diff --git a/Documentation/admin-guide/device-mapper/dm-integrity.rst b/Documentation/admin-guide/device-mapper/dm-integrity.rst index c00f9f11e3f3..8439d2ae689b 100644 --- a/Documentation/admin-guide/device-mapper/dm-integrity.rst +++ b/Documentation/admin-guide/device-mapper/dm-integrity.rst @@ -182,12 +182,15 @@ fix_padding space-efficient. If this option is not present, large padding is used - that is for compatibility with older kernels. +allow_discards + Allow block discard requests (a.k.a. TRIM) for the integrity device. + Discards are only allowed to devices using internal hash. -The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can -be changed when reloading the target (load an inactive table and swap the -tables with suspend and resume). The other arguments should not be changed -when reloading the target because the layout of disk data depend on them -and the reloaded target would be non-functional. +The journal mode (D/J), buffer_sectors, journal_watermark, commit_time and +allow_discards can be changed when reloading the target (load an inactive +table and swap the tables with suspend and resume). The other arguments +should not be changed when reloading the target because the layout of disk +data depend on them and the reloaded target would be non-functional. The layout of the formatted block device: diff --git a/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml b/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml index 86cfb599256e..371f18773198 100644 --- a/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml +++ b/Documentation/devicetree/bindings/dma/socionext,uniphier-xdmac.yaml @@ -22,9 +22,7 @@ properties: const: socionext,uniphier-xdmac reg: - items: - - description: XDMAC base register region (offset and length) - - description: XDMAC extension register region (offset and length) + maxItems: 1 interrupts: maxItems: 1 @@ -49,12 +47,13 @@ required: - reg - interrupts - "#dma-cells" + - dma-channels examples: - | xdmac: dma-controller@5fc10000 { compatible = "socionext,uniphier-xdmac"; - reg = <0x5fc10000 0x1000>, <0x5fc20000 0x800>; + reg = <0x5fc10000 0x5300>; interrupts = <0 188 4>; #dma-cells = <2>; dma-channels = <16>; diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 5b58fc4e1268..4574352d6ff4 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -61,8 +61,8 @@ The ``ice`` driver reports the following versions - running - ICE OS Default Package - The name of the DDP package that is active in the device. The DDP - package is loaded by the driver during initialization. Each varation - of DDP package shall have a unique name. + package is loaded by the driver during initialization. Each + variation of the DDP package has a unique name. * - ``fw.app`` - running - 1.3.1.0 diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index dcc252634cf9..b6833c7bb474 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -28,3 +28,5 @@ KVM arm/index devices/index + + running-nested-guests diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst new file mode 100644 index 000000000000..d0a1fc754c84 --- /dev/null +++ b/Documentation/virt/kvm/running-nested-guests.rst @@ -0,0 +1,276 @@ +============================== +Running nested guests with KVM +============================== + +A nested guest is the ability to run a guest inside another guest (it +can be KVM-based or a different hypervisor). The straightforward +example is a KVM guest that in turn runs on a KVM guest (the rest of +this document is built on this example):: + + .----------------. .----------------. + | | | | + | L2 | | L2 | + | (Nested Guest) | | (Nested Guest) | + | | | | + |----------------'--'----------------| + | | + | L1 (Guest Hypervisor) | + | KVM (/dev/kvm) | + | | + .------------------------------------------------------. + | L0 (Host Hypervisor) | + | KVM (/dev/kvm) | + |------------------------------------------------------| + | Hardware (with virtualization extensions) | + '------------------------------------------------------' + +Terminology: + +- L0 – level-0; the bare metal host, running KVM + +- L1 – level-1 guest; a VM running on L0; also called the "guest + hypervisor", as it itself is capable of running KVM. + +- L2 – level-2 guest; a VM running on L1, this is the "nested guest" + +.. note:: The above diagram is modelled after the x86 architecture; + s390x, ppc64 and other architectures are likely to have + a different design for nesting. + + For example, s390x always has an LPAR (LogicalPARtition) + hypervisor running on bare metal, adding another layer and + resulting in at least four levels in a nested setup — L0 (bare + metal, running the LPAR hypervisor), L1 (host hypervisor), L2 + (guest hypervisor), L3 (nested guest). + + This document will stick with the three-level terminology (L0, + L1, and L2) for all architectures; and will largely focus on + x86. + + +Use Cases +--------- + +There are several scenarios where nested KVM can be useful, to name a +few: + +- As a developer, you want to test your software on different operating + systems (OSes). Instead of renting multiple VMs from a Cloud + Provider, using nested KVM lets you rent a large enough "guest + hypervisor" (level-1 guest). This in turn allows you to create + multiple nested guests (level-2 guests), running different OSes, on + which you can develop and test your software. + +- Live migration of "guest hypervisors" and their nested guests, for + load balancing, disaster recovery, etc. + +- VM image creation tools (e.g. ``virt-install``, etc) often run + their own VM, and users expect these to work inside a VM. + +- Some OSes use virtualization internally for security (e.g. to let + applications run safely in isolation). + + +Enabling "nested" (x86) +----------------------- + +From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled +by default for Intel and AMD. (Though your Linux distribution might +override this default.) + +In case you are running a Linux kernel older than v4.19, to enable +nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``. To +persist this setting across reboots, you can add it in a config file, as +shown below: + +1. On the bare metal host (L0), list the kernel modules and ensure that + the KVM modules:: + + $ lsmod | grep -i kvm + kvm_intel 133627 0 + kvm 435079 1 kvm_intel + +2. Show information for ``kvm_intel`` module:: + + $ modinfo kvm_intel | grep -i nested + parm: nested:bool + +3. For the nested KVM configuration to persist across reboots, place the + below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it + doesn't exist):: + + $ cat /etc/modprobe.d/kvm_intel.conf + options kvm-intel nested=y + +4. Unload and re-load the KVM Intel module:: + + $ sudo rmmod kvm-intel + $ sudo modprobe kvm-intel + +5. Verify if the ``nested`` parameter for KVM is enabled:: + + $ cat /sys/module/kvm_intel/parameters/nested + Y + +For AMD hosts, the process is the same as above, except that the module +name is ``kvm-amd``. + + +Additional nested-related kernel parameters (x86) +------------------------------------------------- + +If your hardware is sufficiently advanced (Intel Haswell processor or +higher, which has newer hardware virt extensions), the following +additional features will also be enabled by default: "Shadow VMCS +(Virtual Machine Control Structure)", APIC Virtualization on your bare +metal host (L0). Parameters for Intel hosts:: + + $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs + Y + + $ cat /sys/module/kvm_intel/parameters/enable_apicv + Y + + $ cat /sys/module/kvm_intel/parameters/ept + Y + +.. note:: If you suspect your L2 (i.e. nested guest) is running slower, + ensure the above are enabled (particularly + ``enable_shadow_vmcs`` and ``ept``). + + +Starting a nested guest (x86) +----------------------------- + +Once your bare metal host (L0) is configured for nesting, you should be +able to start an L1 guest with:: + + $ qemu-kvm -cpu host [...] + +The above will pass through the host CPU's capabilities as-is to the +gues); or for better live migration compatibility, use a named CPU +model supported by QEMU. e.g.:: + + $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on + +then the guest hypervisor will subsequently be capable of running a +nested guest with accelerated KVM. + + +Enabling "nested" (s390x) +------------------------- + +1. On the host hypervisor (L0), enable the ``nested`` parameter on + s390x:: + + $ rmmod kvm + $ modprobe kvm nested=1 + +.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive + with the ``nested`` paramter — i.e. to be able to enable + ``nested``, the ``hpage`` parameter *must* be disabled. + +2. The guest hypervisor (L1) must be provided with the ``sie`` CPU + feature — with QEMU, this can be done by using "host passthrough" + (via the command-line ``-cpu host``). + +3. Now the KVM module can be loaded in the L1 (guest hypervisor):: + + $ modprobe kvm + + +Live migration with nested KVM +------------------------------ + +Migrating an L1 guest, with a *live* nested guest in it, to another +bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for +Intel x86 systems, and even on older versions for s390x. + +On AMD systems, once an L1 guest has started an L2 guest, the L1 guest +should no longer be migrated or saved (refer to QEMU documentation on +"savevm"/"loadvm") until the L2 guest shuts down. Attempting to migrate +or save-and-load an L1 guest while an L2 guest is running will result in +undefined behavior. You might see a ``kernel BUG!`` entry in ``dmesg``, a +kernel 'oops', or an outright kernel panic. Such a migrated or loaded L1 +guest can no longer be considered stable or secure, and must be restarted. +Migrating an L1 guest merely configured to support nesting, while not +actually running L2 guests, is expected to function normally even on AMD +systems but may fail once guests are started. + +Migrating an L2 guest is always expected to succeed, so all the following +scenarios should work even on AMD systems: + +- Migrating a nested guest (L2) to another L1 guest on the *same* bare + metal host. + +- Migrating a nested guest (L2) to another L1 guest on a *different* + bare metal host. + +- Migrating a nested guest (L2) to a bare metal host. + +Reporting bugs from nested setups +----------------------------------- + +Debugging "nested" problems can involve sifting through log files across +L0, L1 and L2; this can result in tedious back-n-forth between the bug +reporter and the bug fixer. + +- Mention that you are in a "nested" setup. If you are running any kind + of "nesting" at all, say so. Unfortunately, this needs to be called + out because when reporting bugs, people tend to forget to even + *mention* that they're using nested virtualization. + +- Ensure you are actually running KVM on KVM. Sometimes people do not + have KVM enabled for their guest hypervisor (L1), which results in + them running with pure emulation or what QEMU calls it as "TCG", but + they think they're running nested KVM. Thus confusing "nested Virt" + (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM). + +Information to collect (generic) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The following is not an exhaustive list, but a very good starting point: + + - Kernel, libvirt, and QEMU version from L0 + + - Kernel, libvirt and QEMU version from L1 + + - QEMU command-line of L1 -- when using libvirt, you'll find it here: + ``/var/log/libvirt/qemu/instance.log`` + + - QEMU command-line of L2 -- as above, when using libvirt, get the + complete libvirt-generated QEMU command-line + + - ``cat /sys/cpuinfo`` from L0 + + - ``cat /sys/cpuinfo`` from L1 + + - ``lscpu`` from L0 + + - ``lscpu`` from L1 + + - Full ``dmesg`` output from L0 + + - Full ``dmesg`` output from L1 + +x86-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Both the below commands, ``x86info`` and ``dmidecode``, should be +available on most Linux distributions with the same name: + + - Output of: ``x86info -a`` from L0 + + - Output of: ``x86info -a`` from L1 + + - Output of: ``dmidecode`` from L0 + + - Output of: ``dmidecode`` from L1 + +s390x-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Along with the earlier mentioned generic details, the below is +also recommended: + + - ``/proc/sysinfo`` from L1; this will also include the info from L0 diff --git a/MAINTAINERS b/MAINTAINERS index 26f281d9f32a..091ec22c1a23 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3657,7 +3657,7 @@ L: linux-btrfs@vger.kernel.org S: Maintained W: http://btrfs.wiki.kernel.org/ Q: http://patchwork.kernel.org/project/linux-btrfs/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git F: Documentation/filesystems/btrfs.rst F: fs/btrfs/ F: include/linux/btrfs* @@ -3936,11 +3936,9 @@ F: arch/powerpc/platforms/cell/ CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov M: Jeff Layton -M: Sage Weil L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: include/linux/ceph/ F: include/linux/crush/ @@ -3948,12 +3946,10 @@ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) M: Jeff Layton -M: Sage Weil M: Ilya Dryomov L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/filesystems/ceph.rst F: fs/ceph/ @@ -5935,9 +5931,9 @@ F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION M: Tal Gilboa S: Maintained +F: Documentation/networking/net_dim.rst F: include/linux/dim.h F: lib/dim/ -F: Documentation/networking/net_dim.rst DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" @@ -7119,9 +7115,10 @@ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK M: Kishon Vijay Abraham I +M: Vinod Koul L: linux-kernel@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git F: Documentation/devicetree/bindings/phy/ F: drivers/phy/ F: include/linux/phy/ @@ -7746,11 +7743,6 @@ L: platform-driver-x86@vger.kernel.org S: Orphan F: drivers/platform/x86/tc1100-wmi.c -HP100: Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series -M: Jaroslav Kysela -S: Obsolete -F: drivers/staging/hp/hp100.* - HPET: High Precision Event Timers driver M: Clemens Ladisch S: Maintained @@ -14102,12 +14094,10 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov -M: Sage Weil R: Dongsheng Yang L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/ABI/testing/sysfs-bus-rbd F: drivers/block/rbd.c diff --git a/Makefile b/Makefile index 679f302a8b8b..11fe9b1535de 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os endif -ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED -KBUILD_CFLAGS += -Wno-maybe-uninitialized -endif - # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) KBUILD_CFLAGS += $(call cc-option,-fno-allow-store-data-races) @@ -881,6 +877,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign # disable stringop warnings in gcc 8+ KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +# We'll want to enable this eventually, but it's not going away for 5.7 at least +KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow) + +# Another good warning that we'll want to enable eventually +KBUILD_CFLAGS += $(call cc-disable-warning, restrict) + +# Enabled with W=2, disabled by default as noisy +KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c index 6fdb0ac62b3d..59da6c0b63b6 100644 --- a/arch/arm/crypto/chacha-glue.c +++ b/arch/arm/crypto/chacha-glue.c @@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, return; } - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c index ae5aefc44a4d..ffa8d73fe722 100644 --- a/arch/arm/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index ceec04ec2f40..13cfef4ae22e 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && do_neon) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks_arm(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e133da303a98..a9151884bc85 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -165,8 +165,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) preempt_enable(); #endif - if (!ret) - *oval = oldval; + /* + * Store unconditionally. If ret != 0 the extra store is the least + * of the worries but GCC cannot figure out that __futex_atomic_op() + * is either setting ret to -EFAULT or storing the old value in + * oldval which results in a uninitialized warning at the call site. + */ + *oval = oldval; return ret; } diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c index 37ca3e889848..af2bbca38e70 100644 --- a/arch/arm64/crypto/chacha-neon-glue.c +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -87,9 +87,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, !crypto_simd_usable()) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c index 895d3727c1fb..c5405e6a6db7 100644 --- a/arch/arm64/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index e97b092f56b8..f33ada70c4ed 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -143,13 +143,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && crypto_simd_usable()) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index dd2514bb1511..3862cad2410c 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -32,7 +32,7 @@ UBSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD := y KCOV_INSTRUMENT := n -CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny +CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -fasynchronous-unwind-tables ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 23ebe51410f0..50a279d3ddd7 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index d22d0534dd60..90186cf6473e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -18,6 +18,7 @@ #define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) #define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) +#define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8) .text .pushsection .hyp.text, "ax" @@ -47,6 +48,16 @@ ldp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] .endm +.macro save_sp_el0 ctxt, tmp + mrs \tmp, sp_el0 + str \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] +.endm + +.macro restore_sp_el0 ctxt, tmp + ldr \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] + msr sp_el0, \tmp +.endm + /* * u64 __guest_enter(struct kvm_vcpu *vcpu, * struct kvm_cpu_context *host_ctxt); @@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Save the host's sp_el0 + save_sp_el0 x1, x2 + // Now the host state is stored if we have a pending RAS SError it must // affect the host. If any asynchronous exception is pending we defer // the guest entry. The DSB isn't necessary before v8.2 as any SError @@ -83,6 +97,9 @@ alternative_else_nop_endif // when this feature is enabled for kernel code. ptrauth_switch_to_guest x29, x0, x1, x2 + // Restore the guest's sp_el0 + restore_sp_el0 x29, x0 + // Restore guest regs x0-x17 ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] @@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // Store the guest regs x18-x29, lr save_callee_saved_regs x1 + // Store the guest's sp_el0 + save_sp_el0 x1, x2 + get_host_ctxt x2, x3 // Macro ptrauth_switch_to_guest format: @@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // when this feature is enabled for kernel code. ptrauth_switch_to_host x1, x2, x3, x4, x5 + // Restore the hosts's sp_el0 + restore_sp_el0 x2, x3 + // Now restore the host regs restore_callee_saved_regs x2 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index c2a13ab3c471..9c5cfb04170e 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic) .macro invalid_vector label, target = __hyp_panic .align 2 SYM_CODE_START(\label) -\label: b \target SYM_CODE_END(\label) .endm diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 75b1925763f1..6d2df9fe0b5d 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -15,8 +15,9 @@ /* * Non-VHE: Both host and guest must save everything. * - * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate, - * which are handled as part of the el2 return state) on every switch. + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two @@ -26,12 +27,6 