various Family 17h and 18h CPUs report voltage and current telemetry -information. The following attributes may be reported. - -Attribute Label Description -=============== ======= ================ -in0_input Vcore Core voltage -in1_input Vsoc SoC voltage -curr1_input Icore Core current -curr2_input Isoc SoC current -=============== ======= ================ - -Current values are raw (unscaled) as reported by the CPU. Core current is -reported as multiples of 1A / LSB. SoC is reported as multiples of 0.25A -/ LSB. The real current is board specific. Reported currents should be seen -as rough guidance, and should be scaled using sensors3.conf as appropriate -for a given board. diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 38bc35ac8135..3618a924e78e 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -362,12 +362,6 @@ static const struct hwmon_channel_info *k10temp_info[] = { HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL), - HWMON_CHANNEL_INFO(in, - HWMON_I_INPUT | HWMON_I_LABEL, - HWMON_I_INPUT | HWMON_I_LABEL), - HWMON_CHANNEL_INFO(curr, - HWMON_C_INPUT | HWMON_C_LABEL, - HWMON_C_INPUT | HWMON_C_LABEL), NULL }; From 16c8d2df7ec0eed31b7d3b61cb13206a7fb930cc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 12 Sep 2021 06:45:07 -0600 Subject: [PATCH 072/866] io_uring: ensure symmetry in handling iter types in loop_rw_iter() When setting up the next segment, we check what type the iter is and handle it accordingly. However, when incrementing and processed amount we do not, and both iter advance and addr/len are adjusted, regardless of type. Split the increment side just like we do on the setup side. Fixes: 4017eb91a9e7 ("io_uring: make loop_rw_iter() use original user supplied pointers") Cc: stable@vger.kernel.org Reported-by: Valentina Palmiotti Reviewed-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 16fb7436043c..66a7414c3756 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3263,12 +3263,15 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) ret = nr; break; } + if (!iov_iter_is_bvec(iter)) { + iov_iter_advance(iter, nr); + } else { + req->rw.len -= nr; + req->rw.addr += nr; + } ret += nr; if (nr != iovec.iov_len) break; - req->rw.len -= nr; - req->rw.addr += nr; - iov_iter_advance(iter, nr); } return ret; From 7a842fb589e3cdbe205bc16dc37c30cf13383159 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sun, 12 Sep 2021 03:40:50 +0800 Subject: [PATCH 073/866] io-wq: code clean of io_wqe_create_worker() Remove do_create to save a local variable. Signed-off-by: Hao Xu Signed-off-by: Jens Axboe --- fs/io-wq.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 6c55362c1f99..a1685b40a4bf 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -246,8 +246,6 @@ static bool io_wqe_activate_free_worker(struct io_wqe *wqe, */ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) { - bool do_create = false; - /* * Most likely an attempt to queue unbounded work on an io_wq that * wasn't setup with any unbounded workers. @@ -256,18 +254,15 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) pr_warn_once("io-wq is not configured for unbound workers"); raw_spin_lock(&wqe->lock); - if (acct->nr_workers < acct->max_workers) { - acct->nr_workers++; - do_create = true; + if (acct->nr_workers == acct->max_workers) { + raw_spin_unlock(&wqe->lock); + return true; } + acct->nr_workers++; raw_spin_unlock(&wqe->lock); - if (do_create) { - atomic_inc(&acct->nr_running); - atomic_inc(&wqe->wq->worker_refs); - return create_io_worker(wqe->wq, wqe, acct->index); - } - - return true; + atomic_inc(&acct->nr_running); + atomic_inc(&wqe->wq->worker_refs); + return create_io_worker(wqe->wq, wqe, acct->index); } static void io_wqe_inc_running(struct io_worker *worker) From 767a65e9f31789d80e41edd03a802314905e8fbf Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sun, 12 Sep 2021 03:40:52 +0800 Subject: [PATCH 074/866] io-wq: fix potential race of acct->nr_workers Given max_worker is 1, and we currently have 1 running and it is exiting. There may be race like: io_wqe_enqueue worker1 no work there and timeout unlock(wqe->lock) ->insert work -->io_worker_exit lock(wqe->lock) ->if(!nr_workers) //it's still 1 unlock(wqe->lock) goto run_cancel lock(wqe->lock) nr_workers-- ->dec_running ->worker creation fails unlock(wqe->lock) We enqueued one work but there is no workers, causes hung. Signed-off-by: Hao Xu Signed-off-by: Jens Axboe --- fs/io-wq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index a1685b40a4bf..3d4460df845c 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -176,7 +176,6 @@ static void io_worker_ref_put(struct io_wq *wq) static void io_worker_exit(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; - struct io_wqe_acct *acct = io_wqe_get_acct(worker); if (refcount_dec_and_test(&worker->ref)) complete(&worker->ref_done); @@ -186,7 +185,6 @@ static void io_worker_exit(struct io_worker *worker) if (worker->flags & IO_WORKER_F_FREE) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); - acct->nr_workers--; preempt_disable(); io_wqe_dec_running(worker); worker->flags = 0; @@ -569,6 +567,7 @@ loop: } /* timed out, exit unless we're the last worker */ if (last_timeout && acct->nr_workers > 1) { + acct->nr_workers--; raw_spin_unlock(&wqe->lock); __set_current_state(TASK_RUNNING); break; From 67f3b2f822b7e71cfc9b42dbd9f3144fa2933e0b Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 6 Sep 2021 14:50:03 +0800 Subject: [PATCH 075/866] blk-mq: avoid to iterate over stale request blk-mq can't run allocating driver tag and updating ->rqs[tag] atomically, meantime blk-mq doesn't clear ->rqs[tag] after the driver tag is released. So there is chance to iterating over one stale request just after the tag is allocated and before updating ->rqs[tag]. scsi_host_busy_iter() calls scsi_host_check_in_flight() to count scsi in-flight requests after scsi host is blocked, so no new scsi command can be marked as SCMD_STATE_INFLIGHT. However, driver tag allocation still can be run by blk-mq core. One request is marked as SCMD_STATE_INFLIGHT, but this request may have been kept in another slot of ->rqs[], meantime the slot can be allocated out but ->rqs[] isn't updated yet. Then this in-flight request is counted twice as SCMD_STATE_INFLIGHT. This way causes trouble in handling scsi error. Fixes the issue by not iterating over stale request. Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" Reported-by: luojiaxing Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20210906065003.439019-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 86f87346232a..ff5caeb82542 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -208,7 +208,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; - if (!rq || !refcount_inc_not_zero(&rq->ref)) + if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; From 64794d6db49730d22f440aef0cf4da98a56a4ea3 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 13 Sep 2021 11:10:42 +0900 Subject: [PATCH 076/866] ALSA: oxfw: fix transmission method for Loud models based on OXFW971 Loud Technologies Mackie Onyx 1640i (former model) is identified as the model which uses OXFW971. The analysis of packet dump shows that it transfers events in blocking method of IEC 61883-6, however the default behaviour of ALSA oxfw driver is for non-blocking method. This commit adds code to detect it assuming that all of loud models based on OXFW971 have such quirk. It brings no functional change except for alignment rule of PCM buffer. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20210913021042.10085-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- sound/firewire/oxfw/oxfw.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index cb5b5e3a481b..daf731364695 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -184,13 +184,16 @@ static int detect_quirks(struct snd_oxfw *oxfw, const struct ieee1394_device_id model = val; } - /* - * Mackie Onyx Satellite with base station has a quirk to report a wrong - * value in 'dbs' field of CIP header against its format information. - */ - if (vendor == VENDOR_LOUD && model == MODEL_SATELLITE) + if (vendor == VENDOR_LOUD) { + // Mackie Onyx Satellite with base station has a quirk to report a wrong + // value in 'dbs' field of CIP header against its format information. oxfw->quirks |= SND_OXFW_QUIRK_WRONG_DBS; + // OXFW971-based models may transfer events by blocking method. + if (!(oxfw->quirks & SND_OXFW_QUIRK_JUMBO_PAYLOAD)) + oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION; + } + return 0; } From 3978d816523991dd86cf9aae88c295230a5ea3b2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Sep 2021 19:22:50 +0100 Subject: [PATCH 077/866] afs: Add missing vnode validation checks afs_d_revalidate() should only be validating the directory entry it is given and the directory to which that belongs; it shouldn't be validating the inode/vnode to which that dentry points. Besides, validation need to be done even if we don't call afs_d_revalidate() - which might be the case if we're starting from a file descriptor. In order for afs_d_revalidate() to be fixed, validation points must be added in some other places. Certain directory operations, such as afs_unlink(), already check this, but not all and not all file operations either. Note that the validation of a vnode not only checks to see if the attributes we have are correct, but also gets a promise from the server to notify us if that file gets changed by a third party. Add the following checks: - Check the vnode we're going to make a hard link to. - Check the vnode we're going to move/rename. - Check the vnode we're going to read from. - Check the vnode we're going to write to. - Check the vnode we're going to sync. - Check the vnode we're going to make a mapped page writable for. Some of these aren't strictly necessary as we're going to perform a server operation that might get the attributes anyway from which we can determine if something changed - though it might not get us a callback promise. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111667354.283156.12720698333342917516.stgit@warthog.procyon.org.uk/ --- fs/afs/dir.c | 11 +++++++++++ fs/afs/file.c | 16 +++++++++++++++- fs/afs/write.c | 17 +++++++++++++++-- 3 files changed, 41 insertions(+), 3 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index ac829e63c570..a8e3ae55f1f9 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1792,6 +1792,10 @@ static int afs_link(struct dentry *from, struct inode *dir, goto error; } + ret = afs_validate(vnode, op->key); + if (ret < 0) + goto error_op; + afs_op_set_vnode(op, 0, dvnode); afs_op_set_vnode(op, 1, vnode); op->file[0].dv_delta = 1; @@ -1805,6 +1809,8 @@ static int afs_link(struct dentry *from, struct inode *dir, op->create.reason = afs_edit_dir_for_link; return afs_do_sync_operation(op); +error_op: + afs_put_operation(op); error: d_drop(dentry); _leave(" = %d", ret); @@ -1989,6 +1995,11 @@ static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, if (IS_ERR(op)) return PTR_ERR(op); + ret = afs_validate(vnode, op->key); + op->error = ret; + if (ret < 0) + goto error; + afs_op_set_vnode(op, 0, orig_dvnode); afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */ op->file[0].dv_delta = 1; diff --git a/fs/afs/file.c b/fs/afs/file.c index 6688fff14b0b..4c8d786b53e0 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -24,12 +24,13 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, static int afs_releasepage(struct page *page, gfp_t gfp_flags); static void afs_readahead(struct readahead_control *ractl); +static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); const struct file_operations afs_file_operations = { .open = afs_open, .release = afs_release, .llseek = generic_file_llseek, - .read_iter = generic_file_read_iter, + .read_iter = afs_file_read_iter, .write_iter = afs_file_write, .mmap = afs_file_mmap, .splice_read = generic_file_splice_read, @@ -503,3 +504,16 @@ static int afs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_ops = &afs_vm_ops; return ret; } + +static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); + struct afs_file *af = iocb->ki_filp->private_data; + int ret; + + ret = afs_validate(vnode, af->key); + if (ret < 0) + return ret; + + return generic_file_read_iter(iocb, iter); +} diff --git a/fs/afs/write.c b/fs/afs/write.c index 66b235266893..32a764c24284 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -807,6 +807,7 @@ int afs_writepages(struct address_space *mapping, ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); + struct afs_file *af = iocb->ki_filp->private_data; ssize_t result; size_t count = iov_iter_count(from); @@ -822,6 +823,10 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) if (!count) return 0; + result = afs_validate(vnode, af->key); + if (result < 0) + return result; + result = generic_file_write_iter(iocb, from); _leave(" = %zd", result); @@ -835,13 +840,18 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) */ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - struct inode *inode = file_inode(file); - struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); + struct afs_file *af = file->private_data; + int ret; _enter("{%llx:%llu},{n=%pD},%d", vnode->fid.vid, vnode->fid.vnode, file, datasync); + ret = afs_validate(vnode, af->key); + if (ret < 0) + return ret; + return file_write_and_wait_range(file, start, end); } @@ -855,11 +865,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_file *af = file->private_data; unsigned long priv; vm_fault_t ret = VM_FAULT_RETRY; _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + afs_validate(vnode, af->key); + sb_start_pagefault(inode->i_sb); /* Wait for the page to be written to the cache before we allow it to From 63d49d843ef5fffeea069e0ffdfbd2bf40ba01c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 1 Sep 2021 18:11:33 +0100 Subject: [PATCH 078/866] afs: Fix incorrect triggering of sillyrename on 3rd-party invalidation The AFS filesystem is currently triggering the silly-rename cleanup from afs_d_revalidate() when it sees that a dentry has been changed by a third party[1]. It should not be doing this as the cleanup includes deleting the silly-rename target file on iput. Fix this by removing the places in the d_revalidate handling that validate anything other than the directory and the dirent. It probably should not be looking to validate the target inode of the dentry also. This includes removing the point in afs_d_revalidate() where the inode that a dentry used to point to was marked as being deleted (AFS_VNODE_DELETED). We don't know it got deleted. It could have been renamed or it could have hard links remaining. This was reproduced by cloning a git repo onto an afs volume on one machine, switching to another machine and doing "git status", then switching back to the first and doing "git status". The second status would show weird output due to ".git/index" getting deleted by the above mentioned mechanism. A simpler way to do it is to do: machine 1: touch a machine 2: touch b; mv -f b a machine 1: stat a on an afs volume. The bug shows up as the stat failing with ENOENT and the file server log showing that machine 1 deleted "a". Fixes: 79ddbfa500b3 ("afs: Implement sillyrename for unlink and rename") Reported-by: Markus Suvanto Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=214217#c4 [1] Link: https://lore.kernel.org/r/163111668100.283156.3851669884664475428.stgit@warthog.procyon.org.uk/ --- fs/afs/dir.c | 46 +++++++--------------------------------------- 1 file changed, 7 insertions(+), 39 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index a8e3ae55f1f9..4579bbda4634 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1077,9 +1077,9 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, */ static int afs_d_revalidate_rcu(struct dentry *dentry) { - struct afs_vnode *dvnode, *vnode; + struct afs_vnode *dvnode; struct dentry *parent; - struct inode *dir, *inode; + struct inode *dir; long dir_version, de_version; _enter("%p", dentry); @@ -1109,18 +1109,6 @@ static int afs_d_revalidate_rcu(struct dentry *dentry) return -ECHILD; } - /* Check to see if the vnode referred to by the dentry still - * has a callback. - */ - if (d_really_is_positive(dentry)) { - inode = d_inode_rcu(dentry); - if (inode) { - vnode = AFS_FS_I(inode); - if (!afs_check_validity(vnode)) - return -ECHILD; - } - } - return 1; /* Still valid */ } @@ -1156,17 +1144,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (IS_ERR(key)) key = NULL; - if (d_really_is_positive(dentry)) { - inode = d_inode(dentry); - if (inode) { - vnode = AFS_FS_I(inode); - afs_validate(vnode, key); - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) - goto out_bad; - } - } - - /* lock down the parent dentry so we can peer at it */ + /* Hold the parent dentry so we can peer at it */ parent = dget_parent(dentry); dir = AFS_FS_I(d_inode(parent)); @@ -1175,7 +1153,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (test_bit(AFS_VNODE_DELETED, &dir->flags)) { _debug("%pd: parent dir deleted", dentry); - goto out_bad_parent; + goto not_found; } /* We only need to invalidate a dentry if the server's copy changed @@ -1201,12 +1179,12 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) case 0: /* the filename maps to something */ if (d_really_is_negative(dentry)) - goto out_bad_parent; + goto not_found; inode = d_inode(dentry); if (is_bad_inode(inode)) { printk("kAFS: afs_d_revalidate: %pd2 has bad inode\n", dentry); - goto out_bad_parent; + goto not_found; } vnode = AFS_FS_I(inode); @@ -1228,9 +1206,6 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) dentry, fid.unique, vnode->fid.unique, vnode->vfs_inode.i_generation); - write_seqlock(&vnode->cb_lock); - set_bit(AFS_VNODE_DELETED, &vnode->flags); - write_sequnlock(&vnode->cb_lock); goto not_found; } goto out_valid; @@ -1245,7 +1220,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) default: _debug("failed to iterate dir %pd: %d", parent, ret); - goto out_bad_parent; + goto not_found; } out_valid: @@ -1256,16 +1231,9 @@ out_valid_noupdate: _leave(" = 1 [valid]"); return 1; - /* the dirent, if it exists, now points to a different vnode */ not_found: - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_NFSFS_RENAMED; - spin_unlock(&dentry->d_lock); - -out_bad_parent: _debug("dropping dentry %pd2", dentry); dput(parent); -out_bad: key_put(key); _leave(" = 0 [bad]"); From 6e0e99d58a6530cf65f10e4bb16630c5be6c254d Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Sep 2021 16:43:10 +0100 Subject: [PATCH 079/866] afs: Fix mmap coherency vs 3rd-party changes Fix the coherency management of mmap'd data such that 3rd-party changes become visible as soon as possible after the callback notification is delivered by the fileserver. This is done by the following means: (1) When we break a callback on a vnode specified by the CB.CallBack call from the server, we queue a work item (vnode->cb_work) to go and clobber all the PTEs mapping to that inode. This causes the CPU to trip through the ->map_pages() and ->page_mkwrite() handlers if userspace attempts to access the page(s) again. (Ideally, this would be done in the service handler for CB.CallBack, but the server is waiting for our reply before considering, and we have a list of vnodes, all of which need breaking - and the process of getting the mmap_lock and stripping the PTEs on all CPUs could be quite slow.) (2) Call afs_validate() from the ->map_pages() handler to check to see if the file has changed and to get a new callback promise from the server. Also handle the fileserver telling us that it's dropping all callbacks, possibly after it's been restarted by sending us a CB.InitCallBackState* call by the following means: (3) Maintain a per-cell list of afs files that are currently mmap'd (cell->fs_open_mmaps). (4) Add a work item to each server that is invoked if there are any open mmaps when CB.InitCallBackState happens. This work item goes through the aforementioned list and invokes the vnode->cb_work work item for each one that is currently using this server. This causes the PTEs to be cleared, causing ->map_pages() or ->page_mkwrite() to be called again, thereby calling afs_validate() again. I've chosen to simply strip the PTEs at the point of notification reception rather than invalidate all the pages as well because (a) it's faster, (b) we may get a notification for other reasons than the data being altered (in which case we don't want to clobber the pagecache) and (c) we need to ask the server to find out - and I don't want to wait for the reply before holding up userspace. This was tested using the attached test program: #include #include #include #include #include #include int main(int argc, char *argv[]) { size_t size = getpagesize(); unsigned char *p; bool mod = (argc == 3); int fd; if (argc != 2 && argc != 3) { fprintf(stderr, "Format: %s [mod]\n", argv[0]); exit(2); } fd = open(argv[1], mod ? O_RDWR : O_RDONLY); if (fd < 0) { perror(argv[1]); exit(1); } p = mmap(NULL, size, mod ? PROT_READ|PROT_WRITE : PROT_READ, MAP_SHARED, fd, 0); if (p == MAP_FAILED) { perror("mmap"); exit(1); } for (;;) { if (mod) { p[0]++; msync(p, size, MS_ASYNC); fsync(fd); } printf("%02x", p[0]); fflush(stdout); sleep(1); } } It runs in two modes: in one mode, it mmaps a file, then sits in a loop reading the first byte, printing it and sleeping for a second; in the second mode it mmaps a file, then sits in a loop incrementing the first byte and flushing, then printing and sleeping. Two instances of this program can be run on different machines, one doing the reading and one doing the writing. The reader should see the changes made by the writer, but without this patch, they aren't because validity checking is being done lazily - only on entry to the filesystem. Testing the InitCallBackState change is more complicated. The server has to be taken offline, the saved callback state file removed and then the server restarted whilst the reading-mode program continues to run. The client machine then has to poke the server to trigger the InitCallBackState call. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111668833.283156.382633263709075739.stgit@warthog.procyon.org.uk/ --- fs/afs/callback.c | 42 +++++++++++++++++++++++++++-- fs/afs/cell.c | 2 ++ fs/afs/file.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++- fs/afs/internal.h | 8 ++++++ fs/afs/server.c | 2 ++ fs/afs/super.c | 1 + mm/memory.c | 1 + 7 files changed, 120 insertions(+), 3 deletions(-) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 7d9b23d981bf..1dd7543dbf9f 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -20,6 +20,37 @@ #include #include "internal.h" +/* + * Handle invalidation of an mmap'd file. We invalidate all the PTEs referring + * to the pages in this file's pagecache, forcing the kernel to go through + * ->fault() or ->page_mkwrite() - at which point we can handle invalidation + * more fully. + */ +void afs_invalidate_mmap_work(struct work_struct *work) +{ + struct afs_vnode *vnode = container_of(work, struct afs_vnode, cb_work); + + unmap_mapping_pages(vnode->vfs_inode.i_mapping, 0, 0, false); +} + +void afs_server_init_callback_work(struct work_struct *work) +{ + struct afs_server *server = container_of(work, struct afs_server, initcb_work); + struct afs_vnode *vnode; + struct afs_cell *cell = server->cell; + + down_read(&cell->fs_open_mmaps_lock); + + list_for_each_entry(vnode, &cell->fs_open_mmaps, cb_mmap_link) { + if (vnode->cb_server == server) { + clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + queue_work(system_unbound_wq, &vnode->cb_work); + } + } + + up_read(&cell->fs_open_mmaps_lock); +} + /* * Allow the fileserver to request callback state (re-)initialisation. * Unfortunately, UUIDs are not guaranteed unique. @@ -29,8 +60,10 @@ void afs_init_callback_state(struct afs_server *server) rcu_read_lock(); do { server->cb_s_break++; - server = rcu_dereference(server->uuid_next); - } while (0); + if (!list_empty(&server->cell->fs_open_mmaps)) + queue_work(system_unbound_wq, &server->initcb_work); + + } while ((server = rcu_dereference(server->uuid_next))); rcu_read_unlock(); } @@ -49,6 +82,11 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) afs_lock_may_be_available(vnode); + if (reason != afs_cb_break_for_deleted && + vnode->status.type == AFS_FTYPE_FILE && + atomic_read(&vnode->cb_nr_mmap)) + queue_work(system_unbound_wq, &vnode->cb_work); + trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true); } else { trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, false); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 887b673f6223..d88407fb9bc0 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -166,6 +166,8 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, seqlock_init(&cell->volume_lock); cell->fs_servers = RB_ROOT; seqlock_init(&cell->fs_lock); + INIT_LIST_HEAD(&cell->fs_open_mmaps); + init_rwsem(&cell->fs_open_mmaps_lock); rwlock_init(&cell->vl_servers_lock); cell->flags = (1 << AFS_CELL_FL_CHECK_ALIAS); diff --git a/fs/afs/file.c b/fs/afs/file.c index 4c8d786b53e0..e6c447ae91f3 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -25,6 +25,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags); static void afs_readahead(struct readahead_control *ractl); static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); +static void afs_vm_open(struct vm_area_struct *area); +static void afs_vm_close(struct vm_area_struct *area); +static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); const struct file_operations afs_file_operations = { .open = afs_open, @@ -60,8 +63,10 @@ const struct address_space_operations afs_fs_aops = { }; static const struct vm_operations_struct afs_vm_ops = { + .open = afs_vm_open, + .close = afs_vm_close, .fault = filemap_fault, - .map_pages = filemap_map_pages, + .map_pages = afs_vm_map_pages, .page_mkwrite = afs_page_mkwrite, }; @@ -492,19 +497,79 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags) return 1; } +static void afs_add_open_mmap(struct afs_vnode *vnode) +{ + if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) { + down_write(&vnode->volume->cell->fs_open_mmaps_lock); + + list_add_tail(&vnode->cb_mmap_link, + &vnode->volume->cell->fs_open_mmaps); + + up_write(&vnode->volume->cell->fs_open_mmaps_lock); + } +} + +static void afs_drop_open_mmap(struct afs_vnode *vnode) +{ + if (!atomic_dec_and_test(&vnode->cb_nr_mmap)) + return; + + down_write(&vnode->volume->cell->fs_open_mmaps_lock); + + if (atomic_read(&vnode->cb_nr_mmap) == 0) + list_del_init(&vnode->cb_mmap_link); + + up_write(&vnode->volume->cell->fs_open_mmaps_lock); + flush_work(&vnode->cb_work); +} + /* * Handle setting up a memory mapping on an AFS file. */ static int afs_file_mmap(struct file *file, struct vm_area_struct *vma) { + struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); int ret; + afs_add_open_mmap(vnode); + ret = generic_file_mmap(file, vma); if (ret == 0) vma->vm_ops = &afs_vm_ops; + else + afs_drop_open_mmap(vnode); return ret; } +static void afs_vm_open(struct vm_area_struct *vma) +{ + afs_add_open_mmap(AFS_FS_I(file_inode(vma->vm_file))); +} + +static void afs_vm_close(struct vm_area_struct *vma) +{ + afs_drop_open_mmap(AFS_FS_I(file_inode(vma->vm_file))); +} + +static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) +{ + struct afs_vnode *vnode = AFS_FS_I(file_inode(vmf->vma->vm_file)); + struct afs_file *af = vmf->vma->vm_file->private_data; + + switch (afs_validate(vnode, af->key)) { + case 0: + return filemap_map_pages(vmf, start_pgoff, end_pgoff); + case -ENOMEM: + return VM_FAULT_OOM; + case -EINTR: + case -ERESTARTSYS: + return VM_FAULT_RETRY; + case -ESTALE: + default: + return VM_FAULT_SIGBUS; + } +} + static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5ed416f4ff33..0deeb76c67d0 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -390,6 +390,8 @@ struct afs_cell { /* Active fileserver interaction state. */ struct rb_root fs_servers; /* afs_server (by server UUID) */ seqlock_t fs_lock; /* For fs_servers */ + struct rw_semaphore fs_open_mmaps_lock; + struct list_head fs_open_mmaps; /* List of vnodes that are mmapped */ /* VL server list. */ rwlock_t vl_servers_lock; /* Lock on vl_servers */ @@ -503,6 +505,7 @@ struct afs_server { struct hlist_node addr4_link; /* Link in net->fs_addresses4 */ struct hlist_node addr6_link; /* Link in net->fs_addresses6 */ struct hlist_node proc_link; /* Link in net->fs_proc */ + struct work_struct initcb_work; /* Work for CB.InitCallBackState* */ struct afs_server *gc_next; /* Next server in manager's list */ time64_t unuse_time; /* Time at which last unused */ unsigned long flags; @@ -657,7 +660,10 @@ struct afs_vnode { afs_lock_type_t lock_type : 8; /* outstanding callback notification on this file */ + struct work_struct cb_work; /* Work for mmap'd files */ + struct list_head cb_mmap_link; /* Link in cell->fs_open_mmaps */ void *cb_server; /* Server with callback/filelock */ + atomic_t cb_nr_mmap; /* Number of mmaps */ unsigned int cb_s_break; /* Mass break counter on ->server */ unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ @@ -965,6 +971,8 @@ extern struct fscache_cookie_def afs_vnode_cache_index_def; /* * callback.c */ +extern void afs_invalidate_mmap_work(struct work_struct *); +extern void afs_server_init_callback_work(struct work_struct *work); extern void afs_init_callback_state(struct afs_server *); extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); diff --git a/fs/afs/server.c b/fs/afs/server.c index 684a2b02b9ff..6e5b9a19b234 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -235,6 +235,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell, server->addr_version = alist->version; server->uuid = *uuid; rwlock_init(&server->fs_lock); + INIT_WORK(&server->initcb_work, afs_server_init_callback_work); init_waitqueue_head(&server->probe_wq); INIT_LIST_HEAD(&server->probe_link); spin_lock_init(&server->probe_lock); @@ -467,6 +468,7 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) afs_give_up_callbacks(net, server); + flush_work(&server->initcb_work); afs_put_server(net, server, afs_server_trace_destroy); } diff --git a/fs/afs/super.c b/fs/afs/super.c index e38bb1e7a4d2..d110def8aa8e 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -698,6 +698,7 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->lock_state = AFS_VNODE_LOCK_NONE; init_rwsem(&vnode->rmdir_lock); + INIT_WORK(&vnode->cb_work, afs_invalidate_mmap_work); _leave(" = %p", &vnode->vfs_inode); return &vnode->vfs_inode; diff --git a/mm/memory.c b/mm/memory.c index 25fc46e87214..adf9b9ef8277 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3403,6 +3403,7 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } +EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** * unmap_mapping_range - unmap the portion of all mmaps in the specified From 4fe6a946823a9bc8619fd16b7ea7d15914a30f22 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Sep 2021 21:51:01 +0100 Subject: [PATCH 080/866] afs: Try to avoid taking RCU read lock when checking vnode validity Try to avoid taking the RCU read lock when checking the validity of a vnode's callback state. The only thing it's needed for is to pin the parent volume's server list whilst we search it to find the record of the server we're currently using to see if it has been reinitialised (ie. it sent us a CB.InitCallBackState* RPC). Do this by the following means: (1) Keep an additional per-cell counter (fs_s_break) that's incremented each time any of the fileservers in the cell reinitialises. Since the new counter can be accessed without RCU from the vnode, we can check that first - and only if it differs, get the RCU read lock and check the volume's server list. (2) Replace afs_get_s_break_rcu() with afs_check_server_good() which now indicates whether the callback promise is still expected to be present on the server. This does the checks as described in (1). (3) Restructure afs_check_validity() to take account of the change in (2). We can also get rid of the valid variable and just use the need_clear variable with the addition of the afs_cb_break_no_promise reason. (4) afs_check_validity() probably shouldn't be altering vnode->cb_v_break and vnode->cb_s_break when it doesn't have cb_lock exclusively locked. Move the change to vnode->cb_v_break to __afs_break_callback(). Delegate the change to vnode->cb_s_break to afs_select_fileserver() and set vnode->cb_fs_s_break there also. (5) afs_validate() no longer needs to get the RCU read lock around its call to afs_check_validity() - and can skip the call entirely if we don't have a promise. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111669583.283156.1397603105683094563.stgit@warthog.procyon.org.uk/ --- fs/afs/callback.c | 2 + fs/afs/inode.c | 88 +++++++++++++++++++------------------- fs/afs/internal.h | 2 + fs/afs/rotate.c | 1 + include/trace/events/afs.h | 8 +++- 5 files changed, 54 insertions(+), 47 deletions(-) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1dd7543dbf9f..1b4d5809808d 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -60,6 +60,7 @@ void afs_init_callback_state(struct afs_server *server) rcu_read_lock(); do { server->cb_s_break++; + atomic_inc(&server->cell->fs_s_break); if (!list_empty(&server->cell->fs_open_mmaps)) queue_work(system_unbound_wq, &server->initcb_work); @@ -77,6 +78,7 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { vnode->cb_break++; + vnode->cb_v_break = vnode->volume->cb_v_break; afs_clear_permits(vnode); if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 80b6c8d967d5..126daf9969db 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -587,22 +587,32 @@ static void afs_zap_data(struct afs_vnode *vnode) } /* - * Get the server reinit counter for a vnode's current server. + * Check to see if we have a server currently serving this volume and that it + * hasn't been reinitialised or dropped from the list. */ -static bool afs_get_s_break_rcu(struct afs_vnode *vnode, unsigned int *_s_break) +static bool afs_check_server_good(struct afs_vnode *vnode) { - struct afs_server_list *slist = rcu_dereference(vnode->volume->servers); + struct afs_server_list *slist; struct afs_server *server; + bool good; int i; + if (vnode->cb_fs_s_break == atomic_read(&vnode->volume->cell->fs_s_break)) + return true; + + rcu_read_lock(); + + slist = rcu_dereference(vnode->volume->servers); for (i = 0; i < slist->nr_servers; i++) { server = slist->servers[i].server; if (server == vnode->cb_server) { - *_s_break = READ_ONCE(server->cb_s_break); - return true; + good = (vnode->cb_s_break == server->cb_s_break); + rcu_read_unlock(); + return good; } } + rcu_read_unlock(); return false; } @@ -611,57 +621,46 @@ static bool afs_get_s_break_rcu(struct afs_vnode *vnode, unsigned int *_s_break) */ bool afs_check_validity(struct afs_vnode *vnode) { - struct afs_volume *volume = vnode->volume; enum afs_cb_break_reason need_clear = afs_cb_break_no_break; time64_t now = ktime_get_real_seconds(); - bool valid; - unsigned int cb_break, cb_s_break, cb_v_break; + unsigned int cb_break; int seq = 0; do { read_seqbegin_or_lock(&vnode->cb_lock, &seq); - cb_v_break = READ_ONCE(volume->cb_v_break); cb_break = vnode->cb_break; - if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) && - afs_get_s_break_rcu(vnode, &cb_s_break)) { - if (vnode->cb_s_break != cb_s_break || - vnode->cb_v_break != cb_v_break) { - vnode->cb_s_break = cb_s_break; - vnode->cb_v_break = cb_v_break; - need_clear = afs_cb_break_for_vsbreak; - valid = false; - } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + if (vnode->cb_v_break != vnode->volume->cb_v_break) + need_clear = afs_cb_break_for_v_break; + else if (!afs_check_server_good(vnode)) + need_clear = afs_cb_break_for_s_reinit; + else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) need_clear = afs_cb_break_for_zap; - valid = false; - } else if (vnode->cb_expires_at - 10 <= now) { + else if (vnode->cb_expires_at - 10 <= now) need_clear = afs_cb_break_for_lapsed; - valid = false; - } else { - valid = true; - } } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - valid = true; + ; } else { - vnode->cb_v_break = cb_v_break; - valid = false; + need_clear = afs_cb_break_no_promise; } } while (need_seqretry(&vnode->cb_lock, seq)); done_seqretry(&vnode->cb_lock, seq); - if (need_clear != afs_cb_break_no_break) { - write_seqlock(&vnode->cb_lock); - if (cb_break == vnode->cb_break) - __afs_break_callback(vnode, need_clear); - else - trace_afs_cb_miss(&vnode->fid, need_clear); - write_sequnlock(&vnode->cb_lock); - valid = false; - } + if (need_clear == afs_cb_break_no_break) + return true; - return valid; + write_seqlock(&vnode->cb_lock); + if (need_clear == afs_cb_break_no_promise) + vnode->cb_v_break = vnode->volume->cb_v_break; + else if (cb_break == vnode->cb_break) + __afs_break_callback(vnode, need_clear); + else + trace_afs_cb_miss(&vnode->fid, need_clear); + write_sequnlock(&vnode->cb_lock); + return false; } /* @@ -675,21 +674,20 @@ bool afs_check_validity(struct afs_vnode *vnode) */ int afs_validate(struct afs_vnode *vnode, struct key *key) { - bool valid; int ret; _enter("{v={%llx:%llu} fl=%lx},%x", vnode->fid.vid, vnode->fid.vnode, vnode->flags, key_serial(key)); - rcu_read_lock(); - valid = afs_check_validity(vnode); - rcu_read_unlock(); + if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) { + if (vnode->vfs_inode.i_nlink) + clear_nlink(&vnode->vfs_inode); + goto valid; + } - if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) - clear_nlink(&vnode->vfs_inode); - - if (valid) + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) && + afs_check_validity(vnode)) goto valid; down_write(&vnode->validate_lock); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 0deeb76c67d0..c97618855b46 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -392,6 +392,7 @@ struct afs_cell { seqlock_t fs_lock; /* For fs_servers */ struct rw_semaphore fs_open_mmaps_lock; struct list_head fs_open_mmaps; /* List of vnodes that are mmapped */ + atomic_t fs_s_break; /* Counter of CB.InitCallBackState messages */ /* VL server list. */ rwlock_t vl_servers_lock; /* Lock on vl_servers */ @@ -664,6 +665,7 @@ struct afs_vnode { struct list_head cb_mmap_link; /* Link in cell->fs_open_mmaps */ void *cb_server; /* Server with callback/filelock */ atomic_t cb_nr_mmap; /* Number of mmaps */ + unsigned int cb_fs_s_break; /* Mass server break counter (cell->fs_s_break) */ unsigned int cb_s_break; /* Mass break counter on ->server */ unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index d83f13c44b92..79e1a5f6701b 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -374,6 +374,7 @@ selected_server: if (vnode->cb_server != server) { vnode->cb_server = server; vnode->cb_s_break = server->cb_s_break; + vnode->cb_fs_s_break = atomic_read(&server->cell->fs_s_break); vnode->cb_v_break = vnode->volume->cb_v_break; clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); } diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 9f73ed2cf061..bca73e8c8cde 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -306,11 +306,13 @@ enum afs_flock_operation { enum afs_cb_break_reason { afs_cb_break_no_break, + afs_cb_break_no_promise, afs_cb_break_for_callback, afs_cb_break_for_deleted, afs_cb_break_for_lapsed, + afs_cb_break_for_s_reinit, afs_cb_break_for_unlink, - afs_cb_break_for_vsbreak, + afs_cb_break_for_v_break, afs_cb_break_for_volume_callback, afs_cb_break_for_zap, }; @@ -602,11 +604,13 @@ enum afs_cb_break_reason { #define afs_cb_break_reasons \ EM(afs_cb_break_no_break, "no-break") \ + EM(afs_cb_break_no_promise, "no-promise") \ EM(afs_cb_break_for_callback, "break-cb") \ EM(afs_cb_break_for_deleted, "break-del") \ EM(afs_cb_break_for_lapsed, "break-lapsed") \ + EM(afs_cb_break_for_s_reinit, "s-reinit") \ EM(afs_cb_break_for_unlink, "break-unlink") \ - EM(afs_cb_break_for_vsbreak, "break-vs") \ + EM(afs_cb_break_for_v_break, "break-v") \ EM(afs_cb_break_for_volume_callback, "break-v-cb") \ E_(afs_cb_break_for_zap, "break-zap") From b537a3c21775075395af475dcc6ef212fcf29db8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 10 Sep 2021 00:01:52 +0100 Subject: [PATCH 081/866] afs: Fix corruption in reads at fpos 2G-4G from an OpenAFS server AFS-3 has two data fetch RPC variants, FS.FetchData and FS.FetchData64, and Linux's afs client switches between them when talking to a non-YFS server if the read size, the file position or the sum of the two have the upper 32 bits set of the 64-bit value. This is a problem, however, since the file position and length fields of FS.FetchData are *signed* 32-bit values. Fix this by capturing the capability bits obtained from the fileserver when it's sent an FS.GetCapabilities RPC, rather than just discarding them, and then picking out the VICED_CAPABILITY_64BITFILES flag. This can then be used to decide whether to use FS.FetchData or FS.FetchData64 - and also FS.StoreData or FS.StoreData64 - rather than using upper_32_bits() to switch on the parameter values. This capabilities flag could also be used to limit the maximum size of the file, but all servers must be checked for that. Note that the issue does not exist with FS.StoreData - that uses *unsigned* 32-bit values. It's also not a problem with Auristor servers as its YFS.FetchData64 op uses unsigned 64-bit values. This can be tested by cloning a git repo through an OpenAFS client to an OpenAFS server and then doing "git status" on it from a Linux afs client[1]. Provided the clone has a pack file that's in the 2G-4G range, the git status will show errors like: error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index error: packfile .git/objects/pack/pack-5e813c51d12b6847bbc0fcd97c2bca66da50079c.pack does not match index This can be observed in the server's FileLog with something like the following appearing: Sun Aug 29 19:31:39 2021 SRXAFS_FetchData, Fid = 2303380852.491776.3263114, Host 192.168.11.201:7001, Id 1001 Sun Aug 29 19:31:39 2021 CheckRights: len=0, for host=192.168.11.201:7001 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: Pos 18446744071815340032, Len 3154 Sun Aug 29 19:31:39 2021 FetchData_RXStyle: file size 2400758866 ... Sun Aug 29 19:31:40 2021 SRXAFS_FetchData returns 5 Note the file position of 18446744071815340032. This is the requested file position sign-extended. Fixes: b9b1f8d5930a ("AFS: write support fixes") Reported-by: Markus Suvanto Signed-off-by: David Howells Reviewed-by: Marc Dionne Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org cc: openafs-devel@openafs.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=214217#c9 [1] Link: https://lore.kernel.org/r/951332.1631308745@warthog.procyon.org.uk/ --- fs/afs/fs_probe.c | 8 +++++++- fs/afs/fsclient.c | 31 ++++++++++++++++++++----------- fs/afs/internal.h | 1 + fs/afs/protocol_afs.h | 15 +++++++++++++++ fs/afs/protocol_yfs.h | 6 ++++++ 5 files changed, 49 insertions(+), 12 deletions(-) create mode 100644 fs/afs/protocol_afs.h diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index e7e98ad63a91..c0031a3ab42f 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -9,6 +9,7 @@ #include #include "afs_fs.h" #include "internal.h" +#include "protocol_afs.h" #include "protocol_yfs.h" static unsigned int afs_fs_probe_fast_poll_interval = 30 * HZ; @@ -102,7 +103,7 @@ void afs_fileserver_probe_result(struct afs_call *call) struct afs_addr_list *alist = call->alist; struct afs_server *server = call->server; unsigned int index = call->addr_ix; - unsigned int rtt_us = 0; + unsigned int rtt_us = 0, cap0; int ret = call->error; _enter("%pU,%u", &server->uuid, index); @@ -159,6 +160,11 @@ responded: clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } + cap0 = ntohl(call->tmp); + if (cap0 & AFS3_VICED_CAPABILITY_64BITFILES) + set_bit(AFS_SERVER_FL_HAS_FS64, &server->flags); + else + clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags); } if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index dd3f45d906d2..4943413d9c5f 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -456,9 +456,7 @@ void afs_fs_fetch_data(struct afs_operation *op) struct afs_read *req = op->fetch.req; __be32 *bp; - if (upper_32_bits(req->pos) || - upper_32_bits(req->len) || - upper_32_bits(req->pos + req->len)) + if (test_bit(AFS_SERVER_FL_HAS_FS64, &op->server->flags)) return afs_fs_fetch_data64(op); _enter(""); @@ -1113,9 +1111,7 @@ void afs_fs_store_data(struct afs_operation *op) (unsigned long long)op->store.pos, (unsigned long long)op->store.i_size); - if (upper_32_bits(op->store.pos) || - upper_32_bits(op->store.size) || - upper_32_bits(op->store.i_size)) + if (test_bit(AFS_SERVER_FL_HAS_FS64, &op->server->flags)) return afs_fs_store_data64(op); call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData, @@ -1229,7 +1225,7 @@ static void afs_fs_setattr_size(struct afs_operation *op) key_serial(op->key), vp->fid.vid, vp->fid.vnode); ASSERT(attr->ia_valid & ATTR_SIZE); - if (upper_32_bits(attr->ia_size)) + if (test_bit(AFS_SERVER_FL_HAS_FS64, &op->server->flags)) return afs_fs_setattr_size64(op); call = afs_alloc_flat_call(op->net, &afs_RXFSStoreData_as_Status, @@ -1657,20 +1653,33 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) return ret; count = ntohl(call->tmp); - call->count = count; call->count2 = count; - afs_extract_discard(call, count * sizeof(__be32)); + if (count == 0) { + call->unmarshall = 4; + call->tmp = 0; + break; + } + + /* Extract the first word of the capabilities to call->tmp */ + afs_extract_to_tmp(call); call->unmarshall++; fallthrough; - /* Extract capabilities words */ case 2: ret = afs_extract_data(call, false); if (ret < 0) return ret; - /* TODO: Examine capabilities */ + afs_extract_discard(call, (count - 1) * sizeof(__be32)); + call->unmarshall++; + fallthrough; + + /* Extract remaining capabilities words */ + case 3: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; call->unmarshall++; break; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index c97618855b46..b0fe27ae60db 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -520,6 +520,7 @@ struct afs_server { #define AFS_SERVER_FL_IS_YFS 16 /* Server is YFS not AFS */ #define AFS_SERVER_FL_NO_IBULK 17 /* Fileserver doesn't support FS.InlineBulkStatus */ #define AFS_SERVER_FL_NO_RM2 18 /* Fileserver doesn't support YFS.RemoveFile2 */ +#define AFS_SERVER_FL_HAS_FS64 19 /* Fileserver supports FS.{Fetch,Store}Data64 */ atomic_t ref; /* Object refcount */ atomic_t active; /* Active user count */ u32 addr_version; /* Address list version */ diff --git a/fs/afs/protocol_afs.h b/fs/afs/protocol_afs.h new file mode 100644 index 000000000000..0c39358c8b70 --- /dev/null +++ b/fs/afs/protocol_afs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* AFS protocol bits + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + + +#define AFSCAPABILITIESMAX 196 /* Maximum number of words in a capability set */ + +/* AFS3 Fileserver capabilities word 0 */ +#define AFS3_VICED_CAPABILITY_ERRORTRANS 0x0001 /* Uses UAE errors */ +#define AFS3_VICED_CAPABILITY_64BITFILES 0x0002 /* FetchData64 & StoreData64 supported */ +#define AFS3_VICED_CAPABILITY_WRITELOCKACL 0x0004 /* Can lock a file even without lock perm */ +#define AFS3_VICED_CAPABILITY_SANEACLS 0x0008 /* ACLs reviewed for sanity - don't use */ diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index b5bd03b1d3c7..e4cd89c44c46 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -168,3 +168,9 @@ enum yfs_lock_type { yfs_LockMandatoryWrite = 0x101, yfs_LockMandatoryExtend = 0x102, }; + +/* RXYFS Viced Capability Flags */ +#define YFS_VICED_CAPABILITY_ERRORTRANS 0x0001 /* Deprecated v0.195 */ +#define YFS_VICED_CAPABILITY_64BITFILES 0x0002 /* Deprecated v0.195 */ +#define YFS_VICED_CAPABILITY_WRITELOCKACL 0x0004 /* Can lock a file even without lock perm */ +#define YFS_VICED_CAPABILITY_SANEACLS 0x0008 /* Deprecated v0.195 */ From 9d37e1cab2a9d2cee2737973fa455e6f89eee46a Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 8 Sep 2021 21:55:19 +0100 Subject: [PATCH 082/866] afs: Fix updating of i_blocks on file/dir extension When an afs file or directory is modified locally such that the total file size is extended, i_blocks needs to be recalculated too. Fix this by making afs_write_end() and afs_edit_dir_add() call afs_set_i_size() rather than setting inode->i_size directly as that also recalculates inode->i_blocks. This can be tested by creating and writing into directories and files and then examining them with du. Without this change, directories show a 4 blocks (they start out at 2048 bytes) and files show 0 blocks; with this change, they should show a number of blocks proportional to the file size rounded up to 1024. Fixes: 31143d5d515e ("AFS: implement basic file write support") Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Reported-by: Markus Suvanto Signed-off-by: David Howells Reviewed-by: Marc Dionne Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163113612442.352844.11162345591911691150.stgit@warthog.procyon.org.uk/ --- fs/afs/dir_edit.c | 4 ++-- fs/afs/inode.c | 10 ---------- fs/afs/internal.h | 10 ++++++++++ fs/afs/write.c | 2 +- 4 files changed, 13 insertions(+), 13 deletions(-) diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index f4600c1353ad..540b9fc96824 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -263,7 +263,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, if (b == nr_blocks) { _debug("init %u", b); afs_edit_init_block(meta, block, b); - i_size_write(&vnode->vfs_inode, (b + 1) * AFS_DIR_BLOCK_SIZE); + afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE); } /* Only lower dir pages have a counter in the header. */ @@ -296,7 +296,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode, new_directory: afs_edit_init_block(meta, meta, 0); i_size = AFS_DIR_BLOCK_SIZE; - i_size_write(&vnode->vfs_inode, i_size); + afs_set_i_size(vnode, i_size); slot = AFS_DIR_RESV_BLOCKS0; page = page0; block = meta; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 126daf9969db..8fcffea2daf5 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -53,16 +53,6 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren dump_stack(); } -/* - * Set the file size and block count. Estimate the number of 512 bytes blocks - * used, rounded up to nearest 1K for consistency with other AFS clients. - */ -static void afs_set_i_size(struct afs_vnode *vnode, u64 size) -{ - i_size_write(&vnode->vfs_inode, size); - vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1; -} - /* * Initialise an inode from the vnode status. */ diff --git a/fs/afs/internal.h b/fs/afs/internal.h index b0fe27ae60db..0ad97a8fc0d4 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1596,6 +1596,16 @@ static inline void afs_update_dentry_version(struct afs_operation *op, (void *)(unsigned long)dir_vp->scb.status.data_version; } +/* + * Set the file size and block count. Estimate the number of 512 bytes blocks + * used, rounded up to nearest 1K for consistency with other AFS clients. + */ +static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size) +{ + i_size_write(&vnode->vfs_inode, size); + vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1; +} + /* * Check for a conflicting operation on a directory that we just unlinked from. * If someone managed to sneak a link or an unlink in on the file we just diff --git a/fs/afs/write.c b/fs/afs/write.c index 32a764c24284..2dfe3b3a53d6 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -137,7 +137,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_seqlock(&vnode->cb_lock); i_size = i_size_read(&vnode->vfs_inode); if (maybe_i_size > i_size) - i_size_write(&vnode->vfs_inode, maybe_i_size); + afs_set_i_size(vnode, maybe_i_size); write_sequnlock(&vnode->cb_lock); } From 7bb057134d609b9c038a00b6876cf0d37d0118ce Mon Sep 17 00:00:00 2001 From: Carlo Lobrano Date: Fri, 3 Sep 2021 14:39:13 +0200 Subject: [PATCH 083/866] USB: serial: option: add Telit LN920 compositions This patch adds the following Telit LN920 compositions: 0x1060: tty, adb, rmnet, tty, tty, tty, tty 0x1061: tty, adb, mbim, tty, tty, tty, tty 0x1062: rndis, tty, adb, tty, tty, tty, tty 0x1063: tty, adb, ecm, tty, tty, tty, tty Signed-off-by: Carlo Lobrano Link: https://lore.kernel.org/r/20210903123913.1086513-1-c.lobrano@gmail.com Reviewed-by: Daniele Palmas Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 29c765cc8495..a79f51e35115 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1205,6 +1205,14 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */ .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1060, 0xff), /* Telit LN920 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1061, 0xff), /* Telit LN920 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1062, 0xff), /* Telit LN920 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), From 349bff48ae0f5f8aa2075d0bdc2091a30bd634f6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 27 Aug 2021 17:53:10 +0300 Subject: [PATCH 084/866] platform/x86/intel: punit_ipc: Drop wrong use of ACPI_PTR() ACPI_PTR() is more harmful than helpful. For example, in this case if CONFIG_ACPI=n, the ID table left unused which is not what we want. Instead of adding ifdeffery here and there, drop ACPI_PTR() and unused acpi.h. Fixes: fdca4f16f57d ("platform:x86: add Intel P-Unit mailbox IPC driver") Reported-by: kernel test robot Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210827145310.76239-1-andriy.shevchenko@linux.intel.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/intel/punit_ipc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/platform/x86/intel/punit_ipc.c b/drivers/platform/x86/intel/punit_ipc.c index f58b8543f6ac..66bb39fd0ef9 100644 --- a/drivers/platform/x86/intel/punit_ipc.c +++ b/drivers/platform/x86/intel/punit_ipc.c @@ -8,7 +8,6 @@ * which provide mailbox interface for power management usage. */ -#include #include #include #include @@ -319,7 +318,7 @@ static struct platform_driver intel_punit_ipc_driver = { .remove = intel_punit_ipc_remove, .driver = { .name = "intel_punit_ipc", - .acpi_match_table = ACPI_PTR(punit_ipc_acpi_ids), + .acpi_match_table = punit_ipc_acpi_ids, }, }; From 4c4a3d7cffb42da21ea8891fc7e6808ae05dbcb5 Mon Sep 17 00:00:00 2001 From: Matan Ziv-Av Date: Sun, 29 Aug 2021 15:07:08 +0300 Subject: [PATCH 085/866] lg-laptop: Correctly handle dmi_get_system_info() returning NULL The laptop model is identified by parsing the product name. If no product name is available, do not try to parse it. Default model is 2017. Signed-off-by: Matan Ziv-Av Link: https://lore.kernel.org/r/93ff3bb-503b-f73-bf18-87bae1699ed@svgalib.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/lg-laptop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c index 3e520d5bca07..88b551caeaaf 100644 --- a/drivers/platform/x86/lg-laptop.c +++ b/drivers/platform/x86/lg-laptop.c @@ -655,7 +655,7 @@ static int acpi_add(struct acpi_device *device) goto out_platform_registered; } product = dmi_get_system_info(DMI_PRODUCT_NAME); - if (strlen(product) > 4) + if (product && strlen(product) > 4) switch (product[4]) { case '5': case '6': From 3bf1669b0e033c885ebcb1ddc2334088dd125f2d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 5 Sep 2021 15:02:09 +0200 Subject: [PATCH 086/866] platform/x86: touchscreen_dmi: Add info for the Chuwi HiBook (CWI514) tablet Add touchscreen info for the Chuwi HiBook (CWI514) tablet. This includes info for getting the firmware directly from the UEFI, so that the user does not need to manually install the firmware in /lib/firmware/silead. This change will make the touchscreen on these devices work OOTB, without requiring any manual setup. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210905130210.32810-1-hdegoede@redhat.com --- drivers/platform/x86/touchscreen_dmi.c | 37 ++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 0e1451b1d9c6..1f9cb756b103 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -141,6 +141,33 @@ static const struct ts_dmi_data chuwi_hi10_pro_data = { .properties = chuwi_hi10_pro_props, }; +static const struct property_entry chuwi_hibook_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 30), + PROPERTY_ENTRY_U32("touchscreen-min-y", 4), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1892), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1276), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hibook.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data chuwi_hibook_data = { + .embedded_fw = { + .name = "silead/gsl1680-chuwi-hibook.fw", + .prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 }, + .length = 40392, + .sha256 = { 0xf7, 0xc0, 0xe8, 0x5a, 0x6c, 0xf2, 0xeb, 0x8d, + 0x12, 0xc4, 0x45, 0xbf, 0x55, 0x13, 0x4c, 0x1a, + 0x13, 0x04, 0x31, 0x08, 0x65, 0x73, 0xf7, 0xa8, + 0x1b, 0x7d, 0x59, 0xc9, 0xe6, 0x97, 0xf7, 0x38 }, + }, + .acpi_name = "MSSL0017:00", + .properties = chuwi_hibook_props, +}; + static const struct property_entry chuwi_vi8_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 4), PROPERTY_ENTRY_U32("touchscreen-min-y", 6), @@ -979,6 +1006,16 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), }, }, + { + /* Chuwi HiBook (CWI514) */ + .driver_data = (void *)&chuwi_hibook_data, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), + DMI_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), + /* Above matches are too generic, add bios-date match */ + DMI_MATCH(DMI_BIOS_DATE, "05/07/2016"), + }, + }, { /* Chuwi Vi8 (CWI506) */ .driver_data = (void *)&chuwi_vi8_data, From 196159d278ae3b49e7bbb7c76822e6008fd89b97 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 5 Sep 2021 15:02:10 +0200 Subject: [PATCH 087/866] platform/x86: touchscreen_dmi: Update info for the Chuwi Hi10 Plus (CWI527) tablet Add info for getting the firmware directly from the UEFI for the Chuwi Hi10 Plus (CWI527), so that the user does not need to manually install the firmware in /lib/firmware/silead. This change will make the touchscreen on these devices work OOTB, without requiring any manual setup. Also tweak the min and width/height values a bit for more accurate position reporting. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20210905130210.32810-2-hdegoede@redhat.com --- drivers/platform/x86/touchscreen_dmi.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 1f9cb756b103..033f797861d8 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -100,10 +100,10 @@ static const struct ts_dmi_data chuwi_hi10_air_data = { }; static const struct property_entry chuwi_hi10_plus_props[] = { - PROPERTY_ENTRY_U32("touchscreen-min-x", 0), - PROPERTY_ENTRY_U32("touchscreen-min-y", 5), - PROPERTY_ENTRY_U32("touchscreen-size-x", 1914), - PROPERTY_ENTRY_U32("touchscreen-size-y", 1283), + PROPERTY_ENTRY_U32("touchscreen-min-x", 12), + PROPERTY_ENTRY_U32("touchscreen-min-y", 10), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1908), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1270), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hi10plus.fw"), PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), @@ -111,6 +111,15 @@ static const struct property_entry chuwi_hi10_plus_props[] = { }; static const struct ts_dmi_data chuwi_hi10_plus_data = { + .embedded_fw = { + .name = "silead/gsl1680-chuwi-hi10plus.fw", + .prefix = { 0xf0, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00 }, + .length = 34056, + .sha256 = { 0xfd, 0x0a, 0x08, 0x08, 0x3c, 0xa6, 0x34, 0x4e, + 0x2c, 0x49, 0x9c, 0xcd, 0x7d, 0x44, 0x9d, 0x38, + 0x10, 0x68, 0xb5, 0xbd, 0xb7, 0x2a, 0x63, 0xb5, + 0x67, 0x0b, 0x96, 0xbd, 0x89, 0x67, 0x85, 0x09 }, + }, .acpi_name = "MSSL0017:00", .properties = chuwi_hi10_plus_props, }; From b1a89856fbf63fffde6a4771d8f1ac21df549e50 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 6 Sep 2021 23:07:29 -0700 Subject: [PATCH 088/866] m68k: Double cast io functions to unsigned long m68k builds fail widely with errors such as arch/m68k/include/asm/raw_io.h:20:19: error: cast to pointer from integer of different size arch/m68k/include/asm/raw_io.h:30:32: error: cast to pointer from integer of different size [-Werror=int-to-p On m68k, io functions are defined as macros. The problem is seen if the macro parameter variable size differs from the size of a pointer. Cast the parameter of all io macros to unsigned long before casting it to a pointer to fix the problem. Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20210907060729.2391992-1-linux@roeck-us.net Signed-off-by: Geert Uytterhoeven --- arch/m68k/include/asm/raw_io.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/m68k/include/asm/raw_io.h b/arch/m68k/include/asm/raw_io.h index 911826ea83ce..80eb2396d01e 100644 --- a/arch/m68k/include/asm/raw_io.h +++ b/arch/m68k/include/asm/raw_io.h @@ -17,21 +17,21 @@ * two accesses to memory, which may be undesirable for some devices. */ #define in_8(addr) \ - ({ u8 __v = (*(__force volatile u8 *) (addr)); __v; }) + ({ u8 __v = (*(__force volatile u8 *) (unsigned long)(addr)); __v; }) #define in_be16(addr) \ - ({ u16 __v = (*(__force volatile u16 *) (addr)); __v; }) + ({ u16 __v = (*(__force volatile u16 *) (unsigned long)(addr)); __v; }) #define in_be32(addr) \ - ({ u32 __v = (*(__force volatile u32 *) (addr)); __v; }) + ({ u32 __v = (*(__force volatile u32 *) (unsigned long)(addr)); __v; }) #define in_le16(addr) \ - ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (addr)); __v; }) + ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (unsigned long)(addr)); __v; }) #define in_le32(addr) \ - ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (addr)); __v; }) + ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (unsigned long)(addr)); __v; }) -#define out_8(addr,b) (void)((*(__force volatile u8 *) (addr)) = (b)) -#define out_be16(addr,w) (void)((*(__force volatile u16 *) (addr)) = (w)) -#define out_be32(addr,l) (void)((*(__force volatile u32 *) (addr)) = (l)) -#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (addr)) = cpu_to_le16(w)) -#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (addr)) = cpu_to_le32(l)) +#define out_8(addr,b) (void)((*(__force volatile u8 *) (unsigned long)(addr)) = (b)) +#define out_be16(addr,w) (void)((*(__force volatile u16 *) (unsigned long)(addr)) = (w)) +#define out_be32(addr,l) (void)((*(__force volatile u32 *) (unsigned long)(addr)) = (l)) +#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (unsigned long)(addr)) = cpu_to_le16(w)) +#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (unsigned long)(addr)) = cpu_to_le32(l)) #define raw_inb in_8 #define raw_inw in_be16 From a7b68ed15d1fd72c1e451d5eb6edebee2a624b90 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 7 Sep 2021 14:45:11 +0200 Subject: [PATCH 089/866] m68k: mvme: Remove overdue #warnings in RTC handling The warnings were introduced when converting the MVME147 and MVME16x RTC handling from gettod to hwclk. Replace the #warning by a comment, and return an error to inform the upper layer that writing to the RTC is not yet supported. Signed-off-by: Geert Uytterhoeven Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20210907124511.2723414-1-geert@linux-m68k.org --- arch/m68k/mvme147/config.c | 4 +++- arch/m68k/mvme16x/config.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c index e1e90c49a496..dfd6202fd403 100644 --- a/arch/m68k/mvme147/config.c +++ b/arch/m68k/mvme147/config.c @@ -171,7 +171,6 @@ static int bcd2int (unsigned char b) int mvme147_hwclk(int op, struct rtc_time *t) { -#warning check me! if (!op) { m147_rtc->ctrl = RTC_READ; t->tm_year = bcd2int (m147_rtc->bcd_year); @@ -183,6 +182,9 @@ int mvme147_hwclk(int op, struct rtc_time *t) m147_rtc->ctrl = 0; if (t->tm_year < 70) t->tm_year += 100; + } else { + /* FIXME Setting the time is not yet supported */ + return -EOPNOTSUPP; } return 0; } diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c index b59593c7cfb9..b4422c2dfbbf 100644 --- a/arch/m68k/mvme16x/config.c +++ b/arch/m68k/mvme16x/config.c @@ -436,7 +436,6 @@ int bcd2int (unsigned char b) int mvme16x_hwclk(int op, struct rtc_time *t) { -#warning check me! if (!op) { rtc->ctrl = RTC_READ; t->tm_year = bcd2int (rtc->bcd_year); @@ -448,6 +447,9 @@ int mvme16x_hwclk(int op, struct rtc_time *t) rtc->ctrl = 0; if (t->tm_year < 70) t->tm_year += 100; + } else { + /* FIXME Setting the time is not yet supported */ + return -EOPNOTSUPP; } return 0; } From eca4cf12acda306f851f6d2a05b1c9ef62cf0e81 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 12 Sep 2021 12:34:47 -0400 Subject: [PATCH 090/866] bnxt_en: Fix error recovery regression The recent patch has introduced a regression by not reading the reset count in the ERROR_RECOVERY async event handler. We may have just gone through a reset and the reset count has just incremented. If we don't update the reset count in the ERROR_RECOVERY event handler, the health check timer will see that the reset count has changed and will initiate an unintended reset. Restore the unconditional update of the reset count in bnxt_async_event_process() if error recovery watchdog is enabled. Also, update the reset count at the end of the reset sequence to make it even more robust. Fixes: 1b2b91831983 ("bnxt_en: Fix possible unintended driver initiated error recovery") Reviewed-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9b86516e59a1..8b0a2ae1367c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2213,12 +2213,11 @@ static int bnxt_async_event_process(struct bnxt *bp, DIV_ROUND_UP(fw_health->polling_dsecs * HZ, bp->current_interval * 10); fw_health->tmr_counter = fw_health->tmr_multiplier; - if (!fw_health->enabled) { + if (!fw_health->enabled) fw_health->last_fw_heartbeat = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); - fw_health->last_fw_reset_cnt = - bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - } + fw_health->last_fw_reset_cnt = + bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); netif_info(bp, drv, bp->dev, "Error recovery info: error recovery[1], master[%d], reset count[%u], health status: 0x%x\n", fw_health->master, fw_health->last_fw_reset_cnt, @@ -12207,6 +12206,11 @@ static void bnxt_fw_reset_task(struct work_struct *work) return; } + if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && + bp->fw_health->enabled) { + bp->fw_health->last_fw_reset_cnt = + bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + } bp->fw_reset_state = 0; /* Make sure fw_reset_state is 0 before clearing the flag */ smp_mb__before_atomic(); From 1affc01fdc6035189a5ab2a24948c9419ee0ecf2 Mon Sep 17 00:00:00 2001 From: Edwin Peer Date: Sun, 12 Sep 2021 12:34:48 -0400 Subject: [PATCH 091/866] bnxt_en: make bnxt_free_skbs() safe to call after bnxt_free_mem() The call to bnxt_free_mem(..., false) in the bnxt_half_open_nic() error path will deallocate ring descriptor memory via bnxt_free_?x_rings(), but because irq_re_init is false, the ring info itself is not freed. To simplify error paths, deallocation functions have generally been written to be safe when called on unallocated memory. It should always be safe to call dev_close(), which calls bnxt_free_skbs() a second time, even in this semi- allocated ring state. Calling bnxt_free_skbs() a second time with the rings already freed will cause NULL pointer dereference. Fix it by checking the rings are valid before proceeding in bnxt_free_tx_skbs() and bnxt_free_one_rx_ring_skbs(). Fixes: 975bc99a4a39 ("bnxt_en: Refactor bnxt_free_rx_skbs().") Signed-off-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8b0a2ae1367c..9f9806f1c0fc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2729,6 +2729,9 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; int j; + if (!txr->tx_buf_ring) + continue; + for (j = 0; j < max_idx;) { struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; struct sk_buff *skb; @@ -2813,6 +2816,9 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) } skip_rx_tpa_free: + if (!rxr->rx_buf_ring) + goto skip_rx_buf_free; + for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i]; dma_addr_t mapping = rx_buf->mapping; @@ -2835,6 +2841,11 @@ skip_rx_tpa_free: kfree(data); } } + +skip_rx_buf_free: + if (!rxr->rx_agg_ring) + goto skip_rx_agg_free; + for (i = 0; i < max_agg_idx; i++) { struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i]; struct page *page = rx_agg_buf->page; @@ -2851,6 +2862,8 @@ skip_rx_tpa_free: __free_page(page); } + +skip_rx_agg_free: if (rxr->rx_page) { __free_page(rxr->rx_page); rxr->rx_page = NULL; From 985941e1dd5e996311c29688ca0d3aa1ff8eb0b6 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Sun, 12 Sep 2021 12:34:49 -0400 Subject: [PATCH 092/866] bnxt_en: Clean up completion ring page arrays completely We recently changed the completion ring page arrays to be dynamically allocated to better support the expanded range of ring depths. The cleanup path for this was not quite complete. It might cause the shutdown path to crash if we need to abort before the completion ring arrays have been allocated and initialized. Fix it by initializing the ring_mem->pg_arr to NULL after freeing the completion ring page array. Add a check in bnxt_free_ring() to skip referencing the rmem->pg_arr if it is NULL. Fixes: 03c7448790b8 ("bnxt_en: Don't use static arrays for completion ring pages") Reviewed-by: Andy Gospodarek Reviewed-by: Edwin Peer Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9f9806f1c0fc..f32431a7e5a6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2912,6 +2912,9 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) struct pci_dev *pdev = bp->pdev; int i; + if (!rmem->pg_arr) + goto skip_pages; + for (i = 0; i < rmem->nr_pages; i++) { if (!rmem->pg_arr[i]) continue; @@ -2921,6 +2924,7 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) rmem->pg_arr[i] = NULL; } +skip_pages: if (rmem->pg_tbl) { size_t pg_tbl_size = rmem->nr_pages * 8; @@ -3240,10 +3244,14 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) static void bnxt_free_cp_arrays(struct bnxt_cp_ring_info *cpr) { + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + kfree(cpr->cp_desc_ring); cpr->cp_desc_ring = NULL; + ring->ring_mem.pg_arr = NULL; kfree(cpr->cp_desc_mapping); cpr->cp_desc_mapping = NULL; + ring->ring_mem.dma_arr = NULL; } static int bnxt_alloc_cp_arrays(struct bnxt_cp_ring_info *cpr, int n) From d7807a9adf4856171f8441f13078c33941df48ab Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Mon, 13 Sep 2021 12:04:42 +0800 Subject: [PATCH 093/866] Revert "ipv4: fix memory leaks in ip_cmsg_send() callers" This reverts commit 919483096bfe75dda338e98d56da91a263746a0a. There is only when ip_options_get() return zero need to free. It already called kfree() when return error. Fixes: 919483096bfe ("ipv4: fix memory leaks in ip_cmsg_send() callers") Signed-off-by: Yajun Deng Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/ping.c | 5 ++--- net/ipv4/raw.c | 5 ++--- net/ipv4/udp.c | 5 ++--- 4 files changed, 7 insertions(+), 10 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b297bb28556e..7cef9987ab4a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -279,7 +279,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, case IP_RETOPTS: err = cmsg->cmsg_len - sizeof(struct cmsghdr); - /* Our caller is responsible for freeing ipc->opt */ + /* Our caller is responsible for freeing ipc->opt when err = 0 */ err = ip_options_get(net, &ipc->opt, KERNEL_SOCKPTR(CMSG_DATA(cmsg)), err < 40 ? err : 40); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1e44a43acfe2..c588f9f2f46c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -727,10 +727,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); - if (unlikely(err)) { - kfree(ipc.opt); + if (unlikely(err)) return err; - } + if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bb446e60cf58..1c98063a3ae8 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -562,10 +562,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); - if (unlikely(err)) { - kfree(ipc.opt); + if (unlikely(err)) goto out; - } + if (ipc.opt) free = 1; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8851c9463b4b..d5f5981d7a43 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1122,10 +1122,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (err > 0) err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); - if (unlikely(err < 0)) { - kfree(ipc.opt); + if (unlikely(err < 0)) return err; - } + if (ipc.opt) free = 1; connected = 0; From e50e711351bdc656a8e6ca1022b4293cae8dcd59 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 13 Sep 2021 10:53:49 +0300 Subject: [PATCH 094/866] udp_tunnel: Fix udp_tunnel_nic work-queue type Turn udp_tunnel_nic work-queue to an ordered work-queue. This queue holds the UDP-tunnel configuration commands of the different netdevs. When the netdevs are functions of the same NIC the order of execution may be crucial. Problem example: NIC with 2 PFs, both PFs declare offload quota of up to 3 UDP-ports. $ifconfig eth2 1.1.1.1/16 up $ip link add eth2_19503 type vxlan id 5049 remote 1.1.1.2 dev eth2 dstport 19053 $ip link set dev eth2_19503 up $ip link add eth2_19504 type vxlan id 5049 remote 1.1.1.3 dev eth2 dstport 19054 $ip link set dev eth2_19504 up $ip link add eth2_19505 type vxlan id 5049 remote 1.1.1.4 dev eth2 dstport 19055 $ip link set dev eth2_19505 up $ip link add eth2_19506 type vxlan id 5049 remote 1.1.1.5 dev eth2 dstport 19056 $ip link set dev eth2_19506 up NIC RX port offload infrastructure offloads the first 3 UDP-ports (on all devices which sets NETIF_F_RX_UDP_TUNNEL_PORT feature) and not UDP-port 19056. So both PFs gets this offload configuration. $ip link set dev eth2_19504 down This triggers udp-tunnel-core to remove the UDP-port 19504 from offload-ports-list and offload UDP-port 19056 instead. In this scenario it is important that the UDP-port of 19504 will be removed from both PFs before trying to add UDP-port 19056. The NIC can stop offloading a UDP-port only when all references are removed. Otherwise the NIC may report exceeding of the offload quota. Fixes: cc4e3835eff4 ("udp_tunnel: add central NIC RX port offload infrastructure") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- net/ipv4/udp_tunnel_nic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index 0d122edc368d..b91003538d87 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -935,7 +935,7 @@ static int __init udp_tunnel_nic_init_module(void) { int err; - udp_tunnel_nic_workqueue = alloc_workqueue("udp_tunnel_nic", 0, 0); + udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; From f4bb62e64c88c93060c051195d3bbba804e56945 Mon Sep 17 00:00:00 2001 From: Hoang Le Date: Mon, 13 Sep 2021 16:28:52 +0700 Subject: [PATCH 095/866] tipc: increase timeout in tipc_sk_enqueue() In tipc_sk_enqueue() we use hardcoded 2 jiffies to extract socket buffer from generic queue to particular socket. The 2 jiffies is too short in case there are other high priority tasks get CPU cycles for multiple jiffies update. As result, no buffer could be enqueued to particular socket. To solve this, we switch to use constant timeout 20msecs. Then, the function will be expired between 2 jiffies (CONFIG_100HZ) and 20 jiffies (CONFIG_1000HZ). Fixes: c637c1035534 ("tipc: resolve race problem at unicast message reception") Acked-by: Jon Maloy Signed-off-by: Hoang Le Signed-off-by: David S. Miller --- net/tipc/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index a0a27d87f631..ad570c2450be 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2423,7 +2423,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, u32 dport, struct sk_buff_head *xmitq) { - unsigned long time_limit = jiffies + 2; + unsigned long time_limit = jiffies + usecs_to_jiffies(20000); struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; From e87b5052271e39d62337ade531992b7e5d8c2cfa Mon Sep 17 00:00:00 2001 From: zhang kai Date: Thu, 9 Sep 2021 16:39:18 +0800 Subject: [PATCH 096/866] ipv6: delay fib6_sernum increase in fib6_add only increase fib6_sernum in net namespace after add fib6_info successfully. Signed-off-by: zhang kai Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1bec5b22f80d..0371d2c14145 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1378,7 +1378,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, int err = -ENOMEM; int allow_create = 1; int replace_required = 0; - int sernum = fib6_new_sernum(info->nl_net); if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1478,7 +1477,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); - __fib6_update_sernum_upto_root(rt, sernum); + __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); fib6_start_gc(info->nl_net, rt); } From 111b64e35ea03d58c882832744f571a88bb2e2e2 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Sun, 12 Sep 2021 13:58:07 +0200 Subject: [PATCH 097/866] net: dsa: lantiq_gswip: Add 200ms assert delay The delay is especially needed by the xRX300 and xRX330 SoCs. Without this patch, some phys are sometimes not properly detected. The patch was tested on BT Home Hub 5A and D-Link DWR-966. Fixes: a09d042b0862 ("net: dsa: lantiq: allow to use all GPHYs on xRX300 and xRX330") Signed-off-by: Aleksander Jan Bajkowski Signed-off-by: Martin Blumenstingl Acked-by: Hauke Mehrtens Signed-off-by: David S. Miller --- drivers/net/dsa/lantiq_gswip.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 64d6dfa83122..267324889dd6 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1885,6 +1885,12 @@ static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gph reset_control_assert(gphy_fw->reset); + /* The vendor BSP uses a 200ms delay after asserting the reset line. + * Without this some users are observing that the PHY is not coming up + * on the MDIO bus. + */ + msleep(200); + ret = request_firmware(&fw, gphy_fw->fw_name, dev); if (ret) { dev_err(dev, "failed to load firmware: %s, error: %i\n", From b871895b148256f1721bc565d803860242755a0b Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Sep 2021 22:57:06 +1000 Subject: [PATCH 098/866] powerpc/64s: system call scv tabort fix for corrupt irq soft-mask state If a system call is made with a transaction active, the kernel immediately aborts it and returns. scv system calls disable irqs even earlier in their interrupt handler, and tabort_syscall does not fix this up. This can result in irq soft-mask state being messed up on the next kernel entry, and crashing at BUG_ON(arch_irq_disabled_regs(regs)) in the kernel exit handlers, or possibly worse. This can't easily be fixed in asm because at this point an async irq may have hit, which is soft-masked and marked pending. The pending interrupt has to be replayed before returning to userspace. The fix is to move the tabort_syscall code to C in the main syscall handler, and just skip the system call but otherwise return as usual, which will take care of the pending irqs. This also does a bunch of other things including possible signal delivery to the process, but the doomed transaction should still be aborted when it is eventually returned to. The sc system call path is changed to use the new C function as well to reduce code and path differences. This slows down how quickly system calls are aborted when called while a transaction is active, which could potentially impact TM performance. But making any system call is already bad for performance, and TM is on the way out, so go with simpler over faster. Fixes: 7fa95f9adaee7 ("powerpc/64s: system call support for scv/rfscv instructions") Reported-by: Eirik Fuller Signed-off-by: Nicholas Piggin [mpe: Use #ifdef rather than IS_ENABLED() to fix build error on 32-bit] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210903125707.1601269-1-npiggin@gmail.com --- arch/powerpc/kernel/interrupt.c | 30 ++++++++++++++++++++++ arch/powerpc/kernel/interrupt_64.S | 41 ------------------------------ 2 files changed, 30 insertions(+), 41 deletions(-) diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index a73f3f70a657..2ccc7ea5db00 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32) @@ -136,6 +137,35 @@ notrace long system_call_exception(long r3, long r4, long r5, */ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + /* + * If the system call was made with a transaction active, doom it and + * return without performing the system call. Unless it was an + * unsupported scv vector, in which case it's treated like an illegal + * instruction. + */ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) && + !trap_is_unsupported_scv(regs)) { + /* Enable TM in the kernel, and disable EE (for scv) */ + hard_irq_disable(); + mtmsr(mfmsr() | MSR_TM); + + /* tabort, this dooms the transaction, nothing else */ + asm volatile(".long 0x7c00071d | ((%0) << 16)" + :: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)); + + /* + * Userspace will never see the return value. Execution will + * resume after the tbegin. of the aborted transaction with the + * checkpointed register state. A context switch could occur + * or signal delivered to the process before resuming the + * doomed transaction context, but that should all be handled + * as expected. + */ + return -ENOSYS; + } +#endif // CONFIG_PPC_TRANSACTIONAL_MEM + local_irq_enable(); if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) { diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index d4212d2ff0b5..ec950b08a8dc 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -12,7 +12,6 @@ #include #include #include -#include .section ".toc","aw" SYS_CALL_TABLE: @@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE: .globl system_call_vectored_\name system_call_vectored_\name: _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) @@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real) .globl system_call_common system_call_common: _ASM_NOKPROBE_SYMBOL(system_call_common) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - bne tabort_syscall -END_FTR_SECTION_IFSET(CPU_FTR_TM) -#endif mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) @@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b) RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart) #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -tabort_syscall: -_ASM_NOKPROBE_SYMBOL(tabort_syscall) - /* Firstly we need to enable TM in the kernel */ - mfmsr r10 - li r9, 1 - rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r10, 0 - - /* tabort, this dooms the transaction, nothing else */ - li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R9) - - /* - * Return directly to userspace. We have corrupted user register state, - * but userspace will never see that register state. Execution will - * resume after the tbegin of the aborted transaction with the - * checkpointed register state. - */ - li r9, MSR_RI - andc r10, r10, r9 - mtmsrd r10, 1 - mtspr SPRN_SRR0, r11 - mtspr SPRN_SRR1, r12 - RFI_TO_USER - b . /* prevent speculative execution */ -#endif - /* * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not * touched, no exit work created, then this can be used. From 5379ef2a60431232b9bb01c6d3580b875123d723 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Sep 2021 22:57:07 +1000 Subject: [PATCH 099/866] selftests/powerpc: Add scv versions of the basic TM syscall tests The basic TM vs syscall test code hard codes an sc instruction for the system call, which fails to cover scv even when the userspace libc has support for it. Duplicate the tests with hard coded scv variants so both are tested when possible. Signed-off-by: Nicholas Piggin [mpe: Fix build on old toolchains by using .long for scv] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210903125707.1601269-2-npiggin@gmail.com --- .../selftests/powerpc/tm/tm-syscall-asm.S | 37 ++++++++++++++++++- .../testing/selftests/powerpc/tm/tm-syscall.c | 36 ++++++++++++++---- 2 files changed, 65 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S index bd1ca25febe4..aed632d29fff 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S +++ b/tools/testing/selftests/powerpc/tm/tm-syscall-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include +#include #include .text @@ -26,3 +26,38 @@ FUNC_START(getppid_tm_suspended) 1: li r3, -1 blr + + +.macro scv level + .long (0x44000001 | (\level) << 5) +.endm + +FUNC_START(getppid_scv_tm_active) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + scv 0 + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr + +FUNC_START(getppid_scv_tm_suspended) + PUSH_BASIC_STACK(0) + tbegin. + beq 1f + li r0, __NR_getppid + tsuspend. + scv 0 + tresume. + tend. + POP_BASIC_STACK(0) + blr +1: + li r3, -1 + POP_BASIC_STACK(0) + blr diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c index 467a6b3134b2..b763354c2eb4 100644 --- a/tools/testing/selftests/powerpc/tm/tm-syscall.c +++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c @@ -19,23 +19,36 @@ #include "utils.h" #include "tm.h" +#ifndef PPC_FEATURE2_SCV +#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */ +#endif + extern int getppid_tm_active(void); extern int getppid_tm_suspended(void); +extern int getppid_scv_tm_active(void); +extern int getppid_scv_tm_suspended(void); unsigned retries = 0; #define TEST_DURATION 10 /* seconds */ -pid_t getppid_tm(bool suspend) +pid_t getppid_tm(bool scv, bool suspend) { int i; pid_t pid; for (i = 0; i < TM_RETRIES; i++) { - if (suspend) - pid = getppid_tm_suspended(); - else - pid = getppid_tm_active(); + if (suspend) { + if (scv) + pid = getppid_scv_tm_suspended(); + else + pid = getppid_tm_suspended(); + } else { + if (scv) + pid = getppid_scv_tm_active(); + else + pid = getppid_tm_active(); + } if (pid >= 0) return pid; @@ -82,15 +95,24 @@ int tm_syscall(void) * Test a syscall within a suspended transaction and verify * that it succeeds. */ - FAIL_IF(getppid_tm(true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(false, true) == -1); /* Should succeed. */ /* * Test a syscall within an active transaction and verify that * it fails with the correct failure code. */ - FAIL_IF(getppid_tm(false) != -1); /* Should fail... */ + FAIL_IF(getppid_tm(false, false) != -1); /* Should fail... */ FAIL_IF(!failure_is_persistent()); /* ...persistently... */ FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + + /* Now do it all again with scv if it is available. */ + if (have_hwcap2(PPC_FEATURE2_SCV)) { + FAIL_IF(getppid_tm(true, true) == -1); /* Should succeed. */ + FAIL_IF(getppid_tm(true, false) != -1); /* Should fail... */ + FAIL_IF(!failure_is_persistent()); /* ...persistently... */ + FAIL_IF(!failure_is_syscall()); /* ...with code syscall. */ + } + gettimeofday(&now, 0); } From ae7aaecc3f2f78b76ab3a8d6178610f55aadfa56 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 8 Sep 2021 20:17:17 +1000 Subject: [PATCH 100/866] powerpc/64s: system call rfscv workaround for TM bugs The rfscv instruction does not work correctly with the fake-suspend mode in POWER9, which can end up with the hypervisor restoring an incorrect checkpoint. Work around this by setting the _TIF_RESTOREALL flag if a system call returns to a transaction active state, causing rfid to be used instead of rfscv to return, which will do the right thing. The contents of the registers are irrelevant because they will be overwritten in this case anyway. Fixes: 7fa95f9adaee7 ("powerpc/64s: system call support for scv/rfscv instructions") Reported-by: Eirik Fuller Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210908101718.118522-1-npiggin@gmail.com --- arch/powerpc/kernel/interrupt.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 2ccc7ea5db00..de10a2697258 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -137,6 +137,19 @@ notrace long system_call_exception(long r3, long r4, long r5, */ irq_soft_mask_regs_set_state(regs, IRQS_ENABLED); + /* + * If system call is called with TM active, set _TIF_RESTOREALL to + * prevent RFSCV being used to return to userspace, because POWER9 + * TM implementation has problems with this instruction returning to + * transactional state. Final register values are not relevant because + * the transaction will be aborted upon return anyway. Or in the case + * of unsupported_scv SIGILL fault, the return state does not much + * matter because it's an edge case. + */ + if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) && + unlikely(MSR_TM_TRANSACTIONAL(regs->msr))) + current_thread_info()->flags |= _TIF_RESTOREALL; + /* * If the system call was made with a transaction active, doom it and * return without performing the system call. Unless it was an From 267cdfa21385d78c794768233678756e32b39ead Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 8 Sep 2021 20:17:18 +1000 Subject: [PATCH 101/866] KVM: PPC: Book3S HV: Tolerate treclaim. in fake-suspend mode changing registers POWER9 DD2.2 and 2.3 hardware implements a "fake-suspend" mode where certain TM instructions executed in HV=0 mode cause softpatch interrupts so the hypervisor can emulate them and prevent problematic processor conditions. In this fake-suspend mode, the treclaim. instruction does not modify registers. Unfortunately the rfscv instruction executed by the guest do not generate softpatch interrupts, which can cause the hypervisor to lose track of the fake-suspend mode, and it can execute this treclaim. while not in fake-suspend mode. This modifies GPRs and crashes the hypervisor. It's not trivial to disable scv in the guest with HFSCR now, because they assume a POWER9 has scv available. So this fix saves and restores checkpointed registers across the treclaim. Fixes: 7854f7545bff ("KVM: PPC: Book3S: Rework TM save/restore code and make it C-callable") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210908101718.118522-2-npiggin@gmail.com --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 36 +++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 75079397c2a5..90484425a1e6 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2536,7 +2536,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST) /* The following code handles the fake_suspend = 1 case */ mflr r0 std r0, PPC_LR_STKOFF(r1) - stdu r1, -PPC_MIN_STKFRM(r1) + stdu r1, -TM_FRAME_SIZE(r1) /* Turn on TM. */ mfmsr r8 @@ -2551,10 +2551,42 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) nop + /* + * It's possible that treclaim. may modify registers, if we have lost + * track of fake-suspend state in the guest due to it using rfscv. + * Save and restore registers in case this occurs. + */ + mfspr r3, SPRN_DSCR + mfspr r4, SPRN_XER + mfspr r5, SPRN_AMR + /* SPRN_TAR would need to be saved here if the kernel ever used it */ + mfcr r12 + SAVE_NVGPRS(r1) + SAVE_GPR(2, r1) + SAVE_GPR(3, r1) + SAVE_GPR(4, r1) + SAVE_GPR(5, r1) + stw r12, 8(r1) + std r1, HSTATE_HOST_R1(r13) + /* We have to treclaim here because that's the only way to do S->N */ li r3, TM_CAUSE_KVM_RESCHED TRECLAIM(R3) + GET_PACA(r13) + ld r1, HSTATE_HOST_R1(r13) + REST_GPR(2, r1) + REST_GPR(3, r1) + REST_GPR(4, r1) + REST_GPR(5, r1) + lwz r12, 8(r1) + REST_NVGPRS(r1) + mtspr SPRN_DSCR, r3 + mtspr SPRN_XER, r4 + mtspr SPRN_AMR, r5 + mtcr r12 + HMT_MEDIUM + /* * We were in fake suspend, so we are not going to save the * register state as the guest checkpointed state (since @@ -2582,7 +2614,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG) std r5, VCPU_TFHAR(r9) std r6, VCPU_TFIAR(r9) - addi r1, r1, PPC_MIN_STKFRM + addi r1, r1, TM_FRAME_SIZE ld r0, PPC_LR_STKOFF(r1) mtlr r0 blr From 3a1e92d0896e928ac2a5b58962d05a39afef2e23 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Thu, 9 Sep 2021 12:13:30 +0530 Subject: [PATCH 102/866] powerpc/mce: Fix access error in mce handler We queue an irq work for deferred processing of mce event in realmode mce handler, where translation is disabled. Queuing of the work may result in accessing memory outside RMO region, such access needs the translation to be enabled for an LPAR running with hash mmu else the kernel crashes. After enabling translation in mce_handle_error() we used to leave it enabled to avoid crashing here, but now with the commit 74c3354bc1d89 ("powerpc/pseries/mce: restore msr before returning from handler") we are restoring the MSR to disable translation. Hence to fix this enable the translation before queuing the work. Without this change following trace is seen on injecting SLB multihit in an LPAR running with hash mmu. Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries CPU: 5 PID: 1883 Comm: insmod Tainted: G OE 5.14.0-mce+ #137 NIP: c000000000735d60 LR: c000000000318640 CTR: 0000000000000000 REGS: c00000001ebff9a0 TRAP: 0300 Tainted: G OE (5.14.0-mce+) MSR: 8000000000001003 CR: 28008228 XER: 00000001 CFAR: c00000000031863c DAR: c00000027fa8fe08 DSISR: 40000000 IRQMASK: 0 ... NIP llist_add_batch+0x0/0x40 LR __irq_work_queue_local+0x70/0xc0 Call Trace: 0xc00000001ebffc0c (unreliable) irq_work_queue+0x40/0x70 machine_check_queue_event+0xbc/0xd0 machine_check_early_common+0x16c/0x1f4 Fixes: 74c3354bc1d89 ("powerpc/pseries/mce: restore msr before returning from handler") Signed-off-by: Ganesh Goudar [mpe: Fix comment formatting, trim oops in change log for readability] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210909064330.312432-1-ganeshgr@linux.ibm.com --- arch/powerpc/kernel/mce.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 47a683cd00d2..fd829f7f25a4 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -249,6 +249,7 @@ void machine_check_queue_event(void) { int index; struct machine_check_event evt; + unsigned long msr; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; @@ -262,8 +263,20 @@ void machine_check_queue_event(void) memcpy(&local_paca->mce_info->mce_event_queue[index], &evt, sizeof(evt)); - /* Queue irq work to process this event later. */ - irq_work_queue(&mce_event_process_work); + /* + * Queue irq work to process this event later. Before + * queuing the work enable translation for non radix LPAR, + * as irq_work_queue may try to access memory outside RMO + * region. + */ + if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) { + msr = mfmsr(); + mtmsr(msr | MSR_IR | MSR_DR); + irq_work_queue(&mce_event_process_work); + mtmsr(msr); + } else { + irq_work_queue(&mce_event_process_work); + } } void mce_common_process_ue(struct pt_regs *regs, From a06c2e5c048e5e07fac9daf3073bd0b6582913c7 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 13 Sep 2021 15:49:55 +0300 Subject: [PATCH 103/866] interconnect: qcom: sdm660: Fix id of slv_cnoc_mnoc_cfg The id of slv_cnoc_mnoc_cfg node is mistakenly coded as id of slv_blsp_1. It causes the following warning on slv_blsp_1 node adding. Correct the id of slv_cnoc_mnoc_cfg node. [ 1.948180] ------------[ cut here ]------------ [ 1.954122] WARNING: CPU: 2 PID: 7 at drivers/interconnect/core.c:962 icc_node_add+0xe4/0xf8 [ 1.958994] Modules linked in: [ 1.967399] CPU: 2 PID: 7 Comm: kworker/u16:0 Not tainted 5.14.0-rc6-next-20210818 #21 [ 1.970275] Hardware name: Xiaomi Redmi Note 7 (DT) [ 1.978169] Workqueue: events_unbound deferred_probe_work_func [ 1.982945] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 1.988849] pc : icc_node_add+0xe4/0xf8 [ 1.995699] lr : qnoc_probe+0x350/0x438 [ 1.999519] sp : ffff80001008bb10 [ 2.003337] x29: ffff80001008bb10 x28: 000000000000001a x27: ffffb83ddc61ee28 [ 2.006818] x26: ffff2fe341d44080 x25: ffff2fe340f3aa80 x24: ffffb83ddc98f0e8 [ 2.013938] x23: 0000000000000024 x22: ffff2fe3408b7400 x21: 0000000000000000 [ 2.021054] x20: ffff2fe3408b7410 x19: ffff2fe341d44080 x18: 0000000000000010 [ 2.028173] x17: ffff2fe3bdd0aac0 x16: 0000000000000281 x15: ffff2fe3400f5528 [ 2.035290] x14: 000000000000013f x13: ffff2fe3400f5528 x12: 00000000ffffffea [ 2.042410] x11: ffffb83ddc9109d0 x10: ffffb83ddc8f8990 x9 : ffffb83ddc8f89e8 [ 2.049527] x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001 [ 2.056645] x5 : 0000000000057fa8 x4 : 0000000000000000 x3 : ffffb83ddc9903b0 [ 2.063764] x2 : 1a1f6fde34d45500 x1 : ffff2fe340f3a880 x0 : ffff2fe340f3a880 [ 2.070882] Call trace: [ 2.077989] icc_node_add+0xe4/0xf8 [ 2.080247] qnoc_probe+0x350/0x438 [ 2.083718] platform_probe+0x68/0xd8 [ 2.087191] really_probe+0xb8/0x300 [ 2.091011] __driver_probe_device+0x78/0xe0 [ 2.094659] driver_probe_device+0x80/0x110 [ 2.098911] __device_attach_driver+0x90/0xe0 [ 2.102818] bus_for_each_drv+0x78/0xc8 [ 2.107331] __device_attach+0xf0/0x150 [ 2.110977] device_initial_probe+0x14/0x20 [ 2.114796] bus_probe_device+0x9c/0xa8 [ 2.118963] deferred_probe_work_func+0x88/0xc0 [ 2.122784] process_one_work+0x1a4/0x338 [ 2.127296] worker_thread+0x1f8/0x420 [ 2.131464] kthread+0x150/0x160 [ 2.135107] ret_from_fork+0x10/0x20 [ 2.138495] ---[ end trace 5eea8768cb620e87 ]--- Signed-off-by: Shawn Guo Reviewed-by: Bjorn Andersson Fixes: f80a1d414328 ("interconnect: qcom: Add SDM660 interconnect provider driver") Link: https://lore.kernel.org/r/20210823014003.31391-1-shawn.guo@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/sdm660.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c index 632dbdd21915..ac13046537e8 100644 --- a/drivers/interconnect/qcom/sdm660.c +++ b/drivers/interconnect/qcom/sdm660.c @@ -307,7 +307,7 @@ DEFINE_QNODE(slv_bimc_cfg, SDM660_SLAVE_BIMC_CFG, 4, -1, 56, true, -1, 0, -1, 0) DEFINE_QNODE(slv_prng, SDM660_SLAVE_PRNG, 4, -1, 44, true, -1, 0, -1, 0); DEFINE_QNODE(slv_spdm, SDM660_SLAVE_SPDM, 4, -1, 60, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qdss_cfg, SDM660_SLAVE_QDSS_CFG, 4, -1, 63, true, -1, 0, -1, 0); -DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_BLSP_1, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); +DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_CNOC_MNOC_CFG, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); DEFINE_QNODE(slv_snoc_cfg, SDM660_SLAVE_SNOC_CFG, 4, -1, 70, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qm_cfg, SDM660_SLAVE_QM_CFG, 4, -1, 212, true, -1, 0, -1, 0); DEFINE_QNODE(slv_clk_ctl, SDM660_SLAVE_CLK_CTL, 4, -1, 47, true, -1, 0, -1, 0); From 5833c9b8766298e73c11766f9585d4ea4fa785ff Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 13 Sep 2021 15:49:55 +0300 Subject: [PATCH 104/866] interconnect: qcom: sdm660: Correct NOC_QOS_PRIORITY shift and mask The NOC_QOS_PRIORITY shift and mask do not match what vendor kernel defines [1]. Correct them per vendor kernel. As the result of NOC_QOS_PRIORITY_P0_SHIFT being 0, the definition can be dropped and regmap_update_bits() call on P0 can be simplified a bit. [1] https://source.codeaurora.org/quic/la/kernel/msm-4.4/tree/drivers/soc/qcom/msm_bus/msm_bus_noc_adhoc.c?h=LA.UM.8.2.r1-04800-sdm660.0#n37 Fixes: f80a1d414328 ("interconnect: qcom: Add SDM660 interconnect provider driver") Signed-off-by: Shawn Guo Reviewed-by: Dmitry Baryshkov Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210902054915.28689-1-shawn.guo@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/sdm660.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c index ac13046537e8..99eef7e2d326 100644 --- a/drivers/interconnect/qcom/sdm660.c +++ b/drivers/interconnect/qcom/sdm660.c @@ -44,9 +44,9 @@ #define NOC_PERM_MODE_BYPASS (1 << NOC_QOS_MODE_BYPASS) #define NOC_QOS_PRIORITYn_ADDR(n) (0x8 + (n * 0x1000)) -#define NOC_QOS_PRIORITY_MASK 0xf +#define NOC_QOS_PRIORITY_P1_MASK 0xc +#define NOC_QOS_PRIORITY_P0_MASK 0x3 #define NOC_QOS_PRIORITY_P1_SHIFT 0x2 -#define NOC_QOS_PRIORITY_P0_SHIFT 0x3 #define NOC_QOS_MODEn_ADDR(n) (0xc + (n * 0x1000)) #define NOC_QOS_MODEn_MASK 0x3 @@ -624,13 +624,12 @@ static int qcom_icc_noc_set_qos_priority(struct regmap *rmap, /* Must be updated one at a time, P1 first, P0 last */ val = qos->areq_prio << NOC_QOS_PRIORITY_P1_SHIFT; rc = regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P1_MASK, val); if (rc) return rc; - val = qos->prio_level << NOC_QOS_PRIORITY_P0_SHIFT; return regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P0_MASK, qos->prio_level); } static int qcom_icc_set_noc_qos(struct icc_node *src, u64 max_bw) From cf49e366020396ad83845c1c3bdbaa3c1406f5ce Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 13 Sep 2021 15:49:55 +0300 Subject: [PATCH 105/866] dt-bindings: interconnect: sdm660: Add missing a2noc qos clocks It adds the missing a2noc clocks required for QoS registers programming per downstream kernel[1]. [1] https://source.codeaurora.org/quic/la/kernel/msm-4.4/tree/arch/arm/boot/dts/qcom/sdm660-bus.dtsi?h=LA.UM.8.2.r1-04800-sdm660.0#n43 Signed-off-by: Shawn Guo Reviewed-by: Rob Herring Acked-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210824043435.23190-2-shawn.guo@linaro.org Signed-off-by: Georgi Djakov --- .../bindings/interconnect/qcom,sdm660.yaml | 46 +++++++++++++++++-- 1 file changed, 42 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml index 29de7807df54..bcd41e491f1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml @@ -31,11 +31,11 @@ properties: clocks: minItems: 1 - maxItems: 3 + maxItems: 7 clock-names: minItems: 1 - maxItems: 3 + maxItems: 7 required: - compatible @@ -72,6 +72,32 @@ allOf: contains: enum: - qcom,sdm660-a2noc + then: + properties: + clocks: + items: + - description: Bus Clock. + - description: Bus A Clock. + - description: IPA Clock. + - description: UFS AXI Clock. + - description: Aggregate2 UFS AXI Clock. + - description: Aggregate2 USB3 AXI Clock. + - description: Config NoC USB2 AXI Clock. + clock-names: + items: + - const: bus + - const: bus_a + - const: ipa + - const: ufs_axi + - const: aggre2_ufs_axi + - const: aggre2_usb3_axi + - const: cfg_noc_usb2_axi + + - if: + properties: + compatible: + contains: + enum: - qcom,sdm660-bimc - qcom,sdm660-cnoc - qcom,sdm660-gnoc @@ -91,6 +117,7 @@ examples: - | #include #include + #include bimc: interconnect@1008000 { compatible = "qcom,sdm660-bimc"; @@ -123,9 +150,20 @@ examples: compatible = "qcom,sdm660-a2noc"; reg = <0x01704000 0xc100>; #interconnect-cells = <1>; - clock-names = "bus", "bus_a"; + clock-names = "bus", + "bus_a", + "ipa", + "ufs_axi", + "aggre2_ufs_axi", + "aggre2_usb3_axi", + "cfg_noc_usb2_axi"; clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>, - <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>; + <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>, + <&rpmcc RPM_SMD_IPA_CLK>, + <&gcc GCC_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_USB3_AXI_CLK>, + <&gcc GCC_CFG_NOC_USB2_AXI_CLK>; }; mnoc: interconnect@1745000 { From 13404ac8882f5225af07545215f4975a564c3740 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 13 Sep 2021 15:49:55 +0300 Subject: [PATCH 106/866] interconnect: qcom: sdm660: Add missing a2noc qos clocks It adds the missing a2noc clocks required for QoS registers programming per downstream kernel[1]. Otherwise, qcom_icc_noc_set_qos_priority() call on mas_ufs or mas_usb_hs node will simply result in a hardware hang on SDM660 SoC. [1] https://source.codeaurora.org/quic/la/kernel/msm-4.4/tree/arch/arm/boot/dts/qcom/sdm660-bus.dtsi?h=LA.UM.8.2.r1-04800-sdm660.0#n43 Signed-off-by: Shawn Guo Tested-by: Bjorn Andersson Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20210824043435.23190-3-shawn.guo@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/sdm660.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c index 99eef7e2d326..fb23a5b780a4 100644 --- a/drivers/interconnect/qcom/sdm660.c +++ b/drivers/interconnect/qcom/sdm660.c @@ -173,6 +173,16 @@ static const struct clk_bulk_data bus_mm_clocks[] = { { .id = "iface" }, }; +static const struct clk_bulk_data bus_a2noc_clocks[] = { + { .id = "bus" }, + { .id = "bus_a" }, + { .id = "ipa" }, + { .id = "ufs_axi" }, + { .id = "aggre2_ufs_axi" }, + { .id = "aggre2_usb3_axi" }, + { .id = "cfg_noc_usb2_axi" }, +}; + /** * struct qcom_icc_provider - Qualcomm specific interconnect provider * @provider: generic interconnect provider @@ -809,6 +819,10 @@ static int qnoc_probe(struct platform_device *pdev) qp->bus_clks = devm_kmemdup(dev, bus_mm_clocks, sizeof(bus_mm_clocks), GFP_KERNEL); qp->num_clks = ARRAY_SIZE(bus_mm_clocks); + } else if (of_device_is_compatible(dev->of_node, "qcom,sdm660-a2noc")) { + qp->bus_clks = devm_kmemdup(dev, bus_a2noc_clocks, + sizeof(bus_a2noc_clocks), GFP_KERNEL); + qp->num_clks = ARRAY_SIZE(bus_a2noc_clocks); } else { if (of_device_is_compatible(dev->of_node, "qcom,sdm660-bimc")) qp->is_bimc_node = true; From 6f44578430d7888ade1e3bd919c1c2c0724409e5 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 13 Sep 2021 14:43:30 +0200 Subject: [PATCH 107/866] Revert "ALSA: hda: Drop workaround for a hang at shutdown again" This reverts commit 8fc8e903156f42c66245838441d03607e9067381. It was expected that the fixes in HD-audio codec side would make the workaround redundant, but unfortunately it doesn't seem sufficing. Resurrect the workaround for now. Fixes: 8fc8e903156f ("ALSA: hda: Drop workaround for a hang at shutdown again") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=214045 Link: https://lore.kernel.org/r/20210913124330.24530-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 3aa432d814a2..47777439961c 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -883,10 +883,11 @@ static unsigned int azx_get_pos_skl(struct azx *chip, struct azx_dev *azx_dev) return azx_get_pos_posbuf(chip, azx_dev); } -static void azx_shutdown_chip(struct azx *chip) +static void __azx_shutdown_chip(struct azx *chip, bool skip_link_reset) { azx_stop_chip(chip); - azx_enter_link_reset(chip); + if (!skip_link_reset) + azx_enter_link_reset(chip); azx_clear_irq_pending(chip); display_power(chip, false); } @@ -895,6 +896,11 @@ static void azx_shutdown_chip(struct azx *chip) static DEFINE_MUTEX(card_list_lock); static LIST_HEAD(card_list); +static void azx_shutdown_chip(struct azx *chip) +{ + __azx_shutdown_chip(chip, false); +} + static void azx_add_card_list(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -2357,7 +2363,7 @@ static void azx_shutdown(struct pci_dev *pci) return; chip = card->private_data; if (chip && chip->running) - azx_shutdown_chip(chip); + __azx_shutdown_chip(chip, true); } /* PCI IDs */ From 7b9cf9036609428e845dc300aec13822ba2c4ab3 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 10 Sep 2021 12:51:55 +0200 Subject: [PATCH 108/866] ALSA: usb-audio: Unify mixer resume and reset_resume procedure USB-audio driver assumes that the normal resume would preserve the device configuration while reset_resume wouldn't, and tries to restore the mixer elements only at reset_resume callback. However, this seems too naive, and some devices do behave differently, resetting the volume at the normal resume; this resulted in the inconsistent volume that surprised users. This patch changes the mixer resume code to handle both the normal and reset resume in the same way, always restoring the original mixer element values. This allows us to unify the both callbacks as well as dropping the no longer used reset_resume field, which ends up with a good code reduction. A slight behavior change by this patch is that now we assign restore_mixer_value() as the default resume callback, and the function is no longer called at reset-resume when the resume callback is overridden by the quirk function. That is, if needed, the quirk resume function would have to handle similarly as restore_mixer_value() by itself. Reported-by: En-Shuo Hsu Cc: Yu-Hsuan Hsu Link: https://lore.kernel.org/r/CADDZ45UPsbpAAqP6=ZkTT8BE-yLii4Y7xSDnjK550G2DhQsMew@mail.gmail.com Link: https://lore.kernel.org/r/20210910105155.12862-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/card.c | 18 ++++-------------- sound/usb/mixer.c | 26 ++++---------------------- sound/usb/mixer.h | 3 +-- sound/usb/mixer_quirks.c | 2 +- 4 files changed, 10 insertions(+), 39 deletions(-) diff --git a/sound/usb/card.c b/sound/usb/card.c index fd570a42f043..1764b9302d46 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -1054,7 +1054,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message) return 0; } -static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume) +static int usb_audio_resume(struct usb_interface *intf) { struct snd_usb_audio *chip = usb_get_intfdata(intf); struct snd_usb_stream *as; @@ -1080,7 +1080,7 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume) * we just notify and restart the mixers */ list_for_each_entry(mixer, &chip->mixer_list, list) { - err = snd_usb_mixer_resume(mixer, reset_resume); + err = snd_usb_mixer_resume(mixer); if (err < 0) goto err_out; } @@ -1100,20 +1100,10 @@ err_out: atomic_dec(&chip->active); /* allow autopm after this point */ return err; } - -static int usb_audio_resume(struct usb_interface *intf) -{ - return __usb_audio_resume(intf, false); -} - -static int usb_audio_reset_resume(struct usb_interface *intf) -{ - return __usb_audio_resume(intf, true); -} #else #define usb_audio_suspend NULL #define usb_audio_resume NULL -#define usb_audio_reset_resume NULL +#define usb_audio_resume NULL #endif /* CONFIG_PM */ static const struct usb_device_id usb_audio_ids [] = { @@ -1135,7 +1125,7 @@ static struct usb_driver usb_audio_driver = { .disconnect = usb_audio_disconnect, .suspend = usb_audio_suspend, .resume = usb_audio_resume, - .reset_resume = usb_audio_reset_resume, + .reset_resume = usb_audio_resume, .id_table = usb_audio_ids, .supports_autosuspend = 1, }; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 43bc59575a6e..a2ce535df14b 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -3653,33 +3653,16 @@ static int restore_mixer_value(struct usb_mixer_elem_list *list) return 0; } -static int default_mixer_reset_resume(struct usb_mixer_elem_list *list) -{ - int err; - - if (list->resume) { - err = list->resume(list); - if (err < 0) - return err; - } - return restore_mixer_value(list); -} - -int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume) +int snd_usb_mixer_resume(struct usb_mixer_interface *mixer) { struct usb_mixer_elem_list *list; - usb_mixer_elem_resume_func_t f; int id, err; /* restore cached mixer values */ for (id = 0; id < MAX_ID_ELEMS; id++) { for_each_mixer_elem(list, mixer, id) { - if (reset_resume) - f = list->reset_resume; - else - f = list->resume; - if (f) { - err = f(list); + if (list->resume) { + err = list->resume(list); if (err < 0) return err; } @@ -3700,7 +3683,6 @@ void snd_usb_mixer_elem_init_std(struct usb_mixer_elem_list *list, list->id = unitid; list->dump = snd_usb_mixer_dump_cval; #ifdef CONFIG_PM - list->resume = NULL; - list->reset_resume = default_mixer_reset_resume; + list->resume = restore_mixer_value; #endif } diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 876bbc9a71ad..98ea24d91d80 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -70,7 +70,6 @@ struct usb_mixer_elem_list { bool is_std_info; usb_mixer_elem_dump_func_t dump; usb_mixer_elem_resume_func_t resume; - usb_mixer_elem_resume_func_t reset_resume; }; /* iterate over mixer element list of the given unit id */ @@ -121,7 +120,7 @@ int snd_usb_mixer_vol_tlv(struct snd_kcontrol *kcontrol, int op_flag, #ifdef CONFIG_PM int snd_usb_mixer_suspend(struct usb_mixer_interface *mixer); -int snd_usb_mixer_resume(struct usb_mixer_interface *mixer, bool reset_resume); +int snd_usb_mixer_resume(struct usb_mixer_interface *mixer); #endif int snd_usb_set_cur_mix_value(struct usb_mixer_elem_info *cval, int channel, diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index a66ce0375fd9..46082dc57be0 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -151,7 +151,7 @@ static int add_single_ctl_with_resume(struct usb_mixer_interface *mixer, *listp = list; list->mixer = mixer; list->id = id; - list->reset_resume = resume; + list->resume = resume; kctl = snd_ctl_new1(knew, list); if (!kctl) { kfree(list); From f7ec554b73c5239a96afb9a9c3eb18cb11f539b7 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 13 Sep 2021 21:08:20 +0800 Subject: [PATCH 109/866] net: hns3: add option to turn off page pool feature When page pool is added to the hns3 driver, it is always enabled unconditionally, which means spilt page handling in the hns3 driver is dead code. As there is a requirement to test the performance between spilt page handling in driver and page pool, so add a module param to support disabling the page pool. When the page pool is proved to perform better in most case, the spilt page handling in driver can be removed. Fixes: 93188e9642c3 ("net: hns3: support skb's frag page recycling based on page pool") Signed-off-by: Yunsheng Lin Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 22af3d6ce178..293243bbe407 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -61,6 +61,9 @@ static unsigned int tx_sgl = 1; module_param(tx_sgl, uint, 0600); MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to optimize the IOMMU mapping"); +static bool page_pool_enabled = true; +module_param(page_pool_enabled, bool, 0400); + #define HNS3_SGL_SIZE(nfrag) (sizeof(struct scatterlist) * (nfrag) + \ sizeof(struct sg_table)) #define HNS3_MAX_SGL_SIZE ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM), \ @@ -4753,7 +4756,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) goto out_with_desc_cb; if (!HNAE3_IS_TX_RING(ring)) { - hns3_alloc_page_pool(ring); + if (page_pool_enabled) + hns3_alloc_page_pool(ring); ret = hns3_alloc_ring_buffers(ring); if (ret) From d18e81183b1cb9c309266cbbce9acd3e0c528d04 Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Mon, 13 Sep 2021 21:08:21 +0800 Subject: [PATCH 110/866] net: hns3: pad the short tunnel frame before sending to hardware The hardware cannot handle short tunnel frames below 65 bytes, and will cause vlan tag missing problem. So pads packet size to 65 bytes for tunnel frames to fix this bug. Fixes: 3db084d28dc0("net: hns3: Fix for vxlan tx checksum bug") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 293243bbe407..adc54a726661 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -76,6 +76,7 @@ module_param(page_pool_enabled, bool, 0400); #define HNS3_OUTER_VLAN_TAG 2 #define HNS3_MIN_TX_LEN 33U +#define HNS3_MIN_TUN_PKT_LEN 65U /* hns3_pci_tbl - PCI Device ID Table * @@ -1427,8 +1428,11 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, l4.tcp->doff); break; case IPPROTO_UDP: - if (hns3_tunnel_csum_bug(skb)) - return skb_checksum_help(skb); + if (hns3_tunnel_csum_bug(skb)) { + int ret = skb_put_padto(skb, HNS3_MIN_TUN_PKT_LEN); + + return ret ? ret : skb_checksum_help(skb); + } hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S, From 1dc839ec09d3ab2a4156dc98328b8bc3586f2b70 Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Mon, 13 Sep 2021 21:08:22 +0800 Subject: [PATCH 111/866] net: hns3: change affinity_mask to numa node range Currently, affinity_mask is set to a single cpu. As a result, irqbalance becomes invalid in SUBSET or EXACT mode. To solve this problem, change affinity_mask to numa node range. In this way, irqbalance can be performed on the cpu of the numa node. Fixes: 0812545487ec ("net: hns3: add interrupt affinity support for misc interrupt") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e55ba2e511b1..aed97c934bfb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1528,9 +1528,10 @@ static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev) static int hclge_configure(struct hclge_dev *hdev) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + const struct cpumask *cpumask = cpu_online_mask; struct hclge_cfg cfg; unsigned int i; - int ret; + int node, ret; ret = hclge_get_cfg(hdev, &cfg); if (ret) @@ -1595,11 +1596,12 @@ static int hclge_configure(struct hclge_dev *hdev) hclge_init_kdump_kernel_config(hdev); - /* Set the init affinity based on pci func number */ - i = cpumask_weight(cpumask_of_node(dev_to_node(&hdev->pdev->dev))); - i = i ? PCI_FUNC(hdev->pdev->devfn) % i : 0; - cpumask_set_cpu(cpumask_local_spread(i, dev_to_node(&hdev->pdev->dev)), - &hdev->affinity_mask); + /* Set the affinity based on numa node */ + node = dev_to_node(&hdev->pdev->dev); + if (node != NUMA_NO_NODE) + cpumask = cpumask_of_node(node); + + cpumask_copy(&hdev->affinity_mask, cpumask); return ret; } From b81d8948746520f989e86d66292ff72b5056114a Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Mon, 13 Sep 2021 21:08:23 +0800 Subject: [PATCH 112/866] net: hns3: disable mac in flr process The firmware will not disable mac in flr process. Therefore, the driver needs to proactively disable mac during flr, which is the same as the function reset. Fixes: 35d93a30040c ("net: hns3: adjust the process of PF reset") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index aed97c934bfb..f1e46ba799f9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8127,11 +8127,12 @@ static void hclge_ae_stop(struct hnae3_handle *handle) hclge_clear_arfs_rules(hdev); spin_unlock_bh(&hdev->fd_rule_lock); - /* If it is not PF reset, the firmware will disable the MAC, + /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET) { + hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { hclge_mac_stop_phy(hdev); hclge_update_link_status(hdev); return; From 472430a7b066f19afa1b55867d621b2d6d323e0d Mon Sep 17 00:00:00 2001 From: Jiaran Zhang Date: Mon, 13 Sep 2021 21:08:24 +0800 Subject: [PATCH 113/866] net: hns3: fix the exception when query imp info When the command for querying imp info is issued to the firmware, if the firmware does not support the command, the returned value of bd num is 0. Add protection mechanism before alloc memory to prevent apply for 0-length memory. Fixes: 0b198b0d80ea ("net: hns3: refactor dump m7 info of debugfs") Signed-off-by: Jiaran Zhang Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 68ed1715ac52..87d96f82c318 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -1724,6 +1724,10 @@ hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len) } bd_num = le32_to_cpu(req->bd_num); + if (!bd_num) { + dev_err(&hdev->pdev->dev, "imp statistics bd number is 0!\n"); + return -EINVAL; + } desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); if (!desc_src) From 427900d27d86b820c559037a984bd403f910860f Mon Sep 17 00:00:00 2001 From: Jiaran Zhang Date: Mon, 13 Sep 2021 21:08:25 +0800 Subject: [PATCH 114/866] net: hns3: fix the timing issue of VF clearing interrupt sources Currently, the VF does not clear the interrupt source immediately after receiving the interrupt. As a result, if the second interrupt task is triggered when processing the first interrupt task, clearing the interrupt source before exiting will clear the interrupt sources of the two tasks at the same time. As a result, no interrupt is triggered for the second task. The VF detects the missed message only when the next interrupt is generated. Clearing it immediately after executing check_evt_cause ensures that: 1. Even if two interrupt tasks are triggered at the same time, they can be processed. 2. If the second task is triggered during the processing of the first task and the interrupt source is not cleared, the interrupt is reported after vector0 is enabled. Fixes: b90fcc5bd904 ("net: hns3: add reset handling for VF when doing Core/Global/IMP reset") Signed-off-by: Jiaran Zhang Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 82e727020120..a69e892277b3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2465,6 +2465,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) hclgevf_enable_vector(&hdev->misc_vector, false); event_cause = hclgevf_check_evt_cause(hdev, &clearval); + if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) + hclgevf_clear_event_cause(hdev, clearval); switch (event_cause) { case HCLGEVF_VECTOR0_EVENT_RST: @@ -2477,10 +2479,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) break; } - if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) { - hclgevf_clear_event_cause(hdev, clearval); + if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) hclgevf_enable_vector(&hdev->misc_vector, true); - } return IRQ_HANDLED; } From d168cd797982db9db617113644c87b8f5f3cf27e Mon Sep 17 00:00:00 2001 From: Zhi A Wang Date: Thu, 26 Aug 2021 14:38:34 +0000 Subject: [PATCH 115/866] drm/i915/gvt: fix the usage of ww lock in gvt scheduler. As the APIs related to ww lock in i915 was changed recently, the usage of ww lock in GVT-g scheduler needs to be changed accrodingly. We noticed a deadlock when GVT-g scheduler submits the workload to i915. After some investigation, it seems the way of how to use ww lock APIs has been changed. Releasing a ww now requires a explicit i915_gem_ww_ctx_fini(). Fixes: 67f1120381df ("drm/i915/gvt: Introduce per object locking in GVT scheduler.") Cc: Zhenyu Wang Signed-off-by: Zhi A Wang Signed-off-by: Zhenyu Wang Link: http://patchwork.freedesktop.org/patch/msgid/20210826143834.25410-1-zhi.a.wang@intel.com Acked-by: Zhenyu Wang --- drivers/gpu/drm/i915/gvt/scheduler.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 734c37c5e347..527b59b86312 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -576,7 +576,7 @@ retry: /* No one is going to touch shadow bb from now on. */ i915_gem_object_flush_map(bb->obj); - i915_gem_object_unlock(bb->obj); + i915_gem_ww_ctx_fini(&ww); } } return 0; @@ -630,7 +630,7 @@ retry: return ret; } - i915_gem_object_unlock(wa_ctx->indirect_ctx.obj); + i915_gem_ww_ctx_fini(&ww); /* FIXME: we are not tracking our pinned VMA leaving it * up to the core to fix up the stray pin_count upon From 0bd46e22c5ec3dbfb81b60de475151e3f6b411c2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 9 Sep 2021 12:14:40 +0300 Subject: [PATCH 116/866] nvmet: fix a width vs precision bug in nvmet_subsys_attr_serial_show() This was intended to limit the number of characters printed from "subsys->serial" to NVMET_SN_MAX_SIZE. But accidentally the width specifier was used instead of the precision specifier so it only affects the alignment and not the number of characters printed. Fixes: f04064814c2a ("nvmet: fixup buffer overrun in nvmet_subsys_attr_serial()") Signed-off-by: Dan Carpenter Signed-off-by: Christoph Hellwig --- drivers/nvme/target/configfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index d784f3c200b4..be5d82421e3a 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1067,7 +1067,7 @@ static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item, { struct nvmet_subsys *subsys = to_subsys(item); - return snprintf(page, PAGE_SIZE, "%*s\n", + return snprintf(page, PAGE_SIZE, "%.*s\n", NVMET_SN_MAX_SIZE, subsys->serial); } From 9edceaf43050f5ba1dd7d0011bcf68a736a17743 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Thu, 2 Sep 2021 11:20:02 +0200 Subject: [PATCH 117/866] nvme: avoid race in shutdown namespace removal When we remove the siblings entry, we update ns->head->list, hence we can't separate the removal and test for being empty. They have to be in the same critical section to avoid a race. To avoid breaking the refcounting imbalance again, add a list empty check to nvme_find_ns_head. Fixes: 5396fdac56d8 ("nvme: fix refcounting imbalance when all paths are down") Signed-off-by: Daniel Wagner Reviewed-by: Hannes Reinecke Tested-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7efb31b87f37..97f8211cf92c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3524,7 +3524,9 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys, lockdep_assert_held(&subsys->lock); list_for_each_entry(h, &subsys->nsheads, entry) { - if (h->ns_id == nsid && nvme_tryget_ns_head(h)) + if (h->ns_id != nsid) + continue; + if (!list_empty(&h->list) && nvme_tryget_ns_head(h)) return h; } @@ -3843,6 +3845,10 @@ static void nvme_ns_remove(struct nvme_ns *ns) mutex_lock(&ns->ctrl->subsys->lock); list_del_rcu(&ns->siblings); + if (list_empty(&ns->head->list)) { + list_del_init(&ns->head->entry); + last_path = true; + } mutex_unlock(&ns->ctrl->subsys->lock); /* guarantee not available in head->list */ @@ -3863,13 +3869,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) list_del_init(&ns->list); up_write(&ns->ctrl->namespaces_rwsem); - /* Synchronize with nvme_init_ns_head() */ - mutex_lock(&ns->head->subsys->lock); - if (list_empty(&ns->head->list)) { - list_del_init(&ns->head->entry); - last_path = true; - } - mutex_unlock(&ns->head->subsys->lock); if (last_path) nvme_mpath_shutdown_disk(ns->head); nvme_put_ns(ns); From 510e1a724ab1bf38150be2c1acabb303f98d0047 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Fri, 10 Sep 2021 19:53:37 -0400 Subject: [PATCH 118/866] dma-debug: prevent an error message from causing runtime problems For some drivers, that use the DMA API. This error message can be reached several millions of times per second, causing spam to the kernel's printk buffer and bringing the CPU usage up to 100% (so, it should be rate limited). However, since there is at least one driver that is in the mainline and suffers from the error condition, it is more useful to err_printk() here instead of just rate limiting the error message (in hopes that it will make it easier for other drivers that suffer from this issue to be spotted). Link: https://lkml.kernel.org/r/fd67fbac-64bf-f0ea-01e1-5938ccfab9d0@arm.com Reported-by: Jeremy Linton Signed-off-by: Hamza Mahfooz Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 6c90c69e5311..95445bd6eb72 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -567,7 +567,8 @@ static void add_dma_entry(struct dma_debug_entry *entry) pr_err("cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } else if (rc == -EEXIST) { - pr_err("cacheline tracking EEXIST, overlapping mappings aren't supported\n"); + err_printk(entry->dev, entry, + "cacheline tracking EEXIST, overlapping mappings aren't supported\n"); } } From dd47c104533dedb90434a3f142e94a671ac623a6 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Mon, 13 Sep 2021 17:44:15 +0200 Subject: [PATCH 119/866] io-wq: provide IO_WQ_* constants for IORING_REGISTER_IOWQ_MAX_WORKERS arg items The items passed in the array pointed by the arg parameter of IORING_REGISTER_IOWQ_MAX_WORKERS io_uring_register operation carry certain semantics: they refer to different io-wq worker categories; provide IO_WQ_* constants in the UAPI, so these categories can be referenced in the user space code. Suggested-by: Jens Axboe Complements: 2e480058ddc21ec5 ("io-wq: provide a way to limit max number of workers") Signed-off-by: Eugene Syromiatnikov Link: https://lore.kernel.org/r/20210913154415.GA12890@asgard.redhat.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 5 +++++ include/uapi/linux/io_uring.h | 8 +++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index 3d4460df845c..c2e0e8e80949 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -1281,6 +1282,10 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count) { int i, node, prev = 0; + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + for (i = 0; i < 2; i++) { if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) new_count[i] = task_rlimit(current, RLIMIT_NPROC); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 59ef35154e3d..b270a07b285e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -317,13 +317,19 @@ enum { IORING_REGISTER_IOWQ_AFF = 17, IORING_UNREGISTER_IOWQ_AFF = 18, - /* set/get max number of workers */ + /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + /* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; From a69ae291e1cc2d08ae77c2029579c59c9bde5061 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 13 Sep 2021 17:35:47 +0100 Subject: [PATCH 120/866] x86/uaccess: Fix 32-bit __get_user_asm_u64() when CC_HAS_ASM_GOTO_OUTPUT=y Commit 865c50e1d279 ("x86/uaccess: utilize CONFIG_CC_HAS_ASM_GOTO_OUTPUT") added an optimised version of __get_user_asm() for x86 using 'asm goto'. Like the non-optimised code, the 32-bit implementation of 64-bit get_user() expands to a pair of 32-bit accesses. Unlike the non-optimised code, the _original_ pointer is incremented to copy the high word instead of loading through a new pointer explicitly constructed to point at a 32-bit type. Consequently, if the pointer points at a 64-bit type then we end up loading the wrong data for the upper 32-bits. This was observed as a mount() failure in Android targeting i686 after b0cfcdd9b967 ("d_path: make 'prepend()' fill up the buffer exactly on overflow") because the call to copy_from_kernel_nofault() from prepend_copy() ends up in __get_kernel_nofault() and casts the source pointer to a 'u64 __user *'. An attempt to mount at "/debug_ramdisk" therefore ends up failing trying to mount "/debumdismdisk". Use the existing '__gu_ptr' source pointer to unsigned int for 32-bit __get_user_asm_u64() instead of the original pointer. Cc: Bill Wendling Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Peter Zijlstra Reported-by: Greg Kroah-Hartman Fixes: 865c50e1d279 ("x86/uaccess: utilize CONFIG_CC_HAS_ASM_GOTO_OUTPUT") Signed-off-by: Will Deacon Reviewed-by: Nick Desaulniers Tested-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c9fa7be3df82..5c95d242f38d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -301,8 +301,8 @@ do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ - __get_user_asm(__gu_low, ptr, "l", "=r", label); \ - __get_user_asm(__gu_high, ptr+1, "l", "=r", label); \ + __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ + __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else From 76ae847497bc5207c479de5e2ac487270008b19b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:38 -0700 Subject: [PATCH 121/866] Documentation: raise minimum supported version of GCC to 5.1 commit fad7cd3310db ("nbd: add the check to prevent overflow in __nbd_ioctl()") raised an issue from the fallback helpers added in commit f0907827a8a9 ("compiler.h: enable builtin overflow checkers and add fallback code") Specifically, the helpers for checking whether the results of a multiplication overflowed (__unsigned_mul_overflow, __signed_add_overflow) use the division operator when !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW. This is problematic for 64b operands on 32b hosts. Also, because the macro is type agnostic, it is very difficult to write a similarly type generic macro that dispatches to one of: * div64_s64 * div64_u64 * div_s64 * div_u64 Raising the minimum supported versions allows us to remove all of the fallback helpers for !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW, instead dispatching the compiler builtins. arm64 has already raised the minimum supported GCC version to 5.1, do this for all targets now. See the link below for the previous discussion. Link: https://lore.kernel.org/all/20210909182525.372ee687@canb.auug.org.au/ Link: https://lore.kernel.org/lkml/CAK7LNASs6dvU6D3jL2GG3jW58fXfaj6VNOe55NJnTB8UPuk2pA@mail.gmail.com/ Link: https://github.com/ClangBuiltLinux/linux/issues/1438 Reported-by: Stephen Rothwell Reported-by: Nathan Chancellor Suggested-by: Rasmus Villemoes Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- Documentation/process/changes.rst | 2 +- scripts/min-tool-version.sh | 8 +------- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index d3a8557b66a1..e35ab74a0f80 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -29,7 +29,7 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== Program Minimal version Command to check the version ====================== =============== ======================================== -GNU C 4.9 gcc --version +GNU C 5.1 gcc --version Clang/LLVM (optional) 10.0.1 clang --version GNU make 3.81 make --version binutils 2.23 ld -v diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 319f92104f56..4edc708baa63 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -17,13 +17,7 @@ binutils) echo 2.23.0 ;; gcc) - # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 - # https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk - if [ "$SRCARCH" = arm64 ]; then - echo 5.1.0 - else - echo 4.9.0 - fi + echo 5.1.0 ;; icc) # temporary From 4eb6bd55cfb22ffc20652732340c4962f3ac9a91 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:39 -0700 Subject: [PATCH 122/866] compiler.h: drop fallback overflow checkers Once upgrading the minimum supported version of GCC to 5.1, we can drop the fallback code for !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW. This is effectively a revert of commit f0907827a8a9 ("compiler.h: enable builtin overflow checkers and add fallback code") Link: https://github.com/ClangBuiltLinux/linux/issues/1438#issuecomment-916745801 Suggested-by: Rasmus Villemoes Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 13 --- include/linux/compiler-gcc.h | 4 - include/linux/overflow.h | 138 +--------------------------- tools/include/linux/compiler-gcc.h | 4 - tools/include/linux/overflow.h | 140 +---------------------------- 5 files changed, 6 insertions(+), 293 deletions(-) diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49b0ac8b6fd3..3c4de9b6c6e3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -62,19 +62,6 @@ #define __no_sanitize_coverage #endif -/* - * Not all versions of clang implement the type-generic versions - * of the builtin overflow checkers. Fortunately, clang implements - * __has_builtin allowing us to avoid awkward version - * checks. Unfortunately, we don't know which version of gcc clang - * pretends to be, so the macro may or may not be defined. - */ -#if __has_builtin(__builtin_mul_overflow) && \ - __has_builtin(__builtin_add_overflow) && \ - __has_builtin(__builtin_sub_overflow) -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cb9217fc60af..3f7f6fa0e051 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -128,10 +128,6 @@ #define __no_sanitize_coverage #endif -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 0f12345c21fb..4669632bd72b 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -6,12 +6,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) __builtin_mul_overflow(__a, __b, __d); \ })) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d))) - -#define check_sub_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d))) - -#define check_mul_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d))) - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 95c072b70d0e..a590a1dfafd9 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -38,7 +38,3 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 8712ff70995f..dcb0c1bf6866 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -5,12 +5,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -36,8 +33,6 @@ #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) - -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -73,135 +68,6 @@ __builtin_mul_overflow(__a, __b, __d); \ }) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) - -#define check_sub_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) - -#define check_mul_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** * array_size() - Calculate size of 2-dimensional array. * From adac17e3f61f54927b961d97bd303dd5795a307b Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:40 -0700 Subject: [PATCH 123/866] mm/ksm: remove old GCC 4.9+ check The minimum supported version of GCC has been raised to GCC 5.1. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- mm/ksm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/mm/ksm.c b/mm/ksm.c index 025338128cd9..a5716fdec1aa 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -651,10 +651,8 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * from &migrate_nodes. This will verify that future list.h changes * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. */ -#if defined(GCC_VERSION) && GCC_VERSION >= 40903 BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); -#endif if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); From c0a5c81ca9bedaf38356a6290bf895313fd7361c Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:41 -0700 Subject: [PATCH 124/866] Kconfig.debug: drop GCC 5+ version check for DWARF5 Now that the minimum supported version of GCC is 5.1, we no longer need this Kconfig version check for CONFIG_DEBUG_INFO_DWARF5. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ed4a31e34098..d566f601780f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -295,7 +295,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" - depends on GCC_VERSION >= 50000 || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) depends on !DEBUG_INFO_BTF help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc From d20758951f8f28c0ee1b2a8a6bb8189858083895 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:42 -0700 Subject: [PATCH 125/866] riscv: remove Kconfig check for GCC version for ARCH_RV64I The minimum supported version of GCC is now 5.1. The check wasn't correct as written anyways since GCC_VERSION is 0 when CC=clang. Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: linux-riscv@lists.infradead.org Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- arch/riscv/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c79955655fa4..5fc1d0cc82e1 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -235,7 +235,7 @@ config ARCH_RV32I config ARCH_RV64I bool "RV64I" select 64BIT - select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000 + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8) select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL From 6563139d90ad6178a990d051c7980f0998b5d2e8 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:43 -0700 Subject: [PATCH 126/866] powerpc: remove GCC version check for UPD_CONSTR Now that GCC 5.1 is the minimum supported version, we can drop this workaround for older versions of GCC. This adversely affected clang, too. Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Segher Boessenkool Cc: Christophe Leroy Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Nick Desaulniers Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/asm-const.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/arch/powerpc/include/asm/asm-const.h b/arch/powerpc/include/asm/asm-const.h index 0ce2368bd20f..dbfa5e1e3198 100644 --- a/arch/powerpc/include/asm/asm-const.h +++ b/arch/powerpc/include/asm/asm-const.h @@ -12,16 +12,6 @@ # define ASM_CONST(x) __ASM_CONST(x) #endif -/* - * Inline assembly memory constraint - * - * GCC 4.9 doesn't properly handle pre update memory constraint "m<>" - * - */ -#if defined(GCC_VERSION) && GCC_VERSION < 50000 -#define UPD_CONSTR "" -#else #define UPD_CONSTR "<>" -#endif #endif /* _ASM_POWERPC_ASM_CONST_H */ From 42a7ba1695fcd534216aa3712a6cf42da3340527 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:44 -0700 Subject: [PATCH 127/866] arm64: remove GCC version check for ARCH_SUPPORTS_INT128 Now that GCC 5.1 is the minimally supported compiler version, this Kconfig check is no longer necessary. Cc: Catalin Marinas Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 077f2ec4eeb2..5c7ae4c3954b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -86,7 +86,7 @@ config ARM64 select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_SUPPORTS_CFI_CLANG select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG) + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT From 156102fe0bb669f40f2fd27856b21f9fa8157090 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:45 -0700 Subject: [PATCH 128/866] Makefile: drop GCC < 5 -fno-var-tracking-assignments workaround Now that GCC 5.1 is the minimally supported version, we can drop this workaround for older versions of GCC. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- Makefile | 6 ------ 1 file changed, 6 deletions(-) diff --git a/Makefile b/Makefile index 2d1e491f7737..f9ef07f573e0 100644 --- a/Makefile +++ b/Makefile @@ -849,12 +849,6 @@ endif DEBUG_CFLAGS := -# Workaround for GCC versions < 5.0 -# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61801 -ifdef CONFIG_CC_IS_GCC -DEBUG_CFLAGS += $(call cc-ifversion, -lt, 0500, $(call cc-option, -fno-var-tracking-assignments)) -endif - ifdef CONFIG_DEBUG_INFO ifdef CONFIG_DEBUG_INFO_SPLIT From 4e59869aa6550657cb148ad49835605660ec9b88 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:46 -0700 Subject: [PATCH 129/866] compiler-gcc.h: drop checks for older GCC versions Now that GCC 5.1 is the minimally supported default, drop the values we don't use. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 4 +--- tools/include/linux/compiler-gcc.h | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3f7f6fa0e051..fd82ce169ce9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -98,10 +98,8 @@ #if GCC_VERSION >= 70000 #define KASAN_ABI_VERSION 5 -#elif GCC_VERSION >= 50000 +#else #define KASAN_ABI_VERSION 4 -#elif GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 #endif #if __has_attribute(__no_sanitize_address__) diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index a590a1dfafd9..43d9a46d36f0 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,9 +16,7 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#if GCC_VERSION >= 40300 -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* GCC_VERSION >= 40300 */ +#define __compiletime_error(message) __attribute__((error(message))) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) From 6f20fa2dfa549401860479328371f0d5cee9b114 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:47 -0700 Subject: [PATCH 130/866] vmlinux.lds.h: remove old check for GCC 4.9 Now that GCC 5.1 is the minimally supported version of GCC, we can effectively revert commit 85c2ce9104eb ("sched, vmlinux.lds: Increase STRUCT_ALIGNMENT to 64 bytes for GCC-4.9") Cc: Peter Zijlstra Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index aa50bf2959fe..f2984af2b85b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -116,11 +116,7 @@ * GCC 4.5 and later have a 32 bytes section alignment for structures. * Except GCC 4.9, that feels the need to align on 64 bytes. */ -#if __GNUC__ == 4 && __GNUC_MINOR__ == 9 -#define STRUCT_ALIGNMENT 64 -#else #define STRUCT_ALIGNMENT 32 -#endif #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT) /* From 6d2ef226f2f18d530e48ead0cb5704505628b797 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:20:01 -0700 Subject: [PATCH 131/866] compiler_attributes.h: drop __has_attribute() support for gcc4 Now that GCC 5.1 is the minimally supported default, the manual workaround for older gcc versions not having __has_attribute() are no longer relevant and can be removed. Signed-off-by: Linus Torvalds --- include/linux/compiler_attributes.h | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 2487be0e7199..ba417a5c80af 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -20,26 +20,6 @@ * Provide links to the documentation of each supported compiler, if it exists. */ -/* - * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support gcc < 5, we implement __has_attribute - * by hand. - */ -#ifndef __has_attribute -# define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ 1 -# define __GCC4_has_attribute___copy__ 0 -# define __GCC4_has_attribute___designated_init__ 0 -# define __GCC4_has_attribute___externally_visible__ 1 -# define __GCC4_has_attribute___no_caller_saved_registers__ 0 -# define __GCC4_has_attribute___noclone__ 1 -# define __GCC4_has_attribute___no_profile_instrument_function__ 0 -# define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ 1 -# define __GCC4_has_attribute___no_sanitize_undefined__ 1 -# define __GCC4_has_attribute___fallthrough__ 0 -#endif - /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute */ From d9a7e9df731670acdc69e81748941ad338f47fab Mon Sep 17 00:00:00 2001 From: Doug Smythies Date: Sun, 12 Sep 2021 11:50:29 -0700 Subject: [PATCH 132/866] cpufreq: intel_pstate: Override parameters if HWP forced by BIOS If HWP has been already been enabled by BIOS, it may be necessary to override some kernel command line parameters. Once it has been enabled it requires a reset to be disabled. Suggested-by: Rafael J. Wysocki Signed-off-by: Doug Smythies Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1097f826ad70..8c176b7dae41 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3205,11 +3205,15 @@ static int __init intel_pstate_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -ENODEV; - if (no_load) - return -ENODEV; - id = x86_match_cpu(hwp_support_ids); if (id) { + bool hwp_forced = intel_pstate_hwp_is_enabled(); + + if (hwp_forced) + pr_info("HWP enabled by BIOS\n"); + else if (no_load) + return -ENODEV; + copy_cpu_funcs(&core_funcs); /* * Avoid enabling HWP for processors without EPP support, @@ -3219,8 +3223,7 @@ static int __init intel_pstate_init(void) * If HWP is enabled already, though, there is no choice but to * deal with it. */ - if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || - intel_pstate_hwp_is_enabled()) { + if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) { hwp_active++; hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; @@ -3235,7 +3238,11 @@ static int __init intel_pstate_init(void) goto hwp_cpu_matched; } + pr_info("HWP not enabled\n"); } else { + if (no_load) + return -ENODEV; + id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) { pr_info("CPU model not supported\n"); @@ -3314,10 +3321,9 @@ static int __init intel_pstate_setup(char *str) else if (!strcmp(str, "passive")) default_driver = &intel_cpufreq; - if (!strcmp(str, "no_hwp")) { - pr_info("HWP disabled\n"); + if (!strcmp(str, "no_hwp")) no_hwp = 1; - } + if (!strcmp(str, "force")) force_load = 1; if (!strcmp(str, "hwp_only")) From df26327ea097eb78e7967c45df6b23010c43c28d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:29:44 -0700 Subject: [PATCH 133/866] Drop some straggling mentions of gcc-4.9 as being stale Fix up the admin-guide README file to the new gcc-5.1 requirement, and remove a stale comment about gcc support for the __assume_aligned__ attribute. Signed-off-by: Linus Torvalds --- Documentation/admin-guide/README.rst | 2 +- Documentation/translations/zh_CN/admin-guide/README.rst | 2 +- Documentation/translations/zh_TW/admin-guide/README.rst | 2 +- include/linux/compiler_attributes.h | 1 - 4 files changed, 3 insertions(+), 4 deletions(-) diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 35314b63008c..caa3c09a5c3f 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -259,7 +259,7 @@ Configuring the kernel Compiling the kernel -------------------- - - Make sure you have at least gcc 4.9 available. + - Make sure you have at least gcc 5.1 available. For more information, refer to :ref:`Documentation/process/changes.rst `. Please note that you can still run a.out user programs with this kernel. diff --git a/Documentation/translations/zh_CN/admin-guide/README.rst b/Documentation/translations/zh_CN/admin-guide/README.rst index 669a022f6817..980eb20521cf 100644 --- a/Documentation/translations/zh_CN/admin-guide/README.rst +++ b/Documentation/translations/zh_CN/admin-guide/README.rst @@ -223,7 +223,7 @@ Linux内核5.x版本 编译内核 --------- - - 确保您至少有gcc 4.9可用。 + - 确保您至少有gcc 5.1可用。 有关更多信息，请参阅 :ref:`Documentation/process/changes.rst ` 。 请注意，您仍然可以使用此内核运行a.out用户程序。 diff --git a/Documentation/translations/zh_TW/admin-guide/README.rst b/Documentation/translations/zh_TW/admin-guide/README.rst index b752e50359e6..6ce97edbab37 100644 --- a/Documentation/translations/zh_TW/admin-guide/README.rst +++ b/Documentation/translations/zh_TW/admin-guide/README.rst @@ -226,7 +226,7 @@ Linux內核5.x版本 編譯內核 --------- - - 確保您至少有gcc 4.9可用。 + - 確保您至少有gcc 5.1可用。 有關更多信息，請參閱 :ref:`Documentation/process/changes.rst ` 。 請注意，您仍然可以使用此內核運行a.out用戶程序。 diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ba417a5c80af..ee19cebabcf5 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -54,7 +54,6 @@ * compiler should see some alignment anyway, when the return value is * massaged by 'flags = ptr & 3; ptr &= ~3;'). * - * Optional: only supported since gcc >= 4.9 * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute From 3110b942d36b961858664486d72f815d78c956c3 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 13 Sep 2021 16:25:56 -0300 Subject: [PATCH 134/866] IB/qib: Fix clang confusion of NULL pointer comparison clang becomes confused due to the comparison to NULL in a integer constant expression context: >> drivers/infiniband/hw/qib/qib_sysfs.c:413:1: error: static_assert expression is not an integral constant expression QIB_DIAGC_ATTR(rc_resends); ^~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/infiniband/hw/qib/qib_sysfs.c:406:16: note: expanded from macro 'QIB_DIAGC_ATTR' static_assert(&((struct qib_ibport *)0)->rvp.n_##N != (u64 *)NULL); \ Nathan found __same_type that solves this problem nicely, so use it instead. Reported-by: kernel test robot Suggested-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/qib/qib_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 452e2355d24e..0a3b28142c05 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -403,7 +403,7 @@ static ssize_t diagc_attr_store(struct ib_device *ibdev, u32 port_num, } #define QIB_DIAGC_ATTR(N) \ - static_assert(&((struct qib_ibport *)0)->rvp.n_##N != (u64 *)NULL); \ + static_assert(__same_type(((struct qib_ibport *)0)->rvp.n_##N, u64)); \ static struct qib_diagc_attr qib_diagc_attr_##N = { \ .attr = __ATTR(N, 0664, diagc_attr_show, diagc_attr_store), \ .counter = \ From 099dd788e31b4f426ef49c2785069804925a84e1 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 13 Sep 2021 14:51:10 -0500 Subject: [PATCH 135/866] cifs: remove pathname for file from SPDX header checkpatch complains about source files with filenames (e.g. in these cases just below the SPDX header in comments at the top of various files in fs/cifs). It also is helpful to change this now so will be less confusing when the parent directory is renamed e.g. from fs/cifs to fs/smb_client (or fs/smbfs) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cache.c | 2 +- fs/cifs/cifs_debug.c | 1 - fs/cifs/cifs_fs_sb.h | 1 - fs/cifs/cifs_ioctl.h | 1 - fs/cifs/cifs_spnego.c | 2 +- fs/cifs/cifs_spnego.h | 2 +- fs/cifs/cifs_unicode.c | 1 - fs/cifs/cifsacl.c | 1 - fs/cifs/cifsacl.h | 1 - fs/cifs/cifsencrypt.c | 1 - fs/cifs/cifsfs.c | 1 - fs/cifs/cifsfs.h | 1 - fs/cifs/cifsglob.h | 1 - fs/cifs/cifspdu.h | 1 - fs/cifs/cifsproto.h | 1 - fs/cifs/cifssmb.c | 1 - fs/cifs/connect.c | 1 - fs/cifs/dir.c | 1 - fs/cifs/dns_resolve.c | 1 - fs/cifs/dns_resolve.h | 4 ++-- fs/cifs/export.c | 1 - fs/cifs/file.c | 1 - fs/cifs/fscache.c | 2 +- fs/cifs/fscache.h | 2 +- fs/cifs/inode.c | 1 - fs/cifs/ioctl.c | 1 - fs/cifs/link.c | 1 - fs/cifs/misc.c | 1 - fs/cifs/netmisc.c | 1 - fs/cifs/ntlmssp.h | 1 - fs/cifs/readdir.c | 1 - fs/cifs/rfc1002pdu.h | 1 - fs/cifs/sess.c | 1 - fs/cifs/smb2file.c | 1 - fs/cifs/smb2glob.h | 1 - fs/cifs/smb2inode.c | 1 - fs/cifs/smb2misc.c | 1 - fs/cifs/smb2pdu.c | 1 - fs/cifs/smb2pdu.h | 1 - fs/cifs/smb2proto.h | 1 - fs/cifs/smb2status.h | 1 - fs/cifs/smb2transport.c | 1 - fs/cifs/smberr.h | 1 - fs/cifs/transport.c | 1 - fs/cifs/winucase.c | 1 - fs/cifs/xattr.c | 1 - fs/smbfs_common/smbfsctl.h | 2 +- include/uapi/linux/cifs/cifs_mount.h | 1 - 48 files changed, 8 insertions(+), 49 deletions(-) diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 8a3b30ec860c..8be57aaedab6 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cache.c - CIFS filesystem cache index structure definitions + * CIFS filesystem cache index structure definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 51a824fc926a..de2c12bcfa4b 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs_debug.c * * Copyright (C) International Business Machines Corp., 2000,2005 * diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 4fd788586399..f97407520ea1 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_fs_sb.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index ef723be358af..b87cbbe6d2d4 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_ioctl.h * * Structure definitions for io control for cifs/smb3 * diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 8fa26a8530f8..353bd0dd7026 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifs_spnego.c -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index 31387d0ea32e..e6a0451877d4 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_spnego.h -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 171ad8b42107..e7582dd79179 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/cifs_unicode.c * * Copyright (c) International Business Machines Corp., 2000,2009 * Modified by Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 388eb536cff1..ee3aab3dd4ac 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsacl.c * * Copyright (C) International Business Machines Corp., 2007,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index f8292bcf8594..ccbfc754bd3c 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsacl.h * * Copyright (c) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 2e6f40344037..d118282071b3 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsencrypt.c * * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP * for more detailed information diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8c20bfa187ac..9fa930dfd78d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsfs.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d25a4099b32e..b50da1901ebd 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsfs.h * * Copyright (c) International Business Machines Corp., 2002, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c068f7d8d879..7dd9878e26bf 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsglob.h * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 98e8e5aa0613..d2ff438fd31f 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifspdu.h * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f9740c21ca3d..54966c1a8eb6 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsproto.h * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a8e41c1e80ca..243d17696f06 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifssmb.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0db344807ef1..399a0f084573 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/connect.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 5f8a302ffcb2..6e8e7cc26ae2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dir.c * * vfs operations that deal with dentries * diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 8c616aaeb7c4..0458d28d71aa 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dns_resolve.c * * Copyright (c) 2007 Igor Mammedov * Author(s): Igor Mammedov (niallain@gmail.com) diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 9fa2807ef79e..afc0df381246 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/dns_resolve.h -- DNS Resolver upcall management for CIFS DFS - * Handles host name to IP address resolution + * DNS Resolver upcall management for CIFS DFS + * Handles host name to IP address resolution * * Copyright (c) International Business Machines Corp., 2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 747a540db954..37c28415df1e 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/export.c * * Copyright (C) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index d0216472f1c6..4d10c9343890 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/file.c * * vfs operations that deal with files * diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index fab47fa7df74..8eedd20c44ab 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/fscache.c - CIFS filesystem cache interface + * CIFS filesystem cache interface * * Copyright (c) 2010 Novell, Inc. * Author(s): Suresh Jayaraman diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 82e856b9cf89..9baa1d0f22bd 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/fscache.h - CIFS filesystem cache interface definitions + * CIFS filesystem cache interface definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 50c01cff4c84..19af2d0ec8d5 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/inode.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 42c6a0bac6c8..44ae99454fb3 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/ioctl.c * * vfs operations that deal with io control * diff --git a/fs/cifs/link.c b/fs/cifs/link.c index f0a6d63bc08c..852e54ee82c2 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/link.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 9469f1cf0b46..f4313935e734 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/misc.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 0e728aac67e9..fa9fbd6a819c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/netmisc.c * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 378133ce8869..25a2b8ef88b9 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/ntlmssp.h * * Copyright (c) International Business Machines Corp., 2002,2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 54d77c99e21c..1929e80c09ee 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/readdir.c * * Directory search handling * diff --git a/fs/cifs/rfc1002pdu.h b/fs/cifs/rfc1002pdu.h index 137f7c95afd6..ae1d025da294 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/cifs/rfc1002pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/rfc1002pdu.h * * Protocol Data Unit definitions for RFC 1001/1002 support * diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 118403fbeda2..23e02db7923f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/sess.c * * SMB/CIFS session setup handling routines * diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index c9d8a50062b8..f5dcc4940b6d 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2file.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Author(s): Steve French (sfrench@us.ibm.com), diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index d0e9f3782bd9..ca692b2283cd 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2glob.h * * Definitions for various global variables and structures * diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 957b2594f02e..8297703492ee 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2inode.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 668f77108831..29b5554f6263 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2misc.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b6d2e3591927..672ae78e866a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2pdu.c * * Copyright (C) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e9cac7970b66..f32c99c9ba13 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2pdu.h * * Copyright (c) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 263767f644f8..547945443fa7 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2proto.h * * Copyright (c) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 0215ef36e240..a9e958166fc5 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2status.h * * SMB2 Status code (network error) definitions * Definitions are from MS-ERREF diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 6f7952ea4941..f59b956f9d25 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2transport.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smberr.h b/fs/cifs/smberr.h index 60189efb3236..aeffdad829e2 100644 --- a/fs/cifs/smberr.h +++ b/fs/cifs/smberr.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smberr.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 75a95de320cf..b7379329b741 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/transport.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c index 59b6c577aa0a..2f075b5b50df 100644 --- a/fs/cifs/winucase.c +++ b/fs/cifs/winucase.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/winucase.c * * Copyright (c) Jeffrey Layton , 2013 * diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 9ed481e79ce0..7d8b72d67c80 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/xattr.c * * Copyright (c) International Business Machines Corp., 2003, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/smbfs_common/smbfsctl.h b/fs/smbfs_common/smbfsctl.h index d01e8c9d7a31..926f87cd6af0 100644 --- a/fs/smbfs_common/smbfsctl.h +++ b/fs/smbfs_common/smbfsctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions + * SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2013 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/include/uapi/linux/cifs/cifs_mount.h b/include/uapi/linux/cifs/cifs_mount.h index 69829205fdb5..8e87d27b0951 100644 --- a/include/uapi/linux/cifs/cifs_mount.h +++ b/include/uapi/linux/cifs/cifs_mount.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* - * include/uapi/linux/cifs/cifs_mount.h * * Author(s): Scott Lovenberg (scott.lovenberg@gmail.com) * From 7bbc3d385bd813077acaf0e6fdb2a86a901f5382 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 6 Sep 2021 18:26:34 +0200 Subject: [PATCH 136/866] netfilter: ipset: Fix oversized kvmalloc() calls The commit commit 7661809d493b426e979f39ab512e3adf41fbcc69 Author: Linus Torvalds Date: Wed Jul 14 09:45:49 2021 -0700 mm: don't allow oversized kvmalloc() calls limits the max allocatable memory via kvmalloc() to MAX_INT. Apply the same limit in ipset. Reported-by: syzbot+3493b1873fb3ea827986@syzkaller.appspotmail.com Reported-by: syzbot+2b8443c35458a617c904@syzkaller.appspotmail.com Reported-by: syzbot+ee5cb15f4a0e85e0d54e@syzkaller.appspotmail.com Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_gen.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6186358eac7c..6e391308431d 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -130,11 +130,11 @@ htable_size(u8 hbits) { size_t hsize; - /* We must fit both into u32 in jhash and size_t */ + /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) + if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; From d0ee23f9d78be5531c4b055ea424ed0b489dfe9b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 13 Sep 2021 15:09:00 -0700 Subject: [PATCH 137/866] tools: compiler-gcc.h: Guard error attribute use with __has_attribute When building objtool with HOSTCC=clang, there are several errors along the lines of orc_dump.c:201:28: error: unknown attribute 'error' ignored [-Werror,-Wunknown-attributes] This occurs after commit 4e59869aa655 ("compiler-gcc.h: drop checks for older GCC versions"), which removed the GCC_VERSION gating. The removed version check just so happened to prevent __compiletime_error() from being defined with clang because it pretends to be GCC 4.2.1 for compatibility but the error attribute was not added to clang until 14.0.0. Commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") and commit a3f8a30f3f00 ("Compiler Attributes: use feature checks instead of version checks") refactored the handling of attributes in the main kernel to avoid situations like this but that refactoring has never been done for the tools directory. Refactoring is a rather large undertaking and this has never been an issue before so instead, just guard the definition of __compiletime_error() with __has_attribute() so that there are no more errors. Fixes: 4e59869aa655 ("compiler-gcc.h: drop checks for older GCC versions") Signed-off-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- tools/include/linux/compiler-gcc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 43d9a46d36f0..8816f06fc6c7 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,7 +16,9 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#define __compiletime_error(message) __attribute__((error(message))) +#if __has_attribute(__error__) +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) From 69e73dbfda14fbfe748d3812da1244cce2928dcb Mon Sep 17 00:00:00 2001 From: Andrea Claudi Date: Fri, 10 Sep 2021 18:08:39 +0200 Subject: [PATCH 138/866] ipvs: check that ip_vs_conn_tab_bits is between 8 and 20 ip_vs_conn_tab_bits may be provided by the user through the conn_tab_bits module parameter. If this value is greater than 31, or less than 0, the shift operator used to derive tab_size causes undefined behaviour. Fix this checking ip_vs_conn_tab_bits value to be in the range specified in ipvs Kconfig. If not, simply use default value. Fixes: 6f7edb4881bf ("IPVS: Allow boot time change of hash size") Reported-by: Yi Chen Signed-off-by: Andrea Claudi Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_conn.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c100c6b112c8..2c467c422dc6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1468,6 +1468,10 @@ int __init ip_vs_conn_init(void) int idx; /* Compute size and mask */ + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) { + pr_info("conn_tab_bits not in [8, 20]. Using default value\n"); + ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; + } ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; From 0e6491b559704da720f6da09dd0a52c4df44c514 Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Sat, 11 Sep 2021 08:55:57 +0800 Subject: [PATCH 139/866] bpf: Add oversize check before call kvcalloc() Commit 7661809d493b ("mm: don't allow oversized kvmalloc() calls") add the oversize check. When the allocation is larger than what kmalloc() supports, the following warning triggered: WARNING: CPU: 0 PID: 8408 at mm/util.c:597 kvmalloc_node+0x108/0x110 mm/util.c:597 Modules linked in: CPU: 0 PID: 8408 Comm: syz-executor221 Not tainted 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:kvmalloc_node+0x108/0x110 mm/util.c:597 Call Trace: kvmalloc include/linux/mm.h:806 [inline] kvmalloc_array include/linux/mm.h:824 [inline] kvcalloc include/linux/mm.h:829 [inline] check_btf_line kernel/bpf/verifier.c:9925 [inline] check_btf_info kernel/bpf/verifier.c:10049 [inline] bpf_check+0xd634/0x150d0 kernel/bpf/verifier.c:13759 bpf_prog_load kernel/bpf/syscall.c:2301 [inline] __sys_bpf+0x11181/0x126e0 kernel/bpf/syscall.c:4587 __do_sys_bpf kernel/bpf/syscall.c:4691 [inline] __se_sys_bpf kernel/bpf/syscall.c:4689 [inline] __x64_sys_bpf+0x78/0x90 kernel/bpf/syscall.c:4689 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Reported-by: syzbot+f3e749d4c662818ae439@syzkaller.appspotmail.com Signed-off-by: Bixuan Cui Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210911005557.45518-1-cuibixuan@huawei.com --- kernel/bpf/verifier.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 047ac4b4703b..e76b55917905 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9912,6 +9912,8 @@ static int check_btf_line(struct bpf_verifier_env *env, nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; + if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) + return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || From 4c51de1e8f928a5b05248714d832d7d991ac319a Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 13 Sep 2021 18:29:46 -0500 Subject: [PATCH 140/866] cifs: fix incorrect kernel doc comments Correct kernel-doc comments pointed out by the automated kernel test robot. Reported-by: kernel test robot Signed-off-by: Steve French --- fs/cifs/connect.c | 12 ++++++++++-- fs/cifs/ioctl.c | 2 +- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 399a0f084573..7881115cfbee 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1089,7 +1089,7 @@ next_pdu: module_put_and_exit(0); } -/** +/* * Returns true if srcaddr isn't specified and rhs isn't specified, or * if srcaddr is specified and matches the IP address of the rhs argument */ @@ -1549,6 +1549,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx) /** * cifs_setup_ipc - helper to setup the IPC tcon for the session + * @ses: smb session to issue the request on + * @ctx: the superblock configuration context to use for building the + * new tree connection for the IPC (interprocess communication RPC) * * A new IPC connection is made and stored in the session * tcon_ipc. The IPC tcon has the same lifetime as the session. @@ -1604,6 +1607,7 @@ out: /** * cifs_free_ipc - helper to release the session IPC tcon + * @ses: smb session to unmount the IPC from * * Needs to be called everytime a session is destroyed. * @@ -1854,6 +1858,8 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx __attribute__((unused)), /** * cifs_get_smb_ses - get a session matching @ctx data from @server + * @server: server to setup the session to + * @ctx: superblock configuration context to use to setup the session * * This function assumes it is being called from cifs_mount() where we * already got a server reference (server refcount +1). See @@ -2064,6 +2070,8 @@ cifs_put_tcon(struct cifs_tcon *tcon) /** * cifs_get_tcon - get a tcon matching @ctx data from @ses + * @ses: smb session to issue the request on + * @ctx: the superblock configuration context to use for building the * * - tcon refcount is the number of mount points using the tcon. * - ses refcount is the number of tcon using the session. @@ -3029,7 +3037,7 @@ build_unc_path_to_root(const struct smb3_fs_context *ctx, return full_path; } -/** +/* * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb * * If a referral is found, cifs_sb->ctx->mount_options will be (re-)allocated diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 44ae99454fb3..0359b604bdbc 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -358,7 +358,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (pSMBFile == NULL) break; tcon = tlink_tcon(pSMBFile->tlink); - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); + /* caps = le64_to_cpu(tcon->fsUnixInfo.Capability); */ if (get_user(ExtAttrBits, (int __user *)arg)) { rc = -EFAULT; From 8520e224f547cd070c7c8f97b1fc6d58cff7ccaa Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Sep 2021 01:07:57 +0200 Subject: [PATCH 141/866] bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode Fix cgroup v1 interference when non-root cgroup v2 BPF programs are used. Back in the days, commit bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") embedded per-socket cgroup information into sock->sk_cgrp_data and in order to save 8 bytes in struct sock made both mutually exclusive, that is, when cgroup v1 socket tagging (e.g. net_cls/net_prio) is used, then cgroup v2 falls back to the root cgroup in sock_cgroup_ptr() (&cgrp_dfl_root.cgrp). The assumption made was "there is no reason to mix the two and this is in line with how legacy and v2 compatibility is handled" as stated in bd1060a1d671. However, with Kubernetes more widely supporting cgroups v2 as well nowadays, this assumption no longer holds, and the possibility of the v1/v2 mixed mode with the v2 root fallback being hit becomes a real security issue. Many of the cgroup v2 BPF programs are also used for policy enforcement, just to pick _one_ example, that is, to programmatically deny socket related system calls like connect(2) or bind(2). A v2 root fallback would implicitly cause a policy bypass for the affected Pods. In production environments, we have recently seen this case due to various circumstances: i) a different 3rd party agent and/or ii) a container runtime such as [0] in the user's environment configuring legacy cgroup v1 net_cls tags, which triggered implicitly mentioned root fallback. Another case is Kubernetes projects like kind [1] which create Kubernetes nodes in a container and also add cgroup namespaces to the mix, meaning programs which are attached to the cgroup v2 root of the cgroup namespace get attached to a non-root cgroup v2 path from init namespace point of view. And the latter's root is out of reach for agents on a kind Kubernetes node to configure. Meaning, any entity on the node setting cgroup v1 net_cls tag will trigger the bypass despite cgroup v2 BPF programs attached to the namespace root. Generally, this mutual exclusiveness does not hold anymore in today's user environments and makes cgroup v2 usage from BPF side fragile and unreliable. This fix adds proper struct cgroup pointer for the cgroup v2 case to struct sock_cgroup_data in order to address these issues; this implicitly also fixes the tradeoffs being made back then with regards to races and refcount leaks as stated in bd1060a1d671, and removes the fallback, so that cgroup v2 BPF programs always operate as expected. [0] https://github.com/nestybox/sysbox/ [1] https://kind.sigs.k8s.io/ Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Stanislav Fomichev Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20210913230759.2313-1-daniel@iogearbox.net --- include/linux/cgroup-defs.h | 107 +++++++++-------------------------- include/linux/cgroup.h | 22 +------ kernel/cgroup/cgroup.c | 50 ++++------------ net/core/netclassid_cgroup.c | 7 +-- net/core/netprio_cgroup.c | 10 +--- 5 files changed, 41 insertions(+), 155 deletions(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e1c705fdfa7c..db2e147e069f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overridden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7bf60454a313..75c151413fda 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -extern spinlock_t cgroup_sk_update_lock; -#endif - -void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - unsigned long v; - - /* - * @skcd->val is 64bit but the following is safe on 32bit too as we - * just need the lower ulong to be written and read atomically. - */ - v = READ_ONCE(skcd->val); - - if (v & 3) - return &cgrp_dfl_root.cgrp; - - return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; -#else - return (struct cgroup *)(unsigned long)skcd->val; -#endif + return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 881ce1470beb..8afa8690d288 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - -DEFINE_SPINLOCK(cgroup_sk_update_lock); -static bool cgroup_sk_alloc_disabled __read_mostly; - -void cgroup_sk_alloc_disable(void) -{ - if (cgroup_sk_alloc_disabled) - return; - pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); - cgroup_sk_alloc_disabled = true; -} - -#else - -#define cgroup_sk_alloc_disabled false - -#endif - void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) { - skcd->no_refcnt = 1; - return; - } - /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) return; rcu_read_lock(); - while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->val = (unsigned long)cset->dfl_cgrp; + skcd->cgroup = cset->dfl_cgrp; cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); } - rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { - if (skcd->val) { - if (skcd->no_refcnt) - return; - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); - } + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); - if (skcd->no_refcnt) - return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index b49c57d35a88..1a6a86693b74 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -71,11 +71,8 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n) struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + if (sock) sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); - spin_unlock(&cgroup_sk_update_lock); - } if (--ctx->batch == 0) { ctx->batch = UPDATE_CLASSID_BATCH; return n + 1; @@ -121,8 +118,6 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, struct css_task_iter it; struct task_struct *p; - cgroup_sk_alloc_disable(); - cs->classid = (u32)value; css_task_iter_start(css, 0, &it); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 99a431c56f23..8456dfbe2eb4 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -207,8 +207,6 @@ static ssize_t write_priomap(struct kernfs_open_file *of, if (!dev) return -ENODEV; - cgroup_sk_alloc_disable(); - rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); @@ -221,12 +219,10 @@ static ssize_t write_priomap(struct kernfs_open_file *of, static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + + if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); - spin_unlock(&cgroup_sk_update_lock); - } return 0; } @@ -235,8 +231,6 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; - cgroup_sk_alloc_disable(); - cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; From d8079d8026f82e4435445297d1b77bba1c4c7960 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Sep 2021 01:07:58 +0200 Subject: [PATCH 142/866] bpf, selftests: Add cgroup v1 net_cls classid helpers Minimal set of helpers for net_cls classid cgroupv1 management in order to set an id, join from a process, initiate setup and teardown. cgroupv2 helpers are left as-is, but reused where possible. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210913230759.2313-2-daniel@iogearbox.net --- tools/testing/selftests/bpf/cgroup_helpers.c | 137 +++++++++++++++++-- tools/testing/selftests/bpf/cgroup_helpers.h | 20 ++- 2 files changed, 143 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 033051717ba5..f3daa44a8266 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -12,27 +12,36 @@ #include #include - #include "cgroup_helpers.h" /* * To avoid relying on the system setup, when setup_cgroup_env is called - * we create a new mount namespace, and cgroup namespace. The cgroup2 - * root is mounted at CGROUP_MOUNT_PATH + * we create a new mount namespace, and cgroup namespace. The cgroupv2 + * root is mounted at CGROUP_MOUNT_PATH. Unfortunately, most people don't + * have cgroupv2 enabled at this point in time. It's easier to create our + * own mount namespace and manage it ourselves. We assume /mnt exists. * - * Unfortunately, most people don't have cgroupv2 enabled at this point in time. - * It's easier to create our own mount namespace and manage it ourselves. - * - * We assume /mnt exists. + * Related cgroupv1 helpers are named *classid*(), since we only use the + * net_cls controller for tagging net_cls.classid. We assume the default + * mount under /sys/fs/cgroup/net_cls, which should be the case for the + * vast majority of users. */ #define WALK_FD_LIMIT 16 + #define CGROUP_MOUNT_PATH "/mnt" +#define CGROUP_MOUNT_DFLT "/sys/fs/cgroup" +#define NETCLS_MOUNT_PATH CGROUP_MOUNT_DFLT "/net_cls" #define CGROUP_WORK_DIR "/cgroup-test-work-dir" + #define format_cgroup_path(buf, path) \ snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \ CGROUP_WORK_DIR, path) +#define format_classid_path(buf) \ + snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ + CGROUP_WORK_DIR) + /** * enable_all_controllers() - Enable all available cgroup v2 controllers * @@ -139,8 +148,7 @@ static int nftwfunc(const char *filename, const struct stat *statptr, return 0; } - -static int join_cgroup_from_top(char *cgroup_path) +static int join_cgroup_from_top(const char *cgroup_path) { char cgroup_procs_path[PATH_MAX + 1]; pid_t pid = getpid(); @@ -313,3 +321,114 @@ int cgroup_setup_and_join(const char *path) { } return cg_fd; } + +/** + * setup_classid_environment() - Setup the cgroupv1 net_cls environment + * + * After calling this function, cleanup_classid_environment should be called + * once testing is complete. + * + * This function will print an error to stderr and return 1 if it is unable + * to setup the cgroup environment. If setup is successful, 0 is returned. + */ +int setup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + + if (mount("tmpfs", CGROUP_MOUNT_DFLT, "tmpfs", 0, NULL) && + errno != EBUSY) { + log_err("mount cgroup base"); + return 1; + } + + if (mkdir(NETCLS_MOUNT_PATH, 0777) && errno != EEXIST) { + log_err("mkdir cgroup net_cls"); + return 1; + } + + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && + errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + cleanup_classid_environment(); + + if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) { + log_err("mkdir cgroup work dir"); + return 1; + } + + return 0; +} + +/** + * set_classid() - Set a cgroupv1 net_cls classid + * @id: the numeric classid + * + * Writes the passed classid into the cgroup work dir's net_cls.classid + * file in order to later on trigger socket tagging. + * + * On success, it returns 0, otherwise on failure it returns 1. If there + * is a failure, it prints the error to stderr. + */ +int set_classid(unsigned int id) +{ + char cgroup_workdir[PATH_MAX - 42]; + char cgroup_classid_path[PATH_MAX + 1]; + int fd, rc = 0; + + format_classid_path(cgroup_workdir); + snprintf(cgroup_classid_path, sizeof(cgroup_classid_path), + "%s/net_cls.classid", cgroup_workdir); + + fd = open(cgroup_classid_path, O_WRONLY); + if (fd < 0) { + log_err("Opening cgroup classid: %s", cgroup_classid_path); + return 1; + } + + if (dprintf(fd, "%u\n", id) < 0) { + log_err("Setting cgroup classid"); + rc = 1; + } + + close(fd); + return rc; +} + +/** + * join_classid() - Join a cgroupv1 net_cls classid + * + * This function expects the cgroup work dir to be already created, as we + * join it here. This causes the process sockets to be tagged with the given + * net_cls classid. + * + * On success, it returns 0, otherwise on failure it returns 1. + */ +int join_classid(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return join_cgroup_from_top(cgroup_workdir); +} + +/** + * cleanup_classid_environment() - Cleanup the cgroupv1 net_cls environment + * + * At call time, it moves the calling process to the root cgroup, and then + * runs the deletion process. + * + * On failure, it will print an error to stderr, and try to continue. + */ +void cleanup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + join_cgroup_from_top(NETCLS_MOUNT_PATH); + nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT); +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 5fe3d88e4f0d..629da3854b3e 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_HELPERS_H #define __CGROUP_HELPERS_H + #include #include @@ -8,12 +9,21 @@ #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) - +/* cgroupv2 related */ int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); -int join_cgroup(const char *path); -int setup_cgroup_environment(void); -void cleanup_cgroup_environment(void); unsigned long long get_cgroup_id(const char *path); -#endif +int join_cgroup(const char *path); + +int setup_cgroup_environment(void); +void cleanup_cgroup_environment(void); + +/* cgroupv1 related */ +int set_classid(unsigned int id); +int join_classid(void); + +int setup_classid_environment(void); +void cleanup_classid_environment(void); + +#endif /* __CGROUP_HELPERS_H */ From 43d2b88c29f2d120b4dc22f27b3483eb14bd9815 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Sep 2021 01:07:59 +0200 Subject: [PATCH 143/866] bpf, selftests: Add test case for mixed cgroup v1/v2 Minimal selftest which implements a small BPF policy program to the connect(2) hook which rejects TCP connection requests to port 60123 with EPERM. This is being attached to a non-root cgroup v2 path. The test asserts that this works under cgroup v2-only and under a mixed cgroup v1/v2 environment where net_classid is set in the former case. Before fix: # ./test_progs -t cgroup_v1v2 test_cgroup_v1v2:PASS:server_fd 0 nsec test_cgroup_v1v2:PASS:client_fd 0 nsec test_cgroup_v1v2:PASS:cgroup_fd 0 nsec test_cgroup_v1v2:PASS:server_fd 0 nsec run_test:PASS:skel_open 0 nsec run_test:PASS:prog_attach 0 nsec test_cgroup_v1v2:PASS:cgroup-v2-only 0 nsec run_test:PASS:skel_open 0 nsec run_test:PASS:prog_attach 0 nsec run_test:PASS:join_classid 0 nsec (network_helpers.c:219: errno: None) Unexpected success to connect to server test_cgroup_v1v2:FAIL:cgroup-v1v2 unexpected error: -1 (errno 0) #27 cgroup_v1v2:FAIL Summary: 0/0 PASSED, 0 SKIPPED, 1 FAILED After fix: # ./test_progs -t cgroup_v1v2 #27 cgroup_v1v2:OK Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210913230759.2313-3-daniel@iogearbox.net --- tools/testing/selftests/bpf/network_helpers.c | 27 +++++-- tools/testing/selftests/bpf/network_helpers.h | 1 + .../selftests/bpf/prog_tests/cgroup_v1v2.c | 79 +++++++++++++++++++ .../selftests/bpf/progs/connect4_dropper.c | 26 ++++++ 4 files changed, 127 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c create mode 100644 tools/testing/selftests/bpf/progs/connect4_dropper.c diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 7e9f6375757a..6db1af8fdee7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -208,11 +208,26 @@ error_close: static int connect_fd_to_addr(int fd, const struct sockaddr_storage *addr, - socklen_t addrlen) + socklen_t addrlen, const bool must_fail) { - if (connect(fd, (const struct sockaddr *)addr, addrlen)) { - log_err("Failed to connect to server"); - return -1; + int ret; + + errno = 0; + ret = connect(fd, (const struct sockaddr *)addr, addrlen); + if (must_fail) { + if (!ret) { + log_err("Unexpected success to connect to server"); + return -1; + } + if (errno != EPERM) { + log_err("Unexpected error from connect to server"); + return -1; + } + } else { + if (ret) { + log_err("Failed to connect to server"); + return -1; + } } return 0; @@ -257,7 +272,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) strlen(opts->cc) + 1)) goto error_close; - if (connect_fd_to_addr(fd, &addr, addrlen)) + if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) goto error_close; return fd; @@ -289,7 +304,7 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) return -1; } - if (connect_fd_to_addr(client_fd, &addr, len)) + if (connect_fd_to_addr(client_fd, &addr, len, false)) return -1; return 0; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index da7e132657d5..d198181a5648 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -20,6 +20,7 @@ typedef __u16 __sum16; struct network_helper_opts { const char *cc; int timeout_ms; + bool must_fail; }; /* ipv4 test vector */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c new file mode 100644 index 000000000000..ab3b9bc5e6d1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#include "connect4_dropper.skel.h" + +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int run_test(int cgroup_fd, int server_fd, bool classid) +{ + struct network_helper_opts opts = { + .must_fail = true, + }; + struct connect4_dropper *skel; + int fd, err = 0; + + skel = connect4_dropper__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return -1; + + skel->links.connect_v4_dropper = + bpf_program__attach_cgroup(skel->progs.connect_v4_dropper, + cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.connect_v4_dropper, "prog_attach")) { + err = -1; + goto out; + } + + if (classid && !ASSERT_OK(join_classid(), "join_classid")) { + err = -1; + goto out; + } + + fd = connect_to_fd_opts(server_fd, &opts); + if (fd < 0) + err = -1; + else + close(fd); +out: + connect4_dropper__destroy(skel); + return err; +} + +void test_cgroup_v1v2(void) +{ + struct network_helper_opts opts = {}; + int server_fd, client_fd, cgroup_fd; + static const int port = 60123; + + /* Step 1: Check base connectivity works without any BPF. */ + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) + return; + client_fd = connect_to_fd_opts(server_fd, &opts); + if (!ASSERT_GE(client_fd, 0, "client_fd")) { + close(server_fd); + return; + } + close(client_fd); + close(server_fd); + + /* Step 2: Check BPF policy prog attached to cgroups drops connectivity. */ + cgroup_fd = test__join_cgroup("/connect_dropper"); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + return; + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) { + close(cgroup_fd); + return; + } + ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only"); + setup_classid_environment(); + set_classid(42); + ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2"); + cleanup_classid_environment(); + close(server_fd); + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c new file mode 100644 index 000000000000..b565d997810a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#include +#include + +#include + +#include +#include + +#define VERDICT_REJECT 0 +#define VERDICT_PROCEED 1 + +SEC("cgroup/connect4") +int connect_v4_dropper(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_STREAM) + return VERDICT_PROCEED; + if (ctx->user_port == bpf_htons(60123)) + return VERDICT_REJECT; + return VERDICT_PROCEED; +} + +char _license[] SEC("license") = "GPL"; From 41d3a6bd1d37149b18331fc4bb789c5456a7aeb0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 13 Sep 2021 13:08:51 -0600 Subject: [PATCH 144/866] io_uring: pin SQPOLL data before unlocking ring lock We need to re-check sqd->thread after we've dropped the lock. Pin the sqd before doing the lockdep lock dance, and check if the thread is alive after that. It's either NULL or alive, as the SQPOLL thread cannot exit without holding the same sqd->lock. Reported-and-tested-by: syzbot+337de45f13a4fd54d708@syzkaller.appspotmail.com Fixes: fa84693b3c89 ("io_uring: ensure IORING_REGISTER_IOWQ_MAX_WORKERS works with SQPOLL") Signed-off-by: Jens Axboe --- fs/io_uring.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 66a7414c3756..a864a94364c6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -10563,10 +10563,12 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, * ordering. Fine to drop uring_lock here, we hold * a ref to the ctx. */ + refcount_inc(&sqd->refs); mutex_unlock(&ctx->uring_lock); mutex_lock(&sqd->lock); mutex_lock(&ctx->uring_lock); - tctx = sqd->thread->io_uring; + if (sqd->thread) + tctx = sqd->thread->io_uring; } } else { tctx = current->io_uring; @@ -10580,16 +10582,20 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, if (ret) goto err; - if (sqd) + if (sqd) { mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } if (copy_to_user(arg, new_count, sizeof(new_count))) return -EFAULT; return 0; err: - if (sqd) + if (sqd) { mutex_unlock(&sqd->lock); + io_put_sq_data(sqd); + } return ret; } From 6a2ea0d34af1ca807d5ba6a8350a037ff3cd35cc Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 17 Aug 2021 16:55:31 -0700 Subject: [PATCH 145/866] scsi: st: Add missing break in switch statement in st_ioctl() Clang + -Wimplicit-fallthrough warns: drivers/scsi/st.c:3831:2: warning: unannotated fall-through between switch labels [-Wimplicit-fallthrough] default: ^ drivers/scsi/st.c:3831:2: note: insert 'break;' to avoid fall-through default: ^ break; 1 warning generated. Clang's -Wimplicit-fallthrough is a little bit more pedantic than GCC's, requiring every case block to end in break, return, or fallthrough, rather than allowing implicit fallthroughs to cases that just contain break or return. Add a break so that there is no more warning, as has been done all over the tree already. Link: https://lore.kernel.org/r/20210817235531.172995-1-nathan@kernel.org Fixes: 2e27f576abc6 ("scsi: scsi_ioctl: Call scsi_cmd_ioctl() from scsi_ioctl()") Reviewed-by: Gustavo A. R. Silva Signed-off-by: Nathan Chancellor Signed-off-by: Martin K. Petersen --- drivers/scsi/st.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 9d04929f03a1..ae8636d3780b 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -3823,6 +3823,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) case CDROM_SEND_PACKET: if (!capable(CAP_SYS_RAWIO)) return -EPERM; + break; default: break; } From 96fafe7c6523886308605d30ec92c7936abe7c2c Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 30 Aug 2021 16:10:50 -0700 Subject: [PATCH 146/866] scsi: elx: efct: Fix void-pointer-to-enum-cast warning for efc_nport_topology The kernel test robot flagged an warning for ".../efc_device.c:932:6: warning: cast to smaller integer type 'enum efc_nport_topology' from 'void *'" For the topology events, the "arg" field is generically defined as a void * and is used to pass different arguments. Most of the arguments are pointers to data structures. But for the EFC_EVT_NPORT_TOPOLOGY_NOTIFY event, the argument is an enum value, and the code is typecasting the void * to an enum generating the warning. Fix by converting the EFC_EVT_NPORT_TOPOLOGY_NOTIFY event to pass a pointer to the enum, thus it's a straight-forward pointer dereference in the event handler. Link: https://lore.kernel.org/r/20210830231050.5951-1-jsmart2021@gmail.com Fixes: 202bfdffae27 ("scsi: elx: libefc: FC node ELS and state handling") Reported-by: kernel test robot Co-developed-by: Ram Vegesna Signed-off-by: Ram Vegesna Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/elx/libefc/efc_device.c | 7 +++---- drivers/scsi/elx/libefc/efc_fabric.c | 3 +-- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/elx/libefc/efc_device.c b/drivers/scsi/elx/libefc/efc_device.c index 725ca2a23fb2..52be01333c6e 100644 --- a/drivers/scsi/elx/libefc/efc_device.c +++ b/drivers/scsi/elx/libefc/efc_device.c @@ -928,22 +928,21 @@ __efc_d_wait_topology_notify(struct efc_sm_ctx *ctx, break; case EFC_EVT_NPORT_TOPOLOGY_NOTIFY: { - enum efc_nport_topology topology = - (enum efc_nport_topology)arg; + enum efc_nport_topology *topology = arg; WARN_ON(node->nport->domain->attached); WARN_ON(node->send_ls_acc != EFC_NODE_SEND_LS_ACC_PLOGI); node_printf(node, "topology notification, topology=%d\n", - topology); + *topology); /* At the time the PLOGI was received, the topology was unknown, * so we didn't know which node would perform the domain attach: * 1. The node from which the PLOGI was sent (p2p) or * 2. The node to which the FLOGI was sent (fabric). */ - if (topology == EFC_NPORT_TOPO_P2P) { + if (*topology == EFC_NPORT_TOPO_P2P) { /* if this is p2p, need to attach to the domain using * the d_id from the PLOGI received */ diff --git a/drivers/scsi/elx/libefc/efc_fabric.c b/drivers/scsi/elx/libefc/efc_fabric.c index d397220d9e54..3270ce40196c 100644 --- a/drivers/scsi/elx/libefc/efc_fabric.c +++ b/drivers/scsi/elx/libefc/efc_fabric.c @@ -107,7 +107,6 @@ void efc_fabric_notify_topology(struct efc_node *node) { struct efc_node *tmp_node; - enum efc_nport_topology topology = node->nport->topology; unsigned long index; /* @@ -118,7 +117,7 @@ efc_fabric_notify_topology(struct efc_node *node) if (tmp_node != node) { efc_node_post_event(tmp_node, EFC_EVT_NPORT_TOPOLOGY_NOTIFY, - (void *)topology); + &node->nport->topology); } } } From 59936430e6a6acb0ef943e9306506b2e9c2e45a8 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 30 Aug 2021 16:12:43 -0700 Subject: [PATCH 147/866] scsi: lpfc: Fix CPU to/from endian warnings introduced by ELS processing The kernel test robot reported the following sparse warning: ".../lpfc_els.c:3984:25: sparse: sparse: cast from restricted __be16" For the error being flagged, using be32_to_cpu() on a be16 data type, it was simple enough. But a review of other elements and warnings were also evaluated. This patch corrected several items in the original patch: - Using be32_to_cpu() on a be16 data type - cpu_to_le32() used on a std uint32_t (CPU) data type. Note: This is a byte array, but stored in LE layout by hardware at 32-bit boundaries. So it possibly needed conversion. - Using cpu_to_le32() on a std uint16_t and assigned to a char typeA - Using le32_to_cpu() on a le16 type - Missing cpu_to_le16() on an assignment Link: https://lore.kernel.org/r/20210830231243.6227-1-jsmart2021@gmail.com Fixes: 9064aeb2df8e ("scsi: lpfc: Add EDC ELS support") Reported-by: kernel test robot Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_els.c | 8 ++++---- drivers/scsi/lpfc/lpfc_hw4.h | 2 +- drivers/scsi/lpfc/lpfc_init.c | 16 ++++++++-------- drivers/scsi/lpfc/lpfc_sli.c | 5 +++-- 4 files changed, 16 insertions(+), 15 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index 1254a575fd47..f3fc79b99165 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -4015,11 +4015,11 @@ lpfc_cmpl_els_edc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, be32_to_cpu(pcgd->desc_tag), be32_to_cpu(pcgd->desc_len), be32_to_cpu(pcgd->xmt_signal_capability), - be32_to_cpu(pcgd->xmt_signal_frequency.count), - be32_to_cpu(pcgd->xmt_signal_frequency.units), + be16_to_cpu(pcgd->xmt_signal_frequency.count), + be16_to_cpu(pcgd->xmt_signal_frequency.units), be32_to_cpu(pcgd->rcv_signal_capability), - be32_to_cpu(pcgd->rcv_signal_frequency.count), - be32_to_cpu(pcgd->rcv_signal_frequency.units)); + be16_to_cpu(pcgd->rcv_signal_frequency.count), + be16_to_cpu(pcgd->rcv_signal_frequency.units)); /* Compare driver and Fport capabilities and choose * least common. diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 79a4872c2edb..7359505e6041 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -1167,7 +1167,7 @@ struct lpfc_mbx_read_object { /* Version 0 */ #define lpfc_mbx_rd_object_rlen_MASK 0x00FFFFFF #define lpfc_mbx_rd_object_rlen_WORD word0 uint32_t rd_object_offset; - uint32_t rd_object_name[LPFC_MBX_OBJECT_NAME_LEN_DW]; + __le32 rd_object_name[LPFC_MBX_OBJECT_NAME_LEN_DW]; #define LPFC_OBJ_NAME_SZ 104 /* 26 x sizeof(uint32_t) is 104. */ uint32_t rd_object_cnt; struct lpfc_mbx_host_buf rd_object_hbuf[4]; diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 0ec322f0e3cb..597e5a1ef060 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -5518,7 +5518,7 @@ lpfc_cgn_update_stat(struct lpfc_hba *phba, uint32_t dtag) if (phba->cgn_fpin_frequency && phba->cgn_fpin_frequency != LPFC_FPIN_INIT_FREQ) { value = LPFC_CGN_TIMER_TO_MIN / phba->cgn_fpin_frequency; - cp->cgn_stat_npm = cpu_to_le32(value); + cp->cgn_stat_npm = value; } value = lpfc_cgn_calc_crc32(cp, LPFC_CGN_INFO_SZ, LPFC_CGN_CRC32_SEED); @@ -5547,9 +5547,9 @@ lpfc_cgn_save_evt_cnt(struct lpfc_hba *phba) uint32_t mbps; uint32_t dvalue, wvalue, lvalue, avalue; uint64_t latsum; - uint16_t *ptr; - uint32_t *lptr; - uint16_t *mptr; + __le16 *ptr; + __le32 *lptr; + __le16 *mptr; /* Make sure we have a congestion info buffer */ if (!phba->cgn_i) @@ -5570,7 +5570,7 @@ lpfc_cgn_save_evt_cnt(struct lpfc_hba *phba) if (phba->cgn_fpin_frequency && phba->cgn_fpin_frequency != LPFC_FPIN_INIT_FREQ) { value = LPFC_CGN_TIMER_TO_MIN / phba->cgn_fpin_frequency; - cp->cgn_stat_npm = cpu_to_le32(value); + cp->cgn_stat_npm = value; } /* Read and clear the latency counters for this minute */ @@ -5753,7 +5753,7 @@ lpfc_cgn_save_evt_cnt(struct lpfc_hba *phba) dvalue += le32_to_cpu(cp->cgn_drvr_hr[i]); wvalue += le32_to_cpu(cp->cgn_warn_hr[i]); lvalue += le32_to_cpu(cp->cgn_latency_hr[i]); - mbps += le32_to_cpu(cp->cgn_bw_hr[i]); + mbps += le16_to_cpu(cp->cgn_bw_hr[i]); avalue += le32_to_cpu(cp->cgn_alarm_hr[i]); } if (lvalue) /* Avg of latency averages */ @@ -13411,8 +13411,8 @@ lpfc_init_congestion_buf(struct lpfc_hba *phba) /* last used Index initialized to 0xff already */ - cp->cgn_warn_freq = LPFC_FPIN_INIT_FREQ; - cp->cgn_alarm_freq = LPFC_FPIN_INIT_FREQ; + cp->cgn_warn_freq = cpu_to_le16(LPFC_FPIN_INIT_FREQ); + cp->cgn_alarm_freq = cpu_to_le16(LPFC_FPIN_INIT_FREQ); crc = lpfc_cgn_calc_crc32(cp, LPFC_CGN_INFO_SZ, LPFC_CGN_CRC32_SEED); cp->cgn_info_crc = cpu_to_le32(crc); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index ffd8a140638c..78ce38d7251c 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -22090,6 +22090,7 @@ lpfc_read_object(struct lpfc_hba *phba, char *rdobject, uint32_t *datap, uint32_t shdr_status, shdr_add_status; union lpfc_sli4_cfg_shdr *shdr; struct lpfc_dmabuf *pcmd; + u32 rd_object_name[LPFC_MBX_OBJECT_NAME_LEN_DW] = {0}; /* sanity check on queue memory */ if (!datap) @@ -22113,10 +22114,10 @@ lpfc_read_object(struct lpfc_hba *phba, char *rdobject, uint32_t *datap, memset((void *)read_object->u.request.rd_object_name, 0, LPFC_OBJ_NAME_SZ); - sprintf((uint8_t *)read_object->u.request.rd_object_name, rdobject); + scnprintf((char *)rd_object_name, sizeof(rd_object_name), rdobject); for (j = 0; j < strlen(rdobject); j++) read_object->u.request.rd_object_name[j] = - cpu_to_le32(read_object->u.request.rd_object_name[j]); + cpu_to_le32(rd_object_name[j]); pcmd = kmalloc(sizeof(*pcmd), GFP_KERNEL); if (pcmd) From 37e384095f20cca728500fe5344cd308aa6fd7ff Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 7 Sep 2021 22:09:27 -0700 Subject: [PATCH 148/866] scsi: lpfc: Fix compilation errors on kernels with no CONFIG_DEBUG_FS The Kernel test robot flagged the following warning: ".../lpfc_init.c:7788:35: error: 'struct lpfc_sli4_hba' has no member named 'c_stat'" Reviewing this issue highlighted that one of the recent patches caused the driver to no longer compile cleanly if CONFIG_DEBUG_FS is not set. Correct the different areas that are failing to compile. Link: https://lore.kernel.org/r/20210908050927.37275-1-jsmart2021@gmail.com Fixes: 02243836ad6f ("scsi: lpfc: Add support for the CM framework") Reviewed-by: Nathan Chancellor Build-tested-by: Nathan Chancellor Co-developed-by: Justin Tee Signed-off-by: Justin Tee Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 4 ++-- drivers/scsi/lpfc/lpfc_nvme.c | 2 -- drivers/scsi/lpfc/lpfc_scsi.c | 6 +----- 3 files changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 597e5a1ef060..195169badb37 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -8277,11 +8277,11 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) return 0; out_free_hba_hdwq_info: - free_percpu(phba->sli4_hba.c_stat); #ifdef CONFIG_SCSI_LPFC_DEBUG_FS + free_percpu(phba->sli4_hba.c_stat); out_free_hba_idle_stat: - kfree(phba->sli4_hba.idle_stat); #endif + kfree(phba->sli4_hba.idle_stat); out_free_hba_eq_info: free_percpu(phba->sli4_hba.eq_info); out_free_hba_cpu_map: diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 73a3568ff17e..479b3eed6208 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1489,9 +1489,7 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, struct lpfc_nvme_qhandle *lpfc_queue_info; struct lpfc_nvme_fcpreq_priv *freqpriv; struct nvme_common_command *sqe; -#ifdef CONFIG_SCSI_LPFC_DEBUG_FS uint64_t start = 0; -#endif /* Validate pointers. LLDD fault handling with transport does * have timing races. diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 0fde1e874c7a..63d8ac9f68a7 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5578,12 +5578,8 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device)); int err, idx; u8 *uuid = NULL; -#ifdef CONFIG_SCSI_LPFC_DEBUG_FS - uint64_t start = 0L; + uint64_t start; - if (phba->ktime_on) - start = ktime_get_ns(); -#endif start = ktime_get_ns(); rdata = lpfc_rport_data_from_scsi_device(cmnd->device); From 5d1e15108b8d058d537f19cdef4170d2ae4eed08 Mon Sep 17 00:00:00 2001 From: Chi Minghao Date: Tue, 31 Aug 2021 04:40:58 -0700 Subject: [PATCH 149/866] scsi: lpfc: Remove unneeded variable Fix the following coccicheck REVIEW: ./drivers/scsi/lpfc/lpfc_scsi.c:1498:9-12 REVIEW Unneeded variable Link: https://lore.kernel.org/r/20210831114058.17817-1-lv.ruyi@zte.com.cn Reported-by: Zeal Robot Reviewed-by: James Smart Signed-off-by: Chi Minghao Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_scsi.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 63d8ac9f68a7..befdf864c43b 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1495,7 +1495,6 @@ static int lpfc_bg_err_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc, uint8_t *txop, uint8_t *rxop) { - uint8_t ret = 0; if (sc->prot_flags & SCSI_PROT_IP_CHECKSUM) { switch (scsi_get_prot_op(sc)) { @@ -1548,7 +1547,7 @@ lpfc_bg_err_opcodes(struct lpfc_hba *phba, struct scsi_cmnd *sc, } } - return ret; + return 0; } #endif From 65ef27f7798b57138351d28fd2f61f2afa164400 Mon Sep 17 00:00:00 2001 From: ChanWoo Lee Date: Wed, 1 Sep 2021 11:56:17 +0900 Subject: [PATCH 150/866] scsi: ufs: ufshpb: Remove unused parameters The following parameters are not used in the function. Remove them. *func(): ufshpb_set_hpb_read_to_upiu -> struct ufshpb_lu *hpb -> u32 lpn Link: https://lore.kernel.org/r/20210901025617.31174-1-cw9316.lee@samsung.com Reviewed-by: Daejun Park Reviewed-by: Bart Van Assche Signed-off-by: ChanWoo Lee Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshpb.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 02fb51ae8b25..589af5f6b940 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -333,9 +333,8 @@ ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx, } static void -ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshpb_lu *hpb, - struct ufshcd_lrb *lrbp, u32 lpn, __be64 ppn, - u8 transfer_len, int read_id) +ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, + __be64 ppn, u8 transfer_len, int read_id) { unsigned char *cdb = lrbp->cmd->cmnd; __be64 ppn_tmp = ppn; @@ -703,8 +702,7 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) } } - ufshpb_set_hpb_read_to_upiu(hba, hpb, lrbp, lpn, ppn, transfer_len, - read_id); + ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len, read_id); hpb->stats.hit_cnt++; return 0; From 4e28550829258f7dab97383acaa477bd724c0ff4 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Wed, 1 Sep 2021 16:53:36 +0800 Subject: [PATCH 151/866] scsi: iscsi: Adjust iface sysfs attr detection ISCSI_NET_PARAM_IFACE_ENABLE belongs to enum iscsi_net_param instead of iscsi_iface_param so move it to ISCSI_NET_PARAM. Otherwise, when we call into the driver, we might not match and return that we don't want attr visible in sysfs. Found in code review. Link: https://lore.kernel.org/r/20210901085336.2264295-1-libaokun1@huawei.com Fixes: e746f3451ec7 ("scsi: iscsi: Fix iface sysfs attr detection") Reviewed-by: Lee Duncan Signed-off-by: Baokun Li Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index d8b05d8b5470..922e4c7bd88e 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -441,9 +441,7 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj, struct iscsi_transport *t = iface->transport; int param = -1; - if (attr == &dev_attr_iface_enabled.attr) - param = ISCSI_NET_PARAM_IFACE_ENABLE; - else if (attr == &dev_attr_iface_def_taskmgmt_tmo.attr) + if (attr == &dev_attr_iface_def_taskmgmt_tmo.attr) param = ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO; else if (attr == &dev_attr_iface_header_digest.attr) param = ISCSI_IFACE_PARAM_HDRDGST_EN; @@ -483,7 +481,9 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj, if (param != -1) return t->attr_is_visible(ISCSI_IFACE_PARAM, param); - if (attr == &dev_attr_iface_vlan_id.attr) + if (attr == &dev_attr_iface_enabled.attr) + param = ISCSI_NET_PARAM_IFACE_ENABLE; + else if (attr == &dev_attr_iface_vlan_id.attr) param = ISCSI_NET_PARAM_VLAN_ID; else if (attr == &dev_attr_iface_vlan_priority.attr) param = ISCSI_NET_PARAM_VLAN_PRIORITY; From e4953a93104c1fb1ef7989541f9867cc276467f9 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Wed, 1 Sep 2021 20:55:42 +0530 Subject: [PATCH 152/866] scsi: mpt3sas: Call cpu_relax() before calling udelay() Call cpu_relax() while waiting for the current blk-mq polling instance to complete. Link: https://lore.kernel.org/r/20210901152542.27866-1-sreekanth.reddy@broadcom.com Reviewed-by: Bart Van Assche Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 6c82435bc9cc..27eb652b564f 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -1582,8 +1582,10 @@ mpt3sas_base_pause_mq_polling(struct MPT3SAS_ADAPTER *ioc) * wait for current poll to complete. */ for (qid = 0; qid < iopoll_q_count; qid++) { - while (atomic_read(&ioc->io_uring_poll_queues[qid].busy)) + while (atomic_read(&ioc->io_uring_poll_queues[qid].busy)) { + cpu_relax(); udelay(500); + } } } From 265dfe8ebbabae7959060bd1c3f75c2473b697ed Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 6 Sep 2021 17:01:12 +0800 Subject: [PATCH 153/866] scsi: sd: Free scsi_disk device via put_device() After a device is initialized via device_initialize() it should be freed via put_device(). sd_probe() currently gets this wrong, fix it up. Link: https://lore.kernel.org/r/20210906090112.531442-1-ming.lei@redhat.com Reviewed-by: Bart Van Assche Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index cbd9999f93a6..a8039beb5a02 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3401,15 +3401,16 @@ static int sd_probe(struct device *dev) } device_initialize(&sdkp->dev); - sdkp->dev.parent = dev; + sdkp->dev.parent = get_device(dev); sdkp->dev.class = &sd_disk_class; dev_set_name(&sdkp->dev, "%s", dev_name(dev)); error = device_add(&sdkp->dev); - if (error) - goto out_free_index; + if (error) { + put_device(&sdkp->dev); + goto out; + } - get_device(dev); dev_set_drvdata(dev, sdkp); gd->major = sd_major((index & 0xf0) >> 4); From 7215e909814fed7cda33c954943a4050d8348204 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Mon, 6 Sep 2021 23:06:42 +0900 Subject: [PATCH 154/866] scsi: sd_zbc: Ensure buffer size is aligned to SECTOR_SIZE Reporting zones on a SCSI device sometimes fail with the following error: [76248.516390] ata16.00: invalid transfer count 131328 [76248.523618] sd 15:0:0:0: [sda] REPORT ZONES start lba 536870912 failed The error (from drivers/ata/libata-scsi.c:ata_scsi_zbc_in_xlat()) indicates that buffer size is not aligned to SECTOR_SIZE. This happens when the __vmalloc() failed. Consider we are reporting 4096 zones, then we will have "bufsize = roundup((4096 + 1) * 64, SECTOR_SIZE)" = (513 * 512) = 262656. Then, __vmalloc() failure halves the bufsize to 131328, which is no longer aligned to SECTOR_SIZE. Use rounddown() to ensure the size is always aligned to SECTOR_SIZE and fix the comment as well. Link: https://lore.kernel.org/r/20210906140642.2267569-1-naohiro.aota@wdc.com Fixes: 23a50861adda ("scsi: sd_zbc: Cleanup sd_zbc_alloc_report_buffer()") Cc: stable@vger.kernel.org # 5.5+ Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Himanshu Madhani Signed-off-by: Naohiro Aota Signed-off-by: Martin K. Petersen --- drivers/scsi/sd_zbc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index b9757f24b0d6..8197d31a81f9 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -154,8 +154,8 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, /* * Report zone buffer size should be at most 64B times the number of - * zones requested plus the 64B reply header, but should be at least - * SECTOR_SIZE for ATA devices. + * zones requested plus the 64B reply header, but should be aligned + * to SECTOR_SIZE for ATA devices. * Make sure that this size does not exceed the hardware capabilities. * Furthermore, since the report zone command cannot be split, make * sure that the allocated buffer can always be mapped by limiting the @@ -174,7 +174,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, *buflen = bufsize; return buf; } - bufsize >>= 1; + bufsize = rounddown(bufsize >> 1, SECTOR_SIZE); } return NULL; From ef7ae7f746e95c6fa4ec2bcfacb949c36263da78 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Mon, 6 Sep 2021 17:18:09 +0200 Subject: [PATCH 155/866] scsi: target: Fix the pgr/alua_support_store functions Commit 356ba2a8bc8d ("scsi: target: tcmu: Make pgr_support and alua_support attributes writable") introduced support for changeable alua_support and pgr_support target attributes. These can only be changed if the backstore is user-backed, otherwise the kernel returns -EINVAL. This triggers a warning in the targetcli/rtslib code when performing a target restore that includes non-userbacked backstores: # targetctl restore Storage Object block/storage1: Cannot set attribute alua_support: [Errno 22] Invalid argument, skipped Storage Object block/storage1: Cannot set attribute pgr_support: [Errno 22] Invalid argument, skipped Fix this warning by returning an error code only if we are really going to flip the PGR/ALUA bit in the transport_flags field, otherwise we will do nothing and return success. Return ENOSYS instead of EINVAL if the pgr/alua attributes can not be changed, this way it will be possible for userspace to understand if the operation failed because an invalid value has been passed to strtobool() or because the attributes are fixed. Fixes: 356ba2a8bc8d ("scsi: target: tcmu: Make pgr_support and alua_support attributes writable") Link: https://lore.kernel.org/r/20210906151809.52811-1-mlombard@redhat.com Reviewed-by: Bodo Stroesser Signed-off-by: Maurizio Lombardi Signed-off-by: Martin K. Petersen --- drivers/target/target_core_configfs.c | 32 +++++++++++++++++---------- 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 102ec644bc8a..023bd4516a68 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -1110,20 +1110,24 @@ static ssize_t alua_support_store(struct config_item *item, { struct se_dev_attrib *da = to_attrib(item); struct se_device *dev = da->da_dev; - bool flag; + bool flag, oldflag; int ret; + ret = strtobool(page, &flag); + if (ret < 0) + return ret; + + oldflag = !(dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_ALUA); + if (flag == oldflag) + return count; + if (!(dev->transport->transport_flags_changeable & TRANSPORT_FLAG_PASSTHROUGH_ALUA)) { pr_err("dev[%p]: Unable to change SE Device alua_support:" " alua_support has fixed value\n", dev); - return -EINVAL; + return -ENOSYS; } - ret = strtobool(page, &flag); - if (ret < 0) - return ret; - if (flag) dev->transport_flags &= ~TRANSPORT_FLAG_PASSTHROUGH_ALUA; else @@ -1145,20 +1149,24 @@ static ssize_t pgr_support_store(struct config_item *item, { struct se_dev_attrib *da = to_attrib(item); struct se_device *dev = da->da_dev; - bool flag; + bool flag, oldflag; int ret; + ret = strtobool(page, &flag); + if (ret < 0) + return ret; + + oldflag = !(dev->transport_flags & TRANSPORT_FLAG_PASSTHROUGH_PGR); + if (flag == oldflag) + return count; + if (!(dev->transport->transport_flags_changeable & TRANSPORT_FLAG_PASSTHROUGH_PGR)) { pr_err("dev[%p]: Unable to change SE Device pgr_support:" " pgr_support has fixed value\n", dev); - return -EINVAL; + return -ENOSYS; } - ret = strtobool(page, &flag); - if (ret < 0) - return ret; - if (flag) dev->transport_flags &= ~TRANSPORT_FLAG_PASSTHROUGH_PGR; else From 450907424d9ebcc28fab42a065c3cddce49ee97d Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 7 Sep 2021 09:52:25 -0700 Subject: [PATCH 156/866] scsi: elx: efct: Do not hold lock while calling fc_vport_terminate() Smatch checker reported the following error: drivers/base/power/sysfs.c:833 dpm_sysfs_remove() warn: sleeping in atomic context With a calling sequence of: efct_lio_npiv_drop_nport() <- disables preempt -> fc_vport_terminate() -> device_del() -> dpm_sysfs_remove() Issue is efct_lio_npiv_drop_nport() is making the fc_vport_terminate() call while holding a lock w/ ipl raised. It is unnecessary to hold the lock over this call, shift where the lock is taken. Link: https://lore.kernel.org/r/20210907165225.10821-1-jsmart2021@gmail.com Reported-by: Dan Carpenter Co-developed-by: Ram Vegesna Signed-off-by: Ram Vegesna Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- drivers/scsi/elx/efct/efct_lio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/elx/efct/efct_lio.c b/drivers/scsi/elx/efct/efct_lio.c index bb3b460dc0bc..4d73e92909ab 100644 --- a/drivers/scsi/elx/efct/efct_lio.c +++ b/drivers/scsi/elx/efct/efct_lio.c @@ -880,11 +880,11 @@ efct_lio_npiv_drop_nport(struct se_wwn *wwn) struct efct *efct = lio_vport->efct; unsigned long flags = 0; - spin_lock_irqsave(&efct->tgt_efct.efct_lio_lock, flags); - if (lio_vport->fc_vport) fc_vport_terminate(lio_vport->fc_vport); + spin_lock_irqsave(&efct->tgt_efct.efct_lio_lock, flags); + list_for_each_entry_safe(vport, next_vport, &efct->tgt_efct.vport_list, list_entry) { if (vport->lio_vport == lio_vport) { From 1f97c29beee774e407839768439b7f51831c3ea1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 7 Sep 2021 23:00:44 +0200 Subject: [PATCH 157/866] scsi: ncr53c8xx: Remove unused retrieve_from_waiting_list() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop retrieve_from_waiting_list() to avoid this warning: drivers/scsi/ncr53c8xx.c:8000:26: warning: ‘retrieve_from_waiting_list’ defined but not used [-Wunused-function] Link: https://lore.kernel.org/r/YTfS/LH5vCN6afDW@ls3530 Fixes: 1c22e327545c ("scsi: ncr53c8xx: Remove unused code") Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Helge Deller Signed-off-by: Martin K. Petersen --- drivers/scsi/ncr53c8xx.c | 23 ----------------------- 1 file changed, 23 deletions(-) diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c index 7a4f5d4dd670..2b8c6fa5e775 100644 --- a/drivers/scsi/ncr53c8xx.c +++ b/drivers/scsi/ncr53c8xx.c @@ -1939,11 +1939,8 @@ static void ncr_start_next_ccb (struct ncb *np, struct lcb * lp, int maxn); static void ncr_put_start_queue(struct ncb *np, struct ccb *cp); static void insert_into_waiting_list(struct ncb *np, struct scsi_cmnd *cmd); -static struct scsi_cmnd *retrieve_from_waiting_list(int to_remove, struct ncb *np, struct scsi_cmnd *cmd); static void process_waiting_list(struct ncb *np, int sts); -#define remove_from_waiting_list(np, cmd) \ - retrieve_from_waiting_list(1, (np), (cmd)) #define requeue_waiting_list(np) process_waiting_list((np), DID_OK) #define reset_waiting_list(np) process_waiting_list((np), DID_RESET) @@ -7997,26 +7994,6 @@ static void insert_into_waiting_list(struct ncb *np, struct scsi_cmnd *cmd) } } -static struct scsi_cmnd *retrieve_from_waiting_list(int to_remove, struct ncb *np, struct scsi_cmnd *cmd) -{ - struct scsi_cmnd **pcmd = &np->waiting_list; - - while (*pcmd) { - if (cmd == *pcmd) { - if (to_remove) { - *pcmd = (struct scsi_cmnd *) cmd->next_wcmd; - cmd->next_wcmd = NULL; - } -#ifdef DEBUG_WAITING_LIST - printk("%s: cmd %lx retrieved from waiting list\n", ncr_name(np), (u_long) cmd); -#endif - return cmd; - } - pcmd = (struct scsi_cmnd **) &(*pcmd)->next_wcmd; - } - return NULL; -} - static void process_waiting_list(struct ncb *np, int sts) { struct scsi_cmnd *waiting_list, *wcmd; From 17dfd54d391ea9f8d136fb137962987cb2c6444c Mon Sep 17 00:00:00 2001 From: jing yangyang Date: Thu, 19 Aug 2021 20:08:05 -0700 Subject: [PATCH 158/866] scsi: megaraid: Fix Coccinelle warning WARNING !A || A && B is equivalent to !A || B This issue was detected with the help of Coccinelle. Link: https://lore.kernel.org/r/20210820030805.12383-1-jing.yangyang@zte.com.cn Reported-by: Zeal Robot Acked-by: Sumit Saxena Signed-off-by: jing yangyang Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_sas_base.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index e4298bf4a482..17c87ac8bb51 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -8773,8 +8773,7 @@ int megasas_update_device_list(struct megasas_instance *instance, if (event_type & SCAN_VD_CHANNEL) { if (!instance->requestorId || - (instance->requestorId && - megasas_get_ld_vf_affiliation(instance, 0))) { + megasas_get_ld_vf_affiliation(instance, 0)) { dcmd_ret = megasas_ld_list_query(instance, MR_LD_QUERY_TYPE_EXPOSED_TO_HOST); if (dcmd_ret != DCMD_SUCCESS) From fc13fc07490982c89f5d9d8d671ec29a39cddc85 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Sep 2021 08:11:39 -0600 Subject: [PATCH 159/866] scsi: Remove SCSI CDROM MAINTAINERS entry There's little point in keeping this one separately maintained these days, so just remove the entry and it'll fall under the SCSI subsystem where it belongs. Link: https://lore.kernel.org/r/c5e12bd1-10de-634c-d6b3-dac79ed01af5@kernel.dk Signed-off-by: Jens Axboe Signed-off-by: Martin K. Petersen --- MAINTAINERS | 7 ------- 1 file changed, 7 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..fd12a39f92ef 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16650,13 +16650,6 @@ M: Lubomir Rintel S: Supported F: drivers/char/pcmcia/scr24x_cs.c -SCSI CDROM DRIVER -M: Jens Axboe -L: linux-scsi@vger.kernel.org -S: Maintained -W: http://www.kernel.dk -F: drivers/scsi/sr* - SCSI RDMA PROTOCOL (SRP) INITIATOR M: Bart Van Assche L: linux-rdma@vger.kernel.org From e699a4e1d37314eb842ba9de19a7ccee7f75da10 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 26 Aug 2021 12:57:14 +0100 Subject: [PATCH 160/866] scsi: sr: Fix spelling mistake "does'nt" -> "doesn't" There is a spelling mistake in a literal string. Fix it. Link: https://lore.kernel.org/r/20210826115714.11844-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/scsi/sr_ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index 79d9aa2df528..ddd00efc4882 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -523,7 +523,7 @@ static int sr_read_sector(Scsi_CD *cd, int lba, int blksize, unsigned char *dest return rc; cd->readcd_known = 0; sr_printk(KERN_INFO, cd, - "CDROM does'nt support READ CD (0xbe) command\n"); + "CDROM doesn't support READ CD (0xbe) command\n"); /* fall & retry the other way */ } /* ... if this fails, we switch the blocksize using MODE SELECT */ From 655a68b2203e44912afe462dff9d83d68ac88333 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 2 Sep 2021 23:36:43 +0100 Subject: [PATCH 161/866] scsi: megaraid: Clean up some inconsistent indenting There are a few statements where the indentation is not correct, clean these up. Link: https://lore.kernel.org/r/20210902223643.56979-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/scsi/megaraid/megaraid_sas_base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 17c87ac8bb51..39d8754e63ac 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -1916,7 +1916,7 @@ void megasas_set_dynamic_target_properties(struct scsi_device *sdev, raid = MR_LdRaidGet(ld, local_map_ptr); if (raid->capability.ldPiMode == MR_PROT_INFO_TYPE_CONTROLLER) - blk_queue_update_dma_alignment(sdev->request_queue, 0x7); + blk_queue_update_dma_alignment(sdev->request_queue, 0x7); mr_device_priv_data->is_tm_capable = raid->capability.tmCapable; @@ -8033,7 +8033,7 @@ skip_firing_dcmds: if (instance->adapter_type != MFI_SERIES) { megasas_release_fusion(instance); - pd_seq_map_sz = sizeof(struct MR_PD_CFG_SEQ_NUM_SYNC) + + pd_seq_map_sz = sizeof(struct MR_PD_CFG_SEQ_NUM_SYNC) + (sizeof(struct MR_PD_CFG_SEQ) * (MAX_PHYSICAL_DEVICES - 1)); for (i = 0; i < 2 ; i++) { From 04c260bdaeede8c703bddc21099e4da96f2909e2 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 2 Sep 2021 23:42:15 +0100 Subject: [PATCH 162/866] scsi: mpt3sas: Clean up some inconsistent indenting There are a couple of statements where the indentation is not correct, clean these up. Remove a redundant break statement. Link: https://lore.kernel.org/r/20210902224215.57286-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_ctl.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 770b241d7bb2..1b79f01f03a4 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -2178,7 +2178,7 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type, mpt3sas_check_cmd_timeout(ioc, ioc->ctl_cmds.status, mpi_request, sizeof(Mpi2DiagReleaseRequest_t)/4, reset_needed); - *issue_reset = reset_needed; + *issue_reset = reset_needed; rc = -EFAULT; goto out; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 2f82b1e629af..d383d4a03436 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -10749,8 +10749,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event) case MPI2_EVENT_PCIE_TOPOLOGY_CHANGE_LIST: _scsih_pcie_topology_change_event(ioc, fw_event); ioc->current_event = NULL; - return; - break; + return; } out: fw_event_work_put(fw_event); From 1cbc9ad3eecd492be33b727b4606ae75bc880676 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 31 Aug 2021 17:53:17 +0300 Subject: [PATCH 163/866] scsi: ufs: ufs-pci: Fix Intel LKF link stability Intel LKF can experience link errors. Make fixes to increase link stability, especially when switching to high speed modes. Link: https://lore.kernel.org/r/20210831145317.26306-1-adrian.hunter@intel.com Fixes: b2c57925df1f ("scsi: ufs: ufs-pci: Add support for Intel LKF") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd-pci.c | 78 +++++++++++++++++++++++++++++++++++ drivers/scsi/ufs/ufshcd.c | 3 +- drivers/scsi/ufs/ufshcd.h | 1 + 3 files changed, 81 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index b3bcc5c882da..149c1aa09103 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -128,6 +128,81 @@ static int ufs_intel_link_startup_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_set_lanes(struct ufs_hba *hba, u32 lanes) +{ + struct ufs_pa_layer_attr pwr_info = hba->pwr_info; + int ret; + + pwr_info.lane_rx = lanes; + pwr_info.lane_tx = lanes; + ret = ufshcd_config_pwr_mode(hba, &pwr_info); + if (ret) + dev_err(hba->dev, "%s: Setting %u lanes, err = %d\n", + __func__, lanes, ret); + return ret; +} + +static int ufs_intel_lkf_pwr_change_notify(struct ufs_hba *hba, + enum ufs_notify_change_status status, + struct ufs_pa_layer_attr *dev_max_params, + struct ufs_pa_layer_attr *dev_req_params) +{ + int err = 0; + + switch (status) { + case PRE_CHANGE: + if (ufshcd_is_hs_mode(dev_max_params) && + (hba->pwr_info.lane_rx != 2 || hba->pwr_info.lane_tx != 2)) + ufs_intel_set_lanes(hba, 2); + memcpy(dev_req_params, dev_max_params, sizeof(*dev_req_params)); + break; + case POST_CHANGE: + if (ufshcd_is_hs_mode(dev_req_params)) { + u32 peer_granularity; + + usleep_range(1000, 1250); + err = ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_GRANULARITY), + &peer_granularity); + } + break; + default: + break; + } + + return err; +} + +static int ufs_intel_lkf_apply_dev_quirks(struct ufs_hba *hba) +{ + u32 granularity, peer_granularity; + u32 pa_tactivate, peer_pa_tactivate; + int ret; + + ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_GRANULARITY), &granularity); + if (ret) + goto out; + + ret = ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_GRANULARITY), &peer_granularity); + if (ret) + goto out; + + ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_TACTIVATE), &pa_tactivate); + if (ret) + goto out; + + ret = ufshcd_dme_peer_get(hba, UIC_ARG_MIB(PA_TACTIVATE), &peer_pa_tactivate); + if (ret) + goto out; + + if (granularity == peer_granularity) { + u32 new_peer_pa_tactivate = pa_tactivate + 2; + + ret = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TACTIVATE), new_peer_pa_tactivate); + } +out: + return ret; +} + #define INTEL_ACTIVELTR 0x804 #define INTEL_IDLELTR 0x808 @@ -351,6 +426,7 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba) struct ufs_host *ufs_host; int err; + hba->nop_out_timeout = 200; hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; hba->caps |= UFSHCD_CAP_CRYPTO; err = ufs_intel_common_init(hba); @@ -381,6 +457,8 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = { .exit = ufs_intel_common_exit, .hce_enable_notify = ufs_intel_hce_enable_notify, .link_startup_notify = ufs_intel_link_startup_notify, + .pwr_change_notify = ufs_intel_lkf_pwr_change_notify, + .apply_dev_quirks = ufs_intel_lkf_apply_dev_quirks, .resume = ufs_intel_resume, .device_reset = ufs_intel_device_reset, }; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 3841ab49f556..67889d74761c 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4776,7 +4776,7 @@ static int ufshcd_verify_dev_init(struct ufs_hba *hba) mutex_lock(&hba->dev_cmd.lock); for (retries = NOP_OUT_RETRIES; retries > 0; retries--) { err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_NOP, - NOP_OUT_TIMEOUT); + hba->nop_out_timeout); if (!err || err == -ETIMEDOUT) break; @@ -9483,6 +9483,7 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) hba->host = host; hba->dev = dev; hba->dev_ref_clk_freq = REF_CLK_FREQ_INVAL; + hba->nop_out_timeout = NOP_OUT_TIMEOUT; INIT_LIST_HEAD(&hba->clk_list_head); spin_lock_init(&hba->outstanding_lock); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 52ea6f350b18..4723f27a55d1 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -858,6 +858,7 @@ struct ufs_hba { /* Device management request data */ struct ufs_dev_cmd dev_cmd; ktime_t last_dme_cmd_tstamp; + int nop_out_timeout; /* Keeps information of the UFS device connected to this host */ struct ufs_dev_info dev_info; From 4521428c48118b0f5f7a637ce7dedd76c29bcdaa Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 11 Sep 2021 14:11:59 +0200 Subject: [PATCH 164/866] scsi: sd: Make sd_spinup_disk() less noisy sd_spinup_disk() is a little bit noisy after commit 848ade90ba9c ("scsi: sd: Do not exit sd_spinup_disk() quietly"): scsi 0:0:0:0: Direct-Access Multiple Card Reader 1.00 PQ: 0 ANSI: 0 sd 0:0:0:0: Attached scsi generic sg0 type 0 sd 0:0:0:0: [sda] Media removed, stopped polling sd 0:0:0:0: [sda] Media removed, stopped polling sd 0:0:0:0: [sda] Attached SCSI removable disk sd 0:0:0:0: [sda] Media removed, stopped polling There's not really a benefit in printing the same message multiple times. Therefore print it only if media_present was previously set. Link: https://lore.kernel.org/r/a2d0a249-6035-9697-626a-e14ec50ef6ee@gmail.com Reviewed-by: Bart Van Assche Signed-off-by: Heiner Kallweit Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a8039beb5a02..523bf2fdc253 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2124,6 +2124,8 @@ sd_spinup_disk(struct scsi_disk *sdkp) retries = 0; do { + bool media_was_present = sdkp->media_present; + cmd[0] = TEST_UNIT_READY; memset((void *) &cmd[1], 0, 9); @@ -2138,7 +2140,8 @@ sd_spinup_disk(struct scsi_disk *sdkp) * with any more polling. */ if (media_not_present(sdkp, &sshdr)) { - sd_printk(KERN_NOTICE, sdkp, "Media removed, stopped polling\n"); + if (media_was_present) + sd_printk(KERN_NOTICE, sdkp, "Media removed, stopped polling\n"); return; } From 1a0db7744e453844aa2db3f2959aea4a378025ea Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Sat, 11 Sep 2021 18:53:06 +0800 Subject: [PATCH 165/866] scsi: bsg: Fix device unregistration device_initialize() is used to take a refcount on the device. However, put_device() is not called during device teardown. This leads to a leak of private data of the driver core, dev_name(), etc. This is reported by kmemleak at boot time if we compile kernel with DEBUG_TEST_DRIVER_REMOVE. Fix memory leaks during unregistration and implement a release function. Link: https://lore.kernel.org/r/20210911105306.1511-1-yuzenghui@huawei.com Fixes: ead09dd3aed5 ("scsi: bsg: Simplify device registration") Reviewed-by: Johan Hovold Signed-off-by: Zenghui Yu Signed-off-by: Martin K. Petersen --- block/bsg.