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); } static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) @@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); } static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index bbeb6a5a6ba6..0be3355e3499 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e15166b0a16d..ad2f172c26a6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 62f7bfeb709e..74f82cf4f781 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -60,7 +60,7 @@ config RISCV select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_SET_MEMORY - select ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_HAS_STRICT_KERNEL_RWX if MMU select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select SPARSEMEM_STATIC if 32BIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 8e18d2c64399..cec462e198ce 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -51,13 +51,10 @@ #define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) /* Interrupt causes (minus the high bit) */ -#define IRQ_U_SOFT 0 #define IRQ_S_SOFT 1 #define IRQ_M_SOFT 3 -#define IRQ_U_TIMER 4 #define IRQ_S_TIMER 5 #define IRQ_M_TIMER 7 -#define IRQ_U_EXT 8 #define IRQ_S_EXT 9 #define IRQ_M_EXT 11 diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 1bb0cd04aec3..5ce50468aff1 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -8,6 +8,7 @@ #ifndef _ASM_RISCV_HWCAP_H #define _ASM_RISCV_HWCAP_H +#include #include #ifndef __ASSEMBLY__ @@ -22,6 +23,27 @@ enum { }; extern unsigned long elf_hwcap; + +#define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_c ('c' - 'a') +#define RISCV_ISA_EXT_d ('d' - 'a') +#define RISCV_ISA_EXT_f ('f' - 'a') +#define RISCV_ISA_EXT_h ('h' - 'a') +#define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_s ('s' - 'a') +#define RISCV_ISA_EXT_u ('u' - 'a') + +#define RISCV_ISA_EXT_MAX 64 + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); + +#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index c38df4771c09..4c5bae7ca01c 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif -#ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_ro(void); -void set_kernel_text_rw(void); -#else -static inline void set_kernel_text_ro(void) { } -static inline void set_kernel_text_rw(void) { } -#endif - int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c index c4c33bf02369..0ec22354018c 100644 --- a/arch/riscv/kernel/cpu_ops.c +++ b/arch/riscv/kernel/cpu_ops.c @@ -15,8 +15,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; -void *__cpu_up_stack_pointer[NR_CPUS]; -void *__cpu_up_task_pointer[NR_CPUS]; +void *__cpu_up_stack_pointer[NR_CPUS] __section(.data); +void *__cpu_up_task_pointer[NR_CPUS] __section(.data); extern const struct cpu_operations cpu_ops_sbi; extern const struct cpu_operations cpu_ops_spinwait; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a5ad00043104..ac202f44a670 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,6 +6,7 @@ * Copyright (C) 2017 SiFive */ +#include #include #include #include @@ -13,15 +14,57 @@ #include unsigned long elf_hwcap __read_mostly; + +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + #ifdef CONFIG_FPU bool has_fpu __read_mostly; #endif +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + if (!isa_bitmap) + return riscv_isa[0]; + return isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap) ? true : false; +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + void riscv_fill_hwcap(void) { struct device_node *node; const char *isa; - size_t i; + char print_str[BITS_PER_LONG + 1]; + size_t i, j, isa_len; static unsigned long isa2hwcap[256] = {0}; isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; @@ -33,8 +76,11 @@ void riscv_fill_hwcap(void) elf_hwcap = 0; + bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); + for_each_of_cpu_node(node) { unsigned long this_hwcap = 0; + unsigned long this_isa = 0; if (riscv_of_processor_hartid(node) < 0) continue; @@ -44,8 +90,24 @@ void riscv_fill_hwcap(void) continue; } - for (i = 0; i < strlen(isa); ++i) + i = 0; + isa_len = strlen(isa); +#if IS_ENABLED(CONFIG_32BIT) + if (!strncmp(isa, "rv32", 4)) + i += 4; +#elif IS_ENABLED(CONFIG_64BIT) + if (!strncmp(isa, "rv64", 4)) + i += 4; +#endif + for (; i < isa_len; ++i) { this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + /* + * TODO: X, Y and Z extension parsing for Host ISA + * bitmap will be added in-future. + */ + if ('a' <= isa[i] && isa[i] < 'x') + this_isa |= (1UL << (isa[i] - 'a')); + } /* * All "okay" hart should have same isa. Set HWCAP based on @@ -56,6 +118,11 @@ void riscv_fill_hwcap(void) elf_hwcap &= this_hwcap; else elf_hwcap = this_hwcap; + + if (riscv_isa[0]) + riscv_isa[0] &= this_isa; + else + riscv_isa[0] = this_isa; } /* We don't support systems with F but without D, so mask those out @@ -65,7 +132,17 @@ void riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (riscv_isa[0] & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ISA extensions %s\n", print_str); + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); #ifdef CONFIG_FPU if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 7c24da59bccf..f383ef5672b2 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -102,7 +102,7 @@ void sbi_shutdown(void) { sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0); } -EXPORT_SYMBOL(sbi_set_timer); +EXPORT_SYMBOL(sbi_shutdown); /** * sbi_clear_ipi() - Clear any pending IPIs for the calling hart. @@ -113,7 +113,7 @@ void sbi_clear_ipi(void) { sbi_ecall(SBI_EXT_0_1_CLEAR_IPI, 0, 0, 0, 0, 0, 0, 0); } -EXPORT_SYMBOL(sbi_shutdown); +EXPORT_SYMBOL(sbi_clear_ipi); /** * sbi_set_timer_v01() - Program the timer for next timer event. @@ -167,6 +167,11 @@ static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask, return result; } + +static void sbi_set_power_off(void) +{ + pm_power_off = sbi_shutdown; +} #else static void __sbi_set_timer_v01(uint64_t stime_value) { @@ -191,6 +196,8 @@ static int __sbi_rfence_v01(int fid, const unsigned long *hart_mask, return 0; } + +static void sbi_set_power_off(void) {} #endif /* CONFIG_RISCV_SBI_V01 */ static void __sbi_set_timer_v02(uint64_t stime_value) @@ -540,16 +547,12 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } -static void sbi_power_off(void) -{ - sbi_shutdown(); -} int __init sbi_init(void) { int ret; - pm_power_off = sbi_power_off; + sbi_set_power_off(); ret = sbi_get_spec_version(); if (ret > 0) sbi_spec_version = ret; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e0a6293093f1..a65a8fa0c22d 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out) for_each_cpu(cpu, in) cpumask_set_cpu(cpuid_to_hartid_map(cpu), out); } +EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask); bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 02087fe539c6..6c854875ac74 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -12,6 +12,8 @@ #include #include +register unsigned long sp_in_global __asm__("sp"); + #ifdef CONFIG_FRAME_POINTER struct stackframe { @@ -19,8 +21,6 @@ struct stackframe { unsigned long ra; }; -register unsigned long sp_in_global __asm__("sp"); - void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 33b16f4212f7..4c8b2a4a6a70 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -12,7 +12,7 @@ vdso-syms += getcpu vdso-syms += flush_icache # Files to link into the vdso -obj-vdso = $(patsubst %, %.o, $(vdso-syms)) +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o @@ -33,15 +33,15 @@ $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) # We also create a special relocatable object that should mirror the symbol -# table and layout of the linked DSO. With ld -R we can then refer to -# these symbols in the kernel code rather than hand-coded addresses. +# table and layout of the linked DSO. With ld --just-symbols we can then +# refer to these symbols in the kernel code rather than hand-coded addresses. SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ -Wl,--build-id -Wl,--hash-style=both $(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE $(call if_changed,vdsold) -LDFLAGS_vdso-syms.o := -r -R +LDFLAGS_vdso-syms.o := -r --just-symbols $(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE $(call if_changed,ld) diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000000..2a956c942211 --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include +#include + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b55be44ff9bd..27a334106708 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -150,7 +150,8 @@ void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = max_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); @@ -501,22 +502,6 @@ static inline void setup_vm_final(void) #endif /* CONFIG_MMU */ #ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_rw(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long text_start = (unsigned long)_text; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5dcf9ff12828..d05bb040fd42 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: case KVM_CAP_S390_VCPU_RESETS: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_S390_HPAGE_1M: diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 69a824f9ef0b..893893642415 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index c4f8039a35e8..0267405ab7c6 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -64,10 +64,13 @@ mm_segment_t enable_sacf_uaccess(void) { mm_segment_t old_fs; unsigned long asce, cr; + unsigned long flags; old_fs = current->thread.mm_segment; if (old_fs & 1) return old_fs; + /* protect against a concurrent page table upgrade */ + local_irq_save(flags); current->thread.mm_segment |= 1; asce = S390_lowcore.kernel_asce; if (likely(old_fs == USER_DS)) { @@ -83,6 +86,7 @@ mm_segment_t enable_sacf_uaccess(void) __ctl_load(asce, 7, 7); set_cpu_flag(CIF_ASCE_SECONDARY); } + local_irq_restore(flags); return old_fs; } EXPORT_SYMBOL(enable_sacf_uaccess); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 498c98a312f4..fff169d64711 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -70,8 +70,20 @@ static void __crst_table_upgrade(void *arg) { struct mm_struct *mm = arg; - if (current->active_mm == mm) - set_user_asce(mm); + /* we must change all active ASCEs to avoid the creation of new TLBs */ + if (current->active_mm == mm) { + S390_lowcore.user_asce = mm->context.asce; + if (current->thread.mm_segment == USER_DS) { + __ctl_load(S390_lowcore.user_asce, 1, 1); + /* Mark user-ASCE present in CR1 */ + clear_cpu_flag(CIF_ASCE_PRIMARY); + } + if (current->thread.mm_segment == USER_DS_SACF) { + __ctl_load(S390_lowcore.user_asce, 7, 7); + /* enable_sacf_uaccess does all or nothing */ + WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY)); + } + } __tlb_flush_local(); } diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 06ef2d4a4701..6737bcea1fa1 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2s_state *state, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); + BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { blake2s_compress_generic(state, block, nblocks, inc); return; } - for (;;) { + do { const size_t blocks = min_t(size_t, nblocks, - PAGE_SIZE / BLAKE2S_BLOCK_SIZE); + SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && @@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2s_state *state, kernel_fpu_end(); nblocks -= blocks; - if (!nblocks) - break; block += blocks * BLAKE2S_BLOCK_SIZE; - } + } while (nblocks); } EXPORT_SYMBOL(blake2s_compress_arch); diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index b412c21ee06e..22250091cdbe 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -153,9 +153,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, bytes <= CHACHA_BLOCK_SIZE) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_fpu_begin(); - chacha_dosimd(state, dst, src, bytes, nrounds); - kernel_fpu_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_fpu_begin(); + chacha_dosimd(state, dst, src, todo, nrounds); + kernel_fpu_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 6dfec19f7d57..dfe921efa9b2 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, struct poly1305_arch_internal *state = ctx; /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || - PAGE_SIZE % POLY1305_BLOCK_SIZE); + BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || + SZ_4K % POLY1305_BLOCK_SIZE); if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || @@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, return; } - for (;;) { - const size_t bytes = min_t(size_t, len, PAGE_SIZE); + do { + const size_t bytes = min_t(size_t, len, SZ_4K); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) @@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, else poly1305_blocks_avx(ctx, inp, bytes, padbit); kernel_fpu_end(); + len -= bytes; - if (!len) - break; inp += bytes; - } + } while (len); } static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 0789e13ece90..1c7f13bb6728 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0e9504fabe52..3063aa9090f9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64) * %rdi: prev task * %rsi: next task */ -SYM_CODE_START(__switch_to_asm) - UNWIND_HINT_FUNC +SYM_FUNC_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm) popq %rbp jmp __switch_to -SYM_CODE_END(__switch_to_asm) +SYM_FUNC_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start) * +----------------------------------------------------+ */ SYM_CODE_START(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 624f5d9b0f79..fd51bac11b46 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -73,7 +73,8 @@ static int hv_cpu_init(unsigned int cpu) struct page *pg; input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); - pg = alloc_page(GFP_KERNEL); + /* hv_cpu_init() can be called with IRQs disabled from hv_resume() */ + pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!pg)) return -ENOMEM; *input_arg = page_address(pg); @@ -254,6 +255,7 @@ static int __init hv_pci_init(void) static int hv_suspend(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + int ret; /* * Reset the hypercall page as it is going to be invalidated @@ -270,12 +272,17 @@ static int hv_suspend(void) hypercall_msr.enable = 0; wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - return 0; + ret = hv_cpu_die(0); + return ret; } static void hv_resume(void) { union hv_x64_msr_hypercall_contents hypercall_msr; + int ret; + + ret = hv_cpu_init(0); + WARN_ON(ret); /* Re-enable the hypercall page */ rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -288,6 +295,7 @@ static void hv_resume(void) hv_hypercall_pg_saved = NULL; } +/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */ static struct syscore_ops hv_syscore_ops = { .suspend = hv_suspend, .resume = hv_resume, diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 85be2f506272..70b96cae5b42 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -61,11 +61,12 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name { /* * Compare the symbol name with the system call name. Skip the - * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. */ return !strcmp(sym + 3, name + 3) || (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || - (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); } #ifndef COMPILE_OFFSETS diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..0dea9f122bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 1c42ecbe75cb..d30805ed323e 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -35,6 +35,8 @@ typedef int (*hyperv_fill_flush_list_func)( rdmsrl(HV_X64_MSR_SINT0 + int_num, val) #define hv_set_synint_state(int_num, val) \ wrmsrl(HV_X64_MSR_SINT0 + int_num, val) +#define hv_recommend_using_aeoi() \ + (!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)) #define hv_get_crash_ctl(val) \ rdmsrl(HV_X64_MSR_CRASH_CTL, val) diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 81b9c63dae1b..e53dda210cd7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), @@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_debug("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881..460ae7f66818 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -183,7 +183,8 @@ recursion_check: */ if (visit_mask) { if (*visit_mask & (1UL << info->type)) { - printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); + if (task == current) + printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); goto unknown; } *visit_mask |= 1UL << info->type; diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a224b5ab103f..54226110bc7f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -344,6 +344,9 @@ bad_address: if (IS_ENABLED(CONFIG_X86_32)) goto the_end; + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index e9cc182aa97e..5b0bd8581fe6 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -8,19 +8,21 @@ #include #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + if (state->task == current) \ + orc_warn(args); \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; - -unsigned int lookup_num_blocks; -bool orc_init; +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; static inline unsigned long orc_ip(const int *ip) { @@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip) #ifdef CONFIG_MODULES +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; case ORC_TYPE_REGS_IRET: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -564,8 +596,8 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } @@ -585,6 +617,9 @@ EXPORT_SYMBOL_GPL(unwind_next_frame); void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { + if (!orc_init) + goto done; + memset(state, 0, sizeof(*state)); state->task = task; @@ -651,7 +686,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 750ff0b29404..d057376bd3d3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* - * AMD SVM AVIC accelerate EOI write and do not trap, - * in-kernel IOAPIC will not be able to receive the EOI. - * In this case, we do lazy update of the pending EOI when - * trying to set IOAPIC irq. + * AMD SVM AVIC accelerate EOI write iff the interrupt is edge + * triggered, in which case the in-kernel IOAPIC will not be able + * to receive the EOI. In this case, we do a lazy update of the + * pending EOI when trying to set IOAPIC irq. */ - if (kvm_apicv_activated(ioapic->kvm)) + if (edge && kvm_apicv_activated(ioapic->kvm)) ioapic_lazy_update_eoi(ioapic, irq); /* diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index cf912b4aaba8..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -345,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f379bacbb26..38f6aeefeb55 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1752,6 +1752,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = DB_VECTOR; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index fd78ffbde644..e44f33c82332 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) */ break; default: - BUG_ON(1); + BUG(); break; } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 87f3f24fef37..51d1a82742fd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c5835f9cb9ad..d786c7d27ce5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -926,19 +926,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); __reserved_bits; \ }) -static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) -{ - u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - - if (kvm_cpu_cap_has(X86_FEATURE_LA57)) - reserved_bits &= ~X86_CR4_LA57; - - if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) - reserved_bits &= ~X86_CR4_UMIP; - - return reserved_bits; -} - static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) @@ -3385,6 +3372,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -9675,7 +9663,9 @@ int kvm_arch_hardware_setup(void *opaque) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; - cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has if (kvm_has_tsc_control) { /* @@ -9707,7 +9697,8 @@ int kvm_arch_check_processor_compat(void *opaque) WARN_ON(!irqs_disabled()); - if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return ops->check_processor_compatibility(); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 59eca6a94ce7..b8c55a2e402d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -43,7 +43,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 78ba57efd16b..3d411716d7ee 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -123,6 +123,7 @@ #include #include #include +#include #include "blk.h" #include "blk-mq.h" @@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); switch (ioprio_class) { default: - dev_err(bfqq->bfqd->queue->backing_dev_info->dev, - "bfq: bad prio class %d\n", ioprio_class); + pr_err("bdi %s: bfq: bad prio class %d\n", + bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), + ioprio_class); /* fall through */ case IOPRIO_CLASS_NONE: /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c5dc833212e1..930212c1a512 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ if (blkg->q->backing_dev_info->dev) - return dev_name(blkg->q->backing_dev_info->dev); + return bdi_dev_name(blkg->q->backing_dev_info); return NULL; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 3ab0c1c704b6..7c1fe605d0d6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -466,7 +466,7 @@ struct ioc_gq { */ atomic64_t vtime; atomic64_t done_vtime; - atomic64_t abs_vdebt; + u64 abs_vdebt; u64 last_vtime; /* @@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 margin_ns = (u64)(ioc->period_us * WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC; - u64 abs_vdebt, vdebt, vshortage, expires, oexpires; + u64 vdebt, vshortage, expires, oexpires; s64 vbudget; u32 hw_inuse; @@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ - abs_vdebt = atomic64_read(&iocg->abs_vdebt); - vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse); + vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); if (vdebt && vbudget > 0) { u64 delta = min_t(u64, vbudget, vdebt); u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse), - abs_vdebt); + iocg->abs_vdebt); atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - atomic64_sub(abs_delta, &iocg->abs_vdebt); - if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0)) - atomic64_set(&iocg->abs_vdebt, 0); + iocg->abs_vdebt -= abs_delta; } /* @@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) u64 expires, oexpires; u32 hw_inuse; + lockdep_assert_held(&iocg->waitq.lock); + /* debt-adjust vtime */ current_hweight(iocg, NULL, &hw_inuse); - vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse); + vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); - /* clear or maintain depending on the overage */ - if (time_before_eq64(vtime, now->vnow)) { + /* + * Clear or maintain depending on the overage. Non-zero vdebt is what + * guarantees that @iocg is online and future iocg_kick_delay() will + * clear use_delay. Don't leave it on when there's no vdebt. + */ + if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); return false; } @@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer); struct ioc_now now; + unsigned long flags; + spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); iocg_kick_delay(iocg, &now, 0); + spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; } @@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer) * should have woken up in the last period and expire idle iocgs. */ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg)) + if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt && + !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); - if (waitqueue_active(&iocg->waitq) || - atomic64_read(&iocg->abs_vdebt)) { + if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); iocg_kick_delay(iocg, &now, 0); @@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && + if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); return; } /* - * We're over budget. If @bio has to be issued regardless, - * remember the abs_cost instead of advancing vtime. - * iocg_kick_waitq() will pay off the debt before waking more IOs. + * We activated above but w/o any synchronization. Deactivation is + * synchronized with waitq.lock and we won't get deactivated as long + * as we're waiting or has debt, so we're good if we're activated + * here. In the unlikely case that we aren't, just issue the IO. + */ + spin_lock_irq(&iocg->waitq.lock); + + if (unlikely(list_empty(&iocg->active_list))) { + spin_unlock_irq(&iocg->waitq.lock); + iocg_commit_bio(iocg, bio, cost); + return; + } + + /* + * We're over budget. If @bio has to be issued regardless, remember + * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay + * off the debt before waking more IOs. + * * This way, the debt is continuously paid off each period with the - * actual budget available to the cgroup. If we just wound vtime, - * we would incorrectly use the current hw_inuse for the entire - * amount which, for example, can lead to the cgroup staying - * blocked for a long time even with substantially raised hw_inuse. + * actual budget available to the cgroup. If we just wound vtime, we + * would incorrectly use the current hw_inuse for the entire amount + * which, for example, can lead to the cgroup staying blocked for a + * long time even with substantially raised hw_inuse. + * + * An iocg with vdebt should stay online so that the timer can keep + * deducting its vdebt and [de]activate use_delay mechanism + * accordingly. We don't want to race against the timer trying to + * clear them and leave @iocg inactive w/ dangling use_delay heavily + * penalizing the cgroup and its descendants. */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { - atomic64_add(abs_cost, &iocg->abs_vdebt); + iocg->abs_vdebt += abs_cost; if (iocg_kick_delay(iocg, &now, cost)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + spin_unlock_irq(&iocg->waitq.lock); return; } @@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - spin_lock_irq(&iocg->waitq.lock); - - /* - * We activated above but w/o any synchronization. Deactivation is - * synchronized with waitq.lock and we won't get deactivated as - * long as we're waiting, so we're good if we're activated here. - * In the unlikely case that we are deactivated, just issue the IO. - */ - if (unlikely(list_empty(&iocg->active_list))) { - spin_unlock_irq(&iocg->waitq.lock); - iocg_commit_bio(iocg, bio, cost); - return; - } - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; @@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct ioc_now now; u32 hw_inuse; u64 abs_cost, cost; + unsigned long flags; /* bypass if disabled or for root cgroup */ if (!ioc->enabled || !iocg->level) @@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, iocg->cursor = bio_end; /* - * Charge if there's enough vtime budget and the existing request - * has cost assigned. Otherwise, account it as debt. See debt - * handling in ioc_rqos_throttle() for details. + * Charge if there's enough vtime budget and the existing request has + * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && - time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) + time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); - else - atomic64_add(abs_cost, &iocg->abs_vdebt); + return; + } + + /* + * Otherwise, account it as debt if @iocg is online, which it should + * be for the vast majority of cases. See debt handling in + * ioc_rqos_throttle() for details. + */ + spin_lock_irqsave(&iocg->waitq.lock, flags); + if (likely(!list_empty(&iocg->active_list))) { + iocg->abs_vdebt += abs_cost; + iocg_kick_delay(iocg, &now, cost); + } else { + iocg_commit_bio(iocg, bio, cost); + } + spin_unlock_irqrestore(&iocg->waitq.lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) @@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); - atomic64_set(&iocg->abs_vdebt, 0); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); iocg->hweight_active = HWEIGHT_WHOLE; diff --git a/block/partitions/core.c b/block/partitions/core.c index bc1ded1331b1..9ef48a8cff86 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -496,7 +496,7 @@ int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) if (!disk_part_scan_enabled(disk)) return 0; - if (bdev->bd_part_count || bdev->bd_openers > 1) + if (bdev->bd_part_count) return -EBUSY; res = invalidate_partition(disk, 0); if (res) diff --git a/crypto/lrw.c b/crypto/lrw.c index 376d7ed3f1f8..3c734b81b3a2 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_skcipher(ctx->child); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/crypto/xts.c b/crypto/xts.c index dbdd8af629e6..6d8cea94b3cf 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_cipher(ctx->tweak); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index b2263ec67b43..5832bc10aca8 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -273,13 +273,13 @@ int acpi_device_set_power(struct acpi_device *device, int state) end: if (result) { dev_warn(&device->dev, "Failed to change power state to %s\n", - acpi_power_state_string(state)); + acpi_power_state_string(target_state)); } else { device->power.state = target_state; ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] transitioned to %s\n", device->pnp.bus_id, - acpi_power_state_string(state))); + acpi_power_state_string(target_state))); } return result; diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index fe1523664816..8558b629880b 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name) dev->dev.release = amba_device_release; dev->dev.bus = &amba_bustype; dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + dev->dev.dma_parms = &dev->dma_parms; dev->res.name = dev_name(&dev->dev); } diff --git a/drivers/base/component.c b/drivers/base/component.c index e97704104784..dcfbe7251dc4 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -256,7 +256,8 @@ static int try_to_bring_up_master(struct master *master, ret = master->ops->bind(master->dev); if (ret < 0) { devres_release_group(master->dev, NULL); - dev_info(master->dev, "master bind failed: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_info(master->dev, "master bind failed: %d\n", ret); return ret; } @@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master, devres_release_group(component->dev, NULL); devres_release_group(master->dev, NULL); - dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", - dev_name(component->dev), component->ops, ret); + if (ret != -EPROBE_DEFER) + dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", + dev_name(component->dev), component->ops, ret); } return ret; diff --git a/drivers/base/core.c b/drivers/base/core.c index 139cdf7e7327..073045cb214e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2370,6 +2370,11 @@ u32 fw_devlink_get_flags(void) return fw_devlink_flags; } +static bool fw_devlink_is_permissive(void) +{ + return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY; +} + /** * device_add - add device to device hierarchy. * @dev: device. @@ -2524,7 +2529,7 @@ int device_add(struct device *dev) if (fw_devlink_flags && is_fwnode_dev && fwnode_has_op(dev->fwnode, add_links)) { fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); - if (fw_ret == -ENODEV) + if (fw_ret == -ENODEV && !fw_devlink_is_permissive()) device_link_wait_for_mandatory_supplier(dev); else if (fw_ret) device_link_wait_for_optional_supplier(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 06ec0e851fa1..94037be7f5d7 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(deferred_devs); -#ifdef CONFIG_MODULES -/* - * In the case of modules, set the default probe timeout to - * 30 seconds to give userland some time to load needed modules - */ -int driver_deferred_probe_timeout = 30; -#else -/* In the case of !modules, no probe timeout needed */ -int driver_deferred_probe_timeout = -1; -#endif +int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); +static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue); static int __init deferred_probe_timeout_setup(char *str) { @@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev) return -ENODEV; } - if (!driver_deferred_probe_timeout) { - dev_WARN(dev, "deferred probe timeout, ignoring dependency"); + if (!driver_deferred_probe_timeout && initcalls_done) { + dev_warn(dev, "deferred probe timeout, ignoring dependency"); return -ETIMEDOUT; } @@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work) list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) dev_info(private->device, "deferred probe pending"); + wake_up(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); @@ -658,6 +651,9 @@ int driver_probe_done(void) */ void wait_for_device_probe(void) { + /* wait for probe timeout */ + wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout); + /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 5255550b7c34..b27d0f6c18c9 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -380,6 +380,8 @@ struct platform_object { */ static void setup_pdev_dma_masks(struct platform_device *pdev) { + pdev->dev.dma_parms = &pdev->dma_parms; + if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); if (!pdev->dev.dma_mask) { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 93468b7c6701..9d21bf0f155e 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -33,6 +33,15 @@ struct virtio_blk_vq { } ____cacheline_aligned_in_smp; struct virtio_blk { + /* + * This mutex must be held by anything that may run after + * virtblk_remove() sets vblk->vdev to NULL. + * + * blk-mq, virtqueue processing, and sysfs attribute code paths are + * shut down before vblk->vdev is set to NULL and therefore do not need + * to hold this mutex. + */ + struct mutex vdev_mutex; struct virtio_device *vdev; /* The disk structure for the kernel. */ @@ -44,6 +53,13 @@ struct virtio_blk { /* Process context for config space updates */ struct work_struct config_work; + /* + * Tracks references from block_device_operations open/release and + * virtio_driver probe/remove so this object can be freed once no + * longer in use. + */ + refcount_t refs; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; @@ -295,10 +311,55 @@ out: return err; } +static void virtblk_get(struct virtio_blk *vblk) +{ + refcount_inc(&vblk->refs); +} + +static void virtblk_put(struct virtio_blk *vblk) +{ + if (refcount_dec_and_test(&vblk->refs)) { + ida_simple_remove(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->vdev_mutex); + kfree(vblk); + } +} + +static int virtblk_open(struct block_device *bd, fmode_t mode) +{ + struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (vblk->vdev) + virtblk_get(vblk); + else + ret = -ENXIO; + + mutex_unlock(&vblk->vdev_mutex); + return ret; +} + +static void virtblk_release(struct gendisk *disk, fmode_t mode) +{ + struct virtio_blk *vblk = disk->private_data; + + virtblk_put(vblk); +} + /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto out; + } /* see if the host passed in geometry config */ if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) { @@ -314,11 +375,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) geo->sectors = 1 << 5; geo->cylinders = get_capacity(bd->bd_disk) >> 11; } - return 0; +out: + mutex_unlock(&vblk->vdev_mutex); + return ret; } static const struct block_device_operations virtblk_fops = { .owner = THIS_MODULE, + .open = virtblk_open, + .release = virtblk_release, .getgeo = virtblk_getgeo, }; @@ -655,6 +720,10 @@ static int virtblk_probe(struct virtio_device *vdev) goto out_free_index; } + /* This reference is dropped in virtblk_remove(). */ + refcount_set(&vblk->refs, 1); + mutex_init(&vblk->vdev_mutex); + vblk->vdev = vdev; vblk->sg_elems = sg_elems; @@ -820,8 +889,6 @@ out: static void virtblk_remove(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; - int index = vblk->index; - int refc; /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); @@ -831,18 +898,21 @@ static void virtblk_remove(struct virtio_device *vdev) blk_mq_free_tag_set(&vblk->tag_set); + mutex_lock(&vblk->vdev_mutex); + /* Stop all the virtqueues. */ vdev->config->reset(vdev); - refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref); + /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ + vblk->vdev = NULL; + put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); - kfree(vblk); - /* Only free device id if we don't have any users */ - if (refc == 1) - ida_simple_remove(&vd_index_ida, index); + mutex_unlock(&vblk->vdev_mutex); + + virtblk_put(vblk); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c index b38359c480ea..eb2ab058a01d 100644 --- a/drivers/bus/mhi/core/init.c +++ b/drivers/bus/mhi/core/init.c @@ -812,10 +812,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl, if (!mhi_cntrl) return -EINVAL; - if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put) - return -EINVAL; - - if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status) + if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put || + !mhi_cntrl->status_cb || !mhi_cntrl->read_reg || + !mhi_cntrl->write_reg) return -EINVAL; ret = parse_config(mhi_cntrl, config); diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5deadfaa053a..095d95bc0e37 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -11,9 +11,6 @@ extern struct bus_type mhi_bus_type; -/* MHI MMIO register mapping */ -#define PCI_INVALID_READ(val) (val == U32_MAX) - #define MHIREGLEN (0x0) #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF) #define MHIREGLEN_MHIREGLEN_SHIFT (0) diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index eb4256b81406..97e06cc586e4 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -18,16 +18,7 @@ int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 *out) { - u32 tmp = readl(base + offset); - - /* If there is any unexpected value, query the link status */ - if (PCI_INVALID_READ(tmp) && - mhi_cntrl->link_status(mhi_cntrl)) - return -EIO; - - *out = tmp; - - return 0; + return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out); } int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, @@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 val) { - writel(val, base + offset); + mhi_cntrl->write_reg(mhi_cntrl, base + offset, val); } void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base, @@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee))) continue; mhi_dev = mhi_alloc_device(mhi_cntrl); - if (!mhi_dev) + if (IS_ERR(mhi_dev)) return; mhi_dev->dev_type = MHI_DEVICE_XFER; @@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) /* Channel name is same for both UL and DL */ mhi_dev->chan_name = mhi_chan->name; - dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan, + dev_set_name(&mhi_dev->dev, "%s_%s", + dev_name(mhi_cntrl->cntrl_dev), mhi_dev->chan_name); /* Init wakeup source if available */ diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index 52690cb5c89c..dc83d65f7784 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl) MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state), msecs_to_jiffies(mhi_cntrl->timeout_ms)); - return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO; + ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT; + if (ret) + mhi_power_down(mhi_cntrl, false); + + return ret; } EXPORT_SYMBOL(mhi_sync_power_up); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4d1e25d1ced1..4d3429b2058f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1059,7 +1059,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, update_turbo_state(); if (global.turbo_disabled) { - pr_warn("Turbo disabled by BIOS or unavailable on processor\n"); + pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); mutex_unlock(&intel_pstate_limits_lock); mutex_unlock(&intel_pstate_driver_lock); return -EPERM; diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index b7bb7c30adeb..b2f9882bc010 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -963,10 +963,12 @@ static void aead_crypt_done(struct device *jrdev, u32 *desc, u32 err, struct caam_drv_private_jr *jrp = dev_get_drvdata(jrdev); struct aead_edesc *edesc; int ecode = 0; + bool has_bklog; dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); edesc = rctx->edesc; + has_bklog = edesc->bklog; if (err) ecode = caam_jr_strstatus(jrdev, err); @@ -979,7 +981,7 @@ static void aead_crypt_done(struct device *jrdev, u32 *desc, u32 err, * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) aead_request_complete(req, ecode); else