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/block/bsg.c b/block/bsg.c index 351095193788..882f56bff14f 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -165,13 +165,20 @@ static const struct file_operations bsg_fops = { .llseek = default_llseek, }; +static void bsg_device_release(struct device *dev) +{ + struct bsg_device *bd = container_of(dev, struct bsg_device, device); + + ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); + kfree(bd); +} + void bsg_unregister_queue(struct bsg_device *bd) { if (bd->queue->kobj.sd) sysfs_remove_link(&bd->queue->kobj, "bsg"); cdev_device_del(&bd->cdev, &bd->device); - ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); - kfree(bd); + put_device(&bd->device); } EXPORT_SYMBOL_GPL(bsg_unregister_queue); @@ -193,11 +200,13 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, if (ret < 0) { if (ret == -ENOSPC) dev_err(parent, "bsg: too many bsg devices\n"); - goto out_kfree; + kfree(bd); + return ERR_PTR(ret); } bd->device.devt = MKDEV(bsg_major, ret); bd->device.class = bsg_class; bd->device.parent = parent; + bd->device.release = bsg_device_release; dev_set_name(&bd->device, "%s", name); device_initialize(&bd->device); @@ -205,7 +214,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, bd->cdev.owner = THIS_MODULE; ret = cdev_device_add(&bd->cdev, &bd->device); if (ret) - goto out_ida_remove; + goto out_put_device; if (q->kobj.sd) { ret = sysfs_create_link(&q->kobj, &bd->device.kobj, "bsg"); @@ -217,10 +226,8 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, out_device_del: cdev_device_del(&bd->cdev, &bd->device); -out_ida_remove: - ida_simple_remove(&bsg_minor_ida, MINOR(bd->device.devt)); -out_kfree: - kfree(bd); +out_put_device: + put_device(&bd->device); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(bsg_register_queue); From b564171ade70570b7f335fa8ed17adb28409e3ac Mon Sep 17 00:00:00 2001 From: Li Li Date: Fri, 10 Sep 2021 09:42:10 -0700 Subject: [PATCH 166/866] binder: fix freeze race Currently cgroup freezer is used to freeze the application threads, and BINDER_FREEZE is used to freeze the corresponding binder interface. There's already a mechanism in ioctl(BINDER_FREEZE) to wait for any existing transactions to drain out before actually freezing the binder interface. But freezing an app requires 2 steps, freezing the binder interface with ioctl(BINDER_FREEZE) and then freezing the application main threads with cgroupfs. This is not an atomic operation. The following race issue might happen. 1) Binder interface is frozen by ioctl(BINDER_FREEZE); 2) Main thread A initiates a new sync binder transaction to process B; 3) Main thread A is frozen by "echo 1 > cgroup.freeze"; 4) The response from process B reaches the frozen thread, which will unexpectedly fail. This patch provides a mechanism to check if there's any new pending transaction happening between ioctl(BINDER_FREEZE) and freezing the main thread. If there's any, the main thread freezing operation can be rolled back to finish the pending transaction. Furthermore, the response might reach the binder driver before the rollback actually happens. That will still cause failed transaction. As the other process doesn't wait for another response of the response, the response transaction failure can be fixed by treating the response transaction like an oneway/async one, allowing it to reach the frozen thread. And it will be consumed when the thread gets unfrozen later. NOTE: This patch reuses the existing definition of struct binder_frozen_status_info but expands the bit assignments of __u32 member sync_recv. To ensure backward compatibility, bit 0 of sync_recv still indicates there's an outstanding sync binder transaction. This patch adds new information to bit 1 of sync_recv, indicating the binder transaction happens exactly when there's a race. If an existing userspace app runs on a new kernel, a sync binder call will set bit 0 of sync_recv so ioctl(BINDER_GET_FROZEN_INFO) still return the expected value (true). The app just doesn't check bit 1 intentionally so it doesn't have the ability to tell if there's a race. This behavior is aligned with what happens on an old kernel which doesn't set bit 1 at all. A new userspace app can 1) check bit 0 to know if there's a sync binder transaction happened when being frozen - same as before; and 2) check bit 1 to know if that sync binder transaction happened exactly when there's a race - a new information for rollback decision. the same time, confirmed the pending transactions succeeded. Fixes: 432ff1e91694 ("binder: BINDER_FREEZE ioctl") Acked-by: Todd Kjos Cc: stable Signed-off-by: Li Li Test: stress test with apps being frozen and initiating binder calls at Link: https://lore.kernel.org/r/20210910164210.2282716-2-dualli@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 35 ++++++++++++++++++++++++----- drivers/android/binder_internal.h | 2 ++ include/uapi/linux/android/binder.h | 7 ++++++ 3 files changed, 38 insertions(+), 6 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d9030cb6b1e4..1a68c2f590cf 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3038,9 +3038,8 @@ static void binder_transaction(struct binder_proc *proc, if (reply) { binder_enqueue_thread_work(thread, tcomplete); binder_inner_proc_lock(target_proc); - if (target_thread->is_dead || target_proc->is_frozen) { - return_error = target_thread->is_dead ? - BR_DEAD_REPLY : BR_FROZEN_REPLY; + if (target_thread->is_dead) { + return_error = BR_DEAD_REPLY; binder_inner_proc_unlock(target_proc); goto err_dead_proc_or_thread; } @@ -4648,6 +4647,22 @@ static int binder_ioctl_get_node_debug_info(struct binder_proc *proc, return 0; } +static bool binder_txns_pending_ilocked(struct binder_proc *proc) +{ + struct rb_node *n; + struct binder_thread *thread; + + if (proc->outstanding_txns > 0) + return true; + + for (n = rb_first(&proc->threads); n; n = rb_next(n)) { + thread = rb_entry(n, struct binder_thread, rb_node); + if (thread->transaction_stack) + return true; + } + return false; +} + static int binder_ioctl_freeze(struct binder_freeze_info *info, struct binder_proc *target_proc) { @@ -4679,8 +4694,13 @@ static int binder_ioctl_freeze(struct binder_freeze_info *info, (!target_proc->outstanding_txns), msecs_to_jiffies(info->timeout_ms)); - if (!ret && target_proc->outstanding_txns) - ret = -EAGAIN; + /* Check pending transactions that wait for reply */ + if (ret >= 0) { + binder_inner_proc_lock(target_proc); + if (binder_txns_pending_ilocked(target_proc)) + ret = -EAGAIN; + binder_inner_proc_unlock(target_proc); + } if (ret < 0) { binder_inner_proc_lock(target_proc); @@ -4696,6 +4716,7 @@ static int binder_ioctl_get_freezer_info( { struct binder_proc *target_proc; bool found = false; + __u32 txns_pending; info->sync_recv = 0; info->async_recv = 0; @@ -4705,7 +4726,9 @@ static int binder_ioctl_get_freezer_info( if (target_proc->pid == info->pid) { found = true; binder_inner_proc_lock(target_proc); - info->sync_recv |= target_proc->sync_recv; + txns_pending = binder_txns_pending_ilocked(target_proc); + info->sync_recv |= target_proc->sync_recv | + (txns_pending << 1); info->async_recv |= target_proc->async_recv; binder_inner_proc_unlock(target_proc); } diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 810c0b84d3f8..402c4d4362a8 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -378,6 +378,8 @@ struct binder_ref { * binder transactions * (protected by @inner_lock) * @sync_recv: process received sync transactions since last frozen + * bit 0: received sync transaction after being frozen + * bit 1: new pending sync transaction during freezing * (protected by @inner_lock) * @async_recv: process received async transactions since last frozen * (protected by @inner_lock) diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 20e435fe657a..3246f2c74696 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -225,7 +225,14 @@ struct binder_freeze_info { struct binder_frozen_status_info { __u32 pid; + + /* process received sync transactions since last frozen + * bit 0: received sync transaction after being frozen + * bit 1: new pending sync transaction during freezing + */ __u32 sync_recv; + + /* process received async transactions since last frozen */ __u32 async_recv; }; From 5fdb55c1ac9585eb23bb2541d5819224429e103d Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Mon, 30 Aug 2021 12:51:46 -0700 Subject: [PATCH 167/866] binder: make sure fd closes complete During BC_FREE_BUFFER processing, the BINDER_TYPE_FDA object cleanup may close 1 or more fds. The close operations are completed using the task work mechanism -- which means the thread needs to return to userspace or the file object may never be dereferenced -- which can lead to hung processes. Force the binder thread back to userspace if an fd is closed during BC_FREE_BUFFER handling. Fixes: 80cd795630d6 ("binder: fix use-after-free due to ksys_close() during fdget()") Cc: stable Reviewed-by: Martijn Coenen Acked-by: Christian Brauner Signed-off-by: Todd Kjos Link: https://lore.kernel.org/r/20210830195146.587206-1-tkjos@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 1a68c2f590cf..9edacc8b9768 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1852,6 +1852,7 @@ static void binder_deferred_fd_close(int fd) } static void binder_transaction_buffer_release(struct binder_proc *proc, + struct binder_thread *thread, struct binder_buffer *buffer, binder_size_t failed_at, bool is_failure) @@ -2011,8 +2012,16 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, &proc->alloc, &fd, buffer, offset, sizeof(fd)); WARN_ON(err); - if (!err) + if (!err) { binder_deferred_fd_close(fd); + /* + * Need to make sure the thread goes + * back to userspace to complete the + * deferred close + */ + if (thread) + thread->looper_need_return = true; + } } } break; default: @@ -3104,7 +3113,7 @@ err_bad_parent: err_copy_data_failed: binder_free_txn_fixups(t); trace_binder_transaction_failed_buffer_release(t->buffer); - binder_transaction_buffer_release(target_proc, t->buffer, + binder_transaction_buffer_release(target_proc, NULL, t->buffer, buffer_offset, true); if (target_node) binder_dec_node_tmpref(target_node); @@ -3183,7 +3192,9 @@ err_invalid_target_handle: * Cleanup buffer and free it. */ static void -binder_free_buf(struct binder_proc *proc, struct binder_buffer *buffer) +binder_free_buf(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer) { binder_inner_proc_lock(proc); if (buffer->transaction) { @@ -3211,7 +3222,7 @@ binder_free_buf(struct binder_proc *proc, struct binder_buffer *buffer) binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, buffer, 0, false); + binder_transaction_buffer_release(proc, thread, buffer, 0, false); binder_alloc_free_buf(&proc->alloc, buffer); } @@ -3413,7 +3424,7 @@ static int binder_thread_write(struct binder_proc *proc, proc->pid, thread->pid, (u64)data_ptr, buffer->debug_id, buffer->transaction ? "active" : "finished"); - binder_free_buf(proc, buffer); + binder_free_buf(proc, thread, buffer); break; } @@ -4106,7 +4117,7 @@ retry: buffer->transaction = NULL; binder_cleanup_transaction(t, "fd fixups failed", BR_FAILED_REPLY); - binder_free_buf(proc, buffer); + binder_free_buf(proc, thread, buffer); binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, "%d:%d %stransaction %d fd fixups failed %d/%d, line %d\n", proc->pid, thread->pid, From 7a8aa39d44564703620d937bb54cdea2d003657f Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 13 Sep 2021 17:05:51 +0100 Subject: [PATCH 168/866] nvmem: core: Add stubs for nvmem_cell_read_variable_le_u32/64 if !CONFIG_NVMEM When I added nvmem_cell_read_variable_le_u32() and nvmem_cell_read_variable_le_u64() I forgot to add the "static inline" stub functions for when CONFIG_NVMEM wasn't defined. Add them now. This was causing problems with randconfig builds that compiled `drivers/soc/qcom/cpr.c`. Fixes: 6feba6a62c57 ("PM: AVS: qcom-cpr: Use nvmem_cell_read_variable_le_u32()") Fixes: a28e824fb827 ("nvmem: core: Add functions to make number reading easy") Reported-by: kernel test robot Reviewed-by: Bjorn Andersson Signed-off-by: Douglas Anderson Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210913160551.12907-1-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 923dada24eb4..c0c0cefc3b92 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -150,6 +150,20 @@ static inline int nvmem_cell_read_u64(struct device *dev, return -EOPNOTSUPP; } +static inline int nvmem_cell_read_variable_le_u32(struct device *dev, + const char *cell_id, + u32 *val) +{ + return -EOPNOTSUPP; +} + +static inline int nvmem_cell_read_variable_le_u64(struct device *dev, + const char *cell_id, + u64 *val) +{ + return -EOPNOTSUPP; +} + static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { From 212b5d2d3ed9d7db2702e4805f36a346c3985e1d Mon Sep 17 00:00:00 2001 From: Jian Cai Date: Mon, 13 Sep 2021 10:46:13 -0600 Subject: [PATCH 169/866] coresight: syscfg: Fix compiler warning This fixes warnings with -Wimplicit-function-declaration, e.g. drivers/hwtracing/coresight/coresight-syscfg.c:455:15: error: implicit declaration of function 'kzalloc' [-Werror, -Wimplicit-function-declaration] csdev_item = kzalloc(sizeof(struct cscfg_registered_csdev), GFP_KERNEL); Link: https://lore.kernel.org/r/20210830172820.2840433-1-jiancai@google.com Fixes: 85e2414c518a ("coresight: syscfg: Initial coresight system configuration") Reviewed-by: Guenter Roeck Signed-off-by: Jian Cai Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210913164613.1675791-2-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-syscfg.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c index fc0760f55c53..43054568430f 100644 --- a/drivers/hwtracing/coresight/coresight-syscfg.c +++ b/drivers/hwtracing/coresight/coresight-syscfg.c @@ -5,6 +5,7 @@ */ #include +#include #include "coresight-config.h" #include "coresight-etm-perf.h" From 92dc0b1f46e12cfabd28d709bb34f7a39431b44f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Sep 2021 14:45:38 +0200 Subject: [PATCH 170/866] staging: greybus: uart: fix tty use after free User space can hold a tty open indefinitely and tty drivers must not release the underlying structures until the last user is gone. Switch to using the tty-port reference counter to manage the life time of the greybus tty state to avoid use after free after a disconnect. Fixes: a18e15175708 ("greybus: more uart work") Cc: stable@vger.kernel.org # 4.9 Reviewed-by: Alex Elder Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210906124538.22358-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/uart.c | 62 ++++++++++++++++++---------------- 1 file changed, 32 insertions(+), 30 deletions(-) diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c index e6d860a9678e..dc4ed0ff1ae2 100644 --- a/drivers/staging/greybus/uart.c +++ b/drivers/staging/greybus/uart.c @@ -761,6 +761,17 @@ out: gbphy_runtime_put_autosuspend(gb_tty->gbphy_dev); } +static void gb_tty_port_destruct(struct tty_port *port) +{ + struct gb_tty *gb_tty = container_of(port, struct gb_tty, port); + + if (gb_tty->minor != GB_NUM_MINORS) + release_minor(gb_tty); + kfifo_free(&gb_tty->write_fifo); + kfree(gb_tty->buffer); + kfree(gb_tty); +} + static const struct tty_operations gb_ops = { .install = gb_tty_install, .open = gb_tty_open, @@ -786,6 +797,7 @@ static const struct tty_port_operations gb_port_ops = { .dtr_rts = gb_tty_dtr_rts, .activate = gb_tty_port_activate, .shutdown = gb_tty_port_shutdown, + .destruct = gb_tty_port_destruct, }; static int gb_uart_probe(struct gbphy_device *gbphy_dev, @@ -798,17 +810,11 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, int retval; int minor; - gb_tty = kzalloc(sizeof(*gb_tty), GFP_KERNEL); - if (!gb_tty) - return -ENOMEM; - connection = gb_connection_create(gbphy_dev->bundle, le16_to_cpu(gbphy_dev->cport_desc->id), gb_uart_request_handler); - if (IS_ERR(connection)) { - retval = PTR_ERR(connection); - goto exit_tty_free; - } + if (IS_ERR(connection)) + return PTR_ERR(connection); max_payload = gb_operation_get_payload_size_max(connection); if (max_payload < sizeof(struct gb_uart_send_data_request)) { @@ -816,13 +822,23 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, goto exit_connection_destroy; } + gb_tty = kzalloc(sizeof(*gb_tty), GFP_KERNEL); + if (!gb_tty) { + retval = -ENOMEM; + goto exit_connection_destroy; + } + + tty_port_init(&gb_tty->port); + gb_tty->port.ops = &gb_port_ops; + gb_tty->minor = GB_NUM_MINORS; + gb_tty->buffer_payload_max = max_payload - sizeof(struct gb_uart_send_data_request); gb_tty->buffer = kzalloc(gb_tty->buffer_payload_max, GFP_KERNEL); if (!gb_tty->buffer) { retval = -ENOMEM; - goto exit_connection_destroy; + goto exit_put_port; } INIT_WORK(&gb_tty->tx_work, gb_uart_tx_write_work); @@ -830,7 +846,7 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, retval = kfifo_alloc(&gb_tty->write_fifo, GB_UART_WRITE_FIFO_SIZE, GFP_KERNEL); if (retval) - goto exit_buf_free; + goto exit_put_port; gb_tty->credits = GB_UART_FIRMWARE_CREDITS; init_completion(&gb_tty->credits_complete); @@ -844,7 +860,7 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, } else { retval = minor; } - goto exit_kfifo_free; + goto exit_put_port; } gb_tty->minor = minor; @@ -853,9 +869,6 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, init_waitqueue_head(&gb_tty->wioctl); mutex_init(&gb_tty->mutex); - tty_port_init(&gb_tty->port); - gb_tty->port.ops = &gb_port_ops; - gb_tty->connection = connection; gb_tty->gbphy_dev = gbphy_dev; gb_connection_set_data(connection, gb_tty); @@ -863,7 +876,7 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, retval = gb_connection_enable_tx(connection); if (retval) - goto exit_release_minor; + goto exit_put_port; send_control(gb_tty, gb_tty->ctrlout); @@ -890,16 +903,10 @@ static int gb_uart_probe(struct gbphy_device *gbphy_dev, exit_connection_disable: gb_connection_disable(connection); -exit_release_minor: - release_minor(gb_tty); -exit_kfifo_free: - kfifo_free(&gb_tty->write_fifo); -exit_buf_free: - kfree(gb_tty->buffer); +exit_put_port: + tty_port_put(&gb_tty->port); exit_connection_destroy: gb_connection_destroy(connection); -exit_tty_free: - kfree(gb_tty); return retval; } @@ -930,15 +937,10 @@ static void gb_uart_remove(struct gbphy_device *gbphy_dev) gb_connection_disable_rx(connection); tty_unregister_device(gb_tty_driver, gb_tty->minor); - /* FIXME - free transmit / receive buffers */ - gb_connection_disable(connection); - tty_port_destroy(&gb_tty->port); gb_connection_destroy(connection); - release_minor(gb_tty); - kfifo_free(&gb_tty->write_fifo); - kfree(gb_tty->buffer); - kfree(gb_tty); + + tty_port_put(&gb_tty->port); } static int gb_tty_init(void) From 8480ed9c2bbd56fc86524998e5f2e3e22f5038f6 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 27 Aug 2021 14:32:06 +0200 Subject: [PATCH 171/866] xen/balloon: use a kernel thread instead a workqueue Today the Xen ballooning is done via delayed work in a workqueue. This might result in workqueue hangups being reported in case of large amounts of memory are being ballooned in one go (here 16GB): BUG: workqueue lockup - pool cpus=6 node=0 flags=0x0 nice=0 stuck for 64s! Showing busy workqueues and worker pools: workqueue events: flags=0x0 pwq 12: cpus=6 node=0 flags=0x0 nice=0 active=2/256 refcnt=3 in-flight: 229:balloon_process pending: cache_reap workqueue events_freezable_power_: flags=0x84 pwq 12: cpus=6 node=0 flags=0x0 nice=0 active=1/256 refcnt=2 pending: disk_events_workfn workqueue mm_percpu_wq: flags=0x8 pwq 12: cpus=6 node=0 flags=0x0 nice=0 active=1/256 refcnt=2 pending: vmstat_update pool 12: cpus=6 node=0 flags=0x0 nice=0 hung=64s workers=3 idle: 2222 43 This can easily be avoided by using a dedicated kernel thread for doing the ballooning work. Reported-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20210827123206.15429-1-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/xen/balloon.c | 62 +++++++++++++++++++++++++++++++------------ 1 file changed, 45 insertions(+), 17 deletions(-) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 671c71245a7b..2d2803883306 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -43,6 +43,8 @@ #include #include #include +#include +#include #include #include #include @@ -115,7 +117,7 @@ static struct ctl_table xen_root[] = { #define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1) /* - * balloon_process() state: + * balloon_thread() state: * * BP_DONE: done or nothing to do, * BP_WAIT: wait to be rescheduled, @@ -130,6 +132,8 @@ enum bp_state { BP_ECANCELED }; +/* Main waiting point for xen-balloon thread. */ +static DECLARE_WAIT_QUEUE_HEAD(balloon_thread_wq); static DEFINE_MUTEX(balloon_mutex); @@ -144,10 +148,6 @@ static xen_pfn_t frame_list[PAGE_SIZE / sizeof(xen_pfn_t)]; static LIST_HEAD(ballooned_pages); static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); -/* Main work function, always executed in process context. */ -static void balloon_process(struct work_struct *work); -static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); - /* When ballooning out (allocating memory to return to Xen) we don't really want the kernel to try too hard since that can trigger the oom killer. */ #define GFP_BALLOON \ @@ -366,7 +366,7 @@ static void xen_online_page(struct page *page, unsigned int order) static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v) { if (val == MEM_ONLINE) - schedule_delayed_work(&balloon_worker, 0); + wake_up(&balloon_thread_wq); return NOTIFY_OK; } @@ -491,18 +491,43 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) } /* - * As this is a work item it is guaranteed to run as a single instance only. + * Stop waiting if either state is not BP_EAGAIN and ballooning action is + * needed, or if the credit has changed while state is BP_EAGAIN. + */ +static bool balloon_thread_cond(enum bp_state state, long credit) +{ + if (state != BP_EAGAIN) + credit = 0; + + return current_credit() != credit || kthread_should_stop(); +} + +/* + * As this is a kthread it is guaranteed to run as a single instance only. * We may of course race updates of the target counts (which are protected * by the balloon lock), or with changes to the Xen hard limit, but we will * recover from these in time. */ -static void balloon_process(struct work_struct *work) +static int balloon_thread(void *unused) { enum bp_state state = BP_DONE; long credit; + unsigned long timeout; + set_freezable(); + for (;;) { + if (state == BP_EAGAIN) + timeout = balloon_stats.schedule_delay * HZ; + else + timeout = 3600 * HZ; + credit = current_credit(); + + wait_event_interruptible_timeout(balloon_thread_wq, + balloon_thread_cond(state, credit), timeout); + + if (kthread_should_stop()) + return 0; - do { mutex_lock(&balloon_mutex); credit = current_credit(); @@ -529,12 +554,7 @@ static void balloon_process(struct work_struct *work) mutex_unlock(&balloon_mutex); cond_resched(); - - } while (credit && state == BP_DONE); - - /* Schedule more work if there is some still to be done. */ - if (state == BP_EAGAIN) - schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ); + } } /* Resets the Xen limit, sets new target, and kicks off processing. */ @@ -542,7 +562,7 @@ void balloon_set_new_target(unsigned long target) { /* No need for lock. Not read-modify-write updates. */ balloon_stats.target_pages = target; - schedule_delayed_work(&balloon_worker, 0); + wake_up(&balloon_thread_wq); } EXPORT_SYMBOL_GPL(balloon_set_new_target); @@ -647,7 +667,7 @@ void free_xenballooned_pages(int nr_pages, struct page **pages) /* The balloon may be too large now. Shrink it if needed. */ if (current_credit()) - schedule_delayed_work(&balloon_worker, 0); + wake_up(&balloon_thread_wq); mutex_unlock(&balloon_mutex); } @@ -679,6 +699,8 @@ static void __init balloon_add_region(unsigned long start_pfn, static int __init balloon_init(void) { + struct task_struct *task; + if (!xen_domain()) return -ENODEV; @@ -722,6 +744,12 @@ static int __init balloon_init(void) } #endif + task = kthread_run(balloon_thread, NULL, "xen-balloon"); + if (IS_ERR(task)) { + pr_err("xen-balloon thread could not be started, ballooning will not work!\n"); + return PTR_ERR(task); + } + /* Init the xen-balloon driver. */ xen_balloon_init(); From 0560204b360a332c321124dbc5cdfd3364533a74 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 3 Sep 2021 10:49:36 +0200 Subject: [PATCH 172/866] PM: base: power: don't try to use non-existing RTC for storing data If there is no legacy RTC device, don't try to use it for storing trace data across suspend/resume. Cc: Signed-off-by: Juergen Gross Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20210903084937.19392-2-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/base/power/trace.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c index a97f33d0c59f..94665037f4a3 100644 --- a/drivers/base/power/trace.c +++ b/drivers/base/power/trace.c @@ -13,6 +13,7 @@ #include #include #include +#include #include @@ -165,6 +166,9 @@ void generate_pm_trace(const void *tracedata, unsigned int user) const char *file = *(const char **)(tracedata + 2); unsigned int user_hash_value, file_hash_value; + if (!x86_platform.legacy.rtc) + return; + user_hash_value = user % USERHASH; file_hash_value = hash_string(lineno, file, FILEHASH); set_magic_time(user_hash_value, file_hash_value, dev_hash_value); @@ -267,6 +271,9 @@ static struct notifier_block pm_trace_nb = { static int __init early_resume_init(void) { + if (!x86_platform.legacy.rtc) + return 0; + hash_value_early_read = read_magic_time(); register_pm_notifier(&pm_trace_nb); return 0; @@ -277,6 +284,9 @@ static int __init late_resume_init(void) unsigned int val = hash_value_early_read; unsigned int user, file, dev; + if (!x86_platform.legacy.rtc) + return 0; + user = val % USERHASH; val = val / USERHASH; file = val % FILEHASH; From 9af4bf2171c1a9e3f2ebb21140c0e34e60b2a22a Mon Sep 17 00:00:00 2001 From: Lee Shawn C Date: Tue, 6 Jul 2021 23:25:41 +0800 Subject: [PATCH 173/866] drm/i915/dp: return proper DPRX link training result After DPRX link training, intel_dp_link_train_phy() did not return the training result properly. If link training failed, i915 driver would not run into link train fallback function. And no hotplug uevent would be received by user space application. Fixes: b30edfd8d0b4 ("drm/i915: Switch to LTTPR non-transparent mode link training") Cc: Ville Syrjala Cc: Imre Deak Cc: Jani Nikula Cc: Cooper Chiou Cc: William Tseng Signed-off-by: Lee Shawn C Reviewed-by: Imre Deak Signed-off-by: Imre Deak Link: https://patchwork.freedesktop.org/patch/msgid/20210706152541.25021-1-shawn.c.lee@intel.com (cherry picked from commit dab1b47e57e053b2a02c22ead8e7449f79961335) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_dp_link_training.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 053a3c2f7267..508a514c5e37 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -848,7 +848,7 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp, } if (ret) - intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX); + ret = intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX); if (intel_dp->set_idle_link_train) intel_dp->set_idle_link_train(intel_dp, crtc_state); From c8dead5751b81dfa6b10449b740ed1062ff670c5 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 20 Aug 2021 15:52:59 +0800 Subject: [PATCH 174/866] drm/i915/dp: Use max params for panels < eDP 1.4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Users reported that after commit 2bbd6dba84d4 ("drm/i915: Try to use fast+narrow link on eDP again and fall back to the old max strategy on failure"), the screen starts to have wobbly effect. Commit a5c936add6a2 ("drm/i915/dp: Use slow and wide link training for everything") doesn't help either, that means the affected eDP 1.2 panels only work with max params. So use max params for panels < eDP 1.4 as Windows does to solve the issue. v3: - Do the eDP rev check in intel_edp_init_dpcd() v2: - Check eDP 1.4 instead of DPCD 1.1 to apply max params Cc: stable@vger.kernel.org Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/3714 Fixes: 2bbd6dba84d4 ("drm/i915: Try to use fast+narrow link on eDP again and fall back to the old max strategy on failure") Fixes: a5c936add6a2 ("drm/i915/dp: Use slow and wide link training for everything") Suggested-by: Ville Syrjälä Signed-off-by: Kai-Heng Feng Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210820075301.693099-1-kai.heng.feng@canonical.com (cherry picked from commit d7f213c131adf0bec8b731553eb82990cdac265d) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_dp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 04175f359fd6..abe3d61b6243 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2445,11 +2445,14 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) */ if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_DPCD_REV, intel_dp->edp_dpcd, sizeof(intel_dp->edp_dpcd)) == - sizeof(intel_dp->edp_dpcd)) + sizeof(intel_dp->edp_dpcd)) { drm_dbg_kms(&dev_priv->drm, "eDP DPCD: %*ph\n", (int)sizeof(intel_dp->edp_dpcd), intel_dp->edp_dpcd); + intel_dp->use_max_params = intel_dp->edp_dpcd[0] < DP_EDP_14; + } + /* * This has to be called after intel_dp->edp_dpcd is filled, PSR checks * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1] From 415406380c29694e12b164f05e467659381feca5 Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Mon, 23 Aug 2021 09:31:37 -0700 Subject: [PATCH 175/866] drm/i915/guc: drop guc_communication_enabled The function is only used from within GEM_BUG_ON(), which is causing warnings with Wunneeded-internal-declaration in some builds. Since the function is a simple wrapper around a CT function, we can just call the CT function directly instead. Fixes: 1fb12c587152 ("drm/i915/guc: skip disabling CTBs before sanitizing the GuC") Reported-by: kernel test robot Signed-off-by: Daniele Ceraolo Spurio Cc: Matthew Brost Cc: John Harrison Reviewed-by: Matthew Brost Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20210823163137.19770-1-daniele.ceraolospurio@intel.com (cherry picked from commit 5db1856781e45c9610f7652a19cc656b984235e7) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/uc/intel_uc.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index b104fb7607eb..86c318516e14 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -172,11 +172,6 @@ void intel_uc_driver_remove(struct intel_uc *uc) __uc_free_load_err_log(uc); } -static inline bool guc_communication_enabled(struct intel_guc *guc) -{ - return intel_guc_ct_enabled(&guc->ct); -} - /* * Events triggered while CT buffers are disabled are logged in the SCRATCH_15 * register using the same bits used in the CT message payload. Since our @@ -210,7 +205,7 @@ static void guc_get_mmio_msg(struct intel_guc *guc) static void guc_handle_mmio_msg(struct intel_guc *guc) { /* we need communication to be enabled to reply to GuC */ - GEM_BUG_ON(!guc_communication_enabled(guc)); + GEM_BUG_ON(!intel_guc_ct_enabled(&guc->ct)); spin_lock_irq(&guc->irq_lock); if (guc->mmio_msg) { @@ -226,7 +221,7 @@ static int guc_enable_communication(struct intel_guc *guc) struct drm_i915_private *i915 = gt->i915; int ret; - GEM_BUG_ON(guc_communication_enabled(guc)); + GEM_BUG_ON(intel_guc_ct_enabled(&guc->ct)); ret = i915_inject_probe_error(i915, -ENXIO); if (ret) @@ -662,7 +657,7 @@ static int __uc_resume(struct intel_uc *uc, bool enable_communication) return 0; /* Make sure we enable communication if and only if it's disabled */ - GEM_BUG_ON(enable_communication == guc_communication_enabled(guc)); + GEM_BUG_ON(enable_communication == intel_guc_ct_enabled(&guc->ct)); if (enable_communication) guc_enable_communication(guc); From 04a3ab6acd54b104838b3f6bd715447631c6e87d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Date: Tue, 31 Aug 2021 14:29:31 +0200 Subject: [PATCH 176/866] drm/i915/gem: Fix the mman selftest MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using the I915_MMAP_TYPE_FIXED mmap type requires the TTM backend, so for that mmap type, use __i915_gem_object_create_user() instead of i915_gem_object_create_internal(), as we really want to tests objects mmap-able by user-space. This also means that the out-of-space error happens at object creation and returns -ENXIO rather than -ENOSPC, so fix the code up to expect that on out-of-offset-space errors. Finally only use I915_MMAP_TYPE_FIXED for LMEM and SMEM for now if testing on LMEM-capable devices. For stolen LMEM, we still take the same path as for integrated, as that haven't been moved over to TTM yet, and user-space should not be able to create out of stolen LMEM anyway. v2: - Check the presence of the obj->ops->mmap_offset callback rather than hardcoding the supported mmap regions in can_mmap() (Maarten Lankhorst) Fixes: 7961c5b60f23 ("drm/i915: Add TTM offset argument to mmap.") Cc: Maarten Lankhorst Signed-off-by: Thomas Hellström Reviewed-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210831122931.157536-1-thomas.hellstrom@linux.intel.com (cherry picked from commit 450cede7f3804ca7f8b3da210ebefa61c0958f22) Signed-off-by: Jani Nikula --- .../drm/i915/gem/selftests/i915_gem_mman.c | 26 ++++++++++++++----- 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index b20f5621f62b..a2c34e5a1c54 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -581,6 +581,20 @@ static enum i915_mmap_type default_mapping(struct drm_i915_private *i915) return I915_MMAP_TYPE_GTT; } +static struct drm_i915_gem_object * +create_sys_or_internal(struct drm_i915_private *i915, + unsigned long size) +{ + if (HAS_LMEM(i915)) { + struct intel_memory_region *sys_region = + i915->mm.regions[INTEL_REGION_SMEM]; + + return __i915_gem_object_create_user(i915, size, &sys_region, 1); + } + + return i915_gem_object_create_internal(i915, size); +} + static bool assert_mmap_offset(struct drm_i915_private *i915, unsigned long size, int expected) @@ -589,7 +603,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, u64 offset; int ret; - obj = i915_gem_object_create_internal(i915, size); + obj = create_sys_or_internal(i915, size); if (IS_ERR(obj)) return expected && expected == PTR_ERR(obj); @@ -633,6 +647,7 @@ static int igt_mmap_offset_exhaustion(void *arg) struct drm_mm_node *hole, *next; int loop, err = 0; u64 offset; + int enospc = HAS_LMEM(i915) ? -ENXIO : -ENOSPC; /* Disable background reaper */ disable_retire_worker(i915); @@ -683,14 +698,14 @@ static int igt_mmap_offset_exhaustion(void *arg) } /* Too large */ - if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, -ENOSPC)) { + if (!assert_mmap_offset(i915, 2 * PAGE_SIZE, enospc)) { pr_err("Unexpectedly succeeded in inserting too large object into single page hole\n"); err = -EINVAL; goto out; } /* Fill the hole, further allocation attempts should then fail */ - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + obj = create_sys_or_internal(i915, PAGE_SIZE); if (IS_ERR(obj)) { err = PTR_ERR(obj); pr_err("Unable to create object for reclaimed hole\n"); @@ -703,7 +718,7 @@ static int igt_mmap_offset_exhaustion(void *arg) goto err_obj; } - if (!assert_mmap_offset(i915, PAGE_SIZE, -ENOSPC)) { + if (!assert_mmap_offset(i915, PAGE_SIZE, enospc)) { pr_err("Unexpectedly succeeded in inserting object into no holes!\n"); err = -EINVAL; goto err_obj; @@ -839,10 +854,9 @@ static int wc_check(struct drm_i915_gem_object *obj) static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type) { - struct drm_i915_private *i915 = to_i915(obj->base.dev); bool no_map; - if (HAS_LMEM(i915)) + if (obj->ops->mmap_offset) return type == I915_MMAP_TYPE_FIXED; else if (type == I915_MMAP_TYPE_FIXED) return false; From 031536665f64aaeb7e7439d96689a4011407abb8 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 2 Sep 2021 16:20:48 +0200 Subject: [PATCH 177/866] drm/i915: Release ctx->syncobj on final put, not on ctx close MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gem context refcounting is another exercise in least locking design it seems, where most things get destroyed upon context closure (which can race with anything really). Only the actual memory allocation and the locks survive while holding a reference. This tripped up Jason when reimplementing the single timeline feature in commit 00dae4d3d35d4f526929633b76e00b0ab4d3970d Author: Jason Ekstrand Date: Thu Jul 8 10:48:12 2021 -0500 drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4) We could fix the bug by holding ctx->mutex in execbuf and clear the pointer (again while holding the mutex) context_close, but it's cleaner to just make the context object actually invariant over its _entire_ lifetime. This way any other ioctl that's potentially racing, but holding a full reference, can still rely on ctx->syncobj being an immutable pointer. Which without this change, is not the case. Reviewed-by: Maarten Lankhorst Signed-off-by: Daniel Vetter Fixes: 00dae4d3d35d ("drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4)") Cc: Jason Ekstrand Cc: Chris Wilson Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: Matthew Brost Cc: Matthew Auld Cc: Maarten Lankhorst Cc: "Thomas Hellström" Cc: Lionel Landwerlin Cc: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/20210902142057.929669-2-daniel.vetter@ffwll.ch (cherry picked from commit c238980efd3b35af70fc926066cf7440f50a97a9) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index cff72679ad7c..9ccf4b29b82e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -986,6 +986,9 @@ void i915_gem_context_release(struct kref *ref) trace_i915_context_free(ctx); GEM_BUG_ON(!i915_gem_context_is_closed(ctx)); + if (ctx->syncobj) + drm_syncobj_put(ctx->syncobj); + mutex_destroy(&ctx->engines_mutex); mutex_destroy(&ctx->lut_mutex); @@ -1205,9 +1208,6 @@ static void context_close(struct i915_gem_context *ctx) if (vm) i915_vm_close(vm); - if (ctx->syncobj) - drm_syncobj_put(ctx->syncobj); - ctx->file_priv = ERR_PTR(-EBADF); /* From 00598d5c69318a1fcb4147878e16754ba9103be6 Mon Sep 17 00:00:00 2001 From: Vinay Belgaumkar Date: Tue, 7 Sep 2021 16:27:04 -0700 Subject: [PATCH 178/866] drm/i915: Get PM ref before accessing HW register Seeing these errors when GT is likely in suspend state- "RPM wakelock ref not held during HW access" Ensure GT is awake before trying to access HW registers. Avoid reading the register if that is not the case. Signed-off-by: Vinay Belgaumkar Fixes: 41e5c17ebfc2 ("drm/i915/guc/slpc: Sysfs hooks for SLPC") Reviewed-by: Tvrtko Ursulin Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20210907232704.12982-1-vinay.belgaumkar@intel.com (cherry picked from commit f25e3908b9cd4a3fe819e9bdcdde58f20bacb34c) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_rps.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index d812b27835f8..591a5224287e 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1973,8 +1973,14 @@ u32 intel_rps_read_actual_frequency(struct intel_rps *rps) u32 intel_rps_read_punit_req(struct intel_rps *rps) { struct intel_uncore *uncore = rps_to_uncore(rps); + struct intel_runtime_pm *rpm = rps_to_uncore(rps)->rpm; + intel_wakeref_t wakeref; + u32 freq = 0; - return intel_uncore_read(uncore, GEN6_RPNSWREQ); + with_intel_runtime_pm_if_in_use(rpm, wakeref) + freq = intel_uncore_read(uncore, GEN6_RPNSWREQ); + + return freq; } static u32 intel_rps_get_req(u32 pureq) From 79e9e30a9292a62d25ab75488d3886108db1eaad Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 3 Sep 2021 00:05:50 -0500 Subject: [PATCH 179/866] serial: 8250: 8250_omap: Fix RX_LVL register offset Commit b67e830d38fa ("serial: 8250: 8250_omap: Fix possible interrupt storm on K3 SoCs") introduced fixup including a register read to RX_LVL, however, we should be using word offset than byte offset since our registers are on 4 byte boundary (port.regshift = 2) for 8250_omap. Fixes: b67e830d38fa ("serial: 8250: 8250_omap: Fix possible interrupt storm on K3 SoCs") Cc: stable Cc: Jan Kiszka Cc: Vignesh Raghavendra Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20210903050550.29050-1-nm@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_omap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 891fd8345e25..73e5f1dbd075 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -106,7 +106,7 @@ #define UART_OMAP_EFR2_TIMEOUT_BEHAVE BIT(6) /* RX FIFO occupancy indicator */ -#define UART_OMAP_RX_LVL 0x64 +#define UART_OMAP_RX_LVL 0x19 struct omap8250_priv { int line; From 74e1eb3b4a1ef2e564b4bdeb6e92afe844e900de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 11 Sep 2021 15:20:17 +0200 Subject: [PATCH 180/866] serial: mvebu-uart: fix driver's tx_empty callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Driver's tx_empty callback should signal when the transmit shift register is empty. So when the last character has been sent. STAT_TX_FIFO_EMP bit signals only that HW transmit FIFO is empty, which happens when the last byte is loaded into transmit shift register. STAT_TX_EMP bit signals when the both HW transmit FIFO and transmit shift register are empty. So replace STAT_TX_FIFO_EMP check by STAT_TX_EMP in mvebu_uart_tx_empty() callback function. Fixes: 30530791a7a0 ("serial: mvebu-uart: initial support for Armada-3700 serial port") Cc: stable Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20210911132017.25505-1-pali@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/mvebu-uart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 231de29a6452..ab226da75f7b 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -163,7 +163,7 @@ static unsigned int mvebu_uart_tx_empty(struct uart_port *port) st = readl(port->membase + UART_STAT); spin_unlock_irqrestore(&port->lock, flags); - return (st & STAT_TX_FIFO_EMP) ? TIOCSER_TEMT : 0; + return (st & STAT_TX_EMP) ? TIOCSER_TEMT : 0; } static unsigned int mvebu_uart_get_mctrl(struct uart_port *port) From 13be2efc390acd2a46a69a359f6efc00ca434599 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 5 Mar 2021 12:21:40 +0000 Subject: [PATCH 181/866] rtc: cmos: Disable irq around direct invocation of cmos_interrupt() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As previously noted in commit 66e4f4a9cc38 ("rtc: cmos: Use spin_lock_irqsave() in cmos_interrupt()"): <4>[ 254.192378] WARNING: inconsistent lock state <4>[ 254.192384] 5.12.0-rc1-CI-CI_DRM_9834+ #1 Not tainted <4>[ 254.192396] -------------------------------- <4>[ 254.192400] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. <4>[ 254.192409] rtcwake/5309 [HC0[0]:SC0[0]:HE1:SE1] takes: <4>[ 254.192429] ffffffff8263c5f8 (rtc_lock){?...}-{2:2}, at: cmos_interrupt+0x18/0x100 <4>[ 254.192481] {IN-HARDIRQ-W} state was registered at: <4>[ 254.192488] lock_acquire+0xd1/0x3d0 <4>[ 254.192504] _raw_spin_lock+0x2a/0x40 <4>[ 254.192519] cmos_interrupt+0x18/0x100 <4>[ 254.192536] rtc_handler+0x1f/0xc0 <4>[ 254.192553] acpi_ev_fixed_event_detect+0x109/0x13c <4>[ 254.192574] acpi_ev_sci_xrupt_handler+0xb/0x28 <4>[ 254.192596] acpi_irq+0x13/0x30 <4>[ 254.192620] __handle_irq_event_percpu+0x43/0x2c0 <4>[ 254.192641] handle_irq_event_percpu+0x2b/0x70 <4>[ 254.192661] handle_irq_event+0x2f/0x50 <4>[ 254.192680] handle_fasteoi_irq+0x9e/0x150 <4>[ 254.192693] __common_interrupt+0x76/0x140 <4>[ 254.192715] common_interrupt+0x96/0xc0 <4>[ 254.192732] asm_common_interrupt+0x1e/0x40 <4>[ 254.192750] _raw_spin_unlock_irqrestore+0x38/0x60 <4>[ 254.192767] resume_irqs+0xba/0xf0 <4>[ 254.192786] dpm_resume_noirq+0x245/0x3d0 <4>[ 254.192811] suspend_devices_and_enter+0x230/0xaa0 <4>[ 254.192835] pm_suspend.cold.8+0x301/0x34a <4>[ 254.192859] state_store+0x7b/0xe0 <4>[ 254.192879] kernfs_fop_write_iter+0x11d/0x1c0 <4>[ 254.192899] new_sync_write+0x11d/0x1b0 <4>[ 254.192916] vfs_write+0x265/0x390 <4>[ 254.192933] ksys_write+0x5a/0xd0 <4>[ 254.192949] do_syscall_64+0x33/0x80 <4>[ 254.192965] entry_SYSCALL_64_after_hwframe+0x44/0xae <4>[ 254.192986] irq event stamp: 43775 <4>[ 254.192994] hardirqs last enabled at (43775): [] asm_sysvec_apic_timer_interrupt+0x12/0x20 <4>[ 254.193023] hardirqs last disabled at (43774): [] sysvec_apic_timer_interrupt+0xa/0xb0 <4>[ 254.193049] softirqs last enabled at (42548): [] __do_softirq+0x342/0x48e <4>[ 254.193074] softirqs last disabled at (42543): [] irq_exit_rcu+0xad/0xd0 <4>[ 254.193101] other info that might help us debug this: <4>[ 254.193107] Possible unsafe locking scenario: <4>[ 254.193112] CPU0 <4>[ 254.193117] ---- <4>[ 254.193121] lock(rtc_lock); <4>[ 254.193137] <4>[ 254.193142] lock(rtc_lock); <4>[ 254.193156] *** DEADLOCK *** <4>[ 254.193161] 6 locks held by rtcwake/5309: <4>[ 254.193174] #0: ffff888104861430 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x5a/0xd0 <4>[ 254.193232] #1: ffff88810f823288 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0xe7/0x1c0 <4>[ 254.193282] #2: ffff888100cef3c0 (kn->active#285 <7>[ 254.192706] i915 0000:00:02.0: [drm:intel_modeset_setup_hw_state [i915]] [CRTC:51:pipe A] hw state readout: disabled <4>[ 254.193307] ){.+.+}-{0:0}, at: kernfs_fop_write_iter+0xf0/0x1c0 <4>[ 254.193333] #3: ffffffff82649fa8 (system_transition_mutex){+.+.}-{3:3}, at: pm_suspend.cold.8+0xce/0x34a <4>[ 254.193387] #4: ffffffff827a2108 (acpi_scan_lock){+.+.}-{3:3}, at: acpi_suspend_begin+0x47/0x70 <4>[ 254.193433] #5: ffff8881019ea178 (&dev->mutex){....}-{3:3}, at: device_resume+0x68/0x1e0 <4>[ 254.193485] stack backtrace: <4>[ 254.193492] CPU: 1 PID: 5309 Comm: rtcwake Not tainted 5.12.0-rc1-CI-CI_DRM_9834+ #1 <4>[ 254.193514] Hardware name: Google Soraka/Soraka, BIOS MrChromebox-4.10 08/25/2019 <4>[ 254.193524] Call Trace: <4>[ 254.193536] dump_stack+0x7f/0xad <4>[ 254.193567] mark_lock.part.47+0x8ca/0xce0 <4>[ 254.193604] __lock_acquire+0x39b/0x2590 <4>[ 254.193626] ? asm_sysvec_apic_timer_interrupt+0x12/0x20 <4>[ 254.193660] lock_acquire+0xd1/0x3d0 <4>[ 254.193677] ? cmos_interrupt+0x18/0x100 <4>[ 254.193716] _raw_spin_lock+0x2a/0x40 <4>[ 254.193735] ? cmos_interrupt+0x18/0x100 <4>[ 254.193758] cmos_interrupt+0x18/0x100 <4>[ 254.193785] cmos_resume+0x2ac/0x2d0 <4>[ 254.193813] ? acpi_pm_set_device_wakeup+0x1f/0x110 <4>[ 254.193842] ? pnp_bus_suspend+0x10/0x10 <4>[ 254.193864] pnp_bus_resume+0x5e/0x90 <4>[ 254.193885] dpm_run_callback+0x5f/0x240 <4>[ 254.193914] device_resume+0xb2/0x1e0 <4>[ 254.193942] ? pm_dev_err+0x25/0x25 <4>[ 254.193974] dpm_resume+0xea/0x3f0 <4>[ 254.194005] dpm_resume_end+0x8/0x10 <4>[ 254.194030] suspend_devices_and_enter+0x29b/0xaa0 <4>[ 254.194066] pm_suspend.cold.8+0x301/0x34a <4>[ 254.194094] state_store+0x7b/0xe0 <4>[ 254.194124] kernfs_fop_write_iter+0x11d/0x1c0 <4>[ 254.194151] new_sync_write+0x11d/0x1b0 <4>[ 254.194183] vfs_write+0x265/0x390 <4>[ 254.194207] ksys_write+0x5a/0xd0 <4>[ 254.194232] do_syscall_64+0x33/0x80 <4>[ 254.194251] entry_SYSCALL_64_after_hwframe+0x44/0xae <4>[ 254.194274] RIP: 0033:0x7f07d79691e7 <4>[ 254.194293] Code: 64 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 <4>[ 254.194312] RSP: 002b:00007ffd9cc2c768 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 <4>[ 254.194337] RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007f07d79691e7 <4>[ 254.194352] RDX: 0000000000000004 RSI: 0000556ebfc63590 RDI: 000000000000000b <4>[ 254.194366] RBP: 0000556ebfc63590 R08: 0000000000000000 R09: 0000000000000004 <4>[ 254.194379] R10: 0000556ebf0ec2a6 R11: 0000000000000246 R12: 0000000000000004 which breaks S3-resume on fi-kbl-soraka presumably as that's slow enough to trigger the alarm during the suspend. Fixes: 6950d046eb6e ("rtc: cmos: Replace spin_lock_irqsave with spin_lock in hard IRQ") References: 66e4f4a9cc38 ("rtc: cmos: Use spin_lock_irqsave() in cmos_interrupt()"): Signed-off-by: Chris Wilson Cc: Xiaofei Tan Cc: Alexandre Belloni Cc: Alessandro Zummo Cc: Ville Syrjälä Reviewed-by: Ville Syrjälä Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210305122140.28774-1-chris@chris-wilson.co.uk --- drivers/rtc/rtc-cmos.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index eb15067a605e..4eb53412b808 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1047,7 +1047,9 @@ static void cmos_check_wkalrm(struct device *dev) * ACK the rtc irq here */ if (t_now >= cmos->alarm_expires && cmos_use_acpi_alarm()) { + local_irq_disable(); cmos_interrupt(0, (void *)cmos->rtc); + local_irq_enable(); return; } From 81065b35e2486c024c7aa86caed452e1f01a59d4 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 13 Sep 2021 14:52:39 -0700 Subject: [PATCH 182/866] x86/mce: Avoid infinite loop for copy from user recovery There are two cases for machine check recovery: 1) The machine check was triggered by ring3 (application) code. This is the simpler case. The machine check handler simply queues work to be executed on return to user. That code unmaps the page from all users and arranges to send a SIGBUS to the task that triggered the poison. 2) The machine check was triggered in kernel code that is covered by an exception table entry. In this case the machine check handler still queues a work entry to unmap the page, etc. but this will not be called right away because the #MC handler returns to the fix up code address in the exception table entry. Problems occur if the kernel triggers another machine check before the return to user processes the first queued work item. Specifically, the work is queued using the ->mce_kill_me callback structure in the task struct for the current thread. Attempting to queue a second work item using this same callback results in a loop in the linked list of work functions to call. So when the kernel does return to user, it enters an infinite loop processing the same entry for ever. There are some legitimate scenarios where the kernel may take a second machine check before returning to the user. 1) Some code (e.g. futex) first tries a get_user() with page faults disabled. If this fails, the code retries with page faults enabled expecting that this will resolve the page fault. 2) Copy from user code retries a copy in byte-at-time mode to check whether any additional bytes can be copied. On the other side of the fence are some bad drivers that do not check the return value from individual get_user() calls and may access multiple user addresses without noticing that some/all calls have failed. Fix by adding a counter (current->mce_count) to keep track of repeated machine checks before task_work() is called. First machine check saves the address information and calls task_work_add(). Subsequent machine checks before that task_work call back is executed check that the address is in the same page as the first machine check (since the callback will offline exactly one page). Expected worst case is four machine checks before moving on (e.g. one user access with page faults disabled, then a repeat to the same address with page faults enabled ... repeat in copy tail bytes). Just in case there is some code that loops forever enforce a limit of 10. [ bp: Massage commit message, drop noinstr, fix typo, extend panic messages. ] Fixes: 5567d11c21a1 ("x86/mce: Send #MC singal from task work") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/YT/IJ9ziLqmtqEPu@agluck-desk2.amr.corp.intel.com --- arch/x86/kernel/cpu/mce/core.c | 43 +++++++++++++++++++++++++--------- include/linux/sched.h | 1 + 2 files changed, 33 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 8cb7816d03b4..193204aee880 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin static void kill_me_now(struct callback_head *ch) { + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; force_sig(SIGBUS); } @@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb) int flags = MF_ACTION_REQUIRED; int ret; + p->mce_count = 0; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) @@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, int kill_current_task) { - current->mce_addr = m->addr; - current->mce_kflags = m->kflags; - current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); - current->mce_whole_page = whole_page(m); + int count = ++current->mce_count; - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + + if (kill_current_task) + current->mce_kill_me.func = kill_me_now; + else + current->mce_kill_me.func = kill_me_maybe; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } @@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } else { /* @@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1780260f237b..361c7bc72cbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES From f81c08f897adafd2ed43f86f00207ff929f0b2eb Mon Sep 17 00:00:00 2001 From: Faizel K B Date: Thu, 2 Sep 2021 17:14:44 +0530 Subject: [PATCH 183/866] usb: testusb: Fix for showing the connection speed testusb' application which uses 'usbtest' driver reports 'unknown speed' from the function 'find_testdev'. The variable 'entry->speed' was not updated from the application. The IOCTL mentioned in the FIXME comment can only report whether the connection is low speed or not. Speed is read using the IOCTL USBDEVFS_GET_SPEED which reports the proper speed grade. The call is implemented in the function 'handle_testdev' where the file descriptor was availble locally. Sample output is given below where 'high speed' is printed as the connected speed. sudo ./testusb -a high speed /dev/bus/usb/001/011 0 /dev/bus/usb/001/011 test 0, 0.000015 secs /dev/bus/usb/001/011 test 1, 0.194208 secs /dev/bus/usb/001/011 test 2, 0.077289 secs /dev/bus/usb/001/011 test 3, 0.170604 secs /dev/bus/usb/001/011 test 4, 0.108335 secs /dev/bus/usb/001/011 test 5, 2.788076 secs /dev/bus/usb/001/011 test 6, 2.594610 secs /dev/bus/usb/001/011 test 7, 2.905459 secs /dev/bus/usb/001/011 test 8, 2.795193 secs /dev/bus/usb/001/011 test 9, 8.372651 secs /dev/bus/usb/001/011 test 10, 6.919731 secs /dev/bus/usb/001/011 test 11, 16.372687 secs /dev/bus/usb/001/011 test 12, 16.375233 secs /dev/bus/usb/001/011 test 13, 2.977457 secs /dev/bus/usb/001/011 test 14 --> 22 (Invalid argument) /dev/bus/usb/001/011 test 17, 0.148826 secs /dev/bus/usb/001/011 test 18, 0.068718 secs /dev/bus/usb/001/011 test 19, 0.125992 secs /dev/bus/usb/001/011 test 20, 0.127477 secs /dev/bus/usb/001/011 test 21 --> 22 (Invalid argument) /dev/bus/usb/001/011 test 24, 4.133763 secs /dev/bus/usb/001/011 test 27, 2.140066 secs /dev/bus/usb/001/011 test 28, 2.120713 secs /dev/bus/usb/001/011 test 29, 0.507762 secs Signed-off-by: Faizel K B Link: https://lore.kernel.org/r/20210902114444.15106-1-faizel.kb@dicortech.com Signed-off-by: Greg Kroah-Hartman --- tools/usb/testusb.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/tools/usb/testusb.c b/tools/usb/testusb.c index ee8208b2f946..69c3ead25313 100644 --- a/tools/usb/testusb.c +++ b/tools/usb/testusb.c @@ -265,12 +265,6 @@ nomem: } entry->ifnum = ifnum; - - /* FIXME update USBDEVFS_CONNECTINFO so it tells about high speed etc */ - - fprintf(stderr, "%s speed\t%s\t%u\n", - speed(entry->speed), entry->name, entry->ifnum); - entry->next = testdevs; testdevs = entry; return 0; @@ -299,6 +293,14 @@ static void *handle_testdev (void *arg) return 0; } + status = ioctl(fd, USBDEVFS_GET_SPEED, NULL); + if (status < 0) + fprintf(stderr, "USBDEVFS_GET_SPEED failed %d\n", status); + else + dev->speed = status; + fprintf(stderr, "%s speed\t%s\t%u\n", + speed(dev->speed), dev->name, dev->ifnum); + restart: for (i = 0; i < TEST_CASES; i++) { if (dev->test != -1 && dev->test != i) From 79f528afa93918519574773ea49a444c104bc1bd Mon Sep 17 00:00:00 2001 From: Anton Eidelman Date: Sun, 12 Sep 2021 12:54:57 -0600 Subject: [PATCH 184/866] nvme-multipath: fix ANA state updates when a namespace is not present nvme_update_ana_state() has a deficiency that results in a failure to properly update the ana state for a namespace in the following case: NSIDs in ctrl->namespaces: 1, 3, 4 NSIDs in desc->nsids: 1, 2, 3, 4 Loop iteration 0: ns index = 0, n = 0, ns->head->ns_id = 1, nsid = 1, MATCH. Loop iteration 1: ns index = 1, n = 1, ns->head->ns_id = 3, nsid = 2, NO MATCH. Loop iteration 2: ns index = 2, n = 2, ns->head->ns_id = 4, nsid = 4, MATCH. Where the update to the ANA state of NSID 3 is missed. To fix this increment n and retry the update with the same ns when ns->head->ns_id is higher than nsid, Signed-off-by: Anton Eidelman Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg --- drivers/nvme/host/multipath.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5d7bc58a27bd..e8ccdd398f78 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -600,14 +600,17 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) { - unsigned nsid = le32_to_cpu(desc->nsids[n]); - + unsigned nsid; +again: + nsid = le32_to_cpu(desc->nsids[n]); if (ns->head->ns_id < nsid) continue; if (ns->head->ns_id == nsid) nvme_update_ns_ana_state(desc, ns); if (++n == nr_nsids) break; + if (ns->head->ns_id > nsid) + goto again; } up_read(&ctrl->namespaces_rwsem); return 0; From 9817d763dbe15327b9b3ff4404fa6f27f927e744 Mon Sep 17 00:00:00 2001 From: Ruozhu Li Date: Mon, 6 Sep 2021 11:51:34 +0800 Subject: [PATCH 185/866] nvme-rdma: destroy cm id before destroy qp to avoid use after free We should always destroy cm_id before destroy qp to avoid to get cma event after qp was destroyed, which may lead to use after free. In RDMA connection establishment error flow, don't destroy qp in cm event handler.Just report cm_error to upper level, qp will be destroy in nvme_rdma_alloc_queue() after destroy cm id. Signed-off-by: Ruozhu Li Reviewed-by: Max Gurtovoy Signed-off-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index a68704e39084..042c594bc57e 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -656,8 +656,8 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) return; - nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + nvme_rdma_destroy_queue_ib(queue); mutex_destroy(&queue->queue_lock); } @@ -1815,14 +1815,10 @@ static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue) for (i = 0; i < queue->queue_size; i++) { ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]); if (ret) - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue, @@ -1916,14 +1912,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) if (ret) { dev_err(ctrl->ctrl.device, "rdma_connect_locked failed (%d).\n", ret); - goto out_destroy_queue_ib; + return ret; } return 0; - -out_destroy_queue_ib: - nvme_rdma_destroy_queue_ib(queue); - return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1954,8 +1946,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_UNREACHABLE: - nvme_rdma_destroy_queue_ib(queue); - fallthrough; case RDMA_CM_EVENT_ADDR_ERROR: dev_dbg(queue->ctrl->ctrl.device, "CM error event %d\n", ev->event); From 70f437fb4395ad4d1d16fab9a1ad9fbc9fc0579b Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 9 Sep 2021 08:54:52 -0700 Subject: [PATCH 186/866] nvme-tcp: fix io_work priority inversion Dispatching requests inline with the .queue_rq() call may block while holding the send_mutex. If the tcp io_work also happens to schedule, it may see the req_list is non-empty, leaving "pending" true and remaining in TASK_RUNNING. Since io_work is of higher scheduling priority, the .queue_rq task may not get a chance to run, blocking forward progress and leading to io timeouts. Instead of checking for pending requests within io_work, let the queueing restart io_work outside the send_mutex lock if there is more work to be done. Fixes: a0fdd1418007f ("nvme-tcp: rerun io_work if req_list is not empty") Reported-by: Samuel Jones Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index e2ab12f3f51c..e4249b7dc056 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -274,6 +274,12 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) } while (ret > 0); } +static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) +{ + return !list_empty(&queue->send_list) || + !llist_empty(&queue->req_list) || queue->more_requests; +} + static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, bool sync, bool last) { @@ -294,9 +300,10 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, nvme_tcp_send_all(queue); queue->more_requests = false; mutex_unlock(&queue->send_mutex); - } else if (last) { - queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } + + if (last && nvme_tcp_queue_more(queue)) + queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work); } static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue) @@ -906,12 +913,6 @@ done: read_unlock_bh(&sk->sk_callback_lock); } -static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) -{ - return !list_empty(&queue->send_list) || - !llist_empty(&queue->req_list) || queue->more_requests; -} - static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue) { queue->request = NULL; @@ -1145,8 +1146,7 @@ static void nvme_tcp_io_work(struct work_struct *w) pending = true; else if (unlikely(result < 0)) break; - } else - pending = !llist_empty(&queue->req_list); + } result = nvme_tcp_try_recv(queue); if (result > 0) From f5dfd98a80ff8d50cf4ae2820857d7f5a46cbab9 Mon Sep 17 00:00:00 2001 From: Pavel Hofman Date: Mon, 6 Sep 2021 15:08:22 +0200 Subject: [PATCH 187/866] usb: gadget: u_audio: EP-OUT bInterval in fback frequency The patch increases the bitshift in feedback frequency calculation with EP-OUT bInterval value. Tests have revealed that Win10 and OSX UAC2 drivers require the feedback frequency to be based on the actual packet interval instead of on the USB2 microframe. Otherwise they ignore the feedback value. Linux snd-usb-audio driver detects the applied bitshift automatically. Tested-by: Henrik Enquist Signed-off-by: Pavel Hofman Cc: stable Link: https://lore.kernel.org/r/20210906130822.12256-1-pavel.hofman@ivitera.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_audio.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index 32ef22857083..ad16163b5ff8 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -96,11 +96,13 @@ static const struct snd_pcm_hardware uac_pcm_hardware = { }; static void u_audio_set_fback_frequency(enum usb_device_speed speed, + struct usb_ep *out_ep, unsigned long long freq, unsigned int pitch, void *buf) { u32 ff = 0; + const struct usb_endpoint_descriptor *ep_desc; /* * Because the pitch base is 1000000, the final divider here @@ -128,8 +130,13 @@ static void u_audio_set_fback_frequency(enum usb_device_speed speed, * byte fromat (that is Q16.16) * * ff = (freq << 16) / 8000 + * + * Win10 and OSX UAC2 drivers require number of samples per packet + * in order to honor the feedback value. + * Linux snd-usb-audio detects the applied bit-shift automatically. */ - freq <<= 4; + ep_desc = out_ep->desc; + freq <<= 4 + (ep_desc->bInterval - 1); } ff = DIV_ROUND_CLOSEST_ULL((freq * pitch), 1953125); @@ -267,7 +274,7 @@ static void u_audio_iso_fback_complete(struct usb_ep *ep, pr_debug("%s: iso_complete status(%d) %d/%d\n", __func__, status, req->actual, req->length); - u_audio_set_fback_frequency(audio_dev->gadget->speed, + u_audio_set_fback_frequency(audio_dev->gadget->speed, audio_dev->out_ep, params->c_srate, prm->pitch, req->buf); @@ -526,7 +533,7 @@ int u_audio_start_capture(struct g_audio *audio_dev) * be meauserd at start of playback */ prm->pitch = 1000000; - u_audio_set_fback_frequency(audio_dev->gadget->speed, + u_audio_set_fback_frequency(audio_dev->gadget->speed, ep, params->c_srate, prm->pitch, req_fback->buf); From 17956b53ebff6a490baf580a836cbd3eae94892b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Sep 2021 12:42:21 +0300 Subject: [PATCH 188/866] usb: gadget: r8a66597: fix a loop in set_feature() This loop is supposed to loop until if reads something other than CS_IDST or until it times out after 30,000 attempts. But because of the || vs && bug, it will never time out and instead it will loop a minimum of 30,000 times. This bug is quite old but the code is only used in USB_DEVICE_TEST_MODE so it probably doesn't affect regular usage. Fixes: 96fe53ef5498 ("usb: gadget: r8a66597-udc: add support for TEST_MODE") Cc: stable Reviewed-by: Yoshihiro Shimoda Acked-by: Felipe Balbi Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20210906094221.GA10957@kili Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/r8a66597-udc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c index 65cae4883454..38e4d6b505a0 100644 --- a/drivers/usb/gadget/udc/r8a66597-udc.c +++ b/drivers/usb/gadget/udc/r8a66597-udc.c @@ -1250,7 +1250,7 @@ static void set_feature(struct r8a66597 *r8a66597, struct usb_ctrlrequest *ctrl) do { tmp = r8a66597_read(r8a66597, INTSTS0) & CTSQ; udelay(1); - } while (tmp != CS_IDST || timeout-- > 0); + } while (tmp != CS_IDST && timeout-- > 0); if (tmp == CS_IDST) r8a66597_bset(r8a66597, From b69ec50b3e55c4b2a85c8bc46763eaf330605847 Mon Sep 17 00:00:00 2001 From: Pawel Laszczak Date: Tue, 7 Sep 2021 08:26:19 +0200 Subject: [PATCH 189/866] usb: cdns3: fix race condition before setting doorbell For DEV_VER_V3 version there exist race condition between clearing ep_sts.EP_STS_TRBERR and setting ep_cmd.EP_CMD_DRDY bit. Setting EP_CMD_DRDY will be ignored by controller when EP_STS_TRBERR is set. So, between these two instructions we have a small time gap in which the EP_STSS_TRBERR can be set. In such case the transfer will not start after setting doorbell. Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") cc: # 5.12.x Tested-by: Aswath Govindraju Reviewed-by: Aswath Govindraju Signed-off-by: Pawel Laszczak Link: https://lore.kernel.org/r/20210907062619.34622-1-pawell@gli-login.cadence.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdns3-gadget.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 5d8c982019af..1f3b4a142212 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -1100,6 +1100,19 @@ static int cdns3_ep_run_stream_transfer(struct cdns3_endpoint *priv_ep, return 0; } +static void cdns3_rearm_drdy_if_needed(struct cdns3_endpoint *priv_ep) +{ + struct cdns3_device *priv_dev = priv_ep->cdns3_dev; + + if (priv_dev->dev_ver < DEV_VER_V3) + return; + + if (readl(&priv_dev->regs->ep_sts) & EP_STS_TRBERR) { + writel(EP_STS_TRBERR, &priv_dev->regs->ep_sts); + writel(EP_CMD_DRDY, &priv_dev->regs->ep_cmd); + } +} + /** * cdns3_ep_run_transfer - start transfer on no-default endpoint hardware * @priv_ep: endpoint object @@ -1351,6 +1364,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, /*clearing TRBERR and EP_STS_DESCMIS before seting DRDY*/ writel(EP_STS_TRBERR | EP_STS_DESCMIS, &priv_dev->regs->ep_sts); writel(EP_CMD_DRDY, &priv_dev->regs->ep_cmd); + cdns3_rearm_drdy_if_needed(priv_ep); trace_cdns3_doorbell_epx(priv_ep->name, readl(&priv_dev->regs->ep_traddr)); } From 856e6e8e0f9300befa87dde09edb578555c99a82 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 31 Aug 2021 16:42:36 +0800 Subject: [PATCH 190/866] usb: dwc2: check return value after calling platform_get_resource() It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value. Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20210831084236.1359677-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/hcd.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index 2a7828971d05..a215ec9e172e 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -5191,6 +5191,10 @@ int dwc2_hcd_init(struct dwc2_hsotg *hsotg) hcd->has_tt = 1; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + retval = -EINVAL; + goto error1; + } hcd->rsrc_start = res->start; hcd->rsrc_len = resource_size(res); From 91fac0741d4817945c6ee0a17591421e7f5ecb86 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 7 Sep 2021 10:23:18 +0200 Subject: [PATCH 191/866] USB: cdc-acm: fix minor-number release If the driver runs out of minor numbers it would release minor 0 and allow another device to claim the minor while still in use. Fortunately, registering the tty class device of the second device would fail (with a stack dump) due to the sysfs name collision so no memory is leaked. Fixes: cae2bc768d17 ("usb: cdc-acm: Decrement tty port's refcount if probe() fail") Cc: stable@vger.kernel.org # 4.19 Cc: Jaejoong Kim Acked-by: Oliver Neukum Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210907082318.7757-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-acm.c | 7 +++++-- drivers/usb/class/cdc-acm.h | 2 ++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 8bbd8e29e60d..4e2f1552f4b7 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -726,7 +726,8 @@ static void acm_port_destruct(struct tty_port *port) { struct acm *acm = container_of(port, struct acm, port); - acm_release_minor(acm); + if (acm->minor != ACM_MINOR_INVALID) + acm_release_minor(acm); usb_put_intf(acm->control); kfree(acm->country_codes); kfree(acm); @@ -1323,8 +1324,10 @@ made_compressed_probe: usb_get_intf(acm->control); /* undone in destruct() */ minor = acm_alloc_minor(acm); - if (minor < 0) + if (minor < 0) { + acm->minor = ACM_MINOR_INVALID; goto err_put_port; + } acm->minor = minor; acm->dev = usb_dev; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 8aef5eb769a0..3aa7f0a3ad71 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -22,6 +22,8 @@ #define ACM_TTY_MAJOR 166 #define ACM_TTY_MINORS 256 +#define ACM_MINOR_INVALID ACM_TTY_MINORS + /* * Requests. */ From aad06846a2304e48e7a223fad8971eed16179606 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 7 Sep 2021 05:30:02 -0700 Subject: [PATCH 192/866] usb: ehci: Simplify platform driver registration Use platform_register_drivers() and platform_unregister_drivers() to register and unregister ehci platform drivers. This simplifies the code and prevents the following build errors seen with sparc:allmodconfig. drivers/usb/host/ehci-hcd.c:1301: error: "PLATFORM_DRIVER" redefined drivers/usb/host/ehci-sh.c:173:31: error: 'ehci_hcd_sh_driver' defined but not used Acked-by: Alan Stern Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20210907123002.3951446-1-linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-hcd.c | 75 +++++++++++++------------------------ 1 file changed, 27 insertions(+), 48 deletions(-) diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 6bdc6d6bf74d..1776c05d0a48 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -1278,29 +1279,39 @@ MODULE_LICENSE ("GPL"); #ifdef CONFIG_USB_EHCI_SH #include "ehci-sh.c" -#define PLATFORM_DRIVER ehci_hcd_sh_driver #endif #ifdef CONFIG_PPC_PS3 #include "ehci-ps3.c" -#define PS3_SYSTEM_BUS_DRIVER ps3_ehci_driver #endif #ifdef CONFIG_USB_EHCI_HCD_PPC_OF #include "ehci-ppc-of.c" -#define OF_PLATFORM_DRIVER ehci_hcd_ppc_of_driver #endif #ifdef CONFIG_XPS_USB_HCD_XILINX #include "ehci-xilinx-of.c" -#define XILINX_OF_PLATFORM_DRIVER ehci_hcd_xilinx_of_driver #endif #ifdef CONFIG_SPARC_LEON #include "ehci-grlib.c" -#define PLATFORM_DRIVER ehci_grlib_driver #endif +static struct platform_driver * const platform_drivers[] = { +#ifdef CONFIG_USB_EHCI_SH + &ehci_hcd_sh_driver, +#endif +#ifdef CONFIG_USB_EHCI_HCD_PPC_OF + &ehci_hcd_ppc_of_driver, +#endif +#ifdef CONFIG_XPS_USB_HCD_XILINX + &ehci_hcd_xilinx_of_driver, +#endif +#ifdef CONFIG_SPARC_LEON + &ehci_grlib_driver, +#endif +}; + static int __init ehci_hcd_init(void) { int retval = 0; @@ -1324,47 +1335,23 @@ static int __init ehci_hcd_init(void) ehci_debug_root = debugfs_create_dir("ehci", usb_debug_root); #endif -#ifdef PLATFORM_DRIVER - retval = platform_driver_register(&PLATFORM_DRIVER); + retval = platform_register_drivers(platform_drivers, ARRAY_SIZE(platform_drivers)); if (retval < 0) goto clean0; -#endif -#ifdef PS3_SYSTEM_BUS_DRIVER - retval = ps3_ehci_driver_register(&PS3_SYSTEM_BUS_DRIVER); +#ifdef CONFIG_PPC_PS3 + retval = ps3_ehci_driver_register(&ps3_ehci_driver); if (retval < 0) - goto clean2; + goto clean1; #endif -#ifdef OF_PLATFORM_DRIVER - retval = platform_driver_register(&OF_PLATFORM_DRIVER); - if (retval < 0) - goto clean3; -#endif + return 0; -#ifdef XILINX_OF_PLATFORM_DRIVER - retval = platform_driver_register(&XILINX_OF_PLATFORM_DRIVER); - if (retval < 0) - goto clean4; +#ifdef CONFIG_PPC_PS3 +clean1: #endif - return retval; - -#ifdef XILINX_OF_PLATFORM_DRIVER - /* platform_driver_unregister(&XILINX_OF_PLATFORM_DRIVER); */ -clean4: -#endif -#ifdef OF_PLATFORM_DRIVER - platform_driver_unregister(&OF_PLATFORM_DRIVER); -clean3: -#endif -#ifdef PS3_SYSTEM_BUS_DRIVER - ps3_ehci_driver_unregister(&PS3_SYSTEM_BUS_DRIVER); -clean2: -#endif -#ifdef PLATFORM_DRIVER - platform_driver_unregister(&PLATFORM_DRIVER); + platform_unregister_drivers(platform_drivers, ARRAY_SIZE(platform_drivers)); clean0: -#endif #ifdef CONFIG_DYNAMIC_DEBUG debugfs_remove(ehci_debug_root); ehci_debug_root = NULL; @@ -1376,18 +1363,10 @@ module_init(ehci_hcd_init); static void __exit ehci_hcd_cleanup(void) { -#ifdef XILINX_OF_PLATFORM_DRIVER - platform_driver_unregister(&XILINX_OF_PLATFORM_DRIVER); -#endif -#ifdef OF_PLATFORM_DRIVER - platform_driver_unregister(&OF_PLATFORM_DRIVER); -#endif -#ifdef PLATFORM_DRIVER - platform_driver_unregister(&PLATFORM_DRIVER); -#endif -#ifdef PS3_SYSTEM_BUS_DRIVER - ps3_ehci_driver_unregister(&PS3_SYSTEM_BUS_DRIVER); +#ifdef CONFIG_PPC_PS3 + ps3_ehci_driver_unregister(&ps3_ehci_driver); #endif + platform_unregister_drivers(platform_drivers, ARRAY_SIZE(platform_drivers)); #ifdef CONFIG_DYNAMIC_DEBUG debugfs_remove(ehci_debug_root); #endif From d91adc5322ab53df4b6d1989242bfb6c63163eb2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 31 Aug 2021 08:54:19 +0200 Subject: [PATCH 193/866] Revert "USB: bcma: Add a check for devm_gpiod_get" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit f3de5d857bb2362b00e2a8d4bc886cd49dcb66db. That commit broke USB on all routers that have USB always powered on and don't require toggling any GPIO. It's a majority of devices actually. The original code worked and seemed safe: vcc GPIO is optional and bcma_hci_platform_power_gpio() takes care of checking the pointer before using it. This revert fixes: [ 10.801127] bcma_hcd: probe of bcma0:11 failed with error -2 Fixes: f3de5d857bb2 ("USB: bcma: Add a check for devm_gpiod_get") Cc: stable Cc: Chuhong Yuan Signed-off-by: Rafał Miłecki Link: https://lore.kernel.org/r/20210831065419.18371-1-zajec5@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/bcma-hcd.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/usb/host/bcma-hcd.c b/drivers/usb/host/bcma-hcd.c index 337b425dd4b0..2df52f75f6b3 100644 --- a/drivers/usb/host/bcma-hcd.c +++ b/drivers/usb/host/bcma-hcd.c @@ -406,12 +406,9 @@ static int bcma_hcd_probe(struct bcma_device *core) return -ENOMEM; usb_dev->core = core; - if (core->dev.of_node) { + if (core->dev.of_node) usb_dev->gpio_desc = devm_gpiod_get(&core->dev, "vcc", GPIOD_OUT_HIGH); - if (IS_ERR(usb_dev->gpio_desc)) - return PTR_ERR(usb_dev->gpio_desc); - } switch (core->id.id) { case BCMA_CORE_USB20_HOST: From 8cfac9a6744fcb143cb3e94ce002f09fd17fadbb Mon Sep 17 00:00:00 2001 From: Li Jun Date: Wed, 8 Sep 2021 10:28:19 +0800 Subject: [PATCH 194/866] usb: dwc3: core: balance phy init and exit After we start to do core soft reset while usb role switch, the phy init is invoked at every switch to device mode, but its counter part de-init is missing, this causes the actual phy init can not be done when we really want to re-init phy like system resume, because the counter maintained by phy core is not 0. considering phy init is actually redundant for role switch, so move out the phy init from core soft reset to dwc3 core init where is the only place required. Fixes: f88359e1588b ("usb: dwc3: core: Do core softreset when switch mode") Cc: Tested-by: faqiang.zhu Tested-by: John Stultz #HiKey960 Acked-by: Felipe Balbi Signed-off-by: Li Jun Link: https://lore.kernel.org/r/1631068099-13559-1-git-send-email-jun.li@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 01866dcb953b..0104a80b185e 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -264,19 +264,6 @@ static int dwc3_core_soft_reset(struct dwc3 *dwc) { u32 reg; int retries = 1000; - int ret; - - usb_phy_init(dwc->usb2_phy); - usb_phy_init(dwc->usb3_phy); - ret = phy_init(dwc->usb2_generic_phy); - if (ret < 0) - return ret; - - ret = phy_init(dwc->usb3_generic_phy); - if (ret < 0) { - phy_exit(dwc->usb2_generic_phy); - return ret; - } /* * We're resetting only the device side because, if we're in host mode, @@ -310,9 +297,6 @@ static int dwc3_core_soft_reset(struct dwc3 *dwc) udelay(1); } while (--retries); - phy_exit(dwc->usb3_generic_phy); - phy_exit(dwc->usb2_generic_phy); - return -ETIMEDOUT; done: @@ -982,9 +966,21 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc->phys_ready = true; } + usb_phy_init(dwc->usb2_phy); + usb_phy_init(dwc->usb3_phy); + ret = phy_init(dwc->usb2_generic_phy); + if (ret < 0) + goto err0a; + + ret = phy_init(dwc->usb3_generic_phy); + if (ret < 0) { + phy_exit(dwc->usb2_generic_phy); + goto err0a; + } + ret = dwc3_core_soft_reset(dwc); if (ret) - goto err0a; + goto err1; if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { From 91bb163e1e4f88092f50dfaa5a816b658753e4b2 Mon Sep 17 00:00:00 2001 From: Minas Harutyunyan Date: Thu, 9 Sep 2021 14:45:15 +0400 Subject: [PATCH 195/866] usb: dwc2: gadget: Fix ISOC flow for BDMA and Slave According USB spec each ISOC transaction should be performed in a designated for that transaction interval. On bus errors or delays in operating system scheduling of client software can result in no packet being transferred for a (micro)frame. An error indication should be returned as status to the client software in such a case. Current implementation in case of missed/dropped interval send same data in next possible interval instead of reporting missed isoc. This fix complete requests with -ENODATA if interval elapsed. HSOTG core in BDMA and Slave modes haven't HW support for (micro)frames tracking, this is why SW should care about tracking of (micro)frames. Because of that method and consider operating system scheduling delays, added few additional checking's of elapsed target (micro)frame: 1. Immediately before enabling EP to start transfer. 2. With any transfer completion interrupt. 3. With incomplete isoc in/out interrupt. 4. With EP disabled interrupt because of incomplete transfer. 5. With OUT token received while EP disabled interrupt (for OUT transfers). 6. With NAK replied to IN token interrupt (for IN transfers). As part of ISOC flow, additionally fixed 'current' and 'target' frame calculation functions. In HS mode SOF limits provided by DSTS register is 0x3fff, but in non HS mode this limit is 0x7ff. Tested by internal tool which also using for dwc3 testing. Signed-off-by: Minas Harutyunyan Cc: stable Link: https://lore.kernel.org/r/95d1423adf4b0f68187c9894820c4b7e964a3f7f.1631175721.git.Minas.Harutyunyan@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/gadget.c | 191 +++++++++++++++++++++----------------- 1 file changed, 107 insertions(+), 84 deletions(-) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 837237e4bc96..f09cbdfac9df 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -115,10 +115,16 @@ static inline bool using_desc_dma(struct dwc2_hsotg *hsotg) */ static inline void dwc2_gadget_incr_frame_num(struct dwc2_hsotg_ep *hs_ep) { + struct dwc2_hsotg *hsotg = hs_ep->parent; + u16 limit = DSTS_SOFFN_LIMIT; + + if (hsotg->gadget.speed != USB_SPEED_HIGH) + limit >>= 3; + hs_ep->target_frame += hs_ep->interval; - if (hs_ep->target_frame > DSTS_SOFFN_LIMIT) { + if (hs_ep->target_frame > limit) { hs_ep->frame_overrun = true; - hs_ep->target_frame &= DSTS_SOFFN_LIMIT; + hs_ep->target_frame &= limit; } else { hs_ep->frame_overrun = false; } @@ -136,10 +142,16 @@ static inline void dwc2_gadget_incr_frame_num(struct dwc2_hsotg_ep *hs_ep) */ static inline void dwc2_gadget_dec_frame_num_by_one(struct dwc2_hsotg_ep *hs_ep) { + struct dwc2_hsotg *hsotg = hs_ep->parent; + u16 limit = DSTS_SOFFN_LIMIT; + + if (hsotg->gadget.speed != USB_SPEED_HIGH) + limit >>= 3; + if (hs_ep->target_frame) hs_ep->target_frame -= 1; else - hs_ep->target_frame = DSTS_SOFFN_LIMIT; + hs_ep->target_frame = limit; } /** @@ -1018,6 +1030,12 @@ static void dwc2_gadget_start_isoc_ddma(struct dwc2_hsotg_ep *hs_ep) dwc2_writel(hsotg, ctrl, depctl); } +static bool dwc2_gadget_target_frame_elapsed(struct dwc2_hsotg_ep *hs_ep); +static void dwc2_hsotg_complete_request(struct dwc2_hsotg *hsotg, + struct dwc2_hsotg_ep *hs_ep, + struct dwc2_hsotg_req *hs_req, + int result); + /** * dwc2_hsotg_start_req - start a USB request from an endpoint's queue * @hsotg: The controller state. @@ -1170,14 +1188,19 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg, } } - if (hs_ep->isochronous && hs_ep->interval == 1) { - hs_ep->target_frame = dwc2_hsotg_read_frameno(hsotg); - dwc2_gadget_incr_frame_num(hs_ep); - - if (hs_ep->target_frame & 0x1) - ctrl |= DXEPCTL_SETODDFR; - else - ctrl |= DXEPCTL_SETEVENFR; + if (hs_ep->isochronous) { + if (!dwc2_gadget_target_frame_elapsed(hs_ep)) { + if (hs_ep->interval == 1) { + if (hs_ep->target_frame & 0x1) + ctrl |= DXEPCTL_SETODDFR; + else + ctrl |= DXEPCTL_SETEVENFR; + } + ctrl |= DXEPCTL_CNAK; + } else { + dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA); + return; + } } ctrl |= DXEPCTL_EPENA; /* ensure ep enabled */ @@ -1325,12 +1348,16 @@ static bool dwc2_gadget_target_frame_elapsed(struct dwc2_hsotg_ep *hs_ep) u32 target_frame = hs_ep->target_frame; u32 current_frame = hsotg->frame_number; bool frame_overrun = hs_ep->frame_overrun; + u16 limit = DSTS_SOFFN_LIMIT; + + if (hsotg->gadget.speed != USB_SPEED_HIGH) + limit >>= 3; if (!frame_overrun && current_frame >= target_frame) return true; if (frame_overrun && current_frame >= target_frame && - ((current_frame - target_frame) < DSTS_SOFFN_LIMIT / 2)) + ((current_frame - target_frame) < limit / 2)) return true; return false; @@ -1713,11 +1740,9 @@ static struct dwc2_hsotg_req *get_ep_head(struct dwc2_hsotg_ep *hs_ep) */ static void dwc2_gadget_start_next_request(struct dwc2_hsotg_ep *hs_ep) { - u32 mask; struct dwc2_hsotg *hsotg = hs_ep->parent; int dir_in = hs_ep->dir_in; struct dwc2_hsotg_req *hs_req; - u32 epmsk_reg = dir_in ? DIEPMSK : DOEPMSK; if (!list_empty(&hs_ep->queue)) { hs_req = get_ep_head(hs_ep); @@ -1733,9 +1758,6 @@ static void dwc2_gadget_start_next_request(struct dwc2_hsotg_ep *hs_ep) } else { dev_dbg(hsotg->dev, "%s: No more ISOC-OUT requests\n", __func__); - mask = dwc2_readl(hsotg, epmsk_reg); - mask |= DOEPMSK_OUTTKNEPDISMSK; - dwc2_writel(hsotg, mask, epmsk_reg); } } @@ -2306,19 +2328,6 @@ static void dwc2_hsotg_ep0_zlp(struct dwc2_hsotg *hsotg, bool dir_in) dwc2_hsotg_program_zlp(hsotg, hsotg->eps_out[0]); } -static void dwc2_hsotg_change_ep_iso_parity(struct dwc2_hsotg *hsotg, - u32 epctl_reg) -{ - u32 ctrl; - - ctrl = dwc2_readl(hsotg, epctl_reg); - if (ctrl & DXEPCTL_EOFRNUM) - ctrl |= DXEPCTL_SETEVENFR; - else - ctrl |= DXEPCTL_SETODDFR; - dwc2_writel(hsotg, ctrl, epctl_reg); -} - /* * dwc2_gadget_get_xfersize_ddma - get transferred bytes amount from desc * @hs_ep - The endpoint on which transfer went @@ -2439,20 +2448,11 @@ static void dwc2_hsotg_handle_outdone(struct dwc2_hsotg *hsotg, int epnum) dwc2_hsotg_ep0_zlp(hsotg, true); } - /* - * Slave mode OUT transfers do not go through XferComplete so - * adjust the ISOC parity here. - */ - if (!using_dma(hsotg)) { - if (hs_ep->isochronous && hs_ep->interval == 1) - dwc2_hsotg_change_ep_iso_parity(hsotg, DOEPCTL(epnum)); - else if (hs_ep->isochronous && hs_ep->interval > 1) - dwc2_gadget_incr_frame_num(hs_ep); - } - /* Set actual frame number for completed transfers */ - if (!using_desc_dma(hsotg) && hs_ep->isochronous) - req->frame_number = hsotg->frame_number; + if (!using_desc_dma(hsotg) && hs_ep->isochronous) { + req->frame_number = hs_ep->target_frame; + dwc2_gadget_incr_frame_num(hs_ep); + } dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, result); } @@ -2766,6 +2766,12 @@ static void dwc2_hsotg_complete_in(struct dwc2_hsotg *hsotg, return; } + /* Set actual frame number for completed transfers */ + if (!using_desc_dma(hsotg) && hs_ep->isochronous) { + hs_req->req.frame_number = hs_ep->target_frame; + dwc2_gadget_incr_frame_num(hs_ep); + } + dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, 0); } @@ -2826,23 +2832,18 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep) dwc2_hsotg_txfifo_flush(hsotg, hs_ep->fifo_index); - if (hs_ep->isochronous) { - dwc2_hsotg_complete_in(hsotg, hs_ep); - return; - } - if ((epctl & DXEPCTL_STALL) && (epctl & DXEPCTL_EPTYPE_BULK)) { int dctl = dwc2_readl(hsotg, DCTL); dctl |= DCTL_CGNPINNAK; dwc2_writel(hsotg, dctl, DCTL); } - return; - } + } else { - if (dctl & DCTL_GOUTNAKSTS) { - dctl |= DCTL_CGOUTNAK; - dwc2_writel(hsotg, dctl, DCTL); + if (dctl & DCTL_GOUTNAKSTS) { + dctl |= DCTL_CGOUTNAK; + dwc2_writel(hsotg, dctl, DCTL); + } } if (!hs_ep->isochronous) @@ -2863,8 +2864,6 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep) /* Update current frame number value. */ hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg); } while (dwc2_gadget_target_frame_elapsed(hs_ep)); - - dwc2_gadget_start_next_request(hs_ep); } /** @@ -2881,8 +2880,8 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep) static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep) { struct dwc2_hsotg *hsotg = ep->parent; + struct dwc2_hsotg_req *hs_req; int dir_in = ep->dir_in; - u32 doepmsk; if (dir_in || !ep->isochronous) return; @@ -2896,28 +2895,39 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep) return; } - if (ep->interval > 1 && - ep->target_frame == TARGET_FRAME_INITIAL) { + if (ep->target_frame == TARGET_FRAME_INITIAL) { u32 ctrl; ep->target_frame = hsotg->frame_number; - dwc2_gadget_incr_frame_num(ep); + if (ep->interval > 1) { + ctrl = dwc2_readl(hsotg, DOEPCTL(ep->index)); + if (ep->target_frame & 0x1) + ctrl |= DXEPCTL_SETODDFR; + else + ctrl |= DXEPCTL_SETEVENFR; - ctrl = dwc2_readl(hsotg, DOEPCTL(ep->index)); - if (ep->target_frame & 0x1) - ctrl |= DXEPCTL_SETODDFR; - else - ctrl |= DXEPCTL_SETEVENFR; - - dwc2_writel(hsotg, ctrl, DOEPCTL(ep->index)); + dwc2_writel(hsotg, ctrl, DOEPCTL(ep->index)); + } } - dwc2_gadget_start_next_request(ep); - doepmsk = dwc2_readl(hsotg, DOEPMSK); - doepmsk &= ~DOEPMSK_OUTTKNEPDISMSK; - dwc2_writel(hsotg, doepmsk, DOEPMSK); + while (dwc2_gadget_target_frame_elapsed(ep)) { + hs_req = get_ep_head(ep); + if (hs_req) + dwc2_hsotg_complete_request(hsotg, ep, hs_req, -ENODATA); + + dwc2_gadget_incr_frame_num(ep); + /* Update current frame number value. */ + hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg); + } + + if (!ep->req) + dwc2_gadget_start_next_request(ep); + } +static void dwc2_hsotg_ep_stop_xfr(struct dwc2_hsotg *hsotg, + struct dwc2_hsotg_ep *hs_ep); + /** * dwc2_gadget_handle_nak - handle NAK interrupt * @hs_ep: The endpoint on which interrupt is asserted. @@ -2935,7 +2945,9 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep) static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep) { struct dwc2_hsotg *hsotg = hs_ep->parent; + struct dwc2_hsotg_req *hs_req; int dir_in = hs_ep->dir_in; + u32 ctrl; if (!dir_in || !hs_ep->isochronous) return; @@ -2977,13 +2989,29 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep) dwc2_writel(hsotg, ctrl, DIEPCTL(hs_ep->index)); } - - dwc2_hsotg_complete_request(hsotg, hs_ep, - get_ep_head(hs_ep), 0); } - if (!using_desc_dma(hsotg)) + if (using_desc_dma(hsotg)) + return; + + ctrl = dwc2_readl(hsotg, DIEPCTL(hs_ep->index)); + if (ctrl & DXEPCTL_EPENA) + dwc2_hsotg_ep_stop_xfr(hsotg, hs_ep); + else + dwc2_hsotg_txfifo_flush(hsotg, hs_ep->fifo_index); + + while (dwc2_gadget_target_frame_elapsed(hs_ep)) { + hs_req = get_ep_head(hs_ep); + if (hs_req) + dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA); + dwc2_gadget_incr_frame_num(hs_ep); + /* Update current frame number value. */ + hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg); + } + + if (!hs_ep->req) + dwc2_gadget_start_next_request(hs_ep); } /** @@ -3048,12 +3076,8 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx, * need to look at completing IN requests here * if operating slave mode */ - if (hs_ep->isochronous && hs_ep->interval > 1) - dwc2_gadget_incr_frame_num(hs_ep); - - dwc2_hsotg_complete_in(hsotg, hs_ep); - if (ints & DXEPINT_NAKINTRPT) - ints &= ~DXEPINT_NAKINTRPT; + if (!hs_ep->isochronous || !(ints & DXEPINT_NAKINTRPT)) + dwc2_hsotg_complete_in(hsotg, hs_ep); if (idx == 0 && !hs_ep->req) dwc2_hsotg_enqueue_setup(hsotg); @@ -3062,10 +3086,8 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx, * We're using DMA, we need to fire an OutDone here * as we ignore the RXFIFO. */ - if (hs_ep->isochronous && hs_ep->interval > 1) - dwc2_gadget_incr_frame_num(hs_ep); - - dwc2_hsotg_handle_outdone(hsotg, idx); + if (!hs_ep->isochronous || !(ints & DXEPINT_OUTTKNEPDIS)) + dwc2_hsotg_handle_outdone(hsotg, idx); } } @@ -4085,6 +4107,7 @@ static int dwc2_hsotg_ep_enable(struct usb_ep *ep, mask |= DIEPMSK_NAKMSK; dwc2_writel(hsotg, mask, DIEPMSK); } else { + epctrl |= DXEPCTL_SNAK; mask = dwc2_readl(hsotg, DOEPMSK); mask |= DOEPMSK_OUTTKNEPDISMSK; dwc2_writel(hsotg, mask, DOEPMSK); From 58877b0824da15698bd85a0a9dbfa8c354e6ecb7 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 9 Sep 2021 12:11:58 +0530 Subject: [PATCH 196/866] usb: core: hcd: Add support for deferring roothub registration It has been observed with certain PCIe USB cards (like Inateck connected to AM64 EVM or J7200 EVM) that as soon as the primary roothub is registered, port status change is handled even before xHC is running leading to cold plug USB devices not detected. For such cases, registering both the root hubs along with the second HCD is required. Add support for deferring roothub registration in usb_add_hcd(), so that both primary and secondary roothubs are registered along with the second HCD. CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Acked-by: Alan Stern Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210909064200.16216-2-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 31 ++++++++++++++++++++++++------- include/linux/usb/hcd.h | 2 ++ 2 files changed, 26 insertions(+), 7 deletions(-) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 0f8b7c93310e..99ff2d23be05 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2775,6 +2775,7 @@ int usb_add_hcd(struct usb_hcd *hcd, { int retval; struct usb_device *rhdev; + struct usb_hcd *shared_hcd; if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); @@ -2935,13 +2936,26 @@ int usb_add_hcd(struct usb_hcd *hcd, goto err_hcd_driver_start; } - /* starting here, usbcore will pay attention to this root hub */ - retval = register_root_hub(hcd); - if (retval != 0) - goto err_register_root_hub; + /* starting here, usbcore will pay attention to the shared HCD roothub */ + shared_hcd = hcd->shared_hcd; + if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) { + retval = register_root_hub(shared_hcd); + if (retval != 0) + goto err_register_root_hub; - if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) - usb_hcd_poll_rh_status(hcd); + if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd)) + usb_hcd_poll_rh_status(shared_hcd); + } + + /* starting here, usbcore will pay attention to this root hub */ + if (!HCD_DEFER_RH_REGISTER(hcd)) { + retval = register_root_hub(hcd); + if (retval != 0) + goto err_register_root_hub; + + if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) + usb_hcd_poll_rh_status(hcd); + } return retval; @@ -2985,6 +2999,7 @@ EXPORT_SYMBOL_GPL(usb_add_hcd); void usb_remove_hcd(struct usb_hcd *hcd) { struct usb_device *rhdev = hcd->self.root_hub; + bool rh_registered; dev_info(hcd->self.controller, "remove, state %x\n", hcd->state); @@ -2995,6 +3010,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) dev_dbg(hcd->self.controller, "roothub graceful disconnect\n"); spin_lock_irq (&hcd_root_hub_lock); + rh_registered = hcd->rh_registered; hcd->rh_registered = 0; spin_unlock_irq (&hcd_root_hub_lock); @@ -3004,7 +3020,8 @@ void usb_remove_hcd(struct usb_hcd *hcd) cancel_work_sync(&hcd->died_work); mutex_lock(&usb_bus_idr_lock); - usb_disconnect(&rhdev); /* Sets rhdev to NULL */ + if (rh_registered) + usb_disconnect(&rhdev); /* Sets rhdev to NULL */ mutex_unlock(&usb_bus_idr_lock); /* diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..2c1fc9212cf2 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,6 +124,7 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -134,6 +135,7 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) +#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default From b7a0a792f864583207c593b50fd1b752ed89f4c1 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 9 Sep 2021 12:11:59 +0530 Subject: [PATCH 197/866] xhci: Set HCD flag to defer primary roothub registration Set "HCD_FLAG_DEFER_RH_REGISTER" to hcd->flags in xhci_run() to defer registering primary roothub in usb_add_hcd(). This will make sure both primary roothub and secondary roothub will be registered along with the second HCD. This is required for cold plugged USB devices to be detected in certain PCIe USB cards (like Inateck USB card connected to AM64 EVM or J7200 EVM). CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210909064200.16216-3-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index f3dabd02382c..93c38b557afd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -692,6 +692,7 @@ int xhci_run(struct usb_hcd *hcd) if (ret) xhci_free_command(xhci, command); } + set_bit(HCD_FLAG_DEFER_RH_REGISTER, &hcd->flags); xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Finished xhci_run for USB2 roothub"); From 5cf86349e98b14f505f83aae45a6df2bacc15a7a Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 9 Sep 2021 12:12:00 +0530 Subject: [PATCH 198/866] usb: core: hcd: Modularize HCD stop configuration in usb_stop_hcd() No functional change. Since configuration to stop HCD is invoked from multiple places, group all of them in usb_stop_hcd(). Tested-by: Chris Chiu Acked-by: Alan Stern Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210909064200.16216-4-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 99ff2d23be05..7ee6e4cc0d89 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2760,6 +2760,26 @@ static void usb_put_invalidate_rhdev(struct usb_hcd *hcd) usb_put_dev(rhdev); } +/** + * usb_stop_hcd - Halt the HCD + * @hcd: the usb_hcd that has to be halted + * + * Stop the root-hub polling timer and invoke the HCD's ->stop callback. + */ +static void usb_stop_hcd(struct usb_hcd *hcd) +{ + hcd->rh_pollable = 0; + clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); + del_timer_sync(&hcd->rh_timer); + + hcd->driver->stop(hcd); + hcd->state = HC_STATE_HALT; + + /* In case the HCD restarted the timer, stop it again. */ + clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); + del_timer_sync(&hcd->rh_timer); +} + /** * usb_add_hcd - finish generic HCD structure initialization and register * @hcd: the usb_hcd structure to initialize @@ -2960,13 +2980,7 @@ int usb_add_hcd(struct usb_hcd *hcd, return retval; err_register_root_hub: - hcd->rh_pollable = 0; - clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); - del_timer_sync(&hcd->rh_timer); - hcd->driver->stop(hcd); - hcd->state = HC_STATE_HALT; - clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); - del_timer_sync(&hcd->rh_timer); + usb_stop_hcd(hcd); err_hcd_driver_start: if (usb_hcd_is_primary_hcd(hcd) && hcd->irq > 0) free_irq(irqnum, hcd); @@ -3039,16 +3053,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) * interrupt occurs), but usb_hcd_poll_rh_status() won't invoke * the hub_status_data() callback. */ - hcd->rh_pollable = 0; - clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); - del_timer_sync(&hcd->rh_timer); - - hcd->driver->stop(hcd); - hcd->state = HC_STATE_HALT; - - /* In case the HCD restarted the timer, stop it again. */ - clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); - del_timer_sync(&hcd->rh_timer); + usb_stop_hcd(hcd); if (usb_hcd_is_primary_hcd(hcd)) { if (hcd->irq > 0) From dbe2518b2d8eabffa74dbf7d9fdd7dacddab7fc0 Mon Sep 17 00:00:00 2001 From: Minas Harutyunyan Date: Sat, 11 Sep 2021 22:58:30 +0400 Subject: [PATCH 199/866] usb: dwc2: gadget: Fix ISOC transfer complete handling for DDMA When last descriptor in a descriptor list completed with XferComplete interrupt, core switching to handle next descriptor and assert BNA interrupt. Both these interrupts are set while dwc2_hsotg_epint() handler called. Each interrupt should be handled separately: first XferComplete interrupt then BNA interrupt, otherwise last completed transfer will not be giveback to function driver as completed request. Fixes: 729cac693eec ("usb: dwc2: Change ISOC DDMA flow") Cc: stable Signed-off-by: Minas Harutyunyan Link: https://lore.kernel.org/r/a36981accc26cd674c5d8f8da6164344b94ec1fe.1631386531.git.Minas.Harutyunyan@synopsys.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/gadget.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index f09cbdfac9df..11d85a6e0b0d 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3067,9 +3067,7 @@ static void dwc2_hsotg_epint(struct dwc2_hsotg *hsotg, unsigned int idx, /* In DDMA handle isochronous requests separately */ if (using_desc_dma(hsotg) && hs_ep->isochronous) { - /* XferCompl set along with BNA */ - if (!(ints & DXEPINT_BNAINTR)) - dwc2_gadget_complete_isoc_request_ddma(hs_ep); + dwc2_gadget_complete_isoc_request_ddma(hs_ep); } else if (dir_in) { /* * We get OutDone from the FIFO, so we only From 595091a1426a3b2625dad322f69fe569dc9d8943 Mon Sep 17 00:00:00 2001 From: Jack Pham Date: Thu, 9 Sep 2021 10:48:10 -0700 Subject: [PATCH 200/866] usb: gadget: f_uac2: Add missing companion descriptor for feedback EP The f_uac2 function fails to enumerate when connected in SuperSpeed due to the feedback endpoint missing the companion descriptor. Add a new ss_epin_fback_desc_comp descriptor and append it behind the ss_epin_fback_desc both in the static definition of the ss_audio_desc structure as well as its dynamic construction in setup_headers(). Fixes: 24f779dac8f3 ("usb: gadget: f_uac2/u_audio: add feedback endpoint support") Cc: stable Signed-off-by: Jack Pham Link: https://lore.kernel.org/r/20210909174811.12534-2-jackp@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_uac2.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 3c34995276e7..d89c1ebb07f4 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -406,6 +406,14 @@ static struct usb_endpoint_descriptor ss_epin_fback_desc = { .bInterval = 4, }; +static struct usb_ss_ep_comp_descriptor ss_epin_fback_desc_comp = { + .bLength = sizeof(ss_epin_fback_desc_comp), + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 0, + .bmAttributes = 0, + .wBytesPerInterval = cpu_to_le16(4), +}; + /* Audio Streaming IN Interface - Alt0 */ static struct usb_interface_descriptor std_as_in_if0_desc = { @@ -597,6 +605,7 @@ static struct usb_descriptor_header *ss_audio_desc[] = { (struct usb_descriptor_header *)&ss_epout_desc_comp, (struct usb_descriptor_header *)&as_iso_out_desc, (struct usb_descriptor_header *)&ss_epin_fback_desc, + (struct usb_descriptor_header *)&ss_epin_fback_desc_comp, (struct usb_descriptor_header *)&std_as_in_if0_desc, (struct usb_descriptor_header *)&std_as_in_if1_desc, @@ -705,6 +714,7 @@ static void setup_headers(struct f_uac2_opts *opts, { struct usb_ss_ep_comp_descriptor *epout_desc_comp = NULL; struct usb_ss_ep_comp_descriptor *epin_desc_comp = NULL; + struct usb_ss_ep_comp_descriptor *epin_fback_desc_comp = NULL; struct usb_endpoint_descriptor *epout_desc; struct usb_endpoint_descriptor *epin_desc; struct usb_endpoint_descriptor *epin_fback_desc; @@ -730,6 +740,7 @@ static void setup_headers(struct f_uac2_opts *opts, epout_desc_comp = &ss_epout_desc_comp; epin_desc_comp = &ss_epin_desc_comp; epin_fback_desc = &ss_epin_fback_desc; + epin_fback_desc_comp = &ss_epin_fback_desc_comp; ep_int_desc = &ss_ep_int_desc; } @@ -773,8 +784,11 @@ static void setup_headers(struct f_uac2_opts *opts, headers[i++] = USBDHDR(&as_iso_out_desc); - if (EPOUT_FBACK_IN_EN(opts)) + if (EPOUT_FBACK_IN_EN(opts)) { headers[i++] = USBDHDR(epin_fback_desc); + if (epin_fback_desc_comp) + headers[i++] = USBDHDR(epin_fback_desc_comp); + } } if (EPIN_EN(opts)) { From f0e8a206a2a53a919e1709c654cb65d519f7befb Mon Sep 17 00:00:00 2001 From: Jack Pham Date: Thu, 9 Sep 2021 10:48:11 -0700 Subject: [PATCH 201/866] usb: gadget: f_uac2: Populate SS descriptors' wBytesPerInterval For Isochronous endpoints, the SS companion descriptor's wBytesPerInterval field is required to reserve bus time in order to transmit the required payload during the service interval. If left at 0, the UAC2 function is unable to transact data on its playback or capture endpoints in SuperSpeed mode. Since f_uac2 currently does not support any bursting this value can be exactly equal to the calculated wMaxPacketSize. Tested with Windows 10 as a host. Fixes: f8cb3d556be3 ("usb: f_uac2: adds support for SS and SSP") Cc: stable Signed-off-by: Jack Pham Link: https://lore.kernel.org/r/20210909174811.12534-3-jackp@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_uac2.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index d89c1ebb07f4..be864560bfea 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1178,6 +1178,9 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) agdev->out_ep_maxpsize = max_t(u16, agdev->out_ep_maxpsize, le16_to_cpu(ss_epout_desc.wMaxPacketSize)); + ss_epin_desc_comp.wBytesPerInterval = ss_epin_desc.wMaxPacketSize; + ss_epout_desc_comp.wBytesPerInterval = ss_epout_desc.wMaxPacketSize; + // HS and SS endpoint addresses are copied from autoconfigured FS descriptors hs_ep_int_desc.bEndpointAddress = fs_ep_int_desc.bEndpointAddress; hs_epout_desc.bEndpointAddress = fs_epout_desc.bEndpointAddress; From 8d753db5c227d1f403c4bc9cae4ae02c862413cd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 8 Sep 2021 21:55:56 +0200 Subject: [PATCH 202/866] misc: genwqe: Fixes DMA mask setting Commit 505b08777d78 ("misc: genwqe: Use dma_set_mask_and_coherent to simplify code") changed the logic in the code. Instead of a ||, a && should have been used to keep the code the same. Fixes: 505b08777d78 ("misc: genwqe: Use dma_set_mask_and_coherent to simplify code") Cc: stable Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/be49835baa8ba6daba5813b399edf6300f7fdbda.1631130862.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/misc/genwqe/card_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c index 2e1befbd1ad9..693981891870 100644 --- a/drivers/misc/genwqe/card_base.c +++ b/drivers/misc/genwqe/card_base.c @@ -1090,7 +1090,7 @@ static int genwqe_pci_setup(struct genwqe_dev *cd) /* check for 64-bit DMA address supported (DAC) */ /* check for 32-bit DMA address supported (SAC) */ - if (dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)) || + if (dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32))) { dev_err(&pci_dev->dev, "err: neither DMA32 nor DMA64 supported\n"); From 06e49073dfba24df4b1073a068631b13a0039c34 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 1 Sep 2021 17:38:06 -0700 Subject: [PATCH 203/866] tty: synclink_gt: rename a conflicting function name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'set_signals()' in synclink_gt.c conflicts with an exported symbol in arch/um/, so change set_signals() to set_gtsignals(). Keep the function names similar by also changing get_signals() to get_gtsignals(). ../drivers/tty/synclink_gt.c:442:13: error: conflicting types for ‘set_signals’ static void set_signals(struct slgt_info *info); ^~~~~~~~~~~ In file included from ../include/linux/irqflags.h:16:0, from ../include/linux/spinlock.h:58, from ../include/linux/mm_types.h:9, from ../include/linux/buildid.h:5, from ../include/linux/module.h:14, from ../drivers/tty/synclink_gt.c:46: ../arch/um/include/asm/irqflags.h:6:5: note: previous declaration of ‘set_signals’ was here int set_signals(int enable); ^~~~~~~~~~~ Fixes: 705b6c7b34f2 ("[PATCH] new driver synclink_gt") Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Paul Fulghum Signed-off-by: Randy Dunlap Link: https://lore.kernel.org/r/20210902003806.17054-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/synclink_gt.c | 44 +++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index a9acd93e85b7..25c558e65ece 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -438,8 +438,8 @@ static void reset_tbufs(struct slgt_info *info); static void tdma_reset(struct slgt_info *info); static bool tx_load(struct slgt_info *info, const char *buf, unsigned int count); -static void get_signals(struct slgt_info *info); -static void set_signals(struct slgt_info *info); +static void get_gtsignals(struct slgt_info *info); +static void set_gtsignals(struct slgt_info *info); static void set_rate(struct slgt_info *info, u32 data_rate); static void bh_transmit(struct slgt_info *info); @@ -720,7 +720,7 @@ static void set_termios(struct tty_struct *tty, struct ktermios *old_termios) if ((old_termios->c_cflag & CBAUD) && !C_BAUD(tty)) { info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); spin_lock_irqsave(&info->lock,flags); - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); } @@ -730,7 +730,7 @@ static void set_termios(struct tty_struct *tty, struct ktermios *old_termios) if (!C_CRTSCTS(tty) || !tty_throttled(tty)) info->signals |= SerialSignal_RTS; spin_lock_irqsave(&info->lock,flags); - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); } @@ -1181,7 +1181,7 @@ static inline void line_info(struct seq_file *m, struct slgt_info *info) /* output current serial signal states */ spin_lock_irqsave(&info->lock,flags); - get_signals(info); + get_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); stat_buf[0] = 0; @@ -1281,7 +1281,7 @@ static void throttle(struct tty_struct * tty) if (C_CRTSCTS(tty)) { spin_lock_irqsave(&info->lock,flags); info->signals &= ~SerialSignal_RTS; - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); } } @@ -1306,7 +1306,7 @@ static void unthrottle(struct tty_struct * tty) if (C_CRTSCTS(tty)) { spin_lock_irqsave(&info->lock,flags); info->signals |= SerialSignal_RTS; - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); } } @@ -1477,7 +1477,7 @@ static int hdlcdev_open(struct net_device *dev) /* inform generic HDLC layer of current DCD status */ spin_lock_irqsave(&info->lock, flags); - get_signals(info); + get_gtsignals(info); spin_unlock_irqrestore(&info->lock, flags); if (info->signals & SerialSignal_DCD) netif_carrier_on(dev); @@ -2229,7 +2229,7 @@ static void isr_txeom(struct slgt_info *info, unsigned short status) if (info->params.mode != MGSL_MODE_ASYNC && info->drop_rts_on_tx_done) { info->signals &= ~SerialSignal_RTS; info->drop_rts_on_tx_done = false; - set_signals(info); + set_gtsignals(info); } #if SYNCLINK_GENERIC_HDLC @@ -2394,7 +2394,7 @@ static void shutdown(struct slgt_info *info) if (!info->port.tty || info->port.tty->termios.c_cflag & HUPCL) { info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); + set_gtsignals(info); } flush_cond_wait(&info->gpio_wait_q); @@ -2422,7 +2422,7 @@ static void program_hw(struct slgt_info *info) else async_mode(info); - set_signals(info); + set_gtsignals(info); info->dcd_chkcount = 0; info->cts_chkcount = 0; @@ -2430,7 +2430,7 @@ static void program_hw(struct slgt_info *info) info->dsr_chkcount = 0; slgt_irq_on(info, IRQ_DCD | IRQ_CTS | IRQ_DSR | IRQ_RI); - get_signals(info); + get_gtsignals(info); if (info->netcount || (info->port.tty && info->port.tty->termios.c_cflag & CREAD)) @@ -2667,7 +2667,7 @@ static int wait_mgsl_event(struct slgt_info *info, int __user *mask_ptr) spin_lock_irqsave(&info->lock,flags); /* return immediately if state matches requested events */ - get_signals(info); + get_gtsignals(info); s = info->signals; events = mask & @@ -3085,7 +3085,7 @@ static int tiocmget(struct tty_struct *tty) unsigned long flags; spin_lock_irqsave(&info->lock,flags); - get_signals(info); + get_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); result = ((info->signals & SerialSignal_RTS) ? TIOCM_RTS:0) + @@ -3124,7 +3124,7 @@ static int tiocmset(struct tty_struct *tty, info->signals &= ~SerialSignal_DTR; spin_lock_irqsave(&info->lock,flags); - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); return 0; } @@ -3135,7 +3135,7 @@ static int carrier_raised(struct tty_port *port) struct slgt_info *info = container_of(port, struct slgt_info, port); spin_lock_irqsave(&info->lock,flags); - get_signals(info); + get_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); return (info->signals & SerialSignal_DCD) ? 1 : 0; } @@ -3150,7 +3150,7 @@ static void dtr_rts(struct tty_port *port, int on) info->signals |= SerialSignal_RTS | SerialSignal_DTR; else info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); + set_gtsignals(info); spin_unlock_irqrestore(&info->lock,flags); } @@ -3948,10 +3948,10 @@ static void tx_start(struct slgt_info *info) if (info->params.mode != MGSL_MODE_ASYNC) { if (info->params.flags & HDLC_FLAG_AUTO_RTS) { - get_signals(info); + get_gtsignals(info); if (!(info->signals & SerialSignal_RTS)) { info->signals |= SerialSignal_RTS; - set_signals(info); + set_gtsignals(info); info->drop_rts_on_tx_done = true; } } @@ -4005,7 +4005,7 @@ static void reset_port(struct slgt_info *info) rx_stop(info); info->signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); + set_gtsignals(info); slgt_irq_off(info, IRQ_ALL | IRQ_MASTER); } @@ -4427,7 +4427,7 @@ static void tx_set_idle(struct slgt_info *info) /* * get state of V24 status (input) signals */ -static void get_signals(struct slgt_info *info) +static void get_gtsignals(struct slgt_info *info) { unsigned short status = rd_reg16(info, SSR); @@ -4489,7 +4489,7 @@ static void msc_set_vcr(struct slgt_info *info) /* * set state of V24 control (output) signals */ -static void set_signals(struct slgt_info *info) +static void set_gtsignals(struct slgt_info *info) { unsigned char val = rd_reg8(info, VCR); if (info->signals & SerialSignal_DTR) From ad7cc2d41b7a8d0c5c5ecff37c3de7a4e137b3a6 Mon Sep 17 00:00:00 2001 From: Cameron Berkenpas Date: Mon, 13 Sep 2021 14:26:29 -0700 Subject: [PATCH 204/866] ALSA: hda/realtek: Quirks to enable speaker output for Lenovo Legion 7i 15IMHG05, Yoga 7i 14ITL5/15ITL5, and 13s Gen2 laptops. This patch initializes and enables speaker output on the Lenovo Legion 7i 15IMHG05, Yoga 7i 14ITL5/15ITL5, and 13s Gen2 series of laptops using the HDA verb sequence specific to each model. Speaker automute is suppressed for the Lenovo Legion 7i 15IMHG05 to avoid breaking speaker output on resume and when devices are unplugged from its headphone jack. Thanks to: Andreas Holzer, Vincent Morel, sycxyc, Max Christian Pohle and all others that helped. [ minor coding style fixes by tiwai ] BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208555 Signed-off-by: Cameron Berkenpas Cc: Link: https://lore.kernel.org/r/20210913212627.339362-1-cam@neo-zeon.de Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 129 ++++++++++++++++++++++++++++++++++ 1 file changed, 129 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8b7a389b6aed..4407f7da57c4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6429,6 +6429,20 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, hda_fixup_thinkpad_acpi(codec, fix, action); } +/* Fixup for Lenovo Legion 15IMHg05 speaker output on headset removal. */ +static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->gen.suppress_auto_mute = 1; + break; + } +} + /* for alc295_fixup_hp_top_speakers */ #include "hp_x360_helper.c" @@ -6646,6 +6660,10 @@ enum { ALC623_FIXUP_LENOVO_THINKSTATION_P340, ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, ALC236_FIXUP_HP_LIMIT_INT_MIC_BOOST, + ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS, + ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, + ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, + ALC287_FIXUP_13S_GEN2_SPEAKERS }; static const struct hda_fixup alc269_fixups[] = { @@ -8236,6 +8254,113 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, }, + [ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + //.v.verbs = legion_15imhg05_coefs, + .v.verbs = (const struct hda_verb[]) { + // set left speaker Legion 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x1a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + // set right speaker Legion 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x42 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, + }, + [ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_legion_15imhg05_speakers, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, + [ALC287_FIXUP_YOGA7_14ITL_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + // set left speaker Yoga 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x1a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + // set right speaker Yoga 7i. + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x46 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, + [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x42 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8630,6 +8755,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP), + SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3852, "Lenovo Yoga 7 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), From da546d6b748e570aa6e44acaa515cfc43baeaa0d Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 3 Sep 2021 00:03:25 +0200 Subject: [PATCH 205/866] arm64: dts: qcom: ipq8074: remove USB tx-fifo-resize property tx-fifo-resize is now added by default by the dwc3-qcom driver to the SNPS DWC3 child node. So, lets drop the tx-fifo-resize property from dwc3-qcom nodes as having it there will cause the dwc3-qcom driver to error and abort probe with: [ 1.362938] dwc3-qcom 8af8800.usb: unable to add property [ 1.368405] dwc3-qcom 8af8800.usb: failed to register DWC3 Core, err=-17 Fixes: cefdd52fa045 ("usb: dwc3: dwc3-qcom: Enable tx-fifo-resize property by default") Signed-off-by: Robert Marko Link: https://lore.kernel.org/r/20210902220325.1783567-1-robimarko@gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/qcom/ipq8074.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index a620ac0d0b19..db333001df4d 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -487,7 +487,6 @@ interrupts = ; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; - tx-fifo-resize; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -528,7 +527,6 @@ interrupts = ; phys = <&qusb_phy_1>, <&usb1_ssphy>; phy-names = "usb2-phy", "usb3-phy"; - tx-fifo-resize; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; From 7049d853cfb928f50b6041cb4a5c6d6c1d8dd201 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:19 +0200 Subject: [PATCH 206/866] tty: unexport tty_ldisc_release Initially, tty_ldisc_release() was exported for speakup (spk_tty) while in staging. Later, the call to this function was removed as it was bogus anyway. Remove the export now. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ldisc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 756a4bfa6a69..3e4e0b20b4bb 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -812,7 +812,6 @@ void tty_ldisc_release(struct tty_struct *tty) tty_ldisc_debug(tty, "released\n"); } -EXPORT_SYMBOL_GPL(tty_ldisc_release); /** * tty_ldisc_init - ldisc setup for new tty From 25a1433216489de4abc889910f744e952cb6dbae Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Sep 2021 21:35:48 +0900 Subject: [PATCH 207/866] mcb: fix error handling in mcb_alloc_bus() There are two bugs: 1) If ida_simple_get() fails then this code calls put_device(carrier) but we haven't yet called get_device(carrier) and probably that leads to a use after free. 2) After device_initialize() then we need to use put_device() to release the bus. This will free the internal resources tied to the device and call mcb_free_bus() which will free the rest. Fixes: 5d9e2ab9fea4 ("mcb: Implement bus->dev.release callback") Fixes: 18d288198099 ("mcb: Correctly initialize the bus's device") Cc: stable@vger.kernel.org Signed-off-by: Dan Carpenter Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/32e160cf6864ce77f9d62948338e24db9fd8ead9.1630931319.git.johannes.thumshirn@wdc.com Signed-off-by: Greg Kroah-Hartman --- drivers/mcb/mcb-core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index edf4ee6eff25..cf128b3471d7 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -275,8 +275,8 @@ struct mcb_bus *mcb_alloc_bus(struct device *carrier) bus_nr = ida_simple_get(&mcb_ida, 0, 0, GFP_KERNEL); if (bus_nr < 0) { - rc = bus_nr; - goto err_free; + kfree(bus); + return ERR_PTR(bus_nr); } bus->bus_nr = bus_nr; @@ -291,12 +291,12 @@ struct mcb_bus *mcb_alloc_bus(struct device *carrier) dev_set_name(&bus->dev, "mcb:%d", bus_nr); rc = device_add(&bus->dev); if (rc) - goto err_free; + goto err_put; return bus; -err_free: - put_device(carrier); - kfree(bus); + +err_put: + put_device(&bus->dev); return ERR_PTR(rc); } EXPORT_SYMBOL_NS_GPL(mcb_alloc_bus, MCB); From 3c3c8e88c8712bfe06cd10d7ca77a94a33610cd6 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 13 Sep 2021 21:01:14 -0500 Subject: [PATCH 208/866] platform/x86: amd-pmc: Increase the response register timeout There have been reports of approximately a 0.9%-1.7% failure rate in SMU communication timeouts with s0i3 entry on some OEM designs. Currently the design in amd-pmc is to try every 100us for up to 20ms. However the GPU driver which also communicates with the SMU using a mailbox register which the driver polls every 1us for up to 2000ms. In the GPU driver this was increased by commit 055162645a40 ("drm/amd/pm: increase time out value when sending msg to SMU") Increase the maximum timeout used by amd-pmc to 2000ms to match this behavior. This has been shown to improve the stability for machines that randomly have failures. Cc: stable@kernel.org Reported-by: Julian Sikorski BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1629 Signed-off-by: Mario Limonciello Acked-by: Shyam Sundar S K Link: https://lore.kernel.org/r/20210914020115.655-1-mario.limonciello@amd.com Signed-off-by: Hans de Goede --- drivers/platform/x86/amd-pmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 3481479a2942..d6a7c896ac86 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -71,7 +71,7 @@ #define AMD_CPU_ID_YC 0x14B5 #define PMC_MSG_DELAY_MIN_US 100 -#define RESPONSE_REGISTER_LOOP_MAX 200 +#define RESPONSE_REGISTER_LOOP_MAX 20000 #define SOC_SUBSYSTEM_IP_MAX 12 #define DELAY_MIN_US 2000 From 550ac9c1aaaaf51fd42e20d461f0b1cdbd55b3d2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Sep 2021 11:08:36 -0700 Subject: [PATCH 209/866] net-caif: avoid user-triggerable WARN_ON(1) syszbot triggers this warning, which looks something we can easily prevent. If we initialize priv->list_field in chnl_net_init(), then always use list_del_init(), we can remove robust_list_del() completely. WARNING: CPU: 0 PID: 3233 at net/caif/chnl_net.c:67 robust_list_del net/caif/chnl_net.c:67 [inline] WARNING: CPU: 0 PID: 3233 at net/caif/chnl_net.c:67 chnl_net_uninit+0xc9/0x2e0 net/caif/chnl_net.c:375 Modules linked in: CPU: 0 PID: 3233 Comm: syz-executor.3 Not tainted 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:robust_list_del net/caif/chnl_net.c:67 [inline] RIP: 0010:chnl_net_uninit+0xc9/0x2e0 net/caif/chnl_net.c:375 Code: 89 eb e8 3a a3 ba f8 48 89 d8 48 c1 e8 03 42 80 3c 28 00 0f 85 bf 01 00 00 48 81 fb 00 14 4e 8d 48 8b 2b 75 d0 e8 17 a3 ba f8 <0f> 0b 5b 5d 41 5c 41 5d e9 0a a3 ba f8 4c 89 e3 e8 02 a3 ba f8 4c RSP: 0018:ffffc90009067248 EFLAGS: 00010202 RAX: 0000000000008780 RBX: ffffffff8d4e1400 RCX: ffffc9000fd34000 RDX: 0000000000040000 RSI: ffffffff88bb6e49 RDI: 0000000000000003 RBP: ffff88802cd9ee08 R08: 0000000000000000 R09: ffffffff8d0e6647 R10: ffffffff88bb6dc2 R11: 0000000000000000 R12: ffff88803791ae08 R13: dffffc0000000000 R14: 00000000e600ffce R15: ffff888073ed3480 FS: 00007fed10fa0700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2c322000 CR3: 00000000164a6000 CR4: 00000000001506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: register_netdevice+0xadf/0x1500 net/core/dev.c:10347 ipcaif_newlink+0x4c/0x260 net/caif/chnl_net.c:468 __rtnl_newlink+0x106d/0x1750 net/core/rtnetlink.c:3458 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3506 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5572 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 __sys_sendto+0x21c/0x320 net/socket.c:2036 __do_sys_sendto net/socket.c:2048 [inline] __se_sys_sendto net/socket.c:2044 [inline] __x64_sys_sendto+0xdd/0x1b0 net/socket.c:2044 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: cc36a070b590 ("net-caif: add CAIF netdevice") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/caif/chnl_net.c | 19 +++---------------- 1 file changed, 3 insertions(+), 16 deletions(-) diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 37b67194c0df..414dc5671c45 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -53,20 +53,6 @@ struct chnl_net { enum caif_states state; }; -static void robust_list_del(struct list_head *delete_node) -{ - struct list_head *list_node; - struct list_head *n; - ASSERT_RTNL(); - list_for_each_safe(list_node, n, &chnl_net_list) { - if (list_node == delete_node) { - list_del(list_node); - return; - } - } - WARN_ON(1); -} - static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) { struct sk_buff *skb; @@ -364,6 +350,7 @@ static int chnl_net_init(struct net_device *dev) ASSERT_RTNL(); priv = netdev_priv(dev); strncpy(priv->name, dev->name, sizeof(priv->name)); + INIT_LIST_HEAD(&priv->list_field); return 0; } @@ -372,7 +359,7 @@ static void chnl_net_uninit(struct net_device *dev) struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); - robust_list_del(&priv->list_field); + list_del_init(&priv->list_field); } static const struct net_device_ops netdev_ops = { @@ -537,7 +524,7 @@ static void __exit chnl_exit_module(void) rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); - list_del(list_node); + list_del_init(list_node); delete_device(dev); } rtnl_unlock(); From d53c66594dc7606b191bb2976901a691d291a316 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Mon, 30 Aug 2021 15:02:09 +0300 Subject: [PATCH 210/866] habanalabs: fix potential race in interrupt wait ioctl We have a potential race where a user interrupt can be received in between user thread value comparison and before request was added to wait list. This means that if no consecutive interrupt will be received, user thread will timeout and fail. The solution is to add the request to wait list before we perform the comparison. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../habanalabs/common/command_submission.c | 35 +++++++++++-------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 7b0516cf808b..9a8b9191c28c 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2740,10 +2740,20 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, else interrupt = &hdev->user_interrupt[interrupt_offset]; + /* Add pending user interrupt to relevant list for the interrupt + * handler to monitor + */ + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + + /* We check for completion value as interrupt could have been received + * before we added the node to the wait list + */ if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; - goto free_fence; + goto remove_pending_user_interrupt; } if (completion_value >= target_value) @@ -2752,14 +2762,7 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx, *status = CS_WAIT_STATUS_BUSY; if (!timeout_us || (*status == CS_WAIT_STATUS_COMPLETED)) - goto free_fence; - - /* Add pending user interrupt to relevant list for the interrupt - * handler to monitor - */ - spin_lock_irqsave(&interrupt->wait_list_lock, flags); - list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head); - spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + goto remove_pending_user_interrupt; wait_again: /* Wait for interrupt handler to signal completion */ @@ -2770,6 +2773,15 @@ wait_again: * If comparison fails, keep waiting until timeout expires */ if (completion_rc > 0) { + spin_lock_irqsave(&interrupt->wait_list_lock, flags); + /* reinit_completion must be called before we check for user + * completion value, otherwise, if interrupt is received after + * the comparison and before the next wait_for_completion, + * we will reach timeout and fail + */ + reinit_completion(&pend->fence.completion); + spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); + if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) { dev_err(hdev->dev, "Failed to copy completion value from user\n"); rc = -EFAULT; @@ -2780,11 +2792,7 @@ wait_again: if (completion_value >= target_value) { *status = CS_WAIT_STATUS_COMPLETED; } else { - spin_lock_irqsave(&interrupt->wait_list_lock, flags); - reinit_completion(&pend->fence.completion); timeout = completion_rc; - - spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); goto wait_again; } } else if (completion_rc == -ERESTARTSYS) { @@ -2802,7 +2810,6 @@ remove_pending_user_interrupt: list_del(&pend->wait_list_node); spin_unlock_irqrestore(&interrupt->wait_list_lock, flags); -free_fence: kfree(pend); hl_ctx_put(ctx); From beb71ee36e4de93c2b21d916fb94558333d99974 Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Wed, 1 Sep 2021 15:48:04 +0300 Subject: [PATCH 211/866] habanalabs: fix kernel OOPs related to staged cs In case of single staged cs with both first/last indications set, we reach a scenario where in cs_release function flow we don't cancel the TDR work before freeing the cs memory, this lead to kernel OOPs since when the timer expires the work pointer will be freed already. In addition treat wait encaps cs "not found" handle as "OK" for the user in order to keep the user interface for both legacy and encpas signal/wait features the same. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- .../habanalabs/common/command_submission.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 9a8b9191c28c..deb080830ecb 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -405,7 +405,7 @@ static void staged_cs_put(struct hl_device *hdev, struct hl_cs *cs) static void cs_handle_tdr(struct hl_device *hdev, struct hl_cs *cs) { bool next_entry_found = false; - struct hl_cs *next; + struct hl_cs *next, *first_cs; if (!cs_needs_timeout(cs)) return; @@ -415,9 +415,16 @@ static void cs_handle_tdr(struct hl_device *hdev, struct hl_cs *cs) /* We need to handle tdr only once for the complete staged submission. * Hence, we choose the CS that reaches this function first which is * the CS marked as 'staged_last'. + * In case single staged cs was submitted which has both first and last + * indications, then "cs_find_first" below will return NULL, since we + * removed the cs node from the list before getting here, + * in such cases just continue with the cs to cancel it's TDR work. */ - if (cs->staged_cs && cs->staged_last) - cs = hl_staged_cs_find_first(hdev, cs->staged_sequence); + if (cs->staged_cs && cs->staged_last) { + first_cs = hl_staged_cs_find_first(hdev, cs->staged_sequence); + if (first_cs) + cs = first_cs; + } spin_unlock(&hdev->cs_mirror_lock); @@ -2026,9 +2033,10 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, spin_unlock(&ctx->sig_mgr.lock); if (!handle_found) { - dev_err(hdev->dev, "Cannot find encapsulated signals handle for seq 0x%llx\n", + /* treat as signal CS already finished */ + dev_dbg(hdev->dev, "Cannot find encapsulated signals handle for seq 0x%llx\n", signal_seq); - rc = -EINVAL; + rc = 0; goto free_cs_chunk_array; } From 3e08f157c2587fc7ada93abed41aae19bcbf8a6b Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Wed, 30 Dec 2020 08:05:18 +0200 Subject: [PATCH 212/866] habanalabs/gaudi: use direct MSI in single mode Due to FLR scenario when running inside a VM, we must not use indirect MSI because it might cause some issues on VM destroy. In a VM we use single MSI mode in contrary to multi MSI mode which is used in bare-metal. Hence direct MSI should be used in single MSI mode only. Signed-off-by: Omer Shpigelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 9 ++++++--- .../misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h | 2 ++ 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 383865be3c2c..5249f8fd4d59 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -5802,6 +5802,7 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, { struct gaudi_device *gaudi = hdev->asic_specific; struct packet_msg_prot *cq_pkt; + u64 msi_addr; u32 tmp; cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); @@ -5823,10 +5824,12 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, cq_pkt->ctl = cpu_to_le32(tmp); cq_pkt->value = cpu_to_le32(1); - if (!gaudi->multi_msi_mode) - msi_vec = 0; + if (gaudi->multi_msi_mode) + msi_addr = mmPCIE_MSI_INTR_0 + msi_vec * 4; + else + msi_addr = mmPCIE_CORE_MSI_REQ; - cq_pkt->addr = cpu_to_le64(CFG_BASE + mmPCIE_MSI_INTR_0 + msi_vec * 4); + cq_pkt->addr = cpu_to_le64(CFG_BASE + msi_addr); } static void gaudi_update_eq_ci(struct hl_device *hdev, u32 val) diff --git a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h index ffdfbd9b3220..1a6576666794 100644 --- a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h +++ b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h @@ -308,6 +308,8 @@ #define mmPCIE_AUX_FLR_CTRL 0xC07394 #define mmPCIE_AUX_DBI 0xC07490 +#define mmPCIE_CORE_MSI_REQ 0xC04100 + #define mmPSOC_PCI_PLL_NR 0xC72100 #define mmSRAM_W_PLL_NR 0x4C8100 #define mmPSOC_HBM_PLL_NR 0xC74100 From d09ff62c820b5950ab9958e77620a8498efe9386 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 2 Sep 2021 09:47:53 +0300 Subject: [PATCH 213/866] habanalabs: fail collective wait when not supported As collective wait operation is required only when NIC ports are available, we disable the option to submit a CS in case all the ports are disabled, which is the current situation in the upstream driver. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index deb080830ecb..5b7de857fbc1 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -1995,6 +1995,15 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type, goto free_cs_chunk_array; } + if (!hdev->nic_ports_mask) { + atomic64_inc(&ctx->cs_counters.validation_drop_cnt); + atomic64_inc(&cntr->validation_drop_cnt); + dev_err(hdev->dev, + "Collective operations not supported when NIC ports are disabled"); + rc = -EINVAL; + goto free_cs_chunk_array; + } + collective_engine_id = chunk->collective_engine_id; } From fcffb759f7d53b8e6c6e91804eec994205099dd3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 3 Sep 2021 09:02:03 +0100 Subject: [PATCH 214/866] habanalabs: Fix spelling mistake "FEADBACK" -> "FEEDBACK" There is a spelling mistake in a literal string. Fix it. Signed-off-by: Colin Ian King Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/gaudi/gaudi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 5249f8fd4d59..14da87b38e83 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -395,7 +395,7 @@ static struct hl_hw_obj_name_entry gaudi_so_id_to_str[] = { static struct hl_hw_obj_name_entry gaudi_monitor_id_to_str[] = { { .id = 200, .name = "MON_OBJ_DMA_DOWN_FEEDBACK_RESET" }, - { .id = 201, .name = "MON_OBJ_DMA_UP_FEADBACK_RESET" }, + { .id = 201, .name = "MON_OBJ_DMA_UP_FEEDBACK_RESET" }, { .id = 203, .name = "MON_OBJ_DRAM_TO_SRAM_QUEUE_FENCE" }, { .id = 204, .name = "MON_OBJ_TPC_0_CLK_GATE" }, { .id = 205, .name = "MON_OBJ_TPC_1_CLK_GATE" }, From 0a5ff77bf0a94468d541735f919a633f167787e9 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 12 Sep 2021 10:25:49 +0300 Subject: [PATCH 215/866] habanalabs/gaudi: fix LBW RR configuration Couple of fixes to the LBW RR configuration: 1. Add missing configuration of the SM RR registers in the DMA_IF. 2. Remove HBW range that doesn't belong. 3. Add entire gap + DBG area, from end of TPC7 to end of entire DBG space. Signed-off-by: Oded Gabbay --- .../misc/habanalabs/gaudi/gaudi_security.c | 115 ++++++++++-------- 1 file changed, 67 insertions(+), 48 deletions(-) diff --git a/drivers/misc/habanalabs/gaudi/gaudi_security.c b/drivers/misc/habanalabs/gaudi/gaudi_security.c index cb265c00cf73..25ac87cebd45 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_security.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_security.c @@ -8,16 +8,21 @@ #include "gaudiP.h" #include "../include/gaudi/asic_reg/gaudi_regs.h" -#define GAUDI_NUMBER_OF_RR_REGS 24 -#define GAUDI_NUMBER_OF_LBW_RANGES 12 +#define GAUDI_NUMBER_OF_LBW_RR_REGS 28 +#define GAUDI_NUMBER_OF_HBW_RR_REGS 24 +#define GAUDI_NUMBER_OF_LBW_RANGES 10 -static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_HIT_WPROT, mmDMA_IF_W_S_DMA0_HIT_WPROT, mmDMA_IF_W_S_DMA1_HIT_WPROT, + mmDMA_IF_E_S_SOB_HIT_WPROT, mmDMA_IF_E_S_DMA0_HIT_WPROT, mmDMA_IF_E_S_DMA1_HIT_WPROT, + mmDMA_IF_W_N_SOB_HIT_WPROT, mmDMA_IF_W_N_DMA0_HIT_WPROT, mmDMA_IF_W_N_DMA1_HIT_WPROT, + mmDMA_IF_E_N_SOB_HIT_WPROT, mmDMA_IF_E_N_DMA0_HIT_WPROT, mmDMA_IF_E_N_DMA1_HIT_WPROT, mmSIF_RTR_0_LBW_RANGE_PROT_HIT_AW, @@ -38,13 +43,17 @@ static u64 gaudi_rr_lbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_HIT_AW, }; -static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_HIT_RPROT, mmDMA_IF_W_S_DMA0_HIT_RPROT, mmDMA_IF_W_S_DMA1_HIT_RPROT, + mmDMA_IF_E_S_SOB_HIT_RPROT, mmDMA_IF_E_S_DMA0_HIT_RPROT, mmDMA_IF_E_S_DMA1_HIT_RPROT, + mmDMA_IF_W_N_SOB_HIT_RPROT, mmDMA_IF_W_N_DMA0_HIT_RPROT, mmDMA_IF_W_N_DMA1_HIT_RPROT, + mmDMA_IF_E_N_SOB_HIT_RPROT, mmDMA_IF_E_N_DMA0_HIT_RPROT, mmDMA_IF_E_N_DMA1_HIT_RPROT, mmSIF_RTR_0_LBW_RANGE_PROT_HIT_AR, @@ -65,13 +74,17 @@ static u64 gaudi_rr_lbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_HIT_AR, }; -static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MIN_WPROT_0, mmDMA_IF_W_S_DMA0_MIN_WPROT_0, mmDMA_IF_W_S_DMA1_MIN_WPROT_0, + mmDMA_IF_E_S_SOB_MIN_WPROT_0, mmDMA_IF_E_S_DMA0_MIN_WPROT_0, mmDMA_IF_E_S_DMA1_MIN_WPROT_0, + mmDMA_IF_W_N_SOB_MIN_WPROT_0, mmDMA_IF_W_N_DMA0_MIN_WPROT_0, mmDMA_IF_W_N_DMA1_MIN_WPROT_0, + mmDMA_IF_E_N_SOB_MIN_WPROT_0, mmDMA_IF_E_N_DMA0_MIN_WPROT_0, mmDMA_IF_E_N_DMA1_MIN_WPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MIN_AW_0, @@ -92,13 +105,17 @@ static u64 gaudi_rr_lbw_min_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MIN_AW_0, }; -static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MAX_WPROT_0, mmDMA_IF_W_S_DMA0_MAX_WPROT_0, mmDMA_IF_W_S_DMA1_MAX_WPROT_0, + mmDMA_IF_E_S_SOB_MAX_WPROT_0, mmDMA_IF_E_S_DMA0_MAX_WPROT_0, mmDMA_IF_E_S_DMA1_MAX_WPROT_0, + mmDMA_IF_W_N_SOB_MAX_WPROT_0, mmDMA_IF_W_N_DMA0_MAX_WPROT_0, mmDMA_IF_W_N_DMA1_MAX_WPROT_0, + mmDMA_IF_E_N_SOB_MAX_WPROT_0, mmDMA_IF_E_N_DMA0_MAX_WPROT_0, mmDMA_IF_E_N_DMA1_MAX_WPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MAX_AW_0, @@ -119,13 +136,17 @@ static u64 gaudi_rr_lbw_max_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MAX_AW_0, }; -static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MIN_RPROT_0, mmDMA_IF_W_S_DMA0_MIN_RPROT_0, mmDMA_IF_W_S_DMA1_MIN_RPROT_0, + mmDMA_IF_E_S_SOB_MIN_RPROT_0, mmDMA_IF_E_S_DMA0_MIN_RPROT_0, mmDMA_IF_E_S_DMA1_MIN_RPROT_0, + mmDMA_IF_W_N_SOB_MIN_RPROT_0, mmDMA_IF_W_N_DMA0_MIN_RPROT_0, mmDMA_IF_W_N_DMA1_MIN_RPROT_0, + mmDMA_IF_E_N_SOB_MIN_RPROT_0, mmDMA_IF_E_N_DMA0_MIN_RPROT_0, mmDMA_IF_E_N_DMA1_MIN_RPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MIN_AR_0, @@ -146,13 +167,17 @@ static u64 gaudi_rr_lbw_min_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MIN_AR_0, }; -static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_LBW_RR_REGS] = { + mmDMA_IF_W_S_SOB_MAX_RPROT_0, mmDMA_IF_W_S_DMA0_MAX_RPROT_0, mmDMA_IF_W_S_DMA1_MAX_RPROT_0, + mmDMA_IF_E_S_SOB_MAX_RPROT_0, mmDMA_IF_E_S_DMA0_MAX_RPROT_0, mmDMA_IF_E_S_DMA1_MAX_RPROT_0, + mmDMA_IF_W_N_SOB_MAX_RPROT_0, mmDMA_IF_W_N_DMA0_MAX_RPROT_0, mmDMA_IF_W_N_DMA1_MAX_RPROT_0, + mmDMA_IF_E_N_SOB_MAX_RPROT_0, mmDMA_IF_E_N_DMA0_MAX_RPROT_0, mmDMA_IF_E_N_DMA1_MAX_RPROT_0, mmSIF_RTR_0_LBW_RANGE_PROT_MAX_AR_0, @@ -173,7 +198,7 @@ static u64 gaudi_rr_lbw_max_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_7_LBW_RANGE_PROT_MAX_AR_0, }; -static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_HIT_AW, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_HIT_AW, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_HIT_AW, @@ -200,7 +225,7 @@ static u64 gaudi_rr_hbw_hit_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_HIT_AW }; -static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_HIT_AR, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_HIT_AR, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_HIT_AR, @@ -227,7 +252,7 @@ static u64 gaudi_rr_hbw_hit_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_HIT_AR }; -static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_LOW_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AW_0, @@ -254,7 +279,7 @@ static u64 gaudi_rr_hbw_base_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_LOW_AW_0 }; -static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_HIGH_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AW_0, @@ -281,7 +306,7 @@ static u64 gaudi_rr_hbw_base_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_HIGH_AW_0 }; -static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_LOW_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AW_0, @@ -308,7 +333,7 @@ static u64 gaudi_rr_hbw_mask_low_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_LOW_AW_0 }; -static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AW_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_HIGH_AW_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AW_0, @@ -335,7 +360,7 @@ static u64 gaudi_rr_hbw_mask_high_aw_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_HIGH_AW_0 }; -static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_LOW_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_LOW_AR_0, @@ -362,7 +387,7 @@ static u64 gaudi_rr_hbw_base_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_LOW_AR_0 }; -static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_BASE_HIGH_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_BASE_HIGH_AR_0, @@ -389,7 +414,7 @@ static u64 gaudi_rr_hbw_base_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_BASE_HIGH_AR_0 }; -static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_LOW_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_LOW_AR_0, @@ -416,7 +441,7 @@ static u64 gaudi_rr_hbw_mask_low_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { mmNIF_RTR_CTRL_7_RANGE_SEC_MASK_LOW_AR_0 }; -static u64 gaudi_rr_hbw_mask_high_ar_regs[GAUDI_NUMBER_OF_RR_REGS] = { +static u64 gaudi_rr_hbw_mask_high_ar_regs[GAUDI_NUMBER_OF_HBW_RR_REGS] = { mmDMA_IF_W_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AR_0, mmDMA_IF_W_S_DOWN_CH1_RANGE_SEC_MASK_HIGH_AR_0, mmDMA_IF_E_S_DOWN_CH0_RANGE_SEC_MASK_HIGH_AR_0, @@ -12849,50 +12874,44 @@ static void gaudi_init_range_registers_lbw(struct hl_device *hdev) u32 lbw_rng_end[GAUDI_NUMBER_OF_LBW_RANGES]; int i, j; - lbw_rng_start[0] = (0xFBFE0000 & 0x3FFFFFF) - 1; - lbw_rng_end[0] = (0xFBFFF000 & 0x3FFFFFF) + 1; + lbw_rng_start[0] = (0xFC0E8000 & 0x3FFFFFF) - 1; /* 0x000E7FFF */ + lbw_rng_end[0] = (0xFC11FFFF & 0x3FFFFFF) + 1; /* 0x00120000 */ - lbw_rng_start[1] = (0xFC0E8000 & 0x3FFFFFF) - 1; - lbw_rng_end[1] = (0xFC120000 & 0x3FFFFFF) + 1; + lbw_rng_start[1] = (0xFC1E8000 & 0x3FFFFFF) - 1; /* 0x001E7FFF */ + lbw_rng_end[1] = (0xFC48FFFF & 0x3FFFFFF) + 1; /* 0x00490000 */ - lbw_rng_start[2] = (0xFC1E8000 & 0x3FFFFFF) - 1; - lbw_rng_end[2] = (0xFC48FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[2] = (0xFC600000 & 0x3FFFFFF) - 1; /* 0x005FFFFF */ + lbw_rng_end[2] = (0xFCC48FFF & 0x3FFFFFF) + 1; /* 0x00C49000 */ - lbw_rng_start[3] = (0xFC600000 & 0x3FFFFFF) - 1; - lbw_rng_end[3] = (0xFCC48FFF & 0x3FFFFFF) + 1; + lbw_rng_start[3] = (0xFCC4A000 & 0x3FFFFFF) - 1; /* 0x00C49FFF */ + lbw_rng_end[3] = (0xFCCDFFFF & 0x3FFFFFF) + 1; /* 0x00CE0000 */ - lbw_rng_start[4] = (0xFCC4A000 & 0x3FFFFFF) - 1; - lbw_rng_end[4] = (0xFCCDFFFF & 0x3FFFFFF) + 1; + lbw_rng_start[4] = (0xFCCE4000 & 0x3FFFFFF) - 1; /* 0x00CE3FFF */ + lbw_rng_end[4] = (0xFCD1FFFF & 0x3FFFFFF) + 1; /* 0x00D20000 */ - lbw_rng_start[5] = (0xFCCE4000 & 0x3FFFFFF) - 1; - lbw_rng_end[5] = (0xFCD1FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[5] = (0xFCD24000 & 0x3FFFFFF) - 1; /* 0x00D23FFF */ + lbw_rng_end[5] = (0xFCD5FFFF & 0x3FFFFFF) + 1; /* 0x00D60000 */ - lbw_rng_start[6] = (0xFCD24000 & 0x3FFFFFF) - 1; - lbw_rng_end[6] = (0xFCD5FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[6] = (0xFCD64000 & 0x3FFFFFF) - 1; /* 0x00D63FFF */ + lbw_rng_end[6] = (0xFCD9FFFF & 0x3FFFFFF) + 1; /* 0x00DA0000 */ - lbw_rng_start[7] = (0xFCD64000 & 0x3FFFFFF) - 1; - lbw_rng_end[7] = (0xFCD9FFFF & 0x3FFFFFF) + 1; + lbw_rng_start[7] = (0xFCDA4000 & 0x3FFFFFF) - 1; /* 0x00DA3FFF */ + lbw_rng_end[7] = (0xFCDDFFFF & 0x3FFFFFF) + 1; /* 0x00DE0000 */ - lbw_rng_start[8] = (0xFCDA4000 & 0x3FFFFFF) - 1; - lbw_rng_end[8] = (0xFCDDFFFF & 0x3FFFFFF) + 1; + lbw_rng_start[8] = (0xFCDE4000 & 0x3FFFFFF) - 1; /* 0x00DE3FFF */ + lbw_rng_end[8] = (0xFCE05FFF & 0x3FFFFFF) + 1; /* 0x00E06000 */ - lbw_rng_start[9] = (0xFCDE4000 & 0x3FFFFFF) - 1; - lbw_rng_end[9] = (0xFCE05FFF & 0x3FFFFFF) + 1; + lbw_rng_start[9] = (0xFCFC9000 & 0x3FFFFFF) - 1; /* 0x00FC8FFF */ + lbw_rng_end[9] = (0xFFFFFFFE & 0x3FFFFFF) + 1; /* 0x03FFFFFF */ - lbw_rng_start[10] = (0xFEC43000 & 0x3FFFFFF) - 1; - lbw_rng_end[10] = (0xFEC43FFF & 0x3FFFFFF) + 1; - - lbw_rng_start[11] = (0xFE484000 & 0x3FFFFFF) - 1; - lbw_rng_end[11] = (0xFE484FFF & 0x3FFFFFF) + 1; - - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_LBW_RR_REGS ; i++) { WREG32(gaudi_rr_lbw_hit_aw_regs[i], (1 << GAUDI_NUMBER_OF_LBW_RANGES) - 1); WREG32(gaudi_rr_lbw_hit_ar_regs[i], (1 << GAUDI_NUMBER_OF_LBW_RANGES) - 1); } - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) + for (i = 0 ; i < GAUDI_NUMBER_OF_LBW_RR_REGS ; i++) for (j = 0 ; j < GAUDI_NUMBER_OF_LBW_RANGES ; j++) { WREG32(gaudi_rr_lbw_min_aw_regs[i] + (j << 2), lbw_rng_start[j]); @@ -12939,12 +12958,12 @@ static void gaudi_init_range_registers_hbw(struct hl_device *hdev) * 6th range is the host */ - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_HBW_RR_REGS ; i++) { WREG32(gaudi_rr_hbw_hit_aw_regs[i], 0x1F); WREG32(gaudi_rr_hbw_hit_ar_regs[i], 0x1D); } - for (i = 0 ; i < GAUDI_NUMBER_OF_RR_REGS ; i++) { + for (i = 0 ; i < GAUDI_NUMBER_OF_HBW_RR_REGS ; i++) { WREG32(gaudi_rr_hbw_base_low_aw_regs[i], dram_addr_lo); WREG32(gaudi_rr_hbw_base_low_ar_regs[i], dram_addr_lo); From 3d3200ae167ba048a29e0c815987a3fdc90fc8d2 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 9 Sep 2021 09:56:37 +0300 Subject: [PATCH 216/866] habanalabs: rate limit multi CS completion errors As user can send wrong arguments to multi CS API, we rate limit the amount of errors dumped to dmesg, in addition we change the severity to warning. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 5b7de857fbc1..a4ed91ed991d 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -2630,7 +2630,8 @@ static int hl_multi_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data) * completed after the poll function. */ if (!mcs_data.completion_bitmap) { - dev_err(hdev->dev, "Multi-CS got completion on wait but no CS completed\n"); + dev_warn_ratelimited(hdev->dev, + "Multi-CS got completion on wait but no CS completed\n"); rc = -EFAULT; } } From 42254c2a4991b98ca3f86040a1a7b7b32a0c8c4a Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Sun, 12 Sep 2021 14:30:35 +0300 Subject: [PATCH 217/866] habanalabs: fix wait offset handling Add handling for case where the user doesn't set wait offset, and keeps it as 0. In such a case the driver will decrement one from this zero value which will cause the code to wait for wrong number of signals. The solution is to treat this case as in legacy wait cs, and wait for the next signal. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/hw_queue.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 76b7de8f1406..0743319b10c7 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -437,6 +437,7 @@ void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev, struct hl_cs_compl *cs_cmpl) { struct hl_cs_encaps_sig_handle *handle = cs->encaps_sig_hdl; + u32 offset = 0; cs_cmpl->hw_sob = handle->hw_sob; @@ -446,9 +447,13 @@ void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev, * set offset 1 for example he mean to wait only for the first * signal only, which will be pre_sob_val, and if he set offset 2 * then the value required is (pre_sob_val + 1) and so on... + * if user set wait offset to 0, then treat it as legacy wait cs, + * wait for the next signal. */ - cs_cmpl->sob_val = handle->pre_sob_val + - (job->encaps_sig_wait_offset - 1); + if (job->encaps_sig_wait_offset) + offset = job->encaps_sig_wait_offset - 1; + + cs_cmpl->sob_val = handle->pre_sob_val + offset; } static int init_wait_cs(struct hl_device *hdev, struct hl_cs *cs, From c8fee41957f036cbc8e840bd91e2087731df7f7e Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Sun, 12 Sep 2021 15:49:00 +0300 Subject: [PATCH 218/866] habanalabs: expose a single cs seq in staged submissions Staged submission consists of multiple command submissions. In order to be explicit, driver should return a single cs sequence for every cs in the submission, or else user may try to wait on an internal CS rather than waiting for the whole submission. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/command_submission.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index a4ed91ed991d..91b57544f7c6 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -1295,6 +1295,12 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks, if (rc) goto free_cs_object; + /* If this is a staged submission we must return the staged sequence + * rather than the internal CS sequence + */ + if (cs->staged_cs) + *cs_seq = cs->staged_sequence; + /* Validate ALL the CS chunks before submitting the CS */ for (i = 0 ; i < num_chunks ; i++) { struct hl_cs_chunk *chunk = &cs_chunk_array[i]; From 59583f747664046aaae5588d56d5954fab66cce8 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Wed, 8 Sep 2021 09:48:22 +0200 Subject: [PATCH 219/866] sparc32: page align size in arch_dma_alloc Commit 53b7670e5735 ("sparc: factor the dma coherent mapping into helper") lost the page align for the calls to dma_make_coherent and srmmu_unmapiorange. The latter cannot handle a non page aligned len argument. Signed-off-by: Andreas Larsson Reviewed-by: Sam Ravnborg Signed-off-by: Christoph Hellwig --- arch/sparc/kernel/ioport.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 8e1d72a16759..7ceae24b0ca9 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -356,7 +356,9 @@ err_nomem: void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { - if (!sparc_dma_free_resource(cpu_addr, PAGE_ALIGN(size))) + size = PAGE_ALIGN(size); + + if (!sparc_dma_free_resource(cpu_addr, size)) return; dma_make_coherent(dma_addr, size); From 4f884f3962767877d7aabbc1ec124d2c307a4257 Mon Sep 17 00:00:00 2001 From: zhenggy Date: Tue, 14 Sep 2021 09:51:15 +0800 Subject: [PATCH 220/866] tcp: fix tp->undo_retrans accounting in tcp_sacktag_one() Commit 10d3be569243 ("tcp-tso: do not split TSO packets at retransmit time") may directly retrans a multiple segments TSO/GSO packet without split, Since this commit, we can no longer assume that a retransmitted packet is a single segment. This patch fixes the tp->undo_retrans accounting in tcp_sacktag_one() that use the actual segments(pcount) of the retransmitted packet. Before that commit (10d3be569243), the assumption underlying the tp->undo_retrans-- seems correct. Fixes: 10d3be569243 ("tcp-tso: do not split TSO packets at retransmit time") Signed-off-by: zhenggy Reviewed-by: Eric Dumazet Acked-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3f7bd7ae7d7a..141e85e6422b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1346,7 +1346,7 @@ static u8 tcp_sacktag_one(struct sock *sk, if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) - tp->undo_retrans--; + tp->undo_retrans = max_t(int, 0, tp->undo_retrans - pcount); if ((sacked & TCPCB_SACKED_ACKED) && before(start_seq, state->reord)) state->reord = start_seq; From d198b27762644c71362e43a7533f89c92b115bcf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Sep 2021 22:18:51 -0700 Subject: [PATCH 221/866] Revert "Revert "ipv4: fix memory leaks in ip_cmsg_send() callers"" This reverts commit d7807a9adf4856171f8441f13078c33941df48ab. As mentioned in https://lkml.org/lkml/2021/9/13/1819 5 years old commit 919483096bfe ("ipv4: fix memory leaks in ip_cmsg_send() callers") was a correct fix. ip_cmsg_send() can loop over multiple cmsghdr() If IP_RETOPTS has been successful, but following cmsghdr generates an error, we do not free ipc.ok If IP_RETOPTS is not successful, we have freed the allocated temporary space, not the one currently in ipc.opt. Sure, code could be refactored, but let's not bring back old bugs. Fixes: d7807a9adf48 ("Revert "ipv4: fix memory leaks in ip_cmsg_send() callers"") Signed-off-by: Eric Dumazet Cc: Yajun Deng Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/ping.c | 5 +++-- net/ipv4/raw.c | 5 +++-- net/ipv4/udp.c | 5 +++-- 4 files changed, 10 insertions(+), 7 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 7cef9987ab4a..b297bb28556e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -279,7 +279,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, case IP_RETOPTS: err = cmsg->cmsg_len - sizeof(struct cmsghdr); - /* Our caller is responsible for freeing ipc->opt when err = 0 */ + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, KERNEL_SOCKPTR(CMSG_DATA(cmsg)), err < 40 ? err : 40); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c588f9f2f46c..1e44a43acfe2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -727,9 +727,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); - if (unlikely(err)) + if (unlikely(err)) { + kfree(ipc.opt); return err; - + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1c98063a3ae8..bb446e60cf58 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -562,9 +562,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); - if (unlikely(err)) + if (unlikely(err)) { + kfree(ipc.opt); goto out; - + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d5f5981d7a43..8851c9463b4b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1122,9 +1122,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (err > 0) err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); - if (unlikely(err < 0)) + if (unlikely(err < 0)) { + kfree(ipc.opt); return err; - + } if (ipc.opt) free = 1; connected = 0; From 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: [PATCH 222/866] iov_iter: add helper to save iov_iter state In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe --- include/linux/uio.h | 15 +++++++++++++++ lib/iov_iter.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..984c4ab74859 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +247,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f2d50d69a6c3..755c10c5138c 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1972,3 +1972,39 @@ int import_single_range(int rw, void __user *buf, size_t len, return 0; } EXPORT_SYMBOL(import_single_range); + +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) +{ + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; +} From 44df58d441a94de40d52fca67dc60790daee4266 Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Tue, 14 Sep 2021 22:38:52 +0800 Subject: [PATCH 223/866] io_uring: fix missing sigmask restore in io_cqring_wait() Move get_timespec() section in io_cqring_wait() before the sigmask saving, otherwise we'll fail to restore sigmask once get_timespec() returns error. Fixes: c73ebb685fb6 ("io_uring: add timeout support for io_uring_enter()") Signed-off-by: Xiaoguang Wang Link: https://lore.kernel.org/r/20210914143852.9663-1-xiaoguang.wang@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index a864a94364c6..94afd087e97b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7518,6 +7518,14 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, break; } while (1); + if (uts) { + struct timespec64 ts; + + if (get_timespec64(&ts, uts)) + return -EFAULT; + timeout = timespec64_to_jiffies(&ts); + } + if (sig) { #ifdef CONFIG_COMPAT if (in_compat_syscall()) @@ -7531,14 +7539,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - if (uts) { - struct timespec64 ts; - - if (get_timespec64(&ts, uts)) - return -EFAULT; - timeout = timespec64_to_jiffies(&ts); - } - init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); From 1619b69edce14c4a4665fa8ff4c587dcc77202a9 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 14 Sep 2021 22:17:23 +1000 Subject: [PATCH 224/866] powerpc/boot: Fix build failure since GCC 4.9 removal Stephen reported that the build was broken since commit 6d2ef226f2f1 ("compiler_attributes.h: drop __has_attribute() support for gcc4"), with errors such as: include/linux/compiler_attributes.h:296:5: warning: "__has_attribute" is not defined, evaluates to 0 [-Wundef] 296 | #if __has_attribute(__warning__) | ^~~~~~~~~~~~~~~ make[2]: *** [arch/powerpc/boot/Makefile:225: arch/powerpc/boot/crt0.o] Error 1 But we expect __has_attribute() to always be defined now that we've stopped using GCC 4. Linus debugged it to the point of reading the GCC sources, and noticing that the problem is that __has_attribute() is not defined when preprocessing assembly files, which is what we're doing here. Our assembly files don't include, or need, compiler_attributes.h, but they are getting it unconditionally from the -include in BOOT_CFLAGS, which is then added in its entirety to BOOT_AFLAGS. That -include was added in commit 77433830ed16 ("powerpc: boot: include compiler_attributes.h") so that we'd have "fallthrough" and other attributes defined for the C files in arch/powerpc/boot. But it's not needed for assembly files. The minimal fix is to move the addition to BOOT_CFLAGS of -include compiler_attributes.h until after we've copied BOOT_CFLAGS into BOOT_AFLAGS. That avoids including compiler_attributes.h for asm files, but makes no other change to BOOT_CFLAGS or BOOT_AFLAGS. Reported-by: Stephen Rothwell Debugged-by: Linus Torvalds Signed-off-by: Michael Ellerman Tested-by: Guenter Roeck Signed-off-by: Linus Torvalds --- arch/powerpc/boot/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6900d0ac2421..089ee3ea55c8 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -35,7 +35,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -include $(srctree)/include/linux/compiler_attributes.h \ $(LINUXINCLUDE) ifdef CONFIG_PPC64_BOOT_WRAPPER @@ -70,6 +69,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y) BOOTCFLAGS += -fno-stack-protector endif +BOOTCFLAGS += -include $(srctree)/include/linux/compiler_attributes.h BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) DTC_FLAGS ?= -p 1024 From 9c7b0ba887513b6681e7883d306df0a0fd580afa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 14 Sep 2021 16:12:52 +0100 Subject: [PATCH 225/866] io_uring: auto-removal for direct open/accept It might be inconvenient that direct open/accept deviates from the update semantics and fails if the slot is taken instead of removing a file sitting there. Implement this auto-removal. Note that removal might need to allocate and so may fail. However, if an empty slot is specified, it's guaraneed to not fail on the fd installation side for valid userspace programs. It's needed for users who can't tolerate such failures, e.g. accept where the other end never retries. Suggested-by: Franz-B. Tuneke Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/c896f14ea46b0eaa6c09d93149e665c2c37979b4.1631632300.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 52 +++++++++++++++++++++++++++++++++------------------ 1 file changed, 34 insertions(+), 18 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 94afd087e97b..ae489ab275dd 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8287,11 +8287,27 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, #endif } +static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, + struct io_rsrc_node *node, void *rsrc) +{ + struct io_rsrc_put *prsrc; + + prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); + if (!prsrc) + return -ENOMEM; + + prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->rsrc = rsrc; + list_add(&prsrc->list, &node->rsrc_list); + return 0; +} + static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; @@ -8307,9 +8323,22 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, slot_index = array_index_nospec(slot_index, ctx->nr_user_files); file_slot = io_fixed_file_slot(&ctx->file_table, slot_index); - ret = -EBADF; - if (file_slot->file_ptr) - goto err; + + if (file_slot->file_ptr) { + struct file *old_file; + + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto err; + + old_file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, slot_index, + ctx->rsrc_node, old_file); + if (ret) + goto err; + file_slot->file_ptr = 0; + needs_switch = true; + } *io_get_tag_slot(ctx->file_data, slot_index) = 0; io_fixed_file_set(file_slot, file); @@ -8321,27 +8350,14 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, ret = 0; err: + if (needs_switch) + io_rsrc_node_switch(ctx, ctx->file_data); io_ring_submit_unlock(ctx, !force_nonblock); if (ret) fput(file); return ret; } -static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, - struct io_rsrc_node *node, void *rsrc) -{ - struct io_rsrc_put *prsrc; - - prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); - if (!prsrc) - return -ENOMEM; - - prsrc->tag = *io_get_tag_slot(data, idx); - prsrc->rsrc = rsrc; - list_add(&prsrc->list, &node->rsrc_list); - return 0; -} - static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_rsrc_update2 *up, unsigned nr_args) From 4ad3ea1c69354328edcccb83c8a4d7d2f55e3c6a Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Aug 2021 15:54:25 -0700 Subject: [PATCH 226/866] drm/i915/selftests: Do not use import_obj uninitialized MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Clang warns a couple of times: drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:63:6: warning: variable 'import_obj' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized] if (import != &obj->base) { ^~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:80:22: note: uninitialized use occurs here i915_gem_object_put(import_obj); ^~~~~~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:63:2: note: remove the 'if' if its condition is always false if (import != &obj->base) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:38:46: note: initialize the variable 'import_obj' to silence this warning struct drm_i915_gem_object *obj, *import_obj; ^ = NULL Shuffle the import_obj initialization above these if statements so that it is not used uninitialized. Fixes: d7b2cb380b3a ("drm/i915/gem: Correct the locking and pin pattern for dma-buf (v8)") Reported-by: Dan Carpenter Reviewed-by: Thomas Hellström Signed-off-by: Nathan Chancellor Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210824225427.2065517-2-nathan@kernel.org (cherry picked from commit 4796054b381a586f4177a24e3d8b5a6a0a32ce62) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index ffae7df5e4d7..532c7955b300 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -59,13 +59,13 @@ static int igt_dmabuf_import_self(void *arg) err = PTR_ERR(import); goto out_dmabuf; } + import_obj = to_intel_bo(import); if (import != &obj->base) { pr_err("i915_gem_prime_import created a new object!\n"); err = -EINVAL; goto out_import; } - import_obj = to_intel_bo(import); i915_gem_object_lock(import_obj, NULL); err = __i915_gem_object_get_pages(import_obj); @@ -176,6 +176,7 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, err = PTR_ERR(import); goto out_dmabuf; } + import_obj = to_intel_bo(import); if (import == &obj->base) { pr_err("i915_gem_prime_import reused gem object!\n"); @@ -183,8 +184,6 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, goto out_import; } - import_obj = to_intel_bo(import); - i915_gem_object_lock(import_obj, NULL); err = __i915_gem_object_get_pages(import_obj); if (err) { From 347c4db2afc7f9cf536144d167579ccf1e9bf028 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Aug 2021 15:54:26 -0700 Subject: [PATCH 227/866] drm/i915/selftests: Always initialize err in igt_dmabuf_import_same_driver_lmem() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Clang warns: drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:127:13: warning: variable 'err' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (PTR_ERR(import) != -EOPNOTSUPP) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:138:9: note: uninitialized use occurs here return err; ^~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:127:9: note: remove the 'if' if its condition is always true } else if (PTR_ERR(import) != -EOPNOTSUPP) { ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c:95:9: note: initialize the variable 'err' to silence this warning int err; ^ = 0 The test is expected to pass if i915_gem_prime_import() returns -EOPNOTSUPP so initialize err to zero in this case. Fixes: cdb35d1ed6d2 ("drm/i915/gem: Migrate to system at dma-buf attach time (v7)") Reported-by: Dan Carpenter Reviewed-by: Thomas Hellström Signed-off-by: Nathan Chancellor Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210824225427.2065517-3-nathan@kernel.org (cherry picked from commit 46f20a353b80d02492655d99714f0566018a17e8) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index 532c7955b300..4a6bb64c3a35 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -128,6 +128,8 @@ static int igt_dmabuf_import_same_driver_lmem(void *arg) pr_err("i915_gem_prime_import failed with the wrong err=%ld\n", PTR_ERR(import)); err = PTR_ERR(import); + } else { + err = 0; } dma_buf_put(dmabuf); From 7889367d7795b3b1766e33ac1ae8a5fbc292108b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 24 Aug 2021 15:54:27 -0700 Subject: [PATCH 228/866] drm/i915: Enable -Wsometimes-uninitialized This warning helps catch uninitialized variables. It should have been enabled at the same time as commit b2423184ac33 ("drm/i915: Enable -Wuninitialized") but I did not realize they were disabled separately. Enable it now that i915 is clean so that it stays that way. Reviewed-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210824225427.2065517-4-nathan@kernel.org (cherry picked from commit 43192617f7816bb74584c1df06f57363afd15337) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/Makefile | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 642a5b5a1b81..335ba9f43d8f 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -19,7 +19,6 @@ subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers) subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable) # clang warnings subdir-ccflags-y += $(call cc-disable-warning, sign-compare) -subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized) subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides) subdir-ccflags-y += $(call cc-disable-warning, frame-address) subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror From cdef1196608892b9a46caa5f2b64095a7f0be60c Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 14 Sep 2021 16:56:23 +0000 Subject: [PATCH 229/866] cpufreq: schedutil: Destroy mutex before kobject_put() frees the memory Since commit e5c6b312ce3c ("cpufreq: schedutil: Use kobject release() method to free sugov_tunables") kobject_put() has kfree()d the attr_set before gov_attr_set_put() returns. kobject_put() isn't the last user of attr_set in gov_attr_set_put(), the subsequent mutex_destroy() triggers a use-after-free: | BUG: KASAN: use-after-free in mutex_is_locked+0x20/0x60 | Read of size 8 at addr ffff000800ca4250 by task cpuhp/2/20 | | CPU: 2 PID: 20 Comm: cpuhp/2 Not tainted 5.15.0-rc1 #12369 | Hardware name: ARM LTD ARM Juno Development Platform/ARM Juno Development | Platform, BIOS EDK II Jul 30 2018 | Call trace: | dump_backtrace+0x0/0x380 | show_stack+0x1c/0x30 | dump_stack_lvl+0x8c/0xb8 | print_address_description.constprop.0+0x74/0x2b8 | kasan_report+0x1f4/0x210 | kasan_check_range+0xfc/0x1a4 | __kasan_check_read+0x38/0x60 | mutex_is_locked+0x20/0x60 | mutex_destroy+0x80/0x100 | gov_attr_set_put+0xfc/0x150 | sugov_exit+0x78/0x190 | cpufreq_offline.isra.0+0x2c0/0x660 | cpuhp_cpufreq_offline+0x14/0x24 | cpuhp_invoke_callback+0x430/0x6d0 | cpuhp_thread_fun+0x1b0/0x624 | smpboot_thread_fn+0x5e0/0xa6c | kthread+0x3a0/0x450 | ret_from_fork+0x10/0x20 Swap the order of the calls. Fixes: e5c6b312ce3c ("cpufreq: schedutil: Use kobject release() method to free sugov_tunables") Cc: 4.7+ # 4.7+ Signed-off-by: James Morse Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq_governor_attr_set.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpufreq/cpufreq_governor_attr_set.c b/drivers/cpufreq/cpufreq_governor_attr_set.c index 66b05a326910..a6f365b9cc1a 100644 --- a/drivers/cpufreq/cpufreq_governor_attr_set.c +++ b/drivers/cpufreq/cpufreq_governor_attr_set.c @@ -74,8 +74,8 @@ unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *l if (count) return count; - kobject_put(&attr_set->kobj); mutex_destroy(&attr_set->update_lock); + kobject_put(&attr_set->kobj); return 0; } EXPORT_SYMBOL_GPL(gov_attr_set_put); From 5d329e1286b0a040264e239b80257c937f6e685f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 14 Sep 2021 11:08:37 -0600 Subject: [PATCH 230/866] io_uring: allow retry for O_NONBLOCK if async is supported A common complaint is that using O_NONBLOCK files with io_uring can be a bit of a pain. Be a bit nicer and allow normal retry IFF the file does support async behavior. This makes it possible to use io_uring more reliably with O_NONBLOCK files, for use cases where it either isn't possible or feasible to modify the file flags. Cc: stable@vger.kernel.org Reported-and-tested-by: Dan Melnic Signed-off-by: Jens Axboe --- fs/io_uring.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ae489ab275dd..3077f85a2638 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2843,7 +2843,8 @@ static bool io_file_supports_nowait(struct io_kiocb *req, int rw) return __io_file_supports_nowait(req->file, rw); } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + int rw) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; @@ -2865,8 +2866,13 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(ret)) return ret; - /* don't allow async punt for O_NONBLOCK or RWF_NOWAIT */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || (file->f_flags & O_NONBLOCK)) + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) req->flags |= REQ_F_NOWAIT; ioprio = READ_ONCE(sqe->ioprio); @@ -3349,7 +3355,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_prep_rw(req, sqe); + return io_prep_rw(req, sqe, READ); } /* @@ -3542,7 +3548,7 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_prep_rw(req, sqe); + return io_prep_rw(req, sqe, WRITE); } static int io_write(struct io_kiocb *req, unsigned int issue_flags) From 6a4746ba06191e23d30230738e94334b26590a8a Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Sat, 11 Sep 2021 10:40:08 +0300 Subject: [PATCH 231/866] ipc: remove memcg accounting for sops objects in do_semtimedop() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Linus proposes to revert an accounting for sops objects in do_semtimedop() because it's really just a temporary buffer for a single semtimedop() system call. This object can consume up to 2 pages, syscall is sleeping one, size and duration can be controlled by user, and this allocation can be repeated by many thread at the same time. However Shakeel Butt pointed that there are much more popular objects with the same life time and similar memory consumption, the accounting of which was decided to be rejected for performance reasons. Considering at least 2 pages for task_struct and 2 pages for the kernel stack, a back of the envelope calculation gives a footprint amplification of <1.5 so this temporal buffer can be safely ignored. The factor would IMO be interesting if it was >> 2 (from the PoV of excessive (ab)use, fine-grained accounting seems to be currently unfeasible due to performance impact). Link: https://lore.kernel.org/lkml/90e254df-0dfe-f080-011e-b7c53ee7fd20@virtuozzo.com/ Fixes: 18319498fdd4 ("memcg: enable accounting of ipc resources") Signed-off-by: Vasily Averin Acked-by: Michal Hocko Reviewed-by: Michal Koutný Acked-by: Shakeel Butt Signed-off-by: Linus Torvalds --- ipc/sem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ipc/sem.c b/ipc/sem.c index f833238df1ce..6693daf4fe11 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2238,7 +2238,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, return -EINVAL; if (nsops > SEMOPM_FAST) { - sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL_ACCOUNT); + sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); if (sops == NULL) return -ENOMEM; } From 8b4bd256674720709a9d858a219fcac6f2f253b5 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Thu, 9 Sep 2021 10:56:12 +0200 Subject: [PATCH 232/866] thermal/drivers/int340x: Do not set a wrong tcc offset on resume After upgrading to Linux 5.13.3 I noticed my laptop would shutdown due to overheat (when it should not). It turned out this was due to commit fe6a6de6692e ("thermal/drivers/int340x/processor_thermal: Fix tcc setting"). What happens is this drivers uses a global variable to keep track of the tcc offset (tcc_offset_save) and uses it on resume. The issue is this variable is initialized to 0, but is only set in tcc_offset_degree_celsius_store, i.e. when the tcc offset is explicitly set by userspace. If that does not happen, the resume path will set the offset to 0 (in my case the h/w default being 3, the offset would become too low after a suspend/resume cycle). The issue did not arise before commit fe6a6de6692e, as the function setting the offset would return if the offset was 0. This is no longer the case (rightfully). Fix this by not applying the offset if it wasn't saved before, reverting back to the old logic. A better approach will come later, but this will be easier to apply to stable kernels. The logic to restore the offset after a resume was there long before commit fe6a6de6692e, but as a value of 0 was considered invalid I'm referencing the commit that made the issue possible in the Fixes tag instead. Fixes: fe6a6de6692e ("thermal/drivers/int340x/processor_thermal: Fix tcc setting") Cc: stable@vger.kernel.org Cc: Srinivas Pandruvada Signed-off-by: Antoine Tenart Signed-off-by: Daniel Lezcano Reviewed-by: Srinivas Pandruvada Tested-by: Srinivas Pandruvada Link: https://lore.kernel.org/r/20210909085613.5577-2-atenart@kernel.org --- .../thermal/intel/int340x_thermal/processor_thermal_device.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c index 0f0038af2ad4..fb64acfd5e07 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c @@ -107,7 +107,7 @@ static int tcc_offset_update(unsigned int tcc) return 0; } -static unsigned int tcc_offset_save; +static int tcc_offset_save = -1; static ssize_t tcc_offset_degree_celsius_store(struct device *dev, struct device_attribute *attr, const char *buf, @@ -352,7 +352,8 @@ int proc_thermal_resume(struct device *dev) proc_dev = dev_get_drvdata(dev); proc_thermal_read_ppcc(proc_dev); - tcc_offset_update(tcc_offset_save); + if (tcc_offset_save >= 0) + tcc_offset_update(tcc_offset_save); return 0; } From 356ed64991c6847a0c4f2e8fa3b1133f7a14f1fc Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 14 Sep 2021 10:33:51 +0800 Subject: [PATCH 233/866] bpf: Handle return value of BPF_PROG_TYPE_STRUCT_OPS prog Currently if a function ptr in struct_ops has a return value, its caller will get a random return value from it, because the return value of related BPF_PROG_TYPE_STRUCT_OPS prog is just dropped. So adding a new flag BPF_TRAMP_F_RET_FENTRY_RET to tell bpf trampoline to save and return the return value of struct_ops prog if ret_size of the function ptr is greater than 0. Also restricting the flag to be used alone. Fixes: 85d33df357b6 ("bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS") Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210914023351.3664499-1-houtao1@huawei.com --- arch/x86/net/bpf_jit_comp.c | 53 ++++++++++++++++++++++++++++--------- include/linux/bpf.h | 3 ++- kernel/bpf/bpf_struct_ops.c | 7 +++-- 3 files changed, 47 insertions(+), 16 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0fe6aacef3db..d24a512fd6f3 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1744,7 +1744,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog *p, int stack_size, bool mod_ret) + struct bpf_prog *p, int stack_size, bool save_ret) { u8 *prog = *pprog; u8 *jmp_insn; @@ -1777,11 +1777,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (emit_call(&prog, p->bpf_func, prog)) return -EINVAL; - /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + /* + * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. + * + * BPF_TRAMP_FENTRY trampoline may need to return the return + * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ - if (mod_ret) + if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ @@ -1828,13 +1832,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_tramp_progs *tp, int stack_size) + struct bpf_tramp_progs *tp, int stack_size, + bool save_ret) { int i; u8 *prog = *pprog; for (i = 0; i < tp->nr_progs; i++) { - if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, + save_ret)) return -EINVAL; } *pprog = prog; @@ -1877,6 +1883,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* + * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1949,17 +1972,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; u8 **branches = NULL; u8 *prog; + bool save_ret; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ if (nr_args > 6) return -ENOTSUPP; - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!is_valid_bpf_tramp_flags(flags)) return -EINVAL; - if (flags & BPF_TRAMP_F_CALL_ORIG) - stack_size += 8; /* room for return value of orig_call */ + /* room for return value of orig_call or fentry prog */ + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2005,7 +2030,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fentry->nr_progs) - if (invoke_bpf(m, &prog, fentry, stack_size)) + if (invoke_bpf(m, &prog, fentry, stack_size, + flags & BPF_TRAMP_F_RET_FENTRY_RET)) return -EINVAL; if (fmod_ret->nr_progs) { @@ -2052,7 +2078,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) { + if (invoke_bpf(m, &prog, fexit, stack_size, false)) { ret = -EINVAL; goto cleanup; } @@ -2072,9 +2098,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - /* restore original return value back into RAX */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); } + /* restore return value of orig_call or fentry prog back into RAX */ + if (save_ret) + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f4c16f19f83e..020a7d5bf470 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -578,11 +578,12 @@ struct btf_func_model { * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) - /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) +/* Return the return value of fentry prog. Only used by bpf_struct_ops. */ +#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index d6731c32864e..9abcc33f02cf 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -368,6 +368,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; + u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -431,10 +432,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = st_ops->func_models[i].ret_size > 0 ? + BPF_TRAMP_F_RET_FENTRY_RET : 0; err = arch_prepare_bpf_trampoline(NULL, image, st_map->image + PAGE_SIZE, - &st_ops->func_models[i], 0, - tprogs, NULL); + &st_ops->func_models[i], + flags, tprogs, NULL); if (err < 0) goto reset_unlock; From 2cc74e1ee31d00393b6698ec80b322fd26523da4 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 8 Sep 2021 13:43:28 +0200 Subject: [PATCH 234/866] IB/cma: Do not send IGMP leaves for sendonly Multicast groups ROCE uses IGMP for Multicast instead of the native Infiniband system where joins are required in order to post messages on the Multicast group. On Ethernet one can send Multicast messages to arbitrary addresses without the need to subscribe to a group. So ROCE correctly does not send IGMP joins during rdma_join_multicast(). F.e. in cma_iboe_join_multicast() we see: if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { So the IGMP join is suppressed as it is unnecessary. However no such check is done in destroy_mc(). And therefore leaving a sendonly multicast group will send an IGMP leave. This means that the following scenario can lead to a multicast receiver unexpectedly being unsubscribed from a MC group: 1. Sender thread does a sendonly join on MC group X. No IGMP join is sent. 2. Receiver thread does a regular join on the same MC Group x. IGMP join is sent and the receiver begins to get messages. 3. Sender thread terminates and destroys MC group X. IGMP leave is sent and the receiver no longer receives data. This patch adds the same logic for sendonly joins to destroy_mc() that is also used in cma_iboe_join_multicast(). Fixes: ab15c95a17b3 ("IB/core: Support for CMA multicast join flags") Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2109081340540.668072@gentwo.de Signed-off-by: Christoph Lameter Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c40791baced5..86ee3b01b3ee 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1810,6 +1810,8 @@ static void cma_release_port(struct rdma_id_private *id_priv) static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { + bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); + if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); @@ -1826,7 +1828,10 @@ static void destroy_mc(struct rdma_id_private *id_priv, cma_set_mgid(id_priv, (struct sockaddr *)&mc->addr, &mgid); - cma_igmp_send(ndev, &mgid, false); + + if (!send_only) + cma_igmp_send(ndev, &mgid, false); + dev_put(ndev); } From 67a44e659888569a133a8f858c8230e9d7aad1d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ernst=20Sj=C3=B6strand?= Date: Thu, 2 Sep 2021 09:50:27 +0200 Subject: [PATCH 235/866] drm/amd/amdgpu: Increase HWIP_MAX_INSTANCE to 10 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Seems like newer cards can have even more instances now. Found by UBSAN: array-index-out-of-bounds in drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c:318:29 index 8 is out of range for type 'uint32_t *[8]' Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1697 Cc: stable@vger.kernel.org Signed-off-by: Ernst Sjöstrand Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dc3c6b3a00e5..d356e329e6f8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -758,7 +758,7 @@ enum amd_hw_ip_block_type { MAX_HWIP }; -#define HWIP_MAX_INSTANCE 8 +#define HWIP_MAX_INSTANCE 10 struct amd_powerplay { void *pp_handle; From 5598d7c21a0bcab900f281dca4efbb1f80add0fe Mon Sep 17 00:00:00 2001 From: Kenneth Feng Date: Mon, 6 Sep 2021 07:55:01 +0800 Subject: [PATCH 236/866] drm/amd/pm: fix the issue of uploading powerplay table fix the issue of uploading powerplay table due to the dependancy of rlc. Signed-off-by: Kenneth Feng Reviewed-by: Jack Gui Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 3ab1ce4d3419..04863a797115 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1404,7 +1404,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && - (adev->asic_type <= CHIP_DIMGREY_CAVEFISH)) + (adev->asic_type <= CHIP_BEIGE_GOBY)) return smu_disable_all_features_with_exception(smu, true, SMU_FEATURE_COUNT); From c92db8d64f9e0313e7ecdc9500db93a5040c9370 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 7 Sep 2021 09:37:52 +0200 Subject: [PATCH 237/866] drm/amdgpu: fix use after free during BO move MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The memory backing old_mem is already freed at that point, move the check a bit more up. Signed-off-by: Christian König Fixes: bfa3357ef9ab ("drm/ttm: allocate resource object instead of embedding it v2") Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1699 Acked-by: Nirmoy Das Reviewed-by: Michel Dänzer Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 38dade421d46..94126dc39688 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, goto out; } + if (bo->type == ttm_bo_type_device && + new_mem->mem_type == TTM_PL_VRAM && + old_mem->mem_type != TTM_PL_VRAM) { + /* amdgpu_bo_fault_reserve_notify will re-set this if the CPU + * accesses the BO after it's moved. + */ + abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; + } + if (adev->mman.buffer_funcs_enabled) { if (((old_mem->mem_type == TTM_PL_SYSTEM && new_mem->mem_type == TTM_PL_VRAM) || @@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; } - if (bo->type == ttm_bo_type_device && - new_mem->mem_type == TTM_PL_VRAM && - old_mem->mem_type != TTM_PL_VRAM) { - /* amdgpu_bo_fault_reserve_notify will re-set this if the CPU - * accesses the BO after it's moved. - */ - abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - } - out: /* update statistics */ atomic64_add(bo->base.size, &adev->num_bytes_moved); From 7bbee36d71502ab9a341505da89a017c7ae2e6b2 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Tue, 7 Sep 2021 14:19:34 +0000 Subject: [PATCH 238/866] amd/display: downgrade validation failure log level In amdgpu_dm_atomic_check, dc_validate_global_state is called. On failure this logs a warning to the kernel journal. However warnings shouldn't be used for atomic test-only commit failures: user-space might be perfoming a lot of atomic test-only commits to find the best hardware configuration. Downgrade the log to a regular DRM atomic message. While at it, use the new device-aware logging infrastructure. This fixes error messages in the kernel when running gamescope [1]. [1]: https://github.com/Plagman/gamescope/issues/245 Reviewed-by: Nicholas Kazlauskas Signed-off-by: Simon Ser Cc: Alex Deucher Cc: Harry Wentland Cc: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 9b1fc54555ee..d55e61d8aa00 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -10492,7 +10492,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; status = dc_validate_global_state(dc, dm_state->context, false); if (status != DC_OK) { - DC_LOG_WARNING("DC global validation failure: %s (%d)", + drm_dbg_atomic(dev, + "DC global validation failure: %s (%d)", dc_status_to_str(status), status); ret = -EINVAL; goto fail; From b04ce53eac2fc326290817a6f64a440b5bffd2e3 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Thu, 2 Sep 2021 13:27:56 +0200 Subject: [PATCH 239/866] drm/amdgpu: use IS_ERR for debugfs APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit debugfs APIs returns encoded error so use IS_ERR for checking return value. v2: return PTR_ERR(ent) References: https://gitlab.freedesktop.org/drm/amd/-/issues/1686 Signed-off-by: Nirmoy Das Reviewed-by: Christian König Reviewed-By: Shashank Sharma Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 10 ++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 4 ++-- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 277128846dd1..463b9c0283f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) struct dentry *ent; int r, i; - - ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev, &fops_ib_preempt); - if (!ent) { + if (IS_ERR(ent)) { DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n"); - return -EIO; + return PTR_ERR(ent); } ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev, &fops_sclk_set); - if (!ent) { + if (IS_ERR(ent)) { DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n"); - return -EIO; + return PTR_ERR(ent); } /* Register debugfs entries for amdgpu_ttm */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 7b634a1517f9..0554576d3695 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev, ent = debugfs_create_file(name, S_IFREG | S_IRUGO, root, ring, &amdgpu_debugfs_ring_fops); - if (!ent) - return -ENOMEM; + if (IS_ERR(ent)) + return PTR_ERR(ent); i_size_write(ent->d_inode, ring->ring_size + 12); ring->ent = ent; From 77e02cf57b6cff9919949defb7fd9b8ac16399a2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Sep 2021 13:23:22 -0700 Subject: [PATCH 240/866] memblock: introduce saner 'memblock_free_ptr()' interface The boot-time allocation interface for memblock is a mess, with 'memblock_alloc()' returning a virtual pointer, but then you are supposed to free it with 'memblock_free()' that takes a _physical_ address. Not only is that all kinds of strange and illogical, but it actually causes bugs, when people then use it like a normal allocation function, and it fails spectacularly on a NULL pointer: https://lore.kernel.org/all/20210912140820.GD25450@xsang-OptiPlex-9020/ or just random memory corruption if the debug checks don't catch it: https://lore.kernel.org/all/61ab2d0c-3313-aaab-514c-e15b7aa054a0@suse.cz/ I really don't want to apply patches that treat the symptoms, when the fundamental cause is this horribly confusing interface. I started out looking at just automating a sane replacement sequence, but because of this mix or virtual and physical addresses, and because people have used the "__pa()" macro that can take either a regular kernel pointer, or just the raw "unsigned long" address, it's all quite messy. So this just introduces a new saner interface for freeing a virtual address that was allocated using 'memblock_alloc()', and that was kept as a regular kernel pointer. And then it converts a couple of users that are obvious and easy to test, including the 'xbc_nodes' case in lib/bootconfig.c that caused problems. Reported-by: kernel test robot Fixes: 40caa127f3c7 ("init: bootconfig: Remove all bootconfig data when the init memory is removed") Cc: Steven Rostedt Cc: Mike Rapoport Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Vlastimil Babka Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 6 ++---- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 3 +-- drivers/base/arch_numa.c | 2 +- drivers/macintosh/smu.c | 2 +- include/linux/memblock.h | 1 + init/main.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- mm/memblock.c | 16 +++++++++++++++- 11 files changed, 27 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 78a32b956e81..5afd98559193 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free_ptr(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1a50434c8a4d..ef885370719a 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PMD_SIZE); + memblock_free_ptr(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PUD_SIZE); + memblock_free_ptr(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a1b5c71099e6..1e9b93b088db 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 737491b13728..e801e30089c4 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - if (phys_dist) - memblock_free(__pa(phys_dist), phys_size); + memblock_free_ptr(phys_dist, phys_size); return; no_emu: diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 46c503486e96..00fb4120a5b3 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -264,7 +264,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 94fb63a7b357..fe63d5ee201b 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free(__pa(smu), sizeof(struct smu_device)); + memblock_free_ptr(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b066024c62e3..34de69b3b8ba 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); +void memblock_free_ptr(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/main.c b/init/main.c index 5c9a48df90e1..3f7216934441 100644 --- a/init/main.c +++ b/init/main.c @@ -924,7 +924,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free(__pa(unknown_options), len); + memblock_free_ptr(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 825277e1e742..a8d0a58deebc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free(__pa(new_descs), new_descs_size); + memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: - memblock_free(__pa(new_log_buf), new_log_buf_len); + memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index f8419cff1147..5ae248b29373 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/mm/memblock.c b/mm/memblock.c index 0ab5a749bfa6..184dcd2e5d99 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_alloc_size); + memblock_free_ptr(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -795,6 +795,20 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.memory, base, size); } +/** + * memblock_free_ptr - free boot memory allocation + * @ptr: starting address of the boot memory allocation + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init_memblock memblock_free_ptr(void *ptr, size_t size) +{ + if (ptr) + memblock_free(__pa(ptr), size); +} + /** * memblock_free - free boot memory block * @base: phys starting address of the boot memory block From 3ca706c189db861b2ca2019a0901b94050ca49d8 Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Tue, 7 Sep 2021 18:03:02 +0800 Subject: [PATCH 241/866] drm/ttm: fix type mismatch error on sparc64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On sparc64, __fls() returns an "int", but the drm TTM code expected it to be "unsigned long" as on x86. As a result, on sparc (and arc, and m68k) you get build errors because 'min()' checks that the types match. As suggested by Linus, it can use min_t instead of min to force the type to be "unsigned int". Suggested-by: Linus Torvalds Signed-off-by: Huang Rui Reviewed-by: Christian König Cc: Alex Deucher Cc: David Airlie Cc: Daniel Vetter Cc: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/gpu/drm/ttm/ttm_pool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index cb38b1a17b09..82cbb29a05aa 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -383,7 +383,8 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, else gfp_flags |= GFP_HIGHUSER; - for (order = min(MAX_ORDER - 1UL, __fls(num_pages)); num_pages; + for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages)); + num_pages; order = min_t(unsigned int, order, __fls(num_pages))) { bool apply_caching = false; struct ttm_pool_type *pt; From 0d818706130e2f4e828c3fc028917677fac76a09 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 13 Sep 2021 06:38:36 -0400 Subject: [PATCH 242/866] virtio: don't fail on !of_device_is_compatible A recent change checking of_device_is_compatible on probe broke some powerpc/pseries setups. Apparently there virtio devices do not have a "compatible" property - they are matched by PCI vendor/device ids. Let's just skip of_node setup but proceed with initialization like we did previously. Fixes: 694a1116b405 ("virtio: Bind virtio device to device-tree node") Reported-by: Alexey Kardashevskiy Cc: Arnd Bergmann Cc: Viresh Kumar Tested-by: Guenter Roeck Acked-by: Jason Wang Reviewed-by: Viresh Kumar Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 588e02fb91d3..0a5b54034d4b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -345,8 +345,13 @@ static int virtio_device_of_init(struct virtio_device *dev) ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device); BUG_ON(ret >= sizeof(compat)); + /* + * On powerpc/pseries virtio devices are PCI devices so PCI + * vendor/device ids play the role of the "compatible" property. + * Simply don't init of_node in this case. + */ if (!of_device_is_compatible(np, compat)) { - ret = -EINVAL; + ret = 0; goto out; } From 6243e3c78ace66d337a1e43b60a1aa8f5b61bd72 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 7 Sep 2021 10:32:24 +0300 Subject: [PATCH 243/866] vduse: missing error code in vduse_init() This should return -ENOMEM if alloc_workqueue() fails. Currently it returns success. Fixes: b66219796563 ("vduse: Introduce VDUSE - vDPA Device in Userspace") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20210907073223.GA18254@kili Signed-off-by: Michael S. Tsirkin Reviewed-by: Xie Yongji Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 29a38ecba19e..e36287feac0e 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1593,8 +1593,10 @@ static int vduse_init(void) vduse_irq_wq = alloc_workqueue("vduse-irq", WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0); - if (!vduse_irq_wq) + if (!vduse_irq_wq) { + ret = -ENOMEM; goto err_wq; + } ret = vduse_domain_init(); if (ret) From 7bb5fb207334758ce6ee84345d6f08e4fb284fe6 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Mon, 6 Sep 2021 22:21:58 +0800 Subject: [PATCH 244/866] vduse: Cleanup the old kernel states after reset failure We should cleanup the old kernel states e.g. interrupt callback no matter whether the userspace handle the reset correctly or not since virtio-vdpa can't handle the reset failure now. Otherwise, the old state might be used after reset which might break something, e.g. the old interrupt callback might be triggered by userspace after reset, which can break the virtio device driver. Signed-off-by: Xie Yongji Link: https://lore.kernel.org/r/20210906142158.181-1-xieyongji@bytedance.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index e36287feac0e..26e3d90d1e7c 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -665,13 +665,11 @@ static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset, static int vduse_vdpa_reset(struct vdpa_device *vdpa) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - - if (vduse_dev_set_status(dev, 0)) - return -EIO; + int ret = vduse_dev_set_status(dev, 0); vduse_dev_reset(dev); - return 0; + return ret; } static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa) From ef12e4bf4276a07fd350179fa63d0d337ea0a867 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 9 Sep 2021 09:36:52 +0300 Subject: [PATCH 245/866] vdpa/mlx5: Clear ready indication for control VQ When clearing VQs ready indication for the data VQs, do the same for the control VQ. Fixes: 5262912ef3cf ("vdpa/mlx5: Add support for control VQ and MAC setting") Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20210909063652.46880-1-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 294ba05e6fc9..64dfd0f500d2 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2145,6 +2145,8 @@ static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) for (i = 0; i < ndev->mvdev.max_vqs; i++) ndev->vqs[i].ready = false; + + ndev->mvdev.cvq.ready = false; } static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) From 759be8993b1b40e05b8908583336b8e230e67b08 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 9 Sep 2021 09:37:38 +0300 Subject: [PATCH 246/866] vdpa/mlx5: Avoid executing set_vq_ready() if device is reset Avoid executing set_vq_ready() if the device has been reset. In such case, the features are cleared and cannot be used in conditional statements. Such reference happens is the function ctrl_vq_idx(). Fixes: 52893733f2c5 ("vdpa/mlx5: Add multiqueue support") Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20210909063738.46970-1-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 64dfd0f500d2..bd56de7484dc 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1714,6 +1714,9 @@ static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; + if (!mvdev->actual_features) + return; + if (!is_index_valid(mvdev, idx)) return; From be9c6bad9b46451ba5bb8d366c51e2475f374981 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 7 Sep 2021 10:32:53 +0300 Subject: [PATCH 247/866] vdpa: potential uninitialized return in vhost_vdpa_va_map() The concern here is that "ret" can be uninitialized if we hit the "goto next" condition on every iteration through the loop. Fixes: 41ba1b5f9d4b ("vdpa: Support transferring virtual addressing during DMA mapping") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/20210907073253.GB18254@kili Signed-off-by: Michael S. Tsirkin Reviewed-by: Xie Yongji Acked-by: Jason Wang Reviewed-by: Stefano Garzarella --- drivers/vhost/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index f41d081777f5..35927ceb26ff 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -640,7 +640,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v, u64 offset, map_size, map_iova = iova; struct vdpa_map_file *map_file; struct vm_area_struct *vma; - int ret; + int ret = 0; mmap_read_lock(dev->mm); From 783a40a1b3ac7f3714d2776fa8ac8cce3535e4f6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Sep 2021 09:06:55 +0200 Subject: [PATCH 248/866] block: check if a profile is actually registered in blk_integrity_unregister While clearing the profile itself is harmless, we really should not clear the stable writes flag if it wasn't set due to a registered integrity profile. Reported-by: Lihong Kou Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Link: https://lore.kernel.org/r/20210914070657.87677-2-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-integrity.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 69a12177dfb6..48bfb53aa857 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -426,8 +426,12 @@ EXPORT_SYMBOL(blk_integrity_register); */ void blk_integrity_unregister(struct gendisk *disk) { + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return; blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); - memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity)); + memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); From 3df49967f6f1d2121b0c27c381ca1c8386b1dab9 Mon Sep 17 00:00:00 2001 From: Lihong Kou Date: Tue, 14 Sep 2021 09:06:56 +0200 Subject: [PATCH 249/866] block: flush the integrity workqueue in blk_integrity_unregister When the integrity profile is unregistered there can still be integrity reads queued up which could see a NULL verify_fn as shown by the race window below: CPU0 CPU1 process_one_work nvme_validate_ns bio_integrity_verify_fn nvme_update_ns_info nvme_update_disk_info blk_integrity_unregister ---set queue->integrity as 0 bio_integrity_process --access bi->profile->verify_fn(bi is a pointer of queue->integity) Before calling blk_integrity_unregister in nvme_update_disk_info, we must make sure that there is no work item in the kintegrityd_wq. Just call blk_flush_integrity to flush the work queue so the bug can be resolved. Signed-off-by: Lihong Kou [hch: split up and shortened the changelog] Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Link: https://lore.kernel.org/r/20210914070657.87677-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-integrity.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 48bfb53aa857..16d5d5338392 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -430,6 +430,9 @@ void blk_integrity_unregister(struct gendisk *disk) if (!bi->profile) return; + + /* ensure all bios are off the integrity workqueue */ + blk_flush_integrity(); blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); memset(bi, 0, sizeof(*bi)); } From 9da4c7276ec5d167972d8f6670d64b59838b4ed2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Sep 2021 09:06:57 +0200 Subject: [PATCH 250/866] nvme: remove the call to nvme_update_disk_info in nvme_ns_remove There is no need to explicitly unregister the integrity profile when deleting the gendisk. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Link: https://lore.kernel.org/r/20210914070657.87677-4-hch@lst.de Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7efb31b87f37..c72283ebf0cc 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3856,8 +3856,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) nvme_cdev_del(&ns->cdev, &ns->cdev_device); del_gendisk(ns->disk); blk_cleanup_queue(ns->queue); - if (blk_get_integrity(ns->disk)) - blk_integrity_unregister(ns->disk); down_write(&ns->ctrl->namespaces_rwsem); list_del_init(&ns->list); From 52ce14c134a003fee03d8fc57442c05a55b53715 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Sun, 12 Sep 2021 22:05:23 +0300 Subject: [PATCH 251/866] bnx2x: Fix enabling network interfaces without VFs This function is called to enable SR-IOV when available, not enabling interfaces without VFs was a regression. Fixes: 65161c35554f ("bnx2x: Fix missing error code in bnx2x_iov_init_one()") Signed-off-by: Adrian Bunk Reported-by: YunQiang Su Tested-by: YunQiang Su Cc: stable@vger.kernel.org Acked-by: Shai Malin Link: https://lore.kernel.org/r/20210912190523.27991-1-bunk@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index f255fd0b16db..6fbf735fca31 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1224,7 +1224,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, /* SR-IOV capability was enabled but there are no VFs*/ if (iov->total == 0) { - err = -EINVAL; + err = 0; goto failed; } From 7366c23ff492ad260776a3ee1aaabba9fc773a8b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 13 Sep 2021 15:06:05 -0700 Subject: [PATCH 252/866] ptp: dp83640: don't define PAGE0 Building dp83640.c on arch/parisc/ produces a build warning for PAGE0 being redefined. Since the macro is not used in the dp83640 driver, just make it a comment for documentation purposes. In file included from ../drivers/net/phy/dp83640.c:23: ../drivers/net/phy/dp83640_reg.h:8: warning: "PAGE0" redefined 8 | #define PAGE0 0x0000 from ../drivers/net/phy/dp83640.c:11: ../arch/parisc/include/asm/page.h:187: note: this is the location of the previous definition 187 | #define PAGE0 ((struct zeropage *)__PAGE_OFFSET) Fixes: cb646e2b02b2 ("ptp: Added a clock driver for the National Semiconductor PHYTER.") Signed-off-by: Randy Dunlap Reported-by: Geert Uytterhoeven Cc: Richard Cochran Cc: John Stultz Cc: Heiner Kallweit Cc: Russell King Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210913220605.19682-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83640_reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83640_reg.h b/drivers/net/phy/dp83640_reg.h index 21aa24c741b9..daae7fa58fb8 100644 --- a/drivers/net/phy/dp83640_reg.h +++ b/drivers/net/phy/dp83640_reg.h @@ -5,7 +5,7 @@ #ifndef HAVE_DP83640_REGISTERS #define HAVE_DP83640_REGISTERS -#define PAGE0 0x0000 +/* #define PAGE0 0x0000 */ #define PHYCR2 0x001c /* PHY Control Register 2 */ #define PAGE4 0x0004 From f68aa100d815b5b4467fd1c3abbe3b99d65fd028 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 3 Sep 2021 10:49:37 +0200 Subject: [PATCH 253/866] xen: reset legacy rtc flag for PV domU A Xen PV guest doesn't have a legacy RTC device, so reset the legacy RTC flag. Otherwise the following WARN splat will occur at boot: [ 1.333404] WARNING: CPU: 1 PID: 1 at /home/gross/linux/head/drivers/rtc/rtc-mc146818-lib.c:25 mc146818_get_time+0x1be/0x210 [ 1.333404] Modules linked in: [ 1.333404] CPU: 1 PID: 1 Comm: swapper/0 Tainted: G W 5.14.0-rc7-default+ #282 [ 1.333404] RIP: e030:mc146818_get_time+0x1be/0x210 [ 1.333404] Code: c0 64 01 c5 83 fd 45 89 6b 14 7f 06 83 c5 64 89 6b 14 41 83 ec 01 b8 02 00 00 00 44 89 63 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 <0f> 0b 48 c7 c7 30 0e ef 82 4c 89 e6 e8 71 2a 24 00 48 c7 c0 ff ff [ 1.333404] RSP: e02b:ffffc90040093df8 EFLAGS: 00010002 [ 1.333404] RAX: 00000000000000ff RBX: ffffc90040093e34 RCX: 0000000000000000 [ 1.333404] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 000000000000000d [ 1.333404] RBP: ffffffff82ef0e30 R08: ffff888005013e60 R09: 0000000000000000 [ 1.333404] R10: ffffffff82373e9b R11: 0000000000033080 R12: 0000000000000200 [ 1.333404] R13: 0000000000000000 R14: 0000000000000002 R15: ffffffff82cdc6d4 [ 1.333404] FS: 0000000000000000(0000) GS:ffff88807d440000(0000) knlGS:0000000000000000 [ 1.333404] CS: 10000e030 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.333404] CR2: 0000000000000000 CR3: 000000000260a000 CR4: 0000000000050660 [ 1.333404] Call Trace: [ 1.333404] ? wakeup_sources_sysfs_init+0x30/0x30 [ 1.333404] ? rdinit_setup+0x2b/0x2b [ 1.333404] early_resume_init+0x23/0xa4 [ 1.333404] ? cn_proc_init+0x36/0x36 [ 1.333404] do_one_initcall+0x3e/0x200 [ 1.333404] kernel_init_freeable+0x232/0x28e [ 1.333404] ? rest_init+0xd0/0xd0 [ 1.333404] kernel_init+0x16/0x120 [ 1.333404] ret_from_fork+0x1f/0x30 Cc: Fixes: 8d152e7a5c7537 ("x86/rtc: Replace paravirt rtc check with platform legacy quirk") Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20210903084937.19392-3-jgross@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/enlighten_pv.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 753f63734c13..349f780a1567 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1214,6 +1214,11 @@ static void __init xen_dom0_set_legacy_features(void) x86_platform.legacy.rtc = 1; } +static void __init xen_domu_set_legacy_features(void) +{ + x86_platform.legacy.rtc = 0; +} + /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { @@ -1359,6 +1364,8 @@ asmlinkage __visible void __init xen_start_kernel(void) add_preferred_console("xenboot", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; + x86_platform.set_legacy_features = + xen_domu_set_legacy_features; } else { const struct dom0_vga_console_info *info = (void *)((char *)xen_start_info + From 36c9b5929b7094ea19a78827c0ede20d2e0e6c9c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 8 Sep 2021 09:36:40 +0200 Subject: [PATCH 254/866] xen: fix usage of pmd_populate in mremap for pv guests Commit 0881ace292b662 ("mm/mremap: use pmd/pud_poplulate to update page table entries") introduced a regression when running as Xen PV guest. Today pmd_populate() for Xen PV assumes that the PFN inserted is referencing a not yet used page table. In case of move_normal_pmd() this is not true, resulting in WARN splats like: [34321.304270] ------------[ cut here ]------------ [34321.304277] WARNING: CPU: 0 PID: 23628 at arch/x86/xen/multicalls.c:102 xen_mc_flush+0x176/0x1a0 [34321.304288] Modules linked in: [34321.304291] CPU: 0 PID: 23628 Comm: apt-get Not tainted 5.14.1-20210906-doflr-mac80211debug+ #1 [34321.304294] Hardware name: MSI MS-7640/890FXA-GD70 (MS-7640) , BIOS V1.8B1 09/13/2010 [34321.304296] RIP: e030:xen_mc_flush+0x176/0x1a0 [34321.304300] Code: 89 45 18 48 c1 e9 3f 48 89 ce e9 20 ff ff ff e8 60 03 00 00 66 90 5b 5d 41 5c 41 5d c3 48 c7 45 18 ea ff ff ff be 01 00 00 00 <0f> 0b 8b 55 00 48 c7 c7 10 97 aa 82 31 db 49 c7 c5 38 97 aa 82 65 [34321.304303] RSP: e02b:ffffc90000a97c90 EFLAGS: 00010002 [34321.304305] RAX: ffff88807d416398 RBX: ffff88807d416350 RCX: ffff88807d416398 [34321.304306] RDX: 0000000000000001 RSI: 0000000000000001 RDI: deadbeefdeadf00d [34321.304308] RBP: ffff88807d416300 R08: aaaaaaaaaaaaaaaa R09: ffff888006160cc0 [34321.304309] R10: deadbeefdeadf00d R11: ffffea000026a600 R12: 0000000000000000 [34321.304310] R13: ffff888012f6b000 R14: 0000000012f6b000 R15: 0000000000000001 [34321.304320] FS: 00007f5071177800(0000) GS:ffff88807d400000(0000) knlGS:0000000000000000 [34321.304322] CS: 10000e030 DS: 0000 ES: 0000 CR0: 0000000080050033 [34321.304323] CR2: 00007f506f542000 CR3: 00000000160cc000 CR4: 0000000000000660 [34321.304326] Call Trace: [34321.304331] xen_alloc_pte+0x294/0x320 [34321.304334] move_pgt_entry+0x165/0x4b0 [34321.304339] move_page_tables+0x6fa/0x8d0 [34321.304342] move_vma.isra.44+0x138/0x500 [34321.304345] __x64_sys_mremap+0x296/0x410 [34321.304348] do_syscall_64+0x3a/0x80 [34321.304352] entry_SYSCALL_64_after_hwframe+0x44/0xae [34321.304355] RIP: 0033:0x7f507196301a [34321.304358] Code: 73 01 c3 48 8b 0d 76 0e 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 19 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 46 0e 0c 00 f7 d8 64 89 01 48 [34321.304360] RSP: 002b:00007ffda1eecd38 EFLAGS: 00000246 ORIG_RAX: 0000000000000019 [34321.304362] RAX: ffffffffffffffda RBX: 000056205f950f30 RCX: 00007f507196301a [34321.304363] RDX: 0000000001a00000 RSI: 0000000001900000 RDI: 00007f506dc56000 [34321.304364] RBP: 0000000001a00000 R08: 0000000000000010 R09: 0000000000000004 [34321.304365] R10: 0000000000000001 R11: 0000000000000246 R12: 00007f506dc56060 [34321.304367] R13: 00007f506dc56000 R14: 00007f506dc56060 R15: 000056205f950f30 [34321.304368] ---[ end trace a19885b78fe8f33e ]--- [34321.304370] 1 of 2 multicall(s) failed: cpu 0 [34321.304371] call 2: op=12297829382473034410 arg=[aaaaaaaaaaaaaaaa] result=-22 Fix that by modifying xen_alloc_ptpage() to only pin the page table in case it wasn't pinned already. Fixes: 0881ace292b662 ("mm/mremap: use pmd/pud_poplulate to update page table entries") Cc: Reported-by: Sander Eikelenboom Tested-by: Sander Eikelenboom Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20210908073640.11299-1-jgross@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/mmu_pv.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1df5f01529e5..8d751939c6f3 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (pinned) { struct page *page = pfn_to_page(pfn); - if (static_branch_likely(&xen_struct_pages_ready)) + pinned = false; + if (static_branch_likely(&xen_struct_pages_ready)) { + pinned = PagePinned(page); SetPagePinned(page); + } xen_mc_batch(); __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(PARAVIRT_LAZY_MMU); From 45da234467f381239d87536c86597149f189d375 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:17:13 +0200 Subject: [PATCH 255/866] xen/pvcalls: backend can be a module It's not clear to me why only the frontend has been tristate. Switch the backend to be, too. Signed-off-by: Jan Beulich Acked-by: Stefano Stabellini Link: https://lore.kernel.org/r/54a6070c-92bb-36a3-2fc0-de9ccca438c5@suse.com Signed-off-by: Juergen Gross --- drivers/xen/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 5f1ce59b44b9..a37eb52fb401 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -214,7 +214,7 @@ config XEN_PVCALLS_FRONTEND implements them. config XEN_PVCALLS_BACKEND - bool "XEN PV Calls backend driver" + tristate "XEN PV Calls backend driver" depends on INET && XEN && XEN_BACKEND help Experimental backend for the Xen PV Calls protocol From ce6a80d1b2f923b1839655a1cda786293feaa085 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:04:25 +0200 Subject: [PATCH 256/866] swiotlb-xen: avoid double free Of the two paths leading to the "error" label in xen_swiotlb_init() one didn't allocate anything, while the other did already free what was allocated. Fixes: b82776005369 ("xen/swiotlb: Use the swiotlb_late_init_with_tbl to init Xen-SWIOTLB late when PV PCI is used") Signed-off-by: Jan Beulich Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/ce9c2adb-8a52-6293-982a-0d6ece943ac6@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 24d11861ac7d..99d518526eaf 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -216,7 +216,6 @@ error: goto retry; } pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc); - free_pages((unsigned long)start, order); return rc; } From 4c092c59015f7adf0f07685f869edb96d997a756 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:04:47 +0200 Subject: [PATCH 257/866] swiotlb-xen: fix late init retry The commit referenced below removed the assignment of "bytes" from xen_swiotlb_init() without - like done for xen_swiotlb_init_early() - adding an assignment on the retry path, thus leading to excessively sized allocations upon retries. Fixes: 2d29960af0be ("swiotlb: dynamically allocate io_tlb_default_mem") Signed-off-by: Jan Beulich Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/778299d6-9cfd-1c13-026e-25ee5d14ecb3@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 99d518526eaf..dbb18dc956f3 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -211,8 +211,8 @@ error: if (repeat--) { /* Min is 2MB */ nslabs = max(1024UL, (nslabs >> 1)); - pr_info("Lowering to %luMB\n", - (nslabs << IO_TLB_SHIFT) >> 20); + bytes = nslabs << IO_TLB_SHIFT; + pr_info("Lowering to %luMB\n", bytes >> 20); goto retry; } pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc); From d9a688add3d412c840e31060847a6a297b552316 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:05:12 +0200 Subject: [PATCH 258/866] swiotlb-xen: maintain slab count properly Generic swiotlb code makes sure to keep the slab count a multiple of the number of slabs per segment. Yet even without checking whether any such assumption is made elsewhere, it is easy to see that xen_swiotlb_fixup() might alter unrelated memory when calling xen_create_contiguous_region() for the last segment, when that's not a full one - the function acts on full order-N regions, not individual pages. Align the slab count suitably when halving it for a retry. Add a build time check and a runtime one. Replace the no longer useful local variable "slabs" by an "order" one calculated just once, outside of the loop. Re-use "order" for calculating "dma_bits", and change the type of the latter as well as the one of "i" while touching this anyway. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/dc054cb0-bec4-4db0-fc06-c9fc957b6e66@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index dbb18dc956f3..08fc694f05b7 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -106,27 +106,26 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr) static int xen_swiotlb_fixup(void *buf, unsigned long nslabs) { - int i, rc; - int dma_bits; + int rc; + unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT); + unsigned int i, dma_bits = order + PAGE_SHIFT; dma_addr_t dma_handle; phys_addr_t p = virt_to_phys(buf); - dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT; + BUILD_BUG_ON(IO_TLB_SEGSIZE & (IO_TLB_SEGSIZE - 1)); + BUG_ON(nslabs % IO_TLB_SEGSIZE); i = 0; do { - int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE); - do { rc = xen_create_contiguous_region( - p + (i << IO_TLB_SHIFT), - get_order(slabs << IO_TLB_SHIFT), + p + (i << IO_TLB_SHIFT), order, dma_bits, &dma_handle); } while (rc && dma_bits++ < MAX_DMA_BITS); if (rc) return rc; - i += slabs; + i += IO_TLB_SEGSIZE; } while (i < nslabs); return 0; } @@ -210,7 +209,7 @@ retry: error: if (repeat--) { /* Min is 2MB */ - nslabs = max(1024UL, (nslabs >> 1)); + nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); bytes = nslabs << IO_TLB_SHIFT; pr_info("Lowering to %luMB\n", bytes >> 20); goto retry; @@ -245,7 +244,7 @@ retry: memblock_free(__pa(start), PAGE_ALIGN(bytes)); if (repeat--) { /* Min is 2MB */ - nslabs = max(1024UL, (nslabs >> 1)); + nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); bytes = nslabs << IO_TLB_SHIFT; pr_info("Lowering to %luMB\n", bytes >> 20); goto retry; From 79ca5f778aafbd69727d577b58d913c9ce8400be Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:05:54 +0200 Subject: [PATCH 259/866] swiotlb-xen: suppress certain init retries Only on the 2nd of the paths leading to xen_swiotlb_init()'s "error" label it is useful to retry the allocation; the first one did already iterate through all possible order values. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/56477481-87da-4962-9661-5e1b277efde0@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 08fc694f05b7..6520d05e62ef 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -184,7 +184,7 @@ retry: order--; } if (!start) - goto error; + goto exit; if (order != get_order(bytes)) { pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n", (PAGE_SIZE << order) >> 20); @@ -214,6 +214,7 @@ error: pr_info("Lowering to %luMB\n", bytes >> 20); goto retry; } +exit: pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc); return rc; } From cabb7f89b24ed40c4640dac3bca044452ab0b386 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:06:37 +0200 Subject: [PATCH 260/866] swiotlb-xen: limit init retries Due to the use of max(1024, ...) there's no point retrying (and issuing bogus log messages) when the number of slabs is already no larger than this minimum value. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/984fa426-2b7b-4b77-5ce8-766619575b7f@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 6520d05e62ef..d30dc5e68a22 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -207,7 +207,7 @@ retry: swiotlb_set_max_segment(PAGE_SIZE); return 0; error: - if (repeat--) { + if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); bytes = nslabs << IO_TLB_SHIFT; @@ -243,7 +243,7 @@ retry: rc = xen_swiotlb_fixup(start, nslabs); if (rc) { memblock_free(__pa(start), PAGE_ALIGN(bytes)); - if (repeat--) { + if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); bytes = nslabs << IO_TLB_SHIFT; From 68573c1b5c4d0ebd90c24c6055abb53c474a8fc2 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:06:55 +0200 Subject: [PATCH 261/866] swiotlb-xen: drop leftover __ref Commit a98f565462f0 ("xen-swiotlb: split xen_swiotlb_init") should not only have added __init to the split off function, but also should have dropped __ref from the one left. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/7cd163e1-fe13-270b-384c-2708e8273d34@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index d30dc5e68a22..f3d81b2697b7 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -154,7 +154,7 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err) #define DEFAULT_NSLABS ALIGN(SZ_64M >> IO_TLB_SHIFT, IO_TLB_SEGSIZE) -int __ref xen_swiotlb_init(void) +int xen_swiotlb_init(void) { enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN; unsigned long bytes = swiotlb_size_or_default(); From 7fd880a38cfefb2d54a912e4ae809110adec1c94 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:07:21 +0200 Subject: [PATCH 262/866] swiotlb-xen: arrange to have buffer info logged I consider it unhelpful that address and size of the buffer aren't put in the log file; it makes diagnosing issues needlessly harder. The majority of callers of swiotlb_init() also passes 1 for the "verbose" parameter. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/2e3c8e68-36b2-4ae9-b829-bf7f75d39d47@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index f3d81b2697b7..afe8c7eb31b9 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -253,7 +253,7 @@ retry: panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc); } - if (swiotlb_init_with_tbl(start, nslabs, false)) + if (swiotlb_init_with_tbl(start, nslabs, true)) panic("Cannot allocate SWIOTLB buffer"); swiotlb_set_max_segment(PAGE_SIZE); } From d859ed25b24289c87a97889653596f8088367e16 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 7 Sep 2021 14:07:47 +0200 Subject: [PATCH 263/866] swiotlb-xen: drop DEFAULT_NSLABS It was introduced by 4035b43da6da ("xen-swiotlb: remove xen_set_nslabs") and then not removed by 2d29960af0be ("swiotlb: dynamically allocate io_tlb_default_mem"). Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/15259326-209a-1d11-338c-5018dc38abe8@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index afe8c7eb31b9..9c9ba500ef23 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -152,8 +152,6 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err) return ""; } -#define DEFAULT_NSLABS ALIGN(SZ_64M >> IO_TLB_SHIFT, IO_TLB_SEGSIZE) - int xen_swiotlb_init(void) { enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN; From c006a06508db4841d256d82f42da392d6391f3d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Mon, 13 Sep 2021 15:40:56 +0200 Subject: [PATCH 264/866] powerpc/xics: Set the IRQ chip data for the ICS native backend MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ICS native driver relies on the IRQ chip data to find the struct 'ics_native' describing the ICS controller but it was removed by commit 248af248a8f4 ("powerpc/xics: Rename the map handler in a check handler"). Revert this change to fix the Microwatt SoC platform. Fixes: 248af248a8f4 ("powerpc/xics: Rename the map handler in a check handler") Signed-off-by: Cédric Le Goater Tested-by: Gustavo Romero Reviewed-by: Joel Stanley Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210913134056.3761960-1-clg@kaod.org --- arch/powerpc/sysdev/xics/xics-common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 5c1a157a83b8..244a727c6ba4 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq, if (xics_ics->check(xics_ics, hwirq)) return -EINVAL; - /* No chip data for the XICS domain */ + /* Let the ICS be the chip data for the XICS domain. For ICS native */ irq_domain_set_info(domain, virq, hwirq, xics_ics->chip, - NULL, handle_fasteoi_irq, NULL, NULL); + xics_ics, handle_fasteoi_irq, NULL, NULL); return 0; } From ac4dfccb96571ca03af7cac64b7a0b2952c97f3a Mon Sep 17 00:00:00 2001 From: Yong Zhi Date: Wed, 15 Sep 2021 09:32:30 +0300 Subject: [PATCH 265/866] ASoC: SOF: Fix DSP oops stack dump output contents Fix @buf arg given to hex_dump_to_buffer() and stack address used in dump error output. Fixes: e657c18a01c8 ('ASoC: SOF: Add xtensa support') Signed-off-by: Yong Zhi Reviewed-by: Pierre-Louis Bossart Reviewed-by: Daniel Baluta Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210915063230.29711-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/xtensa/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/soc/sof/xtensa/core.c b/sound/soc/sof/xtensa/core.c index bbb9a2282ed9..f6e3411b33cf 100644 --- a/sound/soc/sof/xtensa/core.c +++ b/sound/soc/sof/xtensa/core.c @@ -122,9 +122,9 @@ static void xtensa_stack(struct snd_sof_dev *sdev, void *oops, u32 *stack, * 0x0049fbb0: 8000f2d0 0049fc00 6f6c6c61 00632e63 */ for (i = 0; i < stack_words; i += 4) { - hex_dump_to_buffer(stack + i * 4, 16, 16, 4, + hex_dump_to_buffer(stack + i, 16, 16, 4, buf, sizeof(buf), false); - dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i, buf); + dev_err(sdev->dev, "0x%08x: %s\n", stack_ptr + i * 4, buf); } } From a8b92b8c1eac8d655a97b1e90f4d83c25d9b9a18 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 9 Sep 2021 16:59:42 +0200 Subject: [PATCH 266/866] s390/pci_mmio: fully validate the VMA before calling follow_pte() We should not walk/touch page tables outside of VMA boundaries when holding only the mmap sem in read mode. Evil user space can modify the VMA layout just before this function runs and e.g., trigger races with page table removal code since commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap"). find_vma() does not check if the address is >= the VMA start address; use vma_lookup() instead. Reviewed-by: Niklas Schnelle Reviewed-by: Liam R. Howlett Fixes: dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap") Signed-off-by: David Hildenbrand Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_mmio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index ae683aa623ac..c5b35ea129cf 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -159,7 +159,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, mmap_read_lock(current->mm); ret = -EINVAL; - vma = find_vma(current->mm, mmio_addr); + vma = vma_lookup(current->mm, mmio_addr); if (!vma) goto out_unlock_mmap; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) @@ -298,7 +298,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, mmap_read_lock(current->mm); ret = -EINVAL; - vma = find_vma(current->mm, mmio_addr); + vma = vma_lookup(current->mm, mmio_addr); if (!vma) goto out_unlock_mmap; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) From d76b14f3971a0638b6cd0da289f8b48acee287d0 Mon Sep 17 00:00:00 2001 From: Alexander Egorenkov Date: Thu, 9 Sep 2021 12:20:56 +0200 Subject: [PATCH 267/866] s390/sclp: fix Secure-IPL facility detection Prevent out-of-range access if the returned SCLP SCCB response is smaller in size than the address of the Secure-IPL flag. Fixes: c9896acc7851 ("s390/ipl: Provide has_secure sysfs attribute") Cc: stable@vger.kernel.org # 5.2+ Signed-off-by: Alexander Egorenkov Reviewed-by: Christian Borntraeger Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp_early.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index 2f3515fa242a..f3d5c7f4c13d 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -45,13 +45,14 @@ static void __init sclp_early_facilities_detect(void) sclp.has_gisaf = !!(sccb->fac118 & 0x08); sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); - sclp.has_sipl = !!(sccb->cbl & 0x4000); if (sccb->fac85 & 0x02) S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP; if (sccb->fac91 & 0x40) S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_GUEST; if (sccb->cpuoff > 134) sclp.has_diag318 = !!(sccb->byte_134 & 0x80); + if (sccb->cpuoff > 137) + sclp.has_sipl = !!(sccb->cbl & 0x4000); sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2; sclp.rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2; sclp.rzm <<= 20; From 4b26ceac103be7ad71cd4cccf01f97b6017008a6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 1 Sep 2021 14:48:07 +0200 Subject: [PATCH 268/866] s390: update defconfigs Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/configs/debug_defconfig | 8 +++++--- arch/s390/configs/defconfig | 5 ++++- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 37b6115ed80e..6aad18ee131d 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -10,6 +10,7 @@ CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_LSM=y CONFIG_PREEMPT=y +CONFIG_SCHED_CORE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -503,6 +504,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MICROSOFT is not set +# CONFIG_NET_VENDOR_LITEX is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m @@ -661,7 +663,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y @@ -720,6 +721,8 @@ CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_BLAKE2S=m +CONFIG_CRYPTO_MD4=m +CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m @@ -774,7 +777,6 @@ CONFIG_RANDOM32_SELFTEST=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_DMA_API_DEBUG=y -CONFIG_STRING_SELFTEST=y CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y @@ -853,12 +855,12 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y -CONFIG_TEST_SORT=y CONFIG_KPROBES_SANITY_TEST=y CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y +CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 56a1cc85c5d7..f08b161c9446 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_LSM=y +CONFIG_SCHED_CORE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -494,6 +495,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set # CONFIG_NET_VENDOR_MICROSOFT is not set +# CONFIG_NET_VENDOR_LITEX is not set # CONFIG_NET_VENDOR_MARVELL is not set CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m @@ -648,7 +650,6 @@ CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_NFSD_V4_SECURITY_LABEL=y CONFIG_CIFS=m -CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y @@ -708,6 +709,8 @@ CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m CONFIG_CRYPTO_BLAKE2S=m +CONFIG_CRYPTO_MD4=m +CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m From 948e50551b9a07c3ab6b9d208bb8f16fa1b2ad41 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 7 Sep 2021 07:27:11 +0200 Subject: [PATCH 269/866] s390/ap: fix kernel doc comments Get rid of warnings like: drivers/s390/crypto/ap_bus.c:216: warning: bad line: drivers/s390/crypto/ap_bus.c:444: warning: Function parameter or member 'floating' not described in 'ap_interrupt_handler' Reviewed-by: Harald Freudenberger Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/ap_bus.c | 3 ++- drivers/s390/crypto/ap_queue.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index f433428057d9..d9b804943d19 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -213,7 +213,6 @@ static inline int ap_fetch_qci_info(struct ap_config_info *info) * ap_init_qci_info(): Allocate and query qci config info. * Does also update the static variables ap_max_domain_id * and ap_max_adapter_id if this info is available. - */ static void __init ap_init_qci_info(void) { @@ -439,6 +438,7 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused) /** * ap_interrupt_handler() - Schedule ap_tasklet on interrupt * @airq: pointer to adapter interrupt descriptor + * @floating: ignored */ static void ap_interrupt_handler(struct airq_struct *airq, bool floating) { @@ -1786,6 +1786,7 @@ static inline void ap_scan_adapter(int ap) /** * ap_scan_bus(): Scan the AP bus for new devices * Runs periodically, workqueue timer (ap_config_time) + * @unused: Unused pointer. */ static void ap_scan_bus(struct work_struct *unused) { diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index d70c4d3d0907..9ea48bf0ee40 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -20,7 +20,7 @@ static void __ap_flush_queue(struct ap_queue *aq); /** * ap_queue_enable_irq(): Enable interrupt support on this AP queue. - * @qid: The AP queue number + * @aq: The AP queue * @ind: the notification indicator byte * * Enables interruption on AP queue via ap_aqic(). Based on the return @@ -311,7 +311,7 @@ static enum ap_sm_wait ap_sm_read_write(struct ap_queue *aq) /** * ap_sm_reset(): Reset an AP queue. - * @qid: The AP queue number + * @aq: The AP queue * * Submit the Reset command to an AP queue. */ From f5711f9df9242446feccf2bdb6fdc06a72ca1010 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Sep 2021 14:41:35 +0200 Subject: [PATCH 270/866] s390: remove WARN_DYNAMIC_STACK s390 is the only architecture which allows to set the -mwarn-dynamicstack compile option. This however will also always generate a warning with system call stack randomization, which uses alloca to generate some random sized stack frame. On the other hand Linus just enabled "-Werror" by default with commit 3fe617ccafd6 ("Enable '-Werror' by default for all kernel builds"), which means compiles will always fail by default. So instead of playing once again whack-a-mole for something which is s390 specific, simply remove this option. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 10 ---------- arch/s390/Makefile | 7 ------- 2 files changed, 17 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2bd90c51efd3..b86de61b8caa 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -685,16 +685,6 @@ config STACK_GUARD The minimum size for the stack guard should be 256 for 31 bit and 512 for 64 bit. -config WARN_DYNAMIC_STACK - def_bool n - prompt "Emit compiler warnings for function with dynamic stack usage" - help - This option enables the compiler option -mwarn-dynamicstack. If the - compiler supports this options generates warnings for functions - that dynamically allocate stack space using alloca. - - Say N if you are unsure. - endmenu menu "I/O subsystem" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index a3cf33ad009f..450b351dfa8e 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -85,13 +85,6 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD) endif endif -ifdef CONFIG_WARN_DYNAMIC_STACK - ifneq ($(call cc-option,-mwarn-dynamicstack),) - KBUILD_CFLAGS += -mwarn-dynamicstack - KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack - endif -endif - ifdef CONFIG_EXPOLINE ifneq ($(call cc-option,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),) CC_FLAGS_EXPOLINE := -mindirect-branch=thunk From 3782326577d4b02f3d9940e1c96c3e9b31cf5309 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 01:19:32 -0700 Subject: [PATCH 271/866] Revert "of: property: fw_devlink: Add support for "phy-handle" property" This reverts commit cf4b94c8530d14017fbddae26aad064ddc42edd4. Some PHYs pointed to by "phy-handle" will never bind to a driver until a consumer attaches to it. And when the consumer attaches to it, they get forcefully bound to a generic PHY driver. In such cases, parsing the phy-handle property and creating a device link will prevent the consumer from ever probing. We don't want that. So revert support for "phy-handle" property until we come up with a better mechanism for binding PHYs to generic drivers before a consumer tries to attach to it. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915081933.485112-1-saravanak@google.com Signed-off-by: Rob Herring --- drivers/of/property.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/of/property.c b/drivers/of/property.c index 3fd74bb34819..a3483484a5a2 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1291,7 +1291,6 @@ DEFINE_SIMPLE_PROP(pwms, "pwms", "#pwm-cells") DEFINE_SIMPLE_PROP(resets, "resets", "#reset-cells") DEFINE_SIMPLE_PROP(leds, "leds", NULL) DEFINE_SIMPLE_PROP(backlight, "backlight", NULL) -DEFINE_SIMPLE_PROP(phy_handle, "phy-handle", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") @@ -1380,7 +1379,6 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_resets, }, { .parse_prop = parse_leds, }, { .parse_prop = parse_backlight, }, - { .parse_prop = parse_phy_handle, }, { .parse_prop = parse_gpio_compat, }, { .parse_prop = parse_interrupts, }, { .parse_prop = parse_regulators, }, From 1e4ce418b1cb1a810256b5fb3fd33d22d1325993 Mon Sep 17 00:00:00 2001 From: "F.A.Sulaiman" Date: Tue, 24 Aug 2021 20:37:30 +0530 Subject: [PATCH 272/866] HID: betop: fix slab-out-of-bounds Write in betop_probe Syzbot reported slab-out-of-bounds Write bug in hid-betopff driver. The problem is the driver assumes the device must have an input report but some malicious devices violate this assumption. So this patch checks hid_device's input is non empty before it's been used. Reported-by: syzbot+07efed3bc5a1407bd742@syzkaller.appspotmail.com Signed-off-by: F.A. SULAIMAN Reviewed-by: Pavel Skripkin Signed-off-by: Jiri Kosina --- drivers/hid/hid-betopff.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c index 0790fbd3fc9a..467d789f9bc2 100644 --- a/drivers/hid/hid-betopff.c +++ b/drivers/hid/hid-betopff.c @@ -56,15 +56,22 @@ static int betopff_init(struct hid_device *hid) { struct betopff_device *betopff; struct hid_report *report; - struct hid_input *hidinput = - list_first_entry(&hid->inputs, struct hid_input, list); + struct hid_input *hidinput; struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; - struct input_dev *dev = hidinput->input; + struct input_dev *dev; int field_count = 0; int error; int i, j; + if (list_empty(&hid->inputs)) { + hid_err(hid, "no inputs found\n"); + return -ENODEV; + } + + hidinput = list_first_entry(&hid->inputs, struct hid_input, list); + dev = hidinput->input; + if (list_empty(report_list)) { hid_err(hid, "no output reports found\n"); return -ENODEV; From ca465e1f1f9b38fe916a36f7d80c5d25f2337c81 Mon Sep 17 00:00:00 2001 From: Tao Liu Date: Mon, 13 Sep 2021 17:33:44 +0800 Subject: [PATCH 273/866] RDMA/cma: Fix listener leak in rdma_cma_listen_on_all() failure If cma_listen_on_all() fails it leaves the per-device ID still on the listen_list but the state is not set to RDMA_CM_ADDR_BOUND. When the cmid is eventually destroyed cma_cancel_listens() is not called due to the wrong state, however the per-device IDs are still holding the refcount preventing the ID from being destroyed, thus deadlocking: task:rping state:D stack: 0 pid:19605 ppid: 47036 flags:0x00000084 Call Trace: __schedule+0x29a/0x780 ? free_unref_page_commit+0x9b/0x110 schedule+0x3c/0xa0 schedule_timeout+0x215/0x2b0 ? __flush_work+0x19e/0x1e0 wait_for_completion+0x8d/0xf0 _destroy_id+0x144/0x210 [rdma_cm] ucma_close_id+0x2b/0x40 [rdma_ucm] __destroy_id+0x93/0x2c0 [rdma_ucm] ? __xa_erase+0x4a/0xa0 ucma_destroy_id+0x9a/0x120 [rdma_ucm] ucma_write+0xb8/0x130 [rdma_ucm] vfs_write+0xb4/0x250 ksys_write+0xb5/0xd0 ? syscall_trace_enter.isra.19+0x123/0x190 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Ensure that cma_listen_on_all() atomically unwinds its action under the lock during error. Fixes: c80a0c52d85c ("RDMA/cma: Add missing error handling of listen_id") Link: https://lore.kernel.org/r/20210913093344.17230-1-thomas.liu@ucloud.cn Signed-off-by: Tao Liu Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 86ee3b01b3ee..5aa58897965d 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1746,15 +1746,16 @@ static void cma_cancel_route(struct rdma_id_private *id_priv) } } -static void cma_cancel_listens(struct rdma_id_private *id_priv) +static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; + lockdep_assert_held(&lock); + /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ - mutex_lock(&lock); list_del(&id_priv->list); while (!list_empty(&id_priv->listen_list)) { @@ -1768,6 +1769,12 @@ static void cma_cancel_listens(struct rdma_id_private *id_priv) rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } +} + +static void cma_cancel_listens(struct rdma_id_private *id_priv) +{ + mutex_lock(&lock); + _cma_cancel_listens(id_priv); mutex_unlock(&lock); } @@ -2579,7 +2586,7 @@ static int cma_listen_on_all(struct rdma_id_private *id_priv) return 0; err_listen: - list_del(&id_priv->list); + _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); From 67fd71ba16a37c663d139f5ba5296f344d80d072 Mon Sep 17 00:00:00 2001 From: Mizuho Mori Date: Thu, 29 Jul 2021 20:03:25 +0900 Subject: [PATCH 274/866] HID: apple: Fix logical maximum and usage maximum of Magic Keyboard JIS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apple Magic Keyboard(JIS)'s Logical Maximum and Usage Maximum are wrong. Below is a report descriptor. 0x05, 0x01, /* Usage Page (Desktop), */ 0x09, 0x06, /* Usage (Keyboard), */ 0xA1, 0x01, /* Collection (Application), */ 0x85, 0x01, /* Report ID (1), */ 0x05, 0x07, /* Usage Page (Keyboard), */ 0x15, 0x00, /* Logical Minimum (0), */ 0x25, 0x01, /* Logical Maximum (1), */ 0x19, 0xE0, /* Usage Minimum (KB Leftcontrol), */ 0x29, 0xE7, /* Usage Maximum (KB Right GUI), */ 0x75, 0x01, /* Report Size (1), */ 0x95, 0x08, /* Report Count (8), */ 0x81, 0x02, /* Input (Variable), */ 0x95, 0x05, /* Report Count (5), */ 0x75, 0x01, /* Report Size (1), */ 0x05, 0x08, /* Usage Page (LED), */ 0x19, 0x01, /* Usage Minimum (01h), */ 0x29, 0x05, /* Usage Maximum (05h), */ 0x91, 0x02, /* Output (Variable), */ 0x95, 0x01, /* Report Count (1), */ 0x75, 0x03, /* Report Size (3), */ 0x91, 0x03, /* Output (Constant, Variable), */ 0x95, 0x08, /* Report Count (8), */ 0x75, 0x01, /* Report Size (1), */ 0x15, 0x00, /* Logical Minimum (0), */ 0x25, 0x01, /* Logical Maximum (1), */ here is a report descriptor which is parsed one in kernel. see sys/kernel/debug/hid//rdesc 05 01 09 06 a1 01 85 01 05 07 15 00 25 01 19 e0 29 e7 75 01 95 08 81 02 95 05 75 01 05 08 19 01 29 05 91 02 95 01 75 03 91 03 95 08 75 01 15 00 25 01 06 00 ff 09 03 81 03 95 06 75 08 15 00 25 [65] 05 07 19 00 29 [65] 81 00 95 01 75 01 15 00 25 01 05 0c 09 b8 81 02 95 01 75 01 06 01 ff 09 03 81 02 95 01 75 06 81 03 06 02 ff 09 55 85 55 15 00 26 ff 00 75 08 95 40 b1 a2 c0 06 00 ff 09 14 a1 01 85 90 05 84 75 01 95 03 15 00 25 01 09 61 05 85 09 44 09 46 81 02 95 05 81 01 75 08 95 01 15 00 26 ff 00 09 65 81 02 c0 00 Position 64(Logical Maximum) and 70(Usage Maximum) are 101. Both should be 0xE7 to support JIS specific keys(ろ, Eisu, Kana, |) support. position 117 is also 101 but not related(it is Usage 65h). There are no difference of product id between JIS and ANSI. They are same 0x0267. Signed-off-by: Mizuho Mori Signed-off-by: Jiri Kosina --- drivers/hid/hid-apple.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 833fcf07ff35..6ccfa0cb997a 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -336,12 +336,19 @@ static int apple_event(struct hid_device *hdev, struct hid_field *field, /* * MacBook JIS keyboard has wrong logical maximum + * Magic Keyboard JIS has wrong logical maximum */ static __u8 *apple_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct apple_sc *asc = hid_get_drvdata(hdev); + if(*rsize >=71 && rdesc[70] == 0x65 && rdesc[64] == 0x65) { + hid_info(hdev, + "fixing up Magic Keyboard JIS report descriptor\n"); + rdesc[64] = rdesc[70] = 0xe7; + } + if ((asc->quirks & APPLE_RDESC_JIS) && *rsize >= 60 && rdesc[53] == 0x65 && rdesc[59] == 0x65) { hid_info(hdev, From 310e2d43c3ad429c1fba4b175806cf1f55ed73a6 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Sun, 12 Sep 2021 22:24:33 +0100 Subject: [PATCH 275/866] netfilter: ip6_tables: zero-initialize fragment offset ip6tables only sets the `IP6T_F_PROTO` flag on a rule if a protocol is specified (`-p tcp`, for example). However, if the flag is not set, `ip6_packet_match` doesn't call `ipv6_find_hdr` for the skb, in which case the fragment offset is left uninitialized and a garbage value is passed to each matcher. Signed-off-by: Jeremy Sowden Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/ip6_tables.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index de2cf3943b91..a579ea14a69b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -273,6 +273,7 @@ ip6t_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ + acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; From 0c8fbaa553077630e8eae45bd9676cfc01836aeb Mon Sep 17 00:00:00 2001 From: Joshua-Dickens Date: Tue, 14 Sep 2021 13:28:25 -0400 Subject: [PATCH 276/866] HID: wacom: Add new Intuos BT (CTL-4100WL/CTL-6100WL) device IDs Add the new PIDs to wacom_wac.c to support the new models in the Intuos series. [jkosina@suse.cz: fix changelog] Signed-off-by: Joshua Dickens Reviewed-by: Ping Cheng Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index fd51769d0994..33a6908995b1 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -4746,6 +4746,12 @@ static const struct wacom_features wacom_features_0x393 = { "Wacom Intuos Pro S", 31920, 19950, 8191, 63, INTUOSP2S_BT, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 7, .touch_max = 10 }; +static const struct wacom_features wacom_features_0x3c6 = + { "Wacom Intuos BT S", 15200, 9500, 4095, 63, + INTUOSHT3_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 }; +static const struct wacom_features wacom_features_0x3c8 = + { "Wacom Intuos BT M", 21600, 13500, 4095, 63, + INTUOSHT3_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 }; static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID }; @@ -4919,6 +4925,8 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x37A) }, { USB_DEVICE_WACOM(0x37B) }, { BT_DEVICE_WACOM(0x393) }, + { BT_DEVICE_WACOM(0x3c6) }, + { BT_DEVICE_WACOM(0x3c8) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, { USB_DEVICE_WACOM(0x5000) }, From cd65869512ab5668a5d16f789bc4da1319c435c4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:19:14 -0600 Subject: [PATCH 277/866] io_uring: use iov_iter state save/restore helpers Get rid of the need to do re-expand and revert on an iterator when we encounter a short IO, or failure that warrants a retry. Use the new state save/restore helpers instead. We keep the iov_iter_state persistent across retries, if we need to restart the read or write operation. If there's a pending retry, the operation will always exit with the state correctly saved. Signed-off-by: Jens Axboe --- fs/io_uring.c | 82 ++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 61 insertions(+), 21 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 855ea544807f..25bda8a5a4e5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -712,6 +712,7 @@ struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; const struct iovec *free_iovec; struct iov_iter iter; + struct iov_iter_state iter_state; size_t bytes_done; struct wait_page_queue wpq; }; @@ -2608,8 +2609,7 @@ static bool io_resubmit_prep(struct io_kiocb *req) if (!rw) return !io_req_prep_async(req); - /* may have left rw->iter inconsistent on -EIOCBQUEUED */ - iov_iter_revert(&rw->iter, req->result - iov_iter_count(&rw->iter)); + iov_iter_restore(&rw->iter, &rw->iter_state); return true; } @@ -3310,12 +3310,17 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; if (!req->async_data) { + struct io_async_rw *iorw; + if (io_alloc_async_data(req)) { kfree(iovec); return -ENOMEM; } io_req_map_rw(req, iovec, fast_iov, iter); + iorw = req->async_data; + /* we've copied and mapped the iter, ensure state is saved */ + iov_iter_save_state(&iorw->iter, &iorw->iter_state); } return 0; } @@ -3334,6 +3339,7 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) iorw->free_iovec = iov; if (iov) req->flags |= REQ_F_NEED_CLEANUP; + iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } @@ -3437,19 +3443,28 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; - ssize_t io_size, ret, ret2; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; if (rw) { iter = &rw->iter; + state = &rw->iter_state; + /* + * We come here from an earlier attempt, restore our state to + * match in case it doesn't. It's cheap enough that we don't + * need to make this conditional. + */ + iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + state = &__state; + iov_iter_save_state(iter, state); } - io_size = iov_iter_count(iter); - req->result = io_size; + req->result = iov_iter_count(iter); /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3463,7 +3478,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret ?: -EAGAIN; } - ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) { kfree(iovec); return ret; @@ -3479,30 +3494,49 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) /* no retry on NONBLOCK nor RWF_NOWAIT */ if (req->flags & REQ_F_NOWAIT) goto done; - /* some cases will consume bytes even on error returns */ - iov_iter_reexpand(iter, iter->count + iter->truncated); - iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; - } else if (ret <= 0 || ret == io_size || !force_nonblock || + } else if (ret <= 0 || ret == req->result || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; } + /* + * Don't depend on the iter state matching what was consumed, or being + * untouched in case of error. Restore it and we'll advance it + * manually if we need to. + */ + iov_iter_restore(iter, state); + ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); if (ret2) return ret2; iovec = NULL; rw = req->async_data; - /* now use our persistent iterator, if we aren't already */ - iter = &rw->iter; + /* + * Now use our persistent iterator and state, if we aren't already. + * We've restored and mapped the iter to match. + */ + if (iter != &rw->iter) { + iter = &rw->iter; + state = &rw->iter_state; + } do { - io_size -= ret; + /* + * We end up here because of a partial read, either from + * above or inside this loop. Advance the iter by the bytes + * that were consumed. + */ + iov_iter_advance(iter, ret); + if (!iov_iter_count(iter)) + break; rw->bytes_done += ret; + iov_iter_save_state(iter, state); + /* if we can retry, do so with the callbacks armed */ if (!io_rw_should_retry(req)) { kiocb->ki_flags &= ~IOCB_WAITQ; @@ -3520,7 +3554,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; - } while (ret > 0 && ret < io_size); + iov_iter_restore(iter, state); + } while (ret > 0); done: kiocb_done(kiocb, ret, issue_flags); out_free: @@ -3543,19 +3578,24 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter __iter, *iter = &__iter; struct io_async_rw *rw = req->async_data; - ssize_t ret, ret2, io_size; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + struct iov_iter_state __state, *state; + ssize_t ret, ret2; if (rw) { iter = &rw->iter; + state = &rw->iter_state; + iov_iter_restore(iter, state); iovec = NULL; } else { ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); if (ret < 0) return ret; + state = &__state; + iov_iter_save_state(iter, state); } - io_size = iov_iter_count(iter); - req->result = io_size; + req->result = iov_iter_count(iter); + ret2 = 0; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3572,7 +3612,7 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) (req->flags & REQ_F_ISREG)) goto copy_iov; - ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), io_size); + ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) goto out_free; @@ -3619,9 +3659,9 @@ done: kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: - /* some cases will consume bytes even on error returns */ - iov_iter_reexpand(iter, iter->count + iter->truncated); - iov_iter_revert(iter, io_size - iov_iter_count(iter)); + iov_iter_restore(iter, state); + if (ret2 > 0) + iov_iter_advance(iter, ret2); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); return ret ?: -EAGAIN; } From 7dedd3e18077f996a10c47250ac85d080e5f474e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:19:58 -0600 Subject: [PATCH 278/866] Revert "iov_iter: track truncated size" This reverts commit 2112ff5ce0c1128fe7b4d19cfe7f2b8ce5b595fa. We no longer need to track the truncation count, the one user that did need it has been converted to using iov_iter_restore() instead. Signed-off-by: Jens Axboe --- include/linux/uio.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/include/linux/uio.h b/include/linux/uio.h index 984c4ab74859..207101a9c5c3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -53,7 +53,6 @@ struct iov_iter { }; loff_t xarray_start; }; - size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -270,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) { - i->truncated += i->count - count; + if (i->count > count) i->count = count; - } } /* @@ -282,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { - i->truncated -= count - i->count; i->count = count; } From b66ceaf324b394428bb47054140ddf03d8172e64 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 15 Sep 2021 11:00:05 +0100 Subject: [PATCH 279/866] io_uring: move iopoll reissue into regular IO path 230d50d448acb ("io_uring: move reissue into regular IO path") made non-IOPOLL I/O to not retry from ki_complete handler. Follow it steps and do the same for IOPOLL. Same problems, same implementation, same -EAGAIN assumptions. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f80dfee2d5fa7678f0052a8ab3cfca9496a112ca.1631699928.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 25bda8a5a4e5..81b0c2723c72 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -736,7 +736,6 @@ enum { REQ_F_BUFFER_SELECTED_BIT, REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, - REQ_F_DONT_REISSUE_BIT, REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, @@ -783,8 +782,6 @@ enum { REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), - /* don't attempt request reissue, see io_rw_reissue() */ - REQ_F_DONT_REISSUE = BIT(REQ_F_DONT_REISSUE_BIT), /* supports async reads */ REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), /* supports async writes */ @@ -2440,13 +2437,6 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - if (READ_ONCE(req->result) == -EAGAIN && - !(req->flags & REQ_F_DONT_REISSUE)) { - req->iopoll_completed = 0; - io_req_task_queue_reissue(req); - continue; - } - __io_cqring_fill_event(ctx, req->user_data, req->result, io_put_rw_kbuf(req)); (*nr_events)++; @@ -2709,10 +2699,9 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); if (unlikely(res != req->result)) { - if (!(res == -EAGAIN && io_rw_should_reissue(req) && - io_resubmit_prep(req))) { - req_set_fail(req); - req->flags |= REQ_F_DONT_REISSUE; + if (res == -EAGAIN && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; + return; } } @@ -2926,7 +2915,6 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_async_rw *io = req->async_data; - bool check_reissue = kiocb->ki_complete == io_complete_rw; /* add previously done IO, if any */ if (io && io->bytes_done > 0) { @@ -2938,19 +2926,27 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && check_reissue) + if (ret >= 0 && (kiocb->ki_complete == io_complete_rw)) __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); - if (check_reissue && (req->flags & REQ_F_REISSUE)) { + if (req->flags & REQ_F_REISSUE) { req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { io_req_task_queue_reissue(req); } else { + unsigned int cflags = io_put_rw_kbuf(req); + struct io_ring_ctx *ctx = req->ctx; + req_set_fail(req); - __io_req_complete(req, issue_flags, ret, - io_put_rw_kbuf(req)); + if (issue_flags & IO_URING_F_NONBLOCK) { + mutex_lock(&ctx->uring_lock); + __io_req_complete(req, issue_flags, ret, cflags); + mutex_unlock(&ctx->uring_lock); + } else { + __io_req_complete(req, issue_flags, ret, cflags); + } } } } From 10d93a98190aec2c3ff98d9472ab1bf0543aa02c Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 15 Sep 2021 15:21:08 +0300 Subject: [PATCH 280/866] ASoC: SOF: imx: imx8: Bar index is only valid for IRAM and SRAM types i.MX8 only uses SOF_FW_BLK_TYPE_IRAM (1) and SOF_FW_BLK_TYPE_SRAM (3) bars, everything else is left as 0 in sdev->bar[] array. If a broken or purposefully crafted firmware image is loaded with other types of FW_BLK_TYPE then a kernel crash can be triggered. Make sure that only IRAM/SRAM type is converted to bar index. Fixes: 202acc565a1f0 ("ASoC: SOF: imx: Add i.MX8 HW support") Signed-off-by: Peter Ujfalusi Reviewed-by: Daniel Baluta Reviewed-by: Ranjani Sridharan Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20210915122116.18317-5-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/imx/imx8.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 12fedf0984bd..7e9723a10d02 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -365,7 +365,14 @@ static int imx8_remove(struct snd_sof_dev *sdev) /* on i.MX8 there is 1 to 1 match between type and BAR idx */ static int imx8_get_bar_index(struct snd_sof_dev *sdev, u32 type) { - return type; + /* Only IRAM and SRAM bars are valid */ + switch (type) { + case SOF_FW_BLK_TYPE_IRAM: + case SOF_FW_BLK_TYPE_SRAM: + return type; + default: + return -EINVAL; + } } static void imx8_ipc_msg_data(struct snd_sof_dev *sdev, From d9be4a88c3627c270bbe032b623dc43f3b764565 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 15 Sep 2021 15:21:09 +0300 Subject: [PATCH 281/866] ASoC: SOF: imx: imx8m: Bar index is only valid for IRAM and SRAM types i.MX8 only uses SOF_FW_BLK_TYPE_IRAM (1) and SOF_FW_BLK_TYPE_SRAM (3) bars, everything else is left as 0 in sdev->bar[] array. If a broken or purposefully crafted firmware image is loaded with other types of FW_BLK_TYPE then a kernel crash can be triggered. Make sure that only IRAM/SRAM type is converted to bar index. Fixes: afb93d716533d ("ASoC: SOF: imx: Add i.MX8M HW support") Signed-off-by: Peter Ujfalusi Reviewed-by: Daniel Baluta Reviewed-by: Ranjani Sridharan Reviewed-by: Guennadi Liakhovetski Link: https://lore.kernel.org/r/20210915122116.18317-6-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/imx/imx8m.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c index cb822d953767..892e1482f97f 100644 --- a/sound/soc/sof/imx/imx8m.c +++ b/sound/soc/sof/imx/imx8m.c @@ -228,7 +228,14 @@ static int imx8m_remove(struct snd_sof_dev *sdev) /* on i.MX8 there is 1 to 1 match between type and BAR idx */ static int imx8m_get_bar_index(struct snd_sof_dev *sdev, u32 type) { - return type; + /* Only IRAM and SRAM bars are valid */ + switch (type) { + case SOF_FW_BLK_TYPE_IRAM: + case SOF_FW_BLK_TYPE_SRAM: + return type; + default: + return -EINVAL; + } } static void imx8m_ipc_msg_data(struct snd_sof_dev *sdev, From b89a05b21f46150ac10a962aa50109250b56b03b Mon Sep 17 00:00:00 2001 From: Baptiste Lepers Date: Mon, 6 Sep 2021 11:53:10 +1000 Subject: [PATCH 282/866] events: Reuse value read using READ_ONCE instead of re-reading it In perf_event_addr_filters_apply, the task associated with the event (event->ctx->task) is read using READ_ONCE at the beginning of the function, checked, and then re-read from event->ctx->task, voiding all guarantees of the checks. Reuse the value that was read by READ_ONCE to ensure the consistency of the task struct throughout the function. Fixes: 375637bc52495 ("perf/core: Introduce address range filtering") Signed-off-by: Baptiste Lepers Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210906015310.12802-1-baptiste.lepers@gmail.com --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 744e8726c5b2..0c000cb01eeb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10193,7 +10193,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event) return; if (ifh->nr_file_filters) { - mm = get_task_mm(event->ctx->task); + mm = get_task_mm(task); if (!mm) goto restart; From 7687201e37fabf2b7cf2b828f7ca46bf30e2948f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 9 Sep 2021 12:59:17 +0200 Subject: [PATCH 283/866] locking/rwbase: Properly match set_and_save_state() to restore_state() Noticed while looking at the readers race. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Acked-by: Will Deacon Link: https://lkml.kernel.org/r/20210909110203.828203010@infradead.org --- kernel/locking/rwbase_rt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 4ba15088e640..542b0170e4f5 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -220,7 +220,7 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb, for (; atomic_read(&rwb->readers);) { /* Optimized out for rwlocks */ if (rwbase_signal_pending_state(state, current)) { - __set_current_state(TASK_RUNNING); + rwbase_restore_current_state(); __rwbase_write_unlock(rwb, 0, flags); return -EINTR; } From 616be87eac9fa2ab2dca1069712f7236e50f3bf6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 9 Sep 2021 12:59:18 +0200 Subject: [PATCH 284/866] locking/rwbase: Extract __rwbase_write_trylock() The code in rwbase_write_lock() is a little non-obvious vs the read+set 'trylock', extract the sequence into a helper function to clarify the code. This also provides a single site to fix fast-path ordering. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Link: https://lkml.kernel.org/r/YUCq3L+u44NDieEJ@hirez.programming.kicks-ass.net --- kernel/locking/rwbase_rt.c | 46 ++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 19 deletions(-) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 542b0170e4f5..48fbbccdce3f 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -196,6 +196,19 @@ static inline void rwbase_write_downgrade(struct rwbase_rt *rwb) __rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags); } +static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb) +{ + /* Can do without CAS because we're serialized by wait_lock. */ + lockdep_assert_held(&rwb->rtmutex.wait_lock); + + if (!atomic_read(&rwb->readers)) { + atomic_set(&rwb->readers, WRITER_BIAS); + return 1; + } + + return 0; +} + static int __sched rwbase_write_lock(struct rwbase_rt *rwb, unsigned int state) { @@ -210,34 +223,30 @@ static int __sched rwbase_write_lock(struct rwbase_rt *rwb, atomic_sub(READER_BIAS, &rwb->readers); raw_spin_lock_irqsave(&rtm->wait_lock, flags); - /* - * set_current_state() for rw_semaphore - * current_save_and_set_rtlock_wait_state() for rwlock - */ - rwbase_set_and_save_current_state(state); + if (__rwbase_write_trylock(rwb)) + goto out_unlock; - /* Block until all readers have left the critical section. */ - for (; atomic_read(&rwb->readers);) { + rwbase_set_and_save_current_state(state); + for (;;) { /* Optimized out for rwlocks */ if (rwbase_signal_pending_state(state, current)) { rwbase_restore_current_state(); __rwbase_write_unlock(rwb, 0, flags); return -EINTR; } + + if (__rwbase_write_trylock(rwb)) + break; + raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); - - /* - * Schedule and wait for the readers to leave the critical - * section. The last reader leaving it wakes the waiter. - */ - if (atomic_read(&rwb->readers) != 0) - rwbase_schedule(); - set_current_state(state); + rwbase_schedule(); raw_spin_lock_irqsave(&rtm->wait_lock, flags); - } - atomic_set(&rwb->readers, WRITER_BIAS); + set_current_state(state); + } rwbase_restore_current_state(); + +out_unlock: raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); return 0; } @@ -253,8 +262,7 @@ static inline int rwbase_write_trylock(struct rwbase_rt *rwb) atomic_sub(READER_BIAS, &rwb->readers); raw_spin_lock_irqsave(&rtm->wait_lock, flags); - if (!atomic_read(&rwb->readers)) { - atomic_set(&rwb->readers, WRITER_BIAS); + if (__rwbase_write_trylock(rwb)) { raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); return 1; } From 81121524f1c798c9481bd7900450b72ee7ac2eef Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 9 Sep 2021 12:59:19 +0200 Subject: [PATCH 285/866] locking/rwbase: Take care of ordering guarantee for fastpath reader Readers of rwbase can lock and unlock without taking any inner lock, if that happens, we need the ordering provided by atomic operations to satisfy the ordering semantics of lock/unlock. Without that, considering the follow case: { X = 0 initially } CPU 0 CPU 1 ===== ===== rt_write_lock(); X = 1 rt_write_unlock(): atomic_add(READER_BIAS - WRITER_BIAS, ->readers); // ->readers is READER_BIAS. rt_read_lock(): if ((r = atomic_read(->readers)) < 0) // True atomic_try_cmpxchg(->readers, r, r + 1); // succeed. r1 = X; // r1 may be 0, because nothing prevent the reordering // of "X=1" and atomic_add() on CPU 1. Therefore audit every usage of atomic operations that may happen in a fast path, and add necessary barriers. Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20210909110203.953991276@infradead.org --- kernel/locking/rwbase_rt.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index 48fbbccdce3f..88191f6e252c 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -41,6 +41,12 @@ * The risk of writer starvation is there, but the pathological use cases * which trigger it are not necessarily the typical RT workloads. * + * Fast-path orderings: + * The lock/unlock of readers can run in fast paths: lock and unlock are only + * atomic ops, and there is no inner lock to provide ACQUIRE and RELEASE + * semantics of rwbase_rt. Atomic ops should thus provide _acquire() + * and _release() (or stronger). + * * Common code shared between RT rw_semaphore and rwlock */ @@ -53,6 +59,7 @@ static __always_inline int rwbase_read_trylock(struct rwbase_rt *rwb) * set. */ for (r = atomic_read(&rwb->readers); r < 0;) { + /* Fully-ordered if cmpxchg() succeeds, provides ACQUIRE */ if (likely(atomic_try_cmpxchg(&rwb->readers, &r, r + 1))) return 1; } @@ -162,6 +169,8 @@ static __always_inline void rwbase_read_unlock(struct rwbase_rt *rwb, /* * rwb->readers can only hit 0 when a writer is waiting for the * active readers to leave the critical section. + * + * dec_and_test() is fully ordered, provides RELEASE. */ if (unlikely(atomic_dec_and_test(&rwb->readers))) __rwbase_read_unlock(rwb, state); @@ -172,7 +181,11 @@ static inline void __rwbase_write_unlock(struct rwbase_rt *rwb, int bias, { struct rt_mutex_base *rtm = &rwb->rtmutex; - atomic_add(READER_BIAS - bias, &rwb->readers); + /* + * _release() is needed in case that reader is in fast path, pairing + * with atomic_try_cmpxchg() in rwbase_read_trylock(), provides RELEASE + */ + (void)atomic_add_return_release(READER_BIAS - bias, &rwb->readers); raw_spin_unlock_irqrestore(&rtm->wait_lock, flags); rwbase_rtmutex_unlock(rtm); } @@ -201,7 +214,11 @@ static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb) /* Can do without CAS because we're serialized by wait_lock. */ lockdep_assert_held(&rwb->rtmutex.wait_lock); - if (!atomic_read(&rwb->readers)) { + /* + * _acquire is needed in case the reader is in the fast path, pairing + * with rwbase_read_unlock(), provides ACQUIRE. + */ + if (!atomic_read_acquire(&rwb->readers)) { atomic_set(&rwb->readers, WRITER_BIAS); return 1; } From 8914a7a247e065438a0ec86a58c1c359223d2c9e Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Wed, 15 Sep 2021 21:45:54 +0800 Subject: [PATCH 286/866] selftests: be sure to make khdr before other targets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit LKP/0Day reported some building errors about kvm, and errors message are not always same: - lib/x86_64/processor.c:1083:31: error: ‘KVM_CAP_NESTED_STATE’ undeclared (first use in this function); did you mean ‘KVM_CAP_PIT_STATE2’? - lib/test_util.c:189:30: error: ‘MAP_HUGE_16KB’ undeclared (first use in this function); did you mean ‘MAP_HUGE_16GB’? Although kvm relies on the khdr, they still be built in parallel when -j is specified. In this case, it will cause compiling errors. Here we mark target khdr as NOTPARALLEL to make it be always built first. CC: Philip Li Reported-by: kernel test robot Signed-off-by: Li Zhijian Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index fa2ac0e56b43..fe7ee2b0f29c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -48,6 +48,7 @@ ARCH ?= $(SUBARCH) # When local build is done, headers are installed in the default # INSTALL_HDR_PATH usr/include. .PHONY: khdr +.NOTPARALLEL: khdr: ifndef KSFT_KHDR_INSTALL_DONE ifeq (1,$(DEFAULT_INSTALL_HDR_PATH)) From 80be5998ad6339e3e804a772723390cb50b96428 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 15 Sep 2021 09:53:38 +0900 Subject: [PATCH 287/866] tools/bootconfig: Define memblock_free_ptr() to fix build error The lib/bootconfig.c file is shared with the 'bootconfig' tooling, and as a result, the changes incommit 77e02cf57b6c ("memblock: introduce saner 'memblock_free_ptr()' interface") need to also be reflected in the tooling header file. So define the new memblock_free_ptr() wrapper, and remove unused __pa() and memblock_free(). Fixes: 77e02cf57b6c ("memblock: introduce saner 'memblock_free_ptr()' interface") Signed-off-by: Masami Hiramatsu Signed-off-by: Linus Torvalds --- tools/bootconfig/include/linux/memblock.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h index 7862f217d85d..f2e506f7d57f 100644 --- a/tools/bootconfig/include/linux/memblock.h +++ b/tools/bootconfig/include/linux/memblock.h @@ -4,9 +4,8 @@ #include -#define __pa(addr) (addr) #define SMP_CACHE_BYTES 0 #define memblock_alloc(size, align) malloc(size) -#define memblock_free(paddr, size) free(paddr) +#define memblock_free_ptr(paddr, size) free(paddr) #endif From 6f5ddde41069fcd1f0993ec76c9dbbf9d021fd4d Mon Sep 17 00:00:00 2001 From: Yanfei Xu Date: Wed, 15 Sep 2021 15:24:26 +0800 Subject: [PATCH 288/866] blkcg: fix memory leak in blk_iolatency_init BUG: memory leak unreferenced object 0xffff888129acdb80 (size 96): comm "syz-executor.1", pid 12661, jiffies 4294962682 (age 15.220s) hex dump (first 32 bytes): 20 47 c9 85 ff ff ff ff 20 d4 8e 29 81 88 ff ff G...... ..).... 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmalloc include/linux/slab.h:591 [inline] [] kzalloc include/linux/slab.h:721 [inline] [] blk_iolatency_init+0x28/0x190 block/blk-iolatency.c:724 [] blkcg_init_queue+0xb4/0x1c0 block/blk-cgroup.c:1185 [] blk_alloc_queue+0x22a/0x2e0 block/blk-core.c:566 [] blk_mq_init_queue_data block/blk-mq.c:3100 [inline] [] __blk_mq_alloc_disk+0x25/0xd0 block/blk-mq.c:3124 [] loop_add+0x1c3/0x360 drivers/block/loop.c:2344 [] loop_control_get_free drivers/block/loop.c:2501 [inline] [] loop_control_ioctl+0x17e/0x2e0 drivers/block/loop.c:2516 [] vfs_ioctl fs/ioctl.c:51 [inline] [] __do_sys_ioctl fs/ioctl.c:874 [inline] [] __se_sys_ioctl fs/ioctl.c:860 [inline] [] __x64_sys_ioctl+0xfc/0x140 fs/ioctl.c:860 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x44/0xae Once blk_throtl_init() queue init failed, blkcg_iolatency_exit() will not be invoked for cleanup. That leads a memory leak. Swap the blk_throtl_init() and blk_iolatency_init() calls can solve this. Reported-by: syzbot+01321b15cc98e6bf96d6@syzkaller.appspotmail.com Fixes: 19688d7f9592 (block/blk-cgroup: Swap the blk_throtl_init() and blk_iolatency_init() calls) Signed-off-by: Yanfei Xu Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210915072426.4022924-1-yanfei.xu@windriver.com Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 3c88a79a319b..1ded4181a6de 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1182,10 +1182,6 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - ret = blk_iolatency_init(q); - if (ret) - goto err_destroy_all; - ret = blk_ioprio_init(q); if (ret) goto err_destroy_all; @@ -1194,6 +1190,12 @@ int blkcg_init_queue(struct request_queue *q) if (ret) goto err_destroy_all; + ret = blk_iolatency_init(q); + if (ret) { + blk_throtl_exit(q); + goto err_destroy_all; + } + return 0; err_destroy_all: From 858560b27645e7e97aca37ee8f232cccd658fbd2 Mon Sep 17 00:00:00 2001 From: Li Jinlin Date: Tue, 14 Sep 2021 12:26:05 +0800 Subject: [PATCH 289/866] blk-cgroup: fix UAF by grabbing blkcg lock before destroying blkg pd KASAN reports a use-after-free report when doing fuzz test: [693354.104835] ================================================================== [693354.105094] BUG: KASAN: use-after-free in bfq_io_set_weight_legacy+0xd3/0x160 [693354.105336] Read of size 4 at addr ffff888be0a35664 by task sh/1453338 [693354.105607] CPU: 41 PID: 1453338 Comm: sh Kdump: loaded Not tainted 4.18.0-147 [693354.105610] Hardware name: Huawei 2288H V5/BC11SPSCB0, BIOS 0.81 07/02/2018 [693354.105612] Call Trace: [693354.105621] dump_stack+0xf1/0x19b [693354.105626] ? show_regs_print_info+0x5/0x5 [693354.105634] ? printk+0x9c/0xc3 [693354.105638] ? cpumask_weight+0x1f/0x1f [693354.105648] print_address_description+0x70/0x360 [693354.105654] kasan_report+0x1b2/0x330 [693354.105659] ? bfq_io_set_weight_legacy+0xd3/0x160 [693354.105665] ? bfq_io_set_weight_legacy+0xd3/0x160 [693354.105670] bfq_io_set_weight_legacy+0xd3/0x160 [693354.105675] ? bfq_cpd_init+0x20/0x20 [693354.105683] cgroup_file_write+0x3aa/0x510 [693354.105693] ? ___slab_alloc+0x507/0x540 [693354.105698] ? cgroup_file_poll+0x60/0x60 [693354.105702] ? 0xffffffff89600000 [693354.105708] ? usercopy_abort+0x90/0x90 [693354.105716] ? mutex_lock+0xef/0x180 [693354.105726] kernfs_fop_write+0x1ab/0x280 [693354.105732] ? cgroup_file_poll+0x60/0x60 [693354.105738] vfs_write+0xe7/0x230 [693354.105744] ksys_write+0xb0/0x140 [693354.105749] ? __ia32_sys_read+0x50/0x50 [693354.105760] do_syscall_64+0x112/0x370 [693354.105766] ? syscall_return_slowpath+0x260/0x260 [693354.105772] ? do_page_fault+0x9b/0x270 [693354.105779] ? prepare_exit_to_usermode+0xf9/0x1a0 [693354.105784] ? enter_from_user_mode+0x30/0x30 [693354.105793] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.105875] Allocated by task 1453337: [693354.106001] kasan_kmalloc+0xa0/0xd0 [693354.106006] kmem_cache_alloc_node_trace+0x108/0x220 [693354.106010] bfq_pd_alloc+0x96/0x120 [693354.106015] blkcg_activate_policy+0x1b7/0x2b0 [693354.106020] bfq_create_group_hierarchy+0x1e/0x80 [693354.106026] bfq_init_queue+0x678/0x8c0 [693354.106031] blk_mq_init_sched+0x1f8/0x460 [693354.106037] elevator_switch_mq+0xe1/0x240 [693354.106041] elevator_switch+0x25/0x40 [693354.106045] elv_iosched_store+0x1a1/0x230 [693354.106049] queue_attr_store+0x78/0xb0 [693354.106053] kernfs_fop_write+0x1ab/0x280 [693354.106056] vfs_write+0xe7/0x230 [693354.106060] ksys_write+0xb0/0x140 [693354.106064] do_syscall_64+0x112/0x370 [693354.106069] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.106114] Freed by task 1453336: [693354.106225] __kasan_slab_free+0x130/0x180 [693354.106229] kfree+0x90/0x1b0 [693354.106233] blkcg_deactivate_policy+0x12c/0x220 [693354.106238] bfq_exit_queue+0xf5/0x110 [693354.106241] blk_mq_exit_sched+0x104/0x130 [693354.106245] __elevator_exit+0x45/0x60 [693354.106249] elevator_switch_mq+0xd6/0x240 [693354.106253] elevator_switch+0x25/0x40 [693354.106257] elv_iosched_store+0x1a1/0x230 [693354.106261] queue_attr_store+0x78/0xb0 [693354.106264] kernfs_fop_write+0x1ab/0x280 [693354.106268] vfs_write+0xe7/0x230 [693354.106271] ksys_write+0xb0/0x140 [693354.106275] do_syscall_64+0x112/0x370 [693354.106280] entry_SYSCALL_64_after_hwframe+0x65/0xca [693354.106329] The buggy address belongs to the object at ffff888be0a35580 which belongs to the cache kmalloc-1k of size 1024 [693354.106736] The buggy address is located 228 bytes inside of 1024-byte region [ffff888be0a35580, ffff888be0a35980) [693354.107114] The buggy address belongs to the page: [693354.107273] page:ffffea002f828c00 count:1 mapcount:0 mapping:ffff888107c17080 index:0x0 compound_mapcount: 0 [693354.107606] flags: 0x17ffffc0008100(slab|head) [693354.107760] raw: 0017ffffc0008100 ffffea002fcbc808 ffffea0030bd3a08 ffff888107c17080 [693354.108020] raw: 0000000000000000 00000000001c001c 00000001ffffffff 0000000000000000 [693354.108278] page dumped because: kasan: bad access detected [693354.108511] Memory state around the buggy address: [693354.108671] ffff888be0a35500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [693354.116396] ffff888be0a35580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [693354.124473] >ffff888be0a35600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [693354.132421] ^ [693354.140284] ffff888be0a35680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [693354.147912] ffff888be0a35700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [693354.155281] ================================================================== blkgs are protected by both queue and blkcg locks and holding either should stabilize them. However, the path of destroying blkg policy data is only protected by queue lock in blkcg_activate_policy()/blkcg_deactivate_policy(). Other tasks can get the blkg policy data before the blkg policy data is destroyed, and use it after destroyed, which will result in a use-after-free. CPU0 CPU1 blkcg_deactivate_policy spin_lock_irq(&q->queue_lock) bfq_io_set_weight_legacy spin_lock_irq(&blkcg->lock) blkg_to_bfqg(blkg) pd_to_bfqg(blkg->pd[pol->plid]) ^^^^^^blkg->pd[pol->plid] != NULL bfqg != NULL pol->pd_free_fn(blkg->pd[pol->plid]) pd_to_bfqg(blkg->pd[pol->plid]) bfqg_put(bfqg) kfree(bfqg) blkg->pd[pol->plid] = NULL spin_unlock_irq(q->queue_lock); bfq_group_set_weight(bfqg, val, 0) bfqg->entity.new_weight ^^^^^^trigger uaf here spin_unlock_irq(&blkcg->lock); Fix by grabbing the matching blkcg lock before trying to destroy blkg policy data. Suggested-by: Tejun Heo Signed-off-by: Li Jinlin Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210914042605.3260596-1-lijinlin3@huawei.com Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 1ded4181a6de..38b9f7684952 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1366,10 +1366,14 @@ enomem: /* alloc failed, nothing's initialized yet, free everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { + struct blkcg *blkcg = blkg->blkcg; + + spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } + spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; @@ -1401,12 +1405,16 @@ void blkcg_deactivate_policy(struct request_queue *q, __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { + struct blkcg *blkcg = blkg->blkcg; + + spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } + spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); From f6b5f1a56987de837f8e25cd560847106b8632a8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:24 -0700 Subject: [PATCH 290/866] compiler.h: Introduce absolute_pointer macro absolute_pointer() disassociates a pointer from its originating symbol type and context. Use it to prevent compiler warnings/errors such as drivers/net/ethernet/i825xx/82596.c: In function 'i82596_probe': arch/m68k/include/asm/string.h:72:25: error: '__builtin_memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] Such warnings may be reported by gcc 11.x for string and memory operations on fixed addresses. Suggested-by: Linus Torvalds Signed-off-by: Guenter Roeck Reviewed-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b67261a1e3e9..3d5af56337bd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, (typeof(ptr)) (__ptr + (off)); }) #endif +#define absolute_pointer(val) RELOC_HIDE((void *)(val), 0) + #ifndef OPTIMIZER_HIDE_VAR /* Make the optimizer believe the variable can be manipulated arbitrarily. */ #define OPTIMIZER_HIDE_VAR(var) \ From dff2d13114f0beec448da9b3716204eb34b0cf41 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:25 -0700 Subject: [PATCH 291/866] net: i825xx: Use absolute_pointer for memcpy from fixed memory location gcc 11.x reports the following compiler warning/error. drivers/net/ethernet/i825xx/82596.c: In function 'i82596_probe': arch/m68k/include/asm/string.h:72:25: error: '__builtin_memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] Use absolute_pointer() to work around the problem. Cc: Geert Uytterhoeven Signed-off-by: Guenter Roeck Reviewed-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- drivers/net/ethernet/i825xx/82596.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index b8a40146b895..b482f6f633bd 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1144,7 +1144,7 @@ static struct net_device * __init i82596_probe(void) err = -ENODEV; goto out; } - memcpy(eth_addr, (void *) 0xfffc1f2c, ETH_ALEN); /* YUCK! Get addr from NOVRAM */ + memcpy(eth_addr, absolute_pointer(0xfffc1f2c), ETH_ALEN); /* YUCK! Get addr from NOVRAM */ dev->base_addr = MVME_I596_BASE; dev->irq = (unsigned) MVME16x_IRQ_I596; goto found; From 3cb8b1537f8a89a681d2548ded5526280846f6db Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:26 -0700 Subject: [PATCH 292/866] alpha: Move setup.h out of uapi Most of the contents of setup.h have no value for userspace applications. The file was probably moved to uapi accidentally. Keep the file in uapi to define the alpha-specific COMMAND_LINE_SIZE. Move all other defines to arch/alpha/include/asm/setup.h. Suggested-by: Linus Torvalds Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/setup.h | 43 +++++++++++++++++++++++++++++ arch/alpha/include/uapi/asm/setup.h | 42 ++-------------------------- 2 files changed, 46 insertions(+), 39 deletions(-) create mode 100644 arch/alpha/include/asm/setup.h diff --git a/arch/alpha/include/asm/setup.h b/arch/alpha/include/asm/setup.h new file mode 100644 index 000000000000..58fe3f45a235 --- /dev/null +++ b/arch/alpha/include/asm/setup.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ALPHA_SETUP_H +#define __ALPHA_SETUP_H + +#include + +/* + * We leave one page for the initial stack page, and one page for + * the initial process structure. Also, the console eats 3 MB for + * the initial bootloader (one of which we can reclaim later). + */ +#define BOOT_PCB 0x20000000 +#define BOOT_ADDR 0x20000000 +/* Remove when official MILO sources have ELF support: */ +#define BOOT_SIZE (16*1024) + +#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS +#define KERNEL_START_PHYS 0x300000 /* Old bootloaders hardcoded this. */ +#else +#define KERNEL_START_PHYS 0x1000000 /* required: Wildfire/Titan/Marvel */ +#endif + +#define KERNEL_START (PAGE_OFFSET+KERNEL_START_PHYS) +#define SWAPPER_PGD KERNEL_START +#define INIT_STACK (PAGE_OFFSET+KERNEL_START_PHYS+0x02000) +#define EMPTY_PGT (PAGE_OFFSET+KERNEL_START_PHYS+0x04000) +#define EMPTY_PGE (PAGE_OFFSET+KERNEL_START_PHYS+0x08000) +#define ZERO_PGE (PAGE_OFFSET+KERNEL_START_PHYS+0x0A000) + +#define START_ADDR (PAGE_OFFSET+KERNEL_START_PHYS+0x10000) + +/* + * This is setup by the secondary bootstrap loader. Because + * the zero page is zeroed out as soon as the vm system is + * initialized, we need to copy things out into a more permanent + * place. + */ +#define PARAM ZERO_PGE +#define COMMAND_LINE ((char *)(PARAM + 0x0000)) +#define INITRD_START (*(unsigned long *) (PARAM+0x100)) +#define INITRD_SIZE (*(unsigned long *) (PARAM+0x108)) + +#endif diff --git a/arch/alpha/include/uapi/asm/setup.h b/arch/alpha/include/uapi/asm/setup.h index 13b7ee465b0e..f881ea5947cb 100644 --- a/arch/alpha/include/uapi/asm/setup.h +++ b/arch/alpha/include/uapi/asm/setup.h @@ -1,43 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef __ALPHA_SETUP_H -#define __ALPHA_SETUP_H +#ifndef _UAPI__ALPHA_SETUP_H +#define _UAPI__ALPHA_SETUP_H #define COMMAND_LINE_SIZE 256 -/* - * We leave one page for the initial stack page, and one page for - * the initial process structure. Also, the console eats 3 MB for - * the initial bootloader (one of which we can reclaim later). - */ -#define BOOT_PCB 0x20000000 -#define BOOT_ADDR 0x20000000 -/* Remove when official MILO sources have ELF support: */ -#define BOOT_SIZE (16*1024) - -#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS -#define KERNEL_START_PHYS 0x300000 /* Old bootloaders hardcoded this. */ -#else -#define KERNEL_START_PHYS 0x1000000 /* required: Wildfire/Titan/Marvel */ -#endif - -#define KERNEL_START (PAGE_OFFSET+KERNEL_START_PHYS) -#define SWAPPER_PGD KERNEL_START -#define INIT_STACK (PAGE_OFFSET+KERNEL_START_PHYS+0x02000) -#define EMPTY_PGT (PAGE_OFFSET+KERNEL_START_PHYS+0x04000) -#define EMPTY_PGE (PAGE_OFFSET+KERNEL_START_PHYS+0x08000) -#define ZERO_PGE (PAGE_OFFSET+KERNEL_START_PHYS+0x0A000) - -#define START_ADDR (PAGE_OFFSET+KERNEL_START_PHYS+0x10000) - -/* - * This is setup by the secondary bootstrap loader. Because - * the zero page is zeroed out as soon as the vm system is - * initialized, we need to copy things out into a more permanent - * place. - */ -#define PARAM ZERO_PGE -#define COMMAND_LINE ((char*)(PARAM + 0x0000)) -#define INITRD_START (*(unsigned long *) (PARAM+0x100)) -#define INITRD_SIZE (*(unsigned long *) (PARAM+0x108)) - -#endif +#endif /* _UAPI__ALPHA_SETUP_H */ From ebdc20d7bc74e8b6a242ff1f30e9017ffca9092c Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:27 -0700 Subject: [PATCH 293/866] alpha: Use absolute_pointer to define COMMAND_LINE alpha:allmodconfig fails to build with the following error when using gcc 11.x. arch/alpha/kernel/setup.c: In function 'setup_arch': arch/alpha/kernel/setup.c:493:13: error: 'strcmp' reading 1 or more bytes from a region of size 0 Avoid the problem by declaring COMMAND_LINE as absolute_pointer(). Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/setup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/include/asm/setup.h b/arch/alpha/include/asm/setup.h index 58fe3f45a235..262aab99e391 100644 --- a/arch/alpha/include/asm/setup.h +++ b/arch/alpha/include/asm/setup.h @@ -36,7 +36,7 @@ * place. */ #define PARAM ZERO_PGE -#define COMMAND_LINE ((char *)(PARAM + 0x0000)) +#define COMMAND_LINE ((char *)(absolute_pointer(PARAM + 0x0000))) #define INITRD_START (*(unsigned long *) (PARAM+0x100)) #define INITRD_SIZE (*(unsigned long *) (PARAM+0x108)) From 37cb28ec7d3a36a5bace7063a3dba633ab110f8b Mon Sep 17 00:00:00 2001 From: Piotr Krysiuk Date: Wed, 15 Sep 2021 17:04:37 +0100 Subject: [PATCH 294/866] bpf, mips: Validate conditional branch offsets The conditional branch instructions on MIPS use 18-bit signed offsets allowing for a branch range of 128 KBytes (backward and forward). However, this limit is not observed by the cBPF JIT compiler, and so the JIT compiler emits out-of-range branches when translating certain cBPF programs. A specific example of such a cBPF program is included in the "BPF_MAXINSNS: exec all MSH" test from lib/test_bpf.c that executes anomalous machine code containing incorrect branch offsets under JIT. Furthermore, this issue can be abused to craft undesirable machine code, where the control flow is hijacked to execute arbitrary Kernel code. The following steps can be used to reproduce the issue: # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_name="BPF_MAXINSNS: exec all MSH" This should produce multiple warnings from build_bimm() similar to: ------------[ cut here ]------------ WARNING: CPU: 0 PID: 209 at arch/mips/mm/uasm-mips.c:210 build_insn+0x558/0x590 Micro-assembler field overflow Modules linked in: test_bpf(+) CPU: 0 PID: 209 Comm: modprobe Not tainted 5.14.3 #1 Stack : 00000000 807bb824 82b33c9c 801843c0 00000000 00000004 00000000 63c9b5ee 82b33af4 80999898 80910000 80900000 82fd6030 00000001 82b33a98 82087180 00000000 00000000 80873b28 00000000 000000fc 82b3394c 00000000 2e34312e 6d6d6f43 809a180f 809a1836 6f6d203a 80900000 00000001 82b33bac 80900000 00027f80 00000000 00000000 807bb824 00000000 804ed790 001cc317 00000001 [...] Call Trace: [<80108f44>] show_stack+0x38/0x118 [<807a7aac>] dump_stack_lvl+0x5c/0x7c [<807a4b3c>] __warn+0xcc/0x140 [<807a4c3c>] warn_slowpath_fmt+0x8c/0xb8 [<8011e198>] build_insn+0x558/0x590 [<8011e358>] uasm_i_bne+0x20/0x2c [<80127b48>] build_body+0xa58/0x2a94 [<80129c98>] bpf_jit_compile+0x114/0x1e4 [<80613fc4>] bpf_prepare_filter+0x2ec/0x4e4 [<8061423c>] bpf_prog_create+0x80/0xc4 [] test_bpf_init+0x300/0xba8 [test_bpf] [<8010051c>] do_one_initcall+0x50/0x1d4 [<801c5e54>] do_init_module+0x60/0x220 [<801c8b20>] sys_finit_module+0xc4/0xfc [<801144d0>] syscall_common+0x34/0x58 [...] ---[ end trace a287d9742503c645 ]--- Then the anomalous machine code executes: => 0xc0a18000: addiu sp,sp,-16 0xc0a18004: sw s3,0(sp) 0xc0a18008: sw s4,4(sp) 0xc0a1800c: sw s5,8(sp) 0xc0a18010: sw ra,12(sp) 0xc0a18014: move s5,a0 0xc0a18018: move s4,zero 0xc0a1801c: move s3,zero # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a18020: lui t6,0x8012 0xc0a18024: ori t4,t6,0x9e14 0xc0a18028: li a1,0 0xc0a1802c: jalr t4 0xc0a18030: move a0,s5 0xc0a18034: bnez v0,0xc0a1ffb8 # incorrect branch offset 0xc0a18038: move v0,zero 0xc0a1803c: andi s4,s3,0xf 0xc0a18040: b 0xc0a18048 0xc0a18044: sll s4,s4,0x2 [...] # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a1ffa0: lui t6,0x8012 0xc0a1ffa4: ori t4,t6,0x9e14 0xc0a1ffa8: li a1,0 0xc0a1ffac: jalr t4 0xc0a1ffb0: move a0,s5 0xc0a1ffb4: bnez v0,0xc0a1ffb8 # incorrect branch offset 0xc0a1ffb8: move v0,zero 0xc0a1ffbc: andi s4,s3,0xf 0xc0a1ffc0: b 0xc0a1ffc8 0xc0a1ffc4: sll s4,s4,0x2 # __BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0) 0xc0a1ffc8: lui t6,0x8012 0xc0a1ffcc: ori t4,t6,0x9e14 0xc0a1ffd0: li a1,0 0xc0a1ffd4: jalr t4 0xc0a1ffd8: move a0,s5 0xc0a1ffdc: bnez v0,0xc0a3ffb8 # correct branch offset 0xc0a1ffe0: move v0,zero 0xc0a1ffe4: andi s4,s3,0xf 0xc0a1ffe8: b 0xc0a1fff0 0xc0a1ffec: sll s4,s4,0x2 [...] # epilogue 0xc0a3ffb8: lw s3,0(sp) 0xc0a3ffbc: lw s4,4(sp) 0xc0a3ffc0: lw s5,8(sp) 0xc0a3ffc4: lw ra,12(sp) 0xc0a3ffc8: addiu sp,sp,16 0xc0a3ffcc: jr ra 0xc0a3ffd0: nop To mitigate this issue, we assert the branch ranges for each emit call that could generate an out-of-range branch. Fixes: 36366e367ee9 ("MIPS: BPF: Restore MIPS32 cBPF JIT") Fixes: c6610de353da ("MIPS: net: Add BPF JIT") Signed-off-by: Piotr Krysiuk Signed-off-by: Daniel Borkmann Tested-by: Johan Almbladh Acked-by: Johan Almbladh Cc: Paul Burton Cc: Thomas Bogendoerfer Link: https://lore.kernel.org/bpf/20210915160437.4080-1-piotras@gmail.com --- arch/mips/net/bpf_jit.c | 57 +++++++++++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 14 deletions(-) diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 0af88622c619..cb6d22439f71 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -662,6 +662,11 @@ static void build_epilogue(struct jit_ctx *ctx) ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \ func##_positive) +static bool is_bad_offset(int b_off) +{ + return b_off > 0x1ffff || b_off < -0x20000; +} + static int build_body(struct jit_ctx *ctx) { const struct bpf_prog *prog = ctx->skf; @@ -728,7 +733,10 @@ load_common: /* Load return register on DS for failures */ emit_reg_move(r_ret, r_zero, ctx); /* Return with error */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_LD | BPF_W | BPF_IND: @@ -775,8 +783,10 @@ load_ind: emit_jalr(MIPS_R_RA, r_s0, ctx); emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */ /* Check the error value */ - emit_bcond(MIPS_COND_NE, r_ret, 0, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_NE, r_ret, 0, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); /* We are good */ /* X <- P[1:K] & 0xf */ @@ -855,8 +865,10 @@ load_ind: /* A /= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_div(r_A, r_X, ctx); break; @@ -864,8 +876,10 @@ load_ind: /* A %= X */ ctx->flags |= SEEN_X | SEEN_A; /* Check if r_X is zero */ - emit_bcond(MIPS_COND_EQ, r_X, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_X, r_zero, b_off, ctx); emit_load_imm(r_ret, 0, ctx); /* delay slot */ emit_mod(r_A, r_X, ctx); break; @@ -926,7 +940,10 @@ load_ind: break; case BPF_JMP | BPF_JA: /* pc += K */ - emit_b(b_imm(i + k + 1, ctx), ctx); + b_off = b_imm(i + k + 1, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); break; case BPF_JMP | BPF_JEQ | BPF_K: @@ -1056,12 +1073,16 @@ jmp_cmp: break; case BPF_RET | BPF_A: ctx->flags |= SEEN_A; - if (i != prog->len - 1) + if (i != prog->len - 1) { /* * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); + } emit_reg_move(r_ret, r_A, ctx); /* delay slot */ break; case BPF_RET | BPF_K: @@ -1075,7 +1096,10 @@ jmp_cmp: * If this is not the last instruction * then jump to the epilogue */ - emit_b(b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_b(b_off, ctx); emit_nop(ctx); } break; @@ -1133,8 +1157,10 @@ jmp_cmp: /* Load *dev pointer */ emit_load_ptr(r_s0, r_skb, off, ctx); /* error (0) in the delay slot */ - emit_bcond(MIPS_COND_EQ, r_s0, r_zero, - b_imm(prog->len, ctx), ctx); + b_off = b_imm(prog->len, ctx); + if (is_bad_offset(b_off)) + return -E2BIG; + emit_bcond(MIPS_COND_EQ, r_s0, r_zero, b_off, ctx); emit_reg_move(r_ret, r_zero, ctx); if (code == (BPF_ANC | SKF_AD_IFINDEX)) { BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); @@ -1244,7 +1270,10 @@ void bpf_jit_compile(struct bpf_prog *fp) /* Generate the actual JIT code */ build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx)) { + module_memfree(ctx.target); + goto out; + } build_epilogue(&ctx); /* Update the icache */ From fc7c028dcdbfe981bca75d2a7b95f363eb691ef3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 6 Sep 2021 16:06:04 -0700 Subject: [PATCH 295/866] sparc: avoid stringop-overread errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sparc mdesc code does pointer games with 'struct mdesc_hdr', but didn't describe to the compiler how that header is then followed by the data that the header describes. As a result, gcc is now unhappy since it does stricter pointer range tracking, and doesn't understand about how these things work. This results in various errors like: arch/sparc/kernel/mdesc.c: In function ‘mdesc_node_by_name’: arch/sparc/kernel/mdesc.c:647:22: error: ‘strcmp’ reading 1 or more bytes from a region of size 0 [-Werror=stringop-overread] 647 | if (!strcmp(names + ep[ret].name_offset, name)) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ which are easily avoided by just describing 'struct mdesc_hdr' better, and making the node_block() helper function look into that unsized data[] that follows the header. This makes the sparc64 build happy again at least for my cross-compiler version (gcc version 11.2.1). Link: https://lore.kernel.org/lkml/CAHk-=wi4NW3NC0xWykkw=6LnjQD6D_rtRtxY9g8gQAJXtQMi8A@mail.gmail.com/ Cc: Guenter Roeck Cc: David S. Miller Signed-off-by: Linus Torvalds --- arch/sparc/kernel/mdesc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 8e645ddac58e..30f171b7b00c 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -39,6 +39,7 @@ struct mdesc_hdr { u32 node_sz; /* node block size */ u32 name_sz; /* name block size */ u32 data_sz; /* data block size */ + char data[]; } __attribute__((aligned(16))); struct mdesc_elem { @@ -612,7 +613,7 @@ EXPORT_SYMBOL(mdesc_get_node_info); static struct mdesc_elem *node_block(struct mdesc_hdr *mdesc) { - return (struct mdesc_elem *) (mdesc + 1); + return (struct mdesc_elem *) mdesc->data; } static void *name_block(struct mdesc_hdr *mdesc) From b7213ffa0e585feb1aee3e7173e965e66ee0abaa Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 15 Sep 2021 13:56:37 -0700 Subject: [PATCH 296/866] qnx4: avoid stringop-overread errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The qnx4 directory entries are 64-byte blocks that have different contents depending on the a status byte that is in the last byte of the block. In particular, a directory entry can be either a "link info" entry with a 48-byte name and pointers to the real inode information, or an "inode entry" with a smaller 16-byte name and the full inode information. But the code was written to always just treat the directory name as if it was part of that "inode entry", and just extend the name to the longer case if the status byte said it was a link entry. That work just fine and gives the right results, but now that gcc is tracking data structure accesses much more, the code can trigger a compiler error about using up to 48 bytes (the long name) in a structure that only has that shorter name in it: fs/qnx4/dir.c: In function ‘qnx4_readdir’: fs/qnx4/dir.c:51:32: error: ‘strnlen’ specified bound 48 exceeds source size 16 [-Werror=stringop-overread] 51 | size = strnlen(de->di_fname, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from fs/qnx4/qnx4.h:3, from fs/qnx4/dir.c:16: include/uapi/linux/qnx4_fs.h:45:25: note: source object declared here 45 | char di_fname[QNX4_SHORT_NAME_MAX]; | ^~~~~~~~ which is because the source code doesn't really make this whole "one of two different types" explicit. Fix this by introducing a very explicit union of the two types, and basically explaining to the compiler what is really going on. Signed-off-by: Linus Torvalds --- fs/qnx4/dir.c | 51 ++++++++++++++++++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 17 deletions(-) diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index a6ee23aadd28..2a66844b7ff8 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -15,13 +15,27 @@ #include #include "qnx4.h" +/* + * A qnx4 directory entry is an inode entry or link info + * depending on the status field in the last byte. The + * first byte is where the name start either way, and a + * zero means it's empty. + */ +union qnx4_directory_entry { + struct { + char de_name; + char de_pad[62]; + char de_status; + }; + struct qnx4_inode_entry inode; + struct qnx4_link_info link; +}; + static int qnx4_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); unsigned int offset; struct buffer_head *bh; - struct qnx4_inode_entry *de; - struct qnx4_link_info *le; unsigned long blknum; int ix, ino; int size; @@ -38,27 +52,30 @@ static int qnx4_readdir(struct file *file, struct dir_context *ctx) } ix = (ctx->pos >> QNX4_DIR_ENTRY_SIZE_BITS) % QNX4_INODES_PER_BLOCK; for (; ix < QNX4_INODES_PER_BLOCK; ix++, ctx->pos += QNX4_DIR_ENTRY_SIZE) { + union qnx4_directory_entry *de; + const char *name; + offset = ix * QNX4_DIR_ENTRY_SIZE; - de = (struct qnx4_inode_entry *) (bh->b_data + offset); - if (!de->di_fname[0]) + de = (union qnx4_directory_entry *) (bh->b_data + offset); + + if (!de->de_name) continue; - if (!(de->di_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) + if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) continue; - if (!(de->di_status & QNX4_FILE_LINK)) - size = QNX4_SHORT_NAME_MAX; - else - size = QNX4_NAME_MAX; - size = strnlen(de->di_fname, size); - QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, de->di_fname)); - if (!(de->di_status & QNX4_FILE_LINK)) + if (!(de->de_status & QNX4_FILE_LINK)) { + size = sizeof(de->inode.di_fname); + name = de->inode.di_fname; ino = blknum * QNX4_INODES_PER_BLOCK + ix - 1; - else { - le = (struct qnx4_link_info*)de; - ino = ( le32_to_cpu(le->dl_inode_blk) - 1 ) * + } else { + size = sizeof(de->link.dl_fname); + name = de->link.dl_fname; + ino = ( le32_to_cpu(de->link.dl_inode_blk) - 1 ) * QNX4_INODES_PER_BLOCK + - le->dl_inode_ndx; + de->link.dl_inode_ndx; } - if (!dir_emit(ctx, de->di_fname, size, ino, DT_UNKNOWN)) { + size = strnlen(name, size); + QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, name)); + if (!dir_emit(ctx, name, size, ino, DT_UNKNOWN)) { brelse(bh); return 0; } From 34331739e19fd6a293d488add28832ad49c9fc54 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 10 Aug 2021 09:40:36 -0700 Subject: [PATCH 297/866] fpga: machxo2-spi: Return an error on failure Earlier successes leave 'ret' in a non error state, so these errors are not reported. Set ret to -EINVAL before going to the error handler. This addresses two issues reported by smatch: drivers/fpga/machxo2-spi.c:229 machxo2_write_init() warn: missing error code 'ret' drivers/fpga/machxo2-spi.c:316 machxo2_write_complete() warn: missing error code 'ret' [mdf@kernel.org: Reworded commit message] Fixes: 88fb3a002330 ("fpga: lattice machxo2: Add Lattice MachXO2 support") Reported-by: Dan Carpenter Signed-off-by: Tom Rix Signed-off-by: Moritz Fischer --- drivers/fpga/machxo2-spi.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/fpga/machxo2-spi.c b/drivers/fpga/machxo2-spi.c index 1afb41aa20d7..b4a530a31302 100644 --- a/drivers/fpga/machxo2-spi.c +++ b/drivers/fpga/machxo2-spi.c @@ -225,8 +225,10 @@ static int machxo2_write_init(struct fpga_manager *mgr, goto fail; get_status(spi, &status); - if (test_bit(FAIL, &status)) + if (test_bit(FAIL, &status)) { + ret = -EINVAL; goto fail; + } dump_status_reg(&status); spi_message_init(&msg); @@ -313,6 +315,7 @@ static int machxo2_write_complete(struct fpga_manager *mgr, dump_status_reg(&status); if (!test_bit(DONE, &status)) { machxo2_cleanup(mgr); + ret = -EINVAL; goto fail; } From a1e4470823d99e75b596748086e120dea169ed3c Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 13 Aug 2021 14:40:42 +0800 Subject: [PATCH 298/866] fpga: machxo2-spi: Fix missing error code in machxo2_write_complete() The error code is missing in this code scenario, add the error code '-EINVAL' to the return value 'ret'. Eliminate the follow smatch warning: drivers/fpga/machxo2-spi.c:341 machxo2_write_complete() warn: missing error code 'ret'. [mdf@kernel.org: Reworded commit message] Fixes: 88fb3a002330 ("fpga: lattice machxo2: Add Lattice MachXO2 support") Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: Moritz Fischer --- drivers/fpga/machxo2-spi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/fpga/machxo2-spi.c b/drivers/fpga/machxo2-spi.c index b4a530a31302..ea2ec3c6815c 100644 --- a/drivers/fpga/machxo2-spi.c +++ b/drivers/fpga/machxo2-spi.c @@ -338,6 +338,7 @@ static int machxo2_write_complete(struct fpga_manager *mgr, break; if (++refreshloop == MACHXO2_MAX_REFRESH_LOOP) { machxo2_cleanup(mgr); + ret = -EINVAL; goto fail; } } while (1); From 00e1a5d21b4ff514593554167b28a8caeda1497f Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 13 Sep 2021 16:13:26 -0500 Subject: [PATCH 299/866] PCI/VPD: Defer VPD sizing until first access 7bac54497c3e ("PCI/VPD: Determine VPD size in pci_vpd_init()") reads VPD at enumeration-time to find the size. But this is quite slow, and we don't need the size until we actually need data from VPD. Dave reported a boot slowdown of more than two minutes [1]. Defer the VPD sizing until a driver or the user (via sysfs) requests information from VPD. If devices are quirked because VPD is known not to work, don't bother even looking for the VPD capability. The VPD will not be accessible at all. [1] https://lore.kernel.org/r/20210913141818.GA27911@codemonkey.org.uk/ Link: https://lore.kernel.org/r/20210914215543.GA1437800@bjorn-Precision-5520 Fixes: 7bac54497c3e ("PCI/VPD: Determine VPD size in pci_vpd_init()") Signed-off-by: Bjorn Helgaas --- drivers/pci/vpd.c | 36 ++++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-) diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 25557b272a4f..4be24890132e 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -99,6 +99,24 @@ error: return off ?: PCI_VPD_SZ_INVALID; } +static bool pci_vpd_available(struct pci_dev *dev) +{ + struct pci_vpd *vpd = &dev->vpd; + + if (!vpd->cap) + return false; + + if (vpd->len == 0) { + vpd->len = pci_vpd_size(dev); + if (vpd->len == PCI_VPD_SZ_INVALID) { + vpd->cap = 0; + return false; + } + } + + return true; +} + /* * Wait for last operation to complete. * This code has to spin since there is no other notification from the PCI @@ -145,7 +163,7 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, loff_t end = pos + count; u8 *buf = arg; - if (!vpd->cap) + if (!pci_vpd_available(dev)) return -ENODEV; if (pos < 0) @@ -206,7 +224,7 @@ static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, loff_t end = pos + count; int ret = 0; - if (!vpd->cap) + if (!pci_vpd_available(dev)) return -ENODEV; if (pos < 0 || (pos & 3) || (count & 3)) @@ -242,14 +260,11 @@ static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, void pci_vpd_init(struct pci_dev *dev) { + if (dev->vpd.len == PCI_VPD_SZ_INVALID) + return; + dev->vpd.cap = pci_find_capability(dev, PCI_CAP_ID_VPD); mutex_init(&dev->vpd.lock); - - if (!dev->vpd.len) - dev->vpd.len = pci_vpd_size(dev); - - if (dev->vpd.len == PCI_VPD_SZ_INVALID) - dev->vpd.cap = 0; } static ssize_t vpd_read(struct file *filp, struct kobject *kobj, @@ -294,13 +309,14 @@ const struct attribute_group pci_dev_vpd_attr_group = { void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size) { - unsigned int len = dev->vpd.len; + unsigned int len; void *buf; int cnt; - if (!dev->vpd.cap) + if (!pci_vpd_available(dev)) return ERR_PTR(-ENODEV); + len = dev->vpd.len; buf = kmalloc(len, GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); From 6bd65974dedd1e8638e6665e92ccbf26e8a67cbf Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Mon, 13 Sep 2021 18:23:59 +0100 Subject: [PATCH 300/866] PCI/ACPI: Don't reset a fwnode set by OF Commit 375553a93201 ("PCI: Setup ACPI fwnode early and at the same time with OF") added a call to pci_set_acpi_fwnode() in pci_setup_device(), which unconditionally clears any fwnode previously set by pci_set_of_node(). pci_set_acpi_fwnode() looks for ACPI_COMPANION(), which only returns the existing fwnode if it was set by ACPI_COMPANION_SET(). If it was set by OF instead, ACPI_COMPANION() returns NULL and pci_set_acpi_fwnode() accidentally clears the fwnode. To fix this, look for any fwnode instead of just ACPI companions. Fixes a virtio-iommu boot regression in v5.15-rc1. Fixes: 375553a93201 ("PCI: Setup ACPI fwnode early and at the same time with OF") Link: https://lore.kernel.org/r/20210913172358.1775381-1-jean-philippe@linaro.org Signed-off-by: Jean-Philippe Brucker Signed-off-by: Bjorn Helgaas Acked-by: Rob Herring Acked-by: Rafael J. Wysocki --- drivers/pci/pci-acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index a1b1e2a01632..0f40943a9a18 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -937,7 +937,7 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev); void pci_set_acpi_fwnode(struct pci_dev *dev) { - if (!ACPI_COMPANION(&dev->dev) && !pci_dev_is_added(dev)) + if (!dev_fwnode(&dev->dev) && !pci_dev_is_added(dev)) ACPI_COMPANION_SET(&dev->dev, acpi_pci_find_companion(&dev->dev)); } From 60b78ed088ebe1a872ee1320b6c5ad6ee2c4bd9a Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 3 Sep 2021 14:33:11 +0800 Subject: [PATCH 301/866] PCI: Add AMD GPU multi-function power dependencies Some AMD GPUs have built-in USB xHCI and USB Type-C UCSI controllers with power dependencies between the GPU and the other functions as in 6d2e369f0d4c ("PCI: Add NVIDIA GPU multi-function power dependencies"). Add device link support for the AMD integrated USB xHCI and USB Type-C UCSI controllers. Without this, runtime power management, including GPU resume and temp and fan sensors don't work correctly. Reported-at: https://gitlab.freedesktop.org/drm/amd/-/issues/1704 Link: https://lore.kernel.org/r/20210903063311.3606226-1-evan.quan@amd.com Signed-off-by: Evan Quan Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org --- drivers/pci/quirks.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e5089af8ad90..4537d1ea14fd 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5435,7 +5435,7 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda); /* - * Create device link for NVIDIA GPU with integrated USB xHCI Host + * Create device link for GPUs with integrated USB xHCI Host * controller to VGA. */ static void quirk_gpu_usb(struct pci_dev *usb) @@ -5444,9 +5444,11 @@ static void quirk_gpu_usb(struct pci_dev *usb) } DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_SERIAL_USB, 8, quirk_gpu_usb); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_SERIAL_USB, 8, quirk_gpu_usb); /* - * Create device link for NVIDIA GPU with integrated Type-C UCSI controller + * Create device link for GPUs with integrated Type-C UCSI controller * to VGA. Currently there is no class code defined for UCSI device over PCI * so using UNKNOWN class for now and it will be updated when UCSI * over PCI gets a class code. @@ -5459,6 +5461,9 @@ static void quirk_gpu_usb_typec_ucsi(struct pci_dev *ucsi) DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_SERIAL_UNKNOWN, 8, quirk_gpu_usb_typec_ucsi); +DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, PCI_ANY_ID, + PCI_CLASS_SERIAL_UNKNOWN, 8, + quirk_gpu_usb_typec_ucsi); /* * Enable the NVIDIA GPU integrated HDA controller if the BIOS left it From e042a4533fc346a655de7f1b8ac1fa01a2ed96e5 Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Thu, 9 Sep 2021 15:02:21 -0500 Subject: [PATCH 302/866] MAINTAINERS: Add Nirmal Patel as VMD maintainer Change my email to my unaffiliated address and move me to reviewer status. Link: https://lore.kernel.org/r/20210909200221.29981-1-jonathan.derrick@intel.com Signed-off-by: Jon Derrick Signed-off-by: Jon Derrick Signed-off-by: Bjorn Helgaas Cc: Nirmal Patel --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..ca6d6fde85cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14342,7 +14342,8 @@ F: Documentation/devicetree/bindings/pci/intel,ixp4xx-pci.yaml F: drivers/pci/controller/pci-ixp4xx.c PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD) -M: Jonathan Derrick +M: Nirmal Patel +R: Jonathan Derrick L: linux-pci@vger.kernel.org S: Supported F: drivers/pci/controller/vmd.c From 6a52e73368038f47f6618623d75061dc263b26ae Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Sep 2021 16:43:31 +0300 Subject: [PATCH 303/866] net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup DSA supports connecting to a phy-handle, and has a fallback to a non-OF based method of connecting to an internal PHY on the switch's own MDIO bus, if no phy-handle and no fixed-link nodes were present. The -ENODEV error code from the first attempt (phylink_of_phy_connect) is what triggers the second attempt (phylink_connect_phy). However, when the first attempt returns a different error code than -ENODEV, this results in an unbalance of calls to phylink_create and phylink_destroy by the time we exit the function. The phylink instance has leaked. There are many other error codes that can be returned by phylink_of_phy_connect. For example, phylink_validate returns -EINVAL. So this is a practical issue too. Fixes: aab9c4067d23 ("net: dsa: Plug in PHYLINK support") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20210914134331.2303380-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- net/dsa/slave.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 662ff531d4e2..a2bf2d8ac65b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1854,13 +1854,11 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * use the switch internal MDIO bus instead */ ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); - if (ret) { - netdev_err(slave_dev, - "failed to connect to port %d: %d\n", - dp->index, ret); - phylink_destroy(dp->pl); - return ret; - } + } + if (ret) { + netdev_err(slave_dev, "failed to connect to PHY: %pe\n", + ERR_PTR(ret)); + phylink_destroy(dp->pl); } return ret; From 301de697d869be6564aebeb5ab811c84c0a7abed Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Sep 2021 17:05:15 +0300 Subject: [PATCH 304/866] Revert "net: phy: Uniform PHY driver access" This reverts commit 3ac8eed62596387214869319379c1fcba264d8c6, which did more than it said on the box, and not only it replaced to_phy_driver with phydev->drv, but it also removed the "!drv" check, without actually explaining why that is fine. That patch in fact breaks suspend/resume on any system which has PHY devices with no drivers bound. The stack trace is: Unable to handle kernel NULL pointer dereference at virtual address 00000000000000e8 pc : mdio_bus_phy_suspend+0xd8/0xec lr : dpm_run_callback+0x38/0x90 Call trace: mdio_bus_phy_suspend+0xd8/0xec dpm_run_callback+0x38/0x90 __device_suspend+0x108/0x3cc dpm_suspend+0x140/0x210 dpm_suspend_start+0x7c/0xa0 suspend_devices_and_enter+0x13c/0x540 pm_suspend+0x2a4/0x330 Examples why that assumption is not fine: - There is an MDIO bus with a PHY device that doesn't have a specific PHY driver loaded, because mdiobus_register() automatically creates a PHY device for it but there is no specific PHY driver in the system. Normally under those circumstances, the generic PHY driver will be bound lazily to it (at phy_attach_direct time). But some Ethernet drivers attach to their PHY at .ndo_open time. Until then it, the to-be-driven-by-genphy PHY device will not have a driver. The blamed patch amounts to saying "you need to open all net devices before the system can suspend, to avoid the NULL pointer dereference". - There is any raw MDIO device which has 'plausible' values in the PHY ID registers 2 and 3, which is located on an MDIO bus whose driver does not set bus->phy_mask = ~0 (which prevents auto-scanning of PHY devices). An example could be a MAC's internal MDIO bus with PCS devices on it, for serial links such as SGMII. PHY devices will get created for those PCSes too, due to that MDIO bus auto-scanning, and although those PHY devices are not used, they do not bother anybody either. PCS devices are usually managed in Linux as raw MDIO devices. Nonetheless, they do not have a PHY driver, nor does anybody attempt to connect to them (because they are not a PHY), and therefore this patch breaks that. The goal itself of the patch is questionable, so I am going for a straight revert. to_phy_driver does not seem to have a need to be replaced by phydev->drv, in fact that might even trigger code paths which were not given too deep of a thought. For instance: phy_probe populates phydev->drv at the beginning, but does not clean it up on any error (including EPROBE_DEFER). So if the phydev driver requests probe deferral, phydev->drv will remain populated despite there being no driver bound. If a system suspend starts in between the initial probe deferral request and the subsequent probe retry, we will be calling the phydev->drv->suspend method, but _before_ any phydev->drv->probe call has succeeded. That is to say, if the phydev->drv is allocating any driver-private data structure in ->probe, it pretty much expects that data structure to be available in ->suspend. But it may not. That is a pretty insane environment to present to PHY drivers. In the code structure before the blamed patch, mdio_bus_phy_may_suspend would just say "no, don't suspend" to any PHY device which does not have a driver pointer _in_the_device_structure_ (not the phydev->drv). That would essentially ensure that ->suspend will never get called for a device that has not yet successfully completed probe. This is the code structure the patch is returning to, via the revert. Fixes: 3ac8eed62596 ("net: phy: Uniform PHY driver access") Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20210914140515.2311548-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9e2891d8e8dd..ba5ad86ec826 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -233,9 +233,11 @@ static DEFINE_MUTEX(phy_fixup_lock); static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) { + struct device_driver *drv = phydev->mdio.dev.driver; + struct phy_driver *phydrv = to_phy_driver(drv); struct net_device *netdev = phydev->attached_dev; - if (!phydev->drv->suspend) + if (!drv || !phydrv->suspend) return false; /* PHY not attached? May suspend if the PHY has not already been From a57d8c217aadac75530b8e7ffb3a3e1b7bfd0330 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Sep 2021 16:47:26 +0300 Subject: [PATCH 305/866] net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports Sometimes when unbinding the mv88e6xxx driver on Turris MOX, these error messages appear: mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 0 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 100 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 0 from fdb: -2 (and similarly for other ports) What happens is that DSA has a policy "even if there are bugs, let's at least not leak memory" and dsa_port_teardown() clears the dp->fdbs and dp->mdbs lists, which are supposed to be empty. But deleting that cleanup code, the warnings go away. => the FDB and MDB lists (used for refcounting on shared ports, aka CPU and DSA ports) will eventually be empty, but are not empty by the time we tear down those ports. Aka we are deleting them too soon. The addresses that DSA complains about are host-trapped addresses: the local addresses of the ports, and the MAC address of the bridge device. The problem is that offloading those entries happens from a deferred work item scheduled by the SWITCHDEV_FDB_DEL_TO_DEVICE handler, and this races with the teardown of the CPU and DSA ports where the refcounting is kept. In fact, not only it races, but fundamentally speaking, if we iterate through the port list linearly, we might end up tearing down the shared ports even before we delete a DSA user port which has a bridge upper. So as it turns out, we need to first tear down the user ports (and the unused ones, for no better place of doing that), then the shared ports (the CPU and DSA ports). In between, we need to ensure that all work items scheduled by our switchdev handlers (which only run for user ports, hence the reason why we tear them down first) have finished. Fixes: 161ca59d39e9 ("net: dsa: reference count the MDB entries at the cross-chip notifier level") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20210914134726.2305133-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 5 +++++ net/dsa/dsa.c | 5 +++++ net/dsa/dsa2.c | 46 +++++++++++++++++++++++++++++++--------------- net/dsa/dsa_priv.h | 1 + 4 files changed, 42 insertions(+), 15 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index f9a17145255a..258867eff230 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_USER; } +static inline bool dsa_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1dc45e40f961..41f36ad8b0ec 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +void dsa_flush_workqueue(void) +{ + flush_workqueue(dsa_owq); +} + int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 1b2b25d7bd02..eef13cd20f19 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -897,6 +897,33 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->setup = false; } +/* First tear down the non-shared, then the shared ports. This ensures that + * all work items scheduled by our switchdev handlers for user ports have + * completed before we destroy the refcounting kept on the shared ports. + */ +static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) + dsa_port_teardown(dp); + + dsa_flush_workqueue(); + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) + dsa_port_teardown(dp); +} + +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + dsa_switch_teardown(dp->ds); +} + static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -923,26 +950,13 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) return 0; teardown: - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); + dsa_tree_teardown_ports(dst); - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); + dsa_tree_teardown_switches(dst); return err; } -static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); -} - static int dsa_tree_setup_master(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -1052,6 +1066,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 33ab7d7af9eb..a5c9bc7b66c6 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -170,6 +170,7 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops); const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); +void dsa_flush_workqueue(void); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) From 17ac76e050c51497e75871a43aa3328ba54cdafd Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Tue, 31 Aug 2021 15:49:58 +0800 Subject: [PATCH 306/866] drm/exynos: Make use of the helper function devm_platform_ioremap_resource() Use the devm_platform_ioremap_resource() helper instead of calling platform_get_resource() and devm_ioremap_resource() separately Signed-off-by: Cai Huoqing Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 4 +--- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 4 +--- drivers/gpu/drm/exynos/exynos_drm_fimc.c | 5 +---- drivers/gpu/drm/exynos/exynos_drm_fimd.c | 4 +--- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 5 +---- drivers/gpu/drm/exynos/exynos_drm_gsc.c | 6 +----- drivers/gpu/drm/exynos/exynos_drm_rotator.c | 4 +--- drivers/gpu/drm/exynos/exynos_drm_scaler.c | 4 +--- drivers/gpu/drm/exynos/exynos_hdmi.c | 4 +--- 9 files changed, 9 insertions(+), 31 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 9870c4e6af36..b5001db7a95c 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -793,7 +793,6 @@ static int exynos5433_decon_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct decon_context *ctx; - struct resource *res; int ret; int i; @@ -818,8 +817,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev) ctx->clks[i] = clk; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->addr = devm_ioremap_resource(dev, res); + ctx->addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->addr)) return PTR_ERR(ctx->addr); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index e39fac889edc..8d137857818c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1738,7 +1738,6 @@ static const struct component_ops exynos_dsi_component_ops = { static int exynos_dsi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct exynos_dsi *dsi; int ret, i; @@ -1789,8 +1788,7 @@ static int exynos_dsi_probe(struct platform_device *pdev) } } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dsi->reg_base = devm_ioremap_resource(dev, res); + dsi->reg_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dsi->reg_base)) return PTR_ERR(dsi->reg_base); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index a3c718148c45..ecfd82d0afb7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -85,7 +85,6 @@ struct fimc_scaler { /* * A structure of fimc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @lock: locking of operations. * @clocks: fimc clocks. @@ -103,7 +102,6 @@ struct fimc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; spinlock_t lock; struct clk *clocks[FIMC_CLKS_MAX]; @@ -1327,8 +1325,7 @@ static int fimc_probe(struct platform_device *pdev) ctx->num_formats = num_formats; /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 700ca4fa6665..c735e53939d8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -1202,9 +1202,7 @@ static int fimd_probe(struct platform_device *pdev) return PTR_ERR(ctx->lcd_clk); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - ctx->regs = devm_ioremap_resource(dev, res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index b00230626c6a..471fd6c8135f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1449,7 +1449,6 @@ static const struct component_ops g2d_component_ops = { static int g2d_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct g2d_data *g2d; int ret; @@ -1491,9 +1490,7 @@ static int g2d_probe(struct platform_device *pdev) clear_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags); clear_bit(G2D_BIT_ENGINE_BUSY, &g2d->flags); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - g2d->regs = devm_ioremap_resource(dev, res); + g2d->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(g2d->regs)) { ret = PTR_ERR(g2d->regs); goto err_put_clk; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 90d7bf906885..166a80262896 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -86,7 +86,6 @@ struct gsc_scaler { /* * A structure of gsc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @gsc_clk: gsc gate clock. * @sc: scaler infomations. @@ -103,7 +102,6 @@ struct gsc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; const char **clk_names; struct clk *clocks[GSC_MAX_CLOCKS]; @@ -1272,9 +1270,7 @@ static int gsc_probe(struct platform_device *pdev) } } - /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index ee61be4cf152..dec7df35baa9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -278,7 +278,6 @@ static const struct component_ops rotator_component_ops = { static int rotator_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct rot_context *rot; const struct rot_variant *variant; int irq; @@ -292,8 +291,7 @@ static int rotator_probe(struct platform_device *pdev) rot->formats = variant->formats; rot->num_formats = variant->num_formats; rot->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rot->regs = devm_ioremap_resource(dev, regs_res); + rot->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rot->regs)) return PTR_ERR(rot->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index f9ae5b038d59..3a7851b7dc66 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -485,7 +485,6 @@ static const struct component_ops scaler_component_ops = { static int scaler_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct scaler_context *scaler; int irq; int ret, i; @@ -498,8 +497,7 @@ static int scaler_probe(struct platform_device *pdev) (struct scaler_data *)of_device_get_match_data(dev); scaler->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - scaler->regs = devm_ioremap_resource(dev, regs_res); + scaler->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(scaler->regs)) return PTR_ERR(scaler->regs); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index c769dec576de..7655142a4651 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1957,7 +1957,6 @@ static int hdmi_probe(struct platform_device *pdev) struct hdmi_audio_infoframe *audio_infoframe; struct device *dev = &pdev->dev; struct hdmi_context *hdata; - struct resource *res; int ret; hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL); @@ -1979,8 +1978,7 @@ static int hdmi_probe(struct platform_device *pdev) return ret; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdata->regs = devm_ioremap_resource(dev, res); + hdata->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hdata->regs)) { ret = PTR_ERR(hdata->regs); return ret; From 90cc7bed1ed19f869ae7221a6b41887fe762a6a3 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Thu, 16 Sep 2021 08:35:42 +0200 Subject: [PATCH 307/866] parisc: Use absolute_pointer() to define PAGE0 Use absolute_pointer() wrapper for PAGE0 to avoid this compiler warning: arch/parisc/kernel/setup.c: In function 'start_parisc': error: '__builtin_memcmp_eq' specified bound 8 exceeds source size 0 Signed-off-by: Helge Deller Co-Developed-by: Guenter Roeck Suggested-by: Linus Torvalds --- arch/parisc/include/asm/page.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h index d00313d1274e..0561568f7b48 100644 --- a/arch/parisc/include/asm/page.h +++ b/arch/parisc/include/asm/page.h @@ -184,7 +184,7 @@ extern int npmem_ranges; #include #include -#define PAGE0 ((struct zeropage *)__PAGE_OFFSET) +#define PAGE0 ((struct zeropage *)absolute_pointer(__PAGE_OFFSET)) /* DEFINITION OF THE ZERO-PAGE (PAG0) */ /* based on work by Jason Eckhardt (jason@equator.com) */ From d46ef750ed58cbeeba2d9a55c99231c30a172764 Mon Sep 17 00:00:00 2001 From: Evgeny Novikov Date: Tue, 1 Jun 2021 19:38:01 +0300 Subject: [PATCH 308/866] HID: amd_sfh: Fix potential NULL pointer dereference devm_add_action_or_reset() can suddenly invoke amd_mp2_pci_remove() at registration that will cause NULL pointer dereference since corresponding data is not initialized yet. The patch moves initialization of data before devm_add_action_or_reset(). Found by Linux Driver Verification project (linuxtesting.org). [jkosina@suse.cz: rebase] Signed-off-by: Evgeny Novikov Acked-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 79b138fd4261..9a1824757aae 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -251,6 +251,10 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i return rc; } + rc = amd_sfh_hid_client_init(privdata); + if (rc) + return rc; + privdata->cl_data = devm_kzalloc(&pdev->dev, sizeof(struct amdtp_cl_data), GFP_KERNEL); if (!privdata->cl_data) return -ENOMEM; @@ -261,7 +265,7 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i mp2_select_ops(privdata); - return amd_sfh_hid_client_init(privdata); + return 0; } static int __maybe_unused amd_mp2_pci_resume(struct device *dev) From 5297cfa6bdf93e3889f78f9b482e2a595a376083 Mon Sep 17 00:00:00 2001 From: Sai Krishna Potthuri Date: Wed, 18 Aug 2021 12:53:14 +0530 Subject: [PATCH 309/866] EDAC/synopsys: Fix wrong value type assignment for edac_mode dimm->edac_mode contains values of type enum edac_type - not the corresponding capability flags. Fix that. Issue caught by Coverity check "enumerated type mixed with another type." [ bp: Rewrite commit message, add tags. ] Fixes: ae9b56e3996d ("EDAC, synps: Add EDAC support for zynq ddr ecc controller") Signed-off-by: Sai Krishna Potthuri Signed-off-by: Shubhrajyoti Datta Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/20210818072315.15149-1-shubhrajyoti.datta@xilinx.com --- drivers/edac/synopsys_edac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 7e7146b22c16..7d08627e738b 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -782,7 +782,7 @@ static void init_csrows(struct mem_ctl_info *mci) for (j = 0; j < csi->nr_channels; j++) { dimm = csi->channels[j]->dimm; - dimm->edac_mode = EDAC_FLAG_SECDED; + dimm->edac_mode = EDAC_SECDED; dimm->mtype = p_data->get_mtype(priv->baseaddr); dimm->nr_pages = (size >> PAGE_SHIFT) / csi->nr_channels; dimm->grain = SYNPS_EDAC_ERR_GRAIN; From 78edefc05e41352099ffb8f06f8d9b2d091e29cd Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:23 +0200 Subject: [PATCH 310/866] drm/etnaviv: return context from etnaviv_iommu_context_get Being able to have the refcount manipulation in an assignment makes it much easier to parse the code. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_buffer.c | 3 +-- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 +-- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 3 +-- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 6 ++---- drivers/gpu/drm/etnaviv/etnaviv_mmu.h | 4 +++- 5 files changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c index 76d38561c910..cf741c5c82d2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c @@ -397,8 +397,7 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, u32 exec_state, if (switch_mmu_context) { struct etnaviv_iommu_context *old_context = gpu->mmu_context; - etnaviv_iommu_context_get(mmu_context); - gpu->mmu_context = mmu_context; + gpu->mmu_context = etnaviv_iommu_context_get(mmu_context); etnaviv_iommu_context_put(old_context); } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 8f1b5af47dd6..f0b2540e60e4 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -294,8 +294,7 @@ struct etnaviv_vram_mapping *etnaviv_gem_mapping_get( list_del(&mapping->obj_node); } - etnaviv_iommu_context_get(mmu_context); - mapping->context = mmu_context; + mapping->context = etnaviv_iommu_context_get(mmu_context); mapping->use = 1; ret = etnaviv_iommu_map_gem(mmu_context, etnaviv_obj, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 4dd7d9d541c0..486259e154af 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -532,8 +532,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, goto err_submit_objects; submit->ctx = file->driver_priv; - etnaviv_iommu_context_get(submit->ctx->mmu); - submit->mmu_context = submit->ctx->mmu; + submit->mmu_context = etnaviv_iommu_context_get(submit->ctx->mmu); submit->exec_state = args->exec_state; submit->flags = args->flags; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index c297fffe06eb..6722efcf858a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1371,12 +1371,10 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) } if (!gpu->mmu_context) { - etnaviv_iommu_context_get(submit->mmu_context); - gpu->mmu_context = submit->mmu_context; + gpu->mmu_context = etnaviv_iommu_context_get(submit->mmu_context); etnaviv_gpu_start_fe_idleloop(gpu); } else { - etnaviv_iommu_context_get(gpu->mmu_context); - submit->prev_mmu_context = gpu->mmu_context; + submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context); } if (submit->nr_pmrs) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h index d1d6902fd13b..e4a0b7d09c2e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.h @@ -105,9 +105,11 @@ void etnaviv_iommu_dump(struct etnaviv_iommu_context *ctx, void *buf); struct etnaviv_iommu_context * etnaviv_iommu_context_init(struct etnaviv_iommu_global *global, struct etnaviv_cmdbuf_suballoc *suballoc); -static inline void etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx) +static inline struct etnaviv_iommu_context * +etnaviv_iommu_context_get(struct etnaviv_iommu_context *ctx) { kref_get(&ctx->refcount); + return ctx; } void etnaviv_iommu_context_put(struct etnaviv_iommu_context *ctx); void etnaviv_iommu_restore(struct etnaviv_gpu *gpu, From cda7532916f7bc860b36a1806cb8352e6f63dacb Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:24 +0200 Subject: [PATCH 311/866] drm/etnaviv: put submit prev MMU context when it exists The prev context is the MMU context at the time of the job queueing in hardware. As a job might be queued multiple times due to recovery after a GPU hang, we need to make sure to put the stale prev MMU context from a prior queuing, to avoid the reference and thus the MMU context leaking. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 6722efcf858a..0f700400937e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1374,6 +1374,8 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) gpu->mmu_context = etnaviv_iommu_context_get(submit->mmu_context); etnaviv_gpu_start_fe_idleloop(gpu); } else { + if (submit->prev_mmu_context) + etnaviv_iommu_context_put(submit->prev_mmu_context); submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context); } From 23e0f5a57d0ecec86e1fc82194acd94aede21a46 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:25 +0200 Subject: [PATCH 312/866] drm/etnaviv: stop abusing mmu_context as FE running marker While the DMA frontend can only be active when the MMU context is set, the reverse isn't necessarily true, as the frontend can be stopped while the MMU state is kept. Stop treating mmu_context being set as a indication that the frontend is running and instead add a explicit property. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 10 ++++++++-- drivers/gpu/drm/etnaviv/etnaviv_gpu.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 0f700400937e..24d514e70f98 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -569,6 +569,8 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu) /* We rely on the GPU running, so program the clock */ etnaviv_gpu_update_clock(gpu); + gpu->fe_running = false; + return 0; } @@ -637,6 +639,8 @@ void etnaviv_gpu_start_fe(struct etnaviv_gpu *gpu, u32 address, u16 prefetch) VIVS_MMUv2_SEC_COMMAND_CONTROL_ENABLE | VIVS_MMUv2_SEC_COMMAND_CONTROL_PREFETCH(prefetch)); } + + gpu->fe_running = true; } static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu) @@ -1370,7 +1374,7 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) goto out_unlock; } - if (!gpu->mmu_context) { + if (!gpu->fe_running) { gpu->mmu_context = etnaviv_iommu_context_get(submit->mmu_context); etnaviv_gpu_start_fe_idleloop(gpu); } else { @@ -1579,7 +1583,7 @@ int etnaviv_gpu_wait_idle(struct etnaviv_gpu *gpu, unsigned int timeout_ms) static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu) { - if (gpu->initialized && gpu->mmu_context) { + if (gpu->initialized && gpu->fe_running) { /* Replace the last WAIT with END */ mutex_lock(&gpu->lock); etnaviv_buffer_end(gpu); @@ -1594,6 +1598,8 @@ static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu) etnaviv_iommu_context_put(gpu->mmu_context); gpu->mmu_context = NULL; + + gpu->fe_running = false; } gpu->exec_state = -1; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 8ea48697d132..1c75c8ed5bce 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -101,6 +101,7 @@ struct etnaviv_gpu { struct workqueue_struct *wq; struct drm_gpu_scheduler sched; bool initialized; + bool fe_running; /* 'ring'-buffer: */ struct etnaviv_cmdbuf buffer; From 8f3eea9d01d7b0f95b0fe04187c0059019ada85b Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:26 +0200 Subject: [PATCH 313/866] drm/etnaviv: keep MMU context across runtime suspend/resume The MMU state may be kept across a runtime suspend/resume cycle, as we avoid a full hardware reset to keep the latency of the runtime PM small. Don't pretend that the MMU state is lost in driver state. The MMU context is pushed out when new HW jobs with a different context are coming in. The only exception to this is when the GPU is unbound, in which case we need to make sure to also free the last active context. Cc: stable@vger.kernel.org # 5.4 Reported-by: Michael Walle Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 24d514e70f98..0757dcbe6913 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1596,9 +1596,6 @@ static int etnaviv_gpu_hw_suspend(struct etnaviv_gpu *gpu) */ etnaviv_gpu_wait_idle(gpu, 100); - etnaviv_iommu_context_put(gpu->mmu_context); - gpu->mmu_context = NULL; - gpu->fe_running = false; } @@ -1747,6 +1744,9 @@ static void etnaviv_gpu_unbind(struct device *dev, struct device *master, etnaviv_gpu_hw_suspend(gpu); #endif + if (gpu->mmu_context) + etnaviv_iommu_context_put(gpu->mmu_context); + if (gpu->initialized) { etnaviv_cmdbuf_free(&gpu->buffer); etnaviv_iommu_global_fini(gpu); From 725cbc7884c37f3b4f1777bc1aea6432cded8ca5 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:27 +0200 Subject: [PATCH 314/866] drm/etnaviv: exec and MMU state is lost when resetting the GPU When the GPU is reset both the current exec state, as well as all MMU state is lost. Move the driver side state tracking into the reset function to keep hardware and software state from diverging. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 0757dcbe6913..3d64bc3cc604 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -570,6 +570,8 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu) etnaviv_gpu_update_clock(gpu); gpu->fe_running = false; + gpu->exec_state = -1; + gpu->mmu_context = NULL; return 0; } @@ -836,7 +838,6 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) /* Now program the hardware */ mutex_lock(&gpu->lock); etnaviv_gpu_hw_init(gpu); - gpu->exec_state = -1; mutex_unlock(&gpu->lock); pm_runtime_mark_last_busy(gpu->dev); @@ -1061,8 +1062,6 @@ void etnaviv_gpu_recover_hang(struct etnaviv_gpu *gpu) spin_unlock(&gpu->event_spinlock); etnaviv_gpu_hw_init(gpu); - gpu->exec_state = -1; - gpu->mmu_context = NULL; mutex_unlock(&gpu->lock); pm_runtime_mark_last_busy(gpu->dev); From f978a5302f5566480c58ffae64a16d34456801bd Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:28 +0200 Subject: [PATCH 315/866] drm/etnaviv: fix MMU context leak on GPU reset After a reset the GPU is no longer using the MMU context and may be restarted with a different context. While the mmu_state proeprly was cleared, the context wasn't unreferenced, leading to a memory leak. Cc: stable@vger.kernel.org # 5.4 Reported-by: Michael Walle Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 3d64bc3cc604..bc2bdfcbc082 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -571,6 +571,8 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu) gpu->fe_running = false; gpu->exec_state = -1; + if (gpu->mmu_context) + etnaviv_iommu_context_put(gpu->mmu_context); gpu->mmu_context = NULL; return 0; From d6408538f091fb22d47f792d4efa58143d56c3fb Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:29 +0200 Subject: [PATCH 316/866] drm/etnaviv: reference MMU context when setting up hardware state Move the refcount manipulation of the MMU context to the point where the hardware state is programmed. At that point it is also known if a previous MMU state is still there, or the state needs to be reprogrammed with a potentially different context. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 24 +++++++++++----------- drivers/gpu/drm/etnaviv/etnaviv_iommu.c | 4 ++++ drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c | 8 ++++++++ 3 files changed, 24 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index bc2bdfcbc082..cc5b07f86346 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -647,17 +647,19 @@ void etnaviv_gpu_start_fe(struct etnaviv_gpu *gpu, u32 address, u16 prefetch) gpu->fe_running = true; } -static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu) +static void etnaviv_gpu_start_fe_idleloop(struct etnaviv_gpu *gpu, + struct etnaviv_iommu_context *context) { - u32 address = etnaviv_cmdbuf_get_va(&gpu->buffer, - &gpu->mmu_context->cmdbuf_mapping); u16 prefetch; + u32 address; /* setup the MMU */ - etnaviv_iommu_restore(gpu, gpu->mmu_context); + etnaviv_iommu_restore(gpu, context); /* Start command processor */ prefetch = etnaviv_buffer_init(gpu); + address = etnaviv_cmdbuf_get_va(&gpu->buffer, + &gpu->mmu_context->cmdbuf_mapping); etnaviv_gpu_start_fe(gpu, address, prefetch); } @@ -1375,14 +1377,12 @@ struct dma_fence *etnaviv_gpu_submit(struct etnaviv_gem_submit *submit) goto out_unlock; } - if (!gpu->fe_running) { - gpu->mmu_context = etnaviv_iommu_context_get(submit->mmu_context); - etnaviv_gpu_start_fe_idleloop(gpu); - } else { - if (submit->prev_mmu_context) - etnaviv_iommu_context_put(submit->prev_mmu_context); - submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context); - } + if (!gpu->fe_running) + etnaviv_gpu_start_fe_idleloop(gpu, submit->mmu_context); + + if (submit->prev_mmu_context) + etnaviv_iommu_context_put(submit->prev_mmu_context); + submit->prev_mmu_context = etnaviv_iommu_context_get(gpu->mmu_context); if (submit->nr_pmrs) { gpu->event[event[1]].sync_point = &sync_point_perfmon_sample_pre; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c index 1a7c89a67bea..afe5dd6a9925 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c @@ -92,6 +92,10 @@ static void etnaviv_iommuv1_restore(struct etnaviv_gpu *gpu, struct etnaviv_iommuv1_context *v1_context = to_v1_context(context); u32 pgtable; + if (gpu->mmu_context) + etnaviv_iommu_context_put(gpu->mmu_context); + gpu->mmu_context = etnaviv_iommu_context_get(context); + /* set base addresses */ gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_RA, context->global->memory_base); gpu_write(gpu, VIVS_MC_MEMORY_BASE_ADDR_FE, context->global->memory_base); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c index f8bf488e9d71..d664ae29ae20 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c @@ -172,6 +172,10 @@ static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu, if (gpu_read(gpu, VIVS_MMUv2_CONTROL) & VIVS_MMUv2_CONTROL_ENABLE) return; + if (gpu->mmu_context) + etnaviv_iommu_context_put(gpu->mmu_context); + gpu->mmu_context = etnaviv_iommu_context_get(context); + prefetch = etnaviv_buffer_config_mmuv2(gpu, (u32)v2_context->mtlb_dma, (u32)context->global->bad_page_dma); @@ -192,6 +196,10 @@ static void etnaviv_iommuv2_restore_sec(struct etnaviv_gpu *gpu, if (gpu_read(gpu, VIVS_MMUv2_SEC_CONTROL) & VIVS_MMUv2_SEC_CONTROL_ENABLE) return; + if (gpu->mmu_context) + etnaviv_iommu_context_put(gpu->mmu_context); + gpu->mmu_context = etnaviv_iommu_context_get(context); + gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_LOW, lower_32_bits(context->global->v2.pta_dma)); gpu_write(gpu, VIVS_MMUv2_PTA_ADDRESS_HIGH, From f2faea8b64125852fa9acc6771c07fc0311a039b Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 20 Aug 2021 22:18:30 +0200 Subject: [PATCH 317/866] drm/etnaviv: add missing MMU context put when reaping MMU mapping When we forcefully evict a mapping from the the address space and thus the MMU context, the MMU context is leaked, as the mapping no longer points to it, so it doesn't get freed when the GEM object is destroyed. Add the mssing context put to fix the leak. Cc: stable@vger.kernel.org # 5.4 Signed-off-by: Lucas Stach Tested-by: Michael Walle Tested-by: Marek Vasut Reviewed-by: Christian Gmeiner --- drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index dab1b58006d8..9fb1a2aadbcb 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -199,6 +199,7 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu_context *context, */ list_for_each_entry_safe(m, n, &list, scan_node) { etnaviv_iommu_remove_mapping(context, m); + etnaviv_iommu_context_put(m->context); m->context = NULL; list_del_init(&m->mmu_node); list_del_init(&m->scan_node); From 1511df6f5e9ef32826f20db2ee81f8527154dc14 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Tue, 7 Sep 2021 11:58:59 +0200 Subject: [PATCH 318/866] s390/bpf: Fix branch shortening during codegen pass EMIT6_PCREL() macro assumes that the previous pass generated 6 bytes of code, which is not the case if branch shortening took place. Fix by using jit->prg, like all the other EMIT6_PCREL_*() macros. Reported-by: Johan Almbladh Fixes: 4e9b4a6883dd ("s390/bpf: Use relative long branches") Signed-off-by: Ilya Leoshkevich Signed-off-by: Vasily Gorbik --- arch/s390/net/bpf_jit_comp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 88419263a89a..c3bd630e9b43 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -248,8 +248,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) #define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask) \ ({ \ - /* Branch instruction needs 6 bytes */ \ - int rel = (addrs[(i) + (off) + 1] - (addrs[(i) + 1] - 6)) / 2;\ + int rel = (addrs[(i) + (off) + 1] - jit->prg) / 2; \ _EMIT6((op1) | reg(b1, b2) << 16 | (rel & 0xffff), (op2) | (mask));\ REG_SET_SEEN(b1); \ REG_SET_SEEN(b2); \ From 6e61dc9da0b7a0d91d57c2e20b5ea4fd2d4e7e53 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Tue, 7 Sep 2021 13:41:16 +0200 Subject: [PATCH 319/866] s390/bpf: Fix 64-bit subtraction of the -0x80000000 constant The JIT uses agfi for subtracting constants, but -(-0x80000000) cannot be represented as a 32-bit signed binary integer. Fix by using algfi in this particular case. Reported-by: Johan Almbladh Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Reviewed-by: Heiko Carstens Signed-off-by: Ilya Leoshkevich Signed-off-by: Vasily Gorbik --- arch/s390/net/bpf_jit_comp.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index c3bd630e9b43..245f98d5f690 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -794,8 +794,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */ if (!imm) break; - /* agfi %dst,-imm */ - EMIT6_IMM(0xc2080000, dst_reg, -imm); + if (imm == -0x80000000) { + /* algfi %dst,0x80000000 */ + EMIT6_IMM(0xc20a0000, dst_reg, 0x80000000); + } else { + /* agfi %dst,-imm */ + EMIT6_IMM(0xc2080000, dst_reg, -imm); + } break; /* * BPF_MUL From db7bee653859ef7179be933e7d1384644f795f26 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Mon, 6 Sep 2021 15:04:14 +0200 Subject: [PATCH 320/866] s390/bpf: Fix optimizing out zero-extensions Currently the JIT completely removes things like `reg32 += 0`, however, the BPF_ALU semantics requires the target register to be zero-extended in such cases. Fix by optimizing out only the arithmetic operation, but not the subsequent zero-extension. Reported-by: Johan Almbladh Fixes: 054623105728 ("s390/bpf: Add s390x eBPF JIT compiler backend") Reviewed-by: Heiko Carstens Signed-off-by: Ilya Leoshkevich Signed-off-by: Vasily Gorbik --- arch/s390/net/bpf_jit_comp.c | 58 +++++++++++++++++++----------------- 1 file changed, 30 insertions(+), 28 deletions(-) diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 245f98d5f690..840d8594437d 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -760,10 +760,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9080000, dst_reg, src_reg); break; case BPF_ALU | BPF_ADD | BPF_K: /* dst = (u32) dst + (u32) imm */ - if (!imm) - break; - /* alfi %dst,imm */ - EMIT6_IMM(0xc20b0000, dst_reg, imm); + if (imm != 0) { + /* alfi %dst,imm */ + EMIT6_IMM(0xc20b0000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_ADD | BPF_K: /* dst = dst + imm */ @@ -785,10 +785,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9090000, dst_reg, src_reg); break; case BPF_ALU | BPF_SUB | BPF_K: /* dst = (u32) dst - (u32) imm */ - if (!imm) - break; - /* alfi %dst,-imm */ - EMIT6_IMM(0xc20b0000, dst_reg, -imm); + if (imm != 0) { + /* alfi %dst,-imm */ + EMIT6_IMM(0xc20b0000, dst_reg, -imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_SUB | BPF_K: /* dst = dst - imm */ @@ -815,10 +815,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb90c0000, dst_reg, src_reg); break; case BPF_ALU | BPF_MUL | BPF_K: /* dst = (u32) dst * (u32) imm */ - if (imm == 1) - break; - /* msfi %r5,imm */ - EMIT6_IMM(0xc2010000, dst_reg, imm); + if (imm != 1) { + /* msfi %r5,imm */ + EMIT6_IMM(0xc2010000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_MUL | BPF_K: /* dst = dst * imm */ @@ -871,6 +871,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, if (BPF_OP(insn->code) == BPF_MOD) /* lhgi %dst,0 */ EMIT4_IMM(0xa7090000, dst_reg, 0); + else + EMIT_ZERO(dst_reg); break; } /* lhi %w0,0 */ @@ -1003,10 +1005,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4(0xb9820000, dst_reg, src_reg); break; case BPF_ALU | BPF_XOR | BPF_K: /* dst = (u32) dst ^ (u32) imm */ - if (!imm) - break; - /* xilf %dst,imm */ - EMIT6_IMM(0xc0070000, dst_reg, imm); + if (imm != 0) { + /* xilf %dst,imm */ + EMIT6_IMM(0xc0070000, dst_reg, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_XOR | BPF_K: /* dst = dst ^ imm */ @@ -1037,10 +1039,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000d, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_LSH | BPF_K: /* dst = (u32) dst << (u32) imm */ - if (imm == 0) - break; - /* sll %dst,imm(%r0) */ - EMIT4_DISP(0x89000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* sll %dst,imm(%r0) */ + EMIT4_DISP(0x89000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_LSH | BPF_K: /* dst = dst << imm */ @@ -1062,10 +1064,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000c, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_RSH | BPF_K: /* dst = (u32) dst >> (u32) imm */ - if (imm == 0) - break; - /* srl %dst,imm(%r0) */ - EMIT4_DISP(0x88000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* srl %dst,imm(%r0) */ + EMIT4_DISP(0x88000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_RSH | BPF_K: /* dst = dst >> imm */ @@ -1087,10 +1089,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT6_DISP_LH(0xeb000000, 0x000a, dst_reg, dst_reg, src_reg, 0); break; case BPF_ALU | BPF_ARSH | BPF_K: /* ((s32) dst >> imm */ - if (imm == 0) - break; - /* sra %dst,imm(%r0) */ - EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm); + if (imm != 0) { + /* sra %dst,imm(%r0) */ + EMIT4_DISP(0x8a000000, dst_reg, REG_0, imm); + } EMIT_ZERO(dst_reg); break; case BPF_ALU64 | BPF_ARSH | BPF_K: /* ((s64) dst) >>= imm */ From 54607282fae6148641a08d81a6e0953b541249c7 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 16 Sep 2021 10:44:06 +0200 Subject: [PATCH 321/866] EDAC/dmc520: Assign the proper type to dimm->edac_mode dimm->edac_mode contains values of type enum edac_type - not the corresponding capability flags. Fix that. Fixes: 1088750d7839 ("EDAC: Add EDAC driver for DMC520") Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/20210916085258.7544-1-bp@alien8.de --- drivers/edac/dmc520_edac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/edac/dmc520_edac.c b/drivers/edac/dmc520_edac.c index fc1153ab1ebb..b8a7d9594afd 100644 --- a/drivers/edac/dmc520_edac.c +++ b/drivers/edac/dmc520_edac.c @@ -464,7 +464,7 @@ static void dmc520_init_csrow(struct mem_ctl_info *mci) dimm->grain = pvt->mem_width_in_bytes; dimm->dtype = dt; dimm->mtype = mt; - dimm->edac_mode = EDAC_FLAG_SECDED; + dimm->edac_mode = EDAC_SECDED; dimm->nr_pages = pages_per_rank / csi->nr_channels; } } From be830389bd49d3f1f8737bd45513361628641c08 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 14 Sep 2021 14:08:47 +0300 Subject: [PATCH 322/866] ALSA: pcxhr: "fix" PCXHR_REG_TO_PORT definition The following preprocessor directive is non-compliant: #undef PCXHR_REG_TO_PORT(x) gcc warns about extra tokens but nobody sees them as they are under if branch which is never parsed. Make it an #error, it is not clear to me what the author meant. Signed-off-by: Alexey Dobriyan Link: https://lore.kernel.org/r/YUCCv47sm4zf9OVO@localhost.localdomain Signed-off-by: Takashi Iwai --- sound/pci/pcxhr/pcxhr_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c index 87d24224c042..23f253effb4f 100644 --- a/sound/pci/pcxhr/pcxhr_core.c +++ b/sound/pci/pcxhr/pcxhr_core.c @@ -52,7 +52,7 @@ #define PCXHR_DSP 2 #if (PCXHR_DSP_OFFSET_MAX > PCXHR_PLX_OFFSET_MIN) -#undef PCXHR_REG_TO_PORT(x) +#error PCXHR_REG_TO_PORT(x) #else #define PCXHR_REG_TO_PORT(x) ((x)>PCXHR_DSP_OFFSET_MAX ? PCXHR_PLX : PCXHR_DSP) #endif From 94d508fa3186d0cbc63765aa94d5cf3bd847694c Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Thu, 16 Sep 2021 10:56:46 +0100 Subject: [PATCH 323/866] ALSA: hda/cs8409: Setup Dolphin Headset Mic as Phantom Jack Dell's requirement to have headset mic as phantom jack on this specific dolphin hardware platform. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Link: https://lore.kernel.org/r/20210916095646.7631-1-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_cs8409.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 3c7ef55d016e..31ff11ab868e 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -1207,6 +1207,9 @@ void dolphin_fixups(struct hda_codec *codec, const struct hda_fixup *fix, int ac snd_hda_jack_add_kctl(codec, DOLPHIN_LO_PIN_NID, "Line Out", true, SND_JACK_HEADPHONE, NULL); + snd_hda_jack_add_kctl(codec, DOLPHIN_AMIC_PIN_NID, "Microphone", true, + SND_JACK_MICROPHONE, NULL); + cs8409_fix_caps(codec, DOLPHIN_HP_PIN_NID); cs8409_fix_caps(codec, DOLPHIN_LO_PIN_NID); cs8409_fix_caps(codec, DOLPHIN_AMIC_PIN_NID); From 5aeb05b27f81269a2bf2e15eab9fc0f9a400d3a8 Mon Sep 17 00:00:00 2001 From: Laurentiu Tudor Date: Wed, 15 Sep 2021 11:09:39 +0300 Subject: [PATCH 324/866] software node: balance refcount for managed software nodes software_node_notify(), on KOBJ_REMOVE drops the refcount twice on managed software nodes, thus leading to underflow errors. Balance the refcount by bumping it in the device_create_managed_software_node() function. The error [1] was encountered after adding a .shutdown() op to our fsl-mc-bus driver. [1] pc : refcount_warn_saturate+0xf8/0x150 lr : refcount_warn_saturate+0xf8/0x150 sp : ffff80001009b920 x29: ffff80001009b920 x28: ffff1a2420318000 x27: 0000000000000000 x26: ffffccac15e7a038 x25: 0000000000000008 x24: ffffccac168e0030 x23: ffff1a2428a82000 x22: 0000000000080000 x21: ffff1a24287b5000 x20: 0000000000000001 x19: ffff1a24261f4400 x18: ffffffffffffffff x17: 6f72645f726f7272 x16: 0000000000000000 x15: ffff80009009b607 x14: 0000000000000000 x13: ffffccac16602670 x12: 0000000000000a17 x11: 000000000000035d x10: ffffccac16602670 x9 : ffffccac16602670 x8 : 00000000ffffefff x7 : ffffccac1665a670 x6 : ffffccac1665a670 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 00000000ffffffff x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff1a2420318000 Call trace: refcount_warn_saturate+0xf8/0x150 kobject_put+0x10c/0x120 software_node_notify+0xd8/0x140 device_platform_notify+0x4c/0xb4 device_del+0x188/0x424 fsl_mc_device_remove+0x2c/0x4c rebofind sp.c__fsl_mc_device_remove+0x14/0x2c device_for_each_child+0x5c/0xac dprc_remove+0x9c/0xc0 fsl_mc_driver_remove+0x28/0x64 __device_release_driver+0x188/0x22c device_release_driver+0x30/0x50 bus_remove_device+0x128/0x134 device_del+0x16c/0x424 fsl_mc_bus_remove+0x8c/0x114 fsl_mc_bus_shutdown+0x14/0x20 platform_shutdown+0x28/0x40 device_shutdown+0x15c/0x330 __do_sys_reboot+0x218/0x2a0 __arm64_sys_reboot+0x28/0x34 invoke_syscall+0x48/0x114 el0_svc_common+0x40/0xdc do_el0_svc+0x2c/0x94 el0_svc+0x2c/0x54 el0t_64_sync_handler+0xa8/0x12c el0t_64_sync+0x198/0x19c ---[ end trace 32eb1c71c7d86821 ]--- Fixes: 151f6ff78cdf ("software node: Provide replacement for device_add_properties()") Reported-by: Jon Nettleton Suggested-by: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Laurentiu Tudor Cc: 5.12+ # 5.12+ [ rjw: Fix up the software_node_notify() invocation ] Signed-off-by: Rafael J. Wysocki --- drivers/base/swnode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 7bd0f3cfb7eb..c46f6a8e14d2 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -1116,6 +1116,9 @@ int device_create_managed_software_node(struct device *dev, to_swnode(fwnode)->managed = true; set_secondary_fwnode(dev, fwnode); + if (device_is_registered(dev)) + software_node_notify(dev); + return 0; } EXPORT_SYMBOL_GPL(device_create_managed_software_node); From 98dc68f8b0c2248bdc3688c90d2499247b9432e4 Mon Sep 17 00:00:00 2001 From: Xiang wangx Date: Thu, 16 Sep 2021 20:24:42 +0800 Subject: [PATCH 325/866] selftests: nci: replace unsigned int with int Should not use comparison of unsigned expressions < 0. Signed-off-by: Xiang wangx Signed-off-by: David S. Miller --- tools/testing/selftests/nci/nci_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c index e1bf55dabdf6..162c41e9bcae 100644 --- a/tools/testing/selftests/nci/nci_dev.c +++ b/tools/testing/selftests/nci/nci_dev.c @@ -746,7 +746,7 @@ int read_write_nci_cmd(int nfc_sock, int virtual_fd, const __u8 *cmd, __u32 cmd_ const __u8 *rsp, __u32 rsp_len) { char buf[256]; - unsigned int len; + int len; send(nfc_sock, &cmd[3], cmd_len - 3, 0); len = read(virtual_fd, buf, cmd_len); From 8a8e1813ffc35111fc0b6db49968ceb0e1615ced Mon Sep 17 00:00:00 2001 From: Marc Herbert Date: Thu, 16 Sep 2021 11:50:08 +0300 Subject: [PATCH 326/866] ASoC: SOF: loader: release_firmware() on load failure to avoid batching Invoke release_firmware() when the firmware fails to boot in sof_probe_continue(). The request_firmware() framework must be informed of failures in sof_probe_continue() otherwise its internal "batching" feature (different from caching) cached the firmware image forever. Attempts to correct the file in /lib/firmware/ were then silently and confusingly ignored until the next reboot. Unloading the drivers did not help because from their disconnected perspective the firmware had failed so there was nothing to release. Also leverage the new snd_sof_fw_unload() function to simplify the snd_sof_device_remove() function. Signed-off-by: Marc Herbert Reviewed-by: Pierre-Louis Bossart Reviewed-by: Guennadi Liakhovetski Reviewed-by: Ranjani Sridharan Signed-off-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20210916085008.28929-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/core.c | 4 +--- sound/soc/sof/loader.c | 2 ++ 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 3e4dd4a86363..59d0d7b2b55c 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -371,7 +371,6 @@ int snd_sof_device_remove(struct device *dev) dev_warn(dev, "error: %d failed to prepare DSP for device removal", ret); - snd_sof_fw_unload(sdev); snd_sof_ipc_free(sdev); snd_sof_free_debug(sdev); snd_sof_free_trace(sdev); @@ -394,8 +393,7 @@ int snd_sof_device_remove(struct device *dev) snd_sof_remove(sdev); /* release firmware */ - release_firmware(pdata->fw); - pdata->fw = NULL; + snd_sof_fw_unload(sdev); return 0; } diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 2b38a77cd594..9c3f251a0dd0 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -880,5 +880,7 @@ EXPORT_SYMBOL(snd_sof_run_firmware); void snd_sof_fw_unload(struct snd_sof_dev *sdev) { /* TODO: support module unloading at runtime */ + release_firmware(sdev->pdata->fw); + sdev->pdata->fw = NULL; } EXPORT_SYMBOL(snd_sof_fw_unload); From 25766ee44ff8db4cdf8471b587dffb28b7b9d17f Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 16 Sep 2021 11:53:42 +0300 Subject: [PATCH 327/866] ASoC: SOF: loader: Re-phrase the missing firmware error to avoid duplication In case the firmware is missing we will have the following in the kernel log: 1 | Direct firmware load for intel/sof/sof-tgl-h.ri failed with error -2 2 | error: request firmware intel/sof/sof-tgl-h.ri failed err: -2 3 | you may need to download the firmware from https://github.com/thesofproject/sof-bin/ 4 | error: failed to load DSP firmware -2 5 | error: sof_probe_work failed err: -2 The first line is the standard, request_firmware() warning. The second and third line is printed in snd_sof_load_firmware_raw() Note that the first and second line is mostly identical. With this patch the log will be changed to: 1 | Direct firmware load for intel/sof/sof-tgl-h.ri failed with error -2 2 | error: sof firmware file is missing, you might need to 3 | download it from https://github.com/thesofproject/sof-bin/ 4 | error: failed to load DSP firmware -2 5 | error: sof_probe_work failed err: -2 Signed-off-by: Peter Ujfalusi Reviewed-by: Ranjani Sridharan Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210916085342.29993-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/loader.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c index 9c3f251a0dd0..bb79c77775b3 100644 --- a/sound/soc/sof/loader.c +++ b/sound/soc/sof/loader.c @@ -729,10 +729,10 @@ int snd_sof_load_firmware_raw(struct snd_sof_dev *sdev) ret = request_firmware(&plat_data->fw, fw_filename, sdev->dev); if (ret < 0) { - dev_err(sdev->dev, "error: request firmware %s failed err: %d\n", - fw_filename, ret); dev_err(sdev->dev, - "you may need to download the firmware from https://github.com/thesofproject/sof-bin/\n"); + "error: sof firmware file is missing, you might need to\n"); + dev_err(sdev->dev, + " download it from https://github.com/thesofproject/sof-bin/\n"); goto err; } else { dev_dbg(sdev->dev, "request_firmware %s successful\n", From 84fb7dfc7463afcba61281f36535576a7f7b0626 Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Sun, 12 Sep 2021 23:23:21 +0200 Subject: [PATCH 328/866] net: wan: wanxl: define CROSS_COMPILE_M68K It was used but never set. The hardcoded value from before the dawn of time was non-standard; the usual name for cross-tools is $TRIPLET-$TOOL Signed-off-by: Adam Borowski Signed-off-by: David S. Miller --- drivers/net/wan/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile index f6b92efffc94..480bcd1f6c1c 100644 --- a/drivers/net/wan/Makefile +++ b/drivers/net/wan/Makefile @@ -34,6 +34,8 @@ obj-$(CONFIG_SLIC_DS26522) += slic_ds26522.o clean-files := wanxlfw.inc $(obj)/wanxl.o: $(obj)/wanxlfw.inc +CROSS_COMPILE_M68K = m68k-linux-gnu- + ifeq ($(CONFIG_WANXL_BUILD_FIRMWARE),y) ifeq ($(ARCH),m68k) M68KCC = $(CC) From 7c3a0a018e672a9723a79b128227272562300055 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 15 Sep 2021 07:47:27 +0300 Subject: [PATCH 329/866] net/{mlx5|nfp|bnxt}: Remove unnecessary RTNL lock assert Remove the assert from the callback priv lookup function since it does not require RTNL lock and is already protected by flow_indr_block_lock. This will avoid warnings from being emitted to dmesg if the driver registers its callback after an ingress qdisc was created for a netdevice. The warnings started after the following patch was merged: commit 74fc4f828769 ("net: Fix offloading indirect devices dependency on qdisc order creation") Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 3 --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 3 --- drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 --- 3 files changed, 9 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 46fae1acbeed..e6a4a768b10b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1884,9 +1884,6 @@ bnxt_tc_indr_block_cb_lookup(struct bnxt *bp, struct net_device *netdev) { struct bnxt_flower_indr_block_cb_priv *cb_priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &bp->tc_indr_block_list, list) if (cb_priv->tunnel_netdev == netdev) return cb_priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 51a4d80f7fa3..de03684528bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -300,9 +300,6 @@ mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv, { struct mlx5e_rep_indr_block_priv *cb_priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &rpriv->uplink_priv.tc_indr_block_priv_list, list) diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 556c3495211d..64c0ef57ad42 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1767,9 +1767,6 @@ nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app, struct nfp_flower_indr_block_cb_priv *cb_priv; struct nfp_flower_priv *priv = app->priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &priv->indr_block_cb_priv, list) if (cb_priv->netdev == netdev) return cb_priv; From 40ee363c844fcb6ae0f1f5cfea68aed7e268c2f4 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 15 Sep 2021 10:19:07 -0700 Subject: [PATCH 330/866] igc: fix tunnel offloading Checking tunnel offloading, it turns out that offloading doesn't work as expected. The following script allows to reproduce the issue. Call it as `testscript DEVICE LOCALIP REMOTEIP NETMASK' === SNIP === if [ $# -ne 4 ] then echo "Usage $0 DEVICE LOCALIP REMOTEIP NETMASK" exit 1 fi DEVICE="$1" LOCAL_ADDRESS="$2" REMOTE_ADDRESS="$3" NWMASK="$4" echo "Driver: $(ethtool -i ${DEVICE} | awk '/^driver:/{print $2}') " ethtool -k "${DEVICE}" | grep tx-udp echo echo "Set up NIC and tunnel..." ip addr add "${LOCAL_ADDRESS}/${NWMASK}" dev "${DEVICE}" ip link set "${DEVICE}" up sleep 2 ip link add vxlan1 type vxlan id 42 \ remote "${REMOTE_ADDRESS}" \ local "${LOCAL_ADDRESS}" \ dstport 0 \ dev "${DEVICE}" ip addr add fc00::1/64 dev vxlan1 ip link set vxlan1 up sleep 2 rm -f vxlan.pcap echo "Running tcpdump and iperf3..." ( nohup tcpdump -i any -w vxlan.pcap >/dev/null 2>&1 ) & sleep 2 iperf3 -c fc00::2 >/dev/null pkill tcpdump echo echo -n "Max. Paket Size: " tcpdump -r vxlan.pcap -nnle 2>/dev/null \ | grep "${LOCAL_ADDRESS}.*> ${REMOTE_ADDRESS}.*OTV" \ | awk '{print $8}' | awk -F ':' '{print $1}' \ | sort -n | tail -1 echo ip link del vxlan1 ip addr del ${LOCAL_ADDRESS}/${NWMASK} dev "${DEVICE}" === SNAP === The expected outcome is Max. Paket Size: 64904 This is what you see on igb, the code igc has been taken from. However, on igc the output is Max. Paket Size: 1516 so the GSO aggregate packets are segmented by the kernel before calling igc_xmit_frame. Inside the subsequent call to igc_tso, the check for skb_is_gso(skb) fails and the function returns prematurely. It turns out that this occurs because the feature flags aren't set entirely correctly in igc_probe. In contrast to the original code from igb_probe, igc_probe neglects to set the flags required to allow tunnel offloading. Setting the same flags as igb fixes the issue on igc. Fixes: 34428dff3679 ("igc: Add GSO partial support") Signed-off-by: Paolo Abeni Tested-by: Corinna Vinschen Acked-by: Sasha Neftin Tested-by: Nechama Kraus Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/igc/igc_main.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index b877efae61df..0e19b4d02e62 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6350,7 +6350,9 @@ static int igc_probe(struct pci_dev *pdev, if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= netdev->features; + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->mpls_features |= NETIF_F_HW_CSUM; + netdev->hw_enc_features |= netdev->vlan_features; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; From ee8a9600b5391f434905c46bec7f77d34505083e Mon Sep 17 00:00:00 2001 From: David Thompson Date: Wed, 15 Sep 2021 14:08:48 -0400 Subject: [PATCH 331/866] mlxbf_gige: clear valid_polarity upon open The network interface managed by the mlxbf_gige driver can get into a problem state where traffic does not flow. In this state, the interface will be up and enabled, but will stop processing received packets. This problem state will happen if three specific conditions occur: 1) driver has received more than (N * RxRingSize) packets but less than (N+1 * RxRingSize) packets, where N is an odd number Note: the command "ethtool -g " will display the current receive ring size, which currently defaults to 128 2) the driver's interface was disabled via "ifconfig oob_net0 down" during the window described in #1. 3) the driver's interface is re-enabled via "ifconfig oob_net0 up" This patch ensures that the driver's "valid_polarity" field is cleared during the open() method so that it always matches the receive polarity used by hardware. Without this fix, the driver needs to be unloaded and reloaded to correct this problem state. Fixes: f92e1869d74e ("Add Mellanox BlueField Gigabit Ethernet driver") Reviewed-by: Asmaa Mnebhi Signed-off-by: David Thompson Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 3e85b17f5857..6704f5c1aa32 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -142,6 +142,13 @@ static int mlxbf_gige_open(struct net_device *netdev) err = mlxbf_gige_clean_port(priv); if (err) goto free_irqs; + + /* Clear driver's valid_polarity to match hardware, + * since the above call to clean_port() resets the + * receive polarity used by hardware. + */ + priv->valid_polarity = 0; + err = mlxbf_gige_rx_init(priv); if (err) goto free_irqs; From b3a7b268c147119a9776185b4f37e1555ead9d68 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Tue, 7 Sep 2021 09:53:03 -0400 Subject: [PATCH 332/866] drm/amd/display: Add NULL checks for vblank workqueue [Why] If we're running a headless config with 0 links then the vblank workqueue will be NULL - causing a NULL pointer exception during any commit. [How] Guard access to the workqueue if it's NULL and don't queue or flush work if it is. Reported-by: Mike Lothian BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1700 Fixes: 58aa1c50e5a231 ("drm/amd/display: Use vblank control events for PSR enable/disable") Signed-off-by: Nicholas Kazlauskas Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 32 +++++++++++-------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d55e61d8aa00..14ba5eeb974f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6024,21 +6024,23 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) return 0; #if defined(CONFIG_DRM_AMD_DC_DCN) - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) - return -ENOMEM; + if (dm->vblank_control_workqueue) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return -ENOMEM; - INIT_WORK(&work->work, vblank_control_worker); - work->dm = dm; - work->acrtc = acrtc; - work->enable = enable; + INIT_WORK(&work->work, vblank_control_worker); + work->dm = dm; + work->acrtc = acrtc; + work->enable = enable; - if (acrtc_state->stream) { - dc_stream_retain(acrtc_state->stream); - work->stream = acrtc_state->stream; + if (acrtc_state->stream) { + dc_stream_retain(acrtc_state->stream); + work->stream = acrtc_state->stream; + } + + queue_work(dm->vblank_control_workqueue, &work->work); } - - queue_work(dm->vblank_control_workqueue, &work->work); #endif return 0; @@ -8648,7 +8650,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * If PSR or idle optimizations are enabled then flush out * any pending work before hardware programming. */ - flush_workqueue(dm->vblank_control_workqueue); + if (dm->vblank_control_workqueue) + flush_workqueue(dm->vblank_control_workqueue); #endif bundle->stream_update.stream = acrtc_state->stream; @@ -8983,7 +8986,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* if there mode set or reset, disable eDP PSR */ if (mode_set_reset_required) { #if defined(CONFIG_DRM_AMD_DC_DCN) - flush_workqueue(dm->vblank_control_workqueue); + if (dm->vblank_control_workqueue) + flush_workqueue(dm->vblank_control_workqueue); #endif amdgpu_dm_psr_disable_all(dm); } From 2a54d110bd4393fe412ef2c9c2d05fcd92785d1a Mon Sep 17 00:00:00 2001 From: Anson Jacob Date: Thu, 9 Sep 2021 12:48:29 -0400 Subject: [PATCH 333/866] drm/amd/display: dc_assert_fp_enabled assert only if FPU is not enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Assert only when FPU is not enabled. Fixes: 0ea7ee821701 ("drm/amd/display: Add DC_FP helper to check FPU state") Signed-off-by: Anson Jacob Cc: Christian König Cc: Hersen Wu Cc: Harry Wentland Cc: Rodrigo Siqueira Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c index c9f47d167472..b1bf80da3a55 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c @@ -62,7 +62,7 @@ inline void dc_assert_fp_enabled(void) depth = *pcpu; put_cpu_ptr(&fpu_recursion_depth); - ASSERT(depth > 1); + ASSERT(depth >= 1); } /** From 8f48ba303dfb15dc354e95a3ade59dea4614123a Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Wed, 8 Sep 2021 13:34:26 +0800 Subject: [PATCH 334/866] drm/amdgpu: fix sysfs_emit/sysfs_emit_at warnings(v2) sysfs_emit and sysfs_emit_at requrie a page boundary aligned buf address. Make them happy! v2: use an inline function. Warning Log: [ 492.545174] invalid sysfs_emit_at: buf:00000000f19bdfde at:0 [ 492.546416] WARNING: CPU: 7 PID: 1304 at fs/sysfs/file.c:765 sysfs_emit_at+0x4a/0xa0 [ 492.654805] Call Trace: [ 492.655353] ? smu_cmn_get_metrics_table+0x40/0x50 [amdgpu] [ 492.656780] vangogh_print_clk_levels+0x369/0x410 [amdgpu] [ 492.658245] vangogh_common_print_clk_levels+0x77/0x80 [amdgpu] [ 492.659733] ? preempt_schedule_common+0x18/0x30 [ 492.660713] smu_print_ppclk_levels+0x65/0x90 [amdgpu] [ 492.662107] amdgpu_get_pp_od_clk_voltage+0x13d/0x190 [amdgpu] [ 492.663620] dev_attr_show+0x1d/0x40 Signed-off-by: Lang Yu Acked-by: Huang Rui Signed-off-by: Alex Deucher --- .../gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c | 8 ++++++-- drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 4 +++- .../drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 4 +++- drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c | 16 ++++++++++------ drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c | 2 ++ .../gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 12 ++++++++---- .../gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c | 6 ++++-- drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h | 13 +++++++++++++ 8 files changed, 49 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index e343cc218990..082f01893f3d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -771,8 +771,12 @@ static int arcturus_print_clk_levels(struct smu_context *smu, struct smu_11_0_dpm_context *dpm_context = NULL; uint32_t gen_speed, lane_width; - if (amdgpu_ras_intr_triggered()) - return sysfs_emit(buf, "unavailable\n"); + smu_cmn_get_sysfs_buf(&buf, &size); + + if (amdgpu_ras_intr_triggered()) { + size += sysfs_emit_at(buf, size, "unavailable\n"); + return size; + } dpm_context = smu_dpm->dpm_context; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index a5fc5d7cb6c7..aec7cb21cc0f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -1279,6 +1279,8 @@ static int navi10_print_clk_levels(struct smu_context *smu, struct smu_11_0_overdrive_table *od_settings = smu->od_settings; uint32_t min_value, max_value; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_GFXCLK: case SMU_SCLK: @@ -1392,7 +1394,7 @@ static int navi10_print_clk_levels(struct smu_context *smu, case SMU_OD_RANGE: if (!smu->od_enabled || !od_table || !od_settings) break; - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); if (navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_GFXCLK_LIMITS)) { navi10_od_setting_get_range(od_settings, SMU_11_0_ODSETTING_GFXCLKFMIN, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 5e292c3f5050..d7519688065f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -1058,6 +1058,8 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu, uint32_t min_value, max_value; uint32_t smu_version; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_GFXCLK: case SMU_SCLK: @@ -1180,7 +1182,7 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu, if (!smu->od_enabled || !od_table || !od_settings) break; - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); if (sienna_cichlid_is_od_feature_supported(od_settings, SMU_11_0_7_ODCAP_GFXCLK_LIMITS)) { sienna_cichlid_get_od_setting_range(od_settings, SMU_11_0_7_ODSETTING_GFXCLKFMIN, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 3a3421452e57..f6ef0ce6e9e2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -589,10 +589,12 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, if (ret) return ret; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_OD_SCLK: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -601,7 +603,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, break; case SMU_OD_CCLK: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n", smu->cpu_core_id_select); + size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n", smu->cpu_core_id_select); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -610,7 +612,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, break; case SMU_OD_RANGE: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq); size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n", @@ -688,10 +690,12 @@ static int vangogh_print_clk_levels(struct smu_context *smu, if (ret) return ret; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_OD_SCLK: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -700,7 +704,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu, break; case SMU_OD_CCLK: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "CCLK_RANGE in Core%d:\n", smu->cpu_core_id_select); + size += sysfs_emit_at(buf, size, "CCLK_RANGE in Core%d:\n", smu->cpu_core_id_select); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (smu->cpu_actual_soft_min_freq > 0) ? smu->cpu_actual_soft_min_freq : smu->cpu_default_soft_min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", @@ -709,7 +713,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu, break; case SMU_OD_RANGE: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq); size += sysfs_emit_at(buf, size, "CCLK: %7uMhz %10uMhz\n", diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 5aa175e12a78..145f13b8c977 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -497,6 +497,8 @@ static int renoir_print_clk_levels(struct smu_context *smu, if (ret) return ret; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_OD_RANGE: if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index ab652028e003..5019903db492 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -733,15 +733,19 @@ static int aldebaran_print_clk_levels(struct smu_context *smu, uint32_t freq_values[3] = {0}; uint32_t min_clk, max_clk; - if (amdgpu_ras_intr_triggered()) - return sysfs_emit(buf, "unavailable\n"); + smu_cmn_get_sysfs_buf(&buf, &size); + + if (amdgpu_ras_intr_triggered()) { + size += sysfs_emit_at(buf, size, "unavailable\n"); + return size; + } dpm_context = smu_dpm->dpm_context; switch (type) { case SMU_OD_SCLK: - size = sysfs_emit(buf, "%s:\n", "GFXCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "GFXCLK"); fallthrough; case SMU_SCLK: ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_GFXCLK, &now); @@ -795,7 +799,7 @@ static int aldebaran_print_clk_levels(struct smu_context *smu, break; case SMU_OD_MCLK: - size = sysfs_emit(buf, "%s:\n", "MCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "MCLK"); fallthrough; case SMU_MCLK: ret = aldebaran_get_current_clk_freq_by_table(smu, SMU_UCLK, &now); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 627ba2eec7fd..a403657151ba 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -1052,16 +1052,18 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu, int i, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; + smu_cmn_get_sysfs_buf(&buf, &size); + switch (clk_type) { case SMU_OD_SCLK: - size = sysfs_emit(buf, "%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK"); size += sysfs_emit_at(buf, size, "0: %10uMhz\n", (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq); size += sysfs_emit_at(buf, size, "1: %10uMhz\n", (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq); break; case SMU_OD_RANGE: - size = sysfs_emit(buf, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", smu->gfx_default_hard_min_freq, smu->gfx_default_soft_max_freq); break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index 16993daa2ae0..4054d9493e77 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -110,5 +110,18 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev); int smu_cmn_set_mp1_state(struct smu_context *smu, enum pp_mp1_state mp1_state); +/* + * Helper function to make sysfs_emit_at() happy. Align buf to + * the current page boundary and record the offset. + */ +static inline void smu_cmn_get_sysfs_buf(char **buf, int *offset) +{ + if (!*buf || !offset) + return; + + *offset = offset_in_page(*buf); + *buf -= *offset; +} + #endif #endif From 8492d3a07d3c7a0c69df0dec2ae835f5557b8835 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Tue, 24 Aug 2021 17:02:57 +0800 Subject: [PATCH 335/866] drm/amdgpu: update SMU PPSMC for cyan skilfish Add some PPSMC MSGs for cyan skilfish. Signed-off-by: Lang Yu Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h index 6e6088760b18..909a86aa60f3 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_8_ppsmc.h @@ -65,6 +65,13 @@ #define PPSMC_MSG_SetDriverTableVMID 0x34 #define PPSMC_MSG_SetSoftMinCclk 0x35 #define PPSMC_MSG_SetSoftMaxCclk 0x36 -#define PPSMC_Message_Count 0x37 +#define PPSMC_MSG_GetGfxFrequency 0x37 +#define PPSMC_MSG_GetGfxVid 0x38 +#define PPSMC_MSG_ForceGfxFreq 0x39 +#define PPSMC_MSG_UnForceGfxFreq 0x3A +#define PPSMC_MSG_ForceGfxVid 0x3B +#define PPSMC_MSG_UnforceGfxVid 0x3C +#define PPSMC_MSG_GetEnabledSmuFeatures 0x3D +#define PPSMC_Message_Count 0x3E #endif From c007e17c8476cb3c1032864f60936f2b7586010b Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Fri, 27 Aug 2021 14:16:31 +0800 Subject: [PATCH 336/866] drm/amdgpu: update SMU driver interface for cyan skilfish(v3) Add SmuMetrics_t definition for cyan skilfish. v2: update SmuMetrics_t definition. v3: cleanup and rearrange the order of fields. Signed-off-by: Lang Yu Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- .../pm/inc/smu11_driver_if_cyan_skillfish.h | 86 ++++++++----------- 1 file changed, 35 insertions(+), 51 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h index 8a08ecc34c69..4884a4e1f261 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h +++ b/drivers/gpu/drm/amd/pm/inc/smu11_driver_if_cyan_skillfish.h @@ -33,63 +33,47 @@ #define TABLE_PMSTATUSLOG 3 // Called by Tools for Agm logging #define TABLE_DPMCLOCKS 4 // Called by Driver; defined here, but not used, for backward compatible #define TABLE_MOMENTARY_PM 5 // Called by Tools; defined here, but not used, for backward compatible -#define TABLE_COUNT 6 +#define TABLE_SMU_METRICS 6 // Called by Driver +#define TABLE_COUNT 7 -#define NUM_DSPCLK_LEVELS 8 -#define NUM_SOCCLK_DPM_LEVELS 8 -#define NUM_DCEFCLK_DPM_LEVELS 4 -#define NUM_FCLK_DPM_LEVELS 4 -#define NUM_MEMCLK_DPM_LEVELS 4 +typedef struct SmuMetricsTable_t { + //CPU status + uint16_t CoreFrequency[6]; //[MHz] + uint32_t CorePower[6]; //[mW] + uint16_t CoreTemperature[6]; //[centi-Celsius] + uint16_t L3Frequency[2]; //[MHz] + uint16_t L3Temperature[2]; //[centi-Celsius] + uint16_t C0Residency[6]; //Percentage -#define NUMBER_OF_PSTATES 8 -#define NUMBER_OF_CORES 8 + // GFX status + uint16_t GfxclkFrequency; //[MHz] + uint16_t GfxTemperature; //[centi-Celsius] -typedef enum { - S3_TYPE_ENTRY, - S5_TYPE_ENTRY, -} Sleep_Type_e; + // SOC IP info + uint16_t SocclkFrequency; //[MHz] + uint16_t VclkFrequency; //[MHz] + uint16_t DclkFrequency; //[MHz] + uint16_t MemclkFrequency; //[MHz] -typedef enum { - GFX_OFF = 0, - GFX_ON = 1, -} GFX_Mode_e; + // power, VF info for CPU/GFX telemetry rails, and then socket power total + uint32_t Voltage[2]; //[mV] indices: VDDCR_VDD, VDDCR_GFX + uint32_t Current[2]; //[mA] indices: VDDCR_VDD, VDDCR_GFX + uint32_t Power[2]; //[mW] indices: VDDCR_VDD, VDDCR_GFX + uint32_t CurrentSocketPower; //[mW] -typedef enum { - CPU_P0 = 0, - CPU_P1, - CPU_P2, - CPU_P3, - CPU_P4, - CPU_P5, - CPU_P6, - CPU_P7 -} CPU_PState_e; + uint16_t SocTemperature; //[centi-Celsius] + uint16_t EdgeTemperature; + uint16_t ThrottlerStatus; + uint16_t Spare; -typedef enum { - CPU_CORE0 = 0, - CPU_CORE1, - CPU_CORE2, - CPU_CORE3, - CPU_CORE4, - CPU_CORE5, - CPU_CORE6, - CPU_CORE7 -} CORE_ID_e; +} SmuMetricsTable_t; -typedef enum { - DF_DPM0 = 0, - DF_DPM1, - DF_DPM2, - DF_DPM3, - DF_PState_Count -} DF_PState_e; - -typedef enum { - GFX_DPM0 = 0, - GFX_DPM1, - GFX_DPM2, - GFX_DPM3, - GFX_PState_Count -} GFX_PState_e; +typedef struct SmuMetrics_t { + SmuMetricsTable_t Current; + SmuMetricsTable_t Average; + uint32_t SampleStartTime; + uint32_t SampleStopTime; + uint32_t Accnt; +} SmuMetrics_t; #endif From 3061fe937ea9990524e73af6d04baca60ad5b137 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Fri, 27 Aug 2021 15:03:50 +0800 Subject: [PATCH 337/866] drm/amdgpu: add some pptable funcs for cyan skilfish(v3) Add print_clk_levels and read_sensor pptable funcs for cyan skilfish. v2: keep consitency and add get_gpu_metrics callback. v3: use sysfs_emit_at() in sysfs show function. Signed-off-by: Lang Yu Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- .../amd/pm/swsmu/smu11/cyan_skillfish_ppt.c | 347 ++++++++++++++++++ 1 file changed, 347 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c index b05f9541accc..e1fab030cfc5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c @@ -44,6 +44,12 @@ #undef pr_info #undef pr_debug +#define FEATURE_MASK(feature) (1ULL << feature) +#define SMC_DPM_FEATURE ( \ + FEATURE_MASK(FEATURE_FCLK_DPM_BIT) | \ + FEATURE_MASK(FEATURE_SOC_DPM_BIT) | \ + FEATURE_MASK(FEATURE_GFX_DPM_BIT)) + static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 0), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetSmuVersion, 0), @@ -52,14 +58,354 @@ static struct cmn2asic_msg_mapping cyan_skillfish_message_map[SMU_MSG_MAX_COUNT] MSG_MAP(SetDriverDramAddrLow, PPSMC_MSG_SetDriverTableDramAddrLow, 0), MSG_MAP(TransferTableSmu2Dram, PPSMC_MSG_TransferTableSmu2Dram, 0), MSG_MAP(TransferTableDram2Smu, PPSMC_MSG_TransferTableDram2Smu, 0), + MSG_MAP(GetEnabledSmuFeatures, PPSMC_MSG_GetEnabledSmuFeatures, 0), + MSG_MAP(RequestGfxclk, PPSMC_MSG_RequestGfxclk, 0), + MSG_MAP(ForceGfxVid, PPSMC_MSG_ForceGfxVid, 0), + MSG_MAP(UnforceGfxVid, PPSMC_MSG_UnforceGfxVid, 0), }; +static struct cmn2asic_mapping cyan_skillfish_table_map[SMU_TABLE_COUNT] = { + TAB_MAP_VALID(SMU_METRICS), +}; + +static int cyan_skillfish_tables_init(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct smu_table *tables = smu_table->tables; + + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, + sizeof(SmuMetrics_t), + PAGE_SIZE, + AMDGPU_GEM_DOMAIN_VRAM); + + smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); + if (!smu_table->metrics_table) + goto err0_out; + + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); + if (!smu_table->gpu_metrics_table) + goto err1_out; + + smu_table->metrics_time = 0; + + return 0; + +err1_out: + smu_table->gpu_metrics_table_size = 0; + kfree(smu_table->metrics_table); +err0_out: + return -ENOMEM; +} + +static int cyan_skillfish_init_smc_tables(struct smu_context *smu) +{ + int ret = 0; + + ret = cyan_skillfish_tables_init(smu); + if (ret) + return ret; + + return smu_v11_0_init_smc_tables(smu); +} + +static int cyan_skillfish_finit_smc_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + kfree(smu_table->metrics_table); + smu_table->metrics_table = NULL; + + kfree(smu_table->gpu_metrics_table); + smu_table->gpu_metrics_table = NULL; + smu_table->gpu_metrics_table_size = 0; + + smu_table->metrics_time = 0; + + return 0; +} + +static int +cyan_skillfish_get_smu_metrics_data(struct smu_context *smu, + MetricsMember_t member, + uint32_t *value) +{ + struct smu_table_context *smu_table = &smu->smu_table; + SmuMetrics_t *metrics = (SmuMetrics_t *)smu_table->metrics_table; + int ret = 0; + + mutex_lock(&smu->metrics_lock); + + ret = smu_cmn_get_metrics_table_locked(smu, NULL, false); + if (ret) { + mutex_unlock(&smu->metrics_lock); + return ret; + } + + switch (member) { + case METRICS_CURR_GFXCLK: + *value = metrics->Current.GfxclkFrequency; + break; + case METRICS_CURR_SOCCLK: + *value = metrics->Current.SocclkFrequency; + break; + case METRICS_CURR_VCLK: + *value = metrics->Current.VclkFrequency; + break; + case METRICS_CURR_DCLK: + *value = metrics->Current.DclkFrequency; + break; + case METRICS_CURR_UCLK: + *value = metrics->Current.MemclkFrequency; + break; + case METRICS_AVERAGE_SOCKETPOWER: + *value = (metrics->Current.CurrentSocketPower << 8) / + 1000; + break; + case METRICS_TEMPERATURE_EDGE: + *value = metrics->Current.GfxTemperature / 100 * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_TEMPERATURE_HOTSPOT: + *value = metrics->Current.SocTemperature / 100 * + SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; + break; + case METRICS_VOLTAGE_VDDSOC: + *value = metrics->Current.Voltage[0]; + break; + case METRICS_VOLTAGE_VDDGFX: + *value = metrics->Current.Voltage[1]; + break; + case METRICS_THROTTLER_STATUS: + *value = metrics->Current.ThrottlerStatus; + break; + default: + *value = UINT_MAX; + break; + } + + mutex_unlock(&smu->metrics_lock); + + return ret; +} + +static int cyan_skillfish_read_sensor(struct smu_context *smu, + enum amd_pp_sensors sensor, + void *data, + uint32_t *size) +{ + int ret = 0; + + if (!data || !size) + return -EINVAL; + + mutex_lock(&smu->sensor_lock); + + switch (sensor) { + case AMDGPU_PP_SENSOR_GFX_SCLK: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_CURR_GFXCLK, + (uint32_t *)data); + *(uint32_t *)data *= 100; + *size = 4; + break; + case AMDGPU_PP_SENSOR_GFX_MCLK: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_CURR_UCLK, + (uint32_t *)data); + *(uint32_t *)data *= 100; + *size = 4; + break; + case AMDGPU_PP_SENSOR_GPU_POWER: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_AVERAGE_SOCKETPOWER, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_HOTSPOT_TEMP: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_TEMPERATURE_HOTSPOT, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_EDGE_TEMP: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_TEMPERATURE_EDGE, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_VDDNB: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_VOLTAGE_VDDSOC, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_VDDGFX: + ret = cyan_skillfish_get_smu_metrics_data(smu, + METRICS_VOLTAGE_VDDGFX, + (uint32_t *)data); + *size = 4; + break; + default: + ret = -EOPNOTSUPP; + break; + } + + mutex_unlock(&smu->sensor_lock); + + return ret; +} + +static int cyan_skillfish_get_current_clk_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *value) +{ + MetricsMember_t member_type; + + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + member_type = METRICS_CURR_GFXCLK; + break; + case SMU_FCLK: + case SMU_MCLK: + member_type = METRICS_CURR_UCLK; + break; + case SMU_SOCCLK: + member_type = METRICS_CURR_SOCCLK; + break; + case SMU_VCLK: + member_type = METRICS_CURR_VCLK; + break; + case SMU_DCLK: + member_type = METRICS_CURR_DCLK; + break; + default: + return -EINVAL; + } + + return cyan_skillfish_get_smu_metrics_data(smu, member_type, value); +} + +static int cyan_skillfish_print_clk_levels(struct smu_context *smu, + enum smu_clk_type clk_type, + char *buf) +{ + int ret = 0, size = 0; + uint32_t cur_value = 0; + + smu_cmn_get_sysfs_buf(&buf, &size); + + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + case SMU_FCLK: + case SMU_MCLK: + case SMU_SOCCLK: + case SMU_VCLK: + case SMU_DCLK: + ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value); + if (ret) + return ret; + size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value); + break; + default: + dev_warn(smu->adev->dev, "Unsupported clock type\n"); + return ret; + } + + return size; +} + +static bool cyan_skillfish_is_dpm_running(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + uint32_t feature_mask[2]; + uint64_t feature_enabled; + + /* we need to re-init after suspend so return false */ + if (adev->in_suspend) + return false; + + ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2); + + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[0] | + ((uint64_t)feature_mask[1] << 32); + + return !!(feature_enabled & SMC_DPM_FEATURE); +} + +static ssize_t cyan_skillfish_get_gpu_metrics(struct smu_context *smu, + void **table) +{ + struct smu_table_context *smu_table = &smu->smu_table; + struct gpu_metrics_v2_2 *gpu_metrics = + (struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table; + SmuMetrics_t metrics; + int i, ret = 0; + + ret = smu_cmn_get_metrics_table(smu, &metrics, true); + if (ret) + return ret; + + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2); + + gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature; + gpu_metrics->temperature_soc = metrics.Current.SocTemperature; + + gpu_metrics->average_socket_power = metrics.Current.CurrentSocketPower; + gpu_metrics->average_soc_power = metrics.Current.Power[0]; + gpu_metrics->average_gfx_power = metrics.Current.Power[1]; + + gpu_metrics->average_gfxclk_frequency = metrics.Average.GfxclkFrequency; + gpu_metrics->average_socclk_frequency = metrics.Average.SocclkFrequency; + gpu_metrics->average_uclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_fclk_frequency = metrics.Average.MemclkFrequency; + gpu_metrics->average_vclk_frequency = metrics.Average.VclkFrequency; + gpu_metrics->average_dclk_frequency = metrics.Average.DclkFrequency; + + gpu_metrics->current_gfxclk = metrics.Current.GfxclkFrequency; + gpu_metrics->current_socclk = metrics.Current.SocclkFrequency; + gpu_metrics->current_uclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_fclk = metrics.Current.MemclkFrequency; + gpu_metrics->current_vclk = metrics.Current.VclkFrequency; + gpu_metrics->current_dclk = metrics.Current.DclkFrequency; + + for (i = 0; i < 6; i++) { + gpu_metrics->temperature_core[i] = metrics.Current.CoreTemperature[i]; + gpu_metrics->average_core_power[i] = metrics.Average.CorePower[i]; + gpu_metrics->current_coreclk[i] = metrics.Current.CoreFrequency[i]; + } + + for (i = 0; i < 2; i++) { + gpu_metrics->temperature_l3[i] = metrics.Current.L3Temperature[i]; + gpu_metrics->current_l3clk[i] = metrics.Current.L3Frequency[i]; + } + + gpu_metrics->throttle_status = metrics.Current.ThrottlerStatus; + gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); + + *table = (void *)gpu_metrics; + + return sizeof(struct gpu_metrics_v2_2); +} + static const struct pptable_funcs cyan_skillfish_ppt_funcs = { .check_fw_status = smu_v11_0_check_fw_status, .check_fw_version = smu_v11_0_check_fw_version, .init_power = smu_v11_0_init_power, .fini_power = smu_v11_0_fini_power, + .init_smc_tables = cyan_skillfish_init_smc_tables, + .fini_smc_tables = cyan_skillfish_finit_smc_tables, + .read_sensor = cyan_skillfish_read_sensor, + .print_clk_levels = cyan_skillfish_print_clk_levels, + .is_dpm_running = cyan_skillfish_is_dpm_running, + .get_gpu_metrics = cyan_skillfish_get_gpu_metrics, .register_irq_handler = smu_v11_0_register_irq_handler, .notify_memory_pool_location = smu_v11_0_notify_memory_pool_location, .send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param, @@ -72,5 +418,6 @@ void cyan_skillfish_set_ppt_funcs(struct smu_context *smu) { smu->ppt_funcs = &cyan_skillfish_ppt_funcs; smu->message_map = cyan_skillfish_message_map; + smu->table_map = cyan_skillfish_table_map; smu->is_apu = true; } From abd0a16ac72c98c46e7a1a91d591121b9c95cf97 Mon Sep 17 00:00:00 2001 From: Lang Yu Date: Fri, 27 Aug 2021 15:20:51 +0800 Subject: [PATCH 338/866] drm/amdgpu: add manual sclk/vddc setting support for cyan skilfish(v3) Add manual sclk/vddc setting supoort via pp_od_clk_voltage sysfs to maintain consistency with other asics. As cyan skillfish doesn't support DPM, there is only a single frequency and voltage to adjust. v2: maintain consistency and add command guide. v3: adjust user settings storage and coding style. Command guide: echo vc point sclk vddc > pp_od_clk_voltage "vc" - sclk voltage curve "point" - must be 0 "sclk" - target value of sclk(MHz), should be in safe range "vddc" - target value of vddc(mV), a 6.25(mV) stepping is recommended and should be in safe range (the real vddc is an approximation of target value) echo c > pp_od_clk_voltage "c" - commit the changes of sclk and vddc, only after the commit command, the target values set by "vc" command will take effect echo r > pp_od_clk_voltage "r" - reset sclk and vddc to default value, a subsequent commit command is needed to take effect Example: 1) Check default sclk and vddc $ cat pp_od_clk_voltage OD_SCLK: 0: 1800Mhz * OD_VDDC: 0: 862mV * OD_RANGE: SCLK: 1000Mhz 2000Mhz VDDC: 700mV 1129mV 2) Set sclk to 1500MHz and vddc to 700mV $ echo vc 0 1500 700 > pp_od_clk_voltage $ echo c > pp_od_clk_voltage $ cat pp_od_clk_voltage OD_SCLK: 0: 1500Mhz * OD_VDDC: 0: 693mV * OD_RANGE: SCLK: 1000Mhz 2000Mhz VDDC: 700mV 1129mV 3) Reset sclk and vddc to default $ echo r > pp_od_clk_voltage $ echo c > pp_od_clk_voltage $ cat pp_od_clk_voltage OD_SCLK: 0: 1800Mhz * OD_VDDC: 0: 874mV * OD_RANGE: SCLK: 1000Mhz 2000Mhz VDDC: 700mV 1129mV NOTE: We don't specify an explicit safe range, you can set any values between min and max at your own risk. Enjoy! Signed-off-by: Lang Yu Reviewed-by: Lijo Lazar Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/inc/smu_types.h | 5 +- .../amd/pm/swsmu/smu11/cyan_skillfish_ppt.c | 134 ++++++++++++++++++ 2 files changed, 138 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h index 6f1b1b50d527..18b862a90fbe 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h @@ -226,7 +226,10 @@ __SMU_DUMMY_MAP(SetUclkDpmMode), \ __SMU_DUMMY_MAP(LightSBR), \ __SMU_DUMMY_MAP(GfxDriverResetRecovery), \ - __SMU_DUMMY_MAP(BoardPowerCalibration), + __SMU_DUMMY_MAP(BoardPowerCalibration), \ + __SMU_DUMMY_MAP(RequestGfxclk), \ + __SMU_DUMMY_MAP(ForceGfxVid), \ + __SMU_DUMMY_MAP(UnforceGfxVid), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c index e1fab030cfc5..3d4c65bc29dc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c @@ -44,6 +44,21 @@ #undef pr_info #undef pr_debug +/* unit: MHz */ +#define CYAN_SKILLFISH_SCLK_MIN 1000 +#define CYAN_SKILLFISH_SCLK_MAX 2000 +#define CYAN_SKILLFISH_SCLK_DEFAULT 1800 + +/* unit: mV */ +#define CYAN_SKILLFISH_VDDC_MIN 700 +#define CYAN_SKILLFISH_VDDC_MAX 1129 +#define CYAN_SKILLFISH_VDDC_MAGIC 5118 // 0x13fe + +static struct gfx_user_settings { + uint32_t sclk; + uint32_t vddc; +} cyan_skillfish_user_settings; + #define FEATURE_MASK(feature) (1ULL << feature) #define SMC_DPM_FEATURE ( \ FEATURE_MASK(FEATURE_FCLK_DPM_BIT) | \ @@ -297,6 +312,27 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu, smu_cmn_get_sysfs_buf(&buf, &size); switch (clk_type) { + case SMU_OD_SCLK: + ret = cyan_skillfish_get_smu_metrics_data(smu, METRICS_CURR_GFXCLK, &cur_value); + if (ret) + return ret; + size += sysfs_emit_at(buf, size,"%s:\n", "OD_SCLK"); + size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value); + break; + case SMU_OD_VDDC_CURVE: + ret = cyan_skillfish_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDGFX, &cur_value); + if (ret) + return ret; + size += sysfs_emit_at(buf, size,"%s:\n", "OD_VDDC"); + size += sysfs_emit_at(buf, size, "0: %umV *\n", cur_value); + break; + case SMU_OD_RANGE: + size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE"); + size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", + CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX); + size += sysfs_emit_at(buf, size, "VDDC: %7umV %10umV\n", + CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX); + break; case SMU_GFXCLK: case SMU_SCLK: case SMU_FCLK: @@ -394,6 +430,103 @@ static ssize_t cyan_skillfish_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_2); } +static int cyan_skillfish_od_edit_dpm_table(struct smu_context *smu, + enum PP_OD_DPM_TABLE_COMMAND type, + long input[], uint32_t size) +{ + int ret = 0; + uint32_t vid; + + switch (type) { + case PP_OD_EDIT_VDDC_CURVE: + if (size != 3 || input[0] != 0) { + dev_err(smu->adev->dev, "Invalid parameter!\n"); + return -EINVAL; + } + + if (input[1] <= CYAN_SKILLFISH_SCLK_MIN || + input[1] > CYAN_SKILLFISH_SCLK_MAX) { + dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n", + CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX); + return -EINVAL; + } + + if (input[2] <= CYAN_SKILLFISH_VDDC_MIN || + input[2] > CYAN_SKILLFISH_VDDC_MAX) { + dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n", + CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX); + return -EINVAL; + } + + cyan_skillfish_user_settings.sclk = input[1]; + cyan_skillfish_user_settings.vddc = input[2]; + + break; + case PP_OD_RESTORE_DEFAULT_TABLE: + if (size != 0) { + dev_err(smu->adev->dev, "Invalid parameter!\n"); + return -EINVAL; + } + + cyan_skillfish_user_settings.sclk = CYAN_SKILLFISH_SCLK_DEFAULT; + cyan_skillfish_user_settings.vddc = CYAN_SKILLFISH_VDDC_MAGIC; + + break; + case PP_OD_COMMIT_DPM_TABLE: + if (size != 0) { + dev_err(smu->adev->dev, "Invalid parameter!\n"); + return -EINVAL; + } + + if (cyan_skillfish_user_settings.sclk < CYAN_SKILLFISH_SCLK_MIN || + cyan_skillfish_user_settings.sclk > CYAN_SKILLFISH_SCLK_MAX) { + dev_err(smu->adev->dev, "Invalid sclk! Valid sclk range: %uMHz - %uMhz\n", + CYAN_SKILLFISH_SCLK_MIN, CYAN_SKILLFISH_SCLK_MAX); + return -EINVAL; + } + + if ((cyan_skillfish_user_settings.vddc != CYAN_SKILLFISH_VDDC_MAGIC) && + (cyan_skillfish_user_settings.vddc < CYAN_SKILLFISH_VDDC_MIN || + cyan_skillfish_user_settings.vddc > CYAN_SKILLFISH_VDDC_MAX)) { + dev_err(smu->adev->dev, "Invalid vddc! Valid vddc range: %umV - %umV\n", + CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX); + return -EINVAL; + } + + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_RequestGfxclk, + cyan_skillfish_user_settings.sclk, NULL); + if (ret) { + dev_err(smu->adev->dev, "Set sclk failed!\n"); + return ret; + } + + if (cyan_skillfish_user_settings.vddc == CYAN_SKILLFISH_VDDC_MAGIC) { + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_UnforceGfxVid, NULL); + if (ret) { + dev_err(smu->adev->dev, "Unforce vddc failed!\n"); + return ret; + } + } else { + /* + * PMFW accepts SVI2 VID code, convert voltage to VID: + * vid = (uint32_t)((1.55 - voltage) * 160.0 + 0.00001) + */ + vid = (1550 - cyan_skillfish_user_settings.vddc) * 160 / 1000; + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ForceGfxVid, vid, NULL); + if (ret) { + dev_err(smu->adev->dev, "Force vddc failed!\n"); + return ret; + } + } + + break; + default: + return -EOPNOTSUPP; + } + + return ret; +} + static const struct pptable_funcs cyan_skillfish_ppt_funcs = { .check_fw_status = smu_v11_0_check_fw_status, @@ -406,6 +539,7 @@ static const struct pptable_funcs cyan_skillfish_ppt_funcs = { .print_clk_levels = cyan_skillfish_print_clk_levels, .is_dpm_running = cyan_skillfish_is_dpm_running, .get_gpu_metrics = cyan_skillfish_get_gpu_metrics, + .od_edit_dpm_table = cyan_skillfish_od_edit_dpm_table, .register_irq_handler = smu_v11_0_register_irq_handler, .notify_memory_pool_location = smu_v11_0_notify_memory_pool_location, .send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param, From fb932dfeb87411a8a01c995576198bfc302df339 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Tue, 31 Aug 2021 17:42:15 -0400 Subject: [PATCH 339/866] drm/amdkfd: make needs_pcie_atomics FW-version dependent On some GPUs the PCIe atomic requirement for KFD depends on the MEC firmware version. Add a firmware version check for this. The minimum firmware version that works without atomics can be updated in the device_info structure for each GPU type. Move PCIe atomic detection from kgd2kfd_probe into kgd2kfd_device_init because the MEC firmware is not loaded yet at the probe stage. Signed-off-by: Felix Kuehling Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 44 ++++++++++++++++--------- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 + 2 files changed, 29 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 16a57b70cc1a..30fde852af19 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -468,6 +468,7 @@ static const struct kfd_device_info navi10_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -487,6 +488,7 @@ static const struct kfd_device_info navi12_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -506,6 +508,7 @@ static const struct kfd_device_info navi14_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 145, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -525,6 +528,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 4, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -544,6 +548,7 @@ static const struct kfd_device_info navy_flounder_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -562,7 +567,8 @@ static const struct kfd_device_info vangogh_device_info = { .mqd_size_aligned = MQD_SIZE_ALIGNED, .needs_iommu_device = false, .supports_cwsr = true, - .needs_pci_atomics = false, + .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, @@ -582,6 +588,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 2, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -601,6 +608,7 @@ static const struct kfd_device_info beige_goby_device_info = { .needs_iommu_device = false, .supports_cwsr = true, .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 8, @@ -619,7 +627,8 @@ static const struct kfd_device_info yellow_carp_device_info = { .mqd_size_aligned = MQD_SIZE_ALIGNED, .needs_iommu_device = false, .supports_cwsr = true, - .needs_pci_atomics = false, + .needs_pci_atomics = true, + .no_atomic_fw_version = 92, .num_sdma_engines = 1, .num_xgmi_sdma_engines = 0, .num_sdma_queues_per_engine = 2, @@ -708,20 +717,6 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, if (!kfd) return NULL; - /* Allow BIF to recode atomics to PCIe 3.0 AtomicOps. - * 32 and 64-bit requests are possible and must be - * supported. - */ - kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd); - if (device_info->needs_pci_atomics && - !kfd->pci_atomic_requested) { - dev_info(kfd_device, - "skipped device %x:%x, PCI rejects atomics\n", - pdev->vendor, pdev->device); - kfree(kfd); - return NULL; - } - kfd->kgd = kgd; kfd->device_info = device_info; kfd->pdev = pdev; @@ -821,6 +816,23 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, kfd->vm_info.vmid_num_kfd = kfd->vm_info.last_vmid_kfd - kfd->vm_info.first_vmid_kfd + 1; + /* Allow BIF to recode atomics to PCIe 3.0 AtomicOps. + * 32 and 64-bit requests are possible and must be + * supported. + */ + kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kfd->kgd); + if (!kfd->pci_atomic_requested && + kfd->device_info->needs_pci_atomics && + (!kfd->device_info->no_atomic_fw_version || + kfd->mec_fw_version < kfd->device_info->no_atomic_fw_version)) { + dev_info(kfd_device, + "skipped device %x:%x, PCI rejects atomics %d<%d\n", + kfd->pdev->vendor, kfd->pdev->device, + kfd->mec_fw_version, + kfd->device_info->no_atomic_fw_version); + return false; + } + /* Verify module parameters regarding mapped process number*/ if ((hws_max_conc_proc < 0) || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index ab83b0de6b22..6d8f9bb2d905 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -207,6 +207,7 @@ struct kfd_device_info { bool supports_cwsr; bool needs_iommu_device; bool needs_pci_atomics; + uint32_t no_atomic_fw_version; unsigned int num_sdma_engines; unsigned int num_xgmi_sdma_engines; unsigned int num_sdma_queues_per_engine; From 9987fbb368038d41bfdcda2a3f7f4945d7daa9a5 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Mon, 16 Aug 2021 15:57:12 -0400 Subject: [PATCH 340/866] drm/amd/display: Get backlight from PWM if DMCU is not initialized On Carrizo/Stoney systems we set backlight through panel_cntl, i.e. directly via the PWM registers, if DMCU is not initialized. We always read it back through ABM registers which leads to a mismatch and forces atomic_commit to program the backlight each time. Instead make sure we use the same logic for backlight readback, i.e. read it from panel_cntl if DMCU is not initialized. We also need to remove some extraneous and incorrect calculations at the end of dce_get_16_bit_backlight_from_pwm. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1666 Cc: stable@vger.kernel.org Reviewed-by: Josip Pavic Acked-by: Mikita Lipski Signed-off-by: Harry Wentland Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 16 ++++++++++++---- .../gpu/drm/amd/display/dc/dce/dce_panel_cntl.c | 10 ---------- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 8bd7f42a8053..1e44b13c1c7d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2586,13 +2586,21 @@ static struct abm *get_abm_from_stream_res(const struct dc_link *link) int dc_link_get_backlight_level(const struct dc_link *link) { - struct abm *abm = get_abm_from_stream_res(link); + struct panel_cntl *panel_cntl = link->panel_cntl; + struct dc *dc = link->ctx->dc; + struct dmcu *dmcu = dc->res_pool->dmcu; + bool fw_set_brightness = true; - if (abm == NULL || abm->funcs->get_current_backlight == NULL) + if (dmcu) + fw_set_brightness = dmcu->funcs->is_dmcu_initialized(dmcu); + + if (!fw_set_brightness && panel_cntl->funcs->get_current_backlight) + return panel_cntl->funcs->get_current_backlight(panel_cntl); + else if (abm != NULL && abm->funcs->get_current_backlight != NULL) + return (int) abm->funcs->get_current_backlight(abm); + else return DC_ERROR_UNEXPECTED; - - return (int) abm->funcs->get_current_backlight(abm); } int dc_link_get_target_backlight_pwm(const struct dc_link *link) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c index e92339235863..e8570060d007 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c @@ -49,7 +49,6 @@ static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_cntl) { uint64_t current_backlight; - uint32_t round_result; uint32_t bl_period, bl_int_count; uint32_t bl_pwm, fractional_duty_cycle_en; uint32_t bl_period_mask, bl_pwm_mask; @@ -84,15 +83,6 @@ static unsigned int dce_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_c current_backlight = div_u64(current_backlight, bl_period); current_backlight = (current_backlight + 1) >> 1; - current_backlight = (uint64_t)(current_backlight) * bl_period; - - round_result = (uint32_t)(current_backlight & 0xFFFFFFFF); - - round_result = (round_result >> (bl_int_count-1)) & 1; - - current_backlight >>= bl_int_count; - current_backlight += round_result; - return (uint32_t)(current_backlight); } From 90517c9838602846daa0feec7b37382fed61b001 Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Wed, 25 Aug 2021 16:27:47 -0400 Subject: [PATCH 341/866] drm/amd/display: dsc mst 2 4K displays go dark with 2 lane HBR3 [Why] call stack of amdgpu dsc mst pbn, slot num calculation is as below: -compute_bpp_x16_from_target_bandwidth -decide_dsc_target_bpp_x16 -setup_dsc_config -dc_dsc_compute_bandwidth_range -compute_mst_dsc_configs_for_link -compute_mst_dsc_configs_for_state from pbn -> dsc target bpp_x16 bpp_x16 is calulated by compute_bpp_x16_from_target_bandwidth. Beside pixel clock and bpp, num_slices_h and bpp_increment_div will also affect bpp_x16. from dsc target bpp_x16 -> pbn within dm_update_mst_vcpi_slots_for_dsc, pbn = drm_dp_calc_pbn_mode(clock, bpp_x16, true); drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc) { return DIV_ROUND_UP_ULL(mul_u32_u32(clock * (bpp / 16), 64 * 1006), 8 * 54 * 1000 * 1000); } bpp / 16 trunc digits after decimal point. This will cause calculation delta. drm_dp_calc_pbn_mode does not have other informations, like num_slices_h, bpp_increment_div. therefore, it does not do revese calcuation properly from bpp_x16 to pbn. pbn from drm_dp_calc_pbn_mode is less than pbn from compute_mst_dsc_configs_for_state. This cause not enough mst slot allocated to display. display could not visually light up. [How] pass pbn from compute_mst_dsc_configs_for_state to dm_update_mst_vcpi_slots_for_dsc Cc: stable@vger.kernel.org Reviewed-by: Scott Foster Acked-by: Mikita Lipski Signed-off-by: Hersen Wu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 22 ++++++++++++++----- .../display/amdgpu_dm/amdgpu_dm_mst_types.c | 18 +++++++-------- .../display/amdgpu_dm/amdgpu_dm_mst_types.h | 11 +++++++++- 3 files changed, 34 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 14ba5eeb974f..deb8010efc69 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6794,14 +6794,15 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = { #if defined(CONFIG_DRM_AMD_DC_DCN) static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, - struct dc_state *dc_state) + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { struct dc_stream_state *stream = NULL; struct drm_connector *connector; struct drm_connector_state *new_con_state; struct amdgpu_dm_connector *aconnector; struct dm_connector_state *dm_conn_state; - int i, j, clock, bpp; + int i, j, clock; int vcpi, pbn_div, pbn = 0; for_each_new_connector_in_state(state, connector, new_con_state, i) { @@ -6840,9 +6841,15 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, } pbn_div = dm_mst_get_pbn_divider(stream->link); - bpp = stream->timing.dsc_cfg.bits_per_pixel; clock = stream->timing.pix_clk_100hz / 10; - pbn = drm_dp_calc_pbn_mode(clock, bpp, true); + /* pbn is calculated by compute_mst_dsc_configs_for_state*/ + for (j = 0; j < dc_state->stream_count; j++) { + if (vars[j].aconnector == aconnector) { + pbn = vars[j].pbn; + break; + } + } + vcpi = drm_dp_mst_atomic_enable_dsc(state, aconnector->port, pbn, pbn_div, @@ -10247,6 +10254,9 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, int ret, i; bool lock_and_validation_needed = false; struct dm_crtc_state *dm_old_crtc_state; +#if defined(CONFIG_DRM_AMD_DC_DCN) + struct dsc_mst_fairness_vars vars[MAX_PIPES]; +#endif trace_amdgpu_dm_atomic_check_begin(state); @@ -10477,10 +10487,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; #if defined(CONFIG_DRM_AMD_DC_DCN) - if (!compute_mst_dsc_configs_for_state(state, dm_state->context)) + if (!compute_mst_dsc_configs_for_state(state, dm_state->context, vars)) goto fail; - ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context); + ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context, vars); if (ret) goto fail; #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 1bcba6943fd7..7af0d58c231b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -518,12 +518,7 @@ struct dsc_mst_fairness_params { uint32_t num_slices_h; uint32_t num_slices_v; uint32_t bpp_overwrite; -}; - -struct dsc_mst_fairness_vars { - int pbn; - bool dsc_enabled; - int bpp_x16; + struct amdgpu_dm_connector *aconnector; }; static int kbps_to_peak_pbn(int kbps) @@ -750,12 +745,12 @@ static void try_disable_dsc(struct drm_atomic_state *state, static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, struct dc_state *dc_state, - struct dc_link *dc_link) + struct dc_link *dc_link, + struct dsc_mst_fairness_vars *vars) { int i; struct dc_stream_state *stream; struct dsc_mst_fairness_params params[MAX_PIPES]; - struct dsc_mst_fairness_vars vars[MAX_PIPES]; struct amdgpu_dm_connector *aconnector; int count = 0; bool debugfs_overwrite = false; @@ -776,6 +771,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, params[count].timing = &stream->timing; params[count].sink = stream->sink; aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context; + params[count].aconnector = aconnector; params[count].port = aconnector->port; params[count].clock_force_enable = aconnector->dsc_settings.dsc_force_enable; if (params[count].clock_force_enable == DSC_CLK_FORCE_ENABLE) @@ -798,6 +794,7 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, } /* Try no compression */ for (i = 0; i < count; i++) { + vars[i].aconnector = params[i].aconnector; vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps); vars[i].dsc_enabled = false; vars[i].bpp_x16 = 0; @@ -851,7 +848,8 @@ static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, } bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state) + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars) { int i, j; struct dc_stream_state *stream; @@ -882,7 +880,7 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, return false; mutex_lock(&aconnector->mst_mgr.lock); - if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) { + if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link, vars)) { mutex_unlock(&aconnector->mst_mgr.lock); return false; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index b38bd68121ce..900d3f7a8498 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -39,8 +39,17 @@ void dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev); #if defined(CONFIG_DRM_AMD_DC_DCN) + +struct dsc_mst_fairness_vars { + int pbn; + bool dsc_enabled; + int bpp_x16; + struct amdgpu_dm_connector *aconnector; +}; + bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state, - struct dc_state *dc_state); + struct dc_state *dc_state, + struct dsc_mst_fairness_vars *vars); #endif #endif From 4e00a434a08e0654a4dd9347485d9ec85deee1ef Mon Sep 17 00:00:00 2001 From: Qingqing Zhuo Date: Fri, 27 Aug 2021 06:58:38 -0400 Subject: [PATCH 342/866] drm/amd/display: Fix unstable HPCP compliance on Chrome Barcelo [Why] Intermittently, there presents two occurrences of 0 stream commits in a single HPD event. Current HDCP sequence does not consider such scenerio, and will thus disable HDCP. [How] Add condition check to include stream remove and re-enable case for HDCP enable. Reviewed-by: Bhawanpreet Lakha Acked-by: Mikita Lipski Signed-off-by: Qingqing Zhuo Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 22 +++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index deb8010efc69..5975233dfa77 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8067,8 +8067,26 @@ static bool is_content_protection_different(struct drm_connector_state *state, state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED) state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED; - /* Check if something is connected/enabled, otherwise we start hdcp but nothing is connected/enabled - * hot-plug, headless s3, dpms + /* Stream removed and re-enabled + * + * Can sometimes overlap with the HPD case, + * thus set update_hdcp to false to avoid + * setting HDCP multiple times. + * + * Handles: DESIRED -> DESIRED (Special case) + */ + if (!(old_state->crtc && old_state->crtc->enabled) && + state->crtc && state->crtc->enabled && + connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) { + dm_con_state->update_hdcp = false; + return true; + } + + /* Hot-plug, headless s3, dpms + * + * Only start HDCP if the display is connected/enabled. + * update_hdcp flag will be set to false until the next + * HPD comes in. * * Handles: DESIRED -> DESIRED (Special case) */ From 71ae30997a8f1791835167d3ceb8d1fab32407db Mon Sep 17 00:00:00 2001 From: Meenakshikumar Somasundaram Date: Mon, 30 Aug 2021 14:01:10 -0400 Subject: [PATCH 343/866] drm/amd/display: Link training retry fix for abort case [Why] If link training is aborted, it shall be retried if sink is present. [How] Check hpd status to find out whether sink is present or not. If sink is present, then link training shall be tried again with same settings. Otherwise, link training shall be aborted. Reviewed-by: Jimmy Kizito Acked-by: Mikita Lipski Signed-off-by: Meenakshikumar Somasundaram Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 330edd666b7d..ceda98a63ff3 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1840,9 +1840,13 @@ bool perform_link_training_with_retries( dp_disable_link_phy(link, signal); /* Abort link training if failure due to sink being unplugged. */ - if (status == LINK_TRAINING_ABORT) - break; - else if (do_fallback) { + if (status == LINK_TRAINING_ABORT) { + enum dc_connection_type type = dc_connection_none; + + dc_link_detect_sink(link, &type); + if (type == dc_connection_none) + break; + } else if (do_fallback) { decide_fallback_link_setting(*link_setting, ¤t_setting, status); /* Fail link training if reduced link bandwidth no longer meets * stream requirements. From fefc01f042f44ede373ee66773b8238dd8fdcb55 Mon Sep 17 00:00:00 2001 From: James Zhu Date: Tue, 7 Sep 2021 11:13:02 -0400 Subject: [PATCH 344/866] drm/amdkfd: separate kfd_iommu_resume from kfd_resume Separate kfd_iommu_resume from kfd_resume for fine-tuning of amdgpu device init/resume/reset/recovery sequence. v2: squash in fix for !CONFIG_HSA_AMD Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211277 Signed-off-by: James Zhu Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 6 ++++++ drivers/gpu/drm/amd/amdkfd/kfd_device.c | 12 ++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index ec028cf963f5..089c7b967008 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -327,6 +327,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, const struct kgd2kfd_shared_resources *gpu_resources); void kgd2kfd_device_exit(struct kfd_dev *kfd); void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm); +int kgd2kfd_resume_iommu(struct kfd_dev *kfd); int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm); int kgd2kfd_pre_reset(struct kfd_dev *kfd); int kgd2kfd_post_reset(struct kfd_dev *kfd); @@ -365,6 +366,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) { } +static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd) +{ + return 0; +} + static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) { return 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 30fde852af19..98d1b3ab3a46 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1069,17 +1069,21 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) return ret; } -static int kfd_resume(struct kfd_dev *kfd) +int kgd2kfd_resume_iommu(struct kfd_dev *kfd) { int err = 0; err = kfd_iommu_resume(kfd); - if (err) { + if (err) dev_err(kfd_device, "Failed to resume IOMMU for device %x:%x\n", kfd->pdev->vendor, kfd->pdev->device); - return err; - } + return err; +} + +static int kfd_resume(struct kfd_dev *kfd) +{ + int err = 0; err = kfd->dqm->ops.start(kfd->dqm); if (err) { From 8066008482e533e91934bee49765bf8b4a7c40db Mon Sep 17 00:00:00 2001 From: James Zhu Date: Tue, 7 Sep 2021 11:27:31 -0400 Subject: [PATCH 345/866] drm/amdgpu: add amdgpu_amdkfd_resume_iommu Add amdgpu_amdkfd_resume_iommu for amdgpu. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211277 Signed-off-by: James Zhu Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 10 ++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + 2 files changed, 11 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 3003ee1c9487..1d41c2c00623 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm) kgd2kfd_suspend(adev->kfd.dev, run_pm); } +int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev) +{ + int r = 0; + + if (adev->kfd.dev) + r = kgd2kfd_resume_iommu(adev->kfd.dev); + + return r; +} + int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm) { int r = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 089c7b967008..3bc52b2c604f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void); void amdgpu_amdkfd_fini(void); void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm); +int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev); int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm); void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev, const void *ih_ring_entry); From f02abeb0779700c308e661a412451b38962b8a0b Mon Sep 17 00:00:00 2001 From: James Zhu Date: Tue, 7 Sep 2021 11:32:22 -0400 Subject: [PATCH 346/866] drm/amdgpu: move iommu_resume before ip init/resume Separate iommu_resume from kfd_resume, and move it before other amdgpu ip init/resume. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211277 Signed-off-by: James Zhu Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 41c6b3aacd37..ab3794c42d36 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2394,6 +2394,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (r) goto init_failed; + r = amdgpu_amdkfd_resume_iommu(adev); + if (r) + goto init_failed; + r = amdgpu_device_ip_hw_init_phase1(adev); if (r) goto init_failed; @@ -3148,6 +3152,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev) { int r; + r = amdgpu_amdkfd_resume_iommu(adev); + if (r) + return r; + r = amdgpu_device_ip_resume_phase1(adev); if (r) return r; @@ -4601,6 +4609,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle, dev_warn(tmp_adev->dev, "asic atom init failed!"); } else { dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n"); + r = amdgpu_amdkfd_resume_iommu(tmp_adev); + if (r) + goto out; + r = amdgpu_device_ip_resume_phase1(tmp_adev); if (r) goto out; From 93def70cf8b23de5049d101b7dd5367864694bd3 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Mon, 13 Sep 2021 10:08:23 +0200 Subject: [PATCH 347/866] drm/radeon: pass drm dev radeon_agp_head_init directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pass drm dev directly as rdev->ddev gets initialized later on at radeon_device_init(). Bug: https://bugzilla.kernel.org/show_bug.cgi?id=214375 Signed-off-by: Nirmoy Das Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 0473583dcdac..482fb0ae6cb5 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -119,7 +119,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) #endif if (pci_find_capability(pdev, PCI_CAP_ID_AGP)) - rdev->agp = radeon_agp_head_init(rdev->ddev); + rdev->agp = radeon_agp_head_init(dev); if (rdev->agp) { rdev->agp->agp_mtrr = arch_phys_wc_add( rdev->agp->agp_info.aper_base, From 8b514e898ee7f861eb8863c647d258f71053af40 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 9 Sep 2021 11:01:00 +0800 Subject: [PATCH 348/866] drm/amd/pm: fix runpm hang when amdgpu loaded prior to sound driver Current RUNPM mechanism relies on PMFW to master the timing for BACO in/exit. And that needs cooperation from sound driver for dstate change notification for function 1(audio). Otherwise(on sound driver missing), BACO cannot be kicked in correctly and hang will be observed on RUNPM exit. By switching back to legacy message way on sound driver missing, we are able to fix the runpm hang observed for the scenario below: amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded Signed-off-by: Evan Quan Reported-and-tested-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Lijo Lazar Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- .../gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 24 +++++++++++++++++-- .../amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 4 ++-- drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c | 21 ++++++++++++++++ drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h | 2 ++ 4 files changed, 47 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index aec7cb21cc0f..b1ad451af06b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2274,7 +2274,27 @@ static int navi10_baco_enter(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->in_runpm) + /* + * This aims the case below: + * amdgpu driver loaded -> runpm suspend kicked -> sound driver loaded + * + * For NAVI10 and later ASICs, we rely on PMFW to handle the runpm. To + * make that possible, PMFW needs to acknowledge the dstate transition + * process for both gfx(function 0) and audio(function 1) function of + * the ASIC. + * + * The PCI device's initial runpm status is RUNPM_SUSPENDED. So as the + * device representing the audio function of the ASIC. And that means + * even if the sound driver(snd_hda_intel) was not loaded yet, it's still + * possible runpm suspend kicked on the ASIC. However without the dstate + * transition notification from audio function, pmfw cannot handle the + * BACO in/exit correctly. And that will cause driver hang on runpm + * resuming. + * + * To address this, we revert to legacy message way(driver masters the + * timing for BACO in/exit) on sound driver missing. + */ + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO); else return smu_v11_0_baco_enter(smu); @@ -2284,7 +2304,7 @@ static int navi10_baco_exit(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->in_runpm) { + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { /* Wait for PMFW handling for the Dstate change */ msleep(10); return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index d7519688065f..ca57221e3962 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2189,7 +2189,7 @@ static int sienna_cichlid_baco_enter(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->in_runpm) + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO); else return smu_v11_0_baco_enter(smu); @@ -2199,7 +2199,7 @@ static int sienna_cichlid_baco_exit(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->in_runpm) { + if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { /* Wait for PMFW handling for the Dstate change */ msleep(10); return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 66711ab24c15..843d2cbfc71d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -1053,3 +1053,24 @@ int smu_cmn_set_mp1_state(struct smu_context *smu, return ret; } + +bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev) +{ + struct pci_dev *p = NULL; + bool snd_driver_loaded; + + /* + * If the ASIC comes with no audio function, we always assume + * it is "enabled". + */ + p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus), + adev->pdev->bus->number, 1); + if (!p) + return true; + + snd_driver_loaded = pci_is_enabled(p) ? true : false; + + pci_dev_put(p); + + return snd_driver_loaded; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index 4054d9493e77..beea03810bca 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -123,5 +123,7 @@ static inline void smu_cmn_get_sysfs_buf(char **buf, int *offset) *buf -= *offset; } +bool smu_cmn_is_audio_func_enabled(struct amdgpu_device *adev); + #endif #endif From 114518ff3b30a3f0611f384fb58e0a968fdf7f5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Thu, 9 Sep 2021 18:56:28 +0200 Subject: [PATCH 349/866] drm/amdgpu: Drop inline from amdgpu_ras_eeprom_max_record_count MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This was unusual; normally, inline functions are declared static as well, and defined in a header file if used by multiple compilation units. The latter would be more involved in this case, so just drop the inline declaration for now. Fixes compile failure building for ppc64le on RHEL 8: In file included from ../drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h:32, from ../drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:33: ../drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c: In function ‘amdgpu_ras_recovery_init’: ../drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h:90:17: error: inlining failed in call to ‘always_inline’ ‘amdgpu_ras_eeprom_max_record_count’: function body not available 90 | inline uint32_t amdgpu_ras_eeprom_max_record_count(void); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:1985:34: note: called from here 1985 | max_eeprom_records_len = amdgpu_ras_eeprom_max_record_count(); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fixes: c84d46707ebb "drm/amdgpu: validate bad page threshold in ras(v3)" Reviewed-by: Lyude Paul Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index dc44c946a244..98732518543e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -757,7 +757,7 @@ Out: return res; } -inline uint32_t amdgpu_ras_eeprom_max_record_count(void) +uint32_t amdgpu_ras_eeprom_max_record_count(void) { return RAS_MAX_RECORD_COUNT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h index f95fc61b3021..6bb00578bfbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h @@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control, int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control, struct eeprom_table_record *records, const u32 num); -inline uint32_t amdgpu_ras_eeprom_max_record_count(void); +uint32_t amdgpu_ras_eeprom_max_record_count(void); void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control); From b287e4946873d706f94d95bdb2bf099dc8902181 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Mon, 13 Sep 2021 10:34:11 +0200 Subject: [PATCH 350/866] drm/amdgpu: Demote TMZ unsupported log message from warning to info As the user cannot do anything about the unsupported Trusted Memory Zone (TMZ) feature, do not warn about it, but make it informational, so demote the log level from warning to info. Signed-off-by: Paul Menzel Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index c7797eac83c3..9ff600a38559 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) break; default: adev->gmc.tmz_enabled = false; - dev_warn(adev->dev, + dev_info(adev->dev, "Trusted Memory Zone (TMZ) feature not supported\n"); break; } From cd51a57eb59fd56f3fe7ce9cadef444451bcf804 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Fri, 10 Sep 2021 15:37:41 +0000 Subject: [PATCH 351/866] amd/display: enable panel orientation quirks This patch allows panel orientation quirks from DRM core to be used. They attach a DRM connector property "panel orientation" which indicates in which direction the panel has been mounted. Some machines have the internal screen mounted with a rotation. Since the panel orientation quirks need the native mode from the EDID, check for it in amdgpu_dm_connector_ddc_get_modes. Signed-off-by: Simon Ser Cc: Alex Deucher Cc: Harry Wentland Cc: Nicholas Kazlauskas Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 5975233dfa77..00b10879baf7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7528,6 +7528,32 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder, } } +static void amdgpu_set_panel_orientation(struct drm_connector *connector) +{ + struct drm_encoder *encoder; + struct amdgpu_encoder *amdgpu_encoder; + const struct drm_display_mode *native_mode; + + if (connector->connector_type != DRM_MODE_CONNECTOR_eDP && + connector->connector_type != DRM_MODE_CONNECTOR_LVDS) + return; + + encoder = amdgpu_dm_connector_to_encoder(connector); + if (!encoder) + return; + + amdgpu_encoder = to_amdgpu_encoder(encoder); + + native_mode = &amdgpu_encoder->native_mode; + if (native_mode->hdisplay == 0 || native_mode->vdisplay == 0) + return; + + drm_connector_set_panel_orientation_with_quirk(connector, + DRM_MODE_PANEL_ORIENTATION_UNKNOWN, + native_mode->hdisplay, + native_mode->vdisplay); +} + static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector, struct edid *edid) { @@ -7556,6 +7582,8 @@ static void amdgpu_dm_connector_ddc_get_modes(struct drm_connector *connector, * restored here. */ amdgpu_dm_update_freesync_caps(connector, edid); + + amdgpu_set_panel_orientation(connector); } else { amdgpu_dm_connector->num_modes = 0; } From a70939851f9ced298dc7d523374b8c4d05239caf Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Mon, 13 Sep 2021 14:56:44 -0400 Subject: [PATCH 352/866] drm/amd/display: Fix white screen page fault for gpuvm [Why] The "base_addr_is_mc_addr" field was added for dcn3.1 support but pa_config was never updated to set it to false. Uninitialized memory causes it to be set to true which results in address mistranslation and white screen. [How] Use memset to ensure all fields are initialized to 0 by default. Fixes: 64b1d0e8d500 ("drm/amd/display: Add DCN3.1 HWSEQ") Signed-off-by: Nicholas Kazlauskas Acked-by: Alex Deucher Acked-by: Aaron Liu Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 00b10879baf7..66c799f5c7cf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -998,6 +998,8 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ uint32_t agp_base, agp_bot, agp_top; PHYSICAL_ADDRESS_LOC page_table_start, page_table_end, page_table_base; + memset(pa_config, 0, sizeof(*pa_config)); + logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); From 92554cbe0a36494f6dd760bc25ce5e5cdc60fc47 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 14 Sep 2021 10:50:47 -0400 Subject: [PATCH 353/866] drm/amdgpu/display: add a proper license to dc_link_dp.c Was missing. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/core/dc_link_dp.c | 24 ++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index ceda98a63ff3..f6dbc5a74757 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1,4 +1,26 @@ -/* Copyright 2015 Advanced Micro Devices, Inc. */ +/* + * Copyright 2015 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + */ #include "dm_services.h" #include "dc.h" #include "dc_link_dp.h" From e22e509c1cd90b48ae31099905418de74515e56f Mon Sep 17 00:00:00 2001 From: Alim Akhtar Date: Wed, 15 Sep 2021 20:18:44 +0900 Subject: [PATCH 354/866] dt-bindings: ufs: Add bindings for Samsung ufs host This patch adds DT bindings for Samsung ufs hci Signed-off-by: Alim Akhtar Signed-off-by: Chanho Park Link: https://lore.kernel.org/r/20210915111844.42752-1-chanho61.park@samsung.com Signed-off-by: Rob Herring --- .../bindings/ufs/samsung,exynos-ufs.yaml | 89 +++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml diff --git a/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml new file mode 100644 index 000000000000..b9ca8ef4f2be --- /dev/null +++ b/Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml @@ -0,0 +1,89 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ufs/samsung,exynos-ufs.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Samsung SoC series UFS host controller Device Tree Bindings + +maintainers: + - Alim Akhtar + +description: | + Each Samsung UFS host controller instance should have its own node. + This binding define Samsung specific binding other then what is used + in the common ufshcd bindings + [1] Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt + +properties: + + compatible: + enum: + - samsung,exynos7-ufs + + reg: + items: + - description: HCI register + - description: vendor specific register + - description: unipro register + - description: UFS protector register + + reg-names: + items: + - const: hci + - const: vs_hci + - const: unipro + - const: ufsp + + clocks: + items: + - description: ufs link core clock + - description: unipro main clock + + clock-names: + items: + - const: core_clk + - const: sclk_unipro_main + + interrupts: + maxItems: 1 + + phys: + maxItems: 1 + + phy-names: + const: ufs-phy + +required: + - compatible + - reg + - interrupts + - phys + - phy-names + - clocks + - clock-names + +additionalProperties: false + +examples: + - | + #include + #include + + ufs: ufs@15570000 { + compatible = "samsung,exynos7-ufs"; + reg = <0x15570000 0x100>, + <0x15570100 0x100>, + <0x15571000 0x200>, + <0x15572000 0x300>; + reg-names = "hci", "vs_hci", "unipro", "ufsp"; + interrupts = ; + clocks = <&clock_fsys1 ACLK_UFS20_LINK>, + <&clock_fsys1 SCLK_UFSUNIPRO20_USER>; + clock-names = "core_clk", "sclk_unipro_main"; + pinctrl-names = "default"; + pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>; + phys = <&ufs_phy>; + phy-names = "ufs-phy"; + }; +... From 71eabafac1eb67d590d4500eaf38177537ea6d4a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 17 Aug 2021 05:01:51 +0300 Subject: [PATCH 355/866] drm/tegra: dc: Remove unused variables Remove unused variables from tegra_crtc_update_memory_bandwidth(). Fixes: 04d5d5df9df7 ("drm/tegra: dc: Support memory bandwidth management") Reported-by: kernel test robot Signed-off-by: Dmitry Osipenko Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/dc.c | 3 --- drivers/gpu/drm/tegra/dc.h | 6 ------ 2 files changed, 9 deletions(-) diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 16c7aabb94d3..a29d64f87563 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1845,7 +1845,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, bool prepare_bandwidth_transition) { const struct tegra_plane_state *old_tegra_state, *new_tegra_state; - const struct tegra_dc_state *old_dc_state, *new_dc_state; u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw; const struct drm_plane_state *old_plane_state; const struct drm_crtc_state *old_crtc_state; @@ -1858,8 +1857,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, return; old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); - old_dc_state = to_const_dc_state(old_crtc_state); - new_dc_state = to_const_dc_state(crtc->state); if (!crtc->state->active) { if (!old_crtc_state->active) diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index f0cb691852a1..40378308d527 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -35,12 +35,6 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state) return NULL; } -static inline const struct tegra_dc_state * -to_const_dc_state(const struct drm_crtc_state *state) -{ - return to_dc_state((struct drm_crtc_state *)state); -} - struct tegra_dc_stats { unsigned long frames; unsigned long vblank; From 8a44924e1400d75db5c6fdaf199038580df4f79f Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 17 Aug 2021 05:01:52 +0300 Subject: [PATCH 356/866] drm/tegra: uapi: Fix wrong mapping end address in case of disabled IOMMU All jobs are failing on Tegra20 because it doesn't use IOMMU and mapping function uses size of mapping that is zero instead of BO size, fix it. Fixes: d7c591bc1a3f ("drm/tegra: Implement new UAPI") Signed-off-by: Dmitry Osipenko Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/uapi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index dc16a24f4dbe..690a339c52ec 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -222,7 +222,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f mapping->iova = sg_dma_address(mapping->sgt->sgl); } - mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size; + mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size; err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX), GFP_KERNEL); From a81cf839a064af27349b857fe347e97dd98c12a0 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 17 Aug 2021 05:01:53 +0300 Subject: [PATCH 357/866] gpu/host1x: fence: Make spinlock static The DEFINE_SPINLOCK macro creates a global spinlock symbol that is visible to the whole kernel. This is unintended in the code, fix it. Fixes: 687db2207b1b ("gpu: host1x: Add DMA fence implementation") Signed-off-by: Dmitry Osipenko Reviewed-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/host1x/fence.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index 6941add95d0f..e49083b0b09e 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -15,7 +15,7 @@ #include "intr.h" #include "syncpt.h" -DEFINE_SPINLOCK(lock); +static DEFINE_SPINLOCK(lock); struct host1x_syncpt_fence { struct dma_fence base; From c3dbfb9c49eef7d07904e5fd5e158dd6688bbab3 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 2 Sep 2021 22:33:09 +0200 Subject: [PATCH 358/866] gpu: host1x: Plug potential memory leak The memory allocated for a DMA fence could be leaked if the code failed to allocate the waiter object. Make sure to release the fence allocation on failure. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Thierry Reding --- drivers/gpu/host1x/fence.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index e49083b0b09e..ecab72882192 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -152,8 +152,10 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) return ERR_PTR(-ENOMEM); fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL); - if (!fence->waiter) + if (!fence->waiter) { + kfree(fence); return ERR_PTR(-ENOMEM); + } fence->sp = sp; fence->threshold = threshold; From e35ac9d0b56e9efefaeeb84b635ea26c2839ea86 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 9 Sep 2021 17:53:56 +0100 Subject: [PATCH 359/866] arm64/sve: Use correct size when reinitialising SVE state When we need a buffer for SVE register state we call sve_alloc() to make sure that one is there. In order to avoid repeated allocations and frees we keep the buffer around unless we change vector length and just memset() it to ensure a clean register state. The function that deals with this takes the task to operate on as an argument, however in the case where we do a memset() we initialise using the SVE state size for the current task rather than the task passed as an argument. This is only an issue in the case where we are setting the register state for a task via ptrace and the task being configured has a different vector length to the task tracing it. In the case where the buffer is larger in the traced process we will leak old state from the traced process to itself, in the case where the buffer is smaller in the traced process we will overflow the buffer and corrupt memory. Fixes: bc0ee4760364 ("arm64/sve: Core task context handling") Cc: # 4.15.x Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20210909165356.10675-1-broonie@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 5a294f20e9de..ff4962750b3d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -513,7 +513,7 @@ size_t sve_state_size(struct task_struct const *task) void sve_alloc(struct task_struct *task) { if (task->thread.sve_state) { - memset(task->thread.sve_state, 0, sve_state_size(current)); + memset(task->thread.sve_state, 0, sve_state_size(task)); return; } From 861dc4f52e6992c933998fb4dd03fefe1fa5ce27 Mon Sep 17 00:00:00 2001 From: Lv Ruyi Date: Wed, 1 Sep 2021 18:11:26 -0700 Subject: [PATCH 360/866] arm64/kernel: remove duplicate include in process.c Remove all but the first include of linux/sched.h from process.c Reported-by: Zeal Robot Signed-off-by: Lv Ruyi Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20210902011126.29828-1-lv.ruyi@zte.com.cn Signed-off-by: Catalin Marinas --- arch/arm64/kernel/process.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 19100fe8f7e4..1a1213cca173 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include From 9fcb2e93f41c07a400885325e7dbdfceba6efaec Mon Sep 17 00:00:00 2001 From: Dan Li Date: Tue, 14 Sep 2021 17:44:02 +0800 Subject: [PATCH 361/866] arm64: Mark __stack_chk_guard as __ro_after_init __stack_chk_guard is setup once while init stage and never changed after that. Although the modification of this variable at runtime will usually cause the kernel to crash (so does the attacker), it should be marked as __ro_after_init, and it should not affect performance if it is placed in the ro_after_init section. Signed-off-by: Dan Li Acked-by: Mark Rutland Link: https://lore.kernel.org/r/1631612642-102881-1-git-send-email-ashimida@linux.alibaba.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 1a1213cca173..40adb8cdbf5a 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -57,7 +57,7 @@ #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include -unsigned long __stack_chk_guard __read_mostly; +unsigned long __stack_chk_guard __ro_after_init; EXPORT_SYMBOL(__stack_chk_guard); #endif From db71f8fb44956714249a526647c143bac5bb96a1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 16 Sep 2021 11:14:47 -0700 Subject: [PATCH 362/866] 3com 3c515: make it compile on 64-bit architectures This driver isn't enabled most places because of the ISA config dependency, but alpha still has it. And I think the 'Jensen' actually did have an ISA slot. However, it doesn't build cleanly, because the "Vortex bus master" code just casts the skb->data pointer to 'int': outl((int) (skb->data), ioaddr + Wn7_MasterAddr); which is all kinds of broken. Even on a good old traditional PC/AT it would be broken because the high bits will be random kernel address bits, but presumably the hardware ignores those bits. I mean, it's ISA. We're talking 16MB dma limits. The "good old days". Make the build happy with this kind of craziness by using the proper isa_virt_to_bus() handling that the full bus master code uses anyway (the Vortex bus mastering is a limited special case). Who knows, this might even work. Reported-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/net/ethernet/3com/3c515.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 8d90fed5d33e..6f0ea2facea9 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -1050,7 +1050,7 @@ static netdev_tx_t corkscrew_start_xmit(struct sk_buff *skb, #ifdef VORTEX_BUS_MASTER if (vp->bus_master) { /* Set the bus-master controller to transfer the packet. */ - outl((int) (skb->data), ioaddr + Wn7_MasterAddr); + outl(isa_virt_to_bus(skb->data), ioaddr + Wn7_MasterAddr); outw((skb->len + 3) & ~3, ioaddr + Wn7_MasterLen); vp->tx_skb = skb; outw(StartDMADown, ioaddr + EL3_CMD); From 35a3f4ef0ab543daa1725b0c963eb8c05e3376f8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 8 Sep 2021 22:00:33 -0700 Subject: [PATCH 363/866] alpha: Declare virt_to_phys and virt_to_bus parameter as pointer to volatile Some drivers pass a pointer to volatile data to virt_to_bus() and virt_to_phys(), and that works fine. One exception is alpha. This results in a number of compile errors such as drivers/net/wan/lmc/lmc_main.c: In function 'lmc_softreset': drivers/net/wan/lmc/lmc_main.c:1782:50: error: passing argument 1 of 'virt_to_bus' discards 'volatile' qualifier from pointer target type drivers/atm/ambassador.c: In function 'do_loader_command': drivers/atm/ambassador.c:1747:58: error: passing argument 1 of 'virt_to_bus' discards 'volatile' qualifier from pointer target type Declare the parameter of virt_to_phys and virt_to_bus as pointer to volatile to fix the problem. Signed-off-by: Guenter Roeck Acked-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/io.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h index 0fab5ac90775..c9cb554fbe54 100644 --- a/arch/alpha/include/asm/io.h +++ b/arch/alpha/include/asm/io.h @@ -60,7 +60,7 @@ extern inline void set_hae(unsigned long new_hae) * Change virtual addresses to physical addresses and vv. */ #ifdef USE_48_BIT_KSEG -static inline unsigned long virt_to_phys(void *address) +static inline unsigned long virt_to_phys(volatile void *address) { return (unsigned long)address - IDENT_ADDR; } @@ -70,7 +70,7 @@ static inline void * phys_to_virt(unsigned long address) return (void *) (address + IDENT_ADDR); } #else -static inline unsigned long virt_to_phys(void *address) +static inline unsigned long virt_to_phys(volatile void *address) { unsigned long phys = (unsigned long)address; @@ -106,7 +106,7 @@ static inline void * phys_to_virt(unsigned long address) extern unsigned long __direct_map_base; extern unsigned long __direct_map_size; -static inline unsigned long __deprecated virt_to_bus(void *address) +static inline unsigned long __deprecated virt_to_bus(volatile void *address) { unsigned long phys = virt_to_phys(address); unsigned long bus = phys + __direct_map_base; From b60cee5bae733f49ba33840804c159a8e474cfda Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 9 Sep 2021 11:47:14 -0700 Subject: [PATCH 364/866] cpufreq: vexpress: Drop unused variable arm:allmodconfig fails to build with the following error. drivers/cpufreq/vexpress-spc-cpufreq.c:454:13: error: unused variable 'cur_cluster' Remove the unused variable. Fixes: bb8c26d9387f ("cpufreq: vexpress: Set CPUFREQ_IS_COOLING_DEV flag") Cc: Viresh Kumar Signed-off-by: Guenter Roeck Reviewed-by: Kees Cook Signed-off-by: Linus Torvalds --- drivers/cpufreq/vexpress-spc-cpufreq.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c index 284b6bd040b1..d295f405c4bb 100644 --- a/drivers/cpufreq/vexpress-spc-cpufreq.c +++ b/drivers/cpufreq/vexpress-spc-cpufreq.c @@ -451,7 +451,6 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy) static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy) { struct device *cpu_dev; - int cur_cluster = cpu_to_cluster(policy->cpu); cpu_dev = get_cpu_device(policy->cpu); if (!cpu_dev) { From 39a71f712d8a13728febd8f3cb3f6db7e1fa7221 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 15 Sep 2021 15:28:06 -0600 Subject: [PATCH 365/866] selftests:kvm: fix get_warnings_count() ignoring fscanf() return warn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix get_warnings_count() to check fscanf() return value to get rid of the following warning: x86_64/mmio_warning_test.c: In function ‘get_warnings_count’: x86_64/mmio_warning_test.c:85:2: warning: ignoring return value of ‘fscanf’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 85 | fscanf(f, "%d", &warnings); | ^~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Shuah Khan Acked-by: Paolo Bonzini Signed-off-by: Shuah Khan --- tools/testing/selftests/kvm/x86_64/mmio_warning_test.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index e6480fd5c4bd..8039e1eff938 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -82,7 +82,8 @@ int get_warnings_count(void) FILE *f; f = popen("dmesg | grep \"WARNING:\" | wc -l", "r"); - fscanf(f, "%d", &warnings); + if (fscanf(f, "%d", &warnings) < 1) + warnings = 0; fclose(f); return warnings; From 3a4f0cc693cd3d80e66a255f0bff0e2c0461eef1 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 15 Sep 2021 15:28:07 -0600 Subject: [PATCH 366/866] selftests:kvm: fix get_trans_hugepagesz() ignoring fscanf() return warn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix get_trans_hugepagesz() to check fscanf() return value to get rid of the following warning: lib/test_util.c: In function ‘get_trans_hugepagesz’: lib/test_util.c:138:2: warning: ignoring return value of ‘fscanf’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 138 | fscanf(f, "%ld", &size); | ^~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Shuah Khan Acked-by: Paolo Bonzini Signed-off-by: Shuah Khan --- tools/testing/selftests/kvm/lib/test_util.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index af1031fed97f..938cd423643e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -129,13 +129,16 @@ size_t get_trans_hugepagesz(void) { size_t size; FILE *f; + int ret; TEST_ASSERT(thp_configured(), "THP is not configured in host kernel"); f = fopen("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", "r"); TEST_ASSERT(f != NULL, "Error in opening transparent_hugepage/hpage_pmd_size"); - fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + ret = fscanf(f, "%ld", &size); + TEST_ASSERT(ret < 1, "Error reading transparent_hugepage/hpage_pmd_size"); fclose(f); return size; From 20175d5eac5bb94a7a3719ef275337fc9abf26ac Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 15 Sep 2021 15:28:08 -0600 Subject: [PATCH 367/866] selftests: kvm: move get_run_delay() into lib/test_util get_run_delay() is defined static in xen_shinfo_test and steal_time test. Move it to lib and remove code duplication. Signed-off-by: Shuah Khan Acked-by: Paolo Bonzini Signed-off-by: Shuah Khan --- tools/testing/selftests/kvm/include/test_util.h | 1 + tools/testing/selftests/kvm/lib/test_util.c | 15 +++++++++++++++ tools/testing/selftests/kvm/steal_time.c | 15 --------------- .../selftests/kvm/x86_64/xen_shinfo_test.c | 15 --------------- 4 files changed, 16 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d79be15dd3d2..c7409b9b4e5b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -102,6 +102,7 @@ const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); void backing_src_help(void); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); +long get_run_delay(void); /* * Whether or not the given source type is shared memory (as opposed to diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 938cd423643e..f80dd38a38b2 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "linux/kernel.h" @@ -303,3 +304,17 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) TEST_FAIL("Unknown backing src type: %s", type_name); return -1; } + +long get_run_delay(void) +{ + char path[64]; + long val[2]; + FILE *fp; + + sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); + fp = fopen(path, "r"); + fscanf(fp, "%ld %ld ", &val[0], &val[1]); + fclose(fp); + + return val[1]; +} diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index ecec30865a74..51fe95a5c36a 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include @@ -217,20 +216,6 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpuid) #endif -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static void *do_steal_time(void *arg) { struct timespec ts, stop; diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 117bf49a3d79..eda0d2a51224 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,7 +14,6 @@ #include #include #include -#include #define VCPU_ID 5 @@ -98,20 +97,6 @@ static void guest_code(void) GUEST_DONE(); } -static long get_run_delay(void) -{ - char path[64]; - long val[2]; - FILE *fp; - - sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); - fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); - fclose(fp); - - return val[1]; -} - static int cmp_timespec(struct timespec *a, struct timespec *b) { if (a->tv_sec > b->tv_sec) From f5013d412a43662b63f3d5f3a804d63213acd471 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 15 Sep 2021 15:28:09 -0600 Subject: [PATCH 368/866] selftests: kvm: fix get_run_delay() ignoring fscanf() return warn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix get_run_delay() to check fscanf() return value to get rid of the following warning. When fscanf() fails return MIN_RUN_DELAY_NS from get_run_delay(). Move MIN_RUN_DELAY_NS from steal_time.c to test_util.h so get_run_delay() and steal_time.c can use it. lib/test_util.c: In function ‘get_run_delay’: lib/test_util.c:316:2: warning: ignoring return value of ‘fscanf’ declared with attribute ‘warn_unused_result’ [-Wunused-result] 316 | fscanf(fp, "%ld %ld ", &val[0], &val[1]); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Shuah Khan Acked-by: Paolo Bonzini Signed-off-by: Shuah Khan --- tools/testing/selftests/kvm/include/test_util.h | 2 ++ tools/testing/selftests/kvm/lib/test_util.c | 4 +++- tools/testing/selftests/kvm/steal_time.c | 1 - 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index c7409b9b4e5b..451fed5ce8e7 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -95,6 +95,8 @@ struct vm_mem_backing_src_alias { uint32_t flag; }; +#define MIN_RUN_DELAY_NS 200000UL + bool thp_configured(void); size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index f80dd38a38b2..a9107bfae402 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -313,7 +313,9 @@ long get_run_delay(void) sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid)); fp = fopen(path, "r"); - fscanf(fp, "%ld %ld ", &val[0], &val[1]); + /* Return MIN_RUN_DELAY_NS upon failure just to be safe */ + if (fscanf(fp, "%ld %ld ", &val[0], &val[1]) < 2) + val[1] = MIN_RUN_DELAY_NS; fclose(fp); return val[1]; diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 51fe95a5c36a..2172d65b85e4 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -19,7 +19,6 @@ #define NR_VCPUS 4 #define ST_GPA_BASE (1 << 30) -#define MIN_RUN_DELAY_NS 200000UL static void *st_gva[NR_VCPUS]; static uint64_t guest_stolen_time[NR_VCPUS]; From 040b8907ccf1c78d020aca29800036565d761d73 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 Apr 2020 23:31:24 +0200 Subject: [PATCH 369/866] drm/rockchip: cdn-dp-core: Make cdn_dp_core_resume __maybe_unused With the new static annotation, the compiler warns when the functions are actually unused: drivers/gpu/drm/rockchip/cdn-dp-core.c:1123:12: error: 'cdn_dp_resume' defined but not used [-Werror=unused-function] 1123 | static int cdn_dp_resume(struct device *dev) | ^~~~~~~~~~~~~ Mark them __maybe_unused to suppress that warning as well. [ Not so 'new' static annotations any more, and I removed the part of the patch that added __maybe_unused to cdn_dp_suspend(), because it's used by the shutdown/remove code. So only the resume function ends up possibly unused if CONFIG_PM isn't set - Linus ] Fixes: 7c49abb4c2f8 ("drm/rockchip: cdn-dp-core: Make cdn_dp_core_suspend/resume static") Signed-off-by: Arnd Bergmann Reviewed-by: Enric Balletbo i Serra Signed-off-by: Linus Torvalds --- drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index 8ab3247dbc4a..13c6b857158f 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -1123,7 +1123,7 @@ static int cdn_dp_suspend(struct device *dev) return ret; } -static int cdn_dp_resume(struct device *dev) +static __maybe_unused int cdn_dp_resume(struct device *dev) { struct cdn_dp_device *dp = dev_get_drvdata(dev); From 3c0d2a46c0141913dc6fd126c57d0615677d946e Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 8 Sep 2021 20:57:43 -0700 Subject: [PATCH 370/866] net: 6pack: Fix tx timeout and slot time tx timeout and slot time are currently specified in units of HZ. On Alpha, HZ is defined as 1024. When building alpha:allmodconfig, this results in the following error message. drivers/net/hamradio/6pack.c: In function 'sixpack_open': drivers/net/hamradio/6pack.c:71:41: error: unsigned conversion from 'int' to 'unsigned char' changes value from '256' to '0' In the 6PACK protocol, tx timeout is specified in units of 10 ms and transmitted over the wire: https://www.linux-ax25.org/wiki/6PACK Defining a value dependent on HZ doesn't really make sense, and presumably comes from the (very historical) situation where HZ was originally 100. Note that the SIXP_SLOTTIME use explicitly is about 10ms granularity: mod_timer(&sp->tx_t, jiffies + ((when + 1) * HZ) / 100); and the SIXP_TXDELAY walue is sent as a byte over the wire. Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/net/hamradio/6pack.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 8fe8887d506a..6192244b304a 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -68,9 +68,9 @@ #define SIXP_DAMA_OFF 0 /* default level 2 parameters */ -#define SIXP_TXDELAY (HZ/4) /* in 1 s */ +#define SIXP_TXDELAY 25 /* 250 ms */ #define SIXP_PERSIST 50 /* in 256ths */ -#define SIXP_SLOTTIME (HZ/10) /* in 1 s */ +#define SIXP_SLOTTIME 10 /* 100 ms */ #define SIXP_INIT_RESYNC_TIMEOUT (3*HZ/2) /* in 1 s */ #define SIXP_RESYNC_TIMEOUT 5*HZ /* in 1 s */ From e6fab7af6ba1bc77c78713a83876f60ca7a4a064 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Thu, 16 Sep 2021 21:31:51 +0300 Subject: [PATCH 371/866] hwmon: (mlxreg-fan) Return non-zero value when fan current state is enforced from sysfs Fan speed minimum can be enforced from sysfs. For example, setting current fan speed to 20 is used to enforce fan speed to be at 100% speed, 19 - to be not below 90% speed, etcetera. This feature provides ability to limit fan speed according to some system wise considerations, like absence of some replaceable units or high system ambient temperature. Request for changing fan minimum speed is configuration request and can be set only through 'sysfs' write procedure. In this situation value of argument 'state' is above nominal fan speed maximum. Return non-zero code in this case to avoid thermal_cooling_device_stats_update() call, because in this case statistics update violates thermal statistics table range. The issues is observed in case kernel is configured with option CONFIG_THERMAL_STATISTICS. Here is the trace from KASAN: [ 159.506659] BUG: KASAN: slab-out-of-bounds in thermal_cooling_device_stats_update+0x7d/0xb0 [ 159.516016] Read of size 4 at addr ffff888116163840 by task hw-management.s/7444 [ 159.545625] Call Trace: [ 159.548366] dump_stack+0x92/0xc1 [ 159.552084] ? thermal_cooling_device_stats_update+0x7d/0xb0 [ 159.635869] thermal_zone_device_update+0x345/0x780 [ 159.688711] thermal_zone_device_set_mode+0x7d/0xc0 [ 159.694174] mlxsw_thermal_modules_init+0x48f/0x590 [mlxsw_core] [ 159.700972] ? mlxsw_thermal_set_cur_state+0x5a0/0x5a0 [mlxsw_core] [ 159.731827] mlxsw_thermal_init+0x763/0x880 [mlxsw_core] [ 160.070233] RIP: 0033:0x7fd995909970 [ 160.074239] Code: 73 01 c3 48 8b 0d 28 d5 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 99 2d 2c 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff .. [ 160.095242] RSP: 002b:00007fff54f5d938 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 160.103722] RAX: ffffffffffffffda RBX: 0000000000000013 RCX: 00007fd995909970 [ 160.111710] RDX: 0000000000000013 RSI: 0000000001906008 RDI: 0000000000000001 [ 160.119699] RBP: 0000000001906008 R08: 00007fd995bc9760 R09: 00007fd996210700 [ 160.127687] R10: 0000000000000073 R11: 0000000000000246 R12: 0000000000000013 [ 160.135673] R13: 0000000000000001 R14: 00007fd995bc8600 R15: 0000000000000013 [ 160.143671] [ 160.145338] Allocated by task 2924: [ 160.149242] kasan_save_stack+0x19/0x40 [ 160.153541] __kasan_kmalloc+0x7f/0xa0 [ 160.157743] __kmalloc+0x1a2/0x2b0 [ 160.161552] thermal_cooling_device_setup_sysfs+0xf9/0x1a0 [ 160.167687] __thermal_cooling_device_register+0x1b5/0x500 [ 160.173833] devm_thermal_of_cooling_device_register+0x60/0xa0 [ 160.180356] mlxreg_fan_probe+0x474/0x5e0 [mlxreg_fan] [ 160.248140] [ 160.249807] The buggy address belongs to the object at ffff888116163400 [ 160.249807] which belongs to the cache kmalloc-1k of size 1024 [ 160.263814] The buggy address is located 64 bytes to the right of [ 160.263814] 1024-byte region [ffff888116163400, ffff888116163800) [ 160.277536] The buggy address belongs to the page: [ 160.282898] page:0000000012275840 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888116167000 pfn:0x116160 [ 160.294872] head:0000000012275840 order:3 compound_mapcount:0 compound_pincount:0 [ 160.303251] flags: 0x200000000010200(slab|head|node=0|zone=2) [ 160.309694] raw: 0200000000010200 ffffea00046f7208 ffffea0004928208 ffff88810004dbc0 [ 160.318367] raw: ffff888116167000 00000000000a0006 00000001ffffffff 0000000000000000 [ 160.327033] page dumped because: kasan: bad access detected [ 160.333270] [ 160.334937] Memory state around the buggy address: [ 160.356469] >ffff888116163800: fc .. Fixes: 65afb4c8e7e4 ("hwmon: (mlxreg-fan) Add support for Mellanox FAN driver") Signed-off-by: Vadim Pasternak Link: https://lore.kernel.org/r/20210916183151.869427-1-vadimp@nvidia.com Signed-off-by: Guenter Roeck --- drivers/hwmon/mlxreg-fan.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index 116681fde33d..89fe7b9fe26b 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -315,8 +315,8 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, { struct mlxreg_fan *fan = cdev->devdata; unsigned long cur_state; + int i, config = 0; u32 regval; - int i; int err; /* @@ -329,6 +329,12 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, * overwritten. */ if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) { + /* + * This is configuration change, which is only supported through sysfs. + * For configuration non-zero value is to be returned to avoid thermal + * statistics update. + */ + config = 1; state -= MLXREG_FAN_MAX_STATE; for (i = 0; i < state; i++) fan->cooling_levels[i] = state; @@ -343,7 +349,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval); if (state < cur_state) - return 0; + return config; state = cur_state; } @@ -359,7 +365,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, dev_err(fan->dev, "Failed to write PWM duty\n"); return err; } - return 0; + return config; } static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = { From 129803e642ac3d828b3c73ff10f570c42d962ef8 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Wed, 25 Aug 2021 09:41:22 +0200 Subject: [PATCH 372/866] pinctrl: core: Remove duplicated word from devm_pinctrl_unregister() Remove duplicated "which" from devm_pinctrl_unregister() kernel doc description. Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/8b75e5dfd9363f35ebdd7812e119757379678f97.1629877281.git.michal.simek@xilinx.com Signed-off-by: Linus Walleij --- drivers/pinctrl/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index a4ac87c8b4f8..5082102d7d0d 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2306,7 +2306,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_register_and_init); /** * devm_pinctrl_unregister() - Resource managed version of pinctrl_unregister(). - * @dev: device for which which resource was allocated + * @dev: device for which resource was allocated * @pctldev: the pinctrl device to unregister. */ void devm_pinctrl_unregister(struct device *dev, struct pinctrl_dev *pctldev) From e9a9970bf520c99e530d8f1fa5b5c22671fad4ef Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 16 Sep 2021 14:07:33 -0700 Subject: [PATCH 373/866] fpga: dfl: Avoid reads to AFU CSRs during enumeration CSR address space for Accelerator Functional Units (AFU) is not available during the early Device Feature List (DFL) enumeration. Early access to this space results in invalid data and port errors. This change adds a condition to prevent an early read from the AFU CSR space. Fixes: 1604986c3e6b ("fpga: dfl: expose feature revision from struct dfl_device") Cc: stable@vger.kernel.org Signed-off-by: Russ Weight Signed-off-by: Moritz Fischer --- drivers/fpga/dfl.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index c99b78ee008a..f86666cf2c6a 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -1019,16 +1019,18 @@ create_feature_instance(struct build_feature_devs_info *binfo, { unsigned int irq_base, nr_irqs; struct dfl_feature_info *finfo; + u8 revision = 0; int ret; - u8 revision; u64 v; - v = readq(binfo->ioaddr + ofst); - revision = FIELD_GET(DFH_REVISION, v); + if (fid != FEATURE_ID_AFU) { + v = readq(binfo->ioaddr + ofst); + revision = FIELD_GET(DFH_REVISION, v); - /* read feature size and id if inputs are invalid */ - size = size ? size : feature_size(v); - fid = fid ? fid : feature_id(v); + /* read feature size and id if inputs are invalid */ + size = size ? size : feature_size(v); + fid = fid ? fid : feature_id(v); + } if (binfo->len - ofst < size) return -EINVAL; From 7e6f8d6f4a42ef9b693ff1b49267c546931d4619 Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Tue, 31 Aug 2021 17:36:12 +0530 Subject: [PATCH 374/866] pinctrl: amd: Add irq field data pinctrl_amd use gpiochip_get_data() to get their local state containers back from the gpiochip passed as amd_gpio chip data. Hence added irq field data to get directly using amd_gpio chip data. Signed-off-by: Basavaraj Natikar Tested-by: Mario Limonciello Acked-by: Shyam Sundar S K Link: https://lore.kernel.org/r/20210831120613.1514899-2-Basavaraj.Natikar@amd.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 9 ++++----- drivers/pinctrl/pinctrl-amd.h | 1 + 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index c001f2ed20f8..8292bd5c13f3 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -902,7 +902,6 @@ static struct pinctrl_desc amd_pinctrl_desc = { static int amd_gpio_probe(struct platform_device *pdev) { int ret = 0; - int irq_base; struct resource *res; struct amd_gpio *gpio_dev; struct gpio_irq_chip *girq; @@ -925,9 +924,9 @@ static int amd_gpio_probe(struct platform_device *pdev) if (!gpio_dev->base) return -ENOMEM; - irq_base = platform_get_irq(pdev, 0); - if (irq_base < 0) - return irq_base; + gpio_dev->irq = platform_get_irq(pdev, 0); + if (gpio_dev->irq < 0) + return gpio_dev->irq; #ifdef CONFIG_PM_SLEEP gpio_dev->saved_regs = devm_kcalloc(&pdev->dev, amd_pinctrl_desc.npins, @@ -987,7 +986,7 @@ static int amd_gpio_probe(struct platform_device *pdev) goto out2; } - ret = devm_request_irq(&pdev->dev, irq_base, amd_gpio_irq_handler, + ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler, IRQF_SHARED, KBUILD_MODNAME, gpio_dev); if (ret) goto out2; diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 95e763424042..1d4317073654 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -98,6 +98,7 @@ struct amd_gpio { struct resource *res; struct platform_device *pdev; u32 *saved_regs; + int irq; }; /* KERNCZ configuration*/ From acd47b9f28e55b505aedb842131b40904e151d7c Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Tue, 31 Aug 2021 17:36:13 +0530 Subject: [PATCH 375/866] pinctrl: amd: Handle wake-up interrupt Enable/disable power management wakeup mode, which is disabled by default. enable_irq_wake enables wakes the system from sleep. Hence added enable/disable irq_wake to handle wake-up interrupt. Signed-off-by: Basavaraj Natikar Tested-by: Mario Limonciello Acked-by: Shyam Sundar S K Link: https://lore.kernel.org/r/20210831120613.1514899-3-Basavaraj.Natikar@amd.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 8292bd5c13f3..8d0f88e9ca88 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -445,6 +445,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); + int err; raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); @@ -457,6 +458,15 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) writel(pin_reg, gpio_dev->base + (d->hwirq)*4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); + if (on) + err = enable_irq_wake(gpio_dev->irq); + else + err = disable_irq_wake(gpio_dev->irq); + + if (err) + dev_err(&gpio_dev->pdev->dev, "failed to %s wake-up interrupt\n", + on ? "enable" : "disable"); + return 0; } From d36a97736b2cc9b13db0dfdf6f32b115ec193614 Mon Sep 17 00:00:00 2001 From: David Collins Date: Thu, 16 Sep 2021 18:51:37 +0530 Subject: [PATCH 376/866] pinctrl: qcom: spmi-gpio: correct parent irqspec translation pmic_gpio_child_to_parent_hwirq() and gpiochip_populate_parent_fwspec_fourcell() translate a pinctrl- spmi-gpio irqspec to an SPMI controller irqspec. When they do this, they use a fixed SPMI slave ID of 0 and a fixed GPIO peripheral offset of 0xC0 (corresponding to SPMI address 0xC000). This translation results in an incorrect irqspec for secondary PMICs that don't have a slave ID of 0 as well as for PMIC chips which have GPIO peripherals located at a base address other than 0xC000. Correct this issue by passing the slave ID of the pinctrl-spmi- gpio device's parent in the SPMI controller irqspec and by calculating the peripheral ID base from the device tree 'reg' property of the pinctrl-spmi-gpio device. Signed-off-by: David Collins Signed-off-by: satya priya Fixes: ca69e2d165eb ("qcom: spmi-gpio: add support for hierarchical IRQ chip") Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1631798498-10864-2-git-send-email-skakit@codeaurora.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 37 ++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 98bf0e2a2a8d..b2562e893139 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved. + * Copyright (c) 2012-2014, 2016-2021 The Linux Foundation. All rights reserved. */ #include @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -171,6 +172,8 @@ struct pmic_gpio_state { struct pinctrl_dev *ctrl; struct gpio_chip chip; struct irq_chip irq; + u8 usid; + u8 pid_base; }; static const struct pinconf_generic_params pmic_gpio_bindings[] = { @@ -949,12 +952,36 @@ static int pmic_gpio_child_to_parent_hwirq(struct gpio_chip *chip, unsigned int *parent_hwirq, unsigned int *parent_type) { - *parent_hwirq = child_hwirq + 0xc0; + struct pmic_gpio_state *state = gpiochip_get_data(chip); + + *parent_hwirq = child_hwirq + state->pid_base; *parent_type = child_type; return 0; } +static void *pmic_gpio_populate_parent_fwspec(struct gpio_chip *chip, + unsigned int parent_hwirq, + unsigned int parent_type) +{ + struct pmic_gpio_state *state = gpiochip_get_data(chip); + struct irq_fwspec *fwspec; + + fwspec = kzalloc(sizeof(*fwspec), GFP_KERNEL); + if (!fwspec) + return NULL; + + fwspec->fwnode = chip->irq.parent_domain->fwnode; + + fwspec->param_count = 4; + fwspec->param[0] = state->usid; + fwspec->param[1] = parent_hwirq; + /* param[2] must be left as 0 */ + fwspec->param[3] = parent_type; + + return fwspec; +} + static int pmic_gpio_probe(struct platform_device *pdev) { struct irq_domain *parent_domain; @@ -965,6 +992,7 @@ static int pmic_gpio_probe(struct platform_device *pdev) struct pmic_gpio_pad *pad, *pads; struct pmic_gpio_state *state; struct gpio_irq_chip *girq; + const struct spmi_device *parent_spmi_dev; int ret, npins, i; u32 reg; @@ -984,6 +1012,9 @@ static int pmic_gpio_probe(struct platform_device *pdev) state->dev = &pdev->dev; state->map = dev_get_regmap(dev->parent, NULL); + parent_spmi_dev = to_spmi_device(dev->parent); + state->usid = parent_spmi_dev->usid; + state->pid_base = reg >> 8; pindesc = devm_kcalloc(dev, npins, sizeof(*pindesc), GFP_KERNEL); if (!pindesc) @@ -1059,7 +1090,7 @@ static int pmic_gpio_probe(struct platform_device *pdev) girq->fwnode = of_node_to_fwnode(state->dev->of_node); girq->parent_domain = parent_domain; girq->child_to_parent_hwirq = pmic_gpio_child_to_parent_hwirq; - girq->populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_fourcell; + girq->populate_parent_alloc_arg = pmic_gpio_populate_parent_fwspec; girq->child_offset_to_irq = pmic_gpio_child_offset_to_irq; girq->child_irq_domain_ops.translate = pmic_gpio_domain_translate; From a11de92523f75a8140cf8eea3ce9b628f7a3cc77 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 16 Sep 2021 11:55:01 +0200 Subject: [PATCH 377/866] dt-bindings: net: dsa: sja1105: update nxp,sja1105.yaml reference Changeset 62568bdbe6f6 ("dt-bindings: net: dsa: sja1105: convert to YAML schema") renamed: Documentation/devicetree/bindings/net/dsa/sja1105.txt to: Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml. Update its cross-reference accordingly. Fixes: 62568bdbe6f6 ("dt-bindings: net: dsa: sja1105: convert to YAML schema") Reviewed-by: Vladimir Oltean Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/994ce6c6358746ff600459822b9f6e336db933c9.1631785820.git.mchehab+huawei@kernel.org --- Documentation/networking/dsa/sja1105.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index 564caeebe2b2..29b1bae0cf00 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -296,7 +296,7 @@ not available. Device Tree bindings and board design ===================================== -This section references ``Documentation/devicetree/bindings/net/dsa/sja1105.txt`` +This section references ``Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml`` and aims to showcase some potential switch caveats. RMII PHY role and out-of-band signaling From c8087adc8865c76500dbc072a46b61d35f6c908b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 16 Sep 2021 11:55:02 +0200 Subject: [PATCH 378/866] dt-bindings: arm: mediatek: mmsys: update mediatek,mmsys.yaml reference Changeset cba3c40d1f97 ("dt-bindings: arm: mediatek: mmsys: convert to YAML format") renamed: Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.txt to: Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml. Update its cross-reference accordingly. Fixes: cba3c40d1f97 ("dt-bindings: arm: mediatek: mmsys: convert to YAML format") Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/a87eb079a73e8ab41cdf6e40e80b1d1f868da6bd.1631785820.git.mchehab+huawei@kernel.org --- .../devicetree/bindings/display/mediatek/mediatek,disp.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt index fbb59c9ddda6..78044c340e20 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt @@ -9,7 +9,7 @@ function block. All DISP device tree nodes must be siblings to the central MMSYS_CONFIG node. For a description of the MMSYS_CONFIG binding, see -Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.txt. +Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml. DISP function blocks ==================== From e8f69b16ee776da88589b5271e3f46020efc8f6c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 12:12:04 +0200 Subject: [PATCH 379/866] net: hso: fix muxed tty registration If resource allocation and registration fail for a muxed tty device (e.g. if there are no more minor numbers) the driver should not try to deregister the never-registered (or already-deregistered) tty. Fix up the error handling to avoid dereferencing a NULL pointer when attempting to remove the character device. Fixes: 72dc1c096c70 ("HSO: add option hso driver") Cc: stable@vger.kernel.org # 2.6.27 Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/usb/hso.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index a57251ba5991..f97813a4e8d1 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2719,14 +2719,14 @@ struct hso_device *hso_create_mux_serial_device(struct usb_interface *interface, serial = kzalloc(sizeof(*serial), GFP_KERNEL); if (!serial) - goto exit; + goto err_free_dev; hso_dev->port_data.dev_serial = serial; serial->parent = hso_dev; if (hso_serial_common_create (serial, 1, CTRL_URB_RX_SIZE, CTRL_URB_TX_SIZE)) - goto exit; + goto err_free_serial; serial->tx_data_length--; serial->write_data = hso_mux_serial_write_data; @@ -2742,11 +2742,9 @@ struct hso_device *hso_create_mux_serial_device(struct usb_interface *interface, /* done, return it */ return hso_dev; -exit: - if (serial) { - tty_unregister_device(tty_drv, serial->minor); - kfree(serial); - } +err_free_serial: + kfree(serial); +err_free_dev: kfree(hso_dev); return NULL; From 23ca067b3295d935835b71f743235f9e5ab31cc5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 1 Sep 2021 10:44:03 +0200 Subject: [PATCH 380/866] mm: Fully initialize invalidate_lock, amend lock class later The function __init_rwsem() is not part of the official API, it just a helper function used by init_rwsem(). Changing the lock's class and name should be done by using lockdep_set_class_and_name() after the has been fully initialized. The overhead of the additional class struct and setting it twice is negligible and it works across all locks. Fully initialize the lock with init_rwsem() and then set the custom class and name for the lock. Fixes: 730633f0b7f95 ("mm: Protect operations adding pages to page cache with invalidate_lock") Link: https://lore.kernel.org/r/20210901084403.g4fezi23cixemlhh@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jan Kara --- fs/inode.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 37710ca863b5..ed0cab8a32db 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -190,8 +190,10 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; mapping->writeback_index = 0; - __init_rwsem(&mapping->invalidate_lock, "mapping.invalidate_lock", - &sb->s_type->invalidate_lock_key); + init_rwsem(&mapping->invalidate_lock); + lockdep_set_class_and_name(&mapping->invalidate_lock, + &sb->s_type->invalidate_lock_key, + "mapping.invalidate_lock"); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ From 3abe2eec87059260bf31033a8863c67c5d45b9d0 Mon Sep 17 00:00:00 2001 From: Trevor Wu Date: Fri, 17 Sep 2021 16:28:05 +0800 Subject: [PATCH 381/866] ASoC: mediatek: mt8195: remove wrong fixup assignment on HDMITX S24_LE params fixup is only required for DPTX. Remove fixup ops assignment for HDMITX. Fixes: 40d605df0a7b ("ASoC: mediatek: mt8195: add machine driver with mt6359, rt1019 and rt5682") Signed-off-by: Trevor Wu Link: https://lore.kernel.org/r/20210917082805.30898-1-trevor.wu@mediatek.com Signed-off-by: Mark Brown --- sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c b/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c index c97ace7387b4..de09f67c0450 100644 --- a/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c +++ b/sound/soc/mediatek/mt8195/mt8195-mt6359-rt1019-rt5682.c @@ -424,8 +424,8 @@ static int mt8195_hdmi_codec_init(struct snd_soc_pcm_runtime *rtd) return snd_soc_component_set_jack(cmpnt_codec, &priv->hdmi_jack, NULL); } -static int mt8195_hdmitx_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, - struct snd_pcm_hw_params *params) +static int mt8195_dptx_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, + struct snd_pcm_hw_params *params) { /* fix BE i2s format to 32bit, clean param mask first */ @@ -902,7 +902,7 @@ static struct snd_soc_dai_link mt8195_mt6359_rt1019_rt5682_dai_links[] = { .no_pcm = 1, .dpcm_playback = 1, .ops = &mt8195_dptx_ops, - .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup, + .be_hw_params_fixup = mt8195_dptx_hw_params_fixup, SND_SOC_DAILINK_REG(DPTX_BE), }, [DAI_LINK_ETDM1_IN_BE] = { @@ -953,7 +953,6 @@ static struct snd_soc_dai_link mt8195_mt6359_rt1019_rt5682_dai_links[] = { SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS, .dpcm_playback = 1, - .be_hw_params_fixup = mt8195_hdmitx_dptx_hw_params_fixup, SND_SOC_DAILINK_REG(ETDM3_OUT_BE), }, [DAI_LINK_PCM1_BE] = { From cfacfefd382af3b42905108b54f02820dca225c4 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 17 Sep 2021 11:51:08 +0300 Subject: [PATCH 382/866] ASoC: SOF: trace: Omit error print when waking up trace sleepers Do not print error message from snd_sof_trace_notify_for_error() when possible sleeping trace work is woken up to flush the remaining debug information. This action by itself is not an error, it is just an action we take when an error occurs to make sure that all information have been fed to the userspace (if we have trace in use). Signed-off-by: Peter Ujfalusi Reviewed-by: Ranjani Sridharan Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20210917085108.25532-1-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/trace.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/sof/trace.c b/sound/soc/sof/trace.c index f72a6e83e6af..58f6ca5cf491 100644 --- a/sound/soc/sof/trace.c +++ b/sound/soc/sof/trace.c @@ -530,7 +530,6 @@ void snd_sof_trace_notify_for_error(struct snd_sof_dev *sdev) return; if (sdev->dtrace_is_enabled) { - dev_err(sdev->dev, "error: waking up any trace sleepers\n"); sdev->dtrace_error = true; wake_up(&sdev->trace_sleep); } From dc9660590d106bb58d145233fffca4efadad3655 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 16 Sep 2021 16:41:02 +0200 Subject: [PATCH 383/866] regulator: max14577: Revert "regulator: max14577: Add proper module aliases strings" This reverts commit 0da6736ecd10b45e535b100acd58df2db4c099d8. The MODULE_DEVICE_TABLE already creates proper alias. Having another MODULE_ALIAS causes the alias to be duplicated: $ modinfo max14577-regulator.ko alias: platform:max77836-regulator alias: platform:max14577-regulator description: Maxim 14577/77836 regulator driver alias: platform:max77836-regulator alias: platform:max14577-regulator Cc: Marek Szyprowski Fixes: 0da6736ecd10 ("regulator: max14577: Add proper module aliases strings") Signed-off-by: Krzysztof Kozlowski Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/20210916144102.120980-1-krzysztof.kozlowski@canonical.com Signed-off-by: Mark Brown --- drivers/regulator/max14577-regulator.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c index 1d78b455cc48..e34face736f4 100644 --- a/drivers/regulator/max14577-regulator.c +++ b/drivers/regulator/max14577-regulator.c @@ -269,5 +269,3 @@ module_exit(max14577_regulator_exit); MODULE_AUTHOR("Krzysztof Kozlowski "); MODULE_DESCRIPTION("Maxim 14577/77836 regulator driver"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:max14577-regulator"); -MODULE_ALIAS("platform:max77836-regulator"); From 3c9cfb5269f76d447dbadb67835368f3111a91d7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 14:17:35 +0300 Subject: [PATCH 384/866] net: update NXP copyright text NXP Legal insists that the following are not fine: - Saying "NXP Semiconductors" instead of "NXP", since the company's registered name is "NXP" - Putting a "(c)" sign in the copyright string - Putting a comma in the copyright string The only accepted copyright string format is "Copyright NXP". This patch changes the copyright headers in the networking files that were sent by me, or derived from code sent by me. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 2 +- drivers/net/dsa/ocelot/felix.h | 2 +- drivers/net/dsa/ocelot/felix_vsc9959.c | 2 +- drivers/net/dsa/sja1105/sja1105_clocking.c | 2 +- drivers/net/dsa/sja1105/sja1105_devlink.c | 2 +- drivers/net/dsa/sja1105/sja1105_flower.c | 2 +- drivers/net/dsa/sja1105/sja1105_mdio.c | 2 +- drivers/net/dsa/sja1105/sja1105_spi.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.h | 2 +- drivers/net/dsa/sja1105/sja1105_vl.c | 2 +- drivers/net/dsa/sja1105/sja1105_vl.h | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.h | 2 +- drivers/net/ethernet/mscc/ocelot_devlink.c | 2 +- drivers/net/ethernet/mscc/ocelot_mrp.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/pcs/pcs-xpcs-nxp.c | 2 +- include/linux/dsa/ocelot.h | 2 +- include/linux/packing.h | 2 +- lib/packing.c | 2 +- net/dsa/tag_ocelot.c | 2 +- net/dsa/tag_ocelot_8021q.c | 2 +- tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 2 +- 24 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3656e67af789..a3a9636430d6 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019-2021 NXP Semiconductors +/* Copyright 2019-2021 NXP * * This is an umbrella module for all network switches that are * register-compatible with Ocelot and that perform I/O to their host CPU diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 5854bab43327..54024b6f9498 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #ifndef _MSCC_FELIX_H #define _MSCC_FELIX_H diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index f966a253d1c7..9e2ac8e46619 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Copyright 2017 Microsemi Corporation - * Copyright 2018-2019 NXP Semiconductors + * Copyright 2018-2019 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 387a1f2f161c..5bbf1707f2af 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 05c7f4ca3b1a..0569ff066634 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018-2019, Vladimir Oltean - * Copyright 2020 NXP Semiconductors + * Copyright 2020 NXP */ #include "sja1105.h" diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c index 6c10ffa968ce..72b9b39b0989 100644 --- a/drivers/net/dsa/sja1105/sja1105_flower.c +++ b/drivers/net/dsa/sja1105/sja1105_flower.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include "sja1105.h" #include "sja1105_vl.h" diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 705d3900e43a..215dd17ca790 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021, NXP Semiconductors +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index d60a530d0272..d3c9ad6d39d4 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH * Copyright (c) 2018-2019, Vladimir Oltean */ diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 7a422ef4deb6..baba204ad62f 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include "sja1105_static_config.h" diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index bce0f5c03d0b..6a372d5f22ae 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause */ -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _SJA1105_STATIC_CONFIG_H diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index ec7b65daec20..6802f4057cc0 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_vl.h b/drivers/net/dsa/sja1105/sja1105_vl.h index 173d78963fed..51fba0dce91a 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.h +++ b/drivers/net/dsa/sja1105/sja1105_vl.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #ifndef _SJA1105_VL_H #define _SJA1105_VL_H diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c index ee1468e3eaa3..91f02c505028 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP * * The Integrated Endpoint Register Block (IERB) is configured by pre-boot * software and is supposed to be to ENETC what a NVRAM is to a 'real' PCIe diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h index b3b774e0998a..c2ce47c4be9f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ -/* Copyright 2021 NXP Semiconductors */ +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/ethernet/mscc/ocelot_devlink.c b/drivers/net/ethernet/mscc/ocelot_devlink.c index edafbd37d12c..b8737efd2a85 100644 --- a/drivers/net/ethernet/mscc/ocelot_devlink.c +++ b/drivers/net/ethernet/mscc/ocelot_devlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP */ #include #include "ocelot.h" diff --git a/drivers/net/ethernet/mscc/ocelot_mrp.c b/drivers/net/ethernet/mscc/ocelot_mrp.c index 08b481a93460..4b0941f09f71 100644 --- a/drivers/net/ethernet/mscc/ocelot_mrp.c +++ b/drivers/net/ethernet/mscc/ocelot_mrp.c @@ -2,7 +2,7 @@ /* Microsemi Ocelot Switch driver * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index c0c465a4a981..e54b9fb2a97a 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -5,7 +5,7 @@ * mscc_ocelot_switch_lib. * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c index 984c9f7f16a8..d16fc58cd48d 100644 --- a/drivers/net/pcs/pcs-xpcs-nxp.c +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP */ #include #include "pcs-xpcs.h" diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index c6bc45ae5e03..435777a0073c 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 - * Copyright 2019-2021 NXP Semiconductors + * Copyright 2019-2021 NXP */ #ifndef _NET_DSA_TAG_OCELOT_H diff --git a/include/linux/packing.h b/include/linux/packing.h index 54667735cc67..8d6571feb95d 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause - * Copyright (c) 2016-2018, NXP Semiconductors + * Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _LINUX_PACKING_H diff --git a/lib/packing.c b/lib/packing.c index 6ed72dccfdb5..9a72f4bbf0e2 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index d37ab98e7fe1..8025ed778d33 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #include #include diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 3038a257ba05..59072930cb02 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP * * An implementation of the software-defined tag_8021q.c tagger format, which * also preserves full functionality under a vlan_filtering bridge. It does diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..f7d84549cc3e 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Copyright 2020 NXP Semiconductors +# Copyright 2020 NXP WAIT_TIME=1 NUM_NETIFS=4 From 02319bf15acf54004216e40ac9c171437f24be24 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Sep 2021 14:33:35 -0700 Subject: [PATCH 385/866] net: dsa: bcm_sf2: Fix array overrun in bcm_sf2_num_active_ports() After d12e1c464988 ("net: dsa: b53: Set correct number of ports in the DSA struct") we stopped setting dsa_switch::num_ports to DSA_MAX_PORTS, which created an off by one error between the statically allocated bcm_sf2_priv::port_sts array (of size DSA_MAX_PORTS). When dsa_is_cpu_port() is used, we end-up accessing an out of bounds member and causing a NPD. Fix this by iterating with the appropriate port count using ds->num_ports. Fixes: d12e1c464988 ("net: dsa: b53: Set correct number of ports in the DSA struct") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 6ce9ec1283e0..b6c4b3adb171 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -68,7 +68,7 @@ static unsigned int bcm_sf2_num_active_ports(struct dsa_switch *ds) struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); unsigned int port, count = 0; - for (port = 0; port < ARRAY_SIZE(priv->port_sts); port++) { + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_cpu_port(ds, port)) continue; if (priv->port_sts[port].enabled) From a9b3043de47b7f8cbe38c36aee572526665b6315 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Sun, 12 Sep 2021 11:56:26 +0900 Subject: [PATCH 386/866] ksmbd: transport_rdma: Don't include rwlock.h directly rwlock.h specifically asks to not be included directly. In fact, the proper spinlock.h include isn't needed either, it comes with the huge pile that kthread.h ends up pulling in, so just drop it entirely. Signed-off-by: Mike Galbraith Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/transport_rdma.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 52b2556e76b1..3a7fa23ba850 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -20,7 +20,6 @@ #define SUBMOD_NAME "smb_direct" #include -#include #include #include #include From 89c485c7a3ecbc2ebd568f9c9c2edf3a8cf7485b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 16 Sep 2021 17:24:54 -0400 Subject: [PATCH 387/866] NLM: Fix svcxdr_encode_owner() Dai Ngo reports that, since the XDR overhaul, the NLM server crashes when the TEST procedure wants to return NLM_DENIED. There is a bug in svcxdr_encode_owner() that none of our standard test cases found. Replace the open-coded function with a call to an appropriate pre-fabricated XDR helper. Reported-by: Dai Ngo Fixes: a6a63ca5652e ("lockd: Common NLM XDR helpers") Signed-off-by: Chuck Lever --- fs/lockd/svcxdr.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/fs/lockd/svcxdr.h b/fs/lockd/svcxdr.h index c69a0bb76c94..4f1a451da5ba 100644 --- a/fs/lockd/svcxdr.h +++ b/fs/lockd/svcxdr.h @@ -134,18 +134,9 @@ svcxdr_decode_owner(struct xdr_stream *xdr, struct xdr_netobj *obj) static inline bool svcxdr_encode_owner(struct xdr_stream *xdr, const struct xdr_netobj *obj) { - unsigned int quadlen = XDR_QUADLEN(obj->len); - __be32 *p; - - if (xdr_stream_encode_u32(xdr, obj->len) < 0) + if (obj->len > XDR_MAX_NETOBJ) return false; - p = xdr_reserve_space(xdr, obj->len); - if (!p) - return false; - p[quadlen - 1] = 0; /* XDR pad */ - memcpy(p, obj->data, obj->len); - - return true; + return xdr_stream_encode_opaque(xdr, obj->data, obj->len) > 0; } #endif /* _LOCKD_SVCXDR_H_ */ From 02579b2ff8b0becfb51d85a975908ac4ab15fba8 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Thu, 16 Sep 2021 14:22:12 -0400 Subject: [PATCH 388/866] nfsd: back channel stuck in SEQ4_STATUS_CB_PATH_DOWN When the back channel enters SEQ4_STATUS_CB_PATH_DOWN state, the client recovers by sending BIND_CONN_TO_SESSION but the server fails to recover the back channel and leaves it as NFSD4_CB_DOWN. Fix by enhancing nfsd4_bind_conn_to_session to probe the back channel by calling nfsd4_probe_callback. Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever --- fs/nfsd/nfs4state.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4b6d60b46b0a..ba8bab17175e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3570,7 +3570,7 @@ static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_s } static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, - struct nfsd4_session *session, u32 req) + struct nfsd4_session *session, u32 req, struct nfsd4_conn **conn) { struct nfs4_client *clp = session->se_client; struct svc_xprt *xpt = rqst->rq_xprt; @@ -3593,6 +3593,8 @@ static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, else status = nfserr_inval; spin_unlock(&clp->cl_lock); + if (status == nfs_ok && conn) + *conn = c; return status; } @@ -3617,8 +3619,16 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(session->se_client, rqstp)) goto out; - status = nfsd4_match_existing_connection(rqstp, session, bcts->dir); - if (status == nfs_ok || status == nfserr_inval) + status = nfsd4_match_existing_connection(rqstp, session, + bcts->dir, &conn); + if (status == nfs_ok) { + if (bcts->dir == NFS4_CDFC4_FORE_OR_BOTH || + bcts->dir == NFS4_CDFC4_BACK) + conn->cn_flags |= NFS4_CDFC4_BACK; + nfsd4_probe_callback(session->se_client); + goto out; + } + if (status == nfserr_inval) goto out; status = nfsd4_map_bcts_dir(&bcts->dir); if (status) From bbc9a6eb5eec03dcafee266b19f56295e3b2aa8f Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 17 Aug 2021 07:55:40 +0800 Subject: [PATCH 389/866] btrfs: replace BUG_ON() in btrfs_csum_one_bio() with proper error handling There is a BUG_ON() in btrfs_csum_one_bio() to catch code logic error. It has indeed caught several bugs during subpage development. But the BUG_ON() itself will bring down the whole system which is an overkill. Replace it with a WARN() and exit gracefully, so that it won't crash the whole system while we can still catch the code logic error. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/file-item.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 2673c6ba7a4e..0b9401a5afd3 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -665,7 +665,18 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio, if (!ordered) { ordered = btrfs_lookup_ordered_extent(inode, offset); - BUG_ON(!ordered); /* Logic error */ + /* + * The bio range is not covered by any ordered extent, + * must be a code logic error. + */ + if (unlikely(!ordered)) { + WARN(1, KERN_WARNING + "no ordered extent for root %llu ino %llu offset %llu\n", + inode->root->root_key.objectid, + btrfs_ino(inode), offset); + kvfree(sums); + return BLK_STS_IOERR; + } } nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, From acbee9aff8aea4b9b66ab3d5cee6b8dbc153dc38 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 8 Sep 2021 16:29:26 +0100 Subject: [PATCH 390/866] btrfs: fix transaction handle leak after verity rollback failure During a verity rollback, if we fail to update the inode or delete the orphan, we abort the transaction and return without releasing our transaction handle. Fix that by releasing the handle. Fixes: 146054090b0859 ("btrfs: initial fsverity support") Fixes: 705242538ff348 ("btrfs: verity metadata orphan items") Reviewed-by: Boris Burkov Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/verity.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c index 28d443d3ef93..4968535dfff0 100644 --- a/fs/btrfs/verity.c +++ b/fs/btrfs/verity.c @@ -451,7 +451,7 @@ static int del_orphan(struct btrfs_trans_handle *trans, struct btrfs_inode *inod */ static int rollback_verity(struct btrfs_inode *inode) { - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; struct btrfs_root *root = inode->root; int ret; @@ -473,6 +473,7 @@ static int rollback_verity(struct btrfs_inode *inode) trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; btrfs_handle_fs_error(root->fs_info, ret, "failed to start transaction in verity rollback %llu", (u64)inode->vfs_inode.i_ino); @@ -490,8 +491,9 @@ static int rollback_verity(struct btrfs_inode *inode) btrfs_abort_transaction(trans, ret); goto out; } - btrfs_end_transaction(trans); out: + if (trans) + btrfs_end_transaction(trans); return ret; } From 6b225baababf1e3d41a4250e802cbd193e1343fb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 8 Sep 2021 19:05:44 +0100 Subject: [PATCH 391/866] btrfs: fix mount failure due to past and transient device flush error When we get an error flushing one device, during a super block commit, we record the error in the device structure, in the field 'last_flush_error'. This is used to later check if we should error out the super block commit, depending on whether the number of flush errors is greater than or equals to the maximum tolerated device failures for a raid profile. However if we get a transient device flush error, unmount the filesystem and later try to mount it, we can fail the mount because we treat that past error as critical and consider the device is missing. Even if it's very likely that the error will happen again, as it's probably due to a hardware related problem, there may be cases where the error might not happen again. One example is during testing, and a test case like the new generic/648 from fstests always triggers this. The test cases generic/019 and generic/475 also trigger this scenario, but very sporadically. When this happens we get an error like this: $ mount /dev/sdc /mnt mount: /mnt wrong fs type, bad option, bad superblock on /dev/sdc, missing codepage or helper program, or other error. $ dmesg (...) [12918.886926] BTRFS warning (device sdc): chunk 13631488 missing 1 devices, max tolerance is 0 for writable mount [12918.888293] BTRFS warning (device sdc): writable mount is not allowed due to too many missing devices [12918.890853] BTRFS error (device sdc): open_ctree failed The failure happens because when btrfs_check_rw_degradable() is called at mount time, or at remount from RO to RW time, is sees a non zero value in a device's ->last_flush_error attribute, and therefore considers that the device is 'missing'. Fix this by setting a device's ->last_flush_error to zero when we close a device, making sure the error is not seen on the next mount attempt. We only need to track flush errors during the current mount, so that we never commit a super block if such errors happened. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 464485aa7318..2ec3b8ac8fa3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1137,6 +1137,19 @@ static void btrfs_close_one_device(struct btrfs_device *device) atomic_set(&device->dev_stats_ccnt, 0); extent_io_tree_release(&device->alloc_state); + /* + * Reset the flush error record. We might have a transient flush error + * in this mount, and if so we aborted the current transaction and set + * the fs to an error state, guaranteeing no super blocks can be further + * committed. However that error might be transient and if we unmount the + * filesystem and mount it again, we should allow the mount to succeed + * (btrfs_check_rw_degradable() should not fail) - if after mounting the + * filesystem again we still get flush errors, then we will again abort + * any transaction and set the error state, guaranteeing no commits of + * unsafe super blocks. + */ + device->last_flush_error = 0; + /* Verify the device is back in a pristine state */ ASSERT(!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)); ASSERT(!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)); From 0619b7901473c380abc05d45cf9c70bee0707db3 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 16 Sep 2021 20:43:29 +0800 Subject: [PATCH 392/866] btrfs: prevent __btrfs_dump_space_info() to underflow its free space It's not uncommon where __btrfs_dump_space_info() gets called under over-commit situations. In that case free space would underflow as total allocated space is not enough to handle all the over-committed space. Such underflow values can sometimes cause confusion for users enabled enospc_debug mount option, and takes some seconds for developers to convert the underflow value to signed result. Just output the free space as s64 to avoid such problem. Reported-by: Eli V Link: https://lore.kernel.org/linux-btrfs/CAJtFHUSy4zgyhf-4d9T+KdJp9w=UgzC2A0V=VtmaeEpcGgm1-Q@mail.gmail.com/ CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Anand Jain Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/space-info.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 5ada02e0e629..aa5be0b24987 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -414,9 +414,10 @@ static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, { lockdep_assert_held(&info->lock); - btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull", + /* The free space could be negative in case of overcommit */ + btrfs_info(fs_info, "space_info %llu has %lld free, is %sfull", info->flags, - info->total_bytes - btrfs_space_info_used(info, true), + (s64)(info->total_bytes - btrfs_space_info_used(info, true)), info->full ? "" : "not "); btrfs_info(fs_info, "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu zone_unusable=%llu", From 31c8025fac3d8bbff7ce4602338d88efc2d7972c Mon Sep 17 00:00:00 2001 From: David Brazdil Date: Fri, 17 Sep 2021 14:14:23 +0100 Subject: [PATCH 393/866] of: restricted dma: Fix condition for rmem init of_dma_set_restricted_buffer fails to handle negative return values from of_property_count_elems_of_size, e.g. when the property does not exist. This results in an attempt to assign a non-existent reserved memory region to the device and a warning being printed. Fix the condition to take negative values into account. Fixes: f3cfd136aef0 ("of: restricted dma: Don't fail device probe on rmem init failure") Cc: Will Deacon Signed-off-by: David Brazdil Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210917131423.2760155-1-dbrazdil@google.com Signed-off-by: Rob Herring --- drivers/of/device.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 5b043ee30824..b0800c260f64 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -85,7 +85,11 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np) break; } - if (i != count && of_reserved_mem_device_init_by_idx(dev, of_node, i)) + /* + * Attempt to initialize a restricted-dma-pool region if one was found. + * Note that count can hold a negative error code. + */ + if (i < count && of_reserved_mem_device_init_by_idx(dev, of_node, i)) dev_warn(dev, "failed to initialise \"restricted-dma-pool\" memory node\n"); } From 55c21d57eafb7b379bb7b3e93baf9ca2695895b0 Mon Sep 17 00:00:00 2001 From: David Heidelberg Date: Sun, 12 Sep 2021 18:51:20 +0200 Subject: [PATCH 394/866] dt-bindings: arm: Fix Toradex compatible typo Fix board compatible typo reported by dtbs_check. Fixes: f4d1577e9bc6 ("dt-bindings: arm: Convert Tegra board/soc bindings to json-schema") Signed-off-by: David Heidelberg Link: https://lore.kernel.org/r/20210912165120.188490-1-david@ixit.cz Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/arm/tegra.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/arm/tegra.yaml b/Documentation/devicetree/bindings/arm/tegra.yaml index b962fa6d649c..d79d36ac0c44 100644 --- a/Documentation/devicetree/bindings/arm/tegra.yaml +++ b/Documentation/devicetree/bindings/arm/tegra.yaml @@ -54,7 +54,7 @@ properties: - const: toradex,apalis_t30 - const: nvidia,tegra30 - items: - - const: toradex,apalis_t30-eval-v1.1 + - const: toradex,apalis_t30-v1.1-eval - const: toradex,apalis_t30-eval - const: toradex,apalis_t30-v1.1 - const: toradex,apalis_t30 From e3fc065682ebbbd15b0ce0036800f4acbf765d46 Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Fri, 17 Sep 2021 18:14:26 +0000 Subject: [PATCH 395/866] cifs: Deferred close performance improvements During unlink/rename instead of closing all the deferred handles under tcon, close only handles under the requested dentry. Signed-off-by: Rohith Surabattula Signed-off-by: Steve French --- fs/cifs/cifsproto.h | 3 +++ fs/cifs/inode.c | 6 +++--- fs/cifs/misc.c | 37 +++++++++++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+), 3 deletions(-) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 54966c1a8eb6..d0f85b666662 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -267,6 +267,9 @@ extern void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode); extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon); +extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon, + const char *path); + extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx); extern void cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 19af2d0ec8d5..82848412ad85 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1624,7 +1624,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } - cifs_close_deferred_file(CIFS_I(inode)); + cifs_close_deferred_file_under_dentry(tcon, full_path); if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -2113,9 +2113,9 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_deferred_file(CIFS_I(d_inode(source_dentry))); + cifs_close_deferred_file_under_dentry(tcon, from_name); if (d_inode(target_dentry) != NULL) - cifs_close_deferred_file(CIFS_I(d_inode(target_dentry))); + cifs_close_deferred_file_under_dentry(tcon, to_name); rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index f4313935e734..05138f92d905 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -780,6 +780,43 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) kfree(tmp_list); } } +void +cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) +{ + struct cifsFileInfo *cfile; + struct list_head *tmp; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + void *page; + const char *full_path; + + INIT_LIST_HEAD(&file_head); + page = alloc_dentry_path(); + spin_lock(&tcon->open_file_lock); + list_for_each(tmp, &tcon->openFileList) { + cfile = list_entry(tmp, struct cifsFileInfo, tlist); + full_path = build_path_from_dentry(cfile->dentry, page); + if (strstr(full_path, path)) { + if (delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + break; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } + } + } + } + spin_unlock(&tcon->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } + free_dentry_path(page); +} /* parses DFS refferal V3 structure * caller is responsible for freeing target_nodes From 71826b068884050d5fdd37fda857ba1539c513d3 Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Fri, 17 Sep 2021 17:29:42 +0000 Subject: [PATCH 396/866] cifs: Fix soft lockup during fsstress Below traces are observed during fsstress and system got hung. [ 130.698396] watchdog: BUG: soft lockup - CPU#6 stuck for 26s! Cc: stable@vger.kernel.org # 5.13+ Signed-off-by: Rohith Surabattula Signed-off-by: Steve French --- fs/cifs/misc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 05138f92d905..03da00eb7c04 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -735,7 +735,7 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) if (cancel_delayed_work(&cfile->deferred)) { tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) - continue; + break; tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } @@ -766,7 +766,7 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) if (cancel_delayed_work(&cfile->deferred)) { tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) - continue; + break; tmp_list->cfile = cfile; list_add_tail(&tmp_list->list, &file_head); } From 35866f3f779aef5e7ba84e4d1023fe2e2a0e219e Mon Sep 17 00:00:00 2001 From: Rohith Surabattula Date: Fri, 17 Sep 2021 16:50:40 -0500 Subject: [PATCH 397/866] cifs: Not to defer close on file when lock is set Close file immediately when lock is set. Cc: stable@vger.kernel.org # 5.13+ Signed-off-by: Rohith Surabattula Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 1 + fs/cifs/file.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 7dd9878e26bf..e916470468ea 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1399,6 +1399,7 @@ struct cifsInodeInfo { #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ #define CIFS_INO_MODIFIED_ATTR (6) /* Indicate change in mtime/ctime */ +#define CIFS_INO_CLOSE_ON_LOCK (7) /* Not to defer the close when lock is set */ unsigned long flags; spinlock_t writers_lock; unsigned int writers; /* Number of writers on this inode */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 4d10c9343890..6796fc73b304 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -882,6 +882,7 @@ int cifs_close(struct inode *inode, struct file *file) dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); if ((cinode->oplock == CIFS_CACHE_RHW_FLG) && cinode->lease_granted && + !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { if (test_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { inode->i_ctime = inode->i_mtime = current_time(inode); @@ -1864,6 +1865,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag, tcon->ses->server); cifs_sb = CIFS_FILE_SB(file); + set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && From f58eae6c5fa882d6d0a6b7587a099602a59d57b5 Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Fri, 17 Sep 2021 22:14:08 +0900 Subject: [PATCH 398/866] ksmbd: prevent out of share access Because of .., files outside the share directory could be accessed. To prevent this, normalize the given path and remove all . and .. components. In addition to the usual large set of regression tests (smbtorture and xfstests), ran various tests on this to specifically check path name validation including libsmb2 tests to verify path normalization: ./examples/smb2-ls-async smb://172.30.1.15/homes2/../ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/../ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/../../ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/../ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/..bar/ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/bar../ ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/bar.. ./examples/smb2-ls-async smb://172.30.1.15/homes2/foo/bar../../../../ Signed-off-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/misc.c | 76 ++++++++++++++++++++++++++++++++++++++++------ fs/ksmbd/misc.h | 3 +- fs/ksmbd/smb2pdu.c | 14 ++++++--- 3 files changed, 77 insertions(+), 16 deletions(-) diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 0b307ca28a19..3eac3c01749f 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -191,19 +191,77 @@ int get_nlink(struct kstat *st) return nlink; } -void ksmbd_conv_path_to_unix(char *path) +char *ksmbd_conv_path_to_unix(char *path) { + size_t path_len, remain_path_len, out_path_len; + char *out_path, *out_next; + int i, pre_dotdot_cnt = 0, slash_cnt = 0; + bool is_last; + strreplace(path, '\\', '/'); -} + path_len = strlen(path); + remain_path_len = path_len; + if (path_len == 0) + return ERR_PTR(-EINVAL); -void ksmbd_strip_last_slash(char *path) -{ - int len = strlen(path); + out_path = kzalloc(path_len + 2, GFP_KERNEL); + if (!out_path) + return ERR_PTR(-ENOMEM); + out_path_len = 0; + out_next = out_path; - while (len && path[len - 1] == '/') { - path[len - 1] = '\0'; - len--; - } + do { + char *name = path + path_len - remain_path_len; + char *next = strchrnul(name, '/'); + size_t name_len = next - name; + + is_last = !next[0]; + if (name_len == 2 && name[0] == '.' && name[1] == '.') { + pre_dotdot_cnt++; + /* handle the case that path ends with "/.." */ + if (is_last) + goto follow_dotdot; + } else { + if (pre_dotdot_cnt) { +follow_dotdot: + slash_cnt = 0; + for (i = out_path_len - 1; i >= 0; i--) { + if (out_path[i] == '/' && + ++slash_cnt == pre_dotdot_cnt + 1) + break; + } + + if (i < 0 && + slash_cnt != pre_dotdot_cnt) { + kfree(out_path); + return ERR_PTR(-EINVAL); + } + + out_next = &out_path[i+1]; + *out_next = '\0'; + out_path_len = i + 1; + + } + + if (name_len != 0 && + !(name_len == 1 && name[0] == '.') && + !(name_len == 2 && name[0] == '.' && name[1] == '.')) { + next[0] = '\0'; + sprintf(out_next, "%s/", name); + out_next += name_len + 1; + out_path_len += name_len + 1; + next[0] = '/'; + } + pre_dotdot_cnt = 0; + } + + remain_path_len -= name_len + 1; + } while (!is_last); + + if (out_path_len > 0) + out_path[out_path_len-1] = '\0'; + path[path_len] = '\0'; + return out_path; } void ksmbd_conv_path_to_windows(char *path) diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index af8717d4d85b..b7b10139ada2 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -16,8 +16,7 @@ int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); char *convert_to_nt_pathname(char *filename, char *sharepath); int get_nlink(struct kstat *st); -void ksmbd_conv_path_to_unix(char *path); -void ksmbd_strip_last_slash(char *path); +char *ksmbd_conv_path_to_unix(char *path); void ksmbd_conv_path_to_windows(char *path); char *ksmbd_extract_sharename(char *treename); char *convert_to_unix_name(struct ksmbd_share_config *share, char *name); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index c86164dc70bb..46e0275a77a8 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -634,7 +634,7 @@ static char * smb2_get_name(struct ksmbd_share_config *share, const char *src, const int maxlen, struct nls_table *local_nls) { - char *name, *unixname; + char *name, *norm_name, *unixname; name = smb_strndup_from_utf16(src, maxlen, 1, local_nls); if (IS_ERR(name)) { @@ -643,11 +643,15 @@ smb2_get_name(struct ksmbd_share_config *share, const char *src, } /* change it to absolute unix name */ - ksmbd_conv_path_to_unix(name); - ksmbd_strip_last_slash(name); - - unixname = convert_to_unix_name(share, name); + norm_name = ksmbd_conv_path_to_unix(name); + if (IS_ERR(norm_name)) { + kfree(name); + return norm_name; + } kfree(name); + + unixname = convert_to_unix_name(share, norm_name); + kfree(norm_name); if (!unixname) { pr_err("can not convert absolute name\n"); return ERR_PTR(-ENOMEM); From e7165b1dff06b6e4373ab7758b21f3d9ed8a64ca Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 14 Sep 2021 00:49:25 +0200 Subject: [PATCH 399/866] pinctrl/rockchip: add a queue for deferred pin output settings on probe The separation of pinctrl and gpio drivers created a tiny window where a pinconfig setting might produce a null-pointer dereference. The affected device were rk3288-veyron devices in this case. Pinctrl-hogs are claimed when the pinctrl driver is registered, at which point their pinconfig settings will be applied. At this time the now separate gpio devices will not have been created yet and the matching driver won't have probed yet, making the gpio->foo() call run into a null-ptr. As probing is not really guaranteed to have been completed at a specific time, introduce a queue that can hold the output settings until the gpio driver has probed and will (in a separate patch) fetch the elements of the list. We expect the gpio driver to empty the list, but will nevertheless empty it ourself on remove if that didn't happen. Fixes: 9ce9a02039de ("pinctrl/rockchip: drop the gpio related codes") Signed-off-by: Heiko Stuebner Link: https://lore.kernel.org/r/20210913224926.1260726-4-heiko@sntech.de Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-rockchip.c | 67 ++++++++++++++++++++++++++++++ drivers/pinctrl/pinctrl-rockchip.h | 10 +++++ 2 files changed, 77 insertions(+) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index ae33e376695f..5ce260f152ce 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -2092,6 +2092,23 @@ static bool rockchip_pinconf_pull_valid(struct rockchip_pin_ctrl *ctrl, return false; } +static int rockchip_pinconf_defer_output(struct rockchip_pin_bank *bank, + unsigned int pin, u32 arg) +{ + struct rockchip_pin_output_deferred *cfg; + + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return -ENOMEM; + + cfg->pin = pin; + cfg->arg = arg; + + list_add_tail(&cfg->head, &bank->deferred_output); + + return 0; +} + /* set the pin config settings for a specified pin */ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, unsigned long *configs, unsigned num_configs) @@ -2136,6 +2153,22 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, if (rc != RK_FUNC_GPIO) return -EINVAL; + /* + * Check for gpio driver not being probed yet. + * The lock makes sure that either gpio-probe has completed + * or the gpio driver hasn't probed yet. + */ + mutex_lock(&bank->deferred_lock); + if (!gpio || !gpio->direction_output) { + rc = rockchip_pinconf_defer_output(bank, pin - bank->pin_base, arg); + mutex_unlock(&bank->deferred_lock); + if (rc) + return rc; + + break; + } + mutex_unlock(&bank->deferred_lock); + rc = gpio->direction_output(gpio, pin - bank->pin_base, arg); if (rc) @@ -2204,6 +2237,11 @@ static int rockchip_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, if (rc != RK_FUNC_GPIO) return -EINVAL; + if (!gpio || !gpio->get) { + arg = 0; + break; + } + rc = gpio->get(gpio, pin - bank->pin_base); if (rc < 0) return rc; @@ -2450,6 +2488,9 @@ static int rockchip_pinctrl_register(struct platform_device *pdev, pin_bank->name, pin); pdesc++; } + + INIT_LIST_HEAD(&pin_bank->deferred_output); + mutex_init(&pin_bank->deferred_lock); } ret = rockchip_pinctrl_parse_dt(pdev, info); @@ -2716,6 +2757,31 @@ static int rockchip_pinctrl_probe(struct platform_device *pdev) return 0; } +static int rockchip_pinctrl_remove(struct platform_device *pdev) +{ + struct rockchip_pinctrl *info = platform_get_drvdata(pdev); + struct rockchip_pin_bank *bank; + struct rockchip_pin_output_deferred *cfg; + int i; + + of_platform_depopulate(&pdev->dev); + + for (i = 0; i < info->ctrl->nr_banks; i++) { + bank = &info->ctrl->pin_banks[i]; + + mutex_lock(&bank->deferred_lock); + while (!list_empty(&bank->deferred_output)) { + cfg = list_first_entry(&bank->deferred_output, + struct rockchip_pin_output_deferred, head); + list_del(&cfg->head); + kfree(cfg); + } + mutex_unlock(&bank->deferred_lock); + } + + return 0; +} + static struct rockchip_pin_bank px30_pin_banks[] = { PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", IOMUX_SOURCE_PMU, IOMUX_SOURCE_PMU, @@ -3175,6 +3241,7 @@ static const struct of_device_id rockchip_pinctrl_dt_match[] = { static struct platform_driver rockchip_pinctrl_driver = { .probe = rockchip_pinctrl_probe, + .remove = rockchip_pinctrl_remove, .driver = { .name = "rockchip-pinctrl", .pm = &rockchip_pinctrl_dev_pm_ops, diff --git a/drivers/pinctrl/pinctrl-rockchip.h b/drivers/pinctrl/pinctrl-rockchip.h index 589d4d2a98c9..91f10279d084 100644 --- a/drivers/pinctrl/pinctrl-rockchip.h +++ b/drivers/pinctrl/pinctrl-rockchip.h @@ -141,6 +141,8 @@ struct rockchip_drv { * @toggle_edge_mode: bit mask to toggle (falling/rising) edge mode * @recalced_mask: bit mask to indicate a need to recalulate the mask * @route_mask: bits describing the routing pins of per bank + * @deferred_output: gpio output settings to be done after gpio bank probed + * @deferred_lock: mutex for the deferred_output shared btw gpio and pinctrl */ struct rockchip_pin_bank { struct device *dev; @@ -169,6 +171,8 @@ struct rockchip_pin_bank { u32 toggle_edge_mode; u32 recalced_mask; u32 route_mask; + struct list_head deferred_output; + struct mutex deferred_lock; }; /** @@ -243,6 +247,12 @@ struct rockchip_pin_config { unsigned int nconfigs; }; +struct rockchip_pin_output_deferred { + struct list_head head; + unsigned int pin; + u32 arg; +}; + /** * struct rockchip_pin_group: represent group of pins of a pinmux function. * @name: name of the pin group, used to lookup the group. From 59dd178e1d7cb6cac03b32aba7ed9bbce6761b6f Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 14 Sep 2021 00:49:26 +0200 Subject: [PATCH 400/866] gpio/rockchip: fetch deferred output settings on probe Fetch the output settings the pinctrl driver may have created for pinctrl hogs and set the relevant pins as requested. Fixes: 9ce9a02039de ("pinctrl/rockchip: drop the gpio related codes") Signed-off-by: Heiko Stuebner Link: https://lore.kernel.org/r/20210913224926.1260726-5-heiko@sntech.de Signed-off-by: Linus Walleij --- drivers/gpio/gpio-rockchip.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 036b2d959503..d67c64a39e47 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -689,6 +689,7 @@ static int rockchip_gpio_probe(struct platform_device *pdev) struct device_node *pctlnp = of_get_parent(np); struct pinctrl_dev *pctldev = NULL; struct rockchip_pin_bank *bank = NULL; + struct rockchip_pin_output_deferred *cfg; static int gpio; int id, ret; @@ -716,12 +717,33 @@ static int rockchip_gpio_probe(struct platform_device *pdev) if (ret) return ret; + /* + * Prevent clashes with a deferred output setting + * being added right at this moment. + */ + mutex_lock(&bank->deferred_lock); + ret = rockchip_gpiolib_register(bank); if (ret) { clk_disable_unprepare(bank->clk); + mutex_unlock(&bank->deferred_lock); return ret; } + while (!list_empty(&bank->deferred_output)) { + cfg = list_first_entry(&bank->deferred_output, + struct rockchip_pin_output_deferred, head); + list_del(&cfg->head); + + ret = rockchip_gpio_direction_output(&bank->gpio_chip, cfg->pin, cfg->arg); + if (ret) + dev_warn(dev, "setting output pin %u to %u failed\n", cfg->pin, cfg->arg); + + kfree(cfg); + } + + mutex_unlock(&bank->deferred_lock); + platform_set_drvdata(pdev, bank); dev_info(dev, "probed %pOF\n", np); From 6d56262c3d224699b29b9bb6b4ace8bab7d692c2 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 18 Sep 2021 18:45:12 +0900 Subject: [PATCH 401/866] ksmbd: add validation for FILE_FULL_EA_INFORMATION of smb2_get_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add validation to check whether req->InputBufferLength is smaller than smb2_ea_info_req structure size. Cc: Ronnie Sahlberg Cc: Ralph Böhme Cc: Steve French Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 46e0275a77a8..6304c9bda479 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4045,6 +4045,10 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, path = &fp->filp->f_path; /* single EA entry is requested with given user.* name */ if (req->InputBufferLength) { + if (le32_to_cpu(req->InputBufferLength) < + sizeof(struct smb2_ea_info_req)) + return -EINVAL; + ea_req = (struct smb2_ea_info_req *)req->Buffer; } else { /* need to send all EAs, if no specific EA is requested*/ From efafec27c5658ed987e720130772f8933c685e87 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Sep 2021 10:05:06 -0700 Subject: [PATCH 402/866] spi: Fix tegra20 build with CONFIG_PM=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without CONFIG_PM enabled, the SET_RUNTIME_PM_OPS() macro ends up being empty, and the only use of tegra_slink_runtime_{resume,suspend} goes away, resulting in drivers/spi/spi-tegra20-slink.c:1200:12: error: ‘tegra_slink_runtime_resume’ defined but not used [-Werror=unused-function] 1200 | static int tegra_slink_runtime_resume(struct device *dev) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/spi/spi-tegra20-slink.c:1188:12: error: ‘tegra_slink_runtime_suspend’ defined but not used [-Werror=unused-function] 1188 | static int tegra_slink_runtime_suspend(struct device *dev) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ mark the functions __maybe_unused to make the build happy. This hits the alpha allmodconfig build (and others). Reported-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/spi/spi-tegra20-slink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c index ebd27f883033..56c6feb2ba3e 100644 --- a/drivers/spi/spi-tegra20-slink.c +++ b/drivers/spi/spi-tegra20-slink.c @@ -1185,7 +1185,7 @@ static int tegra_slink_resume(struct device *dev) } #endif -static int tegra_slink_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_slink_runtime_suspend(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct tegra_slink_data *tspi = spi_master_get_devdata(master); @@ -1197,7 +1197,7 @@ static int tegra_slink_runtime_suspend(struct device *dev) return 0; } -static int tegra_slink_runtime_resume(struct device *dev) +static int __maybe_unused tegra_slink_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct tegra_slink_data *tspi = spi_master_get_devdata(master); From cc9d3aaa5331577a8658e25473a27ba5949023d8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Sep 2021 10:57:10 -0700 Subject: [PATCH 403/866] alpha: make 'Jensen' IO functions build again MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Jensen IO functions are overly copmplicated because some of the IO addresses refer to special 'local IO' ports, and they get accessed differently. That then makes gcc not actually inline them, and since they were marked "extern inline" when included through the regular path, and then only marked "inline" when included from sys_jensen.c, you never necessarily got a body for the IO functions at all. The intent of the sys_jensen.c code is to actually get the non-inlined copy generated, so remove the 'inline' from the magic macro that is supposed to sort this all out. Also, do not mix 'extern inline' functions (that may or may not be inlined and will not generate a function body if they are not) with 'static inline' (that _will_ generate a function body when not inlined). Because gcc will complain about this situation: error: ‘jensen_bus_outb’ is static but used in inline function ‘jensen_outb’ which is not static because gcc basically doesn't know whether to generate a body for that static inline function or not for that call site. So make all of these use that __EXTERN_INLINE marker. Gcc will generally not inline these things on use, and then generate the function body out-of-line in sys_jensen.c. This makes the core IO functions build for the alpha Jensen config. Not that the rest then builds, because it turns out Jensen also doesn't enable PCI, which then makes other drievrs very unhappy, but that's a separate issue. Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/jensen.h | 8 ++++---- arch/alpha/kernel/sys_jensen.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h index 916895155a88..1c4131453db2 100644 --- a/arch/alpha/include/asm/jensen.h +++ b/arch/alpha/include/asm/jensen.h @@ -111,18 +111,18 @@ __EXTERN_INLINE void jensen_set_hae(unsigned long addr) * convinced that I need one of the newer machines. */ -static inline unsigned int jensen_local_inb(unsigned long addr) +__EXTERN_INLINE unsigned int jensen_local_inb(unsigned long addr) { return 0xff & *(vuip)((addr << 9) + EISA_VL82C106); } -static inline void jensen_local_outb(u8 b, unsigned long addr) +__EXTERN_INLINE void jensen_local_outb(u8 b, unsigned long addr) { *(vuip)((addr << 9) + EISA_VL82C106) = b; mb(); } -static inline unsigned int jensen_bus_inb(unsigned long addr) +__EXTERN_INLINE unsigned int jensen_bus_inb(unsigned long addr) { long result; @@ -131,7 +131,7 @@ static inline unsigned int jensen_bus_inb(unsigned long addr) return __kernel_extbl(result, addr & 3); } -static inline void jensen_bus_outb(u8 b, unsigned long addr) +__EXTERN_INLINE void jensen_bus_outb(u8 b, unsigned long addr) { jensen_set_hae(0); *(vuip)((addr << 7) + EISA_IO + 0x00) = b * 0x01010101; diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index e5d870ff225f..436914c4851b 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -17,7 +17,7 @@ #include -#define __EXTERN_INLINE inline +#define __EXTERN_INLINE #include #include #undef __EXTERN_INLINE From cd395d529faf46bd7fd799852a659ca1bd650a27 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Sep 2021 11:15:01 -0700 Subject: [PATCH 404/866] tgafb: clarify dependencies MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The TGA boards were based on the DECchip 21030 PCI graphics accelerator used mainly for alpha, and existed in a TURBOchannel (TC) version for the DECstation (MIPS) workstations. However, the config option for the TGA code is a bit confused, and says depends on FB && (ALPHA || TC) because people didn't really want to enable the option for random PCI environments, so the "ALPHA" stands in for that case (while the TC case is then the MIPS DECstation case). So that config dependency is kind of a mixture of architecture and bus choices. But it's incorrect, in that there were non-PCI-based alpha hardware, and then the driver just causes warnings: drivers/video/fbdev/tgafb.c:1532:13: error: ‘tgafb_unregister’ defined but not used [-Werror=unused-function] 1532 | static void tgafb_unregister(struct device *dev) | ^~~~~~~~~~~~~~~~ drivers/video/fbdev/tgafb.c:1387:12: error: ‘tgafb_register’ defined but not used [-Werror=unused-function] 1387 | static int tgafb_register(struct device *dev) | ^~~~~~~~~~~~~~ so let's make the config option dependencies a bit more explict: depends on FB depends on PCI || TC depends on ALPHA || TC where that first "FB" is the software configuration dependency, the second "PCI || TC" is the hardware bus dependency, while that final "ALPHA || TC" dependency is the "don't bother asking except for these situations. We could make that third case have "COMPILE_TEST" as an option, and mark the register/unregister functions as __maybe_unused, but I'm not sure it's really worth it. Signed-off-by: Linus Torvalds --- drivers/video/fbdev/Kconfig | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index d33c5cd684c0..b26b79dfcac9 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -582,7 +582,9 @@ config FB_HP300 config FB_TGA tristate "TGA/SFB+ framebuffer support" - depends on FB && (ALPHA || TC) + depends on FB + depends on PCI || TC + depends on ALPHA || TC select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT From 7efbcc8c075c5e9ef69b2379b75b58a699f23eb3 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Sat, 11 Sep 2021 10:08:53 +0530 Subject: [PATCH 405/866] perf annotate: Fix fused instr logic for assembly functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some x86 microarchitectures fuse a subset of cmp/test/ALU instructions with branch instructions, and thus perf annotate highlight such valid pairs as fused. When annotated with source, perf uses struct disasm_line to contain either source or instruction line from objdump output. Usually, a C statement generates multiple instructions which include such cmp/test/ALU + branch instruction pairs. But in case of assembly function, each individual assembly source line generate one instruction. The 'perf annotate' instruction fusion logic assumes the previous disasm_line as the previous instruction line, which is wrong because, for assembly function, previous disasm_line contains source line. And thus perf fails to highlight valid fused instruction pairs for assembly functions. Fix it by searching backward until we find an instruction line and consider that disasm_line as fused with current branch instruction. Before: │ cmpq %rcx, RIP+8(%rsp) 0.00 │ cmp %rcx,0x88(%rsp) │ je .Lerror_bad_iret <--- Source line 0.14 │ ┌──je b4 <--- Instruction line │ │movl %ecx, %eax After: │ cmpq %rcx, RIP+8(%rsp) 0.00 │ ┌──cmp %rcx,0x88(%rsp) │ │je .Lerror_bad_iret 0.14 │ ├──je b4 │ │movl %ecx, %eax Reviewed-by: Jin Yao Signed-off-by: Ravi Bangoria Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Kim Phillips Cc: Mark Rutland Cc: Namhyung Kim Link: https //lore.kernel.org/r/20210911043854.8373-1-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browser.c | 33 ++++++++++++++++++++++--------- tools/perf/ui/browser.h | 2 +- tools/perf/ui/browsers/annotate.c | 24 +++++++++++++++------- 3 files changed, 42 insertions(+), 17 deletions(-) diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 781afe42e90e..fa5bd5c20e96 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -757,25 +757,40 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, } void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down) + unsigned int row, int diff, bool arrow_down) { - unsigned int end_row; + int end_row; - if (row >= browser->top_idx) - end_row = row - browser->top_idx; - else + if (diff <= 0) return; SLsmg_set_char_set(1); if (arrow_down) { + if (row + diff <= browser->top_idx) + return; + + end_row = row + diff - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); - SLsmg_write_char(SLSMG_ULCORN_CHAR); - ui_browser__gotorc(browser, end_row, column); - SLsmg_draw_hline(2); - ui_browser__gotorc(browser, end_row + 1, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); + + while (--end_row >= 0 && end_row > (int)(row - browser->top_idx)) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_draw_vline(1); + } + + end_row = (int)(row - browser->top_idx); + if (end_row >= 0) { + ui_browser__gotorc(browser, end_row, column - 1); + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_hline(2); + } } else { + if (row < browser->top_idx) + return; + + end_row = row - browser->top_idx; ui_browser__gotorc(browser, end_row, column - 1); SLsmg_write_char(SLSMG_LTEE_CHAR); ui_browser__gotorc(browser, end_row, column); diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h index 3678eb88f119..510ce4554050 100644 --- a/tools/perf/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -51,7 +51,7 @@ void ui_browser__write_graph(struct ui_browser *browser, int graph); void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, u64 start, u64 end); void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column, - unsigned int row, bool arrow_down); + unsigned int row, int diff, bool arrow_down); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *browser, const char *title, diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ef4da4295bf7..e81c2493efdf 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -125,13 +125,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int ab->selection = al; } -static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) +static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor) { struct disasm_line *pos = list_prev_entry(cursor, al.node); const char *name; + int diff = 1; + + while (pos && pos->al.offset == -1) { + pos = list_prev_entry(pos, al.node); + if (!ab->opts->hide_src_code) + diff++; + } if (!pos) - return false; + return 0; if (ins__is_lock(&pos->ins)) name = pos->ops.locked.ins.name; @@ -139,9 +146,11 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor) name = pos->ins.name; if (!name || !cursor->ins.name) - return false; + return 0; - return ins__is_fused(ab->arch, name, cursor->ins.name); + if (ins__is_fused(ab->arch, name, cursor->ins.name)) + return diff; + return 0; } static void annotate_browser__draw_current_jump(struct ui_browser *browser) @@ -155,6 +164,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) struct annotation *notes = symbol__annotation(sym); u8 pcnt_width = annotation__pcnt_width(notes); int width; + int diff = 0; /* PLT symbols contain external offsets */ if (strstr(sym->name, "@plt")) @@ -205,11 +215,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) pcnt_width + 2 + notes->widths.addr + width, from, to); - if (is_fused(ab, cursor)) { + diff = is_fused(ab, cursor); + if (diff > 0) { ui_browser__mark_fused(browser, pcnt_width + 3 + notes->widths.addr + width, - from - 1, - to > from); + from - diff, diff, to > from); } } From ff6f41fbcee9830f88413cbb08dc45e543243b55 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Sat, 11 Sep 2021 16:30:53 +0300 Subject: [PATCH 406/866] perf script: Fix ip display when type != attr->type set_print_ip_opts() was not being called when type != attr->type because there is not a one-to-one relationship between output types and attr->type. That resulted in ip not printing. The attr_type() function is removed, and the match of attr->type to output type is corrected. Example on ADL using taskset to select an atom cpu: # perf record -e cpu_atom/cpu-cycles/ taskset 0x1000 uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.003 MB perf.data (7 samples) ] Before: # perf script | head taskset 428 [-01] 10394.179041: 1 cpu_atom/cpu-cycles/: taskset 428 [-01] 10394.179043: 1 cpu_atom/cpu-cycles/: taskset 428 [-01] 10394.179044: 11 cpu_atom/cpu-cycles/: taskset 428 [-01] 10394.179045: 407 cpu_atom/cpu-cycles/: taskset 428 [-01] 10394.179046: 16789 cpu_atom/cpu-cycles/: taskset 428 [-01] 10394.179052: 676300 cpu_atom/cpu-cycles/: uname 428 [-01] 10394.179278: 4079859 cpu_atom/cpu-cycles/: After: # perf script | head taskset 428 10394.179041: 1 cpu_atom/cpu-cycles/: ffffffff95a0bb97 __intel_pmu_enable_all.constprop.48+0x47 ([kernel.kallsyms]) taskset 428 10394.179043: 1 cpu_atom/cpu-cycles/: ffffffff95a0bb97 __intel_pmu_enable_all.constprop.48+0x47 ([kernel.kallsyms]) taskset 428 10394.179044: 11 cpu_atom/cpu-cycles/: ffffffff95a0bb97 __intel_pmu_enable_all.constprop.48+0x47 ([kernel.kallsyms]) taskset 428 10394.179045: 407 cpu_atom/cpu-cycles/: ffffffff95a0bb97 __intel_pmu_enable_all.constprop.48+0x47 ([kernel.kallsyms]) taskset 428 10394.179046: 16789 cpu_atom/cpu-cycles/: ffffffff95a0bb97 __intel_pmu_enable_all.constprop.48+0x47 ([kernel.kallsyms]) taskset 428 10394.179052: 676300 cpu_atom/cpu-cycles/: 7f829ef73800 cfree+0x0 (/lib/libc-2.32.so) uname 428 10394.179278: 4079859 cpu_atom/cpu-cycles/: ffffffff95bae912 vma_interval_tree_remove+0x1f2 ([kernel.kallsyms]) Signed-off-by: Adrian Hunter Reviewed-by: Kan Liang Cc: Jin Yao Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20210911133053.15682-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 0e824f7d8b19..6211d0b84b7a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -368,16 +368,6 @@ static inline int output_type(unsigned int type) return OUTPUT_TYPE_OTHER; } -static inline unsigned int attr_type(unsigned int type) -{ - switch (type) { - case OUTPUT_TYPE_SYNTH: - return PERF_TYPE_SYNTH; - default: - return type; - } -} - static bool output_set_by_user(void) { int j; @@ -556,6 +546,18 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } +static struct evsel *find_first_output_type(struct evlist *evlist, + unsigned int type) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (output_type(evsel->core.attr.type) == (int)type) + return evsel; + } + return NULL; +} + /* * verify all user requested events exist and the samples * have the expected data @@ -567,7 +569,7 @@ static int perf_session__check_output_opt(struct perf_session *session) struct evsel *evsel; for (j = 0; j < OUTPUT_TYPE_MAX; ++j) { - evsel = perf_session__find_first_evtype(session, attr_type(j)); + evsel = find_first_output_type(session->evlist, j); /* * even if fields is set to 0 (ie., show nothing) event must From 57f0ff059e3daa4e70a811cb1d31a49968262d20 Mon Sep 17 00:00:00 2001 From: Michael Petlan Date: Mon, 19 Jul 2021 16:53:32 +0200 Subject: [PATCH 407/866] perf machine: Initialize srcline string member in add_location struct It's later supposed to be either a correct address or NULL. Without the initialization, it may contain an undefined value which results in the following segmentation fault: # perf top --sort comm -g --ignore-callees=do_idle terminates with: #0 0x00007ffff56b7685 in __strlen_avx2 () from /lib64/libc.so.6 #1 0x00007ffff55e3802 in strdup () from /lib64/libc.so.6 #2 0x00005555558cb139 in hist_entry__init (callchain_size=, sample_self=true, template=0x7fffde7fb110, he=0x7fffd801c250) at util/hist.c:489 #3 hist_entry__new (template=template@entry=0x7fffde7fb110, sample_self=sample_self@entry=true) at util/hist.c:564 #4 0x00005555558cb4ba in hists__findnew_entry (hists=hists@entry=0x5555561d9e38, entry=entry@entry=0x7fffde7fb110, al=al@entry=0x7fffde7fb420, sample_self=sample_self@entry=true) at util/hist.c:657 #5 0x00005555558cba1b in __hists__add_entry (hists=hists@entry=0x5555561d9e38, al=0x7fffde7fb420, sym_parent=, bi=bi@entry=0x0, mi=mi@entry=0x0, sample=sample@entry=0x7fffde7fb4b0, sample_self=true, ops=0x0, block_info=0x0) at util/hist.c:288 #6 0x00005555558cbb70 in hists__add_entry (sample_self=true, sample=0x7fffde7fb4b0, mi=0x0, bi=0x0, sym_parent=, al=, hists=0x5555561d9e38) at util/hist.c:1056 #7 iter_add_single_cumulative_entry (iter=0x7fffde7fb460, al=) at util/hist.c:1056 #8 0x00005555558cc8a4 in hist_entry_iter__add (iter=iter@entry=0x7fffde7fb460, al=al@entry=0x7fffde7fb420, max_stack_depth=, arg=arg@entry=0x7fffffff7db0) at util/hist.c:1231 #9 0x00005555557cdc9a in perf_event__process_sample (machine=, sample=0x7fffde7fb4b0, evsel=, event=, tool=0x7fffffff7db0) at builtin-top.c:842 #10 deliver_event (qe=, qevent=) at builtin-top.c:1202 #11 0x00005555558a9318 in do_flush (show_progress=false, oe=0x7fffffff80e0) at util/ordered-events.c:244 #12 __ordered_events__flush (oe=oe@entry=0x7fffffff80e0, how=how@entry=OE_FLUSH__TOP, timestamp=timestamp@entry=0) at util/ordered-events.c:323 #13 0x00005555558a9789 in __ordered_events__flush (timestamp=, how=, oe=) at util/ordered-events.c:339 #14 ordered_events__flush (how=OE_FLUSH__TOP, oe=0x7fffffff80e0) at util/ordered-events.c:341 #15 ordered_events__flush (oe=oe@entry=0x7fffffff80e0, how=how@entry=OE_FLUSH__TOP) at util/ordered-events.c:339 #16 0x00005555557cd631 in process_thread (arg=0x7fffffff7db0) at builtin-top.c:1114 #17 0x00007ffff7bb817a in start_thread () from /lib64/libpthread.so.0 #18 0x00007ffff5656dc3 in clone () from /lib64/libc.so.6 If you look at the frame #2, the code is: 488 if (he->srcline) { 489 he->srcline = strdup(he->srcline); 490 if (he->srcline == NULL) 491 goto err_rawdata; 492 } If he->srcline is not NULL (it is not NULL if it is uninitialized rubbish), it gets strdupped and strdupping a rubbish random string causes the problem. Also, if you look at the commit 1fb7d06a509e, it adds the srcline property into the struct, but not initializing it everywhere needed. Committer notes: Now I see, when using --ignore-callees=do_idle we end up here at line 2189 in add_callchain_ip(): 2181 if (al.sym != NULL) { 2182 if (perf_hpp_list.parent && !*parent && 2183 symbol__match_regex(al.sym, &parent_regex)) 2184 *parent = al.sym; 2185 else if (have_ignore_callees && root_al && 2186 symbol__match_regex(al.sym, &ignore_callees_regex)) { 2187 /* Treat this symbol as the root, 2188 forgetting its callees. */ 2189 *root_al = al; 2190 callchain_cursor_reset(cursor); 2191 } 2192 } And the al that doesn't have the ->srcline field initialized will be copied to the root_al, so then, back to: 1211 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, 1212 int max_stack_depth, void *arg) 1213 { 1214 int err, err2; 1215 struct map *alm = NULL; 1216 1217 if (al) 1218 alm = map__get(al->map); 1219 1220 err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, 1221 iter->evsel, al, max_stack_depth); 1222 if (err) { 1223 map__put(alm); 1224 return err; 1225 } 1226 1227 err = iter->ops->prepare_entry(iter, al); 1228 if (err) 1229 goto out; 1230 1231 err = iter->ops->add_single_entry(iter, al); 1232 if (err) 1233 goto out; 1234 That al at line 1221 is what hist_entry_iter__add() (called from sample__resolve_callchain()) saw as 'root_al', and then: iter->ops->add_single_entry(iter, al); will go on with al->srcline with a bogus value, I'll add the above sequence to the cset and apply, thanks! Signed-off-by: Michael Petlan CC: Milian Wolff Cc: Jiri Olsa Fixes: 1fb7d06a509e ("perf report Use srcline from callchain for hist entries") Link: https //lore.kernel.org/r/20210719145332.29747-1-mpetlan@redhat.com Reported-by: Juri Lelli Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index da19be7da284..44e40bad0e33 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2149,6 +2149,7 @@ static int add_callchain_ip(struct thread *thread, al.filtered = 0; al.sym = NULL; + al.srcline = NULL; if (!cpumode) { thread__find_cpumode_addr_location(thread, ip, &al); } else { From aba5daeb645181ee5a046bc00c231fd045882aaa Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 17 Sep 2021 22:44:40 -0700 Subject: [PATCH 408/866] libperf evsel: Make use of FD robust. FD uses xyarray__entry that may return NULL if an index is out of bounds. If NULL is returned then a segv happens as FD unconditionally dereferences the pointer. This was happening in a case of with perf iostat as shown below. The fix is to make FD an "int*" rather than an int and handle the NULL case as either invalid input or a closed fd. $ sudo gdb --args perf stat --iostat list ... Breakpoint 1, perf_evsel__alloc_fd (evsel=0x5555560951a0, ncpus=1, nthreads=1) at evsel.c:50 50 { (gdb) bt #0 perf_evsel__alloc_fd (evsel=0x5555560951a0, ncpus=1, nthreads=1) at evsel.c:50 #1 0x000055555585c188 in evsel__open_cpu (evsel=0x5555560951a0, cpus=0x555556093410, threads=0x555556086fb0, start_cpu=0, end_cpu=1) at util/evsel.c:1792 #2 0x000055555585cfb2 in evsel__open (evsel=0x5555560951a0, cpus=0x0, threads=0x555556086fb0) at util/evsel.c:2045 #3 0x000055555585d0db in evsel__open_per_thread (evsel=0x5555560951a0, threads=0x555556086fb0) at util/evsel.c:2065 #4 0x00005555558ece64 in create_perf_stat_counter (evsel=0x5555560951a0, config=0x555555c34700 , target=0x555555c2f1c0 , cpu=0) at util/stat.c:590 #5 0x000055555578e927 in __run_perf_stat (argc=1, argv=0x7fffffffe4a0, run_idx=0) at builtin-stat.c:833 #6 0x000055555578f3c6 in run_perf_stat (argc=1, argv=0x7fffffffe4a0, run_idx=0) at builtin-stat.c:1048 #7 0x0000555555792ee5 in cmd_stat (argc=1, argv=0x7fffffffe4a0) at builtin-stat.c:2534 #8 0x0000555555835ed3 in run_builtin (p=0x555555c3f540 , argc=3, argv=0x7fffffffe4a0) at perf.c:313 #9 0x0000555555836154 in handle_internal_command (argc=3, argv=0x7fffffffe4a0) at perf.c:365 #10 0x000055555583629f in run_argv (argcp=0x7fffffffe2ec, argv=0x7fffffffe2e0) at perf.c:409 #11 0x0000555555836692 in main (argc=3, argv=0x7fffffffe4a0) at perf.c:539 ... (gdb) c Continuing. Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (uncore_iio_0/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/). /bin/dmesg | grep -i perf may provide additional information. Program received signal SIGSEGV, Segmentation fault. 0x00005555559b03ea in perf_evsel__close_fd_cpu (evsel=0x5555560951a0, cpu=1) at evsel.c:166 166 if (FD(evsel, cpu, thread) >= 0) v3. fixes a bug in perf_evsel__run_ioctl where the sense of a branch was backward. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210918054440.2350466-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evsel.c | 64 +++++++++++++++++++++++++++--------------- 1 file changed, 41 insertions(+), 23 deletions(-) diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index d8886720e83d..8441e3e1aaac 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -43,7 +43,7 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y)) +#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y)) #define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL) int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) @@ -54,7 +54,10 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { - FD(evsel, cpu, thread) = -1; + int *fd = FD(evsel, cpu, thread); + + if (fd) + *fd = -1; } } } @@ -80,7 +83,7 @@ sys_perf_event_open(struct perf_event_attr *attr, static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd) { struct perf_evsel *leader = evsel->leader; - int fd; + int *fd; if (evsel == leader) { *group_fd = -1; @@ -95,10 +98,10 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou return -ENOTCONN; fd = FD(leader, cpu, thread); - if (fd == -1) + if (fd == NULL || *fd == -1) return -EBADF; - *group_fd = fd; + *group_fd = *fd; return 0; } @@ -138,7 +141,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, for (cpu = 0; cpu < cpus->nr; cpu++) { for (thread = 0; thread < threads->nr; thread++) { - int fd, group_fd; + int fd, group_fd, *evsel_fd; + + evsel_fd = FD(evsel, cpu, thread); + if (evsel_fd == NULL) + return -EINVAL; err = get_group_fd(evsel, cpu, thread, &group_fd); if (err < 0) @@ -151,7 +158,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, if (fd < 0) return -errno; - FD(evsel, cpu, thread) = fd; + *evsel_fd = fd; } } @@ -163,9 +170,12 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - if (FD(evsel, cpu, thread) >= 0) - close(FD(evsel, cpu, thread)); - FD(evsel, cpu, thread) = -1; + int *fd = FD(evsel, cpu, thread); + + if (fd && *fd >= 0) { + close(*fd); + *fd = -1; + } } } @@ -209,13 +219,12 @@ void perf_evsel__munmap(struct perf_evsel *evsel) for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread); - struct perf_mmap *map = MMAP(evsel, cpu, thread); + int *fd = FD(evsel, cpu, thread); - if (fd < 0) + if (fd == NULL || *fd < 0) continue; - perf_mmap__munmap(map); + perf_mmap__munmap(MMAP(evsel, cpu, thread)); } } @@ -239,15 +248,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread); - struct perf_mmap *map = MMAP(evsel, cpu, thread); + int *fd = FD(evsel, cpu, thread); + struct perf_mmap *map; - if (fd < 0) + if (fd == NULL || *fd < 0) continue; + map = MMAP(evsel, cpu, thread); perf_mmap__init(map, NULL, false, NULL); - ret = perf_mmap__mmap(map, &mp, fd, cpu); + ret = perf_mmap__mmap(map, &mp, *fd, cpu); if (ret) { perf_evsel__munmap(evsel); return ret; @@ -260,7 +270,9 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread) { - if (FD(evsel, cpu, thread) < 0 || MMAP(evsel, cpu, thread) == NULL) + int *fd = FD(evsel, cpu, thread); + + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL) return NULL; return MMAP(evsel, cpu, thread)->base; @@ -295,17 +307,18 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu, thread); memset(count, 0, sizeof(*count)); - if (FD(evsel, cpu, thread) < 0) + if (fd == NULL || *fd < 0) return -EINVAL; if (MMAP(evsel, cpu, thread) && !perf_mmap__read_self(MMAP(evsel, cpu, thread), count)) return 0; - if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) + if (readn(*fd, count->values, size) <= 0) return -errno; return 0; @@ -318,8 +331,13 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int fd = FD(evsel, cpu, thread), - err = ioctl(fd, ioc, arg); + int err; + int *fd = FD(evsel, cpu, thread); + + if (fd == NULL || *fd < 0) + return -1; + + err = ioctl(*fd, ioc, arg); if (err) return err; From 219d720e6df71c2607d7120d6b9281614863e5b1 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 14 Sep 2021 10:00:04 -0700 Subject: [PATCH 409/866] perf bpf: Ignore deprecation warning when using libbpf's btf__get_from_id() Perf code re-implements libbpf's btf__load_from_kernel_by_id() API as a weak function, presumably to dynamically link against old version of libbpf shared library. Unfortunately this causes compilation warning when perf is compiled against libbpf v0.6+. For now, just ignore deprecation warning, but there might be a better solution, depending on perf's needs. Signed-off-by: Andrii Nakryiko Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: kernel-team@fb.com LPU-Reference: 20210914170004.4185659-1-andrii@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-event.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 683f6d63560e..1a7112a87736 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -24,7 +24,10 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) { struct btf *btf; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" int err = btf__get_from_id(id, &btf); +#pragma GCC diagnostic pop return err ? ERR_PTR(err) : btf; } From ab41f75ee6a06fa9b947a59c8f9de92370463e40 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Sep 2021 14:12:39 -0700 Subject: [PATCH 410/866] alpha: mark 'Jensen' platform as no longer broken Ok, it almost certainly is still broken on actual hardware, but the immediate reason for it having been marked BROKEN was a build error that is fixed by just making sure the low-level IO header file is included sufficiently early that the __EXTERN_INLINE hackery takes effect. This was marked broken back in 2017 by commit 1883c9f49d02 ("alpha: mark jensen as broken"), but Ulrich Teichert made me look at it as part of my cross-build work to make sure -Werror actually does the right thing. There are lots of alpha configurations that do not build cleanly, but now it's no longer because Jensen wouldn't be buildable. That said, because the Jensen platform doesn't force PCI to be enabled (Jensen only had EISA), it ends up being somewhat interesting as a source of odd configs. Reported-by: Ulrich Teichert Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/alpha/kernel/sys_jensen.c | 10 +++++----- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 02e5b673bdad..11e99358aa58 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -199,7 +199,6 @@ config ALPHA_EIGER config ALPHA_JENSEN bool "Jensen" - depends on BROKEN select HAVE_EISA help DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index 436914c4851b..5c9c88428124 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -7,6 +7,11 @@ * * Code supporting the Jensen. */ +#define __EXTERN_INLINE +#include +#include +#undef __EXTERN_INLINE + #include #include #include @@ -17,11 +22,6 @@ #include -#define __EXTERN_INLINE -#include -#include -#undef __EXTERN_INLINE - #include #include #include From d4d016caa4b85b9aa98d7ec8c84e928621a614bc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 18 Sep 2021 14:45:48 -0700 Subject: [PATCH 411/866] alpha: move __udiv_qrnnd library function to arch/alpha/lib/ We already had the implementation for __udiv_qrnnd (unsigned divide for multi-precision arithmetic) as part of the alpha math emulation code. But you can disable the math emulation code - even if you shouldn't - and then the MPI code that actually wants this functionality (and is needed by various crypto functions) will fail to build. So move the extended-precision divide code to be a regular library function, just like all the regular division code is. That way ie is available regardless of math-emulation. Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/asm-prototypes.h | 1 + arch/alpha/lib/Makefile | 1 + arch/alpha/{math-emu/qrnnd.S => lib/udiv-qrnnd.S} | 2 ++ arch/alpha/math-emu/Makefile | 2 +- arch/alpha/math-emu/math.c | 2 -- 5 files changed, 5 insertions(+), 3 deletions(-) rename arch/alpha/{math-emu/qrnnd.S => lib/udiv-qrnnd.S} (98%) diff --git a/arch/alpha/include/asm/asm-prototypes.h b/arch/alpha/include/asm/asm-prototypes.h index b34cc1f06720..c8ae46fc2e74 100644 --- a/arch/alpha/include/asm/asm-prototypes.h +++ b/arch/alpha/include/asm/asm-prototypes.h @@ -16,3 +16,4 @@ extern void __divlu(void); extern void __remlu(void); extern void __divqu(void); extern void __remqu(void); +extern unsigned long __udiv_qrnnd(unsigned long *, unsigned long, unsigned long , unsigned long); diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile index 854d5e79979e..1cc74f7b50ef 100644 --- a/arch/alpha/lib/Makefile +++ b/arch/alpha/lib/Makefile @@ -14,6 +14,7 @@ ev6-$(CONFIG_ALPHA_EV6) := ev6- ev67-$(CONFIG_ALPHA_EV67) := ev67- lib-y = __divqu.o __remqu.o __divlu.o __remlu.o \ + udiv-qrnnd.o \ udelay.o \ $(ev6-y)memset.o \ $(ev6-y)memcpy.o \ diff --git a/arch/alpha/math-emu/qrnnd.S b/arch/alpha/lib/udiv-qrnnd.S similarity index 98% rename from arch/alpha/math-emu/qrnnd.S rename to arch/alpha/lib/udiv-qrnnd.S index d6373ec1bff9..b887aa5428e5 100644 --- a/arch/alpha/math-emu/qrnnd.S +++ b/arch/alpha/lib/udiv-qrnnd.S @@ -25,6 +25,7 @@ # along with GCC; see the file COPYING. If not, write to the # Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, # MA 02111-1307, USA. +#include .set noreorder .set noat @@ -161,3 +162,4 @@ $Odd: ret $31,($26),1 .end __udiv_qrnnd +EXPORT_SYMBOL(__udiv_qrnnd) diff --git a/arch/alpha/math-emu/Makefile b/arch/alpha/math-emu/Makefile index 6eda0973e183..3206402a8792 100644 --- a/arch/alpha/math-emu/Makefile +++ b/arch/alpha/math-emu/Makefile @@ -7,4 +7,4 @@ ccflags-y := -w obj-$(CONFIG_MATHEMU) += math-emu.o -math-emu-objs := math.o qrnnd.o +math-emu-objs := math.o diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c index f7cef66af88d..4212258f3cfd 100644 --- a/arch/alpha/math-emu/math.c +++ b/arch/alpha/math-emu/math.c @@ -403,5 +403,3 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask) egress: return si_code; } - -EXPORT_SYMBOL(__udiv_qrnnd); From d62d5aed3354ae57d57fae1e59948913f360d4eb Mon Sep 17 00:00:00 2001 From: Ariel Marcovitch Date: Wed, 1 Sep 2021 17:52:12 +0300 Subject: [PATCH 412/866] checkkconfigsymbols.py: Forbid passing 'HEAD' to --commit As opposed to the --diff option, --commit can get ref names instead of commit hashes. When using the --commit option, the script resets the working directory to the commit before the given ref, by adding '~' to the end of the ref. However, the 'HEAD' ref is relative, and so when the working directory is reset to 'HEAD~', 'HEAD' points to what was 'HEAD~'. Then when the script resets to 'HEAD' it actually stays in the same commit. In this case, the script won't report any cases because there is no diff between the cases of the two refs. Prevent the user from using HEAD refs. A better solution might be to resolve the refs before doing the reset, but for now just disallow such refs. Signed-off-by: Ariel Marcovitch Signed-off-by: Masahiro Yamada --- scripts/checkkconfigsymbols.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/scripts/checkkconfigsymbols.py b/scripts/checkkconfigsymbols.py index b9b0f15e5880..c57c990c3244 100755 --- a/scripts/checkkconfigsymbols.py +++ b/scripts/checkkconfigsymbols.py @@ -102,6 +102,9 @@ def parse_options(): "continue.") if args.commit: + if args.commit.startswith('HEAD'): + sys.exit("The --commit option can't use the HEAD ref") + args.find = False if args.ignore: From aa0f5ea12e477b2940a57fcda4908627e0beed0f Mon Sep 17 00:00:00 2001 From: Ariel Marcovitch Date: Wed, 1 Sep 2021 19:49:52 +0300 Subject: [PATCH 413/866] checkkconfigsymbols.py: Remove skipping of help lines in parse_kconfig_file When parsing Kconfig files to find symbol definitions and references, lines after a 'help' line are skipped until a new config definition starts. However, Kconfig statements can actually be after a help section, as long as these have shallower indentation. These are skipped by the parser. This means that symbols referenced in this kind of statements are ignored by this function and thus are not considered undefined references in case the symbol is not defined. Remove the 'skip' logic entirely, as it is not needed if we just use the STMT regex to find the end of help lines. However, this means that keywords that appear as part of the help message (i.e. with the same indentation as the help lines) it will be considered as a reference/definition. This can happen now as well, but only with REGEX_KCONFIG_DEF lines. Also, the keyword must have a SYMBOL after it, which probably means that someone referenced a config in the help so it seems like a bonus :) The real solution is to keep track of the indentation when a the first help line in encountered and then handle DEF and STMT lines only if the indentation is shallower. Signed-off-by: Ariel Marcovitch Signed-off-by: Masahiro Yamada --- scripts/checkkconfigsymbols.py | 8 -------- 1 file changed, 8 deletions(-) diff --git a/scripts/checkkconfigsymbols.py b/scripts/checkkconfigsymbols.py index c57c990c3244..217d21abc86e 100755 --- a/scripts/checkkconfigsymbols.py +++ b/scripts/checkkconfigsymbols.py @@ -34,7 +34,6 @@ REGEX_SOURCE_SYMBOL = re.compile(SOURCE_SYMBOL) REGEX_KCONFIG_DEF = re.compile(DEF) REGEX_KCONFIG_EXPR = re.compile(EXPR) REGEX_KCONFIG_STMT = re.compile(STMT) -REGEX_KCONFIG_HELP = re.compile(r"^\s+help\s*$") REGEX_FILTER_SYMBOLS = re.compile(r"[A-Za-z0-9]$") REGEX_NUMERIC = re.compile(r"0[xX][0-9a-fA-F]+|[0-9]+") REGEX_QUOTES = re.compile("(\"(.*?)\")") @@ -435,7 +434,6 @@ def parse_kconfig_file(kfile): lines = [] defined = [] references = [] - skip = False if not os.path.exists(kfile): return defined, references @@ -451,12 +449,6 @@ def parse_kconfig_file(kfile): if REGEX_KCONFIG_DEF.match(line): symbol_def = REGEX_KCONFIG_DEF.findall(line) defined.append(symbol_def[0]) - skip = False - elif REGEX_KCONFIG_HELP.match(line): - skip = True - elif skip: - # ignore content of help messages - pass elif REGEX_KCONFIG_STMT.match(line): line = REGEX_QUOTES.sub("", line) symbols = get_symbols_in_line(line) From ec783c7cb2495c5a3b8ca10db8056d43c528f940 Mon Sep 17 00:00:00 2001 From: Kortan Date: Wed, 8 Sep 2021 11:28:48 +0800 Subject: [PATCH 414/866] gen_compile_commands: fix missing 'sys' package We need to import the 'sys' package since the script has called sys.exit() method. Fixes: 6ad7cbc01527 ("Makefile: Add clang-tidy and static analyzer support to makefile") Signed-off-by: Kortan Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- scripts/clang-tools/gen_compile_commands.py | 1 + 1 file changed, 1 insertion(+) diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index 0033eedce003..1d1bde1fd45e 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -13,6 +13,7 @@ import logging import os import re import subprocess +import sys _DEFAULT_OUTPUT = 'compile_commands.json' _DEFAULT_LOG_LEVEL = 'WARNING' From 4e70b646bae578bb51c89204b5b81ef499436482 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Sep 2021 10:43:53 +0200 Subject: [PATCH 415/866] sh: Add missing FORCE prerequisites in Makefile make: arch/sh/boot/Makefile:87: FORCE prerequisite is missing Add the missing FORCE prerequisites for all build targets identified by "make help". Fixes: e1f86d7b4b2a5213 ("kbuild: warn if FORCE is missing for if_changed(_dep,_rule) and filechk") Signed-off-by: Geert Uytterhoeven Signed-off-by: Masahiro Yamada --- arch/sh/boot/Makefile | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile index 58592dfa5cb6..c081e7e2d6e7 100644 --- a/arch/sh/boot/Makefile +++ b/arch/sh/boot/Makefile @@ -80,30 +80,30 @@ $(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE $(call if_changed,lzo) -$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2 +$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2 FORCE $(call if_changed,uimage,bzip2) -$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz +$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE $(call if_changed,uimage,gzip) -$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma +$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE $(call if_changed,uimage,lzma) -$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz +$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz FORCE $(call if_changed,uimage,xz) -$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo +$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo FORCE $(call if_changed,uimage,lzo) -$(obj)/uImage.bin: $(obj)/vmlinux.bin +$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE $(call if_changed,uimage,none) OBJCOPYFLAGS_vmlinux.srec := -I binary -O srec -$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux +$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux FORCE $(call if_changed,objcopy) OBJCOPYFLAGS_uImage.srec := -I binary -O srec -$(obj)/uImage.srec: $(obj)/uImage +$(obj)/uImage.srec: $(obj)/uImage FORCE $(call if_changed,objcopy) $(obj)/uImage: $(obj)/uImage.$(suffix-y) From 7c80144626db460bc3969027810a540741865fb1 Mon Sep 17 00:00:00 2001 From: Ramji Jiyani Date: Thu, 16 Sep 2021 09:21:22 +0000 Subject: [PATCH 416/866] kbuild: Fix comment typo in scripts/Makefile.modpost Change comment "create one .mod.c file pr. module" to "create one .mod.c file per module" Signed-off-by: Ramji Jiyani Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index eef56d629799..48585c4d04ad 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -13,7 +13,7 @@ # Stage 2 is handled by this file and does the following # 1) Find all modules listed in modules.order # 2) modpost is then used to -# 3) create one .mod.c file pr. module +# 3) create one .mod.c file per module # 4) create one Module.symvers file with CRC for all exported symbols # Step 3 is used to place certain information in the module's ELF From 7fa6a2746616c8de4c40b748c2bb0656e00624ff Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 16 Sep 2021 11:40:16 -0700 Subject: [PATCH 417/866] x86/build: Do not add -falign flags unconditionally for clang clang does not support -falign-jumps and only recently gained support for -falign-loops. When one of the configuration options that adds these flags is enabled, clang warns and all cc-{disable-warning,option} that follow fail because -Werror gets added to test for the presence of this warning: clang-14: warning: optimization flag '-falign-jumps=0' is not supported [-Wignored-optimization-argument] To resolve this, add a couple of cc-option calls when building with clang; gcc has supported these options since 3.2 so there is no point in testing for their support. -falign-functions was implemented in clang-7, -falign-loops was implemented in clang-14, and -falign-jumps has not been implemented yet. Link: https://lore.kernel.org/r/YSQE2f5teuvKLkON@Ryzen-9-3900X.localdomain/ Link: https://lore.kernel.org/r/20210824022640.2170859-2-nathan@kernel.org/ Reported-by: kernel test robot Reviewed-by: Nick Desaulniers Acked-by: Borislav Petkov Signed-off-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- arch/x86/Makefile_32.cpu | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index e7355f8b51c2..94834c4b5e5e 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -4,6 +4,12 @@ tune = $(call cc-option,-mtune=$(1),$(2)) +ifdef CONFIG_CC_IS_CLANG +align := -falign-functions=0 $(call cc-option,-falign-jumps=0) $(call cc-option,-falign-loops=0) +else +align := -falign-functions=0 -falign-jumps=0 -falign-loops=0 +endif + cflags-$(CONFIG_M486SX) += -march=i486 cflags-$(CONFIG_M486) += -march=i486 cflags-$(CONFIG_M586) += -march=i586 @@ -19,11 +25,11 @@ cflags-$(CONFIG_MK6) += -march=k6 # They make zero difference whatsosever to performance at this time. cflags-$(CONFIG_MK7) += -march=athlon cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -cflags-$(CONFIG_MCRUSOE) += -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0 -cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0 +cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align) +cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align) cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) -cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0 +cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align) cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) += -march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) From 0664684e1ebd7875e120d0cecd525bac4805f8ed Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 16 Sep 2021 11:40:17 -0700 Subject: [PATCH 418/866] kbuild: Add -Werror=ignored-optimization-argument to CLANG_FLAGS Similar to commit 589834b3a009 ("kbuild: Add -Werror=unknown-warning-option to CLANG_FLAGS"). Clang ignores certain GCC flags that it has not implemented, only emitting a warning: $ echo | clang -fsyntax-only -falign-jumps -x c - clang-14: warning: optimization flag '-falign-jumps' is not supported [-Wignored-optimization-argument] When one of these flags gets added to KBUILD_CFLAGS unconditionally, all subsequent cc-{disable-warning,option} calls fail because -Werror was added to these invocations to turn the above warning and the equivalent -W flag warning into errors. To catch the presence of these flags earlier, turn -Wignored-optimization-argument into an error so that the flags can either be implemented or ignored via cc-option and there are no more weird errors. Reviewed-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- scripts/Makefile.clang | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/scripts/Makefile.clang b/scripts/Makefile.clang index 4cce8fd0779c..51fc23e2e9e5 100644 --- a/scripts/Makefile.clang +++ b/scripts/Makefile.clang @@ -29,7 +29,12 @@ CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) else CLANG_FLAGS += -fintegrated-as endif +# By default, clang only warns when it encounters an unknown warning flag or +# certain optimization flags it knows it has not implemented. +# Make it behave more like gcc by erroring when these flags are encountered +# so they can be implemented or wrapped in cc-option. CLANG_FLAGS += -Werror=unknown-warning-option +CLANG_FLAGS += -Werror=ignored-optimization-argument KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_AFLAGS += $(CLANG_FLAGS) export CLANG_FLAGS From f0c15b360fb65ee39849afe987c16eb3d0175d0d Mon Sep 17 00:00:00 2001 From: Sean Young Date: Tue, 14 Sep 2021 16:57:46 +0200 Subject: [PATCH 419/866] media: ir_toy: prevent device from hanging during transmit If the IR Toy is receiving IR while a transmit is done, it may end up hanging. We can prevent this from happening by re-entering sample mode just before issuing the transmit command. Link: https://github.com/bengtmartensson/HarcHardware/discussions/25 Cc: stable@vger.kernel.org Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- drivers/media/rc/ir_toy.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c index 3e729a17b35f..48d52baec1a1 100644 --- a/drivers/media/rc/ir_toy.c +++ b/drivers/media/rc/ir_toy.c @@ -24,6 +24,7 @@ static const u8 COMMAND_VERSION[] = { 'v' }; // End transmit and repeat reset command so we exit sump mode static const u8 COMMAND_RESET[] = { 0xff, 0xff, 0, 0, 0, 0, 0 }; static const u8 COMMAND_SMODE_ENTER[] = { 's' }; +static const u8 COMMAND_SMODE_EXIT[] = { 0 }; static const u8 COMMAND_TXSTART[] = { 0x26, 0x24, 0x25, 0x03 }; #define REPLY_XMITCOUNT 't' @@ -309,12 +310,30 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count) buf[i] = cpu_to_be16(v); } - buf[count] = cpu_to_be16(0xffff); + buf[count] = 0xffff; irtoy->tx_buf = buf; irtoy->tx_len = size; irtoy->emitted = 0; + // There is an issue where if the unit is receiving IR while the + // first TXSTART command is sent, the device might end up hanging + // with its led on. It does not respond to any command when this + // happens. To work around this, re-enter sample mode. + err = irtoy_command(irtoy, COMMAND_SMODE_EXIT, + sizeof(COMMAND_SMODE_EXIT), STATE_RESET); + if (err) { + dev_err(irtoy->dev, "exit sample mode: %d\n", err); + return err; + } + + err = irtoy_command(irtoy, COMMAND_SMODE_ENTER, + sizeof(COMMAND_SMODE_ENTER), STATE_COMMAND); + if (err) { + dev_err(irtoy->dev, "enter sample mode: %d\n", err); + return err; + } + err = irtoy_command(irtoy, COMMAND_TXSTART, sizeof(COMMAND_TXSTART), STATE_TX); kfree(buf); From cf9579976f724ad517cc15b7caadea728c7e245c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:32 +0300 Subject: [PATCH 420/866] net: mdio: introduce a shutdown method to mdio device drivers MDIO-attached devices might have interrupts and other things that might need quiesced when we kexec into a new kernel. Things are even more creepy when those interrupt lines are shared, and in that case it is absolutely mandatory to disable all interrupt sources. Moreover, MDIO devices might be DSA switches, and DSA needs its own shutdown method to unlink from the DSA master, which is a new requirement that appeared after commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"). So introduce a ->shutdown method in the MDIO device driver structure. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/mdio_device.c | 11 +++++++++++ include/linux/mdio.h | 3 +++ 2 files changed, 14 insertions(+) diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index c94cb5382dc9..250742ffdfd9 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -179,6 +179,16 @@ static int mdio_remove(struct device *dev) return 0; } +static void mdio_shutdown(struct device *dev) +{ + struct mdio_device *mdiodev = to_mdio_device(dev); + struct device_driver *drv = mdiodev->dev.driver; + struct mdio_driver *mdiodrv = to_mdio_driver(drv); + + if (mdiodrv->shutdown) + mdiodrv->shutdown(mdiodev); +} + /** * mdio_driver_register - register an mdio_driver with the MDIO layer * @drv: new mdio_driver to register @@ -193,6 +203,7 @@ int mdio_driver_register(struct mdio_driver *drv) mdiodrv->driver.bus = &mdio_bus_type; mdiodrv->driver.probe = mdio_probe; mdiodrv->driver.remove = mdio_remove; + mdiodrv->driver.shutdown = mdio_shutdown; retval = driver_register(&mdiodrv->driver); if (retval) { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ffb787d5ebde..5e6dc38f418e 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -80,6 +80,9 @@ struct mdio_driver { /* Clears up any memory if needed */ void (*remove)(struct mdio_device *mdiodev); + + /* Quiesces the device on system shutdown, turns off interrupts etc */ + void (*shutdown)(struct mdio_device *mdiodev); }; static inline struct mdio_driver * From 0650bf52b31ff35dc6430fc2e37969c36baba724 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:33 +0300 Subject: [PATCH 421/866] net: dsa: be compatible with masters which unregister on shutdown Lino reports that on his system with bcmgenet as DSA master and KSZ9897 as a switch, rebooting or shutting down never works properly. What does the bcmgenet driver have special to trigger this, that other DSA masters do not? It has an implementation of ->shutdown which simply calls its ->remove implementation. Otherwise said, it unregisters its network interface on shutdown. This message can be seen in a loop, and it hangs the reboot process there: unregister_netdevice: waiting for eth0 to become free. Usage count = 3 So why 3? A usage count of 1 is normal for a registered network interface, and any virtual interface which links itself as an upper of that will increment it via dev_hold. In the case of DSA, this is the call path: dsa_slave_create -> netdev_upper_dev_link -> __netdev_upper_dev_link -> __netdev_adjacent_dev_insert -> dev_hold So a DSA switch with 3 interfaces will result in a usage count elevated by two, and netdev_wait_allrefs will wait until they have gone away. Other stacked interfaces, like VLAN, watch NETDEV_UNREGISTER events and delete themselves, but DSA cannot just vanish and go poof, at most it can unbind itself from the switch devices, but that must happen strictly earlier compared to when the DSA master unregisters its net_device, so reacting on the NETDEV_UNREGISTER event is way too late. It seems that it is a pretty established pattern to have a driver's ->shutdown hook redirect to its ->remove hook, so the same code is executed regardless of whether the driver is unbound from the device, or the system is just shutting down. As Florian puts it, it is quite a big hammer for bcmgenet to unregister its net_device during shutdown, but having a common code path with the driver unbind helps ensure it is well tested. So DSA, for better or for worse, has to live with that and engage in an arms race of implementing the ->shutdown hook too, from all individual drivers, and do something sane when paired with masters that unregister their net_device there. The only sane thing to do, of course, is to unlink from the master. However, complications arise really quickly. The pattern of redirecting ->shutdown to ->remove is not unique to bcmgenet or even to net_device drivers. In fact, SPI controllers do it too (see dspi_shutdown -> dspi_remove), and presumably, I2C controllers and MDIO controllers do it too (this is something I have not researched too deeply, but even if this is not the case today, it is certainly plausible to happen in the future, and must be taken into consideration). Since DSA switches might be SPI devices, I2C devices, MDIO devices, the insane implication is that for the exact same DSA switch device, we might have both ->shutdown and ->remove getting called. So we need to do something with that insane environment. The pattern I've come up with is "if this, then not that", so if either ->shutdown or ->remove gets called, we set the device's drvdata to NULL, and in the other hook, we check whether the drvdata is NULL and just do nothing. This is probably not necessary for platform devices, just for devices on buses, but I would really insist for consistency among drivers, because when code is copy-pasted, it is not always copy-pasted from the best sources. So depending on whether the DSA switch's ->remove or ->shutdown will get called first, we cannot really guarantee even for the same driver if rebooting will result in the same code path on all platforms. But nonetheless, we need to do something minimally reasonable on ->shutdown too to fix the bug. Of course, the ->remove will do more (a full teardown of the tree, with all data structures freed, and this is why the bug was not caught for so long). The new ->shutdown method is kept separate from dsa_unregister_switch not because we couldn't have unregistered the switch, but simply in the interest of doing something quick and to the point. The big question is: does the DSA switch's ->shutdown get called earlier than the DSA master's ->shutdown? If not, there is still a risk that we might still trigger the WARN_ON in unregister_netdevice that says we are attempting to unregister a net_device which has uppers. That's no good. Although the reference to the master net_device won't physically go away even if DSA's ->shutdown comes afterwards, remember we have a dev_hold on it. The answer to that question lies in this comment above device_link_add: * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). so the fact that DSA uses device_link_add towards its master is not exactly for nothing. device_shutdown() walks devices_kset from the back, so this is our guarantee that DSA's shutdown happens before the master's shutdown. Fixes: 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Tested-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_mdio.c | 21 ++++++++- drivers/net/dsa/b53/b53_mmap.c | 13 ++++++ drivers/net/dsa/b53/b53_priv.h | 5 +++ drivers/net/dsa/b53/b53_spi.c | 13 ++++++ drivers/net/dsa/b53/b53_srab.c | 21 ++++++++- drivers/net/dsa/bcm_sf2.c | 12 ++++++ drivers/net/dsa/dsa_loop.c | 22 +++++++++- drivers/net/dsa/lan9303-core.c | 6 +++ drivers/net/dsa/lan9303.h | 1 + drivers/net/dsa/lan9303_i2c.c | 24 +++++++++-- drivers/net/dsa/lan9303_mdio.c | 15 +++++++ drivers/net/dsa/lantiq_gswip.c | 18 ++++++++ drivers/net/dsa/microchip/ksz8795_spi.c | 11 ++++- drivers/net/dsa/microchip/ksz9477_i2c.c | 14 +++++- drivers/net/dsa/microchip/ksz9477_spi.c | 8 +++- drivers/net/dsa/mt7530.c | 18 ++++++++ drivers/net/dsa/mv88e6060.c | 18 ++++++++ drivers/net/dsa/mv88e6xxx/chip.c | 22 +++++++++- drivers/net/dsa/ocelot/felix_vsc9959.c | 20 ++++++++- drivers/net/dsa/ocelot/seville_vsc9953.c | 20 ++++++++- drivers/net/dsa/qca/ar9331.c | 18 ++++++++ drivers/net/dsa/qca8k.c | 18 ++++++++ drivers/net/dsa/realtek-smi-core.c | 20 ++++++++- drivers/net/dsa/sja1105/sja1105_main.c | 21 ++++++++- drivers/net/dsa/vitesse-vsc73xx-core.c | 6 +++ drivers/net/dsa/vitesse-vsc73xx-platform.c | 22 +++++++++- drivers/net/dsa/vitesse-vsc73xx-spi.c | 22 +++++++++- drivers/net/dsa/vitesse-vsc73xx.h | 1 + include/net/dsa.h | 1 + net/dsa/dsa2.c | 50 ++++++++++++++++++++++ 30 files changed, 457 insertions(+), 24 deletions(-) diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index a533a90e3904..a7aeb3c132c9 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -351,9 +351,25 @@ static int b53_mdio_probe(struct mdio_device *mdiodev) static void b53_mdio_remove(struct mdio_device *mdiodev) { struct b53_device *dev = dev_get_drvdata(&mdiodev->dev); - struct dsa_switch *ds = dev->ds; - dsa_unregister_switch(ds); + if (!dev) + return; + + b53_switch_remove(dev); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void b53_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct b53_device *dev = dev_get_drvdata(&mdiodev->dev); + + if (!dev) + return; + + b53_switch_shutdown(dev); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id b53_of_match[] = { @@ -373,6 +389,7 @@ MODULE_DEVICE_TABLE(of, b53_of_match); static struct mdio_driver b53_mdio_driver = { .probe = b53_mdio_probe, .remove = b53_mdio_remove, + .shutdown = b53_mdio_shutdown, .mdiodrv.driver = { .name = "bcm53xx", .of_match_table = b53_of_match, diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c index 82680e083cc2..ae4c79d39bc0 100644 --- a/drivers/net/dsa/b53/b53_mmap.c +++ b/drivers/net/dsa/b53/b53_mmap.c @@ -316,9 +316,21 @@ static int b53_mmap_remove(struct platform_device *pdev) if (dev) b53_switch_remove(dev); + platform_set_drvdata(pdev, NULL); + return 0; } +static void b53_mmap_shutdown(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + + if (dev) + b53_switch_shutdown(dev); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id b53_mmap_of_table[] = { { .compatible = "brcm,bcm3384-switch" }, { .compatible = "brcm,bcm6328-switch" }, @@ -331,6 +343,7 @@ MODULE_DEVICE_TABLE(of, b53_mmap_of_table); static struct platform_driver b53_mmap_driver = { .probe = b53_mmap_probe, .remove = b53_mmap_remove, + .shutdown = b53_mmap_shutdown, .driver = { .name = "b53-switch", .of_match_table = b53_mmap_of_table, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 5d068acf7cf8..959a52d41f0a 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -228,6 +228,11 @@ static inline void b53_switch_remove(struct b53_device *dev) dsa_unregister_switch(dev->ds); } +static inline void b53_switch_shutdown(struct b53_device *dev) +{ + dsa_switch_shutdown(dev->ds); +} + #define b53_build_op(type_op_size, val_type) \ static inline int b53_##type_op_size(struct b53_device *dev, u8 page, \ u8 reg, val_type val) \ diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c index ecb9f7f6b335..01e37b75471e 100644 --- a/drivers/net/dsa/b53/b53_spi.c +++ b/drivers/net/dsa/b53/b53_spi.c @@ -321,9 +321,21 @@ static int b53_spi_remove(struct spi_device *spi) if (dev) b53_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } +static void b53_spi_shutdown(struct spi_device *spi) +{ + struct b53_device *dev = spi_get_drvdata(spi); + + if (dev) + b53_switch_shutdown(dev); + + spi_set_drvdata(spi, NULL); +} + static const struct of_device_id b53_spi_of_match[] = { { .compatible = "brcm,bcm5325" }, { .compatible = "brcm,bcm5365" }, @@ -344,6 +356,7 @@ static struct spi_driver b53_spi_driver = { }, .probe = b53_spi_probe, .remove = b53_spi_remove, + .shutdown = b53_spi_shutdown, }; module_spi_driver(b53_spi_driver); diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 3f4249de70c5..4591bb1c05d2 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -629,17 +629,34 @@ static int b53_srab_probe(struct platform_device *pdev) static int b53_srab_remove(struct platform_device *pdev) { struct b53_device *dev = platform_get_drvdata(pdev); - struct b53_srab_priv *priv = dev->priv; - b53_srab_intr_set(priv, false); + if (!dev) + return 0; + + b53_srab_intr_set(dev->priv, false); b53_switch_remove(dev); + platform_set_drvdata(pdev, NULL); + return 0; } +static void b53_srab_shutdown(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + + if (!dev) + return; + + b53_switch_shutdown(dev); + + platform_set_drvdata(pdev, NULL); +} + static struct platform_driver b53_srab_driver = { .probe = b53_srab_probe, .remove = b53_srab_remove, + .shutdown = b53_srab_shutdown, .driver = { .name = "b53-srab-switch", .of_match_table = b53_srab_of_match, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index b6c4b3adb171..7578a5c38df5 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1512,6 +1512,9 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) { struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); + if (!priv) + return 0; + priv->wol_ports_mask = 0; /* Disable interrupts */ bcm_sf2_intr_disable(priv); @@ -1523,6 +1526,8 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) if (priv->type == BCM7278_DEVICE_ID) reset_control_assert(priv->rcdev); + platform_set_drvdata(pdev, NULL); + return 0; } @@ -1530,6 +1535,9 @@ static void bcm_sf2_sw_shutdown(struct platform_device *pdev) { struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); + if (!priv) + return; + /* For a kernel about to be kexec'd we want to keep the GPHY on for a * successful MDIO bus scan to occur. If we did turn off the GPHY * before (e.g: port_disable), this will also power it back on. @@ -1538,6 +1546,10 @@ static void bcm_sf2_sw_shutdown(struct platform_device *pdev) */ if (priv->hw_params.num_gphy == 1) bcm_sf2_gphy_enable_set(priv->dev->ds, true); + + dsa_switch_shutdown(priv->dev->ds); + + platform_set_drvdata(pdev, NULL); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index bfdf3324aac3..e638e3eea911 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -340,10 +340,29 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) static void dsa_loop_drv_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); - struct dsa_loop_priv *ps = ds->priv; + struct dsa_loop_priv *ps; + + if (!ds) + return; + + ps = ds->priv; dsa_unregister_switch(ds); dev_put(ps->netdev); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void dsa_loop_drv_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static struct mdio_driver dsa_loop_drv = { @@ -352,6 +371,7 @@ static struct mdio_driver dsa_loop_drv = { }, .probe = dsa_loop_drv_probe, .remove = dsa_loop_drv_remove, + .shutdown = dsa_loop_drv_shutdown, }; #define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index d7ce281570b5..89f920289ae2 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1379,6 +1379,12 @@ int lan9303_remove(struct lan9303 *chip) } EXPORT_SYMBOL(lan9303_remove); +void lan9303_shutdown(struct lan9303 *chip) +{ + dsa_switch_shutdown(chip->ds); +} +EXPORT_SYMBOL(lan9303_shutdown); + MODULE_AUTHOR("Juergen Borleis "); MODULE_DESCRIPTION("Core driver for SMSC/Microchip LAN9303 three port ethernet switch"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h index 11f590b64701..c7f73efa50f0 100644 --- a/drivers/net/dsa/lan9303.h +++ b/drivers/net/dsa/lan9303.h @@ -10,3 +10,4 @@ extern const struct lan9303_phy_ops lan9303_indirect_phy_ops; int lan9303_probe(struct lan9303 *chip, struct device_node *np); int lan9303_remove(struct lan9303 *chip); +void lan9303_shutdown(struct lan9303 *chip); diff --git a/drivers/net/dsa/lan9303_i2c.c b/drivers/net/dsa/lan9303_i2c.c index 9bffaef65a04..8ca4713310fa 100644 --- a/drivers/net/dsa/lan9303_i2c.c +++ b/drivers/net/dsa/lan9303_i2c.c @@ -67,13 +67,28 @@ static int lan9303_i2c_probe(struct i2c_client *client, static int lan9303_i2c_remove(struct i2c_client *client) { - struct lan9303_i2c *sw_dev; + struct lan9303_i2c *sw_dev = i2c_get_clientdata(client); - sw_dev = i2c_get_clientdata(client); if (!sw_dev) - return -ENODEV; + return 0; - return lan9303_remove(&sw_dev->chip); + lan9303_remove(&sw_dev->chip); + + i2c_set_clientdata(client, NULL); + + return 0; +} + +static void lan9303_i2c_shutdown(struct i2c_client *client) +{ + struct lan9303_i2c *sw_dev = i2c_get_clientdata(client); + + if (!sw_dev) + return; + + lan9303_shutdown(&sw_dev->chip); + + i2c_set_clientdata(client, NULL); } /*-------------------------------------------------------------------------*/ @@ -97,6 +112,7 @@ static struct i2c_driver lan9303_i2c_driver = { }, .probe = lan9303_i2c_probe, .remove = lan9303_i2c_remove, + .shutdown = lan9303_i2c_shutdown, .id_table = lan9303_i2c_id, }; module_i2c_driver(lan9303_i2c_driver); diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c index 9cbe80460b53..bbb7032409ba 100644 --- a/drivers/net/dsa/lan9303_mdio.c +++ b/drivers/net/dsa/lan9303_mdio.c @@ -138,6 +138,20 @@ static void lan9303_mdio_remove(struct mdio_device *mdiodev) return; lan9303_remove(&sw_dev->chip); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void lan9303_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct lan9303_mdio *sw_dev = dev_get_drvdata(&mdiodev->dev); + + if (!sw_dev) + return; + + lan9303_shutdown(&sw_dev->chip); + + dev_set_drvdata(&mdiodev->dev, NULL); } /*-------------------------------------------------------------------------*/ @@ -155,6 +169,7 @@ static struct mdio_driver lan9303_mdio_driver = { }, .probe = lan9303_mdio_probe, .remove = lan9303_mdio_remove, + .shutdown = lan9303_mdio_shutdown, }; mdio_module_driver(lan9303_mdio_driver); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 267324889dd6..3ff4b7e177f3 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -2184,6 +2184,9 @@ static int gswip_remove(struct platform_device *pdev) struct gswip_priv *priv = platform_get_drvdata(pdev); int i; + if (!priv) + return 0; + /* disable the switch */ gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); @@ -2197,9 +2200,23 @@ static int gswip_remove(struct platform_device *pdev) for (i = 0; i < priv->num_gphy_fw; i++) gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + platform_set_drvdata(pdev, NULL); + return 0; } +static void gswip_shutdown(struct platform_device *pdev) +{ + struct gswip_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct gswip_hw_info gswip_xrx200 = { .max_ports = 7, .cpu_port = 6, @@ -2223,6 +2240,7 @@ MODULE_DEVICE_TABLE(of, gswip_of_match); static struct platform_driver gswip_driver = { .probe = gswip_probe, .remove = gswip_remove, + .shutdown = gswip_shutdown, .driver = { .name = "gswip", .of_match_table = gswip_of_match, diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index ea7550d1b634..866767b70d65 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -94,6 +94,8 @@ static int ksz8795_spi_remove(struct spi_device *spi) if (dev) ksz_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } @@ -101,8 +103,15 @@ static void ksz8795_spi_shutdown(struct spi_device *spi) { struct ksz_device *dev = spi_get_drvdata(spi); - if (dev && dev->dev_ops->shutdown) + if (!dev) + return; + + if (dev->dev_ops->shutdown) dev->dev_ops->shutdown(dev); + + dsa_switch_shutdown(dev->ds); + + spi_set_drvdata(spi, NULL); } static const struct of_device_id ksz8795_dt_ids[] = { diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 4e053a25d077..f3afb8b8c4cc 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -56,7 +56,10 @@ static int ksz9477_i2c_remove(struct i2c_client *i2c) { struct ksz_device *dev = i2c_get_clientdata(i2c); - ksz_switch_remove(dev); + if (dev) + ksz_switch_remove(dev); + + i2c_set_clientdata(i2c, NULL); return 0; } @@ -65,8 +68,15 @@ static void ksz9477_i2c_shutdown(struct i2c_client *i2c) { struct ksz_device *dev = i2c_get_clientdata(i2c); - if (dev && dev->dev_ops->shutdown) + if (!dev) + return; + + if (dev->dev_ops->shutdown) dev->dev_ops->shutdown(dev); + + dsa_switch_shutdown(dev->ds); + + i2c_set_clientdata(i2c, NULL); } static const struct i2c_device_id ksz9477_i2c_id[] = { diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index 15bc11b3cda4..e3cb0e6c9f6f 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -72,6 +72,8 @@ static int ksz9477_spi_remove(struct spi_device *spi) if (dev) ksz_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } @@ -79,8 +81,10 @@ static void ksz9477_spi_shutdown(struct spi_device *spi) { struct ksz_device *dev = spi_get_drvdata(spi); - if (dev && dev->dev_ops->shutdown) - dev->dev_ops->shutdown(dev); + if (dev) + dsa_switch_shutdown(dev->ds); + + spi_set_drvdata(spi, NULL); } static const struct of_device_id ksz9477_dt_ids[] = { diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d0cba2d1cd68..094737e5084a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -3286,6 +3286,9 @@ mt7530_remove(struct mdio_device *mdiodev) struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev); int ret = 0; + if (!priv) + return; + ret = regulator_disable(priv->core_pwr); if (ret < 0) dev_err(priv->dev, @@ -3301,11 +3304,26 @@ mt7530_remove(struct mdio_device *mdiodev) dsa_unregister_switch(priv->ds); mutex_destroy(&priv->reg_mutex); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mt7530_shutdown(struct mdio_device *mdiodev) +{ + struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static struct mdio_driver mt7530_mdio_driver = { .probe = mt7530_probe, .remove = mt7530_remove, + .shutdown = mt7530_shutdown, .mdiodrv.driver = { .name = "mt7530", .of_match_table = mt7530_of_match, diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 24b8219fd607..a4c6eb9a52d0 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -290,7 +290,24 @@ static void mv88e6060_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + if (!ds) + return; + dsa_unregister_switch(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mv88e6060_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id mv88e6060_of_match[] = { @@ -303,6 +320,7 @@ static const struct of_device_id mv88e6060_of_match[] = { static struct mdio_driver mv88e6060_driver = { .probe = mv88e6060_probe, .remove = mv88e6060_remove, + .shutdown = mv88e6060_shutdown, .mdiodrv.driver = { .name = "mv88e6060", .of_match_table = mv88e6060_of_match, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c45ca2473743..fb10422d2c33 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -6389,7 +6389,12 @@ out: static void mv88e6xxx_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); - struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_chip *chip; + + if (!ds) + return; + + chip = ds->priv; if (chip->info->ptp_support) { mv88e6xxx_hwtstamp_free(chip); @@ -6410,6 +6415,20 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mv88e6xxx_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id mv88e6xxx_of_match[] = { @@ -6433,6 +6452,7 @@ MODULE_DEVICE_TABLE(of, mv88e6xxx_of_match); static struct mdio_driver mv88e6xxx_driver = { .probe = mv88e6xxx_probe, .remove = mv88e6xxx_remove, + .shutdown = mv88e6xxx_shutdown, .mdiodrv.driver = { .name = "mv88e6085", .of_match_table = mv88e6xxx_of_match, diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9e2ac8e46619..11b42fd812e4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1472,9 +1472,10 @@ err_pci_enable: static void felix_pci_remove(struct pci_dev *pdev) { - struct felix *felix; + struct felix *felix = pci_get_drvdata(pdev); - felix = pci_get_drvdata(pdev); + if (!felix) + return; dsa_unregister_switch(felix->ds); @@ -1482,6 +1483,20 @@ static void felix_pci_remove(struct pci_dev *pdev) kfree(felix); pci_disable_device(pdev); + + pci_set_drvdata(pdev, NULL); +} + +static void felix_pci_shutdown(struct pci_dev *pdev) +{ + struct felix *felix = pci_get_drvdata(pdev); + + if (!felix) + return; + + dsa_switch_shutdown(felix->ds); + + pci_set_drvdata(pdev, NULL); } static struct pci_device_id felix_ids[] = { @@ -1498,6 +1513,7 @@ static struct pci_driver felix_vsc9959_pci_driver = { .id_table = felix_ids, .probe = felix_pci_probe, .remove = felix_pci_remove, + .shutdown = felix_pci_shutdown, }; module_pci_driver(felix_vsc9959_pci_driver); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index deae923c8b7a..de1d34a1f1e4 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1245,18 +1245,33 @@ err_alloc_felix: static int seville_remove(struct platform_device *pdev) { - struct felix *felix; + struct felix *felix = platform_get_drvdata(pdev); - felix = platform_get_drvdata(pdev); + if (!felix) + return 0; dsa_unregister_switch(felix->ds); kfree(felix->ds); kfree(felix); + platform_set_drvdata(pdev, NULL); + return 0; } +static void seville_shutdown(struct platform_device *pdev) +{ + struct felix *felix = platform_get_drvdata(pdev); + + if (!felix) + return; + + dsa_switch_shutdown(felix->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id seville_of_match[] = { { .compatible = "mscc,vsc9953-switch" }, { }, @@ -1266,6 +1281,7 @@ MODULE_DEVICE_TABLE(of, seville_of_match); static struct platform_driver seville_vsc9953_driver = { .probe = seville_probe, .remove = seville_remove, + .shutdown = seville_shutdown, .driver = { .name = "mscc_seville", .of_match_table = of_match_ptr(seville_of_match), diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 563d8a279030..a6bfb6abc51a 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -1083,6 +1083,9 @@ static void ar9331_sw_remove(struct mdio_device *mdiodev) struct ar9331_sw_priv *priv = dev_get_drvdata(&mdiodev->dev); unsigned int i; + if (!priv) + return; + for (i = 0; i < ARRAY_SIZE(priv->port); i++) { struct ar9331_sw_port *port = &priv->port[i]; @@ -1094,6 +1097,20 @@ static void ar9331_sw_remove(struct mdio_device *mdiodev) dsa_unregister_switch(&priv->ds); reset_control_assert(priv->sw_reset); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void ar9331_sw_shutdown(struct mdio_device *mdiodev) +{ + struct ar9331_sw_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(&priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id ar9331_sw_of_match[] = { @@ -1104,6 +1121,7 @@ static const struct of_device_id ar9331_sw_of_match[] = { static struct mdio_driver ar9331_sw_mdio_driver = { .probe = ar9331_sw_probe, .remove = ar9331_sw_remove, + .shutdown = ar9331_sw_shutdown, .mdiodrv.driver = { .name = AR9331_SW_NAME, .of_match_table = ar9331_sw_of_match, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index bda5a9bf4f52..a984f06f6f04 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1880,10 +1880,27 @@ qca8k_sw_remove(struct mdio_device *mdiodev) struct qca8k_priv *priv = dev_get_drvdata(&mdiodev->dev); int i; + if (!priv) + return; + for (i = 0; i < QCA8K_NUM_PORTS; i++) qca8k_port_set_status(priv, i, 0); dsa_unregister_switch(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void qca8k_sw_shutdown(struct mdio_device *mdiodev) +{ + struct qca8k_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } #ifdef CONFIG_PM_SLEEP @@ -1940,6 +1957,7 @@ static const struct of_device_id qca8k_of_match[] = { static struct mdio_driver qca8kmdio_driver = { .probe = qca8k_sw_probe, .remove = qca8k_sw_remove, + .shutdown = qca8k_sw_shutdown, .mdiodrv.driver = { .name = "qca8k", .of_match_table = qca8k_of_match, diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c index 8e49d4f85d48..dd2f0d6208b3 100644 --- a/drivers/net/dsa/realtek-smi-core.c +++ b/drivers/net/dsa/realtek-smi-core.c @@ -464,16 +464,33 @@ static int realtek_smi_probe(struct platform_device *pdev) static int realtek_smi_remove(struct platform_device *pdev) { - struct realtek_smi *smi = dev_get_drvdata(&pdev->dev); + struct realtek_smi *smi = platform_get_drvdata(pdev); + + if (!smi) + return 0; dsa_unregister_switch(smi->ds); if (smi->slave_mii_bus) of_node_put(smi->slave_mii_bus->dev.of_node); gpiod_set_value(smi->reset, 1); + platform_set_drvdata(pdev, NULL); + return 0; } +static void realtek_smi_shutdown(struct platform_device *pdev) +{ + struct realtek_smi *smi = platform_get_drvdata(pdev); + + if (!smi) + return; + + dsa_switch_shutdown(smi->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id realtek_smi_of_match[] = { { .compatible = "realtek,rtl8366rb", @@ -495,6 +512,7 @@ static struct platform_driver realtek_smi_driver = { }, .probe = realtek_smi_probe, .remove = realtek_smi_remove, + .shutdown = realtek_smi_shutdown, }; module_platform_driver(realtek_smi_driver); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 2f8cc6686c38..7c0db80eff00 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3335,13 +3335,29 @@ static int sja1105_probe(struct spi_device *spi) static int sja1105_remove(struct spi_device *spi) { struct sja1105_private *priv = spi_get_drvdata(spi); - struct dsa_switch *ds = priv->ds; - dsa_unregister_switch(ds); + if (!priv) + return 0; + + dsa_unregister_switch(priv->ds); + + spi_set_drvdata(spi, NULL); return 0; } +static void sja1105_shutdown(struct spi_device *spi) +{ + struct sja1105_private *priv = spi_get_drvdata(spi); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + spi_set_drvdata(spi, NULL); +} + static const struct of_device_id sja1105_dt_ids[] = { { .compatible = "nxp,sja1105e", .data = &sja1105e_info }, { .compatible = "nxp,sja1105t", .data = &sja1105t_info }, @@ -3365,6 +3381,7 @@ static struct spi_driver sja1105_driver = { }, .probe = sja1105_probe, .remove = sja1105_remove, + .shutdown = sja1105_shutdown, }; module_spi_driver(sja1105_driver); diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 19ce4aa0973b..a4b1447ff055 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1225,6 +1225,12 @@ int vsc73xx_remove(struct vsc73xx *vsc) } EXPORT_SYMBOL(vsc73xx_remove); +void vsc73xx_shutdown(struct vsc73xx *vsc) +{ + dsa_switch_shutdown(vsc->ds); +} +EXPORT_SYMBOL(vsc73xx_shutdown); + MODULE_AUTHOR("Linus Walleij "); MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/vitesse-vsc73xx-platform.c b/drivers/net/dsa/vitesse-vsc73xx-platform.c index 2a57f337b2a2..fe4b154a0a57 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-platform.c +++ b/drivers/net/dsa/vitesse-vsc73xx-platform.c @@ -116,7 +116,26 @@ static int vsc73xx_platform_remove(struct platform_device *pdev) { struct vsc73xx_platform *vsc_platform = platform_get_drvdata(pdev); - return vsc73xx_remove(&vsc_platform->vsc); + if (!vsc_platform) + return 0; + + vsc73xx_remove(&vsc_platform->vsc); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static void vsc73xx_platform_shutdown(struct platform_device *pdev) +{ + struct vsc73xx_platform *vsc_platform = platform_get_drvdata(pdev); + + if (!vsc_platform) + return; + + vsc73xx_shutdown(&vsc_platform->vsc); + + platform_set_drvdata(pdev, NULL); } static const struct vsc73xx_ops vsc73xx_platform_ops = { @@ -144,6 +163,7 @@ MODULE_DEVICE_TABLE(of, vsc73xx_of_match); static struct platform_driver vsc73xx_platform_driver = { .probe = vsc73xx_platform_probe, .remove = vsc73xx_platform_remove, + .shutdown = vsc73xx_platform_shutdown, .driver = { .name = "vsc73xx-platform", .of_match_table = vsc73xx_of_match, diff --git a/drivers/net/dsa/vitesse-vsc73xx-spi.c b/drivers/net/dsa/vitesse-vsc73xx-spi.c index 81eca4a5781d..645398901e05 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-spi.c +++ b/drivers/net/dsa/vitesse-vsc73xx-spi.c @@ -163,7 +163,26 @@ static int vsc73xx_spi_remove(struct spi_device *spi) { struct vsc73xx_spi *vsc_spi = spi_get_drvdata(spi); - return vsc73xx_remove(&vsc_spi->vsc); + if (!vsc_spi) + return 0; + + vsc73xx_remove(&vsc_spi->vsc); + + spi_set_drvdata(spi, NULL); + + return 0; +} + +static void vsc73xx_spi_shutdown(struct spi_device *spi) +{ + struct vsc73xx_spi *vsc_spi = spi_get_drvdata(spi); + + if (!vsc_spi) + return; + + vsc73xx_shutdown(&vsc_spi->vsc); + + spi_set_drvdata(spi, NULL); } static const struct vsc73xx_ops vsc73xx_spi_ops = { @@ -191,6 +210,7 @@ MODULE_DEVICE_TABLE(of, vsc73xx_of_match); static struct spi_driver vsc73xx_spi_driver = { .probe = vsc73xx_spi_probe, .remove = vsc73xx_spi_remove, + .shutdown = vsc73xx_spi_shutdown, .driver = { .name = "vsc73xx-spi", .of_match_table = vsc73xx_of_match, diff --git a/drivers/net/dsa/vitesse-vsc73xx.h b/drivers/net/dsa/vitesse-vsc73xx.h index 7478f8d4e0a9..30b951504e65 100644 --- a/drivers/net/dsa/vitesse-vsc73xx.h +++ b/drivers/net/dsa/vitesse-vsc73xx.h @@ -27,3 +27,4 @@ struct vsc73xx_ops { int vsc73xx_is_addr_valid(u8 block, u8 subblock); int vsc73xx_probe(struct vsc73xx *vsc); int vsc73xx_remove(struct vsc73xx *vsc); +void vsc73xx_shutdown(struct vsc73xx *vsc); diff --git a/include/net/dsa.h b/include/net/dsa.h index 258867eff230..6e29c0e080f6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1046,6 +1046,7 @@ static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); +void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index eef13cd20f19..fa88e58705f0 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1562,3 +1562,53 @@ void dsa_unregister_switch(struct dsa_switch *ds) mutex_unlock(&dsa2_mutex); } EXPORT_SYMBOL_GPL(dsa_unregister_switch); + +/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is + * blocking that operation from completion, due to the dev_hold taken inside + * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of + * the DSA master, so that the system can reboot successfully. + */ +void dsa_switch_shutdown(struct dsa_switch *ds) +{ + struct net_device *master, *slave_dev; + LIST_HEAD(unregister_list); + struct dsa_port *dp; + + mutex_lock(&dsa2_mutex); + rtnl_lock(); + + list_for_each_entry(dp, &ds->dst->ports, list) { + if (dp->ds != ds) + continue; + + if (!dsa_port_is_user(dp)) + continue; + + master = dp->cpu_dp->master; + slave_dev = dp->slave; + + netdev_upper_dev_unlink(master, slave_dev); + /* Just unlinking ourselves as uppers of the master is not + * sufficient. When the master net device unregisters, that will + * also call dev_close, which we will catch as NETDEV_GOING_DOWN + * and trigger a dev_close on our own devices (dsa_slave_close). + * In turn, that will call dev_mc_unsync on the master's net + * device. If the master is also a DSA switch port, this will + * trigger dsa_slave_set_rx_mode which will call dev_mc_sync on + * its own master. Lockdep will complain about the fact that + * all cascaded masters have the same dsa_master_addr_list_lock_key, + * which it normally would not do if the cascaded masters would + * be in a proper upper/lower relationship, which we've just + * destroyed. + * To suppress the lockdep warnings, let's actually unregister + * the DSA slave interfaces too, to avoid the nonsensical + * multicast address list synchronization on shutdown. + */ + unregister_netdevice_queue(slave_dev, &unregister_list); + } + unregister_netdevice_many(&unregister_list); + + rtnl_unlock(); + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_switch_shutdown); From 46baae56e1001a771a5d132aa883cb5605013ae2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:34 +0300 Subject: [PATCH 422/866] net: dsa: hellcreek: be compatible with masters which unregister on shutdown Since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), DSA gained a requirement which it did not fulfill, which is to unlink itself from the DSA master at shutdown time. Since the hellcreek driver was introduced after the bad commit, it has never worked with DSA masters which decide to unregister their net_device on shutdown, effectively hanging the reboot process. Hellcreek is a platform device driver, so we probably cannot have the oddities of ->shutdown and ->remove getting both called for the exact same struct device. But to be in line with the pattern from the other device drivers which are on slow buses, implement the same "if this then not that" pattern of either running the ->shutdown or the ->remove hook. The driver's current ->remove implementation makes that very easy because it already zeroes out its device_drvdata on ->remove. Fixes: e4b27ebc780f ("net: dsa: Add DSA driver for Hirschmann Hellcreek switches") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Acked-by: Kurt Kanzenbach Signed-off-by: David S. Miller --- drivers/net/dsa/hirschmann/hellcreek.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 542cfc4ccb08..354655f9ed00 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -1916,6 +1916,9 @@ static int hellcreek_remove(struct platform_device *pdev) { struct hellcreek *hellcreek = platform_get_drvdata(pdev); + if (!hellcreek) + return 0; + hellcreek_hwtstamp_free(hellcreek); hellcreek_ptp_free(hellcreek); dsa_unregister_switch(hellcreek->ds); @@ -1924,6 +1927,18 @@ static int hellcreek_remove(struct platform_device *pdev) return 0; } +static void hellcreek_shutdown(struct platform_device *pdev) +{ + struct hellcreek *hellcreek = platform_get_drvdata(pdev); + + if (!hellcreek) + return; + + dsa_switch_shutdown(hellcreek->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct hellcreek_platform_data de1soc_r1_pdata = { .name = "r4c30", .num_ports = 4, @@ -1946,6 +1961,7 @@ MODULE_DEVICE_TABLE(of, hellcreek_of_match); static struct platform_driver hellcreek_driver = { .probe = hellcreek_probe, .remove = hellcreek_remove, + .shutdown = hellcreek_shutdown, .driver = { .name = "hellcreek", .of_match_table = hellcreek_of_match, From fe4053078cd0f02a3fa140c43660f327702a9f10 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:35 +0300 Subject: [PATCH 423/866] net: dsa: microchip: ksz8863: be compatible with masters which unregister on shutdown Since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), DSA gained a requirement which it did not fulfill, which is to unlink itself from the DSA master at shutdown time. Since the Microchip sub-driver for KSZ8863 was introduced after the bad commit, it has never worked with DSA masters which decide to unregister their net_device on shutdown, effectively hanging the reboot process. To fix that, we need to call dsa_switch_shutdown. Since this driver expects the MDIO bus to be backed by mdio_bitbang, I don't think there is currently any MDIO bus driver which implements its ->shutdown by redirecting it to ->remove, but in any case, to be compatible with that pattern, it is necessary to implement an "if this then not that" scheme, to avoid ->remove and ->shutdown from being called both for the same struct device. Fixes: 60a364760002 ("net: dsa: microchip: Add Microchip KSZ8863 SMI based driver support") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8863_smi.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c index 11293485138c..5883fa7edda2 100644 --- a/drivers/net/dsa/microchip/ksz8863_smi.c +++ b/drivers/net/dsa/microchip/ksz8863_smi.c @@ -191,6 +191,18 @@ static void ksz8863_smi_remove(struct mdio_device *mdiodev) if (dev) ksz_switch_remove(dev); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void ksz8863_smi_shutdown(struct mdio_device *mdiodev) +{ + struct ksz_device *dev = dev_get_drvdata(&mdiodev->dev); + + if (dev) + dsa_switch_shutdown(dev->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id ksz8863_dt_ids[] = { @@ -203,6 +215,7 @@ MODULE_DEVICE_TABLE(of, ksz8863_dt_ids); static struct mdio_driver ksz8863_driver = { .probe = ksz8863_smi_probe, .remove = ksz8863_smi_remove, + .shutdown = ksz8863_smi_shutdown, .mdiodrv.driver = { .name = "ksz8863-switch", .of_match_table = ksz8863_dt_ids, From a68e9da48568a0adf5dc817ef81971c0d1aa0672 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:36 +0300 Subject: [PATCH 424/866] net: dsa: xrs700x: be compatible with masters which unregister on shutdown Since commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"), DSA gained a requirement which it did not fulfill, which is to unlink itself from the DSA master at shutdown time. Since the Arrow SpeedChips XRS700x driver was introduced after the bad commit, it has never worked with DSA masters which decide to unregister their net_device on shutdown, effectively hanging the reboot process. To fix that, we need to call dsa_switch_shutdown. These devices can be connected by I2C or by MDIO, and if I search for I2C or MDIO bus drivers that implement their ->shutdown by redirecting it to ->remove I don't see any, however this does not mean it would not be possible. To be compatible with that pattern, it is necessary to implement an "if this then not that" scheme, to avoid ->remove and ->shutdown from being called both for the same struct device. Fixes: ee00b24f32eb ("net: dsa: add Arrow SpeedChips XRS700x driver") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Reviewed-by: George McCollister Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/xrs700x/xrs700x.c | 6 ++++++ drivers/net/dsa/xrs700x/xrs700x.h | 1 + drivers/net/dsa/xrs700x/xrs700x_i2c.c | 18 ++++++++++++++++++ drivers/net/dsa/xrs700x/xrs700x_mdio.c | 18 ++++++++++++++++++ 4 files changed, 43 insertions(+) diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 130abb0f1438..469420941054 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -822,6 +822,12 @@ void xrs700x_switch_remove(struct xrs700x *priv) } EXPORT_SYMBOL(xrs700x_switch_remove); +void xrs700x_switch_shutdown(struct xrs700x *priv) +{ + dsa_switch_shutdown(priv->ds); +} +EXPORT_SYMBOL(xrs700x_switch_shutdown); + MODULE_AUTHOR("George McCollister "); MODULE_DESCRIPTION("Arrow SpeedChips XRS700x DSA driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/xrs700x/xrs700x.h b/drivers/net/dsa/xrs700x/xrs700x.h index ff62cf61b091..4d58257471d2 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.h +++ b/drivers/net/dsa/xrs700x/xrs700x.h @@ -40,3 +40,4 @@ struct xrs700x { struct xrs700x *xrs700x_switch_alloc(struct device *base, void *devpriv); int xrs700x_switch_register(struct xrs700x *priv); void xrs700x_switch_remove(struct xrs700x *priv); +void xrs700x_switch_shutdown(struct xrs700x *priv); diff --git a/drivers/net/dsa/xrs700x/xrs700x_i2c.c b/drivers/net/dsa/xrs700x/xrs700x_i2c.c index 489d9385b4f0..6deae388a0d6 100644 --- a/drivers/net/dsa/xrs700x/xrs700x_i2c.c +++ b/drivers/net/dsa/xrs700x/xrs700x_i2c.c @@ -109,11 +109,28 @@ static int xrs700x_i2c_remove(struct i2c_client *i2c) { struct xrs700x *priv = i2c_get_clientdata(i2c); + if (!priv) + return 0; + xrs700x_switch_remove(priv); + i2c_set_clientdata(i2c, NULL); + return 0; } +static void xrs700x_i2c_shutdown(struct i2c_client *i2c) +{ + struct xrs700x *priv = i2c_get_clientdata(i2c); + + if (!priv) + return; + + xrs700x_switch_shutdown(priv); + + i2c_set_clientdata(i2c, NULL); +} + static const struct i2c_device_id xrs700x_i2c_id[] = { { "xrs700x-switch", 0 }, {}, @@ -137,6 +154,7 @@ static struct i2c_driver xrs700x_i2c_driver = { }, .probe = xrs700x_i2c_probe, .remove = xrs700x_i2c_remove, + .shutdown = xrs700x_i2c_shutdown, .id_table = xrs700x_i2c_id, }; diff --git a/drivers/net/dsa/xrs700x/xrs700x_mdio.c b/drivers/net/dsa/xrs700x/xrs700x_mdio.c index 44f58bee04a4..d01cf1073d49 100644 --- a/drivers/net/dsa/xrs700x/xrs700x_mdio.c +++ b/drivers/net/dsa/xrs700x/xrs700x_mdio.c @@ -136,7 +136,24 @@ static void xrs700x_mdio_remove(struct mdio_device *mdiodev) { struct xrs700x *priv = dev_get_drvdata(&mdiodev->dev); + if (!priv) + return; + xrs700x_switch_remove(priv); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void xrs700x_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct xrs700x *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + xrs700x_switch_shutdown(priv); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id __maybe_unused xrs700x_mdio_dt_ids[] = { @@ -155,6 +172,7 @@ static struct mdio_driver xrs700x_mdio_driver = { }, .probe = xrs700x_mdio_probe, .remove = xrs700x_mdio_remove, + .shutdown = xrs700x_mdio_shutdown, }; mdio_module_driver(xrs700x_mdio_driver); From 3ede7f84c7c21f93c5eac611d60eba3f2c765e0f Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 08:27:10 +0200 Subject: [PATCH 425/866] xen-netback: correct success/error reporting for the SKB-with-fraglist case When re-entering the main loop of xenvif_tx_check_gop() a 2nd time, the special considerations for the head of the SKB no longer apply. Don't mistakenly report ERROR to the frontend for the first entry in the list, even if - from all I can tell - this shouldn't matter much as the overall transmit will need to be considered failed anyway. Signed-off-by: Jan Beulich Reviewed-by: Paul Durrant Signed-off-by: David S. Miller --- drivers/net/xen-netback/netback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 39a01c2a3058..32d5bc4919d8 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -499,7 +499,7 @@ check_frags: * the header's copy failed, and they are * sharing a slot, send an error */ - if (i == 0 && sharedslot) + if (i == 0 && !first_shinfo && sharedslot) xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR); else From afd92d82c9d715fb97565408755acad81573591a Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 17 Sep 2021 16:34:06 +0800 Subject: [PATCH 426/866] virtio-net: fix pages leaking when building skb in big mode We try to use build_skb() if we had sufficient tailroom. But we forget to release the unused pages chained via private in big mode which will leak pages. Fixing this by release the pages after building the skb in big mode. Cc: Xuan Zhuo Fixes: fb32856b16ad ("virtio-net: page_to_skb() use build_skb when there's sufficient tailroom") Signed-off-by: Jason Wang Reviewed-by: Xuan Zhuo Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 271d38c1d9f8..79bd2585ec6b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -423,6 +423,10 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, skb_reserve(skb, p - buf); skb_put(skb, len); + + page = (struct page *)page->private; + if (page) + give_pages(rq, page); goto ok; } From 7237a494decfa17d0b9d0076e6cee3235719de90 Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 17 Sep 2021 13:22:05 +0300 Subject: [PATCH 427/866] enetc: Fix illegal access when reading affinity_hint irq_set_affinity_hit() stores a reference to the cpumask_t parameter in the irq descriptor, and that reference can be accessed later from irq_affinity_hint_proc_show(). Since the cpu_mask parameter passed to irq_set_affinity_hit() has only temporary storage (it's on the stack memory), later accesses to it are illegal. Thus reads from the corresponding procfs affinity_hint file can result in paging request oops. The issue is fixed by the get_cpu_mask() helper, which provides a permanent storage for the cpumask_t parameter. Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3ca93adb9662..7f90c27c0e79 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1879,7 +1879,6 @@ static void enetc_clear_bdrs(struct enetc_ndev_priv *priv) static int enetc_setup_irqs(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; - cpumask_t cpu_mask; int i, j, err; for (i = 0; i < priv->bdr_int_num; i++) { @@ -1908,9 +1907,7 @@ static int enetc_setup_irqs(struct enetc_ndev_priv *priv) enetc_wr(hw, ENETC_SIMSITRV(idx), entry); } - cpumask_clear(&cpu_mask); - cpumask_set_cpu(i % num_online_cpus(), &cpu_mask); - irq_set_affinity_hint(irq, &cpu_mask); + irq_set_affinity_hint(irq, get_cpu_mask(i % num_online_cpus())); } return 0; From 9f7afa05c9522b086327929ae622facab0f0f72b Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Fri, 17 Sep 2021 13:22:06 +0300 Subject: [PATCH 428/866] enetc: Fix uninitialized struct dim_sample field usage The only struct dim_sample member that does not get initialized by dim_update_sample() is comp_ctr. (There is special API to initialize comp_ctr: dim_update_sample_with_comps(), and it is currently used only for RDMA.) comp_ctr is used to compute curr_stats->cmps and curr_stats->cpe_ratio (see dim_calc_stats()) which in turn are consumed by the rdma_dim_*() API. Therefore, functionally, the net_dim*() API consumers are not affected. Nevertheless, fix the computation of statistics based on an uninitialized variable, even if the mentioned statistics are not used at the moment. Fixes: ae0e6a5d1627 ("enetc: Add adaptive interrupt coalescing") Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 7f90c27c0e79..042327b9981f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -419,7 +419,7 @@ static void enetc_rx_dim_work(struct work_struct *w) static void enetc_rx_net_dim(struct enetc_int_vector *v) { - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; v->comp_cnt++; From 87758511075ec961486fe78d7548dd709b524433 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Sep 2021 14:05:47 -0700 Subject: [PATCH 429/866] igc: fix build errors for PTP When IGC=y and PTP_1588_CLOCK=m, the ptp_*() interface family is not available to the igc driver. Make this driver depend on PTP_1588_CLOCK_OPTIONAL so that it will build without errors. Various igc commits have used ptp_*() functions without checking that PTP_1588_CLOCK is enabled. Fix all of these here. Fixes these build errors: ld: drivers/net/ethernet/intel/igc/igc_main.o: in function `igc_msix_other': igc_main.c:(.text+0x6494): undefined reference to `ptp_clock_event' ld: igc_main.c:(.text+0x64ef): undefined reference to `ptp_clock_event' ld: igc_main.c:(.text+0x6559): undefined reference to `ptp_clock_event' ld: drivers/net/ethernet/intel/igc/igc_ethtool.o: in function `igc_ethtool_get_ts_info': igc_ethtool.c:(.text+0xc7a): undefined reference to `ptp_clock_index' ld: drivers/net/ethernet/intel/igc/igc_ptp.o: in function `igc_ptp_feature_enable_i225': igc_ptp.c:(.text+0x330): undefined reference to `ptp_find_pin' ld: igc_ptp.c:(.text+0x36f): undefined reference to `ptp_find_pin' ld: drivers/net/ethernet/intel/igc/igc_ptp.o: in function `igc_ptp_init': igc_ptp.c:(.text+0x11cd): undefined reference to `ptp_clock_register' ld: drivers/net/ethernet/intel/igc/igc_ptp.o: in function `igc_ptp_stop': igc_ptp.c:(.text+0x12dd): undefined reference to `ptp_clock_unregister' ld: drivers/platform/x86/dell/dell-wmi-privacy.o: in function `dell_privacy_wmi_probe': Fixes: 64433e5bf40ab ("igc: Enable internal i225 PPS") Fixes: 60dbede0c4f3d ("igc: Add support for ethtool GET_TS_INFO command") Fixes: 87938851b6efb ("igc: enable auxiliary PHC functions for the i225") Fixes: 5f2958052c582 ("igc: Add basic skeleton for PTP") Signed-off-by: Randy Dunlap Cc: Ederson de Souza Cc: Tony Nguyen Cc: Vinicius Costa Gomes Cc: Jeff Kirsher Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jesse Brandeburg Cc: intel-wired-lan@lists.osuosl.org Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index b0b6f90deb7d..ed8ea63bb172 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -335,6 +335,7 @@ config IGC tristate "Intel(R) Ethernet Controller I225-LM/I225-V support" default n depends on PCI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports Intel(R) Ethernet Controller I225-LM/I225-V family of adapters. From 48e6d083b3aa006052db687fb26eeceef1d325b6 Mon Sep 17 00:00:00 2001 From: Alejandro Concepcion-Rodriguez Date: Fri, 17 Sep 2021 18:49:59 +0000 Subject: [PATCH 430/866] docs: net: dsa: sja1105: fix reference to sja1105.txt The file sja1105.txt was converted to nxp,sja1105.yaml. Signed-off-by: Alejandro Concepcion-Rodriguez Signed-off-by: David S. Miller --- Documentation/networking/dsa/sja1105.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index 564caeebe2b2..29b1bae0cf00 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -296,7 +296,7 @@ not available. Device Tree bindings and board design ===================================== -This section references ``Documentation/devicetree/bindings/net/dsa/sja1105.txt`` +This section references ``Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml`` and aims to showcase some potential switch caveats. RMII PHY role and out-of-band signaling From 2dcb96bacce36021c2f3eaae0cef607b5bb71ede Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 18 Sep 2021 14:42:35 +0200 Subject: [PATCH 431/866] net: core: Correct the sock::sk_lock.owned lockdep annotations lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It is just lockdep wise equivalent. In fact it's an open coded trivial mutex implementation with some interesting features. sock::sk_lock.slock is a regular spinlock protecting the 'mutex' representation sock::sk_lock.owned which is a plain boolean. If 'owned' is true, then some other task holds the 'mutex', otherwise it is uncontended. As this locking construct is obviously endangered by lock ordering issues as any other locking primitive it got lockdep annotated via a dedicated dependency map sock::sk_lock.dep_map which has to be updated at the lock and unlock sites. lock_sock_nested() is a straight forward 'mutex' lock operation: might_sleep(); spin_lock_bh(sock::sk_lock.slock) while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } The lockdep annotation for sock::sk_lock.owned is for unknown reasons _after_ the lock has been acquired, i.e. after the code block above and after releasing sock::sk_lock.slock, but inside the bottom halves disabled region: spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); The placement after the unlock is obvious because otherwise the mutex_acquire() would nest into the spin lock held region. But that's from the lockdep perspective still the wrong place: 1) The mutex_acquire() is issued _after_ the successful acquisition which is pointless because in a dead lock scenario this point is never reached which means that if the deadlock is the first instance of exposing the wrong lock order lockdep does not have a chance to detect it. 2) It only works because lockdep is rather lax on the context from which the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves and therefore non-preemptible region is obviously invalid, except for a trylock which is clearly not the case here. This 'works' stops working on RT enabled kernels where the bottom halves serialization is done via a local lock, which exposes this misplacement because the 'mutex' and the local lock nest the wrong way around and lockdep complains rightfully about a lock inversion. The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH] lockdep: annotate sk_locks") which introduced this. Fix it by moving the mutex_acquire() in front of the actual lock acquisition, which is what the regular mutex_lock() operation does as well. lock_sock_fast() is not that straight forward. It looks at the first glance like a convoluted trylock operation: spin_lock_bh(sock::sk_lock.slock) if (!sock::sk_lock.owned) return false; while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); return true; But that's not the case: lock_sock_fast() is an interesting optimization for short critical sections which can run with bottom halves disabled and sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in the non contended case by preventing other lockers to acquire sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which in turn avoids the overhead of doing the heavy processing in release_sock() including waking up wait queue waiters. In the contended case, i.e. when sock::sk_lock.owned == true the behavior is the same as lock_sock_nested(). Semantically this shortcut means, that the task acquired the 'mutex' even if it does not touch the sock::sk_lock.owned field in the non-contended case. Not telling lockdep about this shortcut acquisition is hiding potential lock ordering violations in the fast path. As a consequence the same reasoning as for the above lock_sock_nested() case vs. the placement of the lockdep annotation applies. The current placement of the lockdep annotation was just copied from the original lock_sock(), now renamed to lock_sock_nested(), implementation. Fix this by moving the mutex_acquire() in front of the actual lock acquisition and adding the corresponding mutex_release() into unlock_sock_fast(). Also document the fast path return case with a comment. Reported-by: Sebastian Siewior Signed-off-by: Thomas Gleixner Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 1 + net/core/sock.c | 37 +++++++++++++++++++++++-------------- 2 files changed, 24 insertions(+), 14 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 66a9a90f9558..c005c3c750e8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1640,6 +1640,7 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) release_sock(sk); __release(&sk->sk_lock.slock); } else { + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } diff --git a/net/core/sock.c b/net/core/sock.c index 62627e868e03..512e629f9780 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3179,17 +3179,15 @@ EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); + might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); - /* - * The sk_lock has mutex_lock() semantics here: - */ - mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); - local_bh_enable(); + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); @@ -3227,24 +3225,35 @@ EXPORT_SYMBOL(release_sock); */ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (!sk->sk_lock.owned) + if (!sk->sk_lock.owned) { /* - * Note : We must disable BH + * Fast path return with bottom halves disabled and + * sock::sk_lock.slock held. + * + * The 'mutex' is not contended and holding + * sock::sk_lock.slock prevents all other lockers to + * proceed so the corresponding unlock_sock_fast() can + * avoid the slow path of release_sock() completely and + * just release slock. + * + * From a semantical POV this is equivalent to 'acquiring' + * the 'mutex', hence the corresponding lockdep + * mutex_release() has to happen in the fast path of + * unlock_sock_fast(). */ return false; + } __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); - /* - * The sk_lock has mutex_lock() semantics here: - */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); __acquire(&sk->sk_lock.slock); - local_bh_enable(); + spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(lock_sock_fast); From 163957c43d96c2409d9d9d2e94823f7300f6e52c Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Fri, 17 Sep 2021 08:39:04 -0700 Subject: [PATCH 432/866] net: mscc: ocelot: remove buggy and useless write to ANA_PFC_PFC_CFG A useless write to ANA_PFC_PFC_CFG was left in while refactoring ocelot to phylink. Since priority flow control is disabled, writing the speed has no effect. Further, it was using ethtool.h SPEED_ instead of OCELOT_SPEED_ macros, which are incorrectly offset for GENMASK. Lastly, for priority flow control to properly function, some scenarios would rely on the rate adaptation from the PCS while the MAC speed would be fixed. So it isn't used, and even if it was, neither "speed" nor "mac_speed" are necessarily the correct values to be used. Fixes: e6e12df625f2 ("net: mscc: ocelot: convert to phylink") Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index c581b955efb3..08be0440af28 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -569,10 +569,6 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, ocelot_port_writel(ocelot_port, DEV_CLOCK_CFG_LINK_SPEED(speed), DEV_CLOCK_CFG); - /* No PFC */ - ocelot_write_gix(ocelot, ANA_PFC_PFC_CFG_FC_LINK_SPEED(speed), - ANA_PFC_PFC_CFG, port); - /* Core: Enable port for frame transfer */ ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); From ba68e9941984792f7e8a7be90b8245eb0d2b4d7b Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Fri, 17 Sep 2021 08:39:05 -0700 Subject: [PATCH 433/866] net: mscc: ocelot: remove buggy duplicate write to DEV_CLOCK_CFG When updating ocelot to use phylink, a second write to DEV_CLOCK_CFG was mistakenly left in. It used the variable "speed" which, previously, would would have been assigned a value of OCELOT_SPEED_1000. In phylink the variable is be SPEED_1000, which is invalid for the DEV_CLOCK_LINK_SPEED macro. Removing it as unnecessary and buggy. Fixes: e6e12df625f2 ("net: mscc: ocelot: convert to phylink") Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 08be0440af28..729ba826ba17 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -563,12 +563,6 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, ocelot_port_writel(ocelot_port, DEV_MAC_ENA_CFG_RX_ENA | DEV_MAC_ENA_CFG_TX_ENA, DEV_MAC_ENA_CFG); - /* Take MAC, Port, Phy (intern) and PCS (SGMII/Serdes) clock out of - * reset - */ - ocelot_port_writel(ocelot_port, DEV_CLOCK_CFG_LINK_SPEED(speed), - DEV_CLOCK_CFG); - /* Core: Enable port for frame transfer */ ocelot_fields_write(ocelot, port, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1); From fdb475838539cb516caeeeaed06b4b5bc62c9179 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Sep 2021 11:20:58 +0200 Subject: [PATCH 434/866] net: freescale: drop unneeded MODULE_ALIAS The MODULE_DEVICE_TABLE already creates proper alias for platform driver. Having another MODULE_ALIAS causes the alias to be duplicated. Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 80bd5c629fa0..ec87b370bba1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4176,5 +4176,4 @@ static struct platform_driver fec_driver = { module_platform_driver(fec_driver); -MODULE_ALIAS("platform:"DRIVER_NAME); MODULE_LICENSE("GPL"); From fd292c189a979838622d5e03e15fa688c81dd50b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 17:29:16 +0300 Subject: [PATCH 435/866] net: dsa: tear down devlink port regions when tearing down the devlink port on error Commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal") decided it was fine to ignore errors on certain ports that fail to probe, and go on with the ports that do probe fine. Commit fb6ec87f7229 ("net: dsa: Fix type was not set for devlink port") noticed that devlink_port_type_eth_set(dlp, dp->slave); does not get called, and devlink notices after a timeout of 3600 seconds and prints a WARN_ON. So it went ahead to unregister the devlink port. And because there exists an UNUSED port flavour, we actually re-register the devlink port as UNUSED. Commit 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") added devlink port regions, which are set up by the driver and not by DSA. When we trigger the devlink port deregistration and reregistration as unused, devlink now prints another WARN_ON, from here: devlink_port_unregister: WARN_ON(!list_empty(&devlink_port->region_list)); So the port still has regions, which makes sense, because they were set up by the driver, and the driver doesn't know we're unregistering the devlink port. Somebody needs to tear them down, and optionally (actually it would be nice, to be consistent) set them up again for the new devlink port. But DSA's layering stays in our way quite badly here. The options I've considered are: 1. Introduce a function in devlink to just change a port's type and flavour. No dice, devlink keeps a lot of state, it really wants the port to not be registered when you set its parameters, so changing anything can only be done by destroying what we currently have and recreating it. 2. Make DSA cache the parameters passed to dsa_devlink_port_region_create, and the region returned, keep those in a list, then when the devlink port unregister needs to take place, the existing devlink regions are destroyed by DSA, and we replay the creation of new regions using the cached parameters. Problem: mv88e6xxx keeps the region pointers in chip->ports[port].region, and these will remain stale after DSA frees them. There are many things DSA can do, but updating mv88e6xxx's private pointers is not one of them. 3. Just let the driver do it (i.e. introduce a very specific method called ds->ops->port_reinit_as_unused, which unregisters its devlink port devlink regions, then the old devlink port, then registers the new one, then the devlink port regions for it). While it does work, as opposed to the others, it's pretty horrible from an API perspective and we can do better. 4. Introduce a new pair of methods, ->port_setup and ->port_teardown, which in the case of mv88e6xxx must register and unregister the devlink port regions. Call these 2 methods when the port must be reinitialized as unused. Naturally, I went for the 4th approach. Fixes: 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 16 ++++++- drivers/net/dsa/mv88e6xxx/devlink.c | 73 ++++------------------------- drivers/net/dsa/mv88e6xxx/devlink.h | 6 ++- include/net/dsa.h | 8 ++++ net/dsa/dsa2.c | 51 ++++++++++++++++++-- 5 files changed, 81 insertions(+), 73 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index fb10422d2c33..8ab0be793811 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3071,7 +3071,7 @@ static void mv88e6xxx_teardown(struct dsa_switch *ds) { mv88e6xxx_teardown_devlink_params(ds); dsa_devlink_resources_unregister(ds); - mv88e6xxx_teardown_devlink_regions(ds); + mv88e6xxx_teardown_devlink_regions_global(ds); } static int mv88e6xxx_setup(struct dsa_switch *ds) @@ -3215,7 +3215,7 @@ unlock: if (err) goto out_resources; - err = mv88e6xxx_setup_devlink_regions(ds); + err = mv88e6xxx_setup_devlink_regions_global(ds); if (err) goto out_params; @@ -3229,6 +3229,16 @@ out_resources: return err; } +static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port) +{ + return mv88e6xxx_setup_devlink_regions_port(ds, port); +} + +static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port) +{ + mv88e6xxx_teardown_devlink_regions_port(ds, port); +} + /* prod_id for switch families which do not have a PHY model number */ static const u16 family_prod_id_table[] = { [MV88E6XXX_FAMILY_6341] = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, @@ -6116,6 +6126,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .change_tag_protocol = mv88e6xxx_change_tag_protocol, .setup = mv88e6xxx_setup, .teardown = mv88e6xxx_teardown, + .port_setup = mv88e6xxx_port_setup, + .port_teardown = mv88e6xxx_port_teardown, .phylink_validate = mv88e6xxx_validate, .phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state, .phylink_mac_config = mv88e6xxx_mac_config, diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 0c0f5ea6680c..381068395c63 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -647,26 +647,25 @@ static struct mv88e6xxx_region mv88e6xxx_regions[] = { }, }; -static void -mv88e6xxx_teardown_devlink_regions_global(struct mv88e6xxx_chip *chip) +void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds) { + struct mv88e6xxx_chip *chip = ds->priv; int i; for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++) dsa_devlink_region_destroy(chip->regions[i]); } -static void -mv88e6xxx_teardown_devlink_regions_port(struct mv88e6xxx_chip *chip, - int port) +void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port) { + struct mv88e6xxx_chip *chip = ds->priv; + dsa_devlink_region_destroy(chip->ports[port].region); } -static int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip, - int port) +int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, int port) { + struct mv88e6xxx_chip *chip = ds->priv; struct devlink_region *region; region = dsa_devlink_port_region_create(ds, @@ -681,40 +680,10 @@ static int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, return 0; } -static void -mv88e6xxx_teardown_devlink_regions_ports(struct mv88e6xxx_chip *chip) -{ - int port; - - for (port = 0; port < mv88e6xxx_num_ports(chip); port++) - mv88e6xxx_teardown_devlink_regions_port(chip, port); -} - -static int mv88e6xxx_setup_devlink_regions_ports(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip) -{ - int port; - int err; - - for (port = 0; port < mv88e6xxx_num_ports(chip); port++) { - err = mv88e6xxx_setup_devlink_regions_port(ds, chip, port); - if (err) - goto out; - } - - return 0; - -out: - while (port-- > 0) - mv88e6xxx_teardown_devlink_regions_port(chip, port); - - return err; -} - -static int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip) +int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds) { bool (*cond)(struct mv88e6xxx_chip *chip); + struct mv88e6xxx_chip *chip = ds->priv; struct devlink_region_ops *ops; struct devlink_region *region; u64 size; @@ -753,30 +722,6 @@ out: return PTR_ERR(region); } -int mv88e6xxx_setup_devlink_regions(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - err = mv88e6xxx_setup_devlink_regions_global(ds, chip); - if (err) - return err; - - err = mv88e6xxx_setup_devlink_regions_ports(ds, chip); - if (err) - mv88e6xxx_teardown_devlink_regions_global(chip); - - return err; -} - -void mv88e6xxx_teardown_devlink_regions(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds->priv; - - mv88e6xxx_teardown_devlink_regions_ports(chip); - mv88e6xxx_teardown_devlink_regions_global(chip); -} - int mv88e6xxx_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack) diff --git a/drivers/net/dsa/mv88e6xxx/devlink.h b/drivers/net/dsa/mv88e6xxx/devlink.h index 3d72db3dcf95..65ce6a6858b9 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.h +++ b/drivers/net/dsa/mv88e6xxx/devlink.h @@ -12,8 +12,10 @@ int mv88e6xxx_devlink_param_get(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int mv88e6xxx_devlink_param_set(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); -int mv88e6xxx_setup_devlink_regions(struct dsa_switch *ds); -void mv88e6xxx_teardown_devlink_regions(struct dsa_switch *ds); +int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds); +void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds); +int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, int port); +void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port); int mv88e6xxx_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, diff --git a/include/net/dsa.h b/include/net/dsa.h index 6e29c0e080f6..d784e76113b8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -585,8 +585,16 @@ struct dsa_switch_ops { int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); + + /* Per-port initialization and destruction methods. Mandatory if the + * driver registers devlink port regions, optional otherwise. + */ + int (*port_setup)(struct dsa_switch *ds, int port); + void (*port_teardown)(struct dsa_switch *ds, int port); + u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index fa88e58705f0..f14897d9b31d 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -429,6 +429,7 @@ static int dsa_port_setup(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; + struct dsa_switch *ds = dp->ds; bool dsa_port_enabled = false; int err = 0; @@ -438,6 +439,12 @@ static int dsa_port_setup(struct dsa_port *dp) INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); + if (ds->ops->port_setup) { + err = ds->ops->port_setup(ds, dp->index); + if (err) + return err; + } + switch (dp->type) { case DSA_PORT_TYPE_UNUSED: dsa_port_disable(dp); @@ -480,8 +487,11 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); if (err && dsa_port_link_registered) dsa_port_link_unregister_of(dp); - if (err) + if (err) { + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); return err; + } dp->setup = true; @@ -533,11 +543,15 @@ static int dsa_port_devlink_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a, *tmp; if (!dp->setup) return; + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + devlink_port_type_clear(dlp); switch (dp->type) { @@ -581,6 +595,36 @@ static void dsa_port_devlink_teardown(struct dsa_port *dp) dp->devlink_port_setup = false; } +/* Destroy the current devlink port, and create a new one which has the UNUSED + * flavour. At this point, any call to ds->ops->port_setup has been already + * balanced out by a call to ds->ops->port_teardown, so we know that any + * devlink port regions the driver had are now unregistered. We then call its + * ds->ops->port_setup again, in order for the driver to re-create them on the + * new devlink port. + */ +static int dsa_port_reinit_as_unused(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + int err; + + dsa_port_devlink_teardown(dp); + dp->type = DSA_PORT_TYPE_UNUSED; + err = dsa_port_devlink_setup(dp); + if (err) + return err; + + if (ds->ops->port_setup) { + /* On error, leave the devlink port registered, + * dsa_switch_teardown will clean it up later. + */ + err = ds->ops->port_setup(ds, dp->index); + if (err) + return err; + } + + return 0; +} + static int dsa_devlink_info_get(struct devlink *dl, struct devlink_info_req *req, struct netlink_ext_ack *extack) @@ -938,12 +982,9 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { err = dsa_port_setup(dp); if (err) { - dsa_port_devlink_teardown(dp); - dp->type = DSA_PORT_TYPE_UNUSED; - err = dsa_port_devlink_setup(dp); + err = dsa_port_reinit_as_unused(dp); if (err) goto teardown; - continue; } } From 029497e66bdc762e001880e4c85a91f35a54b1e2 Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Sun, 19 Sep 2021 13:57:25 +0200 Subject: [PATCH 436/866] net: bgmac-bcma: handle deferred probe error due to mac-address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Due to the inclusion of nvmem handling into the mac-address getter function of_get_mac_address() by commit d01f449c008a ("of_net: add NVMEM support to of_get_mac_address") it is now possible to get a -EPROBE_DEFER return code. Which did cause bgmac to assign a random ethernet address. This exact issue happened on my Meraki MR32. The nvmem provider is an EEPROM (at24c64) which gets instantiated once the module driver is loaded... This happens once the filesystem becomes available. With this patch, bgmac_probe() will propagate the -EPROBE_DEFER error. Then the driver subsystem will reschedule the probe at a later time. Cc: Petr Štetiar Cc: Michael Walle Fixes: d01f449c008a ("of_net: add NVMEM support to of_get_mac_address") Signed-off-by: Christian Lamparter Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 85fa0ab7201c..9513cfb5ba58 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -129,6 +129,8 @@ static int bgmac_probe(struct bcma_device *core) bcma_set_drvdata(core, bgmac); err = of_get_mac_address(bgmac->dev->of_node, bgmac->net_dev->dev_addr); + if (err == -EPROBE_DEFER) + return err; /* If no MAC address assigned via device tree, check SPROM */ if (err) { From 48514a22333099b93c33ea1c7c97dad3f7a611ce Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 17 Sep 2021 13:26:14 -0600 Subject: [PATCH 437/866] selftests: net: af_unix: Fix incorrect args in test result msg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the args to fprintf(). Splitting the message ends up passing incorrect arg for "sigurg %d" and an extra arg overall. The test result message ends up incorrect. test_unix_oob.c: In function ‘main’: test_unix_oob.c:274:43: warning: format ‘%d’ expects argument of type ‘int’, but argument 3 has type ‘char *’ [-Wformat=] 274 | fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", | ~^ | | | int | %s 275 | "atmark %d\n", signal_recvd, len, oob, atmark); | ~~~~~~~~~~~~~ | | | char * test_unix_oob.c:274:19: warning: too many arguments for format [-Wformat-extra-args] 274 | fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", Signed-off-by: Shuah Khan Signed-off-by: David S. Miller --- tools/testing/selftests/net/af_unix/test_unix_oob.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index 0f3e3763f4f8..3dece8b29253 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -271,8 +271,9 @@ main(int argc, char **argv) read_oob(pfd, &oob); if (!signal_recvd || len != 127 || oob != '%' || atmark != 1) { - fprintf(stderr, "Test 3 failed, sigurg %d len %d OOB %c ", - "atmark %d\n", signal_recvd, len, oob, atmark); + fprintf(stderr, + "Test 3 failed, sigurg %d len %d OOB %c atmark %d\n", + signal_recvd, len, oob, atmark); die(1); } From 72a3c58d18fd780eecd80178bb2132ce741a0a74 Mon Sep 17 00:00:00 2001 From: Lama Kayal Date: Sun, 19 Sep 2021 14:55:45 +0300 Subject: [PATCH 438/866] net/mlx4_en: Resolve bad operstate value Any link state change that's done prior to net device registration isn't reflected on the state, thus the operational state is left obsolete, with 'UNKNOWN' status. To resolve the issue, query link state from FW upon open operations to ensure operational state is updated. Fixes: c27a02cd94d6 ("mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC") Signed-off-by: Lama Kayal Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx4/en_netdev.c | 47 ++++++++++++------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 - 2 files changed, 29 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a2f61a87cef8..35154635ec3a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1269,7 +1269,6 @@ static void mlx4_en_do_set_rx_mode(struct work_struct *work) if (!netif_carrier_ok(dev)) { if (!mlx4_en_QUERY_PORT(mdev, priv->port)) { if (priv->port_state.link_state) { - priv->last_link_state = MLX4_DEV_EVENT_PORT_UP; netif_carrier_on(dev); en_dbg(LINK, priv, "Link Up\n"); } @@ -1557,26 +1556,36 @@ static void mlx4_en_service_task(struct work_struct *work) mutex_unlock(&mdev->state_lock); } -static void mlx4_en_linkstate(struct work_struct *work) +static void mlx4_en_linkstate(struct mlx4_en_priv *priv) +{ + struct mlx4_en_port_state *port_state = &priv->port_state; + struct mlx4_en_dev *mdev = priv->mdev; + struct net_device *dev = priv->dev; + bool up; + + if (mlx4_en_QUERY_PORT(mdev, priv->port)) + port_state->link_state = MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN; + + up = port_state->link_state == MLX4_PORT_STATE_DEV_EVENT_PORT_UP; + if (up == netif_carrier_ok(dev)) + netif_carrier_event(dev); + if (!up) { + en_info(priv, "Link Down\n"); + netif_carrier_off(dev); + } else { + en_info(priv, "Link Up\n"); + netif_carrier_on(dev); + } +} + +static void mlx4_en_linkstate_work(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, linkstate_task); struct mlx4_en_dev *mdev = priv->mdev; - int linkstate = priv->link_state; mutex_lock(&mdev->state_lock); - /* If observable port state changed set carrier state and - * report to system log */ - if (priv->last_link_state != linkstate) { - if (linkstate == MLX4_DEV_EVENT_PORT_DOWN) { - en_info(priv, "Link Down\n"); - netif_carrier_off(priv->dev); - } else { - en_info(priv, "Link Up\n"); - netif_carrier_on(priv->dev); - } - } - priv->last_link_state = linkstate; + mlx4_en_linkstate(priv); mutex_unlock(&mdev->state_lock); } @@ -2079,9 +2088,11 @@ static int mlx4_en_open(struct net_device *dev) mlx4_en_clear_stats(dev); err = mlx4_en_start_port(dev); - if (err) + if (err) { en_err(priv, "Failed starting port:%d\n", priv->port); - + goto out; + } + mlx4_en_linkstate(priv); out: mutex_unlock(&mdev->state_lock); return err; @@ -3168,7 +3179,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); INIT_WORK(&priv->restart_task, mlx4_en_restart); - INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); + INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate_work); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index f3d1a20201ef..6bf558c5ec10 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -552,7 +552,6 @@ struct mlx4_en_priv { struct mlx4_hwq_resources res; int link_state; - int last_link_state; bool port_up; int port; int registered; From e30cd812dffadc58241ae378e48728e6a161becd Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 17 Sep 2021 15:53:56 -0600 Subject: [PATCH 439/866] selftests: net: af_unix: Fix makefile to use TEST_GEN_PROGS Makefile uses TEST_PROGS instead of TEST_GEN_PROGS to define executables. TEST_PROGS is for shell scripts that need to be installed and run by the common lib.mk framework. The common framework doesn't touch TEST_PROGS when it does build and clean. As a result "make kselftest-clean" and "make clean" fail to remove executables. Run and install work because the common framework runs and installs TEST_PROGS. Build works because the Makefile defines "all" rule which is unnecessary if TEST_GEN_PROGS is used. Use TEST_GEN_PROGS so the common framework can handle build/run/ install/clean properly. Signed-off-by: Shuah Khan Signed-off-by: David S. Miller --- tools/testing/selftests/net/af_unix/Makefile | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index cfc7f4f97fd1..df341648f818 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,5 +1,2 @@ -##TEST_GEN_FILES := test_unix_oob -TEST_PROGS := test_unix_oob +TEST_GEN_PROGS := test_unix_oob include ../../lib.mk - -all: $(TEST_PROGS) From b1044a9b8100a0cc5c9d2e1e2f9ca4bb8e32b23a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 10:06:46 -0700 Subject: [PATCH 440/866] Revert drm/vc4 hdmi runtime PM changes This reverts commits 9984d6664ce9 ("drm/vc4: hdmi: Make sure the controller is powered in detect") 411efa18e4b0 ("drm/vc4: hdmi: Move the HSM clock enable to runtime_pm") as Michael Stapelberg reports that the new runtime PM changes cause his Raspberry Pi 3 to hang on boot, probably due to interactions with other changes in the DRM tree (because a bisect points to the merge in commit e058a84bfddc: "Merge tag 'drm-next-2021-07-01' of git://.../drm"). Revert these two commits until it's been resolved. Link: https://lore.kernel.org/all/871r5mp7h2.fsf@midna.i-did-not-set--mail-host-address--so-tickle-me/ Reported-and-tested-by: Michael Stapelberg Cc: Maxime Ripard Cc: Dave Stevenson Cc: Dave Airlie Signed-off-by: Linus Torvalds --- drivers/gpu/drm/vc4/vc4_hdmi.c | 44 ++++++++-------------------------- 1 file changed, 10 insertions(+), 34 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 4a1115043114..1acf64222aa3 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -167,8 +167,6 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); bool connected = false; - WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev)); - if (vc4_hdmi->hpd_gpio && gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio)) { connected = true; @@ -189,12 +187,10 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) } } - pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_connected; } cec_phys_addr_invalidate(vc4_hdmi->cec_adap); - pm_runtime_put(&vc4_hdmi->pdev->dev); return connector_status_disconnected; } @@ -635,6 +631,7 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder, vc4_hdmi->variant->phy_disable(vc4_hdmi); clk_disable_unprepare(vc4_hdmi->pixel_bvb_clock); + clk_disable_unprepare(vc4_hdmi->hsm_clock); clk_disable_unprepare(vc4_hdmi->pixel_clock); ret = pm_runtime_put(&vc4_hdmi->pdev->dev); @@ -947,6 +944,13 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, return; } + ret = clk_prepare_enable(vc4_hdmi->hsm_clock); + if (ret) { + DRM_ERROR("Failed to turn on HSM clock: %d\n", ret); + clk_disable_unprepare(vc4_hdmi->pixel_clock); + return; + } + vc4_hdmi_cec_update_clk_div(vc4_hdmi); if (pixel_rate > 297000000) @@ -959,6 +963,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, ret = clk_set_min_rate(vc4_hdmi->pixel_bvb_clock, bvb_rate); if (ret) { DRM_ERROR("Failed to set pixel bvb clock rate: %d\n", ret); + clk_disable_unprepare(vc4_hdmi->hsm_clock); clk_disable_unprepare(vc4_hdmi->pixel_clock); return; } @@ -966,6 +971,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, ret = clk_prepare_enable(vc4_hdmi->pixel_bvb_clock); if (ret) { DRM_ERROR("Failed to turn on pixel bvb clock: %d\n", ret); + clk_disable_unprepare(vc4_hdmi->hsm_clock); clk_disable_unprepare(vc4_hdmi->pixel_clock); return; } @@ -2114,29 +2120,6 @@ static int vc5_hdmi_init_resources(struct vc4_hdmi *vc4_hdmi) return 0; } -#ifdef CONFIG_PM -static int vc4_hdmi_runtime_suspend(struct device *dev) -{ - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - - clk_disable_unprepare(vc4_hdmi->hsm_clock); - - return 0; -} - -static int vc4_hdmi_runtime_resume(struct device *dev) -{ - struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - int ret; - - ret = clk_prepare_enable(vc4_hdmi->hsm_clock); - if (ret) - return ret; - - return 0; -} -#endif - static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) { const struct vc4_hdmi_variant *variant = of_device_get_match_data(dev); @@ -2391,18 +2374,11 @@ static const struct of_device_id vc4_hdmi_dt_match[] = { {} }; -static const struct dev_pm_ops vc4_hdmi_pm_ops = { - SET_RUNTIME_PM_OPS(vc4_hdmi_runtime_suspend, - vc4_hdmi_runtime_resume, - NULL) -}; - struct platform_driver vc4_hdmi_driver = { .probe = vc4_hdmi_dev_probe, .remove = vc4_hdmi_dev_remove, .driver = { .name = "vc4_hdmi", .of_match_table = vc4_hdmi_dt_match, - .pm = &vc4_hdmi_pm_ops, }, }; From 31ad37bd6faf871c070650f72ac9488ceeeceeb0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 10:11:53 -0700 Subject: [PATCH 441/866] Revert "drm/vc4: hdmi: Remove drm_encoder->crtc usage" This reverts commit 27da370e0fb343a0baf308f503bb3e5dcdfe3362. Sudip Mukherjee reports that this broke pulseaudio with a NULL pointer dereference in vc4_hdmi_audio_prepare(), bisected it to this commit, and confirmed that a revert fixed the problem. Revert the problematic commit until fixed. Link: https://lore.kernel.org/all/CADVatmPB9-oKd=ypvj25UYysVo6EZhQ6bCM7EvztQBMyiZfAyw@mail.gmail.com/ Link: https://lore.kernel.org/all/CADVatmN5EpRshGEPS_JozbFQRXg5w_8LFB3OMP1Ai-ghxd3w4g@mail.gmail.com/ Reported-and-tested-by: Sudip Mukherjee Cc: Maxime Ripard Cc: Emma Anholt Cc: Dave Airlie Signed-off-by: Linus Torvalds --- drivers/gpu/drm/vc4/vc4_hdmi.c | 40 +++++++++++----------------------- 1 file changed, 13 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 1acf64222aa3..b4b4653fe301 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -432,7 +432,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder) struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); struct drm_connector *connector = &vc4_hdmi->connector; struct drm_connector_state *cstate = connector->state; - struct drm_crtc *crtc = cstate->crtc; + struct drm_crtc *crtc = encoder->crtc; const struct drm_display_mode *mode = &crtc->state->adjusted_mode; union hdmi_infoframe frame; int ret; @@ -537,11 +537,8 @@ static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder, static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) { + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); - struct drm_connector *connector = &vc4_hdmi->connector; - struct drm_connector_state *cstate = connector->state; - struct drm_crtc *crtc = cstate->crtc; - struct drm_display_mode *mode = &crtc->state->adjusted_mode; if (!vc4_hdmi_supports_scrambling(encoder, mode)) return; @@ -562,18 +559,17 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); - struct drm_connector *connector = &vc4_hdmi->connector; - struct drm_connector_state *cstate = connector->state; + struct drm_crtc *crtc = encoder->crtc; /* - * At boot, connector->state will be NULL. Since we don't know the + * At boot, encoder->crtc will be NULL. Since we don't know the * state of the scrambler and in order to avoid any * inconsistency, let's disable it all the time. */ - if (cstate && !vc4_hdmi_supports_scrambling(encoder, &cstate->crtc->mode)) + if (crtc && !vc4_hdmi_supports_scrambling(encoder, &crtc->mode)) return; - if (cstate && !vc4_hdmi_mode_needs_scrambling(&cstate->crtc->mode)) + if (crtc && !vc4_hdmi_mode_needs_scrambling(&crtc->mode)) return; if (delayed_work_pending(&vc4_hdmi->scrambling_work)) @@ -895,9 +891,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, vc4_hdmi_encoder_get_connector_state(encoder, state); struct vc4_hdmi_connector_state *vc4_conn_state = conn_state_to_vc4_hdmi_conn_state(conn_state); - struct drm_crtc_state *crtc_state = - drm_atomic_get_new_crtc_state(state, conn_state->crtc); - struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); unsigned long bvb_rate, pixel_rate, hsm_rate; int ret; @@ -991,11 +985,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_connector_state *conn_state = - vc4_hdmi_encoder_get_connector_state(encoder, state); - struct drm_crtc_state *crtc_state = - drm_atomic_get_new_crtc_state(state, conn_state->crtc); - struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); @@ -1018,11 +1008,7 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder, static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_connector_state *conn_state = - vc4_hdmi_encoder_get_connector_state(encoder, state); - struct drm_crtc_state *crtc_state = - drm_atomic_get_new_crtc_state(state, conn_state->crtc); - struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC; @@ -1210,8 +1196,8 @@ static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi, static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi, unsigned int samplerate) { - struct drm_connector *connector = &vc4_hdmi->connector; - struct drm_crtc *crtc = connector->state->crtc; + struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; + struct drm_crtc *crtc = encoder->crtc; const struct drm_display_mode *mode = &crtc->state->adjusted_mode; u32 n, cts; u64 tmp; @@ -1244,13 +1230,13 @@ static inline struct vc4_hdmi *dai_to_hdmi(struct snd_soc_dai *dai) static int vc4_hdmi_audio_startup(struct device *dev, void *data) { struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - struct drm_connector *connector = &vc4_hdmi->connector; + struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; /* * If the HDMI encoder hasn't probed, or the encoder is * currently in DVI mode, treat the codec dai as missing. */ - if (!connector->state || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) & + if (!encoder->crtc || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) & VC4_HDMI_RAM_PACKET_ENABLE)) return -ENODEV; From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 19 Sep 2021 10:36:09 -0700 Subject: [PATCH 442/866] parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled Linus noticed odd declaration rules for pci_iounmap() in iomap.h and pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or GENERIC_IOMAP when CONFIG_PCI was disabled. Testing on parisc seems to indicate that we need pci_iounmap() only when CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved cleanly into pci_iomap.h in sync with the declarations of pci_iomap(). Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=O8nw@mail.gmail.com/ Signed-off-by: Helge Deller Suggested-by: Linus Torvalds Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional") Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- arch/parisc/lib/iomap.c | 4 +++- include/asm-generic/iomap.h | 10 ---------- include/asm-generic/pci_iomap.h | 3 +++ 3 files changed, 6 insertions(+), 11 deletions(-) diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index f03adb1999e7..367f6397bda7 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr) } } +#ifdef CONFIG_PCI void pci_iounmap(struct pci_dev *dev, void __iomem * addr) { if (!INDIRECT_ADDR(addr)) { iounmap(addr); } } +EXPORT_SYMBOL(pci_iounmap); +#endif EXPORT_SYMBOL(ioread8); EXPORT_SYMBOL(ioread16); @@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep); EXPORT_SYMBOL(iowrite32_rep); EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); -EXPORT_SYMBOL(pci_iounmap); diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 9b3eb6d86200..08237ae8b840 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) } #endif -#ifdef CONFIG_PCI -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ -struct pci_dev; -extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#elif defined(CONFIG_GENERIC_IOMAP) -struct pci_dev; -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ } -#endif - #include #endif diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index df636c6d8e6c..5a2f9bf53384 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, unsigned long offset, unsigned long maxlen); +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); /* Create a virtual mapping cookie for a port on a given PCI device. * Do not call this directly, it exists to make it easier for architectures * to override */ @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, { return NULL; } +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ } #endif #endif /* __ASM_GENERIC_PCI_IOMAP_H */ From 4fef6115903afed5a7f21b387ad132b4c8838bc7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 10:37:00 -0700 Subject: [PATCH 443/866] alpha: enable GENERIC_PCI_IOMAP unconditionally With the previous commit (9caea0007601: "parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") we can now enable GENERIC_PCI_IOMAP unconditionally on alpha, and if PCI is not enabled we will just get the nice empty helper functions that allow mixed-bus drivers to build. Example driver: the old 3com/3c59x.c driver works with either the PCI or the EISA version of the 3x59x card, but wouldn't build in an EISA-only configuration because of missing pci_iomap() and pci_iounmap() dummy wrappers. Most of the other PCI infrastructure just becomes empty wrappers even without GENERIC_PCI_IOMAP, and it's not obvious that the pci_iomap functionality shouldn't do the same, but this works. Cc: Ulrich Teichert Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 11e99358aa58..4e87783c90ad 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -20,7 +20,7 @@ config ALPHA select NEED_SG_DMA_LENGTH select VIRT_TO_BUS select GENERIC_IRQ_PROBE - select GENERIC_PCI_IOMAP if PCI + select GENERIC_PCI_IOMAP select AUTO_IRQ_AFFINITY if SMP select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION From bc1abb9e55cedaeac4602426f8fc83fb3a5b1c35 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 10:49:42 -0700 Subject: [PATCH 444/866] dmascc: use proper 'virt_to_bus()' rather than casting to 'int' The old dmascc driver depends on the legacy ISA_DMA_API, and blindly just casts the kernel virtual address to 'int' for set_dma_addr(). That works only incidentally, and because the high bits of the address will be ignored anyway. And on 64-bit architectures it causes warnings. Admittedly, 64-bit architectures with ISA are basically dead - I think the only example of this is alpha, and nobody would ever use the dmascc driver there. But hey, the fix is easy enough, the end result is cleaner, and it's yet another configuration that now builds without warnings. If somebody actually uses this driver on an alpha and this fixes it for you, please email me. Because that is just incredibly bizarre. Signed-off-by: Linus Torvalds --- drivers/net/hamradio/dmascc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c index b50b7fafd8d6..f4c3efc3e074 100644 --- a/drivers/net/hamradio/dmascc.c +++ b/drivers/net/hamradio/dmascc.c @@ -973,7 +973,7 @@ static inline void tx_on(struct scc_priv *priv) flags = claim_dma_lock(); set_dma_mode(priv->param.dma, DMA_MODE_WRITE); set_dma_addr(priv->param.dma, - (int) priv->tx_buf[priv->tx_tail] + n); + virt_to_bus(priv->tx_buf[priv->tx_tail]) + n); set_dma_count(priv->param.dma, priv->tx_len[priv->tx_tail] - n); release_dma_lock(flags); @@ -1020,7 +1020,7 @@ static inline void rx_on(struct scc_priv *priv) flags = claim_dma_lock(); set_dma_mode(priv->param.dma, DMA_MODE_READ); set_dma_addr(priv->param.dma, - (int) priv->rx_buf[priv->rx_head]); + virt_to_bus(priv->rx_buf[priv->rx_head])); set_dma_count(priv->param.dma, BUF_SIZE); release_dma_lock(flags); enable_dma(priv->param.dma); @@ -1233,7 +1233,7 @@ static void special_condition(struct scc_priv *priv, int rc) if (priv->param.dma >= 0) { flags = claim_dma_lock(); set_dma_addr(priv->param.dma, - (int) priv->rx_buf[priv->rx_head]); + virt_to_bus(priv->rx_buf[priv->rx_head])); set_dma_count(priv->param.dma, BUF_SIZE); release_dma_lock(flags); } else { From 316e8d79a0959c302b0c462ab64b069599f10eef Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 17:13:35 -0700 Subject: [PATCH 445/866] pci_iounmap'2: Electric Boogaloo: try to make sense of it all Nathan Chancellor reports that the recent change to pci_iounmap in commit 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") causes build errors on arm64. It took me about two hours to convince myself that I think I know what the logic of that mess of #ifdef's in the header file really aim to do, and rewrite it to be easier to follow. Famous last words. Anyway, the code has now been lifted from that grotty header file into lib/pci_iomap.c, and has fairly extensive comments about what the logic is. It also avoids indirecting through another confusing (and badly named) helper function that has other preprocessor config conditionals. Let's see what odd architecture did something else strange in this area to break things. But my arm64 cross build is clean. Fixes: 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") Reported-by: Nathan Chancellor Cc: Helge Deller Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- include/asm-generic/io.h | 26 +++--------------------- lib/pci_iomap.c | 43 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 23 deletions(-) diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..cc7338f9e0d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } -#define __pci_ioport_unmap __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) -{ - uintptr_t start = (uintptr_t) PCI_IOBASE; - uintptr_t addr = (uintptr_t) p; - - if (addr >= start && addr < start + IO_SPACE_LIMIT) - return; - iounmap(p); -} +#define ARCH_HAS_GENERIC_IOPORT_MAP #endif #ifndef ioport_unmap @@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) {} -#endif - #ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ - __pci_ioport_unmap(p); -} +#define ARCH_WANTS_GENERIC_PCI_IOUNMAP +#endif #endif -#endif /* CONFIG_GENERIC_IOMAP */ #ifndef xlate_dev_mem_ptr #define xlate_dev_mem_ptr xlate_dev_mem_ptr diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index 2d3eb1cb73b8..ce39ce9f3526 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -134,4 +134,47 @@ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) return pci_iomap_wc_range(dev, bar, 0, maxlen); } EXPORT_SYMBOL_GPL(pci_iomap_wc); + +/* + * pci_iounmap() somewhat illogically comes from lib/iomap.c for the + * CONFIG_GENERIC_IOMAP case, because that's the code that knows about + * the different IOMAP ranges. + * + * But if the architecture does not use the generic iomap code, and if + * it has _not_ defined it's own private pci_iounmap function, we define + * it here. + * + * NOTE! This default implementation assumes that if the architecture + * support ioport mapping (HAS_IOPORT_MAP), the ioport mapping will + * be fixed to the range [ PCI_IOBASE, PCI_IOBASE+IO_SPACE_LIMIT [, + * and does not need unmapping with 'ioport_unmap()'. + * + * If you have different rules for your architecture, you need to + * implement your own pci_iounmap() that knows the rules for where + * and how IO vs MEM get mapped. + * + * This code is odd, and the ARCH_HAS/ARCH_WANTS #define logic comes + * from legacy header file behavior. In particular, + * it would seem to make sense to do the iounmap(p) for the non-IO-space + * case here regardless, but that's not what the old header file code + * did. Probably incorrectly, but this is meant to be bug-for-bug + * compatible. + */ +#if defined(ARCH_WANTS_GENERIC_PCI_IOUNMAP) + +void pci_iounmap(struct pci_dev *dev, void __iomem *p) +{ +#ifdef ARCH_HAS_GENERIC_IOPORT_MAP + uintptr_t start = (uintptr_t) PCI_IOBASE; + uintptr_t addr = (uintptr_t) p; + + if (addr >= start && addr < start + IO_SPACE_LIMIT) + return; + iounmap(p); +#endif +} +EXPORT_SYMBOL(pci_iounmap); + +#endif /* ARCH_WANTS_GENERIC_PCI_IOUNMAP */ + #endif /* CONFIG_PCI */ From e4e737bb5c170df6135a127739a9e6148ee3da82 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 17:28:22 -0700 Subject: [PATCH 446/866] Linux 5.15-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 34a0afc3a8eb..5e7c1d854441 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Opossums on Parade # *DOCUMENTATION* From b51593c4cd739dff7fc40bbed368572d98b19ae8 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Fri, 17 Sep 2021 09:13:23 -0400 Subject: [PATCH 447/866] init/do_mounts.c: Harden split_fs_names() against buffer overflow split_fs_names() currently takes comma separate list of filesystems and converts it into individual filesystem strings. Pleaces these strings in the input buffer passed by caller and returns number of strings. If caller manages to pass input string bigger than buffer, then we can write beyond the buffer. Or if string just fits buffer, we will still write beyond the buffer as we append a '\0' byte at the end. Pass size of input buffer to split_fs_names() and put enough checks in place so such buffer overrun possibilities do not occur. This patch does few things. - Add a parameter "size" to split_fs_names(). This specifies size of input buffer. - Use strlcpy() (instead of strcpy()) so that we can't go beyond buffer size. If input string "names" is larger than passed in buffer, input string will be truncated to fit in buffer. - Stop appending extra '\0' character at the end and avoid one possibility of going beyond the input buffer size. - Do not use extra loop to count number of strings. - Previously if one passed "rootfstype=foo,,bar", split_fs_names() will return only 1 string "foo" (and "bar" will be truncated due to extra ,). After this patch, now split_fs_names() will return 3 strings ("foo", zero-sized-string, and "bar"). Callers of split_fs_names() have been modified to check for zero sized string and skip to next one. Reported-by: xu xin Signed-off-by: Vivek Goyal Reviewed-by: Jan Kara Signed-off-by: Al Viro --- init/do_mounts.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/init/do_mounts.c b/init/do_mounts.c index 2ed30ff6c906..9207bde9ca3f 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -338,20 +338,19 @@ __setup("rootflags=", root_data_setup); __setup("rootfstype=", fs_names_setup); __setup("rootdelay=", root_delay_setup); -static int __init split_fs_names(char *page, char *names) +/* This can return zero length strings. Caller should check */ +static int __init split_fs_names(char *page, size_t size, char *names) { - int count = 0; + int count = 1; char *p = page; - strcpy(p, root_fs_names); + strlcpy(p, root_fs_names, size); while (*p++) { - if (p[-1] == ',') + if (p[-1] == ',') { p[-1] = '\0'; + count++; + } } - *p = '\0'; - - for (p = page; *p; p += strlen(p)+1) - count++; return count; } @@ -404,12 +403,16 @@ void __init mount_block_root(char *name, int flags) scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)", MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); if (root_fs_names) - num_fs = split_fs_names(fs_names, root_fs_names); + num_fs = split_fs_names(fs_names, PAGE_SIZE, root_fs_names); else num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE); retry: for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) { - int err = do_mount_root(name, p, flags, root_mount_data); + int err; + + if (!*p) + continue; + err = do_mount_root(name, p, flags, root_mount_data); switch (err) { case 0: goto out; @@ -543,10 +546,12 @@ static int __init mount_nodev_root(void) fs_names = (void *)__get_free_page(GFP_KERNEL); if (!fs_names) return -EINVAL; - num_fs = split_fs_names(fs_names, root_fs_names); + num_fs = split_fs_names(fs_names, PAGE_SIZE, root_fs_names); for (i = 0, fstype = fs_names; i < num_fs; i++, fstype += strlen(fstype) + 1) { + if (!*fstype) + continue; if (!fs_is_nodev(fstype)) continue; err = do_mount_root(root_device_name, fstype, root_mountflags, From 40c8ee67cfc49d00a13ccbf542e307b6b5421ad3 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 14 Sep 2021 12:12:10 +0300 Subject: [PATCH 448/866] init: don't panic if mount_nodev_root failed Attempt to mount 9p file system as root gives the following kernel panic: 9pnet_virtio: no channels available for device root Kernel panic - not syncing: VFS: Unable to mount root "root" (9p), err=-2 CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.15.0-rc1+ #127 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x45/0x59 panic+0x1e2/0x44b ? __warn_printk+0xf3/0xf3 ? free_unref_page+0x2d4/0x4a0 ? trace_hardirqs_on+0x32/0x120 ? free_unref_page+0x2d4/0x4a0 mount_root+0x189/0x1e0 prepare_namespace+0x136/0x165 kernel_init_freeable+0x3b8/0x3cb ? rest_init+0x2e0/0x2e0 kernel_init+0x19/0x130 ret_from_fork+0x1f/0x30 Kernel Offset: disabled ---[ end Kernel panic - not syncing: VFS: Unable to mount root "root" (9p), err=-2 ]--- QEMU command line: "qemu-system-x86_64 -append root=/dev/root rw rootfstype=9p rootflags=trans=virtio ..." This error is because root_device_name is truncated in prepare_namespace() from being "/dev/root" to be "root" prior to call to mount_nodev_root(). As a solution, don't treat errors in mount_nodev_root() as errors that require panics and allow failback to the mount flow that existed before patch citied in Fixes tag. Fixes: f9259be6a9e7 ("init: allow mounting arbitrary non-blockdevice filesystems as root") Signed-off-by: Leon Romanovsky Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- init/do_mounts.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/init/do_mounts.c b/init/do_mounts.c index 9207bde9ca3f..762b534978d9 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -558,9 +558,6 @@ static int __init mount_nodev_root(void) root_mount_data); if (!err) break; - if (err != -EACCES && err != -EINVAL) - panic("VFS: Unable to mount root \"%s\" (%s), err=%d\n", - root_device_name, fstype, err); } free_page((unsigned long)fs_names); From 3765996e4f0b8a755cab215a08df744490c76052 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Sat, 18 Sep 2021 16:52:32 +0800 Subject: [PATCH 449/866] napi: fix race inside napi_enable The process will cause napi.state to contain NAPI_STATE_SCHED and not in the poll_list, which will cause napi_disable() to get stuck. The prefix "NAPI_STATE_" is removed in the figure below, and NAPI_STATE_HASHED is ignored in napi.state. CPU0 | CPU1 | napi.state =============================================================================== napi_disable() | | SCHED | NPSVC napi_enable() | | { | | smp_mb__before_atomic(); | | clear_bit(SCHED, &n->state); | | NPSVC | napi_schedule_prep() | SCHED | NPSVC | napi_poll() | | napi_complete_done() | | { | | if (n->state & (NPSVC | | (1) | _BUSY_POLL))) | | return false; | | ................ | | } | SCHED | NPSVC | | clear_bit(NPSVC, &n->state); | | SCHED } | | | | napi_schedule_prep() | | SCHED | MISSED (2) (1) Here return direct. Because of NAPI_STATE_NPSVC exists. (2) NAPI_STATE_SCHED exists. So not add napi.poll_list to sd->poll_list Since NAPI_STATE_SCHED already exists and napi is not in the sd->poll_list queue, NAPI_STATE_SCHED cannot be cleared and will always exist. 1. This will cause this queue to no longer receive packets. 2. If you encounter napi_disable under the protection of rtnl_lock, it will cause the entire rtnl_lock to be locked, affecting the overall system. This patch uses cmpxchg to implement napi_enable(), which ensures that there will be no race due to the separation of clear two bits. Fixes: 2d8bff12699abc ("netpoll: Close race condition between poll_one_napi and napi_disable") Signed-off-by: Xuan Zhuo Reviewed-by: Dust Li Signed-off-by: David S. Miller --- net/core/dev.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 74fd402d26dd..7ee9fecd3aff 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6923,12 +6923,16 @@ EXPORT_SYMBOL(napi_disable); */ void napi_enable(struct napi_struct *n) { - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - clear_bit(NAPI_STATE_NPSVC, &n->state); - if (n->dev->threaded && n->thread) - set_bit(NAPI_STATE_THREADED, &n->state); + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); + + new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); + if (n->dev->threaded && n->thread) + new |= NAPIF_STATE_THREADED; + } while (cmpxchg(&n->state, val, new) != val); } EXPORT_SYMBOL(napi_enable); From 563f23b002534176f49524b5ca0e1d94d8906c40 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 17 Sep 2021 16:02:18 +0300 Subject: [PATCH 450/866] nexthop: Fix division by zero while replacing a resilient group The resilient nexthop group torture tests in fib_nexthop.sh exposed a possible division by zero while replacing a resilient group [1]. The division by zero occurs when the data path sees a resilient nexthop group with zero buckets. The tests replace a resilient nexthop group in a loop while traffic is forwarded through it. The tests do not specify the number of buckets while performing the replacement, resulting in the kernel allocating a stub resilient table (i.e, 'struct nh_res_table') with zero buckets. This table should never be visible to the data path, but the old nexthop group (i.e., 'oldg') might still be used by the data path when the stub table is assigned to it. Fix this by only assigning the stub table to the old nexthop group after making sure the group is no longer used by the data path. Tested with fib_nexthops.sh: Tests passed: 222 Tests failed: 0 [1] divide error: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 1850 Comm: ping Not tainted 5.14.0-custom-10271-ga86eb53057fe #1107 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:nexthop_select_path+0x2d2/0x1a80 [...] Call Trace: fib_select_multipath+0x79b/0x1530 fib_select_path+0x8fb/0x1c10 ip_route_output_key_hash_rcu+0x1198/0x2da0 ip_route_output_key_hash+0x190/0x340 ip_route_output_flow+0x21/0x120 raw_sendmsg+0x91d/0x2e10 inet_sendmsg+0x9e/0xe0 __sys_sendto+0x23d/0x360 __x64_sys_sendto+0xe1/0x1b0 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Cc: stable@vger.kernel.org Fixes: 283a72a5599e ("nexthop: Add implementation of resilient next-hop groups") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 75ca4b6e484f..0e75fd3e57b4 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1982,6 +1982,8 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_grp, newg); if (newg->resilient) { + /* Make sure concurrent readers are not using 'oldg' anymore. */ + synchronize_net(); rcu_assign_pointer(oldg->res_table, tmp_table); rcu_assign_pointer(oldg->spare->res_table, tmp_table); } From 5bed8b0704c9ecccc8f4a2c377d7c8e21090a82e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 20 Sep 2021 02:51:52 -0400 Subject: [PATCH 451/866] bnxt_en: Fix TX timeout when TX ring size is set to the smallest The smallest TX ring size we support must fit a TX SKB with MAX_SKB_FRAGS + 1. Because the first TX BD for a packet is always a long TX BD, we need an extra TX BD to fit this packet. Define BNXT_MIN_TX_DESC_CNT with this value to make this more clear. The current code uses a minimum that is off by 1. Fix it using this constant. The tx_wake_thresh to determine when to wake up the TX queue is half the ring size but we must have at least BNXT_MIN_TX_DESC_CNT for the next packet which may have maximum fragments. So the comparison of the available TX BDs with tx_wake_thresh should be >= instead of > in the current code. Otherwise, at the smallest ring size, we will never wake up the TX queue and will cause TX timeout. Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Reviewed-by: Pavan Chebbi Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++---- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 +++++ drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 037767b370d5..62f84cc91e4d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -391,7 +391,7 @@ static bool bnxt_txr_netif_try_stop_queue(struct bnxt *bp, * netif_tx_queue_stopped(). */ smp_mb(); - if (bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh) { + if (bnxt_tx_avail(bp, txr) >= bp->tx_wake_thresh) { netif_tx_wake_queue(txq); return false; } @@ -764,7 +764,7 @@ next_tx_int: smp_mb(); if (unlikely(netif_tx_queue_stopped(txq)) && - bnxt_tx_avail(bp, txr) > bp->tx_wake_thresh && + bnxt_tx_avail(bp, txr) >= bp->tx_wake_thresh && READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING) netif_tx_wake_queue(txq); } @@ -2416,7 +2416,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) { tx_pkts++; /* return full budget so NAPI will complete. */ - if (unlikely(tx_pkts > bp->tx_wake_thresh)) { + if (unlikely(tx_pkts >= bp->tx_wake_thresh)) { rx_pkts = budget; raw_cons = NEXT_RAW_CMP(raw_cons); if (budget) @@ -3640,7 +3640,7 @@ static int bnxt_init_tx_rings(struct bnxt *bp) u16 i; bp->tx_wake_thresh = max_t(int, bp->tx_ring_size / 2, - MAX_SKB_FRAGS + 1); + BNXT_MIN_TX_DESC_CNT); for (i = 0; i < bp->tx_nr_rings; i++) { struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index ec046e7a2484..19fe6478e9b4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -629,6 +629,11 @@ struct nqe_cn { #define BNXT_MAX_RX_JUM_DESC_CNT (RX_DESC_CNT * MAX_RX_AGG_PAGES - 1) #define BNXT_MAX_TX_DESC_CNT (TX_DESC_CNT * MAX_TX_PAGES - 1) +/* Minimum TX BDs for a TX packet with MAX_SKB_FRAGS + 1. We need one extra + * BD because the first TX BD is always a long BD. + */ +#define BNXT_MIN_TX_DESC_CNT (MAX_SKB_FRAGS + 2) + #define RX_RING(x) (((x) & ~(RX_DESC_CNT - 1)) >> (BNXT_PAGE_SHIFT - 4)) #define RX_IDX(x) ((x) & (RX_DESC_CNT - 1)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index b056e3c29bbd..7260910e75fb 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -798,7 +798,7 @@ static int bnxt_set_ringparam(struct net_device *dev, if ((ering->rx_pending > BNXT_MAX_RX_DESC_CNT) || (ering->tx_pending > BNXT_MAX_TX_DESC_CNT) || - (ering->tx_pending <= MAX_SKB_FRAGS)) + (ering->tx_pending < BNXT_MIN_TX_DESC_CNT)) return -EINVAL; if (netif_running(dev)) From 211f323768a25b30c106fd38f15a0f62c7c2b5f4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Sep 2021 11:18:47 +0200 Subject: [PATCH 452/866] USB: serial: mos7840: remove duplicated 0xac24 device ID 0xac24 device ID is already defined and used via BANDB_DEVICE_ID_USO9ML2_4. Remove the duplicate from the list. Fixes: 27f1281d5f72 ("USB: serial: Extra device/vendor ID for mos7840 driver") Signed-off-by: Krzysztof Kozlowski Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/mos7840.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index d7fe33ca73e4..925067a7978d 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -107,7 +107,6 @@ #define BANDB_DEVICE_ID_USOPTL4_2P 0xBC02 #define BANDB_DEVICE_ID_USOPTL4_4 0xAC44 #define BANDB_DEVICE_ID_USOPTL4_4P 0xBC03 -#define BANDB_DEVICE_ID_USOPTL2_4 0xAC24 /* Interrupt Routine Defines */ @@ -186,7 +185,6 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL4_2P) }, { USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL4_4) }, { USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL4_4P) }, - { USB_DEVICE(USB_VENDOR_ID_BANDB, BANDB_DEVICE_ID_USOPTL2_4) }, {} /* terminating entry */ }; MODULE_DEVICE_TABLE(usb, id_table); From 1ca200a8c6f079950a04ea3c3380fe8cf78e95a2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Sep 2021 11:18:48 +0200 Subject: [PATCH 453/866] USB: serial: option: remove duplicate USB device ID The device ZTE 0x0094 is already on the list. Signed-off-by: Krzysztof Kozlowski Fixes: b9e44fe5ecda ("USB: option: cleanup zte 3g-dongle's pid in option.c") Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index a79f51e35115..02a35f26ee82 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1658,7 +1658,6 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0060, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0070, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0073, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0094, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0130, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0133, 0xff, 0xff, 0xff), From 42a99a0be307562c1bfef32bad8f89aa3c428edd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 11:57:49 +0200 Subject: [PATCH 454/866] ptp: ocp: add COMMON_CLK dependency Without CONFIG_COMMON_CLK, this fails to link: arm-linux-gnueabi-ld: drivers/ptp/ptp_ocp.o: in function `ptp_ocp_register_i2c': ptp_ocp.c:(.text+0xcc0): undefined reference to `__clk_hw_register_fixed_rate' arm-linux-gnueabi-ld: ptp_ocp.c:(.text+0xcf4): undefined reference to `devm_clk_hw_register_clkdev' arm-linux-gnueabi-ld: drivers/ptp/ptp_ocp.o: in function `ptp_ocp_detach': ptp_ocp.c:(.text+0x1c24): undefined reference to `clk_hw_unregister_fixed_rate' Fixes: a7e1abad13f3 ("ptp: Add clock driver for the OpenCompute TimeCard.") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/ptp/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index f02bedf41264..458218f88c5e 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -174,6 +174,7 @@ config PTP_1588_CLOCK_OCP depends on I2C && MTD depends on SERIAL_8250 depends on !S390 + depends on COMMON_CLK select NET_DEVLINK help This driver adds support for an OpenCompute time card. From aa3233ea7bdb6c4004f5032a3a07417ea51dc409 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 11:55:09 +0200 Subject: [PATCH 455/866] staging: r8188eu: fix -Wrestrict warnings Adding back the nonstandard ioctl commands caused -Wrestrict warnings when building with 'make W=1': drivers/staging/r8188eu/os_dep/ioctl_linux.c: In function 'rtw_mp_read_rf': drivers/staging/r8188eu/os_dep/ioctl_linux.c:5515:27: error: 'sprintf' argument 3 overlaps destination object 'extra' [-Werror=restrict] 5515 | sprintf(extra, "%s %d", extra, strtou); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/staging/r8188eu/os_dep/ioctl_linux.c:5470:54: note: destination object referenced by 'restrict'-qualified argument 1 was declared here 5470 | struct iw_point *wrqu, char *extra) | ~~~~~~^~~~~ Change these to the same construct used elsewhere in that driver, with an offset to the string to make the warning go away. The ioctl commands were previously removed, and it's unlikely that anything is actually using them, so ideally I would prefer to have them removed again. The lack of range checking of the 'extra' output buffer is also slightly worrying, but I did not check whether this could cause harm. Fixes: 2b42bd58b321 ("staging: r8188eu: introduce new os_dep dir for RTL8188eu driver") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210920095525.1150678-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/staging/r8188eu/os_dep/ioctl_linux.