crypto_finalize_aead_request(jrp->engine, req, ecode); @@ -995,10 +997,12 @@ static void skcipher_crypt_done(struct device *jrdev, u32 *desc, u32 err, struct caam_drv_private_jr *jrp = dev_get_drvdata(jrdev); int ivsize = crypto_skcipher_ivsize(skcipher); int ecode = 0; + bool has_bklog; dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); edesc = rctx->edesc; + has_bklog = edesc->bklog; if (err) ecode = caam_jr_strstatus(jrdev, err); @@ -1028,7 +1032,7 @@ static void skcipher_crypt_done(struct device *jrdev, u32 *desc, u32 err, * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) skcipher_request_complete(req, ecode); else crypto_finalize_skcipher_request(jrp->engine, req, ecode); @@ -1711,7 +1715,7 @@ static struct skcipher_edesc *skcipher_edesc_alloc(struct skcipher_request *req, if (ivsize || mapped_dst_nents > 1) sg_to_sec4_set_last(edesc->sec4_sg + dst_sg_idx + - mapped_dst_nents); + mapped_dst_nents - 1 + !!ivsize); if (sec4_sg_bytes) { edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg, diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 943bc0296267..27ff4a3d037e 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -583,10 +583,12 @@ static inline void ahash_done_cpy(struct device *jrdev, u32 *desc, u32 err, struct caam_hash_state *state = ahash_request_ctx(req); struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash); int ecode = 0; + bool has_bklog; dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); edesc = state->edesc; + has_bklog = edesc->bklog; if (err) ecode = caam_jr_strstatus(jrdev, err); @@ -603,7 +605,7 @@ static inline void ahash_done_cpy(struct device *jrdev, u32 *desc, u32 err, * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) req->base.complete(&req->base, ecode); else crypto_finalize_hash_request(jrp->engine, req, ecode); @@ -632,10 +634,12 @@ static inline void ahash_done_switch(struct device *jrdev, u32 *desc, u32 err, struct caam_hash_state *state = ahash_request_ctx(req); int digestsize = crypto_ahash_digestsize(ahash); int ecode = 0; + bool has_bklog; dev_dbg(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err); edesc = state->edesc; + has_bklog = edesc->bklog; if (err) ecode = caam_jr_strstatus(jrdev, err); @@ -663,7 +667,7 @@ static inline void ahash_done_switch(struct device *jrdev, u32 *desc, u32 err, * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) req->base.complete(&req->base, ecode); else crypto_finalize_hash_request(jrp->engine, req, ecode); diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index 4fcae37a2e33..2e44d685618f 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -121,11 +121,13 @@ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context) struct caam_drv_private_jr *jrp = dev_get_drvdata(dev); struct rsa_edesc *edesc; int ecode = 0; + bool has_bklog; if (err) ecode = caam_jr_strstatus(dev, err); edesc = req_ctx->edesc; + has_bklog = edesc->bklog; rsa_pub_unmap(dev, edesc, req); rsa_io_unmap(dev, edesc, req); @@ -135,7 +137,7 @@ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context) * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) akcipher_request_complete(req, ecode); else crypto_finalize_akcipher_request(jrp->engine, req, ecode); @@ -152,11 +154,13 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err, struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req); struct rsa_edesc *edesc; int ecode = 0; + bool has_bklog; if (err) ecode = caam_jr_strstatus(dev, err); edesc = req_ctx->edesc; + has_bklog = edesc->bklog; switch (key->priv_form) { case FORM1: @@ -176,7 +180,7 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err, * If no backlog flag, the completion of the request is done * by CAAM, not crypto engine. */ - if (!edesc->bklog) + if (!has_bklog) akcipher_request_complete(req, ecode); else crypto_finalize_akcipher_request(jrp->engine, req, ecode); diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c index e92b352fb0ad..43d9e2420110 100644 --- a/drivers/crypto/chelsio/chcr_ktls.c +++ b/drivers/crypto/chelsio/chcr_ktls.c @@ -673,41 +673,14 @@ int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) return 0; } -/* - * chcr_write_cpl_set_tcb_ulp: update tcb values. - * TCB is responsible to create tcp headers, so all the related values - * should be correctly updated. - * @tx_info - driver specific tls info. - * @q - tx queue on which packet is going out. - * @tid - TCB identifier. - * @pos - current index where should we start writing. - * @word - TCB word. - * @mask - TCB word related mask. - * @val - TCB word related value. - * @reply - set 1 if looking for TP response. - * return - next position to write. - */ -static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - struct sge_eth_txq *q, u32 tid, - void *pos, u16 word, u64 mask, +static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + u32 tid, void *pos, u16 word, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; struct ulptx_idata *idata; struct ulp_txpkt *txpkt; - void *save_pos = NULL; - u8 buf[48] = {0}; - int left; - left = (void *)q->q.stat - pos; - if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { - if (!left) { - pos = q->q.desc; - } else { - save_pos = pos; - pos = buf; - } - } /* ULP_TXPKT */ txpkt = pos; txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); @@ -732,18 +705,54 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, idata = (struct ulptx_idata *)(cpl + 1); idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); idata->len = htonl(0); + pos = idata + 1; - if (save_pos) { - pos = chcr_copy_to_txd(buf, &q->q, save_pos, - CHCR_SET_TCB_FIELD_LEN); - } else { - /* check again if we are at the end of the queue */ - if (left == CHCR_SET_TCB_FIELD_LEN) + return pos; +} + + +/* + * chcr_write_cpl_set_tcb_ulp: update tcb values. + * TCB is responsible to create tcp headers, so all the related values + * should be correctly updated. + * @tx_info - driver specific tls info. + * @q - tx queue on which packet is going out. + * @tid - TCB identifier. + * @pos - current index where should we start writing. + * @word - TCB word. + * @mask - TCB word related mask. + * @val - TCB word related value. + * @reply - set 1 if looking for TP response. + * return - next position to write. + */ +static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q, u32 tid, + void *pos, u16 word, u64 mask, + u64 val, u32 reply) +{ + int left = (void *)q->q.stat - pos; + + if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { + if (!left) { pos = q->q.desc; - else - pos = idata + 1; + } else { + u8 buf[48] = {0}; + + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + mask, val, reply); + + return chcr_copy_to_txd(buf, &q->q, pos, + CHCR_SET_TCB_FIELD_LEN); + } } + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + mask, val, reply); + + /* check again if we are at the end of the queue */ + if (left == CHCR_SET_TCB_FIELD_LEN) + pos = q->q.desc; + return pos; } diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index ccc9eda1bc28..07df88f2e305 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -388,7 +388,8 @@ static long dma_buf_ioctl(struct file *file, return ret; - case DMA_BUF_SET_NAME: + case DMA_BUF_SET_NAME_A: + case DMA_BUF_SET_NAME_B: return dma_buf_set_name(dmabuf, (const char __user *)arg); default: @@ -655,8 +656,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put); * calls attach() of dma_buf_ops to allow device-specific attach functionality * @dmabuf: [in] buffer to attach device to. * @dev: [in] device to be attached. - * @importer_ops [in] importer operations for the attachment - * @importer_priv [in] importer private pointer for the attachment + * @importer_ops: [in] importer operations for the attachment + * @importer_priv: [in] importer private pointer for the attachment * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 092483644315..023db6883d05 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -241,7 +241,8 @@ config FSL_RAID config HISI_DMA tristate "HiSilicon DMA Engine support" - depends on ARM64 || (COMPILE_TEST && PCI_MSI) + depends on ARM64 || COMPILE_TEST + depends on PCI_MSI select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 4830ba658ce1..d31076d9ef25 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -232,10 +232,6 @@ static void chan_dev_release(struct device *dev) struct dma_chan_dev *chan_dev; chan_dev = container_of(dev, typeof(*chan_dev), device); - if (atomic_dec_and_test(chan_dev->idr_ref)) { - ida_free(&dma_ida, chan_dev->dev_id); - kfree(chan_dev->idr_ref); - } kfree(chan_dev); } @@ -1043,27 +1039,9 @@ static int get_dma_id(struct dma_device *device) } static int __dma_async_device_channel_register(struct dma_device *device, - struct dma_chan *chan, - int chan_id) + struct dma_chan *chan) { int rc = 0; - int chancnt = device->chancnt; - atomic_t *idr_ref; - struct dma_chan *tchan; - - tchan = list_first_entry_or_null(&device->channels, - struct dma_chan, device_node); - if (!tchan) - return -ENODEV; - - if (tchan->dev) { - idr_ref = tchan->dev->idr_ref; - } else { - idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL); - if (!idr_ref) - return -ENOMEM; - atomic_set(idr_ref, 0); - } chan->local = alloc_percpu(typeof(*chan->local)); if (!chan->local) @@ -1079,29 +1057,36 @@ static int __dma_async_device_channel_register(struct dma_device *device, * When the chan_id is a negative value, we are dynamically adding * the channel. Otherwise we are static enumerating. */ - chan->chan_id = chan_id < 0 ? chancnt : chan_id; + mutex_lock(&device->chan_mutex); + chan->chan_id = ida_alloc(&device->chan_ida, GFP_KERNEL); + mutex_unlock(&device->chan_mutex); + if (chan->chan_id < 0) { + pr_err("%s: unable to alloc ida for chan: %d\n", + __func__, chan->chan_id); + goto err_out; + } + chan->dev->device.class = &dma_devclass; chan->dev->device.parent = device->dev; chan->dev->chan = chan; - chan->dev->idr_ref = idr_ref; chan->dev->dev_id = device->dev_id; - atomic_inc(idr_ref); dev_set_name(&chan->dev->device, "dma%dchan%d", device->dev_id, chan->chan_id); - rc = device_register(&chan->dev->device); if (rc) - goto err_out; + goto err_out_ida; chan->client_count = 0; - device->chancnt = chan->chan_id + 1; + device->chancnt++; return 0; + err_out_ida: + mutex_lock(&device->chan_mutex); + ida_free(&device->chan_ida, chan->chan_id); + mutex_unlock(&device->chan_mutex); err_out: free_percpu(chan->local); kfree(chan->dev); - if (atomic_dec_return(idr_ref) == 0) - kfree(idr_ref); return rc; } @@ -1110,7 +1095,7 @@ int dma_async_device_channel_register(struct dma_device *device, { int rc; - rc = __dma_async_device_channel_register(device, chan, -1); + rc = __dma_async_device_channel_register(device, chan); if (rc < 0) return rc; @@ -1130,6 +1115,9 @@ static void __dma_async_device_channel_unregister(struct dma_device *device, device->chancnt--; chan->dev->chan = NULL; mutex_unlock(&dma_list_mutex); + mutex_lock(&device->chan_mutex); + ida_free(&device->chan_ida, chan->chan_id); + mutex_unlock(&device->chan_mutex); device_unregister(&chan->dev->device); free_percpu(chan->local); } @@ -1152,7 +1140,7 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_unregister); */ int dma_async_device_register(struct dma_device *device) { - int rc, i = 0; + int rc; struct dma_chan* chan; if (!device) @@ -1257,9 +1245,12 @@ int dma_async_device_register(struct dma_device *device) if (rc != 0) return rc; + mutex_init(&device->chan_mutex); + ida_init(&device->chan_ida); + /* represent channels in sysfs. Probably want devs too */ list_for_each_entry(chan, &device->channels, device_node) { - rc = __dma_async_device_channel_register(device, chan, i++); + rc = __dma_async_device_channel_register(device, chan); if (rc < 0) goto err_out; } @@ -1334,6 +1325,7 @@ void dma_async_device_unregister(struct dma_device *device) */ dma_cap_set(DMA_PRIVATE, device->cap_mask); dma_channel_rebalance(); + ida_free(&dma_ida, device->dev_id); dma_device_put(device); mutex_unlock(&dma_list_mutex); } diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index a2cadfa2e6d7..364dd34799d4 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -240,7 +240,7 @@ static bool is_threaded_test_run(struct dmatest_info *info) struct dmatest_thread *thread; list_for_each_entry(thread, &dtc->threads, node) { - if (!thread->done) + if (!thread->done && !thread->pending) return true; } } @@ -662,8 +662,8 @@ static int dmatest_func(void *data) flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT; ktime = ktime_get(); - while (!kthread_should_stop() - && !(params->iterations && total_tests >= params->iterations)) { + while (!(kthread_should_stop() || + (params->iterations && total_tests >= params->iterations))) { struct dma_async_tx_descriptor *tx = NULL; struct dmaengine_unmap_data *um; dma_addr_t *dsts; diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c index 10117f271b12..d683232d7fea 100644 --- a/drivers/dma/mmp_tdma.c +++ b/drivers/dma/mmp_tdma.c @@ -363,6 +363,8 @@ static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac) gen_pool_free(gpool, (unsigned long)tdmac->desc_arr, size); tdmac->desc_arr = NULL; + if (tdmac->status == DMA_ERROR) + tdmac->status = DMA_COMPLETE; return; } @@ -443,7 +445,8 @@ static struct dma_async_tx_descriptor *mmp_tdma_prep_dma_cyclic( if (!desc) goto err_out; - mmp_tdma_config_write(chan, direction, &tdmac->slave_config); + if (mmp_tdma_config_write(chan, direction, &tdmac->slave_config)) + goto err_out; while (buf < buf_len) { desc = &tdmac->desc_arr[i]; diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c index 581e7a290d98..a3b0b4c56a19 100644 --- a/drivers/dma/pch_dma.c +++ b/drivers/dma/pch_dma.c @@ -865,6 +865,7 @@ static int pch_dma_probe(struct pci_dev *pdev, } pci_set_master(pdev); + pd->dma.dev = &pdev->dev; err = request_irq(pdev->irq, pd_irq, IRQF_SHARED, DRV_NAME, pd); if (err) { @@ -880,7 +881,6 @@ static int pch_dma_probe(struct pci_dev *pdev, goto err_free_irq; } - pd->dma.dev = &pdev->dev; INIT_LIST_HEAD(&pd->dma.channels); diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index f6a2f42ffc51..b9f0d9636620 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -816,6 +816,13 @@ static bool tegra_dma_eoc_interrupt_deasserted(struct tegra_dma_channel *tdc) static void tegra_dma_synchronize(struct dma_chan *dc) { struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc); + int err; + + err = pm_runtime_get_sync(tdc->tdma->dev); + if (err < 0) { + dev_err(tdc2dev(tdc), "Failed to synchronize DMA: %d\n", err); + return; + } /* * CPU, which handles interrupt, could be busy in @@ -825,6 +832,8 @@ static void tegra_dma_synchronize(struct dma_chan *dc) wait_event(tdc->wq, tegra_dma_eoc_interrupt_deasserted(tdc)); tasklet_kill(&tdc->tasklet); + + pm_runtime_put(tdc->tdma->dev); } static unsigned int tegra_dma_sg_bytes_xferred(struct tegra_dma_channel *tdc, diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c index d7b965049ccb..fb7c8150b0d1 100644 --- a/drivers/dma/ti/k3-psil.c +++ b/drivers/dma/ti/k3-psil.c @@ -27,6 +27,7 @@ struct psil_endpoint_config *psil_get_ep_config(u32 thread_id) soc_ep_map = &j721e_ep_map; } else { pr_err("PSIL: No compatible machine found for map\n"); + mutex_unlock(&ep_map_mutex); return ERR_PTR(-ENOTSUPP); } pr_debug("%s: Using map for %s\n", __func__, soc_ep_map->name); diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index aecd5a35a296..5429497d3560 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -1230,16 +1230,16 @@ static enum dma_status xilinx_dma_tx_status(struct dma_chan *dchan, return ret; spin_lock_irqsave(&chan->lock, flags); - - desc = list_last_entry(&chan->active_list, - struct xilinx_dma_tx_descriptor, node); - /* - * VDMA and simple mode do not support residue reporting, so the - * residue field will always be 0. - */ - if (chan->has_sg && chan->xdev->dma_config->dmatype != XDMA_TYPE_VDMA) - residue = xilinx_dma_get_residue(chan, desc); - + if (!list_empty(&chan->active_list)) { + desc = list_last_entry(&chan->active_list, + struct xilinx_dma_tx_descriptor, node); + /* + * VDMA and simple mode do not support residue reporting, so the + * residue field will always be 0. + */ + if (chan->has_sg && chan->xdev->dma_config->dmatype != XDMA_TYPE_VDMA) + residue = xilinx_dma_get_residue(chan, desc); + } spin_unlock_irqrestore(&chan->lock, flags); dma_set_residue(txstate, residue); diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 31f9f0e369b9..55b031d2c989 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -16,7 +16,7 @@ int efi_tpm_final_log_size; EXPORT_SYMBOL(efi_tpm_final_log_size); -static int tpm2_calc_event_log_size(void *data, int count, void *size_info) +static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info) { struct tcg_pcr_event2_head *header; int event_size, size = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f84f9e35a73b..affde2de2a0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3372,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - - amdgpu_amdkfd_suspend(adev, !fbcon); - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); + amdgpu_amdkfd_suspend(adev, !fbcon); + /* evict vram memory */ amdgpu_bo_evict_vram(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8ea86ffdea0d..466bfe541e45 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -85,9 +85,10 @@ * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask * - 3.36.0 - Allow reading more status registers on si/cik + * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 36 +#define KMS_DRIVER_MINOR 37 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h index 074a9a09c0a7..a5b60c9a2418 100644 --- a/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h +++ b/drivers/gpu/drm/amd/amdgpu/navi10_sdma_pkt_open.h @@ -73,6 +73,22 @@ #define SDMA_OP_AQL_COPY 0 #define SDMA_OP_AQL_BARRIER_OR 0 +#define SDMA_GCR_RANGE_IS_PA (1 << 18) +#define SDMA_GCR_SEQ(x) (((x) & 0x3) << 16) +#define SDMA_GCR_GL2_WB (1 << 15) +#define SDMA_GCR_GL2_INV (1 << 14) +#define SDMA_GCR_GL2_DISCARD (1 << 13) +#define SDMA_GCR_GL2_RANGE(x) (((x) & 0x3) << 11) +#define SDMA_GCR_GL2_US (1 << 10) +#define SDMA_GCR_GL1_INV (1 << 9) +#define SDMA_GCR_GLV_INV (1 << 8) +#define SDMA_GCR_GLK_INV (1 << 7) +#define SDMA_GCR_GLK_WB (1 << 6) +#define SDMA_GCR_GLM_INV (1 << 5) +#define SDMA_GCR_GLM_WB (1 << 4) +#define SDMA_GCR_GL1_RANGE(x) (((x) & 0x3) << 2) +#define SDMA_GCR_GLI_INV(x) (((x) & 0x3) << 0) + /*define for op field*/ #define SDMA_PKT_HEADER_op_offset 0 #define SDMA_PKT_HEADER_op_mask 0x000000FF diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index ebfd2cdf4e65..d2840c2f6286 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -382,6 +382,18 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring, unsigned vmid = AMDGPU_JOB_GET_VMID(job); uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid); + /* Invalidate L2, because if we don't do it, we might get stale cache + * lines from previous IBs. + */ + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_GCR_REQ)); + amdgpu_ring_write(ring, 0); + amdgpu_ring_write(ring, (SDMA_GCR_GL2_INV | + SDMA_GCR_GL2_WB | + SDMA_GCR_GLM_INV | + SDMA_GCR_GLM_WB) << 16); + amdgpu_ring_write(ring, 0xffffff80); + amdgpu_ring_write(ring, 0xffff); + /* An IB packet must end on a 8 DW boundary--the next dword * must be on a 8-dword boundary. Our IB packet below is 6 * dwords long, thus add x number of NOPs, such that, in @@ -1595,7 +1607,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = { SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 + 10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */ - .emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */ + .emit_ib_size = 5 + 7 + 6, /* sdma_v5_0_ring_emit_ib */ .emit_ib = sdma_v5_0_ring_emit_ib, .emit_fence = sdma_v5_0_ring_emit_fence, .emit_pipeline_sync = sdma_v5_0_ring_emit_pipeline_sync, 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 c5ba5d46a148..9c83c1303f08 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2008,17 +2008,22 @@ void