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/staging/r8188eu/os_dep/ioctl_linux.c b/drivers/staging/r8188eu/os_dep/ioctl_linux.c index 81d4255d1785..1fd375076001 100644 --- a/drivers/staging/r8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/r8188eu/os_dep/ioctl_linux.c @@ -5372,8 +5372,8 @@ static int rtw_mp_read_reg(struct net_device *dev, pnext++; if (*pnext != '\0') { - strtout = simple_strtoul(pnext, &ptmp, 16); - sprintf(extra, "%s %d", extra, strtout); + strtout = simple_strtoul(pnext, &ptmp, 16); + sprintf(extra + strlen(extra), " %d", strtout); } else { break; } @@ -5405,7 +5405,7 @@ static int rtw_mp_read_reg(struct net_device *dev, pnext++; if (*pnext != '\0') { strtout = simple_strtoul(pnext, &ptmp, 16); - sprintf(extra, "%s %d", extra, strtout); + sprintf(extra + strlen(extra), " %d", strtout); } else { break; } @@ -5512,7 +5512,7 @@ static int rtw_mp_read_rf(struct net_device *dev, pnext++; if (*pnext != '\0') { strtou = simple_strtoul(pnext, &ptmp, 16); - sprintf(extra, "%s %d", extra, strtou); + sprintf(extra + strlen(extra), " %d", strtou); } else { break; } From a49b50a3c1c3226d26e1dd11e8b763f27e477623 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Tue, 7 Sep 2021 13:21:37 +0800 Subject: [PATCH 456/866] KVM: arm64: nvhe: Fix missing FORCE for hyp-reloc.S build rule Add FORCE so that if_changed can detect the command line change. We'll otherwise see a compilation warning since commit e1f86d7b4b2a ("kbuild: warn if FORCE is missing for if_changed(_dep,_rule) and filechk"). arch/arm64/kvm/hyp/nvhe/Makefile:58: FORCE prerequisite is missing Cc: David Brazdil Cc: Masahiro Yamada Signed-off-by: Zenghui Yu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210907052137.1059-1-yuzenghui@huawei.com --- arch/arm64/kvm/hyp/nvhe/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 5df6193fc430..8d741f71377f 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -54,7 +54,7 @@ $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE # runtime. Because the hypervisor is part of the kernel binary, relocations # produce a kernel VA. We enumerate relocations targeting hyp at build time # and convert the kernel VAs at those positions to hyp VAs. -$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel +$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE $(call if_changed,hyprel) # 5) Compile hyp-reloc.S and link it into the existing partially linked object. From e840f42a49925707fca90e6c7a4095118fdb8c4d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 19 Sep 2021 14:09:49 +0100 Subject: [PATCH 457/866] KVM: arm64: Fix PMU probe ordering Russell reported that since 5.13, KVM's probing of the PMU has started to fail on his HW. As it turns out, there is an implicit ordering dependency between the architectural PMU probing code and and KVM's own probing. If, due to probe ordering reasons, KVM probes before the PMU driver, it will fail to detect the PMU and prevent it from being advertised to guests as well as the VMM. Obviously, this is one probing too many, and we should be able to deal with any ordering. Add a callback from the PMU code into KVM to advertise the registration of a host CPU PMU, allowing for any probing order. Fixes: 5421db1be3b1 ("KVM: arm64: Divorce the perf code from oprofile helpers") Reported-by: "Russell King (Oracle)" Tested-by: Russell King (Oracle) Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/YUYRKVflRtUytzy5@shell.armlinux.org.uk Cc: stable@vger.kernel.org --- arch/arm64/kvm/perf.c | 3 --- arch/arm64/kvm/pmu-emul.c | 9 ++++++++- drivers/perf/arm_pmu.c | 2 ++ include/kvm/arm_pmu.h | 3 --- include/linux/perf/arm_pmu.h | 6 ++++++ 5 files changed, 16 insertions(+), 7 deletions(-) diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index f9bb3b14130e..c84fe24b2ea1 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -50,9 +50,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { int kvm_perf_init(void) { - if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled()) - static_branch_enable(&kvm_arm_pmu_available); - return perf_register_guest_info_callbacks(&kvm_guest_cbs); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index f5065f23b413..2af3c37445e0 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -740,7 +740,14 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, kvm_pmu_create_perf_event(vcpu, select_idx); } -int kvm_pmu_probe_pmuver(void) +void kvm_host_pmu_init(struct arm_pmu *pmu) +{ + if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF && + !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled()) + static_branch_enable(&kvm_arm_pmu_available); +} + +static int kvm_pmu_probe_pmuver(void) { struct perf_event_attr attr = { }; struct perf_event *event; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 3cbc3baf087f..295cc7952d0e 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -952,6 +952,8 @@ int armpmu_register(struct arm_pmu *pmu) pmu->name, pmu->num_events, has_nmi ? ", using NMIs" : ""); + kvm_host_pmu_init(pmu); + return 0; out_destroy: diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 864b9997efb2..90f21898aad8 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -61,7 +61,6 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); -int kvm_pmu_probe_pmuver(void); #else struct kvm_pmu { }; @@ -118,8 +117,6 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } -static inline int kvm_pmu_probe_pmuver(void) { return 0xf; } - #endif #endif diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 505480217cf1..2512e2f9cd4e 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -163,6 +163,12 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn); static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } #endif +#ifdef CONFIG_KVM +void kvm_host_pmu_init(struct arm_pmu *pmu); +#else +#define kvm_host_pmu_init(x) do { } while(0) +#endif + /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); struct arm_pmu *armpmu_alloc_atomic(void); From e184cec5e29d8eb3c3435b12a9074b75e2d69e4a Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 15 Sep 2021 21:52:06 +0800 Subject: [PATCH 458/866] net: hns3: fix change RSS 'hfunc' ineffective issue When user change rss 'hfunc' without set rss 'hkey' by ethtool -X command, the driver will ignore the 'hfunc' for the hkey is NULL. It's unreasonable. So fix it. Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Fixes: 374ad291762a ("net: hns3: Add RSS general configuration support for VF") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_main.c | 45 ++++++++++------ .../hisilicon/hns3/hns3vf/hclgevf_main.c | 52 ++++++++++++------- 2 files changed, 64 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f1e46ba799f9..36c8741445e8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -4741,6 +4741,24 @@ static int hclge_get_rss(struct hnae3_handle *handle, u32 *indir, return 0; } +static int hclge_parse_rss_hfunc(struct hclge_vport *vport, const u8 hfunc, + u8 *hash_algo) +{ + switch (hfunc) { + case ETH_RSS_HASH_TOP: + *hash_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; + return 0; + case ETH_RSS_HASH_XOR: + *hash_algo = HCLGE_RSS_HASH_ALGO_SIMPLE; + return 0; + case ETH_RSS_HASH_NO_CHANGE: + *hash_algo = vport->rss_algo; + return 0; + default: + return -EINVAL; + } +} + static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc) { @@ -4750,30 +4768,27 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, u8 hash_algo; int ret, i; + ret = hclge_parse_rss_hfunc(vport, hfunc, &hash_algo); + if (ret) { + dev_err(&hdev->pdev->dev, "invalid hfunc type %u\n", hfunc); + return ret; + } + /* Set the RSS Hash Key if specififed by the user */ if (key) { - switch (hfunc) { - case ETH_RSS_HASH_TOP: - hash_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; - break; - case ETH_RSS_HASH_XOR: - hash_algo = HCLGE_RSS_HASH_ALGO_SIMPLE; - break; - case ETH_RSS_HASH_NO_CHANGE: - hash_algo = vport->rss_algo; - break; - default: - return -EINVAL; - } - ret = hclge_set_rss_algo_key(hdev, hash_algo, key); if (ret) return ret; /* Update the shadow RSS key with user specified qids */ memcpy(vport->rss_hash_key, key, HCLGE_RSS_KEY_SIZE); - vport->rss_algo = hash_algo; + } else { + ret = hclge_set_rss_algo_key(hdev, hash_algo, + vport->rss_hash_key); + if (ret) + return ret; } + vport->rss_algo = hash_algo; /* Update the shadow RSS table with user specified qids */ for (i = 0; i < ae_dev->dev_specs.rss_ind_tbl_size; i++) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a69e892277b3..5fdac8685f95 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -816,40 +816,56 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key, return 0; } +static int hclgevf_parse_rss_hfunc(struct hclgevf_dev *hdev, const u8 hfunc, + u8 *hash_algo) +{ + switch (hfunc) { + case ETH_RSS_HASH_TOP: + *hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ; + return 0; + case ETH_RSS_HASH_XOR: + *hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE; + return 0; + case ETH_RSS_HASH_NO_CHANGE: + *hash_algo = hdev->rss_cfg.hash_algo; + return 0; + default: + return -EINVAL; + } +} + static int hclgevf_set_rss(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg; + u8 hash_algo; int ret, i; if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) { + ret = hclgevf_parse_rss_hfunc(hdev, hfunc, &hash_algo); + if (ret) + return ret; + /* Set the RSS Hash Key if specififed by the user */ if (key) { - switch (hfunc) { - case ETH_RSS_HASH_TOP: - rss_cfg->hash_algo = - HCLGEVF_RSS_HASH_ALGO_TOEPLITZ; - break; - case ETH_RSS_HASH_XOR: - rss_cfg->hash_algo = - HCLGEVF_RSS_HASH_ALGO_SIMPLE; - break; - case ETH_RSS_HASH_NO_CHANGE: - break; - default: - return -EINVAL; - } - - ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo, - key); - if (ret) + ret = hclgevf_set_rss_algo_key(hdev, hash_algo, key); + if (ret) { + dev_err(&hdev->pdev->dev, + "invalid hfunc type %u\n", hfunc); return ret; + } /* Update the shadow RSS key with user specified qids */ memcpy(rss_cfg->rss_hash_key, key, HCLGEVF_RSS_KEY_SIZE); + } else { + ret = hclgevf_set_rss_algo_key(hdev, hash_algo, + rss_cfg->rss_hash_key); + if (ret) + return ret; } + rss_cfg->hash_algo = hash_algo; } /* update the shadow RSS table with user specified qids */ From 91bc0d5272d3a4dc3d4fd2a74387c7e7361bbe96 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 15 Sep 2021 21:52:07 +0800 Subject: [PATCH 459/866] net: hns3: fix inconsistent vf id print The vf id from ethtool is added 1 before configured to driver. So it's necessary to minus 1 when printing it, in order to keep consistent with user's configuration. Fixes: dd74f815dd41 ("net: hns3: Add support for rule add/delete for flow director") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 36c8741445e8..c0f25ea043b0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -6642,10 +6642,13 @@ static int hclge_fd_parse_ring_cookie(struct hclge_dev *hdev, u64 ring_cookie, u8 vf = ethtool_get_flow_spec_ring_vf(ring_cookie); u16 tqps; + /* To keep consistent with user's configuration, minus 1 when + * printing 'vf', because vf id from ethtool is added 1 for vf. + */ if (vf > hdev->num_req_vfs) { dev_err(&hdev->pdev->dev, - "Error: vf id (%u) > max vf num (%u)\n", - vf, hdev->num_req_vfs); + "Error: vf id (%u) should be less than %u\n", + vf - 1, hdev->num_req_vfs); return -EINVAL; } From 311c0aaa9b4bb8dc65f22634e15963316b17c921 Mon Sep 17 00:00:00 2001 From: Jiaran Zhang Date: Wed, 15 Sep 2021 21:52:08 +0800 Subject: [PATCH 460/866] net: hns3: fix misuse vf id and vport id in some logs vport_id include PF and VFs, vport_id = 0 means PF, other values mean VFs. So the actual vf id is equal to vport_id minus 1. Some VF print logs are actually vport, and logs of vf id actually use vport id, so this patch fixes them. Fixes: ac887be5b0fe ("net: hns3: change print level of RAS error log from warning to error") Fixes: adcf738b804b ("net: hns3: cleanup some print format warning") Signed-off-by: Jiaran Zhang Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c | 8 ++++---- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 10 ++++++---- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- 4 files changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 718c16d686fa..bb9b026ae88e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -2445,12 +2445,12 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, return; } - dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%u), queue_id(%u)\n", + dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vport(%u), queue_id(%u)\n", vf_id, q_id); if (vf_id) { if (vf_id >= hdev->num_alloc_vport) { - dev_err(dev, "invalid vf id(%u)\n", vf_id); + dev_err(dev, "invalid vport(%u)\n", vf_id); return; } @@ -2463,8 +2463,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, ret = hclge_inform_reset_assert_to_vf(&hdev->vport[vf_id]); if (ret) - dev_err(dev, "inform reset to vf(%u) failed %d!\n", - hdev->vport->vport_id, ret); + dev_err(dev, "inform reset to vport(%u) failed %d!\n", + vf_id, ret); } else { set_bit(HNAE3_FUNC_RESET, reset_requests); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c0f25ea043b0..afc88a41a89c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3661,7 +3661,8 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) if (ret) { dev_err(&hdev->pdev->dev, "set vf(%u) rst failed %d!\n", - vport->vport_id, ret); + vport->vport_id - HCLGE_VF_VPORT_START_NUM, + ret); return ret; } @@ -3676,7 +3677,8 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) if (ret) dev_warn(&hdev->pdev->dev, "inform reset to vf(%u) failed %d!\n", - vport->vport_id, ret); + vport->vport_id - HCLGE_VF_VPORT_START_NUM, + ret); } return 0; @@ -11467,11 +11469,11 @@ static void hclge_clear_resetting_state(struct hclge_dev *hdev) struct hclge_vport *vport = &hdev->vport[i]; int ret; - /* Send cmd to clear VF's FUNC_RST_ING */ + /* Send cmd to clear vport's FUNC_RST_ING */ ret = hclge_set_vf_rst(hdev, vport->vport_id, false); if (ret) dev_warn(&hdev->pdev->dev, - "clear vf(%u) rst failed %d!\n", + "clear vport(%u) rst failed %d!\n", vport->vport_id, ret); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 2ce5302c5956..07aa6ada4fdb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -566,7 +566,7 @@ static int hclge_reset_vf(struct hclge_vport *vport) struct hclge_dev *hdev = vport->back; dev_warn(&hdev->pdev->dev, "PF received VF reset request from VF %u!", - vport->vport_id); + vport->vport_id - HCLGE_VF_VPORT_START_NUM); return hclge_func_reset_cmd(hdev, vport->vport_id); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 78d5bf1ea561..44618cc4cca1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -581,7 +581,7 @@ int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "vf%u, qs%u failed to set tx_rate:%d, ret=%d\n", + "vport%u, qs%u failed to set tx_rate:%d, ret=%d\n", vport->vport_id, shap_cfg_cmd->qs_id, max_tx_rate, ret); return ret; From 63b1279d9905100a14da9e043de7b28e99dba3f8 Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Wed, 15 Sep 2021 21:52:09 +0800 Subject: [PATCH 461/866] net: hns3: check queue id range before using The input parameters may not be reliable. Before using the queue id, we should check this parameter. Otherwise, memory overwriting may occur. Fixes: d34100184685 ("net: hns3: refactor the mailbox message between PF and VF") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 07aa6ada4fdb..65d78ee4d65a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -590,9 +590,17 @@ static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req, struct hclge_respond_to_vf_msg *resp_msg) { + struct hnae3_handle *handle = &vport->nic; + struct hclge_dev *hdev = vport->back; u16 queue_id, qid_in_pf; memcpy(&queue_id, mbx_req->msg.data, sizeof(queue_id)); + if (queue_id >= handle->kinfo.num_tqps) { + dev_err(&hdev->pdev->dev, "Invalid queue id(%u) from VF %u\n", + queue_id, mbx_req->mbx_src_vfid); + return; + } + qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id); memcpy(resp_msg->data, &qid_in_pf, sizeof(qid_in_pf)); resp_msg->len = sizeof(qid_in_pf); From ef39d632608e66f428c1246836fd060cf4818d67 Mon Sep 17 00:00:00 2001 From: liaoguojia Date: Wed, 15 Sep 2021 21:52:10 +0800 Subject: [PATCH 462/866] net: hns3: check vlan id before using it The input parameters may not be reliable, so check the vlan id before using it, otherwise may set wrong vlan id into hardware. Fixes: dc8131d846d4 ("net: hns3: Fix for packet loss due wrong filter config in VLAN tbls") Signed-off-by: liaoguojia Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index afc88a41a89c..14e9daf09f8c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9817,6 +9817,9 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, if (is_kill && !vlan_id) return 0; + if (vlan_id >= VLAN_N_VID) + return -EINVAL; + ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id); if (ret) { dev_err(&hdev->pdev->dev, From 5126b9d3d4acdebc12b9d436282f88d8a1b5146c Mon Sep 17 00:00:00 2001 From: Yufeng Mo Date: Wed, 15 Sep 2021 21:52:11 +0800 Subject: [PATCH 463/866] net: hns3: fix a return value error in hclge_get_reset_status() hclge_get_reset_status() should return the tqp reset status. However, if the CMDQ fails, the caller will take it as tqp reset success status by mistake. Therefore, uses a parameters to get the tqp reset status instead. Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by: Yufeng Mo Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 14e9daf09f8c..47fea8985861 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10726,7 +10726,8 @@ static int hclge_reset_tqp_cmd_send(struct hclge_dev *hdev, u16 queue_id, return 0; } -static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) +static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id, + u8 *reset_status) { struct hclge_reset_tqp_queue_cmd *req; struct hclge_desc desc; @@ -10744,7 +10745,9 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) return ret; } - return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B); + *reset_status = hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B); + + return 0; } u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id) @@ -10763,7 +10766,7 @@ static int hclge_reset_tqp_cmd(struct hnae3_handle *handle) struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; u16 reset_try_times = 0; - int reset_status; + u8 reset_status; u16 queue_gid; int ret; u16 i; @@ -10779,7 +10782,11 @@ static int hclge_reset_tqp_cmd(struct hnae3_handle *handle) } while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) { - reset_status = hclge_get_reset_status(hdev, queue_gid); + ret = hclge_get_reset_status(hdev, queue_gid, + &reset_status); + if (ret) + return ret; + if (reset_status) break; From 4403f8062abecf24794e0fd3a3e424cc63ba6662 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 16 Sep 2021 17:05:29 +0200 Subject: [PATCH 464/866] xen/x86: drop redundant zeroing from cpu_initialize_context() Just after having obtained the pointer from kzalloc() there's no reason at all to set part of the area to all zero yet another time. Similarly there's no point explicitly clearing "ldt_ents". Signed-off-by: Jan Beulich Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/14881835-a48e-29fa-0870-e177b10fcf65@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/smp_pv.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 96afadf9878e..7ed56c6075b0 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -290,8 +290,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_rw(cpu); - memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - /* * Bring up the CPU in cpu_bringup_and_idle() with the stack * pointing just below where pt_regs would be if it were a normal @@ -308,8 +306,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) xen_copy_trap_info(ctxt->trap_ctxt); - ctxt->ldt_ents = 0; - BUG_ON((unsigned long)gdt & ~PAGE_MASK); gdt_mfn = arbitrary_virt_to_mfn(gdt); From f28347cc66395e96712f5c2db0a302ee75bafce6 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 08:13:08 +0200 Subject: [PATCH 465/866] Xen/gntdev: don't ignore kernel unmapping error While working on XSA-361 and its follow-ups, I failed to spot another place where the kernel mapping part of an operation was not treated the same as the user space part. Detect and propagate errors and add a 2nd pr_debug(). Signed-off-by: Jan Beulich Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/c2513395-74dc-aea3-9192-fd265aa44e35@suse.com Signed-off-by: Juergen Gross --- drivers/xen/gntdev.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 1e7f6b1c0c97..fec1b6537166 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -381,6 +381,14 @@ static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset, map->unmap_ops[offset+i].handle, map->unmap_ops[offset+i].status); map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE; + if (use_ptemod) { + if (map->kunmap_ops[offset+i].status) + err = -EINVAL; + pr_debug("kunmap handle=%u st=%d\n", + map->kunmap_ops[offset+i].handle, + map->kunmap_ops[offset+i].status); + map->kunmap_ops[offset+i].handle = INVALID_GRANT_HANDLE; + } } return err; } From 9074c79b62b6e0d91d7f716c6e4e9968eaf9e043 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 12:45:49 +0200 Subject: [PATCH 466/866] swiotlb-xen: ensure to issue well-formed XENMEM_exchange requests While the hypervisor hasn't been enforcing this, we would still better avoid issuing requests with GFNs not aligned to the requested order. Instead of altering the value also in the call to panic(), drop it there for being static and hence easy to determine without being part of the panic message. Signed-off-by: Jan Beulich Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/7b3998e3-1233-4e5a-89ec-d740e77eb166@suse.com Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 9c9ba500ef23..c0c38672fee3 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -230,10 +230,11 @@ retry: /* * Get IO TLB memory from any location. */ - start = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); + start = memblock_alloc(PAGE_ALIGN(bytes), + IO_TLB_SEGSIZE << IO_TLB_SHIFT); if (!start) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, PAGE_ALIGN(bytes), PAGE_SIZE); + panic("%s: Failed to allocate %lu bytes\n", + __func__, PAGE_ALIGN(bytes)); /* * And replace that memory with pages under 4GB. From e243ae953b5926eba1a8fbea64cbf68094f86a44 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 12:48:03 +0200 Subject: [PATCH 467/866] PCI: only build xen-pcifront in PV-enabled environments The driver's module init function, pcifront_init(), invokes xen_pv_domain() first thing. That construct produces constant "false" when !CONFIG_XEN_PV. Hence there's no point building the driver in non-PV configurations. Drop the (now implicit and generally wrong) X86 dependency: At present, XEN_PV can only be set when X86 is also enabled. In general an architecture supporting Xen PV (and PCI) would want to have this driver built. Signed-off-by: Jan Beulich Reviewed-by: Stefano Stabellini Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/3a7f6c9b-215d-b593-8056-b5fe605dafd7@suse.com Signed-off-by: Juergen Gross --- drivers/pci/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 0c473d75e625..43e615aa12ff 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -110,7 +110,7 @@ config PCI_PF_STUB config XEN_PCIDEV_FRONTEND tristate "Xen PCI Frontend" - depends on X86 && XEN + depends on XEN_PV select PCI_XEN select XEN_XENBUS_FRONTEND default y From 8e1034a526652f265ed993fab7f659eb8ae4b6f0 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 12:49:04 +0200 Subject: [PATCH 468/866] xen/pci-swiotlb: reduce visibility of symbols xen_swiotlb and pci_xen_swiotlb_init() are only used within the file defining them, so make them static and remove the stubs. Otoh pci_xen_swiotlb_detect() has a use (as function pointer) from the main pci-swiotlb.c file - convert its stub to a #define to NULL. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/aef5fc33-9c02-4df0-906a-5c813142e13c@suse.com Signed-off-by: Juergen Gross --- arch/x86/include/asm/xen/swiotlb-xen.h | 6 +----- arch/x86/xen/pci-swiotlb-xen.c | 4 ++-- 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h index 6b56d0d45d15..66b4ddde7743 100644 --- a/arch/x86/include/asm/xen/swiotlb-xen.h +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -3,14 +3,10 @@ #define _ASM_X86_SWIOTLB_XEN_H #ifdef CONFIG_SWIOTLB_XEN -extern int xen_swiotlb; extern int __init pci_xen_swiotlb_detect(void); -extern void __init pci_xen_swiotlb_init(void); extern int pci_xen_swiotlb_init_late(void); #else -#define xen_swiotlb (0) -static inline int __init pci_xen_swiotlb_detect(void) { return 0; } -static inline void __init pci_xen_swiotlb_init(void) { } +#define pci_xen_swiotlb_detect NULL static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; } #endif diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 54f9aa7e8457..46df59aeaa06 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -18,7 +18,7 @@ #endif #include -int xen_swiotlb __read_mostly; +static int xen_swiotlb __read_mostly; /* * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary @@ -56,7 +56,7 @@ int __init pci_xen_swiotlb_detect(void) return xen_swiotlb; } -void __init pci_xen_swiotlb_init(void) +static void __init pci_xen_swiotlb_init(void) { if (xen_swiotlb) { xen_swiotlb_init_early(); From 794d5b8a497ff053f56856472e2fae038fa761aa Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 12:50:38 +0200 Subject: [PATCH 469/866] swiotlb-xen: this is PV-only on x86 The code is unreachable for HVM or PVH, and it also makes little sense in auto-translated environments. On Arm, with xen_{create,destroy}_contiguous_region() both being stubs, I have a hard time seeing what good the Xen specific variant does - the generic one ought to be fine for all purposes there. Still Arm code explicitly references symbols here, so the code will continue to be included there. Instead of making PCI_XEN's "select" conditional, simply drop it - SWIOTLB_XEN will be available unconditionally in the PV case anyway, and is - as explained above - dead code in non-PV environments. This in turn allows dropping the stubs for xen_{create,destroy}_contiguous_region(), the former of which was broken anyway - it failed to set the DMA handle output. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/5947b8ae-fdc7-225c-4838-84712265fc1e@suse.com Signed-off-by: Juergen Gross --- arch/x86/Kconfig | 1 - drivers/xen/Kconfig | 1 + include/xen/xen-ops.h | 12 ------------ 3 files changed, 1 insertion(+), 13 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 88fb922c23a0..a71ced4c711f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2605,7 +2605,6 @@ config PCI_OLPC config PCI_XEN def_bool y depends on PCI && XEN - select SWIOTLB_XEN config MMCONF_FAM10H def_bool y diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index a37eb52fb401..22f5aff0c136 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -177,6 +177,7 @@ config XEN_GRANT_DMA_ALLOC config SWIOTLB_XEN def_bool y + depends on XEN_PV || ARM || ARM64 select DMA_OPS select SWIOTLB diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 39a5580f8feb..db28e79b77ee 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -46,19 +46,7 @@ extern unsigned long *xen_contiguous_bitmap; int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); - void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); -#else -static inline int xen_create_contiguous_region(phys_addr_t pstart, - unsigned int order, - unsigned int address_bits, - dma_addr_t *dma_handle) -{ - return 0; -} - -static inline void xen_destroy_contiguous_region(phys_addr_t pstart, - unsigned int order) { } #endif #if defined(CONFIG_XEN_PV) From ebcc36ea1960d79406d417cb6b107946da8b5210 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Wed, 15 Sep 2021 05:32:43 -0700 Subject: [PATCH 470/866] MAINTAINERS: Update Broadcom RDMA maintainers Updating the bnxt_re maintainers as Naresh decided to leave Broadcom. Link: https://lore.kernel.org/r/1631709163-2287-13-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..9c495ecd2248 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3821,7 +3821,6 @@ F: drivers/scsi/mpi3mr/ BROADCOM NETXTREME-E ROCE DRIVER M: Selvin Xavier -M: Naresh Kumar PBS L: linux-rdma@vger.kernel.org S: Supported W: http://www.broadcom.com From 5b1e985f7626307c451f98883f5e2665ee208e1c Mon Sep 17 00:00:00 2001 From: Sindhu Devale Date: Thu, 16 Sep 2021 14:12:19 -0500 Subject: [PATCH 471/866] RDMA/irdma: Skip CQP ring during a reset Due to duplicate reset flags, CQP commands are processed during reset. This leads CQP failures such as below: irdma0: [Delete Local MAC Entry Cmd Error][op_code=49] status=-27 waiting=1 completion_err=0 maj=0x0 min=0x0 Remove the redundant flag and set the correct reset flag so CPQ is paused during reset Fixes: 8498a30e1b94 ("RDMA/irdma: Register auxiliary driver and implement private channel OPs") Link: https://lore.kernel.org/r/20210916191222.824-2-shiraz.saleem@intel.com Reported-by: LiLiang Signed-off-by: Sindhu Devale Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/cm.c | 4 ++-- drivers/infiniband/hw/irdma/hw.c | 6 +++--- drivers/infiniband/hw/irdma/i40iw_if.c | 2 +- drivers/infiniband/hw/irdma/main.h | 1 - drivers/infiniband/hw/irdma/utils.c | 2 +- drivers/infiniband/hw/irdma/verbs.c | 3 +-- 6 files changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 6b62299abfbb..6dea0a49d171 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3496,7 +3496,7 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || last_ae == IRDMA_AE_BAD_CLOSE || - last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->reset)) { + last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) { issue_close = 1; iwqp->cm_id = NULL; qp->term_flags = 0; @@ -4250,7 +4250,7 @@ void irdma_cm_teardown_connections(struct irdma_device *iwdev, u32 *ipaddr, teardown_entry); attr.qp_state = IB_QPS_ERR; irdma_modify_qp(&cm_node->iwqp->ibqp, &attr, IB_QP_STATE, NULL); - if (iwdev->reset) + if (iwdev->rf->reset) irdma_cm_disconn(cm_node->iwqp); irdma_rem_ref_cm_node(cm_node); } diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 00de5ee9a260..33c06a3a4f63 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -1489,7 +1489,7 @@ void irdma_reinitialize_ieq(struct irdma_sc_vsi *vsi) irdma_puda_dele_rsrc(vsi, IRDMA_PUDA_RSRC_TYPE_IEQ, false); if (irdma_initialize_ieq(iwdev)) { - iwdev->reset = true; + iwdev->rf->reset = true; rf->gen_ops.request_reset(rf); } } @@ -1632,13 +1632,13 @@ void irdma_rt_deinit_hw(struct irdma_device *iwdev) case IEQ_CREATED: if (!iwdev->roce_mode) irdma_puda_dele_rsrc(&iwdev->vsi, IRDMA_PUDA_RSRC_TYPE_IEQ, - iwdev->reset); + iwdev->rf->reset); fallthrough; case ILQ_CREATED: if (!iwdev->roce_mode) irdma_puda_dele_rsrc(&iwdev->vsi, IRDMA_PUDA_RSRC_TYPE_ILQ, - iwdev->reset); + iwdev->rf->reset); break; default: ibdev_warn(&iwdev->ibdev, "bad init_state = %d\n", iwdev->init_state); diff --git a/drivers/infiniband/hw/irdma/i40iw_if.c b/drivers/infiniband/hw/irdma/i40iw_if.c index bddf88194d09..d219f64b2c3d 100644 --- a/drivers/infiniband/hw/irdma/i40iw_if.c +++ b/drivers/infiniband/hw/irdma/i40iw_if.c @@ -55,7 +55,7 @@ static void i40iw_close(struct i40e_info *cdev_info, struct i40e_client *client, iwdev = to_iwdev(ibdev); if (reset) - iwdev->reset = true; + iwdev->rf->reset = true; iwdev->iw_status = 0; irdma_port_ibevent(iwdev); diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 743d9e143a99..b678fe712447 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -346,7 +346,6 @@ struct irdma_device { bool roce_mode:1; bool roce_dcqcn_en:1; bool dcb:1; - bool reset:1; bool iw_ooo:1; enum init_completion_state init_state; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index e94470991fe0..ac91ea5296db 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2507,7 +2507,7 @@ void irdma_modify_qp_to_err(struct irdma_sc_qp *sc_qp) struct irdma_qp *qp = sc_qp->qp_uk.back_qp; struct ib_qp_attr attr; - if (qp->iwdev->reset) + if (qp->iwdev->rf->reset) return; attr.qp_state = IB_QPS_ERR; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 4fc323402073..829ddfa7e144 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -535,8 +535,7 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) irdma_qp_rem_ref(&iwqp->ibqp); wait_for_completion(&iwqp->free_qp); irdma_free_lsmm_rsrc(iwqp); - if (!iwdev->reset) - irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); + irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); if (!iwqp->user_mode) { if (iwqp->iwscq) { From f4475f249445b3c1fb99919b0514a075b6d6b3d4 Mon Sep 17 00:00:00 2001 From: Sindhu Devale Date: Thu, 16 Sep 2021 14:12:20 -0500 Subject: [PATCH 472/866] RDMA/irdma: Validate number of CQ entries on create CQ Add lower bound check for CQ entries at creation time. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Link: https://lore.kernel.org/r/20210916191222.824-3-shiraz.saleem@intel.com Signed-off-by: Sindhu Devale Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 829ddfa7e144..23c47482c749 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2034,7 +2034,7 @@ static int irdma_create_cq(struct ib_cq *ibcq, /* Kmode allocations */ int rsize; - if (entries > rf->max_cqe) { + if (entries < 1 || entries > rf->max_cqe) { err_code = -EINVAL; goto cq_free_rsrc; } From d3bdcd59633907ee306057b6bb70f06dce47dddc Mon Sep 17 00:00:00 2001 From: Sindhu Devale Date: Thu, 16 Sep 2021 14:12:21 -0500 Subject: [PATCH 473/866] RDMA/irdma: Report correct WC error when transport retry counter is exceeded When the retry counter exceeds, as the remote QP didn't send any Ack or Nack an asynchronous event (AE) for too many retries is generated. Add code to handle the AE and set the correct IB WC error code IB_WC_RETRY_EXC_ERR. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Link: https://lore.kernel.org/r/20210916191222.824-4-shiraz.saleem@intel.com Signed-off-by: Sindhu Devale Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/hw.c | 3 +++ drivers/infiniband/hw/irdma/user.h | 1 + drivers/infiniband/hw/irdma/verbs.c | 2 ++ 3 files changed, 6 insertions(+) diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 33c06a3a4f63..cb9a8e24e3b7 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -176,6 +176,9 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, case IRDMA_AE_LLP_RECEIVED_MPA_CRC_ERROR: qp->flush_code = FLUSH_GENERAL_ERR; break; + case IRDMA_AE_LLP_TOO_MANY_RETRIES: + qp->flush_code = FLUSH_RETRY_EXC_ERR; + break; default: qp->flush_code = FLUSH_FATAL_ERR; break; diff --git a/drivers/infiniband/hw/irdma/user.h b/drivers/infiniband/hw/irdma/user.h index ff705f323233..267102d1049d 100644 --- a/drivers/infiniband/hw/irdma/user.h +++ b/drivers/infiniband/hw/irdma/user.h @@ -102,6 +102,7 @@ enum irdma_flush_opcode { FLUSH_REM_OP_ERR, FLUSH_LOC_LEN_ERR, FLUSH_FATAL_ERR, + FLUSH_RETRY_EXC_ERR, }; enum irdma_cmpl_status { diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 23c47482c749..c7e129ee74d0 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3352,6 +3352,8 @@ static enum ib_wc_status irdma_flush_err_to_ib_wc_status(enum irdma_flush_opcode return IB_WC_LOC_LEN_ERR; case FLUSH_GENERAL_ERR: return IB_WC_WR_FLUSH_ERR; + case FLUSH_RETRY_EXC_ERR: + return IB_WC_RETRY_EXC_ERR; case FLUSH_FATAL_ERR: default: return IB_WC_FATAL_ERR; From 9f7fa37a6bd90f2749c67f8524334c387d972eb9 Mon Sep 17 00:00:00 2001 From: Sindhu Devale Date: Thu, 16 Sep 2021 14:12:22 -0500 Subject: [PATCH 474/866] RDMA/irdma: Report correct WC error when there are MW bind errors Report the correct WC error when MW bind error related asynchronous events are generated by HW. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Link: https://lore.kernel.org/r/20210916191222.824-5-shiraz.saleem@intel.com Signed-off-by: Sindhu Devale Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/hw.c | 5 +++++ drivers/infiniband/hw/irdma/user.h | 1 + drivers/infiniband/hw/irdma/verbs.c | 2 ++ 3 files changed, 8 insertions(+) diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index cb9a8e24e3b7..7de525a5ccf8 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -179,6 +179,11 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, case IRDMA_AE_LLP_TOO_MANY_RETRIES: qp->flush_code = FLUSH_RETRY_EXC_ERR; break; + case IRDMA_AE_AMP_MWBIND_INVALID_RIGHTS: + case IRDMA_AE_AMP_MWBIND_BIND_DISABLED: + case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS: + qp->flush_code = FLUSH_MW_BIND_ERR; + break; default: qp->flush_code = FLUSH_FATAL_ERR; break; diff --git a/drivers/infiniband/hw/irdma/user.h b/drivers/infiniband/hw/irdma/user.h index 267102d1049d..3dcbb1fbf2c6 100644 --- a/drivers/infiniband/hw/irdma/user.h +++ b/drivers/infiniband/hw/irdma/user.h @@ -103,6 +103,7 @@ enum irdma_flush_opcode { FLUSH_LOC_LEN_ERR, FLUSH_FATAL_ERR, FLUSH_RETRY_EXC_ERR, + FLUSH_MW_BIND_ERR, }; enum irdma_cmpl_status { diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index c7e129ee74d0..7110ebf834f9 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3354,6 +3354,8 @@ static enum ib_wc_status irdma_flush_err_to_ib_wc_status(enum irdma_flush_opcode return IB_WC_WR_FLUSH_ERR; case FLUSH_RETRY_EXC_ERR: return IB_WC_RETRY_EXC_ERR; + case FLUSH_MW_BIND_ERR: + return IB_WC_MW_BIND_ERR; case FLUSH_FATAL_ERR: default: return IB_WC_FATAL_ERR; From d8b1e10a2b8efaf71d151aa756052fbf2f3b6d57 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Sep 2021 10:56:32 -0700 Subject: [PATCH 475/866] sparc64: fix pci_iounmap() when CONFIG_PCI is not set Guenter reported [1] that the pci_iounmap() changes remain problematic, with sparc64 allnoconfig and tinyconfig still not building due to the header file changes and confusion with the arch-specific pci_iounmap() implementation. I'm pretty convinced that sparc should just use GENERIC_IOMAP instead of doing its own thing, since it turns out that the sparc64 version of pci_iounmap() is somewhat buggy (see [2]). But in the meantime, this just fixes the build by avoiding the trivial re-definition of the empty case. Link: https://lore.kernel.org/lkml/20210920134424.GA346531@roeck-us.net/ [1] Link: https://lore.kernel.org/lkml/CAHk-=wgheheFx9myQyy5osh79BAazvmvYURAtub2gQtMvLrhqQ@mail.gmail.com/ [2] Reported-by: Guenter Roeck Cc: David Miller Signed-off-by: Linus Torvalds --- arch/sparc/lib/iomap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/sparc/lib/iomap.c b/arch/sparc/lib/iomap.c index c9da9f139694..f3a8cd491ce0 100644 --- a/arch/sparc/lib/iomap.c +++ b/arch/sparc/lib/iomap.c @@ -19,8 +19,10 @@ void ioport_unmap(void __iomem *addr) EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); +#ifdef CONFIG_PCI void pci_iounmap(struct pci_dev *dev, void __iomem * addr) { /* nothing to do */ } EXPORT_SYMBOL(pci_iounmap); +#endif From e8f71f89236ef82d449991bfbc237e3cb6ea584f Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 8 Sep 2021 12:08:17 -0700 Subject: [PATCH 476/866] drm/nouveau/nvkm: Replace -ENOSYS with -ENODEV nvkm test builds fail with the following error. drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c: In function 'nvkm_control_mthd_pstate_info': drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c:60:35: error: overflow in conversion from 'int' to '__s8' {aka 'signed char'} changes value from '-251' to '5' The code builds on most architectures, but fails on parisc where ENOSYS is defined as 251. Replace the error code with -ENODEV (-19). The actual error code does not really matter and is not passed to userspace - it just has to be negative. Fixes: 7238eca4cf18 ("drm/nouveau: expose pstate selection per-power source in sysfs") Signed-off-by: Guenter Roeck Cc: Ben Skeggs Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Linus Torvalds --- drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c index b0ece71aefde..ce774579c89d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/ctrl.c @@ -57,7 +57,7 @@ nvkm_control_mthd_pstate_info(struct nvkm_control *ctrl, void *data, u32 size) args->v0.count = 0; args->v0.ustate_ac = NVIF_CONTROL_PSTATE_INFO_V0_USTATE_DISABLE; args->v0.ustate_dc = NVIF_CONTROL_PSTATE_INFO_V0_USTATE_DISABLE; - args->v0.pwrsrc = -ENOSYS; + args->v0.pwrsrc = -ENODEV; args->v0.pstate = NVIF_CONTROL_PSTATE_INFO_V0_PSTATE_UNKNOWN; } From d4ffd5df9d18031b6a53f934388726775b4452d3 Mon Sep 17 00:00:00 2001 From: Jiashuo Liang Date: Fri, 30 Jul 2021 11:01:52 +0800 Subject: [PATCH 477/866] x86/fault: Fix wrong signal when vsyscall fails with pkey The function __bad_area_nosemaphore() calls kernelmode_fixup_or_oops() with the parameter @signal being actually @pkey, which will send a signal numbered with the argument in @pkey. This bug can be triggered when the kernel fails to access user-given memory pages that are protected by a pkey, so it can go down the do_user_addr_fault() path and pass the !user_mode() check in __bad_area_nosemaphore(). Most cases will simply run the kernel fixup code to make an -EFAULT. But when another condition current->thread.sig_on_uaccess_err is met, which is only used to emulate vsyscall, the kernel will generate the wrong signal. Add a new parameter @pkey to kernelmode_fixup_or_oops() to fix this. [ bp: Massage commit message, fix build error as reported by the 0day bot: https://lkml.kernel.org/r/202109202245.APvuT8BX-lkp@intel.com ] Fixes: 5042d40a264c ("x86/fault: Bypass no_context() for implicit kernel faults from usermode") Reported-by: kernel test robot Signed-off-by: Jiashuo Liang Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Link: https://lkml.kernel.org/r/20210730030152.249106-1-liangjs@pku.edu.cn --- arch/x86/include/asm/pkeys.h | 2 -- arch/x86/mm/fault.c | 26 ++++++++++++++++++-------- include/linux/pkeys.h | 2 ++ 3 files changed, 20 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 5c7bcaa79623..1d5f14aff5f6 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define ARCH_DEFAULT_PKEY 0 - /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b2eefdefc108..84a2c8c4af73 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -710,7 +710,8 @@ oops: static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, - unsigned long address, int signal, int si_code) + unsigned long address, int signal, int si_code, + u32 pkey) { WARN_ON_ONCE(user_mode(regs)); @@ -735,8 +736,12 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, set_signal_archinfo(address, error_code); - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); + if (si_code == SEGV_PKUERR) { + force_sig_pkuerr((void __user *)address, pkey); + } else { + /* XXX: hwpoison faults will set the wrong code. */ + force_sig_fault(signal, si_code, (void __user *)address); + } } /* @@ -798,7 +803,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGSEGV, si_code, pkey); return; } @@ -930,7 +936,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } @@ -1396,7 +1403,8 @@ good_area: */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, - SIGBUS, BUS_ADRERR); + SIGBUS, BUS_ADRERR, + ARCH_DEFAULT_PKEY); return; } @@ -1416,7 +1424,8 @@ good_area: return; if (fatal_signal_pending(current) && !user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, 0, 0); + kernelmode_fixup_or_oops(regs, error_code, address, + 0, 0, ARCH_DEFAULT_PKEY); return; } @@ -1424,7 +1433,8 @@ good_area: /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, - SIGSEGV, SEGV_MAPERR); + SIGSEGV, SEGV_MAPERR, + ARCH_DEFAULT_PKEY); return; } diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 6beb26b7151d..86be8bf27b41 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -4,6 +4,8 @@ #include +#define ARCH_DEFAULT_PKEY 0 + #ifdef CONFIG_ARCH_HAS_PKEYS #include #else /* ! CONFIG_ARCH_HAS_PKEYS */ From c9c3b6811f7429b8c292de5774cea67f3a033eb2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Sep 2021 14:28:35 +0200 Subject: [PATCH 478/866] netfilter: conntrack: make max chain length random Similar to commit 67d6d681e15b ("ipv4: make exception cache less predictible"): Use a random drop length to make it harder to detect when entries were hashed to same bucket list. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 94e18fb9690d..91b7edaa635c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -77,7 +77,8 @@ static __read_mostly bool nf_conntrack_locks_all; #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) -#define MAX_CHAINLEN 64u +#define MIN_CHAINLEN 8u +#define MAX_CHAINLEN (32u - MIN_CHAINLEN) static struct conntrack_gc_work conntrack_gc_work; @@ -842,6 +843,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; + unsigned int max_chainlen; unsigned int chainlen = 0; unsigned int sequence; int err = -EEXIST; @@ -857,13 +859,15 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) &ct->tuplehash[IP_CT_DIR_REPLY].tuple); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); + /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode) { if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -873,7 +877,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1103,8 +1107,8 @@ drop: int __nf_conntrack_confirm(struct sk_buff *skb) { + unsigned int chainlen = 0, sequence, max_chainlen; const struct nf_conntrack_zone *zone; - unsigned int chainlen = 0, sequence; unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; @@ -1168,6 +1172,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) goto dying; } + max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ @@ -1175,7 +1180,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) + if (chainlen++ > max_chainlen) goto chaintoolong; } @@ -1184,7 +1189,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, zone, net)) goto out; - if (chainlen++ > MAX_CHAINLEN) { + if (chainlen++ > max_chainlen) { chaintoolong: nf_ct_add_to_dying_list(ct); NF_CT_STAT_INC(net, chaintoolong); From b16ac3c4c886f323b06ae942f02ebd2a70bf8840 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Sep 2021 14:28:36 +0200 Subject: [PATCH 479/866] netfilter: conntrack: include zone id in tuple hash again commit deedb59039f111 ("netfilter: nf_conntrack: add direction support for zones") removed the zone id from the hash value. This has implications on hash chain lengths with overlapping tuples, which can hit 64k entries on released kernels, before upper droplimit was added in d7e7747ac5c ("netfilter: refuse insertion if chain has grown too large"). With that change reverted, test script coming with this series shows linear insertion time growth: 10000 entries in 3737 ms (now 10000 total, loop 1) 10000 entries in 16994 ms (now 20000 total, loop 2) 10000 entries in 47787 ms (now 30000 total, loop 3) 10000 entries in 72731 ms (now 40000 total, loop 4) 10000 entries in 95761 ms (now 50000 total, loop 5) 10000 entries in 96809 ms (now 60000 total, loop 6) inserted 60000 entries from packet path in 333825 ms With d7e7747ac5c in place, the test fails. There are three supported zone use cases: 1. Connection is in the default zone (zone 0). This means to special config (the default). 2. Connection is in a different zone (1 to 2**16). This means rules are in place to put packets in the desired zone, e.g. derived from vlan id or interface. 3. Original direction is in zone X and Reply is in zone 0. 3) allows to use of the existing NAT port collision avoidance to provide connectivity to internet/wan even when the various zones have overlapping source networks separated via policy routing. In case the original zone is 0 all three cases are identical. There is no way to place original direction in zone x and reply in zone y (with y != 0). Zones need to be assigned manually via the iptables/nftables ruleset, before conntrack lookup occurs (raw table in iptables) using the "CT" target conntrack template support (-j CT --{zone,zone-orig,zone-reply} X). Normally zone assignment happens based on incoming interface, but could also be derived from packet mark, vlan id and so on. This means that when case 3 is used, the ruleset will typically not even assign a connection tracking template to the "reply" packets, so lookup happens in zone 0. However, it is possible that reply packets also match a ct zone assignment rule which sets up a template for zone X (X > 0) in original direction only. Therefore, after making the zone id part of the hash, we need to do a second lookup using the reply zone id if we did not find an entry on the first lookup. In practice, most deployments will either not use zones at all or the origin and reply zones are the same, no second lookup is required in either case. After this change, packet path insertion test passes with constant insertion times: 10000 entries in 1064 ms (now 10000 total, loop 1) 10000 entries in 1074 ms (now 20000 total, loop 2) 10000 entries in 1066 ms (now 30000 total, loop 3) 10000 entries in 1079 ms (now 40000 total, loop 4) 10000 entries in 1081 ms (now 50000 total, loop 5) 10000 entries in 1082 ms (now 60000 total, loop 6) inserted 60000 entries from packet path in 6452 ms Cc: Daniel Borkmann Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 67 ++++++++++++++++++++++++------- 1 file changed, 52 insertions(+), 15 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 91b7edaa635c..97b91d62589d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -189,11 +189,13 @@ seqcount_spinlock_t nf_conntrack_generation __read_mostly; static siphash_key_t nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, const struct net *net) { struct { struct nf_conntrack_man src; union nf_inet_addr dst_addr; + unsigned int zone; u32 net_mix; u16 dport; u16 proto; @@ -206,6 +208,7 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, /* The direction must be ignored, so handle usable members manually. */ combined.src = tuple->src; combined.dst_addr = tuple->dst.u3; + combined.zone = zoneid; combined.net_mix = net_hash_mix(net); combined.dport = (__force __u16)tuple->dst.u.all; combined.proto = tuple->dst.protonum; @@ -220,15 +223,17 @@ static u32 scale_hash(u32 hash) static u32 __hash_conntrack(const struct net *net, const struct nf_conntrack_tuple *tuple, + unsigned int zoneid, unsigned int size) { - return reciprocal_scale(hash_conntrack_raw(tuple, net), size); + return reciprocal_scale(hash_conntrack_raw(tuple, zoneid, net), size); } static u32 hash_conntrack(const struct net *net, - const struct nf_conntrack_tuple *tuple) + const struct nf_conntrack_tuple *tuple, + unsigned int zoneid) { - return scale_hash(hash_conntrack_raw(tuple, net)); + return scale_hash(hash_conntrack_raw(tuple, zoneid, net)); } static bool nf_ct_get_tuple_ports(const struct sk_buff *skb, @@ -651,9 +656,11 @@ static void nf_ct_delete_from_lists(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); clean_from_lists(ct); @@ -820,8 +827,20 @@ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - return __nf_conntrack_find_get(net, zone, tuple, - hash_conntrack_raw(tuple, net)); + unsigned int rid, zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + struct nf_conntrack_tuple_hash *thash; + + thash = __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, zone_id, net)); + + if (thash) + return thash; + + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (rid != zone_id) + return __nf_conntrack_find_get(net, zone, tuple, + hash_conntrack_raw(tuple, rid, net)); + return thash; } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); @@ -854,9 +873,11 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) do { sequence = read_seqcount_begin(&nf_conntrack_generation); hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_ORIGINAL)); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); max_chainlen = MIN_CHAINLEN + prandom_u32_max(MAX_CHAINLEN); @@ -1137,8 +1158,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = scale_hash(hash); reply_hash = hash_conntrack(net, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - + &ct->tuplehash[IP_CT_DIR_REPLY].tuple, + nf_ct_zone_id(nf_ct_zone(ct), IP_CT_DIR_REPLY)); } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related @@ -1251,7 +1272,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, rcu_read_lock(); begin: nf_conntrack_get_ht(&ct_hash, &hsize); - hash = __hash_conntrack(net, tuple, hsize); + hash = __hash_conntrack(net, tuple, nf_ct_zone_id(zone, IP_CT_DIR_REPLY), hsize); hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); @@ -1692,8 +1713,8 @@ resolve_normal_ct(struct nf_conn *tmpl, struct nf_conntrack_tuple_hash *h; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + u32 hash, zone_id, rid; struct nf_conn *ct; - u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, @@ -1704,8 +1725,20 @@ resolve_normal_ct(struct nf_conn *tmpl, /* look for tuple match */ zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); - hash = hash_conntrack_raw(&tuple, state->net); + + zone_id = nf_ct_zone_id(zone, IP_CT_DIR_ORIGINAL); + hash = hash_conntrack_raw(&tuple, zone_id, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); + + if (!h) { + rid = nf_ct_zone_id(zone, IP_CT_DIR_REPLY); + if (zone_id != rid) { + u32 tmp = hash_conntrack_raw(&tuple, rid, state->net); + + h = __nf_conntrack_find_get(state->net, zone, &tuple, tmp); + } + } + if (!h) { h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); @@ -2542,12 +2575,16 @@ int nf_conntrack_hash_resize(unsigned int hashsize) for (i = 0; i < nf_conntrack_htable_size; i++) { while (!hlist_nulls_empty(&nf_conntrack_hash[i])) { + unsigned int zone_id; + h = hlist_nulls_entry(nf_conntrack_hash[i].first, struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); + + zone_id = nf_ct_zone_id(nf_ct_zone(ct), NF_CT_DIRECTION(h)); bucket = __hash_conntrack(nf_ct_net(ct), - &h->tuple, hashsize); + &h->tuple, zone_id, hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } From d2966dc77ba7b2678f7aee97bf9a65702ec8e2b6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Sep 2021 14:28:37 +0200 Subject: [PATCH 480/866] netfilter: nat: include zone id in nat table hash again Similar to the conntrack change, also use the zone id for the nat source lists if the zone id is valid in both directions. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 7008961f5cb0..273117683922 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -150,13 +150,16 @@ static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) /* We keep an extra hash for each conntrack, for fast searching. */ static unsigned int -hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) +hash_by_src(const struct net *net, + const struct nf_conntrack_zone *zone, + const struct nf_conntrack_tuple *tuple) { unsigned int hash; struct { struct nf_conntrack_man src; u32 net_mix; u32 protonum; + u32 zone; } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); @@ -165,9 +168,13 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) /* Original src, to ensure we map it consistently if poss. */ combined.src = tuple->src; - combined.net_mix = net_hash_mix(n); + combined.net_mix = net_hash_mix(net); combined.protonum = tuple->dst.protonum; + /* Zone ID can be used provided its valid for both directions */ + if (zone->dir == NF_CT_DEFAULT_ZONE_DIR) + combined.zone = zone->id; + hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); @@ -272,7 +279,7 @@ find_appropriate_src(struct net *net, struct nf_conntrack_tuple *result, const struct nf_nat_range2 *range) { - unsigned int h = hash_by_src(net, tuple); + unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn *ct; hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { @@ -619,7 +626,7 @@ nf_nat_setup_info(struct nf_conn *ct, unsigned int srchash; spinlock_t *lock; - srchash = hash_by_src(net, + srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); @@ -788,7 +795,7 @@ static void __nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; - h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); From 0f1148abb226f3639845738cdf3d2534ceb1d059 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Sep 2021 14:28:38 +0200 Subject: [PATCH 481/866] selftests: netfilter: add selftest for directional zone support Add a script to exercise NAT port clash resolution with directional zones. Add net namespaces that use the same IP address and connect them to a gateway. Gateway uses policy routing based on iif/mark and conntrack zones to isolate the client namespaces. In server direction, same zone with NAT to single address is used. Then, connect to a server from each client netns, using identical connection id, i.e. saddr:sport -> daddr:dport. Expectation is for all connections to succeeed: NAT gatway is supposed to do port reallocation for each of the (clashing) connections. This is based on the description/use case provided in the commit message of deedb59039f111 ("netfilter: nf_conntrack: add direction support for zones"). Cc: Daniel Borkmann Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../selftests/netfilter/nft_nat_zones.sh | 309 ++++++++++++++++++ 1 file changed, 309 insertions(+) create mode 100755 tools/testing/selftests/netfilter/nft_nat_zones.sh diff --git a/tools/testing/selftests/netfilter/nft_nat_zones.sh b/tools/testing/selftests/netfilter/nft_nat_zones.sh new file mode 100755 index 000000000000..b9ab37380f33 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat_zones.sh @@ -0,0 +1,309 @@ +#!/bin/bash +# +# Test connection tracking zone and NAT source port reallocation support. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Don't increase too much, 2000 clients should work +# just fine but script can then take several minutes with +# KASAN/debug builds. +maxclients=100 + +have_iperf=1 +ret=0 + +# client1---. +# veth1-. +# | +# NAT Gateway --veth0--> Server +# | | +# veth2-' | +# client2---' | +# .... | +# clientX----vethX---' + +# All clients share identical IP address. +# NAT Gateway uses policy routing and conntrack zones to isolate client +# namespaces. Each client connects to Server, each with colliding tuples: +# clientsaddr:10000 -> serveraddr:dport +# NAT Gateway is supposed to do port reallocation for each of the +# connections. + +sfx=$(mktemp -u "XXXXXXXX") +gw="ns-gw-$sfx" +cl1="ns-cl1-$sfx" +cl2="ns-cl2-$sfx" +srv="ns-srv-$sfx" + +v4gc1=$(sysctl -n net.ipv4.neigh.default.gc_thresh1 2>/dev/null) +v4gc2=$(sysctl -n net.ipv4.neigh.default.gc_thresh2 2>/dev/null) +v4gc3=$(sysctl -n net.ipv4.neigh.default.gc_thresh3 2>/dev/null) +v6gc1=$(sysctl -n net.ipv6.neigh.default.gc_thresh1 2>/dev/null) +v6gc2=$(sysctl -n net.ipv6.neigh.default.gc_thresh2 2>/dev/null) +v6gc3=$(sysctl -n net.ipv6.neigh.default.gc_thresh3 2>/dev/null) + +cleanup() +{ + ip netns del $gw + ip netns del $srv + for i in $(seq 1 $maxclients); do + ip netns del ns-cl$i-$sfx 2>/dev/null + done + + sysctl -q net.ipv4.neigh.default.gc_thresh1=$v4gc1 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh2=$v4gc2 2>/dev/null + sysctl -q net.ipv4.neigh.default.gc_thresh3=$v4gc3 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh1=$v6gc1 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh2=$v6gc2 2>/dev/null + sysctl -q net.ipv6.neigh.default.gc_thresh3=$v6gc3 2>/dev/null +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +conntrack -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without conntrack tool" + exit $ksft_skip +fi + +iperf3 -v >/dev/null 2>&1 +if [ $? -ne 0 ];then + have_iperf=0 +fi + +ip netns add "$gw" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi +ip -net "$gw" link set lo up + +trap cleanup EXIT + +ip netns add "$srv" +if [ $? -ne 0 ];then + echo "SKIP: Could not create server netns $srv" + exit $ksft_skip +fi + +ip link add veth0 netns "$gw" type veth peer name eth0 netns "$srv" +ip -net "$gw" link set veth0 up +ip -net "$srv" link set lo up +ip -net "$srv" link set eth0 up + +sysctl -q net.ipv6.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv6.neigh.default.gc_thresh3=4096 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh1=512 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh2=1024 2>/dev/null +sysctl -q net.ipv4.neigh.default.gc_thresh3=4096 2>/dev/null + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + + ip netns add "$cl" + if [ $? -ne 0 ];then + echo "SKIP: Could not create client netns $cl" + exit $ksft_skip + fi + ip link add veth$i netns "$gw" type veth peer name eth0 netns "$cl" > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip + fi +done + +for i in $(seq 1 $maxclients);do + cl="ns-cl$i-$sfx" + echo netns exec "$cl" ip link set lo up + echo netns exec "$cl" ip link set eth0 up + echo netns exec "$cl" sysctl -q net.ipv4.tcp_syn_retries=2 + echo netns exec "$gw" ip link set veth$i up + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.arp_ignore=2 + echo netns exec "$gw" sysctl -q net.ipv4.conf.veth$i.rp_filter=0 + + # clients have same IP addresses. + echo netns exec "$cl" ip addr add 10.1.0.3/24 dev eth0 + echo netns exec "$cl" ip addr add dead:1::3/64 dev eth0 + echo netns exec "$cl" ip route add default via 10.1.0.2 dev eth0 + echo netns exec "$cl" ip route add default via dead:1::2 dev eth0 + + # NB: same addresses on client-facing interfaces. + echo netns exec "$gw" ip addr add 10.1.0.2/24 dev veth$i + echo netns exec "$gw" ip addr add dead:1::2/64 dev veth$i + + # gw: policy routing + echo netns exec "$gw" ip route add 10.1.0.0/24 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add dead:1::0/64 dev veth$i table $((1000+i)) + echo netns exec "$gw" ip route add 10.3.0.0/24 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip route add dead:3::0/64 dev veth0 table $((1000+i)) + echo netns exec "$gw" ip rule add fwmark $i lookup $((1000+i)) +done | ip -batch /dev/stdin + +ip -net "$gw" addr add 10.3.0.1/24 dev veth0 +ip -net "$gw" addr add dead:3::1/64 dev veth0 + +ip -net "$srv" addr add 10.3.0.99/24 dev eth0 +ip -net "$srv" addr add dead:3::99/64 dev eth0 + +ip netns exec $gw nft -f /dev/stdin< /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv4.conf.all.rp_filter=0 >/dev/null + +# useful for debugging: allows to use 'ping' from clients to gateway. +ip netns exec "$gw" sysctl -q net.ipv4.fwmark_reflect=1 > /dev/null +ip netns exec "$gw" sysctl -q net.ipv6.fwmark_reflect=1 > /dev/null + +for i in $(seq 1 $maxclients); do + cl="ns-cl$i-$sfx" + ip netns exec $cl ping -i 0.5 -q -c 3 10.3.0.99 > /dev/null 2>&1 & + if [ $? -ne 0 ]; then + echo FAIL: Ping failure from $cl 1>&2 + ret=1 + break + fi +done + +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" | grep -q "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 counter packets 3 bytes 252 }" + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth$i" 1>&2 + ip netns exec $gw nft get element inet raw inicmp "{ 10.1.0.3 . \"veth$i\" . 10.3.0.99 }" 1>&2 + break + fi +done + +ip netns exec $gw nft get element inet raw inicmp "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 }" | grep -q "{ 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: counter icmp mismatch for veth0: { 10.3.0.99 . \"veth0\" . 10.3.0.1 counter packets $((3 * $maxclients)) bytes $((252 * $maxclients)) }" + ip netns exec $gw nft get element inet raw inicmp "{ 10.3.99 . \"veth0\" . 10.3.0.1 }" 1>&2 +fi + +if [ $ret -eq 0 ]; then + echo "PASS: ping test from all $maxclients namespaces" +fi + +if [ $have_iperf -eq 0 ];then + echo "SKIP: iperf3 not installed" + if [ $ret -ne 0 ];then + exit $ret + fi + exit $ksft_skip +fi + +ip netns exec $srv iperf3 -s > /dev/null 2>&1 & +iperfpid=$! +sleep 1 + +for i in $(seq 1 $maxclients); do + if [ $ret -ne 0 ]; then + break + fi + cl="ns-cl$i-$sfx" + ip netns exec $cl iperf3 -c 10.3.0.99 --cport 10000 -n 1 > /dev/null + if [ $? -ne 0 ]; then + echo FAIL: Failure to connect for $cl 1>&2 + ip netns exec $gw conntrack -S 1>&2 + ret=1 + fi +done +if [ $ret -eq 0 ];then + echo "PASS: iperf3 connections for all $maxclients net namespaces" +fi + +kill $iperfpid +wait + +for i in $(seq 1 $maxclients); do + ip netns exec $gw nft get element inet raw inflows "{ 10.1.0.3 . 10000 . \"veth$i\" . 10.3.0.99 . 5201 }" > /dev/null + if [ $? -ne 0 ];then + ret=1 + echo "FAIL: can't find expected tcp entry for veth$i" 1>&2 + break + fi +done +if [ $ret -eq 0 ];then + echo "PASS: Found client connection for all $maxclients net namespaces" +fi + +ip netns exec $gw nft get element inet raw inflows "{ 10.3.0.99 . 5201 . \"veth0\" . 10.3.0.1 . 10000 }" > /dev/null +if [ $? -ne 0 ];then + ret=1 + echo "FAIL: cannot find return entry on veth0" 1>&2 +fi + +exit $ret From cb89f63ba662d2b56583f4dd3dd2b7f03b6d6587 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Sep 2021 14:28:39 +0200 Subject: [PATCH 482/866] selftests: netfilter: add zone stress test with colliding tuples Add 20k entries to the connection tracking table, once from the data plane, once via ctnetlink. In both cases, each entry lives in a different conntrack zone and addresses/ports are identical. Expectation is that insertions work and occurs in constant time: PASS: added 10000 entries in 1215 ms (now 10000 total, loop 1) PASS: added 10000 entries in 1214 ms (now 20000 total, loop 2) PASS: inserted 20000 entries from packet path in 2434 ms total PASS: added 10000 entries in 57631 ms (now 10000 total) PASS: added 10000 entries in 58572 ms (now 20000 total) PASS: inserted 20000 entries via ctnetlink in 116205 ms Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../selftests/netfilter/nft_zones_many.sh | 156 ++++++++++++++++++ 1 file changed, 156 insertions(+) create mode 100755 tools/testing/selftests/netfilter/nft_zones_many.sh diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh new file mode 100755 index 000000000000..ac646376eb01 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -0,0 +1,156 @@ +#!/bin/bash + +# Test insertion speed for packets with identical addresses/ports +# that are all placed in distinct conntrack zones. + +sfx=$(mktemp -u "XXXXXXXX") +ns="ns-$sfx" + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +zones=20000 +have_ct_tool=0 +ret=0 + +cleanup() +{ + ip netns del $ns +} + +ip netns add $ns +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $gw" + exit $ksft_skip +fi + +trap cleanup EXIT + +conntrack -V > /dev/null 2>&1 +if [ $? -eq 0 ];then + have_ct_tool=1 +fi + +ip -net "$ns" link set lo up + +test_zones() { + local max_zones=$1 + +ip netns exec $ns sysctl -q net.netfilter.nf_conntrack_udp_timeout=3600 +ip netns exec $ns nft -f /dev/stdin</dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + if [ $? -ne 0 ] ;then + ret=1 + break + fi + + stop=$(date +%s%3N) + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + done + + if [ $have_ct_tool -eq 1 ]; then + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries from packet path in $duration ms total" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries from packet path in $duration ms total, expected $max_zones entries" + ret=1 + fi + fi + + if [ $ret -ne 0 ];then + echo "FAIL: insert $max_zones entries from packet path" 1>&2 + fi +} + +test_conntrack_tool() { + local max_zones=$1 + + ip netns exec $ns conntrack -F >/dev/null 2>/dev/null + + local outerstart=$(date +%s%3N) + local start=$(date +%s%3N) + local stop=$start + local i=0 + while [ $i -lt $max_zones ]; do + i=$((i + 1)) + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i >/dev/null 2>&1 + if [ $? -ne 0 ];then + ip netns exec "$ns" conntrack -I -s 1.1.1.1 -d 2.2.2.2 --protonum 6 \ + --timeout 3600 --state ESTABLISHED --sport 12345 --dport 1000 --zone $i > /dev/null + echo "FAIL: conntrack -I returned an error" + ret=1 + break + fi + + if [ $((i%10000)) -eq 0 ];then + stop=$(date +%s%3N) + + local duration=$((stop-start)) + echo "PASS: added 10000 entries in $duration ms (now $i total)" + start=$stop + fi + done + + local count=$(ip netns exec "$ns" conntrack -C) + local duration=$((stop-outerstart)) + + if [ $count -eq $max_zones ]; then + echo "PASS: inserted $count entries via ctnetlink in $duration ms" + else + ip netns exec $ns conntrack -S 1>&2 + echo "FAIL: inserted $count entries via ctnetlink in $duration ms, expected $max_zones entries ($duration ms)" + ret=1 + fi +} + +test_zones $zones + +if [ $have_ct_tool -eq 1 ];then + test_conntrack_tool $zones +else + echo "SKIP: Could not run ctnetlink insertion test without conntrack tool" + if [ $ret -eq 0 ];then + exit $ksft_skip + fi +fi + +exit $ret From a499b03bf36b0c2e3b958a381d828678ab0ffc5e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 13 Sep 2021 14:42:33 +0200 Subject: [PATCH 483/866] netfilter: nf_tables: unlink table before deleting it syzbot reports following UAF: BUG: KASAN: use-after-free in memcmp+0x18f/0x1c0 lib/string.c:955 nla_strcmp+0xf2/0x130 lib/nlattr.c:836 nft_table_lookup.part.0+0x1a2/0x460 net/netfilter/nf_tables_api.c:570 nft_table_lookup net/netfilter/nf_tables_api.c:4064 [inline] nf_tables_getset+0x1b3/0x860 net/netfilter/nf_tables_api.c:4064 nfnetlink_rcv_msg+0x659/0x13f0 net/netfilter/nfnetlink.c:285 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 Problem is that all get operations are lockless, so the commit_mutex held by nft_rcv_nl_event() isn't enough to stop a parallel GET request from doing read-accesses to the table object even after synchronize_rcu(). To avoid this, unlink the table first and store the table objects in on-stack scratch space. Fixes: 6001a930ce03 ("netfilter: nftables: introduce table ownership") Reported-and-tested-by: syzbot+f31660cf279b0557160c@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 081437dd75b7..33e771cd847c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9599,7 +9599,6 @@ static void __nft_release_table(struct net *net, struct nft_table *table) table->use--; nf_tables_chain_destroy(&ctx); } - list_del(&table->list); nf_tables_table_destroy(&ctx); } @@ -9612,6 +9611,8 @@ static void __nft_release_tables(struct net *net) if (nft_table_has_owner(table)) continue; + list_del(&table->list); + __nft_release_table(net, table); } } @@ -9619,31 +9620,38 @@ static void __nft_release_tables(struct net *net) static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct nft_table *table, *to_delete[8]; struct nftables_pernet *nft_net; struct netlink_notify *n = ptr; - struct nft_table *table, *nt; struct net *net = n->net; - bool release = false; + unsigned int deleted; + bool restart = false; if (event != NETLINK_URELEASE || n->protocol != NETLINK_NETFILTER) return NOTIFY_DONE; nft_net = nft_pernet(net); + deleted = 0; mutex_lock(&nft_net->commit_mutex); +again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { __nft_release_hook(net, table); - release = true; + list_del_rcu(&table->list); + to_delete[deleted++] = table; + if (deleted >= ARRAY_SIZE(to_delete)) + break; } } - if (release) { + if (deleted) { + restart = deleted >= ARRAY_SIZE(to_delete); synchronize_rcu(); - list_for_each_entry_safe(table, nt, &nft_net->tables, list) { - if (nft_table_has_owner(table) && - n->portid == table->nlpid) - __nft_release_table(net, table); - } + while (deleted) + __nft_release_table(net, to_delete[--deleted]); + + if (restart) + goto again; } mutex_unlock(&nft_net->commit_mutex); From 45928afe94a094bcda9af858b96673d59bc4a0e9 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 13 Sep 2021 20:38:52 +0200 Subject: [PATCH 484/866] netfilter: nf_tables: Fix oversized kvmalloc() calls The commit 7661809d493b ("mm: don't allow oversized kvmalloc() calls") limits the max allocatable memory via kvmalloc() to MAX_INT. Reported-by: syzbot+cd43695a64bcd21b8596@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 33e771cd847c..b9546defdc28 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4336,7 +4336,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (ops->privsize != NULL) size = ops->privsize(nla, &desc); alloc_size = sizeof(*set) + size + udlen; - if (alloc_size < size) + if (alloc_size < size || alloc_size > INT_MAX) return -ENOMEM; set = kvzalloc(alloc_size, GFP_KERNEL); if (!set) From 30db406923b9285a9bac06a6af5e74bd6d0f1d06 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 15 Sep 2021 16:46:38 +0200 Subject: [PATCH 485/866] netfilter: nf_nat_masquerade: make async masq_inet6_event handling generic masq_inet6_event is called asynchronously from system work queue, because the inet6 notifier is atomic and nf_iterate_cleanup can sleep. The ipv4 and device notifiers call nf_iterate_cleanup directly. This is legal, but these notifiers are called with RTNL mutex held. A large conntrack table with many devices coming and going will have severe impact on the system usability, with 'ip a' blocking for several seconds. This change places the defer code into a helper and makes it more generic so ipv4 and ifdown notifiers can be converted to defer the cleanup walk as well in a follow patch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_masquerade.c | 122 ++++++++++++++++++------------ 1 file changed, 75 insertions(+), 47 deletions(-) diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c index 8e8a65d46345..415919a6ac1a 100644 --- a/net/netfilter/nf_nat_masquerade.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -9,8 +9,19 @@ #include +struct masq_dev_work { + struct work_struct work; + struct net *net; + union nf_inet_addr addr; + int ifindex; + int (*iter)(struct nf_conn *i, void *data); +}; + +#define MAX_MASQ_WORKER_COUNT 16 + static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; +static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, @@ -63,6 +74,63 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + + w = container_of(work, struct masq_dev_work, work); + + nf_ct_iterate_cleanup_net(w->net, w->iter, (void *)w, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&masq_worker_count); + module_put(THIS_MODULE); +} + +/* Iterate conntrack table in the background and remove conntrack entries + * that use the device/address being removed. + * + * In case too many work items have been queued already or memory allocation + * fails iteration is skipped, conntrack entries will time out eventually. + */ +static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, + int ifindex, + int (*iter)(struct nf_conn *i, void *data), + gfp_t gfp_flags) +{ + struct masq_dev_work *w; + + if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) + return; + + net = maybe_get_net(net); + if (!net) + return; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kzalloc(sizeof(*w), gfp_flags); + if (w) { + /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ + atomic_inc(&masq_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = ifindex; + w->net = net; + w->iter = iter; + if (addr) + w->addr = *addr; + schedule_work(&w->work); + return; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); +} + static int device_cmp(struct nf_conn *i, void *ifindex) { const struct nf_conn_nat *nat = nfct_nat(i); @@ -136,8 +204,6 @@ static struct notifier_block masq_inet_notifier = { }; #if IS_ENABLED(CONFIG_IPV6) -static atomic_t v6_worker_count __read_mostly; - static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, @@ -187,13 +253,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); -struct masq_dev_work { - struct work_struct work; - struct net *net; - struct in6_addr addr; - int ifindex; -}; - static int inet6_cmp(struct nf_conn *ct, void *work) { struct masq_dev_work *w = (struct masq_dev_work *)work; @@ -204,21 +263,7 @@ static int inet6_cmp(struct nf_conn *ct, void *work) tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - return ipv6_addr_equal(&w->addr, &tuple->dst.u3.in6); -} - -static void iterate_cleanup_work(struct work_struct *work) -{ - struct masq_dev_work *w; - - w = container_of(work, struct masq_dev_work, work); - - nf_ct_iterate_cleanup_net(w->net, inet6_cmp, (void *)w, 0, 0); - - put_net(w->net); - kfree(w); - atomic_dec(&v6_worker_count); - module_put(THIS_MODULE); + return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). @@ -233,36 +278,19 @@ static int masq_inet6_event(struct notifier_block *this, { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; - struct masq_dev_work *w; - struct net *net; + union nf_inet_addr addr; - if (event != NETDEV_DOWN || atomic_read(&v6_worker_count) >= 16) + if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; - net = maybe_get_net(dev_net(dev)); - if (!net) - return NOTIFY_DONE; - if (!try_module_get(THIS_MODULE)) - goto err_module; + memset(&addr, 0, sizeof(addr)); - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (w) { - atomic_inc(&v6_worker_count); + addr.in6 = ifa->addr; - INIT_WORK(&w->work, iterate_cleanup_work); - w->ifindex = dev->ifindex; - w->net = net; - w->addr = ifa->addr; - schedule_work(&w->work); - - return NOTIFY_DONE; - } - - module_put(THIS_MODULE); - err_module: - put_net(net); + nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet6_cmp, + GFP_ATOMIC); return NOTIFY_DONE; } From 7970a19b71044bf4dc2c1becc200275bdf1884d4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 15 Sep 2021 16:46:39 +0200 Subject: [PATCH 486/866] netfilter: nf_nat_masquerade: defer conntrack walk to work queue The ipv4 and device notifiers are called with RTNL mutex held. The table walk can take some time, better not block other RTNL users. 'ip a' has been reported to block for up to 20 seconds when conntrack table has many entries and device down events are frequent (e.g., PPP). Reported-and-tested-by: Martin Zaharinov Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_masquerade.c | 50 +++++++++++++++---------------- 1 file changed, 24 insertions(+), 26 deletions(-) diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c index 415919a6ac1a..acd73f717a08 100644 --- a/net/netfilter/nf_nat_masquerade.c +++ b/net/netfilter/nf_nat_masquerade.c @@ -131,13 +131,14 @@ static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, put_net(net); } -static int device_cmp(struct nf_conn *i, void *ifindex) +static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); + const struct masq_dev_work *w = arg; if (!nat) return 0; - return nat->masq_index == (int)(long)ifindex; + return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, @@ -153,8 +154,8 @@ static int masq_device_event(struct notifier_block *this, * and forget them. */ - nf_ct_iterate_cleanup_net(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_nat_masq_schedule(net, NULL, dev->ifindex, + device_cmp, GFP_KERNEL); } return NOTIFY_DONE; @@ -162,35 +163,45 @@ static int masq_device_event(struct notifier_block *this, static int inet_cmp(struct nf_conn *ct, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - struct net_device *dev = ifa->ifa_dev->dev; struct nf_conntrack_tuple *tuple; + struct masq_dev_work *w = ptr; - if (!device_cmp(ct, (void *)(long)dev->ifindex)) + if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - return ifa->ifa_address == tuple->dst.u3.ip; + return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; - struct net *net = dev_net(idev->dev); + const struct in_ifaddr *ifa = ptr; + const struct in_device *idev; + const struct net_device *dev; + union nf_inet_addr addr; + + if (event != NETDEV_DOWN) + return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ + idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; - if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup_net(net, inet_cmp, ptr, 0, 0); + memset(&addr, 0, sizeof(addr)); + + addr.ip = ifa->ifa_address; + + dev = idev->dev; + nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, + inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } @@ -253,19 +264,6 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); -static int inet6_cmp(struct nf_conn *ct, void *work) -{ - struct masq_dev_work *w = (struct masq_dev_work *)work; - struct nf_conntrack_tuple *tuple; - - if (!device_cmp(ct, (void *)(long)w->ifindex)) - return 0; - - tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - - return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); -} - /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. @@ -289,7 +287,7 @@ static int masq_inet6_event(struct notifier_block *this, addr.in6 = ifa->addr; - nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet6_cmp, + nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, GFP_ATOMIC); return NOTIFY_DONE; } From cc8072153aafd65bff1b3679a112cb6ba71ab375 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 11:56:25 +0200 Subject: [PATCH 487/866] netfilter: iptable_raw: drop bogus net_init annotation This is a leftover from the times when this function was wired up via pernet_operations. Now its called when userspace asks for the table. With CONFIG_NET_NS=n, iptable_raw_table_init memory has been discarded already and we get a kernel crash. Other tables are fine, __net_init annotation was removed already. Fixes: fdacd57c79b7 ("netfilter: x_tables: never register tables by default") Reported-by: youling 257 Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/iptable_raw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b88e0f36cd05..8265c6765705 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -42,7 +42,7 @@ iptable_raw_hook(void *priv, struct sk_buff *skb, static struct nf_hook_ops *rawtable_ops __read_mostly; -static int __net_init iptable_raw_table_init(struct net *net) +static int iptable_raw_table_init(struct net *net) { struct ipt_replace *repl; const struct xt_table *table = &packet_raw; From b53deef054e58fe4f37c66211b8ece9f8fc1aa13 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 18:50:17 +0200 Subject: [PATCH 488/866] netfilter: log: work around missing softdep backend module iptables/nftables has two types of log modules: 1. backend, e.g. nf_log_syslog, which implement the functionality 2. frontend, e.g. xt_LOG or nft_log, which call the functionality provided by backend based on nf_tables or xtables rule set. Problem is that the request_module() call to load the backed in nf_logger_find_get() might happen with nftables transaction mutex held in case the call path is via nf_tables/nft_compat. This can cause deadlocks (see 'Fixes' tags for details). The chosen solution as to let modprobe deal with this by adding 'pre: ' soft dep tag to xt_LOG (to load the syslog backend) and xt_NFLOG (to load nflog backend). Eric reports that this breaks on systems with older modprobe that doesn't support softdeps. Another, similar issue occurs when someone either insmods xt_(NF)LOG directly or unloads the backend module (possible if no log frontend is in use): because the frontend module is already loaded, modprobe is not invoked again so the softdep isn't evaluated. Add a workaround: If nf_logger_find_get() returns -ENOENT and call is not via nft_compat, load the backend explicitly and try again. Else, let nft_compat ask for deferred request_module via nf_tables infra. Softdeps are kept in-place, so with newer modprobe the dependencies are resolved from userspace. Fixes: cefa31a9d461 ("netfilter: nft_log: perform module load from nf_tables") Fixes: a38b5b56d6f4 ("netfilter: nf_log: add module softdeps") Reported-and-tested-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 17 ++++++++++++++++- net/netfilter/xt_LOG.c | 10 +++++++++- net/netfilter/xt_NFLOG.c | 10 +++++++++- 3 files changed, 34 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 272bcdb1392d..f69cc73c5813 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -19,6 +19,7 @@ #include #include #include +#include /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 @@ -257,8 +258,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); - if (ret < 0) + if (ret < 0) { + if (ret == -ENOENT) { + const char *modname = NULL; + + if (strcmp(target->name, "LOG") == 0) + modname = "nf_log_syslog"; + else if (strcmp(target->name, "NFLOG") == 0) + modname = "nfnetlink_log"; + + if (modname && + nft_request_module(ctx->net, "%s", modname) == -EAGAIN) + return -EAGAIN; + } + return ret; + } /* The standard target cannot be used */ if (!target->target) diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index 2ff75f7637b0..f39244f9c0ed 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -44,6 +44,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; + int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; @@ -58,7 +59,14 @@ static int log_tg_check(const struct xt_tgchk_param *par) return -EINVAL; } - return nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nf_log_syslog"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); + } + + return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index fb5793208059..e660c3710a10 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -42,13 +42,21 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) static int nflog_tg_check(const struct xt_tgchk_param *par) { const struct xt_nflog_info *info = par->targinfo; + int ret; if (info->flags & ~XT_NFLOG_MASK) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + if (ret != 0 && !par->nft_compat) { + request_module("%s", "nfnetlink_log"); + + ret = nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); + } + + return ret; } static void nflog_tg_destroy(const struct xt_tgdtor_param *par) From e9edc188fc76499b0b9bd60364084037f6d03773 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Sep 2021 15:15:56 -0700 Subject: [PATCH 489/866] netfilter: conntrack: serialize hash resizes and cleanups Syzbot was able to trigger the following warning [1] No repro found by syzbot yet but I was able to trigger similar issue by having 2 scripts running in parallel, changing conntrack hash sizes, and: for j in `seq 1 1000` ; do unshare -n /bin/true >/dev/null ; done It would take more than 5 minutes for net_namespace structures to be cleaned up. This is because nf_ct_iterate_cleanup() has to restart everytime a resize happened. By adding a mutex, we can serialize hash resizes and cleanups and also make get_next_corpse() faster by skipping over empty buckets. Even without resizes in the picture, this patch considerably speeds up network namespace dismantles. [1] INFO: task syz-executor.0:8312 can't die for more than 144 seconds. task:syz-executor.0 state:R running task stack:25672 pid: 8312 ppid: 6573 flags:0x00004006 Call Trace: context_switch kernel/sched/core.c:4955 [inline] __schedule+0x940/0x26f0 kernel/sched/core.c:6236 preempt_schedule_common+0x45/0xc0 kernel/sched/core.c:6408 preempt_schedule_thunk+0x16/0x18 arch/x86/entry/thunk_64.S:35 __local_bh_enable_ip+0x109/0x120 kernel/softirq.c:390 local_bh_enable include/linux/bottom_half.h:32 [inline] get_next_corpse net/netfilter/nf_conntrack_core.c:2252 [inline] nf_ct_iterate_cleanup+0x15a/0x450 net/netfilter/nf_conntrack_core.c:2275 nf_conntrack_cleanup_net_list+0x14c/0x4f0 net/netfilter/nf_conntrack_core.c:2469 ops_exit_list+0x10d/0x160 net/core/net_namespace.c:171 setup_net+0x639/0xa30 net/core/net_namespace.c:349 copy_net_ns+0x319/0x760 net/core/net_namespace.c:470 create_new_namespaces+0x3f6/0xb20 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc1/0x1f0 kernel/nsproxy.c:226 ksys_unshare+0x445/0x920 kernel/fork.c:3128 __do_sys_unshare kernel/fork.c:3202 [inline] __se_sys_unshare kernel/fork.c:3200 [inline] __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3200 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f63da68e739 RSP: 002b:00007f63d7c05188 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007f63da792f80 RCX: 00007f63da68e739 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000040000000 RBP: 00007f63da6e8cc4 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f63da792f80 R13: 00007fff50b75d3f R14: 00007f63d7c05300 R15: 0000000000022000 Showing all locks held in the system: 1 lock held by khungtaskd/27: #0: ffffffff8b980020 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x53/0x260 kernel/locking/lockdep.c:6446 2 locks held by kworker/u4:2/153: #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: arch_atomic64_set arch/x86/include/asm/atomic64_64.h:34 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: arch_atomic_long_set include/linux/atomic/atomic-long.h:41 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: atomic_long_set include/linux/atomic/atomic-instrumented.h:1198 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: set_work_data kernel/workqueue.c:634 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: set_work_pool_and_clear_pending kernel/workqueue.c:661 [inline] #0: ffff888010c69138 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x896/0x1690 kernel/workqueue.c:2268 #1: ffffc9000140fdb0 ((kfence_timer).work){+.+.}-{0:0}, at: process_one_work+0x8ca/0x1690 kernel/workqueue.c:2272 1 lock held by systemd-udevd/2970: 1 lock held by in:imklog/6258: #0: ffff88807f970ff0 (&f->f_pos_lock){+.+.}-{3:3}, at: __fdget_pos+0xe9/0x100 fs/file.c:990 3 locks held by kworker/1:6/8158: 1 lock held by syz-executor.0/8312: 2 locks held by kworker/u4:13/9320: 1 lock held by syz-executor.5/10178: 1 lock held by syz-executor.4/10217: Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_core.c | 70 ++++++++++++++++--------------- 1 file changed, 37 insertions(+), 33 deletions(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 97b91d62589d..770a63103c7a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -74,6 +74,9 @@ static __read_mostly struct kmem_cache *nf_conntrack_cachep; static DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; +/* serialize hash resizes and nf_ct_iterate_cleanup */ +static DEFINE_MUTEX(nf_conntrack_mutex); + #define GC_SCAN_INTERVAL (120u * HZ) #define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) @@ -2263,28 +2266,31 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), spinlock_t *lockp; for (; *bucket < nf_conntrack_htable_size; (*bucket)++) { + struct hlist_nulls_head *hslot = &nf_conntrack_hash[*bucket]; + + if (hlist_nulls_empty(hslot)) + continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); nf_conntrack_lock(lockp); - if (*bucket < nf_conntrack_htable_size) { - hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) - continue; - /* All nf_conn objects are added to hash table twice, one - * for original direction tuple, once for the reply tuple. - * - * Exception: In the IPS_NAT_CLASH case, only the reply - * tuple is added (the original tuple already existed for - * a different object). - * - * We only need to call the iterator once for each - * conntrack, so we just use the 'reply' direction - * tuple while iterating. - */ - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - goto found; - } + hlist_nulls_for_each_entry(h, n, hslot, hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) + continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; } spin_unlock(lockp); local_bh_enable(); @@ -2302,26 +2308,20 @@ found: static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - unsigned int bucket = 0, sequence; + unsigned int bucket = 0; struct nf_conn *ct; might_sleep(); - for (;;) { - sequence = read_seqcount_begin(&nf_conntrack_generation); + mutex_lock(&nf_conntrack_mutex); + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ - while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ - - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); - } - - if (!read_seqcount_retry(&nf_conntrack_generation, sequence)) - break; - bucket = 0; + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); } + mutex_unlock(&nf_conntrack_mutex); } struct iter_data { @@ -2557,8 +2557,10 @@ int nf_conntrack_hash_resize(unsigned int hashsize) if (!hash) return -ENOMEM; + mutex_lock(&nf_conntrack_mutex); old_size = nf_conntrack_htable_size; if (old_size == hashsize) { + mutex_unlock(&nf_conntrack_mutex); kvfree(hash); return 0; } @@ -2598,6 +2600,8 @@ int nf_conntrack_hash_resize(unsigned int hashsize) nf_conntrack_all_unlock(); local_bh_enable(); + mutex_unlock(&nf_conntrack_mutex); + synchronize_net(); kvfree(old_hash); return 0; From af505cad9567f7a500d34bf183696d570d7f6810 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Thu, 2 Sep 2021 12:29:17 +0200 Subject: [PATCH 490/866] debugfs: debugfs_create_file_size(): use IS_ERR to check for error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit debugfs_create_file() returns encoded error so use IS_ERR for checking return value. Reviewed-by: Christian König Signed-off-by: Nirmoy Das Fixes: ff9fb72bc077 ("debugfs: return error values, not NULL") Cc: stable References: https://gitlab.freedesktop.org/drm/amd/-/issues/1686 Link: https://lore.kernel.org/r/20210902102917.2233-1-nirmoy.das@amd.com Signed-off-by: Greg Kroah-Hartman --- fs/debugfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 8129a430d789..2f117c57160d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -528,7 +528,7 @@ void debugfs_create_file_size(const char *name, umode_t mode, { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); - if (de) + if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); From 555f66d0f8a38537456acc77043d0e4469fcbe8e Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Tue, 14 Sep 2021 11:20:06 +0200 Subject: [PATCH 491/866] nvme-fc: update hardware queues before using them In case the number of hardware queues changes, we need to update the tagset and the mapping of ctx to hctx first. If we try to create and connect the I/O queues first, this operation will fail (target will reject the connect call due to the wrong number of queues) and hence we bail out of the recreate function. Then we will to try the very same operation again, thus we don't make any progress. Signed-off-by: Daniel Wagner Reviewed-by: Ming Lei Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b08a61ca283f..b5d9a5507de5 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2951,14 +2951,6 @@ nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl) if (ctrl->ctrl.queue_count == 1) return 0; - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); - if (ret) - goto out_free_io_queues; - - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); - if (ret) - goto out_delete_hw_queues; - if (prior_ioq_cnt != nr_io_queues) { dev_info(ctrl->ctrl.device, "reconnect: revising io queue count from %d to %d\n", @@ -2968,6 +2960,14 @@ nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl) nvme_unfreeze(&ctrl->ctrl); } + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); + if (ret) + goto out_free_io_queues; + + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); + if (ret) + goto out_delete_hw_queues; + return 0; out_delete_hw_queues: From e5445dae29d25d7b03e0a10d3d4277a1d0c8119b Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 14 Sep 2021 11:20:07 +0200 Subject: [PATCH 492/866] nvme-fc: avoid race between time out and tear down To avoid race between time out and tear down, in tear down process, first we quiesce the queue, and then delete the timer and cancel the time out work for the queue. This patch merges the admin and io sync ops into the queue teardown logic as shown in the RDMA patch 3017013dcc "nvme-rdma: avoid race between time out and tear down". There is no teardown_lock in nvme-fc. Signed-off-by: James Smart Tested-by: Daniel Wagner Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b5d9a5507de5..6ebe68396712 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2487,6 +2487,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues) */ if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_fc_terminate_exchange, &ctrl->ctrl); blk_mq_tagset_wait_completed_request(&ctrl->tag_set); @@ -2510,6 +2511,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues) * clean up the admin queue. Same thing as above. */ blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_fc_terminate_exchange, &ctrl->ctrl); blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set); From bdaa1365667103e7a754e87c08b846a979ce322b Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 14 Sep 2021 11:20:08 +0200 Subject: [PATCH 493/866] nvme-fc: remove freeze/unfreeze around update_nr_hw_queues Remove the freeze/unfreeze around changes to the number of hardware queues. Study and retest has indicated there are no ios that can be active at this point so there is nothing to freeze. nvme-fc is draining the queues in the shutdown and error recovery path in __nvme_fc_abort_outstanding_ios. This patch primarily reverts 88e837ed0f1f "nvme-fc: wait for queues to freeze before calling update_hr_hw_queues". It's not an exact revert as it leaves the adjusting of hw queues only if the count changes. Signed-off-by: James Smart [dwagner: added explanation why no IO is pending] Signed-off-by: Daniel Wagner Reviewed-by: Ming Lei Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 6ebe68396712..aa14ad963d91 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2957,9 +2957,7 @@ nvme_fc_recreate_io_queues(struct nvme_fc_ctrl *ctrl) dev_info(ctrl->ctrl.device, "reconnect: revising io queue count from %d to %d\n", prior_ioq_cnt, nr_io_queues); - nvme_wait_freeze(&ctrl->ctrl); blk_mq_update_nr_hw_queues(&ctrl->tag_set, nr_io_queues); - nvme_unfreeze(&ctrl->ctrl); } ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); From e371af033c560b9dd1e861f8f0b503142bf0a06c Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 14 Sep 2021 18:38:55 +0300 Subject: [PATCH 494/866] nvme-tcp: fix incorrect h2cdata pdu offset accounting When the controller sends us multiple r2t PDUs in a single request we need to account for it correctly as our send/recv context run concurrently (i.e. we get a new r2t with r2t_offset before we updated our iterator and req->data_sent marker). This can cause wrong offsets to be sent to the controller. To fix that, we will first know that this may happen only in the send sequence of the last page, hence we will take the r2t_offset to the h2c PDU data_offset, and in nvme_tcp_try_send_data loop, we make sure to increment the request markers also when we completed a PDU but we are expecting more r2t PDUs as we still did not send the entire data of the request. Fixes: 825619b09ad3 ("nvme-tcp: fix possible use-after-completion") Reported-by: Nowak, Lukasz Tested-by: Nowak, Lukasz Signed-off-by: Sagi Grimberg Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index e4249b7dc056..3c1c29dd3020 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -620,7 +620,7 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst); data->ttag = pdu->ttag; data->command_id = nvme_cid(rq); - data->data_offset = cpu_to_le32(req->data_sent); + data->data_offset = pdu->r2t_offset; data->data_length = cpu_to_le32(req->pdu_len); return 0; } @@ -953,7 +953,15 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) nvme_tcp_ddgst_update(queue->snd_hash, page, offset, ret); - /* fully successful last write*/ + /* + * update the request iterator except for the last payload send + * in the request where we don't want to modify it as we may + * compete with the RX path completing the request. + */ + if (req->data_sent + ret < req->data_len) + nvme_tcp_advance_req(req, ret); + + /* fully successful last send in current PDU */ if (last && ret == len) { if (queue->data_digest) { nvme_tcp_ddgst_final(queue->snd_hash, @@ -965,7 +973,6 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) } return 1; } - nvme_tcp_advance_req(req, ret); } return -EAGAIN; } From 298ba0e3d4af539cc37f982d4c011a0f07fca48c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Sep 2021 08:38:20 +0200 Subject: [PATCH 495/866] nvme: keep ctrl->namespaces ordered Various places in the nvme code that rely on ctrl->namespace to be ordered. Ensure that the namespae is inserted into the list at the right position from the start instead of sorting it after the fact. Fixes: 540c801c65eb ("NVMe: Implement namespace list scanning") Reported-by: Anton Eidelman Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Reviewed-by: Damien Le Moal --- drivers/nvme/host/core.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6600e138945e..e486845d2c7e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -3716,15 +3715,6 @@ out_unlock: return ret; } -static int ns_cmp(void *priv, const struct list_head *a, - const struct list_head *b) -{ - struct nvme_ns *nsa = container_of(a, struct nvme_ns, list); - struct nvme_ns *nsb = container_of(b, struct nvme_ns, list); - - return nsa->head->ns_id - nsb->head->ns_id; -} - struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns, *ret = NULL; @@ -3745,6 +3735,22 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid) } EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU); +/* + * Add the namespace to the controller list while keeping the list ordered. + */ +static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) +{ + struct nvme_ns *tmp; + + list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) { + if (tmp->head->ns_id < ns->head->ns_id) { + list_add(&ns->list, &tmp->list); + return; + } + } + list_add(&ns->list, &ns->ctrl->namespaces); +} + static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, struct nvme_ns_ids *ids) { @@ -3795,9 +3801,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, goto out_unlink_ns; down_write(&ctrl->namespaces_rwsem); - list_add_tail(&ns->list, &ctrl->namespaces); + nvme_ns_add_to_ctrl_list(ns); up_write(&ctrl->namespaces_rwsem); - nvme_get_ctrl(ctrl); if (device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups)) @@ -4080,10 +4085,6 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_scan_ns_list(ctrl) != 0) nvme_scan_ns_sequential(ctrl); mutex_unlock(&ctrl->scan_lock); - - down_write(&ctrl->namespaces_rwsem); - list_sort(NULL, &ctrl->namespaces, ns_cmp); - up_write(&ctrl->namespaces_rwsem); } /* From 96f5bd03e1be606987644b71899ea56a8d05f825 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 20 Sep 2021 12:03:45 +0200 Subject: [PATCH 496/866] xen/balloon: fix balloon kthread freezing Commit 8480ed9c2bbd56 ("xen/balloon: use a kernel thread instead a workqueue") switched the Xen balloon driver to use a kernel thread. Unfortunately the patch omitted to call try_to_freeze() or to use wait_event_freezable_timeout(), causing a system suspend to fail. Fixes: 8480ed9c2bbd56 ("xen/balloon: use a kernel thread instead a workqueue") Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20210920100345.21939-1-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/xen/balloon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 2d2803883306..43ebfe36ac27 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -522,8 +522,8 @@ static int balloon_thread(void *unused) timeout = 3600 * HZ; credit = current_credit(); - wait_event_interruptible_timeout(balloon_thread_wq, - balloon_thread_cond(state, credit), timeout); + wait_event_freezable_timeout(balloon_thread_wq, + balloon_thread_cond(state, credit), timeout); if (kthread_should_stop()) return 0; From 0594c58161b6e0f3da8efa9c6e3d4ba52b652717 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 20 Sep 2021 18:15:11 +0200 Subject: [PATCH 497/866] xen/x86: fix PV trap handling on secondary processors The initial observation was that in PV mode under Xen 32-bit user space didn't work anymore. Attempts of system calls ended in #GP(0x402). All of the sudden the vector 0x80 handler was not in place anymore. As it turns out up to 5.13 redundant initialization did occur: Once from cpu_initialize_context() (through its VCPUOP_initialise hypercall) and a 2nd time while each CPU was brought fully up. This 2nd initialization is now gone, uncovering that the 1st one was flawed: Unlike for the set_trap_table hypercall, a full virtual IDT needs to be specified here; the "vector" fields of the individual entries are of no interest. With many (kernel) IDT entries still(?) (i.e. at that point at least) empty, the syscall vector 0x80 ended up in slot 0x20 of the virtual IDT, thus becoming the domain's handler for vector 0x20. Make xen_convert_trap_info() fit for either purpose, leveraging the fact that on the xen_copy_trap_info() path the table starts out zero-filled. This includes moving out the writing of the sentinel, which would also have lead to a buffer overrun in the xen_copy_trap_info() case if all (kernel) IDT entries were populated. Convert the writing of the sentinel to clearing of the entire table entry rather than just the address field. (I didn't bother trying to identify the commit which uncovered the issue in 5.14; the commit named below is the one which actually introduced the bad code.) Fixes: f87e4cac4f4e ("xen: SMP guest support") Cc: stable@vger.kernel.org Signed-off-by: Jan Beulich Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/7a266932-092e-b68f-f2bb-1473b61adc6e@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/enlighten_pv.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 349f780a1567..6e0d0754f94f 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -755,8 +755,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) preempt_enable(); } -static void xen_convert_trap_info(const struct desc_ptr *desc, - struct trap_info *traps) +static unsigned xen_convert_trap_info(const struct desc_ptr *desc, + struct trap_info *traps, bool full) { unsigned in, out, count; @@ -766,17 +766,18 @@ static void xen_convert_trap_info(const struct desc_ptr *desc, for (in = out = 0; in < count; in++) { gate_desc *entry = (gate_desc *)(desc->address) + in; - if (cvt_gate_to_trap(in, entry, &traps[out])) + if (cvt_gate_to_trap(in, entry, &traps[out]) || full) out++; } - traps[out].address = 0; + + return out; } void xen_copy_trap_info(struct trap_info *traps) { const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); - xen_convert_trap_info(desc, traps); + xen_convert_trap_info(desc, traps, true); } /* Load a new IDT into Xen. In principle this can be per-CPU, so we @@ -786,6 +787,7 @@ static void xen_load_idt(const struct desc_ptr *desc) { static DEFINE_SPINLOCK(lock); static struct trap_info traps[257]; + unsigned out; trace_xen_cpu_load_idt(desc); @@ -793,7 +795,8 @@ static void xen_load_idt(const struct desc_ptr *desc) memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); - xen_convert_trap_info(desc, traps); + out = xen_convert_trap_info(desc, traps, false); + memset(&traps[out], 0, sizeof(traps[0])); xen_mc_flush(); if (HYPERVISOR_set_trap_table(traps)) From 8aa83e6395ce047a506f0b16edca45f36c1ae7f8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 20 Sep 2021 14:04:21 +0200 Subject: [PATCH 498/866] x86/setup: Call early_reserve_memory() earlier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit in Fixes introduced early_reserve_memory() to do all needed initial memblock_reserve() calls in one function. Unfortunately, the call of early_reserve_memory() is done too late for Xen dom0, as in some cases a Xen hook called by e820__memory_setup() will need those memory reservations to have happened already. Move the call of early_reserve_memory() before the call of e820__memory_setup() in order to avoid such problems. Fixes: a799c2bd29d1 ("x86/setup: Consolidate early memory reservations") Reported-by: Marek Marczykowski-Górecki Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov Tested-by: Marek Marczykowski-Górecki Tested-by: Nathan Chancellor Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210920120421.29276-1-jgross@suse.com --- arch/x86/kernel/setup.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 79f164141116..40ed44ead063 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -830,6 +830,20 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); + /* + * Do some memory reservations *before* memory is added to memblock, so + * memblock allocations won't overwrite it. + * + * After this point, everything still needed from the boot loader or + * firmware or kernel text should be early reserved or marked not RAM in + * e820. All other memory is free game. + * + * This call needs to happen before e820__memory_setup() which calls the + * xen_memory_setup() on Xen dom0 which relies on the fact that those + * early reservations have happened already. + */ + early_reserve_memory(); + iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; e820__memory_setup(); parse_setup_data(); @@ -876,18 +890,6 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - /* - * Do some memory reservations *before* memory is added to - * memblock, so memblock allocations won't overwrite it. - * Do it after early param, so we could get (unlikely) panic from - * serial. - * - * After this point everything still needed from the boot loader or - * firmware or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - early_reserve_memory(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux From 6c90731980655280ea07ce4b21eb97457bf86286 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Mon, 20 Sep 2021 21:18:14 +0200 Subject: [PATCH 499/866] net/smc: add missing error check in smc_clc_prfx_set() Coverity stumbled over a missing error check in smc_clc_prfx_set(): *** CID 1475954: Error handling issues (CHECKED_RETURN) /net/smc/smc_clc.c: 233 in smc_clc_prfx_set() >>> CID 1475954: Error handling issues (CHECKED_RETURN) >>> Calling "kernel_getsockname" without checking return value (as is done elsewhere 8 out of 10 times). 233 kernel_getsockname(clcsock, (struct sockaddr *)&addrs); Add the return code check in smc_clc_prfx_set(). Fixes: c246d942eabc ("net/smc: restructure netinfo for CLC proposal msgs") Reported-by: Julian Wiedmann Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/smc_clc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e286dafd6e88..6ec1ebe878ae 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -230,7 +230,8 @@ static int smc_clc_prfx_set(struct socket *clcsock, goto out_rel; } /* get address to which the internal TCP socket is bound */ - kernel_getsockname(clcsock, (struct sockaddr *)&addrs); + if (kernel_getsockname(clcsock, (struct sockaddr *)&addrs) < 0) + goto out_rel; /* analyze IP specific data of net_device belonging to TCP socket */ addr6 = (struct sockaddr_in6 *)&addrs; rcu_read_lock(); From a18cee4791b1123d0a6579a7c89f4b87e48abe03 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Mon, 20 Sep 2021 21:18:15 +0200 Subject: [PATCH 500/866] net/smc: fix 'workqueue leaked lock' in smc_conn_abort_work The abort_work is scheduled when a connection was detected to be out-of-sync after a link failure. The work calls smc_conn_kill(), which calls smc_close_active_abort() and that might end up calling smc_close_cancel_work(). smc_close_cancel_work() cancels any pending close_work and tx_work but needs to release the sock_lock before and acquires the sock_lock again afterwards. So when the sock_lock was NOT acquired before then it may be held after the abort_work completes. Thats why the sock_lock is acquired before the call to smc_conn_kill() in __smc_lgr_terminate(), but this is missing in smc_conn_abort_work(). Fix that by acquiring the sock_lock first and release it after the call to smc_conn_kill(). Fixes: b286a0651e44 ("net/smc: handle incoming CDC validation message") Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- net/smc/smc_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index af227b65669e..8280c938be80 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1474,7 +1474,9 @@ static void smc_conn_abort_work(struct work_struct *work) abort_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + lock_sock(&smc->sk); smc_conn_kill(conn, true); + release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } From e5845aa0eadda3d8a950eb8845c1396827131f30 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 21 Sep 2021 01:49:18 +0300 Subject: [PATCH 501/866] net: dsa: fix dsa_tree_setup error path Since the blamed commit, dsa_tree_teardown_switches() was split into two smaller functions, dsa_tree_teardown_switches and dsa_tree_teardown_ports. However, the error path of dsa_tree_setup stopped calling dsa_tree_teardown_ports. Fixes: a57d8c217aad ("net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f14897d9b31d..f54639a3a822 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1089,6 +1089,7 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) teardown_master: dsa_tree_teardown_master(dst); teardown_switches: + dsa_tree_teardown_ports(dst); dsa_tree_teardown_switches(dst); teardown_cpu_ports: dsa_tree_teardown_cpu_ports(dst); From 3e95cfa24e24fbd7fb7675ab972a5aa507c7a89c Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Tue, 21 Sep 2021 15:41:23 +0900 Subject: [PATCH 502/866] Doc: networking: Fox a typo in ice.rst This patch fixes a spelling typo in ice.rst Signed-off-by: Masanari Iida Signed-off-by: David S. Miller --- Documentation/networking/device_drivers/ethernet/intel/ice.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index e7d9cbff771b..67b7a701ce9e 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -851,7 +851,7 @@ NOTES: - 0x88A8 traffic will not be received unless VLAN stripping is disabled with the following command:: - # ethool -K rxvlan off + # ethtool -K rxvlan off - 0x88A8/0x8100 double VLANs cannot be used with 0x8100 or 0x8100/0x8100 VLANS configured on the same port. 0x88a8/0x8100 traffic will not be received if From 2566fffd6011df17dfba0b216fe9a154d3eb3f75 Mon Sep 17 00:00:00 2001 From: Radhakrishna Sripada Date: Tue, 14 Sep 2021 15:07:44 -0700 Subject: [PATCH 503/866] drm/i915: Update memory bandwidth parameters Earlier while calculating derated bw we would use 90% of the calculated bw. Starting ADL-P we use a non standard derating. Updating the formulae to reflect the same. Bspec: 64631 v2: Use the new derating value only for ADL-P(MattR) Fixes: 4d32fe2f14a7 ("drm/i915/adl_p: Update memory bandwidth parameters") Cc: Matt Roper Signed-off-by: Radhakrishna Sripada Reviewed-by: Matt Roper Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210914220744.16042-1-radhakrishna.sripada@intel.com (cherry picked from commit f6d66fc8cf5f673ea76407be84dc17dbb3eda108) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_bw.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index e91e0e0191fb..4b94256d7319 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -222,31 +222,42 @@ static int icl_sagv_max_dclk(const struct intel_qgv_info *qi) struct intel_sa_info { u16 displayrtids; - u8 deburst, deprogbwlimit; + u8 deburst, deprogbwlimit, derating; }; static const struct intel_sa_info icl_sa_info = { .deburst = 8, .deprogbwlimit = 25, /* GB/s */ .displayrtids = 128, + .derating = 10, }; static const struct intel_sa_info tgl_sa_info = { .deburst = 16, .deprogbwlimit = 34, /* GB/s */ .displayrtids = 256, + .derating = 10, }; static const struct intel_sa_info rkl_sa_info = { .deburst = 16, .deprogbwlimit = 20, /* GB/s */ .displayrtids = 128, + .derating = 10, }; static const struct intel_sa_info adls_sa_info = { .deburst = 16, .deprogbwlimit = 38, /* GB/s */ .displayrtids = 256, + .derating = 10, +}; + +static const struct intel_sa_info adlp_sa_info = { + .deburst = 16, + .deprogbwlimit = 38, /* GB/s */ + .displayrtids = 256, + .derating = 20, }; static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa) @@ -302,7 +313,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel bw = icl_calc_bw(sp->dclk, clpchgroup * 32 * num_channels, ct); bi->deratedbw[j] = min(maxdebw, - bw * 9 / 10); /* 90% */ + bw * (100 - sa->derating) / 100); drm_dbg_kms(&dev_priv->drm, "BW%d / QGV %d: num_planes=%d deratedbw=%u\n", @@ -400,7 +411,9 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv) if (IS_DG2(dev_priv)) dg2_get_bw_info(dev_priv); - else if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) + else if (IS_ALDERLAKE_P(dev_priv)) + icl_get_bw_info(dev_priv, &adlp_sa_info); + else if (IS_ALDERLAKE_S(dev_priv)) icl_get_bw_info(dev_priv, &adls_sa_info); else if (IS_ROCKETLAKE(dev_priv)) icl_get_bw_info(dev_priv, &rkl_sa_info); From f9b23c157a78c77545099312394d484ce4f35b8b Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Mon, 30 Aug 2021 14:09:48 +0200 Subject: [PATCH 504/866] drm/i915: Move __i915_gem_free_object to ttm_bo_destroy MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we implement delayed destroy, we may have a second call to the delete_mem_notify() handler, while free_object() only should be called once. Move it to bo->destroy(), to ensure it's only called once. This fixes some weird memory corruption issues with delayed destroy when async eviction is used. Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210830121006.2978297-2-maarten.lankhorst@linux.intel.com Fixes: 213d50927763 ("drm/i915/ttm: Introduce a TTM i915 gem object backend") Cc: Thomas Hellström Reviewed-by: Thomas Hellström (cherry picked from commit 48b0961269546716c3232748bf37e64e49fb866c) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 35eedc14f522..6ea13159bffc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -356,11 +356,8 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); - if (likely(obj)) { - /* This releases all gem object bindings to the backend. */ + if (likely(obj)) i915_ttm_free_cached_io_st(obj); - __i915_gem_free_object(obj); - } } static struct intel_memory_region * @@ -875,8 +872,12 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + /* This releases all gem object bindings to the backend. */ + __i915_gem_free_object(obj); + i915_gem_object_release_memory_region(obj); mutex_destroy(&obj->ttm.get_io_page.lock); + if (obj->ttm.created) call_rcu(&obj->rcu, __i915_gem_free_object_rcu); } From b875fb313a10bf816b5d49d8d7642d1cc9905f2f Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 9 Aug 2021 12:48:05 -0700 Subject: [PATCH 505/866] drm/i915: Free all DMC payloads MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Free all the DMC payloads, not just DMC_MAIN. unreferenced object 0xffff88ff32d4d800 (size 1024): comm "kworker/1:5", pid 701, jiffies 4294904239 (age 109.736s) hex dump (first 32 bytes): 40 40 00 0c 03 00 00 00 00 00 00 00 00 00 00 00 @@.............. 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000ba9d0d95>] dmc_load_work_fn+0x34d/0x510 [i915] [<000000001049fcab>] process_one_work+0x261/0x550 [<00000000eeb995ac>] worker_thread+0x49/0x3c0 [<0000000021031dc3>] kthread+0x10b/0x140 [<000000004a0f69ee>] ret_from_fork+0x1f/0x30 unreferenced object 0xffff88ff0bde4000 (size 1024): comm "kworker/0:3", pid 708, jiffies 4294904469 (age 108.816s) hex dump (first 32 bytes): 40 40 00 0c 01 00 00 00 00 00 00 00 00 00 00 00 @@.............. 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000ba9d0d95>] dmc_load_work_fn+0x34d/0x510 [i915] [<000000001049fcab>] process_one_work+0x261/0x550 [<00000000eeb995ac>] worker_thread+0x49/0x3c0 [<0000000021031dc3>] kthread+0x10b/0x140 [<000000004a0f69ee>] ret_from_fork+0x1f/0x30 Fixes: 3d5928a168a9 ("drm/i915/xelpd: Pipe A DMC plugging") Cc: Anusha Srivatsa Cc: José Roberto de Souza Signed-off-by: Chris Wilson Signed-off-by: Lucas De Marchi Reviewed-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20210809194805.3793060-1-lucas.demarchi@intel.com (cherry picked from commit 064b877dff4252ced91a1c8b1f129073f2991f6e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/display/intel_dmc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 3c3c6cb5c0df..b3c8e1c450ef 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -805,11 +805,14 @@ void intel_dmc_ucode_resume(struct drm_i915_private *dev_priv) */ void intel_dmc_ucode_fini(struct drm_i915_private *dev_priv) { + int id; + if (!HAS_DMC(dev_priv)) return; intel_dmc_ucode_suspend(dev_priv); drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref); - kfree(dev_priv->dmc.dmc_info[DMC_FW_MAIN].payload); + for (id = 0; id < DMC_FW_MAX; id++) + kfree(dev_priv->dmc.dmc_info[id].payload); } From 8c8a3b5bd960cd88f7655b5251dc28741e11f139 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Wed, 15 Sep 2021 12:03:35 -0700 Subject: [PATCH 506/866] arm64: add MTE supported check to thread switching and syscall entry/exit This lets us avoid doing unnecessary work on hardware that does not support MTE, and will allow us to freely use MTE instructions in the code called by mte_thread_switch(). Since this would mean that we do a redundant check in mte_check_tfsr_el1(), remove it and add two checks now required in its callers. This also avoids an unnecessary DSB+ISB sequence on the syscall exit path for hardware not supporting MTE. Fixes: 65812c6921cc ("arm64: mte: Enable async tag check fault") Cc: # 5.13.x Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/I02fd000d1ef2c86c7d2952a7f099b254ec227a5d Link: https://lore.kernel.org/r/20210915190336.398390-1-pcc@google.com [catalin.marinas@arm.com: adjust the commit log slightly] Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mte.h | 6 ++++++ arch/arm64/kernel/mte.c | 10 ++++------ 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 3f93b9e0b339..02511650cffe 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -99,11 +99,17 @@ void mte_check_tfsr_el1(void); static inline void mte_check_tfsr_entry(void) { + if (!system_supports_mte()) + return; + mte_check_tfsr_el1(); } static inline void mte_check_tfsr_exit(void) { + if (!system_supports_mte()) + return; + /* * The asynchronous faults are sync'ed automatically with * TFSR_EL1 on kernel entry but for exit an explicit dsb() diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 9d314a3bad3b..e5e801bc5312 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -142,12 +142,7 @@ void mte_enable_kernel_async(void) #ifdef CONFIG_KASAN_HW_TAGS void mte_check_tfsr_el1(void) { - u64 tfsr_el1; - - if (!system_supports_mte()) - return; - - tfsr_el1 = read_sysreg_s(SYS_TFSR_EL1); + u64 tfsr_el1 = read_sysreg_s(SYS_TFSR_EL1); if (unlikely(tfsr_el1 & SYS_TFSR_EL1_TF1)) { /* @@ -199,6 +194,9 @@ void mte_thread_init_user(void) void mte_thread_switch(struct task_struct *next) { + if (!system_supports_mte()) + return; + mte_update_sctlr_user(next); /* From 5135e96a3dd2f4555ae6981c3155a62bcf3227f6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 21 Sep 2021 00:42:08 +0300 Subject: [PATCH 507/866] net: dsa: don't allocate the slave_mii_bus using devres The Linux device model permits both the ->shutdown and ->remove driver methods to get called during a shutdown procedure. Example: a DSA switch which sits on an SPI bus, and the SPI bus driver calls this on its ->shutdown method: spi_unregister_controller -> device_for_each_child(&ctlr->dev, NULL, __unregister); -> spi_unregister_device(to_spi_device(dev)); -> device_del(&spi->dev); So this is a simple pattern which can theoretically appear on any bus, although the only other buses on which I've been able to find it are I2C: i2c_del_adapter -> device_for_each_child(&adap->dev, NULL, __unregister_client); -> i2c_unregister_device(client); -> device_unregister(&client->dev); The implication of this pattern is that devices on these buses can be unregistered after having been shut down. The drivers for these devices might choose to return early either from ->remove or ->shutdown if the other callback has already run once, and they might choose that the ->shutdown method should only perform a subset of the teardown done by ->remove (to avoid unnecessary delays when rebooting). So in other words, the device driver may choose on ->remove to not do anything (therefore to not unregister an MDIO bus it has registered on ->probe), because this ->remove is actually triggered by the device_shutdown path, and its ->shutdown method has already run and done the minimally required cleanup. This used to be fine until the blamed commit, but now, the following BUG_ON triggers: void mdiobus_free(struct mii_bus *bus) { /* For compatibility with error handling in drivers. */ if (bus->state == MDIOBUS_ALLOCATED) { kfree(bus); return; } BUG_ON(bus->state != MDIOBUS_UNREGISTERED); bus->state = MDIOBUS_RELEASED; put_device(&bus->dev); } In other words, there is an attempt to free an MDIO bus which was not unregistered. The attempt to free it comes from the devres release callbacks of the SPI device, which are executed after the device is unregistered. I'm not saying that the fact that MDIO buses allocated using devres would automatically get unregistered wasn't strange. I'm just saying that the commit didn't care about auditing existing call paths in the kernel, and now, the following code sequences are potentially buggy: (a) devm_mdiobus_alloc followed by plain mdiobus_register, for a device located on a bus that unregisters its children on shutdown. After the blamed patch, either both the alloc and the register should use devres, or none should. (b) devm_mdiobus_alloc followed by plain mdiobus_register, and then no mdiobus_unregister at all in the remove path. After the blamed patch, nobody unregisters the MDIO bus anymore, so this is even more buggy than the previous case which needs a specific bus configuration to be seen, this one is an unconditional bug. In this case, DSA falls into category (a), it tries to be helpful and registers an MDIO bus on behalf of the switch, which might be on such a bus. I've no idea why it does it under devres. It does this on probe: if (!ds->slave_mii_bus && ds->ops->phy_read) alloc and register mdio bus and this on remove: if (ds->slave_mii_bus && ds->ops->phy_read) unregister mdio bus I _could_ imagine using devres because the condition used on remove is different than the condition used on probe. So strictly speaking, DSA cannot determine whether the ds->slave_mii_bus it sees on remove is the ds->slave_mii_bus that _it_ has allocated on probe. Using devres would have solved that problem. But nonetheless, the existing code already proceeds to unregister the MDIO bus, even though it might be unregistering an MDIO bus it has never registered. So I can only guess that no driver that implements ds->ops->phy_read also allocates and registers ds->slave_mii_bus itself. So in that case, if unregistering is fine, freeing must be fine too. Stop using devres and free the MDIO bus manually. This will make devres stop attempting to free a still registered MDIO bus on ->shutdown. Fixes: ac3a68d56651 ("net: phy: don't abuse devres in devm_mdiobus_register()") Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Tested-by: Lino Sanfilippo Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f54639a3a822..b29262eee00b 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -880,7 +880,7 @@ static int dsa_switch_setup(struct dsa_switch *ds) devlink_params_publish(ds->devlink); if (!ds->slave_mii_bus && ds->ops->phy_read) { - ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); + ds->slave_mii_bus = mdiobus_alloc(); if (!ds->slave_mii_bus) { err = -ENOMEM; goto teardown; @@ -890,13 +890,16 @@ static int dsa_switch_setup(struct dsa_switch *ds) err = mdiobus_register(ds->slave_mii_bus); if (err < 0) - goto teardown; + goto free_slave_mii_bus; } ds->setup = true; return 0; +free_slave_mii_bus: + if (ds->slave_mii_bus && ds->ops->phy_read) + mdiobus_free(ds->slave_mii_bus); teardown: if (ds->ops->teardown) ds->ops->teardown(ds); @@ -921,8 +924,11 @@ static void dsa_switch_teardown(struct dsa_switch *ds) if (!ds->setup) return; - if (ds->slave_mii_bus && ds->ops->phy_read) + if (ds->slave_mii_bus && ds->ops->phy_read) { mdiobus_unregister(ds->slave_mii_bus); + mdiobus_free(ds->slave_mii_bus); + ds->slave_mii_bus = NULL; + } dsa_switch_unregister_notifier(ds); From 74b6d7d13307b016f4b5bba8198297824c0ee6df Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 21 Sep 2021 00:42:09 +0300 Subject: [PATCH 508/866] net: dsa: realtek: register the MDIO bus under devres MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Linux device model permits both the ->shutdown and ->remove driver methods to get called during a shutdown procedure. Example: a DSA switch which sits on an SPI bus, and the SPI bus driver calls this on its ->shutdown method: spi_unregister_controller -> device_for_each_child(&ctlr->dev, NULL, __unregister); -> spi_unregister_device(to_spi_device(dev)); -> device_del(&spi->dev); So this is a simple pattern which can theoretically appear on any bus, although the only other buses on which I've been able to find it are I2C: i2c_del_adapter -> device_for_each_child(&adap->dev, NULL, __unregister_client); -> i2c_unregister_device(client); -> device_unregister(&client->dev); The implication of this pattern is that devices on these buses can be unregistered after having been shut down. The drivers for these devices might choose to return early either from ->remove or ->shutdown if the other callback has already run once, and they might choose that the ->shutdown method should only perform a subset of the teardown done by ->remove (to avoid unnecessary delays when rebooting). So in other words, the device driver may choose on ->remove to not do anything (therefore to not unregister an MDIO bus it has registered on ->probe), because this ->remove is actually triggered by the device_shutdown path, and its ->shutdown method has already run and done the minimally required cleanup. This used to be fine until the blamed commit, but now, the following BUG_ON triggers: void mdiobus_free(struct mii_bus *bus) { /* For compatibility with error handling in drivers. */ if (bus->state == MDIOBUS_ALLOCATED) { kfree(bus); return; } BUG_ON(bus->state != MDIOBUS_UNREGISTERED); bus->state = MDIOBUS_RELEASED; put_device(&bus->dev); } In other words, there is an attempt to free an MDIO bus which was not unregistered. The attempt to free it comes from the devres release callbacks of the SPI device, which are executed after the device is unregistered. I'm not saying that the fact that MDIO buses allocated using devres would automatically get unregistered wasn't strange. I'm just saying that the commit didn't care about auditing existing call paths in the kernel, and now, the following code sequences are potentially buggy: (a) devm_mdiobus_alloc followed by plain mdiobus_register, for a device located on a bus that unregisters its children on shutdown. After the blamed patch, either both the alloc and the register should use devres, or none should. (b) devm_mdiobus_alloc followed by plain mdiobus_register, and then no mdiobus_unregister at all in the remove path. After the blamed patch, nobody unregisters the MDIO bus anymore, so this is even more buggy than the previous case which needs a specific bus configuration to be seen, this one is an unconditional bug. In this case, the Realtek drivers fall under category (b). To solve it, we can register the MDIO bus under devres too, which restores the previous behavior. Fixes: ac3a68d56651 ("net: phy: don't abuse devres in devm_mdiobus_register()") Reported-by: Lino Sanfilippo Reported-by: Alvin Šipraga Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/realtek-smi-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c index dd2f0d6208b3..2fcfd917b876 100644 --- a/drivers/net/dsa/realtek-smi-core.c +++ b/drivers/net/dsa/realtek-smi-core.c @@ -368,7 +368,7 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi) smi->slave_mii_bus->parent = smi->dev; smi->ds->slave_mii_bus = smi->slave_mii_bus; - ret = of_mdiobus_register(smi->slave_mii_bus, mdio_np); + ret = devm_of_mdiobus_register(smi->dev, smi->slave_mii_bus, mdio_np); if (ret) { dev_err(smi->dev, "unable to register MDIO bus %s\n", smi->slave_mii_bus->id); From 1bb30b20b49773369c299d4d6c65227201328663 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Sep 2021 16:13:42 +0300 Subject: [PATCH 509/866] thermal/core: Potential buffer overflow in thermal_build_list_of_policies() After printing the list of thermal governors, then this function prints a newline character. The problem is that "size" has not been updated after printing the last governor. This means that it can write one character (the NUL terminator) beyond the end of the buffer. Get rid of the "size" variable and just use "PAGE_SIZE - count" directly. Fixes: 1b4f48494eb2 ("thermal: core: group functions related to governor handling") Signed-off-by: Dan Carpenter Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210916131342.GB25094@kili --- drivers/thermal/thermal_core.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 97ef9b040b84..51374f4e1cca 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -222,15 +222,14 @@ int thermal_build_list_of_policies(char *buf) { struct thermal_governor *pos; ssize_t count = 0; - ssize_t size = PAGE_SIZE; mutex_lock(&thermal_governor_lock); list_for_each_entry(pos, &thermal_governor_list, governor_list) { - size = PAGE_SIZE - count; - count += scnprintf(buf + count, size, "%s ", pos->name); + count += scnprintf(buf + count, PAGE_SIZE - count, "%s ", + pos->name); } - count += scnprintf(buf + count, size, "\n"); + count += scnprintf(buf + count, PAGE_SIZE - count, "\n"); mutex_unlock(&thermal_governor_lock); From cf96921876dcee4d6ac07b9de470368a075ba9ad Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Tue, 7 Sep 2021 23:25:42 +0200 Subject: [PATCH 510/866] thermal/drivers/tsens: Fix wrong check for tzd in irq handlers Some devices can have some thermal sensors disabled from the factory. The current two irq handler functions check all the sensor by default and the check if the sensor was actually registered is wrong. The tzd is actually never set if the registration fails hence the IS_ERR check is wrong. Signed-off-by: Ansuel Smith Reviewed-by: Matthias Kaehlcke Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210907212543.20220-1-ansuelsmth@gmail.com --- drivers/thermal/qcom/tsens.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index 4c7ebd1d3f9c..b1162e566a70 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -417,7 +417,7 @@ static irqreturn_t tsens_critical_irq_thread(int irq, void *data) const struct tsens_sensor *s = &priv->sensor[i]; u32 hw_id = s->hw_id; - if (IS_ERR(s->tzd)) + if (!s->tzd) continue; if (!tsens_threshold_violated(priv, hw_id, &d)) continue; @@ -467,7 +467,7 @@ static irqreturn_t tsens_irq_thread(int irq, void *data) const struct tsens_sensor *s = &priv->sensor[i]; u32 hw_id = s->hw_id; - if (IS_ERR(s->tzd)) + if (!s->tzd) continue; if (!tsens_threshold_violated(priv, hw_id, &d)) continue; From 5b72dafaca73b33416c82457ae615e6f2022e901 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 17 Sep 2021 21:48:29 -0700 Subject: [PATCH 511/866] platform/x86: dell: fix DELL_WMI_PRIVACY dependencies & build error When DELL_WMI=y, DELL_WMI_PRIVACY=y, and LEDS_TRIGGER_AUDIO=m, there is a linker error since the LEDS trigger code is built as a loadable module. This happens because DELL_WMI_PRIVACY is a bool that depends on a tristate (LEDS_TRIGGER_AUDIO=m), which can be dangerous. ld: drivers/platform/x86/dell/dell-wmi-privacy.o: in function `dell_privacy_wmi_probe': dell-wmi-privacy.c:(.text+0x3df): undefined reference to `ledtrig_audio_get' Fixes: 8af9fa37b8a3 ("platform/x86: dell-privacy: Add support for Dell hardware privacy") Signed-off-by: Randy Dunlap Cc: Perry Yuan Cc: Dell.Client.Kernel@dell.com Cc: platform-driver-x86@vger.kernel.org Cc: Hans de Goede Cc: Mark Gross Link: https://lore.kernel.org/r/20210918044829.19222-1-rdunlap@infradead.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/dell/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 821aba31821c..42513eab1d06 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -166,8 +166,7 @@ config DELL_WMI config DELL_WMI_PRIVACY bool "Dell WMI Hardware Privacy Support" - depends on DELL_WMI - depends on LEDS_TRIGGER_AUDIO + depends on LEDS_TRIGGER_AUDIO = y || DELL_WMI = LEDS_TRIGGER_AUDIO help This option adds integration with the "Dell Hardware Privacy" feature of Dell laptops to the dell-wmi driver. From b201cb0ebe87b209e252d85668e517ac1929e250 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= Date: Mon, 20 Sep 2021 18:03:12 +0200 Subject: [PATCH 512/866] platform/x86/intel: hid: Add DMI switches allow list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some devices, even non convertible ones, can send incorrect SW_TABLET_MODE reports. Add an allow list and accept such reports only from devices in it. Bug reported for Dell XPS 17 9710 on: https://gitlab.freedesktop.org/libinput/libinput/-/issues/662 Reported-by: Tobias Gurtzick Suggested-by: Hans de Goede Tested-by: Tobias Gurtzick Signed-off-by: José Expósito Link: https://lore.kernel.org/r/20210920160312.9787-1-jose.exposito89@gmail.com [hdegoede@redhat.com: Check dmi_switches_auto_add_allow_list only once] Signed-off-by: Hans de Goede --- drivers/platform/x86/intel/hid.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index a33a5826e81a..08598942a6d7 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -118,12 +118,30 @@ static const struct dmi_system_id dmi_vgbs_allow_list[] = { { } }; +/* + * Some devices, even non convertible ones, can send incorrect SW_TABLET_MODE + * reports. Accept such reports only from devices in this list. + */ +static const struct dmi_system_id dmi_auto_add_switch[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */), + }, + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */), + }, + }, + {} /* Array terminator */ +}; + struct intel_hid_priv { struct input_dev *input_dev; struct input_dev *array; struct input_dev *switches; bool wakeup_mode; - bool dual_accel; + bool auto_add_switch; }; #define HID_EVENT_FILTER_UUID "eeec56b3-4442-408f-a792-4edd4d758054" @@ -452,10 +470,8 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) * Some convertible have unreliable VGBS return which could cause incorrect * SW_TABLET_MODE report, in these cases we enable support when receiving * the first event instead of during driver setup. - * - * See dual_accel_detect.h for more info on the dual_accel check. */ - if (!priv->switches && !priv->dual_accel && (event == 0xcc || event == 0xcd)) { + if (!priv->switches && priv->auto_add_switch && (event == 0xcc || event == 0xcd)) { dev_info(&device->dev, "switch event received, enable switches supports\n"); err = intel_hid_switches_setup(device); if (err) @@ -596,7 +612,8 @@ static int intel_hid_probe(struct platform_device *device) return -ENOMEM; dev_set_drvdata(&device->dev, priv); - priv->dual_accel = dual_accel_detect(); + /* See dual_accel_detect.h for more info on the dual_accel check. */ + priv->auto_add_switch = dmi_check_system(dmi_auto_add_switch) && !dual_accel_detect(); err = intel_hid_input_setup(device); if (err) { From 6f6aab1caf6c7fef46852aaab03f4e8250779e52 Mon Sep 17 00:00:00 2001 From: Tobias Jakobi Date: Tue, 21 Sep 2021 12:07:02 +0200 Subject: [PATCH 513/866] platform/x86: gigabyte-wmi: add support for B550I Aorus Pro AX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Tested with a AMD Ryzen 7 5800X. Signed-off-by: Tobias Jakobi Acked-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20210921100702.3838-1-tjakobi@math.uni-bielefeld.de Signed-off-by: Hans de Goede --- drivers/platform/x86/gigabyte-wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 7f3a03f937f6..d53634c8a6e0 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -144,6 +144,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550I AORUS PRO AX"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), From 59a68d4138086c015ab8241c3267eec5550fbd44 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 17 Sep 2021 15:59:30 +0100 Subject: [PATCH 514/866] arm64: Mitigate MTE issues with str{n}cmp() As with strlen(), the patches importing the updated str{n}cmp() implementations were originally developed and tested before the advent of CONFIG_KASAN_HW_TAGS, and have subsequently revealed not to be MTE-safe. Since in-kernel MTE is still a rather niche case, let it temporarily fall back to the generic C versions for correctness until we can figure out the best fix. Fixes: 758602c04409 ("arm64: Import latest version of Cortex Strings' strcmp") Fixes: 020b199bc70d ("arm64: Import latest version of Cortex Strings' strncmp") Cc: # 5.14.x Reported-by: Branislav Rankov Signed-off-by: Robin Murphy Acked-by: Mark Rutland Link: https://lore.kernel.org/r/34dc4d12eec0adae49b0ac927df642ed10089d40.1631890770.git.robin.murphy@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 5 +++++ arch/arm64/include/asm/string.h | 2 ++ arch/arm64/lib/strcmp.S | 2 +- arch/arm64/lib/strncmp.S | 2 +- 4 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 89faca0e740d..bfa58409a4d4 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -525,6 +525,11 @@ alternative_endif #define EXPORT_SYMBOL_NOKASAN(name) EXPORT_SYMBOL(name) #endif +#ifdef CONFIG_KASAN_HW_TAGS +#define EXPORT_SYMBOL_NOHWKASAN(name) +#else +#define EXPORT_SYMBOL_NOHWKASAN(name) EXPORT_SYMBOL_NOKASAN(name) +#endif /* * Emit a 64-bit absolute little endian symbol reference in a way that * ensures that it will be resolved at build time, even when building a diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h index 3a3264ff47b9..95f7686b728d 100644 --- a/arch/arm64/include/asm/string.h +++ b/arch/arm64/include/asm/string.h @@ -12,11 +12,13 @@ extern char *strrchr(const char *, int c); #define __HAVE_ARCH_STRCHR extern char *strchr(const char *, int c); +#ifndef CONFIG_KASAN_HW_TAGS #define __HAVE_ARCH_STRCMP extern int strcmp(const char *, const char *); #define __HAVE_ARCH_STRNCMP extern int strncmp(const char *, const char *, __kernel_size_t); +#endif #define __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index d7bee210a798..83bcad72ec97 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -173,4 +173,4 @@ L(done): ret SYM_FUNC_END_PI(strcmp) -EXPORT_SYMBOL_NOKASAN(strcmp) +EXPORT_SYMBOL_NOHWKASAN(strcmp) diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index 48d44f7fddb1..e42bcfcd37e6 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -258,4 +258,4 @@ L(ret0): ret SYM_FUNC_END_PI(strncmp) -EXPORT_SYMBOL_NOKASAN(strncmp) +EXPORT_SYMBOL_NOHWKASAN(strncmp) From d9d1232b48344c6c72dbdf89fae1e7638e5df757 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:57:36 +0200 Subject: [PATCH 515/866] misc: bcm-vk: fix tty registration race Make sure to set the tty class-device driver data before registering the tty to avoid having a racing open() dereference a NULL pointer. Fixes: 91ca10d6fa07 ("misc: bcm-vk: add ttyVK support") Cc: stable@vger.kernel.org # 5.12 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917115736.5816-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/bcm-vk/bcm_vk_tty.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/misc/bcm-vk/bcm_vk_tty.c b/drivers/misc/bcm-vk/bcm_vk_tty.c index 1b6076a89ca6..6669625ba4c8 100644 --- a/drivers/misc/bcm-vk/bcm_vk_tty.c +++ b/drivers/misc/bcm-vk/bcm_vk_tty.c @@ -267,13 +267,13 @@ int bcm_vk_tty_init(struct bcm_vk *vk, char *name) struct device *tty_dev; tty_port_init(&vk->tty[i].port); - tty_dev = tty_port_register_device(&vk->tty[i].port, tty_drv, - i, dev); + tty_dev = tty_port_register_device_attr(&vk->tty[i].port, + tty_drv, i, dev, vk, + NULL); if (IS_ERR(tty_dev)) { err = PTR_ERR(tty_dev); goto unwind; } - dev_set_drvdata(tty_dev, vk); vk->tty[i].is_opened = false; } From ce1c42b4dacfe7d71c852d8bf3371067ccba865c Mon Sep 17 00:00:00 2001 From: Julian Sikorski Date: Mon, 13 Sep 2021 20:14:55 +0200 Subject: [PATCH 516/866] Re-enable UAS for LaCie Rugged USB3-FW with fk quirk Further testing has revealed that LaCie Rugged USB3-FW does work with uas as long as US_FL_NO_REPORT_OPCODES and US_FL_NO_SAME are enabled. Link: https://lore.kernel.org/linux-usb/2167ea48-e273-a336-a4e0-10a4e883e75e@redhat.com/ Cc: stable Suggested-by: Hans de Goede Reviewed-by: Hans de Goede Acked-by: Oliver Neukum Signed-off-by: Julian Sikorski Link: https://lore.kernel.org/r/20210913181454.7365-1-belegdol+github@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/unusual_uas.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index c35a6db993f1..4051c8cd0cd8 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -50,7 +50,7 @@ UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999, "LaCie", "Rugged USB3-FW", USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_IGNORE_UAS), + US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME), /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI From b55d37ef6b7db3eda9b4495a8d9b0a944ee8c67d Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Mon, 13 Sep 2021 23:01:06 +0200 Subject: [PATCH 517/866] usb-storage: Add quirk for ScanLogic SL11R-IDE older than 2.6c ScanLogic SL11R-IDE with firmware older than 2.6c (the latest one) has broken tag handling, preventing the device from working at all: usb 1-1: new full-speed USB device number 2 using uhci_hcd usb 1-1: New USB device found, idVendor=04ce, idProduct=0002, bcdDevice= 2.60 usb 1-1: New USB device strings: Mfr=1, Product=1, SerialNumber=0 usb 1-1: Product: USB Device usb 1-1: Manufacturer: USB Device usb-storage 1-1:1.0: USB Mass Storage device detected scsi host2: usb-storage 1-1:1.0 usbcore: registered new interface driver usb-storage usb 1-1: reset full-speed USB device number 2 using uhci_hcd usb 1-1: reset full-speed USB device number 2 using uhci_hcd usb 1-1: reset full-speed USB device number 2 using uhci_hcd usb 1-1: reset full-speed USB device number 2 using uhci_hcd Add US_FL_BULK_IGNORE_TAG to fix it. Also update my e-mail address. 2.6c is the only firmware that claims Linux compatibility. The firmware can be upgraded using ezotgdbg utility: https://github.com/asciilifeform/ezotgdbg Acked-by: Alan Stern Signed-off-by: Ondrej Zary Cc: stable Link: https://lore.kernel.org/r/20210913210106.12717-1-linux@zary.sk Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/unusual_devs.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index efa972be2ee3..c6b3fcf90180 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -416,9 +416,16 @@ UNUSUAL_DEV( 0x04cb, 0x0100, 0x0000, 0x2210, USB_SC_UFI, USB_PR_DEVICE, NULL, US_FL_FIX_INQUIRY | US_FL_SINGLE_LUN), /* - * Reported by Ondrej Zary + * Reported by Ondrej Zary * The device reports one sector more and breaks when that sector is accessed + * Firmwares older than 2.6c (the latest one and the only that claims Linux + * support) have also broken tag handling */ +UNUSUAL_DEV( 0x04ce, 0x0002, 0x0000, 0x026b, + "ScanLogic", + "SL11R-IDE", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_FIX_CAPACITY | US_FL_BULK_IGNORE_TAG), UNUSUAL_DEV( 0x04ce, 0x0002, 0x026c, 0x026c, "ScanLogic", "SL11R-IDE", From 517c7bf99bad3d6b9360558414aae634b7472d80 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Sep 2021 16:57:37 +0300 Subject: [PATCH 518/866] usb: musb: tusb6010: uninitialized data in tusb_fifo_write_unaligned() This is writing to the first 1 - 3 bytes of "val" and then writing all four bytes to musb_writel(). The last byte is always going to be garbage. Zero out the last bytes instead. Fixes: 550a7375fe72 ("USB: Add MUSB and TUSB support") Signed-off-by: Dan Carpenter Cc: stable Link: https://lore.kernel.org/r/20210916135737.GI25094@kili Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/tusb6010.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index c42937692207..c968ecda42aa 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -190,6 +190,7 @@ tusb_fifo_write_unaligned(void __iomem *fifo, const u8 *buf, u16 len) } if (len > 0) { /* Write the rest 1 - 3 bytes to FIFO */ + val = 0; memcpy(&val, buf, len); musb_writel(fifo, 0, val); } From c86a2d9058c5a4a05d20ef89e699b7a6b2c89da6 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 17 Sep 2021 00:27:05 +0200 Subject: [PATCH 519/866] cpumask: Omit terminating null byte in cpumap_print_{list,bitmask}_to_buf The changes in the patch series [1] introduced a terminating null byte when reading from cpulist or cpumap sysfs files, for example: $ xxd /sys/devices/system/node/node0/cpulist 00000000: 302d 310a 00 0-1.. Before this change, the output looked as follows: $ xxd /sys/devices/system/node/node0/cpulist 00000000: 302d 310a 0-1. Fix this regression by excluding the terminating null byte from the returned length in cpumap_print_list_to_buf and cpumap_print_bitmask_to_buf. [1] https://lore.kernel.org/all/20210806110251.560-1-song.bao.hua@hisilicon.com/ Fixes: 1fae562983ca ("cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list") Acked-by: Barry Song Acked-by: Yury Norov Signed-off-by: Tobias Klauser Link: https://lore.kernel.org/r/20210916222705.13554-1-tklauser@distanz.ch Signed-off-by: Greg Kroah-Hartman --- include/linux/cpumask.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5d4d07a9e1ed..1e7399fc69c0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -996,14 +996,15 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * - * Returns the length of how many bytes have been copied. + * Returns the length of how many bytes have been copied, excluding + * terminating '\0'. */ static inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } /** @@ -1018,7 +1019,7 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG From d5f6545934c47e97c0b48a645418e877b452a992 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 20 Sep 2021 10:26:21 -0700 Subject: [PATCH 520/866] qnx4: work around gcc false positive warning bug In commit b7213ffa0e58 ("qnx4: avoid stringop-overread errors") I tried to teach gcc about how the directory entry structure can be two different things depending on a status flag. It made the code clearer, and it seemed to make gcc happy. However, Arnd points to a gcc bug, where despite using two different members of a union, gcc then gets confused, and uses the size of one of the members to decide if a string overrun happens. And not necessarily the rigth one. End result: with some configurations, gcc-11 will still complain about the source buffer size being overread: fs/qnx4/dir.c: In function 'qnx4_readdir': fs/qnx4/dir.c:76:32: error: 'strnlen' specified bound [16, 48] exceeds source size 1 [-Werror=stringop-overread] 76 | size = strnlen(name, size); | ^~~~~~~~~~~~~~~~~~~ fs/qnx4/dir.c:26:22: note: source object declared here 26 | char de_name; | ^~~~~~~ because gcc will get confused about which union member entry is actually getting accessed, even when the source code is very clear about it. Gcc internally will have combined two "redundant" pointers (pointing to different union elements that are at the same offset), and takes the size checking from one or the other - not necessarily the right one. This is clearly a gcc bug, but we can work around it fairly easily. The biggest thing here is the big honking comment about why we do what we do. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578#c6 Reported-and-tested-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- fs/qnx4/dir.c | 36 +++++++++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 9 deletions(-) diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index 2a66844b7ff8..66645a5a35f3 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -20,12 +20,33 @@ * depending on the status field in the last byte. The * first byte is where the name start either way, and a * zero means it's empty. + * + * Also, due to a bug in gcc, we don't want to use the + * real (differently sized) name arrays in the inode and + * link entries, but always the 'de_name[]' one in the + * fake struct entry. + * + * See + * + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=99578#c6 + * + * for details, but basically gcc will take the size of the + * 'name' array from one of the used union entries randomly. + * + * This use of 'de_name[]' (48 bytes) avoids the false positive + * warnings that would happen if gcc decides to use 'inode.di_name' + * (16 bytes) even when the pointer and size were to come from + * 'link.dl_name' (48 bytes). + * + * In all cases the actual name pointer itself is the same, it's + * only the gcc internal 'what is the size of this field' logic + * that can get confused. */ union qnx4_directory_entry { struct { - char de_name; - char de_pad[62]; - char de_status; + const char de_name[48]; + u8 de_pad[15]; + u8 de_status; }; struct qnx4_inode_entry inode; struct qnx4_link_info link; @@ -53,29 +74,26 @@ static int qnx4_readdir(struct file *file, struct dir_context *ctx) ix = (ctx->pos >> QNX4_DIR_ENTRY_SIZE_BITS) % QNX4_INODES_PER_BLOCK; for (; ix < QNX4_INODES_PER_BLOCK; ix++, ctx->pos += QNX4_DIR_ENTRY_SIZE) { union qnx4_directory_entry *de; - const char *name; offset = ix * QNX4_DIR_ENTRY_SIZE; de = (union qnx4_directory_entry *) (bh->b_data + offset); - if (!de->de_name) + if (!de->de_name[0]) continue; if (!(de->de_status & (QNX4_FILE_USED|QNX4_FILE_LINK))) continue; if (!(de->de_status & QNX4_FILE_LINK)) { size = sizeof(de->inode.di_fname); - name = de->inode.di_fname; ino = blknum * QNX4_INODES_PER_BLOCK + ix - 1; } else { size = sizeof(de->link.dl_fname); - name = de->link.dl_fname; ino = ( le32_to_cpu(de->link.dl_inode_blk) - 1 ) * QNX4_INODES_PER_BLOCK + de->link.dl_inode_ndx; } - size = strnlen(name, size); + size = strnlen(de->de_name, size); QNX4DEBUG((KERN_INFO "qnx4_readdir:%.*s\n", size, name)); - if (!dir_emit(ctx, name, size, ino, DT_UNKNOWN)) { + if (!dir_emit(ctx, de->de_name, size, ino, DT_UNKNOWN)) { brelse(bh); return 0; } From 7af526c740bdbd5b4dcebba04ace5b3b0c07801f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 14 Sep 2021 11:29:49 +0200 Subject: [PATCH 521/866] nvmem: NVMEM_NINTENDO_OTP should depend on WII The Nintendo Wii and Wii U OTP is only present on Nintendo Wii and Wii U consoles. Hence add a dependency on WII, to prevent asking the user about this driver when configuring a kernel without Nintendo Wii and Wii U console support. Fixes: 3683b761fe3a10ad ("nvmem: nintendo-otp: Add new driver for the Wii and Wii U OTP") Reviewed-by: Emmanuel Gil Peyrot Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/01318920709dddc4d85fe895e2083ca0eee234d8.1631611652.git.geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index 39854d43758b..da414617a54d 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -109,6 +109,7 @@ config MTK_EFUSE config NVMEM_NINTENDO_OTP tristate "Nintendo Wii and Wii U OTP Support" + depends on WII || COMPILE_TEST help This is a driver exposing the OTP of a Nintendo Wii or Wii U console. From 708c87168b6121abc74b2a57d0c498baaf70cbea Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 6 Sep 2021 12:43:01 +0300 Subject: [PATCH 522/866] ceph: fix off by one bugs in unsafe_request_wait() The "> max" tests should be ">= max" to prevent an out of bounds access on the next lines. Fixes: e1a4541ec0b9 ("ceph: flush the mdlog before waiting on unsafe reqs") Signed-off-by: Dan Carpenter Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 6c0e52fd0743..3e42d0466521 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2263,7 +2263,7 @@ retry: list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; - if (unlikely(s->s_mds > max)) { + if (unlikely(s->s_mds >= max)) { spin_unlock(&ci->i_unsafe_lock); goto retry; } @@ -2277,7 +2277,7 @@ retry: list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; - if (unlikely(s->s_mds > max)) { + if (unlikely(s->s_mds >= max)) { spin_unlock(&ci->i_unsafe_lock); goto retry; } From bb509a6ffed2c8b0950f637ab5779aa818ed1596 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Thu, 16 Sep 2021 15:50:23 +0100 Subject: [PATCH 523/866] comedi: Fix memory leak in compat_insnlist() `compat_insnlist()` handles the 32-bit version of the `COMEDI_INSNLIST` ioctl (whenwhen `CONFIG_COMPAT` is enabled). It allocates memory to temporarily hold an array of `struct comedi_insn` converted from the 32-bit version in user space. This memory is only being freed if there is a fault while filling the array, otherwise it is leaked. Add a call to `kfree()` to fix the leak. Fixes: b8d47d881305 ("comedi: get rid of compat_alloc_user_space() mess in COMEDI_INSNLIST compat") Cc: Al Viro Cc: Greg Kroah-Hartman Cc: linux-staging@lists.linux.dev Cc: # 5.13+ Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20210916145023.157479-1-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/comedi/comedi_fops.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index df77b6bf5c64..763cea8418f8 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -3090,6 +3090,7 @@ static int compat_insnlist(struct file *file, unsigned long arg) mutex_lock(&dev->mutex); rc = do_insnlist_ioctl(dev, insns, insnlist32.n_insns, file); mutex_unlock(&dev->mutex); + kfree(insns); return rc; } From 2de9d8e0d2fe3a1eb632def2245529067cb35db5 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:09:37 -0700 Subject: [PATCH 524/866] driver core: fw_devlink: Improve handling of cyclic dependencies When we have a dependency of the form: Device-A -> Device-C Device-B Device-C -> Device-B Where, * Indentation denotes "child of" parent in previous line. * X -> Y denotes X is consumer of Y based on firmware (Eg: DT). We have cyclic dependency: device-A -> device-C -> device-B -> device-A fw_devlink current treats device-C -> device-B dependency as an invalid dependency and doesn't enforce it but leaves the rest of the dependencies as is. While the current behavior is necessary, it is not sufficient if the false dependency in this example is actually device-A -> device-C. When this is the case, device-C will correctly probe defer waiting for device-B to be added, but device-A will be incorrectly probe deferred by fw_devlink waiting on device-C to probe successfully. Due to this, none of the devices in the cycle will end up probing. To fix this, we need to go relax all the dependencies in the cycle like we already do in the other instances where fw_devlink detects cycles. A real world example of this was reported[1] and analyzed[2]. [1] - https://lore.kernel.org/lkml/0a2c4106-7f48-2bb5-048e-8c001a7c3fda@samsung.com/ [2] - https://lore.kernel.org/lkml/CAGETcx8peaew90SWiux=TyvuGgvTQOmO4BFALz7aj0Za5QdNFQ@mail.gmail.com/ Fixes: f9aa460672c9 ("driver core: Refactor fw_devlink feature") Cc: stable Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915170940.617415-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index e65dd803a453..316df6027093 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1772,14 +1772,21 @@ static int fw_devlink_create_devlink(struct device *con, * be broken by applying logic. Check for these types of cycles and * break them so that devices in the cycle probe properly. * - * If the supplier's parent is dependent on the consumer, then - * the consumer-supplier dependency is a false dependency. So, - * treat it as an invalid link. + * If the supplier's parent is dependent on the consumer, then the + * consumer and supplier have a cyclic dependency. Since fw_devlink + * can't tell which of the inferred dependencies are incorrect, don't + * enforce probe ordering between any of the devices in this cyclic + * dependency. Do this by relaxing all the fw_devlink device links in + * this cycle and by treating the fwnode link between the consumer and + * the supplier as an invalid dependency. */ sup_dev = fwnode_get_next_parent_dev(sup_handle); if (sup_dev && device_is_dependent(con, sup_dev)) { - dev_dbg(con, "Not linking to %pfwP - False link\n", - sup_handle); + dev_info(con, "Fixing up cyclic dependency with %pfwP (%s)\n", + sup_handle, dev_name(sup_dev)); + device_links_write_lock(); + fw_devlink_relax_cycle(con, sup_dev); + device_links_write_unlock(); ret = -EINVAL; } else { /* From cb1bcf5ed536747013fe2b3f9bd56ce3242c295a Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 20 Sep 2021 20:07:34 +0900 Subject: [PATCH 525/866] ALSA: firewire-motu: fix truncated bytes in message tracepoints In MOTU protocol v2/v3, first two data chunks across 2nd and 3rd data channels includes message bytes from device. The total size of message is 48 bits per data block. The 'data_block_message' tracepoints event produced by ALSA firewire-motu driver exposes the sequence of messages to userspace in 64 bit storage, however lower 32 bits are actually available since current implementation truncates 16 bits in upper of the message as a result of bit shift operation within 32 bit storage. This commit fixes the bug by perform the bit shift in 64 bit storage. Fixes: c6b0b9e65f09 ("ALSA: firewire-motu: add tracepoints for messages for unique protocol") Cc: Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20210920110734.27161-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- sound/firewire/motu/amdtp-motu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/firewire/motu/amdtp-motu.c b/sound/firewire/motu/amdtp-motu.c index 5388b85fb60e..a18c2c033e83 100644 --- a/sound/firewire/motu/amdtp-motu.c +++ b/sound/firewire/motu/amdtp-motu.c @@ -276,10 +276,11 @@ static void __maybe_unused copy_message(u64 *frames, __be32 *buffer, /* This is just for v2/v3 protocol. */ for (i = 0; i < data_blocks; ++i) { - *frames = (be32_to_cpu(buffer[1]) << 16) | - (be32_to_cpu(buffer[2]) >> 16); + *frames = be32_to_cpu(buffer[1]); + *frames <<= 16; + *frames |= be32_to_cpu(buffer[2]) >> 16; + ++frames; buffer += data_block_quadlets; - frames++; } } From 0e3dbf765fe22060acbcb8eb8c4d256e655a1247 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 20 Sep 2021 13:12:28 +0100 Subject: [PATCH 526/866] kselftest/arm64: signal: Skip tests if required features are missing During initialization of a signal testcase, features declared as required are properly checked against the running system but no action is then taken to effectively skip such a testcase. Fix core signals test logic to abort initialization and report such a testcase as skipped to the KSelfTest framework. Fixes: f96bf4340316 ("kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils") Signed-off-by: Cristian Marussi Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20210920121228.35368-1-cristian.marussi@arm.com Signed-off-by: Catalin Marinas --- tools/testing/selftests/arm64/signal/test_signals_utils.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 6836510a522f..22722abc9dfa 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -266,16 +266,19 @@ int test_init(struct tdescr *td) td->feats_supported |= FEAT_SSBS; if (getauxval(AT_HWCAP) & HWCAP_SVE) td->feats_supported |= FEAT_SVE; - if (feats_ok(td)) + if (feats_ok(td)) { fprintf(stderr, "Required Features: [%s] supported\n", feats_to_string(td->feats_required & td->feats_supported)); - else + } else { fprintf(stderr, "Required Features: [%s] NOT supported\n", feats_to_string(td->feats_required & ~td->feats_supported)); + td->result = KSFT_SKIP; + return 0; + } } /* Perform test specific additional initialization */ From e44fd5081c50b0ffdb75ce6c83452e60173d791b Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 20 Sep 2021 19:01:42 -0500 Subject: [PATCH 527/866] ksmbd: log that server is experimental at module load While we are working through detailed security reviews of ksmbd server code we should remind users that it is an experimental module by adding a warning when the module loads. Currently the module shows as experimental in Kconfig and is disabled by default, but we don't want to confuse users. Although ksmbd passes a wide variety of the important functional tests (since initial focus had been largely on functional testing such as smbtorture, xfstests etc.), and ksmbd has added key security features (e.g. GCM256 encryption, Kerberos support), there are ongoing detailed reviews of the code base for path processing and network buffer decoding, and this patch reminds users that the module should be considered "experimental." Reviewed-by: Namjae Jeon Reviewed-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/ksmbd/server.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index e6a9f6aa47eb..2a2b2135bfde 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -584,6 +584,9 @@ static int __init ksmbd_server_init(void) ret = ksmbd_workqueue_init(); if (ret) goto err_crypto_destroy; + + pr_warn_once("The ksmbd server is experimental, use at your own risk.\n"); + return 0; err_crypto_destroy: From 9f6323311c7064414bfd1edb28e0837baf6b3c7f Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 18 Sep 2021 21:02:39 +0900 Subject: [PATCH 528/866] ksmbd: add default data stream name in FILE_STREAM_INFORMATION Windows client expect to get default stream name(::DATA) in FILE_STREAM_INFORMATION response even if there is no stream data in file. This patch fix update failure when writing ppt or doc files. Signed-off-by: Namjae Jeon Reviewed-By: Tom Talpey Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 6304c9bda479..f59f9b8be51c 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4428,17 +4428,15 @@ static void get_file_stream_info(struct ksmbd_work *work, file_info->NextEntryOffset = cpu_to_le32(next); } - if (nbytes) { + if (!S_ISDIR(stat.mode)) { file_info = (struct smb2_file_stream_info *) &rsp->Buffer[nbytes]; streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName, "::$DATA", 7, conn->local_nls, 0); streamlen *= 2; file_info->StreamNameLength = cpu_to_le32(streamlen); - file_info->StreamSize = S_ISDIR(stat.mode) ? 0 : - cpu_to_le64(stat.size); - file_info->StreamAllocationSize = S_ISDIR(stat.mode) ? 0 : - cpu_to_le64(stat.size); + file_info->StreamSize = 0; + file_info->StreamAllocationSize = 0; nbytes += sizeof(struct smb2_file_stream_info) + streamlen; } From 96c8395e2166efa86082f3b71567ffd84936439b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 21 Sep 2021 15:44:06 +0100 Subject: [PATCH 529/866] spi: Revert modalias changes During the v5.13 cycle we updated the SPI subsystem to generate OF style modaliases for SPI devices, replacing the old Linux style modalises we used to generate based on spi_device_id which are the DT style name with the vendor removed. Unfortunately this means that we start only reporting OF style modalises and not the old ones and there is nothing that ensures that drivers list every possible OF compatible string in their OF ID table. The result is that there are systems which have been relying on loading modules based on the old style that are now broken, as found by Russell King with spi-nor on Macchiatobin. spi-nor is a particularly problematic case for this, it only lists a single generic DT compatible jedec,spi-nor in the driver but supports a huge raft of device specific compatibles, with a large set of part numbers many of which are offered by multiple vendors. Russell's searches of upstream device trees has turned up examples with vendor names written in non-standard ways too. To make matters worse up until 8ff16cf77ce3 ("Documentation: devicetree: m25p80: add "nor-jedec" binding") the generic compatible was not part of the binding so there are device trees out there written to that binding version which don't list it all. The sheer number of parts supported together with our previous approach of ignoring the vendor ID makes robustly fixing this by adding compatibles to the spi-nor driver seem problematic, the current DT binding document does not list all the parts supported by the driver at the minute (further patches will fix this). I've also investigated supporting both formats of modalias simultaneously but that doesn't seem possible, especially without breaking our userspace ABI which is obviously not viable. Instead revert the relevant changes for now: e09f2ab8eecc ("spi: update modalias_show after of_device_uevent_modalias support") 3ce6c9e2617e ("spi: add of_device_uevent_modalias support") This will unfortunately mean that any system which had started having modules autoload based on the OF compatibles for drivers that list things there but not in the spi_device_ids will now not have those modules load which is itself a regression. Since it affects a narrower time window and the particularly problematic spi-nor driver may be critical to system boot on smaller systems this seems the best of a series of bad options. I will start an audit of SPI drivers to identify and fix cases where things won't autoload using spi_device_id, this is not great but seems to be the best way forward that anyone has been able to identify. Thanks to Russell for both his report and the additional diagnostic and analysis work he has done here, the detailed research above was his work. Fixes: e09f2ab8eecc ("spi: update modalias_show after of_device_uevent_modalias support") Fixes: 3ce6c9e2617e ("spi: add of_device_uevent_modalias support") Reported-by: Russell King (Oracle) Suggested-by: Russell King (Oracle) Signed-off-by: Mark Brown Tested-by: Russell King (Oracle) Cc: Andreas Schwab Cc: Marco Felsch --- drivers/spi/spi.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 57e2499ec1ed..aea037c65985 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -58,10 +58,6 @@ modalias_show(struct device *dev, struct device_attribute *a, char *buf) const struct spi_device *spi = to_spi_device(dev); int len; - len = of_device_modalias(dev, buf, PAGE_SIZE); - if (len != -ENODEV) - return len; - len = acpi_device_modalias(dev, buf, PAGE_SIZE - 1); if (len != -ENODEV) return len; @@ -367,10 +363,6 @@ static int spi_uevent(struct device *dev, struct kobj_uevent_env *env) const struct spi_device *spi = to_spi_device(dev); int rc; - rc = of_device_uevent_modalias(dev, env); - if (rc != -ENODEV) - return rc; - rc = acpi_device_uevent_modalias(dev, env); if (rc != -ENODEV) return rc; From e946d3c887a9dc33aa82a349c6284f4a084163f4 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Sep 2021 23:33:35 +0300 Subject: [PATCH 530/866] cifs: fix a sign extension bug The problem is the mismatched types between "ctx->total_len" which is an unsigned int, "rc" which is an int, and "ctx->rc" which is a ssize_t. The code does: ctx->rc = (rc == 0) ? ctx->total_len : rc; We want "ctx->rc" to store the negative "rc" error code. But what happens is that "rc" is type promoted to a high unsigned int and 'ctx->rc" will store the high positive value instead of a negative value. The fix is to change "rc" from an int to a ssize_t. Fixes: c610c4b619e5 ("CIFS: Add asynchronous write support through kernel AIO") Signed-off-by: Dan Carpenter Signed-off-by: Steve French --- fs/cifs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6796fc73b304..0ab5bb24b8ca 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3113,7 +3113,7 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; struct dentry *dentry = ctx->cfile->dentry; - int rc; + ssize_t rc; tcon = tlink_tcon(ctx->cfile->tlink); cifs_sb = CIFS_SB(dentry->d_sb); From 248f064af222a1f97ee02c84a98013dfbccad386 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Tue, 21 Sep 2021 16:52:15 +0200 Subject: [PATCH 531/866] s390/qeth: fix NULL deref in qeth_clear_working_pool_list() When qeth_set_online() calls qeth_clear_working_pool_list() to roll back after an error exit from qeth_hardsetup_card(), we are at risk of accessing card->qdio.in_q before it was allocated by qeth_alloc_qdio_queues() via qeth_mpc_initialize(). qeth_clear_working_pool_list() then dereferences NULL, and by writing to queue->bufs[i].pool_entry scribbles all over the CPU's lowcore. Resulting in a crash when those lowcore areas are used next (eg. on the next machine-check interrupt). Such a scenario would typically happen when the device is first set online and its queues aren't allocated yet. An early IO error or certain misconfigs (eg. mismatched transport mode, bad portno) then cause us to error out from qeth_hardsetup_card() with card->qdio.in_q still being NULL. Fix it by checking the pointer for NULL before accessing it. Note that we also have (rare) paths inside qeth_mpc_initialize() where a configuration change can cause us to free the existing queues, expecting that subsequent code will allocate them again. If we then error out before that re-allocation happens, the same bug occurs. Fixes: eff73e16ee11 ("s390/qeth: tolerate pre-filled RX buffer") Reported-by: Stefan Raspl Root-caused-by: Heiko Carstens Signed-off-by: Julian Wiedmann Reviewed-by: Alexandra Winter Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 41ca6273b750..3fba440a0731 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -202,6 +202,9 @@ static void qeth_clear_working_pool_list(struct qeth_card *card) &card->qdio.in_buf_pool.entry_list, list) list_del(&pool_entry->list); + if (!queue) + return; + for (i = 0; i < ARRAY_SIZE(queue->bufs); i++) queue->bufs[i].pool_entry = NULL; } From ee909d0b1dac8632eeb78cbf17661d6c7674bbd0 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Tue, 21 Sep 2021 16:52:16 +0200 Subject: [PATCH 532/866] s390/qeth: Fix deadlock in remove_discipline Problem: qeth_close_dev_handler is a worker that tries to acquire card->discipline_mutex via drv->set_offline() in ccwgroup_set_offline(). Since commit b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal") qeth_remove_discipline() is called under card->discipline_mutex and cancels the work and waits for it to finish. STOPLAN reception with reason code IPA_RC_VEPA_TO_VEB_TRANSITION is the only situation that schedules close_dev_work. In that situation scheduling qeth recovery will also result in an offline interface, when resetting the isolation mode fails, if the external switch is still set to VEB. And since commit 0b9902c1fcc5 ("s390/qeth: fix deadlock during recovery") qeth recovery does not aquire card->discipline_mutex anymore. So we accept the longer pathlength of qeth_schedule_recovery in this error situation and re-use the existing function. As a side-benefit this changes the hwtrap to behave like during recovery instead of like during a user-triggered set_offline. Fixes: b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal") Signed-off-by: Alexandra Winter Acked-by: Julian Wiedmann Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- drivers/s390/net/qeth_core.h | 1 - drivers/s390/net/qeth_core_main.c | 16 ++++------------ drivers/s390/net/qeth_l2_main.c | 1 - drivers/s390/net/qeth_l3_main.c | 1 - 4 files changed, 4 insertions(+), 15 deletions(-) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 535a60b3946d..a5aa0bdc61d6 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -858,7 +858,6 @@ struct qeth_card { struct napi_struct napi; struct qeth_rx rx; struct delayed_work buffer_reclaim_work; - struct work_struct close_dev_work; }; static inline bool qeth_card_hw_is_reachable(struct qeth_card *card) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 3fba440a0731..9f26706051e5 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -70,15 +70,6 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, static int qeth_qdio_establish(struct qeth_card *); static void qeth_free_qdio_queues(struct qeth_card *card); -static void qeth_close_dev_handler(struct work_struct *work) -{ - struct qeth_card *card; - - card = container_of(work, struct qeth_card, close_dev_work); - QETH_CARD_TEXT(card, 2, "cldevhdl"); - ccwgroup_set_offline(card->gdev); -} - static const char *qeth_get_cardname(struct qeth_card *card) { if (IS_VM_NIC(card)) { @@ -795,10 +786,12 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card, case IPA_CMD_STOPLAN: if (cmd->hdr.return_code == IPA_RC_VEPA_TO_VEB_TRANSITION) { dev_err(&card->gdev->dev, - "Interface %s is down because the adjacent port is no longer in reflective relay mode\n", + "Adjacent port of interface %s is no longer in reflective relay mode, trigger recovery\n", netdev_name(card->dev)); - schedule_work(&card->close_dev_work); + /* Set offline, then probably fail to set online: */ + qeth_schedule_recovery(card); } else { + /* stay online for subsequent STARTLAN */ dev_warn(&card->gdev->dev, "The link for interface %s on CHPID 0x%X failed\n", netdev_name(card->dev), card->info.chpid); @@ -1540,7 +1533,6 @@ static void qeth_setup_card(struct qeth_card *card) INIT_LIST_HEAD(&card->ipato.entries); qeth_init_qdio_info(card); INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work); - INIT_WORK(&card->close_dev_work, qeth_close_dev_handler); hash_init(card->rx_mode_addrs); hash_init(card->local_addrs4); hash_init(card->local_addrs6); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 72e84ff9fea5..dc6c00768d91 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -2307,7 +2307,6 @@ static void qeth_l2_remove_device(struct ccwgroup_device *gdev) if (gdev->state == CCWGROUP_ONLINE) qeth_set_offline(card, card->discipline, false); - cancel_work_sync(&card->close_dev_work); if (card->dev->reg_state == NETREG_REGISTERED) { priv = netdev_priv(card->dev); if (priv->brport_features & BR_LEARNING_SYNC) { diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 3a523e700a5a..6fd3e288f059 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1969,7 +1969,6 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_set_offline(card, card->discipline, false); - cancel_work_sync(&card->close_dev_work); if (card->dev->reg_state == NETREG_REGISTERED) unregister_netdev(card->dev); From d2b59bd4b06d84a4eadb520b0f71c62fe8ec0a62 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Tue, 21 Sep 2021 16:52:17 +0200 Subject: [PATCH 533/866] s390/qeth: fix deadlock during failing recovery Commit 0b9902c1fcc5 ("s390/qeth: fix deadlock during recovery") removed taking discipline_mutex inside qeth_do_reset(), fixing potential deadlocks. An error path was missed though, that still takes discipline_mutex and thus has the original deadlock potential. Intermittent deadlocks were seen when a qeth channel path is configured offline, causing a race between qeth_do_reset and ccwgroup_remove. Call qeth_set_offline() directly in the qeth_do_reset() error case and then a new variant of ccwgroup_set_offline(), without taking discipline_mutex. Fixes: b41b554c1ee7 ("s390/qeth: fix locking for discipline setup / removal") Signed-off-by: Alexandra Winter Reviewed-by: Julian Wiedmann Signed-off-by: Julian Wiedmann Signed-off-by: Jakub Kicinski --- arch/s390/include/asm/ccwgroup.h | 2 +- drivers/s390/cio/ccwgroup.c | 10 ++++++++-- drivers/s390/net/qeth_core_main.c | 3 ++- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h index 36dbf5043fc0..aa995d91cd1d 100644 --- a/arch/s390/include/asm/ccwgroup.h +++ b/arch/s390/include/asm/ccwgroup.h @@ -55,7 +55,7 @@ int ccwgroup_create_dev(struct device *root, struct ccwgroup_driver *gdrv, int num_devices, const char *buf); extern int ccwgroup_set_online(struct ccwgroup_device *gdev); -extern int ccwgroup_set_offline(struct ccwgroup_device *gdev); +int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv); extern int ccwgroup_probe_ccwdev(struct ccw_device *cdev); extern void ccwgroup_remove_ccwdev(struct ccw_device *cdev); diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index 2ec741106cb6..f0538609dfe4 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -77,12 +77,13 @@ EXPORT_SYMBOL(ccwgroup_set_online); /** * ccwgroup_set_offline() - disable a ccwgroup device * @gdev: target ccwgroup device + * @call_gdrv: Call the registered gdrv set_offline function * * This function attempts to put the ccwgroup device into the offline state. * Returns: * %0 on success and a negative error value on failure. */ -int ccwgroup_set_offline(struct ccwgroup_device *gdev) +int ccwgroup_set_offline(struct ccwgroup_device *gdev, bool call_gdrv) { struct ccwgroup_driver *gdrv = to_ccwgroupdrv(gdev->dev.driver); int ret = -EINVAL; @@ -91,11 +92,16 @@ int ccwgroup_set_offline(struct ccwgroup_device *gdev) return -EAGAIN; if (gdev->state == CCWGROUP_OFFLINE) goto out; + if (!call_gdrv) { + ret = 0; + goto offline; + } if (gdrv->set_offline) ret = gdrv->set_offline(gdev); if (ret) goto out; +offline: gdev->state = CCWGROUP_OFFLINE; out: atomic_set(&gdev->onoff, 0); @@ -124,7 +130,7 @@ static ssize_t ccwgroup_online_store(struct device *dev, if (value == 1) ret = ccwgroup_set_online(gdev); else if (value == 0) - ret = ccwgroup_set_offline(gdev); + ret = ccwgroup_set_offline(gdev, true); else ret = -EINVAL; out: diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 9f26706051e5..e9807d2996a9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5514,7 +5514,8 @@ static int qeth_do_reset(void *data) dev_info(&card->gdev->dev, "Device successfully recovered!\n"); } else { - ccwgroup_set_offline(card->gdev); + qeth_set_offline(card, disc, true); + ccwgroup_set_offline(card->gdev, false); dev_warn(&card->gdev->dev, "The qeth device driver failed to recover an error on the device\n"); } From 88b099006d83b0bf452379cad4ce494329084726 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 17 Sep 2021 17:43:49 +0300 Subject: [PATCH 534/866] scsi: ufs: core: Revert "scsi: ufs: Synchronize SCSI and UFS error handling" This reverts commit a113eaaf86373362b053279049907ff82b5df6c8. There are a couple of issues with the commit: 1. It causes deadlocks. 2. It causes the shost->eh_cmd_q list of failed requests not to be processed, ever. So revert it. 1. Deadlocks The SCSI error handler runs with requests blocked beginning when scsi_schedule_eh() sets SHOST_RECOVERY state, continuing through scsi_error_handler() callback ->eh_strategy_handler() until scsi_restart_operations() is called. By setting eh_strategy_handler to ufshcd_err_handler, the patch changed the UFS error handler to run with requests blocked, including PM requests, for the entire run of the error handler. That conflicts with UFS error handler existing synchronization with UFS device PM operations. The UFS error handler synchronizes with runtime PM by doing pm_runtime_get_sync() prior to blocking requests itself. It synchronizes with system PM by use of hba->host_sem, again before blocking requests itself. However, if requests are already blocked, then PM operations will block. So: the UFS error handler blocks waiting on PM + PM blocks waiting on SCSI PM requests to process or fail + PM requests are blocked waiting on error handling to finish = deadlock This happens both for runtime PM and system PM. Prior to the patch, these deadlocks could not happen even if SCSI error handling was running, because the presence of requests in shost->eh_cmd_q would mean the queues could not be suspended, which would mean that, should the UFS error handler run at the same time, it would not need to wait for PM or vice versa. Please note these scenarios are not just theoretical, they were found during testing on a Samsung Galaxy Book S. 2. ->eh_strategy_handler() must process shost->eh_cmd_q list of failed requests, as all other eh_strategy_handler's do except UFS error handler. Refer for example: scsi_unjam_host(), ata_scsi_error() and sas_scsi_recover_host(). Link: https://lore.kernel.org/r/20210917144349.14058-1-adrian.hunter@intel.com Fixes: a113eaaf8637 ("scsi: ufs: Synchronize SCSI and UFS error handling") Reviewed-by: Bart Van Assche Signed-off-by: Adrian Hunter Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 111 +++++++++++++++++++------------------- drivers/scsi/ufs/ufshcd.h | 4 ++ 2 files changed, 58 insertions(+), 57 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 67889d74761c..a3df5804b2c7 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -17,8 +17,6 @@ #include #include #include -#include -#include "../scsi_transport_api.h" #include "ufshcd.h" #include "ufs_quirks.h" #include "unipro.h" @@ -237,6 +235,7 @@ static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up); static irqreturn_t ufshcd_intr(int irq, void *__hba); static int ufshcd_change_power_mode(struct ufs_hba *hba, struct ufs_pa_layer_attr *pwr_mode); +static void ufshcd_schedule_eh_work(struct ufs_hba *hba); static int ufshcd_setup_hba_vreg(struct ufs_hba *hba, bool on); static int ufshcd_setup_vreg(struct ufs_hba *hba, bool on); static inline int ufshcd_config_vreg_hpm(struct ufs_hba *hba, @@ -2759,8 +2758,13 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd) out: up_read(&hba->clk_scaling_lock); - if (ufs_trigger_eh()) - scsi_schedule_eh(hba->host); + if (ufs_trigger_eh()) { + unsigned long flags; + + spin_lock_irqsave(hba->host->host_lock, flags); + ufshcd_schedule_eh_work(hba); + spin_unlock_irqrestore(hba->host->host_lock, flags); + } return err; } @@ -3919,35 +3923,6 @@ out: } EXPORT_SYMBOL_GPL(ufshcd_dme_get_attr); -static inline bool ufshcd_is_saved_err_fatal(struct ufs_hba *hba) -{ - lockdep_assert_held(hba->host->host_lock); - - return (hba->saved_uic_err & UFSHCD_UIC_DL_PA_INIT_ERROR) || - (hba->saved_err & (INT_FATAL_ERRORS | UFSHCD_UIC_HIBERN8_MASK)); -} - -static void ufshcd_schedule_eh(struct ufs_hba *hba) -{ - bool schedule_eh = false; - unsigned long flags; - - spin_lock_irqsave(hba->host->host_lock, flags); - /* handle fatal errors only when link is not in error state */ - if (hba->ufshcd_state != UFSHCD_STATE_ERROR) { - if (hba->force_reset || ufshcd_is_link_broken(hba) || - ufshcd_is_saved_err_fatal(hba)) - hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_FATAL; - else - hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_NON_FATAL; - schedule_eh = true; - } - spin_unlock_irqrestore(hba->host->host_lock, flags); - - if (schedule_eh) - scsi_schedule_eh(hba->host); -} - /** * ufshcd_uic_pwr_ctrl - executes UIC commands (which affects the link power * state) and waits for it to take effect. @@ -3968,7 +3943,6 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) { DECLARE_COMPLETION_ONSTACK(uic_async_done); unsigned long flags; - bool schedule_eh = false; u8 status; int ret; bool reenable_intr = false; @@ -4038,14 +4012,10 @@ out: ufshcd_enable_intr(hba, UIC_COMMAND_COMPL); if (ret) { ufshcd_set_link_broken(hba); - schedule_eh = true; + ufshcd_schedule_eh_work(hba); } - out_unlock: spin_unlock_irqrestore(hba->host->host_lock, flags); - - if (schedule_eh) - ufshcd_schedule_eh(hba); mutex_unlock(&hba->uic_cmd_mutex); return ret; @@ -5911,6 +5881,27 @@ out: return err_handling; } +/* host lock must be held before calling this func */ +static inline bool ufshcd_is_saved_err_fatal(struct ufs_hba *hba) +{ + return (hba->saved_uic_err & UFSHCD_UIC_DL_PA_INIT_ERROR) || + (hba->saved_err & (INT_FATAL_ERRORS | UFSHCD_UIC_HIBERN8_MASK)); +} + +/* host lock must be held before calling this func */ +static inline void ufshcd_schedule_eh_work(struct ufs_hba *hba) +{ + /* handle fatal errors only when link is not in error state */ + if (hba->ufshcd_state != UFSHCD_STATE_ERROR) { + if (hba->force_reset || ufshcd_is_link_broken(hba) || + ufshcd_is_saved_err_fatal(hba)) + hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_FATAL; + else + hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED_NON_FATAL; + queue_work(hba->eh_wq, &hba->eh_work); + } +} + static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow) { down_write(&hba->clk_scaling_lock); @@ -6044,11 +6035,11 @@ static bool ufshcd_is_pwr_mode_restore_needed(struct ufs_hba *hba) /** * ufshcd_err_handler - handle UFS errors that require s/w attention - * @host: SCSI host pointer + * @work: pointer to work structure */ -static void ufshcd_err_handler(struct Scsi_Host *host) +static void ufshcd_err_handler(struct work_struct *work) { - struct ufs_hba *hba = shost_priv(host); + struct ufs_hba *hba; unsigned long flags; bool err_xfer = false; bool err_tm = false; @@ -6056,9 +6047,10 @@ static void ufshcd_err_handler(struct Scsi_Host *host) int tag; bool needs_reset = false, needs_restore = false; + hba = container_of(work, struct ufs_hba, eh_work); + down(&hba->host_sem); spin_lock_irqsave(hba->host->host_lock, flags); - hba->host->host_eh_scheduled = 0; if (ufshcd_err_handling_should_stop(hba)) { if (hba->ufshcd_state != UFSHCD_STATE_ERROR) hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL; @@ -6371,6 +6363,7 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status) "host_regs: "); ufshcd_print_pwr_info(hba); } + ufshcd_schedule_eh_work(hba); retval |= IRQ_HANDLED; } /* @@ -6382,10 +6375,6 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status) hba->errors = 0; hba->uic_error = 0; spin_unlock(hba->host->host_lock); - - if (queue_eh_work) - ufshcd_schedule_eh(hba); - return retval; } @@ -7048,17 +7037,15 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) * will be to send LU reset which, again, is a spec violation. * To avoid these unnecessary/illegal steps, first we clean up * the lrb taken by this cmd and re-set it in outstanding_reqs, - * then queue the error handler and bail. + * then queue the eh_work and bail. */ if (lrbp->lun == UFS_UPIU_UFS_DEVICE_WLUN) { ufshcd_update_evt_hist(hba, UFS_EVT_ABORT, lrbp->lun); spin_lock_irqsave(host->host_lock, flags); hba->force_reset = true; + ufshcd_schedule_eh_work(hba); spin_unlock_irqrestore(host->host_lock, flags); - - ufshcd_schedule_eh(hba); - goto release; } @@ -7191,10 +7178,11 @@ static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd) spin_lock_irqsave(hba->host->host_lock, flags); hba->force_reset = true; + ufshcd_schedule_eh_work(hba); dev_err(hba->dev, "%s: reset in progress - 1\n", __func__); spin_unlock_irqrestore(hba->host->host_lock, flags); - ufshcd_err_handler(hba->host); + flush_work(&hba->eh_work); spin_lock_irqsave(hba->host->host_lock, flags); if (hba->ufshcd_state == UFSHCD_STATE_ERROR) @@ -8604,6 +8592,8 @@ static void ufshcd_hba_exit(struct ufs_hba *hba) if (hba->is_powered) { ufshcd_exit_clk_scaling(hba); ufshcd_exit_clk_gating(hba); + if (hba->eh_wq) + destroy_workqueue(hba->eh_wq); ufs_debugfs_hba_exit(hba); ufshcd_variant_hba_exit(hba); ufshcd_setup_vreg(hba, false); @@ -9448,10 +9438,6 @@ static int ufshcd_set_dma_mask(struct ufs_hba *hba) return dma_set_mask_and_coherent(hba->dev, DMA_BIT_MASK(32)); } -static struct scsi_transport_template ufshcd_transport_template = { - .eh_strategy_handler = ufshcd_err_handler, -}; - /** * ufshcd_alloc_host - allocate Host Bus Adapter (HBA) * @dev: pointer to device handle @@ -9478,7 +9464,6 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = -ENOMEM; goto out_error; } - host->transportt = &ufshcd_transport_template; hba = shost_priv(host); hba->host = host; hba->dev = dev; @@ -9518,6 +9503,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) int err; struct Scsi_Host *host = hba->host; struct device *dev = hba->dev; + char eh_wq_name[sizeof("ufs_eh_wq_00")]; if (!mmio_base) { dev_err(hba->dev, @@ -9571,6 +9557,17 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) hba->max_pwr_info.is_valid = false; + /* Initialize work queues */ + snprintf(eh_wq_name, sizeof(eh_wq_name), "ufs_eh_wq_%d", + hba->host->host_no); + hba->eh_wq = create_singlethread_workqueue(eh_wq_name); + if (!hba->eh_wq) { + dev_err(hba->dev, "%s: failed to create eh workqueue\n", + __func__); + err = -ENOMEM; + goto out_disable; + } + INIT_WORK(&hba->eh_work, ufshcd_err_handler); INIT_WORK(&hba->eeh_work, ufshcd_exception_event_handler); sema_init(&hba->host_sem, 1); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 4723f27a55d1..f0da5d3db1fa 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -741,6 +741,8 @@ struct ufs_hba_monitor { * @is_powered: flag to check if HBA is powered * @shutting_down: flag to check if shutdown has been invoked * @host_sem: semaphore used to serialize concurrent contexts + * @eh_wq: Workqueue that eh_work works on + * @eh_work: Worker to handle UFS errors that require s/w attention * @eeh_work: Worker to handle exception events * @errors: HBA errors * @uic_error: UFS interconnect layer error status @@ -843,6 +845,8 @@ struct ufs_hba { struct semaphore host_sem; /* Work Queues */ + struct workqueue_struct *eh_wq; + struct work_struct eh_work; struct work_struct eeh_work; /* HBA Errors */ From 1d479e6c9cb2b40abfb455863a4e9335db882e33 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 17 Sep 2021 14:23:14 -0700 Subject: [PATCH 535/866] scsi: sd_zbc: Support disks with more than 2**32 logical blocks This patch addresses the following Coverity report about the zno * sdkp->zone_blocks expression: CID 1475514 (#1 of 1): Unintentional integer overflow (OVERFLOW_BEFORE_WIDEN) overflow_before_widen: Potentially overflowing expression zno * sdkp->zone_blocks with type unsigned int (32 bits, unsigned) is evaluated using 32-bit arithmetic, and then used in a context that expects an expression of type sector_t (64 bits, unsigned). Link: https://lore.kernel.org/r/20210917212314.2362324-1-bvanassche@acm.org Fixes: 5795eb443060 ("scsi: sd_zbc: emulate ZONE_APPEND commands") Cc: Johannes Thumshirn Cc: Damien Le Moal Cc: Hannes Reinecke Reviewed-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Himanshu Madhani Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/sd_zbc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 8197d31a81f9..ed06798983f8 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -280,7 +280,7 @@ static void sd_zbc_update_wp_offset_workfn(struct work_struct *work) { struct scsi_disk *sdkp; unsigned long flags; - unsigned int zno; + sector_t zno; int ret; sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work); From d04a968c33684b15d1206e23fc1119ce0f0587fb Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 16 Sep 2021 10:54:04 -0700 Subject: [PATCH 536/866] scsi: ufs: core: Unbreak the reset handler A command tag is passed as the second argument of the __ufshcd_transfer_req_compl() call in ufshcd_eh_device_reset_handler() instead of a bitmask. Fix this by passing a bitmask as argument instead of a command tag. Link: https://lore.kernel.org/r/20210916175408.2260084-1-bvanassche@acm.org Fixes: a45f937110fa ("scsi: ufs: Optimize host lock on transfer requests send/compl paths") Cc: Can Guo Reviewed-by: Avri Altman Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index a3df5804b2c7..029c9631ec2b 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -6865,7 +6865,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) err = ufshcd_clear_cmd(hba, pos); if (err) break; - __ufshcd_transfer_req_compl(hba, pos, /*retry_requests=*/true); + __ufshcd_transfer_req_compl(hba, 1U << pos, false); } } From 5f8579038842d77e6ce05e1df6bf9dd493b0e3ef Mon Sep 17 00:00:00 2001 From: Dmitry Bogdanov Date: Wed, 15 Sep 2021 18:32:39 +0300 Subject: [PATCH 537/866] scsi: qla2xxx: Restore initiator in dual mode In dual mode in case of disabling the target, the whole port goes offline and initiator is turned off too. Fix restoring initiator mode after disabling target in dual mode. Link: https://lore.kernel.org/r/20210915153239.8035-1-d.bogdanov@yadro.com Fixes: 0645cb8350cd ("scsi: qla2xxx: Add mode control for each physical port") Reviewed-by: Himanshu Madhani Signed-off-by: Dmitry Bogdanov Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 1e4e3e83b5c7..5fc7697f0af4 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -7169,7 +7169,8 @@ qla2x00_abort_isp(scsi_qla_host_t *vha) return 0; break; case QLA2XXX_INI_MODE_DUAL: - if (!qla_dual_mode_enabled(vha)) + if (!qla_dual_mode_enabled(vha) && + !qla_ini_mode_enabled(vha)) return 0; break; case QLA2XXX_INI_MODE_ENABLED: From bc41fcbffd5759c9610f7de211420eae6b379503 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 15 Sep 2021 17:07:13 +0800 Subject: [PATCH 538/866] scsi: fas216: Kill scmd->tag The driver is attempting to allocate a tag internally which is a no-go with blk-mq. Switch the driver to use the request tag and kill usage of scmd->tag and scmd->device->current_tag. [jpg: Change to use scsi_cmd_to_rq()] Link: https://lore.kernel.org/r/1631696835-136198-2-git-send-email-john.garry@huawei.com Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/arm/fas216.c | 31 ++++++++----------------------- 1 file changed, 8 insertions(+), 23 deletions(-) diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c index 9c4458a99025..cf71ef488e36 100644 --- a/drivers/scsi/arm/fas216.c +++ b/drivers/scsi/arm/fas216.c @@ -77,7 +77,6 @@ * I was thinking that this was a good chip until I found this restriction ;( */ #define SCSI2_SYNC -#undef SCSI2_TAG #undef DEBUG_CONNECT #undef DEBUG_MESSAGES @@ -990,7 +989,7 @@ fas216_reselected_intr(FAS216_Info *info) info->scsi.disconnectable = 0; if (info->SCpnt->device->id == target && info->SCpnt->device->lun == lun && - info->SCpnt->tag == tag) { + scsi_cmd_to_rq(info->SCpnt)->tag == tag) { fas216_log(info, LOG_CONNECT, "reconnected previously executing command"); } else { queue_add_cmd_tail(&info->queues.disconnected, info->SCpnt); @@ -1791,8 +1790,9 @@ static void fas216_start_command(FAS216_Info *info, struct scsi_cmnd *SCpnt) /* * add tag message if required */ - if (SCpnt->tag) - msgqueue_addmsg(&info->scsi.msgs, 2, SIMPLE_QUEUE_TAG, SCpnt->tag); + if (SCpnt->device->simple_tags) + msgqueue_addmsg(&info->scsi.msgs, 2, SIMPLE_QUEUE_TAG, + scsi_cmd_to_rq(SCpnt)->tag); do { #ifdef SCSI2_SYNC @@ -1815,20 +1815,8 @@ static void fas216_start_command(FAS216_Info *info, struct scsi_cmnd *SCpnt) static void fas216_allocate_tag(FAS216_Info *info, struct scsi_cmnd *SCpnt) { -#ifdef SCSI2_TAG - /* - * tagged queuing - allocate a new tag to this command - */ - if (SCpnt->device->simple_tags && SCpnt->cmnd[0] != REQUEST_SENSE && - SCpnt->cmnd[0] != INQUIRY) { - SCpnt->device->current_tag += 1; - if (SCpnt->device->current_tag == 0) - SCpnt->device->current_tag = 1; - SCpnt->tag = SCpnt->device->current_tag; - } else -#endif - set_bit(SCpnt->device->id * 8 + - (u8)(SCpnt->device->lun & 0x7), info->busyluns); + set_bit(SCpnt->device->id * 8 + + (u8)(SCpnt->device->lun & 0x7), info->busyluns); info->stats.removes += 1; switch (SCpnt->cmnd[0]) { @@ -2117,7 +2105,6 @@ request_sense: init_SCp(SCpnt); SCpnt->SCp.Message = 0; SCpnt->SCp.Status = 0; - SCpnt->tag = 0; SCpnt->host_scribble = (void *)fas216_rq_sns_done; /* @@ -2223,7 +2210,6 @@ static int fas216_queue_command_lck(struct scsi_cmnd *SCpnt, init_SCp(SCpnt); info->stats.queues += 1; - SCpnt->tag = 0; spin_lock(&info->host_lock); @@ -3003,9 +2989,8 @@ void fas216_print_devices(FAS216_Info *info, struct seq_file *m) dev = &info->device[scd->id]; seq_printf(m, " %d/%llu ", scd->id, scd->lun); if (scd->tagged_supported) - seq_printf(m, "%3sabled(%3d) ", - scd->simple_tags ? "en" : "dis", - scd->current_tag); + seq_printf(m, "%3sabled ", + scd->simple_tags ? "en" : "dis"); else seq_puts(m, "unsupported "); From 756fb6a895afbf1f0615d93ebdd14863a00b1198 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 15 Sep 2021 17:07:14 +0800 Subject: [PATCH 539/866] scsi: acornscsi: Remove tagged queuing vestiges The acornscsi driver has a config option to enable tagged queuing, but this option gets disabled in the driver itself with the comment 'needs to be debugged'. As this is a _really_ old driver I doubt anyone will be wanting to invest time here, so remove the tagged queue vestiges and make our lives easier. [jpg: Use scsi_cmd_to_rq()] Link: https://lore.kernel.org/r/1631696835-136198-3-git-send-email-john.garry@huawei.com Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/arm/Kconfig | 11 ---- drivers/scsi/arm/acornscsi.c | 103 ++++++++--------------------------- drivers/scsi/arm/queue.c | 2 +- 3 files changed, 23 insertions(+), 93 deletions(-) diff --git a/drivers/scsi/arm/Kconfig b/drivers/scsi/arm/Kconfig index f34badc75196..9f64133f976a 100644 --- a/drivers/scsi/arm/Kconfig +++ b/drivers/scsi/arm/Kconfig @@ -10,17 +10,6 @@ config SCSI_ACORNSCSI_3 This enables support for the Acorn SCSI card (aka30). If you have an Acorn system with one of these, say Y. If unsure, say N. -config SCSI_ACORNSCSI_TAGGED_QUEUE - bool "Support SCSI 2 Tagged queueing" - depends on SCSI_ACORNSCSI_3 - help - Say Y here to enable tagged queuing support on the Acorn SCSI card. - - This is a feature of SCSI-2 which improves performance: the host - adapter can send several SCSI commands to a device's queue even if - previous commands haven't finished yet. Some SCSI devices don't - implement this properly, so the safe answer is N. - config SCSI_ACORNSCSI_SYNC bool "Support SCSI 2 Synchronous Transfers" depends on SCSI_ACORNSCSI_3 diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c index 4a84599ff491..b4cb5fb19998 100644 --- a/drivers/scsi/arm/acornscsi.c +++ b/drivers/scsi/arm/acornscsi.c @@ -52,12 +52,8 @@ * You can tell if you have a device that supports tagged queueing my * cating (eg) /proc/scsi/acornscsi/0 and see if the SCSI revision is reported * as '2 TAG'. - * - * Also note that CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE is normally set in the config - * scripts, but disabled here. Once debugged, remove the #undef, otherwise to debug, - * comment out the undef. */ -#undef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE + /* * SCSI-II Synchronous transfer support. * @@ -171,7 +167,7 @@ static void acornscsi_done(AS_Host *host, struct scsi_cmnd **SCpntp, unsigned int result); static int acornscsi_reconnect_finish(AS_Host *host); static void acornscsi_dma_cleanup(AS_Host *host); -static void acornscsi_abortcmd(AS_Host *host, unsigned char tag); +static void acornscsi_abortcmd(AS_Host *host); /* ==================================================================================== * Miscellaneous @@ -741,17 +737,6 @@ intr_ret_t acornscsi_kick(AS_Host *host) #endif if (from_queue) { -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - /* - * tagged queueing - allocate a new tag to this command - */ - if (SCpnt->device->simple_tags) { - SCpnt->device->current_tag += 1; - if (SCpnt->device->current_tag == 0) - SCpnt->device->current_tag = 1; - SCpnt->tag = SCpnt->device->current_tag; - } else -#endif set_bit(SCpnt->device->id * 8 + (u8)(SCpnt->device->lun & 0x07), host->busyluns); @@ -1192,7 +1177,7 @@ void acornscsi_dma_intr(AS_Host *host) * the device recognises the attention. */ if (dmac_read(host, DMAC_STATUS) & STATUS_RQ0) { - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); dmac_write(host, DMAC_TXCNTLO, 0); dmac_write(host, DMAC_TXCNTHI, 0); @@ -1560,23 +1545,6 @@ void acornscsi_message(AS_Host *host) acornscsi_sbic_issuecmd(host, CMND_ASSERTATN); switch (host->scsi.last_message) { -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - case HEAD_OF_QUEUE_TAG: - case ORDERED_QUEUE_TAG: - case SIMPLE_QUEUE_TAG: - /* - * ANSI standard says: (Section SCSI-2 Rev. 10c Sect 5.6.17) - * If a target does not implement tagged queuing and a queue tag - * message is received, it shall respond with a MESSAGE REJECT - * message and accept the I/O process as if it were untagged. - */ - printk(KERN_NOTICE "scsi%d.%c: disabling tagged queueing\n", - host->host->host_no, acornscsi_target(host)); - host->SCpnt->device->simple_tags = 0; - set_bit(host->SCpnt->device->id * 8 + - (u8)(host->SCpnt->device->lun & 0x7), host->busyluns); - break; -#endif case EXTENDED_MESSAGE | (EXTENDED_SDTR << 8): /* * Target can't handle synchronous transfers @@ -1687,24 +1655,11 @@ void acornscsi_buildmessages(AS_Host *host) #if 0 /* does the device need the current command aborted */ if (cmd_aborted) { - acornscsi_abortcmd(host->SCpnt->tag); + acornscsi_abortcmd(host); return; } #endif -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - if (host->SCpnt->tag) { - unsigned int tag_type; - - if (host->SCpnt->cmnd[0] == REQUEST_SENSE || - host->SCpnt->cmnd[0] == TEST_UNIT_READY || - host->SCpnt->cmnd[0] == INQUIRY) - tag_type = HEAD_OF_QUEUE_TAG; - else - tag_type = SIMPLE_QUEUE_TAG; - msgqueue_addmsg(&host->scsi.msgs, 2, tag_type, host->SCpnt->tag); - } -#endif #ifdef CONFIG_SCSI_ACORNSCSI_SYNC if (host->device[host->SCpnt->device->id].sync_state == SYNC_NEGOCIATE) { @@ -1798,7 +1753,7 @@ int acornscsi_reconnect(AS_Host *host) "to reconnect with\n", host->host->host_no, '0' + target); acornscsi_dumplog(host, target); - acornscsi_abortcmd(host, 0); + acornscsi_abortcmd(host); if (host->SCpnt) { queue_add_cmd_tail(&host->queues.disconnected, host->SCpnt); host->SCpnt = NULL; @@ -1821,7 +1776,7 @@ int acornscsi_reconnect_finish(AS_Host *host) host->scsi.disconnectable = 0; if (host->SCpnt->device->id == host->scsi.reconnected.target && host->SCpnt->device->lun == host->scsi.reconnected.lun && - host->SCpnt->tag == host->scsi.reconnected.tag) { + scsi_cmd_to_tag(host->SCpnt) == host->scsi.reconnected.tag) { #if (DEBUG & (DEBUG_QUEUES|DEBUG_DISCON)) DBG(host->SCpnt, printk("scsi%d.%c: reconnected", host->host->host_no, acornscsi_target(host))); @@ -1848,7 +1803,7 @@ int acornscsi_reconnect_finish(AS_Host *host) } if (!host->SCpnt) - acornscsi_abortcmd(host, host->scsi.reconnected.tag); + acornscsi_abortcmd(host); else { /* * Restore data pointer from SAVED pointers. @@ -1889,21 +1844,15 @@ void acornscsi_disconnect_unexpected(AS_Host *host) * Function: void acornscsi_abortcmd(AS_host *host, unsigned char tag) * Purpose : abort a currently executing command * Params : host - host with connected command to abort - * tag - tag to abort */ static -void acornscsi_abortcmd(AS_Host *host, unsigned char tag) +void acornscsi_abortcmd(AS_Host *host) { host->scsi.phase = PHASE_ABORTED; sbic_arm_write(host, SBIC_CMND, CMND_ASSERTATN); msgqueue_flush(&host->scsi.msgs); -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - if (tag) - msgqueue_addmsg(&host->scsi.msgs, 2, ABORT_TAG, tag); - else -#endif - msgqueue_addmsg(&host->scsi.msgs, 1, ABORT); + msgqueue_addmsg(&host->scsi.msgs, 1, ABORT); } /* ========================================================================================== @@ -1993,7 +1942,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) printk(KERN_ERR "scsi%d.%c: PHASE_CONNECTING, SSR %02X?\n", host->host->host_no, acornscsi_target(host), ssr); acornscsi_dumplog(host, host->SCpnt ? host->SCpnt->device->id : 8); - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); } return INTR_PROCESSING; @@ -2029,7 +1978,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) printk(KERN_ERR "scsi%d.%c: PHASE_CONNECTED, SSR %02X?\n", host->host->host_no, acornscsi_target(host), ssr); acornscsi_dumplog(host, host->SCpnt ? host->SCpnt->device->id : 8); - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); } return INTR_PROCESSING; @@ -2075,20 +2024,20 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) case 0x18: /* -> PHASE_DATAOUT */ /* COMMAND -> DATA OUT */ if (host->scsi.SCp.sent_command != host->SCpnt->cmd_len) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); acornscsi_dma_setup(host, DMA_OUT); if (!acornscsi_starttransfer(host)) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); host->scsi.phase = PHASE_DATAOUT; return INTR_IDLE; case 0x19: /* -> PHASE_DATAIN */ /* COMMAND -> DATA IN */ if (host->scsi.SCp.sent_command != host->SCpnt->cmd_len) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); acornscsi_dma_setup(host, DMA_IN); if (!acornscsi_starttransfer(host)) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); host->scsi.phase = PHASE_DATAIN; return INTR_IDLE; @@ -2156,7 +2105,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) /* MESSAGE IN -> DATA OUT */ acornscsi_dma_setup(host, DMA_OUT); if (!acornscsi_starttransfer(host)) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); host->scsi.phase = PHASE_DATAOUT; return INTR_IDLE; @@ -2165,7 +2114,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) /* MESSAGE IN -> DATA IN */ acornscsi_dma_setup(host, DMA_IN); if (!acornscsi_starttransfer(host)) - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); host->scsi.phase = PHASE_DATAIN; return INTR_IDLE; @@ -2206,7 +2155,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) switch (ssr) { case 0x19: /* -> PHASE_DATAIN */ case 0x89: /* -> PHASE_DATAIN */ - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); return INTR_IDLE; case 0x1b: /* -> PHASE_STATUSIN */ @@ -2255,7 +2204,7 @@ intr_ret_t acornscsi_sbicintr(AS_Host *host, int in_irq) switch (ssr) { case 0x18: /* -> PHASE_DATAOUT */ case 0x88: /* -> PHASE_DATAOUT */ - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); return INTR_IDLE; case 0x1b: /* -> PHASE_STATUSIN */ @@ -2482,7 +2431,6 @@ static int acornscsi_queuecmd_lck(struct scsi_cmnd *SCpnt, SCpnt->scsi_done = done; SCpnt->host_scribble = NULL; SCpnt->result = 0; - SCpnt->tag = 0; SCpnt->SCp.phase = (int)acornscsi_datadirection(SCpnt->cmnd[0]); SCpnt->SCp.sent_command = 0; SCpnt->SCp.scsi_xferred = 0; @@ -2581,7 +2529,7 @@ static enum res_abort acornscsi_do_abort(AS_Host *host, struct scsi_cmnd *SCpnt) break; default: - acornscsi_abortcmd(host, host->SCpnt->tag); + acornscsi_abortcmd(host); res = res_snooze; } local_irq_restore(flags); @@ -2747,9 +2695,6 @@ char *acornscsi_info(struct Scsi_Host *host) #ifdef CONFIG_SCSI_ACORNSCSI_SYNC " SYNC" #endif -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - " TAG" -#endif #if (DEBUG & DEBUG_NO_WRITE) " NOWRITE (" __stringify(NO_WRITE) ")" #endif @@ -2770,9 +2715,6 @@ static int acornscsi_show_info(struct seq_file *m, struct Scsi_Host *instance) #ifdef CONFIG_SCSI_ACORNSCSI_SYNC " SYNC" #endif -#ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE - " TAG" -#endif #if (DEBUG & DEBUG_NO_WRITE) " NOWRITE (" __stringify(NO_WRITE) ")" #endif @@ -2827,9 +2769,8 @@ static int acornscsi_show_info(struct seq_file *m, struct Scsi_Host *instance) seq_printf(m, "Device/Lun TaggedQ Sync\n"); seq_printf(m, " %d/%llu ", scd->id, scd->lun); if (scd->tagged_supported) - seq_printf(m, "%3sabled(%3d) ", - scd->simple_tags ? "en" : "dis", - scd->current_tag); + seq_printf(m, "%3sabled ", + scd->simple_tags ? "en" : "dis"); else seq_printf(m, "unsupported "); diff --git a/drivers/scsi/arm/queue.c b/drivers/scsi/arm/queue.c index e5559f27669d..c6f71a7d1b8e 100644 --- a/drivers/scsi/arm/queue.c +++ b/drivers/scsi/arm/queue.c @@ -214,7 +214,7 @@ struct scsi_cmnd *queue_remove_tgtluntag(Queue_t *queue, int target, int lun, list_for_each(l, &queue->head) { QE_t *q = list_entry(l, QE_t, list); if (q->SCpnt->device->id == target && q->SCpnt->device->lun == lun && - q->SCpnt->tag == tag) { + scsi_cmd_to_rq(q->SCpnt)->tag == tag) { SCpnt = __queue_remove(queue, l); break; } From a4869faf9642518145a8aa4b52e0d5ab0e7ee896 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 15 Sep 2021 17:07:15 +0800 Subject: [PATCH 540/866] scsi: core: Remove 'current_tag' The 'current_tag' field in struct scsi_device is unused now; remove it. Link: https://lore.kernel.org/r/1631696835-136198-4-git-send-email-john.garry@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 09a17f6e93a7..b97e142a7ca9 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -146,7 +146,6 @@ struct scsi_device { struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; struct scsi_vpd __rcu *vpd_pg89; - unsigned char current_tag; /* current tag */ struct scsi_target *sdev_target; blist_flags_t sdev_bflags; /* black/white flags as also found in From cdbc16c552f27ac211a44f9959d813b4f3188223 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Sep 2021 16:22:51 +0300 Subject: [PATCH 541/866] scsi: lpfc: Fix sprintf() overflow in lpfc_display_fpin_wwpn() This scnprintf() uses the wrong limit. It should be "LPFC_FPIN_WWPN_LINE_SZ - len" instead of LPFC_FPIN_WWPN_LINE_SZ. Link: https://lore.kernel.org/r/20210916132251.GD25094@kili Fixes: 428569e66fa7 ("scsi: lpfc: Expand FPIN and RDF receive logging") Reviewed-by: James Smart Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_els.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index f3fc79b99165..052c0e5b1119 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -9387,7 +9387,7 @@ lpfc_display_fpin_wwpn(struct lpfc_hba *phba, __be64 *wwnlist, u32 cnt) /* Extract the next WWPN from the payload */ wwn = *wwnlist++; wwpn = be64_to_cpu(wwn); - len += scnprintf(buf + len, LPFC_FPIN_WWPN_LINE_SZ, + len += scnprintf(buf + len, LPFC_FPIN_WWPN_LINE_SZ - len, " %016llx", wwpn); /* Log a message if we are on the last WWPN From 6dacc371b77f473770ec646e220303a84fe96c11 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 16 Sep 2021 16:23:31 +0300 Subject: [PATCH 542/866] scsi: lpfc: Use correct scnprintf() limit The limit should be "PAGE_SIZE - len" instead of "PAGE_SIZE". We're not going to hit the limit so this fix will not affect runtime. Link: https://lore.kernel.org/r/20210916132331.GE25094@kili Fixes: 5b9e70b22cc5 ("scsi: lpfc: raise sg count for nvme to use available sg resources") Reviewed-by: James Smart Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_attr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index b35bf70a8c0d..1e5a30eb04de 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -6204,7 +6204,8 @@ lpfc_sg_seg_cnt_show(struct device *dev, struct device_attribute *attr, len = scnprintf(buf, PAGE_SIZE, "SGL sz: %d total SGEs: %d\n", phba->cfg_sg_dma_buf_size, phba->cfg_total_seg_cnt); - len += scnprintf(buf + len, PAGE_SIZE, "Cfg: %d SCSI: %d NVME: %d\n", + len += scnprintf(buf + len, PAGE_SIZE - len, + "Cfg: %d SCSI: %d NVME: %d\n", phba->cfg_sg_seg_cnt, phba->cfg_scsi_seg_cnt, phba->cfg_nvme_seg_cnt); return len; From a38923f2d088d1a5cbaa86818abe039b2f87093d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 11:56:22 +0200 Subject: [PATCH 543/866] scsi: lpfc: Fix gcc -Wstringop-overread warning, again I fixed a stringop-overread warning earlier this year, now a second copy of the original code was added and the warning came back: drivers/scsi/lpfc/lpfc_attr.c: In function 'lpfc_cmf_info_show': drivers/scsi/lpfc/lpfc_attr.c:289:25: error: 'strnlen' specified bound 4095 exceeds source size 24 [-Werror=stringop-overread] 289 | strnlen(LPFC_INFO_MORE_STR, PAGE_SIZE - 1), | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix it the same way as the other copy. Link: https://lore.kernel.org/r/20210920095628.1191676-1-arnd@kernel.org Fixes: ada48ba70f6b ("scsi: lpfc: Fix gcc -Wstringop-overread warning") Fixes: 74a7baa2a3ee ("scsi: lpfc: Add cmf_info sysfs entry") Reviewed-by: James Smart Signed-off-by: Arnd Bergmann Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_attr.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 1e5a30eb04de..ebe417921dac 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -285,11 +285,8 @@ buffer_done: "6312 Catching potential buffer " "overflow > PAGE_SIZE = %lu bytes\n", PAGE_SIZE); - strscpy(buf + PAGE_SIZE - 1 - - strnlen(LPFC_INFO_MORE_STR, PAGE_SIZE - 1), - LPFC_INFO_MORE_STR, - strnlen(LPFC_INFO_MORE_STR, PAGE_SIZE - 1) - + 1); + strscpy(buf + PAGE_SIZE - 1 - sizeof(LPFC_INFO_MORE_STR), + LPFC_INFO_MORE_STR, sizeof(LPFC_INFO_MORE_STR) + 1); } return len; } From 9a8ef2c73c727a3c64b70c01697c578c7b10fed2 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 20 Sep 2021 19:32:06 +0100 Subject: [PATCH 544/866] scsi: target: Fix spelling mistake "CONFLIFT" -> "CONFLICT" There is a spelling mistake in a dev_err message. Fix it. Link: https://lore.kernel.org/r/20210920183206.17477-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/target/target_core_pr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 4b94b085625b..3829b61b56c1 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -269,7 +269,7 @@ target_scsi2_reservation_reserve(struct se_cmd *cmd) spin_lock(&dev->dev_reservation_lock); if (dev->reservation_holder && dev->reservation_holder->se_node_acl != sess->se_node_acl) { - pr_err("SCSI-2 RESERVATION CONFLIFT for %s fabric\n", + pr_err("SCSI-2 RESERVATION CONFLICT for %s fabric\n", tpg->se_tpg_tfo->fabric_name); pr_err("Original reserver LUN: %llu %s\n", cmd->se_lun->unpacked_lun, From fbdac19e642899455b4e64c63aafe2325df7aafa Mon Sep 17 00:00:00 2001 From: Wen Xiong Date: Thu, 16 Sep 2021 22:24:21 -0500 Subject: [PATCH 545/866] scsi: ses: Retry failed Send/Receive Diagnostic commands Setting SCSI logging level with error=3, we saw some errors from enclosues: [108017.360833] ses 0:0:9:0: tag#641 Done: NEEDS_RETRY Result: hostbyte=DID_ERROR driverbyte=DRIVER_OK cmd_age=0s [108017.360838] ses 0:0:9:0: tag#641 CDB: Receive Diagnostic 1c 01 01 00 20 00 [108017.427778] ses 0:0:9:0: Power-on or device reset occurred [108017.427784] ses 0:0:9:0: tag#641 Done: SUCCESS Result: hostbyte=DID_OK driverbyte=DRIVER_OK cmd_age=0s [108017.427788] ses 0:0:9:0: tag#641 CDB: Receive Diagnostic 1c 01 01 00 20 00 [108017.427791] ses 0:0:9:0: tag#641 Sense Key : Unit Attention [current] [108017.427793] ses 0:0:9:0: tag#641 Add. Sense: Bus device reset function occurred [108017.427801] ses 0:0:9:0: Failed to get diagnostic page 0x1 [108017.427804] ses 0:0:9:0: Failed to bind enclosure -19 [108017.427895] ses 0:0:10:0: Attached Enclosure device [108017.427942] ses 0:0:10:0: Attached scsi generic sg18 type 13 Retry if the Send/Receive Diagnostic commands complete with a transient error status (NOT_READY or UNIT_ATTENTION with ASC 0x29). Link: https://lore.kernel.org/r/1631849061-10210-2-git-send-email-wenxiong@linux.ibm.com Reviewed-by: Brian King Reviewed-by: James Bottomley Signed-off-by: Wen Xiong Signed-off-by: Martin K. Petersen --- drivers/scsi/ses.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index c2afba2a5414..43e682297fd5 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -87,9 +87,16 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, 0 }; unsigned char recv_page_code; + unsigned int retries = SES_RETRIES; + struct scsi_sense_hdr sshdr; + + do { + ret = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen, + &sshdr, SES_TIMEOUT, 1, NULL); + } while (ret > 0 && --retries && scsi_sense_valid(&sshdr) && + (sshdr.sense_key == NOT_READY || + (sshdr.sense_key == UNIT_ATTENTION && sshdr.asc == 0x29))); - ret = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen, - NULL, SES_TIMEOUT, SES_RETRIES, NULL); if (unlikely(ret)) return ret; @@ -121,9 +128,16 @@ static int ses_send_diag(struct scsi_device *sdev, int page_code, bufflen & 0xff, 0 }; + struct scsi_sense_hdr sshdr; + unsigned int retries = SES_RETRIES; + + do { + result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, buf, bufflen, + &sshdr, SES_TIMEOUT, 1, NULL); + } while (result > 0 && --retries && scsi_sense_valid(&sshdr) && + (sshdr.sense_key == NOT_READY || + (sshdr.sense_key == UNIT_ATTENTION && sshdr.asc == 0x29))); - result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, buf, bufflen, - NULL, SES_TIMEOUT, SES_RETRIES, NULL); if (result) sdev_printk(KERN_ERR, sdev, "SEND DIAGNOSTIC result: %8x\n", result); From f7d848e0fdfa557f181955a769cbb163d54fd292 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 22 Sep 2021 08:30:08 +0200 Subject: [PATCH 546/866] MAINTAINERS: usb, update Peter Korsgaard's entries Peter's e-mail in MAINTAINERS is defunct: This is the qmail-send program at a.mx.sunsite.dk. : Sorry, no mailbox here by that name. (#5.1.1) Peter says: ** Ahh yes, it should be changed to peter@korsgaard.com. However he also says: ** I haven't had access to c67x00 hw for quite some years though, so maybe ** it should be marked Orphan instead? So change as he wishes. Cc: Peter Korsgaard Cc: Linus Torvalds Cc: linux-usb@vger.kernel.org Acked-by: Peter Korsgaard Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210922063008.25758-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..d1bbaf06dc1d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19288,13 +19288,12 @@ S: Maintained F: drivers/usb/misc/chaoskey.c USB CYPRESS C67X00 DRIVER -M: Peter Korsgaard L: linux-usb@vger.kernel.org -S: Maintained +S: Orphan F: drivers/usb/c67x00/ USB DAVICOM DM9601 DRIVER -M: Peter Korsgaard +M: Peter Korsgaard L: netdev@vger.kernel.org S: Maintained W: http://www.linux-usb.org/usbnet From 22d65765f211cc83186fd8b87521159f354c0da9 Mon Sep 17 00:00:00 2001 From: Andrej Shadura Date: Thu, 16 Sep 2021 17:33:11 +0100 Subject: [PATCH 547/866] HID: u2fzero: ignore incomplete packets without data Since the actual_length calculation is performed unsigned, packets shorter than 7 bytes (e.g. packets without data or otherwise truncated) or non-received packets ("zero" bytes) can cause buffer overflow. Link: https://bugzilla.kernel.org/show_bug.cgi?id=214437 Fixes: 42337b9d4d958("HID: add driver for U2F Zero built-in LED and RNG") Signed-off-by: Andrej Shadura Signed-off-by: Jiri Kosina --- drivers/hid/hid-u2fzero.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/hid-u2fzero.c b/drivers/hid/hid-u2fzero.c index 95e0807878c7..d70cd3d7f583 100644 --- a/drivers/hid/hid-u2fzero.c +++ b/drivers/hid/hid-u2fzero.c @@ -198,7 +198,9 @@ static int u2fzero_rng_read(struct hwrng *rng, void *data, } ret = u2fzero_recv(dev, &req, &resp); - if (ret < 0) + + /* ignore errors or packets without data */ + if (ret < offsetof(struct u2f_hid_msg, init.data)) return 0; /* only take the minimum amount of data it is safe to take */ From cef0d022f55364d69017daeb9443bd31510ad6a2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 16 Aug 2021 12:41:19 +0200 Subject: [PATCH 548/866] gpiolib: acpi: Make set-debounce-timeout failures non fatal Commit 8dcb7a15a585 ("gpiolib: acpi: Take into account debounce settings") made the gpiolib-acpi code call gpio_set_debounce_timeout() when requesting GPIOs. This in itself is fine, but it also made gpio_set_debounce_timeout() errors fatal, causing the requesting of the GPIO to fail. This is causing regressions. E.g. on a HP ElitePad 1000 G2 various _AEI specified GPIO ACPI event sources specify a debouncy timeout of 20 ms, but the pinctrl-baytrail.c only supports certain fixed values, the closest ones being 12 or 24 ms and pinctrl-baytrail.c responds with -EINVAL when specified a value which is not one of the fixed values. This is causing the acpi_request_own_gpiod() call to fail for 3 ACPI event sources on the HP ElitePad 1000 G2, which in turn is causing e.g. the battery charging vs discharging status to never get updated, even though a charger has been plugged-in or unplugged. Make gpio_set_debounce_timeout() errors non fatal, warning about the failure instead, to fix this regression. Note we should probably also fix various pinctrl drivers to just pick the first bigger discrete value rather then returning -EINVAL but this will need to be done on a per driver basis, where as this fix at least gets us back to where things were before and thus restores functionality on devices where this was lost due to gpio_set_debounce_timeout() errors. Fixes: 8dcb7a15a585 ("gpiolib: acpi: Take into account debounce settings") Depends-on: 2e2b496cebef ("gpiolib: acpi: Extract acpi_request_own_gpiod() helper") Reviewed-by: Mika Westerberg Signed-off-by: Hans de Goede Acked-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib-acpi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 411525ac4cc4..47712b6903b5 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -313,9 +313,11 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, ret = gpio_set_debounce_timeout(desc, agpio->debounce_timeout); if (ret) - gpiochip_free_own_desc(desc); + dev_warn(chip->parent, + "Failed to set debounce-timeout for pin 0x%04X, err %d\n", + pin, ret); - return ret ? ERR_PTR(ret) : desc; + return desc; } static bool acpi_gpio_in_ignore_list(const char *controller_in, int pin_in) From 2dd824cca3407bc9a2bd11b00f6e117b66fcfcf1 Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Thu, 16 Sep 2021 20:19:35 +0900 Subject: [PATCH 549/866] gpio: uniphier: Fix void functions to remove return value The return type of irq_chip.irq_mask() and irq_chip.irq_unmask() should be void. Fixes: dbe776c2ca54 ("gpio: uniphier: add UniPhier GPIO controller driver") Signed-off-by: Kunihiko Hayashi Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-uniphier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index f99f3c10bed0..39dca147d587 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -184,7 +184,7 @@ static void uniphier_gpio_irq_mask(struct irq_data *data) uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, 0); - return irq_chip_mask_parent(data); + irq_chip_mask_parent(data); } static void uniphier_gpio_irq_unmask(struct irq_data *data) @@ -194,7 +194,7 @@ static void uniphier_gpio_irq_unmask(struct irq_data *data) uniphier_gpio_reg_update(priv, UNIPHIER_GPIO_IRQ_EN, mask, mask); - return irq_chip_unmask_parent(data); + irq_chip_unmask_parent(data); } static int uniphier_gpio_irq_set_type(struct irq_data *data, unsigned int type) From f6c35df22708438c94605b8896d2b4e4d5f342a3 Mon Sep 17 00:00:00 2001 From: Steven Lee Date: Tue, 7 Sep 2021 17:55:25 +0800 Subject: [PATCH 550/866] gpio: gpio-aspeed-sgpio: Fix wrong hwirq in irq handler. The current hwirq is calculated based on the old GPIO pin order(input GPIO range is from 0 to ngpios - 1). It should be calculated based on the current GPIO input pin order(input GPIOs are 0, 2, 4, ..., (ngpios - 1) * 2). Signed-off-by: Steven Lee Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-aspeed-sgpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 10f303d15225..3d6ef37a7702 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -395,7 +395,7 @@ static void aspeed_sgpio_irq_handler(struct irq_desc *desc) reg = ioread32(bank_reg(data, bank, reg_irq_status)); for_each_set_bit(p, ®, 32) - generic_handle_domain_irq(gc->irq.domain, i * 32 + p); + generic_handle_domain_irq(gc->irq.domain, i * 32 + p * 2); } chained_irq_exit(ic, desc); From 0f562b7de99085935d76b00c41ab5caa26ff5c74 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 14 Sep 2021 00:49:23 +0200 Subject: [PATCH 551/866] gpio/rockchip: extended debounce support is only available on v2 The gpio driver runs into issues on v1 gpio blocks, as the db_clk and the whole extended debounce support is only ever defined on v2. So checking for the IS_ERR on the db_clk is not enough, as it will be NULL on v1. Fix this by adding the needed condition for v2 first before checking the existence of the db_clk. This caused my rk3288-veyron-pinky to enter a reboot loop when it tried to enable the power-key as adc-key device. Fixes: 3bcbd1a85b68 ("gpio/rockchip: support next version gpio controller") Signed-off-by: Heiko Stuebner Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-rockchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 036b2d959503..16d9bf7188e3 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -195,7 +195,7 @@ static int rockchip_gpio_set_debounce(struct gpio_chip *gc, unsigned int cur_div_reg; u64 div; - if (!IS_ERR(bank->db_clk)) { + if (bank->gpio_type == GPIO_TYPE_V2 && !IS_ERR(bank->db_clk)) { div_debounce_support = true; freq = clk_get_rate(bank->db_clk); max_debounce = (GENMASK(23, 0) + 1) * 2 * 1000000 / freq; From b22a4705e2e60f342b1b851c9ebdb3ea02f21f8f Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 14 Sep 2021 00:49:24 +0200 Subject: [PATCH 552/866] gpio/rockchip: fix get_direction value handling The function uses the newly introduced rockchip_gpio_readl_bit() which directly returns the actual value of the requeste bit. So using the existing bit-wise check for the bit inside the value will always return 0. Fix this by dropping the bit manipulation on the result. Fixes: 3bcbd1a85b68 ("gpio/rockchip: support next version gpio controller") Signed-off-by: Heiko Stuebner Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-rockchip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 16d9bf7188e3..3335bd57761d 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -141,7 +141,7 @@ static int rockchip_gpio_get_direction(struct gpio_chip *chip, u32 data; data = rockchip_gpio_readl_bit(bank, offset, bank->gpio_regs->port_ddr); - if (data & BIT(offset)) + if (data) return GPIO_LINE_DIRECTION_OUT; return GPIO_LINE_DIRECTION_IN; From 372d1f3e1bfede719864d0d1fbf3146b1e638c88 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 21 Sep 2021 23:32:33 +0300 Subject: [PATCH 553/866] ext2: fix sleeping in atomic bugs on error The ext2_error() function syncs the filesystem so it sleeps. The caller is holding a spinlock so it's not allowed to sleep. ext2_statfs() <- disables preempt -> ext2_count_free_blocks() -> ext2_get_group_desc() Fix this by using WARN() to print an error message and a stack trace instead of using ext2_error(). Link: https://lore.kernel.org/r/20210921203233.GA16529@kili Signed-off-by: Dan Carpenter Signed-off-by: Jan Kara --- fs/ext2/balloc.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 1f3f4326bf3c..c17ccc19b938 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -48,10 +48,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, struct ext2_sb_info *sbi = EXT2_SB(sb); if (block_group >= sbi->s_groups_count) { - ext2_error (sb, "ext2_get_group_desc", - "block_group >= groups_count - " - "block_group = %d, groups_count = %lu", - block_group, sbi->s_groups_count); + WARN(1, "block_group >= groups_count - " + "block_group = %d, groups_count = %lu", + block_group, sbi->s_groups_count); return NULL; } @@ -59,10 +58,9 @@ struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb); offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1); if (!sbi->s_group_desc[group_desc]) { - ext2_error (sb, "ext2_get_group_desc", - "Group descriptor not loaded - " - "block_group = %d, group_desc = %lu, desc = %lu", - block_group, group_desc, offset); + WARN(1, "Group descriptor not loaded - " + "block_group = %d, group_desc = %lu, desc = %lu", + block_group, group_desc, offset); return NULL; } From 2a7313dc81e88adc7bb09d0f056985fa8afc2b89 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 22 Sep 2021 14:19:41 +0100 Subject: [PATCH 554/866] irqchip/armada-370-xp: Fix ack/eoi breakage When converting the driver to using handle_percpu_devid_irq, we forgot to repaint the irq_eoi() callback into irq_ack(), as handle_percpu_devid_fasteoi_ipi() was actually using EOI really early in the handling. Yes this was a stupid idea. Fix this by using the HW ack method as irq_ack(). Fixes: e52e73b7e9f7 ("irqchip/armada-370-xp: Make IPIs use handle_percpu_devid_irq()") Reported-by: Steffen Trumtrar Tested-by: Steffen Trumtrar Signed-off-by: Marc Zyngier Cc: Valentin Schneider Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tuiexq5f.fsf@pengutronix.de --- drivers/irqchip/irq-armada-370-xp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 7557ab551295..53e0fb0562c1 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -359,16 +359,16 @@ static void armada_370_xp_ipi_send_mask(struct irq_data *d, ARMADA_370_XP_SW_TRIG_INT_OFFS); } -static void armada_370_xp_ipi_eoi(struct irq_data *d) +static void armada_370_xp_ipi_ack(struct irq_data *d) { writel(~BIT(d->hwirq), per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS); } static struct irq_chip ipi_irqchip = { .name = "IPI", + .irq_ack = armada_370_xp_ipi_ack, .irq_mask = armada_370_xp_ipi_mask, .irq_unmask = armada_370_xp_ipi_unmask, - .irq_eoi = armada_370_xp_ipi_eoi, .ipi_send_mask = armada_370_xp_ipi_send_mask, }; From 20c36ce2164f1774b487d443ece99b754bc6ad43 Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Thu, 16 Sep 2021 10:52:03 +0800 Subject: [PATCH 555/866] irqdomain: Change the type of 'size' in __irq_domain_add() to be consistent The 'size' is used in struct_size(domain, revmap, size) and its input parameter type is 'size_t'(unsigned int). Changing the size to 'unsigned int' to make the type consistent. Signed-off-by: Bixuan Cui Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210916025203.44841-1-cuibixuan@huawei.com --- include/linux/irqdomain.h | 2 +- kernel/irq/irqdomain.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 23e4ee523576..9ee238ad29ce 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -251,7 +251,7 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 62be16135e7c..bfa289ed57ab 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); * Allocates and initializes an irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) From b99948836162b0cfb03007d9b2c2da9babc057b5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 4 Sep 2021 20:36:44 -0700 Subject: [PATCH 556/866] irqchip/mbigen: Repair non-kernel-doc notation Fix kernel-doc warnings in irq-mbigen.c: irq-mbigen.c:29: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * In mbigen vector register irq-mbigen.c:43: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * offset of clear register in mbigen node irq-mbigen.c:50: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * offset of interrupt type register Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Jun Ma Cc: Yun Wu Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Aditya Srivastava Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210905033644.15988-1-rdunlap@infradead.org --- drivers/irqchip/irq-mbigen.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index f565317a3da3..12df2162108e 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -25,7 +25,7 @@ /* The maximum IRQ pin number of mbigen chip(start from 0) */ #define MAXIMUM_IRQ_PIN_NUM 1407 -/** +/* * In mbigen vector register * bit[21:12]: event id value * bit[11:0]: device id @@ -39,14 +39,14 @@ /* offset of vector register in mbigen node */ #define REG_MBIGEN_VEC_OFFSET 0x200 -/** +/* * offset of clear register in mbigen node * This register is used to clear the status * of interrupt */ #define REG_MBIGEN_CLEAR_OFFSET 0xa000 -/** +/* * offset of interrupt type register * This register is used to configure interrupt * trigger type From 969ac78db78c723a24e9410666b457cc1b0cb3c3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Sep 2021 09:25:19 -0700 Subject: [PATCH 557/866] irqchip/goldfish-pic: Select GENERIC_IRQ_CHIP to fix build irq-goldfish-pic uses GENERIC_IRQ_CHIP interfaces so select that symbol to fix build errors. Fixes these build errors: mips-linux-ld: drivers/irqchip/irq-goldfish-pic.o: in function `goldfish_pic_of_init': irq-goldfish-pic.c:(.init.text+0xc0): undefined reference to `irq_alloc_generic_chip' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0xf4): undefined reference to `irq_gc_unmask_enable_reg' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0xf8): undefined reference to `irq_gc_unmask_enable_reg' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0x100): undefined reference to `irq_gc_mask_disable_reg' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0x104): undefined reference to `irq_gc_mask_disable_reg' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0x11c): undefined reference to `irq_setup_generic_chip' mips-linux-ld: irq-goldfish-pic.c:(.init.text+0x168): undefined reference to `irq_remove_generic_chip' Fixes: 4235ff50cf98 ("irqchip/irq-goldfish-pic: Add Goldfish PIC driver") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Miodrag Dinic Cc: Geert Uytterhoeven Cc: Bartosz Golaszewski Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Goran Ferenc Cc: Aleksandar Markovic Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210905162519.21507-1-rdunlap@infradead.org --- drivers/irqchip/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 4d5924e9f766..aca7b595c4c7 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -409,6 +409,7 @@ config MESON_IRQ_GPIO config GOLDFISH_PIC bool "Goldfish programmable interrupt controller" depends on MIPS && (GOLDFISH || COMPILE_TEST) + select GENERIC_IRQ_CHIP select IRQ_DOMAIN help Say yes here to enable Goldfish interrupt controller driver used From 280bef512933b2dda01d681d8cbe499b98fc5bdd Mon Sep 17 00:00:00 2001 From: Kaige Fu Date: Wed, 15 Sep 2021 10:20:55 +0800 Subject: [PATCH 558/866] irqchip/gic-v3-its: Fix potential VPE leak on error In its_vpe_irq_domain_alloc, when its_vpe_init() returns an error, there is an off-by-one in the number of VPEs to be freed. Fix it by simply passing the number of VPEs allocated, which is the index of the loop iterating over the VPEs. Fixes: 7d75bbb4bc1a ("irqchip/gic-v3-its: Add VPE irq domain allocation/teardown") Signed-off-by: Kaige Fu [maz: fixed commit message] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/d9e36dee512e63670287ed9eff884a5d8d6d27f2.1631672311.git.kaige.fu@linux.alibaba.com --- drivers/irqchip/irq-gic-v3-its.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7f40dca8cda5..eb0882d15366 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4501,7 +4501,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq if (err) { if (i > 0) - its_vpe_irq_domain_free(domain, virq, i - 1); + its_vpe_irq_domain_free(domain, virq, i); its_lpi_free(bitmap, base, nr_ids); its_free_prop_table(vprop_page); From 3ce8c70ecedb4e1f1d36301afb0281be40390f13 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 15 Sep 2021 11:47:30 +0200 Subject: [PATCH 559/866] irqchip/renesas-rza1: Use semicolons instead of commas This code works, but it is cleaner to use semicolons at the end of statements instead of commas. Extracted from a big anonymous patch by Julia Lawall . Signed-off-by: Geert Uytterhoeven Reviewed-by: Ulrich Hecht Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/b1710bb6ea5faa7a7fe74404adb0beb951e0bf8c.1631699160.git.geert+renesas@glider.be --- drivers/irqchip/irq-renesas-rza1.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/irqchip/irq-renesas-rza1.c b/drivers/irqchip/irq-renesas-rza1.c index b0d46ac42b89..72c06e883d1c 100644 --- a/drivers/irqchip/irq-renesas-rza1.c +++ b/drivers/irqchip/irq-renesas-rza1.c @@ -223,12 +223,12 @@ static int rza1_irqc_probe(struct platform_device *pdev) goto out_put_node; } - priv->chip.name = "rza1-irqc", - priv->chip.irq_mask = irq_chip_mask_parent, - priv->chip.irq_unmask = irq_chip_unmask_parent, - priv->chip.irq_eoi = rza1_irqc_eoi, - priv->chip.irq_retrigger = irq_chip_retrigger_hierarchy, - priv->chip.irq_set_type = rza1_irqc_set_type, + priv->chip.name = "rza1-irqc"; + priv->chip.irq_mask = irq_chip_mask_parent; + priv->chip.irq_unmask = irq_chip_unmask_parent; + priv->chip.irq_eoi = rza1_irqc_eoi; + priv->chip.irq_retrigger = irq_chip_retrigger_hierarchy; + priv->chip.irq_set_type = rza1_irqc_set_type; priv->chip.flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE; priv->irq_domain = irq_domain_add_hierarchy(parent, 0, IRQC_NUM_IRQ, From 1ea7812326004afd2803cc968a4776ae5120a597 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 22 Sep 2021 13:53:26 +0300 Subject: [PATCH 560/866] qed: rdma - don't wait for resources under hw error recovery flow If the HW device is during recovery, the HW resources will never return, hence we shouldn't wait for the CID (HW context ID) bitmaps to clear. This fix speeds up the error recovery flow. Fixes: 64515dc899df ("qed: Add infrastructure for error detection and recovery") Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 8 ++++++++ drivers/net/ethernet/qlogic/qed/qed_roce.c | 8 ++++++++ 2 files changed, 16 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index fc8b3e64f153..186d0048a9d1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1297,6 +1297,14 @@ qed_iwarp_wait_cid_map_cleared(struct qed_hwfn *p_hwfn, struct qed_bmap *bmap) prev_weight = weight; while (weight) { + /* If the HW device is during recovery, all resources are + * immediately reset without receiving a per-cid indication + * from HW. In this case we don't expect the cid_map to be + * cleared. + */ + if (p_hwfn->cdev->recov_in_prog) + return 0; + msleep(QED_IWARP_MAX_CID_CLEAN_TIME); weight = bitmap_weight(bmap->bitmap, bmap->max_count); diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index f16a157bb95a..cf5baa5e59bc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -77,6 +77,14 @@ void qed_roce_stop(struct qed_hwfn *p_hwfn) * Beyond the added delay we clear the bitmap anyway. */ while (bitmap_weight(rcid_map->bitmap, rcid_map->max_count)) { + /* If the HW device is during recovery, all resources are + * immediately reset without receiving a per-cid indication + * from HW. In this case we don't expect the cid bitmap to be + * cleared. + */ + if (p_hwfn->cdev->recov_in_prog) + return; + msleep(100); if (wait_count++ > 20) { DP_NOTICE(p_hwfn, "cid bitmap wait timed out\n"); From 977d293e23b48a1129830d7968605f61c4af71a0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 22 Sep 2021 13:12:17 +0200 Subject: [PATCH 561/866] mptcp: ensure tx skbs always have the MPTCP ext Due to signed/unsigned comparison, the expression: info->size_goal - skb->len > 0 evaluates to true when the size goal is smaller than the skb size. That results in lack of tx cache refill, so that the skb allocated by the core TCP code lacks the required MPTCP skb extensions. Due to the above, syzbot is able to trigger the following WARN_ON(): WARNING: CPU: 1 PID: 810 at net/mptcp/protocol.c:1366 mptcp_sendmsg_frag+0x1362/0x1bc0 net/mptcp/protocol.c:1366 Modules linked in: CPU: 1 PID: 810 Comm: syz-executor.4 Not tainted 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:mptcp_sendmsg_frag+0x1362/0x1bc0 net/mptcp/protocol.c:1366 Code: ff 4c 8b 74 24 50 48 8b 5c 24 58 e9 0f fb ff ff e8 13 44 8b f8 4c 89 e7 45 31 ed e8 98 57 2e fe e9 81 f4 ff ff e8 fe 43 8b f8 <0f> 0b 41 bd ea ff ff ff e9 6f f4 ff ff 4c 89 e7 e8 b9 8e d2 f8 e9 RSP: 0018:ffffc9000531f6a0 EFLAGS: 00010216 RAX: 000000000000697f RBX: 0000000000000000 RCX: ffffc90012107000 RDX: 0000000000040000 RSI: ffffffff88eac9e2 RDI: 0000000000000003 RBP: ffff888078b15780 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff88eac017 R11: 0000000000000000 R12: ffff88801de0a280 R13: 0000000000006b58 R14: ffff888066278280 R15: ffff88803c2fe9c0 FS: 00007fd9f866e700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007faebcb2f718 CR3: 00000000267cb000 CR4: 00000000001506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __mptcp_push_pending+0x1fb/0x6b0 net/mptcp/protocol.c:1547 mptcp_release_cb+0xfe/0x210 net/mptcp/protocol.c:3003 release_sock+0xb4/0x1b0 net/core/sock.c:3206 sk_stream_wait_memory+0x604/0xed0 net/core/stream.c:145 mptcp_sendmsg+0xc39/0x1bc0 net/mptcp/protocol.c:1749 inet6_sendmsg+0x99/0xe0 net/ipv6/af_inet6.c:643 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_write_iter+0x2a0/0x3e0 net/socket.c:1057 call_write_iter include/linux/fs.h:2163 [inline] new_sync_write+0x40b/0x640 fs/read_write.c:507 vfs_write+0x7cf/0xae0 fs/read_write.c:594 ksys_write+0x1ee/0x250 fs/read_write.c:647 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x4665f9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fd9f866e188 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000056c038 RCX: 00000000004665f9 RDX: 00000000000e7b78 RSI: 0000000020000000 RDI: 0000000000000003 RBP: 00000000004bfcc4 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000056c038 R13: 0000000000a9fb1f R14: 00007fd9f866e300 R15: 0000000000022000 Fix the issue rewriting the relevant expression to avoid sign-related problems - note: size_goal is always >= 0. Additionally, ensure that the skb in the tx cache always carries the relevant extension. Reported-and-tested-by: syzbot+263a248eec3e875baa7b@syzkaller.appspotmail.com Fixes: 1094c6fe7280 ("mptcp: fix possible divide by zero") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2602f1386160..dbcebf56798f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1316,7 +1316,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, goto alloc_skb; } - must_collapse = (info->size_goal - skb->len > 0) && + must_collapse = (info->size_goal > skb->len) && (skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags); if (must_collapse) { size_bias = skb->len; @@ -1325,7 +1325,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, } alloc_skb: - if (!must_collapse && !ssk->sk_tx_skb_cache && + if (!must_collapse && !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held)) return 0; From b78f26926b17cc289e4f16b63363abe0aa2e8efc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 10 Sep 2021 18:29:25 +0100 Subject: [PATCH 562/866] irqchip/gic: Work around broken Renesas integration Geert reported that the GIC driver locks up on a Renesas system since 005c34ae4b44f085 ("irqchip/gic: Atomically update affinity") fixed the driver to use writeb_relaxed() instead of writel_relaxed(). As it turns out, the interconnect used on this system mandates 32bit wide accesses for all MMIO transactions, even if the GIC architecture specifically mandates for some registers to be byte accessible. Gahhh... Work around the issue by crudly detecting the offending system, and falling back to an inefficient RMW+lock implementation. Reported-by: Geert Uytterhoeven Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/CAMuHMdV+Ev47K5NO8XHsanSq5YRMCHn2gWAQyV-q2LpJVy9HiQ@mail.gmail.com --- drivers/irqchip/irq-gic.c | 52 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index d329ec3d64d8..5f22c9d65e57 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -107,6 +107,8 @@ static DEFINE_RAW_SPINLOCK(cpu_map_lock); #endif +static DEFINE_STATIC_KEY_FALSE(needs_rmw_access); + /* * The GIC mapping of CPU interfaces does not necessarily match * the logical CPU numbering. Let's use a mapping as returned @@ -774,6 +776,25 @@ static int gic_pm_init(struct gic_chip_data *gic) #endif #ifdef CONFIG_SMP +static void rmw_writeb(u8 bval, void __iomem *addr) +{ + static DEFINE_RAW_SPINLOCK(rmw_lock); + unsigned long offset = (unsigned long)addr & 3UL; + unsigned long shift = offset * 8; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&rmw_lock, flags); + + addr -= offset; + val = readl_relaxed(addr); + val &= ~GENMASK(shift + 7, shift); + val |= bval << shift; + writel_relaxed(val, addr); + + raw_spin_unlock_irqrestore(&rmw_lock, flags); +} + static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -788,7 +809,10 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids) return -EINVAL; - writeb_relaxed(gic_cpu_map[cpu], reg); + if (static_branch_unlikely(&needs_rmw_access)) + rmw_writeb(gic_cpu_map[cpu], reg); + else + writeb_relaxed(gic_cpu_map[cpu], reg); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK_DONE; @@ -1375,6 +1399,30 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base) return true; } +static bool gic_enable_rmw_access(void *data) +{ + /* + * The EMEV2 class of machines has a broken interconnect, and + * locks up on accesses that are less than 32bit. So far, only + * the affinity setting requires it. + */ + if (of_machine_is_compatible("renesas,emev2")) { + static_branch_enable(&needs_rmw_access); + return true; + } + + return false; +} + +static const struct gic_quirk gic_quirks[] = { + { + .desc = "broken byte access", + .compatible = "arm,pl390", + .init = gic_enable_rmw_access, + }, + { }, +}; + static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node) { if (!gic || !node) @@ -1391,6 +1439,8 @@ static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node) if (of_property_read_u32(node, "cpu-offset", &gic->percpu_offset)) gic->percpu_offset = 0; + gic_enable_of_quirks(node, gic_quirks, gic); + return 0; error: From 8646e53633f314e4d746a988240d3b951a92f94a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:26 -0700 Subject: [PATCH 563/866] KVM: rseq: Update rseq when processing NOTIFY_RESUME on xfer to KVM guest Invoke rseq's NOTIFY_RESUME handler when processing the flag prior to transferring to a KVM guest, which is roughly equivalent to an exit to userspace and processes many of the same pending actions. While the task cannot be in an rseq critical section as the KVM path is reachable only by via ioctl(KVM_RUN), the side effects that apply to rseq outside of a critical section still apply, e.g. the current CPU needs to be updated if the task is migrated. Clearing TIF_NOTIFY_RESUME without informing rseq can lead to segfaults and other badness in userspace VMMs that use rseq in combination with KVM, e.g. due to the CPU ID being stale after task migration. Fixes: 72c3c0fe54a3 ("x86/kvm: Use generic xfer to guest work function") Reported-by: Peter Foley Bisected-by: Doug Evans Acked-by: Mathieu Desnoyers Cc: Shakeel Butt Cc: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- kernel/entry/kvm.c | 4 +++- kernel/rseq.c | 14 +++++++++++--- 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 49972ee99aff..049fd06b4c3d 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -19,8 +19,10 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NEED_RESCHED) schedule(); - if (ti_work & _TIF_NOTIFY_RESUME) + if (ti_work & _TIF_NOTIFY_RESUME) { tracehook_notify_resume(NULL); + rseq_handle_notify_resume(NULL, NULL); + } ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); if (ret) diff --git a/kernel/rseq.c b/kernel/rseq.c index 35f7bd0fced0..6d45ac3dae7f 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -282,9 +282,17 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(t->flags & PF_EXITING)) return; - ret = rseq_ip_fixup(regs); - if (unlikely(ret < 0)) - goto error; + + /* + * regs is NULL if and only if the caller is in a syscall path. Skip + * fixup and leave rseq_cs as is so that rseq_sycall() will detect and + * kill a misbehaving userspace on debug kernels. + */ + if (regs) { + ret = rseq_ip_fixup(regs); + if (unlikely(ret < 0)) + goto error; + } if (unlikely(rseq_update_cpu_id(t))) goto error; return; From a68de80f61f6af397bc06fb391ff2e571c9c4d80 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:27 -0700 Subject: [PATCH 564/866] entry: rseq: Call rseq_handle_notify_resume() in tracehook_notify_resume() Invoke rseq_handle_notify_resume() from tracehook_notify_resume() now that the two function are always called back-to-back by architectures that have rseq. The rseq helper is stubbed out for architectures that don't support rseq, i.e. this is a nop across the board. Note, tracehook_notify_resume() is horribly named and arguably does not belong in tracehook.h as literally every line of code in it has nothing to do with tracing. But, that's been true since commit a42c6ded827d ("move key_repace_session_keyring() into tracehook_notify_resume()") first usurped tracehook_notify_resume() back in 2012. Punt cleaning that mess up to future patches. No functional change intended. Acked-by: Mathieu Desnoyers Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm/kernel/signal.c | 1 - arch/arm64/kernel/signal.c | 4 +--- arch/csky/kernel/signal.c | 4 +--- arch/mips/kernel/signal.c | 4 +--- arch/powerpc/kernel/signal.c | 4 +--- include/linux/tracehook.h | 2 ++ kernel/entry/common.c | 4 +--- kernel/entry/kvm.c | 4 +--- 8 files changed, 8 insertions(+), 19 deletions(-) diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index d0a800be0486..a41e27ace391 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -628,7 +628,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) uprobe_notify_resume(regs); } else { tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); } } local_irq_disable(); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 9fe70b12b34f..c287b9407f28 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -940,10 +940,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_flags & _TIF_NOTIFY_RESUME) { + if (thread_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } if (thread_flags & _TIF_FOREIGN_FPSTATE) fpsimd_restore_current_state(); diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 312f046d452d..bc4238b9f709 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -260,8 +260,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index f1e985109da0..c9b2a75563e1 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -906,10 +906,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } user_enter(); } diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e600764a926c..b93b87df499d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) do_signal(current); } - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3e80c4bc66f7..2564b7434b4d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -197,6 +197,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); } /* diff --git a/kernel/entry/common.c b/kernel/entry/common.c index bf16395b9e13..d5a61d565ad5 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) handle_signal_work(regs, ti_work); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } /* Architecture specific TIF work */ arch_exit_to_user_mode_work(regs, ti_work); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 049fd06b4c3d..49972ee99aff 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -19,10 +19,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NEED_RESCHED) schedule(); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(NULL); - rseq_handle_notify_resume(NULL, NULL); - } ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); if (ret) From de5f4213dafa8f8b0b52cdaf06bb35ad4cab1681 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:28 -0700 Subject: [PATCH 565/866] tools: Move x86 syscall number fallbacks to .../uapi/ Move unistd_{32,64}.h from x86/include/asm to x86/include/uapi/asm so that tools/selftests that install kernel headers, e.g. KVM selftests, can include non-uapi tools headers, e.g. to get 'struct list_head', without effectively overriding the installed non-tool uapi headers. Swapping KVM's search order, e.g. to search the kernel headers before tool headers, is not a viable option as doing results in linux/type.h and other core headers getting pulled from the kernel headers, which do not have the kernel-internal typedefs that are used through tools, including many files outside of selftests/kvm's control. Prior to commit cec07f53c398 ("perf tools: Move syscall number fallbacks from perf-sys.h to tools/arch/x86/include/asm/"), the handcoded numbers were actual fallbacks, i.e. overriding unistd_{32,64}.h from the kernel headers was unintentional. Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/arch/x86/include/{ => uapi}/asm/unistd_32.h | 0 tools/arch/x86/include/{ => uapi}/asm/unistd_64.h | 0 2 files changed, 0 insertions(+), 0 deletions(-) rename tools/arch/x86/include/{ => uapi}/asm/unistd_32.h (100%) rename tools/arch/x86/include/{ => uapi}/asm/unistd_64.h (100%) diff --git a/tools/arch/x86/include/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h similarity index 100% rename from tools/arch/x86/include/asm/unistd_32.h rename to tools/arch/x86/include/uapi/asm/unistd_32.h diff --git a/tools/arch/x86/include/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h similarity index 100% rename from tools/arch/x86/include/asm/unistd_64.h rename to tools/arch/x86/include/uapi/asm/unistd_64.h From 61e52f1630f54713f5dffa1ab4bb49772235aa5a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:29 -0700 Subject: [PATCH 566/866] KVM: selftests: Add a test for KVM_RUN+rseq to detect task migration bugs Add a test to verify an rseq's CPU ID is updated correctly if the task is migrated while the kernel is handling KVM_RUN. This is a regression test for a bug introduced by commit 72c3c0fe54a3 ("x86/kvm: Use generic xfer to guest work function"), where TIF_NOTIFY_RESUME would be cleared by KVM without updating rseq, leading to a stale CPU ID and other badness. Signed-off-by: Sean Christopherson Acked-by: Mathieu Desnoyers Message-Id: <20210901203030.1292304-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 3 + tools/testing/selftests/kvm/rseq_test.c | 236 ++++++++++++++++++++++++ 3 files changed, 240 insertions(+) create mode 100644 tools/testing/selftests/kvm/rseq_test.c diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 98053d3afbda..618bf9bc7f3f 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -48,6 +48,7 @@ /kvm_page_table_test /memslot_modification_stress_test /memslot_perf_test +/rseq_test /set_memory_region_test /steal_time /kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 5d05801ab816..9ac325cfc94a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -80,6 +80,7 @@ TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += kvm_page_table_test TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test TEST_GEN_PROGS_x86_64 += memslot_perf_test +TEST_GEN_PROGS_x86_64 += rseq_test TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test @@ -93,6 +94,7 @@ TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += kvm_page_table_test +TEST_GEN_PROGS_aarch64 += rseq_test TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test @@ -104,6 +106,7 @@ TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS_s390x += kvm_page_table_test +TEST_GEN_PROGS_s390x += rseq_test TEST_GEN_PROGS_s390x += set_memory_region_test TEST_GEN_PROGS_s390x += kvm_binary_stats_test diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c new file mode 100644 index 000000000000..060538bd405a --- /dev/null +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID 0 + +static __thread volatile struct rseq __rseq = { + .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, +}; + +/* + * Use an arbitrary, bogus signature for configuring rseq, this test does not + * actually enter an rseq critical section. + */ +#define RSEQ_SIG 0xdeadbeef + +/* + * Any bug related to task migration is likely to be timing-dependent; perform + * a large number of migrations to reduce the odds of a false negative. + */ +#define NR_TASK_MIGRATIONS 100000 + +static pthread_t migration_thread; +static cpu_set_t possible_mask; +static bool done; + +static atomic_t seq_cnt; + +static void guest_code(void) +{ + for (;;) + GUEST_SYNC(0); +} + +static void sys_rseq(int flags) +{ + int r; + + r = syscall(__NR_rseq, &__rseq, sizeof(__rseq), flags, RSEQ_SIG); + TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); +} + +static void *migration_worker(void *ign) +{ + cpu_set_t allowed_mask; + int r, i, nr_cpus, cpu; + + CPU_ZERO(&allowed_mask); + + nr_cpus = CPU_COUNT(&possible_mask); + + for (i = 0; i < NR_TASK_MIGRATIONS; i++) { + cpu = i % nr_cpus; + if (!CPU_ISSET(cpu, &possible_mask)) + continue; + + CPU_SET(cpu, &allowed_mask); + + /* + * Bump the sequence count twice to allow the reader to detect + * that a migration may have occurred in between rseq and sched + * CPU ID reads. An odd sequence count indicates a migration + * is in-progress, while a completely different count indicates + * a migration occurred since the count was last read. + */ + atomic_inc(&seq_cnt); + + /* + * Ensure the odd count is visible while sched_getcpu() isn't + * stable, i.e. while changing affinity is in-progress. + */ + smp_wmb(); + r = sched_setaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_setaffinity failed, errno = %d (%s)", + errno, strerror(errno)); + smp_wmb(); + atomic_inc(&seq_cnt); + + CPU_CLR(cpu, &allowed_mask); + + /* + * Wait 1-10us before proceeding to the next iteration and more + * specifically, before bumping seq_cnt again. A delay is + * needed on three fronts: + * + * 1. To allow sched_setaffinity() to prompt migration before + * ioctl(KVM_RUN) enters the guest so that TIF_NOTIFY_RESUME + * (or TIF_NEED_RESCHED, which indirectly leads to handling + * NOTIFY_RESUME) is handled in KVM context. + * + * If NOTIFY_RESUME/NEED_RESCHED is set after KVM enters + * the guest, the guest will trigger a IO/MMIO exit all the + * way to userspace and the TIF flags will be handled by + * the generic "exit to userspace" logic, not by KVM. The + * exit to userspace is necessary to give the test a chance + * to check the rseq CPU ID (see #2). + * + * Alternatively, guest_code() could include an instruction + * to trigger an exit that is handled by KVM, but any such + * exit requires architecture specific code. + * + * 2. To let ioctl(KVM_RUN) make its way back to the test + * before the next round of migration. The test's check on + * the rseq CPU ID must wait for migration to complete in + * order to avoid false positive, thus any kernel rseq bug + * will be missed if the next migration starts before the + * check completes. + * + * 3. To ensure the read-side makes efficient forward progress, + * e.g. if sched_getcpu() involves a syscall. Stalling the + * read-side means the test will spend more time waiting for + * sched_getcpu() to stabilize and less time trying to hit + * the timing-dependent bug. + * + * Because any bug in this area is likely to be timing-dependent, + * run with a range of delays at 1us intervals from 1us to 10us + * as a best effort to avoid tuning the test to the point where + * it can hit _only_ the original bug and not detect future + * regressions. + * + * The original bug can reproduce with a delay up to ~500us on + * x86-64, but starts to require more iterations to reproduce + * as the delay creeps above ~10us, and the average runtime of + * each iteration obviously increases as well. Cap the delay + * at 10us to keep test runtime reasonable while minimizing + * potential coverage loss. + * + * The lower bound for reproducing the bug is likely below 1us, + * e.g. failures occur on x86-64 with nanosleep(0), but at that + * point the overhead of the syscall likely dominates the delay. + * Use usleep() for simplicity and to avoid unnecessary kernel + * dependencies. + */ + usleep((i % 10) + 1); + } + done = true; + return NULL; +} + +int main(int argc, char *argv[]) +{ + int r, i, snapshot; + struct kvm_vm *vm; + u32 cpu, rseq_cpu; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); + TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, + strerror(errno)); + + if (CPU_COUNT(&possible_mask) < 2) { + print_skip("Only one CPU, task migration not possible\n"); + exit(KSFT_SKIP); + } + + sys_rseq(0); + + /* + * Create and run a dummy VM that immediately exits to userspace via + * GUEST_SYNC, while concurrently migrating the process by setting its + * CPU affinity. + */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + pthread_create(&migration_thread, NULL, migration_worker, 0); + + for (i = 0; !done; i++) { + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + "Guest failed?"); + + /* + * Verify rseq's CPU matches sched's CPU. Ensure migration + * doesn't occur between sched_getcpu() and reading the rseq + * cpu_id by rereading both if the sequence count changes, or + * if the count is odd (migration in-progress). + */ + do { + /* + * Drop bit 0 to force a mismatch if the count is odd, + * i.e. if a migration is in-progress. + */ + snapshot = atomic_read(&seq_cnt) & ~1; + + /* + * Ensure reading sched_getcpu() and rseq.cpu_id + * complete in a single "no migration" window, i.e. are + * not reordered across the seq_cnt reads. + */ + smp_rmb(); + cpu = sched_getcpu(); + rseq_cpu = READ_ONCE(__rseq.cpu_id); + smp_rmb(); + } while (snapshot != atomic_read(&seq_cnt)); + + TEST_ASSERT(rseq_cpu == cpu, + "rseq CPU = %d, sched CPU = %d\n", rseq_cpu, cpu); + } + + /* + * Sanity check that the test was able to enter the guest a reasonable + * number of times, e.g. didn't get stalled too often/long waiting for + * sched_getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a + * fairly conservative ratio on x86-64, which can do _more_ KVM_RUNs + * than migrations given the 1us+ delay in the migration task. + */ + TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2), + "Only performed %d KVM_RUNs, task stalled too much?\n", i); + + pthread_join(migration_thread, NULL); + + kvm_vm_free(vm); + + sys_rseq(RSEQ_FLAG_UNREGISTER); + + return 0; +} From 2da4a23599c263bd4a7658c2fe561cb3a73ea6ae Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:30 -0700 Subject: [PATCH 567/866] KVM: selftests: Remove __NR_userfaultfd syscall fallback Revert the __NR_userfaultfd syscall fallback added for KVM selftests now that x86's unistd_{32,63}.h overrides are under uapi/ and thus not in KVM selftests' search path, i.e. now that KVM gets x86 syscall numbers from the installed kernel headers. No functional change intended. Reviewed-by: Ben Gardon Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-6-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/arch/x86/include/uapi/asm/unistd_64.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index 4205ed4158bf..cb52a3a8b8fc 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -1,7 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NR_userfaultfd -#define __NR_userfaultfd 282 -#endif #ifndef __NR_perf_event_open # define __NR_perf_event_open 298 #endif From 7117003fe4e3c8977744f2ad33bb95fd3e10023f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 20 Sep 2021 17:02:54 -0700 Subject: [PATCH 568/866] KVM: x86: Mark all registers as avail/dirty at vCPU creation Mark all registers as available and dirty at vCPU creation, as the vCPU has obviously not been loaded into hardware, let alone been given the chance to be modified in hardware. On SVM, reading from "uninitialized" hardware is a non-issue as VMCBs are zero allocated (thus not truly uninitialized) and hardware does not allow for arbitrary field encoding schemes. On VMX, backing memory for VMCSes is also zero allocated, but true initialization of the VMCS _technically_ requires VMWRITEs, as the VMX architectural specification technically allows CPU implementations to encode fields with arbitrary schemes. E.g. a CPU could theoretically store the inverted value of every field, which would result in VMREAD to a zero-allocated field returns all ones. In practice, only the AR_BYTES fields are known to be manipulated by hardware during VMREAD/VMREAD; no known hardware or VMM (for nested VMX) does fancy encoding of cacheable field values (CR0, CR3, CR4, etc...). In other words, this is technically a bug fix, but practically speakings it's a glorified nop. Failure to mark registers as available has been a lurking bug for quite some time. The original register caching supported only GPRs (+RIP, which is kinda sorta a GPR), with the masks initialized at ->vcpu_reset(). That worked because the two cacheable registers, RIP and RSP, are generally speaking not read as side effects in other flows. Arguably, commit aff48baa34c0 ("KVM: Fetch guest cr3 from hardware on demand") was the first instance of failure to mark regs available. While _just_ marking CR3 available during vCPU creation wouldn't have fixed the VMREAD from an uninitialized VMCS bug because ept_update_paging_mode_cr0() unconditionally read vmcs.GUEST_CR3, marking CR3 _and_ intentionally not reading GUEST_CR3 when it's available would have avoided VMREAD to a technically-uninitialized VMCS. Fixes: aff48baa34c0 ("KVM: Fetch guest cr3 from hardware on demand") Fixes: 6de4f3ada40b ("KVM: Cache pdptrs") Fixes: 6de12732c42c ("KVM: VMX: Optimize vmx_get_rflags()") Fixes: 2fb92db1ec08 ("KVM: VMX: Cache vmcs segment fields") Fixes: bd31fe495d0d ("KVM: VMX: Add proper cache tracking for CR0") Fixes: f98c1e77127d ("KVM: VMX: Add proper cache tracking for CR4") Fixes: 5addc235199f ("KVM: VMX: Cache vmcs.EXIT_QUALIFICATION using arch avail_reg flags") Fixes: 8791585837f6 ("KVM: VMX: Cache vmcs.EXIT_INTR_INFO using arch avail_reg flags") Signed-off-by: Sean Christopherson Message-Id: <20210921000303.400537-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28ef14155726..06026f3d7ea2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10652,6 +10652,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) int r; vcpu->arch.last_vmentry_cpu = -1; + vcpu->arch.regs_avail = ~0; + vcpu->arch.regs_dirty = ~0; if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; From 03a6e84069d1870f5b3d360e64cb330b66f76dee Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 20 Sep 2021 17:02:55 -0700 Subject: [PATCH 569/866] KVM: x86: Clear KVM's cached guest CR3 at RESET/INIT Explicitly zero the guest's CR3 and mark it available+dirty at RESET/INIT. Per Intel's SDM and AMD's APM, CR3 is zeroed at both RESET and INIT. For RESET, this is a nop as vcpu is zero-allocated. For INIT, the bug has likely escaped notice because no firmware/kernel puts its page tables root at PA=0, let alone relies on INIT to get the desired CR3 for such page tables. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20210921000303.400537-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 06026f3d7ea2..8a83dd1b882e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10895,6 +10895,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0xfff0); + vcpu->arch.cr3 = 0; + kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3); + /* * CR0.CD/NW are set on RESET, preserved on INIT. Note, some versions * of Intel's SDM list CD/NW as being set on INIT, but they contradict From 90b54129e8df909ccca527b2d69bcb1f0216aa8f Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 21 Sep 2021 17:11:20 +0000 Subject: [PATCH 570/866] selftests: KVM: Fix check for !POLLIN in demand_paging_test The logical not operator applies only to the left hand side of a bitwise operator. As such, the check for POLLIN not being set in revents wrong. Fix it by adding parentheses around the bitwise expression. Fixes: 4f72180eb4da ("KVM: selftests: Add demand paging content to the demand paging test") Reviewed-by: Andrew Jones Signed-off-by: Oliver Upton Message-Id: <20210921171121.2148982-2-oupton@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/demand_paging_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index e79c1b64977f..10edae425ab3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -179,7 +179,7 @@ static void *uffd_handler_thread_fn(void *arg) return NULL; } - if (!pollfd[0].revents & POLLIN) + if (!(pollfd[0].revents & POLLIN)) continue; r = read(uffd, &msg, sizeof(msg)); From 01f91acb55be7aac3950b89c458bcea9ef6e4f49 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 21 Sep 2021 17:11:21 +0000 Subject: [PATCH 571/866] selftests: KVM: Align SMCCC call with the spec in steal_time The SMC64 calling convention passes a function identifier in w0 and its parameters in x1-x17. Given this, there are two deviations in the SMC64 call performed by the steal_time test: the function identifier is assigned to a 64 bit register and the parameter is only 32 bits wide. Align the call with the SMCCC by using a 32 bit register to handle the function identifier and increasing the parameter width to 64 bits. Suggested-by: Andrew Jones Signed-off-by: Oliver Upton Reviewed-by: Andrew Jones Message-Id: <20210921171121.2148982-3-oupton@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/steal_time.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index ecec30865a74..aafaa8e38b7c 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -118,12 +118,12 @@ struct st_time { uint64_t st_time; }; -static int64_t smccc(uint32_t func, uint32_t arg) +static int64_t smccc(uint32_t func, uint64_t arg) { unsigned long ret; asm volatile( - "mov x0, %1\n" + "mov w0, %w1\n" "mov x1, %2\n" "hvc #0\n" "mov %0, x0\n" From cd36ae8761775e78154ba6bd7a3bd2ab538c589f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 7 Sep 2021 17:24:01 -0700 Subject: [PATCH 572/866] KVM: VMX: Remove defunct "nr_active_uret_msrs" field Remove vcpu_vmx.nr_active_uret_msrs and its associated comment, which are both defunct now that KVM keeps the list constant and instead explicitly tracks which entries need to be loaded into hardware. No functional change intended. Fixes: ee9d22e08d13 ("KVM: VMX: Use flag to indicate "active" uret MSRs instead of sorting list") Signed-off-by: Sean Christopherson Message-Id: <20210908002401.1947049-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 4858c5fd95f2..02ab3468885f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -248,12 +248,8 @@ struct vcpu_vmx { * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to * be loaded into hardware if those conditions aren't met. - * nr_active_uret_msrs tracks the number of MSRs that need to be loaded - * into hardware when running the guest. guest_uret_msrs[] is resorted - * whenever the number of "active" uret MSRs is modified. */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; From eb7511bf9182292ef1df1082d23039e856d1ddfb Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Fri, 3 Sep 2021 10:37:06 +0800 Subject: [PATCH 573/866] KVM: x86: Handle SRCU initialization failure during page track init Check the return of init_srcu_struct(), which can fail due to OOM, when initializing the page track mechanism. Lack of checking leads to a NULL pointer deref found by a modified syzkaller. Reported-by: TCS Robot Signed-off-by: Haimin Zhang Message-Id: <1630636626-12262-1-git-send-email-tcs_kernel@tencent.com> [Move the call towards the beginning of kvm_arch_init_vm. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_page_track.h | 2 +- arch/x86/kvm/mmu/page_track.c | 4 ++-- arch/x86/kvm/x86.c | 7 ++++++- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 87bd6025d91d..6a5f3acf2b33 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node { struct kvm_page_track_notifier_node *node); }; -void kvm_page_track_init(struct kvm *kvm); +int kvm_page_track_init(struct kvm *kvm); void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *slot); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 269f11f92fd0..21427e84a82e 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm) cleanup_srcu_struct(&head->track_srcu); } -void kvm_page_track_init(struct kvm *kvm) +int kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; head = &kvm->arch.track_notifier_head; - init_srcu_struct(&head->track_srcu); INIT_HLIST_HEAD(&head->track_notifier_list); + return init_srcu_struct(&head->track_srcu); } /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8a83dd1b882e..42c5c7a195ae 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11144,9 +11144,15 @@ void kvm_arch_free_vm(struct kvm *kvm) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { + int ret; + if (type) return -EINVAL; + ret = kvm_page_track_init(kvm); + if (ret) + return ret; + INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); @@ -11179,7 +11185,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_apicv_init(kvm); kvm_hv_init_vm(kvm); - kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); kvm_xen_init_vm(kvm); From ed7023a11bd820fca50e61911a670ddf3e01f73f Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 9 Sep 2021 01:17:31 +0800 Subject: [PATCH 574/866] KVM: nVMX: fix comments of handle_vmon() "VMXON pointer" is saved in vmx->nested.vmxon_ptr since commit 3573e22cfeca ("KVM: nVMX: additional checks on vmxon region"). Also, handle_vmptrld() & handle_vmclear() now have logic to check the VMCS pointer against the VMXON pointer. So just remove the obsolete comments of handle_vmon(). Signed-off-by: Yu Zhang Message-Id: <20210908171731.18885-1-yu.c.zhang@linux.intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ccb03d69546c..35cd938afa1d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4899,14 +4899,7 @@ out_vmcs02: return -ENOMEM; } -/* - * Emulate the VMXON instruction. - * Currently, we just remember that VMX is active, and do not save or even - * inspect the argument to VMXON (the so-called "VMXON pointer") because we - * do not currently need to store anything in that guest-allocated memory - * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their - * argument is different from the VMXON pointer (which the spec says they do). - */ +/* Emulate the VMXON instruction. */ static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; From ae232ea460888dc5a8b37e840c553b02521fbf18 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 2 Sep 2021 12:11:00 +0900 Subject: [PATCH 575/866] KVM: do not shrink halt_poll_ns below grow_start grow_halt_poll_ns() ignores values between 0 and halt_poll_ns_grow_start (10000 by default). However, when we shrink halt_poll_ns we may fall way below halt_poll_ns_grow_start and endup with halt_poll_ns values that don't make a lot of sense: like 1 or 9, or 19. VCPU1 trace (halt_poll_ns_shrink equals 2): VCPU1 grow 10000 VCPU1 shrink 5000 VCPU1 shrink 2500 VCPU1 shrink 1250 VCPU1 shrink 625 VCPU1 shrink 312 VCPU1 shrink 156 VCPU1 shrink 78 VCPU1 shrink 39 VCPU1 shrink 19 VCPU1 shrink 9 VCPU1 shrink 4 Mirror what grow_halt_poll_ns() does and set halt_poll_ns to 0 as soon as new shrink-ed halt_poll_ns value falls below halt_poll_ns_grow_start. Signed-off-by: Sergey Senozhatsky Signed-off-by: Paolo Bonzini Message-Id: <20210902031100.252080-1-senozhatsky@chromium.org> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 439d3b4cd1a9..8495a01d1e41 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3134,15 +3134,19 @@ out: static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { - unsigned int old, val, shrink; + unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); + grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; + if (val < grow_start) + val = 0; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } From bb18a677746543e7f5eeb478129c92cedb0f9658 Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Wed, 15 Sep 2021 10:17:55 -0700 Subject: [PATCH 576/866] KVM: SEV: Acquire vcpu mutex when updating VMSA The update-VMSA ioctl touches data stored in struct kvm_vcpu, and therefore should not be performed concurrently with any VCPU ioctl that might cause KVM or the processor to use the same data. Adds vcpu mutex guard to the VMSA updating code. Refactors out __sev_launch_update_vmsa() function to deal with per vCPU parts of sev_launch_update_vmsa(). Fixes: ad73109ae7ec ("KVM: SVM: Provide support to launch and run an SEV-ES guest") Signed-off-by: Peter Gonda Cc: Marc Orr Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Brijesh Singh Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: <20210915171755.3773766-1-pgonda@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 51 ++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 22 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 75e0b21ad07c..61c4bf4b3a0a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -595,43 +595,50 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) return 0; } +static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + int *error) +{ + struct sev_data_launch_update_vmsa vmsa; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of + * the VMSA memory content (i.e it will write the same memory region + * with the guest's key), so invalidate it first. + */ + clflush_cache_range(svm->vmsa, PAGE_SIZE); + + vmsa.reserved = 0; + vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.address = __sme_pa(svm->vmsa); + vmsa.len = PAGE_SIZE; + return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); +} + static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { - struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_update_vmsa vmsa; struct kvm_vcpu *vcpu; int i, ret; if (!sev_es_guest(kvm)) return -ENOTTY; - vmsa.reserved = 0; - kvm_for_each_vcpu(i, vcpu, kvm) { - struct vcpu_svm *svm = to_svm(vcpu); - - /* Perform some pre-encryption checks against the VMSA */ - ret = sev_es_sync_vmsa(svm); + ret = mutex_lock_killable(&vcpu->mutex); if (ret) return ret; - /* - * The LAUNCH_UPDATE_VMSA command will perform in-place - * encryption of the VMSA memory content (i.e it will write - * the same memory region with the guest's key), so invalidate - * it first. - */ - clflush_cache_range(svm->vmsa, PAGE_SIZE); + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); - vmsa.handle = sev->handle; - vmsa.address = __sme_pa(svm->vmsa); - vmsa.len = PAGE_SIZE; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, - &argp->error); + mutex_unlock(&vcpu->mutex); if (ret) return ret; - - svm->vcpu.arch.guest_state_protected = true; } return 0; From f1815e0aa770f2127c5df31eb5c2f0e37b60fa77 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Sun, 12 Sep 2021 18:18:15 +0000 Subject: [PATCH 577/866] KVM: SVM: fix missing sev_decommission in sev_receive_start DECOMMISSION the current SEV context if binding an ASID fails after RECEIVE_START. Per AMD's SEV API, RECEIVE_START generates a new guest context and thus needs to be paired with DECOMMISSION: The RECEIVE_START command is the only command other than the LAUNCH_START command that generates a new guest context and guest handle. The missing DECOMMISSION can result in subsequent SEV launch failures, as the firmware leaks memory and might not able to allocate more SEV guest contexts in the future. Note, LAUNCH_START suffered the same bug, but was previously fixed by commit 934002cd660b ("KVM: SVM: Call SEV Guest Decommission if ASID binding fails"). Cc: Alper Gun Cc: Borislav Petkov Cc: Brijesh Singh Cc: David Rienjes Cc: Marc Orr Cc: John Allen Cc: Peter Gonda Cc: Sean Christopherson Cc: Tom Lendacky Cc: Vipin Sharma Cc: stable@vger.kernel.org Reviewed-by: Marc Orr Acked-by: Brijesh Singh Fixes: af43cbbf954b ("KVM: SVM: Add support for KVM_SEV_RECEIVE_START command") Signed-off-by: Mingwei Zhang Reviewed-by: Sean Christopherson Message-Id: <20210912181815.3899316-1-mizhang@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 61c4bf4b3a0a..4d68a37a8a24 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1404,8 +1404,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start.handle, error); - if (ret) + if (ret) { + sev_decommission(start.handle); goto e_free_session; + } params.handle = start.handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, From 50c038018d6be20361e8a2890262746a4ac5b11f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 14 Sep 2021 14:09:50 -0700 Subject: [PATCH 578/866] KVM: SEV: Pin guest memory for write for RECEIVE_UPDATE_DATA Require the target guest page to be writable when pinning memory for RECEIVE_UPDATE_DATA. Per the SEV API, the PSP writes to guest memory: The result is then encrypted with GCTX.VEK and written to the memory pointed to by GUEST_PADDR field. Fixes: 15fb7de1a7f5 ("KVM: SVM: Add KVM_SEV_RECEIVE_UPDATE_DATA command") Cc: stable@vger.kernel.org Cc: Peter Gonda Cc: Marc Orr Cc: Tom Lendacky Cc: Brijesh Singh Signed-off-by: Sean Christopherson Message-Id: <20210914210951.2994260-2-seanjc@google.com> Reviewed-by: Brijesh Singh Reviewed-by: Peter Gonda Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4d68a37a8a24..002d9885a3f4 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1473,7 +1473,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Pin guest memory */ guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, - PAGE_SIZE, &n, 0); + PAGE_SIZE, &n, 1); if (IS_ERR(guest_page)) { ret = PTR_ERR(guest_page); goto e_free_trans; From e9337c843c4b4eaa4afb752a7272ef3d04c46381 Mon Sep 17 00:00:00 2001 From: Hou Wenlong Date: Wed, 18 Aug 2021 11:36:31 +0800 Subject: [PATCH 579/866] kvm: fix wrong exception emulation in check_rdtsc According to Intel's SDM Vol2 and AMD's APM Vol3, when CR4.TSD is set, use rdtsc/rdtscp instruction above privilege level 0 should trigger a #GP. Fixes: d7eb82030699e ("KVM: SVM: Add intercept checks for remaining group7 instructions") Signed-off-by: Hou Wenlong Message-Id: <1297c0dd3f1bb47a6d089f850b629c7aa0247040.1629257115.git.houwenlong93@linux.alibaba.com> Reviewed-by: Sean Christopherson Reviewed-by: Jim Mattson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2837110e66ed..c589ac832265 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4206,7 +4206,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt) u64 cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) - return emulate_ud(ctxt); + return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } From 4eeef2424153e79910d65248b5e1abf137d050e9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Sep 2021 11:32:19 -0700 Subject: [PATCH 580/866] KVM: x86: Query vcpu->vcpu_idx directly and drop its accessor Read vcpu->vcpu_idx directly instead of bouncing through the one-line wrapper, kvm_vcpu_get_idx(), and drop the wrapper. The wrapper is a remnant of the original implementation and serves no purpose; remove it before it gains more users. Back when kvm_vcpu_get_idx() was added by commit 497d72d80a78 ("KVM: Add kvm_vcpu_get_idx to get vcpu index in kvm->vcpus"), the implementation was more than just a simple wrapper as vcpu->vcpu_idx did not exist and retrieving the index meant walking over the vCPU array to find the given vCPU. When vcpu_idx was introduced by commit 8750e72a79dd ("KVM: remember position in kvm->vcpus array"), the helper was left behind, likely to avoid extra thrash (but even then there were only two users, the original arm usage having been removed at some point in the past). No functional change intended. Suggested-by: Vitaly Kuznetsov Signed-off-by: Sean Christopherson Reviewed-by: Maxim Levitsky Reviewed-by: Vitaly Kuznetsov Message-Id: <20210910183220.2397812-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/s390/kvm/interrupt.c | 4 ++-- arch/s390/kvm/kvm-s390.c | 2 +- arch/s390/kvm/kvm-s390.h | 2 +- arch/x86/kvm/hyperv.c | 7 +++---- arch/x86/kvm/hyperv.h | 2 +- include/linux/kvm_host.h | 5 ----- 6 files changed, 8 insertions(+), 14 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 16256e17a544..10722455fd02 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); - set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 752a0ffab9bf..6a6dd5e1daf6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4066,7 +4066,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ecd741ee3276..52bc8fbaa60a 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 232a86a6faaf..d5124b520f76 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); - hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + hv_vcpu->vp_index = vcpu->vcpu_idx; return 0; } @@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) @@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ - if (hv_vcpu->vp_index == vcpu_idx) + if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); - else if (new_vp_index == vcpu_idx) + else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 730da8537d05..ed1c4e546d04 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); + return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 041ca7f15ea4..000ea73dd324 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -721,11 +721,6 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) -{ - return vcpu->vcpu_idx; -} - #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + slots->used_slots; memslot++) \ From 94c245a245ff6552a320257f97d5171d03f7ee3a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Sep 2021 11:32:20 -0700 Subject: [PATCH 581/866] KVM: x86: Identify vCPU0 by its vcpu_idx instead of its vCPUs array entry Use vcpu_idx to identify vCPU0 when updating HyperV's TSC page, which is shared by all vCPUs and "owned" by vCPU0 (because vCPU0 is the only vCPU that's guaranteed to exist). Using kvm_get_vcpu() to find vCPU works, but it's a rather odd and suboptimal method to check the index of a given vCPU. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Jim Mattson Reviewed-by: Maxim Levitsky Reviewed-by: Vitaly Kuznetsov Message-Id: <20210910183220.2397812-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 42c5c7a195ae..11017c94f0aa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2969,7 +2969,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_set) kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); - if (v == kvm_get_vcpu(v->kvm, 0)) + if (!v->vcpu_idx) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } From 24a996ade34d00deef5dee2c33aacd8fda91ec31 Mon Sep 17 00:00:00 2001 From: Chenyi Qiang Date: Tue, 14 Sep 2021 17:50:41 +0800 Subject: [PATCH 582/866] KVM: nVMX: Fix nested bus lock VM exit Nested bus lock VM exits are not supported yet. If L2 triggers bus lock VM exit, it will be directed to L1 VMM, which would cause unexpected behavior. Therefore, handle L2's bus lock VM exits in L0 directly. Fixes: fe6b6bc802b4 ("KVM: VMX: Enable bus lock VM exit") Signed-off-by: Chenyi Qiang Reviewed-by: Sean Christopherson Reviewed-by: Xiaoyao Li Message-Id: <20210914095041.29764-1-chenyi.qiang@intel.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 35cd938afa1d..bc9c9cc228ea 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5896,6 +5896,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, case EXIT_REASON_VMFUNC: /* VM functions are emulated through L2->L0 vmexits. */ return true; + case EXIT_REASON_BUS_LOCK: + /* + * At present, bus lock VM exit is never exposed to L1. + * Handle L2's bus locks in L0 directly. + */ + return true; default: break; } From f43c887cb7cb5b66c4167d40a4209027f5fdb5ce Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Tue, 21 Sep 2021 08:03:44 -0700 Subject: [PATCH 583/866] KVM: SEV: Update svm_vm_copy_asid_from for SEV-ES For mirroring SEV-ES the mirror VM will need more then just the ASID. The FD and the handle are required to all the mirror to call psp commands. The mirror VM will need to call KVM_SEV_LAUNCH_UPDATE_VMSA to setup its vCPUs' VMSAs for SEV-ES. Signed-off-by: Peter Gonda Cc: Marc Orr Cc: Nathan Tempelman Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Steve Rutherford Cc: Brijesh Singh Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 54526d1fd593 ("KVM: x86: Support KVM VMs sharing SEV context", 2021-04-21) Message-Id: <20210921150345.2221634-2-pgonda@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 002d9885a3f4..5ec10ed85862 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1724,8 +1724,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) { struct file *source_kvm_file; struct kvm *source_kvm; - struct kvm_sev_info *mirror_sev; - unsigned int asid; + struct kvm_sev_info source_sev, *mirror_sev; int ret; source_kvm_file = fget(source_fd); @@ -1748,7 +1747,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) goto e_source_unlock; } - asid = to_kvm_svm(source_kvm)->sev_info.asid; + memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info, + sizeof(source_sev)); /* * The mirror kvm holds an enc_context_owner ref so its asid can't @@ -1768,8 +1768,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) /* Set enc_context_owner and copy its encryption context over */ mirror_sev = &to_kvm_svm(kvm)->sev_info; mirror_sev->enc_context_owner = source_kvm; - mirror_sev->asid = asid; mirror_sev->active = true; + mirror_sev->asid = source_sev.asid; + mirror_sev->fd = source_sev.fd; + mirror_sev->es_active = source_sev.es_active; + mirror_sev->handle = source_sev.handle; + /* + * Do not copy ap_jump_table. Since the mirror does not share the same + * KVM contexts as the original, and they may have different + * memory-views. + */ mutex_unlock(&kvm->lock); return 0; From 5b92b6ca92b65bef811048c481e4446f4828500a Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Tue, 21 Sep 2021 08:03:45 -0700 Subject: [PATCH 584/866] KVM: SEV: Allow some commands for mirror VM A mirrored SEV-ES VM will need to call KVM_SEV_LAUNCH_UPDATE_VMSA to setup its vCPUs and have them measured, and their VMSAs encrypted. Without this change, it is impossible to have mirror VMs as part of SEV-ES VMs. Also allow the guest status check and debugging commands since they do not change any guest state. Signed-off-by: Peter Gonda Cc: Marc Orr Cc: Nathan Tempelman Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Steve Rutherford Cc: Brijesh Singh Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 54526d1fd593 ("KVM: x86: Support KVM VMs sharing SEV context", 2021-04-21) Message-Id: <20210921150345.2221634-3-pgonda@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 5ec10ed85862..c36b5fe4c27c 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1510,6 +1510,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } +static bool cmd_allowed_from_miror(u32 cmd_id) +{ + /* + * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES + * active mirror VMs. Also allow the debugging and status commands. + */ + if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA || + cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT || + cmd_id == KVM_SEV_DBG_ENCRYPT) + return true; + + return false; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; @@ -1526,8 +1540,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); - /* enc_context_owner handles all memory enc operations */ - if (is_mirroring_enc_context(kvm)) { + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !cmd_allowed_from_miror(sev_cmd.id)) { r = -EINVAL; goto out; } From a1e638da1ba4078caa0374507cf0d9ec140a255f Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Sep 2021 17:36:55 +0000 Subject: [PATCH 585/866] KVM: selftests: Change backing_src flag to -s in demand_paging_test Every other KVM selftest uses -s for the backing_src, so switch demand_paging_test to match. Reviewed-by: Ben Gardon Reviewed-by: Andrew Jones Signed-off-by: David Matlack Message-Id: <20210917173657.44011-2-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/demand_paging_test.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 10edae425ab3..71e18e9a3c13 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -416,7 +416,7 @@ static void help(char *name) { puts(""); printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" - " [-b memory] [-t type] [-v vcpus] [-o]\n", name); + " [-b memory] [-s type] [-v vcpus] [-o]\n", name); guest_modes_help(); printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); @@ -426,7 +426,7 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); - printf(" -t: The type of backing memory to use. Default: anonymous\n"); + printf(" -s: The type of backing memory to use. Default: anonymous\n"); backing_src_help(); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" @@ -446,7 +446,7 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:u:d:b:t:v:o")) != -1) { + while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:o")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -465,7 +465,7 @@ int main(int argc, char *argv[]) case 'b': guest_percpu_mem_size = parse_size(optarg); break; - case 't': + case 's': p.src_type = parse_backing_src_type(optarg); break; case 'v': @@ -485,7 +485,7 @@ int main(int argc, char *argv[]) if (p.uffd_mode == UFFDIO_REGISTER_MODE_MINOR && !backing_src_is_shared(p.src_type)) { - TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -t"); + TEST_FAIL("userfaultfd MINOR mode requires shared memory; pick a different -s"); } for_each_guest_mode(run_test, &p); From 9f2fc5554a4093e80084389f760d0b06ec2ff782 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Sep 2021 17:36:56 +0000 Subject: [PATCH 586/866] KVM: selftests: Refactor help message for -s backing_src All selftests that support the backing_src option were printing their own description of the flag and then calling backing_src_help() to dump the list of available backing sources. Consolidate the flag printing in backing_src_help() to align indentation, reduce duplicated strings, and improve consistency across tests. Note: Passing "-s" to backing_src_help is unnecessary since every test uses the same flag. However I decided to keep it for code readability at the call sites. While here this opportunistically fixes the incorrectly interleaved printing -x help message and list of backing source types in dirty_log_perf_test. Fixes: 609e6202ea5f ("KVM: selftests: Support multiple slots in dirty_log_perf_test") Reviewed-by: Ben Gardon Reviewed-by: Andrew Jones Signed-off-by: David Matlack Message-Id: <20210917173657.44011-3-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- .../selftests/kvm/access_tracking_perf_test.c | 6 ++---- .../testing/selftests/kvm/demand_paging_test.c | 5 ++--- .../testing/selftests/kvm/dirty_log_perf_test.c | 8 +++----- tools/testing/selftests/kvm/include/test_util.h | 4 +++- .../testing/selftests/kvm/kvm_page_table_test.c | 7 ++----- tools/testing/selftests/kvm/lib/test_util.c | 17 +++++++++++++---- 6 files changed, 25 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 71e277c7c3f3..5d95113c7b7c 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -371,9 +371,7 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); exit(0); } @@ -381,7 +379,7 @@ static void help(char *name) int main(int argc, char *argv[]) { struct test_params params = { - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, .vcpus = 1, }; diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 71e18e9a3c13..1510b21e6306 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -426,8 +426,7 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); - printf(" -s: The type of backing memory to use. Default: anonymous\n"); - backing_src_help(); + backing_src_help("-s"); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); @@ -439,7 +438,7 @@ int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, .partition_vcpu_memory_access = true, }; int opt; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 479868570d59..b076dfa3ae1b 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -308,11 +308,9 @@ static void help(char *name) printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n\n"); + backing_src_help("-s"); printf(" -x: Split the memory region into this number of memslots.\n" - " (default: 1)"); - backing_src_help(); + " (default: 1)\n"); puts(""); exit(0); } @@ -324,7 +322,7 @@ int main(int argc, char *argv[]) .iterations = TEST_HOST_LOOP_N, .wr_fract = 1, .partition_vcpu_memory_access = true, - .backing_src = VM_MEM_SRC_ANONYMOUS, + .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, }; int opt; diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d79be15dd3d2..4fa1db32c05e 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -90,6 +90,8 @@ enum vm_mem_backing_src_type { NUM_SRC_TYPES, }; +#define DEFAULT_VM_MEM_SRC VM_MEM_SRC_ANONYMOUS + struct vm_mem_backing_src_alias { const char *name; uint32_t flag; @@ -100,7 +102,7 @@ size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); -void backing_src_help(void); +void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); /* diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 0d04a7db7f24..36407cb0ec85 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -456,10 +456,7 @@ static void help(char *name) " (default: 1G)\n"); printf(" -v: specify the number of vCPUs to run\n" " (default: 1)\n"); - printf(" -s: specify the type of memory that should be used to\n" - " back the guest data region.\n" - " (default: anonymous)\n\n"); - backing_src_help(); + backing_src_help("-s"); puts(""); } @@ -468,7 +465,7 @@ int main(int argc, char *argv[]) int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); struct test_params p = { .test_mem_size = DEFAULT_TEST_MEM_SIZE, - .src_type = VM_MEM_SRC_ANONYMOUS, + .src_type = DEFAULT_VM_MEM_SRC, }; int opt; diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index af1031fed97f..e487f798e095 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -279,13 +279,22 @@ size_t get_backing_src_pagesz(uint32_t i) } } -void backing_src_help(void) +static void print_available_backing_src_types(const char *prefix) { int i; - printf("Available backing src types:\n"); + printf("%sAvailable backing src types:\n", prefix); + for (i = 0; i < NUM_SRC_TYPES; i++) - printf("\t%s\n", vm_mem_backing_src_alias(i)->name); + printf("%s %s\n", prefix, vm_mem_backing_src_alias(i)->name); +} + +void backing_src_help(const char *flag) +{ + printf(" %s: specify the type of memory that should be used to\n" + " back the guest data region. (default: %s)\n", + flag, vm_mem_backing_src_alias(DEFAULT_VM_MEM_SRC)->name); + print_available_backing_src_types(" "); } enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) @@ -296,7 +305,7 @@ enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name) if (!strcmp(type_name, vm_mem_backing_src_alias(i)->name)) return i; - backing_src_help(); + print_available_backing_src_types(""); TEST_FAIL("Unknown backing src type: %s", type_name); return -1; } From 7c236b816ef16c2969a88ced658dab667e9dd4ee Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Sep 2021 17:36:57 +0000 Subject: [PATCH 587/866] KVM: selftests: Create a separate dirty bitmap per slot The calculation to get the per-slot dirty bitmap was incorrect leading to a buffer overrun. Fix it by splitting out the dirty bitmap into a separate bitmap per slot. Fixes: 609e6202ea5f ("KVM: selftests: Support multiple slots in dirty_log_perf_test") Signed-off-by: David Matlack Reviewed-by: Andrew Jones Message-Id: <20210917173657.44011-4-dmatlack@google.com> Signed-off-by: Paolo Bonzini --- .../selftests/kvm/dirty_log_perf_test.c | 54 +++++++++++++------ 1 file changed, 39 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index b076dfa3ae1b..7ffab5bd5ce5 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -118,42 +118,64 @@ static inline void disable_dirty_logging(struct kvm_vm *vm, int slots) toggle_dirty_logging(vm, slots, false); } -static void get_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_get_dirty_log(vm, slot, slot_bitmap); + kvm_vm_get_dirty_log(vm, slot, bitmaps[i]); } } -static void clear_dirty_log(struct kvm_vm *vm, int slots, unsigned long *bitmap, - uint64_t nr_pages) +static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], + int slots, uint64_t pages_per_slot) { - uint64_t slot_pages = nr_pages / slots; int i; for (i = 0; i < slots; i++) { int slot = PERF_TEST_MEM_SLOT_INDEX + i; - unsigned long *slot_bitmap = bitmap + i * slot_pages; - kvm_vm_clear_dirty_log(vm, slot, slot_bitmap, 0, slot_pages); + kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot); } } +static unsigned long **alloc_bitmaps(int slots, uint64_t pages_per_slot) +{ + unsigned long **bitmaps; + int i; + + bitmaps = malloc(slots * sizeof(bitmaps[0])); + TEST_ASSERT(bitmaps, "Failed to allocate bitmaps array."); + + for (i = 0; i < slots; i++) { + bitmaps[i] = bitmap_zalloc(pages_per_slot); + TEST_ASSERT(bitmaps[i], "Failed to allocate slot bitmap."); + } + + return bitmaps; +} + +static void free_bitmaps(unsigned long *bitmaps[], int slots) +{ + int i; + + for (i = 0; i < slots; i++) + free(bitmaps[i]); + + free(bitmaps); +} + static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; pthread_t *vcpu_threads; struct kvm_vm *vm; - unsigned long *bmap; + unsigned long **bitmaps; uint64_t guest_num_pages; uint64_t host_num_pages; + uint64_t pages_per_slot; int vcpu_id; struct timespec start; struct timespec ts_diff; @@ -171,7 +193,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); host_num_pages = vm_num_host_pages(mode, guest_num_pages); - bmap = bitmap_zalloc(host_num_pages); + pages_per_slot = host_num_pages / p->slots; + + bitmaps = alloc_bitmaps(p->slots, pages_per_slot); if (dirty_log_manual_caps) { cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; @@ -239,7 +263,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) iteration, ts_diff.tv_sec, ts_diff.tv_nsec); clock_gettime(CLOCK_MONOTONIC, &start); - get_dirty_log(vm, p->slots, bmap, host_num_pages); + get_dirty_log(vm, bitmaps, p->slots); ts_diff = timespec_elapsed(start); get_dirty_log_total = timespec_add(get_dirty_log_total, ts_diff); @@ -248,7 +272,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (dirty_log_manual_caps) { clock_gettime(CLOCK_MONOTONIC, &start); - clear_dirty_log(vm, p->slots, bmap, host_num_pages); + clear_dirty_log(vm, bitmaps, p->slots, pages_per_slot); ts_diff = timespec_elapsed(start); clear_dirty_log_total = timespec_add(clear_dirty_log_total, ts_diff); @@ -281,7 +305,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); } - free(bmap); + free_bitmaps(bitmaps, p->slots); free(vcpu_threads); perf_test_destroy_vm(vm); } From 2f9b68f57c6278c322793a06063181deded0ad69 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 27 Aug 2021 11:25:14 +0200 Subject: [PATCH 588/866] KVM: x86: Fix stack-out-of-bounds memory access from ioapic_write_indirect() KASAN reports the following issue: BUG: KASAN: stack-out-of-bounds in kvm_make_vcpus_request_mask+0x174/0x440 [kvm] Read of size 8 at addr ffffc9001364f638 by task qemu-kvm/4798 CPU: 0 PID: 4798 Comm: qemu-kvm Tainted: G X --------- --- Hardware name: AMD Corporation DAYTONA_X/DAYTONA_X, BIOS RYM0081C 07/13/2020 Call Trace: dump_stack+0xa5/0xe6 print_address_description.constprop.0+0x18/0x130 ? kvm_make_vcpus_request_mask+0x174/0x440 [kvm] __kasan_report.cold+0x7f/0x114 ? kvm_make_vcpus_request_mask+0x174/0x440 [kvm] kasan_report+0x38/0x50 kasan_check_range+0xf5/0x1d0 kvm_make_vcpus_request_mask+0x174/0x440 [kvm] kvm_make_scan_ioapic_request_mask+0x84/0xc0 [kvm] ? kvm_arch_exit+0x110/0x110 [kvm] ? sched_clock+0x5/0x10 ioapic_write_indirect+0x59f/0x9e0 [kvm] ? static_obj+0xc0/0xc0 ? __lock_acquired+0x1d2/0x8c0 ? kvm_ioapic_eoi_inject_work+0x120/0x120 [kvm] The problem appears to be that 'vcpu_bitmap' is allocated as a single long on stack and it should really be KVM_MAX_VCPUS long. We also seem to clear the lower 16 bits of it with bitmap_zero() for no particular reason (my guess would be that 'bitmap' and 'vcpu_bitmap' variables in kvm_bitmap_or_dest_vcpus() caused the confusion: while the later is indeed 16-bit long, the later should accommodate all possible vCPUs). Fixes: 7ee30bc132c6 ("KVM: x86: deliver KVM IOAPIC scan request to target vCPUs") Fixes: 9a2ae9f6b6bb ("KVM: x86: Zero the IOAPIC scan request dest vCPUs bitmap") Reported-by: Dr. David Alan Gilbert Signed-off-by: Vitaly Kuznetsov Reviewed-by: Maxim Levitsky Reviewed-by: Sean Christopherson Message-Id: <20210827092516.1027264-7-vkuznets@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/ioapic.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index ff005fe738a4..8c065da73f8e 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) unsigned index; bool mask_before, mask_after; union kvm_ioapic_redirect_entry *e; - unsigned long vcpu_bitmap; int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; + DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) irq.shorthand = APIC_DEST_NOSHORT; irq.dest_id = e->fields.dest_id; irq.msi_redir_hint = false; - bitmap_zero(&vcpu_bitmap, 16); + bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); if (old_dest_mode != e->fields.dest_mode || old_dest_id != e->fields.dest_id) { /* @@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) kvm_lapic_irq_dest_mode( !!e->fields.dest_mode); kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, - &vcpu_bitmap); + vcpu_bitmap); } kvm_make_scan_ioapic_request_mask(ioapic->kvm, - &vcpu_bitmap); + vcpu_bitmap); } else { kvm_make_scan_ioapic_request(ioapic->kvm); } From 85b640450ddcfa09cf72771b69a9c3daf0ddc772 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Aug 2021 11:25:09 +0200 Subject: [PATCH 589/866] KVM: Clean up benign vcpu->cpu data races when kicking vCPUs Fix a benign data race reported by syzbot+KCSAN[*] by ensuring vcpu->cpu is read exactly once, and by ensuring the vCPU is booted from guest mode if kvm_arch_vcpu_should_kick() returns true. Fix a similar race in kvm_make_vcpus_request_mask() by ensuring the vCPU is interrupted if kvm_request_needs_ipi() returns true. Reading vcpu->cpu before vcpu->mode (via kvm_arch_vcpu_should_kick() or kvm_request_needs_ipi()) means the target vCPU could get migrated (change vcpu->cpu) and enter !OUTSIDE_GUEST_MODE between reading vcpu->cpud and reading vcpu->mode. If that happens, the kick/IPI will be sent to the old pCPU, not the new pCPU that is now running the vCPU or reading SPTEs. Although failing to kick the vCPU is not exactly ideal, practically speaking it cannot cause a functional issue unless there is also a bug in the caller, and any such bug would exist regardless of kvm_vcpu_kick()'s behavior. The purpose of sending an IPI is purely to get a vCPU into the host (or out of reading SPTEs) so that the vCPU can recognize a change in state, e.g. a KVM_REQ_* request. If vCPU's handling of the state change is required for correctness, KVM must ensure either the vCPU sees the change before entering the guest, or that the sender sees the vCPU as running in guest mode. All architectures handle this by (a) sending the request before calling kvm_vcpu_kick() and (b) checking for requests _after_ setting vcpu->mode. x86's READING_SHADOW_PAGE_TABLES has similar requirements; KVM needs to ensure it kicks and waits for vCPUs that started reading SPTEs _before_ MMU changes were finalized, but any vCPU that starts reading after MMU changes were finalized will see the new state and can continue on uninterrupted. For uses of kvm_vcpu_kick() that are not paired with a KVM_REQ_*, e.g. x86's kvm_arch_sync_dirty_log(), the order of the kick must not be relied upon for functional correctness, e.g. in the dirty log case, userspace cannot assume it has a 100% complete log if vCPUs are still running. All that said, eliminate the benign race since the cost of doing so is an "extra" atomic cmpxchg() in the case where the target vCPU is loaded by the current pCPU or is not loaded at all. I.e. the kick will be skipped due to kvm_vcpu_exiting_guest_mode() seeing a compatible vcpu->mode as opposed to the kick being skipped because of the cpu checks. Keep the "cpu != me" checks even though they appear useless/impossible at first glance. x86 processes guest IPI writes in a fast path that runs in IN_GUEST_MODE, i.e. can call kvm_vcpu_kick() from IN_GUEST_MODE. And calling kvm_vm_bugged()->kvm_make_vcpus_request_mask() from IN_GUEST or READING_SHADOW_PAGE_TABLES is perfectly reasonable. Note, a race with the cpu_online() check in kvm_vcpu_kick() likely persists, e.g. the vCPU could exit guest mode and get offlined between the cpu_online() check and the sending of smp_send_reschedule(). But, the online check appears to exist only to avoid a WARN in x86's native_smp_send_reschedule() that fires if the target CPU is not online. The reschedule WARN exists because CPU offlining takes the CPU out of the scheduling pool, i.e. the WARN is intended to detect the case where the kernel attempts to schedule a task on an offline CPU. The actual sending of the IPI is a non-issue as at worst it will simpy be dropped on the floor. In other words, KVM's usurping of the reschedule IPI could theoretically trigger a WARN if the stars align, but there will be no loss of functionality. [*] https://syzkaller.appspot.com/bug?extid=cd4154e502f43f10808a Cc: Venkatesh Srinivas Cc: Vitaly Kuznetsov Fixes: 97222cc83163 ("KVM: Emulate local APIC in kernel") Signed-off-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20210827092516.1027264-2-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8495a01d1e41..490c8cb8cc8d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -263,14 +263,26 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, continue; kvm_make_request(req, vcpu); - cpu = vcpu->cpu; if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; - if (tmp != NULL && cpu != -1 && cpu != me && - kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, tmp); + /* + * Note, the vCPU could get migrated to a different pCPU at any + * point after kvm_request_needs_ipi(), which could result in + * sending an IPI to the previous pCPU. But, that's ok because + * the purpose of the IPI is to ensure the vCPU returns to + * OUTSIDE_GUEST_MODE, which is satisfied if the vCPU migrates. + * Entering READING_SHADOW_PAGE_TABLES after this point is also + * ok, as the requirement is only that KVM wait for vCPUs that + * were reading SPTEs _before_ any changes were finalized. See + * kvm_vcpu_kick() for more details on handling requests. + */ + if (tmp != NULL && kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != me) + __cpumask_set_cpu(cpu, tmp); + } } called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); @@ -3294,16 +3306,24 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; + int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); + } put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); From 0bbc2ca8515f9cdf11df84ccb63dc7c44bc3d8f4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 27 Aug 2021 11:25:10 +0200 Subject: [PATCH 590/866] KVM: KVM: Use cpumask_available() to check for NULL cpumask when kicking vCPUs Check for a NULL cpumask_var_t when kicking multiple vCPUs via cpumask_available(), which performs a !NULL check if and only if cpumasks are configured to be allocated off-stack. This is a meaningless optimization, e.g. avoids a TEST+Jcc and TEST+CMOV on x86, but more importantly helps document that the NULL check is necessary even though all callers pass in a local variable. No functional change intended. Cc: Lai Jiangshan Signed-off-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Message-Id: <20210827092516.1027264-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 490c8cb8cc8d..e95e7a9e4d53 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -235,9 +235,13 @@ static void ack_flush(void *_completed) { } -static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) { - if (unlikely(!cpus)) + const struct cpumask *cpus; + + if (likely(cpumask_available(tmp))) + cpus = tmp; + else cpus = cpu_online_mask; if (cpumask_empty(cpus)) @@ -267,6 +271,14 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; + /* + * tmp can be "unavailable" if cpumasks are allocated off stack + * as allocation of the mask is deliberately not fatal and is + * handled by falling back to kicking all online CPUs. + */ + if (!cpumask_available(tmp)) + continue; + /* * Note, the vCPU could get migrated to a different pCPU at any * point after kvm_request_needs_ipi(), which could result in @@ -278,7 +290,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, * were reading SPTEs _before_ any changes were finalized. See * kvm_vcpu_kick() for more details on handling requests. */ - if (tmp != NULL && kvm_request_needs_ipi(vcpu, req)) { + if (kvm_request_needs_ipi(vcpu, req)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != -1 && cpu != me) __cpumask_set_cpu(cpu, tmp); From 8d68bad6d869fae8f4d50ab6423538dec7da72d1 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 7 Sep 2021 18:35:30 +0200 Subject: [PATCH 591/866] KVM: nVMX: Filter out all unsupported controls when eVMCS was activated Windows Server 2022 with Hyper-V role enabled failed to boot on KVM when enlightened VMCS is advertised. Debugging revealed there are two exposed secondary controls it is not happy with: SECONDARY_EXEC_ENABLE_VMFUNC and SECONDARY_EXEC_SHADOW_VMCS. These controls are known to be unsupported, as there are no corresponding fields in eVMCSv1 (see the comment above EVMCS1_UNSUPPORTED_2NDEXEC definition). Previously, commit 31de3d2500e4 ("x86/kvm/hyper-v: move VMX controls sanitization out of nested_enable_evmcs()") introduced the required filtering mechanism for VMX MSRs but for some reason put only known to be problematic (and not full EVMCS1_UNSUPPORTED_* lists) controls there. Note, Windows Server 2022 seems to have gained some sanity check for VMX MSRs: it doesn't even try to launch a guest when there's something it doesn't like, nested_evmcs_check_controls() mechanism can't catch the problem. Let's be bold this time and instead of playing whack-a-mole just filter out all unsupported controls from VMX MSRs. Fixes: 31de3d2500e4 ("x86/kvm/hyper-v: move VMX controls sanitization out of nested_enable_evmcs()") Signed-off-by: Vitaly Kuznetsov Message-Id: <20210907163530.110066-1-vkuznets@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/evmcs.c | 12 +++++++++--- arch/x86/kvm/vmx/vmx.c | 9 +++++---- 2 files changed, 14 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index 0dab1b7b529f..ba6f99f584ac 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; + break; + case MSR_IA32_VMX_PINBASED_CTLS: + ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; + break; + case MSR_IA32_VMX_VMFUNC: + ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC; break; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0c2c0d5ae873..f7eb0ce0ddb5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &msr_info->data)) return 1; /* - * Enlightened VMCS v1 doesn't have certain fields, but buggy - * Hyper-V versions are still trying to use corresponding - * features when they are exposed. Filter out the essential - * minimum. + * Enlightened VMCS v1 doesn't have certain VMCS fields but + * instead of just ignoring the features, different Hyper-V + * versions are either trying to use them and fail or do some + * sanity checking and refuse to boot. Filter all unsupported + * features out. */ if (!msr_info->host_initiated && vmx->nested.enlightened_vmcs_enabled) From e2e6e449d68ddf4ccb0bf72cc50fbc6c69fe7f63 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:49 +0300 Subject: [PATCH 592/866] KVM: x86: nSVM: restore the L1 host state prior to resuming nested guest on SMM exit Otherwise guest entry code might see incorrect L1 state (e.g paging state). Fixes: 37be407b2ce8 ("KVM: nSVM: Fix L1 state corruption upon return from SMM") Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-3-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 05e8d4d27969..35cac2046f69 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4351,11 +4351,6 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (svm_allocate_nested(svm)) return 1; - vmcb12 = map.hva; - - nested_load_control_from_vmcb12(svm, &vmcb12->control); - - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); kvm_vcpu_unmap(vcpu, &map, true); /* @@ -4369,6 +4364,13 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); + /* + * Enter the nested guest now + */ + vmcb12 = map.hva; + nested_load_control_from_vmcb12(svm, &vmcb12->control); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); + kvm_vcpu_unmap(vcpu, &map_save, true); } } From 37687c403a641f251cb2ef2e7830b88aa0647ba9 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:50 +0300 Subject: [PATCH 593/866] KVM: x86: reset pdptrs_from_userspace when exiting smm When exiting SMM, pdpts are loaded again from the guest memory. This fixes a theoretical bug, when exit from SMM triggers entry to the nested guest which re-uses some of the migration code which uses this flag as a workaround for a legacy userspace. Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 11017c94f0aa..ba70e8f11f2c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7658,6 +7658,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) /* Process a latched INIT or SMI, if any. */ kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; } kvm_mmu_reset_context(vcpu); From e85d3e7b495bb6c0b847a693f5f6d4bd429fae55 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:51 +0300 Subject: [PATCH 594/866] KVM: x86: SVM: call KVM_REQ_GET_NESTED_STATE_PAGES on exit from SMM mode Currently the KVM_REQ_GET_NESTED_STATE_PAGES on SVM only reloads PDPTRs, and MSR bitmap, with former not really needed for SMM as SMM exit code reloads them again from SMRAM'S CR3, and later happens to work since MSR bitmap isn't modified while in SMM. Still it is better to be consistient with VMX. Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-5-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 9 ++++++--- arch/x86/kvm/svm/svm.c | 2 +- arch/x86/kvm/svm/svm.h | 3 ++- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 2545d0c61985..b41a21cac544 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -579,7 +579,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to } int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, - struct vmcb *vmcb12) + struct vmcb *vmcb12, bool from_vmrun) { struct vcpu_svm *svm = to_svm(vcpu); int ret; @@ -609,13 +609,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, nested_vmcb02_prepare_save(svm, vmcb12); ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm), true); + nested_npt_enabled(svm), from_vmrun); if (ret) return ret; if (!npt_enabled) vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + if (!from_vmrun) + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + svm_set_gif(svm, true); return 0; @@ -681,7 +684,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) svm->nested.nested_run_pending = 1; - if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12)) + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; if (nested_svm_vmrun_msrpm(svm)) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 35cac2046f69..ffdde862a5f6 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4369,7 +4369,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) */ vmcb12 = map.hva; nested_load_control_from_vmcb12(svm, &vmcb12->control); - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); kvm_vcpu_unmap(vcpu, &map_save, true); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 524d943f3efc..128a54b1fbf1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } -int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12); +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, + u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); void svm_leave_nested(struct vcpu_svm *svm); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); From 136a55c054ca03b44b74efe03f136d495dd84ec8 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Wed, 22 Sep 2021 10:28:43 -0400 Subject: [PATCH 595/866] KVM: x86: nSVM: refactor svm_leave_smm and smm_enter_smm Use return statements instead of nested if, and fix error path to free all the maps that were allocated. Suggested-by: Sean Christopherson Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 135 +++++++++++++++++++++-------------------- 1 file changed, 69 insertions(+), 66 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ffdde862a5f6..196bb3d22383 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4285,43 +4285,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) struct kvm_host_map map_save; int ret; - if (is_guest_mode(vcpu)) { - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + if (!is_guest_mode(vcpu)) + return 0; - svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); - ret = nested_svm_vmexit(svm); - if (ret) - return ret; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; - /* - * KVM uses VMCB01 to store L1 host state while L2 runs but - * VMCB01 is going to be used during SMM and thus the state will - * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save - * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the - * format of the area is identical to guest save area offsetted - * by 0x400 (matches the offset of 'struct vmcb_save_area' - * within 'struct vmcb'). Note: HSAVE area may also be used by - * L1 hypervisor to save additional host context (e.g. KVM does - * that, see svm_prepare_guest_switch()) which must be - * preserved. - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + ret = nested_svm_vmexit(svm); + if (ret) + return ret; - BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_guest_switch()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), + &map_save) == -EINVAL) + return 1; - svm_copy_vmrun_state(map_save.hva + 0x400, - &svm->vmcb01.ptr->save); + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); - kvm_vcpu_unmap(vcpu, &map_save, true); - } + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); return 0; } @@ -4329,52 +4330,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - int ret = 0; + u64 saved_efer, vmcb12_gpa; + struct vmcb *vmcb12; + int ret; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { - u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); - u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - struct vmcb *vmcb12; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; - if (guest) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return 1; + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + return 0; - if (!(saved_efer & EFER_SVME)) - return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; - if (kvm_vcpu_map(vcpu, - gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) - return 1; + saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + if (!(saved_efer & EFER_SVME)) + return 1; - if (svm_allocate_nested(svm)) - return 1; + vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + return 1; - kvm_vcpu_unmap(vcpu, &map, true); + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + goto unmap_map; - /* - * Restore L1 host state from L1 HSAVE area as VMCB01 was - * used during SMM (see svm_enter_smm()) - */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) - return 1; + if (svm_allocate_nested(svm)) + goto unmap_save; - svm_copy_vmrun_state(&svm->vmcb01.ptr->save, - map_save.hva + 0x400); + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ - /* - * Enter the nested guest now - */ - vmcb12 = map.hva; - nested_load_control_from_vmcb12(svm, &vmcb12->control); - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); - kvm_vcpu_unmap(vcpu, &map_save, true); - } - } + /* + * Enter the nested guest now + */ + vmcb12 = map.hva; + nested_load_control_from_vmcb12(svm, &vmcb12->control); + ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + +unmap_save: + kvm_vcpu_unmap(vcpu, &map_save, true); +unmap_map: + kvm_vcpu_unmap(vcpu, &map, true); return ret; } From c42dec148b3e1a88835e275b675e5155f99abd43 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:52 +0300 Subject: [PATCH 596/866] KVM: x86: VMX: synthesize invalid VM exit when emulating invalid guest state Since no actual VM entry happened, the VM exit information is stale. To avoid this, synthesize an invalid VM guest state VM exit. Suggested-by: Sean Christopherson Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-6-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f7eb0ce0ddb5..1c2296fa7f2b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6622,10 +6622,21 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->soft_vnmi_blocked)) vmx->loaded_vmcs->entry_time = ktime_get(); - /* Don't enter VMX if guest state is invalid, let the exit handler - start emulation until we arrive back to a valid state */ - if (vmx->emulation_required) + /* + * Don't enter VMX if guest state is invalid, let the exit handler + * start emulation until we arrive back to a valid state. Synthesize a + * consistency check VM-Exit due to invalid guest state and bail. + */ + if (unlikely(vmx->emulation_required)) { + vmx->fail = 0; + vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; + vmx->exit_reason.failed_vmentry = 1; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + vmx->exit_qualification = ENTRY_FAIL_DEFAULT; + kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + vmx->exit_intr_info = 0; return EXIT_FASTPATH_NONE; + } trace_kvm_entry(vcpu); From c8607e4a086fae05efe5bffb47c5199c65e7216e Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:53 +0300 Subject: [PATCH 597/866] KVM: x86: nVMX: don't fail nested VM entry on invalid guest state if !from_vmentry It is possible that when non root mode is entered via special entry (!from_vmentry), that is from SMM or from loading the nested state, the L2 state could be invalid in regard to non unrestricted guest mode, but later it can become valid. (for example when RSM emulation restores segment registers from SMRAM) Thus delay the check to VM entry, where we will check this and fail. Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-7-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 7 ++++++- arch/x86/kvm/vmx/vmx.c | 5 ++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bc9c9cc228ea..b89c78e952b7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Guest state is invalid and unrestricted guest is disabled, * which means L1 attempted VMEntry to L2 with invalid state. * Fail the VMEntry. + * + * However when force loading the guest state (SMM exit or + * loading nested state after migration, it is possible to + * have invalid guest state now, which will be later fixed by + * restoring L2 register state */ - if (CC(!vmx_guest_state_valid(vcpu))) { + if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1c2296fa7f2b..7df6f4b8931f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6628,7 +6628,10 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * consistency check VM-Exit due to invalid guest state and bail. */ if (unlikely(vmx->emulation_required)) { - vmx->fail = 0; + + /* We don't emulate invalid state of a nested guest */ + vmx->fail = is_guest_mode(vcpu); + vmx->exit_reason.full = EXIT_REASON_INVALID_STATE; vmx->exit_reason.failed_vmentry = 1; kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); From dbab610a5be69c2c5e4fdd7135d14b6bab2667a5 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 13 Sep 2021 17:09:54 +0300 Subject: [PATCH 598/866] KVM: x86: nVMX: re-evaluate emulation_required on nested VM exit If L1 had invalid state on VM entry (can happen on SMM transactions when we enter from real mode, straight to nested guest), then after we load 'host' state from VMCS12, the state has to become valid again, but since we load the segment registers with __vmx_set_segment we weren't always updating emulation_required. Update emulation_required explicitly at end of load_vmcs12_host_state. Signed-off-by: Maxim Levitsky Message-Id: <20210913140954.165665-8-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 2 ++ arch/x86/kvm/vmx/vmx.c | 8 ++++---- arch/x86/kvm/vmx/vmx.h | 1 + 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b89c78e952b7..eedcebf58004 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4356,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL); + + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7df6f4b8931f..9ecfcf13a046 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) vmx_prepare_switch_to_host(to_vmx(vcpu)); } -static bool emulation_required(struct kvm_vcpu *vcpu) +bool vmx_emulation_required(struct kvm_vcpu *vcpu) { return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu); } @@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) vmcs_writel(GUEST_RFLAGS, rflags); if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM) - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) @@ -3078,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } /* depends on vcpu->arch.cr0 to be set to a new value */ - vmx->emulation_required = emulation_required(vcpu); + vmx->emulation_required = vmx_emulation_required(vcpu); } static int vmx_get_max_tdp_level(void) @@ -3331,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int { __vmx_set_segment(vcpu, var, seg); - to_vmx(vcpu)->emulation_required = emulation_required(vcpu); + to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu); } static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 02ab3468885f..592217fd7d92 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -355,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); +bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu); From e1fc1553cd78292ab3521c94c9dd6e3e70e606a1 Mon Sep 17 00:00:00 2001 From: Fares Mehanna Date: Wed, 15 Sep 2021 13:39:50 +0000 Subject: [PATCH 599/866] kvm: x86: Add AMD PMU MSRs to msrs_to_save_all[] Intel PMU MSRs is in msrs_to_save_all[], so add AMD PMU MSRs to have a consistent behavior between Intel and AMD when using KVM_GET_MSRS, KVM_SET_MSRS or KVM_GET_MSR_INDEX_LIST. We have to add legacy and new MSRs to handle guests running without X86_FEATURE_PERFCTR_CORE. Signed-off-by: Fares Mehanna Message-Id: <20210915133951.22389-1-faresx@amazon.de> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ba70e8f11f2c..aabd3a2ec1bc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, }; static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; From 7df835a32a8bedf7ce88efcfa7c9b245b52ff139 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Sep 2021 13:38:29 +0200 Subject: [PATCH 600/866] md: fix a lock order reversal in md_alloc Commit b0140891a8cea3 ("md: Fix race when creating a new md device.") not only moved assigning mddev->gendisk before calling add_disk, which fixes the races described in the commit log, but also added a mddev->open_mutex critical section over add_disk and creation of the md kobj. Adding a kobject after add_disk is racy vs deleting the gendisk right after adding it, but md already prevents against that by holding a mddev->active reference. On the other hand taking this lock added a lock order reversal with what is not disk->open_mutex (used to be bdev->bd_mutex when the commit was added) for partition devices, which need that lock for the internal open for the partition scan, and a recent commit also takes it for non-partitioned devices, leading to further lockdep splatter. Fixes: b0140891a8ce ("md: Fix race when creating a new md device.") Fixes: d62633873590 ("block: support delayed holder registration") Reported-by: syzbot+fadc0aaf497e6a493b9f@syzkaller.appspotmail.com Signed-off-by: Christoph Hellwig Tested-by: syzbot+fadc0aaf497e6a493b9f@syzkaller.appspotmail.com Reviewed-by: NeilBrown Signed-off-by: Song Liu --- drivers/md/md.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index ae8fe54ea358..6c0c3d0d905a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5700,10 +5700,6 @@ static int md_alloc(dev_t dev, char *name) disk->flags |= GENHD_FL_EXT_DEVT; disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; - /* As soon as we call add_disk(), another thread could get - * through to md_open, so make sure it doesn't get too far - */ - mutex_lock(&mddev->open_mutex); add_disk(disk); error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md"); @@ -5718,7 +5714,6 @@ static int md_alloc(dev_t dev, char *name) if (mddev->kobj.sd && sysfs_create_group(&mddev->kobj, &md_bitmap_group)) pr_debug("pointless warning\n"); - mutex_unlock(&mddev->open_mutex); abort: mutex_unlock(&disks_mutex); if (!error && mddev->kobj.sd) { From 8f1b7ba55c61d2c9f3a47a4759db43abfb59fc16 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 22 Sep 2021 08:35:58 +0200 Subject: [PATCH 601/866] MAINTAINERS: ARM/VT8500, remove defunct e-mail linux@prisktech.co.nz is defunct: 4.1.2 : Recipient address rejected: Domain not found Remove it from MAINTAINERS and mark the ARM/VT8500 entry orphan. Signed-off-by: Jiri Slaby Signed-off-by: Linus Torvalds --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index ca6d6fde85cf..0227e15e2484 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2804,9 +2804,8 @@ F: arch/arm/mach-pxa/include/mach/vpac270.h F: arch/arm/mach-pxa/vpac270.c ARM/VT8500 ARM ARCHITECTURE -M: Tony Prisk L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/i2c/i2c-wmt.txt F: arch/arm/mach-vt8500/ F: drivers/clocksource/timer-vt8500.c From bc0bdc5afaa740d782fbf936aaeebd65e5c2921d Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 15 Sep 2021 17:21:43 -0300 Subject: [PATCH 602/866] RDMA/cma: Do not change route.addr.src_addr.ss_family If the state is not idle then rdma_bind_addr() will immediately fail and no change to global state should happen. For instance if the state is already RDMA_CM_LISTEN then this will corrupt the src_addr and would cause the test in cma_cancel_operation(): if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) To view a mangled src_addr, eg with a IPv6 loopback address but an IPv4 family, failing the test. This would manifest as this trace from syzkaller: BUG: KASAN: use-after-free in __list_add_valid+0x93/0xa0 lib/list_debug.c:26 Read of size 8 at addr ffff8881546491e0 by task syz-executor.1/32204 CPU: 1 PID: 32204 Comm: syz-executor.1 Not tainted 5.12.0-rc8-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:232 __kasan_report mm/kasan/report.c:399 [inline] kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416 __list_add_valid+0x93/0xa0 lib/list_debug.c:26 __list_add include/linux/list.h:67 [inline] list_add_tail include/linux/list.h:100 [inline] cma_listen_on_all drivers/infiniband/core/cma.c:2557 [inline] rdma_listen+0x787/0xe00 drivers/infiniband/core/cma.c:3751 ucma_listen+0x16a/0x210 drivers/infiniband/core/ucma.c:1102 ucma_write+0x259/0x350 drivers/infiniband/core/ucma.c:1732 vfs_write+0x28e/0xa30 fs/read_write.c:603 ksys_write+0x1ee/0x250 fs/read_write.c:658 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae Which is indicating that an rdma_id_private was destroyed without doing cma_cancel_listens(). Instead of trying to re-use the src_addr memory to indirectly create an any address build one explicitly on the stack and bind to that as any other normal flow would do. Link: https://lore.kernel.org/r/0-v1-9fbb33f5e201+2a-cma_listen_jgg@nvidia.com Cc: stable@vger.kernel.org Fixes: 732d41c545bb ("RDMA/cma: Make the locking for automatic state transition more clear") Reported-by: syzbot+6bb0528b13611047209c@syzkaller.appspotmail.com Tested-by: Hao Sun Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 5aa58897965d..8862b0e572f0 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3783,9 +3783,13 @@ int rdma_listen(struct rdma_cm_id *id, int backlog) int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { + struct sockaddr_in any_in = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + }; + /* For a well behaved ULP state will be RDMA_CM_IDLE */ - id->route.addr.src_addr.ss_family = AF_INET; - ret = rdma_bind_addr(id, cma_src_addr(id_priv)); + ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, From d81ff5fe14a950f53e2833cfa196e7bb3fd5d4e3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 10 Sep 2021 15:33:32 -0700 Subject: [PATCH 603/866] x86/asm: Fix SETZ size enqcmds() build failure When building under GCC 4.9 and 5.5: arch/x86/include/asm/special_insns.h: Assembler messages: arch/x86/include/asm/special_insns.h:286: Error: operand size mismatch for `setz' Change the type to "bool" for condition code arguments, as documented. Fixes: 7f5933f81bd8 ("x86/asm: Add an enqcmds() wrapper for the ENQCMDS instruction") Co-developed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Signed-off-by: Kees Cook Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210910223332.3224851-1-keescook@chromium.org --- arch/x86/include/asm/special_insns.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index f3fbb84ff8a7..68c257a3de0d 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -275,7 +275,7 @@ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; - int zf; + bool zf; /* * ENQCMDS %(rdx), rax From 80f6e3080bfcf865062a926817b3ca6c4a137a57 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 16 Sep 2021 13:34:24 -0700 Subject: [PATCH 604/866] fs-verity: fix signed integer overflow with i_size near S64_MAX If the file size is almost S64_MAX, the calculated number of Merkle tree levels exceeds FS_VERITY_MAX_LEVELS, causing FS_IOC_ENABLE_VERITY to fail. This is unintentional, since as the comment above the definition of FS_VERITY_MAX_LEVELS states, it is enough for over U64_MAX bytes of data using SHA-256 and 4K blocks. (Specifically, 4096*128**8 >= 2**64.) The bug is actually that when the number of blocks in the first level is calculated from i_size, there is a signed integer overflow due to i_size being signed. Fix this by treating i_size as unsigned. This was found by the new test "generic: test fs-verity EFBIG scenarios" (https://lkml.kernel.org/r/b1d116cd4d0ea74b9cd86f349c672021e005a75c.1631558495.git.boris@bur.io). This didn't affect ext4 or f2fs since those have a smaller maximum file size, but it did affect btrfs which allows files up to S64_MAX bytes. Reported-by: Boris Burkov Fixes: 3fda4c617e84 ("fs-verity: implement FS_IOC_ENABLE_VERITY ioctl") Fixes: fd2d1acfcadf ("fs-verity: add the hook for file ->open()") Cc: # v5.4+ Reviewed-by: Boris Burkov Link: https://lore.kernel.org/r/20210916203424.113376-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/verity/enable.c | 2 +- fs/verity/open.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/verity/enable.c b/fs/verity/enable.c index 77e159a0346b..60a4372aa4d7 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -177,7 +177,7 @@ static int build_merkle_tree(struct file *filp, * (level 0) and ascending to the root node (level 'num_levels - 1'). * Then at the end (level 'num_levels'), calculate the root hash. */ - blocks = (inode->i_size + params->block_size - 1) >> + blocks = ((u64)inode->i_size + params->block_size - 1) >> params->log_blocksize; for (level = 0; level <= params->num_levels; level++) { err = build_merkle_tree_level(filp, level, blocks, params, diff --git a/fs/verity/open.c b/fs/verity/open.c index 60ff8af7219f..92df87f5fa38 100644 --- a/fs/verity/open.c +++ b/fs/verity/open.c @@ -89,7 +89,7 @@ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, */ /* Compute number of levels and the number of blocks in each level */ - blocks = (inode->i_size + params->block_size - 1) >> log_blocksize; + blocks = ((u64)inode->i_size + params->block_size - 1) >> log_blocksize; pr_debug("Data is %lld bytes (%llu blocks)\n", inode->i_size, blocks); while (blocks > 1) { if (params->num_levels >= FS_VERITY_MAX_LEVELS) { From c4aa1eeb093b09fbae9329a080172c58ace8da8c Mon Sep 17 00:00:00 2001 From: Dinh Nguyen Date: Wed, 22 Sep 2021 14:30:01 -0500 Subject: [PATCH 605/866] MAINTAINERS: update entry for NIOS2 Ley Foon has left Intel and will no longer be able to maintain NIOS2. Update the MAINTAINER's entry to Dinh Nguyen. Acked-by: Ley Foon Tan Signed-off-by: Dinh Nguyen Signed-off-by: Linus Torvalds --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0227e15e2484..4806d2156a80 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13254,9 +13254,9 @@ F: Documentation/scsi/NinjaSCSI.rst F: drivers/scsi/nsp32* NIOS2 ARCHITECTURE -M: Ley Foon Tan +M: Dinh Nguyen S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/lftan/nios2.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git F: arch/nios2/ NITRO ENCLAVES (NE) From 2e36a964ada4f7bda24f3caa971a33500e23af36 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Sep 2021 12:16:51 -0400 Subject: [PATCH 606/866] MAINTAINERS: Update SWIOTLB maintainership Konrad's new job role is putting a serious cramp on him being a responsive maintainer and as such he is handing off the reins to Christoph Hellwig. Thank you! Acked-by: Christoph Hellwig Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Linus Torvalds --- MAINTAINERS | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4806d2156a80..a8a1b1c283e2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17968,10 +17968,11 @@ F: Documentation/admin-guide/svga.rst F: arch/x86/boot/video* SWIOTLB SUBSYSTEM -M: Konrad Rzeszutek Wilk +M: Christoph Hellwig L: iommu@lists.linux-foundation.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb.git +W: http://git.infradead.org/users/hch/dma-mapping.git +T: git git://git.infradead.org/users/hch/dma-mapping.git F: arch/*/kernel/pci-swiotlb.c F: include/linux/swiotlb.h F: kernel/dma/swiotlb.c From 4057525736b159bd456732d11270af2cc49ec21f Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Sep 2021 12:16:52 -0400 Subject: [PATCH 607/866] MAINTAINERS: Update Xen-[PCI,SWIOTLB,Block] maintainership MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Konrad's new job role is putting a serious cramp on him being a responsive maintainer and as such he is handing off the reins to Juergen, Roger, and Stefano. Thank you! Acked-by: Juergen Gross Acked-by: Roger Pau Monné Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Linus Torvalds --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index a8a1b1c283e2..2e75360c7b8b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20475,7 +20475,6 @@ F: samples/bpf/xdpsock* F: tools/lib/bpf/xsk* XEN BLOCK SUBSYSTEM -M: Konrad Rzeszutek Wilk M: Roger Pau Monné L: xen-devel@lists.xenproject.org (moderated for non-subscribers) S: Supported @@ -20523,7 +20522,7 @@ S: Supported F: drivers/net/xen-netback/* XEN PCI SUBSYSTEM -M: Konrad Rzeszutek Wilk +M: Juergen Gross L: xen-devel@lists.xenproject.org (moderated for non-subscribers) S: Supported F: arch/x86/pci/*xen* @@ -20546,7 +20545,8 @@ S: Supported F: sound/xen/* XEN SWIOTLB SUBSYSTEM -M: Konrad Rzeszutek Wilk +M: Juergen Gross +M: Stefano Stabellini L: xen-devel@lists.xenproject.org (moderated for non-subscribers) L: iommu@lists.linux-foundation.org S: Supported From 58e2cf5d794616b84f591d4d1276c8953278ce24 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 1 Sep 2021 09:09:28 +0200 Subject: [PATCH 608/866] init: Revert accidental changes to print irqs_disabled() Commit f8ade8dddb16 ("xsurf100: drop include of lib8390.c") accidentally changed init/main.c. Revert that part. Fixes: f8ade8dddb16 ("xsurf100: drop include of lib8390.c") Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- init/main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/init/main.c b/init/main.c index 3f7216934441..81a79a77db46 100644 --- a/init/main.c +++ b/init/main.c @@ -1242,7 +1242,7 @@ trace_initcall_start_cb(void *data, initcall_t fn) { ktime_t *calltime = (ktime_t *)data; - printk(KERN_DEBUG "calling %pS @ %i irqs_disabled() %d\n", fn, task_pid_nr(current), irqs_disabled()); + printk(KERN_DEBUG "calling %pS @ %i\n", fn, task_pid_nr(current)); *calltime = ktime_get(); } @@ -1256,8 +1256,8 @@ trace_initcall_finish_cb(void *data, initcall_t fn, int ret) rettime = ktime_get(); delta = ktime_sub(rettime, *calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; - printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs, irqs_disabled() %d\n", - fn, ret, duration, irqs_disabled()); + printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n", + fn, ret, duration); } static ktime_t initcall_calltime; From 18a015bccf9e8927008d0a255c9f14b8ec15a648 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 22 Sep 2021 21:00:57 +0900 Subject: [PATCH 609/866] ksmbd: check protocol id in ksmbd_verify_smb_message() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When second smb2 pdu has invalid protocol id, ksmbd doesn't detect it and allow to process smb2 request. This patch add the check it in ksmbd_verify_smb_message() and don't use protocol id of smb2 request as protocol id of response. Reviewed-by: Ronnie Sahlberg Reviewed-by: Ralph Böhme Reported-by: Ronnie Sahlberg Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 2 +- fs/ksmbd/smb_common.c | 13 +++++++++---- fs/ksmbd/smb_common.h | 1 + 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index f59f9b8be51c..fd9d5595a5ca 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -433,7 +433,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) work->compound_pfid = KSMBD_NO_FID; } memset((char *)rsp_hdr + 4, 0, sizeof(struct smb2_hdr) + 2); - rsp_hdr->ProtocolId = rcv_hdr->ProtocolId; + rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; rsp_hdr->Command = rcv_hdr->Command; diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 43d3123d8b62..40f4fafa2e11 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -129,16 +129,22 @@ int ksmbd_lookup_protocol_idx(char *str) * * check for valid smb signature and packet direction(request/response) * - * Return: 0 on success, otherwise 1 + * Return: 0 on success, otherwise -EINVAL */ int ksmbd_verify_smb_message(struct ksmbd_work *work) { - struct smb2_hdr *smb2_hdr = work->request_buf; + struct smb2_hdr *smb2_hdr = work->request_buf + work->next_smb2_rcv_hdr_off; + struct smb_hdr *hdr; if (smb2_hdr->ProtocolId == SMB2_PROTO_NUMBER) return ksmbd_smb2_check_message(work); - return 0; + hdr = work->request_buf; + if (*(__le32 *)hdr->Protocol == SMB1_PROTO_NUMBER && + hdr->Command == SMB_COM_NEGOTIATE) + return 0; + + return -EINVAL; } /** @@ -265,7 +271,6 @@ static int ksmbd_negotiate_smb_dialect(void *buf) return BAD_PROT_ID; } -#define SMB_COM_NEGOTIATE 0x72 int ksmbd_init_smb_server(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 57c667c1be06..0a6af447cc45 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -210,6 +210,7 @@ FILE_READ_ATTRIBUTES | FILE_WRITE_ATTRIBUTES) #define SMB1_PROTO_NUMBER cpu_to_le32(0x424d53ff) +#define SMB_COM_NEGOTIATE 0x72 #define SMB1_CLIENT_GUID_SIZE (16) struct smb_hdr { From 4ea477988c423a57241ea4840b12832de6fabdfd Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 21 Sep 2021 14:19:33 +0900 Subject: [PATCH 610/866] ksmbd: remove follow symlinks support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use LOOKUP_NO_SYMLINKS flags for default lookup to prohibit the middle of symlink component lookup and remove follow symlinks parameter support. We re-implement it as reparse point later. Test result: smbclient -Ulinkinjeon%1234 //172.30.1.42/share -c "get hacked/passwd passwd" NT_STATUS_OBJECT_NAME_NOT_FOUND opening remote file \hacked\passwd Cc: Ralph Böhme Cc: Steve French Acked-by: Ronnie Sahlberg Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 43 ++++++++++--------------------------------- fs/ksmbd/vfs.c | 32 +++++++++----------------------- 2 files changed, 19 insertions(+), 56 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index fd9d5595a5ca..0c49a0e887d3 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2632,13 +2632,9 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { - /* - * On delete request, instead of following up, need to - * look the current entity - */ - rc = ksmbd_vfs_kern_path(name, 0, &path, 1); - if (!rc) { + rc = ksmbd_vfs_kern_path(name, LOOKUP_NO_SYMLINKS, &path, 1); + if (!rc) { + if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { /* * If file exists with under flags, return access * denied error. @@ -2657,25 +2653,10 @@ int smb2_open(struct ksmbd_work *work) path_put(&path); goto err_out; } - } - } else { - if (test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS)) { - /* - * Use LOOKUP_FOLLOW to follow the path of - * symlink in path buildup - */ - rc = ksmbd_vfs_kern_path(name, LOOKUP_FOLLOW, &path, 1); - if (rc) { /* Case for broken link ?*/ - rc = ksmbd_vfs_kern_path(name, 0, &path, 1); - } - } else { - rc = ksmbd_vfs_kern_path(name, 0, &path, 1); - if (!rc && d_is_symlink(path.dentry)) { - rc = -EACCES; - path_put(&path); - goto err_out; - } + } else if (d_is_symlink(path.dentry)) { + rc = -EACCES; + path_put(&path); + goto err_out; } } @@ -4751,12 +4732,8 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, struct path path; int rc = 0, len; int fs_infoclass_size = 0; - int lookup_flags = 0; - if (test_share_config_flag(share, KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS)) - lookup_flags = LOOKUP_FOLLOW; - - rc = ksmbd_vfs_kern_path(share->path, lookup_flags, &path, 0); + rc = ksmbd_vfs_kern_path(share->path, LOOKUP_NO_SYMLINKS, &path, 0); if (rc) { pr_err("cannot create vfs path\n"); return -EIO; @@ -5333,7 +5310,7 @@ static int smb2_rename(struct ksmbd_work *work, } ksmbd_debug(SMB, "new name %s\n", new_name); - rc = ksmbd_vfs_kern_path(new_name, 0, &path, 1); + rc = ksmbd_vfs_kern_path(new_name, LOOKUP_NO_SYMLINKS, &path, 1); if (rc) file_present = false; else @@ -5407,7 +5384,7 @@ static int smb2_create_link(struct ksmbd_work *work, } ksmbd_debug(SMB, "target name is %s\n", target_name); - rc = ksmbd_vfs_kern_path(link_name, 0, &path, 0); + rc = ksmbd_vfs_kern_path(link_name, LOOKUP_NO_SYMLINKS, &path, 0); if (rc) file_present = false; else diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index b047f2980d96..3733e4944c1d 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -166,7 +166,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) struct dentry *dentry; int err; - dentry = kern_path_create(AT_FDCWD, name, &path, 0); + dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_NO_SYMLINKS); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); if (err != -ENOENT) @@ -203,7 +203,8 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) struct dentry *dentry; int err; - dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY); + dentry = kern_path_create(AT_FDCWD, name, &path, + LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); if (err != -EEXIST) @@ -588,16 +589,11 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) struct path path; struct dentry *parent; int err; - int flags = 0; if (ksmbd_override_fsids(work)) return -ENOMEM; - if (test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS)) - flags = LOOKUP_FOLLOW; - - err = kern_path(name, flags, &path); + err = kern_path(name, LOOKUP_NO_SYMLINKS, &path); if (err) { ksmbd_debug(VFS, "can't get %s, err %d\n", name, err); ksmbd_revert_fsids(work); @@ -652,16 +648,11 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, struct path oldpath, newpath; struct dentry *dentry; int err; - int flags = 0; if (ksmbd_override_fsids(work)) return -ENOMEM; - if (test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS)) - flags = LOOKUP_FOLLOW; - - err = kern_path(oldname, flags, &oldpath); + err = kern_path(oldname, LOOKUP_NO_SYMLINKS, &oldpath); if (err) { pr_err("cannot get linux path for %s, err = %d\n", oldname, err); @@ -669,7 +660,7 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, } dentry = kern_path_create(AT_FDCWD, newname, &newpath, - flags | LOOKUP_REVAL); + LOOKUP_NO_SYMLINKS | LOOKUP_REVAL); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); pr_err("path create err for %s, err %d\n", newname, err); @@ -788,7 +779,6 @@ int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, struct dentry *src_dent, *trap_dent, *src_child; char *dst_name; int err; - int flags; dst_name = extract_last_component(newname); if (!dst_name) @@ -797,12 +787,8 @@ int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, src_dent_parent = dget_parent(fp->filp->f_path.dentry); src_dent = fp->filp->f_path.dentry; - flags = LOOKUP_DIRECTORY; - if (test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS)) - flags |= LOOKUP_FOLLOW; - - err = kern_path(newname, flags, &dst_path); + err = kern_path(newname, LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, + &dst_path); if (err) { ksmbd_debug(VFS, "Cannot get path for %s [%d]\n", newname, err); goto out; @@ -861,7 +847,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, const char *name, int err = 0; if (name) { - err = kern_path(name, 0, &path); + err = kern_path(name, LOOKUP_NO_SYMLINKS, &path); if (err) { pr_err("cannot get linux path for %s, err %d\n", name, err); From 09d23174402da0f10e98da2c61bb5ac8e7d79fdd Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Mon, 20 Sep 2021 19:18:50 +0200 Subject: [PATCH 611/866] ALSA: rawmidi: introduce SNDRV_RAWMIDI_IOCTL_USER_PVERSION The new framing mode causes the user space regression, because the alsa-lib code does not initialize the reserved space in the params structure when the device is opened. This change adds SNDRV_RAWMIDI_IOCTL_USER_PVERSION like we do for the PCM interface for the protocol acknowledgment. Cc: David Henningsson Cc: Fixes: 08fdced60ca0 ("ALSA: rawmidi: Add framing mode") BugLink: https://github.com/alsa-project/alsa-lib/issues/178 Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20210920171850.154186-1-perex@perex.cz Signed-off-by: Takashi Iwai --- include/sound/rawmidi.h | 1 + include/uapi/sound/asound.h | 1 + sound/core/rawmidi.c | 9 +++++++++ 3 files changed, 11 insertions(+) diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 989e1517332d..7a08ed2acd60 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -98,6 +98,7 @@ struct snd_rawmidi_file { struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *input; struct snd_rawmidi_substream *output; + unsigned int user_pversion; /* supported protocol version */ }; struct snd_rawmidi_str { diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6c0a4a67ad2e..6f30231bdb88 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -873,12 +873,21 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long return -EINVAL; } } + case SNDRV_RAWMIDI_IOCTL_USER_PVERSION: + if (get_user(rfile->user_pversion, (unsigned int __user *)arg)) + return -EFAULT; + return 0; + case SNDRV_RAWMIDI_IOCTL_PARAMS: { struct snd_rawmidi_params params; if (copy_from_user(¶ms, argp, sizeof(struct snd_rawmidi_params))) return -EFAULT; + if (rfile->user_pversion < SNDRV_PROTOCOL_VERSION(2, 0, 2)) { + params.mode = 0; + memset(params.reserved, 0, sizeof(params.reserved)); + } switch (params.stream) { case SNDRV_RAWMIDI_STREAM_OUTPUT: if (rfile->output == NULL) From c32dfec6c1c36bbbcd5d33e949d99aeb215877ec Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 22 Sep 2021 13:30:59 +0200 Subject: [PATCH 612/866] USB: serial: cp210x: fix dropped characters with CP2102 Some CP2102 do not support event-insertion mode but return no error when attempting to enable it. This means that any event escape characters in the input stream will not be escaped by the device and consequently regular data may be interpreted as escape sequences and be removed from the stream by the driver. The reporter's device has batch number DCL00X etched into it and as discovered by the SHA2017 Badge team, counterfeit devices with that marking can be detected by sending malformed vendor requests. [1][2] Tests confirm that the possibly counterfeit CP2102 returns a single byte in response to a malformed two-byte part-number request, while an original CP2102 returns two bytes. Assume that every CP2102 that behaves this way also does not support event-insertion mode (e.g. cannot report parity errors). [1] https://mobile.twitter.com/sha2017badge/status/1167902087289532418 [2] https://hackaday.com/2017/08/14/hands-on-with-the-shacamp-2017-badge/#comment-3903376 Reported-by: Malte Di Donato Tested-by: Malte Di Donato Fixes: a7207e9835a4 ("USB: serial: cp210x: add support for line-status events") Cc: stable@vger.kernel.org # 5.9 Link: https://lore.kernel.org/r/20210922113100.20888-1-johan@kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 66a6ac50a4cd..b98454fe08ea 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -258,6 +258,7 @@ struct cp210x_serial_private { speed_t max_speed; bool use_actual_rate; bool no_flow_control; + bool no_event_mode; }; enum cp210x_event_state { @@ -1113,12 +1114,16 @@ static void cp210x_change_speed(struct tty_struct *tty, static void cp210x_enable_event_mode(struct usb_serial_port *port) { + struct cp210x_serial_private *priv = usb_get_serial_data(port->serial); struct cp210x_port_private *port_priv = usb_get_serial_port_data(port); int ret; if (port_priv->event_mode) return; + if (priv->no_event_mode) + return; + port_priv->event_state = ES_DATA; port_priv->event_mode = true; @@ -2074,6 +2079,33 @@ static void cp210x_init_max_speed(struct usb_serial *serial) priv->use_actual_rate = use_actual_rate; } +static void cp2102_determine_quirks(struct usb_serial *serial) +{ + struct cp210x_serial_private *priv = usb_get_serial_data(serial); + u8 *buf; + int ret; + + buf = kmalloc(2, GFP_KERNEL); + if (!buf) + return; + /* + * Some (possibly counterfeit) CP2102 do not support event-insertion + * mode and respond differently to malformed vendor requests. + * Specifically, they return one instead of two bytes when sent a + * two-byte part-number request. + */ + ret = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0), + CP210X_VENDOR_SPECIFIC, REQTYPE_DEVICE_TO_HOST, + CP210X_GET_PARTNUM, 0, buf, 2, USB_CTRL_GET_TIMEOUT); + if (ret == 1) { + dev_dbg(&serial->interface->dev, + "device does not support event-insertion mode\n"); + priv->no_event_mode = true; + } + + kfree(buf); +} + static int cp210x_get_fw_version(struct usb_serial *serial, u16 value) { struct cp210x_serial_private *priv = usb_get_serial_data(serial); @@ -2109,6 +2141,9 @@ static void cp210x_determine_type(struct usb_serial *serial) } switch (priv->partnum) { + case CP210X_PARTNUM_CP2102: + cp2102_determine_quirks(serial); + break; case CP210X_PARTNUM_CP2105: case CP210X_PARTNUM_CP2108: cp210x_get_fw_version(serial, CP210X_GET_FW_VER); From 90ca6e7db83a06e9173bee5bb34ded3b37f4948d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 22 Sep 2021 13:31:00 +0200 Subject: [PATCH 613/866] USB: serial: cp210x: add part-number debug printk Add a part-number debug printk to facilitate debugging. Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index b98454fe08ea..fd51498ab108 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -2140,6 +2140,8 @@ static void cp210x_determine_type(struct usb_serial *serial) return; } + dev_dbg(&serial->interface->dev, "partnum = 0x%02x\n", priv->partnum); + switch (priv->partnum) { case CP210X_PARTNUM_CP2102: cp2102_determine_quirks(serial); From 8cd9da85d2bd87ce889043e7b1735723dd10eb89 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 13 Sep 2021 16:53:32 +0200 Subject: [PATCH 614/866] posix-cpu-timers: Prevent spuriously armed 0-value itimer Resetting/stopping an itimer eventually leads to it being reprogrammed with an actual "0" value. As a result the itimer expires on the next tick, triggering an unexpected signal. To fix this, make sure that struct signal_struct::it[CPUCLOCK_PROF/VIRT]::expires is set to 0 when setitimer() passes a 0 it_value, indicating that the timer must stop. Fixes: 406dd42bd1ba ("posix-cpu-timers: Force next expiration recalc after itimer reset") Reported-by: Victor Stinner Reported-by: Chris Hixon Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210913145332.232023-1-frederic@kernel.org --- kernel/time/posix-cpu-timers.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ee736861b18f..643d412ac623 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1404,7 +1404,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, } } - *newval += now; + if (*newval) + *newval += now; } /* From 98d46b021f6ee246c7a73f9d490d4cddb4511a3b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 6 Sep 2021 10:35:59 +0200 Subject: [PATCH 615/866] Revert "mac80211: do not use low data rates for data frames with no ack flag" This reverts commit d333322361e7 ("mac80211: do not use low data rates for data frames with no ack flag"). Returning false early in rate_control_send_low breaks sending broadcast packets, since rate control will not select a rate for it. Before re-introducing a fixed version of this patch, we should probably also make some changes to rate control to be more conservative in selecting rates for no-ack packets and also prevent using probing rates on them, since we won't get any feedback. Fixes: d333322361e7 ("mac80211: do not use low data rates for data frames with no ack flag") Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20210906083559.9109-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/rate.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index e5935e3d7a07..8c6416129d5b 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -392,10 +392,6 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, int mcast_rate; bool use_basicrate = false; - if (ieee80211_is_tx_data(txrc->skb) && - info->flags & IEEE80211_TX_CTL_NO_ACK) - return false; - if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); From fe94bac626d9c1c5bc98ab32707be8a9d7f8adba Mon Sep 17 00:00:00 2001 From: Chih-Kang Chang Date: Mon, 30 Aug 2021 15:32:40 +0800 Subject: [PATCH 616/866] mac80211: Fix ieee80211_amsdu_aggregate frag_tail bug In ieee80211_amsdu_aggregate() set a pointer frag_tail point to the end of skb_shinfo(head)->frag_list, and use it to bind other skb in the end of this function. But when execute ieee80211_amsdu_aggregate() ->ieee80211_amsdu_realloc_pad()->pskb_expand_head(), the address of skb_shinfo(head)->frag_list will be changed. However, the ieee80211_amsdu_aggregate() not update frag_tail after call pskb_expand_head(). That will cause the second skb can't bind to the head skb appropriately.So we update the address of frag_tail to fix it. Fixes: 6e0456b54545 ("mac80211: add A-MSDU tx support") Signed-off-by: Chih-Kang Chang Signed-off-by: Zong-Zhe Yang Signed-off-by: Ping-Ke Shih Link: https://lore.kernel.org/r/20210830073240.12736-1-pkshih@realtek.com [reword comment] Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2d1193ed3eb5..824bed71be13 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3380,6 +3380,14 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* If n == 2, the "while (*frag_tail)" loop above didn't execute + * and frag_tail should be &skb_shinfo(head)->frag_list. + * However, ieee80211_amsdu_prepare_head() can reallocate it. + * Reload frag_tail to have it pointing to the correct place. + */ + if (n == 2) + frag_tail = &skb_shinfo(head)->frag_list; + /* * Pad out the previous subframe to a multiple of 4 by adding the * padding to the next one, that's being added. Note that head->len From a6555f844549cd190eb060daef595f94d3de1582 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 27 Aug 2021 22:42:30 +0800 Subject: [PATCH 617/866] mac80211: Drop frames from invalid MAC address in ad-hoc mode WARNING: CPU: 1 PID: 9 at net/mac80211/sta_info.c:554 sta_info_insert_rcu+0x121/0x12a0 Modules linked in: CPU: 1 PID: 9 Comm: kworker/u8:1 Not tainted 5.14.0-rc7+ #253 Workqueue: phy3 ieee80211_iface_work RIP: 0010:sta_info_insert_rcu+0x121/0x12a0 ... Call Trace: ieee80211_ibss_finish_sta+0xbc/0x170 ieee80211_ibss_work+0x13f/0x7d0 ieee80211_iface_work+0x37a/0x500 process_one_work+0x357/0x850 worker_thread+0x41/0x4d0 If an Ad-Hoc node receives packets with invalid source MAC address, it hits a WARN_ON in sta_info_insert_check(), this can spam the log. Signed-off-by: YueHaibing Link: https://lore.kernel.org/r/20210827144230.39944-1-yuehaibing@huawei.com Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 99ed68f7dc36..c4071b015c18 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4131,7 +4131,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) if (!bssid) return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || - ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2) || + !is_valid_ether_addr(hdr->addr2)) return false; if (ieee80211_is_beacon(hdr->frame_control)) return true; From 13cb6d826e0ac0d144b0d48191ff1a111d32f0c6 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 20 Sep 2021 14:45:22 +0200 Subject: [PATCH 618/866] mac80211: limit injected vht mcs/nss in ieee80211_parse_tx_radiotap Limit max values for vht mcs and nss in ieee80211_parse_tx_radiotap routine in order to fix the following warning reported by syzbot: WARNING: CPU: 0 PID: 10717 at include/net/mac80211.h:989 ieee80211_rate_set_vht include/net/mac80211.h:989 [inline] WARNING: CPU: 0 PID: 10717 at include/net/mac80211.h:989 ieee80211_parse_tx_radiotap+0x101e/0x12d0 net/mac80211/tx.c:2244 Modules linked in: CPU: 0 PID: 10717 Comm: syz-executor.5 Not tainted 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:ieee80211_rate_set_vht include/net/mac80211.h:989 [inline] RIP: 0010:ieee80211_parse_tx_radiotap+0x101e/0x12d0 net/mac80211/tx.c:2244 RSP: 0018:ffffc9000186f3e8 EFLAGS: 00010216 RAX: 0000000000000618 RBX: ffff88804ef76500 RCX: ffffc900143a5000 RDX: 0000000000040000 RSI: ffffffff888f478e RDI: 0000000000000003 RBP: 00000000ffffffff R08: 0000000000000000 R09: 0000000000000100 R10: ffffffff888f46f9 R11: 0000000000000000 R12: 00000000fffffff8 R13: ffff88804ef7653c R14: 0000000000000001 R15: 0000000000000004 FS: 00007fbf5718f700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2de23000 CR3: 000000006a671000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600 Call Trace: ieee80211_monitor_select_queue+0xa6/0x250 net/mac80211/iface.c:740 netdev_core_pick_tx+0x169/0x2e0 net/core/dev.c:4089 __dev_queue_xmit+0x6f9/0x3710 net/core/dev.c:4165 __bpf_tx_skb net/core/filter.c:2114 [inline] __bpf_redirect_no_mac net/core/filter.c:2139 [inline] __bpf_redirect+0x5ba/0xd20 net/core/filter.c:2162 ____bpf_clone_redirect net/core/filter.c:2429 [inline] bpf_clone_redirect+0x2ae/0x420 net/core/filter.c:2401 bpf_prog_eeb6f53a69e5c6a2+0x59/0x234 bpf_dispatcher_nop_func include/linux/bpf.h:717 [inline] __bpf_prog_run include/linux/filter.h:624 [inline] bpf_prog_run include/linux/filter.h:631 [inline] bpf_test_run+0x381/0xa30 net/bpf/test_run.c:119 bpf_prog_test_run_skb+0xb84/0x1ee0 net/bpf/test_run.c:663 bpf_prog_test_run kernel/bpf/syscall.c:3307 [inline] __sys_bpf+0x2137/0x5df0 kernel/bpf/syscall.c:4605 __do_sys_bpf kernel/bpf/syscall.c:4691 [inline] __se_sys_bpf kernel/bpf/syscall.c:4689 [inline] __x64_sys_bpf+0x75/0xb0 kernel/bpf/syscall.c:4689 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x4665f9 Reported-by: syzbot+0196ac871673f0c20f68@syzkaller.appspotmail.com Fixes: 646e76bb5daf4 ("mac80211: parse VHT info in injected frames") Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/c26c3f02dcb38ab63b2f2534cb463d95ee81bb13.1632141760.git.lorenzo@kernel.org Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 824bed71be13..8921088a5df6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2209,7 +2209,11 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } vht_mcs = iterator.this_arg[4] >> 4; + if (vht_mcs > 11) + vht_mcs = 0; vht_nss = iterator.this_arg[4] & 0xF; + if (!vht_nss || vht_nss > 8) + vht_nss = 1; break; /* From b9731062ce8afd35cf723bf3a8ad55d208f915a5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 20 Sep 2021 15:40:05 +0200 Subject: [PATCH 619/866] mac80211: mesh: fix potentially unaligned access The pointer here points directly into the frame, so the access is potentially unaligned. Use get_unaligned_le16 to avoid that. Fixes: 3f52b7e328c5 ("mac80211: mesh power save basics") Link: https://lore.kernel.org/r/20210920154009.3110ff75be0c.Ib6a2ff9e9cc9bc6fca50fce631ec1ce725cc926b@changeid Signed-off-by: Johannes Berg --- net/mac80211/mesh_ps.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c index 204830a55240..3fbd0b9ff913 100644 --- a/net/mac80211/mesh_ps.c +++ b/net/mac80211/mesh_ps.c @@ -2,6 +2,7 @@ /* * Copyright 2012-2013, Marco Porsch * Copyright 2012-2013, cozybit Inc. + * Copyright (C) 2021 Intel Corporation */ #include "mesh.h" @@ -588,7 +589,7 @@ void ieee80211_mps_frame_release(struct sta_info *sta, /* only transmit to PS STA with announced, non-zero awake window */ if (test_sta_flag(sta, WLAN_STA_PS_STA) && - (!elems->awake_window || !le16_to_cpu(*elems->awake_window))) + (!elems->awake_window || !get_unaligned_le16(elems->awake_window))) return; if (!test_sta_flag(sta, WLAN_STA_MPSP_OWNER)) From 313bbd1990b6ddfdaa7da098d0c56b098a833572 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 15 Sep 2021 11:29:37 +0200 Subject: [PATCH 620/866] mac80211-hwsim: fix late beacon hrtimer handling Thomas explained in https://lore.kernel.org/r/87mtoeb4hb.ffs@tglx that our handling of the hrtimer here is wrong: If the timer fires late (e.g. due to vCPU scheduling, as reported by Dmitry/syzbot) then it tries to actually rearm the timer at the next deadline, which might be in the past already: 1 2 3 N N+1 | | | ... | | ^ intended to fire here (1) ^ next deadline here (2) ^ actually fired here The next time it fires, it's later, but will still try to schedule for the next deadline (now 3), etc. until it catches up with N, but that might take a long time, causing stalls etc. Now, all of this is simulation, so we just have to fix it, but note that the behaviour is wrong even per spec, since there's no value then in sending all those beacons unaligned - they should be aligned to the TBTT (1, 2, 3, ... in the picture), and if we're a bit (or a lot) late, then just resume at that point. Therefore, change the code to use hrtimer_forward_now() which will ensure that the next firing of the timer would be at N+1 (in the picture), i.e. the next interval point after the current time. Suggested-by: Thomas Gleixner Reported-by: Dmitry Vyukov Reported-by: syzbot+0e964fad69a9c462bc1e@syzkaller.appspotmail.com Fixes: 01e59e467ecf ("mac80211_hwsim: hrtimer beacon") Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210915112936.544f383472eb.I3f9712009027aa09244b65399bf18bf482a8c4f1@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index ffa894f7312a..0adae76eb8df 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1867,8 +1867,8 @@ mac80211_hwsim_beacon(struct hrtimer *timer) bcn_int -= data->bcn_delta; data->bcn_delta = 0; } - hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer), - ns_to_ktime(bcn_int * NSEC_PER_USEC)); + hrtimer_forward_now(&data->beacon_timer, + ns_to_ktime(bcn_int * NSEC_PER_USEC)); return HRTIMER_RESTART; } From 3106a0847525befe3e22fc723909d1b21eb0d520 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 22 Sep 2021 13:25:40 +0300 Subject: [PATCH 621/866] nexthop: Fix memory leaks in nexthop notification chain listeners syzkaller discovered memory leaks [1] that can be reduced to the following commands: # ip nexthop add id 1 blackhole # devlink dev reload pci/0000:06:00.0 As part of the reload flow, mlxsw will unregister its netdevs and then unregister from the nexthop notification chain. Before unregistering from the notification chain, mlxsw will receive delete notifications for nexthop objects using netdevs registered by mlxsw or their uppers. mlxsw will not receive notifications for nexthops using netdevs that are not dismantled as part of the reload flow. For example, the blackhole nexthop above that internally uses the loopback netdev as its nexthop device. One way to fix this problem is to have listeners flush their nexthop tables after unregistering from the notification chain. This is error-prone as evident by this patch and also not symmetric with the registration path where a listener receives a dump of all the existing nexthops. Therefore, fix this problem by replaying delete notifications for the listener being unregistered. This is symmetric to the registration path and also consistent with the netdev notification chain. The above means that unregister_nexthop_notifier(), like register_nexthop_notifier(), will have to take RTNL in order to iterate over the existing nexthops and that any callers of the function cannot hold RTNL. This is true for mlxsw and netdevsim, but not for the VXLAN driver. To avoid a deadlock, change the latter to unregister its nexthop listener without holding RTNL, making it symmetric to the registration path. [1] unreferenced object 0xffff88806173d600 (size 512): comm "syz-executor.0", pid 1290, jiffies 4295583142 (age 143.507s) hex dump (first 32 bytes): 41 9d 1e 60 80 88 ff ff 08 d6 73 61 80 88 ff ff A..`......sa.... 08 d6 73 61 80 88 ff ff 01 00 00 00 00 00 00 00 ..sa............ backtrace: [] kmemleak_alloc_recursive include/linux/kmemleak.h:43 [inline] [] slab_post_alloc_hook+0x96/0x490 mm/slab.h:522 [] slab_alloc_node mm/slub.c:3206 [inline] [] slab_alloc mm/slub.c:3214 [inline] [] kmem_cache_alloc_trace+0x163/0x370 mm/slub.c:3231 [] kmalloc include/linux/slab.h:591 [inline] [] kzalloc include/linux/slab.h:721 [inline] [] mlxsw_sp_nexthop_obj_group_create drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:4918 [inline] [] mlxsw_sp_nexthop_obj_new drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5054 [inline] [] mlxsw_sp_nexthop_obj_event+0x59a/0x2910 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5239 [] notifier_call_chain+0xbd/0x210 kernel/notifier.c:83 [] blocking_notifier_call_chain kernel/notifier.c:318 [inline] [] blocking_notifier_call_chain+0x72/0xa0 kernel/notifier.c:306 [] call_nexthop_notifiers+0x156/0x310 net/ipv4/nexthop.c:244 [] insert_nexthop net/ipv4/nexthop.c:2336 [inline] [] nexthop_add net/ipv4/nexthop.c:2644 [inline] [] rtm_new_nexthop+0x14e8/0x4d10 net/ipv4/nexthop.c:2913 [] rtnetlink_rcv_msg+0x448/0xbf0 net/core/rtnetlink.c:5572 [] netlink_rcv_skb+0x173/0x480 net/netlink/af_netlink.c:2504 [] rtnetlink_rcv+0x22/0x30 net/core/rtnetlink.c:5590 [] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [] netlink_unicast+0x5ae/0x7f0 net/netlink/af_netlink.c:1340 [] netlink_sendmsg+0x8e1/0xe30 net/netlink/af_netlink.c:1929 [] sock_sendmsg_nosec net/socket.c:704 [inline] [] sock_sendmsg net/socket.c:724 [inline] [] ____sys_sendmsg+0x874/0x9f0 net/socket.c:2409 [] ___sys_sendmsg+0x104/0x170 net/socket.c:2463 [] __sys_sendmsg+0x111/0x1f0 net/socket.c:2492 [] __do_sys_sendmsg net/socket.c:2501 [inline] [] __se_sys_sendmsg net/socket.c:2499 [inline] [] __x64_sys_sendmsg+0x7d/0xc0 net/socket.c:2499 Fixes: 2a014b200bbd ("mlxsw: spectrum_router: Add support for nexthop objects") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 2 +- net/ipv4/nexthop.c | 19 ++++++++++++++----- 2 files changed, 15 insertions(+), 6 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 5a8df5a195cb..141635a35c28 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -4756,12 +4756,12 @@ static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) LIST_HEAD(list); unsigned int h; - rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); } + rtnl_lock(); list_for_each_entry(net, net_list, exit_list) vxlan_destroy_tunnels(net, &list); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 0e75fd3e57b4..9e8100728d46 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3567,6 +3567,7 @@ static struct notifier_block nh_netdev_notifier = { }; static int nexthops_dump(struct net *net, struct notifier_block *nb, + enum nexthop_event_type event_type, struct netlink_ext_ack *extack) { struct rb_root *root = &net->nexthop.rb_root; @@ -3577,8 +3578,7 @@ static int nexthops_dump(struct net *net, struct notifier_block *nb, struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); - err = call_nexthop_notifier(nb, net, NEXTHOP_EVENT_REPLACE, nh, - extack); + err = call_nexthop_notifier(nb, net, event_type, nh, extack); if (err) break; } @@ -3592,7 +3592,7 @@ int register_nexthop_notifier(struct net *net, struct notifier_block *nb, int err; rtnl_lock(); - err = nexthops_dump(net, nb, extack); + err = nexthops_dump(net, nb, NEXTHOP_EVENT_REPLACE, extack); if (err) goto unlock; err = blocking_notifier_chain_register(&net->nexthop.notifier_chain, @@ -3605,8 +3605,17 @@ EXPORT_SYMBOL(register_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { - return blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, - nb); + int err; + + rtnl_lock(); + err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, + nb); + if (err) + goto unlock; + nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); +unlock: + rtnl_unlock(); + return err; } EXPORT_SYMBOL(unregister_nexthop_notifier); From 5b099870c8e0eb026a1560894d94f827832491cf Mon Sep 17 00:00:00 2001 From: Guvenc Gulce Date: Wed, 22 Sep 2021 19:21:29 +0200 Subject: [PATCH 622/866] MAINTAINERS: remove Guvenc Gulce as net/smc maintainer Remove myself as net/smc maintainer, as I am leaving IBM soon and can not maintain net/smc anymore. Cc: Julian Wiedmann Acked-by: Karsten Graul Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..3c814976443e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16955,7 +16955,6 @@ F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS M: Karsten Graul -M: Guvenc Gulce L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ From 31339440b2d0a4987030aac026adbaba44e22490 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 22 Sep 2021 19:30:37 +0100 Subject: [PATCH 623/866] nfc: st-nci: Add SPI ID matching DT compatible Currently autoloading for SPI devices does not use the DT ID table, it uses SPI modalises. Supporting OF modalises is going to be difficult if not impractical, an attempt was made but has been reverted, so ensure that module autoloading works for this driver by adding the part name used in the compatible to the list of SPI IDs. Fixes: 96c8395e2166 ("spi: Revert modalias changes") Signed-off-by: Mark Brown Signed-off-by: David S. Miller --- drivers/nfc/st-nci/spi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index a620c34790e6..0875b773fb41 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -278,6 +278,7 @@ static int st_nci_spi_remove(struct spi_device *dev) static struct spi_device_id st_nci_spi_id_table[] = { {ST_NCI_SPI_DRIVER_NAME, 0}, + {"st21nfcb-spi", 0}, {} }; MODULE_DEVICE_TABLE(spi, st_nci_spi_id_table); From e68daf61ed13832aef8892200a874139700ca754 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 22 Sep 2021 16:55:48 -0700 Subject: [PATCH 624/866] net: ethernet: mtk_eth_soc: avoid creating duplicate offload entries Sometimes multiple CLS_REPLACE calls are issued for the same connection. rhashtable_insert_fast does not check for these duplicates, so multiple hardware flow entries can be created. Fix this by checking for an existing entry early Fixes: 502e84e2382d ("net: ethernet: mtk_eth_soc: add flow offloading support") Signed-off-by: Felix Fietkau Signed-off-by: Ilya Lipnitskiy Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index b5f68f66d42a..7bb1f20002b5 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -186,6 +186,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f) int hash; int i; + if (rhashtable_lookup(ð->flow_table, &f->cookie, mtk_flow_ht_params)) + return -EEXIST; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) { struct flow_match_meta match; From acc64f52afac15e9e44d9b5253271346841786e0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 22 Sep 2021 19:03:38 -0700 Subject: [PATCH 625/866] net: mscc: ocelot: fix forwarding from BLOCKING ports remaining enabled The blamed commit made the fatally incorrect assumption that ports which aren't in the FORWARDING STP state should not have packets forwarded towards them, and that is all that needs to be done. However, that logic alone permits BLOCKING ports to forward to FORWARDING ports, which of course allows packet storms to occur when there is an L2 loop. The ocelot_get_bridge_fwd_mask should not only ask "what can the bridge do for you", but "what can you do for the bridge". This way, only FORWARDING ports forward to the other FORWARDING ports from the same bridging domain, and we are still compatible with the idea of multiple bridges. Fixes: df291e54ccca ("net: ocelot: support multiple bridges") Suggested-by: Colin Foster Reported-by: Colin Foster Signed-off-by: Vladimir Oltean Signed-off-by: Colin Foster Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 729ba826ba17..559177e6ded4 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1293,14 +1293,19 @@ static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond, return mask; } -static u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, +static u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port, struct net_device *bridge) { + struct ocelot_port *ocelot_port = ocelot->ports[src_port]; u32 mask = 0; int port; + if (!ocelot_port || ocelot_port->bridge != bridge || + ocelot_port->stp_state != BR_STATE_FORWARDING) + return 0; + for (port = 0; port < ocelot->num_phys_ports; port++) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; + ocelot_port = ocelot->ports[port]; if (!ocelot_port) continue; @@ -1366,7 +1371,7 @@ void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot) struct net_device *bridge = ocelot_port->bridge; struct net_device *bond = ocelot_port->bond; - mask = ocelot_get_bridge_fwd_mask(ocelot, bridge); + mask = ocelot_get_bridge_fwd_mask(ocelot, port, bridge); mask |= cpu_fwd_mask; mask &= ~BIT(port); if (bond) { From fdbccea419dc782079ce5881d2705cc9e3881480 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 23 Sep 2021 09:51:45 +0300 Subject: [PATCH 626/866] net/mlx4_en: Don't allow aRFS for encapsulated packets Driver doesn't support aRFS for encapsulated packets, return early error in such a case. Fixes: 1eb8c695bda9 ("net/mlx4_en: Add accelerated RFS support") Signed-off-by: Aya Levin Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 35154635ec3a..8af7f2827322 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -372,6 +372,9 @@ mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, int nhoff = skb_network_offset(skb); int ret = 0; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + if (skb->protocol != htons(ETH_P_IP)) return -EPROTONOSUPPORT; From 4d88c339c423eefe2fd48215016cb0c75fcb4c4d Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Thu, 23 Sep 2021 03:16:05 -0700 Subject: [PATCH 627/866] atlantic: Fix issue in the pm resume flow. After fixing hibernation resume flow, another usecase was found which should be explicitly handled - resume when device is in "down" state. Invoke aq_nic_init jointly with aq_nic_start only if ndev was already up during suspend/hibernate. We still need to perform nic_deinit() if caller requests for it, to handle the freeze/resume scenarios. Fixes: 57f780f1c433 ("atlantic: Fix driver resume flow.") Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index dee9ff74d6d6..d4b1976ee69b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -413,13 +413,13 @@ static int atl_resume_common(struct device *dev, bool deep) if (deep) { /* Reinitialize Nic/Vecs objects */ aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); - - ret = aq_nic_init(nic); - if (ret) - goto err_exit; } if (netif_running(nic->ndev)) { + ret = aq_nic_init(nic); + if (ret) + goto err_exit; + ret = aq_nic_start(nic); if (ret) goto err_exit; From aee77e1169c1900fe4248dc186962e745b479d9e Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 14 Sep 2021 18:48:12 +0300 Subject: [PATCH 628/866] KVM: x86: nSVM: restore int_vector in svm_clear_vintr In svm_clear_vintr we try to restore the virtual interrupt injection that might be pending, but we fail to restore the interrupt vector. Signed-off-by: Maxim Levitsky Message-Id: <20210914154825.104886-2-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 196bb3d22383..d674304d45a2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & V_IRQ_INJECTION_BITS_MASK; + + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); From 1ad32105d78e4b5da60688eca014bcd45271318f Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 14 Sep 2021 18:48:13 +0300 Subject: [PATCH 629/866] KVM: x86: selftests: test simultaneous uses of V_IRQ from L1 and L0 Test that if: * L1 disables virtual interrupt masking, and INTR intercept. * L1 setups a virtual interrupt to be injected to L2 and enters L2 with interrupts disabled, thus the virtual interrupt is pending. * Now an external interrupt arrives in L1 and since L1 doesn't intercept it, it should be delivered to L2 when it enables interrupts. to do this L0 (abuses) V_IRQ to setup an interrupt window, and returns to L2. * L2 enables interrupts. This should trigger the interrupt window, injection of the external interrupt and delivery of the virtual interrupt that can now be done. * Test that now L2 gets those interrupts. This is the test that demonstrates the issue that was fixed in the previous patch. Signed-off-by: Maxim Levitsky Message-Id: <20210914154825.104886-3-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/.gitignore | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/x86_64/svm_int_ctl_test.c | 128 ++++++++++++++++++ 3 files changed, 130 insertions(+) create mode 100644 tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 618bf9bc7f3f..b8dbabe24ac2 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -24,6 +24,7 @@ /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test +/x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/userspace_msr_exit_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 9ac325cfc94a..d1774f461393 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -56,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c new file mode 100644 index 000000000000..df04f56ce859 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_int_ctl_test + * + * Copyright (C) 2021, Red Hat, Inc. + * + * Nested SVM testing: test simultaneous use of V_IRQ from L1 and L0. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "apic.h" + +#define VCPU_ID 0 + +static struct kvm_vm *vm; + +bool vintr_irq_called; +bool intr_irq_called; + +#define VINTR_IRQ_NUMBER 0x20 +#define INTR_IRQ_NUMBER 0x30 + +static void vintr_irq_handler(struct ex_regs *regs) +{ + vintr_irq_called = true; +} + +static void intr_irq_handler(struct ex_regs *regs) +{ + x2apic_write_reg(APIC_EOI, 0x00); + intr_irq_called = true; +} + +static void l2_guest_code(struct svm_test_data *svm) +{ + /* This code raises interrupt INTR_IRQ_NUMBER in the L1's LAPIC, + * and since L1 didn't enable virtual interrupt masking, + * L2 should receive it and not L1. + * + * L2 also has virtual interrupt 'VINTR_IRQ_NUMBER' pending in V_IRQ + * so it should also receive it after the following 'sti'. + */ + x2apic_write_reg(APIC_ICR, + APIC_DEST_SELF | APIC_INT_ASSERT | INTR_IRQ_NUMBER); + + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + GUEST_ASSERT(vintr_irq_called); + GUEST_ASSERT(intr_irq_called); + + __asm__ __volatile__( + "vmcall\n" + ); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + x2apic_enable(); + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* No virtual interrupt masking */ + vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + /* No intercepts for real and virtual interrupts */ + vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + + /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ + vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); + vmcb->control.int_vector = VINTR_IRQ_NUMBER; + + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); + vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("%s", (const char *)uc.args[0]); + break; + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } +done: + kvm_vm_free(vm); + return 0; +} From d1cba6c9223751f580dcd97501f513a8a9bf88bc Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 14 Sep 2021 18:48:14 +0300 Subject: [PATCH 630/866] KVM: x86: nSVM: test eax for 4K alignment for GP errata workaround GP SVM errata workaround made the #GP handler always emulate the SVM instructions. However these instructions #GP in case the operand is not 4K aligned, but the workaround code didn't check this and we ended up emulating these instructions anyway. This is only an emulation accuracy check bug as there is no harm for KVM to read/write unaligned vmcb images. Fixes: 82a11e9c6fa2 ("KVM: SVM: Add emulation support for #GP triggered by SVM instructions") Signed-off-by: Maxim Levitsky Message-Id: <20210914154825.104886-4-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d674304d45a2..989685098b3e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2224,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; From faf6b755629627f19feafa75b32e81cd7738f12d Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Tue, 14 Sep 2021 18:48:16 +0300 Subject: [PATCH 631/866] KVM: x86: nSVM: don't copy virt_ext from vmcb12 These field correspond to features that we don't expose yet to L2 While currently there are no CVE worthy features in this field, if AMD adds more features to this field, that could allow guest escapes similar to CVE-2021-3653 and CVE-2021-3656. Signed-off-by: Maxim Levitsky Message-Id: <20210914154825.104886-6-mlevitsk@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b41a21cac544..510b833cbd39 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); - svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; svm->vmcb->control.int_state = svm->nested.ctl.int_state; svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; From f81602958c115fc7c87b985f71574042a20ff858 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 18 Sep 2021 08:56:27 +0800 Subject: [PATCH 632/866] KVM: X86: Fix missed remote tlb flush in rmap_write_protect() When kvm->tlbs_dirty > 0, some rmaps might have been deleted without flushing tlb remotely after kvm_sync_page(). If @gfn was writable before and it's rmaps was deleted in kvm_sync_page(), and if the tlb entry is still in a remote running VCPU, the @gfn is not safely protected. To fix the problem, kvm_sync_page() does the remote flush when needed to avoid the problem. Fixes: a4ee1ca4a36e ("KVM: MMU: delay flush all tlbs on sync_page path") Signed-off-by: Lai Jiangshan Signed-off-by: Paolo Bonzini Message-Id: <20210918005636.3675-2-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/paging_tmpl.h | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 7d03e9b7ccfa..efce0a935e23 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -1047,14 +1047,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr, * Using the cached information from sp->gfns is safe because: * - The spte has a reference to the struct page, so the pfn for a given gfn * can't change unless all sptes pointing to it are nuked first. - * - * Note: - * We should flush all tlbs if spte is dropped even though guest is - * responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page - * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't - * used by guest then tlbs are not flushed, so guest is allowed to access the - * freed pages. - * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -1107,13 +1099,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return 0; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - /* - * Update spte before increasing tlbs_dirty to make - * sure no tlb flush is lost after spte is zapped; see - * the comments in kvm_flush_remote_tlbs(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } @@ -1128,12 +1114,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - /* - * The same as above where we are doing - * prefetch_invalid_gpte(). - */ - smp_wmb(); - vcpu->kvm->tlbs_dirty++; + set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH; continue; } From 22b70e6f2da0a4c8b1421b00cfc3016bc9d4d9d4 Mon Sep 17 00:00:00 2001 From: dann frazier Date: Thu, 23 Sep 2021 08:50:02 -0600 Subject: [PATCH 633/866] arm64: Restore forced disabling of KPTI on ThunderX A noted side-effect of commit 0c6c2d3615ef ("arm64: Generate cpucaps.h") is that cpucaps are now sorted, changing the enumeration order. This assumed no dependencies between cpucaps, which turned out not to be true in one case. UNMAP_KERNEL_AT_EL0 currently needs to be processed after WORKAROUND_CAVIUM_27456. ThunderX systems are incompatible with KPTI, so unmap_kernel_at_el0() bails if WORKAROUND_CAVIUM_27456 is set. But because of the sorting, WORKAROUND_CAVIUM_27456 will not yet have been considered when unmap_kernel_at_el0() checks for it, so the kernel tries to run w/ KPTI - and quickly falls over. Because all ThunderX implementations have homogeneous CPUs, we can remove this dependency by just checking the current CPU for the erratum. Fixes: 0c6c2d3615ef ("arm64: Generate cpucaps.h") Cc: # 5.13.x Signed-off-by: dann frazier Suggested-by: Suzuki K Poulose Reviewed-by: Suzuki K Poulose Reviewed-by: Mark Brown Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20210923145002.3394558-1-dann.frazier@canonical.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f8a3067d10c6..6ec7036ef7e1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1526,9 +1526,13 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, /* * For reasons that aren't entirely clear, enabling KPTI on Cavium * ThunderX leads to apparent I-cache corruption of kernel text, which - * ends as well as you might imagine. Don't even try. + * ends as well as you might imagine. Don't even try. We cannot rely + * on the cpus_have_*cap() helpers here to detect the CPU erratum + * because cpucap detection order may change. However, since we know + * affected CPUs are always in a homogeneous configuration, it is + * safe to rely on this_cpu_has_cap() here. */ - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) { + if (this_cpu_has_cap(ARM64_WORKAROUND_CAVIUM_27456)) { str = "ARM64_WORKAROUND_CAVIUM_27456"; __kpti_forced = -1; } From 65855ed8b03437e79e42f2a89a993206981ac6cb Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 18 Sep 2021 08:56:28 +0800 Subject: [PATCH 634/866] KVM: X86: Synchronize the shadow pagetable before link it If gpte is changed from non-present to present, the guest doesn't need to flush tlb per SDM. So the host must synchronze sp before link it. Otherwise the guest might use a wrong mapping. For example: the guest first changes a level-1 pagetable, and then links its parent to a new place where the original gpte is non-present. Finally the guest can access the remapped area without flushing the tlb. The guest's behavior should be allowed per SDM, but the host kvm mmu makes it wrong. Fixes: 4731d4c7a077 ("KVM: MMU: out of sync shadow core") Signed-off-by: Lai Jiangshan Signed-off-by: Paolo Bonzini Message-Id: <20210918005636.3675-3-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 17 ++++++++++------- arch/x86/kvm/mmu/paging_tmpl.h | 23 +++++++++++++++++++++-- 2 files changed, 31 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2d7e61122af8..1a64ba5b9437 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) } while (!sp->unsync_children); } -static void mmu_sync_children(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *parent) +static int mmu_sync_children(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *parent, bool can_yield) { int i; struct kvm_mmu_page *sp; @@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + if (!can_yield) { + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + return -EINTR; + } + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); + return 0; } static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) @@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } - if (sp->unsync_children) - kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - __clear_sp_write_flooding_count(sp); trace_get_page: @@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); write_unlock(&vcpu->kvm->mmu_lock); @@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) if (IS_VALID_PAE_ROOT(root)) { root &= PT64_BASE_ADDR_MASK; sp = to_shadow_page(root); - mmu_sync_children(vcpu, sp); + mmu_sync_children(vcpu, sp, true); } } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index efce0a935e23..913d52a7923e 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; - sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access); + sp = kvm_mmu_get_page(vcpu, table_gfn, addr, + it.level-1, false, access); + /* + * We must synchronize the pagetable before linking it + * because the guest doesn't need to flush tlb when + * the gpte is changed from non-present to present. + * Otherwise, the guest may use the wrong mapping. + * + * For PG_LEVEL_4K, kvm_mmu_get_page() has already + * synchronized it transiently via kvm_sync_page(). + * + * For higher level pagetable, we synchronize it via + * the slower mmu_sync_children(). If it needs to + * break, some progress has been made; return + * RET_PF_RETRY and retry on the next #PF. + * KVM_REQ_MMU_SYNC is not necessary but it + * expedites the process. + */ + if (sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; } /* From 6bc6db000295332bae2c1e8815d7450b72923d23 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 18 Sep 2021 08:56:29 +0800 Subject: [PATCH 635/866] KVM: Remove tlbs_dirty There is no user of tlbs_dirty. Signed-off-by: Lai Jiangshan Signed-off-by: Paolo Bonzini Message-Id: <20210918005636.3675-4-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 10 ++-------- 2 files changed, 2 insertions(+), 9 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 000ea73dd324..0f18df7fe874 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -608,7 +608,6 @@ struct kvm { unsigned long mmu_notifier_range_start; unsigned long mmu_notifier_range_end; #endif - long tlbs_dirty; struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e95e7a9e4d53..7851f3a1b5f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -326,13 +326,8 @@ EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { - /* - * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in - * kvm_make_all_cpus_request. - */ - long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); - ++kvm->stat.generic.remote_tlb_flush_requests; + /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. @@ -347,7 +342,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif @@ -552,7 +546,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, } } - if (range->flush_on_ret && (ret || kvm->tlbs_dirty)) + if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (locked) From 93368aab0efc87288cac65e99c9ed2e0ffc9e7d0 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 21 Sep 2021 22:35:30 +0800 Subject: [PATCH 636/866] erofs: fix up erofs_lookup tracepoint Fix up a misuse that the filename pointer isn't always valid in the ring buffer, and we should copy the content instead. Link: https://lore.kernel.org/r/20210921143531.81356-1-hsiangkao@linux.alibaba.com Fixes: 13f06f48f7bf ("staging: erofs: support tracepoint") Cc: stable@vger.kernel.org # 4.19+ Reviewed-by: Chao Yu Signed-off-by: Gao Xiang --- include/trace/events/erofs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h index bf9806fd1306..db4f2cec8360 100644 --- a/include/trace/events/erofs.h +++ b/include/trace/events/erofs.h @@ -35,20 +35,20 @@ TRACE_EVENT(erofs_lookup, TP_STRUCT__entry( __field(dev_t, dev ) __field(erofs_nid_t, nid ) - __field(const char *, name ) + __string(name, dentry->d_name.name ) __field(unsigned int, flags ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->nid = EROFS_I(dir)->nid; - __entry->name = dentry->d_name.name; + __assign_str(name, dentry->d_name.name); __entry->flags = flags; ), TP_printk("dev = (%d,%d), pnid = %llu, name:%s, flags:%x", show_dev_nid(__entry), - __entry->name, + __get_str(name), __entry->flags) ); From d705117ddd724a9d4877e338e4587010ab6a1c62 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Wed, 22 Sep 2021 17:51:41 +0800 Subject: [PATCH 637/866] erofs: fix misbehavior of unsupported chunk format check Unsupported chunk format should be checked with "if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL)" Found when checking with 4k-byte blockmap (although currently mkfs uses inode chunk indexes format by default.) Link: https://lore.kernel.org/r/20210922095141.233938-1-hsiangkao@linux.alibaba.com Fixes: c5aa903a59db ("erofs: support reading chunk-based uncompressed files") Reviewed-by: Liu Bo Reviewed-by: Chao Yu Signed-off-by: Gao Xiang --- fs/erofs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 31ac3a73b390..a552399e211d 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -176,7 +176,7 @@ static struct page *erofs_read_inode(struct inode *inode, } if (vi->datalayout == EROFS_INODE_CHUNK_BASED) { - if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_ALL)) { + if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL) { erofs_err(inode->i_sb, "unsupported chunk format %x of nid %llu", vi->chunkformat, vi->nid); From c40dd3ca2a45d5bd6e8b3f4ace5cb81493096263 Mon Sep 17 00:00:00 2001 From: Yue Hu Date: Tue, 14 Sep 2021 11:59:15 +0800 Subject: [PATCH 638/866] erofs: clear compacted_2b if compacted_4b_initial > totalidx Currently, the whole indexes will only be compacted 4B if compacted_4b_initial > totalidx. So, the calculated compacted_2b is worthless for that case. It may waste CPU resources. No need to update compacted_4b_initial as mkfs since it's used to fulfill the alignment of the 1st compacted_2b pack and would handle the case above. We also need to clarify compacted_4b_end here. It's used for the last lclusters which aren't fitted in the previous compacted_2b packs. Some messages are from Xiang. Link: https://lore.kernel.org/r/20210914035915.1190-1-zbestahu@gmail.com Signed-off-by: Yue Hu Reviewed-by: Gao Xiang Reviewed-by: Chao Yu [ Gao Xiang: it's enough to use "compacted_4b_initial < totalidx". ] Signed-off-by: Gao Xiang --- fs/erofs/zmap.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 9fb98d85a3ce..7a6df35fdc91 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -369,7 +369,8 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, if (compacted_4b_initial == 32 / 4) compacted_4b_initial = 0; - if (vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) + if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) && + compacted_4b_initial < totalidx) compacted_2b = rounddown(totalidx - compacted_4b_initial, 16); else compacted_2b = 0; From a3727a8bac0a9e77c70820655fd8715523ba3db7 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 23 Sep 2021 09:50:11 -0400 Subject: [PATCH 639/866] selinux,smack: fix subjective/objective credential use mixups Jann Horn reported a problem with commit eb1231f73c4d ("selinux: clarify task subjective and objective credentials") where some LSM hooks were attempting to access the subjective credentials of a task other than the current task. Generally speaking, it is not safe to access another task's subjective credentials and doing so can cause a number of problems. Further, while looking into the problem, I realized that Smack was suffering from a similar problem brought about by a similar commit 1fb057dcde11 ("smack: differentiate between subjective and objective task credentials"). This patch addresses this problem by restoring the use of the task's objective credentials in those cases where the task is other than the current executing task. Not only does this resolve the problem reported by Jann, it is arguably the correct thing to do in these cases. Cc: stable@vger.kernel.org Fixes: eb1231f73c4d ("selinux: clarify task subjective and objective credentials") Fixes: 1fb057dcde11 ("smack: differentiate between subjective and objective task credentials") Reported-by: Jann Horn Acked-by: Eric W. Biederman Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- security/selinux/hooks.c | 4 ++-- security/smack/smack_lsm.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6517f221d52c..e7ebd45ca345 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2157,7 +2157,7 @@ static int selinux_ptrace_access_check(struct task_struct *child, static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(&selinux_state, - task_sid_subj(parent), task_sid_obj(current), + task_sid_obj(parent), task_sid_obj(current), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } @@ -6222,7 +6222,7 @@ static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *m struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; - u32 sid = task_sid_subj(target); + u32 sid = task_sid_obj(target); int rc; isec = selinux_ipc(msq); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index cacbe7518519..21a0e7c3b8de 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2016,7 +2016,7 @@ static int smk_curacc_on_task(struct task_struct *p, int access, const char *caller) { struct smk_audit_info ad; - struct smack_known *skp = smk_of_task_struct_subj(p); + struct smack_known *skp = smk_of_task_struct_obj(p); int rc; smk_ad_init(&ad, caller, LSM_AUDIT_DATA_TASK); @@ -3480,7 +3480,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) */ static int smack_getprocattr(struct task_struct *p, char *name, char **value) { - struct smack_known *skp = smk_of_task_struct_subj(p); + struct smack_known *skp = smk_of_task_struct_obj(p); char *cp; int slen; From 1f828223b7991a228bc2aef837b78737946d44b2 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 22 Sep 2021 15:49:06 -0700 Subject: [PATCH 640/866] memcg: flush lruvec stats in the refault MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prior to the commit 7e1c0d6f5820 ("memcg: switch lruvec stats to rstat") and the commit aa48e47e3906 ("memcg: infrastructure to flush memcg stats"), each lruvec memcg stats can be off by (nr_cgroups * nr_cpus * 32) at worst and for unbounded amount of time. The commit aa48e47e3906 moved the lruvec stats to rstat infrastructure and the commit 7e1c0d6f5820 bounded the error for all the lruvec stats to (nr_cpus * 32) at worst for at most 2 seconds. More specifically it decoupled the number of stats and the number of cgroups from the error rate. However this reduction in error comes with the cost of triggering the slowpath of stats update more frequently. Previously in the slowpath the kernel adds the stats up the memcg tree. After aa48e47e3906, the kernel triggers the asyn lruvec stats flush through queue_work(). This causes regression reports from 0day kernel bot [1] as well as from phoronix test suite [2]. We tried two options to fix the regression: 1) Increase the threshold to trigger the slowpath in lruvec stats update codepath from 32 to 512. 2) Remove the slowpath from lruvec stats update codepath and instead flush the stats in the page refault codepath. The assumption is that the kernel timely flush the stats, so, the update tree would be small in the refault codepath to not cause the preformance impact. Following are the results of will-it-scale/page_fault[1|2|3] benchmark on four settings i.e. (1) 5.15-rc1 as baseline (2) 5.15-rc1 with aa48e47e3906 and 7e1c0d6f5820 reverted (3) 5.15-rc1 with option-1 (4) 5.15-rc1 with option-2. test (1) (2) (3) (4) pg_f1 368563 406277 (10.23%) 399693 (8.44%) 416398 (12.97%) pg_f2 338399 372133 (9.96%) 369180 (9.09%) 381024 (12.59%) pg_f3 500853 575399 (14.88%) 570388 (13.88%) 576083 (15.02%) From the above result, it seems like the option-2 not only solves the regression but also improves the performance for at least these benchmarks. Feng Tang (intel) ran the aim7 benchmark with these two options and confirms that option-1 reduces the regression but option-2 removes the regression. Michael Larabel (phoronix) ran multiple benchmarks with these options and reported the results at [3] and it shows for most benchmarks option-2 removes the regression introduced by the commit aa48e47e3906 ("memcg: infrastructure to flush memcg stats"). Based on the experiment results, this patch proposed the option-2 as the solution to resolve the regression. Link: https://lore.kernel.org/all/20210726022421.GB21872@xsang-OptiPlex-9020 [1] Link: https://www.phoronix.com/scan.php?page=article&item=linux515-compile-regress [2] Link: https://openbenchmarking.org/result/2109226-DEBU-LINUX5104 [3] Fixes: aa48e47e3906 ("memcg: infrastructure to flush memcg stats") Signed-off-by: Shakeel Butt Tested-by: Michael Larabel Cc: Johannes Weiner Cc: Roman Gushchin Cc: Feng Tang Cc: Michal Hocko Cc: Hillf Danton , Cc: Michal Koutný Cc: Andrew Morton , Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 10 ---------- mm/workingset.c | 1 + 2 files changed, 1 insertion(+), 10 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b762215d73eb..6da5020a8656 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -106,9 +106,6 @@ static bool do_memsw_account(void) /* memcg and lruvec stats flushing */ static void flush_memcg_stats_dwork(struct work_struct *w); static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); -static void flush_memcg_stats_work(struct work_struct *w); -static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work); -static DEFINE_PER_CPU(unsigned int, stats_flush_threshold); static DEFINE_SPINLOCK(stats_flush_lock); #define THRESHOLDS_EVENTS_TARGET 128 @@ -682,8 +679,6 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, /* Update lruvec */ __this_cpu_add(pn->lruvec_stats_percpu->state[idx], val); - if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH)) - queue_work(system_unbound_wq, &stats_flush_work); } /** @@ -5361,11 +5356,6 @@ static void flush_memcg_stats_dwork(struct work_struct *w) queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); } -static void flush_memcg_stats_work(struct work_struct *w) -{ - mem_cgroup_flush_stats(); -} - static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); diff --git a/mm/workingset.c b/mm/workingset.c index d4268d8e9a82..d5b81e4f4cbe 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -352,6 +352,7 @@ void workingset_refault(struct page *page, void *shadow) inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); + mem_cgroup_flush_stats(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if From 5501765a02a6c324f78581e6bb8209d054fe13ae Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:09:38 -0700 Subject: [PATCH 641/866] driver core: fw_devlink: Add support for FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD If a parent device is also a supplier to a child device, fw_devlink=on by design delays the probe() of the child device until the probe() of the parent finishes successfully. However, some drivers of such parent devices (where parent is also a supplier) expect the child device to finish probing successfully as soon as they are added using device_add() and before the probe() of the parent device has completed successfully. One example of such a case is discussed in the link mentioned below. Add a flag to make fw_devlink=on not enforce these supplier-consumer relationships, so these drivers can continue working. Link: https://lore.kernel.org/netdev/CAGETcx_uj0V4DChME-gy5HGKTYnxLBX=TH2rag29f_p=UcG+Tg@mail.gmail.com/ Fixes: ea718c699055 ("Revert "Revert "driver core: Set fw_devlink=on by default""") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915170940.617415-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 19 +++++++++++++++++++ include/linux/fwnode.h | 11 ++++++++--- 2 files changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 316df6027093..21d4cb5d3767 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1722,6 +1722,25 @@ static int fw_devlink_create_devlink(struct device *con, struct device *sup_dev; int ret = 0; + /* + * In some cases, a device P might also be a supplier to its child node + * C. However, this would defer the probe of C until the probe of P + * completes successfully. This is perfectly fine in the device driver + * model. device_add() doesn't guarantee probe completion of the device + * by the time it returns. + * + * However, there are a few drivers that assume C will finish probing + * as soon as it's added and before P finishes probing. So, we provide + * a flag to let fw_devlink know not to delay the probe of C until the + * probe of P completes successfully. + * + * When such a flag is set, we can't create device links where P is the + * supplier of C as that would delay the probe of C. + */ + if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD && + fwnode_is_ancestor_of(sup_handle, con->fwnode)) + return -EINVAL; + sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 59828516ebaf..9f4ad719bfe3 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -22,10 +22,15 @@ struct device; * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. * NOT_DEVICE: The fwnode will never be populated as a struct device. * INITIALIZED: The hardware corresponding to fwnode has been initialized. + * NEEDS_CHILD_BOUND_ON_ADD: For this fwnode/device to probe successfully, its + * driver needs its child devices to be bound with + * their respective drivers as soon as they are + * added. */ -#define FWNODE_FLAG_LINKS_ADDED BIT(0) -#define FWNODE_FLAG_NOT_DEVICE BIT(1) -#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) struct fwnode_handle { struct fwnode_handle *secondary; From 04f41c68f18886aea5afc68be945e7195ea1d598 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:09:39 -0700 Subject: [PATCH 642/866] net: mdiobus: Set FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD for mdiobus parents There are many instances of PHYs that depend on a switch to supply a resource (Eg: interrupts). Switches also expects the PHYs to be probed by their specific drivers as soon as they are added. If that doesn't happen, then the switch would force the use of generic PHY drivers for the PHY even if the PHY might have specific driver available. fw_devlink=on by design can cause delayed probes of PHY. To avoid, this we need to set the FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD for the switch's fwnode before the PHYs are added. The most generic way to do this is to set this flag for the parent of MDIO busses which is typically the switch. For more context: https://lore.kernel.org/lkml/YTll0i6Rz3WAAYzs@lunn.ch/#t Fixes: ea718c699055 ("Revert "Revert "driver core: Set fw_devlink=on by default""") Suggested-by: Andrew Lunn Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915170940.617415-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/net/phy/mdio_bus.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 53f034fc2ef7..ee8313a4ac71 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -525,6 +525,10 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) NULL == bus->read || NULL == bus->write) return -EINVAL; + if (bus->parent && bus->parent->of_node) + bus->parent->of_node->fwnode.flags |= + FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD; + BUG_ON(bus->state != MDIOBUS_ALLOCATED && bus->state != MDIOBUS_UNREGISTERED); From 12064c1768439fa0882547010afae6b52aafa7af Mon Sep 17 00:00:00 2001 From: Jia He Date: Thu, 23 Sep 2021 11:35:57 +0800 Subject: [PATCH 643/866] Revert "ACPI: Add memory semantics to acpi_os_map_memory()" This reverts commit 437b38c51162f8b87beb28a833c4d5dc85fa864e. The memory semantics added in commit 437b38c51162 causes SystemMemory Operation region, whose address range is not described in the EFI memory map to be mapped as NormalNC memory on arm64 platforms (through acpi_os_map_memory() in acpi_ex_system_memory_space_handler()). This triggers the following abort on an ARM64 Ampere eMAG machine, because presumably the physical address range area backing the Opregion does not support NormalNC memory attributes driven on the bus. Internal error: synchronous external abort: 96000410 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0+ #462 Hardware name: MiTAC RAPTOR EV-883832-X3-0001/RAPTOR, BIOS 0.14 02/22/2019 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [...snip...] Call trace: acpi_ex_system_memory_space_handler+0x26c/0x2c8 acpi_ev_address_space_dispatch+0x228/0x2c4 acpi_ex_access_region+0x114/0x268 acpi_ex_field_datum_io+0x128/0x1b8 acpi_ex_extract_from_field+0x14c/0x2ac acpi_ex_read_data_from_field+0x190/0x1b8 acpi_ex_resolve_node_to_value+0x1ec/0x288 acpi_ex_resolve_to_value+0x250/0x274 acpi_ds_evaluate_name_path+0xac/0x124 acpi_ds_exec_end_op+0x90/0x410 acpi_ps_parse_loop+0x4ac/0x5d8 acpi_ps_parse_aml+0xe0/0x2c8 acpi_ps_execute_method+0x19c/0x1ac acpi_ns_evaluate+0x1f8/0x26c acpi_ns_init_one_device+0x104/0x140 acpi_ns_walk_namespace+0x158/0x1d0 acpi_ns_initialize_devices+0x194/0x218 acpi_initialize_objects+0x48/0x50 acpi_init+0xe0/0x498 If the Opregion address range is not present in the EFI memory map there is no way for us to determine the memory attributes to use to map it - defaulting to NormalNC does not work (and it is not correct on a memory region that may have read side-effects) and therefore commit 437b38c51162 should be reverted, which means reverting back to the original behavior whereby address ranges that are mapped using acpi_os_map_memory() default to the safe devicenGnRnE attributes on ARM64 if the mapped address range is not defined in the EFI memory map. Fixes: 437b38c51162 ("ACPI: Add memory semantics to acpi_os_map_memory()") Signed-off-by: Jia He Acked-by: Lorenzo Pieralisi Acked-by: Catalin Marinas Signed-off-by: Rafael J. Wysocki --- arch/arm64/include/asm/acpi.h | 3 --- arch/arm64/kernel/acpi.c | 19 +++---------------- drivers/acpi/osl.c | 23 +++++++---------------- include/acpi/acpi_io.h | 8 -------- 4 files changed, 10 insertions(+), 43 deletions(-) diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 7535dc7cc5aa..bd68e1b7f29f 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -50,9 +50,6 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr); void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); #define acpi_os_ioremap acpi_os_ioremap -void __iomem *acpi_os_memmap(acpi_physical_address phys, acpi_size size); -#define acpi_os_memmap acpi_os_memmap - typedef u64 phys_cpuid_t; #define PHYS_CPUID_INVALID INVALID_HWID diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 1c9c2f7a1c04..f3851724fe35 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -273,8 +273,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) return __pgprot(PROT_DEVICE_nGnRnE); } -static void __iomem *__acpi_os_ioremap(acpi_physical_address phys, - acpi_size size, bool memory) +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { efi_memory_desc_t *md, *region = NULL; pgprot_t prot; @@ -300,11 +299,9 @@ static void __iomem *__acpi_os_ioremap(acpi_physical_address phys, * It is fine for AML to remap regions that are not represented in the * EFI memory map at all, as it only describes normal memory, and MMIO * regions that require a virtual mapping to make them accessible to - * the EFI runtime services. Determine the region default - * attributes by checking the requested memory semantics. + * the EFI runtime services. */ - prot = memory ? __pgprot(PROT_NORMAL_NC) : - __pgprot(PROT_DEVICE_nGnRnE); + prot = __pgprot(PROT_DEVICE_nGnRnE); if (region) { switch (region->type) { case EFI_LOADER_CODE: @@ -364,16 +361,6 @@ static void __iomem *__acpi_os_ioremap(acpi_physical_address phys, return __ioremap(phys, size, prot); } -void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) -{ - return __acpi_os_ioremap(phys, size, false); -} - -void __iomem *acpi_os_memmap(acpi_physical_address phys, acpi_size size) -{ - return __acpi_os_ioremap(phys, size, true); -} - /* * Claim Synchronous External Aborts as a firmware first notification. * diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index a43f1521efe6..45c5c0e45e33 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -284,8 +284,7 @@ acpi_map_lookup_virt(void __iomem *virt, acpi_size size) #define should_use_kmap(pfn) page_is_ram(pfn) #endif -static void __iomem *acpi_map(acpi_physical_address pg_off, unsigned long pg_sz, - bool memory) +static void __iomem *acpi_map(acpi_physical_address pg_off, unsigned long pg_sz) { unsigned long pfn; @@ -295,8 +294,7 @@ static void __iomem *acpi_map(acpi_physical_address pg_off, unsigned long pg_sz, return NULL; return (void __iomem __force *)kmap(pfn_to_page(pfn)); } else - return memory ? acpi_os_memmap(pg_off, pg_sz) : - acpi_os_ioremap(pg_off, pg_sz); + return acpi_os_ioremap(pg_off, pg_sz); } static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr) @@ -311,10 +309,9 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr) } /** - * __acpi_os_map_iomem - Get a virtual address for a given physical address range. + * acpi_os_map_iomem - Get a virtual address for a given physical address range. * @phys: Start of the physical address range to map. * @size: Size of the physical address range to map. - * @memory: true if remapping memory, false if IO * * Look up the given physical address range in the list of existing ACPI memory * mappings. If found, get a reference to it and return a pointer to it (its @@ -324,8 +321,8 @@ static void acpi_unmap(acpi_physical_address pg_off, void __iomem *vaddr) * During early init (when acpi_permanent_mmap has not been set yet) this * routine simply calls __acpi_map_table() to get the job done. */ -static void __iomem __ref -*__acpi_os_map_iomem(acpi_physical_address phys, acpi_size size, bool memory) +void __iomem __ref +*acpi_os_map_iomem(acpi_physical_address phys, acpi_size size) { struct acpi_ioremap *map; void __iomem *virt; @@ -356,7 +353,7 @@ static void __iomem __ref pg_off = round_down(phys, PAGE_SIZE); pg_sz = round_up(phys + size, PAGE_SIZE) - pg_off; - virt = acpi_map(phys, size, memory); + virt = acpi_map(phys, size); if (!virt) { mutex_unlock(&acpi_ioremap_lock); kfree(map); @@ -375,17 +372,11 @@ out: mutex_unlock(&acpi_ioremap_lock); return map->virt + (phys - map->phys); } - -void __iomem *__ref -acpi_os_map_iomem(acpi_physical_address phys, acpi_size size) -{ - return __acpi_os_map_iomem(phys, size, false); -} EXPORT_SYMBOL_GPL(acpi_os_map_iomem); void *__ref acpi_os_map_memory(acpi_physical_address phys, acpi_size size) { - return (void *)__acpi_os_map_iomem(phys, size, true); + return (void *)acpi_os_map_iomem(phys, size); } EXPORT_SYMBOL_GPL(acpi_os_map_memory); diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h index a0212e67d6f4..027faa8883aa 100644 --- a/include/acpi/acpi_io.h +++ b/include/acpi/acpi_io.h @@ -14,14 +14,6 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, } #endif -#ifndef acpi_os_memmap -static inline void __iomem *acpi_os_memmap(acpi_physical_address phys, - acpi_size size) -{ - return ioremap_cache(phys, size); -} -#endif - extern bool acpi_permanent_mmap; void __iomem __ref From 03ab9cb982b622239cc2542ce7617b98a9ea159e Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 20 Sep 2021 13:14:15 +0100 Subject: [PATCH 644/866] cifs: Deal with some warnings from W=1 Deal with some warnings generated from make W=1: (1) Add/remove/fix kerneldoc parameters descriptions. (2) Turn cifs' rqst_page_get_length()'s banner comment into a kerneldoc comment. It should probably be prefixed with "cifs_" though. Signed-off-by: David Howells Signed-off-by: Steve French --- fs/cifs/misc.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 03da00eb7c04..f2916b51652a 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -590,6 +590,7 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) /** * cifs_queue_oplock_break - queue the oplock break handler for cfile + * @cfile: The file to break the oplock on * * This function is called from the demultiplex thread when it * receives an oplock break for @cfile. @@ -1065,6 +1066,9 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) /** * cifs_alloc_hash - allocate hash and hash context together + * @name: The name of the crypto hash algo + * @shash: Where to put the pointer to the hash algo + * @sdesc: Where to put the pointer to the hash descriptor * * The caller has to make sure @sdesc is initialized to either NULL or * a valid context. Both can be freed via cifs_free_hash(). @@ -1103,6 +1107,8 @@ cifs_alloc_hash(const char *name, /** * cifs_free_hash - free hash and hash context together + * @shash: Where to find the pointer to the hash algo + * @sdesc: Where to find the pointer to the hash descriptor * * Freeing a NULL hash or context is safe. */ @@ -1118,8 +1124,10 @@ cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc) /** * rqst_page_get_length - obtain the length and offset for a page in smb_rqst - * Input: rqst - a smb_rqst, page - a page index for rqst - * Output: *len - the length for this page, *offset - the offset for this page + * @rqst: The request descriptor + * @page: The index of the page to query + * @len: Where to store the length for this page: + * @offset: Where to store the offset for this page */ void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, unsigned int *len, unsigned int *offset) @@ -1152,6 +1160,8 @@ void extract_unc_hostname(const char *unc, const char **h, size_t *len) /** * copy_path_name - copy src path to dst, possibly truncating + * @dst: The destination buffer + * @src: The source name * * returns number of bytes written (including trailing nul) */ From c48977f020d5846215e2ff7e8172e7b46b3d64b4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 14:16:00 +0200 Subject: [PATCH 645/866] drm/amd/display: fix empty debug macros Using an empty macro expansion as a conditional expression produces a W=1 warning: drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.c: In function 'dce_aux_transfer_with_retries': drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.c:775:156: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 775 | "dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER"); | ^ drivers/gpu/drm/amd/amdgpu/../display/dc/dce/dce_aux.c:783:155: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 783 | "dce_aux_transfer_with_retries: AUX_RET_SUCCESS: AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK"); | ^ Expand it to "do { } while (0)" instead to make the expression more robust and avoid the warning. Fixes: 56aca2309301 ("drm/amd/display: Add AUX I2C tracing.") Signed-off-by: Arnd Bergmann Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_aux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index e14f99b4b0c3..3c3347341103 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -42,7 +42,7 @@ #define DC_LOGGER \ engine->ctx->logger -#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */ +#define DC_TRACE_LEVEL_MESSAGE(...) do { } while (0) #define IS_DC_I2CAUX_LOGGING_ENABLED() (false) #define LOG_FLAG_Error_I2cAux LOG_ERROR #define LOG_FLAG_I2cAux_DceAux LOG_I2C_AUX @@ -76,7 +76,7 @@ enum { #define DEFAULT_AUX_ENGINE_MULT 0 #define DEFAULT_AUX_ENGINE_LENGTH 69 -#define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */ +#define DC_TRACE_LEVEL_MESSAGE(...) do { } while (0) static void release_engine( struct dce_aux *engine) From 6de0653f7719bd0aa61f683fba16ae0e2c4ead64 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 17 Sep 2021 12:05:30 -0400 Subject: [PATCH 646/866] MAINTAINERS: fix up entry for AMD Powerplay Fix the path to cover both the older powerplay infrastructure and the newer SwSMU infrastructure. Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index ca6d6fde85cf..556957c5aa5c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -977,12 +977,12 @@ L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/amd-pmc.* -AMD POWERPLAY +AMD POWERPLAY AND SWSMU M: Evan Quan L: amd-gfx@lists.freedesktop.org S: Supported T: git https://gitlab.freedesktop.org/agd5f/linux.git -F: drivers/gpu/drm/amd/pm/powerplay/ +F: drivers/gpu/drm/amd/pm/ AMD PTDMA DRIVER M: Sanjay R Mehta From 7beb26dcedaa977ece5be7c712a66b7b6c66fc2b Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 13 Sep 2021 10:03:36 -0400 Subject: [PATCH 647/866] drm/amdkfd: SVM map to gpus check vma boundary SVM range may includes multiple VMAs with different vm_flags, if prange page index is the last page of the VMA offset + npages, update GPU mapping to create GPU page table with same VMA access permission. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9fc8021bb0ab..432d5aae0962 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1178,7 +1178,11 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, for (i = offset; i < offset + npages; i++) { last_domain = dma_addr[i] & SVM_RANGE_VRAM_DOMAIN; dma_addr[i] &= ~SVM_RANGE_VRAM_DOMAIN; - if ((prange->start + i) < prange->last && + + /* Collect all pages in the same address range and memory domain + * that can be mapped with a single call to update mapping. + */ + if (i < offset + npages - 1 && last_domain == (dma_addr[i + 1] & SVM_RANGE_VRAM_DOMAIN)) continue; From f63251184a81039ebc805306505838c2a073e51a Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Tue, 14 Sep 2021 16:33:40 -0400 Subject: [PATCH 648/866] drm/amdkfd: fix dma mapping leaking warning For xnack off, restore work dma unmap previous system memory page, and dma map the updated system memory page to update GPU mapping, this is not dma mapping leaking, remove the WARN_ONCE for dma mapping leaking. prange->dma_addr store the VRAM page pfn after the range migrated to VRAM, should not dma unmap VRAM page when updating GPU mapping or remove prange. Add helper svm_is_valid_dma_mapping_addr to check VRAM page and error cases. Mask out SVM_RANGE_VRAM_DOMAIN flag in dma_addr before calling amdgpu vm update to avoid BUG_ON(*addr & 0xFFFF00000000003FULL), and set it again immediately after. This flag is used to know the type of page later to dma unmapping system memory page. Fixes: 1d5dbfe6c06a ("drm/amdkfd: classify and map mixed svm range pages in GPU") Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 432d5aae0962..9d0f65a90002 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -118,6 +118,13 @@ static void svm_range_remove_notifier(struct svm_range *prange) mmu_interval_notifier_remove(&prange->notifier); } +static bool +svm_is_valid_dma_mapping_addr(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr && !dma_mapping_error(dev, dma_addr) && + !(dma_addr & SVM_RANGE_VRAM_DOMAIN); +} + static int svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange, unsigned long offset, unsigned long npages, @@ -139,8 +146,7 @@ svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange, addr += offset; for (i = 0; i < npages; i++) { - if (WARN_ONCE(addr[i] && !dma_mapping_error(dev, addr[i]), - "leaking dma mapping\n")) + if (svm_is_valid_dma_mapping_addr(dev, addr[i])) dma_unmap_page(dev, addr[i], PAGE_SIZE, dir); page = hmm_pfn_to_page(hmm_pfns[i]); @@ -209,7 +215,7 @@ void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr, return; for (i = offset; i < offset + npages; i++) { - if (!dma_addr[i] || dma_mapping_error(dev, dma_addr[i])) + if (!svm_is_valid_dma_mapping_addr(dev, dma_addr[i])) continue; pr_debug("dma unmapping 0x%llx\n", dma_addr[i] >> PAGE_SHIFT); dma_unmap_page(dev, dma_addr[i], PAGE_SIZE, dir); @@ -1165,7 +1171,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned long last_start; int last_domain; int r = 0; - int64_t i; + int64_t i, j; last_start = prange->start + offset; @@ -1205,6 +1211,10 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, NULL, dma_addr, &vm->last_update, &table_freed); + + for (j = last_start - prange->start; j <= i; j++) + dma_addr[j] |= last_domain; + if (r) { pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start); goto out; From 305d568b72f17f674155a2a8275f865f207b3808 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 16 Sep 2021 15:34:46 -0300 Subject: [PATCH 649/866] RDMA/cma: Ensure rdma_addr_cancel() happens before issuing more requests The FSM can run in a circle allowing rdma_resolve_ip() to be called twice on the same id_priv. While this cannot happen without going through the work, it violates the invariant that the same address resolution background request cannot be active twice. CPU 1 CPU 2 rdma_resolve_addr(): RDMA_CM_IDLE -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) #1 process_one_req(): for #1 addr_handler(): RDMA_CM_ADDR_QUERY -> RDMA_CM_ADDR_BOUND mutex_unlock(&id_priv->handler_mutex); [.. handler still running ..] rdma_resolve_addr(): RDMA_CM_ADDR_BOUND -> RDMA_CM_ADDR_QUERY rdma_resolve_ip(addr_handler) !! two requests are now on the req_list rdma_destroy_id(): destroy_id_handler_unlock(): _destroy_id(): cma_cancel_operation(): rdma_addr_cancel() // process_one_req() self removes it spin_lock_bh(&lock); cancel_delayed_work(&req->work); if (!list_empty(&req->list)) == true ! rdma_addr_cancel() returns after process_on_req #1 is done kfree(id_priv) process_one_req(): for #2 addr_handler(): mutex_lock(&id_priv->handler_mutex); !! Use after free on id_priv rdma_addr_cancel() expects there to be one req on the list and only cancels the first one. The self-removal behavior of the work only happens after the handler has returned. This yields a situations where the req_list can have two reqs for the same "handle" but rdma_addr_cancel() only cancels the first one. The second req remains active beyond rdma_destroy_id() and will use-after-free id_priv once it inevitably triggers. Fix this by remembering if the id_priv has called rdma_resolve_ip() and always cancel before calling it again. This ensures the req_list never gets more than one item in it and doesn't cost anything in the normal flow that never uses this strange error path. Link: https://lore.kernel.org/r/0-v1-3bc675b8006d+22-syz_cancel_uaf_jgg@nvidia.com Cc: stable@vger.kernel.org Fixes: e51060f08a61 ("IB: IP address based RDMA connection manager") Reported-by: syzbot+dc3dfba010d7671e05f5@syzkaller.appspotmail.com Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/cma.c | 23 +++++++++++++++++++++++ drivers/infiniband/core/cma_priv.h | 1 + 2 files changed, 24 insertions(+) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 8862b0e572f0..704ce595542c 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1783,6 +1783,14 @@ static void cma_cancel_operation(struct rdma_id_private *id_priv, { switch (state) { case RDMA_CM_ADDR_QUERY: + /* + * We can avoid doing the rdma_addr_cancel() based on state, + * only RDMA_CM_ADDR_QUERY has a work that could still execute. + * Notice that the addr_handler work could still be exiting + * outside this state, however due to the interaction with the + * handler_mutex the work is guaranteed not to touch id_priv + * during exit. + */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: @@ -3425,6 +3433,21 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { + /* + * The FSM can return back to RDMA_CM_ADDR_BOUND after + * rdma_resolve_ip() is called, eg through the error + * path in addr_handler(). If this happens the existing + * request must be canceled before issuing a new one. + * Since canceling a request is a bit slow and this + * oddball path is rare, keep track once a request has + * been issued. The track turns out to be a permanent + * state since this is the only cancel as it is + * immediately before rdma_resolve_ip(). + */ + if (id_priv->used_resolve_ip) + rdma_addr_cancel(&id->route.addr.dev_addr); + else + id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, diff --git a/drivers/infiniband/core/cma_priv.h b/drivers/infiniband/core/cma_priv.h index 5c463da99845..f92f101ea981 100644 --- a/drivers/infiniband/core/cma_priv.h +++ b/drivers/infiniband/core/cma_priv.h @@ -91,6 +91,7 @@ struct rdma_id_private { u8 afonly; u8 timeout; u8 min_rnr_timer; + u8 used_resolve_ip; enum ib_gid_type gid_type; /* From 8bd8d1dff9eb90255c030d2e52a4f65a7fef33a9 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 2 Sep 2021 22:26:31 +0100 Subject: [PATCH 650/866] vfio/pci: add missing identifier name in argument of function prototype The function prototype is missing an identifier name. Add one. Signed-off-by: Colin Ian King Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20210902212631.54260-1-colin.king@canonical.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 68198e0f2a63..a03b5a99c2da 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -565,7 +565,7 @@ static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot) } struct vfio_pci_walk_info { - int (*fn)(struct pci_dev *, void *data); + int (*fn)(struct pci_dev *pdev, void *data); void *data; struct pci_dev *pdev; bool slot; From ab39d3cef526ba09c4c6923b4cd7e6ec1c5d4faa Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Thu, 23 Sep 2021 11:58:43 +0800 Subject: [PATCH 651/866] drm/amd/pm: Update intermediate power state for SI Update the current state as boot state during dpm initialization. During the subsequent initialization, set_power_state gets called to transition to the final power state. set_power_state refers to values from the current state and without current state populated, it could result in NULL pointer dereference. For ex: on platforms where PCI speed change is supported through ACPI ATCS method, the link speed of current state needs to be queried before deciding on changing to final power state's link speed. The logic to query ATCS-support was broken on certain platforms. The issue became visible when broken ATCS-support logic got fixed with commit f9b7f3703ff9 ("drm/amdgpu/acpi: make ATPX/ATCS structures global (v2)"). Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1698 Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/powerplay/si_dpm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c index bdbbeb959c68..81f82aa05ec2 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c @@ -6867,6 +6867,8 @@ static int si_dpm_enable(struct amdgpu_device *adev) si_enable_auto_throttle_source(adev, AMDGPU_DPM_AUTO_THROTTLE_SRC_THERMAL, true); si_thermal_start_thermal_controller(adev); + ni_update_current_ps(adev, boot_ps); + return 0; } From 7d6687200a939176847090bbde5cb79a82792a2f Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 17 Sep 2021 14:32:14 -0400 Subject: [PATCH 652/866] drm/amdkfd: handle svm migrate init error If svm migration init failed to create pgmap for device memory, set pgmap type to 0 to disable device SVM support capability. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index dab290a4d19d..165e0ebb619d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -894,6 +894,9 @@ int svm_migrate_init(struct amdgpu_device *adev) r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); + + /* Disable SVM support capability */ + pgmap->type = 0; devm_release_mem_region(adev->dev, res->start, res->end - res->start + 1); return PTR_ERR(r); From 197ae17722e989942b36e33e044787877f158574 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 20 Sep 2021 17:25:52 -0400 Subject: [PATCH 653/866] drm/amdkfd: fix svm_migrate_fini warning Device manager releases device-specific resources when a driver disconnects from a device, devm_memunmap_pages and devm_release_mem_region calls in svm_migrate_fini are redundant. It causes below warning trace after patch "drm/amdgpu: Split amdgpu_device_fini into early and late", so remove function svm_migrate_fini. BUG: https://gitlab.freedesktop.org/drm/amd/-/issues/1718 WARNING: CPU: 1 PID: 3646 at drivers/base/devres.c:795 devm_release_action+0x51/0x60 Call Trace: ? memunmap_pages+0x360/0x360 svm_migrate_fini+0x2d/0x60 [amdgpu] kgd2kfd_device_exit+0x23/0xa0 [amdgpu] amdgpu_amdkfd_device_fini_sw+0x1d/0x30 [amdgpu] amdgpu_device_fini_sw+0x45/0x290 [amdgpu] amdgpu_driver_release_kms+0x12/0x30 [amdgpu] drm_dev_release+0x20/0x40 [drm] release_nodes+0x196/0x1e0 device_release_driver_internal+0x104/0x1d0 driver_detach+0x47/0x90 bus_remove_driver+0x7a/0xd0 pci_unregister_driver+0x3d/0x90 amdgpu_exit+0x11/0x20 [amdgpu] Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_device.c | 1 - drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 13 ++++--------- drivers/gpu/drm/amd/amdkfd/kfd_migrate.h | 5 ----- 3 files changed, 4 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 98d1b3ab3a46..c2a4d920da40 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -971,7 +971,6 @@ out: void kgd2kfd_device_exit(struct kfd_dev *kfd) { if (kfd->init_complete) { - svm_migrate_fini((struct amdgpu_device *)kfd->kgd); device_queue_manager_uninit(kfd->dqm); kfd_interrupt_exit(kfd); kfd_topology_remove_device(kfd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 165e0ebb619d..4a16e3c257b9 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -891,6 +891,10 @@ int svm_migrate_init(struct amdgpu_device *adev) pgmap->ops = &svm_migrate_pgmap_ops; pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev); pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + + /* Device manager releases device-specific resources, memory region and + * pgmap when driver disconnects from device. + */ r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { pr_err("failed to register HMM device memory\n"); @@ -911,12 +915,3 @@ int svm_migrate_init(struct amdgpu_device *adev) return 0; } - -void svm_migrate_fini(struct amdgpu_device *adev) -{ - struct dev_pagemap *pgmap = &adev->kfd.dev->pgmap; - - devm_memunmap_pages(adev->dev, pgmap); - devm_release_mem_region(adev->dev, pgmap->range.start, - pgmap->range.end - pgmap->range.start + 1); -} diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index 0de76b5d4973..2f5b3394c9ed 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -47,7 +47,6 @@ unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); int svm_migrate_init(struct amdgpu_device *adev); -void svm_migrate_fini(struct amdgpu_device *adev); #else @@ -55,10 +54,6 @@ static inline int svm_migrate_init(struct amdgpu_device *adev) { return 0; } -static inline void svm_migrate_fini(struct amdgpu_device *adev) -{ - /* empty */ -} #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */ From 28406a21999152ff7faa30b194f734565bdd8e0d Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 23 Sep 2021 15:01:27 +0530 Subject: [PATCH 654/866] pinctrl: qcom: sc7280: Add PM suspend callbacks Use PM suspend callbacks from msm core, without this the hog_sleep pins don't change state in suspend. Signed-off-by: Rajendra Nayak Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/1632389487-11283-1-git-send-email-rnayak@codeaurora.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-sc7280.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c index afddf6d60dbe..9017ede409c9 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c @@ -1496,6 +1496,7 @@ static const struct of_device_id sc7280_pinctrl_of_match[] = { static struct platform_driver sc7280_pinctrl_driver = { .driver = { .name = "sc7280-pinctrl", + .pm = &msm_pinctrl_dev_pm_ops, .of_match_table = sc7280_pinctrl_of_match, }, .probe = sc7280_pinctrl_probe, From 4f22262280ccb5c0a18a42029313938aabfaff12 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 23 Sep 2021 12:42:35 -0500 Subject: [PATCH 655/866] cifs: Clear modified attribute bit from inode flags Clear CIFS_INO_MODIFIED_ATTR bit from inode flags after updating mtime and ctime Signed-off-by: Rohith Surabattula Reviewed-by: Paulo Alcantara (SUSE) Acked-by: Ronnie Sahlberg Cc: stable@vger.kernel.org # 5.13+ Signed-off-by: Steve French --- fs/cifs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0ab5bb24b8ca..13f3182cf796 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -884,7 +884,7 @@ int cifs_close(struct inode *inode, struct file *file) cinode->lease_granted && !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { - if (test_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { + if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { inode->i_ctime = inode->i_mtime = current_time(inode); cifs_fscache_update_inode_cookie(inode); } From b06d893ef2492245d0319b4136edb4c346b687a3 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 23 Sep 2021 16:00:31 -0500 Subject: [PATCH 656/866] smb3: correct smb3 ACL security descriptor Address warning: fs/smbfs_client/smb2pdu.c:2425 create_sd_buf() warn: struct type mismatch 'smb3_acl vs cifs_acl' Pointed out by Dan Carpenter via smatch code analysis tool Reported-by: Dan Carpenter Acked-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 672ae78e866a..7829c590eeac 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2397,7 +2397,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd); /* Ship the ACL for now. we will copy it into buf later. */ aclptr = ptr; - ptr += sizeof(struct cifs_acl); + ptr += sizeof(struct smb3_acl); /* create one ACE to hold the mode embedded in reserved special SID */ acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode); @@ -2422,7 +2422,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ acl.AclSize = cpu_to_le16(acl_size); acl.AceCount = cpu_to_le16(ace_count); - memcpy(aclptr, &acl, sizeof(struct cifs_acl)); + memcpy(aclptr, &acl, sizeof(struct smb3_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); *len = roundup(ptr - (__u8 *)buf, 8); From 1db1aa98871defd9316d13f59708f2277c4f9232 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 23 Sep 2021 18:52:40 -0500 Subject: [PATCH 657/866] smb3: correct server pointer dereferencing check to be more consistent Address warning: fs/smbfs_client/misc.c:273 header_assemble() warn: variable dereferenced before check 'treeCon->ses->server' Pointed out by Dan Carpenter via smatch code analysis tool Although the check is likely unneeded, adding it makes the code more consistent and easier to read, as the same check is done elsewhere in the function. Reported-by: Dan Carpenter Acked-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/misc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index f2916b51652a..bb1185fff8cc 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -264,7 +264,8 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , /* Uid is not converted */ buffer->Uid = treeCon->ses->Suid; - buffer->Mid = get_next_mid(treeCon->ses->server); + if (treeCon->ses->server) + buffer->Mid = get_next_mid(treeCon->ses->server); } if (treeCon->Flags & SMB_SHARE_IS_IN_DFS) buffer->Flags2 |= SMBFLG2_DFS; From 9ed38fd4a15417cac83967360cf20b853bfab9b6 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 23 Sep 2021 19:18:37 -0500 Subject: [PATCH 658/866] cifs: fix incorrect check for null pointer in header_assemble Although very unlikely that the tlink pointer would be null in this case, get_next_mid function can in theory return null (but not an error) so need to check for null (not for IS_ERR, which can not be returned here). Address warning: fs/smbfs_client/connect.c:2392 cifs_match_super() warn: 'tlink' isn't an ERR_PTR Pointed out by Dan Carpenter via smatch code analysis tool CC: stable@vger.kernel.org Reported-by: Dan Carpenter Acked-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/connect.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 7881115cfbee..c3b94c1e4591 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2389,9 +2389,10 @@ cifs_match_super(struct super_block *sb, void *data) spin_lock(&cifs_tcp_ses_lock); cifs_sb = CIFS_SB(sb); tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); - if (IS_ERR(tlink)) { + if (tlink == NULL) { + /* can not match superblock if tlink were ever null */ spin_unlock(&cifs_tcp_ses_lock); - return rc; + return 0; } tcon = tlink_tcon(tlink); ses = tcon->ses; From fbf094ce524113c694acabf3d385883f88372829 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Thu, 23 Sep 2021 22:00:33 +0000 Subject: [PATCH 659/866] selftests: KVM: Call ucall_init when setting up in rseq_test While x86 does not require any additional setup to use the ucall infrastructure, arm64 needs to set up the MMIO address used to signal a ucall to userspace. rseq_test does not initialize the MMIO address, resulting in the test spinning indefinitely. Fix the issue by calling ucall_init() during setup. Fixes: 61e52f1630f5 ("KVM: selftests: Add a test for KVM_RUN+rseq to detect task migration bugs") Signed-off-by: Oliver Upton Message-Id: <20210923220033.4172362-1-oupton@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/rseq_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 060538bd405a..c5e0dd664a7b 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -180,6 +180,7 @@ int main(int argc, char *argv[]) * CPU affinity. */ vm = vm_create_default(VCPU_ID, 0, guest_code); + ucall_init(vm, NULL); pthread_create(&migration_thread, NULL, migration_worker, 0); From 386ca9d7fd189b641bc5a82871e38dea9f67af85 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 24 Sep 2021 00:51:47 +0000 Subject: [PATCH 660/866] selftests: KVM: Explicitly use movq to read xmm registers Compiling the KVM selftests with clang emits the following warning: >> include/x86_64/processor.h:297:25: error: variable 'xmm0' is uninitialized when used here [-Werror,-Wuninitialized] >> return (unsigned long)xmm0; where xmm0 is accessed via an uninitialized register variable. Indeed, this is a misuse of register variables, which really should only be used for specifying register constraints on variables passed to inline assembly. Rather than attempting to read xmm registers via register variables, just explicitly perform the movq from the desired xmm register. Fixes: 783e9e51266e ("kvm: selftests: add API testing infrastructure") Signed-off-by: Oliver Upton Message-Id: <20210924005147.1122357-1-oupton@google.com> Reviewed-by: Ricardo Koller Signed-off-by: Paolo Bonzini --- .../selftests/kvm/include/x86_64/processor.h | 34 +++++++++---------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 242ae8e09a65..eba8bd08293e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -312,37 +312,37 @@ static inline void set_xmm(int n, unsigned long val) } } -typedef unsigned long v1di __attribute__ ((vector_size (8))); +#define GET_XMM(__xmm) \ +({ \ + unsigned long __val; \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val) : : #__xmm); \ + __val; \ +}) + static inline unsigned long get_xmm(int n) { assert(n >= 0 && n <= 7); - register v1di xmm0 __asm__("%xmm0"); - register v1di xmm1 __asm__("%xmm1"); - register v1di xmm2 __asm__("%xmm2"); - register v1di xmm3 __asm__("%xmm3"); - register v1di xmm4 __asm__("%xmm4"); - register v1di xmm5 __asm__("%xmm5"); - register v1di xmm6 __asm__("%xmm6"); - register v1di xmm7 __asm__("%xmm7"); switch (n) { case 0: - return (unsigned long)xmm0; + return GET_XMM(xmm0); case 1: - return (unsigned long)xmm1; + return GET_XMM(xmm1); case 2: - return (unsigned long)xmm2; + return GET_XMM(xmm2); case 3: - return (unsigned long)xmm3; + return GET_XMM(xmm3); case 4: - return (unsigned long)xmm4; + return GET_XMM(xmm4); case 5: - return (unsigned long)xmm5; + return GET_XMM(xmm5); case 6: - return (unsigned long)xmm6; + return GET_XMM(xmm6); case 7: - return (unsigned long)xmm7; + return GET_XMM(xmm7); } + + /* never reached */ return 0; } From 3bd18ba7d859eb1fbef3beb1e80c24f6f7d7596c Mon Sep 17 00:00:00 2001 From: Uwe Brandt Date: Tue, 21 Sep 2021 19:54:46 +0200 Subject: [PATCH 661/866] USB: serial: cp210x: add ID for GW Instek GDM-834x Digital Multimeter Add the USB serial device ID for the GW Instek GDM-834x Digital Multimeter. Signed-off-by: Uwe Brandt Link: https://lore.kernel.org/r/YUxFl3YUCPGJZd8Y@hovoldconsulting.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index fd51498ab108..189279869a8b 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -233,6 +233,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1FB9, 0x0602) }, /* Lake Shore Model 648 Magnet Power Supply */ { USB_DEVICE(0x1FB9, 0x0700) }, /* Lake Shore Model 737 VSM Controller */ { USB_DEVICE(0x1FB9, 0x0701) }, /* Lake Shore Model 776 Hall Matrix */ + { USB_DEVICE(0x2184, 0x0030) }, /* GW Instek GDM-834x Digital Multimeter */ { USB_DEVICE(0x2626, 0xEA60) }, /* Aruba Networks 7xxx USB Serial Console */ { USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */ { USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */ From 9e3eed534f8235a4a596a9dae5b8a6425d81ea1a Mon Sep 17 00:00:00 2001 From: Slark Xiao Date: Fri, 17 Sep 2021 19:01:06 +0800 Subject: [PATCH 662/866] USB: serial: option: add device id for Foxconn T99W265 Adding support for Foxconn device T99W265 for enumeration with PID 0xe0db. usb-devices output for 0xe0db T: Bus=04 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 19 Spd=5000 MxCh= 0 D: Ver= 3.20 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=0489 ProdID=e0db Rev=05.04 S: Manufacturer=Microsoft S: Product=Generic Mobile Broadband Adapter S: SerialNumber=6c50f452 C: #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option I: If#=0x3 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option if0/1: MBIM, if2:Diag, if3:GNSS, if4: Modem Signed-off-by: Slark Xiao Link: https://lore.kernel.org/r/20210917110106.9852-1-slark_xiao@163.com [ johan: use USB_DEVICE_INTERFACE_CLASS(), amend comment ] Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 02a35f26ee82..6cfb5d33609f 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -2075,6 +2075,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ From 505d9dcb0f7ddf9d075e729523a33d38642ae680 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 26 Aug 2021 16:04:27 +0300 Subject: [PATCH 663/866] crypto: ccp - fix resource leaks in ccp_run_aes_gcm_cmd() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are three bugs in this code: 1) If we ccp_init_data() fails for &src then we need to free aad. Use goto e_aad instead of goto e_ctx. 2) The label to free the &final_wa was named incorrectly as "e_tag" but it should have been "e_final_wa". One error path leaked &final_wa. 3) The &tag was leaked on one error path. In that case, I added a free before the goto because the resource was local to that block. Fixes: 36cf515b9bbe ("crypto: ccp - Enable support for AES GCM on v5 CCPs") Reported-by: "minihanshen(沈明航)" Signed-off-by: Dan Carpenter Reviewed-by: John Allen Tested-by: John Allen Signed-off-by: Herbert Xu --- drivers/crypto/ccp/ccp-ops.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index bb88198c874e..aa4e1a500691 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -778,7 +778,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) in_place ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); if (ret) - goto e_ctx; + goto e_aad; if (in_place) { dst = src; @@ -863,7 +863,7 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) op.u.aes.size = 0; ret = cmd_q->ccp->vdata->perform->aes(&op); if (ret) - goto e_dst; + goto e_final_wa; if (aes->action == CCP_AES_ACTION_ENCRYPT) { /* Put the ciphered tag after the ciphertext. */ @@ -873,17 +873,19 @@ ccp_run_aes_gcm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) ret = ccp_init_dm_workarea(&tag, cmd_q, authsize, DMA_BIDIRECTIONAL); if (ret) - goto e_tag; + goto e_final_wa; ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize); - if (ret) - goto e_tag; + if (ret) { + ccp_dm_free(&tag); + goto e_final_wa; + } ret = crypto_memneq(tag.address, final_wa.address, authsize) ? -EBADMSG : 0; ccp_dm_free(&tag); } -e_tag: +e_final_wa: ccp_dm_free(&final_wa); e_dst: From 0e14ef38669ce4faa80589247fe8ed8a3780f414 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 21 Sep 2021 22:40:26 -0700 Subject: [PATCH 664/866] crypto: x86/sm4 - Fix frame pointer stack corruption sm4_aesni_avx_crypt8() sets up the frame pointer (which includes pushing RBP) before doing a conditional sibling call to sm4_aesni_avx_crypt4(), which sets up an additional frame pointer. Things will not go well when sm4_aesni_avx_crypt4() pops only the innermost single frame pointer and then tries to return to the outermost frame pointer. Sibling calls need to occur with an empty stack frame. Do the conditional sibling call *before* setting up the stack pointer. This fixes the following warning: arch/x86/crypto/sm4-aesni-avx-asm_64.o: warning: objtool: sm4_aesni_avx_crypt8()+0x8: sibling call from callable instruction with modified stack frame Fixes: a7ee22ee1445 ("crypto: x86/sm4 - add AES-NI/AVX/x86_64 implementation") Reported-by: kernel test robot Reported-by: Arnd Bergmann Acked-by: Peter Zijlstra (Intel) Reviewed-by: Tianjia Zhang Signed-off-by: Josh Poimboeuf Signed-off-by: Herbert Xu --- arch/x86/crypto/sm4-aesni-avx-asm_64.S | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index fa2c3f50aecb..18d2f5199194 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8) * %rdx: src (1..8 blocks) * %rcx: num blocks (1..8) */ - FRAME_BEGIN - cmpq $5, %rcx; jb sm4_aesni_avx_crypt4; + + FRAME_BEGIN + vmovdqu (0 * 16)(%rdx), RA0; vmovdqu (1 * 16)(%rdx), RA1; vmovdqu (2 * 16)(%rdx), RA2; From f7e745f8e94492a8ac0b0a26e25f2b19d342918f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 23 Sep 2021 00:05:04 -0400 Subject: [PATCH 665/866] sctp: break out if skb_header_pointer returns NULL in sctp_rcv_ootb We should always check if skb_header_pointer's return is NULL before using it, otherwise it may cause null-ptr-deref, as syzbot reported: KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:sctp_rcv_ootb net/sctp/input.c:705 [inline] RIP: 0010:sctp_rcv+0x1d84/0x3220 net/sctp/input.c:196 Call Trace: sctp6_rcv+0x38/0x60 net/sctp/ipv6.c:1109 ip6_protocol_deliver_rcu+0x2e9/0x1ca0 net/ipv6/ip6_input.c:422 ip6_input_finish+0x62/0x170 net/ipv6/ip6_input.c:463 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip6_input+0x9c/0xd0 net/ipv6/ip6_input.c:472 dst_input include/net/dst.h:460 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ipv6_rcv+0x28c/0x3c0 net/ipv6/ip6_input.c:297 Fixes: 3acb50c18d8d ("sctp: delay as much as possible skb_linearize") Reported-by: syzbot+581aff2ae6b860625116@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/input.c b/net/sctp/input.c index 5ef86fdb1176..1f1786021d9c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -702,7 +702,7 @@ static int sctp_rcv_ootb(struct sk_buff *skb) ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(_ch)) + if (!ch || ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); From ea1300b9df7c8e8b65695a08b8f6aaf4b25fec9c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Sep 2021 17:04:11 -0700 Subject: [PATCH 666/866] mptcp: don't return sockets in foreign netns mptcp_token_get_sock() may return a mptcp socket that is in a different net namespace than the socket that received the token value. The mptcp syncookie code path had an explicit check for this, this moves the test into mptcp_token_get_sock() function. Eventually token.c should be converted to pernet storage, but such change is not suitable for net tree. Fixes: 2c5ebd001d4f0 ("mptcp: refactor token container") Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/mptcp_diag.c | 2 +- net/mptcp/protocol.h | 2 +- net/mptcp/subflow.c | 2 +- net/mptcp/syncookies.c | 13 +------------ net/mptcp/token.c | 11 ++++++++--- net/mptcp/token_test.c | 14 ++++++++------ 6 files changed, 20 insertions(+), 24 deletions(-) diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f48eb6315bbb..292374fb0779 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -36,7 +36,7 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb, struct sock *sk; net = sock_net(in_skb->sk); - msk = mptcp_token_get_sock(req->id.idiag_cookie[0]); + msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]); if (!msk) goto out_nosk; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d3e6fd1615f1..dc984676c5eb 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -709,7 +709,7 @@ int mptcp_token_new_connect(struct sock *sk); void mptcp_token_accept(struct mptcp_subflow_request_sock *r, struct mptcp_sock *msk); bool mptcp_token_exists(u32 token); -struct mptcp_sock *mptcp_token_get_sock(u32 token); +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); void mptcp_token_destroy(struct mptcp_sock *msk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 1de7ce883c37..6172f380dfb7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -86,7 +86,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) struct mptcp_sock *msk; int local_id; - msk = mptcp_token_get_sock(subflow_req->token); + msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); return NULL; diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c index 37127781aee9..7f22526346a7 100644 --- a/net/mptcp/syncookies.c +++ b/net/mptcp/syncookies.c @@ -108,18 +108,12 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl e->valid = 0; - msk = mptcp_token_get_sock(e->token); + msk = mptcp_token_get_sock(net, e->token); if (!msk) { spin_unlock_bh(&join_entry_locks[i]); return false; } - /* If this fails, the token got re-used in the mean time by another - * mptcp socket in a different netns, i.e. entry is outdated. - */ - if (!net_eq(sock_net((struct sock *)msk), net)) - goto err_put; - subflow_req->remote_nonce = e->remote_nonce; subflow_req->local_nonce = e->local_nonce; subflow_req->backup = e->backup; @@ -128,11 +122,6 @@ bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subfl subflow_req->msk = msk; spin_unlock_bh(&join_entry_locks[i]); return true; - -err_put: - spin_unlock_bh(&join_entry_locks[i]); - sock_put((struct sock *)msk); - return false; } void __init mptcp_join_cookie_init(void) diff --git a/net/mptcp/token.c b/net/mptcp/token.c index a98e554b034f..e581b341c5be 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -231,6 +231,7 @@ found: /** * mptcp_token_get_sock - retrieve mptcp connection sock using its token + * @net: restrict to this namespace * @token: token of the mptcp connection to retrieve * * This function returns the mptcp connection structure with the given token. @@ -238,7 +239,7 @@ found: * * returns NULL if no connection with the given token value exists. */ -struct mptcp_sock *mptcp_token_get_sock(u32 token) +struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token) { struct hlist_nulls_node *pos; struct token_bucket *bucket; @@ -251,11 +252,15 @@ struct mptcp_sock *mptcp_token_get_sock(u32 token) again: sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) { msk = mptcp_sk(sk); - if (READ_ONCE(msk->token) != token) + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) continue; + if (!refcount_inc_not_zero(&sk->sk_refcnt)) goto not_found; - if (READ_ONCE(msk->token) != token) { + + if (READ_ONCE(msk->token) != token || + !net_eq(sock_net(sk), net)) { sock_put(sk); goto again; } diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index e1bd6f0a0676..5d984bec1cd8 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -11,6 +11,7 @@ static struct mptcp_subflow_request_sock *build_req_sock(struct kunit *test) GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, req); mptcp_token_init_request((struct request_sock *)req); + sock_net_set((struct sock *)req, &init_net); return req; } @@ -22,7 +23,7 @@ static void mptcp_token_test_req_basic(struct kunit *test) KUNIT_ASSERT_EQ(test, 0, mptcp_token_new_request((struct request_sock *)req)); KUNIT_EXPECT_NE(test, 0, (int)req->token); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(req->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, req->token)); /* cleanup */ mptcp_token_destroy_request((struct request_sock *)req); @@ -55,6 +56,7 @@ static struct mptcp_sock *build_msk(struct kunit *test) msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); + sock_net_set((struct sock *)msk, &init_net); return msk; } @@ -74,11 +76,11 @@ static void mptcp_token_test_msk_basic(struct kunit *test) mptcp_token_new_connect((struct sock *)icsk)); KUNIT_EXPECT_NE(test, 0, (int)ctx->token); KUNIT_EXPECT_EQ(test, ctx->token, msk->token); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, ctx->token)); KUNIT_EXPECT_EQ(test, 2, (int)refcount_read(&sk->sk_refcnt)); mptcp_token_destroy(msk); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(ctx->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, ctx->token)); } static void mptcp_token_test_accept(struct kunit *test) @@ -90,11 +92,11 @@ static void mptcp_token_test_accept(struct kunit *test) mptcp_token_new_request((struct request_sock *)req)); msk->token = req->token; mptcp_token_accept(req, msk); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* this is now a no-op */ mptcp_token_destroy_request((struct request_sock *)req); - KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); @@ -116,7 +118,7 @@ static void mptcp_token_test_destroyed(struct kunit *test) /* simulate race on removal */ refcount_set(&sk->sk_refcnt, 0); - KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(msk->token)); + KUNIT_EXPECT_PTR_EQ(test, null_msk, mptcp_token_get_sock(&init_net, msk->token)); /* cleanup */ mptcp_token_destroy(msk); From 3f4a08909e2c740f8045efc74c4cf82eeaae3e36 Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Thu, 23 Sep 2021 17:04:12 -0700 Subject: [PATCH 667/866] mptcp: allow changing the 'backup' bit when no sockets are open current Linux refuses to change the 'backup' bit of MPTCP endpoints, i.e. using MPTCP_PM_CMD_SET_FLAGS, unless it finds (at least) one subflow that matches the endpoint address. There is no reason for that, so we can just ignore the return value of mptcp_nl_addr_backup(). In this way, endpoints can reconfigure their 'backup' flag even if no MPTCP sockets are open (or more generally, in case the MP_PRIO message is not sent out). Fixes: 0f9f696a502e ("mptcp: add set_flags command in PM netlink") Signed-off-by: Davide Caratti Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/pm_netlink.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c4f9a5ce3815..050eea231528 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1718,9 +1718,7 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) list_for_each_entry(entry, &pernet->local_addr_list, list) { if (addresses_equal(&entry->addr, &addr.addr, true)) { - ret = mptcp_nl_addr_backup(net, &entry->addr, bkup); - if (ret) - return ret; + mptcp_nl_addr_backup(net, &entry->addr, bkup); if (bkup) entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; From 5ba1071f7554c4027bdbd712a146111de57918de Mon Sep 17 00:00:00 2001 From: Numfor Mbiziwo-Tiapo Date: Thu, 23 Sep 2021 09:18:43 -0700 Subject: [PATCH 668/866] x86/insn, tools/x86: Fix undefined behavior due to potential unaligned accesses Don't perform unaligned loads in __get_next() and __peek_nbyte_next() as these are forms of undefined behavior: "A pointer to an object or incomplete type may be converted to a pointer to a different object or incomplete type. If the resulting pointer is not correctly aligned for the pointed-to type, the behavior is undefined." (from http://www.open-std.org/jtc1/sc22/wg14/www/docs/n1256.pdf) These problems were identified using the undefined behavior sanitizer (ubsan) with the tools version of the code and perf test. [ bp: Massage commit message. ] Signed-off-by: Numfor Mbiziwo-Tiapo Signed-off-by: Ian Rogers Signed-off-by: Borislav Petkov Acked-by: Masami Hiramatsu Link: https://lkml.kernel.org/r/20210923161843.751834-1-irogers@google.com --- arch/x86/lib/insn.c | 4 ++-- tools/arch/x86/lib/insn.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 058f19b20465..c565def611e2 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -37,10 +37,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index c41f95815480..797699462cd8 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -37,10 +37,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); }) + ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) From 4bb0bd81ce5e97092dfda6a106d414b703ec0ee8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Jul 2021 17:19:00 +0000 Subject: [PATCH 669/866] m68k: Handle arrivals of multiple signals correctly When we have several pending signals, have entered with the kernel with large exception frame *and* have already built at least one sigframe, regs->stkadj is going to be non-zero and regs->format/sr/pc are going to be junk - the real values are in shifted exception stack frame we'd built when putting together the first sigframe. If that happens, subsequent sigframes are going to be garbage. Not hard to fix - just need to find the "adjusted" frame first and look for format/vector/sr/pc in it. Signed-off-by: Al Viro Tested-by: Michael Schmitz Reviewed-by: Michael Schmitz Tested-by: Finn Thain Link: https://lore.kernel.org/r/YP2dBIAPTaVvHiZ6@zeniv-ca.linux.org.uk Signed-off-by: Geert Uytterhoeven --- arch/m68k/kernel/signal.c | 88 +++++++++++++++++++-------------------- 1 file changed, 42 insertions(+), 46 deletions(-) diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 8f215e79e70e..cd11eb101eac 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -447,7 +447,7 @@ static inline void save_fpu_state(struct sigcontext *sc, struct pt_regs *regs) if (CPU_IS_060 ? sc->sc_fpstate[2] : sc->sc_fpstate[0]) { fpu_version = sc->sc_fpstate[0]; - if (CPU_IS_020_OR_030 && + if (CPU_IS_020_OR_030 && !regs->stkadj && regs->vector >= (VEC_FPBRUC * 4) && regs->vector <= (VEC_FPNAN * 4)) { /* Clear pending exception in 68882 idle frame */ @@ -510,7 +510,7 @@ static inline int rt_save_fpu_state(struct ucontext __user *uc, struct pt_regs * if (!(CPU_IS_060 || CPU_IS_COLDFIRE)) context_size = fpstate[1]; fpu_version = fpstate[0]; - if (CPU_IS_020_OR_030 && + if (CPU_IS_020_OR_030 && !regs->stkadj && regs->vector >= (VEC_FPBRUC * 4) && regs->vector <= (VEC_FPNAN * 4)) { /* Clear pending exception in 68882 idle frame */ @@ -832,18 +832,24 @@ badframe: return 0; } +static inline struct pt_regs *rte_regs(struct pt_regs *regs) +{ + return (void *)regs + regs->stkadj; +} + static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, unsigned long mask) { + struct pt_regs *tregs = rte_regs(regs); sc->sc_mask = mask; sc->sc_usp = rdusp(); sc->sc_d0 = regs->d0; sc->sc_d1 = regs->d1; sc->sc_a0 = regs->a0; sc->sc_a1 = regs->a1; - sc->sc_sr = regs->sr; - sc->sc_pc = regs->pc; - sc->sc_formatvec = regs->format << 12 | regs->vector; + sc->sc_sr = tregs->sr; + sc->sc_pc = tregs->pc; + sc->sc_formatvec = tregs->format << 12 | tregs->vector; save_a5_state(sc, regs); save_fpu_state(sc, regs); } @@ -851,6 +857,7 @@ static void setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs *regs) { struct switch_stack *sw = (struct switch_stack *)regs - 1; + struct pt_regs *tregs = rte_regs(regs); greg_t __user *gregs = uc->uc_mcontext.gregs; int err = 0; @@ -871,9 +878,9 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs * err |= __put_user(sw->a5, &gregs[13]); err |= __put_user(sw->a6, &gregs[14]); err |= __put_user(rdusp(), &gregs[15]); - err |= __put_user(regs->pc, &gregs[16]); - err |= __put_user(regs->sr, &gregs[17]); - err |= __put_user((regs->format << 12) | regs->vector, &uc->uc_formatvec); + err |= __put_user(tregs->pc, &gregs[16]); + err |= __put_user(tregs->sr, &gregs[17]); + err |= __put_user((tregs->format << 12) | tregs->vector, &uc->uc_formatvec); err |= rt_save_fpu_state(uc, regs); return err; } @@ -890,13 +897,14 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct sigframe __user *frame; - int fsize = frame_extra_sizes(regs->format); + struct pt_regs *tregs = rte_regs(regs); + int fsize = frame_extra_sizes(tregs->format); struct sigcontext context; int err = 0, sig = ksig->sig; if (fsize < 0) { pr_debug("setup_frame: Unknown frame format %#x\n", - regs->format); + tregs->format); return -EFAULT; } @@ -907,7 +915,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, err |= __put_user(sig, &frame->sig); - err |= __put_user(regs->vector, &frame->code); + err |= __put_user(tregs->vector, &frame->code); err |= __put_user(&frame->sc, &frame->psc); if (_NSIG_WORDS > 1) @@ -933,34 +941,28 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, push_cache ((unsigned long) &frame->retcode); - /* - * Set up registers for signal handler. All the state we are about - * to destroy is successfully copied to sigframe. - */ - wrusp ((unsigned long) frame); - regs->pc = (unsigned long) ksig->ka.sa.sa_handler; - adjustformat(regs); - /* * This is subtle; if we build more than one sigframe, all but the * first one will see frame format 0 and have fsize == 0, so we won't * screw stkadj. */ - if (fsize) + if (fsize) { regs->stkadj = fsize; - - /* Prepare to skip over the extra stuff in the exception frame. */ - if (regs->stkadj) { - struct pt_regs *tregs = - (struct pt_regs *)((ulong)regs + regs->stkadj); + tregs = rte_regs(regs); pr_debug("Performing stackadjust=%04lx\n", regs->stkadj); - /* This must be copied with decreasing addresses to - handle overlaps. */ tregs->vector = 0; tregs->format = 0; - tregs->pc = regs->pc; tregs->sr = regs->sr; } + + /* + * Set up registers for signal handler. All the state we are about + * to destroy is successfully copied to sigframe. + */ + wrusp ((unsigned long) frame); + tregs->pc = (unsigned long) ksig->ka.sa.sa_handler; + adjustformat(regs); + return 0; } @@ -968,7 +970,8 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; - int fsize = frame_extra_sizes(regs->format); + struct pt_regs *tregs = rte_regs(regs); + int fsize = frame_extra_sizes(tregs->format); int err = 0, sig = ksig->sig; if (fsize < 0) { @@ -1018,34 +1021,27 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, push_cache ((unsigned long) &frame->retcode); - /* - * Set up registers for signal handler. All the state we are about - * to destroy is successfully copied to sigframe. - */ - wrusp ((unsigned long) frame); - regs->pc = (unsigned long) ksig->ka.sa.sa_handler; - adjustformat(regs); - /* * This is subtle; if we build more than one sigframe, all but the * first one will see frame format 0 and have fsize == 0, so we won't * screw stkadj. */ - if (fsize) + if (fsize) { regs->stkadj = fsize; - - /* Prepare to skip over the extra stuff in the exception frame. */ - if (regs->stkadj) { - struct pt_regs *tregs = - (struct pt_regs *)((ulong)regs + regs->stkadj); + tregs = rte_regs(regs); pr_debug("Performing stackadjust=%04lx\n", regs->stkadj); - /* This must be copied with decreasing addresses to - handle overlaps. */ tregs->vector = 0; tregs->format = 0; - tregs->pc = regs->pc; tregs->sr = regs->sr; } + + /* + * Set up registers for signal handler. All the state we are about + * to destroy is successfully copied to sigframe. + */ + wrusp ((unsigned long) frame); + tregs->pc = (unsigned long) ksig->ka.sa.sa_handler; + adjustformat(regs); return 0; } From 50e43a57334400668952f8e551c9d87d3ed2dfef Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Jul 2021 17:19:45 +0000 Subject: [PATCH 670/866] m68k: Update ->thread.esp0 before calling syscall_trace() in ret_from_signal We get there when sigreturn has performed obscene acts on kernel stack; in particular, the location of pt_regs has shifted. We are about to call syscall_trace(), which might stop for tracer. If that happens, we'd better have task_pt_regs() returning correct result... Fucked-up-by: Al Viro Fixes: bd6f56a75bb2 ("m68k: Missing syscall_trace() on sigreturn") Signed-off-by: Al Viro Tested-by: Michael Schmitz Reviewed-by: Michael Schmitz Tested-by: Finn Thain Link: https://lore.kernel.org/r/YP2dMWeV1LkHiOpr@zeniv-ca.linux.org.uk Signed-off-by: Geert Uytterhoeven --- arch/m68k/kernel/entry.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 9dd76fbb7c6b..ff9e842cec0f 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -186,6 +186,8 @@ ENTRY(ret_from_signal) movel %curptr@(TASK_STACK),%a1 tstb %a1@(TINFO_FLAGS+2) jge 1f + lea %sp@(SWITCH_STACK_SIZE),%a1 + movel %a1,%curptr@(TASK_THREAD+THREAD_ESP0) jbsr syscall_trace 1: RESTORE_SWITCH_STACK addql #4,%sp From 0d20abde987bed05a8963c8aa4276019d54ff9e7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Jul 2021 17:20:13 +0000 Subject: [PATCH 671/866] m68k: Leave stack mangling to asm wrapper of sigreturn() sigreturn has to deal with an unpleasant problem - exception stack frames have different sizes, depending upon the exception (and processor model, as well) and variable-sized part of exception frame may contain information needed for instruction restart. So when signal handler terminates and calls sigreturn to resume the execution at the place where we'd been when we caught the signal, it has to rearrange the frame at the bottom of kernel stack. Worse, it might need to open a gap in the kernel stack, shifting pt_regs towards lower addresses. Doing that from C is insane - we'd need to shift stack frames (return addresses, local variables, etc.) of C call chain, right under the nose of compiler and hope it won't fall apart horribly. What had been actually done is only slightly less insane - an inline asm in mangle_kernel_stack() moved the stuff around, then reset stack pointer and jumped to label in asm glue. However, we can avoid all that mess if the asm wrapper we have to use anyway would reserve some space on the stack between switch_stack and the C stack frame of do_{rt_,}sigreturn(). Then C part can simply memmove() pt_regs + switch_stack, memcpy() the variable part of exception frame into the opened gap - all of that without inline asm, buggering C call chain, magical jumps to asm labels, etc. Asm wrapper would need to know where the moved switch_stack has ended up - it might have been shifted into the gap we'd reserved before do_rt_sigreturn() call. That's where it needs to set the stack pointer to. So let the C part return just that and be done with that. While we are at it, the call of berr_040cleanup() we need to do when returning via 68040 bus error exception frame can be moved into C part as well. Signed-off-by: Al Viro Tested-by: Michael Schmitz Reviewed-by: Michael Schmitz Tested-by: Finn Thain Link: https://lore.kernel.org/r/YP2dTQPm1wGPWFgD@zeniv-ca.linux.org.uk Signed-off-by: Geert Uytterhoeven --- arch/m68k/68000/entry.S | 3 - arch/m68k/coldfire/entry.S | 3 - arch/m68k/include/asm/traps.h | 4 ++ arch/m68k/kernel/entry.S | 55 ++++++++--------- arch/m68k/kernel/signal.c | 109 +++++++++++++--------------------- 5 files changed, 70 insertions(+), 104 deletions(-) diff --git a/arch/m68k/68000/entry.S b/arch/m68k/68000/entry.S index 259b3661b614..cce465e850fe 100644 --- a/arch/m68k/68000/entry.S +++ b/arch/m68k/68000/entry.S @@ -25,7 +25,6 @@ .globl system_call .globl resume .globl ret_from_exception -.globl ret_from_signal .globl sys_call_table .globl bad_interrupt .globl inthandler1 @@ -59,8 +58,6 @@ do_trace: subql #4,%sp /* dummy return address */ SAVE_SWITCH_STACK jbsr syscall_trace_leave - -ret_from_signal: RESTORE_SWITCH_STACK addql #4,%sp jra ret_from_exception diff --git a/arch/m68k/coldfire/entry.S b/arch/m68k/coldfire/entry.S index d43a02795a4a..68adb7b5b296 100644 --- a/arch/m68k/coldfire/entry.S +++ b/arch/m68k/coldfire/entry.S @@ -51,7 +51,6 @@ sw_usp: .globl system_call .globl resume .globl ret_from_exception -.globl ret_from_signal .globl sys_call_table .globl inthandler @@ -98,8 +97,6 @@ ENTRY(system_call) subql #4,%sp /* dummy return address */ SAVE_SWITCH_STACK jbsr syscall_trace_leave - -ret_from_signal: RESTORE_SWITCH_STACK addql #4,%sp diff --git a/arch/m68k/include/asm/traps.h b/arch/m68k/include/asm/traps.h index 4aff3358fbaf..a9d5c1c870d3 100644 --- a/arch/m68k/include/asm/traps.h +++ b/arch/m68k/include/asm/traps.h @@ -267,6 +267,10 @@ struct frame { } un; }; +#ifdef CONFIG_M68040 +asmlinkage void berr_040cleanup(struct frame *fp); +#endif + #endif /* __ASSEMBLY__ */ #endif /* _M68K_TRAPS_H */ diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index ff9e842cec0f..8fa9822b5922 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -78,20 +78,38 @@ ENTRY(__sys_clone3) ENTRY(sys_sigreturn) SAVE_SWITCH_STACK - movel %sp,%sp@- | switch_stack pointer - pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + movel %sp,%a1 | switch_stack pointer + lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer + lea %sp@(-84),%sp | leave a gap + movel %a1,%sp@- + movel %a0,%sp@- jbsr do_sigreturn - addql #8,%sp - RESTORE_SWITCH_STACK - rts + jra 1f | shared with rt_sigreturn() ENTRY(sys_rt_sigreturn) SAVE_SWITCH_STACK - movel %sp,%sp@- | switch_stack pointer - pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + movel %sp,%a1 | switch_stack pointer + lea %sp@(SWITCH_STACK_SIZE),%a0 | pt_regs pointer + lea %sp@(-84),%sp | leave a gap + movel %a1,%sp@- + movel %a0,%sp@- + | stack contents: + | [original pt_regs address] [original switch_stack address] + | [gap] [switch_stack] [pt_regs] [exception frame] jbsr do_rt_sigreturn - addql #8,%sp + +1: + | stack contents now: + | [original pt_regs address] [original switch_stack address] + | [unused part of the gap] [moved switch_stack] [moved pt_regs] + | [replacement exception frame] + | return value of do_{rt_,}sigreturn() points to moved switch_stack. + + movel %d0,%sp | discard the leftover junk RESTORE_SWITCH_STACK + | stack contents now is just [syscall return address] [pt_regs] [frame] + | return pt_regs.d0 + movel %sp@(PT_OFF_D0+4),%d0 rts ENTRY(buserr) @@ -182,27 +200,6 @@ do_trace_exit: addql #4,%sp jra .Lret_from_exception -ENTRY(ret_from_signal) - movel %curptr@(TASK_STACK),%a1 - tstb %a1@(TINFO_FLAGS+2) - jge 1f - lea %sp@(SWITCH_STACK_SIZE),%a1 - movel %a1,%curptr@(TASK_THREAD+THREAD_ESP0) - jbsr syscall_trace -1: RESTORE_SWITCH_STACK - addql #4,%sp -/* on 68040 complete pending writebacks if any */ -#ifdef CONFIG_M68040 - bfextu %sp@(PT_OFF_FORMATVEC){#0,#4},%d0 - subql #7,%d0 | bus error frame ? - jbne 1f - movel %sp,%sp@- - jbsr berr_040cleanup - addql #4,%sp -1: -#endif - jra .Lret_from_exception - ENTRY(system_call) SAVE_ALL_SYS diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index cd11eb101eac..338817d0cb3f 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -641,56 +641,35 @@ static inline void siginfo_build_tests(void) static int mangle_kernel_stack(struct pt_regs *regs, int formatvec, void __user *fp) { - int fsize = frame_extra_sizes(formatvec >> 12); - if (fsize < 0) { + int extra = frame_extra_sizes(formatvec >> 12); + char buf[sizeof_field(struct frame, un)]; + + if (extra < 0) { /* * user process trying to return with weird frame format */ pr_debug("user process returning with weird frame format\n"); - return 1; + return -1; } - if (!fsize) { - regs->format = formatvec >> 12; - regs->vector = formatvec & 0xfff; - } else { - struct switch_stack *sw = (struct switch_stack *)regs - 1; - /* yes, twice as much as max(sizeof(frame.un.fmt)) */ - unsigned long buf[sizeof_field(struct frame, un) / 2]; + if (extra && copy_from_user(buf, fp, extra)) + return -1; + regs->format = formatvec >> 12; + regs->vector = formatvec & 0xfff; + if (extra) { + void *p = (struct switch_stack *)regs - 1; + struct frame *new = (void *)regs - extra; + int size = sizeof(struct pt_regs)+sizeof(struct switch_stack); - /* that'll make sure that expansion won't crap over data */ - if (copy_from_user(buf + fsize / 4, fp, fsize)) - return 1; - - /* point of no return */ - regs->format = formatvec >> 12; - regs->vector = formatvec & 0xfff; -#define frame_offset (sizeof(struct pt_regs)+sizeof(struct switch_stack)) - __asm__ __volatile__ ( -#ifdef CONFIG_COLDFIRE - " movel %0,%/sp\n\t" - " bra ret_from_signal\n" -#else - " movel %0,%/a0\n\t" - " subl %1,%/a0\n\t" /* make room on stack */ - " movel %/a0,%/sp\n\t" /* set stack pointer */ - /* move switch_stack and pt_regs */ - "1: movel %0@+,%/a0@+\n\t" - " dbra %2,1b\n\t" - " lea %/sp@(%c3),%/a0\n\t" /* add offset of fmt */ - " lsrl #2,%1\n\t" - " subql #1,%1\n\t" - /* copy to the gap we'd made */ - "2: movel %4@+,%/a0@+\n\t" - " dbra %1,2b\n\t" - " bral ret_from_signal\n" + memmove(p - extra, p, size); + memcpy(p - extra + size, buf, extra); + current->thread.esp0 = (unsigned long)&new->ptregs; +#ifdef CONFIG_M68040 + /* on 68040 complete pending writebacks if any */ + if (new->ptregs.format == 7) // bus error frame + berr_040cleanup(new); #endif - : /* no outputs, it doesn't ever return */ - : "a" (sw), "d" (fsize), "d" (frame_offset/4-1), - "n" (frame_offset), "a" (buf + fsize/4) - : "a0"); -#undef frame_offset } - return 0; + return extra; } static inline int @@ -698,7 +677,6 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u { int formatvec; struct sigcontext context; - int err = 0; siginfo_build_tests(); @@ -707,7 +685,7 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u /* get previous context */ if (copy_from_user(&context, usc, sizeof(context))) - goto badframe; + return -1; /* restore passed registers */ regs->d0 = context.sc_d0; @@ -720,15 +698,10 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, void __u wrusp(context.sc_usp); formatvec = context.sc_formatvec; - err = restore_fpu_state(&context); + if (restore_fpu_state(&context)) + return -1; - if (err || mangle_kernel_stack(regs, formatvec, fp)) - goto badframe; - - return 0; - -badframe: - return 1; + return mangle_kernel_stack(regs, formatvec, fp); } static inline int @@ -745,7 +718,7 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw, err = __get_user(temp, &uc->uc_mcontext.version); if (temp != MCONTEXT_VERSION) - goto badframe; + return -1; /* restore passed registers */ err |= __get_user(regs->d0, &gregs[0]); err |= __get_user(regs->d1, &gregs[1]); @@ -774,22 +747,17 @@ rt_restore_ucontext(struct pt_regs *regs, struct switch_stack *sw, err |= restore_altstack(&uc->uc_stack); if (err) - goto badframe; + return -1; - if (mangle_kernel_stack(regs, temp, &uc->uc_extra)) - goto badframe; - - return 0; - -badframe: - return 1; + return mangle_kernel_stack(regs, temp, &uc->uc_extra); } -asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) +asmlinkage void *do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) { unsigned long usp = rdusp(); struct sigframe __user *frame = (struct sigframe __user *)(usp - 4); sigset_t set; + int size; if (!access_ok(frame, sizeof(*frame))) goto badframe; @@ -801,20 +769,22 @@ asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->sc, frame + 1)) + size = restore_sigcontext(regs, &frame->sc, frame + 1); + if (size < 0) goto badframe; - return regs->d0; + return (void *)sw - size; badframe: force_sig(SIGSEGV); - return 0; + return sw; } -asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) +asmlinkage void *do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) { unsigned long usp = rdusp(); struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4); sigset_t set; + int size; if (!access_ok(frame, sizeof(*frame))) goto badframe; @@ -823,13 +793,14 @@ asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) set_current_blocked(&set); - if (rt_restore_ucontext(regs, sw, &frame->uc)) + size = rt_restore_ucontext(regs, sw, &frame->uc); + if (size < 0) goto badframe; - return regs->d0; + return (void *)sw - size; badframe: force_sig(SIGSEGV); - return 0; + return sw; } static inline struct pt_regs *rte_regs(struct pt_regs *regs) From 1dc4027bc8b524ed03c4db391cd7910eb4ee19d2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:00 +0200 Subject: [PATCH 672/866] m68k: Document that access_ok is broken for !CONFIG_CPU_HAS_ADDRESS_SPACES Document that access_ok is completely broken for coldfire and friends at the moment. Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-2-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/include/asm/uaccess.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index f98208ccbbcd..610bfe8d64d5 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -16,6 +16,10 @@ static inline int access_ok(const void __user *addr, unsigned long size) { + /* + * XXX: for !CONFIG_CPU_HAS_ADDRESS_SPACES this really needs to check + * for TASK_SIZE! + */ return 1; } From c4f607c3124e4d2f33604f933b29496ce4111753 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:01 +0200 Subject: [PATCH 673/866] m68k: Remove the 030 case in virt_to_phys_slow The 030 case in virt_to_phys_slow can't ever be reached, so remove it. Suggested-by: Michael Schmitz Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-3-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/mm/cache.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c index b486c0889eec..e7c1cabbfac4 100644 --- a/arch/m68k/mm/cache.c +++ b/arch/m68k/mm/cache.c @@ -49,24 +49,7 @@ static unsigned long virt_to_phys_slow(unsigned long vaddr) if (mmusr & MMU_R_040) return (mmusr & PAGE_MASK) | (vaddr & ~PAGE_MASK); } else { - unsigned short mmusr; - unsigned long *descaddr; - - asm volatile ("ptestr %3,%2@,#7,%0\n\t" - "pmove %%psr,%1" - : "=a&" (descaddr), "=m" (mmusr) - : "a" (vaddr), "d" (get_fs().seg)); - if (mmusr & (MMU_I|MMU_B|MMU_L)) - return 0; - descaddr = phys_to_virt((unsigned long)descaddr); - switch (mmusr & MMU_NUM) { - case 1: - return (*descaddr & 0xfe000000) | (vaddr & 0x01ffffff); - case 2: - return (*descaddr & 0xfffc0000) | (vaddr & 0x0003ffff); - case 3: - return (*descaddr & PAGE_MASK) | (vaddr & ~PAGE_MASK); - } + WARN_ON_ONCE(!CPU_IS_040_OR_060); } return 0; } From 25d2cae4a5578695f667e868ada38b0b73eb1080 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:02 +0200 Subject: [PATCH 674/866] m68k: Use BUILD_BUG for passing invalid sizes to get_user/put_user Simplify the handling a bit by using the common helper instead of referencing undefined symbols. Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-4-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/include/asm/uaccess.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 610bfe8d64d5..01334a9658c4 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -39,9 +39,6 @@ static inline int access_ok(const void __user *addr, #define MOVES "move" #endif -extern int __put_user_bad(void); -extern int __get_user_bad(void); - #define __put_user_asm(res, x, ptr, bwl, reg, err) \ asm volatile ("\n" \ "1: "MOVES"."#bwl" %2,%1\n" \ @@ -105,8 +102,7 @@ asm volatile ("\n" \ break; \ } \ default: \ - __pu_err = __put_user_bad(); \ - break; \ + BUILD_BUG(); \ } \ __pu_err; \ }) @@ -179,8 +175,7 @@ asm volatile ("\n" \ break; \ } \ default: \ - __gu_err = __get_user_bad(); \ - break; \ + BUILD_BUG(); \ } \ __gu_err; \ }) From 01eec1af5ec49b331948ace8f2287580e1594383 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:03 +0200 Subject: [PATCH 675/866] m68k: Factor the 8-byte lowlevel {get,put}_user code into helpers Add new helpers for doing the grunt work of the 8-byte {get,put}_user routines to allow for better reuse. Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-5-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/include/asm/uaccess.h | 111 +++++++++++++++++--------------- 1 file changed, 60 insertions(+), 51 deletions(-) diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 01334a9658c4..288ef7d11a7a 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -57,6 +57,31 @@ asm volatile ("\n" \ : "+d" (res), "=m" (*(ptr)) \ : #reg (x), "i" (err)) +#define __put_user_asm8(res, x, ptr) \ +do { \ + const void *__pu_ptr = (const void __force *)(ptr); \ + \ + asm volatile ("\n" \ + "1: "MOVES".l %2,(%1)+\n" \ + "2: "MOVES".l %R2,(%1)\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .even\n" \ + "10: movel %3,%0\n" \ + " jra 3b\n" \ + " .previous\n" \ + "\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 4\n" \ + " .long 1b,10b\n" \ + " .long 2b,10b\n" \ + " .long 3b,10b\n" \ + " .previous" \ + : "+d" (res), "+a" (__pu_ptr) \ + : "r" (x), "i" (-EFAULT) \ + : "memory"); \ +} while (0) + /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. @@ -78,29 +103,8 @@ asm volatile ("\n" \ __put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT); \ break; \ case 8: \ - { \ - const void __user *__pu_ptr = (ptr); \ - asm volatile ("\n" \ - "1: "MOVES".l %2,(%1)+\n" \ - "2: "MOVES".l %R2,(%1)\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .even\n" \ - "10: movel %3,%0\n" \ - " jra 3b\n" \ - " .previous\n" \ - "\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 4\n" \ - " .long 1b,10b\n" \ - " .long 2b,10b\n" \ - " .long 3b,10b\n" \ - " .previous" \ - : "+d" (__pu_err), "+a" (__pu_ptr) \ - : "r" (__pu_val), "i" (-EFAULT) \ - : "memory"); \ + __put_user_asm8(__pu_err, __pu_val, ptr); \ break; \ - } \ default: \ BUILD_BUG(); \ } \ @@ -130,6 +134,38 @@ asm volatile ("\n" \ (x) = (__force typeof(*(ptr)))(__force unsigned long)__gu_val; \ }) +#define __get_user_asm8(res, x, ptr) \ +do { \ + const void *__gu_ptr = (const void __force *)(ptr); \ + union { \ + u64 l; \ + __typeof__(*(ptr)) t; \ + } __gu_val; \ + \ + asm volatile ("\n" \ + "1: "MOVES".l (%2)+,%1\n" \ + "2: "MOVES".l (%2),%R1\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .even\n" \ + "10: move.l %3,%0\n" \ + " sub.l %1,%1\n" \ + " sub.l %R1,%R1\n" \ + " jra 3b\n" \ + " .previous\n" \ + "\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 4\n" \ + " .long 1b,10b\n" \ + " .long 2b,10b\n" \ + " .previous" \ + : "+d" (res), "=&r" (__gu_val.l), \ + "+a" (__gu_ptr) \ + : "i" (-EFAULT) \ + : "memory"); \ + (x) = __gu_val.t; \ +} while (0) + #define __get_user(x, ptr) \ ({ \ int __gu_err = 0; \ @@ -144,36 +180,9 @@ asm volatile ("\n" \ case 4: \ __get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \ break; \ - case 8: { \ - const void __user *__gu_ptr = (ptr); \ - union { \ - u64 l; \ - __typeof__(*(ptr)) t; \ - } __gu_val; \ - asm volatile ("\n" \ - "1: "MOVES".l (%2)+,%1\n" \ - "2: "MOVES".l (%2),%R1\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .even\n" \ - "10: move.l %3,%0\n" \ - " sub.l %1,%1\n" \ - " sub.l %R1,%R1\n" \ - " jra 3b\n" \ - " .previous\n" \ - "\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 4\n" \ - " .long 1b,10b\n" \ - " .long 2b,10b\n" \ - " .previous" \ - : "+d" (__gu_err), "=&r" (__gu_val.l), \ - "+a" (__gu_ptr) \ - : "i" (-EFAULT) \ - : "memory"); \ - (x) = __gu_val.t; \ + case 8: \ + __get_user_asm8(__gu_err, x, ptr); \ break; \ - } \ default: \ BUILD_BUG(); \ } \ From 8ade83390930d61c64fe3ab49081990c9d43d0d2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:04 +0200 Subject: [PATCH 676/866] m68k: Provide __{get,put}_kernel_nofault Allow non-faulting access to kernel addresses without overriding the address space. Implemented by passing the instruction name to the low-level assembly macros as an argument, and force the use of the normal move instructions for kernel access. Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-6-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/include/asm/uaccess.h | 105 +++++++++++++++++++++++++------- 1 file changed, 84 insertions(+), 21 deletions(-) diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 288ef7d11a7a..65581a7874d4 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -39,9 +39,9 @@ static inline int access_ok(const void __user *addr, #define MOVES "move" #endif -#define __put_user_asm(res, x, ptr, bwl, reg, err) \ +#define __put_user_asm(inst, res, x, ptr, bwl, reg, err) \ asm volatile ("\n" \ - "1: "MOVES"."#bwl" %2,%1\n" \ + "1: "inst"."#bwl" %2,%1\n" \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -57,13 +57,13 @@ asm volatile ("\n" \ : "+d" (res), "=m" (*(ptr)) \ : #reg (x), "i" (err)) -#define __put_user_asm8(res, x, ptr) \ +#define __put_user_asm8(inst, res, x, ptr) \ do { \ const void *__pu_ptr = (const void __force *)(ptr); \ \ asm volatile ("\n" \ - "1: "MOVES".l %2,(%1)+\n" \ - "2: "MOVES".l %R2,(%1)\n" \ + "1: "inst".l %2,(%1)+\n" \ + "2: "inst".l %R2,(%1)\n" \ "3:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -94,16 +94,16 @@ do { \ __chk_user_ptr(ptr); \ switch (sizeof (*(ptr))) { \ case 1: \ - __put_user_asm(__pu_err, __pu_val, ptr, b, d, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, b, d, -EFAULT); \ break; \ case 2: \ - __put_user_asm(__pu_err, __pu_val, ptr, w, r, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, w, r, -EFAULT); \ break; \ case 4: \ - __put_user_asm(__pu_err, __pu_val, ptr, l, r, -EFAULT); \ + __put_user_asm(MOVES, __pu_err, __pu_val, ptr, l, r, -EFAULT); \ break; \ case 8: \ - __put_user_asm8(__pu_err, __pu_val, ptr); \ + __put_user_asm8(MOVES, __pu_err, __pu_val, ptr); \ break; \ default: \ BUILD_BUG(); \ @@ -113,10 +113,10 @@ do { \ #define put_user(x, ptr) __put_user(x, ptr) -#define __get_user_asm(res, x, ptr, type, bwl, reg, err) ({ \ +#define __get_user_asm(inst, res, x, ptr, type, bwl, reg, err) ({ \ type __gu_val; \ asm volatile ("\n" \ - "1: "MOVES"."#bwl" %2,%1\n" \ + "1: "inst"."#bwl" %2,%1\n" \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -134,7 +134,7 @@ do { \ (x) = (__force typeof(*(ptr)))(__force unsigned long)__gu_val; \ }) -#define __get_user_asm8(res, x, ptr) \ +#define __get_user_asm8(inst, res, x, ptr) \ do { \ const void *__gu_ptr = (const void __force *)(ptr); \ union { \ @@ -143,8 +143,8 @@ do { \ } __gu_val; \ \ asm volatile ("\n" \ - "1: "MOVES".l (%2)+,%1\n" \ - "2: "MOVES".l (%2),%R1\n" \ + "1: "inst".l (%2)+,%1\n" \ + "2: "inst".l (%2),%R1\n" \ "3:\n" \ " .section .fixup,\"ax\"\n" \ " .even\n" \ @@ -172,16 +172,16 @@ do { \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm(__gu_err, x, ptr, u8, b, d, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u8, b, d, -EFAULT); \ break; \ case 2: \ - __get_user_asm(__gu_err, x, ptr, u16, w, r, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u16, w, r, -EFAULT); \ break; \ case 4: \ - __get_user_asm(__gu_err, x, ptr, u32, l, r, -EFAULT); \ + __get_user_asm(MOVES, __gu_err, x, ptr, u32, l, r, -EFAULT); \ break; \ case 8: \ - __get_user_asm8(__gu_err, x, ptr); \ + __get_user_asm8(MOVES, __gu_err, x, ptr); \ break; \ default: \ BUILD_BUG(); \ @@ -330,16 +330,19 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n) switch (n) { case 1: - __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1); + __put_user_asm(MOVES, res, *(u8 *)from, (u8 __user *)to, + b, d, 1); break; case 2: - __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, r, 2); + __put_user_asm(MOVES, res, *(u16 *)from, (u16 __user *)to, + w, r, 2); break; case 3: __constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,); break; case 4: - __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4); + __put_user_asm(MOVES, res, *(u32 *)from, (u32 __user *)to, + l, r, 4); break; case 5: __constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,); @@ -388,6 +391,66 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_FROM_USER #define INLINE_COPY_TO_USER +#define HAVE_GET_KERNEL_NOFAULT + +#define __get_kernel_nofault(dst, src, type, err_label) \ +do { \ + type *__gk_dst = (type *)(dst); \ + type *__gk_src = (type *)(src); \ + int __gk_err = 0; \ + \ + switch (sizeof(type)) { \ + case 1: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u8, b, d, -EFAULT); \ + break; \ + case 2: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u16, w, r, -EFAULT); \ + break; \ + case 4: \ + __get_user_asm("move", __gk_err, *__gk_dst, __gk_src, \ + u32, l, r, -EFAULT); \ + break; \ + case 8: \ + __get_user_asm8("move", __gk_err, *__gk_dst, __gk_src); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + if (unlikely(__gk_err)) \ + goto err_label; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, err_label) \ +do { \ + type __pk_src = *(type *)(src); \ + type *__pk_dst = (type *)(dst); \ + int __pk_err = 0; \ + \ + switch (sizeof(type)) { \ + case 1: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + b, d, -EFAULT); \ + break; \ + case 2: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + w, r, -EFAULT); \ + break; \ + case 4: \ + __put_user_asm("move", __pk_err, __pk_src, __pk_dst, \ + l, r, -EFAULT); \ + break; \ + case 8: \ + __put_user_asm8("move", __pk_err, __pk_src, __pk_dst); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + if (unlikely(__pk_err)) \ + goto err_label; \ +} while (0) + #define user_addr_max() \ (uaccess_kernel() ? ~0UL : TASK_SIZE) From 9fde0348640252c79d462c4d29a09a14e8741f5c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2021 09:04:05 +0200 Subject: [PATCH 677/866] m68k: Remove set_fs() Add a m68k-only set_fc helper to set the SFC and DFC registers for the few places that need to override it for special MM operations, but disconnect that from the deprecated kernel-wide set_fs() API. Note that the SFC/DFC registers are context switched, so there is no need to disable preemption. Partially based on an earlier patch from Linus Torvalds . Signed-off-by: Christoph Hellwig Reviewed-by: Michael Schmitz Tested-by: Michael Schmitz Link: https://lore.kernel.org/r/20210916070405.52750-7-hch@lst.de Signed-off-by: Geert Uytterhoeven --- arch/m68k/68000/entry.S | 1 - arch/m68k/Kconfig | 1 - arch/m68k/coldfire/entry.S | 1 - arch/m68k/include/asm/processor.h | 31 +++++++++++++-- arch/m68k/include/asm/segment.h | 59 ----------------------------- arch/m68k/include/asm/thread_info.h | 3 -- arch/m68k/include/asm/tlbflush.h | 11 ++---- arch/m68k/include/asm/uaccess.h | 4 -- arch/m68k/kernel/asm-offsets.c | 2 +- arch/m68k/kernel/entry.S | 5 +-- arch/m68k/kernel/process.c | 4 +- arch/m68k/kernel/traps.c | 13 ++----- arch/m68k/mac/misc.c | 1 - arch/m68k/mm/cache.c | 6 +-- arch/m68k/mm/init.c | 6 --- arch/m68k/mm/kmap.c | 1 - arch/m68k/mm/memory.c | 1 - arch/m68k/mm/motorola.c | 2 +- arch/m68k/sun3/config.c | 3 +- arch/m68k/sun3/mmu_emu.c | 6 +-- arch/m68k/sun3/sun3ints.c | 1 - arch/m68k/sun3x/prom.c | 1 - 22 files changed, 46 insertions(+), 117 deletions(-) delete mode 100644 arch/m68k/include/asm/segment.h diff --git a/arch/m68k/68000/entry.S b/arch/m68k/68000/entry.S index cce465e850fe..997b54933015 100644 --- a/arch/m68k/68000/entry.S +++ b/arch/m68k/68000/entry.S @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 774c35f47eea..0b50da08a9c5 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -29,7 +29,6 @@ config M68K select NO_DMA if !MMU && !COLDFIRE select OLD_SIGACTION select OLD_SIGSUSPEND3 - select SET_FS select UACCESS_MEMCPY if !MMU select VIRT_TO_BUS select ZONE_DMA diff --git a/arch/m68k/coldfire/entry.S b/arch/m68k/coldfire/entry.S index 68adb7b5b296..9f337c70243a 100644 --- a/arch/m68k/coldfire/entry.S +++ b/arch/m68k/coldfire/entry.S @@ -31,7 +31,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index 3750819ac5a1..f4d82c619a5c 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -9,7 +9,6 @@ #define __ASM_M68K_PROCESSOR_H #include -#include #include #include @@ -75,11 +74,37 @@ static inline void wrusp(unsigned long usp) #define TASK_UNMAPPED_BASE 0 #endif +/* Address spaces (or Function Codes in Motorola lingo) */ +#define USER_DATA 1 +#define USER_PROGRAM 2 +#define SUPER_DATA 5 +#define SUPER_PROGRAM 6 +#define CPU_SPACE 7 + +#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES +/* + * Set the SFC/DFC registers for special MM operations. For most normal + * operation these remain set to USER_DATA for the uaccess routines. + */ +static inline void set_fc(unsigned long val) +{ + WARN_ON_ONCE(in_interrupt()); + + __asm__ __volatile__ ("movec %0,%/sfc\n\t" + "movec %0,%/dfc\n\t" + : /* no outputs */ : "r" (val) : "memory"); +} +#else +static inline void set_fc(unsigned long val) +{ +} +#endif /* CONFIG_CPU_HAS_ADDRESS_SPACES */ + struct thread_struct { unsigned long ksp; /* kernel stack pointer */ unsigned long usp; /* user stack pointer */ unsigned short sr; /* saved status register */ - unsigned short fs; /* saved fs (sfc, dfc) */ + unsigned short fc; /* saved fc (sfc, dfc) */ unsigned long crp[2]; /* cpu root pointer */ unsigned long esp0; /* points to SR of stack frame */ unsigned long faddr; /* info about last fault */ @@ -92,7 +117,7 @@ struct thread_struct { #define INIT_THREAD { \ .ksp = sizeof(init_stack) + (unsigned long) init_stack, \ .sr = PS_S, \ - .fs = __KERNEL_DS, \ + .fc = USER_DATA, \ } /* diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h deleted file mode 100644 index 2b5e68a71ef7..000000000000 --- a/arch/m68k/include/asm/segment.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _M68K_SEGMENT_H -#define _M68K_SEGMENT_H - -/* define constants */ -/* Address spaces (FC0-FC2) */ -#define USER_DATA (1) -#ifndef __USER_DS -#define __USER_DS (USER_DATA) -#endif -#define USER_PROGRAM (2) -#define SUPER_DATA (5) -#ifndef __KERNEL_DS -#define __KERNEL_DS (SUPER_DATA) -#endif -#define SUPER_PROGRAM (6) -#define CPU_SPACE (7) - -#ifndef __ASSEMBLY__ - -typedef struct { - unsigned long seg; -} mm_segment_t; - -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#ifdef CONFIG_CPU_HAS_ADDRESS_SPACES -/* - * Get/set the SFC/DFC registers for MOVES instructions - */ -#define USER_DS MAKE_MM_SEG(__USER_DS) -#define KERNEL_DS MAKE_MM_SEG(__KERNEL_DS) - -static inline mm_segment_t get_fs(void) -{ - mm_segment_t _v; - __asm__ ("movec %/dfc,%0":"=r" (_v.seg):); - return _v; -} - -static inline void set_fs(mm_segment_t val) -{ - __asm__ __volatile__ ("movec %0,%/sfc\n\t" - "movec %0,%/dfc\n\t" - : /* no outputs */ : "r" (val.seg) : "memory"); -} - -#else -#define USER_DS MAKE_MM_SEG(TASK_SIZE) -#define KERNEL_DS MAKE_MM_SEG(0xFFFFFFFF) -#define get_fs() (current_thread_info()->addr_limit) -#define set_fs(x) (current_thread_info()->addr_limit = (x)) -#endif - -#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) - -#endif /* __ASSEMBLY__ */ - -#endif /* _M68K_SEGMENT_H */ diff --git a/arch/m68k/include/asm/thread_info.h b/arch/m68k/include/asm/thread_info.h index 15a757073fa5..c952658ba792 100644 --- a/arch/m68k/include/asm/thread_info.h +++ b/arch/m68k/include/asm/thread_info.h @@ -4,7 +4,6 @@ #include #include -#include /* * On machines with 4k pages we default to an 8k thread size, though we @@ -27,7 +26,6 @@ struct thread_info { struct task_struct *task; /* main task structure */ unsigned long flags; - mm_segment_t addr_limit; /* thread address space */ int preempt_count; /* 0 => preemptable, <0 => BUG */ __u32 cpu; /* should always be 0 on m68k */ unsigned long tp_value; /* thread pointer */ @@ -37,7 +35,6 @@ struct thread_info { #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ - .addr_limit = KERNEL_DS, \ .preempt_count = INIT_PREEMPT_COUNT, \ } diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h index a6318ccd308f..b882e2f4f551 100644 --- a/arch/m68k/include/asm/tlbflush.h +++ b/arch/m68k/include/asm/tlbflush.h @@ -13,13 +13,12 @@ static inline void flush_tlb_kernel_page(void *addr) if (CPU_IS_COLDFIRE) { mmu_write(MMUOR, MMUOR_CNL); } else if (CPU_IS_040_OR_060) { - mm_segment_t old_fs = get_fs(); - set_fs(KERNEL_DS); + set_fc(SUPER_DATA); __asm__ __volatile__(".chip 68040\n\t" "pflush (%0)\n\t" ".chip 68k" : : "a" (addr)); - set_fs(old_fs); + set_fc(USER_DATA); } else if (CPU_IS_020_OR_030) __asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr)); } @@ -84,12 +83,8 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { - if (vma->vm_mm == current->active_mm) { - mm_segment_t old_fs = force_uaccess_begin(); - + if (vma->vm_mm == current->active_mm) __flush_tlb_one(addr); - force_uaccess_end(old_fs); - } } static inline void flush_tlb_range(struct vm_area_struct *vma, diff --git a/arch/m68k/include/asm/uaccess.h b/arch/m68k/include/asm/uaccess.h index 65581a7874d4..ba670523885c 100644 --- a/arch/m68k/include/asm/uaccess.h +++ b/arch/m68k/include/asm/uaccess.h @@ -9,7 +9,6 @@ */ #include #include -#include #include /* We let the MMU do all checking */ @@ -451,9 +450,6 @@ do { \ goto err_label; \ } while (0) -#define user_addr_max() \ - (uaccess_kernel() ? ~0UL : TASK_SIZE) - extern long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c index ccea355052ef..906d73230537 100644 --- a/arch/m68k/kernel/asm-offsets.c +++ b/arch/m68k/kernel/asm-offsets.c @@ -31,7 +31,7 @@ int main(void) DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); DEFINE(THREAD_USP, offsetof(struct thread_struct, usp)); DEFINE(THREAD_SR, offsetof(struct thread_struct, sr)); - DEFINE(THREAD_FS, offsetof(struct thread_struct, fs)); + DEFINE(THREAD_FC, offsetof(struct thread_struct, fc)); DEFINE(THREAD_CRP, offsetof(struct thread_struct, crp)); DEFINE(THREAD_ESP0, offsetof(struct thread_struct, esp0)); DEFINE(THREAD_FPREG, offsetof(struct thread_struct, fp)); diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 8fa9822b5922..9434fca68de5 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include @@ -337,7 +336,7 @@ resume: /* save fs (sfc,%dfc) (may be pointing to kernel memory) */ movec %sfc,%d0 - movew %d0,%a0@(TASK_THREAD+THREAD_FS) + movew %d0,%a0@(TASK_THREAD+THREAD_FC) /* save usp */ /* it is better to use a movel here instead of a movew 8*) */ @@ -423,7 +422,7 @@ resume: movel %a0,%usp /* restore fs (sfc,%dfc) */ - movew %a1@(TASK_THREAD+THREAD_FS),%a0 + movew %a1@(TASK_THREAD+THREAD_FC),%a0 movec %a0,%sfc movec %a0,%dfc diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index db49f9091711..1ab692b952cd 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -92,7 +92,7 @@ void show_regs(struct pt_regs * regs) void flush_thread(void) { - current->thread.fs = __USER_DS; + current->thread.fc = USER_DATA; #ifdef CONFIG_FPU if (!FPU_IS_EMU) { unsigned long zero = 0; @@ -155,7 +155,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, * Must save the current SFC/DFC value, NOT the value when * the parent was last descheduled - RGH 10-08-96 */ - p->thread.fs = get_fs().seg; + p->thread.fc = USER_DATA; if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 5b19fcdcd69e..9718ce94cc84 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -181,9 +181,8 @@ static inline void access_error060 (struct frame *fp) static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) { unsigned long mmusr; - mm_segment_t old_fs = get_fs(); - set_fs(MAKE_MM_SEG(wbs)); + set_fc(wbs); if (iswrite) asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr)); @@ -192,7 +191,7 @@ static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr)); - set_fs(old_fs); + set_fc(USER_DATA); return mmusr; } @@ -201,10 +200,8 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba, unsigned long wbd) { int res = 0; - mm_segment_t old_fs = get_fs(); - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(MAKE_MM_SEG(wbs)); + set_fc(wbs); switch (wbs & WBSIZ_040) { case BA_SIZE_BYTE: @@ -218,9 +215,7 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba, break; } - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(old_fs); - + set_fc(USER_DATA); pr_debug("do_040writeback1, res=%d\n", res); diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 90f4e9ca1276..4fab34791758 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -18,7 +18,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c index e7c1cabbfac4..dde978e66f14 100644 --- a/arch/m68k/mm/cache.c +++ b/arch/m68k/mm/cache.c @@ -90,11 +90,9 @@ void flush_icache_user_range(unsigned long address, unsigned long endaddr) void flush_icache_range(unsigned long address, unsigned long endaddr) { - mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); + set_fc(SUPER_DATA); flush_icache_user_range(address, endaddr); - set_fs(old_fs); + set_fc(USER_DATA); } EXPORT_SYMBOL(flush_icache_range); diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 5d749e188246..1b47bec15832 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -72,12 +72,6 @@ void __init paging_init(void) if (!empty_zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); - - /* - * Set up SFC/DFC registers (user data space). - */ - set_fs (USER_DS); - max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT; free_area_init(max_zone_pfn); } diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 1269d513b221..20ddf71b43d0 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -17,7 +17,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c index fe75aecfb238..c2c03b0a1567 100644 --- a/arch/m68k/mm/memory.c +++ b/arch/m68k/mm/memory.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 3a653f0a4188..9f3f77785aa7 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -467,7 +467,7 @@ void __init paging_init(void) /* * Set up SFC/DFC registers */ - set_fs(KERNEL_DS); + set_fc(USER_DATA); #ifdef DEBUG printk ("before free_area_init\n"); diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index f7dd47232b6c..203f428a0344 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -31,7 +31,6 @@ #include #include #include -#include #include char sun3_reserved_pmeg[SUN3_PMEGS_NUM]; @@ -89,7 +88,7 @@ void __init sun3_init(void) sun3_reserved_pmeg[249] = 1; sun3_reserved_pmeg[252] = 1; sun3_reserved_pmeg[253] = 1; - set_fs(KERNEL_DS); + set_fc(USER_DATA); } /* Without this, Bad Things happen when something calls arch_reset. */ diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c index 7aa879b7c7ff..7ec20817c0c9 100644 --- a/arch/m68k/sun3/mmu_emu.c +++ b/arch/m68k/sun3/mmu_emu.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -191,14 +190,13 @@ void __init mmu_emu_init(unsigned long bootmem_end) for(seg = 0; seg < PAGE_OFFSET; seg += SUN3_PMEG_SIZE) sun3_put_segmap(seg, SUN3_INVALID_PMEG); - set_fs(MAKE_MM_SEG(3)); + set_fc(3); for(seg = 0; seg < 0x10000000; seg += SUN3_PMEG_SIZE) { i = sun3_get_segmap(seg); for(j = 1; j < CONTEXTS_NUM; j++) (*(romvec->pv_setctxt))(j, (void *)seg, i); } - set_fs(KERNEL_DS); - + set_fc(USER_DATA); } /* erase the mappings for a dead context. Uses the pg_dir for hints diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c index 41ae422119d3..36cc280a4505 100644 --- a/arch/m68k/sun3/sun3ints.c +++ b/arch/m68k/sun3/sun3ints.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/sun3x/prom.c b/arch/m68k/sun3x/prom.c index 74d2fe57524b..64c23bfaa90c 100644 --- a/arch/m68k/sun3x/prom.c +++ b/arch/m68k/sun3x/prom.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include From 14351f08ed5c8b888cdd95651152db7e096ee27f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 16 Sep 2021 12:05:28 -0300 Subject: [PATCH 678/866] RDMA/hns: Work around broken constant propagation in gcc 8 gcc 8.3 and 5.4 throw this: In function 'modify_qp_init_to_rtr', ././include/linux/compiler_types.h:322:38: error: call to '__compiletime_assert_1859' declared with attribute error: FIELD_PREP: value too large for the field _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) [..] drivers/infiniband/hw/hns/hns_roce_common.h:91:52: note: in expansion of macro 'FIELD_PREP' *((__le32 *)ptr + (field_h) / 32) |= cpu_to_le32(FIELD_PREP( \ ^~~~~~~~~~ drivers/infiniband/hw/hns/hns_roce_common.h:95:39: note: in expansion of macro '_hr_reg_write' #define hr_reg_write(ptr, field, val) _hr_reg_write(ptr, field, val) ^~~~~~~~~~~~~ drivers/infiniband/hw/hns/hns_roce_hw_v2.c:4412:2: note: in expansion of macro 'hr_reg_write' hr_reg_write(context, QPC_LP_PKTN_INI, lp_pktn_ini); Because gcc has miscalculated the constantness of lp_pktn_ini: mtu = ib_mtu_enum_to_int(ib_mtu); if (WARN_ON(mtu < 0)) [..] lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); Since mtu is limited to {256,512,1024,2048,4096} lp_pktn_ini is between 4 and 8 which is compatible with the 4 bit field in the FIELD_PREP. Work around this broken compiler by adding a 'can never be true' constraint on lp_pktn_ini's value which clears out the problem. Fixes: f0cb411aad23 ("RDMA/hns: Use new interface to modify QP context") Link: https://lore.kernel.org/r/0-v1-c773ecb137bc+11f-hns_gcc8_jgg@nvidia.com Reported-by: Geert Uytterhoeven Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 5b9953105752..a9c00a2e8ebd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4397,7 +4397,12 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, hr_qp->path_mtu = ib_mtu; mtu = ib_mtu_enum_to_int(ib_mtu); - if (WARN_ON(mtu < 0)) + if (WARN_ON(mtu <= 0)) + return -EINVAL; +#define MAX_LP_MSG_LEN 65536 + /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */ + lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); + if (WARN_ON(lp_pktn_ini >= 0xF)) return -EINVAL; if (attr_mask & IB_QP_PATH_MTU) { @@ -4405,10 +4410,6 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, hr_reg_clear(qpc_mask, QPC_MTU); } -#define MAX_LP_MSG_LEN 65536 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 64KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - hr_reg_write(context, QPC_LP_PKTN_INI, lp_pktn_ini); hr_reg_clear(qpc_mask, QPC_LP_PKTN_INI); From 2938b2978a70d4cc10777ee71c9e512ffe4e0f4b Mon Sep 17 00:00:00 2001 From: Paul Fertser Date: Fri, 24 Sep 2021 12:30:09 +0300 Subject: [PATCH 679/866] hwmon: (tmp421) handle I2C errors Function i2c_smbus_read_byte_data() can return a negative error number instead of the data read if I2C transaction failed for whatever reason. Lack of error checking can lead to serious issues on production hardware, e.g. errors treated as temperatures produce spurious critical temperature-crossed-threshold errors in BMC logs for OCP server hardware. The patch was tested with Mellanox OCP Mezzanine card emulating TMP421 protocol for temperature sensing which sometimes leads to I2C protocol error during early boot up stage. Fixes: 9410700b881f ("hwmon: Add driver for Texas Instruments TMP421/422/423 sensor chips") Cc: stable@vger.kernel.org Signed-off-by: Paul Fertser Link: https://lore.kernel.org/r/20210924093011.26083-1-fercerpav@gmail.com [groeck: dropped unnecessary line breaks] Signed-off-by: Guenter Roeck --- drivers/hwmon/tmp421.c | 38 ++++++++++++++++++++++++++++---------- 1 file changed, 28 insertions(+), 10 deletions(-) diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c index ede66ea6a730..8fd8c3a94dfe 100644 --- a/drivers/hwmon/tmp421.c +++ b/drivers/hwmon/tmp421.c @@ -119,38 +119,56 @@ static int temp_from_u16(u16 reg) return (temp * 1000 + 128) / 256; } -static struct tmp421_data *tmp421_update_device(struct device *dev) +static int tmp421_update_device(struct tmp421_data *data) { - struct tmp421_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; + int ret = 0; int i; mutex_lock(&data->update_lock); if (time_after(jiffies, data->last_updated + (HZ / 2)) || !data->valid) { - data->config = i2c_smbus_read_byte_data(client, - TMP421_CONFIG_REG_1); + ret = i2c_smbus_read_byte_data(client, TMP421_CONFIG_REG_1); + if (ret < 0) + goto exit; + data->config = ret; for (i = 0; i < data->channels; i++) { - data->temp[i] = i2c_smbus_read_byte_data(client, - TMP421_TEMP_MSB[i]) << 8; - data->temp[i] |= i2c_smbus_read_byte_data(client, - TMP421_TEMP_LSB[i]); + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_MSB[i]); + if (ret < 0) + goto exit; + data->temp[i] = ret << 8; + + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_LSB[i]); + if (ret < 0) + goto exit; + data->temp[i] |= ret; } data->last_updated = jiffies; data->valid = 1; } +exit: mutex_unlock(&data->update_lock); - return data; + if (ret < 0) { + data->valid = 0; + return ret; + } + + return 0; } static int tmp421_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { - struct tmp421_data *tmp421 = tmp421_update_device(dev); + struct tmp421_data *tmp421 = dev_get_drvdata(dev); + int ret = 0; + + ret = tmp421_update_device(tmp421); + if (ret) + return ret; switch (attr) { case hwmon_temp_input: From 540effa7f283d25bcc13c0940d808002fee340b8 Mon Sep 17 00:00:00 2001 From: Paul Fertser Date: Fri, 24 Sep 2021 12:30:10 +0300 Subject: [PATCH 680/866] hwmon: (tmp421) report /PVLD condition as fault For both local and remote sensors all the supported ICs can report an "undervoltage lockout" condition which means the conversion wasn't properly performed due to insufficient power supply voltage and so the measurement results can't be trusted. Fixes: 9410700b881f ("hwmon: Add driver for Texas Instruments TMP421/422/423 sensor chips") Signed-off-by: Paul Fertser Link: https://lore.kernel.org/r/20210924093011.26083-2-fercerpav@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/tmp421.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c index 8fd8c3a94dfe..c9ef83627bb7 100644 --- a/drivers/hwmon/tmp421.c +++ b/drivers/hwmon/tmp421.c @@ -179,10 +179,10 @@ static int tmp421_read(struct device *dev, enum hwmon_sensor_types type, return 0; case hwmon_temp_fault: /* - * The OPEN bit signals a fault. This is bit 0 of the temperature - * register (low byte). + * Any of OPEN or /PVLD bits indicate a hardware mulfunction + * and the conversion result may be incorrect */ - *val = tmp421->temp[channel] & 0x01; + *val = !!(tmp421->temp[channel] & 0x03); return 0; default: return -EOPNOTSUPP; @@ -195,9 +195,6 @@ static umode_t tmp421_is_visible(const void *data, enum hwmon_sensor_types type, { switch (attr) { case hwmon_temp_fault: - if (channel == 0) - return 0; - return 0444; case hwmon_temp_input: return 0444; default: From 724e8af85854c4d3401313b6dd7d79cf792d8990 Mon Sep 17 00:00:00 2001 From: Paul Fertser Date: Fri, 24 Sep 2021 12:30:11 +0300 Subject: [PATCH 681/866] hwmon: (tmp421) fix rounding for negative values Old code produces -24999 for 0b1110011100000000 input in standard format due to always rounding up rather than "away from zero". Use the common macro for division, unify and simplify the conversion code along the way. Fixes: 9410700b881f ("hwmon: Add driver for Texas Instruments TMP421/422/423 sensor chips") Signed-off-by: Paul Fertser Link: https://lore.kernel.org/r/20210924093011.26083-3-fercerpav@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/tmp421.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c index c9ef83627bb7..b963a369c5ab 100644 --- a/drivers/hwmon/tmp421.c +++ b/drivers/hwmon/tmp421.c @@ -100,23 +100,17 @@ struct tmp421_data { s16 temp[4]; }; -static int temp_from_s16(s16 reg) +static int temp_from_raw(u16 reg, bool extended) { /* Mask out status bits */ int temp = reg & ~0xf; - return (temp * 1000 + 128) / 256; -} + if (extended) + temp = temp - 64 * 256; + else + temp = (s16)temp; -static int temp_from_u16(u16 reg) -{ - /* Mask out status bits */ - int temp = reg & ~0xf; - - /* Add offset for extended temperature range. */ - temp -= 64 * 256; - - return (temp * 1000 + 128) / 256; + return DIV_ROUND_CLOSEST(temp * 1000, 256); } static int tmp421_update_device(struct tmp421_data *data) @@ -172,10 +166,8 @@ static int tmp421_read(struct device *dev, enum hwmon_sensor_types type, switch (attr) { case hwmon_temp_input: - if (tmp421->config & TMP421_CONFIG_RANGE) - *val = temp_from_u16(tmp421->temp[channel]); - else - *val = temp_from_s16(tmp421->temp[channel]); + *val = temp_from_raw(tmp421->temp[channel], + tmp421->config & TMP421_CONFIG_RANGE); return 0; case hwmon_temp_fault: /* From 6f7d70467121f790b36af2d84bc02b5c236bf5e6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 23 Sep 2021 22:11:13 +0200 Subject: [PATCH 682/866] hwmon: (ltc2947) Properly handle errors when looking for the external clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The return value of devm_clk_get should in general be propagated to upper layer. In this case the clk is optional, use the appropriate wrapper instead of interpreting all errors as "The optional clk is not available". Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210923201113.398932-1-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck --- drivers/hwmon/ltc2947-core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/ltc2947-core.c b/drivers/hwmon/ltc2947-core.c index bb3f7749a0b0..5423466de697 100644 --- a/drivers/hwmon/ltc2947-core.c +++ b/drivers/hwmon/ltc2947-core.c @@ -989,8 +989,12 @@ static int ltc2947_setup(struct ltc2947_data *st) return ret; /* check external clock presence */ - extclk = devm_clk_get(st->dev, NULL); - if (!IS_ERR(extclk)) { + extclk = devm_clk_get_optional(st->dev, NULL); + if (IS_ERR(extclk)) + return dev_err_probe(st->dev, PTR_ERR(extclk), + "Failed to get external clock\n"); + + if (extclk) { unsigned long rate_hz; u8 pre = 0, div, tbctl; u64 aux; From 325fd36ae76a6d089983b2d2eccb41237d35b221 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 23 Sep 2021 16:23:33 +0300 Subject: [PATCH 683/866] net: enetc: fix the incorrect clearing of IF_MODE bits The enetc phylink .mac_config handler intends to clear the IFMODE field (bits 1:0) of the PM0_IF_MODE register, but incorrectly clears all the other fields instead. For normal operation, the bug was inconsequential, due to the fact that we write the PM0_IF_MODE register in two stages, first in phylink .mac_config (which incorrectly cleared out a bunch of stuff), then we update the speed and duplex to the correct values in phylink .mac_link_up. Judging by the code (not tested), it looks like maybe loopback mode was broken, since this is one of the settings in PM0_IF_MODE which is incorrectly cleared. Fixes: c76a97218dcb ("net: enetc: force the RGMII speed and duplex instead of operating in inband mode") Reported-by: Pavel Machek (CIP) Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc_pf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 60d94e0a07d6..4c977dfc44f0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -541,8 +541,7 @@ static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode) if (phy_interface_mode_is_rgmii(phy_mode)) { val = enetc_port_rd(hw, ENETC_PM0_IF_MODE); - val &= ~ENETC_PM0_IFM_EN_AUTO; - val &= ENETC_PM0_IFM_IFMODE_MASK; + val &= ~(ENETC_PM0_IFM_EN_AUTO | ENETC_PM0_IFM_IFMODE_MASK); val |= ENETC_PM0_IFM_IFMODE_GMII | ENETC_PM0_IFM_RG; enetc_port_wr(hw, ENETC_PM0_IF_MODE, val); } From 597aa16c782496bf74c5dc3b45ff472ade6cee64 Mon Sep 17 00:00:00 2001 From: Xiao Liang Date: Thu, 23 Sep 2021 23:03:19 +0800 Subject: [PATCH 684/866] net: ipv4: Fix rtnexthop len when RTA_FLOW is present Multipath RTA_FLOW is embedded in nexthop. Dump it in fib_add_nexthop() to get the length of rtnexthop correct. Fixes: b0f60193632e ("ipv4: Refactor nexthop attributes in fib_dump_info") Signed-off-by: Xiao Liang Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- include/net/nexthop.h | 2 +- net/ipv4/fib_semantics.c | 16 +++++++++------- net/ipv6/route.c | 5 +++-- 4 files changed, 14 insertions(+), 11 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 21c5386d4a6d..ab5348e57db1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -597,5 +597,5 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, - int nh_weight, u8 rt_family); + int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 10e1777877e6..28085b995ddc 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -325,7 +325,7 @@ int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; - if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0) + if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b42c429cebbe..3364cb9c67e0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1661,7 +1661,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, - int nh_weight, u8 rt_family) + int nh_weight, u8 rt_family, u32 nh_tclassid) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; @@ -1679,6 +1679,9 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, rtnh->rtnh_flags = flags; + if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid)) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; @@ -1706,14 +1709,13 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) } for_nexthops(fi) { - if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, - AF_INET) < 0) - goto nla_put_failure; + u32 nh_tclassid = 0; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; + nh_tclassid = nh->nh_tclassid; #endif + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, + AF_INET, nh_tclassid) < 0) + goto nla_put_failure; } endfor_nexthops(fi); mp_end: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dbc224023977..9b9ef09382ab 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5681,14 +5681,15 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, - rt->fib6_nh->fib_nh_weight, AF_INET6) < 0) + rt->fib6_nh->fib_nh_weight, AF_INET6, + 0) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6) < 0) + AF_INET6, 0) < 0) goto nla_put_failure; } From 5ab8a447bcfee1ded709e7ff5dc7608ca9f66ae2 Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Fri, 24 Sep 2021 01:00:16 +0300 Subject: [PATCH 685/866] smsc95xx: fix stalled rx after link change After commit 05b35e7eb9a1 ("smsc95xx: add phylib support"), link changes are no longer propagated to usbnet. As a result, rx URB allocation won't happen until there is a packet sent out first (this might never happen, e.g. running just ssh server with a static IP). Fix by triggering usbnet EVENT_LINK_CHANGE. Fixes: 05b35e7eb9a1 ("smsc95xx: add phylib support") Signed-off-by: Aaro Koskinen Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 7d953974eb9b..26b1bd8e845b 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1178,7 +1178,10 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) static void smsc95xx_handle_link_change(struct net_device *net) { + struct usbnet *dev = netdev_priv(net); + phy_print_status(net->phydev); + usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); } static int smsc95xx_start_phy(struct usbnet *dev) From 4526fe74c3c5095cc55931a3a6fb4932f9e06002 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Fri, 24 Sep 2021 11:26:52 +0200 Subject: [PATCH 686/866] drivers: net: mhi: fix error path in mhi_net_newlink Fix double free_netdev when mhi_prepare_for_transfer fails. Fixes: 3ffec6a14f24 ("net: Add mhi-net driver") Signed-off-by: Daniele Palmas Reviewed-by: Manivannan Sadhasivam Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/mhi_net.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c index d127eb6e9257..aaa628f859fd 100644 --- a/drivers/net/mhi_net.c +++ b/drivers/net/mhi_net.c @@ -321,7 +321,7 @@ static int mhi_net_newlink(struct mhi_device *mhi_dev, struct net_device *ndev) /* Start MHI channels */ err = mhi_prepare_for_transfer(mhi_dev); if (err) - goto out_err; + return err; /* Number of transfer descriptors determines size of the queue */ mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE); @@ -331,10 +331,6 @@ static int mhi_net_newlink(struct mhi_device *mhi_dev, struct net_device *ndev) return err; return 0; - -out_err: - free_netdev(ndev); - return err; } static void mhi_net_dellink(struct mhi_device *mhi_dev, struct net_device *ndev) From adfc8f9d2f9fefd880abc82cfbf62cbfe6539c97 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 23 Sep 2021 17:29:39 -0700 Subject: [PATCH 687/866] NIOS2: fix kconfig unmet dependency warning for SERIAL_CORE_CONSOLE SERIAL_CORE_CONSOLE depends on TTY so EARLY_PRINTK should also depend on TTY so that it does not select SERIAL_CORE_CONSOLE inadvertently. WARNING: unmet direct dependencies detected for SERIAL_CORE_CONSOLE Depends on [n]: TTY [=n] && HAS_IOMEM [=y] Selected by [y]: - EARLY_PRINTK [=y] Fixes: e8bf5bc776ed ("nios2: add early printk support") Signed-off-by: Randy Dunlap Cc: Dinh Nguyen Signed-off-by: Dinh Nguyen --- arch/nios2/Kconfig.debug | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index a8bc06e96ef5..ca1beb87f987 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -3,9 +3,10 @@ config EARLY_PRINTK bool "Activate early kernel debugging" default y + depends on TTY select SERIAL_CORE_CONSOLE help - Enable early printk on console + Enable early printk on console. This is useful for kernel debugging when your machine crashes very early before the console code is initialized. You should normally say N here, unless you want to debug such a crash. From a86cd017a40a66b1a3db005bfee4e76a1ae9a432 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 13 Sep 2021 11:04:42 +0300 Subject: [PATCH 688/866] RDMA/usnic: Lock VF with mutex instead of spinlock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Usnic VF doesn't need lock in atomic context to create QPs, so it is safe to use mutex instead of spinlock. Such change fixes the following smatch error. Smatch static checker warning: lib/kobject.c:289 kobject_set_name_vargs() warn: sleeping in atomic context Fixes: 514aee660df4 ("RDMA: Globally allocate and release QP memory") Link: https://lore.kernel.org/r/2a0e295786c127e518ebee8bb7cafcb819a625f6.1631520231.git.leonro@nvidia.com Reported-by: Dan Carpenter Signed-off-by: Leon Romanovsky Reviewed-by: Håkon Bugge Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/usnic/usnic_ib.h | 2 +- drivers/infiniband/hw/usnic/usnic_ib_main.c | 2 +- drivers/infiniband/hw/usnic/usnic_ib_verbs.c | 16 ++++++++-------- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/usnic/usnic_ib.h b/drivers/infiniband/hw/usnic/usnic_ib.h index 84dd682d2334..b350081aeb5a 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib.h +++ b/drivers/infiniband/hw/usnic/usnic_ib.h @@ -90,7 +90,7 @@ struct usnic_ib_dev { struct usnic_ib_vf { struct usnic_ib_dev *pf; - spinlock_t lock; + struct mutex lock; struct usnic_vnic *vnic; unsigned int qp_grp_ref_cnt; struct usnic_ib_pd *pd; diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 228e9a36dad0..d346dd48e731 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -572,7 +572,7 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev, } vf->pf = pf; - spin_lock_init(&vf->lock); + mutex_init(&vf->lock); mutex_lock(&pf->usdev_lock); list_add_tail(&vf->link, &pf->vf_dev_list); /* diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 06a4e9d4545d..756a83bcff58 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -196,7 +196,7 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, for (i = 0; dev_list[i]; i++) { dev = dev_list[i]; vf = dev_get_drvdata(dev); - spin_lock(&vf->lock); + mutex_lock(&vf->lock); vnic = vf->vnic; if (!usnic_vnic_check_room(vnic, res_spec)) { usnic_dbg("Found used vnic %s from %s\n", @@ -208,10 +208,10 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, vf, pd, res_spec, trans_spec); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); goto qp_grp_check; } - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } usnic_uiom_free_dev_list(dev_list); @@ -220,7 +220,7 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, /* Try to find resources on an unused vf */ list_for_each_entry(vf, &us_ibdev->vf_dev_list, link) { - spin_lock(&vf->lock); + mutex_lock(&vf->lock); vnic = vf->vnic; if (vf->qp_grp_ref_cnt == 0 && usnic_vnic_check_room(vnic, res_spec) == 0) { @@ -228,10 +228,10 @@ find_free_vf_and_create_qp_grp(struct ib_qp *qp, vf, pd, res_spec, trans_spec); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); goto qp_grp_check; } - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } usnic_info("No free qp grp found on %s\n", @@ -253,9 +253,9 @@ static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp) WARN_ON(qp_grp->state != IB_QPS_RESET); - spin_lock(&vf->lock); + mutex_lock(&vf->lock); usnic_ib_qp_grp_destroy(qp_grp); - spin_unlock(&vf->lock); + mutex_unlock(&vf->lock); } static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd) From 42de956ca7e5f6c47048dde640f797e783b23198 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 21 Sep 2021 09:11:59 -0300 Subject: [PATCH 689/866] vfio/ap_ops: Add missed vfio_uninit_group_dev() Without this call an xarray entry is leaked when the vfio_ap device is unprobed. It was missed when the below patch was rebased across the dev_set patch. Keep the remove function in the same order as the error unwind in probe. Fixes: eb0feefd4c02 ("vfio/ap_ops: Convert to use vfio_register_group_dev()") Reviewed-by: Christoph Hellwig Tested-by: Tony Krowiak Signed-off-by: Jason Gunthorpe Reviewed-by: Tony Krowiak Link: https://lore.kernel.org/r/0-v3-f9b50340cdbb+e4-ap_uninit_jgg@nvidia.com Signed-off-by: Alex Williamson --- drivers/s390/crypto/vfio_ap_ops.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 118939a7729a..623d5269a52c 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -361,6 +361,7 @@ err_list: mutex_lock(&matrix_dev->lock); list_del(&matrix_mdev->node); mutex_unlock(&matrix_dev->lock); + vfio_uninit_group_dev(&matrix_mdev->vdev); kfree(matrix_mdev); err_dec_available: atomic_inc(&matrix_dev->available_instances); @@ -376,9 +377,10 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev) mutex_lock(&matrix_dev->lock); vfio_ap_mdev_reset_queues(matrix_mdev); list_del(&matrix_mdev->node); + mutex_unlock(&matrix_dev->lock); + vfio_uninit_group_dev(&matrix_mdev->vdev); kfree(matrix_mdev); atomic_inc(&matrix_dev->available_instances); - mutex_unlock(&matrix_dev->lock); } static ssize_t name_show(struct mdev_type *mtype, From 87c1696655787895689618c8b63c5efe66b8f2ab Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 21 Sep 2021 08:24:57 -0600 Subject: [PATCH 690/866] io-wq: ensure we exit if thread group is exiting Dave reports that a coredumping workload gets stuck in 5.15-rc2, and identified the culprit in the Fixes line below. The problem is that relying solely on fatal_signal_pending() to gate whether to exit or not fails miserably if a process gets eg SIGILL sent. Don't exclusively rely on fatal signals, also check if the thread group is exiting. Fixes: 15e20db2e0ce ("io-wq: only exit on fatal signals") Reported-by: Dave Chinner Signed-off-by: Jens Axboe --- fs/io-wq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index c2e0e8e80949..c2360cdc403d 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -584,7 +584,8 @@ loop: if (!get_signal(&ksig)) continue; - if (fatal_signal_pending(current)) + if (fatal_signal_pending(current) || + signal_group_exit(current->signal)) break; continue; } From bd99c71bd14072ce2920f6d0c2fe43df072c653c Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Wed, 22 Sep 2021 18:12:36 +0800 Subject: [PATCH 691/866] io_uring: fix race between poll completion and cancel_hash insertion If poll arming and poll completion runs in parallel, there maybe races. For instance, run io_poll_add in iowq and io_poll_task_func in original context, then: iowq original context io_poll_add vfs_poll (interruption happens tw queued to original context) io_poll_task_func generate cqe del from cancel_hash[] if !poll.done insert to cancel_hash[] The entry left in cancel_hash[], similar case for fast poll. Fix it by set poll.done = true when del from cancel_hash[]. Fixes: 5082620fb2ca ("io_uring: terminate multishot poll for CQ ring overflow") Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210922101238.7177-2-haoxu@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index e372d5b9f6dc..43530aae6180 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5337,10 +5337,8 @@ static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask) } if (req->poll.events & EPOLLONESHOT) flags = 0; - if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) { - req->poll.done = true; + if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) flags = 0; - } if (flags & IORING_CQE_F_MORE) ctx->cq_extra++; @@ -5371,6 +5369,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) if (done) { io_poll_remove_double(req); hash_del(&req->hash_node); + req->poll.done = true; } else { req->result = 0; add_wait_queue(req->poll.head, &req->poll.wait); @@ -5508,6 +5507,7 @@ static void io_async_task_func(struct io_kiocb *req, bool *locked) hash_del(&req->hash_node); io_poll_remove_double(req); + apoll->poll.done = true; spin_unlock(&ctx->completion_lock); if (!READ_ONCE(apoll->poll.canceled)) From a62682f92eedb41c1cd8290fa875a4b85624fb9a Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Wed, 22 Sep 2021 18:12:37 +0800 Subject: [PATCH 692/866] io_uring: fix missing set of EPOLLONESHOT for CQ ring overflow We should set EPOLLONESHOT if cqring_fill_event() returns false since io_poll_add() decides to put req or not by it. Fixes: 5082620fb2ca ("io_uring: terminate multishot poll for CQ ring overflow") Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210922101238.7177-3-haoxu@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 43530aae6180..ac0c06d5c629 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5337,8 +5337,10 @@ static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask) } if (req->poll.events & EPOLLONESHOT) flags = 0; - if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) + if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) { + req->poll.events |= EPOLLONESHOT; flags = 0; + } if (flags & IORING_CQE_F_MORE) ctx->cq_extra++; From 5b7aa38d86f348847a48f71e9ac7715406de900e Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Wed, 22 Sep 2021 18:12:38 +0800 Subject: [PATCH 693/866] io_uring: fix potential req refcount underflow For multishot mode, there may be cases like: iowq original context io_poll_add _arm_poll() mask = vfs_poll() is not 0 if mask (2) io_poll_complete() compl_unlock (interruption happens tw queued to original context) io_poll_task_func() compl_lock (3) done = io_poll_complete() is true compl_unlock put req ref (1) if (poll->flags & EPOLLONESHOT) put req ref EPOLLONESHOT flag in (1) may be from (2) or (3), so there are multiple combinations that can cause ref underfow. Let's address it by: - check the return value in (2) as done - change (1) to if (done) in this way, we only do ref put in (1) if 'oneshot flag' is from (2) - do poll.done check in io_poll_task_func(), so that we won't put ref for the second time. Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20210922101238.7177-4-haoxu@linux.alibaba.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ac0c06d5c629..7707cdb7b372 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5367,6 +5367,10 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) } else { bool done; + if (req->poll.done) { + spin_unlock(&ctx->completion_lock); + return; + } done = __io_poll_complete(req, req->result); if (done) { io_poll_remove_double(req); @@ -5830,6 +5834,7 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *ctx = req->ctx; struct io_poll_table ipt; __poll_t mask; + bool done; ipt.pt._qproc = io_poll_queue_proc; @@ -5838,13 +5843,13 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) if (mask) { /* no async, we'd stolen it */ ipt.error = 0; - io_poll_complete(req, mask); + done = io_poll_complete(req, mask); } spin_unlock(&ctx->completion_lock); if (mask) { io_cqring_ev_posted(ctx); - if (poll->events & EPOLLONESHOT) + if (done) io_put_req(req); } return ipt.error; From 8bab4c09f24ec8d4a7a78ab343620f89d3a24804 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 24 Sep 2021 07:12:27 -0600 Subject: [PATCH 694/866] io_uring: allow conditional reschedule for intensive iterators If we have a lot of threads and rings, the tctx list can get quite big. This is especially true if we keep creating new threads and rings. Likewise for the provided buffers list. Be nice and insert a conditional reschedule point while iterating the nodes for deletion. Link: https://lore.kernel.org/io-uring/00000000000064b6b405ccb41113@google.com/ Reported-by: syzbot+111d2a03f51f5ae73775@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 7707cdb7b372..ef3c94a55fbd 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9173,8 +9173,10 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) struct io_buffer *buf; unsigned long index; - xa_for_each(&ctx->io_buffers, index, buf) + xa_for_each(&ctx->io_buffers, index, buf) { __io_remove_buffers(ctx, buf, index, -1U); + cond_resched(); + } } static void io_req_cache_free(struct list_head *list) @@ -9672,8 +9674,10 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx) struct io_tctx_node *node; unsigned long index; - xa_for_each(&tctx->xa, index, node) + xa_for_each(&tctx->xa, index, node) { io_uring_del_tctx_node(index); + cond_resched(); + } if (wq) { /* * Must be after io_uring_del_task_file() (removes nodes under From 9990da93d2bf9892c2c14c958bef050d4e461a1a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 24 Sep 2021 07:39:08 -0600 Subject: [PATCH 695/866] io_uring: put provided buffer meta data under memcg accounting For each provided buffer, we allocate a struct io_buffer to hold the data associated with it. As a large number of buffers can be provided, account that data with memcg. Fixes: ddf0322db79c ("io_uring: add IORING_OP_PROVIDE_BUFFERS") Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ef3c94a55fbd..01e49d01fe74 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4387,7 +4387,7 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) int i, bid = pbuf->bid; for (i = 0; i < pbuf->nbufs; i++) { - buf = kmalloc(sizeof(*buf), GFP_KERNEL); + buf = kmalloc(sizeof(*buf), GFP_KERNEL_ACCOUNT); if (!buf) break; From cdb31c29d397a8076d81fd1458d091c647ef94ba Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 24 Sep 2021 08:43:54 -0600 Subject: [PATCH 696/866] io_uring: don't punt files update to io-wq unconditionally There's no reason to punt it unconditionally, we just need to ensure that the submit lock grabbing is conditional. Fixes: 05f3fb3c5397 ("io_uring: avoid ring quiesce for fixed file set unregister and update") Signed-off-by: Jens Axboe --- fs/io_uring.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 01e49d01fe74..c6139ace11fa 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6340,19 +6340,16 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) struct io_uring_rsrc_update2 up; int ret; - if (issue_flags & IO_URING_F_NONBLOCK) - return -EAGAIN; - up.offset = req->rsrc_update.offset; up.data = req->rsrc_update.arg; up.nr = 0; up.tags = 0; up.resv = 0; - mutex_lock(&ctx->uring_lock); + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, req->rsrc_update.nr_args); - mutex_unlock(&ctx->uring_lock); + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); if (ret < 0) req_set_fail(req); From 9f3a2cb228c28606895d15f13b30d1f7402dc745 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 24 Sep 2021 17:14:48 +0100 Subject: [PATCH 697/866] io_uring: kill extra checks in io_write() We don't retry short writes and so we would never get to async setup in io_write() in that case. Thus ret2 > 0 is always false and iov_iter_advance() is never used. Apparently, the same is found by Coverity, which complains on the code. Fixes: cd65869512ab ("io_uring: use iov_iter state save/restore helpers") Reported-by: Dave Jones Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/5b33e61034748ef1022766efc0fb8854cfcf749c.1632500058.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c6139ace11fa..2b3232d53e79 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3605,7 +3605,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_save_state(iter, state); } req->result = iov_iter_count(iter); - ret2 = 0; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) @@ -3670,8 +3669,6 @@ done: } else { copy_iov: iov_iter_restore(iter, state); - if (ret2 > 0) - iov_iter_advance(iter, ret2); ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); return ret ?: -EAGAIN; } From a647a524a46736786c95cdb553a070322ca096e3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 24 Sep 2021 19:07:04 +0800 Subject: [PATCH 698/866] block: don't call rq_qos_ops->done_bio if the bio isn't tracked rq_qos framework is only applied on request based driver, so: 1) rq_qos_done_bio() needn't to be called for bio based driver 2) rq_qos_done_bio() needn't to be called for bio which isn't tracked, such as bios ended from error handling code. Especially in bio_endio(): 1) request queue is referred via bio->bi_bdev->bd_disk->queue, which may be gone since request queue refcount may not be held in above two cases 2) q->rq_qos may be freed in blk_cleanup_queue() when calling into __rq_qos_done_bio() Fix the potential kernel panic by not calling rq_qos_ops->done_bio if the bio isn't tracked. This way is safe because both ioc_rqos_done_bio() and blkcg_iolatency_done_bio() are nop if the bio isn't tracked. Reported-by: Yu Kuai Cc: tj@kernel.org Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20210924110704.1541818-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/bio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bio.c b/block/bio.c index 5df3dd282e40..a6fb6a0b4295 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1466,7 +1466,7 @@ again: if (!bio_integrity_endio(bio)) return; - if (bio->bi_bdev) + if (bio->bi_bdev && bio_flagged(bio, BIO_TRACKED)) rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio); if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { From 5afedf670caf30a2b5a52da96eb7eac7dee6a9c9 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Thu, 23 Sep 2021 21:49:21 +0800 Subject: [PATCH 699/866] blktrace: Fix uaf in blk_trace access after removing by sysfs There is an use-after-free problem triggered by following process: P1(sda) P2(sdb) echo 0 > /sys/block/sdb/trace/enable blk_trace_remove_queue synchronize_rcu blk_trace_free relay_close rcu_read_lock __blk_add_trace trace_note_tsk (Iterate running_trace_list) relay_close_buf relay_destroy_buf kfree(buf) trace_note(sdb's bt) relay_reserve buf->offset <- nullptr deference (use-after-free) !!! rcu_read_unlock [ 502.714379] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 502.715260] #PF: supervisor read access in kernel mode [ 502.715903] #PF: error_code(0x0000) - not-present page [ 502.716546] PGD 103984067 P4D 103984067 PUD 17592b067 PMD 0 [ 502.717252] Oops: 0000 [#1] SMP [ 502.720308] RIP: 0010:trace_note.isra.0+0x86/0x360 [ 502.732872] Call Trace: [ 502.733193] __blk_add_trace.cold+0x137/0x1a3 [ 502.733734] blk_add_trace_rq+0x7b/0xd0 [ 502.734207] blk_add_trace_rq_issue+0x54/0xa0 [ 502.734755] blk_mq_start_request+0xde/0x1b0 [ 502.735287] scsi_queue_rq+0x528/0x1140 ... [ 502.742704] sg_new_write.isra.0+0x16e/0x3e0 [ 502.747501] sg_ioctl+0x466/0x1100 Reproduce method: ioctl(/dev/sda, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sda, BLKTRACESTART) ioctl(/dev/sdb, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sdb, BLKTRACESTART) echo 0 > /sys/block/sdb/trace/enable & // Add delay(mdelay/msleep) before kernel enters blk_trace_free() ioctl$SG_IO(/dev/sda, SG_IO, ...) // Enters trace_note_tsk() after blk_trace_free() returned // Use mdelay in rcu region rather than msleep(which may schedule out) Remove blk_trace from running_list before calling blk_trace_free() by sysfs if blk_trace is at Blktrace_running state. Fixes: c71a896154119f ("blktrace: add ftrace plugin") Signed-off-by: Zhihao Cheng Link: https://lore.kernel.org/r/20210923134921.109194-1-chengzhihao1@huawei.com Signed-off-by: Jens Axboe --- kernel/trace/blktrace.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index c221e4c3f625..fa91f398f28b 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1605,6 +1605,14 @@ static int blk_trace_remove_queue(struct request_queue *q) if (bt == NULL) return -EINVAL; + if (bt->trace_state == Blktrace_running) { + bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); + relay_flush(bt->rchan); + } + put_probe_ref(); synchronize_rcu(); blk_trace_free(bt); From f278eb3d8178f9c31f8dfad7e91440e603dd7f1a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 23 Sep 2021 10:37:51 +0800 Subject: [PATCH 700/866] block: hold ->invalidate_lock in blkdev_fallocate When running ->fallocate(), blkdev_fallocate() should hold mapping->invalidate_lock to prevent page cache from being accessed, otherwise stale data may be read in page cache. Without this patch, blktests block/009 fails sometimes. With this patch, block/009 can pass always. Also as Jan pointed out, no pages can be created in the discarded area while you are holding the invalidate_lock, so remove the 2nd truncate_bdev_range(). Cc: Jan Kara Signed-off-by: Ming Lei Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20210923023751.1441091-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/fops.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/block/fops.c b/block/fops.c index ffce6f6c68dd..1e970c247e0e 100644 --- a/block/fops.c +++ b/block/fops.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "blk.h" static struct inode *bdev_file_inode(struct file *file) @@ -553,7 +554,8 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) static long blkdev_fallocate(struct file *file, int mode, loff_t start, loff_t len) { - struct block_device *bdev = I_BDEV(bdev_file_inode(file)); + struct inode *inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(inode); loff_t end = start + len - 1; loff_t isize; int error; @@ -580,10 +582,12 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; + filemap_invalidate_lock(inode->i_mapping); + /* Invalidate the page cache, including dirty pages. */ error = truncate_bdev_range(bdev, file->f_mode, start, end); if (error) - return error; + goto fail; switch (mode) { case FALLOC_FL_ZERO_RANGE: @@ -600,17 +604,12 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, GFP_KERNEL, 0); break; default: - return -EOPNOTSUPP; + error = -EOPNOTSUPP; } - if (error) - return error; - /* - * Invalidate the page cache again; if someone wandered in and dirtied - * a page, we just discard it - userspace has no way of knowing whether - * the write happened before or after discard completing... - */ - return truncate_bdev_range(bdev, file->f_mode, start, end); + fail: + filemap_invalidate_unlock(inode->i_mapping); + return error; } const struct file_operations def_blk_fops = { From 7df778be2f61e1a23002d1f2f5d6aaf702771eb8 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 24 Sep 2021 20:04:29 +0100 Subject: [PATCH 701/866] io_uring: make OP_CLOSE consistent with direct open From recently open/accept are now able to manipulate fixed file table, but it's inconsistent that close can't. Close the gap, keep API same as with open/accept, i.e. via sqe->file_slot. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2b3232d53e79..82f867983bb3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -502,6 +502,7 @@ struct io_poll_update { struct io_close { struct file *file; int fd; + u32 file_slot; }; struct io_timeout_data { @@ -1098,6 +1099,8 @@ static int io_req_prep_async(struct io_kiocb *req); static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index); +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags); + static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer); static struct kmem_cache *req_cachep; @@ -4591,12 +4594,16 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || - sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) + sqe->rw_flags || sqe->buf_index) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; req->close.fd = READ_ONCE(sqe->fd); + req->close.file_slot = READ_ONCE(sqe->file_index); + if (req->close.file_slot && req->close.fd) + return -EINVAL; + return 0; } @@ -4608,6 +4615,11 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) struct file *file = NULL; int ret = -EBADF; + if (req->close.file_slot) { + ret = io_close_fixed(req, issue_flags); + goto err; + } + spin_lock(&files->file_lock); fdt = files_fdtable(files); if (close->fd >= fdt->max_fds) { @@ -8401,6 +8413,44 @@ err: return ret; } +static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) +{ + unsigned int offset = req->close.file_slot - 1; + struct io_ring_ctx *ctx = req->ctx; + struct io_fixed_file *file_slot; + struct file *file; + int ret, i; + + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + ret = -ENXIO; + if (unlikely(!ctx->file_data)) + goto out; + ret = -EINVAL; + if (offset >= ctx->nr_user_files) + goto out; + ret = io_rsrc_node_switch_start(ctx); + if (ret) + goto out; + + i = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, i); + ret = -EBADF; + if (!file_slot->file_ptr) + goto out; + + file = (struct file *)(file_slot->file_ptr & FFS_MASK); + ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file); + if (ret) + goto out; + + file_slot->file_ptr = 0; + io_rsrc_node_switch(ctx, ctx->file_data); + ret = 0; +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + return ret; +} + static int __io_sqe_files_update(struct io_ring_ctx *ctx, struct io_uring_rsrc_update2 *up, unsigned nr_args) From acfa299a4a63a58e5e81a87cb16798f20d35f7d7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 24 Sep 2021 15:43:20 -0700 Subject: [PATCH 702/866] mm, hwpoison: add is_free_buddy_page() in HWPoisonHandlable() Commit fcc00621d88b ("mm/hwpoison: retry with shake_page() for unhandlable pages") changed the return value of __get_hwpoison_page() to retry for transiently unhandlable cases. However, __get_hwpoison_page() currently fails to properly judge buddy pages as handlable, so hard/soft offline for buddy pages always fail as "unhandlable page". This is totally regrettable. So let's add is_free_buddy_page() in HWPoisonHandlable(), so that __get_hwpoison_page() returns different return values between buddy pages and unhandlable pages as intended. Link: https://lkml.kernel.org/r/20210909004131.163221-1-naoya.horiguchi@linux.dev Fixes: fcc00621d88b ("mm/hwpoison: retry with shake_page() for unhandlable pages") Signed-off-by: Naoya Horiguchi Acked-by: David Hildenbrand Reviewed-by: Yang Shi Cc: Tony Luck Cc: Oscar Salvador Cc: Mike Kravetz Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 54879c339024..41901c7bb58f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1126,7 +1126,7 @@ static int page_action(struct page_state *ps, struct page *p, */ static inline bool HWPoisonHandlable(struct page *page) { - return PageLRU(page) || __PageMovable(page); + return PageLRU(page) || __PageMovable(page) || is_free_buddy_page(page); } static int __get_hwpoison_page(struct page *page) From fa360beac4b62d54879a88b182afef4b369c9700 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 24 Sep 2021 15:43:23 -0700 Subject: [PATCH 703/866] kasan: fix Kconfig check of CC_HAS_WORKING_NOSANITIZE_ADDRESS In the main KASAN config option CC_HAS_WORKING_NOSANITIZE_ADDRESS is checked for instrumentation-based modes. However, if HAVE_ARCH_KASAN_HW_TAGS is true all modes may still be selected. To fix, also make the software modes depend on CC_HAS_WORKING_NOSANITIZE_ADDRESS. Link: https://lkml.kernel.org/r/20210910084240.1215803-1-elver@google.com Fixes: 6a63a63ff1ac ("kasan: introduce CONFIG_KASAN_HW_TAGS") Signed-off-by: Marco Elver Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.kasan | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 1e2d10f86011..cdc842d090db 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -66,6 +66,7 @@ choice config KASAN_GENERIC bool "Generic mode" depends on HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC + depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS select SLUB_DEBUG if SLUB select CONSTRUCTORS help @@ -86,6 +87,7 @@ config KASAN_GENERIC config KASAN_SW_TAGS bool "Software tag-based mode" depends on HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS + depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS select SLUB_DEBUG if SLUB select CONSTRUCTORS help From 892ab4bbd063cfe7f6bbb183e6be69d9907a61de Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Fri, 24 Sep 2021 15:43:26 -0700 Subject: [PATCH 704/866] mm/damon: don't use strnlen() with known-bogus source length gcc knows the true length too, and rightfully complains. Link: https://lkml.kernel.org/r/20210912204447.10427-1-kilobyte@angband.pl Signed-off-by: Adam Borowski Cc: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs-test.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h index 930e83bceef0..4eddcfa73996 100644 --- a/mm/damon/dbgfs-test.h +++ b/mm/damon/dbgfs-test.h @@ -20,27 +20,27 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) ssize_t nr_integers = 0, i; question = "123"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); KUNIT_EXPECT_EQ(test, 123ul, answers[0]); kfree(answers); question = "123abc"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); KUNIT_EXPECT_EQ(test, 123ul, answers[0]); kfree(answers); question = "a123"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); question = "12 35"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); for (i = 0; i < nr_integers; i++) @@ -48,7 +48,7 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) kfree(answers); question = "12 35 46"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers); for (i = 0; i < nr_integers; i++) @@ -56,7 +56,7 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) kfree(answers); question = "12 35 abc 46"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); for (i = 0; i < 2; i++) @@ -64,13 +64,13 @@ static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) kfree(answers); question = ""; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); question = "\n"; - answers = str_to_target_ids(question, strnlen(question, 128), + answers = str_to_target_ids(question, strlen(question), &nr_integers); KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); kfree(answers); From 867050247e295cf20fce046a92a7e6491fcfe066 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 24 Sep 2021 15:43:29 -0700 Subject: [PATCH 705/866] xtensa: increase size of gcc stack frame check xtensa frame size is larger than the frame size for almost all other architectures. This results in more than 50 "the frame size of is larger than 1024 bytes" errors when trying to build xtensa:allmodconfig. Increase frame size for xtensa to 1536 bytes to avoid compile errors due to frame size limits. Link: https://lkml.kernel.org/r/20210912025235.3514761-1-linux@roeck-us.net Signed-off-by: Guenter Roeck Reviewed-by: Max Filippov Cc: Chris Zankel Cc: David Laight Cc: Masahiro Yamada Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d566f601780f..2a9b6dcdac4f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -346,7 +346,7 @@ config FRAME_WARN int "Warn for stack frames larger than" range 0 8192 default 2048 if GCC_PLUGIN_LATENT_ENTROPY - default 1536 if (!64BIT && PARISC) + default 1536 if (!64BIT && (PARISC || XTENSA)) default 1024 if (!64BIT && !PARISC) default 2048 if 64BIT help From de6ee659684b1a2b149e0780d3c5e8032f3647d6 Mon Sep 17 00:00:00 2001 From: Liu Yuntao Date: Fri, 24 Sep 2021 15:43:32 -0700 Subject: [PATCH 706/866] mm/shmem.c: fix judgment error in shmem_is_huge() In the case of SHMEM_HUGE_WITHIN_SIZE, the page index is not rounded up correctly. When the page index points to the first page in a huge page, round_up() cannot bring it to the end of the huge page, but to the end of the previous one. An example: HPAGE_PMD_NR on my machine is 512(2 MB huge page size). After allcoating a 3000 KB buffer, I access it at location 2050 KB. In shmem_is_huge(), the corresponding index happens to be 512. After rounded up by HPAGE_PMD_NR, it will still be 512 which is smaller than i_size, and shmem_is_huge() will return true. As a result, my buffer takes an additional huge page, and that shouldn't happen when shmem_enabled is set to within_size. Link: https://lkml.kernel.org/r/20210909032007.18353-1-liuyuntao10@huawei.com Fixes: f3f0e1d2150b2b ("khugepaged: add support of collapse for tmpfs/shmem pages") Signed-off-by: Liu Yuntao Acked-by: Kirill A. Shutemov Acked-by: Hugh Dickins Cc: wuxu.wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 88742953532c..b5860f4a2738 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -490,9 +490,9 @@ bool shmem_is_huge(struct vm_area_struct *vma, case SHMEM_HUGE_ALWAYS: return true; case SHMEM_HUGE_WITHIN_SIZE: - index = round_up(index, HPAGE_PMD_NR); + index = round_up(index + 1, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >= HPAGE_PMD_SIZE && (i_size >> PAGE_SHIFT) >= index) + if (i_size >> PAGE_SHIFT >= index) return true; fallthrough; case SHMEM_HUGE_ADVISE: From 9c0f0a03e386f4e1df33db676401547e1b7800c6 Mon Sep 17 00:00:00 2001 From: Wengang Wang Date: Fri, 24 Sep 2021 15:43:35 -0700 Subject: [PATCH 707/866] ocfs2: drop acl cache for directories too ocfs2_data_convert_worker() is currently dropping any cached acl info for FILE before down-converting meta lock. It should also drop for DIRECTORY. Otherwise the second acl lookup returns the cached one (from VFS layer) which could be already stale. The problem we are seeing is that the acl changes on one node doesn't get refreshed on other nodes in the following case: Node 1 Node 2 -------------- ---------------- getfacl dir1 getfacl dir1 <-- this is OK setfacl -m u:user1:rwX dir1 getfacl dir1 <-- see the change for user1 getfacl dir1 <-- can't see change for user1 Link: https://lkml.kernel.org/r/20210903012631.6099-1-wen.gang.wang@oracle.com Signed-off-by: Wengang Wang Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlmglue.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 359524b7341f..801e60bab955 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3951,7 +3951,7 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres, oi = OCFS2_I(inode); oi->ip_dir_lock_gen++; mlog(0, "generation: %u\n", oi->ip_dir_lock_gen); - goto out; + goto out_forget; } if (!S_ISREG(inode->i_mode)) @@ -3982,6 +3982,7 @@ static int ocfs2_data_convert_worker(struct ocfs2_lock_res *lockres, filemap_fdatawait(mapping); } +out_forget: forget_all_cached_acls(inode); out: From d09c38726c78effaf910a1e3f31e247b5b031d56 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 24 Sep 2021 15:43:38 -0700 Subject: [PATCH 708/866] scripts/sorttable: riscv: fix undeclared identifier 'EM_RISCV' error Fix the following build failure reported in [1] by adding a conditional definition of EM_RISCV in order to allow cross-compilation on machines which do not have EM_RISCV definition in their host. scripts/sorttable.c:352:7: error: use of undeclared identifier 'EM_RISCV' EM_RISCV was added to in glibc 2.24 so builds on systems with glibc headers < 2.24 should show this error. [mkubecek@suse.cz: changelog addition] Link: https://lore.kernel.org/lkml/e8965b25-f15b-c7b4-748c-d207dda9c8e8@i2se.com/ [1] Link: https://lkml.kernel.org/r/20210913030625.4525-1-miles.chen@mediatek.com Fixes: 54fed35fd393 ("riscv: Enable BUILDTIME_TABLE_SORT") Signed-off-by: Miles Chen Reported-by: Stefan Wahren Tested-by: Stefan Wahren Reviewed-by: Jisheng Zhang Cc: Michal Kubecek Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Markus Mayer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/sorttable.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/scripts/sorttable.c b/scripts/sorttable.c index f355869c65cd..6ee4fa882919 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -54,6 +54,10 @@ #define EM_ARCV2 195 #endif +#ifndef EM_RISCV +#define EM_RISCV 243 +#endif + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); From ebaeab2fe87987cef28eb5ab174c42cd28594387 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 24 Sep 2021 15:43:41 -0700 Subject: [PATCH 709/866] tools/vm/page-types: remove dependency on opt_file for idle page tracking Idle page tracking can also be used for process address space, not only file mappings. Without this change, using with '-i' option for process address space encounters below errors reported. $ sudo ./page-types -p $(pidof bash) -i mark page idle: Bad file descriptor mark page idle: Bad file descriptor mark page idle: Bad file descriptor mark page idle: Bad file descriptor ... Link: https://lkml.kernel.org/r/20210917032826.10669-1-changbin.du@gmail.com Signed-off-by: Changbin Du Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/page-types.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 0517c744b04e..f62f10c988db 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -1331,7 +1331,7 @@ int main(int argc, char *argv[]) if (opt_list && opt_list_mapcnt) kpagecount_fd = checked_open(PROC_KPAGECOUNT, O_RDONLY); - if (opt_mark_idle && opt_file) + if (opt_mark_idle) page_idle_fd = checked_open(SYS_KERNEL_MM_PAGE_IDLE, O_RDWR); if (opt_list && opt_pid) From b7cd9fa5ccc392d9f2269edc4cb82508632c28da Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Fri, 24 Sep 2021 15:43:44 -0700 Subject: [PATCH 710/866] lib/zlib_inflate/inffast: check config in C to avoid unused function warning Building Linux for ppc64le with Ubuntu clang version 12.0.0-3ubuntu1~21.04.1 shows the warning below. arch/powerpc/boot/inffast.c:20:1: warning: unused function 'get_unaligned16' [-Wunused-function] get_unaligned16(const unsigned short *p) ^ 1 warning generated. Fix it by moving the check from the preprocessor to C, so the compiler sees the use. Link: https://lkml.kernel.org/r/20210920084332.5752-1-pmenzel@molgen.mpg.de Signed-off-by: Paul Menzel Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Cc: Nick Desaulniers Cc: Christophe Leroy Cc: Zhen Lei Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/zlib_inflate/inffast.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c index f19c4fbe1be7..2843f9bb42ac 100644 --- a/lib/zlib_inflate/inffast.c +++ b/lib/zlib_inflate/inffast.c @@ -253,13 +253,12 @@ void inflate_fast(z_streamp strm, unsigned start) sfrom = (unsigned short *)(from); loops = len >> 1; - do -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - *sout++ = *sfrom++; -#else - *sout++ = get_unaligned16(sfrom++); -#endif - while (--loops); + do { + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + *sout++ = *sfrom++; + else + *sout++ = get_unaligned16(sfrom++); + } while (--loops); out = (unsigned char *)sout; from = (unsigned char *)sfrom; } else { /* dist == 1 or dist == 2 */ From 243418e3925d5b5b0657ae54c322d43035e97eed Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 24 Sep 2021 15:43:47 -0700 Subject: [PATCH 711/866] mm: fs: invalidate bh_lrus for only cold path The kernel test robot reported the regression of fio.write_iops[1] with commit 8cc621d2f45d ("mm: fs: invalidate BH LRU during page migration"). Since lru_add_drain is called frequently, invalidate bh_lrus there could increase bh_lrus cache miss ratio, which needs more IO in the end. This patch moves the bh_lrus invalidation from the hot path( e.g., zap_page_range, pagevec_release) to cold path(i.e., lru_add_drain_all, lru_cache_disable). Zhengjun Xing confirmed "I test the patch, the regression reduced to -2.9%" [1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/ [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration Link: https://lkml.kernel.org/r/20210907212347.1977686-1-minchan@kernel.org Signed-off-by: Minchan Kim Reported-by: kernel test robot Reviewed-by: Chris Goldsworthy Tested-by: "Xing, Zhengjun" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 8 ++++++-- include/linux/buffer_head.h | 4 ++-- mm/swap.c | 19 ++++++++++++++++--- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index ab7573d72dd7..c615387aedca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1425,12 +1425,16 @@ void invalidate_bh_lrus(void) } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); -void invalidate_bh_lrus_cpu(int cpu) +/* + * It's called from workqueue context so we need a bh_lru_lock to close + * the race with preemption/irq. + */ +void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); - b = per_cpu_ptr(&bh_lrus, cpu); + b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6486d3c19463..36f33685c8c0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); -void invalidate_bh_lrus_cpu(int cpu); +void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); @@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } -static inline void invalidate_bh_lrus_cpu(int cpu) {} +static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; } #define buffer_heads_over_limit 0 diff --git a/mm/swap.c b/mm/swap.c index 897200d27dd0..af3cad4e5378 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -620,7 +620,6 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); - invalidate_bh_lrus_cpu(cpu); } /** @@ -703,6 +702,20 @@ void lru_add_drain(void) local_unlock(&lru_pvecs.lock); } +/* + * It's called from per-cpu workqueue context in SMP case so + * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on + * the same cpu. It shouldn't be a problem in !SMP case since + * the core is only one and the locks will disable preemption. + */ +static void lru_add_and_bh_lrus_drain(void) +{ + local_lock(&lru_pvecs.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&lru_pvecs.lock); + invalidate_bh_lrus_cpu(); +} + void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); @@ -717,7 +730,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { - lru_add_drain(); + lru_add_and_bh_lrus_drain(); } /* @@ -858,7 +871,7 @@ void lru_cache_disable(void) */ __lru_add_drain_all(true); #else - lru_add_drain(); + lru_add_and_bh_lrus_drain(); #endif } From a4ce73910427e960b2c7f4d83229153c327d0ee7 Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Fri, 24 Sep 2021 15:43:50 -0700 Subject: [PATCH 712/866] mm/debug: sync up MR_CONTIG_RANGE and MR_LONGTERM_PIN Sync up MR_CONTIG_RANGE and MR_LONGTERM_PIN to migrate_reason_names. Link: https://lkml.kernel.org/r/20210921064553.293905-2-o451686892@gmail.com Fixes: 310253514bbf ("mm/migrate: rename migration reason MR_CMA to MR_CONTIG_RANGE") Fixes: d1e153fea2a8 ("mm/gup: migrate pinned pages out of movable zone") Signed-off-by: Weizhao Ouyang Reviewed-by: "Huang, Ying" Reviewed-by: John Hubbard Cc: Anshuman Khandual Cc: Michal Hocko Cc: Pavel Tatashin Cc: Yang Shi Cc: Zi Yan Cc: Dave Hansen Cc: Minchan Kim Cc: Mina Almasry Cc: "Matthew Wilcox (Oracle)" Cc: Oscar Salvador Cc: Wei Xu Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/debug.c b/mm/debug.c index e73fe0a8ec3d..e61037cded98 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -24,7 +24,8 @@ const char *migrate_reason_names[MR_TYPES] = { "syscall_or_cpuset", "mempolicy_mbind", "numa_misplaced", - "cma", + "contig_range", + "longterm_pin", }; const struct trace_print_flags pageflag_names[] = { From 57ed7b4303a1c4d1885019fef03e6a5af2e8468a Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Fri, 24 Sep 2021 15:43:53 -0700 Subject: [PATCH 713/866] mm/debug: sync up latest migrate_reason to migrate_reason_names Sync up MR_DEMOTION to migrate_reason_names and add a synch prompt. Link: https://lkml.kernel.org/r/20210921064553.293905-3-o451686892@gmail.com Fixes: 26aa2d199d6f ("mm/migrate: demote pages during reclaim") Signed-off-by: Weizhao Ouyang Reviewed-by: "Huang, Ying" Reviewed-by: John Hubbard Cc: Anshuman Khandual Cc: Michal Hocko Cc: Pavel Tatashin Cc: Yang Shi Cc: Zi Yan Cc: Dave Hansen Cc: Minchan Kim Cc: Mina Almasry Cc: "Matthew Wilcox (Oracle)" Cc: Oscar Salvador Cc: Wei Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 6 +++++- mm/debug.c | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 326250996b4e..c8077e936691 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,6 +19,11 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 +/* + * Keep sync with: + * - macro MIGRATE_REASON in include/trace/events/migrate.h + * - migrate_reason_names[MR_TYPES] in mm/debug.c + */ enum migrate_reason { MR_COMPACTION, MR_MEMORY_FAILURE, @@ -32,7 +37,6 @@ enum migrate_reason { MR_TYPES }; -/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/mm/debug.c b/mm/debug.c index e61037cded98..fae0f81ad831 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -26,6 +26,7 @@ const char *migrate_reason_names[MR_TYPES] = { "numa_misplaced", "contig_range", "longterm_pin", + "demotion", }; const struct trace_print_flags pageflag_names[] = { From e8e9f1e6327005be9656aa135aeb9dfdaf6b3032 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 24 Sep 2021 15:43:57 -0700 Subject: [PATCH 714/866] sh: pgtable-3level: fix cast to pointer from integer of different size If X2TLB=y (CPU_SHX2=y or CPU_SHX3=y, e.g. migor_defconfig), pgd_t.pgd is "unsigned long long", causing: In file included from arch/sh/include/asm/pgtable.h:13, from include/linux/pgtable.h:6, from include/linux/mm.h:33, from arch/sh/kernel/asm-offsets.c:14: arch/sh/include/asm/pgtable-3level.h: In function `pud_pgtable': arch/sh/include/asm/pgtable-3level.h:37:9: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 37 | return (pmd_t *)pud_val(pud); | ^ Fix this by adding an intermediate cast to "unsigned long", which is basically what the old code did before. Link: https://lkml.kernel.org/r/2c2eef3c9a2f57e5609100a4864715ccf253d30f.1631713483.git.geert+renesas@glider.be Fixes: 9cf6fa2458443118 ("mm: rename pud_page_vaddr to pud_pgtable and make it return pmd_t *") Signed-off-by: Geert Uytterhoeven Tested-by: Daniel Palmer Acked-by: Rob Landley Cc: Yoshinori Sato Cc: Rich Felker Cc: "Aneesh Kumar K . V" Cc: Jacopo Mondi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/asm/pgtable-3level.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 56bf35c2f29c..cdced80a7ffa 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -34,7 +34,7 @@ typedef struct { unsigned long long pmd; } pmd_t; static inline pmd_t *pud_pgtable(pud_t pud) { - return (pmd_t *)pud_val(pud); + return (pmd_t *)(unsigned long)pud_val(pud); } /* only used by the stubbed out hugetlb gup code, should never be called */ From 19532869feb9b0a97d17ddc14609d1e53a5b60db Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 24 Sep 2021 15:44:00 -0700 Subject: [PATCH 715/866] kasan: always respect CONFIG_KASAN_STACK Currently, the asan-stack parameter is only passed along if CFLAGS_KASAN_SHADOW is not empty, which requires KASAN_SHADOW_OFFSET to be defined in Kconfig so that the value can be checked. In RISC-V's case, KASAN_SHADOW_OFFSET is not defined in Kconfig, which means that asan-stack does not get disabled with clang even when CONFIG_KASAN_STACK is disabled, resulting in large stack warnings with allmodconfig: drivers/video/fbdev/omap2/omapfb/displays/panel-lgphilips-lb035q02.c:117:12: error: stack frame size (14400) exceeds limit (2048) in function 'lb035q02_connect' [-Werror,-Wframe-larger-than] static int lb035q02_connect(struct omap_dss_device *dssdev) ^ 1 error generated. Ensure that the value of CONFIG_KASAN_STACK is always passed along to the compiler so that these warnings do not happen when CONFIG_KASAN_STACK is disabled. Link: https://github.com/ClangBuiltLinux/linux/issues/1453 References: 6baec880d7a5 ("kasan: turn off asan-stack for clang-8 and earlier") Link: https://lkml.kernel.org/r/20210922205525.570068-1-nathan@kernel.org Signed-off-by: Nathan Chancellor Reviewed-by: Marco Elver Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Nick Desaulniers Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/Makefile.kasan | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 801c415bac59..b9e94c5e7097 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -33,10 +33,11 @@ else CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \ $(call cc-param,asan-globals=1) \ $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ - $(call cc-param,asan-stack=$(stack_enable)) \ $(call cc-param,asan-instrument-allocas=1) endif +CFLAGS_KASAN += $(call cc-param,asan-stack=$(stack_enable)) + endif # CONFIG_KASAN_GENERIC ifdef CONFIG_KASAN_SW_TAGS From 5c91c0e77b8f2681e2b269c8abb4c5acef434d5b Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Fri, 24 Sep 2021 15:44:03 -0700 Subject: [PATCH 716/866] mm/memory_failure: fix the missing pte_unmap() call The paired pte_unmap() call is missing before the dev_pagemap_mapping_shift() returns. So fix it. David says: "I guess this code never runs on 32bit / highmem, that's why we didn't notice so far". [akpm@linux-foundation.org: cleanup] Link: https://lkml.kernel.org/r/20210923122642.4999-1-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Reviewed-by: David Hildenbrand Cc: Naoya Horiguchi Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 41901c7bb58f..3e6449f2102a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -306,6 +306,7 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, struct vm_area_struct *vma) { unsigned long address = vma_address(page, vma); + unsigned long ret = 0; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -329,11 +330,10 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, if (pmd_devmap(*pmd)) return PMD_SHIFT; pte = pte_offset_map(pmd, address); - if (!pte_present(*pte)) - return 0; - if (pte_devmap(*pte)) - return PAGE_SHIFT; - return 0; + if (pte_present(*pte) && pte_devmap(*pte)) + ret = PAGE_SHIFT; + pte_unmap(pte); + return ret; } /* From bcbda81020c3ee77e2c098cadf3e84f99ca3de17 Mon Sep 17 00:00:00 2001 From: Chen Jun Date: Fri, 24 Sep 2021 15:44:06 -0700 Subject: [PATCH 717/866] mm: fix uninitialized use in overcommit_policy_handler We get an unexpected value of /proc/sys/vm/overcommit_memory after running the following program: int main() { int fd = open("/proc/sys/vm/overcommit_memory", O_RDWR); write(fd, "1", 1); write(fd, "2", 1); close(fd); } write(fd, "2", 1) will pass *ppos = 1 to proc_dointvec_minmax. proc_dointvec_minmax will return 0 without setting new_policy. t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos) -->do_proc_dointvec -->__do_proc_dointvec if (write) { if (proc_first_pos_non_zero_ignore(ppos, table)) goto out; sysctl_overcommit_memory = new_policy; so sysctl_overcommit_memory will be set to an uninitialized value. Check whether new_policy has been changed by proc_dointvec_minmax. Link: https://lkml.kernel.org/r/20210923020524.13289-1-chenjun102@huawei.com Fixes: 56f3547bfa4d ("mm: adjust vm_committed_as_batch according to vm overcommit policy") Signed-off-by: Chen Jun Acked-by: Michal Hocko Reviewed-by: Feng Tang Reviewed-by: Kefeng Wang Cc: Rui Xiang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/util.c b/mm/util.c index 499b6b5767ed..bacabe446906 100644 --- a/mm/util.c +++ b/mm/util.c @@ -787,7 +787,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; - int new_policy; + int new_policy = -1; int ret; /* @@ -805,7 +805,7 @@ int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); - if (ret) + if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); From 265fd1991c1db85fbabaad4946ca0e63e2ae688d Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Sat, 25 Sep 2021 00:06:16 +0900 Subject: [PATCH 718/866] ksmbd: use LOOKUP_BENEATH to prevent the out of share access instead of removing '..' in a given path, call kern_path with LOOKUP_BENEATH flag to prevent the out of share access. ran various test on this: smb2-cat-async smb://127.0.0.1/homes/../out_of_share smb2-cat-async smb://127.0.0.1/homes/foo/../../out_of_share smbclient //127.0.0.1/homes -c "mkdir ../foo2" smbclient //127.0.0.1/homes -c "rename bar ../bar" Cc: Ronnie Sahlberg Cc: Ralph Boehme Tested-by: Steve French Tested-by: Namjae Jeon Acked-by: Namjae Jeon Signed-off-by: Hyunchul Lee Signed-off-by: Steve French --- fs/ksmbd/misc.c | 100 ++++++--------------------- fs/ksmbd/misc.h | 7 +- fs/ksmbd/smb2pdu.c | 74 ++++++++------------ fs/ksmbd/vfs.c | 166 ++++++++++++++++++++++++--------------------- fs/ksmbd/vfs.h | 9 ++- 5 files changed, 145 insertions(+), 211 deletions(-) diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 3eac3c01749f..6a19f4bc692d 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -158,25 +158,21 @@ out: * Return : windows path string or error */ -char *convert_to_nt_pathname(char *filename, char *sharepath) +char *convert_to_nt_pathname(char *filename) { char *ab_pathname; - int len, name_len; - name_len = strlen(filename); - ab_pathname = kmalloc(name_len, GFP_KERNEL); - if (!ab_pathname) - return NULL; + if (strlen(filename) == 0) { + ab_pathname = kmalloc(2, GFP_KERNEL); + ab_pathname[0] = '\\'; + ab_pathname[1] = '\0'; + } else { + ab_pathname = kstrdup(filename, GFP_KERNEL); + if (!ab_pathname) + return NULL; - ab_pathname[0] = '\\'; - ab_pathname[1] = '\0'; - - len = strlen(sharepath); - if (!strncmp(filename, sharepath, len) && name_len != len) { - strscpy(ab_pathname, &filename[len], name_len); ksmbd_conv_path_to_windows(ab_pathname); } - return ab_pathname; } @@ -191,77 +187,19 @@ int get_nlink(struct kstat *st) return nlink; } -char *ksmbd_conv_path_to_unix(char *path) +void ksmbd_conv_path_to_unix(char *path) { - size_t path_len, remain_path_len, out_path_len; - char *out_path, *out_next; - int i, pre_dotdot_cnt = 0, slash_cnt = 0; - bool is_last; - strreplace(path, '\\', '/'); - path_len = strlen(path); - remain_path_len = path_len; - if (path_len == 0) - return ERR_PTR(-EINVAL); +} - out_path = kzalloc(path_len + 2, GFP_KERNEL); - if (!out_path) - return ERR_PTR(-ENOMEM); - out_path_len = 0; - out_next = out_path; +void ksmbd_strip_last_slash(char *path) +{ + int len = strlen(path); - do { - char *name = path + path_len - remain_path_len; - char *next = strchrnul(name, '/'); - size_t name_len = next - name; - - is_last = !next[0]; - if (name_len == 2 && name[0] == '.' && name[1] == '.') { - pre_dotdot_cnt++; - /* handle the case that path ends with "/.." */ - if (is_last) - goto follow_dotdot; - } else { - if (pre_dotdot_cnt) { -follow_dotdot: - slash_cnt = 0; - for (i = out_path_len - 1; i >= 0; i--) { - if (out_path[i] == '/' && - ++slash_cnt == pre_dotdot_cnt + 1) - break; - } - - if (i < 0 && - slash_cnt != pre_dotdot_cnt) { - kfree(out_path); - return ERR_PTR(-EINVAL); - } - - out_next = &out_path[i+1]; - *out_next = '\0'; - out_path_len = i + 1; - - } - - if (name_len != 0 && - !(name_len == 1 && name[0] == '.') && - !(name_len == 2 && name[0] == '.' && name[1] == '.')) { - next[0] = '\0'; - sprintf(out_next, "%s/", name); - out_next += name_len + 1; - out_path_len += name_len + 1; - next[0] = '/'; - } - pre_dotdot_cnt = 0; - } - - remain_path_len -= name_len + 1; - } while (!is_last); - - if (out_path_len > 0) - out_path[out_path_len-1] = '\0'; - path[path_len] = '\0'; - return out_path; + while (len && path[len - 1] == '/') { + path[len - 1] = '\0'; + len--; + } } void ksmbd_conv_path_to_windows(char *path) @@ -298,7 +236,7 @@ char *ksmbd_extract_sharename(char *treename) * * Return: converted name on success, otherwise NULL */ -char *convert_to_unix_name(struct ksmbd_share_config *share, char *name) +char *convert_to_unix_name(struct ksmbd_share_config *share, const char *name) { int no_slash = 0, name_len, path_len; char *new_name; diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index b7b10139ada2..253366bd0951 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -14,12 +14,13 @@ struct ksmbd_file; int match_pattern(const char *str, size_t len, const char *pattern); int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); -char *convert_to_nt_pathname(char *filename, char *sharepath); +char *convert_to_nt_pathname(char *filename); int get_nlink(struct kstat *st); -char *ksmbd_conv_path_to_unix(char *path); +void ksmbd_conv_path_to_unix(char *path); +void ksmbd_strip_last_slash(char *path); void ksmbd_conv_path_to_windows(char *path); char *ksmbd_extract_sharename(char *treename); -char *convert_to_unix_name(struct ksmbd_share_config *share, char *name); +char *convert_to_unix_name(struct ksmbd_share_config *share, const char *name); #define KSMBD_DIR_INFO_ALIGNMENT 8 struct ksmbd_dir_info; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 0c49a0e887d3..761e12171dc4 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -634,7 +634,7 @@ static char * smb2_get_name(struct ksmbd_share_config *share, const char *src, const int maxlen, struct nls_table *local_nls) { - char *name, *norm_name, *unixname; + char *name; name = smb_strndup_from_utf16(src, maxlen, 1, local_nls); if (IS_ERR(name)) { @@ -642,23 +642,9 @@ smb2_get_name(struct ksmbd_share_config *share, const char *src, return name; } - /* change it to absolute unix name */ - norm_name = ksmbd_conv_path_to_unix(name); - if (IS_ERR(norm_name)) { - kfree(name); - return norm_name; - } - kfree(name); - - unixname = convert_to_unix_name(share, norm_name); - kfree(norm_name); - if (!unixname) { - pr_err("can not convert absolute name\n"); - return ERR_PTR(-ENOMEM); - } - - ksmbd_debug(SMB, "absolute name = %s\n", unixname); - return unixname; + ksmbd_conv_path_to_unix(name); + ksmbd_strip_last_slash(name); + return name; } int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) @@ -2352,7 +2338,7 @@ static int smb2_creat(struct ksmbd_work *work, struct path *path, char *name, return rc; } - rc = ksmbd_vfs_kern_path(name, 0, path, 0); + rc = ksmbd_vfs_kern_path(work, name, 0, path, 0); if (rc) { pr_err("cannot get linux path (%s), err = %d\n", name, rc); @@ -2427,7 +2413,7 @@ int smb2_open(struct ksmbd_work *work) struct oplock_info *opinfo; __le32 *next_ptr = NULL; int req_op_level = 0, open_flags = 0, may_flags = 0, file_info = 0; - int rc = 0, len = 0; + int rc = 0; int contxt_cnt = 0, query_disk_id = 0; int maximal_access_ctxt = 0, posix_ctxt = 0; int s_type = 0; @@ -2499,17 +2485,11 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } } else { - len = strlen(share->path); - ksmbd_debug(SMB, "share path len %d\n", len); - name = kmalloc(len + 1, GFP_KERNEL); + name = kstrdup("", GFP_KERNEL); if (!name) { - rsp->hdr.Status = STATUS_NO_MEMORY; rc = -ENOMEM; goto err_out1; } - - memcpy(name, share->path, len); - *(name + len) = '\0'; } req_op_level = req->RequestedOplockLevel; @@ -2632,7 +2612,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - rc = ksmbd_vfs_kern_path(name, LOOKUP_NO_SYMLINKS, &path, 1); + rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, 1); if (!rc) { if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { /* @@ -2661,11 +2641,8 @@ int smb2_open(struct ksmbd_work *work) } if (rc) { - if (rc == -EACCES) { - ksmbd_debug(SMB, - "User does not have right permission\n"); + if (rc != -ENOENT) goto err_out; - } ksmbd_debug(SMB, "can not get linux path for %s, rc = %d\n", name, rc); rc = 0; @@ -3161,7 +3138,7 @@ err_out1: rsp->hdr.Status = STATUS_INVALID_PARAMETER; else if (rc == -EOPNOTSUPP) rsp->hdr.Status = STATUS_NOT_SUPPORTED; - else if (rc == -EACCES || rc == -ESTALE) + else if (rc == -EACCES || rc == -ESTALE || rc == -EXDEV) rsp->hdr.Status = STATUS_ACCESS_DENIED; else if (rc == -ENOENT) rsp->hdr.Status = STATUS_OBJECT_NAME_INVALID; @@ -4277,8 +4254,7 @@ static int get_file_all_info(struct ksmbd_work *work, return -EACCES; } - filename = convert_to_nt_pathname(fp->filename, - work->tcon->share_conf->path); + filename = convert_to_nt_pathname(fp->filename); if (!filename) return -ENOMEM; @@ -4733,7 +4709,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, int rc = 0, len; int fs_infoclass_size = 0; - rc = ksmbd_vfs_kern_path(share->path, LOOKUP_NO_SYMLINKS, &path, 0); + rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path); if (rc) { pr_err("cannot create vfs path\n"); return -EIO; @@ -5282,7 +5258,7 @@ static int smb2_rename(struct ksmbd_work *work, goto out; len = strlen(new_name); - if (new_name[len - 1] != '/') { + if (len > 0 && new_name[len - 1] != '/') { pr_err("not allow base filename in rename\n"); rc = -ESHARE; goto out; @@ -5310,11 +5286,14 @@ static int smb2_rename(struct ksmbd_work *work, } ksmbd_debug(SMB, "new name %s\n", new_name); - rc = ksmbd_vfs_kern_path(new_name, LOOKUP_NO_SYMLINKS, &path, 1); - if (rc) + rc = ksmbd_vfs_kern_path(work, new_name, LOOKUP_NO_SYMLINKS, &path, 1); + if (rc) { + if (rc != -ENOENT) + goto out; file_present = false; - else + } else { path_put(&path); + } if (ksmbd_share_veto_filename(share, new_name)) { rc = -ENOENT; @@ -5384,11 +5363,14 @@ static int smb2_create_link(struct ksmbd_work *work, } ksmbd_debug(SMB, "target name is %s\n", target_name); - rc = ksmbd_vfs_kern_path(link_name, LOOKUP_NO_SYMLINKS, &path, 0); - if (rc) + rc = ksmbd_vfs_kern_path(work, link_name, LOOKUP_NO_SYMLINKS, &path, 0); + if (rc) { + if (rc != -ENOENT) + goto out; file_present = false; - else + } else { path_put(&path); + } if (file_info->ReplaceIfExists) { if (file_present) { @@ -5548,7 +5530,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, * inode size is retained by backup inode size. */ size = i_size_read(inode); - rc = ksmbd_vfs_truncate(work, NULL, fp, alloc_blks * 512); + rc = ksmbd_vfs_truncate(work, fp, alloc_blks * 512); if (rc) { pr_err("truncate failed! filename : %s, err %d\n", fp->filename, rc); @@ -5585,7 +5567,7 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) { ksmbd_debug(SMB, "filename : %s truncated to newsize %lld\n", fp->filename, newsize); - rc = ksmbd_vfs_truncate(work, NULL, fp, newsize); + rc = ksmbd_vfs_truncate(work, fp, newsize); if (rc) { ksmbd_debug(SMB, "truncate failed! filename : %s err %d\n", fp->filename, rc); @@ -5862,7 +5844,7 @@ int smb2_set_info(struct ksmbd_work *work) return 0; err_out: - if (rc == -EACCES || rc == -EPERM) + if (rc == -EACCES || rc == -EPERM || rc == -EXDEV) rsp->hdr.Status = STATUS_ACCESS_DENIED; else if (rc == -EINVAL) rsp->hdr.Status = STATUS_INVALID_PARAMETER; diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 3733e4944c1d..b41954294d38 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -19,6 +19,8 @@ #include #include +#include "../internal.h" /* for vfs_path_lookup */ + #include "glob.h" #include "oplock.h" #include "connection.h" @@ -44,7 +46,6 @@ static char *extract_last_component(char *path) p++; } else { p = NULL; - pr_err("Invalid path %s\n", path); } return p; } @@ -155,7 +156,7 @@ int ksmbd_vfs_query_maximal_access(struct user_namespace *user_ns, /** * ksmbd_vfs_create() - vfs helper for smb create file * @work: work - * @name: file name + * @name: file name that is relative to share * @mode: file create mode * * Return: 0 on success, otherwise error @@ -166,7 +167,8 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) struct dentry *dentry; int err; - dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_NO_SYMLINKS); + dentry = ksmbd_vfs_kern_path_create(work, name, + LOOKUP_NO_SYMLINKS, &path); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); if (err != -ENOENT) @@ -191,7 +193,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) /** * ksmbd_vfs_mkdir() - vfs helper for smb create directory * @work: work - * @name: directory name + * @name: directory name that is relative to share * @mode: directory create mode * * Return: 0 on success, otherwise error @@ -203,8 +205,9 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) struct dentry *dentry; int err; - dentry = kern_path_create(AT_FDCWD, name, &path, - LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY); + dentry = ksmbd_vfs_kern_path_create(work, name, + LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, + &path); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); if (err != -EEXIST) @@ -579,7 +582,7 @@ int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id) /** * ksmbd_vfs_remove_file() - vfs helper for smb rmdir or unlink - * @name: absolute directory or file name + * @name: directory or file name that is relative to share * * Return: 0 on success, otherwise error */ @@ -593,7 +596,7 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) if (ksmbd_override_fsids(work)) return -ENOMEM; - err = kern_path(name, LOOKUP_NO_SYMLINKS, &path); + err = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, false); if (err) { ksmbd_debug(VFS, "can't get %s, err %d\n", name, err); ksmbd_revert_fsids(work); @@ -638,7 +641,7 @@ out_err: /** * ksmbd_vfs_link() - vfs helper for creating smb hardlink * @oldname: source file name - * @newname: hardlink name + * @newname: hardlink name that is relative to share * * Return: 0 on success, otherwise error */ @@ -659,8 +662,9 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, goto out1; } - dentry = kern_path_create(AT_FDCWD, newname, &newpath, - LOOKUP_NO_SYMLINKS | LOOKUP_REVAL); + dentry = ksmbd_vfs_kern_path_create(work, newname, + LOOKUP_NO_SYMLINKS | LOOKUP_REVAL, + &newpath); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); pr_err("path create err for %s, err %d\n", newname, err); @@ -781,14 +785,17 @@ int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, int err; dst_name = extract_last_component(newname); - if (!dst_name) - return -EINVAL; + if (!dst_name) { + dst_name = newname; + newname = ""; + } src_dent_parent = dget_parent(fp->filp->f_path.dentry); src_dent = fp->filp->f_path.dentry; - err = kern_path(newname, LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, - &dst_path); + err = ksmbd_vfs_kern_path(work, newname, + LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, + &dst_path, false); if (err) { ksmbd_debug(VFS, "Cannot get path for %s [%d]\n", newname, err); goto out; @@ -834,61 +841,43 @@ out: /** * ksmbd_vfs_truncate() - vfs helper for smb file truncate * @work: work - * @name: old filename * @fid: file id of old file * @size: truncate to given size * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_truncate(struct ksmbd_work *work, const char *name, +int ksmbd_vfs_truncate(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t size) { - struct path path; int err = 0; + struct file *filp; + + filp = fp->filp; + + /* Do we need to break any of a levelII oplock? */ + smb_break_all_levII_oplock(work, fp, 1); + + if (!work->tcon->posix_extensions) { + struct inode *inode = file_inode(filp); + + if (size < inode->i_size) { + err = check_lock_range(filp, size, + inode->i_size - 1, WRITE); + } else { + err = check_lock_range(filp, inode->i_size, + size - 1, WRITE); + } - if (name) { - err = kern_path(name, LOOKUP_NO_SYMLINKS, &path); if (err) { - pr_err("cannot get linux path for %s, err %d\n", - name, err); - return err; + pr_err("failed due to lock\n"); + return -EAGAIN; } - err = vfs_truncate(&path, size); - if (err) - pr_err("truncate failed for %s err %d\n", - name, err); - path_put(&path); - } else { - struct file *filp; - - filp = fp->filp; - - /* Do we need to break any of a levelII oplock? */ - smb_break_all_levII_oplock(work, fp, 1); - - if (!work->tcon->posix_extensions) { - struct inode *inode = file_inode(filp); - - if (size < inode->i_size) { - err = check_lock_range(filp, size, - inode->i_size - 1, WRITE); - } else { - err = check_lock_range(filp, inode->i_size, - size - 1, WRITE); - } - - if (err) { - pr_err("failed due to lock\n"); - return -EAGAIN; - } - } - - err = vfs_truncate(&filp->f_path, size); - if (err) - pr_err("truncate failed for filename : %s err %d\n", - fp->filename, err); } + err = vfs_truncate(&filp->f_path, size); + if (err) + pr_err("truncate failed for filename : %s err %d\n", + fp->filename, err); return err; } @@ -1206,22 +1195,25 @@ static int ksmbd_vfs_lookup_in_dir(struct path *dir, char *name, size_t namelen) /** * ksmbd_vfs_kern_path() - lookup a file and get path info - * @name: name of file for lookup + * @name: file path that is relative to share * @flags: lookup flags * @path: if lookup succeed, return path info * @caseless: caseless filename lookup * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_kern_path(char *name, unsigned int flags, struct path *path, - bool caseless) +int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, + unsigned int flags, struct path *path, bool caseless) { + struct ksmbd_share_config *share_conf = work->tcon->share_conf; int err; - if (name[0] != '/') - return -EINVAL; - - err = kern_path(name, flags, path); + flags |= LOOKUP_BENEATH; + err = vfs_path_lookup(share_conf->vfs_path.dentry, + share_conf->vfs_path.mnt, + name, + flags, + path); if (!err) return 0; @@ -1235,11 +1227,10 @@ int ksmbd_vfs_kern_path(char *name, unsigned int flags, struct path *path, return -ENOMEM; path_len = strlen(filepath); - remain_len = path_len - 1; + remain_len = path_len; - err = kern_path("/", flags, &parent); - if (err) - goto out; + parent = share_conf->vfs_path; + path_get(&parent); while (d_can_lookup(parent.dentry)) { char *filename = filepath + path_len - remain_len; @@ -1252,21 +1243,21 @@ int ksmbd_vfs_kern_path(char *name, unsigned int flags, struct path *path, err = ksmbd_vfs_lookup_in_dir(&parent, filename, filename_len); - if (err) { - path_put(&parent); - goto out; - } - path_put(&parent); - next[0] = '\0'; - - err = kern_path(filepath, flags, &parent); if (err) goto out; - if (is_last) { - path->mnt = parent.mnt; - path->dentry = parent.dentry; + next[0] = '\0'; + + err = vfs_path_lookup(share_conf->vfs_path.dentry, + share_conf->vfs_path.mnt, + filepath, + flags, + &parent); + if (err) + goto out; + else if (is_last) { + *path = parent; goto out; } @@ -1282,6 +1273,23 @@ out: return err; } +struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, + const char *name, + unsigned int flags, + struct path *path) +{ + char *abs_name; + struct dentry *dent; + + abs_name = convert_to_unix_name(work->tcon->share_conf, name); + if (!abs_name) + return ERR_PTR(-ENOMEM); + + dent = kern_path_create(AT_FDCWD, abs_name, path, flags); + kfree(abs_name); + return dent; +} + int ksmbd_vfs_remove_acl_xattrs(struct user_namespace *user_ns, struct dentry *dentry) { diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index 85db50abdb24..7b1dcaa3fbdc 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -126,7 +126,7 @@ int ksmbd_vfs_link(struct ksmbd_work *work, int ksmbd_vfs_getattr(struct path *path, struct kstat *stat); int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, char *newname); -int ksmbd_vfs_truncate(struct ksmbd_work *work, const char *name, +int ksmbd_vfs_truncate(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t size); struct srv_copychunk; int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, @@ -152,8 +152,13 @@ int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns, struct dentry *dentry, char *attr_name); -int ksmbd_vfs_kern_path(char *name, unsigned int flags, struct path *path, +int ksmbd_vfs_kern_path(struct ksmbd_work *work, + char *name, unsigned int flags, struct path *path, bool caseless); +struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, + const char *name, + unsigned int flags, + struct path *path); int ksmbd_vfs_empty_dir(struct ksmbd_file *fp); void ksmbd_vfs_set_fadvise(struct file *filp, __le32 option); int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp, From b193e15ac69d56f35e1d8e2b5d16cbd47764d053 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E7=8E=8B=E8=B4=87?= Date: Fri, 24 Sep 2021 10:35:58 +0800 Subject: [PATCH 719/866] net: prevent user from passing illegal stab size We observed below report when playing with netlink sock: UBSAN: shift-out-of-bounds in net/sched/sch_api.c:580:10 shift exponent 249 is too large for 32-bit type CPU: 0 PID: 685 Comm: a.out Not tainted Call Trace: dump_stack_lvl+0x8d/0xcf ubsan_epilogue+0xa/0x4e __ubsan_handle_shift_out_of_bounds+0x161/0x182 __qdisc_calculate_pkt_len+0xf0/0x190 __dev_queue_xmit+0x2ed/0x15b0 it seems like kernel won't check the stab log value passing from user, and will use the insane value later to calculate pkt_len. This patch just add a check on the size/cell_log to avoid insane calculation. Reported-by: Abaci Signed-off-by: Michael Wang Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 1 + net/sched/sch_api.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 6d7b12cba015..bf79f3a890af 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -11,6 +11,7 @@ #include #define DEFAULT_TX_QUEUE_LEN 1000 +#define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5e90e9b160e3..12f39a2dffd4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -513,6 +513,12 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return stab; } + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); From 5816b3e6577eaa676ceb00a848f0fd65fe2adc29 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 26 Sep 2021 14:08:19 -0700 Subject: [PATCH 720/866] Linux 5.15-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5e7c1d854441..437ccc66a1c2 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Opossums on Parade # *DOCUMENTATION* From 18d46769d54aba03c2c3fa666fe810f264b5d7b8 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Tue, 21 Sep 2021 14:45:27 +0900 Subject: [PATCH 721/866] ksmbd: remove RFC1002 check in smb2 request MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In smb_common.c you have this function : ksmbd_smb_request() which is called from connection.c once you have read the initial 4 bytes for the next length+smb2 blob. It checks the first byte of this 4 byte preamble for valid values, i.e. a NETBIOSoverTCP SESSION_MESSAGE or a SESSION_KEEP_ALIVE. We don't need to check this for ksmbd since it only implements SMB2 over TCP port 445. The netbios stuff was only used in very old servers when SMB ran over TCP port 139. Now that we run over TCP port 445, this is actually not a NB header anymore and you can just treat it as a 4 byte length field that must be less than 16Mbyte. and remove the references to the RFC1002 constants that no longer applies. Cc: Tom Talpey Cc: Ronnie Sahlberg Cc: Ralph Böhme Cc: Steve French Cc: Sergey Senozhatsky Acked-by: Hyunchul Lee Signed-off-by: Ronnie Sahlberg Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb_common.c | 15 +-------------- fs/ksmbd/smb_common.h | 8 -------- 2 files changed, 1 insertion(+), 22 deletions(-) diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 40f4fafa2e11..5901b2884c60 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -155,20 +155,7 @@ int ksmbd_verify_smb_message(struct ksmbd_work *work) */ bool ksmbd_smb_request(struct ksmbd_conn *conn) { - int type = *(char *)conn->request_buf; - - switch (type) { - case RFC1002_SESSION_MESSAGE: - /* Regular SMB request */ - return true; - case RFC1002_SESSION_KEEP_ALIVE: - ksmbd_debug(SMB, "RFC 1002 session keep alive\n"); - break; - default: - ksmbd_debug(SMB, "RFC 1002 unknown request type 0x%x\n", type); - } - - return false; + return conn->request_buf[0] == 0; } static bool supported_protocol(int idx) diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 0a6af447cc45..994abede27e9 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -48,14 +48,6 @@ #define CIFS_DEFAULT_IOSIZE (64 * 1024) #define MAX_CIFS_SMALL_BUFFER_SIZE 448 /* big enough for most */ -/* RFC 1002 session packet types */ -#define RFC1002_SESSION_MESSAGE 0x00 -#define RFC1002_SESSION_REQUEST 0x81 -#define RFC1002_POSITIVE_SESSION_RESPONSE 0x82 -#define RFC1002_NEGATIVE_SESSION_RESPONSE 0x83 -#define RFC1002_RETARGET_SESSION_RESPONSE 0x84 -#define RFC1002_SESSION_KEEP_ALIVE 0x85 - /* Responses when opening a file. */ #define F_SUPERSEDED 0 #define F_OPENED 1 From d72a9c158893d537d769a669a5837bc80b0f851c Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 24 Sep 2021 09:24:08 +0900 Subject: [PATCH 722/866] ksmbd: fix invalid request buffer access in compound MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Ronnie reported invalid request buffer access in chained command when inserting garbage value to NextCommand of compound request. This patch add validation check to avoid this issue. Cc: Tom Talpey Cc: Ronnie Sahlberg Cc: Ralph Böhme Tested-by: Steve French Reviewed-by: Steve French Acked-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 761e12171dc4..cea376b2dd8f 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -459,13 +459,22 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) bool is_chained_smb2_message(struct ksmbd_work *work) { struct smb2_hdr *hdr = work->request_buf; - unsigned int len; + unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) return false; hdr = ksmbd_req_buf_next(work); - if (le32_to_cpu(hdr->NextCommand) > 0) { + next_cmd = le32_to_cpu(hdr->NextCommand); + if (next_cmd > 0) { + if ((u64)work->next_smb2_rcv_hdr_off + next_cmd + + __SMB2_HEADER_STRUCTURE_SIZE > + get_rfc1002_len(work->request_buf)) { + pr_err("next command(%u) offset exceeds smb msg size\n", + next_cmd); + return false; + } + ksmbd_debug(SMB, "got SMB2 chained command\n"); init_chained_smb2_rsp(work); return true; From 88a04049c08cd62e698bc1b1af2d09574b9e0aee Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Thu, 23 Sep 2021 17:59:27 +0530 Subject: [PATCH 723/866] HID: amd_sfh: Fix potential NULL pointer dereference The cl_data field of a privdata must be allocated and updated before using in amd_sfh_hid_client_init() function. Hence handling NULL pointer cl_data accordingly. Fixes: d46ef750ed58 ("HID: amd_sfh: Fix potential NULL pointer dereference") Signed-off-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- drivers/hid/amd-sfh-hid/amd_sfh_pcie.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index 9a1824757aae..05c007b213f2 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -251,21 +251,17 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i return rc; } - rc = amd_sfh_hid_client_init(privdata); - if (rc) - return rc; - privdata->cl_data = devm_kzalloc(&pdev->dev, sizeof(struct amdtp_cl_data), GFP_KERNEL); if (!privdata->cl_data) return -ENOMEM; - rc = devm_add_action_or_reset(&pdev->dev, amd_mp2_pci_remove, privdata); + mp2_select_ops(privdata); + + rc = amd_sfh_hid_client_init(privdata); if (rc) return rc; - mp2_select_ops(privdata); - - return 0; + return devm_add_action_or_reset(&pdev->dev, amd_mp2_pci_remove, privdata); } static int __maybe_unused amd_mp2_pci_resume(struct device *dev) From da0468a744501065d9ce3891f8ba35be2969ae4d Mon Sep 17 00:00:00 2001 From: Akira Yokosawa Date: Mon, 20 Sep 2021 16:05:00 +0900 Subject: [PATCH 724/866] drm/i915/guc, docs: Fix pdfdocs build error by removing nested grid Nested grids in grid-table cells are not specified as proper ReST constructs. Commit 572f2a5cd974 ("drm/i915/guc: Update firmware to v62.0.0") added a couple of kerneldoc tables of the form: +---+-------+------------------------------------------------------+ | 1 | 31:0 | +------------------------------------------------+ | +---+-------+ | | | |...| | | Embedded `HXG Message`_ | | +---+-------+ | | | | n | 31:0 | +------------------------------------------------+ | +---+-------+------------------------------------------------------+ For "make htmldocs", they happen to work as one might expect, but they are incompatible with "make latexdocs" and "make pdfdocs", and cause the generated gpu.tex file to become incomplete and unbuildable by xelatex. Restore the compatibility by removing those nested grids in the tables. Size comparison of generated gpu.tex: Sphinx 2.4.4 Sphinx 4.2.0 v5.14: 3238686 3841631 v5.15-rc1: 376270 432729 with this fix: 3377846 3998095 Fixes: 572f2a5cd974 ("drm/i915/guc: Update firmware to v62.0.0") Cc: John Harrison Cc: Michal Wajdeczko Cc: Matthew Brost Cc: Daniele Ceraolo Spurio Cc: Matt Roper Cc: Jonathan Corbet Signed-off-by: Akira Yokosawa Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/4a227569-074f-c501-58bb-d0d8f60a8ae9@gmail.com (cherry picked from commit 017792a041183c4f5ec595f386e76a40ed728cfc) Signed-off-by: Jani Nikula --- .../gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h | 10 +++++----- .../drm/i915/gt/uc/abi/guc_communication_mmio_abi.h | 10 +++++----- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h index 99e1fad5ca20..c9086a600bce 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h @@ -102,11 +102,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64); * | +-------+--------------------------------------------------------------+ * | | 7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message | * +---+-------+--------------------------------------------------------------+ - * | 1 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h index bbf1ddb77434..9baa3cb07d13 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h @@ -38,11 +38,11 @@ * +---+-------+--------------------------------------------------------------+ * | | Bits | Description | * +===+=======+==============================================================+ - * | 0 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 0 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ From c83ff0186401169eb27ce5057d820b7a863455c3 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 21 Sep 2021 14:42:02 +0100 Subject: [PATCH 725/866] drm/i915/request: fix early tracepoints Currently we blow up in trace_dma_fence_init, when calling into get_driver_name or get_timeline_name, since both the engine and context might be NULL(or contain some garbage address) in the case of newly allocated slab objects via the request ctor. Note that we also use SLAB_TYPESAFE_BY_RCU here, which allows requests to be immediately freed, but delay freeing the underlying page by an RCU grace period. With this scheme requests can be re-allocated, at the same time as they are also being read by some lockless RCU lookup mechanism. In the ctor case, which is only called for new slab objects(i.e allocate new page and call the ctor for each object) it's safe to reset the context/engine prior to calling into dma_fence_init, since we can be certain that no one is doing an RCU lookup which might depend on peeking at the engine/context, like in active_engine(), since the object can't yet be externally visible. In the recycled case(which might also be externally visible) the request refcount always transitions from 0->1 after we set the context/engine etc, which should ensure it's valid to dereference the engine for example, when doing an RCU list-walk, so long as we can also increment the refcount first. If the refcount is already zero, then the request is considered complete/released. If it's non-zero, then the request might be in the process of being re-allocated, or potentially still in flight, however after successfully incrementing the refcount, it's possible to carefully inspect the request state, to determine if the request is still what we were looking for. Note that all externally visible requests returned to the cache must have zero refcount. One possible fix then is to move dma_fence_init out from the request ctor. Originally this was how it was done, but it was moved in: commit 855e39e65cfc33a73724f1cc644ffc5754864a20 Author: Chris Wilson Date: Mon Feb 3 09:41:48 2020 +0000 drm/i915: Initialise basic fence before acquiring seqno where it looks like intel_timeline_get_seqno() relied on some of the rq->fence state, but that is no longer the case since: commit 12ca695d2c1ed26b2dcbb528b42813bd0f216cfc Author: Maarten Lankhorst Date: Tue Mar 23 16:49:50 2021 +0100 drm/i915: Do not share hwsp across contexts any more, v8. intel_timeline_get_seqno() could also be cleaned up slightly by dropping the request argument. Moving dma_fence_init back out of the ctor, should ensure we have enough of the request initialised in case of trace_dma_fence_init. Functionally this should be the same, and is effectively what we were already open coding before, except now we also assign the fence->lock and fence->ops, but since these are invariant for recycled requests(which might be externally visible), and will therefore already hold the same value, it shouldn't matter. An alternative fix, since we don't yet have a fully initialised request when in the ctor, is just setting the context/engine as NULL, but this does require adding some extra handling in get_driver_name etc. v2(Daniel): - Try to make the commit message less confusing Fixes: 855e39e65cfc ("drm/i915: Initialise basic fence before acquiring seqno") Signed-off-by: Matthew Auld Cc: Michael Mason Cc: Daniel Vetter Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210921134202.3803151-1-matthew.auld@intel.com (cherry picked from commit be988eaee1cb208c4445db46bc3ceaf75f586f0b) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_request.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index ce446716d092..79da5eca60af 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); - dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0); - rq->capture_list = NULL; init_llist_head(&rq->execute_cb); @@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; - kref_init(&rq->fence.refcount); - rq->fence.flags = 0; - rq->fence.error = 0; - INIT_LIST_HEAD(&rq->fence.cb_list); - ret = intel_timeline_get_seqno(tl, rq, &seqno); if (ret) goto err_free; - rq->fence.context = tl->fence_context; - rq->fence.seqno = seqno; + dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, + tl->fence_context, seqno); RCU_INIT_POINTER(rq->timeline, tl); rq->hwsp_seqno = tl->hwsp_seqno; From 4b8bcaf8a6d6ab5db51e30865def5cb694eb2966 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Tue, 14 Sep 2021 14:34:12 +0530 Subject: [PATCH 726/866] drm/i915: Remove warning from the rps worker In commit 4e5c8a99e1cb ("drm/i915: Drop i915_request.lock requirement for intel_rps_boost()"), we decoupled the rps worker from the pm so that we could avoid the synchronization penalty which makes the assertion liable to run too early. Which makes warning invalid hence removed. Fixes: 4e5c8a99e1cb ("drm/i915: Drop i915_request.lock requirement for intel_rps_boost()") Reviewed-by: Chris Wilson Signed-off-by: Tejas Upadhyay Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210914090412.1393498-1-tejaskumarx.surendrakumar.upadhyay@intel.com (cherry picked from commit a837a0686308d95ad9c48d32b4dfe86a17dc98c2) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gt/intel_rps.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 591a5224287e..0a03fbed9f9b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -882,8 +882,6 @@ void intel_rps_park(struct intel_rps *rps) if (!intel_rps_is_enabled(rps)) return; - GEM_BUG_ON(atomic_read(&rps->num_waiters)); - if (!intel_rps_clear_active(rps)) return; From 94513069eb549737bcfc3d988d6ed4da948a2de8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 27 Sep 2021 11:58:39 +0200 Subject: [PATCH 727/866] mac80211: fix use-after-free in CCMP/GCMP RX When PN checking is done in mac80211, for fragmentation we need to copy the PN to the RX struct so we can later use it to do a comparison, since commit bf30ca922a0c ("mac80211: check defrag PN against current frame"). Unfortunately, in that commit I used the 'hdr' variable without it being necessarily valid, so use-after-free could occur if it was necessary to reallocate (parts of) the frame. Fix this by reloading the variable after the code that results in the reallocations, if any. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=214401. Cc: stable@vger.kernel.org Fixes: bf30ca922a0c ("mac80211: check defrag PN against current frame") Link: https://lore.kernel.org/r/20210927115838.12b9ac6bb233.I1d066acd5408a662c3b6e828122cd314fcb28cdb@changeid Signed-off-by: Johannes Berg --- net/mac80211/wpa.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index bca47fad5a16..4eed23e27610 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -520,6 +520,9 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -749,6 +752,9 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; From 111461d573741c17eafad029ac93474fa9adcce0 Mon Sep 17 00:00:00 2001 From: MichelleJin Date: Mon, 27 Sep 2021 03:34:57 +0000 Subject: [PATCH 728/866] mac80211: check return value of rhashtable_init When rhashtable_init() fails, it returns -EINVAL. However, since error return value of rhashtable_init is not checked, it can cause use of uninitialized pointers. So, fix unhandled errors of rhashtable_init. Signed-off-by: MichelleJin Link: https://lore.kernel.org/r/20210927033457.1020967-4-shjy180909@gmail.com Signed-off-by: Johannes Berg --- net/mac80211/mesh_pathtbl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index efbefcbac3ac..7cab1cf09bf1 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,7 +60,10 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); - rhashtable_init(&newtbl->rhead, &mesh_rht_params); + if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) { + kfree(newtbl); + return NULL; + } return newtbl; } From 33092aca857bf35a8e9cac0e8340c685a4796e90 Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Fri, 24 Sep 2021 22:05:14 +0200 Subject: [PATCH 729/866] mac80211: Fix Ptk0 rekey documentation @IEEE80211_KEY_FLAG_GENERATE_IV setting is irrelevant for RX. Move the requirement to the correct section in the PTK0 rekey documentation. Signed-off-by: Alexander Wetzel Link: https://lore.kernel.org/r/20210924200514.7936-1-alexander@wetzel-home.de Signed-off-by: Johannes Berg --- include/net/mac80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index af0fc13cea34..618d1f427cb2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2818,13 +2818,13 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: - * 1) They do not hand over frames decrypted with the old key to - mac80211 once the call to set_key() with command %DISABLE_KEY has been - completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + * 1) They do not hand over frames decrypted with the old key to mac80211 + once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command - encrypted with the new key and + encrypted with the new key when also needing + @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ From 44b6aa2ef69f5b0edf595810236f4ff61503b7e9 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 24 Sep 2021 23:31:46 +0100 Subject: [PATCH 730/866] net: hns: Fix spelling mistake "maped" -> "mapped" There is a spelling mistake in a dev_err error message. Fix it. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 3e54017a2a5b..07fdab58001d 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -354,7 +354,7 @@ static int hns_mdio_reset(struct mii_bus *bus) if (dev_of_node(bus->parent)) { if (!mdio_dev->subctrl_vbase) { - dev_err(&bus->dev, "mdio sys ctl reg has not maped\n"); + dev_err(&bus->dev, "mdio sys ctl reg has not mapped\n"); return -ENODEV; } From 763716a55cb1f480ffe1a9702e6b5d9ea1a80a24 Mon Sep 17 00:00:00 2001 From: Matthew Hagan Date: Sat, 25 Sep 2021 11:36:27 +0000 Subject: [PATCH 731/866] net: bgmac-platform: handle mac-address deferral This patch is a replication of Christian Lamparter's "net: bgmac-bcma: handle deferred probe error due to mac-address" patch for the bgmac-platform driver [1]. As is the case with the bgmac-bcma driver, this change is to cover the scenario where the MAC address cannot yet be discovered due to reliance on an nvmem provider which is yet to be instantiated, resulting in a random address being assigned that has to be manually overridden. [1] https://lore.kernel.org/netdev/20210919115725.29064-1-chunkeey@gmail.com Signed-off-by: Matthew Hagan Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-platform.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 4ab5bf64d353..df8ff839cc62 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -192,6 +192,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->dma_dev = &pdev->dev; ret = of_get_mac_address(np, bgmac->net_dev->dev_addr); + if (ret == -EPROBE_DEFER) + return ret; + if (ret) dev_warn(&pdev->dev, "MAC address not present in device tree\n"); From 172da89ed0eaf9d9348f5decb86ad04c624b39d1 Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Fri, 10 Sep 2021 13:45:24 +0200 Subject: [PATCH 732/866] s390/cio: avoid excessive path-verification requests Currently when removing a device from cio_ignore list, we trigger a path-verification for all the subchannels available in the system. This could lead to path-verification requests on subchannels with an online device, which could cause unwanted delay. Instead of all the subchannels, trigger the path-verifications to those without an online device. Reported-by: Julian Wiedmann Fixes: 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers") Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Heiko Carstens --- drivers/s390/cio/blacklist.c | 8 +++++--- drivers/s390/cio/css.c | 40 ++++++++++++++++++++++++++++-------- drivers/s390/cio/css.h | 10 ++++++++- 3 files changed, 45 insertions(+), 13 deletions(-) diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index f3c656975e05..93695d535380 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -262,10 +262,12 @@ static int blacklist_parse_proc_parameters(char *buf) if (strcmp("free", parm) == 0) { rc = blacklist_parse_parameters(buf, free, 0); - /* There could be subchannels without proper devices connected. - * evaluate all the entries + /* + * Evaluate the subchannels without an online device. This way, + * no path-verification will be triggered on those subchannels + * and it avoids unnecessary delays. */ - css_schedule_eval_all(); + css_schedule_eval_cond(CSS_EVAL_NOT_ONLINE, 0); } else if (strcmp("add", parm) == 0) rc = blacklist_parse_parameters(buf, add, 0); else if (strcmp("purge", parm) == 0) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 3377097e65de..44461928aab8 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -788,27 +788,49 @@ static int __unset_registered(struct device *dev, void *data) return 0; } -void css_schedule_eval_all_unreg(unsigned long delay) +static int __unset_online(struct device *dev, void *data) +{ + struct idset *set = data; + struct subchannel *sch = to_subchannel(dev); + struct ccw_device *cdev = sch_get_cdev(sch); + + if (cdev && cdev->online) + idset_sch_del(set, sch->schid); + + return 0; +} + +void css_schedule_eval_cond(enum css_eval_cond cond, unsigned long delay) { unsigned long flags; - struct idset *unreg_set; + struct idset *set; /* Find unregistered subchannels. */ - unreg_set = idset_sch_new(); - if (!unreg_set) { + set = idset_sch_new(); + if (!set) { /* Fallback. */ css_schedule_eval_all(); return; } - idset_fill(unreg_set); - bus_for_each_dev(&css_bus_type, NULL, unreg_set, __unset_registered); + idset_fill(set); + switch (cond) { + case CSS_EVAL_UNREG: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_registered); + break; + case CSS_EVAL_NOT_ONLINE: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_online); + break; + default: + break; + } + /* Apply to slow_subchannel_set. */ spin_lock_irqsave(&slow_subchannel_lock, flags); - idset_add_set(slow_subchannel_set, unreg_set); + idset_add_set(slow_subchannel_set, set); atomic_set(&css_eval_scheduled, 1); queue_delayed_work(cio_work_q, &slow_path_work, delay); spin_unlock_irqrestore(&slow_subchannel_lock, flags); - idset_free(unreg_set); + idset_free(set); } void css_wait_for_slow_path(void) @@ -820,7 +842,7 @@ void css_wait_for_slow_path(void) void css_schedule_reprobe(void) { /* Schedule with a delay to allow merging of subsequent calls. */ - css_schedule_eval_all_unreg(1 * HZ); + css_schedule_eval_cond(CSS_EVAL_UNREG, 1 * HZ); } EXPORT_SYMBOL_GPL(css_schedule_reprobe); diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h index c98522cbe276..ede0b905bc6f 100644 --- a/drivers/s390/cio/css.h +++ b/drivers/s390/cio/css.h @@ -34,6 +34,14 @@ #define SNID_STATE3_MULTI_PATH 1 #define SNID_STATE3_SINGLE_PATH 0 +/* + * Conditions used to specify which subchannels need evaluation + */ +enum css_eval_cond { + CSS_EVAL_UNREG, /* unregistered subchannels */ + CSS_EVAL_NOT_ONLINE /* sch without an online-device */ +}; + struct path_state { __u8 state1 : 2; /* path state value 1 */ __u8 state2 : 2; /* path state value 2 */ @@ -136,7 +144,7 @@ static inline struct channel_subsystem *css_by_id(u8 cssid) /* Helper functions to build lists for the slow path. */ void css_schedule_eval(struct subchannel_id schid); void css_schedule_eval_all(void); -void css_schedule_eval_all_unreg(unsigned long delay); +void css_schedule_eval_cond(enum css_eval_cond, unsigned long delay); int css_complete_work(void); int sch_is_pseudo_sch(struct subchannel *); From 2974b8a691a94ad5bf29b584dd4fb03829aa43d1 Mon Sep 17 00:00:00 2001 From: "Desnes A. Nunes do Rosario" Date: Sat, 25 Sep 2021 12:14:18 -0300 Subject: [PATCH 733/866] Revert "ibmvnic: check failover_pending in login response" This reverts commit d437f5aa23aa2b7bd07cd44b839d7546cc17166f. Code has been duplicated through commit <273c29e944bd> "ibmvnic: check failover_pending in login response" Signed-off-by: Desnes A. Nunes do Rosario Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a4579b340120..6aa6ff89a765 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4708,14 +4708,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, return 0; } - if (adapter->failover_pending) { - adapter->init_done_rc = -EAGAIN; - netdev_dbg(netdev, "Failover pending, ignoring login response\n"); - complete(&adapter->init_done); - /* login response buffer will be released on reset */ - return 0; - } - netdev->mtu = adapter->req_mtu - ETH_HLEN; netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); From ab609f25d19858513919369ff3d9a63c02cd9e2e Mon Sep 17 00:00:00 2001 From: Yanfei Xu Date: Sun, 26 Sep 2021 12:53:13 +0800 Subject: [PATCH 734/866] net: mdiobus: Fix memory leak in __mdiobus_register Once device_register() failed, we should call put_device() to decrement reference count for cleanup. Or it will cause memory leak. BUG: memory leak unreferenced object 0xffff888114032e00 (size 256): comm "kworker/1:3", pid 2960, jiffies 4294943572 (age 15.920s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 08 2e 03 14 81 88 ff ff ................ 08 2e 03 14 81 88 ff ff 90 76 65 82 ff ff ff ff .........ve..... backtrace: [] kmalloc include/linux/slab.h:591 [inline] [] kzalloc include/linux/slab.h:721 [inline] [] device_private_init drivers/base/core.c:3203 [inline] [] device_add+0x89b/0xdf0 drivers/base/core.c:3253 [] __mdiobus_register+0xc3/0x450 drivers/net/phy/mdio_bus.c:537 [] __devm_mdiobus_register+0x75/0xf0 drivers/net/phy/mdio_devres.c:87 [] ax88772_init_mdio drivers/net/usb/asix_devices.c:676 [inline] [] ax88772_bind+0x330/0x480 drivers/net/usb/asix_devices.c:786 [] usbnet_probe+0x3ff/0xdf0 drivers/net/usb/usbnet.c:1745 [] usb_probe_interface+0x177/0x370 drivers/usb/core/driver.c:396 [] call_driver_probe drivers/base/dd.c:517 [inline] [] really_probe.part.0+0xe7/0x380 drivers/base/dd.c:596 [] really_probe drivers/base/dd.c:558 [inline] [] __driver_probe_device+0x10c/0x1e0 drivers/base/dd.c:751 [] driver_probe_device+0x2a/0x120 drivers/base/dd.c:781 [] __device_attach_driver+0xf6/0x140 drivers/base/dd.c:898 [] bus_for_each_drv+0xb7/0x100 drivers/base/bus.c:427 [] __device_attach+0x122/0x260 drivers/base/dd.c:969 [] bus_probe_device+0xc6/0xe0 drivers/base/bus.c:487 [] device_add+0x5fb/0xdf0 drivers/base/core.c:3359 [] usb_set_configuration+0x9d9/0xb90 drivers/usb/core/message.c:2170 [] usb_generic_driver_probe+0x8c/0xc0 drivers/usb/core/generic.c:238 BUG: memory leak unreferenced object 0xffff888116f06900 (size 32): comm "kworker/0:2", pid 2670, jiffies 4294944448 (age 7.160s) hex dump (first 32 bytes): 75 73 62 2d 30 30 31 3a 30 30 33 00 00 00 00 00 usb-001:003..... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kstrdup+0x36/0x70 mm/util.c:60 [] kstrdup_const+0x53/0x80 mm/util.c:83 [] kvasprintf_const+0xc2/0x110 lib/kasprintf.c:48 [] kobject_set_name_vargs+0x3b/0xe0 lib/kobject.c:289 [] dev_set_name+0x63/0x90 drivers/base/core.c:3147 [] __mdiobus_register+0xbb/0x450 drivers/net/phy/mdio_bus.c:535 [] __devm_mdiobus_register+0x75/0xf0 drivers/net/phy/mdio_devres.c:87 [] ax88772_init_mdio drivers/net/usb/asix_devices.c:676 [inline] [] ax88772_bind+0x330/0x480 drivers/net/usb/asix_devices.c:786 [] usbnet_probe+0x3ff/0xdf0 drivers/net/usb/usbnet.c:1745 [] usb_probe_interface+0x177/0x370 drivers/usb/core/driver.c:396 [] call_driver_probe drivers/base/dd.c:517 [inline] [] really_probe.part.0+0xe7/0x380 drivers/base/dd.c:596 [] really_probe drivers/base/dd.c:558 [inline] [] __driver_probe_device+0x10c/0x1e0 drivers/base/dd.c:751 [] driver_probe_device+0x2a/0x120 drivers/base/dd.c:781 [] __device_attach_driver+0xf6/0x140 drivers/base/dd.c:898 [] bus_for_each_drv+0xb7/0x100 drivers/base/bus.c:427 [] __device_attach+0x122/0x260 drivers/base/dd.c:969 Reported-by: syzbot+398e7dc692ddbbb4cfec@syzkaller.appspotmail.com Signed-off-by: Yanfei Xu Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/mdio_bus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 53f034fc2ef7..6f4b4e5df639 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -537,6 +537,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); + put_device(&bus->dev); return -EINVAL; } From fe23036192c95b66e60d019d2ec1814d0d561ffd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 26 Sep 2021 19:41:24 +0200 Subject: [PATCH 735/866] dsa: mv88e6xxx: 6161: Use chip wide MAX MTU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The datasheets suggests the 6161 uses a per port setting for jumbo frames. Testing has however shown this is not correct, it uses the old style chip wide MTU control. Change the ops in the 6161 structure to reflect this. Fixes: 1baf0fac10fb ("net: dsa: mv88e6xxx: Use chip-wide max frame size for MTU") Reported by: 曹煜 Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8ab0be793811..86d3cab6ceef 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3725,7 +3725,6 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, .port_set_ether_type = mv88e6351_port_set_ether_type, - .port_set_jumbo_size = mv88e6165_port_set_jumbo_size, .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, .port_pause_limit = mv88e6097_port_pause_limit, .port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit, @@ -3750,6 +3749,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, .phylink_validate = mv88e6185_phylink_validate, + .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; static const struct mv88e6xxx_ops mv88e6165_ops = { From b92ce2f54c0f0ff781e914ec189c25f7bf1b1ec2 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 26 Sep 2021 19:41:25 +0200 Subject: [PATCH 736/866] dsa: mv88e6xxx: Fix MTU definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The MTU passed to the DSA driver is the payload size, typically 1500. However, the switch uses the frame size when applying restrictions. Adjust the MTU with the size of the Ethernet header and the frame checksum. The VLAN header also needs to be included when the frame size it per port, but not when it is global. Fixes: 1baf0fac10fb ("net: dsa: mv88e6xxx: Use chip-wide max frame size for MTU") Reported by: 曹煜 Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 12 ++++++------ drivers/net/dsa/mv88e6xxx/global1.c | 2 ++ drivers/net/dsa/mv88e6xxx/port.c | 2 ++ 3 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 86d3cab6ceef..ed4a6d18142b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2834,8 +2834,8 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; - /* Port Control 2: don't force a good FCS, set the maximum frame size to - * 10240 bytes, disable 802.1q tags checking, don't discard tagged or + /* Port Control 2: don't force a good FCS, set the MTU size to + * 10222 bytes, disable 802.1q tags checking, don't discard tagged or * untagged frames on this port, do a destination address lookup on all * received packets as usual, disable ARP mirroring and don't send a * copy of all transmitted/received frames on this port to the CPU. @@ -2854,7 +2854,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; if (chip->info->ops->port_set_jumbo_size) { - err = chip->info->ops->port_set_jumbo_size(chip, port, 10240); + err = chip->info->ops->port_set_jumbo_size(chip, port, 10218); if (err) return err; } @@ -2944,10 +2944,10 @@ static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) struct mv88e6xxx_chip *chip = ds->priv; if (chip->info->ops->port_set_jumbo_size) - return 10240; + return 10240 - VLAN_ETH_HLEN - ETH_FCS_LEN; else if (chip->info->ops->set_max_frame_size) - return 1632; - return 1522; + return 1632 - VLAN_ETH_HLEN - ETH_FCS_LEN; + return 1522 - VLAN_ETH_HLEN - ETH_FCS_LEN; } static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index 815b0f681d69..5848112036b0 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -232,6 +232,8 @@ int mv88e6185_g1_set_max_frame_size(struct mv88e6xxx_chip *chip, int mtu) u16 val; int err; + mtu += ETH_HLEN + ETH_FCS_LEN; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &val); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index f77e2ee64a60..451028c57af8 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1277,6 +1277,8 @@ int mv88e6165_port_set_jumbo_size(struct mv88e6xxx_chip *chip, int port, u16 reg; int err; + size += VLAN_ETH_HLEN + ETH_FCS_LEN; + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_CTL2, ®); if (err) return err; From b9c587fed61cf88bd45822c3159644445f6d5aa6 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 26 Sep 2021 19:41:26 +0200 Subject: [PATCH 737/866] dsa: mv88e6xxx: Include tagger overhead when setting MTU for DSA and CPU ports MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Same members of the Marvell Ethernet switches impose MTU restrictions on ports used for connecting to the CPU or another switch for DSA. If the MTU is set too low, tagged frames will be discarded. Ensure the worst case tagger overhead is included in setting the MTU for DSA and CPU ports. Fixes: 1baf0fac10fb ("net: dsa: mv88e6xxx: Use chip-wide max frame size for MTU") Reported by: 曹煜 Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 9 ++++++--- drivers/net/dsa/mv88e6xxx/chip.h | 1 + 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index ed4a6d18142b..03744d1c43fc 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2944,10 +2944,10 @@ static int mv88e6xxx_get_max_mtu(struct dsa_switch *ds, int port) struct mv88e6xxx_chip *chip = ds->priv; if (chip->info->ops->port_set_jumbo_size) - return 10240 - VLAN_ETH_HLEN - ETH_FCS_LEN; + return 10240 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; else if (chip->info->ops->set_max_frame_size) - return 1632 - VLAN_ETH_HLEN - ETH_FCS_LEN; - return 1522 - VLAN_ETH_HLEN - ETH_FCS_LEN; + return 1632 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; + return 1522 - VLAN_ETH_HLEN - EDSA_HLEN - ETH_FCS_LEN; } static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) @@ -2955,6 +2955,9 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu) struct mv88e6xxx_chip *chip = ds->priv; int ret = 0; + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + new_mtu += EDSA_HLEN; + mv88e6xxx_reg_lock(chip); if (chip->info->ops->port_set_jumbo_size) ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu); diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 675b1f3e43b7..59f316cc8583 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -18,6 +18,7 @@ #include #include +#define EDSA_HLEN 8 #define MV88E6XXX_N_FID 4096 /* PVT limits for 4-bit port and 5-bit switch */ From 5c34aea341b16e29fde6e6c8d4b18866cd99754d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Sep 2021 10:38:12 -0700 Subject: [PATCH 738/866] perf test: Fix DWARF unwind for optimized builds. To ensure the stack frames are on the stack tail calls optimizations need to be inhibited. If your compiler supports an attribute use it, otherwise use an asm volatile barrier. The barrier fix was suggested here: https://lore.kernel.org/lkml/20201028081123.GT2628@hirez.programming.kicks-ass.net/ Tested with an optimized clang build and by forcing the asm barrier route with an optimized clang build. A GCC bug tracking a proper disable_tail_calls is: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97831 Fixes: 9ae1e990f1ab ("perf tools: Remove broken __no_tail_call attribute") v2. is a rebase. The original fix patch generated quite a lot of discussion over the right place for the fix: https://lore.kernel.org/lkml/20201114000803.909530-1-irogers@google.com/ The patch reflects my preference of it being near the use, so that future code cleanups don't break this somewhat special usage. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Miguel Ojeda Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: clang-built-linux@googlegroups.com Link: http://lore.kernel.org/lkml/20210922173812.456348-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/dwarf-unwind.c | 39 +++++++++++++++++++++++++++------ 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index a288035eb362..c756284b3b13 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -20,6 +20,23 @@ /* For bsearch. We try to unwind functions in shared object. */ #include +/* + * The test will assert frames are on the stack but tail call optimizations lose + * the frame of the caller. Clang can disable this optimization on a called + * function but GCC currently (11/2020) lacks this attribute. The barrier is + * used to inhibit tail calls in these cases. + */ +#ifdef __has_attribute +#if __has_attribute(disable_tail_calls) +#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls)) +#define NO_TAIL_CALL_BARRIER +#endif +#endif +#ifndef NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_ATTRIBUTE +#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory"); +#endif + static int mmap_handler(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return strcmp((const char *) symbol, funcs[idx]); } -noinline int test_dwarf_unwind__thread(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread) { struct perf_sample sample; unsigned long cnt = 0; @@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread) static int global_unwind_retval = -INT_MAX; -noinline int test_dwarf_unwind__compare(void *p1, void *p2) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2) { /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; @@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2) return p1 - p2; } -noinline int test_dwarf_unwind__krava_3(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread) { struct thread *array[2] = {thread, thread}; void *fp = &bsearch; @@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread) return global_unwind_retval; } -noinline int test_dwarf_unwind__krava_2(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread) { - return test_dwarf_unwind__krava_3(thread); + int ret; + + ret = test_dwarf_unwind__krava_3(thread); + NO_TAIL_CALL_BARRIER; + return ret; } -noinline int test_dwarf_unwind__krava_1(struct thread *thread) +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread) { - return test_dwarf_unwind__krava_2(thread); + int ret; + + ret = test_dwarf_unwind__krava_2(thread); + NO_TAIL_CALL_BARRIER; + return ret; } int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) From 0f892fd1bd29a25a62c236c5d4f942ee3295ef49 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 6 Sep 2021 16:22:38 +0100 Subject: [PATCH 739/866] perf tests: Fix flaky test 'Object code reading' This test occasionally fails on aarch64 when a sample is taken in free@plt and it fails with "Bytes read differ from those read by objdump". This is because that symbol is near a section boundary in the elf file. Despite the -z option to always output zeros, objdump uses bfd_map_over_sections() to iterate through the elf file so it doesn't see outside of the sections where these zeros are and can't print them. For example this boundary proceeds free@plt in libc with a gap of 48 bytes between .plt and .text: objdump -d -z --start-address=0x23cc8 --stop-address=0x23d08 libc-2.30.so libc-2.30.so: file format elf64-littleaarch64 Disassembly of section .plt: 0000000000023cc8 <*ABS*+0x7fd00@plt+0x8>: 23cc8: 91018210 add x16, x16, #0x60 23ccc: d61f0220 br x17 Disassembly of section .text: 0000000000023d00 : 23d00: a9bf7bfd stp x29, x30, [sp, #-16]! 23d04: 910003fd mov x29, sp Taking a sample in free@plt is very rare because it is so small, but the test can be forced to fail almost every time on any platform by linking the test with a shared library that has a single empty function and calling it in a loop. The fix is to zero the buffers so that when there is a jump in the addresses output by objdump, zeros are already filled in between. Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/20210906152238.3415467-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/code-reading.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 9866cddebf23..9b4a765e4b73 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, struct thread *thread, struct state *state) { struct addr_location al; - unsigned char buf1[BUFSZ]; - unsigned char buf2[BUFSZ]; + unsigned char buf1[BUFSZ] = {0}; + unsigned char buf2[BUFSZ] = {0}; size_t ret_len; u64 objdump_addr; const char *objdump_name; From 774f2c0890f8aab5d436276ec52a03532256afc7 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 16 Sep 2021 09:13:14 +0100 Subject: [PATCH 740/866] perf vendor events powerpc: Fix spelling mistake "icach" -> "icache" There is a spelling mistake in the description text, fix it. Signed-off-by: Colin King Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: kernel-janitors@vger.kernel.org Link: http://lore.kernel.org/lkml/20210916081314.41751-1-colin.king@canonical.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/powerpc/power8/other.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json index 84a0cedf1fd9..f1f2965f6775 100644 --- a/tools/perf/pmu-events/arch/powerpc/power8/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json @@ -1046,7 +1046,7 @@ { "EventCode": "0x4e010", "EventName": "PM_GCT_NOSLOT_IC_L3MISS", - "BriefDescription": "Gct empty for this thread due to icach l3 miss", + "BriefDescription": "Gct empty for this thread due to icache l3 miss", "PublicDescription": "" }, { From c6613bd4a57798ef0aefbcdb28d8c90d4c9cecd8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 23 Sep 2021 08:42:54 -0700 Subject: [PATCH 741/866] perf arm: Fix off-by-one directory paths. Relative path include works in the regular build due to -I paths but may fail in other situations. v2. Rebase. Comments on v1 were that we should handle include paths differently and it is agreed that can be a sensible refactor but beyond the scope of this change. https://lore.kernel.org/lkml/20210504191227.793712-1-irogers@google.com/ Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sergey Senozhatsky Cc: Stephane Eranian Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: http://lore.kernel.org/lkml/20210923154254.737657-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/auxtrace.c | 8 +++---- tools/perf/arch/arm/util/cs-etm.c | 24 ++++++++++----------- tools/perf/arch/arm/util/perf_regs.c | 2 +- tools/perf/arch/arm/util/pmu.c | 2 +- tools/perf/arch/arm/util/unwind-libdw.c | 6 +++--- tools/perf/arch/arm/util/unwind-libunwind.c | 4 ++-- 6 files changed, 23 insertions(+), 23 deletions(-) diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index c7c7ec0812d5..5fc6a2a3dbc5 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -8,10 +8,10 @@ #include #include -#include "../../util/auxtrace.h" -#include "../../util/debug.h" -#include "../../util/evlist.h" -#include "../../util/pmu.h" +#include "../../../util/auxtrace.h" +#include "../../../util/debug.h" +#include "../../../util/evlist.h" +#include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 515aae470e23..293a23bf8be3 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -16,19 +16,19 @@ #include #include "cs-etm.h" -#include "../../util/debug.h" -#include "../../util/record.h" -#include "../../util/auxtrace.h" -#include "../../util/cpumap.h" -#include "../../util/event.h" -#include "../../util/evlist.h" -#include "../../util/evsel.h" -#include "../../util/perf_api_probe.h" -#include "../../util/evsel_config.h" -#include "../../util/pmu.h" -#include "../../util/cs-etm.h" +#include "../../../util/debug.h" +#include "../../../util/record.h" +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/perf_api_probe.h" +#include "../../../util/evsel_config.h" +#include "../../../util/pmu.h" +#include "../../../util/cs-etm.h" #include // page_size -#include "../../util/session.h" +#include "../../../util/session.h" #include #include diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c index 2864e2e3776d..2833e101a7c6 100644 --- a/tools/perf/arch/arm/util/perf_regs.c +++ b/tools/perf/arch/arm/util/perf_regs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../../util/perf_regs.h" +#include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG_END diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index bbc297a7e2e3..b8b23b9dc598 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,7 +10,7 @@ #include #include "arm-spe.h" -#include "../../util/pmu.h" +#include "../../../util/pmu.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index 36ba4c69c3c5..b7692cb0c733 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include "../../util/unwind-libdw.h" -#include "../../util/perf_regs.h" -#include "../../util/event.h" +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c index 3a550225dfaf..438906bf0014 100644 --- a/tools/perf/arch/arm/util/unwind-libunwind.c +++ b/tools/perf/arch/arm/util/unwind-libunwind.c @@ -3,8 +3,8 @@ #include #include #include "perf_regs.h" -#include "../../util/unwind.h" -#include "../../util/debug.h" +#include "../../../util/unwind.h" +#include "../../../util/debug.h" int libunwind__arch_reg_id(int regnum) { From 4da6552c5d07bfc88576ed9ad7fc81fce4c3ba41 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Fri, 24 Sep 2021 16:19:42 +0800 Subject: [PATCH 742/866] perf doc: Fix typos all over the place Considering that perf and its subcommands have so many parameters, the documentation is always the first stop for perf beginners. Fixing some spelling errors will relax the eyes of some readers a little bit. s/specicfication/specification/ s/caheline/cacheline/ s/tranasaction/transaction/ s/complan/complain/ s/sched_wakep/sched_wakeup/ s/possble/possible/ s/methology/methodology/ Signed-off-by: Like Xu Acked-by: Ian Rogers Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Jonathan Corbet Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210924081942.38368-1-likexu@tencent.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/jitdump-specification.txt | 2 +- tools/perf/Documentation/perf-c2c.txt | 2 +- tools/perf/Documentation/perf-intel-pt.txt | 2 +- tools/perf/Documentation/perf-lock.txt | 2 +- tools/perf/Documentation/perf-script-perl.txt | 2 +- tools/perf/Documentation/perf-script-python.txt | 2 +- tools/perf/Documentation/perf-stat.txt | 2 +- tools/perf/Documentation/topdown.txt | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt index 52152d156ad9..79936355d819 100644 --- a/tools/perf/Documentation/jitdump-specification.txt +++ b/tools/perf/Documentation/jitdump-specification.txt @@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html -The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html +The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index de6beedb7283..3b6a2c84ea02 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -261,7 +261,7 @@ COALESCE User can specify how to sort offsets for cacheline. Following fields are available and governs the final -output fields set for caheline offsets output: +output fields set for cacheline offsets output: tid - coalesced by process TIDs pid - coalesced by process PIDs diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt index 184ba62420f0..db465fa7ee91 100644 --- a/tools/perf/Documentation/perf-intel-pt.txt +++ b/tools/perf/Documentation/perf-intel-pt.txt @@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns. "Transactions" events correspond to the start or end of transactions. The 'flags' field can be used in perf script to determine whether the event is a -tranasaction start, commit or abort. +transaction start, commit or abort. Note that "instructions", "branches" and "transactions" events depend on code flow packets which can be disabled by using the config term "branch=0". Refer diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 74d774592196..1b4d452923d7 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -44,7 +44,7 @@ COMMON OPTIONS -f:: --force:: - Don't complan, do it. + Don't complain, do it. REPORT OPTIONS -------------- diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt index 5a1f68122f50..fa4f39d305a7 100644 --- a/tools/perf/Documentation/perf-script-perl.txt +++ b/tools/perf/Documentation/perf-script-perl.txt @@ -54,7 +54,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt index 0250dc61cf98..cf4b7f4b625a 100644 --- a/tools/perf/Documentation/perf-script-python.txt +++ b/tools/perf/Documentation/perf-script-python.txt @@ -448,7 +448,7 @@ all sched_wakeup events in the system: Traces meant to be processed using a script should be recorded with the above option: -a to enable system-wide collection. -The format file for the sched_wakep event defines the following fields +The format file for the sched_wakeup event defines the following fields (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format): ---- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4c9310be6acc..7e6fb7cbc0f4 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements. Print metrics or metricgroups specified in a comma separated list. For a group all metrics from the group are added. The events from the metrics are automatically measured. -See perf list output for the possble metrics and metricgroups. +See perf list output for the possible metrics and metricgroups. -A:: --no-aggr:: diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt index c6302df4cf29..a15b93fdcf50 100644 --- a/tools/perf/Documentation/topdown.txt +++ b/tools/perf/Documentation/topdown.txt @@ -2,7 +2,7 @@ Using TopDown metrics in user space ----------------------------------- Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown -methology to break down CPU pipeline execution into 4 bottlenecks: +methodology to break down CPU pipeline execution into 4 bottlenecks: frontend bound, backend bound, bad speculation, retiring. For more details on Topdown see [1][5] From a827c007c75be4f6038f3d879045fb1ab6385d6b Mon Sep 17 00:00:00 2001 From: Like Xu Date: Fri, 24 Sep 2021 19:58:17 +0800 Subject: [PATCH 743/866] perf config: Refine error message to eliminate confusion If there is no configuration file at first, the user can write any pair of "key.subkey=value" to the newly created configuration file, while value validation against a valid configurable key is *deferred* until the next execution or the implied execution of "perf config ... ". For example: $ rm ~/.perfconfig $ perf config call-graph.dump-size=65529 $ cat ~/.perfconfig # this file is auto-generated. [call-graph] dump-size = 65529 $ perf config call-graph.dump-size=2048 callchain: Incorrect stack dump size (max 65528): 65529 Error: wrong config key-value pair call-graph.dump-size=65529 The user might expect that the second value 2048 is valid and can be updated to the configuration file, but the error message is very confusing because the first value 65529 is not reported as an error during the last configuration. It is recommended not to change the current behavior of delayed validation (as more effort is needed), but to refine the original error message to *clearly indicate* that the cause of the error is the configuration file. Signed-off-by: Like Xu Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20210924115817.58689-1-likexu@tencent.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/config.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4fb5e90d7a57..60ce5908c664 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set, section->name, item->name); ret = fn(key, value, data); if (ret < 0) { - pr_err("Error: wrong config key-value pair %s=%s\n", + pr_err("Error in the given config file: wrong config key-value pair %s=%s\n", key, value); /* * Can't be just a 'break', as perf_config_set__for_each_entry() From e4fe5d7349e0b1c0d3da5b6b3e1efce591e85bd2 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 27 Sep 2021 16:11:14 +0800 Subject: [PATCH 744/866] perf iostat: Use system-wide mode if the target cpu_list is unspecified An iostate use case like "perf iostat 0000:16,0000:97 -- ls" should be implemented to work in system-wide mode to ensure that the output from print_header() is consistent with the user documentation perf-iostat.txt, rather than incorrectly assuming that the kernel does not support it: Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) \ for event (uncore_iio_0/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/). /bin/dmesg | grep -i perf may provide additional information. This error is easily fixed by assigning system-wide mode by default for IOSTAT_RUN only when the target cpu_list is unspecified. Fixes: f07952b179697771 ("perf stat: Basic support for iostat in perf") Signed-off-by: Like Xu Cc: Alexander Antonov Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210927081115.39568-1-likexu@tencent.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f6e87b7be5fa..f0ecfda34ece 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv) goto out; } else if (verbose) iostat_list(evsel_list, &stat_config); + if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target)) + target.system_wide = true; } if (add_default_attributes()) From 4da8b121884d84476f3d50d46a471471af1aa9df Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 27 Sep 2021 16:11:15 +0800 Subject: [PATCH 745/866] perf iostat: Fix Segmentation fault from NULL 'struct perf_counts_values *' If the 'perf iostat' user specifies two or more iio_root_ports and also specifies the cpu(s) by -C which is not *connected to all* the above iio ports, the iostat_print_metric() will run into trouble: For example: $ perf iostat list S0-uncore_iio_0<0000:16> S1-uncore_iio_0<0000:97> # <--- CPU 1 is located in the socket S0 $ perf iostat 0000:16,0000:97 -C 1 -- ls port Inbound Read(MB) Inbound Write(MB) Outbound Read(MB) Outbound Write(MB) ../perf-iostat: line 12: 104418 Segmentation fault (core dumped) perf stat --iostat$DELIMITER$* The core-dump stack says, in the above corner case, the returned (struct perf_counts_values *) count will be NULL, and the caller iostat_print_metric() apparently doesn't not handle this case. 433 struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); 434 435 if (count->run && count->ena) { (gdb) p count $1 = (struct perf_counts_values *) 0x0 The deeper reason is that there are actually no statistics from the user specified pair "iostat 0000:X, -C (disconnected) Y ", but let's fix it with minimum cost by adding a NULL check in the user space. Fixes: f9ed693e8bc0e7de ("perf stat: Enable iostat mode for x86 platforms") Signed-off-by: Like Xu Cc: Alexander Antonov Cc: Alexander Shishkin Cc: Ian Rogers Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lore.kernel.org/lkml/20210927081115.39568-2-likexu@tencent.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/iostat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index eeafe97b8105..792cd75ade33 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, u8 die = ((struct iio_root_port *)evsel->priv)->die; struct perf_counts_values *count = perf_counts(evsel->counts, die, 0); - if (count->run && count->ena) { + if (count && count->run && count->ena) { if (evsel->prev_raw_counts && !out->force_header) { struct perf_counts_values *prev_count = perf_counts(evsel->prev_raw_counts, die, 0); From 3b1b6e82fb5e08e2cb355d7b2ee8644ec289de66 Mon Sep 17 00:00:00 2001 From: Xu Liang Date: Mon, 27 Sep 2021 15:03:02 +0800 Subject: [PATCH 746/866] net: phy: enhance GPY115 loopback disable function GPY115 need reset PHY when it comes out from loopback mode if the firmware version number (lower 8 bits) is equal to or below 0x76. Fixes: 7d901a1e878a ("net: phy: add Maxlinear GPY115/21x/24x driver") Signed-off-by: Xu Liang Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/mxl-gpy.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 2d5d5081c3b6..5ce1bf03bbd7 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -493,6 +493,25 @@ static int gpy_loopback(struct phy_device *phydev, bool enable) return ret; } +static int gpy115_loopback(struct phy_device *phydev, bool enable) +{ + int ret; + int fw_minor; + + if (enable) + return gpy_loopback(phydev, enable); + + ret = phy_read(phydev, PHY_FWV); + if (ret < 0) + return ret; + + fw_minor = FIELD_GET(PHY_FWV_MINOR_MASK, ret); + if (fw_minor > 0x0076) + return gpy_loopback(phydev, 0); + + return genphy_soft_reset(phydev); +} + static struct phy_driver gpy_drivers[] = { { PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx), @@ -527,7 +546,7 @@ static struct phy_driver gpy_drivers[] = { .handle_interrupt = gpy_handle_interrupt, .set_wol = gpy_set_wol, .get_wol = gpy_get_wol, - .set_loopback = gpy_loopback, + .set_loopback = gpy115_loopback, }, { PHY_ID_MATCH_MODEL(PHY_ID_GPY115C), @@ -544,7 +563,7 @@ static struct phy_driver gpy_drivers[] = { .handle_interrupt = gpy_handle_interrupt, .set_wol = gpy_set_wol, .get_wol = gpy_get_wol, - .set_loopback = gpy_loopback, + .set_loopback = gpy115_loopback, }, { .phy_id = PHY_ID_GPY211B, From 9523b33cc31cf8ce703f8facee9fd16cba36d5ad Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 24 Sep 2021 14:05:25 -0700 Subject: [PATCH 747/866] NIOS2: setup.c: drop unused variable 'dram_start' This is a nuisance when CONFIG_WERROR is set, so drop the variable declaration since the code that used it was removed. ../arch/nios2/kernel/setup.c: In function 'setup_arch': ../arch/nios2/kernel/setup.c:152:13: warning: unused variable 'dram_start' [-Wunused-variable] 152 | int dram_start; Fixes: 7f7bc20bc41a ("nios2: Don't use _end for calculating min_low_pfn") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Reviewed-by: Mike Rapoport Cc: Andreas Oetken Signed-off-by: Dinh Nguyen --- arch/nios2/kernel/setup.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index cf8d687a2644..40bc8fb75e0b 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -149,8 +149,6 @@ static void __init find_limits(unsigned long *min, unsigned long *max_low, void __init setup_arch(char **cmdline_p) { - int dram_start; - console_verbose(); memory_start = memblock_start_of_DRAM(); From 5c49d1850ddd3240d20dc40b01f593e35a184f38 Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Sun, 26 Sep 2021 09:55:45 +0800 Subject: [PATCH 748/866] KVM: VMX: Fix a TSX_CTRL_CPUID_CLEAR field mask issue When updating the host's mask for its MSR_IA32_TSX_CTRL user return entry, clear the mask in the found uret MSR instead of vmx->guest_uret_msrs[i]. Modifying guest_uret_msrs directly is completely broken as 'i' does not point at the MSR_IA32_TSX_CTRL entry. In fact, it's guaranteed to be an out-of-bounds accesses as is always set to kvm_nr_uret_msrs in a prior loop. By sheer dumb luck, the fallout is limited to "only" failing to preserve the host's TSX_CTRL_CPUID_CLEAR. The out-of-bounds access is benign as it's guaranteed to clear a bit in a guest MSR value, which are always zero at vCPU creation on both x86-64 and i386. Cc: stable@vger.kernel.org Fixes: 8ea8b8d6f869 ("KVM: VMX: Use common x86's uret MSR list as the one true list") Signed-off-by: Zhenzhong Duan Reviewed-by: Sean Christopherson Message-Id: <20210926015545.281083-1-zhenzhong.duan@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9ecfcf13a046..116b08904ac3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6848,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); From a89936cce87d60766a75732a9e7e25c51164f47c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:46:17 +0200 Subject: [PATCH 749/866] ipack: ipoctal: fix stack information leak The tty driver name is used also after registering the driver and must specifically not be allocated on the stack to avoid leaking information to user space (or triggering an oops). Drivers should not try to encode topology information in the tty device name but this one snuck in through staging without anyone noticing and another driver has since copied this malpractice. Fixing the ABI is a separate issue, but this at least plugs the security hole. Fixes: ba4dc61fe8c5 ("Staging: ipack: add support for IP-OCTAL mezzanine board") Cc: stable@vger.kernel.org # 3.5 Acked-by: Samuel Iglesias Gonsalvez Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917114622.5412-2-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/ipack/devices/ipoctal.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index c14e65a5d38f..c62fec75987c 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -264,7 +264,6 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, int res; int i; struct tty_driver *tty; - char name[20]; struct ipoctal_channel *channel; struct ipack_region *region; void __iomem *addr; @@ -355,8 +354,11 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, /* Fill struct tty_driver with ipoctal data */ tty->owner = THIS_MODULE; tty->driver_name = KBUILD_MODNAME; - sprintf(name, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); - tty->name = name; + tty->name = kasprintf(GFP_KERNEL, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); + if (!tty->name) { + res = -ENOMEM; + goto err_put_driver; + } tty->major = 0; tty->minor_start = 0; @@ -371,8 +373,7 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, res = tty_register_driver(tty); if (res) { dev_err(&ipoctal->dev->dev, "Can't register tty driver.\n"); - tty_driver_kref_put(tty); - return res; + goto err_free_name; } /* Save struct tty_driver for use it when uninstalling the device */ @@ -409,6 +410,13 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, ipoctal_irq_handler, ipoctal); return 0; + +err_free_name: + kfree(tty->name); +err_put_driver: + tty_driver_kref_put(tty); + + return res; } static inline int ipoctal_copy_write_buffer(struct ipoctal_channel *channel, @@ -696,6 +704,7 @@ static void __ipoctal_remove(struct ipoctal *ipoctal) } tty_unregister_driver(ipoctal->tty_drv); + kfree(ipoctal->tty_drv->name); tty_driver_kref_put(ipoctal->tty_drv); kfree(ipoctal); } From 65c001df517a7bf9be8621b53d43c89f426ce8d6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:46:18 +0200 Subject: [PATCH 750/866] ipack: ipoctal: fix tty registration race Make sure to set the tty class-device driver data before registering the tty to avoid having a racing open() dereference a NULL pointer. Fixes: 9c1d784afc6f ("Staging: ipack/devices/ipoctal: Get rid of ipoctal_list.") Cc: stable@vger.kernel.org # 3.7 Acked-by: Samuel Iglesias Gonsalvez Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917114622.5412-3-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/ipack/devices/ipoctal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index c62fec75987c..262451343127 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -392,13 +392,13 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, spin_lock_init(&channel->lock); channel->pointer_read = 0; channel->pointer_write = 0; - tty_dev = tty_port_register_device(&channel->tty_port, tty, i, NULL); + tty_dev = tty_port_register_device_attr(&channel->tty_port, tty, + i, NULL, channel, NULL); if (IS_ERR(tty_dev)) { dev_err(&ipoctal->dev->dev, "Failed to register tty device.\n"); tty_port_destroy(&channel->tty_port); continue; } - dev_set_drvdata(tty_dev, channel); } /* From cd20d59291d1790dc74248476e928f57fc455189 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:46:19 +0200 Subject: [PATCH 751/866] ipack: ipoctal: fix tty-registration error handling Registration of the ipoctal tty devices is unlikely to fail, but if it ever does, make sure not to deregister a never registered tty device (and dereference a NULL pointer) when the driver is later unbound. Fixes: 2afb41d9d30d ("Staging: ipack/devices/ipoctal: Check tty_register_device return value.") Cc: stable@vger.kernel.org # 3.7 Acked-by: Samuel Iglesias Gonsalvez Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917114622.5412-4-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/ipack/devices/ipoctal.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index 262451343127..d6875aa6a295 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -33,6 +33,7 @@ struct ipoctal_channel { unsigned int pointer_read; unsigned int pointer_write; struct tty_port tty_port; + bool tty_registered; union scc2698_channel __iomem *regs; union scc2698_block __iomem *block_regs; unsigned int board_id; @@ -396,9 +397,11 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, i, NULL, channel, NULL); if (IS_ERR(tty_dev)) { dev_err(&ipoctal->dev->dev, "Failed to register tty device.\n"); + tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); continue; } + channel->tty_registered = true; } /* @@ -698,6 +701,10 @@ static void __ipoctal_remove(struct ipoctal *ipoctal) for (i = 0; i < NR_CHANNELS; i++) { struct ipoctal_channel *channel = &ipoctal->channel[i]; + + if (!channel->tty_registered) + continue; + tty_unregister_device(ipoctal->tty_drv, i); tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); From 445c8132727728dc297492a7d9fc074af3e94ba3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:46:20 +0200 Subject: [PATCH 752/866] ipack: ipoctal: fix missing allocation-failure check Add the missing error handling when allocating the transmit buffer to avoid dereferencing a NULL pointer in write() should the allocation ever fail. Fixes: ba4dc61fe8c5 ("Staging: ipack: add support for IP-OCTAL mezzanine board") Cc: stable@vger.kernel.org # 3.5 Acked-by: Samuel Iglesias Gonsalvez Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917114622.5412-5-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/ipack/devices/ipoctal.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index d6875aa6a295..61c41f535510 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -385,7 +385,9 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, channel = &ipoctal->channel[i]; tty_port_init(&channel->tty_port); - tty_port_alloc_xmit_buf(&channel->tty_port); + res = tty_port_alloc_xmit_buf(&channel->tty_port); + if (res) + continue; channel->tty_port.ops = &ipoctal_tty_port_ops; ipoctal_reset_stats(&channel->stats); From bb8a4fcb2136508224c596a7e665bdba1d7c3c27 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 17 Sep 2021 13:46:21 +0200 Subject: [PATCH 753/866] ipack: ipoctal: fix module reference leak A reference to the carrier module was taken on every open but was only released once when the final reference to the tty struct was dropped. Fix this by taking the module reference and initialising the tty driver data when installing the tty. Fixes: 82a82340bab6 ("ipoctal: get carrier driver to avoid rmmod") Cc: stable@vger.kernel.org # 3.18 Cc: Federico Vaga Acked-by: Samuel Iglesias Gonsalvez Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20210917114622.5412-6-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/ipack/devices/ipoctal.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index 61c41f535510..c709861198e5 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -82,22 +82,34 @@ static int ipoctal_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; } -static int ipoctal_open(struct tty_struct *tty, struct file *file) +static int ipoctal_install(struct tty_driver *driver, struct tty_struct *tty) { struct ipoctal_channel *channel = dev_get_drvdata(tty->dev); struct ipoctal *ipoctal = chan_to_ipoctal(channel, tty->index); - int err; - - tty->driver_data = channel; + int res; if (!ipack_get_carrier(ipoctal->dev)) return -EBUSY; - err = tty_port_open(&channel->tty_port, tty, file); - if (err) - ipack_put_carrier(ipoctal->dev); + res = tty_standard_install(driver, tty); + if (res) + goto err_put_carrier; - return err; + tty->driver_data = channel; + + return 0; + +err_put_carrier: + ipack_put_carrier(ipoctal->dev); + + return res; +} + +static int ipoctal_open(struct tty_struct *tty, struct file *file) +{ + struct ipoctal_channel *channel = tty->driver_data; + + return tty_port_open(&channel->tty_port, tty, file); } static void ipoctal_reset_stats(struct ipoctal_stats *stats) @@ -661,6 +673,7 @@ static void ipoctal_cleanup(struct tty_struct *tty) static const struct tty_operations ipoctal_fops = { .ioctl = NULL, + .install = ipoctal_install, .open = ipoctal_open, .close = ipoctal_close, .write = ipoctal_write_tty, From 4329c8dc110b25d5f04ed20c6821bb60deff279f Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 8 Sep 2021 10:52:36 -0700 Subject: [PATCH 754/866] e100: fix length calculation in e100_get_regs_len commit abf9b902059f ("e100: cleanup unneeded math") tried to simplify e100_get_regs_len and remove a double 'divide and then multiply' calculation that the e100_reg_regs_len function did. This change broke the size calculation entirely as it failed to account for the fact that the numbered registers are actually 4 bytes wide and not 1 byte. This resulted in a significant under allocation of the register buffer used by e100_get_regs. Fix this by properly multiplying the register count by u32 first before adding the size of the dump buffer. Fixes: abf9b902059f ("e100: cleanup unneeded math") Reported-by: Felicitas Hetzelt Signed-off-by: Jacob Keller Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e100.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 373eb027b925..588a59546d12 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2441,7 +2441,11 @@ static void e100_get_drvinfo(struct net_device *netdev, static int e100_get_regs_len(struct net_device *netdev) { struct nic *nic = netdev_priv(netdev); - return 1 + E100_PHY_REGS + sizeof(nic->mem->dump_buf); + + /* We know the number of registers, and the size of the dump buffer. + * Calculate the total size in bytes. + */ + return (1 + E100_PHY_REGS) * sizeof(u32) + sizeof(nic->mem->dump_buf); } static void e100_get_regs(struct net_device *netdev, From 51032e6f17ce990d06123ad7307f258c50d25aa7 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 8 Sep 2021 10:52:37 -0700 Subject: [PATCH 755/866] e100: fix buffer overrun in e100_get_regs The e100_get_regs function is used to implement a simple register dump for the e100 device. The data is broken into a couple of MAC control registers, and then a series of PHY registers, followed by a memory dump buffer. The total length of the register dump is defined as (1 + E100_PHY_REGS) * sizeof(u32) + sizeof(nic->mem->dump_buf). The logic for filling in the PHY registers uses a convoluted inverted count for loop which counts from E100_PHY_REGS (0x1C) down to 0, and assigns the slots 1 + E100_PHY_REGS - i. The first loop iteration will fill in [1] and the final loop iteration will fill in [1 + 0x1C]. This is actually one more than the supposed number of PHY registers. The memory dump buffer is then filled into the space at [2 + E100_PHY_REGS] which will cause that memcpy to assign 4 bytes past the total size. The end result is that we overrun the total buffer size allocated by the kernel, which could lead to a panic or other issues due to memory corruption. It is difficult to determine the actual total number of registers here. The only 8255x datasheet I could find indicates there are 28 total MDI registers. However, we're reading 29 here, and reading them in reverse! In addition, the ethtool e100 register dump interface appears to read the first PHY register to determine if the device is in MDI or MDIx mode. This doesn't appear to be documented anywhere within the 8255x datasheet. I can only assume it must be in register 28 (the extra register we're reading here). Lets not change any of the intended meaning of what we copy here. Just extend the space by 4 bytes to account for the extra register and continue copying the data out in the same order. Change the E100_PHY_REGS value to be the correct total (29) so that the total register dump size is calculated properly. Fix the offset for where we copy the dump buffer so that it doesn't overrun the total size. Re-write the for loop to use counting up instead of the convoluted down-counting. Correct the mdio_read offset to use the 0-based register offsets, but maintain the bizarre reverse ordering so that we have the ABI expected by applications like ethtool. This requires and additional subtraction of 1. It seems a bit odd but it makes the flow of assignment into the register buffer easier to follow. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Felicitas Hetzelt Signed-off-by: Jacob Keller Tested-by: Jacob Keller Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/e100.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 588a59546d12..09ae1939e6db 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2437,7 +2437,7 @@ static void e100_get_drvinfo(struct net_device *netdev, sizeof(info->bus_info)); } -#define E100_PHY_REGS 0x1C +#define E100_PHY_REGS 0x1D static int e100_get_regs_len(struct net_device *netdev) { struct nic *nic = netdev_priv(netdev); @@ -2459,14 +2459,18 @@ static void e100_get_regs(struct net_device *netdev, buff[0] = ioread8(&nic->csr->scb.cmd_hi) << 24 | ioread8(&nic->csr->scb.cmd_lo) << 16 | ioread16(&nic->csr->scb.status); - for (i = E100_PHY_REGS; i >= 0; i--) - buff[1 + E100_PHY_REGS - i] = - mdio_read(netdev, nic->mii.phy_id, i); + for (i = 0; i < E100_PHY_REGS; i++) + /* Note that we read the registers in reverse order. This + * ordering is the ABI apparently used by ethtool and other + * applications. + */ + buff[1 + i] = mdio_read(netdev, nic->mii.phy_id, + E100_PHY_REGS - 1 - i); memset(nic->mem->dump_buf, 0, sizeof(nic->mem->dump_buf)); e100_exec_cb(nic, NULL, e100_dump); msleep(10); - memcpy(&buff[2 + E100_PHY_REGS], nic->mem->dump_buf, - sizeof(nic->mem->dump_buf)); + memcpy(&buff[1 + E100_PHY_REGS], nic->mem->dump_buf, + sizeof(nic->mem->dump_buf)); } static void e100_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) From a2941f6aa71a72be2c82c0a168523a492d093530 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 27 Sep 2021 08:43:06 -0700 Subject: [PATCH 756/866] nvme: add command id quirk for apple controllers Some apple controllers use the command id as an index to implementation specific data structures and will fail if the value is out of bounds. The nvme driver's recently introduced command sequence number breaks this controller. Provide a quirk so these spec incompliant controllers can function as before. The driver will not have the ability to detect bad completions when this quirk is used, but we weren't previously checking this anyway. The quirk bit was selected so that it can readily apply to stable. Link: https://bugzilla.kernel.org/show_bug.cgi?id=214509 Cc: Sven Peter Reported-by: Orlando Chamberlain Reported-by: Aditya Garg Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Tested-by: Sven Peter Link: https://lore.kernel.org/r/20210927154306.387437-1-kbusch@kernel.org Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 4 +++- drivers/nvme/host/nvme.h | 6 ++++++ drivers/nvme/host/pci.c | 3 ++- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e486845d2c7e..7712a8f78337 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -978,6 +978,7 @@ EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) { struct nvme_command *cmd = nvme_req(req)->cmd; + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; blk_status_t ret = BLK_STS_OK; if (!(req->rq_flags & RQF_DONTPREP)) { @@ -1026,7 +1027,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) return BLK_STS_IOERR; } - nvme_req(req)->genctr++; + if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN)) + nvme_req(req)->genctr++; cmd->common.command_id = nvme_cid(req); trace_nvme_setup_cmd(req, cmd); return ret; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9871c0c9374c..ed79a6c7e804 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -138,6 +138,12 @@ enum nvme_quirks { * 48 bits. */ NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), + + /* + * The controller requires the command_id value be be limited, so skip + * encoding the generation sequence number. + */ + NVME_QUIRK_SKIP_CID_GEN = (1 << 17), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b82492cd7503..456a0e8a5718 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3369,7 +3369,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | NVME_QUIRK_128_BYTES_SQES | - NVME_QUIRK_SHARED_TAGS }, + NVME_QUIRK_SHARED_TAGS | + NVME_QUIRK_SKIP_CID_GEN }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } From 78f8876c2d9f6fdeb9ff62ed1911505156cd7b3d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 27 Sep 2021 10:04:10 -0600 Subject: [PATCH 757/866] io-wq: exclusively gate signal based exit on get_signal() return io-wq threads block all signals, except SIGKILL and SIGSTOP. We should not need any extra checking of signal_pending or fatal_signal_pending, rely exclusively on whether or not get_signal() tells us to exit. The original debugging of this issue led to the false positive that we were exiting on non-fatal signals, but that is not the case. The issue was around races with nr_workers accounting. Fixes: 87c169665578 ("io-wq: ensure we exit if thread group is exiting") Fixes: 15e20db2e0ce ("io-wq: only exit on fatal signals") Reported-by: Eric W. Biederman Reported-by: Linus Torvalds Acked-by: "Eric W. Biederman" Signed-off-by: Jens Axboe --- fs/io-wq.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/io-wq.c b/fs/io-wq.c index c2360cdc403d..5bf8aa81715e 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -584,10 +584,7 @@ loop: if (!get_signal(&ksig)) continue; - if (fatal_signal_pending(current) || - signal_group_exit(current->signal)) - break; - continue; + break; } last_timeout = !ret; } From 7d5cfafe8b4006a75b55c2f1fdfdb363f9a5cc98 Mon Sep 17 00:00:00 2001 From: Guo Zhi Date: Wed, 22 Sep 2021 21:48:57 +0800 Subject: [PATCH 758/866] RDMA/hfi1: Fix kernel pointer leak Pointers should be printed with %p or %px rather than cast to 'unsigned long long' and printed with %llx. Change %llx to %p to print the secured pointer. Fixes: 042a00f93aad ("IB/{ipoib,hfi1}: Add a timeout handler for rdma_netdev") Link: https://lore.kernel.org/r/20210922134857.619602-1-qtxuning1999@sjtu.edu.cn Signed-off-by: Guo Zhi Acked-by: Mike Marciniszyn Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index e74ddbe46589..15b0cb0f363f 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -876,14 +876,14 @@ void hfi1_ipoib_tx_timeout(struct net_device *dev, unsigned int q) struct hfi1_ipoib_txq *txq = &priv->txqs[q]; u64 completed = atomic64_read(&txq->complete_txreqs); - dd_dev_info(priv->dd, "timeout txq %llx q %u stopped %u stops %d no_desc %d ring_full %d\n", - (unsigned long long)txq, q, + dd_dev_info(priv->dd, "timeout txq %p q %u stopped %u stops %d no_desc %d ring_full %d\n", + txq, q, __netif_subqueue_stopped(dev, txq->q_idx), atomic_read(&txq->stops), atomic_read(&txq->no_desc), atomic_read(&txq->ring_full)); - dd_dev_info(priv->dd, "sde %llx engine %u\n", - (unsigned long long)txq->sde, + dd_dev_info(priv->dd, "sde %p engine %u\n", + txq->sde, txq->sde ? txq->sde->this_idx : 0); dd_dev_info(priv->dd, "flow %x\n", txq->flow.as_int); dd_dev_info(priv->dd, "sent %llu completed %llu used %llu\n", From cc26aee100588a3f293921342a307b6309ace193 Mon Sep 17 00:00:00 2001 From: Wenpeng Liang Date: Mon, 27 Sep 2021 20:55:56 +0800 Subject: [PATCH 759/866] RDMA/hns: Fix the size setting error when copying CQE in clean_cq() The size of CQE is different for different versions of hardware, so the driver needs to specify the size of CQE explicitly. Fixes: 09a5f210f67e ("RDMA/hns: Add support for CQE in size of 64 Bytes") Link: https://lore.kernel.org/r/20210927125557.15031-2-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index a9c00a2e8ebd..d5f3faa1627a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3299,7 +3299,7 @@ static void __hns_roce_v2_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn, dest = get_cqe_v2(hr_cq, (prod_index + nfreed) & hr_cq->ib_cq.cqe); owner_bit = hr_reg_read(dest, CQE_OWNER); - memcpy(dest, cqe, sizeof(*cqe)); + memcpy(dest, cqe, hr_cq->cqe_size); hr_reg_write(dest, CQE_OWNER, owner_bit); } } From e671f0ecfece14940a9bb81981098910ea278cf7 Mon Sep 17 00:00:00 2001 From: Wenpeng Liang Date: Mon, 27 Sep 2021 20:55:57 +0800 Subject: [PATCH 760/866] RDMA/hns: Add the check of the CQE size of the user space If the CQE size of the user space is not the size supported by the hardware, the creation of CQ should be stopped. Fixes: 09a5f210f67e ("RDMA/hns: Add support for CQE in size of 64 Bytes") Link: https://lore.kernel.org/r/20210927125557.15031-3-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_cq.c | 31 ++++++++++++++++++------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c index 1e9c3c5bee68..d763f097599f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_cq.c +++ b/drivers/infiniband/hw/hns/hns_roce_cq.c @@ -326,19 +326,30 @@ static void set_cq_param(struct hns_roce_cq *hr_cq, u32 cq_entries, int vector, INIT_LIST_HEAD(&hr_cq->rq_list); } -static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata, - struct hns_roce_ib_create_cq *ucmd) +static int set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata, + struct hns_roce_ib_create_cq *ucmd) { struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device); - if (udata) { - if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) - hr_cq->cqe_size = ucmd->cqe_size; - else - hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE; - } else { + if (!udata) { hr_cq->cqe_size = hr_dev->caps.cqe_sz; + return 0; } + + if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size)) { + if (ucmd->cqe_size != HNS_ROCE_V2_CQE_SIZE && + ucmd->cqe_size != HNS_ROCE_V3_CQE_SIZE) { + ibdev_err(&hr_dev->ib_dev, + "invalid cqe size %u.\n", ucmd->cqe_size); + return -EINVAL; + } + + hr_cq->cqe_size = ucmd->cqe_size; + } else { + hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE; + } + + return 0; } int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, @@ -366,7 +377,9 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, set_cq_param(hr_cq, attr->cqe, attr->comp_vector, &ucmd); - set_cqe_size(hr_cq, udata, &ucmd); + ret = set_cqe_size(hr_cq, udata, &ucmd); + if (ret) + return ret; ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr); if (ret) { From 9b3b353ef330e20bc2d99bf3165cc044cff26a09 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 27 Sep 2021 11:26:21 -0700 Subject: [PATCH 761/866] vboxfs: fix broken legacy mount signature checking Commit 9d682ea6bcc7 ("vboxsf: Fix the check for the old binary mount-arguments struct") was meant to fix a build error due to sign mismatch in 'char' and the use of character constants, but it just moved the error elsewhere, in that on some architectures characters and signed and on others they are unsigned, and that's just how the C standard works. The proper fix is a simple "don't do that then". The code was just being silly and odd, and it should never have cared about signed vs unsigned characters in the first place, since what it is testing is not four "characters", but four bytes. And the way to compare four bytes is by using "memcmp()". Which compilers will know to just turn into a single 32-bit compare with a constant, as long as you don't have crazy debug options enabled. Link: https://lore.kernel.org/lkml/20210927094123.576521-1-arnd@kernel.org/ Cc: Arnd Bergmann Cc: Hans de Goede Signed-off-by: Linus Torvalds --- fs/vboxsf/super.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 4f5e59f06284..37dd3fe5b1e9 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -21,10 +21,7 @@ #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ -#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000') -#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377') -#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376') -#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375') +static const unsigned char VBSF_MOUNT_SIGNATURE[4] = "\000\377\376\375"; static int follow_symlinks; module_param(follow_symlinks, int, 0444); @@ -386,12 +383,7 @@ fail_nomem: static int vboxsf_parse_monolithic(struct fs_context *fc, void *data) { - unsigned char *options = data; - - if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 && - options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 && - options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 && - options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) { + if (data && !memcmp(data, VBSF_MOUNT_SIGNATURE, 4)) { vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n"); return -EINVAL; } From f060db99374e80e853ac4916b49f0a903f65e9dc Mon Sep 17 00:00:00 2001 From: Jia He Date: Wed, 22 Sep 2021 23:29:19 +0800 Subject: [PATCH 762/866] ACPI: NFIT: Use fallback node id when numa info in NFIT table is incorrect When ACPI NFIT table is failing to populate correct numa information on arm64, dax_kmem will get NUMA_NO_NODE from the NFIT driver. Without this patch, pmem can't be probed as RAM devices on arm64 guest: $ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s 1g -a 128M kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff] with invalid node: -1 kmem: probe of dax0.0 failed with error -22 Suggested-by: Dan Williams Signed-off-by: Jia He Cc: Fixes: c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM") Link: https://lore.kernel.org/r/20210922152919.6940-1-justin.he@arm.com Signed-off-by: Dan Williams --- drivers/acpi/nfit/core.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index a3ef6cce644c..7dd80acf92c7 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3007,6 +3007,18 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, ndr_desc->target_node = NUMA_NO_NODE; } + /* Fallback to address based numa information if node lookup failed */ + if (ndr_desc->numa_node == NUMA_NO_NODE) { + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address); + dev_info(acpi_desc->dev, "changing numa node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + if (ndr_desc->target_node == NUMA_NO_NODE) { + ndr_desc->target_node = phys_to_target_node(spa->address); + dev_info(acpi_desc->dev, "changing target node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + /* * Persistence domain bits are hierarchical, if * ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then From d55174cccac2e4c2a58ff68b6b573fc0836f73bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Sep 2021 19:34:29 +0200 Subject: [PATCH 763/866] nvdimm/pmem: fix creating the dax group The recent block layer refactoring broke the way how the pmem driver abused device_add_disk. Fix this by properly passing the attribute groups to device_add_disk. Fixes: 52b85909f85d ("block: fold register_disk into device_add_disk") Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Reviewed-by: Dan Williams Tested-by: Darrick J. Wong Link: https://lore.kernel.org/r/20210922173431.2454024-2-hch@lst.de Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 72de88ff0d30..ef4950f80832 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -380,7 +380,6 @@ static int pmem_attach_disk(struct device *dev, struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; struct request_queue *q; - struct device *gendev; struct gendisk *disk; void *addr; int rc; @@ -489,10 +488,8 @@ static int pmem_attach_disk(struct device *dev, } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; - gendev = disk_to_dev(disk); - gendev->groups = pmem_attribute_groups; - device_add_disk(dev, disk, NULL); + device_add_disk(dev, disk, pmem_attribute_groups); if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; From c388a18957efdf31db8e97ec4d2d4b7dc1ca9a44 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Mon, 13 Sep 2021 15:32:20 +0800 Subject: [PATCH 764/866] watchdog/sb_watchdog: fix compilation problem due to COMPILE_TEST Compiling sb_watchdog needs to clearly define SIBYTE_HDR_FEATURES. In arch/mips/sibyte/Platform like: cflags-$(CONFIG_SIBYTE_BCM112X) += \ -I$(srctree)/arch/mips/include/asm/mach-sibyte \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1250_112x_ALL Otherwise, SIBYTE_HDR_FEATURES is SIBYTE_HDR_FMASK_ALL. SIBYTE_HDR_FMASK_ALL is mean: #define SIBYTE_HDR_FMASK_ALL SIBYTE_HDR_FMASK_1250_ALL | SIBYTE_HDR_FMASK_112x_ALL \ | SIBYTE_HDR_FMASK_1480_ALL) So, If not limited to CPU_SB1, we will get such an error: arch/mips/include/asm/sibyte/bcm1480_scd.h:261: error: "M_SPC_CFG_CLEAR" redefined [-Werror] arch/mips/include/asm/sibyte/bcm1480_scd.h:262: error: "M_SPC_CFG_ENABLE" redefined [-Werror] Fixes: da2a68b3eb47 ("watchdog: Enable COMPILE_TEST where possible") Signed-off-by: Jackie Liu Reviewed-by: Guenter Roeck Signed-off-by: Linus Torvalds --- drivers/watchdog/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index b81fe4f7d434..bf59faeb3de1 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1666,7 +1666,7 @@ config WDT_MTX1 config SIBYTE_WDOG tristate "Sibyte SoC hardware watchdog" - depends on CPU_SB1 || (MIPS && COMPILE_TEST) + depends on CPU_SB1 help Watchdog driver for the built in watchdog hardware in Sibyte SoC processors. There are apparently two watchdog timers From b8cf5584ec5b8c67359328b8b03b46657620f304 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 28 Sep 2021 15:04:04 +0900 Subject: [PATCH 765/866] MAINTAINERS: rename cifs_common to smbfs_common in cifs and ksmbd entry commit 23e91d8b7c5a("cifs: rename cifs_common to smbfs_common") cause the following warning from get_maintainer.pl. ./scripts/get_maintainer.pl --self-test=patterns complains: warning: no file matches F: fs/cifs_common/ This patch rename cifs_common to smbfs_common in cifs and ksmbd entry. Reported-by: Lukas Bulwahn Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 5b33791bb8e9..8a8c0e6eb458 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4655,7 +4655,7 @@ W: http://linux-cifs.samba.org/ T: git git://git.samba.org/sfrench/cifs-2.6.git F: Documentation/admin-guide/cifs/ F: fs/cifs/ -F: fs/cifs_common/ +F: fs/smbfs_common/ COMPACTPCI HOTPLUG CORE M: Scott Murray @@ -10193,8 +10193,8 @@ M: Hyunchul Lee L: linux-cifs@vger.kernel.org S: Maintained T: git git://git.samba.org/ksmbd.git -F: fs/cifs_common/ F: fs/ksmbd/ +F: fs/smbfs_common/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins From 8a98ae12fbefdb583a7696de719a1d57e5e940a2 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Wed, 22 Sep 2021 12:11:52 +0100 Subject: [PATCH 766/866] bpf: Exempt CAP_BPF from checks against bpf_jit_limit When introducing CAP_BPF, bpf_jit_charge_modmem() was not changed to treat programs with CAP_BPF as privileged for the purpose of JIT memory allocation. This means that a program without CAP_BPF can block a program with CAP_BPF from loading a program. Fix this by checking bpf_capable() in bpf_jit_charge_modmem(). Fixes: 2c78ee898d8f ("bpf: Implement CAP_BPF") Signed-off-by: Lorenz Bauer Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210922111153.19843-1-lmb@cloudflare.com --- kernel/bpf/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..d6b7dfdd8066 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -827,7 +827,7 @@ int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { - if (!capable(CAP_SYS_ADMIN)) { + if (!bpf_capable()) { atomic_long_sub(pages, &bpf_jit_current); return -EPERM; } From b3aa173d58b437cde5aae5fdce7071212628731b Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 24 Sep 2021 12:35:57 -0700 Subject: [PATCH 767/866] MAINTAINERS: Add btf headers to BPF BPF folks maintain these and they're not picked up by the current MAINTAINERS entries. Files caught by the added globs: include/linux/btf.h include/linux/btf_ids.h include/uapi/linux/btf.h Signed-off-by: Dave Marchevsky Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210924193557.3081469-1-davemarchevsky@fb.com --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a594d5d7edcc..d4122d36e627 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3379,9 +3379,11 @@ F: Documentation/networking/filter.rst F: Documentation/userspace-api/ebpf/ F: arch/*/net/* F: include/linux/bpf* +F: include/linux/btf* F: include/linux/filter.h F: include/trace/events/xdp.h F: include/uapi/linux/bpf* +F: include/uapi/linux/btf* F: include/uapi/linux/filter.h F: kernel/bpf/ F: kernel/trace/bpf_trace.c From bcfd367c2839f2126c048fe59700ec1b538e2b06 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 24 Sep 2021 08:07:25 +0530 Subject: [PATCH 768/866] libbpf: Fix segfault in static linker for objects without BTF When a BPF object is compiled without BTF info (without -g), trying to link such objects using bpftool causes a SIGSEGV due to btf__get_nr_types accessing obj->btf which is NULL. Fix this by checking for the NULL pointer, and return error. Reproducer: $ cat a.bpf.c extern int foo(void); int bar(void) { return foo(); } $ cat b.bpf.c int foo(void) { return 0; } $ clang -O2 -target bpf -c a.bpf.c $ clang -O2 -target bpf -c b.bpf.c $ bpftool gen obj out a.bpf.o b.bpf.o Segmentation fault (core dumped) After fix: $ bpftool gen obj out a.bpf.o b.bpf.o libbpf: failed to find BTF info for object 'a.bpf.o' Error: failed to link 'a.bpf.o': Unknown error -22 (-22) Fixes: a46349227cd8 (libbpf: Add linker extern resolution support for functions and global variables) Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210924023725.70228-1-memxor@gmail.com --- tools/lib/bpf/linker.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 10911a8cad0f..2df880cefdae 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -1649,11 +1649,17 @@ static bool btf_is_non_static(const struct btf_type *t) static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sym_name, int *out_btf_sec_id, int *out_btf_id) { - int i, j, n = btf__get_nr_types(obj->btf), m, btf_id = 0; + int i, j, n, m, btf_id = 0; const struct btf_type *t; const struct btf_var_secinfo *vi; const char *name; + if (!obj->btf) { + pr_warn("failed to find BTF info for object '%s'\n", obj->filename); + return -EINVAL; + } + + n = btf__get_nr_types(obj->btf); for (i = 1; i <= n; i++) { t = btf__type_by_id(obj->btf, i); From 78cc316e9583067884eb8bd154301dc1e9ee945c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 27 Sep 2021 14:39:20 +0200 Subject: [PATCH 769/866] bpf, cgroup: Assign cgroup in cgroup_sk_alloc when called from interrupt If cgroup_sk_alloc() is called from interrupt context, then just assign the root cgroup to skcd->cgroup. Prior to commit 8520e224f547 ("bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode") we would just return, and later on in sock_cgroup_ptr(), we were NULL-testing the cgroup in fast-path, and iff indeed NULL returning the root cgroup (v ?: &cgrp_dfl_root.cgrp). Rather than re-adding the NULL-test to the fast-path we can just assign it once from cgroup_sk_alloc() given v1/v2 handling has been simplified. The migration from NULL test with returning &cgrp_dfl_root.cgrp to assigning &cgrp_dfl_root.cgrp directly does /not/ change behavior for callers of sock_cgroup_ptr(). syzkaller was able to trigger a splat in the legacy netrom code base, where the RX handler in nr_rx_frame() calls nr_make_new() which calls sk_alloc() and therefore cgroup_sk_alloc() with in_interrupt() condition. Thus the NULL skcd->cgroup, where it trips over on cgroup_sk_free() side given it expects a non-NULL object. There are a few other candidates aside from netrom which have similar pattern where in their accept-like implementation, they just call to sk_alloc() and thus cgroup_sk_alloc() instead of sk_clone_lock() with the corresponding cgroup_sk_clone() which then inherits the cgroup from the parent socket. None of them are related to core protocols where BPF cgroup programs are running from. However, in future, they should follow to implement a similar inheritance mechanism. Additionally, with a !CONFIG_CGROUP_NET_PRIO and !CONFIG_CGROUP_NET_CLASSID configuration, the same issue was exposed also prior to 8520e224f547 due to commit e876ecc67db8 ("cgroup: memcg: net: do not associate sock with unrelated cgroup") which added the early in_interrupt() return back then. Fixes: 8520e224f547 ("bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode") Fixes: e876ecc67db8 ("cgroup: memcg: net: do not associate sock with unrelated cgroup") Reported-by: syzbot+df709157a4ecaf192b03@syzkaller.appspotmail.com Reported-by: syzbot+533f389d4026d86a2a95@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Tested-by: syzbot+df709157a4ecaf192b03@syzkaller.appspotmail.com Tested-by: syzbot+533f389d4026d86a2a95@syzkaller.appspotmail.com Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20210927123921.21535-1-daniel@iogearbox.net --- kernel/cgroup/cgroup.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8afa8690d288..570b0c97392a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6574,22 +6574,29 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - /* Don't associate the sock with unrelated interrupted task's cgroup. */ - if (in_interrupt()) - return; + struct cgroup *cgroup; rcu_read_lock(); + /* Don't associate the sock with unrelated interrupted task's cgroup. */ + if (in_interrupt()) { + cgroup = &cgrp_dfl_root.cgrp; + cgroup_get(cgroup); + goto out; + } + while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->cgroup = cset->dfl_cgrp; - cgroup_bpf_get(cset->dfl_cgrp); + cgroup = cset->dfl_cgrp; break; } cpu_relax(); } +out: + skcd->cgroup = cgroup; + cgroup_bpf_get(cgroup); rcu_read_unlock(); } From 435b08ec0094ac1e128afe6cfd0d9311a8c617a7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 27 Sep 2021 14:39:21 +0200 Subject: [PATCH 770/866] bpf, test, cgroup: Use sk_{alloc,free} for test cases BPF test infra has some hacks in place which kzalloc() a socket and perform minimum init via sock_net_set() and sock_init_data(). As a result, the sk's skcd->cgroup is NULL since it didn't go through proper initialization as it would have been the case from sk_alloc(). Rather than re-adding a NULL test in sock_cgroup_ptr() just for this, use sk_{alloc,free}() pair for the test socket. The latter also allows to get rid of the bpf_sk_storage_free() special case. Fixes: 8520e224f547 ("bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode") Fixes: b7a1848e8398 ("bpf: add BPF_PROG_TEST_RUN support for flow dissector") Fixes: 2cb494a36c98 ("bpf: add tests for direct packet access from CGROUP_SKB") Reported-by: syzbot+664b58e9a40fbb2cec71@syzkaller.appspotmail.com Reported-by: syzbot+33f36d0754d4c5c0e102@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Tested-by: syzbot+664b58e9a40fbb2cec71@syzkaller.appspotmail.com Tested-by: syzbot+33f36d0754d4c5c0e102@syzkaller.appspotmail.com Link: https://lore.kernel.org/bpf/20210927123921.21535-2-daniel@iogearbox.net --- net/bpf/test_run.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2eb0e55ef54d..b5f4ef35357c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -552,6 +552,12 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->gso_segs = skb_shinfo(skb)->gso_segs; } +static struct proto bpf_dummy_proto = { + .name = "bpf_dummy", + .owner = THIS_MODULE, + .obj_size = sizeof(struct sock), +}; + int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { @@ -596,20 +602,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, break; } - sk = kzalloc(sizeof(struct sock), GFP_USER); + sk = sk_alloc(net, AF_UNSPEC, GFP_USER, &bpf_dummy_proto, 1); if (!sk) { kfree(data); kfree(ctx); return -ENOMEM; } - sock_net_set(sk, net); sock_init_data(NULL, sk); skb = build_skb(data, 0); if (!skb) { kfree(data); kfree(ctx); - kfree(sk); + sk_free(sk); return -ENOMEM; } skb->sk = sk; @@ -682,8 +687,7 @@ out: if (dev && dev != net->loopback_dev) dev_put(dev); kfree_skb(skb); - bpf_sk_storage_free(sk); - kfree(sk); + sk_free(sk); kfree(ctx); return ret; } From d888eaac4fb1df30320bb1305a8f78efe86524c6 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Mon, 27 Sep 2021 18:01:36 +0200 Subject: [PATCH 771/866] selftests, bpf: Fix makefile dependencies on libbpf When building bpf selftest with make -j, I'm randomly getting build failures such as this one: In file included from progs/bpf_flow.c:19: [...]/tools/testing/selftests/bpf/tools/include/bpf/bpf_helpers.h:11:10: fatal error: 'bpf_helper_defs.h' file not found #include "bpf_helper_defs.h" ^~~~~~~~~~~~~~~~~~~ The file that fails the build varies between runs but it's always in the progs/ subdir. The reason is a missing make dependency on libbpf for the .o files in progs/. There was a dependency before commit 3ac2e20fba07e but that commit removed it to prevent unneeded rebuilds. However, that only works if libbpf has been built already; the 'wildcard' prerequisite does not trigger when there's no bpf_helper_defs.h generated yet. Keep the libbpf as an order-only prerequisite to satisfy both goals. It is always built before the progs/ objects but it does not trigger unnecessary rebuilds by itself. Fixes: 3ac2e20fba07e ("selftests/bpf: BPF object files should depend only on libbpf headers") Signed-off-by: Jiri Benc Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/ee84ab66436fba05a197f952af23c98d90eb6243.1632758415.git.jbenc@redhat.com --- tools/testing/selftests/bpf/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 866531c08e4f..799b88152e9e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -375,7 +375,8 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ $$(INCLUDE_DIR)/vmlinux.h \ - $(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT) + $(wildcard $(BPFDIR)/bpf_*.h) \ + | $(TRUNNER_OUTPUT) $$(BPFOBJ) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS)) From 79e2c306667542b8ee2d9a9d947eadc7039f0a3c Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 23 Sep 2021 10:40:22 +0200 Subject: [PATCH 772/866] selftests, bpf: test_lwt_ip_encap: Really disable rp_filter It's not enough to set net.ipv4.conf.all.rp_filter=0, that does not override a greater rp_filter value on the individual interfaces. We also need to set net.ipv4.conf.default.rp_filter=0 before creating the interfaces. That way, they'll also get their own rp_filter value of zero. Fixes: 0fde56e4385b0 ("selftests: bpf: add test_lwt_ip_encap selftest") Signed-off-by: Jiri Benc Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/b1cdd9d469f09ea6e01e9c89a6071c79b7380f89.1632386362.git.jbenc@redhat.com --- tools/testing/selftests/bpf/test_lwt_ip_encap.sh | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index 59ea56945e6c..b497bb85b667 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -112,6 +112,14 @@ setup() ip netns add "${NS2}" ip netns add "${NS3}" + # rp_filter gets confused by what these tests are doing, so disable it + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -236,11 +244,6 @@ setup() ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} - # rp_filter gets confused by what these tests are doing, so disable it - ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 - TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX) sleep 1 # reduce flakiness From 68223eeec70898cd5e42451a9168cd9b2808e248 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:28:05 -0700 Subject: [PATCH 773/866] driver core: Set deferred probe reason when deferred by driver core When the driver core defers the probe of a device, set the deferred probe reason so that it's easier to debug. The deferred probe reason is available in debugfs under devices_deferred. Reviewed-by: Geert Uytterhoeven Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915172808.620546-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 21d4cb5d3767..bf008040b101 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -975,6 +975,7 @@ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0; + struct fwnode_handle *sup_fw; /* * Device waiting for supplier to become available is not allowed to @@ -983,10 +984,11 @@ int device_links_check_suppliers(struct device *dev) mutex_lock(&fwnode_link_lock); if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) && !fw_devlink_is_permissive()) { - dev_dbg(dev, "probe deferral - wait for supplier %pfwP\n", - list_first_entry(&dev->fwnode->suppliers, - struct fwnode_link, - c_hook)->supplier); + sup_fw = list_first_entry(&dev->fwnode->suppliers, + struct fwnode_link, + c_hook)->supplier; + dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwP\n", + sup_fw); mutex_unlock(&fwnode_link_lock); return -EPROBE_DEFER; } @@ -1001,8 +1003,9 @@ int device_links_check_suppliers(struct device *dev) if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { device_links_missing_supplier(dev); - dev_dbg(dev, "probe deferral - supplier %s not ready\n", - dev_name(link->supplier)); + dev_err_probe(dev, -EPROBE_DEFER, + "supplier %s not ready\n", + dev_name(link->supplier)); ret = -EPROBE_DEFER; break; } From 76f130810b477243ce1312bf5754dc41ce7f91a8 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:28:06 -0700 Subject: [PATCH 774/866] driver core: Create __fwnode_link_del() helper function The same code is repeated in multiple locations. Create a helper function for it. Reviewed-by: Geert Uytterhoeven Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915172808.620546-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index bf008040b101..e215220545f8 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -101,6 +101,19 @@ out: return ret; } +/** + * __fwnode_link_del - Delete a link between two fwnode_handles. + * @link: the fwnode_link to be deleted + * + * The fwnode_link_lock needs to be held when this function is called. + */ +static void __fwnode_link_del(struct fwnode_link *link) +{ + list_del(&link->s_hook); + list_del(&link->c_hook); + kfree(link); +} + /** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted @@ -112,11 +125,8 @@ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -131,11 +141,8 @@ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -1887,9 +1894,7 @@ static void __fw_devlink_link_to_consumers(struct device *dev) if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); } } @@ -1941,9 +1946,7 @@ static void __fw_devlink_link_to_suppliers(struct device *dev, if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); /* If no device link was created, nothing more to do. */ if (ret) From ebd6823af378c7d91f80cbe83ce07b5f166744e4 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:28:07 -0700 Subject: [PATCH 775/866] driver core: Add debug logs when fwnode links are added/deleted This will help with debugging fw_devlink issues. Reviewed-by: Geert Uytterhoeven Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915172808.620546-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/base/core.c b/drivers/base/core.c index e215220545f8..15986cc2fe5e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -95,6 +95,8 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup) list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); + pr_debug("%pfwP Linked as a fwnode consumer to %pfwP\n", + con, sup); out: mutex_unlock(&fwnode_link_lock); @@ -109,6 +111,8 @@ out: */ static void __fwnode_link_del(struct fwnode_link *link) { + pr_debug("%pfwP Dropping the fwnode link to %pfwP\n", + link->consumer, link->supplier); list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); From f2ff7147c6834f244b8ce636b12e71a3bd044629 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:04:25 +0200 Subject: [PATCH 776/866] ALSA: pcsp: Make hrtimer forwarding more robust The hrtimer callback pcsp_do_timer() prepares rearming of the timer with hrtimer_forward(). hrtimer_forward() is intended to provide a mechanism to forward the expiry time of the hrtimer by a multiple of the period argument so that the expiry time greater than the time provided in the 'now' argument. pcsp_do_timer() invokes hrtimer_forward() with the current timer expiry time as 'now' argument. That's providing a periodic timer expiry, but is not really robust when the timer callback is delayed so that the resulting new expiry time is already in the past which causes the callback to be invoked immediately again. If the timer is delayed then the back to back invocation is not really making it better than skipping the missed periods. Sound is distorted in any case. Use hrtimer_forward_now() which ensures that the next expiry is in the future. This prevents hogging the CPU in the timer expiry code and allows later on to remove hrtimer_forward() from the public interfaces. Signed-off-by: Thomas Gleixner Cc: alsa-devel@alsa-project.org Cc: Takashi Iwai Cc: Jaroslav Kysela Link: https://lore.kernel.org/r/20210923153339.623208460@linutronix.de Signed-off-by: Takashi Iwai --- sound/drivers/pcsp/pcsp_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c index ed40d0f7432c..773db4bf0876 100644 --- a/sound/drivers/pcsp/pcsp_lib.c +++ b/sound/drivers/pcsp/pcsp_lib.c @@ -143,7 +143,7 @@ enum hrtimer_restart pcsp_do_timer(struct hrtimer *handle) if (pointer_update) pcsp_pointer_update(chip); - hrtimer_forward(handle, hrtimer_get_expires(handle), ns_to_ktime(ns)); + hrtimer_forward_now(handle, ns_to_ktime(ns)); return HRTIMER_RESTART; } From 6f87d4e637327b1da3294a7cdad60d49faa32742 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Tue, 21 Sep 2021 17:39:34 +0200 Subject: [PATCH 777/866] iommu/dart: Remove iommu_flush_ops apple_dart_tlb_flush_{all,walk} expect to get a struct apple_dart_domain but instead get a struct iommu_domain right now. This breaks those two functions and can lead to kernel panics like the one below. DART can only invalidate the entire TLB and apple_dart_iotlb_sync will already flush everything. There's no need to do that again inside those two functions. Let's just drop them. pci 0000:03:00.0: Removing from iommu group 1 Unable to handle kernel paging request at virtual address 0000000100000023 [...] Call trace: _raw_spin_lock_irqsave+0x54/0xbc apple_dart_hw_stream_command.constprop.0+0x2c/0x130 apple_dart_tlb_flush_all+0x48/0x90 free_io_pgtable_ops+0x40/0x70 apple_dart_domain_free+0x2c/0x44 iommu_group_release+0x68/0xac kobject_cleanup+0x4c/0x1fc kobject_cleanup+0x14c/0x1fc kobject_put+0x64/0x84 iommu_group_remove_device+0x110/0x180 iommu_release_device+0x50/0xa0 [...] Fixes: 46d1fb072e76b161 ("iommu/dart: Add DART iommu driver") Reported-by: Marc Zyngier Signed-off-by: Sven Peter Acked-by: Marc Zyngier Tested-by: Marc Zyngier Link: https://lore.kernel.org/r/20210921153934.35647-1-sven@svenpeter.dev Signed-off-by: Joerg Roedel --- drivers/iommu/apple-dart.c | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 559db9259e65..bc0d9c363184 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -183,7 +183,6 @@ struct apple_dart_master_cfg { static struct platform_driver apple_dart_driver; static const struct iommu_ops apple_dart_iommu_ops; -static const struct iommu_flush_ops apple_dart_tlb_ops; static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom) { @@ -338,22 +337,6 @@ static void apple_dart_iotlb_sync_map(struct iommu_domain *domain, apple_dart_domain_flush_tlb(to_dart_domain(domain)); } -static void apple_dart_tlb_flush_all(void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static void apple_dart_tlb_flush_walk(unsigned long iova, size_t size, - size_t granule, void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static const struct iommu_flush_ops apple_dart_tlb_ops = { - .tlb_flush_all = apple_dart_tlb_flush_all, - .tlb_flush_walk = apple_dart_tlb_flush_walk, -}; - static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -435,7 +418,6 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, .ias = 32, .oas = 36, .coherent_walk = 1, - .tlb = &apple_dart_tlb_ops, .iommu_dev = dart->dev, }; From 0b482d0c75bf321b2fd87d215c3d6df095a601d1 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 22 Sep 2021 13:47:26 +0800 Subject: [PATCH 778/866] iommu/vt-d: Drop "0x" prefix from PCI bus & device addresses 719a19335692 ("iommu/vt-d: Tweak the description of a DMA fault") changed the DMA fault reason from hex to decimal. It also added "0x" prefixes to the PCI bus/device, e.g., - DMAR: [INTR-REMAP] Request device [00:00.5] + DMAR: [INTR-REMAP] Request device [0x00:0x00.5] These no longer match dev_printk() and other similar messages in dmar_match_pci_path() and dmar_acpi_insert_dev_scope(). Drop the "0x" prefixes from the bus and device addresses. Fixes: 719a19335692 ("iommu/vt-d: Tweak the description of a DMA fault") Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210903193711.483999-1-helgaas@kernel.org Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210922054726.499110-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 0ec5514c9980..b7708b93f3fa 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1942,18 +1942,18 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - pr_err("[INTR-REMAP] Request device [0x%02x:0x%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else if (pasid == INVALID_IOASID) - pr_err("[%s NO_PASID] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); else - pr_err("[%s PASID 0x%x] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", pasid, source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, From f0b636804c7c4c564efbca5981e3c56b5c6fe0c5 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 24 Sep 2021 15:45:02 +0200 Subject: [PATCH 779/866] iommu/dart: Clear sid2group entry when a group is freed sid2groups keeps track of which stream id combinations belong to a iommu_group to assign those correctly to devices. When a iommu_group is freed a stale pointer will however remain in sid2groups. This prevents devices with the same stream id combination to ever be attached again (see below). Fix that by creating a shadow copy of the stream id configuration when a group is allocated for the first time and clear the sid2group entry when that group is freed. # echo 1 >/sys/bus/pci/devices/0000\:03\:00.0/remove pci 0000:03:00.0: Removing from iommu group 1 # echo 1 >/sys/bus/pci/rescan [...] pci 0000:03:00.0: BAR 0: assigned [mem 0x6a0000000-0x6a000ffff 64bit pref] pci 0000:03:00.0: BAR 2: assigned [mem 0x6a0010000-0x6a001ffff 64bit pref] pci 0000:03:00.0: BAR 6: assigned [mem 0x6c0100000-0x6c01007ff pref] tg3 0000:03:00.0: Failed to add to iommu group 1: -2 [...] Fixes: 46d1fb072e76b161 ("iommu/dart: Add DART iommu driver") Reported-by: Marc Zyngier Signed-off-by: Sven Peter Tested-by: Marc Zyngier Link: https://lore.kernel.org/r/20210924134502.15589-1-sven@svenpeter.dev Signed-off-by: Joerg Roedel --- drivers/iommu/apple-dart.c | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index bc0d9c363184..fdfa39ec2a4d 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -643,16 +643,34 @@ static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args) return -EINVAL; } +static DEFINE_MUTEX(apple_dart_groups_lock); + +static void apple_dart_release_group(void *iommu_data) +{ + int i, sid; + struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg = iommu_data; + + mutex_lock(&apple_dart_groups_lock); + + for_each_stream_map(i, group_master_cfg, stream_map) + for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) + stream_map->dart->sid2group[sid] = NULL; + + kfree(iommu_data); + mutex_unlock(&apple_dart_groups_lock); +} + static struct iommu_group *apple_dart_device_group(struct device *dev) { - static DEFINE_MUTEX(lock); int i, sid; struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg; struct iommu_group *group = NULL; struct iommu_group *res = ERR_PTR(-EINVAL); - mutex_lock(&lock); + mutex_lock(&apple_dart_groups_lock); for_each_stream_map(i, cfg, stream_map) { for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) { @@ -680,6 +698,20 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) #endif group = generic_device_group(dev); + res = ERR_PTR(-ENOMEM); + if (!group) + goto out; + + group_master_cfg = kzalloc(sizeof(*group_master_cfg), GFP_KERNEL); + if (!group_master_cfg) { + iommu_group_put(group); + goto out; + } + + memcpy(group_master_cfg, cfg, sizeof(*group_master_cfg)); + iommu_group_set_iommudata(group, group_master_cfg, + apple_dart_release_group); + for_each_stream_map(i, cfg, stream_map) for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) stream_map->dart->sid2group[sid] = group; @@ -687,7 +719,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) res = group; out: - mutex_unlock(&lock); + mutex_unlock(&apple_dart_groups_lock); return res; } From ced185824c89b60e65b5a2606954c098320cdfb8 Mon Sep 17 00:00:00 2001 From: Johan Almbladh Date: Mon, 27 Sep 2021 13:11:57 +0000 Subject: [PATCH 780/866] bpf, x86: Fix bpf mapping of atomic fetch implementation Fix the case where the dst register maps to %rax as otherwise this produces an incorrect mapping with the implementation in 981f94c3e921 ("bpf: Add bitwise atomic instructions") as %rax is clobbered given it's part of the cmpxchg as operand. The issue is similar to b29dd96b905f ("bpf, x86: Fix BPF_FETCH atomic and/or/ xor with r0 as src") just that the case of dst register was missed. Before, dst=r0 (%rax) src=r2 (%rsi): [...] c5: mov %rax,%r10 c8: mov 0x0(%rax),%rax <---+ (broken) cc: mov %rax,%r11 | cf: and %rsi,%r11 | d2: lock cmpxchg %r11,0x0(%rax) <---+ d8: jne 0x00000000000000c8 | da: mov %rax,%rsi | dd: mov %r10,%rax | [...] | | After, dst=r0 (%rax) src=r2 (%rsi): | | [...] | da: mov %rax,%r10 | dd: mov 0x0(%r10),%rax <---+ (fixed) e1: mov %rax,%r11 | e4: and %rsi,%r11 | e7: lock cmpxchg %r11,0x0(%r10) <---+ ed: jne 0x00000000000000dd ef: mov %rax,%rsi f2: mov %r10,%rax [...] The remaining combinations were fine as-is though: After, dst=r9 (%r15) src=r0 (%rax): [...] dc: mov %rax,%r10 df: mov 0x0(%r15),%rax e3: mov %rax,%r11 e6: and %r10,%r11 e9: lock cmpxchg %r11,0x0(%r15) ef: jne 0x00000000000000df _ f1: mov %rax,%r10 | (unneeded, but f4: mov %r10,%rax _| not a problem) [...] After, dst=r9 (%r15) src=r4 (%rcx): [...] de: mov %rax,%r10 e1: mov 0x0(%r15),%rax e5: mov %rax,%r11 e8: and %rcx,%r11 eb: lock cmpxchg %r11,0x0(%r15) f1: jne 0x00000000000000e1 f3: mov %rax,%rcx f6: mov %r10,%rax [...] The case of dst == src register is rejected by the verifier and therefore not supported, but x86 JIT also handles this case just fine. After, dst=r0 (%rax) src=r0 (%rax): [...] eb: mov %rax,%r10 ee: mov 0x0(%r10),%rax f2: mov %rax,%r11 f5: and %r10,%r11 f8: lock cmpxchg %r11,0x0(%r10) fe: jne 0x00000000000000ee 100: mov %rax,%r10 103: mov %r10,%rax [...] Fixes: 981f94c3e921 ("bpf: Add bitwise atomic instructions") Reported-by: Johan Almbladh Signed-off-by: Johan Almbladh Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Reviewed-by: Brendan Jackman Acked-by: Alexei Starovoitov --- arch/x86/net/bpf_jit_comp.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d24a512fd6f3..9ea57389c554 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1341,9 +1341,10 @@ st: if (is_imm8(insn->off)) if (insn->imm == (BPF_AND | BPF_FETCH) || insn->imm == (BPF_OR | BPF_FETCH) || insn->imm == (BPF_XOR | BPF_FETCH)) { - u8 *branch_target; bool is64 = BPF_SIZE(insn->code) == BPF_DW; u32 real_src_reg = src_reg; + u32 real_dst_reg = dst_reg; + u8 *branch_target; /* * Can't be implemented with a single x86 insn. @@ -1354,11 +1355,13 @@ st: if (is_imm8(insn->off)) emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0); if (src_reg == BPF_REG_0) real_src_reg = BPF_REG_AX; + if (dst_reg == BPF_REG_0) + real_dst_reg = BPF_REG_AX; branch_target = prog; /* Load old value */ emit_ldx(&prog, BPF_SIZE(insn->code), - BPF_REG_0, dst_reg, insn->off); + BPF_REG_0, real_dst_reg, insn->off); /* * Perform the (commutative) operation locally, * put the result in the AUX_REG. @@ -1369,7 +1372,8 @@ st: if (is_imm8(insn->off)) add_2reg(0xC0, AUX_REG, real_src_reg)); /* Attempt to swap in new value */ err = emit_atomic(&prog, BPF_CMPXCHG, - dst_reg, AUX_REG, insn->off, + real_dst_reg, AUX_REG, + insn->off, BPF_SIZE(insn->code)); if (WARN_ON(err)) return err; @@ -1383,11 +1387,10 @@ st: if (is_imm8(insn->off)) /* Restore R0 after clobbering RAX */ emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX); break; - } err = emit_atomic(&prog, insn->imm, dst_reg, src_reg, - insn->off, BPF_SIZE(insn->code)); + insn->off, BPF_SIZE(insn->code)); if (err) return err; break; From 51bb08dd04a05035a64504faa47651d36b0f3125 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 16:13:02 +0200 Subject: [PATCH 781/866] net: ks8851: fix link error An object file cannot be built for both loadable module and built-in use at the same time: arm-linux-gnueabi-ld: drivers/net/ethernet/micrel/ks8851_common.o: in function `ks8851_probe_common': ks8851_common.c:(.text+0xf80): undefined reference to `__this_module' Change the ks8851_common code to be a standalone module instead, and use Makefile logic to ensure this is built-in if at least one of its two users is. Fixes: 797047f875b5 ("net: ks8851: Implement Parallel bus operations") Link: https://lore.kernel.org/netdev/20210125121937.3900988-1-arnd@kernel.org/ Reviewed-by: Andrew Lunn Acked-by: Marek Vasut Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/micrel/Makefile | 6 ++---- drivers/net/ethernet/micrel/ks8851_common.c | 8 ++++++++ 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/micrel/Makefile b/drivers/net/ethernet/micrel/Makefile index 5cc00d22c708..6ecc4eb30e74 100644 --- a/drivers/net/ethernet/micrel/Makefile +++ b/drivers/net/ethernet/micrel/Makefile @@ -4,8 +4,6 @@ # obj-$(CONFIG_KS8842) += ks8842.o -obj-$(CONFIG_KS8851) += ks8851.o -ks8851-objs = ks8851_common.o ks8851_spi.o -obj-$(CONFIG_KS8851_MLL) += ks8851_mll.o -ks8851_mll-objs = ks8851_common.o ks8851_par.o +obj-$(CONFIG_KS8851) += ks8851_common.o ks8851_spi.o +obj-$(CONFIG_KS8851_MLL) += ks8851_common.o ks8851_par.o obj-$(CONFIG_KSZ884X_PCI) += ksz884x.o diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 3f69bb59ba49..a6db1a8156e1 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -1057,6 +1057,7 @@ int ks8851_suspend(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_suspend); int ks8851_resume(struct device *dev) { @@ -1070,6 +1071,7 @@ int ks8851_resume(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_resume); #endif static int ks8851_register_mdiobus(struct ks8851_net *ks, struct device *dev) @@ -1243,6 +1245,7 @@ err_reg: err_reg_io: return ret; } +EXPORT_SYMBOL_GPL(ks8851_probe_common); int ks8851_remove_common(struct device *dev) { @@ -1261,3 +1264,8 @@ int ks8851_remove_common(struct device *dev) return 0; } +EXPORT_SYMBOL_GPL(ks8851_remove_common); + +MODULE_DESCRIPTION("KS8851 Network driver"); +MODULE_AUTHOR("Ben Dooks "); +MODULE_LICENSE("GPL"); From 05e97b3d33cb25b9d9580b33ea0dd69aa922c529 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 16:15:24 +0200 Subject: [PATCH 782/866] dmascc: add CONFIG_VIRT_TO_BUS dependency Many architectures don't define virt_to_bus() any more, as drivers should be using the dma-mapping interfaces where possible: In file included from drivers/net/hamradio/dmascc.c:27: drivers/net/hamradio/dmascc.c: In function 'tx_on': drivers/net/hamradio/dmascc.c:976:30: error: implicit declaration of function 'virt_to_bus'; did you mean 'virt_to_fix'? [-Werror=implicit-function-declaration] 976 | virt_to_bus(priv->tx_buf[priv->tx_tail]) + n); | ^~~~~~~~~~~ arch/arm/include/asm/dma.h:109:52: note: in definition of macro 'set_dma_addr' 109 | __set_dma_addr(chan, (void *)__bus_to_virt(addr)) | ^~~~ Add the Kconfig dependency to prevent this from being built on architectures without virt_to_bus(). Fixes: bc1abb9e55ce ("dmascc: use proper 'virt_to_bus()' rather than casting to 'int'") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/hamradio/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/hamradio/Kconfig b/drivers/net/hamradio/Kconfig index f4843f9672c1..441da03c23ee 100644 --- a/drivers/net/hamradio/Kconfig +++ b/drivers/net/hamradio/Kconfig @@ -48,6 +48,7 @@ config BPQETHER config DMASCC tristate "High-speed (DMA) SCC driver for AX.25" depends on ISA && AX25 && BROKEN_ON_SMP && ISA_DMA_API + depends on VIRT_TO_BUS help This is a driver for high-speed SCC boards, i.e. those supporting DMA on one port. You usually use those boards to connect your From c23bb54f28d61a48008428e8cd320c947993919b Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Mon, 27 Sep 2021 14:07:18 -0700 Subject: [PATCH 783/866] ionic: fix gathering of debug stats Don't print stats for which we haven't reserved space as it can cause nasty memory bashing and related bad behaviors. Fixes: aa620993b1e5 ("ionic: pull per-q stats work out of queue loops") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_stats.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c index 58a854666c62..c14de5fcedea 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -380,15 +380,6 @@ static void ionic_sw_stats_get_txq_values(struct ionic_lif *lif, u64 **buf, &ionic_dbg_intr_stats_desc[i]); (*buf)++; } - for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { - **buf = IONIC_READ_STAT64(&txqcq->napi_stats, - &ionic_dbg_napi_stats_desc[i]); - (*buf)++; - } - for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { - **buf = txqcq->napi_stats.work_done_cntr[i]; - (*buf)++; - } for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { **buf = txstats->sg_cntr[i]; (*buf)++; From 103bde372f084206c6972be543ecc247ebbff9f3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 27 Sep 2021 14:48:23 -0700 Subject: [PATCH 784/866] net: sun: SUNVNET_COMMON should depend on INET When CONFIG_INET is not set, there are failing references to IPv4 functions, so make this driver depend on INET. Fixes these build errors: sparc64-linux-ld: drivers/net/ethernet/sun/sunvnet_common.o: in function `sunvnet_start_xmit_common': sunvnet_common.c:(.text+0x1a68): undefined reference to `__icmp_send' sparc64-linux-ld: drivers/net/ethernet/sun/sunvnet_common.o: in function `sunvnet_poll_common': sunvnet_common.c:(.text+0x358c): undefined reference to `ip_send_check' Signed-off-by: Randy Dunlap Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Aaron Young Cc: Rashmi Narasimhan Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/sun/Kconfig b/drivers/net/ethernet/sun/Kconfig index 309de38a7530..b0d3f9a2950c 100644 --- a/drivers/net/ethernet/sun/Kconfig +++ b/drivers/net/ethernet/sun/Kconfig @@ -73,6 +73,7 @@ config CASSINI config SUNVNET_COMMON tristate "Common routines to support Sun Virtual Networking" depends on SUN_LDOMS + depends on INET default m config SUNVNET From a9f5970767d11eadc805d5283f202612c7ba1f59 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Sep 2021 17:29:24 -0700 Subject: [PATCH 785/866] net: udp: annotate data race around udp_sk(sk)->corkflag up->corkflag field can be read or written without any lock. Annotate accesses to avoid possible syzbot/KCSAN reports. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/udp.c | 10 +++++----- net/ipv6/udp.c | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8851c9463b4b..2a7825a5b842 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1053,7 +1053,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1361,7 +1361,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, } up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) + if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; @@ -2662,9 +2662,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + WRITE_ONCE(up->corkflag, 1); } else { - up->corkflag = 0; + WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2787,7 +2787,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = up->corkflag; + val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ea53847b5b7e..e505bb007e9f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1303,7 +1303,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); From f4bd73b5a950866f6c6fc98a7b684d307c5d586a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 28 Sep 2021 09:42:27 +0900 Subject: [PATCH 786/866] af_unix: Return errno instead of NULL in unix_create1(). unix_create1() returns NULL on error, and the callers assume that it never fails for reasons other than out of memory. So, the callers always return -ENOMEM when unix_create1() fails. However, it also returns NULL when the number of af_unix sockets exceeds twice the limit controlled by sysctl: fs.file-max. In this case, the callers should return -ENFILE like alloc_empty_file(). This patch changes unix_create1() to return the correct error value instead of NULL on error. Out of curiosity, the assumption has been wrong since 1999 due to this change introduced in 2.2.4 [0]. diff -u --recursive --new-file v2.2.3/linux/net/unix/af_unix.c linux/net/unix/af_unix.c --- v2.2.3/linux/net/unix/af_unix.c Tue Jan 19 11:32:53 1999 +++ linux/net/unix/af_unix.c Sun Mar 21 07:22:00 1999 @@ -388,6 +413,9 @@ { struct sock *sk; + if (atomic_read(&unix_nr_socks) >= 2*max_files) + return NULL; + MOD_INC_USE_COUNT; sk = sk_alloc(PF_UNIX, GFP_KERNEL, 1); if (!sk) { [0]: https://cdn.kernel.org/pub/linux/kernel/v2.2/patch-2.2.4.gz Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/unix/af_unix.c | 49 ++++++++++++++++++++++++++++++---------------- 1 file changed, 32 insertions(+), 17 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 92345c9bb60c..f505b89bda6a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -828,20 +828,25 @@ struct proto unix_stream_proto = { static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, int type) { - struct sock *sk = NULL; struct unix_sock *u; + struct sock *sk; + int err; atomic_long_inc(&unix_nr_socks); - if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) - goto out; + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) { + err = -ENFILE; + goto err; + } if (type == SOCK_STREAM) sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_stream_proto, kern); else /*dgram and seqpacket */ sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_dgram_proto, kern); - if (!sk) - goto out; + if (!sk) { + err = -ENOMEM; + goto err; + } sock_init_data(sock, sk); @@ -861,20 +866,23 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); memset(&u->scm_stat, 0, sizeof(struct scm_stat)); unix_insert_socket(unix_sockets_unbound(sk), sk); -out: - if (sk == NULL) - atomic_long_dec(&unix_nr_socks); - else { - local_bh_disable(); - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - local_bh_enable(); - } + + local_bh_disable(); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + local_bh_enable(); + return sk; + +err: + atomic_long_dec(&unix_nr_socks); + return ERR_PTR(err); } static int unix_create(struct net *net, struct socket *sock, int protocol, int kern) { + struct sock *sk; + if (protocol && protocol != PF_UNIX) return -EPROTONOSUPPORT; @@ -901,7 +909,11 @@ static int unix_create(struct net *net, struct socket *sock, int protocol, return -ESOCKTNOSUPPORT; } - return unix_create1(net, sock, kern, sock->type) ? 0 : -ENOMEM; + sk = unix_create1(net, sock, kern, sock->type); + if (IS_ERR(sk)) + return PTR_ERR(sk); + + return 0; } static int unix_release(struct socket *sock) @@ -1314,12 +1326,15 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, we will have to recheck all again in any case. */ - err = -ENOMEM; - /* create new sock for complete connection */ newsk = unix_create1(sock_net(sk), NULL, 0, sock->type); - if (newsk == NULL) + if (IS_ERR(newsk)) { + err = PTR_ERR(newsk); + newsk = NULL; goto out; + } + + err = -ENOMEM; /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); From c6995117b60ef3f7afca8fb41f906e9f459d869a Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 28 Sep 2021 09:17:20 +0200 Subject: [PATCH 787/866] net: mdio: mscc-miim: Fix the mdio controller According to the documentation the second resource is optional. But the blamed commit ignores that and if the resource is not there it just fails. This patch reverts that to still allow the second resource to be optional because other SoC have the some MDIO controller and doesn't need to second resource. Fixes: 672a1c394950 ("net: mdio: mscc-miim: Make use of the helper function devm_platform_ioremap_resource()") Signed-off-by: Horatiu Vultur Reviewed-by: Cai Huoqing Signed-off-by: David S. Miller --- drivers/net/mdio/mdio-mscc-miim.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index 1ee592d3eae4..17f98f609ec8 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -134,8 +134,9 @@ static int mscc_miim_reset(struct mii_bus *bus) static int mscc_miim_probe(struct platform_device *pdev) { - struct mii_bus *bus; struct mscc_miim_dev *dev; + struct resource *res; + struct mii_bus *bus; int ret; bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev)); @@ -156,10 +157,14 @@ static int mscc_miim_probe(struct platform_device *pdev) return PTR_ERR(dev->regs); } - dev->phy_regs = devm_platform_ioremap_resource(pdev, 1); - if (IS_ERR(dev->phy_regs)) { - dev_err(&pdev->dev, "Unable to map internal phy registers\n"); - return PTR_ERR(dev->phy_regs); + /* This resource is optional */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (res) { + dev->phy_regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(dev->phy_regs)) { + dev_err(&pdev->dev, "Unable to map internal phy registers\n"); + return PTR_ERR(dev->phy_regs); + } } ret = of_mdiobus_register(bus, pdev->dev.of_node); From c894b51e2a23c8c00acb3cea5045c5b70691e790 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 Sep 2021 10:58:34 +0200 Subject: [PATCH 788/866] net: hns3: fix hclge_dbg_dump_tm_pg() stack usage This function copies strings around between multiple buffers including a large on-stack array that causes a build warning on 32-bit systems: drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c: In function 'hclge_dbg_dump_tm_pg': drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c:782:1: error: the frame size of 1424 bytes is larger than 1400 bytes [-Werror=frame-larger-than=] The function can probably be cleaned up a lot, to go back to printing directly into the output buffer, but dynamically allocating the structure is a simpler workaround for now. Fixes: 04d96139ddb3 ("net: hns3: refine function hclge_dbg_dump_tm_pri()") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_debugfs.c | 28 ++++++++++++++++--- 1 file changed, 24 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 87d96f82c318..32f62cd2dd99 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -719,9 +719,9 @@ static void hclge_dbg_fill_shaper_content(struct hclge_tm_shaper_para *para, sprintf(result[(*index)++], "%6u", para->rate); } -static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) +static int __hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *data_str, + char *buf, int len) { - char data_str[ARRAY_SIZE(tm_pg_items)][HCLGE_DBG_DATA_STR_LEN]; struct hclge_tm_shaper_para c_shaper_para, p_shaper_para; char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str; u8 pg_id, sch_mode, weight, pri_bit_map, i, j; @@ -729,8 +729,10 @@ static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) int pos = 0; int ret; - for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) - result[i] = &data_str[i][0]; + for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) { + result[i] = data_str; + data_str += HCLGE_DBG_DATA_STR_LEN; + } hclge_dbg_fill_content(content, sizeof(content), tm_pg_items, NULL, ARRAY_SIZE(tm_pg_items)); @@ -781,6 +783,24 @@ static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) return 0; } +static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) +{ + char *data_str; + int ret; + + data_str = kcalloc(ARRAY_SIZE(tm_pg_items), + HCLGE_DBG_DATA_STR_LEN, GFP_KERNEL); + + if (!data_str) + return -ENOMEM; + + ret = __hclge_dbg_dump_tm_pg(hdev, data_str, buf, len); + + kfree(data_str); + + return ret; +} + static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev, char *buf, int len) { struct hclge_tm_shaper_para shaper_para; From ebc69e897e17373fbe1daaff1debaa77583a5284 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 28 Sep 2021 06:33:15 -0600 Subject: [PATCH 789/866] Revert "block, bfq: honor already-setup queue merges" This reverts commit 2d52c58b9c9bdae0ca3df6a1eab5745ab3f7d80b. We have had several folks complain that this causes hangs for them, which is especially problematic as the commit has also hit stable already. As no resolution seems to be forthcoming right now, revert the patch. Link: https://bugzilla.kernel.org/show_bug.cgi?id=214503 Fixes: 2d52c58b9c9b ("block, bfq: honor already-setup queue merges") Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dd13c2bbc29c..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2662,15 +2662,6 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) * are likely to increase the throughput. */ bfqq->new_bfqq = new_bfqq; - /* - * The above assignment schedules the following redirections: - * each time some I/O for bfqq arrives, the process that - * generated that I/O is disassociated from bfqq and - * associated with new_bfqq. Here we increases new_bfqq->ref - * in advance, adding the number of processes that are - * expected to be associated with new_bfqq as they happen to - * issue I/O. - */ new_bfqq->ref += process_refs; return new_bfqq; } @@ -2733,10 +2724,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, { struct bfq_queue *in_service_bfqq, *new_bfqq; - /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; - /* * Check delayed stable merge for rotational or non-queueing * devs. For this branch to be executed, bfqq must not be @@ -2838,6 +2825,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (bfq_too_late_for_merging(bfqq)) return NULL; + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) return NULL; From e02c16b9cd24925ea627f007df9ca9ee00eaaa62 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Sep 2021 22:36:21 +0000 Subject: [PATCH 790/866] selftests: KVM: Don't clobber XMM register when read There is no need to clobber a register that is only being read from. Oops. Drop the XMM register from the clobbers list. Signed-off-by: Oliver Upton Message-Id: <20210927223621.50178-1-oupton@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/include/x86_64/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index eba8bd08293e..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -315,7 +315,7 @@ static inline void set_xmm(int n, unsigned long val) #define GET_XMM(__xmm) \ ({ \ unsigned long __val; \ - asm volatile("movq %%"#__xmm", %0" : "=r"(__val) : : #__xmm); \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ __val; \ }) From df38d852c6814cbbd010d81e84efb9dc057d5ba6 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 28 Sep 2021 22:07:50 +0800 Subject: [PATCH 791/866] kernfs: also call kernfs_set_rev() for positive dentry A KMSAN warning is reported by Alexander Potapenko: BUG: KMSAN: uninit-value in kernfs_dop_revalidate+0x61f/0x840 fs/kernfs/dir.c:1053 kernfs_dop_revalidate+0x61f/0x840 fs/kernfs/dir.c:1053 d_revalidate fs/namei.c:854 lookup_dcache fs/namei.c:1522 __lookup_hash+0x3a6/0x590 fs/namei.c:1543 filename_create+0x312/0x7c0 fs/namei.c:3657 do_mkdirat+0x103/0x930 fs/namei.c:3900 __do_sys_mkdir fs/namei.c:3931 __se_sys_mkdir fs/namei.c:3929 __x64_sys_mkdir+0xda/0x120 fs/namei.c:3929 do_syscall_x64 arch/x86/entry/common.c:51 It seems a positive dentry in kernfs becomes a negative dentry directly through d_delete() in vfs_rmdir(). dentry->d_time is uninitialized when accessing it in kernfs_dop_revalidate(), because it is only initialized when created as negative dentry in kernfs_iop_lookup(). The problem can be reproduced by the following command: cd /sys/fs/cgroup/pids && mkdir hi && stat hi && rmdir hi && stat hi A simple fixes seems to be initializing d->d_time for positive dentry in kernfs_iop_lookup() as well. The downside is the negative dentry will be revalidated again after it becomes negative in d_delete(), because the revison of its parent must have been increased due to its removal. Alternative solution is implement .d_iput for kernfs, and assign d_time for the newly-generated negative dentry in it. But we may need to take kernfs_rwsem to protect again the concurrent kernfs_link_sibling() on the parent directory, it is a little over-killing. Now the simple fix is chosen. Link: https://marc.info/?l=linux-fsdevel&m=163249838610499 Fixes: c7e7c04274b1 ("kernfs: use VFS negative dentry caching") Reported-by: Alexander Potapenko Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20210928140750.1274441-1-houtao1@huawei.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ba581429bf7b..cfc3ce8b815a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1116,8 +1116,13 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, if (!inode) inode = ERR_PTR(-ENOMEM); } - /* Needed only for negative dentry validation */ - if (!inode) + /* + * Needed for negative dentry validation. + * The negative dentry can be created in kernfs_iop_lookup() + * or transforms from positive dentry in dentry_unlink_inode() + * called from vfs_rmdir(). + */ + if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&kernfs_rwsem); From 66805763a97f8f7bdf742fc0851d85c02ed9411f Mon Sep 17 00:00:00 2001 From: Leslie Shi Date: Thu, 23 Sep 2021 16:05:31 +0800 Subject: [PATCH 792/866] drm/amdgpu: fix gart.bo pin_count leak MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gmc_v{9,10}_0_gart_disable() isn't called matched with correspoding gart_enbale function in SRIOV case. This will lead to gart.bo pin_count leak on driver unload. Cc: Hawking Zhang Signed-off-by: Leslie Shi Signed-off-by: Guchun Chen Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 ++- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 41c3a0d70b7c..e47104a1f559 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v10_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v10_0_gart_disable(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index d90c16a6b2b8..5551359d5dfd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v9_0_gart_disable(adev); return 0; } From 083fa05bbaf65a01866b5440031c822e32ad7510 Mon Sep 17 00:00:00 2001 From: Praful Swarnakar Date: Wed, 22 Sep 2021 23:01:29 +0530 Subject: [PATCH 793/866] drm/amd/display: Fix Display Flicker on embedded panels [Why] ASSR is dependent on Signed PSP Verstage to enable Content Protection for eDP panels. Unsigned PSP verstage is used during development phase causing ASSR to FAIL. As a result, link training is performed with DP_PANEL_MODE_DEFAULT instead of DP_PANEL_MODE_EDP for eDP panels that causes display flicker on some panels. [How] - Do not change panel mode, if ASSR is disabled - Just report and continue to perform eDP link training with right settings further. Signed-off-by: Praful Swarnakar Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index f6dbc5a74757..05eaec03d9f7 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1826,14 +1826,13 @@ bool perform_link_training_with_retries( if (panel_mode == DP_PANEL_MODE_EDP) { struct cp_psp *cp_psp = &stream->ctx->cp_psp; - if (cp_psp && cp_psp->funcs.enable_assr) { - if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { - /* since eDP implies ASSR on, change panel - * mode to disable ASSR - */ - panel_mode = DP_PANEL_MODE_DEFAULT; - } - } + if (cp_psp && cp_psp->funcs.enable_assr) + /* ASSR is bound to fail with unsigned PSP + * verstage used during devlopment phase. + * Report and continue with eDP panel mode to + * perform eDP link training with right settings + */ + cp_psp->funcs.enable_assr(cp_psp->handle, link); } #endif From 9f52c25f59b504a29dda42d83ac1e24d2af535d4 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Sun, 26 Sep 2021 22:19:35 +0800 Subject: [PATCH 794/866] drm/amdgpu: correct initial cp_hqd_quantum for gfx9 didn't read the value of mmCP_HQD_QUANTUM from correct register offset Signed-off-by: Hawking Zhang Reviewed-by: Le Ma Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 603c259b073b..025184a556ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring) /* set static priority for a queue/ring */ gfx_v9_0_mqd_set_priority(ring, mqd); - mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM); + mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM); /* map_queues packet doesn't need activate the queue, * so only kiq need set this field. From 467a51b69d0828887fb1b6719159a6b16da688f8 Mon Sep 17 00:00:00 2001 From: Josip Pavic Date: Fri, 17 Sep 2021 11:01:47 -0400 Subject: [PATCH 795/866] drm/amd/display: initialize backlight_ramping_override to false [Why] Stack variable params.backlight_ramping_override is uninitialized, so it contains junk data [How] Initialize the variable to false Reviewed-by: Roman Li Acked-by: Anson Jacob Signed-off-by: Josip Pavic Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 66c799f5c7cf..e6a68337d42f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1719,6 +1719,7 @@ static int dm_late_init(void *handle) linear_lut[i] = 0xFFFF * i / 15; params.set = 0; + params.backlight_ramping_override = false; params.backlight_ramping_start = 0xCCCC; params.backlight_ramping_reduction = 0xCCCCCCCC; params.backlight_lut_array_size = 16; From d942856865c733ff60450de9691af796ad71d7bc Mon Sep 17 00:00:00 2001 From: Charlene Liu Date: Mon, 20 Sep 2021 14:30:02 -0400 Subject: [PATCH 796/866] drm/amd/display: Pass PCI deviceid into DC [why] pci deviceid not passed to dal dc, without proper break, dcn2.x falls into dcn3.x code path [how] pass in pci deviceid, and break once dal_version initialized. Reviewed-by: Zhan Liu Acked-by: Anson Jacob Signed-off-by: Charlene Liu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e6a68337d42f..1ea31dcc7a8b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1115,6 +1115,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.asic_id.pci_revision_id = adev->pdev->revision; init_data.asic_id.hw_internal_rev = adev->external_rev_id; + init_data.asic_id.chip_id = adev->pdev->device; init_data.asic_id.vram_width = adev->gmc.vram_width; /* TODO: initialize init_data.asic_id.vram_type here!!!! */ From 98122e63a7ecc08c4172a17d97a06ef5536eb268 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Mon, 27 Sep 2021 15:08:44 +0000 Subject: [PATCH 797/866] drm/amdgpu: check tiling flags when creating FB on GFX8- MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On GFX9+, format modifiers are always enabled and ensure the frame-buffers can be scanned out at ADDFB2 time. On GFX8-, format modifiers are not supported and no other check is performed. This means ADDFB2 IOCTLs will succeed even if the tiling isn't supported for scan-out, and will result in garbage displayed on screen [1]. Fix this by adding a check for tiling flags for GFX8 and older. The check is taken from radeonsi in Mesa (see how is_displayable is populated in gfx6_compute_surface). Changes in v2: use drm_WARN_ONCE instead of drm_WARN (Michel) [1]: https://github.com/swaywm/wlroots/issues/3185 Signed-off-by: Simon Ser Acked-by: Michel Dänzer Cc: Alex Deucher Cc: Harry Wentland Cc: Nicholas Kazlauskas Cc: Bas Nieuwenhuizen Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 31 +++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 7a7316731911..dc50c05f23fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb) return 0; } +/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */ +static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb) +{ + u64 micro_tile_mode; + + /* Zero swizzle mode means linear */ + if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0) + return 0; + + micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE); + switch (micro_tile_mode) { + case 0: /* DISPLAY */ + case 3: /* RENDER */ + return 0; + default: + drm_dbg_kms(afb->base.dev, + "Micro tile mode %llu not supported for scanout\n", + micro_tile_mode); + return -EINVAL; + } +} + static void get_block_dimensions(unsigned int block_log2, unsigned int cpp, unsigned int *width, unsigned int *height) { @@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj) { + struct amdgpu_device *adev = drm_to_adev(dev); int ret, i; /* @@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, if (ret) return ret; + if (!dev->mode_config.allow_fb_modifiers) { + drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI, + "GFX9+ requires FB check based on format modifier\n"); + ret = check_tiling_flags_gfx6(rfb); + if (ret) + return ret; + } + if (dev->mode_config.allow_fb_modifiers && !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) { ret = convert_tiling_flags_to_modifier(rfb); From 26db706a6d77b9e184feb11725e97e53b7a89519 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Wed, 25 Aug 2021 13:36:38 +0800 Subject: [PATCH 798/866] drm/amdgpu: force exit gfxoff on sdma resume for rmb s0ix In the s2idle stress test sdma resume fail occasionally,in the failed case GPU is in the gfxoff state.This issue may introduce by firmware miss handle doorbell S/R and now temporary fix the issue by forcing exit gfxoff for sdma resume. Signed-off-by: Prike Liang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 779f5c911e11..e32efcfb0c8b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) msleep(1000); } + /* TODO: check whether can submit a doorbell request to raise + * a doorbell fence to exit gfxoff. + */ + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, false); + sdma_v5_2_soft_reset(adev); /* unhalt the MEs */ sdma_v5_2_enable(adev, true); @@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) /* start the gfx rings and rlc compute queues */ r = sdma_v5_2_gfx_resume(adev); + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, true); if (r) return r; r = sdma_v5_2_rlc_resume(adev); From 9e28cfead2f8f5aba7df03c74c9ec645b5ffc5fd Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Tue, 28 Sep 2021 21:48:49 +0800 Subject: [PATCH 799/866] net: mdio-ipq4019: Fix the error for an optional regs resource The second resource is optional which is only provided on the chipset IPQ5018. But the blamed commit ignores that and if the resource is not there it just fails. the resource is used like this, if (priv->eth_ldo_rdy) { val = readl(priv->eth_ldo_rdy); val |= BIT(0); writel(val, priv->eth_ldo_rdy); fsleep(IPQ_PHY_SET_DELAY_US); } This patch reverts that to still allow the second resource to be optional because other SoC have the some MDIO controller and doesn't need to second resource. Fixes: fa14d03e014a ("net: mdio-ipq4019: Make use of devm_platform_ioremap_resource()") Signed-off-by: Cai Huoqing Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210928134849.2092-1-caihuoqing@baidu.com Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-ipq4019.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 0d7d3e15d2f0..5f4cd24a0241 100644 --- a/drivers/net/mdio/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c @@ -207,6 +207,7 @@ static int ipq4019_mdio_probe(struct platform_device *pdev) { struct ipq4019_mdio_data *priv; struct mii_bus *bus; + struct resource *res; int ret; bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*priv)); @@ -224,7 +225,10 @@ static int ipq4019_mdio_probe(struct platform_device *pdev) return PTR_ERR(priv->mdio_clk); /* The platform resource is provided on the chipset IPQ5018 */ - priv->eth_ldo_rdy = devm_platform_ioremap_resource(pdev, 1); + /* This resource is optional */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (res) + priv->eth_ldo_rdy = devm_ioremap_resource(&pdev->dev, res); bus->name = "ipq4019_mdio"; bus->read = ipq4019_mdio_read; From f936bb42aeb94a069bec7c9e04100d199c372956 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 28 Sep 2021 16:10:49 +0200 Subject: [PATCH 800/866] net: bridge: mcast: Associate the seqcount with its protecting lock. The sequence count bridge_mcast_querier::seq is protected by net_bridge::multicast_lock but seqcount_init() does not associate the seqcount with the lock. This leads to a warning on PREEMPT_RT because preemption is still enabled. Let seqcount_init() associate the seqcount with lock that protects the write section. Remove lockdep_assert_held_once() because lockdep already checks whether the associated lock is held. Fixes: 67b746f94ff39 ("net: bridge: mcast: make sure querier port/address updates are consistent") Reported-by: Mike Galbraith Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Tested-by: Mike Galbraith Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20210928141049.593833-1-bigeasy@linutronix.de Signed-off-by: Jakub Kicinski --- net/bridge/br_multicast.c | 6 ++---- net/bridge/br_private.h | 2 +- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3523c8c7068f..f3d751105343 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1677,8 +1677,6 @@ static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, int ifindex, struct br_ip *saddr) { - lockdep_assert_held_once(&brmctx->br->multicast_lock); - write_seqcount_begin(&querier->seq); querier->port_ifidx = ifindex; memcpy(&querier->addr, saddr, sizeof(*saddr)); @@ -3867,13 +3865,13 @@ void br_multicast_ctx_init(struct net_bridge *br, brmctx->ip4_other_query.delay_time = 0; brmctx->ip4_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip4_querier.seq); + seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; brmctx->ip6_other_query.delay_time = 0; brmctx->ip6_querier.port_ifidx = 0; - seqcount_init(&brmctx->ip6_querier.seq); + seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif timer_setup(&brmctx->ip4_mc_router_timer, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b4cef3a97f12..e8136db44462 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -82,7 +82,7 @@ struct bridge_mcast_other_query { struct bridge_mcast_querier { struct br_ip addr; int port_ifidx; - seqcount_t seq; + seqcount_spinlock_t seq; }; /* IGMP/MLD statistics */ From 1018bf24550fd0feec14648309a0aeb62401f4dc Mon Sep 17 00:00:00 2001 From: Enzo Matsumiya Date: Tue, 28 Sep 2021 19:56:34 -0300 Subject: [PATCH 801/866] ksmbd: fix documentation for 2 functions ksmbd_kthread_fn() and create_socket() returns 0 or error code, and not task_struct/ERR_PTR. Signed-off-by: Enzo Matsumiya Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/transport_tcp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index dc15a5ecd2e0..c14320e03b69 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -215,7 +215,7 @@ out_error: * ksmbd_kthread_fn() - listen to new SMB connections and callback server * @p: arguments to forker thread * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int ksmbd_kthread_fn(void *p) { @@ -387,7 +387,7 @@ static void tcp_destroy_socket(struct socket *ksmbd_socket) /** * create_socket - create socket for ksmbd/0 * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int create_socket(struct interface *iface) { From e8c2da7e329ce004fee748b921e4c765dc2fa338 Mon Sep 17 00:00:00 2001 From: Jonathan Hsu Date: Fri, 24 Sep 2021 16:58:48 +0800 Subject: [PATCH 802/866] scsi: ufs: Fix illegal offset in UPIU event trace Fix incorrect index for UTMRD reference in ufshcd_add_tm_upiu_trace(). Link: https://lore.kernel.org/r/20210924085848.25500-1-jonathan.hsu@mediatek.com Fixes: 4b42d557a8ad ("scsi: ufs: core: Fix wrong Task Tag used in task management request UPIUs") Cc: stable@vger.kernel.org Reviewed-by: Stanley Chu Reviewed-by: Bart Van Assche Signed-off-by: Jonathan Hsu Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 029c9631ec2b..188de6f91050 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -318,8 +318,7 @@ static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, enum ufs_trace_str_t str_t) { - int off = (int)tag - hba->nutrs; - struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[off]; + struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[tag]; if (!trace_ufshcd_upiu_enabled()) return; From dd689ed5aa905daf4ba4c99319a52aad6ea0a796 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 24 Sep 2021 17:51:53 +0800 Subject: [PATCH 803/866] scsi: ses: Fix unsigned comparison with less than zero Fix the following coccicheck warning: ./drivers/scsi/ses.c:137:10-16: WARNING: Unsigned expression compared with zero: result > 0. Link: https://lore.kernel.org/r/1632477113-90378-1-git-send-email-jiapeng.chong@linux.alibaba.com Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: Martin K. Petersen --- drivers/scsi/ses.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 43e682297fd5..0a1734f34587 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -118,7 +118,7 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, static int ses_send_diag(struct scsi_device *sdev, int page_code, void *buf, int bufflen) { - u32 result; + int result; unsigned char cmd[] = { SEND_DIAGNOSTIC, From cced4c0ec7c06f5230a2958907a409c849762293 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 25 Sep 2021 00:03:30 +0100 Subject: [PATCH 804/866] scsi: virtio_scsi: Fix spelling mistake "Unsupport" -> "Unsupported" There are a couple of spelling mistakes in pr_info and pr_err messages. Fix them. Link: https://lore.kernel.org/r/20210924230330.143785-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Martin K. Petersen --- drivers/scsi/virtio_scsi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index c25ce8f0e0af..07d0250f17c3 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -300,7 +300,7 @@ static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi, } break; default: - pr_info("Unsupport virtio scsi event reason %x\n", event->reason); + pr_info("Unsupported virtio scsi event reason %x\n", event->reason); } } @@ -392,7 +392,7 @@ static void virtscsi_handle_event(struct work_struct *work) virtscsi_handle_param_change(vscsi, event); break; default: - pr_err("Unsupport virtio scsi event %x\n", event->event); + pr_err("Unsupported virtio scsi event %x\n", event->event); } virtscsi_kick_event(vscsi, event_node); } From 8e2d81c6b5be0d7629fb50b6f678fc07a4c58fae Mon Sep 17 00:00:00 2001 From: Arun Easi Date: Fri, 24 Sep 2021 20:51:54 -0700 Subject: [PATCH 805/866] scsi: qla2xxx: Fix excessive messages during device logout Disable default logging of some I/O path messages. If desired, the messages can be turned back on by setting ql2xextended_error_logging. Link: https://lore.kernel.org/r/20210925035154.29815-1-njavali@marvell.com Reviewed-by: Ewan D. Milne Reviewed-by: Himanshu Madhani Signed-off-by: Arun Easi Signed-off-by: Nilesh Javali Signed-off-by: Martin K. Petersen --- drivers/scsi/qla2xxx/qla_isr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index ece60267b971..b26f2699adb2 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2634,7 +2634,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, } if (unlikely(logit)) - ql_log(ql_log_warn, fcport->vha, 0x5060, + ql_log(ql_dbg_io, fcport->vha, 0x5060, "NVME-%s ERR Handling - hdl=%x status(%x) tr_len:%x resid=%x ox_id=%x\n", sp->name, sp->handle, comp_status, fd->transferred_length, le32_to_cpu(sts->residual_len), @@ -3491,7 +3491,7 @@ check_scsi_status: out: if (logit) - ql_log(ql_log_warn, fcport->vha, 0x3022, + ql_log(ql_dbg_io, fcport->vha, 0x3022, "FCP command status: 0x%x-0x%x (0x%x) nexus=%ld:%d:%llu portid=%02x%02x%02x oxid=0x%x cdb=%10phN len=0x%x rsp_info=0x%x resid=0x%x fw_resid=0x%x sp=%p cp=%p.\n", comp_status, scsi_status, res, vha->host_no, cp->device->id, cp->device->lun, fcport->d_id.b.domain, From 79a7482249a7353bc86aff8127954d5febf02472 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Mon, 27 Sep 2021 21:44:08 +0530 Subject: [PATCH 806/866] scsi: csiostor: Add module softdep on cxgb4 Both cxgb4 and csiostor drivers run on their own independent Physical Function. But when cxgb4 and csiostor are both being loaded in parallel via modprobe, there is a race when firmware upgrade is attempted by both the drivers. When the cxgb4 driver initiates the firmware upgrade, it halts the firmware and the chip until upgrade is complete. When the csiostor driver is coming up in parallel, the firmware mailbox communication fails with timeouts and the csiostor driver probe fails. Add a module soft dependency on cxgb4 driver to ensure loading csiostor triggers cxgb4 to load first when available to avoid the firmware upgrade race. Link: https://lore.kernel.org/r/1632759248-15382-1-git-send-email-rahul.lakkireddy@chelsio.com Fixes: a3667aaed569 ("[SCSI] csiostor: Chelsio FCoE offload driver") Signed-off-by: Rahul Lakkireddy Signed-off-by: Martin K. Petersen --- drivers/scsi/csiostor/csio_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index 390b07bf92b9..ccbded3353bd 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -1254,3 +1254,4 @@ MODULE_DEVICE_TABLE(pci, csio_pci_tbl); MODULE_VERSION(CSIO_DRV_VERSION); MODULE_FIRMWARE(FW_FNAME_T5); MODULE_FIRMWARE(FW_FNAME_T6); +MODULE_SOFTDEP("pre: cxgb4"); From 513e605d7a9ce136886cb42ebb2c40e9a6eb6333 Mon Sep 17 00:00:00 2001 From: Feng Zhou Date: Tue, 28 Sep 2021 15:23:59 -0700 Subject: [PATCH 807/866] ixgbe: Fix NULL pointer dereference in ixgbe_xdp_setup The ixgbe driver currently generates a NULL pointer dereference with some machine (online cpus < 63). This is due to the fact that the maximum value of num_xdp_queues is nr_cpu_ids. Code is in "ixgbe_set_rss_queues"". Here's how the problem repeats itself: Some machine (online cpus < 63), And user set num_queues to 63 through ethtool. Code is in the "ixgbe_set_channels", adapter->ring_feature[RING_F_FDIR].limit = count; It becomes 63. When user use xdp, "ixgbe_set_rss_queues" will set queues num. adapter->num_rx_queues = rss_i; adapter->num_tx_queues = rss_i; adapter->num_xdp_queues = ixgbe_xdp_queues(adapter); And rss_i's value is from f = &adapter->ring_feature[RING_F_FDIR]; rss_i = f->indices = f->limit; So "num_rx_queues" > "num_xdp_queues", when run to "ixgbe_xdp_setup", for (i = 0; i < adapter->num_rx_queues; i++) if (adapter->xdp_ring[i]->xsk_umem) It leads to panic. Call trace: [exception RIP: ixgbe_xdp+368] RIP: ffffffffc02a76a0 RSP: ffff9fe16202f8d0 RFLAGS: 00010297 RAX: 0000000000000000 RBX: 0000000000000020 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 000000000000001c RDI: ffffffffa94ead90 RBP: ffff92f8f24c0c18 R8: 0000000000000000 R9: 0000000000000000 R10: ffff9fe16202f830 R11: 0000000000000000 R12: ffff92f8f24c0000 R13: ffff9fe16202fc01 R14: 000000000000000a R15: ffffffffc02a7530 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 7 [ffff9fe16202f8f0] dev_xdp_install at ffffffffa89fbbcc 8 [ffff9fe16202f920] dev_change_xdp_fd at ffffffffa8a08808 9 [ffff9fe16202f960] do_setlink at ffffffffa8a20235 10 [ffff9fe16202fa88] rtnl_setlink at ffffffffa8a20384 11 [ffff9fe16202fc78] rtnetlink_rcv_msg at ffffffffa8a1a8dd 12 [ffff9fe16202fcf0] netlink_rcv_skb at ffffffffa8a717eb 13 [ffff9fe16202fd40] netlink_unicast at ffffffffa8a70f88 14 [ffff9fe16202fd80] netlink_sendmsg at ffffffffa8a71319 15 [ffff9fe16202fdf0] sock_sendmsg at ffffffffa89df290 16 [ffff9fe16202fe08] __sys_sendto at ffffffffa89e19c8 17 [ffff9fe16202ff30] __x64_sys_sendto at ffffffffa89e1a64 18 [ffff9fe16202ff38] do_syscall_64 at ffffffffa84042b9 19 [ffff9fe16202ff50] entry_SYSCALL_64_after_hwframe at ffffffffa8c0008c So I fix ixgbe_max_channels so that it will not allow a setting of queues to be higher than the num_online_cpus(). And when run to ixgbe_xdp_setup, take the smaller value of num_rx_queues and num_xdp_queues. Fixes: 4a9b32f30f80 ("ixgbe: fix potential RX buffer starvation for AF_XDP") Signed-off-by: Feng Zhou Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index fc26e4ddeb0d..beda8e0ef7d4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3208,7 +3208,7 @@ static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter) max_combined = ixgbe_max_rss_indices(adapter); } - return max_combined; + return min_t(int, max_combined, num_online_cpus()); } static void ixgbe_get_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 24e06ba6f5e9..13c4782b920a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10112,6 +10112,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) struct ixgbe_adapter *adapter = netdev_priv(dev); struct bpf_prog *old_prog; bool need_reset; + int num_queues; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10161,11 +10162,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) /* Kick start the NAPI context if there is an AF_XDP socket open * on that queue id. This so that receiving will start. */ - if (need_reset && prog) - for (i = 0; i < adapter->num_rx_queues; i++) + if (need_reset && prog) { + num_queues = min_t(int, adapter->num_rx_queues, + adapter->num_xdp_queues); + for (i = 0; i < num_queues; i++) if (adapter->xdp_ring[i]->xsk_pool) (void)ixgbe_xsk_wakeup(adapter->netdev, i, XDP_WAKEUP_RX); + } return 0; } From 5b09e88e1bf7fe86540fab4b5f3eece8abead39e Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 29 Sep 2021 17:35:49 +0800 Subject: [PATCH 808/866] net: hns3: do not allow call hns3_nic_net_open repeatedly hns3_nic_net_open() is not allowed to called repeatly, but there is no checking for this. When doing device reset and setup tc concurrently, there is a small oppotunity to call hns3_nic_net_open repeatedly, and cause kernel bug by calling napi_enable twice. The calltrace information is like below: [ 3078.222780] ------------[ cut here ]------------ [ 3078.230255] kernel BUG at net/core/dev.c:6991! [ 3078.236224] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [ 3078.243431] Modules linked in: hns3 hclgevf hclge hnae3 vfio_iommu_type1 vfio_pci vfio_virqfd vfio pv680_mii(O) [ 3078.258880] CPU: 0 PID: 295 Comm: kworker/u8:5 Tainted: G O 5.14.0-rc4+ #1 [ 3078.269102] Hardware name: , BIOS KpxxxFPGA 1P B600 V181 08/12/2021 [ 3078.276801] Workqueue: hclge hclge_service_task [hclge] [ 3078.288774] pstate: 60400009 (nZCv daif +PAN -UAO -TCO BTYPE=--) [ 3078.296168] pc : napi_enable+0x80/0x84 tc qdisc sho[w 3d0e7v8 .e3t0h218 79] lr : hns3_nic_net_open+0x138/0x510 [hns3] [ 3078.314771] sp : ffff8000108abb20 [ 3078.319099] x29: ffff8000108abb20 x28: 0000000000000000 x27: ffff0820a8490300 [ 3078.329121] x26: 0000000000000001 x25: ffff08209cfc6200 x24: 0000000000000000 [ 3078.339044] x23: ffff0820a8490300 x22: ffff08209cd76000 x21: ffff0820abfe3880 [ 3078.349018] x20: 0000000000000000 x19: ffff08209cd76900 x18: 0000000000000000 [ 3078.358620] x17: 0000000000000000 x16: ffffc816e1727a50 x15: 0000ffff8f4ff930 [ 3078.368895] x14: 0000000000000000 x13: 0000000000000000 x12: 0000259e9dbeb6b4 [ 3078.377987] x11: 0096a8f7e764eb40 x10: 634615ad28d3eab5 x9 : ffffc816ad8885b8 [ 3078.387091] x8 : ffff08209cfc6fb8 x7 : ffff0820ac0da058 x6 : ffff0820a8490344 [ 3078.396356] x5 : 0000000000000140 x4 : 0000000000000003 x3 : ffff08209cd76938 [ 3078.405365] x2 : 0000000000000000 x1 : 0000000000000010 x0 : ffff0820abfe38a0 [ 3078.414657] Call trace: [ 3078.418517] napi_enable+0x80/0x84 [ 3078.424626] hns3_reset_notify_up_enet+0x78/0xd0 [hns3] [ 3078.433469] hns3_reset_notify+0x64/0x80 [hns3] [ 3078.441430] hclge_notify_client+0x68/0xb0 [hclge] [ 3078.450511] hclge_reset_rebuild+0x524/0x884 [hclge] [ 3078.458879] hclge_reset_service_task+0x3c4/0x680 [hclge] [ 3078.467470] hclge_service_task+0xb0/0xb54 [hclge] [ 3078.475675] process_one_work+0x1dc/0x48c [ 3078.481888] worker_thread+0x15c/0x464 [ 3078.487104] kthread+0x160/0x170 [ 3078.492479] ret_from_fork+0x10/0x18 [ 3078.498785] Code: c8027c81 35ffffa2 d50323bf d65f03c0 (d4210000) [ 3078.506889] ---[ end trace 8ebe0340a1b0fb44 ]--- Once hns3_nic_net_open() is excute success, the flag HNS3_NIC_STATE_DOWN will be cleared. So add checking for this flag, directly return when HNS3_NIC_STATE_DOWN is no set. Fixes: e888402789b9 ("net: hns3: call hns3_nic_net_open() while doing HNAE3_UP_CLIENT") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index adc54a726661..5637c075a894 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -779,6 +779,11 @@ static int hns3_nic_net_open(struct net_device *netdev) if (hns3_nic_resetting(netdev)) return -EBUSY; + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) { + netdev_warn(netdev, "net open repeatedly!\n"); + return 0; + } + netif_carrier_off(netdev); ret = hns3_nic_set_real_num_queue(netdev); From a8e76fefe3de9b8e609cf192af75e7878d21fa3a Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 29 Sep 2021 17:35:50 +0800 Subject: [PATCH 809/866] net: hns3: remove tc enable checking Currently, in function hns3_nic_set_real_num_queue(), the driver doesn't report the queue count and offset for disabled tc. If user enables multiple TCs, but only maps user priorities to partial of them, it may cause the queue range of the unmapped TC being displayed abnormally. Fix it by removing the tc enable checking, ensure the queue count is not zero. With this change, the tc_en is useless now, so remove it. Fixes: a75a8efa00c5 ("net: hns3: Fix tc setup when netdev is first up") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 - drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 11 ++--------- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 5 ----- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 -- 4 files changed, 2 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 546a60530384..8ba21d6dc220 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -752,7 +752,6 @@ struct hnae3_tc_info { u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */ u16 tqp_count[HNAE3_MAX_TC]; u16 tqp_offset[HNAE3_MAX_TC]; - unsigned long tc_en; /* bitmap of TC enabled */ u8 num_tc; /* Total number of enabled TCs */ bool mqprio_active; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 5637c075a894..468b8f07bf47 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -623,13 +623,9 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev) return ret; } - for (i = 0; i < HNAE3_MAX_TC; i++) { - if (!test_bit(i, &tc_info->tc_en)) - continue; - + for (i = 0; i < tc_info->num_tc; i++) netdev_set_tc_queue(netdev, i, tc_info->tqp_count[i], tc_info->tqp_offset[i]); - } } ret = netif_set_real_num_tx_queues(netdev, queue_size); @@ -4870,12 +4866,9 @@ static void hns3_init_tx_ring_tc(struct hns3_nic_priv *priv) struct hnae3_tc_info *tc_info = &kinfo->tc_info; int i; - for (i = 0; i < HNAE3_MAX_TC; i++) { + for (i = 0; i < tc_info->num_tc; i++) { int j; - if (!test_bit(i, &tc_info->tc_en)) - continue; - for (j = 0; j < tc_info->tqp_count[i]; j++) { struct hnae3_queue *q; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 4a619e5d3f35..96f96644abab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -441,8 +441,6 @@ static int hclge_mqprio_qopt_check(struct hclge_dev *hdev, static void hclge_sync_mqprio_qopt(struct hnae3_tc_info *tc_info, struct tc_mqprio_qopt_offload *mqprio_qopt) { - int i; - memset(tc_info, 0, sizeof(*tc_info)); tc_info->num_tc = mqprio_qopt->qopt.num_tc; memcpy(tc_info->prio_tc, mqprio_qopt->qopt.prio_tc_map, @@ -451,9 +449,6 @@ static void hclge_sync_mqprio_qopt(struct hnae3_tc_info *tc_info, sizeof_field(struct hnae3_tc_info, tqp_count)); memcpy(tc_info->tqp_offset, mqprio_qopt->qopt.offset, sizeof_field(struct hnae3_tc_info, tqp_offset)); - - for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) - set_bit(tc_info->prio_tc[i], &tc_info->tc_en); } static int hclge_config_tc(struct hclge_dev *hdev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 44618cc4cca1..6f5035a788c0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -687,12 +687,10 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) for (i = 0; i < HNAE3_MAX_TC; i++) { if (hdev->hw_tc_map & BIT(i) && i < kinfo->tc_info.num_tc) { - set_bit(i, &kinfo->tc_info.tc_en); kinfo->tc_info.tqp_offset[i] = i * kinfo->rss_size; kinfo->tc_info.tqp_count[i] = kinfo->rss_size; } else { /* Set to default queue if TC is disable */ - clear_bit(i, &kinfo->tc_info.tc_en); kinfo->tc_info.tqp_offset[i] = 0; kinfo->tc_info.tqp_count[i] = 1; } From d82650be60ee92e7486f755f5387023278aa933f Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 29 Sep 2021 17:35:51 +0800 Subject: [PATCH 810/866] net: hns3: don't rollback when destroy mqprio fail For destroy mqprio is irreversible in stack, so it's unnecessary to rollback the tc configuration when destroy mqprio failed. Otherwise, it may cause the configuration being inconsistent between driver and netstack. As the failure is usually caused by reset, and the driver will restore the configuration after reset, so it can keep the configuration being consistent between driver and hardware. Fixes: 5a5c90917467 ("net: hns3: add support for tc mqprio offload") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 96f96644abab..351b8f179a29 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -514,12 +514,17 @@ static int hclge_setup_tc(struct hnae3_handle *h, return hclge_notify_init_up(hdev); err_out: - /* roll-back */ - memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info)); - if (hclge_config_tc(hdev, &kinfo->tc_info)) - dev_err(&hdev->pdev->dev, - "failed to roll back tc configuration\n"); - + if (!tc) { + dev_warn(&hdev->pdev->dev, + "failed to destroy mqprio, will active after reset, ret = %d\n", + ret); + } else { + /* roll-back */ + memcpy(&kinfo->tc_info, &old_tc_info, sizeof(old_tc_info)); + if (hclge_config_tc(hdev, &kinfo->tc_info)) + dev_err(&hdev->pdev->dev, + "failed to roll back tc configuration\n"); + } hclge_notify_init_up(hdev); return ret; From 0472e95ffeac8e61259eec17ab61608c6b35599d Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 29 Sep 2021 17:35:52 +0800 Subject: [PATCH 811/866] net: hns3: fix mixed flag HCLGE_FLAG_MQPRIO_ENABLE and HCLGE_FLAG_DCB_ENABLE HCLGE_FLAG_MQPRIO_ENABLE is supposed to set when enable multiple TCs with tc mqprio, and HCLGE_FLAG_DCB_ENABLE is supposed to set when enable multiple TCs with ets. But the driver mixed the flags when updating the tm configuration. Furtherly, PFC should be available when HCLGE_FLAG_MQPRIO_ENABLE too, so remove the unnecessary limitation. Fixes: 5a5c90917467 ("net: hns3: add support for tc mqprio offload") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_dcb.c | 7 +++-- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 31 +++---------------- 2 files changed, 10 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 351b8f179a29..307c9e830510 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -247,6 +247,10 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) } hclge_tm_schd_info_update(hdev, num_tc); + if (num_tc > 1) + hdev->flag |= HCLGE_FLAG_DCB_ENABLE; + else + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; ret = hclge_ieee_ets_to_tm_info(hdev, ets); if (ret) @@ -306,8 +310,7 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) u8 i, j, pfc_map, *prio_tc; int ret; - if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) || - hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE) + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; if (pfc->pfc_en == hdev->tm_info.pfc_en) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 6f5035a788c0..f314dbd3ce11 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -727,14 +727,6 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev) for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) hdev->tm_info.prio_tc[i] = (i >= hdev->tm_info.num_tc) ? 0 : i; - - /* DCB is enabled if we have more than 1 TC or pfc_en is - * non-zero. - */ - if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en) - hdev->flag |= HCLGE_FLAG_DCB_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; } static void hclge_tm_pg_info_init(struct hclge_dev *hdev) @@ -765,10 +757,10 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev) static void hclge_update_fc_mode_by_dcb_flag(struct hclge_dev *hdev) { - if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) { + if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en) { if (hdev->fc_mode_last_time == HCLGE_FC_PFC) dev_warn(&hdev->pdev->dev, - "DCB is disable, but last mode is FC_PFC\n"); + "Only 1 tc used, but last mode is FC_PFC\n"); hdev->tm_info.fc_mode = hdev->fc_mode_last_time; } else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) { @@ -794,7 +786,7 @@ static void hclge_update_fc_mode(struct hclge_dev *hdev) } } -static void hclge_pfc_info_init(struct hclge_dev *hdev) +void hclge_tm_pfc_info_update(struct hclge_dev *hdev) { if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) hclge_update_fc_mode(hdev); @@ -810,7 +802,7 @@ static void hclge_tm_schd_info_init(struct hclge_dev *hdev) hclge_tm_vport_info_update(hdev); - hclge_pfc_info_init(hdev); + hclge_tm_pfc_info_update(hdev); } static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev) @@ -1556,19 +1548,6 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) hclge_tm_schd_info_init(hdev); } -void hclge_tm_pfc_info_update(struct hclge_dev *hdev) -{ - /* DCB is enabled if we have more than 1 TC or pfc_en is - * non-zero. - */ - if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en) - hdev->flag |= HCLGE_FLAG_DCB_ENABLE; - else - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; - - hclge_pfc_info_init(hdev); -} - int hclge_tm_init_hw(struct hclge_dev *hdev, bool init) { int ret; @@ -1614,7 +1593,7 @@ int hclge_tm_vport_map_update(struct hclge_dev *hdev) if (ret) return ret; - if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) + if (hdev->tm_info.num_tc == 1 && !hdev->tm_info.pfc_en) return 0; return hclge_tm_bp_setup(hdev); From 108b3c7810e14892c4a1819b1d268a2c785c087c Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Wed, 29 Sep 2021 17:35:53 +0800 Subject: [PATCH 812/866] net: hns3: fix show wrong state when add existing uc mac address Currently, if function adds an existing unicast mac address, eventhough driver will not add this address into hardware, but it will return 0 in function hclge_add_uc_addr_common(). It will cause the state of this unicast mac address is ACTIVE in driver, but it should be in TO-ADD state. To fix this problem, function hclge_add_uc_addr_common() returns -EEXIST if mac address is existing, and delete two error log to avoid printing them all the time after this modification. Fixes: 72110b567479 ("net: hns3: return 0 and print warning when hit duplicate MAC") Signed-off-by: Jian Shen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_main.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 47fea8985861..3391244d9d3d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8708,15 +8708,8 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, } /* check if we just hit the duplicate */ - if (!ret) { - dev_warn(&hdev->pdev->dev, "VF %u mac(%pM) exists\n", - vport->vport_id, addr); - return 0; - } - - dev_err(&hdev->pdev->dev, - "PF failed to add unicast entry(%pM) in the MAC table\n", - addr); + if (!ret) + return -EEXIST; return ret; } @@ -8868,7 +8861,13 @@ static void hclge_sync_vport_mac_list(struct hclge_vport *vport, } else { set_bit(HCLGE_VPORT_STATE_MAC_TBL_CHANGE, &vport->state); - break; + + /* If one unicast mac address is existing in hardware, + * we need to try whether other unicast mac addresses + * are new addresses that can be added. + */ + if (ret != -EEXIST) + break; } } } From 276e60421668d019dc655973b1832ea354c0f36c Mon Sep 17 00:00:00 2001 From: Guangbin Huang Date: Wed, 29 Sep 2021 17:35:54 +0800 Subject: [PATCH 813/866] net: hns3: PF enable promisc for VF when mac table is overflow If unicast mac address table is full, and user add a new mac address, the unicast promisc needs to be enabled for the new unicast mac address can be used. So does the multicast promisc. Now this feature has been implemented for PF, and VF should be implemented too. When the mac table of VF is overflow, PF will enable promisc for this VF. Fixes: 1e6e76101fd9 ("net: hns3: configure promisc mode for VF asynchronously") Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 3391244d9d3d..f5b8d1fee0f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -12796,8 +12796,12 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev) continue; if (vport->vf_info.trusted) { - uc_en = vport->vf_info.request_uc_en > 0; - mc_en = vport->vf_info.request_mc_en > 0; + uc_en = vport->vf_info.request_uc_en > 0 || + vport->overflow_promisc_flags & + HNAE3_OVERFLOW_UPE; + mc_en = vport->vf_info.request_mc_en > 0 || + vport->overflow_promisc_flags & + HNAE3_OVERFLOW_MPE; } bc_en = vport->vf_info.request_bc_en > 0; From 27bf4af69fcb9845fb2f0076db5d562ec072e70f Mon Sep 17 00:00:00 2001 From: Guangbin Huang Date: Wed, 29 Sep 2021 17:35:55 +0800 Subject: [PATCH 814/866] net: hns3: fix always enable rx vlan filter problem after selftest Currently, the rx vlan filter will always be disabled before selftest and be enabled after selftest as the rx vlan filter feature is fixed on in old device earlier than V3. However, this feature is not fixed in some new devices and it can be disabled by user. In this case, it is wrong if rx vlan filter is enabled after selftest. So fix it. Fixes: bcc26e8dc432 ("net: hns3: remove unused code in hns3_self_test()") Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 7ea511d59e91..5ebd96f6833d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -334,7 +334,8 @@ static void hns3_selftest_prepare(struct net_device *ndev, #if IS_ENABLED(CONFIG_VLAN_8021Q) /* Disable the vlan filter for selftest does not support it */ - if (h->ae_algo->ops->enable_vlan_filter) + if (h->ae_algo->ops->enable_vlan_filter && + ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) h->ae_algo->ops->enable_vlan_filter(h, false); #endif @@ -359,7 +360,8 @@ static void hns3_selftest_restore(struct net_device *ndev, bool if_running) h->ae_algo->ops->halt_autoneg(h, false); #if IS_ENABLED(CONFIG_VLAN_8021Q) - if (h->ae_algo->ops->enable_vlan_filter) + if (h->ae_algo->ops->enable_vlan_filter && + ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) h->ae_algo->ops->enable_vlan_filter(h, true); #endif From 0178839ccca36dee238a57e7f4c3c252f5dbbba6 Mon Sep 17 00:00:00 2001 From: Guangbin Huang Date: Wed, 29 Sep 2021 17:35:56 +0800 Subject: [PATCH 815/866] net: hns3: disable firmware compatible features when uninstall PF Currently, the firmware compatible features are enabled in PF driver initialization process, but they are not disabled in PF driver deinitialization process and firmware keeps these features in enabled status. In this case, if load an old PF driver (for example, in VM) which not support the firmware compatible features, firmware will still send mailbox message to PF when link status changed and PF will print "un-supported mailbox message, code = 201". To fix this problem, disable these firmware compatible features in PF driver deinitialization process. Fixes: ed8fb4b262ae ("net: hns3: add link change event report") Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.c | 21 ++++++++++++------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index ac9b69513332..9c2eeaa82294 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -467,7 +467,7 @@ err_csq: return ret; } -static int hclge_firmware_compat_config(struct hclge_dev *hdev) +static int hclge_firmware_compat_config(struct hclge_dev *hdev, bool en) { struct hclge_firmware_compat_cmd *req; struct hclge_desc desc; @@ -475,13 +475,16 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_COMPAT_CFG, false); - req = (struct hclge_firmware_compat_cmd *)desc.data; + if (en) { + req = (struct hclge_firmware_compat_cmd *)desc.data; - hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); - hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); - if (hnae3_dev_phy_imp_supported(hdev)) - hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1); - req->compat = cpu_to_le32(compat); + hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); + hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); + if (hnae3_dev_phy_imp_supported(hdev)) + hnae3_set_bit(compat, HCLGE_PHY_IMP_EN_B, 1); + + req->compat = cpu_to_le32(compat); + } return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -538,7 +541,7 @@ int hclge_cmd_init(struct hclge_dev *hdev) /* ask the firmware to enable some features, driver can work without * it. */ - ret = hclge_firmware_compat_config(hdev); + ret = hclge_firmware_compat_config(hdev, true); if (ret) dev_warn(&hdev->pdev->dev, "Firmware compatible features not enabled(%d).\n", @@ -568,6 +571,8 @@ static void hclge_cmd_uninit_regs(struct hclge_hw *hw) void hclge_cmd_uninit(struct hclge_dev *hdev) { + hclge_firmware_compat_config(hdev, false); + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); /* wait to ensure that the firmware completes the possible left * over commands. From d88fd1b546ff19c8040cfaea76bf16aed1c5a0bb Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 28 Sep 2021 13:32:33 -0700 Subject: [PATCH 816/866] net: phy: bcm7xxx: Fixed indirect MMD operations When EEE support was added to the 28nm EPHY it was assumed that it would be able to support the standard clause 45 over clause 22 register access method. It turns out that the PHY does not support that, which is the very reason for using the indirect shadow mode 2 bank 3 access method. Implement {read,write}_mmd to allow the standard PHY library routines pertaining to EEE querying and configuration to work correctly on these PHYs. This forces us to implement a __phy_set_clr_bits() function that does not grab the MDIO bus lock since the PHY driver's {read,write}_mmd functions are always called with that lock held. Fixes: 83ee102a6998 ("net: phy: bcm7xxx: add support for 28nm EPHY") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 114 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 110 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index e79297a4bae8..27b6a3f507ae 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -27,7 +27,12 @@ #define MII_BCM7XXX_SHD_2_ADDR_CTRL 0xe #define MII_BCM7XXX_SHD_2_CTRL_STAT 0xf #define MII_BCM7XXX_SHD_2_BIAS_TRIM 0x1a +#define MII_BCM7XXX_SHD_3_PCS_CTRL 0x0 +#define MII_BCM7XXX_SHD_3_PCS_STATUS 0x1 +#define MII_BCM7XXX_SHD_3_EEE_CAP 0x2 #define MII_BCM7XXX_SHD_3_AN_EEE_ADV 0x3 +#define MII_BCM7XXX_SHD_3_EEE_LP 0x4 +#define MII_BCM7XXX_SHD_3_EEE_WK_ERR 0x5 #define MII_BCM7XXX_SHD_3_PCS_CTRL_2 0x6 #define MII_BCM7XXX_PCS_CTRL_2_DEF 0x4400 #define MII_BCM7XXX_SHD_3_AN_STAT 0xb @@ -216,25 +221,37 @@ static int bcm7xxx_28nm_resume(struct phy_device *phydev) return genphy_config_aneg(phydev); } -static int phy_set_clr_bits(struct phy_device *dev, int location, - int set_mask, int clr_mask) +static int __phy_set_clr_bits(struct phy_device *dev, int location, + int set_mask, int clr_mask) { int v, ret; - v = phy_read(dev, location); + v = __phy_read(dev, location); if (v < 0) return v; v &= ~clr_mask; v |= set_mask; - ret = phy_write(dev, location, v); + ret = __phy_write(dev, location, v); if (ret < 0) return ret; return v; } +static int phy_set_clr_bits(struct phy_device *dev, int location, + int set_mask, int clr_mask) +{ + int ret; + + mutex_lock(&dev->mdio.bus->mdio_lock); + ret = __phy_set_clr_bits(dev, location, set_mask, clr_mask); + mutex_unlock(&dev->mdio.bus->mdio_lock); + + return ret; +} + static int bcm7xxx_28nm_ephy_01_afe_config_init(struct phy_device *phydev) { int ret; @@ -398,6 +415,93 @@ static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev) return bcm7xxx_28nm_ephy_apd_enable(phydev); } +#define MII_BCM7XXX_REG_INVALID 0xff + +static u8 bcm7xxx_28nm_ephy_regnum_to_shd(u16 regnum) +{ + switch (regnum) { + case MDIO_CTRL1: + return MII_BCM7XXX_SHD_3_PCS_CTRL; + case MDIO_STAT1: + return MII_BCM7XXX_SHD_3_PCS_STATUS; + case MDIO_PCS_EEE_ABLE: + return MII_BCM7XXX_SHD_3_EEE_CAP; + case MDIO_AN_EEE_ADV: + return MII_BCM7XXX_SHD_3_AN_EEE_ADV; + case MDIO_AN_EEE_LPABLE: + return MII_BCM7XXX_SHD_3_EEE_LP; + case MDIO_PCS_EEE_WK_ERR: + return MII_BCM7XXX_SHD_3_EEE_WK_ERR; + default: + return MII_BCM7XXX_REG_INVALID; + } +} + +static bool bcm7xxx_28nm_ephy_dev_valid(int devnum) +{ + return devnum == MDIO_MMD_AN || devnum == MDIO_MMD_PCS; +} + +static int bcm7xxx_28nm_ephy_read_mmd(struct phy_device *phydev, + int devnum, u16 regnum) +{ + u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum); + int ret; + + if (!bcm7xxx_28nm_ephy_dev_valid(devnum) || + shd == MII_BCM7XXX_REG_INVALID) + return -EOPNOTSUPP; + + /* set shadow mode 2 */ + ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Access the desired shadow register address */ + ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd); + if (ret < 0) + goto reset_shadow_mode; + + ret = __phy_read(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT); + +reset_shadow_mode: + /* reset shadow mode 2 */ + __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); + return ret; +} + +static int bcm7xxx_28nm_ephy_write_mmd(struct phy_device *phydev, + int devnum, u16 regnum, u16 val) +{ + u8 shd = bcm7xxx_28nm_ephy_regnum_to_shd(regnum); + int ret; + + if (!bcm7xxx_28nm_ephy_dev_valid(devnum) || + shd == MII_BCM7XXX_REG_INVALID) + return -EOPNOTSUPP; + + /* set shadow mode 2 */ + ret = __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + /* Access the desired shadow register address */ + ret = __phy_write(phydev, MII_BCM7XXX_SHD_2_ADDR_CTRL, shd); + if (ret < 0) + goto reset_shadow_mode; + + /* Write the desired value in the shadow register */ + __phy_write(phydev, MII_BCM7XXX_SHD_2_CTRL_STAT, val); + +reset_shadow_mode: + /* reset shadow mode 2 */ + return __phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, + MII_BCM7XXX_SHD_MODE_2); +} + static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) { int ret; @@ -595,6 +699,8 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev) .get_stats = bcm7xxx_28nm_get_phy_stats, \ .probe = bcm7xxx_28nm_probe, \ .remove = bcm7xxx_28nm_remove, \ + .read_mmd = bcm7xxx_28nm_ephy_read_mmd, \ + .write_mmd = bcm7xxx_28nm_ephy_write_mmd, \ } #define BCM7XXX_40NM_EPHY(_oui, _name) \ From 540cffbab8b8e6c52a4121666ca18d6e94586ed2 Mon Sep 17 00:00:00 2001 From: Andrey Gusakov Date: Thu, 23 Sep 2021 20:22:16 +0300 Subject: [PATCH 817/866] gpio: pca953x: do not ignore i2c errors Per gpio_chip interface, error shall be proparated to the caller. Attempt to silent diagnostics by returning zero (as written in the comment) is plain wrong, because the zero return can be interpreted by the caller as the gpio value. Cc: stable@vger.kernel.org Signed-off-by: Andrey Gusakov Signed-off-by: Nikita Yushchenko Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-pca953x.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index f5cfc0698799..8ebf369b3ba0 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -468,15 +468,8 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) mutex_lock(&chip->i2c_lock); ret = regmap_read(chip->regmap, inreg, ®_val); mutex_unlock(&chip->i2c_lock); - if (ret < 0) { - /* - * NOTE: - * diagnostic already emitted; that's all we should - * do unless gpio_*_value_cansleep() calls become different - * from their nonsleeping siblings (and report faults). - */ - return 0; - } + if (ret < 0) + return ret; return !!(reg_val & bit); } From d1d598104336075e7475d932d200b33108399225 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 20 Sep 2021 09:18:37 +0200 Subject: [PATCH 818/866] MAINTAINERS: update my email address My professional situation changes soon. Update my email address. Signed-off-by: Bartosz Golaszewski Reviewed-by: Linus Walleij Acked-by: Andy Shevchenko --- MAINTAINERS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 5b33791bb8e9..4b98ca39c803 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2961,7 +2961,7 @@ F: crypto/async_tx/ F: include/linux/async_tx.h AT24 EEPROM DRIVER -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-i2c@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -7985,7 +7985,7 @@ F: include/linux/gpio/regmap.h GPIO SUBSYSTEM M: Linus Walleij -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-gpio@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git @@ -11366,7 +11366,7 @@ F: Documentation/devicetree/bindings/iio/proximity/maxbotix,mb1232.yaml F: drivers/iio/proximity/mb1232.c MAXIM MAX77650 PMIC MFD DRIVER -M: Bartosz Golaszewski +M: Bartosz Golaszewski L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/*/*max77650.yaml @@ -18682,7 +18682,7 @@ F: include/linux/clk/ti.h TI DAVINCI MACHINE SUPPORT M: Sekhar Nori -R: Bartosz Golaszewski +R: Bartosz Golaszewski L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci.git From 040d985e27dc39353d50d0f75a6be3330f4fece2 Mon Sep 17 00:00:00 2001 From: Mun Yew Tham Date: Wed, 29 Sep 2021 08:49:11 +0800 Subject: [PATCH 819/866] MAINTAINERS: Update Mun Yew Tham as Altera Pio Driver maintainer Update Altera Pio Driver maintainer's email from to Signed-off-by: Mun Yew Tham Acked-by: Joyce Ooi Signed-off-by: Bartosz Golaszewski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4b98ca39c803..01ff450dda42 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -810,7 +810,7 @@ F: Documentation/devicetree/bindings/dma/altr,msgdma.yaml F: drivers/dma/altera-msgdma.c ALTERA PIO DRIVER -M: Joyce Ooi +M: Mun Yew Tham L: linux-gpio@vger.kernel.org S: Maintained F: drivers/gpio/gpio-altera.c From ce812992f239f45e13c820a52455fec6eacbce1e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 27 Sep 2021 21:47:48 +0900 Subject: [PATCH 820/866] ksmbd: remove NTLMv1 authentication MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove insecure NTLMv1 authentication. Cc: Ronnie Sahlberg Cc: Ralph Böhme Reviewed-by: Tom Talpey Acked-by: Steve French Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/auth.c | 205 ------------------------------------------ fs/ksmbd/crypto_ctx.c | 16 ---- fs/ksmbd/crypto_ctx.h | 8 -- 3 files changed, 229 deletions(-) diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index de36f12070bf..71c989f1568d 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -68,125 +68,6 @@ void ksmbd_copy_gss_neg_header(void *buf) memcpy(buf, NEGOTIATE_GSS_HEADER, AUTH_GSS_LENGTH); } -static void -str_to_key(unsigned char *str, unsigned char *key) -{ - int i; - - key[0] = str[0] >> 1; - key[1] = ((str[0] & 0x01) << 6) | (str[1] >> 2); - key[2] = ((str[1] & 0x03) << 5) | (str[2] >> 3); - key[3] = ((str[2] & 0x07) << 4) | (str[3] >> 4); - key[4] = ((str[3] & 0x0F) << 3) | (str[4] >> 5); - key[5] = ((str[4] & 0x1F) << 2) | (str[5] >> 6); - key[6] = ((str[5] & 0x3F) << 1) | (str[6] >> 7); - key[7] = str[6] & 0x7F; - for (i = 0; i < 8; i++) - key[i] = (key[i] << 1); -} - -static int -smbhash(unsigned char *out, const unsigned char *in, unsigned char *key) -{ - unsigned char key2[8]; - struct des_ctx ctx; - - if (fips_enabled) { - ksmbd_debug(AUTH, "FIPS compliance enabled: DES not permitted\n"); - return -ENOENT; - } - - str_to_key(key, key2); - des_expand_key(&ctx, key2, DES_KEY_SIZE); - des_encrypt(&ctx, out, in); - memzero_explicit(&ctx, sizeof(ctx)); - return 0; -} - -static int ksmbd_enc_p24(unsigned char *p21, const unsigned char *c8, unsigned char *p24) -{ - int rc; - - rc = smbhash(p24, c8, p21); - if (rc) - return rc; - rc = smbhash(p24 + 8, c8, p21 + 7); - if (rc) - return rc; - return smbhash(p24 + 16, c8, p21 + 14); -} - -/* produce a md4 message digest from data of length n bytes */ -static int ksmbd_enc_md4(unsigned char *md4_hash, unsigned char *link_str, - int link_len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md4(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md4 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD4(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md4 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD4(ctx), link_str, link_len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with link_str\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD4(ctx), md4_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md4 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - -static int ksmbd_enc_update_sess_key(unsigned char *md5_hash, char *nonce, - char *server_challenge, int len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md5(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md5 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD5(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md5 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), server_challenge, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with challenge\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), nonce, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with nonce\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD5(ctx), md5_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md5 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - /** * ksmbd_gen_sess_key() - function to generate session key * @sess: session of connection @@ -324,43 +205,6 @@ out: return ret; } -/** - * ksmbd_auth_ntlm() - NTLM authentication handler - * @sess: session of connection - * @pw_buf: NTLM challenge response - * @passkey: user password - * - * Return: 0 on success, error number on error - */ -int ksmbd_auth_ntlm(struct ksmbd_session *sess, char *pw_buf) -{ - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess->ntlmssp.cryptkey, key); - if (rc) { - pr_err("password processing failed\n"); - return rc; - } - - ksmbd_enc_md4(sess->sess_key, user_passkey(sess->user), - CIFS_SMB1_SESSKEY_SIZE); - memcpy(sess->sess_key + CIFS_SMB1_SESSKEY_SIZE, key, - CIFS_AUTH_RESP_SIZE); - sess->sequence_number = 1; - - if (strncmp(pw_buf, key, CIFS_AUTH_RESP_SIZE) != 0) { - ksmbd_debug(AUTH, "ntlmv1 authentication failed\n"); - return -EINVAL; - } - - ksmbd_debug(AUTH, "ntlmv1 authentication pass\n"); - return 0; -} - /** * ksmbd_auth_ntlmv2() - NTLMv2 authentication handler * @sess: session of connection @@ -441,44 +285,6 @@ out: return rc; } -/** - * __ksmbd_auth_ntlmv2() - NTLM2(extended security) authentication handler - * @sess: session of connection - * @client_nonce: client nonce from LM response. - * @ntlm_resp: ntlm response data from client. - * - * Return: 0 on success, error number on error - */ -static int __ksmbd_auth_ntlmv2(struct ksmbd_session *sess, char *client_nonce, - char *ntlm_resp) -{ - char sess_key[CIFS_SMB1_SESSKEY_SIZE] = {0}; - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - rc = ksmbd_enc_update_sess_key(sess_key, - client_nonce, - (char *)sess->ntlmssp.cryptkey, 8); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess_key, key); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - if (memcmp(ntlm_resp, key, CIFS_AUTH_RESP_SIZE) != 0) - rc = -EINVAL; -out: - return rc; -} - /** * ksmbd_decode_ntlmssp_auth_blob() - helper function to construct * authenticate blob @@ -512,17 +318,6 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_off = le32_to_cpu(authblob->NtChallengeResponse.BufferOffset); nt_len = le16_to_cpu(authblob->NtChallengeResponse.Length); - /* process NTLM authentication */ - if (nt_len == CIFS_AUTH_RESP_SIZE) { - if (le32_to_cpu(authblob->NegotiateFlags) & - NTLMSSP_NEGOTIATE_EXTENDED_SEC) - return __ksmbd_auth_ntlmv2(sess, (char *)authblob + - lm_off, (char *)authblob + nt_off); - else - return ksmbd_auth_ntlm(sess, (char *)authblob + - nt_off); - } - /* TODO : use domain name that imported from configuration file */ domain_name = smb_strndup_from_utf16((const char *)authblob + le32_to_cpu(authblob->DomainName.BufferOffset), diff --git a/fs/ksmbd/crypto_ctx.c b/fs/ksmbd/crypto_ctx.c index 5f4b1008d17e..81488d04199d 100644 --- a/fs/ksmbd/crypto_ctx.c +++ b/fs/ksmbd/crypto_ctx.c @@ -81,12 +81,6 @@ static struct shash_desc *alloc_shash_desc(int id) case CRYPTO_SHASH_SHA512: tfm = crypto_alloc_shash("sha512", 0, 0); break; - case CRYPTO_SHASH_MD4: - tfm = crypto_alloc_shash("md4", 0, 0); - break; - case CRYPTO_SHASH_MD5: - tfm = crypto_alloc_shash("md5", 0, 0); - break; default: return NULL; } @@ -214,16 +208,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void) return ____crypto_shash_ctx_find(CRYPTO_SHASH_SHA512); } -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD4); -} - -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD5); -} - static struct ksmbd_crypto_ctx *____crypto_aead_ctx_find(int id) { struct ksmbd_crypto_ctx *ctx; diff --git a/fs/ksmbd/crypto_ctx.h b/fs/ksmbd/crypto_ctx.h index ef11154b43df..4a367c62f653 100644 --- a/fs/ksmbd/crypto_ctx.h +++ b/fs/ksmbd/crypto_ctx.h @@ -15,8 +15,6 @@ enum { CRYPTO_SHASH_CMACAES, CRYPTO_SHASH_SHA256, CRYPTO_SHASH_SHA512, - CRYPTO_SHASH_MD4, - CRYPTO_SHASH_MD5, CRYPTO_SHASH_MAX, }; @@ -43,8 +41,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES(c) ((c)->desc[CRYPTO_SHASH_CMACAES]) #define CRYPTO_SHA256(c) ((c)->desc[CRYPTO_SHASH_SHA256]) #define CRYPTO_SHA512(c) ((c)->desc[CRYPTO_SHASH_SHA512]) -#define CRYPTO_MD4(c) ((c)->desc[CRYPTO_SHASH_MD4]) -#define CRYPTO_MD5(c) ((c)->desc[CRYPTO_SHASH_MD5]) #define CRYPTO_HMACMD5_TFM(c) ((c)->desc[CRYPTO_SHASH_HMACMD5]->tfm) #define CRYPTO_HMACSHA256_TFM(c)\ @@ -52,8 +48,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES_TFM(c) ((c)->desc[CRYPTO_SHASH_CMACAES]->tfm) #define CRYPTO_SHA256_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA256]->tfm) #define CRYPTO_SHA512_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA512]->tfm) -#define CRYPTO_MD4_TFM(c) ((c)->desc[CRYPTO_SHASH_MD4]->tfm) -#define CRYPTO_MD5_TFM(c) ((c)->desc[CRYPTO_SHASH_MD5]->tfm) #define CRYPTO_GCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_GCM]) #define CRYPTO_CCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_CCM]) @@ -64,8 +58,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_hmacsha256(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_cmacaes(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha256(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_gcm(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_ccm(void); void ksmbd_crypto_destroy(void); From 41e76c6a3c83c85e849f10754b8632ea763d9be4 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 20 Sep 2021 16:25:33 -0700 Subject: [PATCH 821/866] nbd: use shifts rather than multiplies commit fad7cd3310db ("nbd: add the check to prevent overflow in __nbd_ioctl()") raised an issue from the fallback helpers added in commit f0907827a8a9 ("compiler.h: enable builtin overflow checkers and add fallback code") ERROR: modpost: "__divdi3" [drivers/block/nbd.ko] undefined! As Stephen Rothwell notes: The added check_mul_overflow() call is being passed 64 bit values. COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW is not set for this build (see include/linux/overflow.h). Specifically, the helpers for checking whether the results of a multiplication overflowed (__unsigned_mul_overflow, __signed_add_overflow) use the division operator when !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW. This is problematic for 64b operands on 32b hosts. This was fixed upstream by commit 76ae847497bc ("Documentation: raise minimum supported version of GCC to 5.1") which is not suitable to be backported to stable. Further, __builtin_mul_overflow() would emit a libcall to a compiler-rt-only symbol when compiling with clang < 14 for 32b targets. ld.lld: error: undefined symbol: __mulodi4 In order to keep stable buildable with GCC 4.9 and clang < 14, modify struct nbd_config to instead track the number of bits of the block size; reconstructing the block size using runtime checked shifts that are not problematic for those compilers and in a ways that can be backported to stable. In nbd_set_size, we do validate that the value of blksize must be a power of two (POT) and is in the range of [512, PAGE_SIZE] (both inclusive). This does modify the debugfs interface. Cc: stable@vger.kernel.org Cc: Arnd Bergmann Cc: Rasmus Villemoes Link: https://github.com/ClangBuiltLinux/linux/issues/1438 Link: https://lore.kernel.org/all/20210909182525.372ee687@canb.auug.org.au/ Link: https://lore.kernel.org/stable/CAHk-=whiQBofgis_rkniz8GBP9wZtSZdcDEffgSLO62BUGV3gg@mail.gmail.com/ Reported-by: Naresh Kamboju Reported-by: Nathan Chancellor Reported-by: Stephen Rothwell Suggested-by: Kees Cook Suggested-by: Linus Torvalds Suggested-by: Pavel Machek Signed-off-by: Nick Desaulniers Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20210920232533.4092046-1-ndesaulniers@google.com Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5170a630778d..1183f7872b71 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -97,13 +97,18 @@ struct nbd_config { atomic_t recv_threads; wait_queue_head_t recv_wq; - loff_t blksize; + unsigned int blksize_bits; loff_t bytesize; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; #endif }; +static inline unsigned int nbd_blksize(struct nbd_config *config) +{ + return 1u << config->blksize_bits; +} + struct nbd_device { struct blk_mq_tag_set tag_set; @@ -146,7 +151,7 @@ static struct dentry *nbd_dbg_dir; #define NBD_MAGIC 0x68797548 -#define NBD_DEF_BLKSIZE 1024 +#define NBD_DEF_BLKSIZE_BITS 10 static unsigned int nbds_max = 16; static int max_part = 16; @@ -317,12 +322,12 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { if (!blksize) - blksize = NBD_DEF_BLKSIZE; + blksize = 1u << NBD_DEF_BLKSIZE_BITS; if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize)) return -EINVAL; nbd->config->bytesize = bytesize; - nbd->config->blksize = blksize; + nbd->config->blksize_bits = __ffs(blksize); if (!nbd->task_recv) return 0; @@ -1337,7 +1342,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - return nbd_set_size(nbd, config->bytesize, config->blksize); + return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) @@ -1406,11 +1411,11 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_BLKSIZE: return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: - return nbd_set_size(nbd, arg, config->blksize); + return nbd_set_size(nbd, arg, nbd_blksize(config)); case NBD_SET_SIZE_BLOCKS: - if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize)) + if (check_shl_overflow(arg, config->blksize_bits, &bytesize)) return -EINVAL; - return nbd_set_size(nbd, bytesize, config->blksize); + return nbd_set_size(nbd, bytesize, nbd_blksize(config)); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; @@ -1476,7 +1481,7 @@ static struct nbd_config *nbd_alloc_config(void) atomic_set(&config->recv_threads, 0); init_waitqueue_head(&config->recv_wq); init_waitqueue_head(&config->conn_wait); - config->blksize = NBD_DEF_BLKSIZE; + config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); try_module_get(THIS_MODULE); return config; @@ -1604,7 +1609,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops); debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout); - debugfs_create_u64("blocksize", 0444, dir, &config->blksize); + debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits); debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops); return 0; @@ -1826,7 +1831,7 @@ nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = { static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) { struct nbd_config *config = nbd->config; - u64 bsize = config->blksize; + u64 bsize = nbd_blksize(config); u64 bytes = config->bytesize; if (info->attrs[NBD_ATTR_SIZE_BYTES]) @@ -1835,7 +1840,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); - if (bytes != config->bytesize || bsize != config->blksize) + if (bytes != config->bytesize || bsize != nbd_blksize(config)) return nbd_set_size(nbd, bytes, bsize); return 0; } From ad9af930680bb396c87582edc172b3a7cf2a3fbf Mon Sep 17 00:00:00 2001 From: Zelin Deng Date: Wed, 29 Sep 2021 13:13:48 +0800 Subject: [PATCH 822/866] x86/kvmclock: Move this_cpu_pvti into kvmclock.h There're other modules might use hv_clock_per_cpu variable like ptp_kvm, so move it into kvmclock.h and export the symbol to make it visiable to other modules. Signed-off-by: Zelin Deng Cc: Message-Id: <1632892429-101194-2-git-send-email-zelin.deng@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvmclock.h | 14 ++++++++++++++ arch/x86/kernel/kvmclock.c | 13 ++----------- 2 files changed, 16 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..73c74b961d0f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may From 773e89ab0056aaa2baa1ffd9f044551654410104 Mon Sep 17 00:00:00 2001 From: Zelin Deng Date: Wed, 29 Sep 2021 13:13:49 +0800 Subject: [PATCH 823/866] ptp: Fix ptp_kvm_getcrosststamp issue for x86 ptp_kvm hv_clock is preallocated to have only HVC_BOOT_ARRAY_SIZE (64) elements; if the PTP_SYS_OFFSET_PRECISE ioctl is executed on vCPUs whose index is 64 of higher, retrieving the struct pvclock_vcpu_time_info pointer with "src = &hv_clock[cpu].pvti" will result in an out-of-bounds access and a wild pointer. Change it to "this_cpu_pvti()" which is guaranteed to be valid. Fixes: 95a3d4454bb1 ("Switch kvmclock data to a PER_CPU variable") Signed-off-by: Zelin Deng Cc: Message-Id: <1632892429-101194-3-git-send-email-zelin.deng@linux.alibaba.com> Signed-off-by: Paolo Bonzini --- drivers/ptp/ptp_kvm_x86.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 3dd519dfc473..d0096cd7096a 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -15,8 +15,6 @@ #include #include -struct pvclock_vsyscall_time_info *hv_clock; - static phys_addr_t clock_pair_gpa; static struct kvm_clock_pairing clock_pair; @@ -28,8 +26,7 @@ int kvm_arch_ptp_init(void) return -ENODEV; clock_pair_gpa = slow_virt_to_phys(&clock_pair); - hv_clock = pvclock_get_pvti_cpu0_va(); - if (!hv_clock) + if (!pvclock_get_pvti_cpu0_va()) return -ENODEV; ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, @@ -64,10 +61,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct pvclock_vcpu_time_info *src; unsigned int version; long ret; - int cpu; - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; + src = this_cpu_pvti(); do { /* From e8a747d0884e554a8c1872da6c8f680a4f893c6d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 29 Sep 2021 15:24:25 -0700 Subject: [PATCH 824/866] KVM: x86: Swap order of CPUID entry "index" vs. "significant flag" checks Check whether a CPUID entry's index is significant before checking for a matching index to hack-a-fix an undefined behavior bug due to consuming uninitialized data. RESET/INIT emulation uses kvm_cpuid() to retrieve CPUID.0x1, which does _not_ have a significant index, and fails to initialize the dummy variable that doubles as EBX/ECX/EDX output _and_ ECX, a.k.a. index, input. Practically speaking, it's _extremely_ unlikely any compiler will yield code that causes problems, as the compiler would need to inline the kvm_cpuid() call to detect the uninitialized data, and intentionally hose the kernel, e.g. insert ud2, instead of simply ignoring the result of the index comparison. Although the sketchy "dummy" pattern was introduced in SVM by commit 66f7b72e1171 ("KVM: x86: Make register state after reset conform to specification"), it wasn't actually broken until commit 7ff6c0350315 ("KVM: x86: Remove stateful CPUID handling") arbitrarily swapped the order of operations such that "index" was checked before the significant flag. Avoid consuming uninitialized data by reverting to checking the flag before the index purely so that the fix can be easily backported; the offending RESET/INIT code has been refactored, moved, and consolidated from vendor code to common x86 since the bug was introduced. A future patch will directly address the bad RESET/INIT behavior. The undefined behavior was detected by syzbot + KernelMemorySanitizer. BUG: KMSAN: uninit-value in cpuid_entry2_find arch/x86/kvm/cpuid.c:68 BUG: KMSAN: uninit-value in kvm_find_cpuid_entry arch/x86/kvm/cpuid.c:1103 BUG: KMSAN: uninit-value in kvm_cpuid+0x456/0x28f0 arch/x86/kvm/cpuid.c:1183 cpuid_entry2_find arch/x86/kvm/cpuid.c:68 [inline] kvm_find_cpuid_entry arch/x86/kvm/cpuid.c:1103 [inline] kvm_cpuid+0x456/0x28f0 arch/x86/kvm/cpuid.c:1183 kvm_vcpu_reset+0x13fb/0x1c20 arch/x86/kvm/x86.c:10885 kvm_apic_accept_events+0x58f/0x8c0 arch/x86/kvm/lapic.c:2923 vcpu_enter_guest+0xfd2/0x6d80 arch/x86/kvm/x86.c:9534 vcpu_run+0x7f5/0x18d0 arch/x86/kvm/x86.c:9788 kvm_arch_vcpu_ioctl_run+0x245b/0x2d10 arch/x86/kvm/x86.c:10020 Local variable ----dummy@kvm_vcpu_reset created at: kvm_vcpu_reset+0x1fb/0x1c20 arch/x86/kvm/x86.c:10812 kvm_apic_accept_events+0x58f/0x8c0 arch/x86/kvm/lapic.c:2923 Reported-by: syzbot+f3985126b746b3d59c9d@syzkaller.appspotmail.com Reported-by: Alexander Potapenko Fixes: 2a24be79b6b7 ("KVM: VMX: Set EDX at INIT with CPUID.0x1, Family-Model-Stepping") Fixes: 7ff6c0350315 ("KVM: x86: Remove stateful CPUID handling") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Reviewed-by: Jim Mattson Message-Id: <20210929222426.1855730-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..751aa85a3001 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } From 7b0035eaa7dab9fd33d6658ad6a755024bdce26c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 29 Sep 2021 16:41:12 -0700 Subject: [PATCH 825/866] KVM: selftests: Ensure all migrations are performed when test is affined Rework the CPU selection in the migration worker to ensure the specified number of migrations are performed when the test iteslf is affined to a subset of CPUs. The existing logic skips iterations if the target CPU is not in the original set of possible CPUs, which causes the test to fail if too many iterations are skipped. ==== Test Assertion Failure ==== rseq_test.c:228: i > (NR_TASK_MIGRATIONS / 2) pid=10127 tid=10127 errno=4 - Interrupted system call 1 0x00000000004018e5: main at rseq_test.c:227 2 0x00007fcc8fc66bf6: ?? ??:0 3 0x0000000000401959: _start at ??:? Only performed 4 KVM_RUNs, task stalled too much? Calculate the min/max possible CPUs as a cheap "best effort" to avoid high runtimes when the test is affined to a small percentage of CPUs. Alternatively, a list or xarray of the possible CPUs could be used, but even in a horrendously inefficient setup, such optimizations are not needed because the runtime is completely dominated by the cost of migrating the task, and the absolute runtime is well under a minute in even truly absurd setups, e.g. running on a subset of vCPUs in a VM that is heavily overcommited (16 vCPUs per pCPU). Fixes: 61e52f1630f5 ("KVM: selftests: Add a test for KVM_RUN+rseq to detect task migration bugs") Reported-by: Dongli Zhang Signed-off-by: Sean Christopherson Message-Id: <20210929234112.1862848-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- tools/testing/selftests/kvm/rseq_test.c | 69 +++++++++++++++++++++---- 1 file changed, 59 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index c5e0dd664a7b..4158da0da2bb 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -39,6 +40,7 @@ static __thread volatile struct rseq __rseq = { static pthread_t migration_thread; static cpu_set_t possible_mask; +static int min_cpu, max_cpu; static bool done; static atomic_t seq_cnt; @@ -57,20 +59,37 @@ static void sys_rseq(int flags) TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); } +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + static void *migration_worker(void *ign) { cpu_set_t allowed_mask; - int r, i, nr_cpus, cpu; + int r, i, cpu; CPU_ZERO(&allowed_mask); - nr_cpus = CPU_COUNT(&possible_mask); - - for (i = 0; i < NR_TASK_MIGRATIONS; i++) { - cpu = i % nr_cpus; - if (!CPU_ISSET(cpu, &possible_mask)) - continue; - + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { CPU_SET(cpu, &allowed_mask); /* @@ -154,6 +173,36 @@ static void *migration_worker(void *ign) return NULL; } +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + int main(int argc, char *argv[]) { int r, i, snapshot; @@ -167,8 +216,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); - if (CPU_COUNT(&possible_mask) < 2) { - print_skip("Only one CPU, task migration not possible\n"); + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); exit(KSFT_SKIP); } From 49054556289e8787501630b7c7a9d407da02e296 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 29 Sep 2021 11:59:17 +0200 Subject: [PATCH 826/866] net: introduce and use lock_sock_fast_nested() Syzkaller reported a false positive deadlock involving the nl socket lock and the subflow socket lock: MPTCP: kernel_bind error, err=-98 ============================================ WARNING: possible recursive locking detected 5.15.0-rc1-syzkaller #0 Not tainted -------------------------------------------- syz-executor998/6520 is trying to acquire lock: ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 but task is already holding lock: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-sk_lock-AF_INET); lock(k-sk_lock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by syz-executor998/6520: #0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802 #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline] #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790 #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 stack backtrace: CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2944 [inline] check_deadlock kernel/locking/lockdep.c:2987 [inline] validate_chain kernel/locking/lockdep.c:3776 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015 lock_acquire kernel/locking/lockdep.c:5625 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590 lock_sock_fast+0x36/0x100 net/core/sock.c:3229 mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 __sock_release net/socket.c:649 [inline] sock_release+0x87/0x1b0 net/socket.c:677 mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900 mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731 genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_no_sendpage+0x101/0x150 net/core/sock.c:2980 kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504 kernel_sendpage net/socket.c:3501 [inline] sock_sendpage+0xe5/0x140 net/socket.c:1003 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0xd4/0x140 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x110/0x180 fs/splice.c:936 splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891 do_splice_direct+0x1b3/0x280 fs/splice.c:979 do_sendfile+0xae9/0x1240 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1314 [inline] __se_sys_sendfile64 fs/read_write.c:1300 [inline] __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f215cb69969 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005 RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08 R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 the problem originates from uncorrect lock annotation in the mptcp code and is only visible since commit 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations"), but is present since the port-based endpoint support initial implementation. This patch addresses the issue introducing a nested variant of lock_sock_fast() and using it in the relevant code path. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations") Suggested-by: Thomas Gleixner Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni Reviewed-by: Thomas Gleixner Signed-off-by: David S. Miller --- include/net/sock.h | 31 ++++++++++++++++++++++++++++++- net/core/sock.c | 20 ++------------------ net/mptcp/protocol.c | 2 +- 3 files changed, 33 insertions(+), 20 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index c005c3c750e8..dc3f8169312e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1623,7 +1623,36 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} /** * unlock_sock_fast - complement of lock_sock_fast diff --git a/net/core/sock.c b/net/core/sock.c index 512e629f9780..7060d183216e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3210,24 +3210,8 @@ void release_sock(struct sock *sk) } EXPORT_SYMBOL(release_sock); -/** - * lock_sock_fast - fast version of lock_sock - * @sk: socket - * - * This version should be used for very small section, where process wont block - * return false if fast path is taken: - * - * sk_lock.slock locked, owned = 0, BH disabled - * - * return true if slow path is taken: - * - * sk_lock.slock unlocked, owned = 1, BH enabled - */ -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { - /* The sk_lock has mutex_lock() semantics here. */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); - might_sleep(); spin_lock_bh(&sk->sk_lock.slock); @@ -3256,7 +3240,7 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) spin_unlock_bh(&sk->sk_lock.slock); return true; } -EXPORT_SYMBOL(lock_sock_fast); +EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dbcebf56798f..e5df0b5971c8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2735,7 +2735,7 @@ cleanup: inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(mptcp_sk(sk), subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); + bool slow = lock_sock_fast_nested(ssk); sock_orphan(ssk); unlock_sock_fast(ssk, slow); From d5ef190693a7d76c5c192d108e8dec48307b46ee Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 29 Sep 2021 18:08:49 +0300 Subject: [PATCH 827/866] net: sched: flower: protect fl_walk() with rcu Patch that refactored fl_walk() to use idr_for_each_entry_continue_ul() also removed rcu protection of individual filters which causes following use-after-free when filter is deleted concurrently. Fix fl_walk() to obtain rcu read lock while iterating and taking the filter reference and temporary release the lock while calling arg->fn() callback that can sleep. KASAN trace: [ 352.773640] ================================================================== [ 352.775041] BUG: KASAN: use-after-free in fl_walk+0x159/0x240 [cls_flower] [ 352.776304] Read of size 4 at addr ffff8881c8251480 by task tc/2987 [ 352.777862] CPU: 3 PID: 2987 Comm: tc Not tainted 5.15.0-rc2+ #2 [ 352.778980] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 352.781022] Call Trace: [ 352.781573] dump_stack_lvl+0x46/0x5a [ 352.782332] print_address_description.constprop.0+0x1f/0x140 [ 352.783400] ? fl_walk+0x159/0x240 [cls_flower] [ 352.784292] ? fl_walk+0x159/0x240 [cls_flower] [ 352.785138] kasan_report.cold+0x83/0xdf [ 352.785851] ? fl_walk+0x159/0x240 [cls_flower] [ 352.786587] kasan_check_range+0x145/0x1a0 [ 352.787337] fl_walk+0x159/0x240 [cls_flower] [ 352.788163] ? fl_put+0x10/0x10 [cls_flower] [ 352.789007] ? __mutex_unlock_slowpath.constprop.0+0x220/0x220 [ 352.790102] tcf_chain_dump+0x231/0x450 [ 352.790878] ? tcf_chain_tp_delete_empty+0x170/0x170 [ 352.791833] ? __might_sleep+0x2e/0xc0 [ 352.792594] ? tfilter_notify+0x170/0x170 [ 352.793400] ? __mutex_unlock_slowpath.constprop.0+0x220/0x220 [ 352.794477] tc_dump_tfilter+0x385/0x4b0 [ 352.795262] ? tc_new_tfilter+0x1180/0x1180 [ 352.796103] ? __mod_node_page_state+0x1f/0xc0 [ 352.796974] ? __build_skb_around+0x10e/0x130 [ 352.797826] netlink_dump+0x2c0/0x560 [ 352.798563] ? netlink_getsockopt+0x430/0x430 [ 352.799433] ? __mutex_unlock_slowpath.constprop.0+0x220/0x220 [ 352.800542] __netlink_dump_start+0x356/0x440 [ 352.801397] rtnetlink_rcv_msg+0x3ff/0x550 [ 352.802190] ? tc_new_tfilter+0x1180/0x1180 [ 352.802872] ? rtnl_calcit.isra.0+0x1f0/0x1f0 [ 352.803668] ? tc_new_tfilter+0x1180/0x1180 [ 352.804344] ? _copy_from_iter_nocache+0x800/0x800 [ 352.805202] ? kasan_set_track+0x1c/0x30 [ 352.805900] netlink_rcv_skb+0xc6/0x1f0 [ 352.806587] ? rht_deferred_worker+0x6b0/0x6b0 [ 352.807455] ? rtnl_calcit.isra.0+0x1f0/0x1f0 [ 352.808324] ? netlink_ack+0x4d0/0x4d0 [ 352.809086] ? netlink_deliver_tap+0x62/0x3d0 [ 352.809951] netlink_unicast+0x353/0x480 [ 352.810744] ? netlink_attachskb+0x430/0x430 [ 352.811586] ? __alloc_skb+0xd7/0x200 [ 352.812349] netlink_sendmsg+0x396/0x680 [ 352.813132] ? netlink_unicast+0x480/0x480 [ 352.813952] ? __import_iovec+0x192/0x210 [ 352.814759] ? netlink_unicast+0x480/0x480 [ 352.815580] sock_sendmsg+0x6c/0x80 [ 352.816299] ____sys_sendmsg+0x3a5/0x3c0 [ 352.817096] ? kernel_sendmsg+0x30/0x30 [ 352.817873] ? __ia32_sys_recvmmsg+0x150/0x150 [ 352.818753] ___sys_sendmsg+0xd8/0x140 [ 352.819518] ? sendmsg_copy_msghdr+0x110/0x110 [ 352.820402] ? ___sys_recvmsg+0xf4/0x1a0 [ 352.821110] ? __copy_msghdr_from_user+0x260/0x260 [ 352.821934] ? _raw_spin_lock+0x81/0xd0 [ 352.822680] ? __handle_mm_fault+0xef3/0x1b20 [ 352.823549] ? rb_insert_color+0x2a/0x270 [ 352.824373] ? copy_page_range+0x16b0/0x16b0 [ 352.825209] ? perf_event_update_userpage+0x2d0/0x2d0 [ 352.826190] ? __fget_light+0xd9/0xf0 [ 352.826941] __sys_sendmsg+0xb3/0x130 [ 352.827613] ? __sys_sendmsg_sock+0x20/0x20 [ 352.828377] ? do_user_addr_fault+0x2c5/0x8a0 [ 352.829184] ? fpregs_assert_state_consistent+0x52/0x60 [ 352.830001] ? exit_to_user_mode_prepare+0x32/0x160 [ 352.830845] do_syscall_64+0x35/0x80 [ 352.831445] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 352.832331] RIP: 0033:0x7f7bee973c17 [ 352.833078] Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 352.836202] RSP: 002b:00007ffcbb368e28 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 352.837524] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7bee973c17 [ 352.838715] RDX: 0000000000000000 RSI: 00007ffcbb368e50 RDI: 0000000000000003 [ 352.839838] RBP: 00007ffcbb36d090 R08: 00000000cea96d79 R09: 00007f7beea34a40 [ 352.841021] R10: 00000000004059bb R11: 0000000000000246 R12: 000000000046563f [ 352.842208] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffcbb36d088 [ 352.843784] Allocated by task 2960: [ 352.844451] kasan_save_stack+0x1b/0x40 [ 352.845173] __kasan_kmalloc+0x7c/0x90 [ 352.845873] fl_change+0x282/0x22db [cls_flower] [ 352.846696] tc_new_tfilter+0x6cf/0x1180 [ 352.847493] rtnetlink_rcv_msg+0x471/0x550 [ 352.848323] netlink_rcv_skb+0xc6/0x1f0 [ 352.849097] netlink_unicast+0x353/0x480 [ 352.849886] netlink_sendmsg+0x396/0x680 [ 352.850678] sock_sendmsg+0x6c/0x80 [ 352.851398] ____sys_sendmsg+0x3a5/0x3c0 [ 352.852202] ___sys_sendmsg+0xd8/0x140 [ 352.852967] __sys_sendmsg+0xb3/0x130 [ 352.853718] do_syscall_64+0x35/0x80 [ 352.854457] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 352.855830] Freed by task 7: [ 352.856421] kasan_save_stack+0x1b/0x40 [ 352.857139] kasan_set_track+0x1c/0x30 [ 352.857854] kasan_set_free_info+0x20/0x30 [ 352.858609] __kasan_slab_free+0xed/0x130 [ 352.859348] kfree+0xa7/0x3c0 [ 352.859951] process_one_work+0x44d/0x780 [ 352.860685] worker_thread+0x2e2/0x7e0 [ 352.861390] kthread+0x1f4/0x220 [ 352.862022] ret_from_fork+0x1f/0x30 [ 352.862955] Last potentially related work creation: [ 352.863758] kasan_save_stack+0x1b/0x40 [ 352.864378] kasan_record_aux_stack+0xab/0xc0 [ 352.865028] insert_work+0x30/0x160 [ 352.865617] __queue_work+0x351/0x670 [ 352.866261] rcu_work_rcufn+0x30/0x40 [ 352.866917] rcu_core+0x3b2/0xdb0 [ 352.867561] __do_softirq+0xf6/0x386 [ 352.868708] Second to last potentially related work creation: [ 352.869779] kasan_save_stack+0x1b/0x40 [ 352.870560] kasan_record_aux_stack+0xab/0xc0 [ 352.871426] call_rcu+0x5f/0x5c0 [ 352.872108] queue_rcu_work+0x44/0x50 [ 352.872855] __fl_put+0x17c/0x240 [cls_flower] [ 352.873733] fl_delete+0xc7/0x100 [cls_flower] [ 352.874607] tc_del_tfilter+0x510/0xb30 [ 352.886085] rtnetlink_rcv_msg+0x471/0x550 [ 352.886875] netlink_rcv_skb+0xc6/0x1f0 [ 352.887636] netlink_unicast+0x353/0x480 [ 352.888285] netlink_sendmsg+0x396/0x680 [ 352.888942] sock_sendmsg+0x6c/0x80 [ 352.889583] ____sys_sendmsg+0x3a5/0x3c0 [ 352.890311] ___sys_sendmsg+0xd8/0x140 [ 352.891019] __sys_sendmsg+0xb3/0x130 [ 352.891716] do_syscall_64+0x35/0x80 [ 352.892395] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 352.893666] The buggy address belongs to the object at ffff8881c8251000 which belongs to the cache kmalloc-2k of size 2048 [ 352.895696] The buggy address is located 1152 bytes inside of 2048-byte region [ffff8881c8251000, ffff8881c8251800) [ 352.897640] The buggy address belongs to the page: [ 352.898492] page:00000000213bac35 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1c8250 [ 352.900110] head:00000000213bac35 order:3 compound_mapcount:0 compound_pincount:0 [ 352.901541] flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) [ 352.902908] raw: 002ffff800010200 0000000000000000 dead000000000122 ffff888100042f00 [ 352.904391] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 352.905861] page dumped because: kasan: bad access detected [ 352.907323] Memory state around the buggy address: [ 352.908218] ffff8881c8251380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 352.909471] ffff8881c8251400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 352.910735] >ffff8881c8251480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 352.912012] ^ [ 352.912642] ffff8881c8251500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 352.913919] ffff8881c8251580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 352.915185] ================================================================== Fixes: d39d714969cd ("idr: introduce idr_for_each_entry_continue_ul()") Signed-off-by: Vlad Buslov Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 23b21253b3c3..eb6345a027e1 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2188,18 +2188,24 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, arg->count = arg->skip; + rcu_read_lock(); idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { /* don't return filters that are being deleted */ if (!refcount_inc_not_zero(&f->refcnt)) continue; + rcu_read_unlock(); + if (arg->fn(tp, f, arg) < 0) { __fl_put(f); arg->stop = 1; + rcu_read_lock(); break; } __fl_put(f); arg->count++; + rcu_read_lock(); } + rcu_read_unlock(); arg->cookie = id; } From a5b8fd657881003ea11c193d147c8f4ba143725d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 29 Sep 2021 08:32:24 -0700 Subject: [PATCH 828/866] net: dev_addr_list: handle first address in __hw_addr_add_ex struct dev_addr_list is used for device addresses, unicast addresses and multicast addresses. The first of those needs special handling of the main address - netdev->dev_addr points directly the data of the entry and drivers write to it freely, so we can't maintain it in the rbtree (for now, at least, to be fixed in net-next). Current work around sprinkles special handling of the first address on the list throughout the code but it missed the case where address is being added. First address will not be visible during subsequent adds. Syzbot found a warning where unicast addresses are modified without holding the rtnl lock, tl;dr is that team generates the same modification multiple times, not necessarily when right locks are held. In the repro we have: macvlan -> team -> veth macvlan adds a unicast address to the team. Team then pushes that address down to its memebers (veths). Next something unrelated makes team sync member addrs again, and because of the bug the addr entries get duplicated in the veths. macvlan gets removed, removes its addr from team which removes only one of the duplicated addresses from veths. This removal is done under rtnl. Next syzbot uses iptables to add a multicast addr to team (which does not hold rtnl lock). Team syncs veth addrs, but because veths' unicast list still has the duplicate it will also get sync, even though this update is intended for mc addresses. Again, uc address updates need rtnl lock, boom. Reported-by: syzbot+7a2ab2cdc14d134de553@syzkaller.appspotmail.com Fixes: 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs with IPv6 addresses, performance of changing link state, attaching a VRF, changing an IPv6 address, etc. go down dramtically.") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/core/dev_addr_lists.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 8c39283c26ae..f0cb38344126 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -50,6 +50,11 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, if (addr_len > MAX_ADDR_LEN) return -EINVAL; + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + goto found_it; + while (*ins_point) { int diff; @@ -64,6 +69,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } else if (diff > 0) { ins_point = &parent->rb_right; } else { +found_it: if (exclusive) return -EEXIST; if (global) { From 656ed8b015f19bf3f6e6b3ddd9a4bb4aa5ca73e1 Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Thu, 30 Sep 2021 14:44:36 +0800 Subject: [PATCH 829/866] net: stmmac: fix EEE init issue when paired with EEE capable PHYs When STMMAC is paired with Energy-Efficient Ethernet(EEE) capable PHY, and the PHY is advertising EEE by default, we need to enable EEE on the xPCS side too, instead of having user to manually trigger the enabling config via ethtool. Fixed this by adding xpcs_config_eee() call in stmmac_eee_init(). Fixes: 7617af3d1a5e ("net: pcs: Introducing support for DWC xpcs Energy Efficient Ethernet") Cc: Michael Sit Wei Hong Signed-off-by: Wong Vee Khee Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 553c4403258a..981ccf47dcea 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -486,6 +486,10 @@ bool stmmac_eee_init(struct stmmac_priv *priv) timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, eee_tw_timer); + if (priv->hw->xpcs) + xpcs_config_eee(priv->hw->xpcs, + priv->plat->mult_fact_100ns, + true); } if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) { From 35306eb23814444bd4021f8a1c3047d3cb0c8b2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Sep 2021 15:57:50 -0700 Subject: [PATCH 830/866] af_unix: fix races in sk_peer_pid and sk_peer_cred accesses Jann Horn reported that SO_PEERCRED and SO_PEERGROUPS implementations are racy, as af_unix can concurrently change sk_peer_pid and sk_peer_cred. In order to fix this issue, this patch adds a new spinlock that needs to be used whenever these fields are read or written. Jann also pointed out that l2cap_sock_get_peer_pid_cb() is currently reading sk->sk_peer_pid which makes no sense, as this field is only possibly set by AF_UNIX sockets. We will have to clean this in a separate patch. This could be done by reverting b48596d1dc25 "Bluetooth: L2CAP: Add get_peer_pid callback" or implementing what was truly expected. Fixes: 109f6e39fa07 ("af_unix: Allow SO_PEERCRED to work across namespaces.") Signed-off-by: Eric Dumazet Reported-by: Jann Horn Cc: Eric W. Biederman Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: David S. Miller --- include/net/sock.h | 2 ++ net/core/sock.c | 32 ++++++++++++++++++++++++++------ net/unix/af_unix.c | 34 ++++++++++++++++++++++++++++------ 3 files changed, 56 insertions(+), 12 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index dc3f8169312e..ae929e21a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -488,8 +488,10 @@ struct sock { u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif + spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 diff --git a/net/core/sock.c b/net/core/sock.c index 7060d183216e..c1601f75ec4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1376,6 +1376,16 @@ set_sndbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f505b89bda6a..efac5989edb5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) From 88d300522cbb2827b679359e98cbadfb46e8226c Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 29 Sep 2021 15:37:18 +0900 Subject: [PATCH 831/866] ksmbd: use correct basic info level in set_file_basic_info() Use correct basic info level in set/get_file_basic_info(). Reviewed-by: Ralph Boehme Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 13 ++++++------- fs/ksmbd/smb2pdu.h | 9 +++++++++ 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index cea376b2dd8f..ce10873cfded 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4161,7 +4161,7 @@ static void get_file_access_info(struct smb2_query_info_rsp *rsp, static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { - struct smb2_file_all_info *basic_info; + struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; @@ -4171,7 +4171,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - basic_info = (struct smb2_file_all_info *)rsp->Buffer; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); @@ -4184,9 +4184,8 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, basic_info->Attributes = fp->f_ci->m_fattr; basic_info->Pad1 = 0; rsp->OutputBufferLength = - cpu_to_le32(offsetof(struct smb2_file_all_info, AllocationSize)); - inc_rfc1001_len(rsp_org, offsetof(struct smb2_file_all_info, - AllocationSize)); + cpu_to_le32(sizeof(struct smb2_file_basic_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_basic_info)); return 0; } @@ -5412,7 +5411,7 @@ out: static int set_file_basic_info(struct ksmbd_file *fp, char *buf, struct ksmbd_share_config *share) { - struct smb2_file_all_info *file_info; + struct smb2_file_basic_info *file_info; struct iattr attrs; struct timespec64 ctime; struct file *filp; @@ -5423,7 +5422,7 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, if (!(fp->daccess & FILE_WRITE_ATTRIBUTES_LE)) return -EACCES; - file_info = (struct smb2_file_all_info *)buf; + file_info = (struct smb2_file_basic_info *)buf; attrs.ia_valid = 0; filp = fp->filp; inode = file_inode(filp); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index bcec845b03f3..261825d06391 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -1464,6 +1464,15 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ char FileName[1]; } __packed; /* level 18 Query */ +struct smb2_file_basic_info { /* data block encoding of response to level 18 */ + __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 Attributes; + __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ +} __packed; + struct smb2_file_alt_name_info { __le32 FileNameLength; char FileName[0]; From 9496e268e3af78a92778bf635488a8ec2dca8996 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 29 Sep 2021 15:41:48 +0900 Subject: [PATCH 832/866] ksmbd: add request buffer validation in smb2_set_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add buffer validation in smb2_set_info, and remove unused variable in set_file_basic_info. and smb2_set_info infolevel functions take structure pointer argument. Cc: Tom Talpey Cc: Ronnie Sahlberg Cc: Ralph Böhme Cc: Sergey Senozhatsky Acked-by: Hyunchul Lee Reviewed-by: Ralph Boehme Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 151 ++++++++++++++++++++++++++++++++------------- 1 file changed, 108 insertions(+), 43 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index ce10873cfded..0d915554f532 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2102,16 +2102,22 @@ out: * smb2_set_ea() - handler for setting extended attributes using set * info command * @eabuf: set info command buffer + * @buf_len: set info command buffer length * @path: dentry path for get ea * * Return: 0 on success, otherwise error */ -static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) +static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, + struct path *path) { struct user_namespace *user_ns = mnt_user_ns(path->mnt); char *attr_name = NULL, *value; int rc = 0; - int next = 0; + unsigned int next = 0; + + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) + return -EINVAL; attr_name = kmalloc(XATTR_NAME_MAX + 1, GFP_KERNEL); if (!attr_name) @@ -2176,7 +2182,13 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) next: next = le32_to_cpu(eabuf->NextEntryOffset); + if (next == 0 || buf_len < next) + break; + buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); + if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + break; + } while (next != 0); kfree(attr_name); @@ -2757,7 +2769,15 @@ int smb2_open(struct ksmbd_work *work) created = true; user_ns = mnt_user_ns(path.mnt); if (ea_buf) { - rc = smb2_set_ea(&ea_buf->ea, &path); + if (le32_to_cpu(ea_buf->ccontext.DataLength) < + sizeof(struct smb2_ea_info)) { + rc = -EINVAL; + goto err_out; + } + + rc = smb2_set_ea(&ea_buf->ea, + le32_to_cpu(ea_buf->ccontext.DataLength), + &path); if (rc == -EOPNOTSUPP) rc = 0; else if (rc) @@ -5341,7 +5361,7 @@ out: static int smb2_create_link(struct ksmbd_work *work, struct ksmbd_share_config *share, struct smb2_file_link_info *file_info, - struct file *filp, + unsigned int buf_len, struct file *filp, struct nls_table *local_nls) { char *link_name = NULL, *target_name = NULL, *pathname = NULL; @@ -5349,6 +5369,10 @@ static int smb2_create_link(struct ksmbd_work *work, bool file_present = true; int rc; + if (buf_len < (u64)sizeof(struct smb2_file_link_info) + + le32_to_cpu(file_info->FileNameLength)) + return -EINVAL; + ksmbd_debug(SMB, "setting FILE_LINK_INFORMATION\n"); pathname = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathname) @@ -5408,10 +5432,10 @@ out: return rc; } -static int set_file_basic_info(struct ksmbd_file *fp, char *buf, +static int set_file_basic_info(struct ksmbd_file *fp, + struct smb2_file_basic_info *file_info, struct ksmbd_share_config *share) { - struct smb2_file_basic_info *file_info; struct iattr attrs; struct timespec64 ctime; struct file *filp; @@ -5422,7 +5446,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, if (!(fp->daccess & FILE_WRITE_ATTRIBUTES_LE)) return -EACCES; - file_info = (struct smb2_file_basic_info *)buf; attrs.ia_valid = 0; filp = fp->filp; inode = file_inode(filp); @@ -5499,7 +5522,8 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, } static int set_file_allocation_info(struct ksmbd_work *work, - struct ksmbd_file *fp, char *buf) + struct ksmbd_file *fp, + struct smb2_file_alloc_info *file_alloc_info) { /* * TODO : It's working fine only when store dos attributes @@ -5507,7 +5531,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, * properly with any smb.conf option */ - struct smb2_file_alloc_info *file_alloc_info; loff_t alloc_blks; struct inode *inode; int rc; @@ -5515,7 +5538,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_alloc_info = (struct smb2_file_alloc_info *)buf; alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); @@ -5551,9 +5573,8 @@ static int set_file_allocation_info(struct ksmbd_work *work, } static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_eof_info *file_eof_info) { - struct smb2_file_eof_info *file_eof_info; loff_t newsize; struct inode *inode; int rc; @@ -5561,7 +5582,6 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_eof_info = (struct smb2_file_eof_info *)buf; newsize = le64_to_cpu(file_eof_info->EndOfFile); inode = file_inode(fp->filp); @@ -5588,7 +5608,8 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, } static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_rename_info *rename_info, + unsigned int buf_len) { struct user_namespace *user_ns; struct ksmbd_file *parent_fp; @@ -5601,6 +5622,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } + if (buf_len < (u64)sizeof(struct smb2_file_rename_info) + + le32_to_cpu(rename_info->FileNameLength)) + return -EINVAL; + user_ns = file_mnt_user_ns(fp->filp); if (ksmbd_stream_fd(fp)) goto next; @@ -5623,14 +5648,13 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, } } next: - return smb2_rename(work, fp, user_ns, - (struct smb2_file_rename_info *)buf, + return smb2_rename(work, fp, user_ns, rename_info, work->sess->conn->local_nls); } -static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) +static int set_file_disposition_info(struct ksmbd_file *fp, + struct smb2_file_disposition_info *file_info) { - struct smb2_file_disposition_info *file_info; struct inode *inode; if (!(fp->daccess & FILE_DELETE_LE)) { @@ -5639,7 +5663,6 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) } inode = file_inode(fp->filp); - file_info = (struct smb2_file_disposition_info *)buf; if (file_info->DeletePending) { if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) @@ -5651,15 +5674,14 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_position_info(struct ksmbd_file *fp, char *buf) +static int set_file_position_info(struct ksmbd_file *fp, + struct smb2_file_pos_info *file_info) { - struct smb2_file_pos_info *file_info; loff_t current_byte_offset; unsigned long sector_size; struct inode *inode; inode = file_inode(fp->filp); - file_info = (struct smb2_file_pos_info *)buf; current_byte_offset = le64_to_cpu(file_info->CurrentByteOffset); sector_size = inode->i_sb->s_blocksize; @@ -5675,12 +5697,11 @@ static int set_file_position_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_mode_info(struct ksmbd_file *fp, char *buf) +static int set_file_mode_info(struct ksmbd_file *fp, + struct smb2_file_mode_info *file_info) { - struct smb2_file_mode_info *file_info; __le32 mode; - file_info = (struct smb2_file_mode_info *)buf; mode = file_info->Mode; if ((mode & ~FILE_MODE_INFO_MASK) || @@ -5710,40 +5731,74 @@ static int set_file_mode_info(struct ksmbd_file *fp, char *buf) * TODO: need to implement an error handling for STATUS_INFO_LENGTH_MISMATCH */ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, - int info_class, char *buf, + struct smb2_set_info_req *req, struct ksmbd_share_config *share) { - switch (info_class) { + unsigned int buf_len = le32_to_cpu(req->BufferLength); + + switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: - return set_file_basic_info(fp, buf, share); + { + if (buf_len < sizeof(struct smb2_file_basic_info)) + return -EINVAL; + return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + } case FILE_ALLOCATION_INFORMATION: - return set_file_allocation_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_alloc_info)) + return -EINVAL; + return set_file_allocation_info(work, fp, + (struct smb2_file_alloc_info *)req->Buffer); + } case FILE_END_OF_FILE_INFORMATION: - return set_end_of_file_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_eof_info)) + return -EINVAL; + return set_end_of_file_info(work, fp, + (struct smb2_file_eof_info *)req->Buffer); + } case FILE_RENAME_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_rename_info(work, fp, buf); + if (buf_len < sizeof(struct smb2_file_rename_info)) + return -EINVAL; + + return set_rename_info(work, fp, + (struct smb2_file_rename_info *)req->Buffer, + buf_len); + } case FILE_LINK_INFORMATION: - return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)buf, fp->filp, - work->sess->conn->local_nls); + { + if (buf_len < sizeof(struct smb2_file_link_info)) + return -EINVAL; + return smb2_create_link(work, work->tcon->share_conf, + (struct smb2_file_link_info *)req->Buffer, + buf_len, fp->filp, + work->sess->conn->local_nls); + } case FILE_DISPOSITION_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_file_disposition_info(fp, buf); + if (buf_len < sizeof(struct smb2_file_disposition_info)) + return -EINVAL; + + return set_file_disposition_info(fp, + (struct smb2_file_disposition_info *)req->Buffer); + } case FILE_FULL_EA_INFORMATION: { if (!(fp->daccess & FILE_WRITE_EA_LE)) { @@ -5752,18 +5807,29 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } - return smb2_set_ea((struct smb2_ea_info *)buf, - &fp->filp->f_path); - } + if (buf_len < sizeof(struct smb2_ea_info)) + return -EINVAL; + return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + buf_len, &fp->filp->f_path); + } case FILE_POSITION_INFORMATION: - return set_file_position_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_pos_info)) + return -EINVAL; + return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + } case FILE_MODE_INFORMATION: - return set_file_mode_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_mode_info)) + return -EINVAL; + + return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + } } - pr_err("Unimplemented Fileinfoclass :%d\n", info_class); + pr_err("Unimplemented Fileinfoclass :%d\n", req->FileInfoClass); return -EOPNOTSUPP; } @@ -5824,8 +5890,7 @@ int smb2_set_info(struct ksmbd_work *work) switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); - rc = smb2_set_info_file(work, fp, req->FileInfoClass, - req->Buffer, work->tcon->share_conf); + rc = smb2_set_info_file(work, fp, req, work->tcon->share_conf); break; case SMB2_O_INFO_SECURITY: ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n"); From 442ff9ebeb0129e90483356f3d79c732e632a7a6 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 29 Sep 2021 15:44:32 +0900 Subject: [PATCH 833/866] ksmbd: add validation in smb2 negotiate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch add validation to check request buffer check in smb2 negotiate and fix null pointer deferencing oops in smb3_preauth_hash_rsp() that found from manual test. Cc: Tom Talpey Cc: Ronnie Sahlberg Cc: Ralph Böhme Cc: Hyunchul Lee Cc: Sergey Senozhatsky Reviewed-by: Ralph Boehme Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 42 +++++++++++++++++++++++++++++++++++++++++- fs/ksmbd/smb_common.c | 32 +++++++++++++++++++++++++++----- 2 files changed, 68 insertions(+), 6 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 0d915554f532..40882fd47feb 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1067,6 +1067,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) struct smb2_negotiate_req *req = work->request_buf; struct smb2_negotiate_rsp *rsp = work->response_buf; int rc = 0; + unsigned int smb2_buf_len, smb2_neg_size; __le32 status; ksmbd_debug(SMB, "Received negotiate request\n"); @@ -1084,6 +1085,44 @@ int smb2_handle_negotiate(struct ksmbd_work *work) goto err_out; } + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4; + if (smb2_neg_size > smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (conn->dialect == SMB311_PROT_ID) { + unsigned int nego_ctxt_off = le32_to_cpu(req->NegotiateContextOffset); + + if (smb2_buf_len < nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size > nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } else { + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } + conn->cli_cap = le32_to_cpu(req->Capabilities); switch (conn->dialect) { case SMB311_PROT_ID: @@ -8244,7 +8283,8 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE) + if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && + conn->preauth_info) ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, conn->preauth_info->Preauth_HashValue); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 5901b2884c60..db8042a173d0 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -169,10 +169,12 @@ static bool supported_protocol(int idx) idx <= server_conf.max_protocol); } -static char *next_dialect(char *dialect, int *next_off) +static char *next_dialect(char *dialect, int *next_off, int bcount) { dialect = dialect + *next_off; - *next_off = strlen(dialect); + *next_off = strnlen(dialect, bcount); + if (dialect[*next_off] != '\0') + return NULL; return dialect; } @@ -187,7 +189,9 @@ static int ksmbd_lookup_dialect_by_name(char *cli_dialects, __le16 byte_count) dialect = cli_dialects; bcount = le16_to_cpu(byte_count); do { - dialect = next_dialect(dialect, &next); + dialect = next_dialect(dialect, &next, bcount); + if (!dialect) + break; ksmbd_debug(SMB, "client requested dialect %s\n", dialect); if (!strcmp(dialect, smb1_protos[i].name)) { @@ -235,13 +239,22 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { - __le32 proto; + int smb_buf_length = get_rfc1002_len(buf); + __le32 proto = ((struct smb2_hdr *)buf)->ProtocolId; - proto = ((struct smb2_hdr *)buf)->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; + int smb2_neg_size = + offsetof(struct smb2_negotiate_req, Dialects) - 4; req = (struct smb2_negotiate_req *)buf; + if (smb2_neg_size > smb_buf_length) + goto err_out; + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb_buf_length) + goto err_out; + return ksmbd_lookup_dialect_by_id(req->Dialects, req->DialectCount); } @@ -251,10 +264,19 @@ static int ksmbd_negotiate_smb_dialect(void *buf) struct smb_negotiate_req *req; req = (struct smb_negotiate_req *)buf; + if (le16_to_cpu(req->ByteCount) < 2) + goto err_out; + + if (offsetof(struct smb_negotiate_req, DialectsArray) - 4 + + le16_to_cpu(req->ByteCount) > smb_buf_length) { + goto err_out; + } + return ksmbd_lookup_dialect_by_name(req->DialectsArray, req->ByteCount); } +err_out: return BAD_PROT_ID; } From 8f77150c15f87796570125a43509f9a81a3d9e49 Mon Sep 17 00:00:00 2001 From: Hyunchul Lee Date: Fri, 24 Sep 2021 22:22:22 +0900 Subject: [PATCH 834/866] ksmbd: add buffer validation for SMB2_CREATE_CONTEXT Add buffer validation for SMB2_CREATE_CONTEXT. Cc: Ronnie Sahlberg Reviewed-by: Ralph Boehme Signed-off-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/oplock.c | 41 +++++++++++++++++++++++++++++++---------- fs/ksmbd/smb2pdu.c | 25 ++++++++++++++++++++++++- fs/ksmbd/smbacl.c | 21 +++++++++++++++++++-- 3 files changed, 74 insertions(+), 13 deletions(-) diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 16b6236d1bd2..f9dae6ef2115 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1451,26 +1451,47 @@ struct lease_ctx_info *parse_lease_state(void *open_req) */ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) { - char *data_offset; struct create_context *cc; unsigned int next = 0; char *name; struct smb2_create_req *req = (struct smb2_create_req *)open_req; + unsigned int remain_len, name_off, name_len, value_off, value_len, + cc_len; - data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset); - cc = (struct create_context *)data_offset; + /* + * CreateContextsOffset and CreateContextsLength are guaranteed to + * be valid because of ksmbd_smb2_check_message(). + */ + cc = (struct create_context *)((char *)req + 4 + + le32_to_cpu(req->CreateContextsOffset)); + remain_len = le32_to_cpu(req->CreateContextsLength); do { - int val; - cc = (struct create_context *)((char *)cc + next); - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - val = le16_to_cpu(cc->NameLength); - if (val < 4) + if (remain_len < offsetof(struct create_context, Buffer)) return ERR_PTR(-EINVAL); - if (memcmp(name, tag, val) == 0) - return cc; next = le32_to_cpu(cc->Next); + name_off = le16_to_cpu(cc->NameOffset); + name_len = le16_to_cpu(cc->NameLength); + value_off = le16_to_cpu(cc->DataOffset); + value_len = le32_to_cpu(cc->DataLength); + cc_len = next ? next : remain_len; + + if ((next & 0x7) != 0 || + next > remain_len || + name_off != offsetof(struct create_context, Buffer) || + name_len < 4 || + name_off + name_len > cc_len || + (value_off & 0x7) != 0 || + (value_off && (value_off < name_off + name_len)) || + ((u64)value_off + value_len > cc_len)) + return ERR_PTR(-EINVAL); + + name = (char *)cc + name_off; + if (memcmp(name, tag, name_len) == 0) + return cc; + + remain_len -= next; } while (next != 0); return NULL; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 40882fd47feb..99c6349a44fa 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2427,6 +2427,10 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, ksmbd_debug(SMB, "Set ACLs using SMB2_CREATE_SD_BUFFER context\n"); sd_buf = (struct create_sd_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_sd_buf_req)) + return -EINVAL; return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd, le32_to_cpu(sd_buf->ccontext.DataLength), true); } @@ -2621,6 +2625,12 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } else if (context) { ea_buf = (struct create_ea_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_ea_buf_req)) { + rc = -EINVAL; + goto err_out1; + } if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) { rsp->hdr.Status = STATUS_ACCESS_DENIED; rc = -EACCES; @@ -2659,6 +2669,12 @@ int smb2_open(struct ksmbd_work *work) } else if (context) { struct create_posix *posix = (struct create_posix *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_posix)) { + rc = -EINVAL; + goto err_out1; + } ksmbd_debug(SMB, "get posix context\n"); posix_mode = le32_to_cpu(posix->Mode); @@ -3049,9 +3065,16 @@ int smb2_open(struct ksmbd_work *work) rc = PTR_ERR(az_req); goto err_out; } else if (az_req) { - loff_t alloc_size = le64_to_cpu(az_req->AllocationSize); + loff_t alloc_size; int err; + if (le16_to_cpu(az_req->ccontext.DataOffset) + + le32_to_cpu(az_req->ccontext.DataLength) < + sizeof(struct create_alloc_size_req)) { + rc = -EINVAL; + goto err_out; + } + alloc_size = le64_to_cpu(az_req->AllocationSize); ksmbd_debug(SMB, "request smb2 create allocate size : %llu\n", alloc_size); diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 0a95cdec8c80..bd792db32623 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -380,7 +380,7 @@ static void parse_dacl(struct user_namespace *user_ns, { int i, ret; int num_aces = 0; - int acl_size; + unsigned int acl_size; char *acl_base; struct smb_ace **ppace; struct posix_acl_entry *cf_pace, *cf_pdace; @@ -392,7 +392,7 @@ static void parse_dacl(struct user_namespace *user_ns, return; /* validate that we do not go past end of acl */ - if (end_of_acl <= (char *)pdacl || + if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); return; @@ -431,8 +431,22 @@ static void parse_dacl(struct user_namespace *user_ns, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { + if (end_of_acl - acl_base < acl_size) + break; + ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; + acl_size = offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth); + + if (end_of_acl - acl_base < acl_size || + ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + (end_of_acl - acl_base < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || + (le16_to_cpu(ppace[i]->size) < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) + break; + acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = smb_map_generic_desired_access(ppace[i]->access_req); @@ -807,6 +821,9 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, if (!pntsd) return -EIO; + if (acl_len < sizeof(struct smb_ntsd)) + return -EINVAL; + owner_sid_ptr = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); group_sid_ptr = (struct smb_sid *)((char *)pntsd + From 4227f811cdeb4d85db91ea6b9adf9ac049cec12e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 29 Sep 2021 19:52:51 +0900 Subject: [PATCH 835/866] ksmbd: fix transform header validation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Validate that the transform and smb request headers are present before checking OriginalMessageSize and SessionId fields. Cc: Ronnie Sahlberg Cc: Ralph Böhme Cc: Sergey Senozhatsky Reviewed-by: Tom Talpey Acked-by: Hyunchul Lee Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 99c6349a44fa..dcf907738610 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -8414,16 +8414,8 @@ int smb3_decrypt_req(struct ksmbd_work *work) unsigned int buf_data_size = pdu_length + 4 - sizeof(struct smb2_transform_hdr); struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; - unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize); int rc = 0; - sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); - if (!sess) { - pr_err("invalid session id(%llx) in transform header\n", - le64_to_cpu(tr_hdr->SessionId)); - return -ECONNABORTED; - } - if (pdu_length + 4 < sizeof(struct smb2_transform_hdr) + sizeof(struct smb2_hdr)) { pr_err("Transform message is too small (%u)\n", @@ -8431,11 +8423,19 @@ int smb3_decrypt_req(struct ksmbd_work *work) return -ECONNABORTED; } - if (pdu_length + 4 < orig_len + sizeof(struct smb2_transform_hdr)) { + if (pdu_length + 4 < + le32_to_cpu(tr_hdr->OriginalMessageSize) + sizeof(struct smb2_transform_hdr)) { pr_err("Transform message is broken\n"); return -ECONNABORTED; } + sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); + if (!sess) { + pr_err("invalid session id(%llx) in transform header\n", + le64_to_cpu(tr_hdr->SessionId)); + return -ECONNABORTED; + } + iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr); iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); From 87ffb310d5e8a441721a9d04dfa7c90cd9da3916 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 30 Sep 2021 15:24:56 +0300 Subject: [PATCH 836/866] ksmbd: missing check for NULL in convert_to_nt_pathname() The kmalloc() does not have a NULL check. This code can be re-written slightly cleaner to just use the kstrdup(). Fixes: 265fd1991c1d ("ksmbd: use LOOKUP_BENEATH to prevent the out of share access") Signed-off-by: Dan Carpenter Acked-by: Namjae Jeon Acked-by: Hyunchul Lee Signed-off-by: Steve French --- fs/ksmbd/misc.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 6a19f4bc692d..60e7ac62c917 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -162,17 +162,14 @@ char *convert_to_nt_pathname(char *filename) { char *ab_pathname; - if (strlen(filename) == 0) { - ab_pathname = kmalloc(2, GFP_KERNEL); - ab_pathname[0] = '\\'; - ab_pathname[1] = '\0'; - } else { - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + if (strlen(filename) == 0) + filename = "\\"; - ksmbd_conv_path_to_windows(ab_pathname); - } + ab_pathname = kstrdup(filename, GFP_KERNEL); + if (!ab_pathname) + return NULL; + + ksmbd_conv_path_to_windows(ab_pathname); return ab_pathname; } From a2c2f0826e2b75560b31daf1cd9a755ab93cf4c6 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 20 Aug 2021 12:45:05 +0800 Subject: [PATCH 837/866] ext4: limit the number of blocks in one ADD_RANGE TLV Now EXT4_FC_TAG_ADD_RANGE uses ext4_extent to track the newly-added blocks, but the limit on the max value of ee_len field is ignored, and it can lead to BUG_ON as shown below when running command "fallocate -l 128M file" on a fast_commit-enabled fs: kernel BUG at fs/ext4/ext4_extents.h:199! invalid opcode: 0000 [#1] SMP PTI CPU: 3 PID: 624 Comm: fallocate Not tainted 5.14.0-rc6+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:ext4_fc_write_inode_data+0x1f3/0x200 Call Trace: ? ext4_fc_write_inode+0xf2/0x150 ext4_fc_commit+0x93b/0xa00 ? ext4_fallocate+0x1ad/0x10d0 ext4_sync_file+0x157/0x340 ? ext4_sync_file+0x157/0x340 vfs_fsync_range+0x49/0x80 do_fsync+0x3d/0x70 __x64_sys_fsync+0x14/0x20 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae Simply fixing it by limiting the number of blocks in one EXT4_FC_TAG_ADD_RANGE TLV. Fixes: aa75f4d3daae ("ext4: main fast-commit commit path") Cc: stable@kernel.org Signed-off-by: Hou Tao Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210820044505.474318-1-houtao1@huawei.com --- fs/ext4/fast_commit.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8e610a381862..8ea5a81e6554 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -892,6 +892,12 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) sizeof(lrange), (u8 *)&lrange, crc)) return -ENOSPC; } else { + unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ? + EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN; + + /* Limit the number of blocks in one extent */ + map.m_len = min(max, map.m_len); + fc_ext.fc_ino = cpu_to_le32(inode->i_ino); ex = (struct ext4_extent *)&fc_ext.fc_ex; ex->ee_block = cpu_to_le32(map.m_lblk); From 6fed83957f21eff11c8496e9f24253b03d2bc1dc Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 23 Aug 2021 14:13:58 +0800 Subject: [PATCH 838/866] ext4: fix reserved space counter leakage When ext4_insert_delayed block receives and recovers from an error from ext4_es_insert_delayed_block(), e.g., ENOMEM, it does not release the space it has reserved for that block insertion as it should. One effect of this bug is that s_dirtyclusters_counter is not decremented and remains incorrectly elevated until the file system has been unmounted. This can result in premature ENOSPC returns and apparent loss of free space. Another effect of this bug is that /sys/fs/ext4//delayed_allocation_blocks can remain non-zero even after syncfs has been executed on the filesystem. Besides, add check for s_dirtyclusters_counter when inode is going to be evicted and freed. s_dirtyclusters_counter can still keep non-zero until inode is written back in .evict_inode(), and thus the check is delayed to .destroy_inode(). Fixes: 51865fda28e5 ("ext4: let ext4 maintain extent status tree") Cc: stable@kernel.org Suggested-by: Gao Xiang Signed-off-by: Jeffle Xu Reviewed-by: Eric Whitney Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210823061358.84473-1-jefflexu@linux.alibaba.com --- fs/ext4/inode.c | 5 +++++ fs/ext4/super.c | 6 ++++++ 2 files changed, 11 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2a076d236ba1..9df1ab070fa5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1628,6 +1628,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; bool allocated = false; + bool reserved = false; /* * If the cluster containing lblk is shared with a delayed, @@ -1644,6 +1645,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { /* bigalloc */ if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) { if (!ext4_es_scan_clu(inode, @@ -1656,6 +1658,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { allocated = true; } @@ -1666,6 +1669,8 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) } ret = ext4_es_insert_delayed_block(inode, lblk, allocated); + if (ret && reserved) + ext4_da_release_space(inode, 1); errout: return ret; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index feca816b6bf3..a52f1572daa5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1352,6 +1352,12 @@ static void ext4_destroy_inode(struct inode *inode) true); dump_stack(); } + + if (EXT4_I(inode)->i_reserved_data_blocks) + ext4_msg(inode->i_sb, KERN_ERR, + "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", + inode->i_ino, EXT4_I(inode), + EXT4_I(inode)->i_reserved_data_blocks); } static void init_once(void *foo) From 75ca6ad408f459f00b09a64f04c774559848c097 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 5 Jun 2021 10:39:32 +0530 Subject: [PATCH 839/866] ext4: fix loff_t overflow in ext4_max_bitmap_size() We should use unsigned long long rather than loff_t to avoid overflow in ext4_max_bitmap_size() for comparison before returning. w/o this patch sbi->s_bitmap_maxbytes was becoming a negative value due to overflow of upper_limit (with has_huge_files as true) Below is a quick test to trigger it on a 64KB pagesize system. sudo mkfs.ext4 -b 65536 -O ^has_extents,^64bit /dev/loop2 sudo mount /dev/loop2 /mnt sudo echo "hello" > /mnt/hello -> This will error out with "echo: write error: File too large" Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Cc: stable@kernel.org Link: https://lore.kernel.org/r/594f409e2c543e90fd836b78188dfa5c575065ba.1622867594.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a52f1572daa5..9b5b2f63b470 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3030,17 +3030,17 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { - loff_t res = EXT4_NDIR_BLOCKS; + unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; - /* This is calculated to be the largest file size for a dense, block + + /* + * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ - if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field @@ -3083,7 +3083,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; - return res; + return (loff_t)res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, From bb9464e08309f6befe80866f5be51778ca355ee9 Mon Sep 17 00:00:00 2001 From: yangerkun Date: Fri, 24 Sep 2021 17:39:17 +0800 Subject: [PATCH 840/866] ext4: flush s_error_work before journal destroy in ext4_fill_super The error path in ext4_fill_super forget to flush s_error_work before journal destroy, and it may trigger the follow bug since flush_stashed_error_work can run concurrently with journal destroy without any protection for sbi->s_journal. [32031.740193] EXT4-fs (loop66): get root inode failed [32031.740484] EXT4-fs (loop66): mount failed [32031.759805] ------------[ cut here ]------------ [32031.759807] kernel BUG at fs/jbd2/transaction.c:373! [32031.760075] invalid opcode: 0000 [#1] SMP PTI [32031.760336] CPU: 5 PID: 1029268 Comm: kworker/5:1 Kdump: loaded 4.18.0 [32031.765112] Call Trace: [32031.765375] ? __switch_to_asm+0x35/0x70 [32031.765635] ? __switch_to_asm+0x41/0x70 [32031.765893] ? __switch_to_asm+0x35/0x70 [32031.766148] ? __switch_to_asm+0x41/0x70 [32031.766405] ? _cond_resched+0x15/0x40 [32031.766665] jbd2__journal_start+0xf1/0x1f0 [jbd2] [32031.766934] jbd2_journal_start+0x19/0x20 [jbd2] [32031.767218] flush_stashed_error_work+0x30/0x90 [ext4] [32031.767487] process_one_work+0x195/0x390 [32031.767747] worker_thread+0x30/0x390 [32031.768007] ? process_one_work+0x390/0x390 [32031.768265] kthread+0x10d/0x130 [32031.768521] ? kthread_flush_work_fn+0x10/0x10 [32031.768778] ret_from_fork+0x35/0x40 static int start_this_handle(...) BUG_ON(journal->j_flags & JBD2_UNMOUNT); <---- Trigger this Besides, after we enable fast commit, ext4_fc_replay can add work to s_error_work but return success, so the latter journal destroy in ext4_load_journal can trigger this problem too. Fix this problem with two steps: 1. Call ext4_commit_super directly in ext4_handle_error for the case that called from ext4_fc_replay 2. Since it's hard to pair the init and flush for s_error_work, we'd better add a extras flush_work before journal destroy in ext4_fill_super Besides, this patch will call ext4_commit_super in ext4_handle_error for any nojournal case too. But it seems safe since the reason we call schedule_work was that we should save error info to sb through journal if available. Conversely, for the nojournal case, it seems useless delay commit superblock to s_error_work. Fixes: c92dc856848f ("ext4: defer saving error info from atomic context") Fixes: 2d01ddc86606 ("ext4: save error info to sb through journal if available") Cc: stable@kernel.org Signed-off-by: yangerkun Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210924093917.1953239-1-yangerkun@huawei.com --- fs/ext4/super.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9b5b2f63b470..0049eac9de1a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -660,7 +660,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. */ - if (continue_fs) + if (continue_fs && journal) schedule_work(&EXT4_SB(sb)->s_error_work); else ext4_commit_super(sb); @@ -5050,12 +5050,15 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { + /* flush s_error_work before journal destroy. */ + flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: + /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); From 42cb447410d024e9d54139ae9c21ea132a8c384c Mon Sep 17 00:00:00 2001 From: yangerkun Date: Tue, 14 Sep 2021 19:14:15 +0800 Subject: [PATCH 841/866] ext4: fix potential infinite loop in ext4_dx_readdir() When ext4_htree_fill_tree() fails, ext4_dx_readdir() can run into an infinite loop since if info->last_pos != ctx->pos this will reset the directory scan and reread the failing entry. For example: 1. a dx_dir which has 3 block, block 0 as dx_root block, block 1/2 as leaf block which own the ext4_dir_entry_2 2. block 1 read ok and call_filldir which will fill the dirent and update the ctx->pos 3. block 2 read fail, but we has already fill some dirent, so we will return back to userspace will a positive return val(see ksys_getdents64) 4. the second ext4_dx_readdir will reset the world since info->last_pos != ctx->pos, and will also init the curr_hash which pos to block 1 5. So we will read block1 too, and once block2 still read fail, we can only fill one dirent because the hash of the entry in block1(besides the last one) won't greater than curr_hash 6. this time, we forget update last_pos too since the read for block2 will fail, and since we has got the one entry, ksys_getdents64 can return success 7. Latter we will trapped in a loop with step 4~6 Cc: stable@kernel.org Signed-off-by: yangerkun Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210914111415.3921954-1-yangerkun@huawei.com --- fs/ext4/dir.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ffb295aa891c..74b172a4adda 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -551,7 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; - int ret; + int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); @@ -599,7 +599,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) info->curr_minor_hash, &info->next_hash); if (ret < 0) - return ret; + goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; @@ -630,7 +630,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) } finished: info->last_pos = ctx->pos; - return 0; + return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) From f2c77973507fd116c3657df1dc048864a2b16a1c Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Fri, 10 Sep 2021 16:03:16 +0800 Subject: [PATCH 842/866] ext4: recheck buffer uptodate bit under buffer lock Commit 8e33fadf945a ("ext4: remove an unnecessary if statement in __ext4_get_inode_loc()") forget to recheck buffer's uptodate bit again under buffer lock, which may overwrite the buffer if someone else have already brought it uptodate and changed it. Fixes: 8e33fadf945a ("ext4: remove an unnecessary if statement in __ext4_get_inode_loc()") Cc: stable@kernel.org Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o Link: https://lore.kernel.org/r/20210910080316.70421-1-yi.zhang@huawei.com --- fs/ext4/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9df1ab070fa5..b7c561ad38dd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4277,6 +4277,12 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, goto has_buffer; lock_buffer(bh); + if (ext4_buffer_uptodate(bh)) { + /* Someone brought it uptodate while we waited */ + unlock_buffer(bh); + goto has_buffer; + } + /* * If we have all information of the inode in memory and this * is the only valid inode in the block, we need not read the From 24ff652573754fe4c03213ebd26b17e86842feb3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 30 Sep 2021 12:43:10 +0200 Subject: [PATCH 843/866] objtool: Teach get_alt_entry() about more relocation types Occasionally objtool encounters symbol (as opposed to section) relocations in .altinstructions. Typically they are the alternatives written by elf_add_alternative() as encountered on a noinstr validation run on vmlinux after having already ran objtool on the individual .o files. Basically this is the counterpart of commit 44f6a7c0755d ("objtool: Fix seg fault with Clang non-section symbols"), because when these new assemblers (binutils now also does this) strip the section symbols, elf_add_reloc_to_insn() is forced to emit symbol based relocations. As such, teach get_alt_entry() about different relocation types. Fixes: 9bc0bb50727c ("objtool/x86: Rewrite retpoline thunk calls") Reported-by: Stephen Rothwell Reported-by: Borislav Petkov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Tested-by: Nathan Chancellor Link: https://lore.kernel.org/r/YVWUvknIEVNkPvnP@hirez.programming.kicks-ass.net --- tools/objtool/special.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bc925cf19e2d..f58ecc50fb10 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,6 +58,24 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } +static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +{ + switch (reloc->sym->type) { + case STT_FUNC: + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; + return true; + + case STT_SECTION: + *sec = reloc->sym->sec; + *off = reloc->addend; + return true; + + default: + return false; + } +} + static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) @@ -91,15 +109,12 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_reloc->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section reloc symbol %s", + if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { + WARN_FUNC("don't know how to handle reloc symbol type: %s", sec, offset + entry->orig, orig_reloc->sym->name); return -1; } - alt->orig_sec = orig_reloc->sym->sec; - alt->orig_off = orig_reloc->addend; - if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); if (!new_reloc) { @@ -116,8 +131,11 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1; - alt->new_sec = new_reloc->sym->sec; - alt->new_off = (unsigned int)new_reloc->addend; + if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { + WARN_FUNC("don't know how to handle reloc symbol type: %s", + sec, offset + entry->new, new_reloc->sym->name); + return -1; + } /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) From 02d029a41dc986e2d5a77ecca45803857b346829 Mon Sep 17 00:00:00 2001 From: Anand K Mistry Date: Wed, 29 Sep 2021 17:04:21 +1000 Subject: [PATCH 844/866] perf/x86: Reset destroy callback on event init failure perf_init_event tries multiple init callbacks and does not reset the event state between tries. When x86_pmu_event_init runs, it unconditionally sets the destroy callback to hw_perf_event_destroy. On the next init attempt after x86_pmu_event_init, in perf_try_init_event, if the pmu's capabilities includes PERF_PMU_CAP_NO_EXCLUDE, the destroy callback will be run. However, if the next init didn't set the destroy callback, hw_perf_event_destroy will be run (since the callback wasn't reset). Looking at other pmu init functions, the common pattern is to only set the destroy callback on a successful init. Resetting the callback on failure tries to replicate that pattern. This was discovered after commit f11dd0d80555 ("perf/x86/amd/ibs: Extend PERF_PMU_CAP_NO_EXCLUDE to IBS Op") when the second (and only second) run of the perf tool after a reboot results in 0 samples being generated. The extra run of hw_perf_event_destroy results in active_events having an extra decrement on each perf run. The second run has active_events == 0 and every subsequent run has active_events < 0. When active_events == 0, the NMI handler will early-out and not record any samples. Signed-off-by: Anand K Mistry Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210929170405.1.I078b98ee7727f9ae9d6df8262bad7e325e40faf0@changeid --- arch/x86/events/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..6dfa8ddaa60f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); + event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && From ecc2123e09f9e71ddc6c53d71e283b8ada685fe2 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 28 Sep 2021 08:19:03 -0700 Subject: [PATCH 845/866] perf/x86/intel: Update event constraints for ICX According to the latest event list, the event encoding 0xEF is only available on the first 4 counters. Add it into the event constraints table. Fixes: 6017608936c1 ("perf/x86/intel: Add Icelake support") Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1632842343-25862-1-git-send-email-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..9a044438072b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT(0xef, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), EVENT_CONSTRAINT_END }; From f792565326825ed806626da50c6f9a928f1079c1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 29 Sep 2021 12:43:13 -0700 Subject: [PATCH 846/866] perf/core: fix userpage->time_enabled of inactive events Users of rdpmc rely on the mmapped user page to calculate accurate time_enabled. Currently, userpage->time_enabled is only updated when the event is added to the pmu. As a result, inactive event (due to counter multiplexing) does not have accurate userpage->time_enabled. This can be reproduced with something like: /* open 20 task perf_event "cycles", to create multiplexing */ fd = perf_event_open(); /* open task perf_event "cycles" */ userpage = mmap(fd); /* use mmap and rdmpc */ while (true) { time_enabled_mmap = xxx; /* use logic in perf_event_mmap_page */ time_enabled_read = read(fd).time_enabled; if (time_enabled_mmap > time_enabled_read) BUG(); } Fix this by updating userpage for inactive events in merge_sched_in. Suggested-by: Peter Zijlstra (Intel) Reported-and-tested-by: Lucian Grijincu Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210929194313.2398474-1-songliubraving@fb.com --- include/linux/perf_event.h | 4 +++- kernel/events/core.c | 34 ++++++++++++++++++++++++++++++---- 2 files changed, 33 insertions(+), 5 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe156a8170aa..9b60bb89d86a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -683,7 +683,9 @@ struct perf_event { /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in. + * context time as it was when the event was last scheduled in, + * or when ctx_sched_in failed to schedule the event because we + * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). diff --git a/kernel/events/core.c b/kernel/events/core.c index 0c000cb01eeb..f23ca260307f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +static inline bool event_update_userpage(struct perf_event *event) +{ + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +} + +static inline void group_update_userpage(struct perf_event *group_event) +{ + struct perf_event *event; + + if (!event_update_userpage(group_event)) + return; + + for_each_sibling_event(event, group_event) + event_update_userpage(event); +} + static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; @@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { + *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } else { + ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); + group_update_userpage(event); } - - *can_add_hw = 0; - ctx->rotate_necessary = 1; - perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6324,6 +6348,8 @@ accounting: ring_buffer_attach(event, rb); + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { From 2630cde26711dab0d0b56a8be1616475be646d13 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Koutn=C3=BD?= Date: Fri, 17 Sep 2021 17:30:37 +0200 Subject: [PATCH 847/866] sched/fair: Add ancestors of unthrottled undecayed cfs_rq MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit a7b359fc6a37 ("sched/fair: Correctly insert cfs_rq's to list on unthrottle") we add cfs_rqs with no runnable tasks but not fully decayed into the load (leaf) list. We may ignore adding some ancestors and therefore breaking tmp_alone_branch invariant. This broke LTP test cfs_bandwidth01 and it was partially fixed in commit fdaba61ef8a2 ("sched/fair: Ensure that the CFS parent is added after unthrottling"). I noticed the named test still fails even with the fix (but with low probability, 1 in ~1000 executions of the test). The reason is when bailing out of unthrottle_cfs_rq early, we may miss adding ancestors of the unthrottled cfs_rq, thus, not joining tmp_alone_branch properly. Fix this by adding ancestors if we notice the unthrottled cfs_rq was added to the load list. Fixes: a7b359fc6a37 ("sched/fair: Correctly insert cfs_rq's to list on unthrottle") Signed-off-by: Michal Koutný Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vincent Guittot Reviewed-by: Odin Ugedal Link: https://lore.kernel.org/r/20210917153037.11176-1-mkoutny@suse.com --- kernel/sched/fair.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ff69f245b939..f6a05d9b5443 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - if (!cfs_rq->load.weight) + /* Nothing to run but something to decay (on_list)? Complete the branch */ + if (!cfs_rq->load.weight) { + if (cfs_rq->on_list) + goto unthrottle_throttle; return; + } task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; From 703066188f63d66cc6b9d678e5b5ef1213c5938e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 27 Sep 2021 12:46:35 +0100 Subject: [PATCH 848/866] sched/fair: Null terminate buffer when updating tunable_scaling This patch null-terminates the temporary buffer in sched_scaling_write() so kstrtouint() does not return failure and checks the value is valid. Before: $ cat /sys/kernel/debug/sched/tunable_scaling 1 $ echo 0 > /sys/kernel/debug/sched/tunable_scaling -bash: echo: write error: Invalid argument $ cat /sys/kernel/debug/sched/tunable_scaling 1 After: $ cat /sys/kernel/debug/sched/tunable_scaling 1 $ echo 0 > /sys/kernel/debug/sched/tunable_scaling $ cat /sys/kernel/debug/sched/tunable_scaling 0 $ echo 3 > /sys/kernel/debug/sched/tunable_scaling -bash: echo: write error: Invalid argument Fixes: 8a99b6833c88 ("sched: Move SCHED_DEBUG sysctl to debugfs") Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Acked-by: Vincent Guittot Link: https://lore.kernel.org/r/20210927114635.GH3959@techsingularity.net --- kernel/sched/debug.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 49716228efb4..17a653b67006 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[16]; + unsigned int scaling; if (cnt > 15) cnt = 15; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; - if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling)) + if (kstrtouint(buf, 10, &scaling)) return -EINVAL; + if (scaling >= SCHED_TUNABLESCALING_END) + return -EINVAL; + + sysctl_sched_tunable_scaling = scaling; if (sched_update_scaling()) return -EINVAL; From 83d40a61046f73103b4e5d8f1310261487ff63b0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 20 Sep 2021 15:31:11 +0200 Subject: [PATCH 849/866] sched: Always inline is_percpu_thread() vmlinux.o: warning: objtool: check_preemption_disabled()+0x81: call to is_percpu_thread() leaves .noinstr.text section Reported-by: Stephen Rothwell Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210928084218.063371959@infradead.org --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 39039ce8ac4c..c1a927ddec64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1720,7 +1720,7 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -static inline bool is_percpu_thread(void) +static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && From 3f008385d46d3cea4a097d2615cd485f2184ba26 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 1 Oct 2021 10:39:33 +0100 Subject: [PATCH 850/866] io_uring: kill fasync We have never supported fasync properly, it would only fire when there is something polling io_uring making it useless. The original support came in through the initial io_uring merge for 5.1. Since it's broken and nobody has reported it, get rid of the fasync bits. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/2f7ca3d344d406d34fa6713824198915c41cea86.1633080236.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 82f867983bb3..6b9e70208782 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -403,7 +403,6 @@ struct io_ring_ctx { struct wait_queue_head cq_wait; unsigned cq_extra; atomic_t cq_timeouts; - struct fasync_struct *cq_fasync; unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; @@ -1614,10 +1613,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) @@ -1631,10 +1628,8 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) } if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } /* Returns true if there are no backlogged entries after the flush */ @@ -9345,13 +9340,6 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) return mask; } -static int io_uring_fasync(int fd, struct file *file, int on) -{ - struct io_ring_ctx *ctx = file->private_data; - - return fasync_helper(fd, file, on, &ctx->cq_fasync); -} - static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { const struct cred *creds; @@ -10145,7 +10133,6 @@ static const struct file_operations io_uring_fops = { .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, - .fasync = io_uring_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif From f5b667ded07569dd6e33885cffd35fd519cfc942 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 1 Oct 2021 19:14:28 +0200 Subject: [PATCH 851/866] thermal: Update information in MAINTAINERS Because Rui is now going to focus on work that is not related to the maintenance of the thermal subsystem in the kernel, Rafael will start to help Daniel with handling the development process as a new member of the thermal maintainers team. Rui will continue to review patches in that area. The thermal development process flow will change so that the material from the thermal git tree will be merged into the thermal branch of the linux-pm.git tree before going into the mainline. Update the information in MAINTAINERS accordingly. Signed-off-by: Rafael J. Wysocki Acked-by: Zhang Rui Acked-by: Daniel Lezcano Signed-off-by: Linus Torvalds --- MAINTAINERS | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 76e0fdcdd877..62257ffca56a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -414,7 +414,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm F: drivers/acpi/pmic/ ACPI THERMAL DRIVER -M: Zhang Rui +M: Rafael J. Wysocki +R: Zhang Rui L: linux-acpi@vger.kernel.org S: Supported W: https://01.org/linux-acpi @@ -18549,13 +18550,14 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-raremono.c THERMAL -M: Zhang Rui +M: Rafael J. Wysocki M: Daniel Lezcano R: Amit Kucheria +R: Zhang Rui L: linux-pm@vger.kernel.org S: Supported Q: https://patchwork.kernel.org/project/linux-pm/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git thermal F: Documentation/devicetree/bindings/thermal/ F: drivers/thermal/ F: include/linux/cpu_cooling.h From ffa2600044979aff4bd6238edb9af815a47d7c32 Mon Sep 17 00:00:00 2001 From: Eddie James Date: Wed, 29 Sep 2021 10:36:04 -0500 Subject: [PATCH 852/866] hwmon: (occ) Fix P10 VRM temp sensors The P10 (temp sensor version 0x10) doesn't do the same VRM status reporting that was used on P9. It just reports the temperature, so drop the check for VRM fru type in the sysfs show function, and don't set the name to "alarm". Fixes: db4919ec86 ("hwmon: (occ) Add new temperature sensor type") Signed-off-by: Eddie James Link: https://lore.kernel.org/r/20210929153604.14968-1-eajames@linux.ibm.com Signed-off-by: Guenter Roeck --- drivers/hwmon/occ/common.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index 0d68a78be980..ae664613289c 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -340,18 +340,11 @@ static ssize_t occ_show_temp_10(struct device *dev, if (val == OCC_TEMP_SENSOR_FAULT) return -EREMOTEIO; - /* - * VRM doesn't return temperature, only alarm bit. This - * attribute maps to tempX_alarm instead of tempX_input for - * VRM - */ - if (temp->fru_type != OCC_FRU_TYPE_VRM) { - /* sensor not ready */ - if (val == 0) - return -EAGAIN; + /* sensor not ready */ + if (val == 0) + return -EAGAIN; - val *= 1000; - } + val *= 1000; break; case 2: val = temp->fru_type; @@ -886,7 +879,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) 0, i); attr++; - if (sensors->temp.version > 1 && + if (sensors->temp.version == 2 && temp->fru_type == OCC_FRU_TYPE_VRM) { snprintf(attr->name, sizeof(attr->name), "temp%d_alarm", s); From f067d5585cda2de1e47dde914a8a4f151659e0ad Mon Sep 17 00:00:00 2001 From: Brandon Wyman Date: Tue, 28 Sep 2021 20:50:51 +0000 Subject: [PATCH 853/866] hwmon: (pmbus/ibm-cffps) max_power_out swap changes The bytes for max_power_out from the ibm-cffps devices differ in byte order for some power supplies. The Witherspoon power supply returns the bytes in MSB/LSB order. The Rainier power supply returns the bytes in LSB/MSB order. The Witherspoon power supply uses version cffps1. The Rainier power supply should use version cffps2. If version is cffps1, swap the bytes before output to max_power_out. Tested: Witherspoon before: 3148. Witherspoon after: 3148. Rainier before: 53255. Rainier after: 2000. Signed-off-by: Brandon Wyman Reviewed-by: Eddie James Link: https://lore.kernel.org/r/20210928205051.1222815-1-bjwyman@gmail.com [groeck: Replaced yoda programming] Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/ibm-cffps.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/pmbus/ibm-cffps.c b/drivers/hwmon/pmbus/ibm-cffps.c index df712ce4b164..53f7d1418bc9 100644 --- a/drivers/hwmon/pmbus/ibm-cffps.c +++ b/drivers/hwmon/pmbus/ibm-cffps.c @@ -171,8 +171,14 @@ static ssize_t ibm_cffps_debugfs_read(struct file *file, char __user *buf, cmd = CFFPS_SN_CMD; break; case CFFPS_DEBUGFS_MAX_POWER_OUT: - rc = i2c_smbus_read_word_swapped(psu->client, - CFFPS_MAX_POWER_OUT_CMD); + if (psu->version == cffps1) { + rc = i2c_smbus_read_word_swapped(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } else { + rc = i2c_smbus_read_word_data(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } + if (rc < 0) return rc; From 2292e2f685cd5c65e3f47bbcf9f469513acc3195 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 27 Sep 2021 10:07:40 +0300 Subject: [PATCH 854/866] hwmon: (pmbus/mp2975) Add missed POUT attribute for page 1 mp2975 controller Add missed attribute for reading POUT from page 1. It is supported by device, but has been missed in initial commit. Fixes: 2c6fcbb21149 ("hwmon: (pmbus) Add support for MPS Multi-phase mp2975 controller") Signed-off-by: Vadim Pasternak Link: https://lore.kernel.org/r/20210927070740.2149290-1-vadimp@nvidia.com Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/mp2975.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c index eb94bd5f4e2a..51986adfbf47 100644 --- a/drivers/hwmon/pmbus/mp2975.c +++ b/drivers/hwmon/pmbus/mp2975.c @@ -54,7 +54,7 @@ #define MP2975_RAIL2_FUNC (PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | \ PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | \ - PMBUS_PHASE_VIRTUAL) + PMBUS_HAVE_POUT | PMBUS_PHASE_VIRTUAL) struct mp2975_data { struct pmbus_driver_info info; From 943c15ac1b84d378da26bba41c83c67e16499ac4 Mon Sep 17 00:00:00 2001 From: Nadezda Lutovinova Date: Tue, 21 Sep 2021 18:51:51 +0300 Subject: [PATCH 855/866] hwmon: (w83791d) Fix NULL pointer dereference by removing unnecessary structure field If driver read val value sufficient for (val & 0x08) && (!(val & 0x80)) && ((val & 0x7) == ((val >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). Cc: stable@vger.kernel.org Signed-off-by: Nadezda Lutovinova Link: https://lore.kernel.org/r/20210921155153.28098-1-lutovinova@ispras.ru [groeck: Dropped unnecessary continuation lines, fixed multi-line alignment] Signed-off-by: Guenter Roeck --- drivers/hwmon/w83791d.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c index 37b25a1474c4..3c1be2c11fdf 100644 --- a/drivers/hwmon/w83791d.c +++ b/drivers/hwmon/w83791d.c @@ -273,9 +273,6 @@ struct w83791d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - /* volts */ u8 in[NUMBER_OF_VIN]; /* Register value */ u8 in_max[NUMBER_OF_VIN]; /* Register value */ @@ -1257,7 +1254,6 @@ static const struct attribute_group w83791d_group_fanpwm45 = { static int w83791d_detect_subclients(struct i2c_client *client) { struct i2c_adapter *adapter = client->adapter; - struct w83791d_data *data = i2c_get_clientdata(client); int address = client->addr; int i, id; u8 val; @@ -1280,22 +1276,19 @@ static int w83791d_detect_subclients(struct i2c_client *client) } val = w83791d_read(client, W83791D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } From 0f36b88173f028e372668ae040ab1a496834d278 Mon Sep 17 00:00:00 2001 From: Nadezda Lutovinova Date: Tue, 21 Sep 2021 18:51:52 +0300 Subject: [PATCH 856/866] hwmon: (w83792d) Fix NULL pointer dereference by removing unnecessary structure field If driver read val value sufficient for (val & 0x08) && (!(val & 0x80)) && ((val & 0x7) == ((val >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). Cc: stable@vger.kernel.org Signed-off-by: Nadezda Lutovinova Link: https://lore.kernel.org/r/20210921155153.28098-2-lutovinova@ispras.ru [groeck: Dropped unnecessary continuation lines, fixed multipline alignment] Signed-off-by: Guenter Roeck --- drivers/hwmon/w83792d.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c index abd5c3a722b9..1f175f381350 100644 --- a/drivers/hwmon/w83792d.c +++ b/drivers/hwmon/w83792d.c @@ -264,9 +264,6 @@ struct w83792d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - u8 in[9]; /* Register value */ u8 in_max[9]; /* Register value */ u8 in_min[9]; /* Register value */ @@ -927,7 +924,6 @@ w83792d_detect_subclients(struct i2c_client *new_client) int address = new_client->addr; u8 val; struct i2c_adapter *adapter = new_client->adapter; - struct w83792d_data *data = i2c_get_clientdata(new_client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -946,21 +942,19 @@ w83792d_detect_subclients(struct i2c_client *new_client) } val = w83792d_read_value(new_client, W83792D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&new_client->dev, - "duplicate addresses 0x%x, use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&new_client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } From dd4d747ef05addab887dc8ff0d6ab9860bbcd783 Mon Sep 17 00:00:00 2001 From: Nadezda Lutovinova Date: Tue, 21 Sep 2021 18:51:53 +0300 Subject: [PATCH 857/866] hwmon: (w83793) Fix NULL pointer dereference by removing unnecessary structure field If driver read tmp value sufficient for (tmp & 0x08) && (!(tmp & 0x80)) && ((tmp & 0x7) == ((tmp >> 4) & 0x7)) from device then Null pointer dereference occurs. (It is possible if tmp = 0b0xyz1xyz, where same literals mean same numbers) Also lm75[] does not serve a purpose anymore after switching to devm_i2c_new_dummy_device() in w83791d_detect_subclients(). The patch fixes possible NULL pointer dereference by removing lm75[]. Found by Linux Driver Verification project (linuxtesting.org). Cc: stable@vger.kernel.org Signed-off-by: Nadezda Lutovinova Link: https://lore.kernel.org/r/20210921155153.28098-3-lutovinova@ispras.ru [groeck: Dropped unnecessary continuation lines, fixed multi-line alignments] Signed-off-by: Guenter Roeck --- drivers/hwmon/w83793.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index e7d0484eabe4..1d2854de1cfc 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -202,7 +202,6 @@ static inline s8 TEMP_TO_REG(long val, s8 min, s8 max) } struct w83793_data { - struct i2c_client *lm75[2]; struct device *hwmon_dev; struct mutex update_lock; char valid; /* !=0 if following fields are valid */ @@ -1566,7 +1565,6 @@ w83793_detect_subclients(struct i2c_client *client) int address = client->addr; u8 tmp; struct i2c_adapter *adapter = client->adapter; - struct w83793_data *data = i2c_get_clientdata(client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -1586,21 +1584,19 @@ w83793_detect_subclients(struct i2c_client *client) } tmp = w83793_read_value(client, W83793_REG_I2C_SUBADDR); - if (!(tmp & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (tmp & 0x7)); - if (!(tmp & 0x80)) { - if (!IS_ERR(data->lm75[0]) - && ((tmp & 0x7) == ((tmp >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclients\n", data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((tmp >> 4) & 0x7)); + + if (!(tmp & 0x88) && (tmp & 0x7) == ((tmp >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (tmp & 0x7)); + return -ENODEV; } + if (!(tmp & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (tmp & 0x7)); + + if (!(tmp & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((tmp >> 4) & 0x7)); + return 0; } From cdc1e6e225e3256d56dc6648411630e71d7c776b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 2 Oct 2021 03:17:29 -0700 Subject: [PATCH 858/866] drm/i915: fix blank screen booting crashes 5.15-rc1 crashes with blank screen when booting up on two ThinkPads using i915. Bisections converge convincingly, but arrive at different and suprising "culprits", none of them the actual culprit. netconsole (with init_netconsole() hacked to call i915_init() when logging has started, instead of by module_init()) tells the story: kernel BUG at drivers/gpu/drm/i915/i915_sw_fence.c:245! with RSI: ffffffff814d408b pointing to sw_fence_dummy_notify(). I've been building with CONFIG_CC_OPTIMIZE_FOR_SIZE=y, and that function needs to be 4-byte aligned. Fixes: 62eaf0ae217d ("drm/i915/guc: Support request cancellation") Signed-off-by: Hugh Dickins Tested-by: Steven Rostedt (VMware) Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/gt/intel_context.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 745e84c72c90..e866105dd174 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -362,8 +362,9 @@ static int __intel_context_active(struct i915_active *active) return 0; } -static int sw_fence_dummy_notify(struct i915_sw_fence *sf, - enum i915_sw_fence_notify state) +static int __i915_sw_fence_call +sw_fence_dummy_notify(struct i915_sw_fence *sf, + enum i915_sw_fence_notify state) { return NOTIFY_DONE; } From 6e9bfdcf0a3b1c8126878c21adcfc343f89d4a6a Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Fri, 1 Oct 2021 15:37:31 +0100 Subject: [PATCH 859/866] cachefiles: Fix oops in trace_cachefiles_mark_buried due to NULL object In cachefiles_mark_object_buried, the dentry in question may not have an owner, and thus our cachefiles_object pointer may be NULL when calling the tracepoint, in which case we will also not have a valid debug_id to print in the tracepoint. Check for NULL object in the tracepoint and if so, just set debug_id to MAX_UINT as was done in 2908f5e101e3 ("fscache: Add a cookie debug ID and use that in traces"). This fixes the following oops: FS-Cache: Cache "mycache" added (type cachefiles) CacheFiles: File cache on vdc registered ... Workqueue: fscache_object fscache_object_work_func [fscache] RIP: 0010:trace_event_raw_event_cachefiles_mark_buried+0x4e/0xa0 [cachefiles] .... Call Trace: cachefiles_mark_object_buried+0xa5/0xb0 [cachefiles] cachefiles_bury_object+0x270/0x430 [cachefiles] cachefiles_walk_to_object+0x195/0x9c0 [cachefiles] cachefiles_lookup_object+0x5a/0xc0 [cachefiles] fscache_look_up_object+0xd7/0x160 [fscache] fscache_object_work_func+0xb2/0x340 [fscache] process_one_work+0x1f1/0x390 worker_thread+0x53/0x3e0 kthread+0x127/0x150 Fixes: 2908f5e101e3 ("fscache: Add a cookie debug ID and use that in traces") Signed-off-by: Dave Wysochanski Signed-off-by: David Howells cc: linux-cachefs@redhat.com Signed-off-by: Linus Torvalds --- include/trace/events/cachefiles.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9a448fe9355d..695bfdbfdcad 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -305,7 +305,7 @@ TRACE_EVENT(cachefiles_mark_buried, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), From 291073a566b2094c7192872cc0f17ce73d83cb76 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Oct 2021 13:34:19 -0700 Subject: [PATCH 860/866] kvm: fix objtool relocation warning The recent change to make objtool aware of more symbol relocation types (commit 24ff65257375: "objtool: Teach get_alt_entry() about more relocation types") also added another check, and resulted in this objtool warning when building kvm on x86: arch/x86/kvm/emulate.o: warning: objtool: __ex_table+0x4: don't know how to handle reloc symbol type: kvm_fastop_exception The reason seems to be that kvm_fastop_exception() is marked as a global symbol, which causes the relocation to ke kept around for objtool. And at the same time, the kvm_fastop_exception definition (which is done as an inline asm statement) doesn't actually set the type of the global, which then makes objtool unhappy. The minimal fix is to just not mark kvm_fastop_exception as being a global symbol. It's only used in that one compilation unit anyway, so it was always pointless. That's how all the other local exception table labels are done. I'm not entirely happy about the kinds of games that the kvm code plays with doing its own exception handling, and the fact that it confused objtool is most definitely a symptom of the code being a bit too subtle and ad-hoc. But at least this trivial one-liner makes objtool no longer upset about what is going on. Fixes: 24ff65257375 ("objtool: Teach get_alt_entry() about more relocation types") Link: https://lore.kernel.org/lkml/CAHk-=wiZwq-0LknKhXN4M+T8jbxn_2i9mcKpO+OaBSSq_Eh7tg@mail.gmail.com/ Cc: Borislav Petkov Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Vitaly Kuznetsov Cc: Wanpeng Li Cc: Jim Mattson Cc: Joerg Roedel Cc: Peter Zijlstra Cc: Josh Poimboeuf Cc: Nathan Chancellor Signed-off-by: Linus Torvalds --- arch/x86/kvm/emulate.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c589ac832265..9a144ca8e146 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); __FOP_RET(#op) asm(".pushsection .fixup, \"ax\"\n" - ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); From 7fab1c12bde926c5a8c7d5984c551d0854d7e0b3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Oct 2021 13:45:48 -0700 Subject: [PATCH 861/866] objtool: print out the symbol type when complaining about it The objtool warning that the kvm instruction emulation code triggered wasn't very useful: arch/x86/kvm/emulate.o: warning: objtool: __ex_table+0x4: don't know how to handle reloc symbol type: kvm_fastop_exception in that it helpfully tells you which symbol name it had trouble figuring out the relocation for, but it doesn't actually say what the unknown symbol type was that triggered it all. In this case it was because of missing type information (type 0, aka STT_NOTYPE), but on the whole it really should just have printed that out as part of the message. Because if this warning triggers, that's very much the first thing you want to know - why did reloc2sec_off() return failure for that symbol? So rather than just saying you can't handle some type of symbol without saying what the type _was_, just print out the type number too. Fixes: 24ff65257375 ("objtool: Teach get_alt_entry() about more relocation types") Link: https://lore.kernel.org/lkml/CAHk-=wiZwq-0LknKhXN4M+T8jbxn_2i9mcKpO+OaBSSq_Eh7tg@mail.gmail.com/ Signed-off-by: Linus Torvalds --- tools/objtool/special.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/objtool/special.c b/tools/objtool/special.c index f58ecc50fb10..f1428e32a505 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -110,8 +110,10 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; } if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { - WARN_FUNC("don't know how to handle reloc symbol type: %s", - sec, offset + entry->orig, orig_reloc->sym->name); + WARN_FUNC("don't know how to handle reloc symbol type %d: %s", + sec, offset + entry->orig, + orig_reloc->sym->type, + orig_reloc->sym->name); return -1; } @@ -132,8 +134,10 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return 1; if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { - WARN_FUNC("don't know how to handle reloc symbol type: %s", - sec, offset + entry->new, new_reloc->sym->name); + WARN_FUNC("don't know how to handle reloc symbol type %d: %s", + sec, offset + entry->new, + new_reloc->sym->type, + new_reloc->sym->name); return -1; } From 9b2f72cc0aa4bb444541bb87581c35b7508b37d3 Mon Sep 17 00:00:00 2001 From: Chen Jingwen Date: Tue, 28 Sep 2021 20:56:57 +0800 Subject: [PATCH 862/866] elf: don't use MAP_FIXED_NOREPLACE for elf interpreter mappings In commit b212921b13bd ("elf: don't use MAP_FIXED_NOREPLACE for elf executable mappings") we still leave MAP_FIXED_NOREPLACE in place for load_elf_interp. Unfortunately, this will cause kernel to fail to start with: 1 (init): Uhuuh, elf segment at 00003ffff7ffd000 requested but the memory is mapped already Failed to execute /init (error -17) The reason is that the elf interpreter (ld.so) has overlapping segments. readelf -l ld-2.31.so Program Headers: Type Offset VirtAddr PhysAddr FileSiz MemSiz Flags Align LOAD 0x0000000000000000 0x0000000000000000 0x0000000000000000 0x000000000002c94c 0x000000000002c94c R E 0x10000 LOAD 0x000000000002dae0 0x000000000003dae0 0x000000000003dae0 0x00000000000021e8 0x0000000000002320 RW 0x10000 LOAD 0x000000000002fe00 0x000000000003fe00 0x000000000003fe00 0x00000000000011ac 0x0000000000001328 RW 0x10000 The reason for this problem is the same as described in commit ad55eac74f20 ("elf: enforce MAP_FIXED on overlaying elf segments"). Not only executable binaries, elf interpreters (e.g. ld.so) can have overlapping elf segments, so we better drop MAP_FIXED_NOREPLACE and go back to MAP_FIXED in load_elf_interp. Fixes: 4ed28639519c ("fs, elf: drop MAP_FIXED usage from elf_map") Cc: # v4.19 Cc: Andrew Morton Cc: Michal Hocko Signed-off-by: Chen Jingwen Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 69d900a8473d..a813b70f594e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -630,7 +630,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED_NOREPLACE; + elf_type |= MAP_FIXED; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; From 9e1ff307c779ce1f0f810c7ecce3d95bbae40896 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Oct 2021 14:08:47 -0700 Subject: [PATCH 863/866] Linux 5.15-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 437ccc66a1c2..7b74223d1309 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Opossums on Parade # *DOCUMENTATION* From 4d8b35968bbf9e42b6b202eedb510e2c82ad8b38 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 4 Oct 2021 10:07:50 -0700 Subject: [PATCH 864/866] objtool: Remove reloc symbol type checks in get_alt_entry() Converting a special section's relocation reference to a symbol is straightforward. No need for objtool to complain that it doesn't know how to handle it. Just handle it. This fixes the following warning: arch/x86/kvm/emulate.o: warning: objtool: __ex_table+0x4: don't know how to handle reloc symbol type: kvm_fastop_exception Fixes: 24ff65257375 ("objtool: Teach get_alt_entry() about more relocation types") Reported-by: Linus Torvalds Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/feadbc3dfb3440d973580fad8d3db873cbfe1694.1633367242.git.jpoimboe@redhat.com Cc: Peter Zijlstra Cc: x86@kernel.org Cc: Miroslav Benes Cc: linux-kernel@vger.kernel.org --- tools/objtool/special.c | 36 +++++++----------------------------- 1 file changed, 7 insertions(+), 29 deletions(-) diff --git a/tools/objtool/special.c b/tools/objtool/special.c index f1428e32a505..83d5f969bcb0 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,22 +58,11 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } -static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, + unsigned long *off) { - switch (reloc->sym->type) { - case STT_FUNC: - *sec = reloc->sym->sec; - *off = reloc->sym->offset + reloc->addend; - return true; - - case STT_SECTION: - *sec = reloc->sym->sec; - *off = reloc->addend; - return true; - - default: - return false; - } + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; } static int get_alt_entry(struct elf *elf, struct special_entry *entry, @@ -109,13 +98,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->orig, - orig_reloc->sym->type, - orig_reloc->sym->name); - return -1; - } + + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); @@ -133,13 +117,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1; - if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->new, - new_reloc->sym->type, - new_reloc->sym->name); - return -1; - } + reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) From dc02368164bd0ec603e3f5b3dd8252744a667b8a Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Sun, 22 Aug 2021 18:50:36 -0400 Subject: [PATCH 865/866] objtool: Make .altinstructions section entry size consistent Commit e31694e0a7a7 ("objtool: Don't make .altinstructions writable") aligned objtool-created and kernel-created .altinstructions section flags, but there remains a minor discrepency in their use of a section entry size: objtool sets one while the kernel build does not. While sh_entsize of sizeof(struct alt_instr) seems intuitive, this small deviation can cause failures with external tooling (kpatch-build). Fix this by creating new .altinstructions sections with sh_entsize of 0 and then later updating sec->sh_size as alternatives are added to the section. An added benefit is avoiding the data descriptor and buffer created by elf_create_section(), but previously unused by elf_add_alternative(). Fixes: 9bc0bb50727c ("objtool/x86: Rewrite retpoline thunk calls") Signed-off-by: Joe Lawrence Reviewed-by: Miroslav Benes Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20210822225037.54620-2-joe.lawrence@redhat.com Cc: Andy Lavr Cc: Peter Zijlstra Cc: x86@kernel.org Cc: linux-kernel@vger.kernel.org --- tools/objtool/arch/x86/decode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index bc821056aba9..0893436cc09f 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -684,7 +684,7 @@ static int elf_add_alternative(struct elf *elf, sec = find_section_by_name(elf, ".altinstructions"); if (!sec) { sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, size, 0); + SHF_ALLOC, 0, 0); if (!sec) { WARN_ELF("elf_create_section"); From fe255fe6ad97685e5a4be0d871f43288dbc10ad6 Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Sun, 22 Aug 2021 18:50:37 -0400 Subject: [PATCH 866/866] objtool: Remove redundant 'len' field from struct section The section structure already contains sh_size, so just remove the extra 'len' member that requires extra mirroring and potential confusion. Suggested-by: Josh Poimboeuf Signed-off-by: Joe Lawrence Reviewed-by: Miroslav Benes Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20210822225037.54620-3-joe.lawrence@redhat.com Cc: Andy Lavr Cc: Peter Zijlstra Cc: x86@kernel.org Cc: linux-kernel@vger.kernel.org --- tools/objtool/check.c | 16 ++++++++-------- tools/objtool/elf.c | 14 ++++++-------- tools/objtool/include/objtool/elf.h | 1 - tools/objtool/orc_gen.c | 2 +- tools/objtool/special.c | 4 ++-- 5 files changed, 17 insertions(+), 20 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e5947fbb9e7a..06b5c164ae93 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -292,7 +292,7 @@ static int decode_instructions(struct objtool_file *file) !strcmp(sec->name, ".entry.text")) sec->noinstr = true; - for (offset = 0; offset < sec->len; offset += insn->len) { + for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { insn = malloc(sizeof(*insn)); if (!insn) { WARN("malloc failed"); @@ -307,7 +307,7 @@ static int decode_instructions(struct objtool_file *file) insn->offset = offset; ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, + sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, &insn->stack_ops); @@ -349,9 +349,9 @@ static struct instruction *find_last_insn(struct objtool_file *file, { struct instruction *insn = NULL; unsigned int offset; - unsigned int end = (sec->len > 10) ? sec->len - 10 : 0; + unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0; - for (offset = sec->len - 1; offset >= end && !insn; offset--) + for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--) insn = find_insn(file, sec, offset); return insn; @@ -389,7 +389,7 @@ static int add_dead_ends(struct objtool_file *file) insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", @@ -424,7 +424,7 @@ reachable: insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", @@ -1561,14 +1561,14 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - if (sec->len % sizeof(struct unwind_hint)) { + if (sec->sh.sh_size % sizeof(struct unwind_hint)) { WARN("struct unwind_hint size mismatch"); return -1; } file->hints = true; - for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { + for (i = 0; i < sec->sh.sh_size / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 8676c7598728..b18f0055b50b 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -286,10 +286,9 @@ static int read_sections(struct elf *elf) return -1; } } - sec->len = sec->sh.sh_size; if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->len; + elf->text_size += sec->sh.sh_size; list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); @@ -734,8 +733,8 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) data->d_size = strlen(str) + 1; data->d_align = 1; - len = strtab->len; - strtab->len += data->d_size; + len = strtab->sh.sh_size; + strtab->sh.sh_size += data->d_size; strtab->changed = true; return len; @@ -790,9 +789,9 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 1; data->d_type = ELF_T_SYM; - sym->idx = symtab->len / sizeof(sym->sym); + sym->idx = symtab->sh.sh_size / sizeof(sym->sym); - symtab->len += data->d_size; + symtab->sh.sh_size += data->d_size; symtab->changed = true; symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); @@ -814,7 +813,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 4; data->d_type = ELF_T_WORD; - symtab_shndx->len += 4; + symtab_shndx->sh.sh_size += 4; symtab_shndx->changed = true; } @@ -855,7 +854,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->len = size; sec->changed = true; sec->data = elf_newdata(s); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e34395047530..075d8291b854 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -38,7 +38,6 @@ struct section { Elf_Data *data; char *name; int idx; - unsigned int len; bool changed, text, rodata, noinstr; }; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index dc9b7dd314b0..b5865e2450cb 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -204,7 +204,7 @@ int orc_create(struct objtool_file *file) /* Add a section terminator */ if (!empty) { - orc_list_add(&orc_list, &null, sec, sec->len); + orc_list_add(&orc_list, &null, sec, sec->sh.sh_size); nr++; } } diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 83d5f969bcb0..06c3eacab3d5 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -159,13 +159,13 @@ int special_get_alts(struct elf *elf, struct list_head *alts) if (!sec) continue; - if (sec->len % entry->size != 0) { + if (sec->sh.sh_size % entry->size != 0) { WARN("%s size not a multiple of %d", sec->name, entry->size); return -1; } - nr_entries = sec->len / entry->size; + nr_entries = sec->sh.sh_size / entry->size; for (idx = 0; idx < nr_entries; idx++) { alt = malloc(sizeof(*alt));