amdgpu_dm_update_connector_after_detect( dc_sink_retain(aconnector->dc_sink); if (sink->dc_edid.length == 0) { aconnector->edid = NULL; - drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); + if (aconnector->dc_link->aux_mode) { + drm_dp_cec_unset_edid( + &aconnector->dm_dp_aux.aux); + } } else { aconnector->edid = - (struct edid *) sink->dc_edid.raw_edid; - + (struct edid *)sink->dc_edid.raw_edid; drm_connector_update_edid_property(connector, - aconnector->edid); - drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, - aconnector->edid); + aconnector->edid); + + if (aconnector->dc_link->aux_mode) + drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, + aconnector->edid); } + amdgpu_dm_update_freesync_caps(connector, aconnector->edid); update_connector_ext_caps(aconnector); } else { @@ -3340,7 +3345,8 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev, const union dc_tiling_info *tiling_info, const uint64_t info, struct dc_plane_dcc_param *dcc, - struct dc_plane_address *address) + struct dc_plane_address *address, + bool force_disable_dcc) { struct dc *dc = adev->dm.dc; struct dc_dcc_surface_param input; @@ -3352,6 +3358,9 @@ fill_plane_dcc_attributes(struct amdgpu_device *adev, memset(&input, 0, sizeof(input)); memset(&output, 0, sizeof(output)); + if (force_disable_dcc) + return 0; + if (!offset) return 0; @@ -3401,7 +3410,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev, union dc_tiling_info *tiling_info, struct plane_size *plane_size, struct dc_plane_dcc_param *dcc, - struct dc_plane_address *address) + struct dc_plane_address *address, + bool force_disable_dcc) { const struct drm_framebuffer *fb = &afb->base; int ret; @@ -3507,7 +3517,8 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev, ret = fill_plane_dcc_attributes(adev, afb, format, rotation, plane_size, tiling_info, - tiling_flags, dcc, address); + tiling_flags, dcc, address, + force_disable_dcc); if (ret) return ret; } @@ -3599,7 +3610,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, const struct drm_plane_state *plane_state, const uint64_t tiling_flags, struct dc_plane_info *plane_info, - struct dc_plane_address *address) + struct dc_plane_address *address, + bool force_disable_dcc) { const struct drm_framebuffer *fb = plane_state->fb; const struct amdgpu_framebuffer *afb = @@ -3681,7 +3693,8 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, plane_info->rotation, tiling_flags, &plane_info->tiling_info, &plane_info->plane_size, - &plane_info->dcc, address); + &plane_info->dcc, address, + force_disable_dcc); if (ret) return ret; @@ -3704,6 +3717,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, struct dc_plane_info plane_info; uint64_t tiling_flags; int ret; + bool force_disable_dcc = false; ret = fill_dc_scaling_info(plane_state, &scaling_info); if (ret) @@ -3718,9 +3732,11 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, if (ret) return ret; + force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend; ret = fill_dc_plane_info_and_addr(adev, plane_state, tiling_flags, &plane_info, - &dc_plane_state->address); + &dc_plane_state->address, + force_disable_dcc); if (ret) return ret; @@ -5342,6 +5358,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, uint64_t tiling_flags; uint32_t domain; int r; + bool force_disable_dcc = false; dm_plane_state_old = to_dm_plane_state(plane->state); dm_plane_state_new = to_dm_plane_state(new_state); @@ -5400,11 +5417,13 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, dm_plane_state_old->dc_state != dm_plane_state_new->dc_state) { struct dc_plane_state *plane_state = dm_plane_state_new->dc_state; + force_disable_dcc = adev->asic_type == CHIP_RAVEN && adev->in_suspend; fill_plane_buffer_attributes( adev, afb, plane_state->format, plane_state->rotation, tiling_flags, &plane_state->tiling_info, &plane_state->plane_size, &plane_state->dcc, - &plane_state->address); + &plane_state->address, + force_disable_dcc); } return 0; @@ -6676,7 +6695,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, fill_dc_plane_info_and_addr( dm->adev, new_plane_state, tiling_flags, &bundle->plane_infos[planes_count], - &bundle->flip_addrs[planes_count].address); + &bundle->flip_addrs[planes_count].address, + false); + + DRM_DEBUG_DRIVER("plane: id=%d dcc_en=%d\n", + new_plane_state->plane->index, + bundle->plane_infos[planes_count].dcc.enable); bundle->surface_updates[planes_count].plane_info = &bundle->plane_infos[planes_count]; @@ -8096,7 +8120,8 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm, ret = fill_dc_plane_info_and_addr( dm->adev, new_plane_state, tiling_flags, plane_info, - &flip_addr->address); + &flip_addr->address, + false); if (ret) goto cleanup; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8489f1e56892..47431ca6986d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; - int count = 0; - struct pipe_ctx *pipe; PERF_TRACE(); for (i = 0; i < MAX_PIPES; i++) { - pipe = &context->res_ctx.pipe_ctx[i]; + int count = 0; + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->plane_state) continue; 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 7cbb1efb4f68..27a7d2a58079 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 @@ -2908,6 +2908,12 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd sizeof(hpd_irq_dpcd_data), "Status: "); + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link) + link->dc->hwss.blank_stream(pipe_ctx); + } + for (i = 0; i < MAX_PIPES; i++) { pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link) @@ -2927,6 +2933,12 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) dc_link_reallocate_mst_payload(link); + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link) + link->dc->hwss.unblank_stream(pipe_ctx, &previous_link_settings); + } + status = false; if (out_link_loss) *out_link_loss = true; @@ -4227,6 +4239,21 @@ void dp_set_fec_enable(struct dc_link *link, bool enable) void dpcd_set_source_specific_data(struct dc_link *link) { const uint32_t post_oui_delay = 30; // 30ms + uint8_t dspc = 0; + enum dc_status ret = DC_ERROR_UNEXPECTED; + + ret = core_link_read_dpcd(link, DP_DOWN_STREAM_PORT_COUNT, &dspc, + sizeof(dspc)); + + if (ret != DC_OK) { + DC_LOG_ERROR("Error in DP aux read transaction," + " not writing source specific data\n"); + return; + } + + /* Return if OUI unsupported */ + if (!(dspc & DP_OUI_SUPPORT)) + return; if (!link->dc->vendor_signature.is_valid) { struct dpcd_amd_signature amd_signature; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 6ddbb00ed37a..4f0e7203dba4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -231,34 +231,6 @@ struct dc_stream_status *dc_stream_get_status( return dc_stream_get_status_from_state(dc->current_state, stream); } -static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc) -{ -#if defined(CONFIG_DRM_AMD_DC_DCN) - unsigned int vupdate_line; - unsigned int lines_to_vupdate, us_to_vupdate, vpos, nvpos; - struct dc_stream_state *stream = pipe_ctx->stream; - unsigned int us_per_line; - - if (stream->ctx->asic_id.chip_family == FAMILY_RV && - ASICREV_IS_RAVEN(stream->ctx->asic_id.hw_internal_rev)) { - - vupdate_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); - if (!dc_stream_get_crtc_position(dc, &stream, 1, &vpos, &nvpos)) - return; - - if (vpos >= vupdate_line) - return; - - us_per_line = stream->timing.h_total * 10000 / stream->timing.pix_clk_100hz; - lines_to_vupdate = vupdate_line - vpos; - us_to_vupdate = lines_to_vupdate * us_per_line; - - /* 70 us is a conservative estimate of cursor update time*/ - if (us_to_vupdate < 70) - udelay(us_to_vupdate); - } -#endif -} /** * dc_stream_set_cursor_attributes() - Update cursor attributes and set cursor surface address @@ -298,9 +270,7 @@ bool dc_stream_set_cursor_attributes( if (!pipe_to_program) { pipe_to_program = pipe_ctx; - - delay_cursor_until_vupdate(pipe_ctx, dc); - dc->hwss.pipe_control_lock(dc, pipe_to_program, true); + dc->hwss.cursor_lock(dc, pipe_to_program, true); } dc->hwss.set_cursor_attribute(pipe_ctx); @@ -309,7 +279,7 @@ bool dc_stream_set_cursor_attributes( } if (pipe_to_program) - dc->hwss.pipe_control_lock(dc, pipe_to_program, false); + dc->hwss.cursor_lock(dc, pipe_to_program, false); return true; } @@ -349,16 +319,14 @@ bool dc_stream_set_cursor_position( if (!pipe_to_program) { pipe_to_program = pipe_ctx; - - delay_cursor_until_vupdate(pipe_ctx, dc); - dc->hwss.pipe_control_lock(dc, pipe_to_program, true); + dc->hwss.cursor_lock(dc, pipe_to_program, true); } dc->hwss.set_cursor_position(pipe_ctx); } if (pipe_to_program) - dc->hwss.pipe_control_lock(dc, pipe_to_program, false); + dc->hwss.cursor_lock(dc, pipe_to_program, false); return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index c279982947e1..10527593868c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2757,6 +2757,7 @@ static const struct hw_sequencer_funcs dce110_funcs = { .disable_plane = dce110_power_down_fe, .pipe_control_lock = dce_pipe_control_lock, .interdependent_update_lock = NULL, + .cursor_lock = dce_pipe_control_lock, .prepare_bandwidth = dce110_prepare_bandwidth, .optimize_bandwidth = dce110_optimize_bandwidth, .set_drr = set_drr, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index b0357546471b..085c1a39b313 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1625,6 +1625,16 @@ void dcn10_pipe_control_lock( hws->funcs.verify_allow_pstate_change_high(dc); } +void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock) +{ + /* cursor lock is per MPCC tree, so only need to lock one pipe per stream */ + if (!pipe || pipe->top_pipe) + return; + + dc->res_pool->mpc->funcs->cursor_lock(dc->res_pool->mpc, + pipe->stream_res.opp->inst, lock); +} + static bool wait_for_reset_trigger_to_occur( struct dc_context *dc_ctx, struct timing_generator *tg) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h index 16a50e05ffbf..af51424315d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h @@ -49,6 +49,7 @@ void dcn10_pipe_control_lock( struct dc *dc, struct pipe_ctx *pipe, bool lock); +void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock); void dcn10_blank_pixel_data( struct dc *dc, struct pipe_ctx *pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c index dd02d3983695..700509bdf503 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c @@ -50,6 +50,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .disable_audio_stream = dce110_disable_audio_stream, .disable_plane = dcn10_disable_plane, .pipe_control_lock = dcn10_pipe_control_lock, + .cursor_lock = dcn10_cursor_lock, .interdependent_update_lock = dcn10_lock_all_pipes, .prepare_bandwidth = dcn10_prepare_bandwidth, .optimize_bandwidth = dcn10_optimize_bandwidth, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c index 04f863499cfb..3fcd408e9103 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c @@ -223,6 +223,9 @@ struct mpcc *mpc1_insert_plane( REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, dpp_id); REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, tree->opp_id); + /* Configure VUPDATE lock set for this MPCC to map to the OPP */ + REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, tree->opp_id); + /* update mpc tree mux setting */ if (tree->opp_list == insert_above_mpcc) { /* insert the toppest mpcc */ @@ -318,6 +321,7 @@ void mpc1_remove_mpcc( REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf); REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf); REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, 0xf); + REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf); /* mark this mpcc as not in use */ mpc10->mpcc_in_use_mask &= ~(1 << mpcc_id); @@ -328,6 +332,7 @@ void mpc1_remove_mpcc( REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf); REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf); REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, 0xf); + REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf); } } @@ -361,6 +366,7 @@ void mpc1_mpc_init(struct mpc *mpc) REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf); REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf); REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, 0xf); + REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf); mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id); } @@ -381,6 +387,7 @@ void mpc1_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id) REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf); REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf); REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, 0xf); + REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf); mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id); @@ -453,6 +460,13 @@ void mpc1_read_mpcc_state( MPCC_BUSY, &s->busy); } +void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock) +{ + struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc); + + REG_SET(CUR[opp_id], 0, CUR_VUPDATE_LOCK_SET, lock ? 1 : 0); +} + static const struct mpc_funcs dcn10_mpc_funcs = { .read_mpcc_state = mpc1_read_mpcc_state, .insert_plane = mpc1_insert_plane, @@ -464,6 +478,7 @@ static const struct mpc_funcs dcn10_mpc_funcs = { .assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect, .init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw, .update_blending = mpc1_update_blending, + .cursor_lock = mpc1_cursor_lock, .set_denorm = NULL, .set_denorm_clamp = NULL, .set_output_csc = NULL, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h index 962a68e322ee..66a4719c22a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h @@ -39,11 +39,12 @@ SRII(MPCC_BG_G_Y, MPCC, inst),\ SRII(MPCC_BG_R_CR, MPCC, inst),\ SRII(MPCC_BG_B_CB, MPCC, inst),\ - SRII(MPCC_BG_B_CB, MPCC, inst),\ - SRII(MPCC_SM_CONTROL, MPCC, inst) + SRII(MPCC_SM_CONTROL, MPCC, inst),\ + SRII(MPCC_UPDATE_LOCK_SEL, MPCC, inst) #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0(inst) \ - SRII(MUX, MPC_OUT, inst) + SRII(MUX, MPC_OUT, inst),\ + VUPDATE_SRII(CUR, VUPDATE_LOCK_SET, inst) #define MPC_COMMON_REG_VARIABLE_LIST \ uint32_t MPCC_TOP_SEL[MAX_MPCC]; \ @@ -55,7 +56,9 @@ uint32_t MPCC_BG_R_CR[MAX_MPCC]; \ uint32_t MPCC_BG_B_CB[MAX_MPCC]; \ uint32_t MPCC_SM_CONTROL[MAX_MPCC]; \ - uint32_t MUX[MAX_OPP]; + uint32_t MUX[MAX_OPP]; \ + uint32_t MPCC_UPDATE_LOCK_SEL[MAX_MPCC]; \ + uint32_t CUR[MAX_OPP]; #define MPC_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\ SF(MPCC0_MPCC_TOP_SEL, MPCC_TOP_SEL, mask_sh),\ @@ -78,7 +81,8 @@ SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FIELD_ALT, mask_sh),\ SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_FRAME_POL, mask_sh),\ SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_TOP_POL, mask_sh),\ - SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh) + SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh),\ + SF(MPCC0_MPCC_UPDATE_LOCK_SEL, MPCC_UPDATE_LOCK_SEL, mask_sh) #define MPC_REG_FIELD_LIST(type) \ type MPCC_TOP_SEL;\ @@ -101,7 +105,9 @@ type MPCC_SM_FIELD_ALT;\ type MPCC_SM_FORCE_NEXT_FRAME_POL;\ type MPCC_SM_FORCE_NEXT_TOP_POL;\ - type MPC_OUT_MUX; + type MPC_OUT_MUX;\ + type MPCC_UPDATE_LOCK_SEL;\ + type CUR_VUPDATE_LOCK_SET; struct dcn_mpc_registers { MPC_COMMON_REG_VARIABLE_LIST @@ -192,4 +198,6 @@ void mpc1_read_mpcc_state( int mpcc_inst, struct mpcc_state *s); +void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 07265ca7d28c..ba849aa31e6e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -181,6 +181,14 @@ enum dcn10_clk_src_array_id { .reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define VUPDATE_SRII(reg_name, block, id)\ + .reg_name[id] = BASE(mm ## reg_name ## 0 ## _ ## block ## id ## _BASE_IDX) + \ + mm ## reg_name ## 0 ## _ ## block ## id + +/* set field/register/bitfield name */ +#define SFRB(field_name, reg_name, bitfield, post_fix)\ + .field_name = reg_name ## __ ## bitfield ## post_fix + /* NBIO */ #define NBIO_BASE_INNER(seg) \ NBIF_BASE__INST0_SEG ## seg @@ -419,11 +427,13 @@ static const struct dcn_mpc_registers mpc_regs = { }; static const struct dcn_mpc_shift mpc_shift = { - MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT) + MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT),\ + SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, __SHIFT) }; static const struct dcn_mpc_mask mpc_mask = { - MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK), + MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK),\ + SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, _MASK) }; #define tg_regs(id)\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 22f421e82733..a023a4d59f41 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2294,7 +2294,8 @@ void dcn20_fpga_init_hw(struct dc *dc) REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2); REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1); - REG_WRITE(REFCLK_CNTL, 0); + if (REG(REFCLK_CNTL)) + REG_WRITE(REFCLK_CNTL, 0); // diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c index 1e73357eda34..6a21228893ee 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c @@ -52,6 +52,7 @@ static const struct hw_sequencer_funcs dcn20_funcs = { .disable_plane = dcn20_disable_plane, .pipe_control_lock = dcn20_pipe_control_lock, .interdependent_update_lock = dcn10_lock_all_pipes, + .cursor_lock = dcn10_cursor_lock, .prepare_bandwidth = dcn20_prepare_bandwidth, .optimize_bandwidth = dcn20_optimize_bandwidth, .update_bandwidth = dcn20_update_bandwidth, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c index de9c857ab3e9..570dfd9a243f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c @@ -545,6 +545,7 @@ const struct mpc_funcs dcn20_mpc_funcs = { .mpc_init = mpc1_mpc_init, .mpc_init_single_inst = mpc1_mpc_init_single_inst, .update_blending = mpc2_update_blending, + .cursor_lock = mpc1_cursor_lock, .get_mpcc_for_dpp = mpc2_get_mpcc_for_dpp, .wait_for_idle = mpc2_assert_idle_mpcc, .assert_mpcc_idle_before_connect = mpc2_assert_mpcc_idle_before_connect, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h index c78fd5123497..496658f420db 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h @@ -179,7 +179,8 @@ SF(MPC_OUT0_DENORM_CLAMP_G_Y, MPC_OUT_DENORM_CLAMP_MAX_G_Y, mask_sh),\ SF(MPC_OUT0_DENORM_CLAMP_G_Y, MPC_OUT_DENORM_CLAMP_MIN_G_Y, mask_sh),\ SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MAX_B_CB, mask_sh),\ - SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh) + SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh),\ + SF(CUR_VUPDATE_LOCK_SET0, CUR_VUPDATE_LOCK_SET, mask_sh) /* * DCN2 MPC_OCSC debug status register: diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 5cdbba0cd873..e4348e3b6389 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -508,6 +508,10 @@ enum dcn20_clk_src_array_id { .block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define VUPDATE_SRII(reg_name, block, id)\ + .reg_name[id] = BASE(mm ## reg_name ## _ ## block ## id ## _BASE_IDX) + \ + mm ## reg_name ## _ ## block ## id + /* NBIO */ #define NBIO_BASE_INNER(seg) \ NBIO_BASE__INST0_SEG ## seg @@ -3064,25 +3068,32 @@ validate_out: return out; } - -bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, - bool fast_validate) +/* + * This must be noinline to ensure anything that deals with FP registers + * is contained within this call; previously our compiling with hard-float + * would result in fp instructions being emitted outside of the boundaries + * of the DC_FP_START/END macros, which makes sense as the compiler has no + * idea about what is wrapped and what is not + * + * This is largely just a workaround to avoid breakage introduced with 5.6, + * ideally all fp-using code should be moved into its own file, only that + * should be compiled with hard-float, and all code exported from there + * should be strictly wrapped with DC_FP_START/END + */ +static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, bool fast_validate) { bool voltage_supported = false; bool full_pstate_supported = false; bool dummy_pstate_supported = false; double p_state_latency_us; - DC_FP_START(); p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = dc->debug.disable_dram_clock_change_vactive_support; if (fast_validate) { - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true); - - DC_FP_END(); - return voltage_supported; + return dcn20_validate_bandwidth_internal(dc, context, true); } // Best case, we support full UCLK switch latency @@ -3111,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, restore_dml_state: context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; +} +bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, + bool fast_validate) +{ + bool voltage_supported = false; + DC_FP_START(); + voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate); DC_FP_END(); return voltage_supported; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c index b9ff9767e08f..707ce0f28fab 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c @@ -53,6 +53,7 @@ static const struct hw_sequencer_funcs dcn21_funcs = { .disable_plane = dcn20_disable_plane, .pipe_control_lock = dcn20_pipe_control_lock, .interdependent_update_lock = dcn10_lock_all_pipes, + .cursor_lock = dcn10_cursor_lock, .prepare_bandwidth = dcn20_prepare_bandwidth, .optimize_bandwidth = dcn20_optimize_bandwidth, .update_bandwidth = dcn20_update_bandwidth, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index b25484aa8222..a721bb401ef0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -284,7 +284,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .dram_channel_width_bytes = 4, .fabric_datapath_to_dcn_data_return_bytes = 32, .dcn_downspread_percent = 0.5, - .downspread_percent = 0.5, + .downspread_percent = 0.38, .dram_page_open_time_ns = 50.0, .dram_rw_turnaround_time_ns = 17.5, .dram_return_buffer_per_channel_bytes = 8192, @@ -340,6 +340,10 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = { .block ## _ ## reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \ mm ## block ## id ## _ ## reg_name +#define VUPDATE_SRII(reg_name, block, id)\ + .reg_name[id] = BASE(mm ## reg_name ## _ ## block ## id ## _BASE_IDX) + \ + mm ## reg_name ## _ ## block ## id + /* NBIO */ #define NBIO_BASE_INNER(seg) \ NBIF0_BASE__INST0_SEG ## seg @@ -1374,64 +1378,49 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param { struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool); struct clk_limit_table *clk_table = &bw_params->clk_table; - unsigned int i, j, k; - int closest_clk_lvl; + struct _vcs_dpi_voltage_scaling_st clock_limits[DC__VOLTAGE_STATES]; + unsigned int i, j, closest_clk_lvl; // Default clock levels are used for diags, which may lead to overclocking. - if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment)) { + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator; dcn2_1_ip.max_num_dpp = pool->base.pipe_count; dcn2_1_soc.num_chans = bw_params->num_channels; - /* Vmin: leave lowest DCN clocks, override with dcfclk, fclk, memclk from fuse */ - dcn2_1_soc.clock_limits[0].state = 0; - dcn2_1_soc.clock_limits[0].dcfclk_mhz = clk_table->entries[0].dcfclk_mhz; - dcn2_1_soc.clock_limits[0].fabricclk_mhz = clk_table->entries[0].fclk_mhz; - dcn2_1_soc.clock_limits[0].socclk_mhz = clk_table->entries[0].socclk_mhz; - dcn2_1_soc.clock_limits[0].dram_speed_mts = clk_table->entries[0].memclk_mhz * 2; - - /* - * Other levels: find closest DCN clocks that fit the given clock limit using dcfclk - * as indicator - */ - - closest_clk_lvl = -1; - /* index currently being filled */ - k = 1; - for (i = 1; i < clk_table->num_entries; i++) { - /* loop backwards, skip duplicate state*/ - for (j = dcn2_1_soc.num_states - 1; j >= k; j--) { + ASSERT(clk_table->num_entries); + for (i = 0; i < clk_table->num_entries; i++) { + /* loop backwards*/ + for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) { if ((unsigned int) dcn2_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) { closest_clk_lvl = j; break; } } - /* if found a lvl that fits, use the DCN clks from it, if not, go to next clk limit*/ - if (closest_clk_lvl != -1) { - dcn2_1_soc.clock_limits[k].state = i; - dcn2_1_soc.clock_limits[k].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; - dcn2_1_soc.clock_limits[k].fabricclk_mhz = clk_table->entries[i].fclk_mhz; - dcn2_1_soc.clock_limits[k].socclk_mhz = clk_table->entries[i].socclk_mhz; - dcn2_1_soc.clock_limits[k].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; + clock_limits[i].state = i; + clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz; + clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz; + clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz; + clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2; - dcn2_1_soc.clock_limits[k].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz; - dcn2_1_soc.clock_limits[k].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz; - dcn2_1_soc.clock_limits[k].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; - dcn2_1_soc.clock_limits[k].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz; - dcn2_1_soc.clock_limits[k].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; - dcn2_1_soc.clock_limits[k].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; - dcn2_1_soc.clock_limits[k].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz; - k++; - } + clock_limits[i].dispclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz; + clock_limits[i].dppclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz; + clock_limits[i].dram_bw_per_chan_gbps = dcn2_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps; + clock_limits[i].dscclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz; + clock_limits[i].dtbclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz; + clock_limits[i].phyclk_d18_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz; + clock_limits[i].phyclk_mhz = dcn2_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz; + } + for (i = 0; i < clk_table->num_entries; i++) + dcn2_1_soc.clock_limits[i] = clock_limits[i]; + if (clk_table->num_entries) { + dcn2_1_soc.num_states = clk_table->num_entries; + /* duplicate last level */ + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; + dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; } - dcn2_1_soc.num_states = k; } - /* duplicate last level */ - dcn2_1_soc.clock_limits[dcn2_1_soc.num_states] = dcn2_1_soc.clock_limits[dcn2_1_soc.num_states - 1]; - dcn2_1_soc.clock_limits[dcn2_1_soc.num_states].state = dcn2_1_soc.num_states; - dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index a38baa73d484..b8ec08e3b7a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params( min_hratio_fact_l = 1.0; min_hratio_fact_c = 1.0; - if (htaps_l <= 1) + if (hratio_l <= 1) min_hratio_fact_l = 2.0; else if (htaps_l <= 6) { if ((hratio_l * 2.0) > 4.0) @@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params( hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz; - if (htaps_c <= 1) + if (hratio_c <= 1) min_hratio_fact_c = 2.0; else if (htaps_c <= 6) { if ((hratio_c * 2.0) > 4.0) @@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params( disp_dlg_regs->refcyc_per_vm_group_vblank = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; disp_dlg_regs->refcyc_per_vm_group_flip = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; + disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); + disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); // Clamp to max for now if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23)) diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h index 094afc4c8173..50ee8aa7ec3b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h @@ -210,6 +210,22 @@ struct mpc_funcs { struct mpcc_blnd_cfg *blnd_cfg, int mpcc_id); + /* + * Lock cursor updates for the specified OPP. + * OPP defines the set of MPCC that are locked together for cursor. + * + * Parameters: + * [in] mpc - MPC context. + * [in] opp_id - The OPP to lock cursor updates on + * [in] lock - lock/unlock the OPP + * + * Return: void + */ + void (*cursor_lock)( + struct mpc *mpc, + int opp_id, + bool lock); + struct mpcc* (*get_mpcc_for_dpp)( struct mpc_tree *tree, int dpp_id); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index d4c1fb242c63..e57467d99d66 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -86,6 +86,7 @@ struct hw_sequencer_funcs { struct dc_state *context, bool lock); void (*set_flip_control_gsl)(struct pipe_ctx *pipe_ctx, bool flip_immediate); + void (*cursor_lock)(struct dc *dc, struct pipe_ctx *pipe, bool lock); /* Timing Related */ void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes, diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index c34eba19860a..6d7bca562eec 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -108,7 +108,7 @@ #define ASSERT(expr) ASSERT_CRITICAL(expr) #else -#define ASSERT(expr) WARN_ON(!(expr)) +#define ASSERT(expr) WARN_ON_ONCE(!(expr)) #endif #define BREAK_TO_DEBUGGER() ASSERT(0) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index 2a12614a12c2..e4e5a53b2b4e 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -1435,7 +1435,8 @@ static int pp_get_asic_baco_capability(void *handle, bool *cap) if (!hwmgr) return -EINVAL; - if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_capability) + if (!(hwmgr->not_vf && amdgpu_dpm) || + !hwmgr->hwmgr_func->get_asic_baco_capability) return 0; mutex_lock(&hwmgr->smu_lock); @@ -1452,8 +1453,7 @@ static int pp_get_asic_baco_state(void *handle, int *state) if (!hwmgr) return -EINVAL; - if (!(hwmgr->not_vf && amdgpu_dpm) || - !hwmgr->hwmgr_func->get_asic_baco_state) + if (!hwmgr->pm_en || !hwmgr->hwmgr_func->get_asic_baco_state) return 0; mutex_lock(&hwmgr->smu_lock); @@ -1470,7 +1470,8 @@ static int pp_set_asic_baco_state(void *handle, int state) if (!hwmgr) return -EINVAL; - if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_asic_baco_state) + if (!(hwmgr->not_vf && amdgpu_dpm) || + !hwmgr->hwmgr_func->set_asic_baco_state) return 0; mutex_lock(&hwmgr->smu_lock); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 283615e44838..9d89ebf3a749 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -3442,8 +3442,12 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr, drm_dp_queue_down_tx(mgr, txmsg); ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); - if (ret > 0 && txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) - ret = -EIO; + if (ret > 0) { + if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) + ret = -EIO; + else + ret = size; + } kfree(txmsg); fail_put: diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 116451101426..4ede08a84e37 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -5111,7 +5111,7 @@ static struct drm_display_mode *drm_mode_displayid_detailed(struct drm_device *d struct drm_display_mode *mode; unsigned pixel_clock = (timings->pixel_clock[0] | (timings->pixel_clock[1] << 8) | - (timings->pixel_clock[2] << 16)); + (timings->pixel_clock[2] << 16)) + 1; unsigned hactive = (timings->hactive[0] | timings->hactive[1] << 8) + 1; unsigned hblank = (timings->hblank[0] | timings->hblank[1] << 8) + 1; unsigned hsync = (timings->hsync[0] | (timings->hsync[1] & 0x7f) << 8) + 1; diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c index 7f386adcf872..910108ccaae1 100644 --- a/drivers/gpu/drm/drm_hdcp.c +++ b/drivers/gpu/drm/drm_hdcp.c @@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev, ret = request_firmware_direct(&fw, (const char *)fw_name, drm_dev->dev); - if (ret < 0) + if (ret < 0) { + *revoked_ksv_cnt = 0; + *revoked_ksv_list = NULL; + ret = 0; goto exit; + } if (fw->size && fw->data) ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list, @@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs, ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list, &revoked_ksv_cnt); + if (ret) + return ret; /* revoked_ksv_cnt will be zero when above function failed */ for (i = 0; i < revoked_ksv_cnt; i++) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index 37f77aee1212..0158e49bf9bb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -182,21 +182,35 @@ i915_gem_object_fence_prepare(struct drm_i915_gem_object *obj, int tiling_mode, unsigned int stride) { struct i915_ggtt *ggtt = &to_i915(obj->base.dev)->ggtt; - struct i915_vma *vma; + struct i915_vma *vma, *vn; + LIST_HEAD(unbind); int ret = 0; if (tiling_mode == I915_TILING_NONE) return 0; mutex_lock(&ggtt->vm.mutex); + + spin_lock(&obj->vma.lock); for_each_ggtt_vma(vma, obj) { + GEM_BUG_ON(vma->vm != &ggtt->vm); + if (i915_vma_fence_prepare(vma, tiling_mode, stride)) continue; - ret = __i915_vma_unbind(vma); - if (ret) - break; + list_move(&vma->vm_link, &unbind); } + spin_unlock(&obj->vma.lock); + + list_for_each_entry_safe(vma, vn, &unbind, vm_link) { + ret = __i915_vma_unbind(vma); + if (ret) { + /* Restore the remaining vma on an error */ + list_splice(&unbind, &ggtt->vm.bound_list); + break; + } + } + mutex_unlock(&ggtt->vm.mutex); return ret; @@ -268,6 +282,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, } mutex_unlock(&obj->mm.lock); + spin_lock(&obj->vma.lock); for_each_ggtt_vma(vma, obj) { vma->fence_size = i915_gem_fence_size(i915, vma->size, tiling, stride); @@ -278,6 +293,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, if (vma->fence) vma->fence->dirty = true; } + spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; i915_gem_object_unlock(obj); diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index 2d0fd50c5312..d4f94ca9ae0d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -1477,8 +1477,10 @@ static int igt_ppgtt_pin_update(void *arg) unsigned int page_size = BIT(first); obj = i915_gem_object_create_internal(dev_priv, page_size); - if (IS_ERR(obj)) - return PTR_ERR(obj); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_vm; + } vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { @@ -1531,8 +1533,10 @@ static int igt_ppgtt_pin_update(void *arg) } obj = i915_gem_object_create_internal(dev_priv, PAGE_SIZE); - if (IS_ERR(obj)) - return PTR_ERR(obj); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_vm; + } vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 91debbc97c9a..08b56d7ab4f4 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -521,6 +521,8 @@ int intel_timeline_read_hwsp(struct i915_request *from, rcu_read_lock(); cl = rcu_dereference(from->hwsp_cacheline); + if (i915_request_completed(from)) /* confirm cacheline is valid */ + goto unlock; if (unlikely(!i915_active_acquire_if_busy(&cl->active))) goto unlock; /* seqno wrapped and completed! */ if (unlikely(i915_request_completed(from))) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9f0653cf0510..d91557d842dc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3358,7 +3358,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) { struct intel_uncore *uncore = &dev_priv->uncore; - u32 de_pipe_masked = GEN8_PIPE_CDCLK_CRC_DONE; + u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) | + GEN8_PIPE_CDCLK_CRC_DONE; u32 de_pipe_enables; u32 de_port_masked = GEN8_AUX_CHANNEL_A; u32 de_port_enables; @@ -3369,13 +3370,10 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) de_misc_masked |= GEN8_DE_MISC_GSE; if (INTEL_GEN(dev_priv) >= 9) { - de_pipe_masked |= GEN9_DE_PIPE_IRQ_FAULT_ERRORS; de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | GEN9_AUX_CHANNEL_D; if (IS_GEN9_LP(dev_priv)) de_port_masked |= BXT_DE_PORT_GMBUS; - } else { - de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS; } if (INTEL_GEN(dev_priv) >= 11) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 08699fa069aa..82e3bc280622 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -158,16 +158,18 @@ vma_create(struct drm_i915_gem_object *obj, GEM_BUG_ON(!IS_ALIGNED(vma->size, I915_GTT_PAGE_SIZE)); + spin_lock(&obj->vma.lock); + if (i915_is_ggtt(vm)) { if (unlikely(overflows_type(vma->size, u32))) - goto err_vma; + goto err_unlock; vma->fence_size = i915_gem_fence_size(vm->i915, vma->size, i915_gem_object_get_tiling(obj), i915_gem_object_get_stride(obj)); if (unlikely(vma->fence_size < vma->size || /* overflow */ vma->fence_size > vm->total)) - goto err_vma; + goto err_unlock; GEM_BUG_ON(!IS_ALIGNED(vma->fence_size, I915_GTT_MIN_ALIGNMENT)); @@ -179,8 +181,6 @@ vma_create(struct drm_i915_gem_object *obj, __set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(vma)); } - spin_lock(&obj->vma.lock); - rb = NULL; p = &obj->vma.tree.rb_node; while (*p) { @@ -225,6 +225,8 @@ vma_create(struct drm_i915_gem_object *obj, return vma; +err_unlock: + spin_unlock(&obj->vma.lock); err_vma: i915_vma_free(vma); return ERR_PTR(-E2BIG); diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index 9dfe7cb530e1..1754c0547069 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -843,6 +843,7 @@ static const struct of_device_id ingenic_drm_of_match[] = { { .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, ingenic_drm_of_match); static struct platform_driver ingenic_drm_driver = { .driver = { diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c index d1086b2a6892..05863b253d68 100644 --- a/drivers/gpu/drm/qxl/qxl_cmd.c +++ b/drivers/gpu/drm/qxl/qxl_cmd.c @@ -480,9 +480,10 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev, return ret; ret = qxl_release_reserve_list(release, true); - if (ret) + if (ret) { + qxl_release_free(qdev, release); return ret; - + } cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release); cmd->type = QXL_SURFACE_CMD_CREATE; cmd->flags = QXL_SURF_FLAG_KEEP_DATA; @@ -499,8 +500,8 @@ int qxl_hw_surface_alloc(struct qxl_device *qdev, /* no need to add a release to the fence for this surface bo, since it is only released when we ask to destroy the surface and it would never signal otherwise */ - qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false); qxl_release_fence_buffer_objects(release); + qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false); surf->hw_surf_alloc = true; spin_lock(&qdev->surf_id_idr_lock); @@ -542,9 +543,8 @@ int qxl_hw_surface_dealloc(struct qxl_device *qdev, cmd->surface_id = id; qxl_release_unmap(qdev, release, &cmd->release_info); - qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false); - qxl_release_fence_buffer_objects(release); + qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false); return 0; } diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 09583a08e141..91f398d51cfa 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -510,8 +510,8 @@ static int qxl_primary_apply_cursor(struct drm_plane *plane) cmd->u.set.visible = 1; qxl_release_unmap(qdev, release, &cmd->release_info); - qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); qxl_release_fence_buffer_objects(release); + qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); return ret; @@ -652,8 +652,8 @@ static void qxl_cursor_atomic_update(struct drm_plane *plane, cmd->u.position.y = plane->state->crtc_y + fb->hot_y; qxl_release_unmap(qdev, release, &cmd->release_info); - qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); qxl_release_fence_buffer_objects(release); + qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); if (old_cursor_bo != NULL) qxl_bo_unpin(old_cursor_bo); @@ -700,8 +700,8 @@ static void qxl_cursor_atomic_disable(struct drm_plane *plane, cmd->type = QXL_CURSOR_HIDE; qxl_release_unmap(qdev, release, &cmd->release_info); - qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); qxl_release_fence_buffer_objects(release); + qxl_push_cursor_ring_release(qdev, release, QXL_CMD_CURSOR, false); } static void qxl_update_dumb_head(struct qxl_device *qdev, diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c index 5bebf1ea1c5d..3599db096973 100644 --- a/drivers/gpu/drm/qxl/qxl_draw.c +++ b/drivers/gpu/drm/qxl/qxl_draw.c @@ -209,9 +209,10 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev, goto out_release_backoff; rects = drawable_set_clipping(qdev, num_clips, clips_bo); - if (!rects) + if (!rects) { + ret = -EINVAL; goto out_release_backoff; - + } drawable = (struct qxl_drawable *)qxl_release_map(qdev, release); drawable->clip.type = SPICE_CLIP_TYPE_RECTS; @@ -242,8 +243,8 @@ void qxl_draw_dirty_fb(struct qxl_device *qdev, } qxl_bo_kunmap(clips_bo); - qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false); qxl_release_fence_buffer_objects(release); + qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false); out_release_backoff: if (ret) diff --git a/drivers/gpu/drm/qxl/qxl_image.c b/drivers/gpu/drm/qxl/qxl_image.c index 43688ecdd8a0..60ab7151b84d 100644 --- a/drivers/gpu/drm/qxl/qxl_image.c +++ b/drivers/gpu/drm/qxl/qxl_image.c @@ -212,7 +212,8 @@ qxl_image_init_helper(struct qxl_device *qdev, break; default: DRM_ERROR("unsupported image bit depth\n"); - return -EINVAL; /* TODO: cleanup */ + qxl_bo_kunmap_atomic_page(qdev, image_bo, ptr); + return -EINVAL; } image->u.bitmap.flags = QXL_BITMAP_TOP_DOWN; image->u.bitmap.x = width; diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 8117a45b3610..72f3f1bbb40c 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -261,11 +261,8 @@ static int qxl_process_single_command(struct qxl_device *qdev, apply_surf_reloc(qdev, &reloc_info[i]); } + qxl_release_fence_buffer_objects(release); ret = qxl_push_command_ring_release(qdev, release, cmd->type, true); - if (ret) - qxl_release_backoff_reserve_list(release); - else - qxl_release_fence_buffer_objects(release); out_free_bos: out_free_release: diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 059939789730..3eb89f1eb0e1 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder) struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); struct mipi_dsi_device *device = dsi->device; - union phy_configure_opts opts = { 0 }; + union phy_configure_opts opts = { }; struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy; u16 delay; int err; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index c1824bdf2418..7879ff58236f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -221,6 +221,7 @@ struct virtio_gpu_fpriv { /* virtio_ioctl.c */ #define DRM_VIRTIO_NUM_IOCTLS 10 extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file); /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 0d6152c99a27..f0d5a8974677 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -39,6 +39,9 @@ int virtio_gpu_gem_create(struct drm_file *file, int ret; u32 handle; + if (vgdev->has_virgl_3d) + virtio_gpu_create_context(dev, file); + ret = virtio_gpu_object_create(vgdev, params, &obj, NULL); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 3f60bf2fe05a..512daff92038 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -34,8 +34,7 @@ #include "virtgpu_drv.h" -static void virtio_gpu_create_context(struct drm_device *dev, - struct drm_file *file) +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file) { struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_fpriv *vfpriv = file->driver_priv; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index f4ea4cef5e23..0a5c8cf409fb 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -53,14 +53,6 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) events_clear, &events_clear); } -static void virtio_gpu_context_destroy(struct virtio_gpu_device *vgdev, - uint32_t ctx_id) -{ - virtio_gpu_cmd_context_destroy(vgdev, ctx_id); - virtio_gpu_notify(vgdev); - ida_free(&vgdev->ctx_id_ida, ctx_id - 1); -} - static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, void (*work_func)(struct work_struct *work)) { @@ -275,14 +267,17 @@ int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file) void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file) { struct virtio_gpu_device *vgdev = dev->dev_private; - struct virtio_gpu_fpriv *vfpriv; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; if (!vgdev->has_virgl_3d) return; - vfpriv = file->driver_priv; + if (vfpriv->context_created) { + virtio_gpu_cmd_context_destroy(vgdev, vfpriv->ctx_id); + virtio_gpu_notify(vgdev); + } - virtio_gpu_context_destroy(vgdev, vfpriv->ctx_id); + ida_free(&vgdev->ctx_id_ida, vfpriv->ctx_id - 1); mutex_destroy(&vfpriv->context_lock); kfree(vfpriv); file->driver_priv = NULL; diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 7c89edbd6c5a..34f07371716d 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1155,6 +1155,7 @@ config HID_ALPS config HID_MCP2221 tristate "Microchip MCP2221 HID USB-to-I2C/SMbus host support" depends on USB_HID && I2C + depends on GPIOLIB ---help--- Provides I2C and SMBUS host adapter functionality over USB-HID through MCP2221 device. diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index fa704153cb00..b2ad319a74b9 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -802,6 +802,7 @@ static int alps_probe(struct hid_device *hdev, const struct hid_device_id *id) break; case HID_DEVICE_ID_ALPS_U1_DUAL: case HID_DEVICE_ID_ALPS_U1: + case HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY: data->dev_type = U1; break; default: diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b18b13147a6f..1c71a1aa76b2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -79,10 +79,10 @@ #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP 0x121F #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 #define HID_DEVICE_ID_ALPS_U1 0x1215 +#define HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY 0x121E #define HID_DEVICE_ID_ALPS_T4_BTNLESS 0x120C #define HID_DEVICE_ID_ALPS_1222 0x1222 - #define USB_VENDOR_ID_AMI 0x046b #define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE 0xff10 @@ -385,6 +385,7 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7349 0x7349 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002 0xc002 #define USB_VENDOR_ID_ELAN 0x04f3 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 @@ -759,6 +760,7 @@ #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2 0xc218 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2 0xc219 #define USB_DEVICE_ID_LOGITECH_G15_LCD 0xc222 +#define USB_DEVICE_ID_LOGITECH_G11 0xc225 #define USB_DEVICE_ID_LOGITECH_G15_V2_LCD 0xc227 #define USB_DEVICE_ID_LOGITECH_G510 0xc22d #define USB_DEVICE_ID_LOGITECH_G510_USB_AUDIO 0xc22e @@ -1097,6 +1099,9 @@ #define USB_DEVICE_ID_SYMBOL_SCANNER_2 0x1300 #define USB_DEVICE_ID_SYMBOL_SCANNER_3 0x1200 +#define I2C_VENDOR_ID_SYNAPTICS 0x06cb +#define I2C_PRODUCT_ID_SYNAPTICS_SYNA2393 0x7a13 + #define USB_VENDOR_ID_SYNAPTICS 0x06cb #define USB_DEVICE_ID_SYNAPTICS_TP 0x0001 #define USB_DEVICE_ID_SYNAPTICS_INT_TP 0x0002 @@ -1111,6 +1116,7 @@ #define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10 #define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3 +#define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index ad4b5412a9f4..ef0cbcd7540d 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -872,6 +872,10 @@ error_hw_stop: } static const struct hid_device_id lg_g15_devices[] = { + /* The G11 is a G15 without the LCD, treat it as a G15 */ + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_G11), + .driver_data = LG_G15 }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G15_LCD), .driver_data = LG_G15 }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 362805ddf377..03c720b47306 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1922,6 +1922,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_EGALAX_SERIAL, MT_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) }, + { .driver_data = MT_CLS_EGALAX, + MT_USB_DEVICE(USB_VENDOR_ID_DWAV, + USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) }, /* Elitegroup panel */ { .driver_data = MT_CLS_SERIAL, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ebec818344af..e4cb543de0cd 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -163,6 +163,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 009000c5d55c..294c84e136d7 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -177,6 +177,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BOGUS_IRQ }, { USB_VENDOR_ID_ALPS_JP, HID_ANY_ID, I2C_HID_QUIRK_RESET_ON_RESUME }, + { I2C_VENDOR_ID_SYNAPTICS, I2C_PRODUCT_ID_SYNAPTICS_SYNA2393, + I2C_HID_QUIRK_RESET_ON_RESUME }, { USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720, I2C_HID_QUIRK_BAD_INPUT_SIZE }, { 0, 0 } diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index c7bc9db5b192..17a638f15082 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; int res; + mutex_lock(&usbhid->mutex); + set_bit(HID_OPENED, &usbhid->iofl); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return 0; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + res = 0; + goto Done; + } res = usb_autopm_get_interface(usbhid->intf); /* the device must be awake to reliably request remote wakeup */ if (res < 0) { clear_bit(HID_OPENED, &usbhid->iofl); - return -EIO; + res = -EIO; + goto Done; } usbhid->intf->needs_remote_wakeup = 1; @@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid) msleep(50); clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + + Done: + mutex_unlock(&usbhid->mutex); return res; } @@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; + mutex_lock(&usbhid->mutex); + /* * Make sure we don't restart data acquisition due to * a resumption we no longer care about by avoiding racing @@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid) clear_bit(HID_IN_POLLING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + hid_cancel_delayed_stuff(usbhid); + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } - hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + mutex_unlock(&usbhid->mutex); } /* @@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid) unsigned int n, insize = 0; int ret; + mutex_lock(&usbhid->mutex); + clear_bit(HID_DISCONNECTED, &usbhid->iofl); usbhid->bufsize = HID_MIN_BUFFER_SIZE; @@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid) usbhid_set_leds(hid); device_set_wakeup_enable(&dev->dev, 1); } + + mutex_unlock(&usbhid->mutex); return 0; fail: @@ -1187,6 +1202,7 @@ fail: usbhid->urbout = NULL; usbhid->urbctrl = NULL; hid_free_buffers(dev, hid); + mutex_unlock(&usbhid->mutex); return ret; } @@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->intf->needs_remote_wakeup = 0; } + mutex_lock(&usbhid->mutex); + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); @@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->urbout = NULL; hid_free_buffers(hid_to_usb_dev(hid), hid); + + mutex_unlock(&usbhid->mutex); } static int usbhid_power(struct hid_device *hid, int lvl) @@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id * INIT_WORK(&usbhid->reset_work, hid_reset); timer_setup(&usbhid->io_retry, hid_retry_timeout, 0); spin_lock_init(&usbhid->lock); + mutex_init(&usbhid->mutex); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 8620408bd7af..75fe85d3d27a 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -80,6 +80,7 @@ struct usbhid_device { dma_addr_t outbuf_dma; /* Output buffer dma */ unsigned long last_out; /* record of last output for timeouts */ + struct mutex mutex; /* start/stop/open/close */ spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ struct timer_list io_retry; /* Retry timer */ diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 5ded94b7bf68..cd71e7133944 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev, data[0] = field->report->id; ret = wacom_get_report(hdev, HID_FEATURE_REPORT, data, n, WAC_CMD_RETRIES); - if (ret == n) { + if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, data, n, 0); + } else if (ret == 2 && features->type != HID_GENERIC) { + features->touch_max = data[1]; } else { features->touch_max = 16; hid_warn(hdev, "wacom_feature_mapping: " diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d99a9d407671..1c96809b51c9 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1427,11 +1427,13 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) { struct input_dev *pad_input = wacom->pad_input; unsigned char *data = wacom->data; + int nbuttons = wacom->features.numbered_buttons; - int buttons = data[282] | ((data[281] & 0x40) << 2); + int expresskeys = data[282]; + int center = (data[281] & 0x40) >> 6; int ring = data[285] & 0x7F; bool ringstatus = data[285] & 0x80; - bool prox = buttons || ringstatus; + bool prox = expresskeys || center || ringstatus; /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ ring = 71 - ring; @@ -1439,7 +1441,8 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) if (ring > 71) ring -= 72; - wacom_report_numbered_buttons(pad_input, 9, buttons); + wacom_report_numbered_buttons(pad_input, nbuttons, + expresskeys | (center << (nbuttons - 1))); input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); @@ -2637,9 +2640,25 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, case HID_DG_TIPSWITCH: hid_data->last_slot_field = equivalent_usage; break; + case HID_DG_CONTACTCOUNT: + hid_data->cc_report = report->id; + hid_data->cc_index = i; + hid_data->cc_value_index = j; + break; } } } + + if (hid_data->cc_report != 0 && + hid_data->cc_index >= 0) { + struct hid_field *field = report->field[hid_data->cc_index]; + int value = field->value[hid_data->cc_value_index]; + if (value) + hid_data->num_expected = value; + } + else { + hid_data->num_expected = wacom_wac->features.touch_max; + } } static void wacom_wac_finger_report(struct hid_device *hdev, @@ -2649,7 +2668,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, struct wacom_wac *wacom_wac = &wacom->wacom_wac; struct input_dev *input = wacom_wac->touch_input; unsigned touch_max = wacom_wac->features.touch_max; - struct hid_data *hid_data = &wacom_wac->hid_data; /* If more packets of data are expected, give us a chance to * process them rather than immediately syncing a partial @@ -2663,7 +2681,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, input_sync(input); wacom_wac->hid_data.num_received = 0; - hid_data->num_expected = 0; /* keep touch state for pen event */ wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac); @@ -2738,73 +2755,12 @@ static void wacom_report_events(struct hid_device *hdev, } } -static void wacom_set_num_expected(struct hid_device *hdev, - struct hid_report *report, - int collection_index, - struct hid_field *field, - int field_index) -{ - struct wacom *wacom = hid_get_drvdata(hdev); - struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct hid_data *hid_data = &wacom_wac->hid_data; - unsigned int original_collection_level = - hdev->collection[collection_index].level; - bool end_collection = false; - int i; - - if (hid_data->num_expected) - return; - - // find the contact count value for this segment - for (i = field_index; i < report->maxfield && !end_collection; i++) { - struct hid_field *field = report->field[i]; - unsigned int field_level = - hdev->collection[field->usage[0].collection_index].level; - unsigned int j; - - if (field_level != original_collection_level) - continue; - - for (j = 0; j < field->maxusage; j++) { - struct hid_usage *usage = &field->usage[j]; - - if (usage->collection_index != collection_index) { - end_collection = true; - break; - } - if (wacom_equivalent_usage(usage->hid) == HID_DG_CONTACTCOUNT) { - hid_data->cc_report = report->id; - hid_data->cc_index = i; - hid_data->cc_value_index = j; - - if (hid_data->cc_report != 0 && - hid_data->cc_index >= 0) { - - struct hid_field *field = - report->field[hid_data->cc_index]; - int value = - field->value[hid_data->cc_value_index]; - - if (value) - hid_data->num_expected = value; - } - } - } - } - - if (hid_data->cc_report == 0 || hid_data->cc_index < 0) - hid_data->num_expected = wacom_wac->features.touch_max; -} - static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *report, int collection_index, struct hid_field *field, int field_index) { struct wacom *wacom = hid_get_drvdata(hdev); - if (WACOM_FINGER_FIELD(field)) - wacom_set_num_expected(hdev, report, collection_index, field, - field_index); wacom_report_events(hdev, report, collection_index, field_index); /* diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 6098e0cbdb4b..533c8b82b344 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -184,11 +184,7 @@ void hv_synic_enable_regs(unsigned int cpu) shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR; shared_sint.masked = false; - if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED) - shared_sint.auto_eoi = false; - else - shared_sint.auto_eoi = true; - + shared_sint.auto_eoi = hv_recommend_using_aeoi(); hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); /* Enable the global synic bit */ diff --git a/drivers/hv/hv_trace.h b/drivers/hv/hv_trace.h index e70783e33680..f9d14db980cb 100644 --- a/drivers/hv/hv_trace.h +++ b/drivers/hv/hv_trace.h @@ -286,8 +286,8 @@ TRACE_EVENT(vmbus_send_tl_connect_request, __field(int, ret) ), TP_fast_assign( - memcpy(__entry->guest_id, &msg->guest_endpoint_id.b, 16); - memcpy(__entry->host_id, &msg->host_service_id.b, 16); + export_guid(__entry->guest_id, &msg->guest_endpoint_id); + export_guid(__entry->host_id, &msg->host_service_id); __entry->ret = ret; ), TP_printk("sending guest_endpoint_id %pUl, host_service_id %pUl, " diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index a68bce4d0ddb..e06c6b9555cf 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -978,6 +978,9 @@ static int vmbus_resume(struct device *child_device) return drv->resume(dev); } +#else +#define vmbus_suspend NULL +#define vmbus_resume NULL #endif /* CONFIG_PM_SLEEP */ /* @@ -997,11 +1000,22 @@ static void vmbus_device_release(struct device *device) } /* - * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than - * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm. + * Note: we must use the "noirq" ops: see the comment before vmbus_bus_pm. + * + * suspend_noirq/resume_noirq are set to NULL to support Suspend-to-Idle: we + * shouldn't suspend the vmbus devices upon Suspend-to-Idle, otherwise there + * is no way to wake up a Generation-2 VM. + * + * The other 4 ops are for hibernation. */ + static const struct dev_pm_ops vmbus_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume) + .suspend_noirq = NULL, + .resume_noirq = NULL, + .freeze_noirq = vmbus_suspend, + .thaw_noirq = vmbus_resume, + .poweroff_noirq = vmbus_suspend, + .restore_noirq = vmbus_resume, }; /* The one and only one */ @@ -2281,6 +2295,9 @@ static int vmbus_bus_resume(struct device *dev) return 0; } +#else +#define vmbus_bus_suspend NULL +#define vmbus_bus_resume NULL #endif /* CONFIG_PM_SLEEP */ static const struct acpi_device_id vmbus_acpi_device_ids[] = { @@ -2291,16 +2308,24 @@ static const struct acpi_device_id vmbus_acpi_device_ids[] = { MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids); /* - * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than - * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the - * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the - * pci "noirq" restore callback runs before "non-noirq" callbacks (see + * Note: we must use the "no_irq" ops, otherwise hibernation can not work with + * PCI device assignment, because "pci_dev_pm_ops" uses the "noirq" ops: in + * the resume path, the pci "noirq" restore op runs before "non-noirq" op (see * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() -> * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's - * resume callback must also run via the "noirq" callbacks. + * resume callback must also run via the "noirq" ops. + * + * Set suspend_noirq/resume_noirq to NULL for Suspend-to-Idle: see the comment + * earlier in this file before vmbus_pm. */ + static const struct dev_pm_ops vmbus_bus_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume) + .suspend_noirq = NULL, + .resume_noirq = NULL, + .freeze_noirq = vmbus_bus_suspend, + .thaw_noirq = vmbus_bus_resume, + .poweroff_noirq = vmbus_bus_suspend, + .restore_noirq = vmbus_bus_resume }; static struct acpi_driver vmbus_acpi_driver = { diff --git a/drivers/i2c/busses/i2c-amd-mp2-pci.c b/drivers/i2c/busses/i2c-amd-mp2-pci.c index 5e4800d72e00..cd3fd5ee5f65 100644 --- a/drivers/i2c/busses/i2c-amd-mp2-pci.c +++ b/drivers/i2c/busses/i2c-amd-mp2-pci.c @@ -349,12 +349,12 @@ static int amd_mp2_pci_probe(struct pci_dev *pci_dev, if (!privdata) return -ENOMEM; + privdata->pci_dev = pci_dev; rc = amd_mp2_pci_init(privdata, pci_dev); if (rc) return rc; mutex_init(&privdata->c2p_lock); - privdata->pci_dev = pci_dev; pm_runtime_set_autosuspend_delay(&pci_dev->dev, 1000); pm_runtime_use_autosuspend(&pci_dev->dev); diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 07c1993274c5..f51702d86a90 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -603,6 +603,7 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id) /* Ack all interrupts except for Rx done */ writel(irq_received & ~ASPEED_I2CD_INTR_RX_DONE, bus->base + ASPEED_I2C_INTR_STS_REG); + readl(bus->base + ASPEED_I2C_INTR_STS_REG); irq_remaining = irq_received; #if IS_ENABLED(CONFIG_I2C_SLAVE) @@ -645,9 +646,11 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id) irq_received, irq_handled); /* Ack Rx done */ - if (irq_received & ASPEED_I2CD_INTR_RX_DONE) + if (irq_received & ASPEED_I2CD_INTR_RX_DONE) { writel(ASPEED_I2CD_INTR_RX_DONE, bus->base + ASPEED_I2C_INTR_STS_REG); + readl(bus->base + ASPEED_I2C_INTR_STS_REG); + } spin_unlock(&bus->lock); return irq_remaining ? IRQ_NONE : IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 44be0926b566..d091a12596ad 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -360,6 +360,9 @@ static bool bcm_iproc_i2c_slave_isr(struct bcm_iproc_i2c_dev *iproc_i2c, value = (u8)((val >> S_RX_DATA_SHIFT) & S_RX_DATA_MASK); i2c_slave_event(iproc_i2c->slave, I2C_SLAVE_WRITE_RECEIVED, &value); + if (rx_status == I2C_SLAVE_RX_END) + i2c_slave_event(iproc_i2c->slave, + I2C_SLAVE_STOP, &value); } } else if (status & BIT(IS_S_TX_UNDERRUN_SHIFT)) { /* Master read other than start */ diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 8280ac7cc1b7..4c4d17ddc96b 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -996,13 +996,14 @@ tegra_i2c_poll_completion_timeout(struct tegra_i2c_dev *i2c_dev, do { u32 status = i2c_readl(i2c_dev, I2C_INT_STATUS); - if (status) + if (status) { tegra_i2c_isr(i2c_dev->irq, i2c_dev); - if (completion_done(complete)) { - s64 delta = ktime_ms_delta(ktimeout, ktime); + if (completion_done(complete)) { + s64 delta = ktime_ms_delta(ktimeout, ktime); - return msecs_to_jiffies(delta) ?: 1; + return msecs_to_jiffies(delta) ?: 1; + } } ktime = ktime_get(); @@ -1029,18 +1030,14 @@ tegra_i2c_wait_completion_timeout(struct tegra_i2c_dev *i2c_dev, disable_irq(i2c_dev->irq); /* - * Under some rare circumstances (like running KASAN + - * NFS root) CPU, which handles interrupt, may stuck in - * uninterruptible state for a significant time. In this - * case we will get timeout if I2C transfer is running on - * a sibling CPU, despite of IRQ being raised. - * - * In order to handle this rare condition, the IRQ status - * needs to be checked after timeout. + * There is a chance that completion may happen after IRQ + * synchronization, which is done by disable_irq(). */ - if (ret == 0) - ret = tegra_i2c_poll_completion_timeout(i2c_dev, - complete, 0); + if (ret == 0 && completion_done(complete)) { + dev_warn(i2c_dev->dev, + "completion done after timeout\n"); + ret = 1; + } } return ret; @@ -1219,15 +1216,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, time_left = tegra_i2c_wait_completion_timeout( i2c_dev, &i2c_dev->dma_complete, xfer_time); - /* - * Synchronize DMA first, since dmaengine_terminate_sync() - * performs synchronization after the transfer's termination - * and we want to get a completion if transfer succeeded. - */ - dmaengine_synchronize(i2c_dev->msg_read ? - i2c_dev->rx_dma_chan : - i2c_dev->tx_dma_chan); - dmaengine_terminate_sync(i2c_dev->msg_read ? i2c_dev->rx_dma_chan : i2c_dev->tx_dma_chan); diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 4794113ecd59..17f14e0eafe4 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -862,7 +862,7 @@ static struct cm_id_private *cm_alloc_id_priv(struct ib_device *device, ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b, &cm.local_id_next, GFP_KERNEL); - if (ret) + if (ret < 0) goto error; cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand; @@ -1828,11 +1828,9 @@ static void cm_format_mra(struct cm_mra_msg *mra_msg, static void cm_format_rej(struct cm_rej_msg *rej_msg, struct cm_id_private *cm_id_priv, - enum ib_cm_rej_reason reason, - void *ari, - u8 ari_length, - const void *private_data, - u8 private_data_len) + enum ib_cm_rej_reason reason, void *ari, + u8 ari_length, const void *private_data, + u8 private_data_len, enum ib_cm_state state) { lockdep_assert_held(&cm_id_priv->lock); @@ -1840,7 +1838,7 @@ static void cm_format_rej(struct cm_rej_msg *rej_msg, IBA_SET(CM_REJ_REMOTE_COMM_ID, rej_msg, be32_to_cpu(cm_id_priv->id.remote_id)); - switch(cm_id_priv->id.state) { + switch (state) { case IB_CM_REQ_RCVD: IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg, be32_to_cpu(0)); IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REQ); @@ -1905,8 +1903,9 @@ static void cm_dup_req_handler(struct cm_work *work, cm_id_priv->private_data_len); break; case IB_CM_TIMEWAIT: - cm_format_rej((struct cm_rej_msg *) msg->mad, cm_id_priv, - IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0); + cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, + IB_CM_REJ_STALE_CONN, NULL, 0, NULL, 0, + IB_CM_TIMEWAIT); break; default: goto unlock; @@ -2904,6 +2903,7 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, u8 ari_length, const void *private_data, u8 private_data_len) { + enum ib_cm_state state = cm_id_priv->id.state; struct ib_mad_send_buf *msg; int ret; @@ -2913,7 +2913,7 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, (ari && ari_length > IB_CM_REJ_ARI_LENGTH)) return -EINVAL; - switch (cm_id_priv->id.state) { + switch (state) { case IB_CM_REQ_SENT: case IB_CM_MRA_REQ_RCVD: case IB_CM_REQ_RCVD: @@ -2925,7 +2925,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, if (ret) return ret; cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason, - ari, ari_length, private_data, private_data_len); + ari, ari_length, private_data, private_data_len, + state); break; case IB_CM_REP_SENT: case IB_CM_MRA_REP_RCVD: @@ -2934,7 +2935,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, if (ret) return ret; cm_format_rej((struct cm_rej_msg *)msg->mad, cm_id_priv, reason, - ari, ari_length, private_data, private_data_len); + ari, ari_length, private_data, private_data_len, + state); break; default: pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__, diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 5128cb16bb48..177333d8bcda 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -360,7 +360,7 @@ lookup_get_fd_uobject(const struct uverbs_api_object *obj, * uverbs_uobject_fd_release(), and the caller is expected to ensure * that release is never done while a call to lookup is possible. */ - if (f->f_op != fd_type->fops) { + if (f->f_op != fd_type->fops || uobject->ufile != ufile) { fput(f); return ERR_PTR(-EBADF); } @@ -474,16 +474,15 @@ alloc_begin_fd_uobject(const struct uverbs_api_object *obj, filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL, fd_type->flags); if (IS_ERR(filp)) { + uverbs_uobject_put(uobj); uobj = ERR_CAST(filp); - goto err_uobj; + goto err_fd; } uobj->object = filp; uobj->id = new_fd; return uobj; -err_uobj: - uverbs_uobject_put(uobj); err_fd: put_unused_fd(new_fd); return uobj; @@ -679,7 +678,6 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj, enum rdma_lookup_mode mode) { assert_uverbs_usecnt(uobj, mode); - uobj->uapi_object->type_class->lookup_put(uobj, mode); /* * In order to unlock an object, either decrease its usecnt for * read access or zero it in case of exclusive access. See @@ -696,6 +694,7 @@ void rdma_lookup_put_uobject(struct ib_uobject *uobj, break; } + uobj->uapi_object->type_class->lookup_put(uobj, mode); /* Pairs with the kref obtained by type->lookup_get */ uverbs_uobject_put(uobj); } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 2d4083bf4a04..17fc25db0311 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -820,6 +820,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) ret = mmget_not_zero(mm); if (!ret) { list_del_init(&priv->list); + if (priv->entry) { + rdma_user_mmap_entry_put(priv->entry); + priv->entry = NULL; + } mm = NULL; continue; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index e8b4b3743661..688f19667221 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -1046,7 +1046,7 @@ i40iw_sc_query_rdma_features(struct i40iw_sc_cqp *cqp, u64 header; wqe = i40iw_sc_cqp_get_next_send_wqe(cqp, scratch); - if (wqe) + if (!wqe) return I40IW_ERR_RING_FULL; set_64bit_val(wqe, 32, feat_mem->pa); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index a66518a5c938..275722cec8c6 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1499,8 +1499,9 @@ static int __mlx4_ib_create_default_rules( int i; for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) { + union ib_flow_spec ib_spec = {}; int ret; - union ib_flow_spec ib_spec; + switch (pdefault_rules->rules_create_list[i]) { case 0: /* no rule */ diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 1456db4b6295..2210759843ba 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -5558,7 +5558,9 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev, rdma_ah_set_path_bits(ah_attr, path->grh_mlid & 0x7f); rdma_ah_set_static_rate(ah_attr, path->static_rate ? path->static_rate - 5 : 0); - if (path->grh_mlid & (1 << 7)) { + + if (path->grh_mlid & (1 << 7) || + ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) { u32 tc_fl = be32_to_cpu(path->tclass_flowlabel); rdma_ah_set_grh(ah_attr, NULL, diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c index 5724cbbe38b1..04d2e72017fe 100644 --- a/drivers/infiniband/sw/rdmavt/cq.c +++ b/drivers/infiniband/sw/rdmavt/cq.c @@ -248,8 +248,8 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, */ if (udata && udata->outlen >= sizeof(__u64)) { cq->ip = rvt_create_mmap_info(rdi, sz, udata, u_wc); - if (!cq->ip) { - err = -ENOMEM; + if (IS_ERR(cq->ip)) { + err = PTR_ERR(cq->ip); goto bail_wc; } diff --git a/drivers/infiniband/sw/rdmavt/mmap.c b/drivers/infiniband/sw/rdmavt/mmap.c index 652f4a7efc1b..37853aa3bcf7 100644 --- a/drivers/infiniband/sw/rdmavt/mmap.c +++ b/drivers/infiniband/sw/rdmavt/mmap.c @@ -154,7 +154,7 @@ done: * @udata: user data (must be valid!) * @obj: opaque pointer to a cq, wq etc * - * Return: rvt_mmap struct on success + * Return: rvt_mmap struct on success, ERR_PTR on failure */ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi, u32 size, struct ib_udata *udata, void *obj) @@ -166,7 +166,7 @@ struct rvt_mmap_info *rvt_create_mmap_info(struct rvt_dev_info *rdi, u32 size, ip = kmalloc_node(sizeof(*ip), GFP_KERNEL, rdi->dparms.node); if (!ip) - return ip; + return ERR_PTR(-ENOMEM); size = PAGE_ALIGN(size); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 0e1b291d2cec..500a7ee04c44 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1244,8 +1244,8 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, qp->ip = rvt_create_mmap_info(rdi, s, udata, qp->r_rq.wq); - if (!qp->ip) { - ret = ERR_PTR(-ENOMEM); + if (IS_ERR(qp->ip)) { + ret = ERR_CAST(qp->ip); goto bail_qpn; } diff --git a/drivers/infiniband/sw/rdmavt/srq.c b/drivers/infiniband/sw/rdmavt/srq.c index 24fef021d51d..f547c115af03 100644 --- a/drivers/infiniband/sw/rdmavt/srq.c +++ b/drivers/infiniband/sw/rdmavt/srq.c @@ -111,8 +111,8 @@ int rvt_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *srq_init_attr, u32 s = sizeof(struct rvt_rwq) + srq->rq.size * sz; srq->ip = rvt_create_mmap_info(dev, s, udata, srq->rq.wq); - if (!srq->ip) { - ret = -ENOMEM; + if (IS_ERR(srq->ip)) { + ret = PTR_ERR(srq->ip); goto bail_wq; } diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index ae92c8080967..9f53aa4feb87 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -920,20 +920,27 @@ static int siw_fastreg_mr(struct ib_pd *pd, struct siw_sqe *sqe) { struct ib_mr *base_mr = (struct ib_mr *)(uintptr_t)sqe->base_mr; struct siw_device *sdev = to_siw_dev(pd->device); - struct siw_mem *mem = siw_mem_id2obj(sdev, sqe->rkey >> 8); + struct siw_mem *mem; int rv = 0; siw_dbg_pd(pd, "STag 0x%08x\n", sqe->rkey); - if (unlikely(!mem || !base_mr)) { + if (unlikely(!base_mr)) { pr_warn("siw: fastreg: STag 0x%08x unknown\n", sqe->rkey); return -EINVAL; } + if (unlikely(base_mr->rkey >> 8 != sqe->rkey >> 8)) { pr_warn("siw: fastreg: STag 0x%08x: bad MR\n", sqe->rkey); - rv = -EINVAL; - goto out; + return -EINVAL; } + + mem = siw_mem_id2obj(sdev, sqe->rkey >> 8); + if (unlikely(!mem)) { + pr_warn("siw: fastreg: STag 0x%08x unknown\n", sqe->rkey); + return -EINVAL; + } + if (unlikely(mem->pd != pd)) { pr_warn("siw: fastreg: PD mismatch\n"); rv = -EINVAL; diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index a03c6d6833df..96fb9ff5ff2e 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -78,7 +78,7 @@ static struct qcom_icc_node *sdm845_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sdm845_osm_l3, }; -const static struct qcom_icc_desc sdm845_icc_osm_l3 = { +static const struct qcom_icc_desc sdm845_icc_osm_l3 = { .nodes = sdm845_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sdm845_osm_l3_nodes), }; @@ -91,7 +91,7 @@ static struct qcom_icc_node *sc7180_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sc7180_osm_l3, }; -const static struct qcom_icc_desc sc7180_icc_osm_l3 = { +static const struct qcom_icc_desc sc7180_icc_osm_l3 = { .nodes = sc7180_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sc7180_osm_l3_nodes), }; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index b013b80caa45..f6c7b969520d 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -192,7 +192,7 @@ static struct qcom_icc_node *aggre1_noc_nodes[] = { [SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc, }; -const static struct qcom_icc_desc sdm845_aggre1_noc = { +static const struct qcom_icc_desc sdm845_aggre1_noc = { .nodes = aggre1_noc_nodes, .num_nodes = ARRAY_SIZE(aggre1_noc_nodes), .bcms = aggre1_noc_bcms, @@ -220,7 +220,7 @@ static struct qcom_icc_node *aggre2_noc_nodes[] = { [SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc, }; -const static struct qcom_icc_desc sdm845_aggre2_noc = { +static const struct qcom_icc_desc sdm845_aggre2_noc = { .nodes = aggre2_noc_nodes, .num_nodes = ARRAY_SIZE(aggre2_noc_nodes), .bcms = aggre2_noc_bcms, @@ -281,7 +281,7 @@ static struct qcom_icc_node *config_noc_nodes[] = { [SLAVE_SERVICE_CNOC] = &srvc_cnoc, }; -const static struct qcom_icc_desc sdm845_config_noc = { +static const struct qcom_icc_desc sdm845_config_noc = { .nodes = config_noc_nodes, .num_nodes = ARRAY_SIZE(config_noc_nodes), .bcms = config_noc_bcms, @@ -297,7 +297,7 @@ static struct qcom_icc_node *dc_noc_nodes[] = { [SLAVE_MEM_NOC_CFG] = &qhs_memnoc, }; -const static struct qcom_icc_desc sdm845_dc_noc = { +static const struct qcom_icc_desc sdm845_dc_noc = { .nodes = dc_noc_nodes, .num_nodes = ARRAY_SIZE(dc_noc_nodes), .bcms = dc_noc_bcms, @@ -315,7 +315,7 @@ static struct qcom_icc_node *gladiator_noc_nodes[] = { [SLAVE_SERVICE_GNOC] = &srvc_gnoc, }; -const static struct qcom_icc_desc sdm845_gladiator_noc = { +static const struct qcom_icc_desc sdm845_gladiator_noc = { .nodes = gladiator_noc_nodes, .num_nodes = ARRAY_SIZE(gladiator_noc_nodes), .bcms = gladiator_noc_bcms, @@ -350,7 +350,7 @@ static struct qcom_icc_node *mem_noc_nodes[] = { [SLAVE_EBI1] = &ebi, }; -const static struct qcom_icc_desc sdm845_mem_noc = { +static const struct qcom_icc_desc sdm845_mem_noc = { .nodes = mem_noc_nodes, .num_nodes = ARRAY_SIZE(mem_noc_nodes), .bcms = mem_noc_bcms, @@ -384,7 +384,7 @@ static struct qcom_icc_node *mmss_noc_nodes[] = { [SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp, }; -const static struct qcom_icc_desc sdm845_mmss_noc = { +static const struct qcom_icc_desc sdm845_mmss_noc = { .nodes = mmss_noc_nodes, .num_nodes = ARRAY_SIZE(mmss_noc_nodes), .bcms = mmss_noc_bcms, @@ -430,7 +430,7 @@ static struct qcom_icc_node *system_noc_nodes[] = { [SLAVE_TCU] = &xs_sys_tcu_cfg, }; -const static struct qcom_icc_desc sdm845_system_noc = { +static const struct qcom_icc_desc sdm845_system_noc = { .nodes = system_noc_nodes, .num_nodes = ARRAY_SIZE(system_noc_nodes), .bcms = system_noc_bcms, diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 58b4a4dbfc78..2ab07ce17abb 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -362,7 +362,7 @@ config IPMMU_VMSA config SPAPR_TCE_IOMMU bool "sPAPR TCE IOMMU Support" - depends on PPC_POWERNV || PPC_PSERIES || (PPC && COMPILE_TEST) + depends on PPC_POWERNV || PPC_PSERIES select IOMMU_API help Enables bits of IOMMU API required by VFIO. The iommu_ops @@ -457,7 +457,7 @@ config S390_AP_IOMMU config MTK_IOMMU bool "MTK IOMMU Support" - depends on ARM || ARM64 || COMPILE_TEST + depends on HAS_DMA depends on ARCH_MEDIATEK || COMPILE_TEST select ARM_DMA_USE_IOMMU select IOMMU_API diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 20cce366e951..1dc3718560d0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -101,6 +101,8 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); static void detach_device(struct device *dev); +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable); /**************************************************************************** * @@ -151,6 +153,26 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom) return container_of(dom, struct protection_domain, domain); } +static void amd_iommu_domain_get_pgtable(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + u64 pt_root = atomic64_read(&domain->pt_root); + + pgtable->root = (u64 *)(pt_root & PAGE_MASK); + pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */ +} + +static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) +{ + u64 pt_root; + + /* lowest 3 bits encode pgtable mode */ + pt_root = mode & 7; + pt_root |= (u64)root; + + return pt_root; +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -1397,13 +1419,18 @@ static struct page *free_sub_pt(unsigned long root, int mode, static void free_pagetable(struct protection_domain *domain) { - unsigned long root = (unsigned long)domain->pt_root; + struct domain_pgtable pgtable; struct page *freelist = NULL; + unsigned long root; - BUG_ON(domain->mode < PAGE_MODE_NONE || - domain->mode > PAGE_MODE_6_LEVEL); + amd_iommu_domain_get_pgtable(domain, &pgtable); + atomic64_set(&domain->pt_root, 0); - freelist = free_sub_pt(root, domain->mode, freelist); + BUG_ON(pgtable.mode < PAGE_MODE_NONE || + pgtable.mode > PAGE_MODE_6_LEVEL); + + root = (unsigned long)pgtable.root; + freelist = free_sub_pt(root, pgtable.mode, freelist); free_page_list(freelist); } @@ -1417,24 +1444,39 @@ static bool increase_address_space(struct protection_domain *domain, unsigned long address, gfp_t gfp) { + struct domain_pgtable pgtable; unsigned long flags; - bool ret = false; - u64 *pte; + bool ret = true; + u64 *pte, root; spin_lock_irqsave(&domain->lock, flags); - if (address <= PM_LEVEL_SIZE(domain->mode) || - WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address <= PM_LEVEL_SIZE(pgtable.mode)) + goto out; + + ret = false; + if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL)) goto out; pte = (void *)get_zeroed_page(gfp); if (!pte) goto out; - *pte = PM_LEVEL_PDE(domain->mode, - iommu_virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; + *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root)); + + pgtable.root = pte; + pgtable.mode += 1; + update_and_flush_device_table(domain, &pgtable); + domain_flush_complete(domain); + + /* + * Device Table needs to be updated and flushed before the new root can + * be published. + */ + root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode); + atomic64_set(&domain->pt_root, root); ret = true; @@ -1451,16 +1493,29 @@ static u64 *alloc_pte(struct protection_domain *domain, gfp_t gfp, bool *updated) { + struct domain_pgtable pgtable; int level, end_lvl; u64 *pte, *page; BUG_ON(!is_power_of_2(page_size)); - while (address > PM_LEVEL_SIZE(domain->mode)) - *updated = increase_address_space(domain, address, gfp) || *updated; + amd_iommu_domain_get_pgtable(domain, &pgtable); - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + while (address > PM_LEVEL_SIZE(pgtable.mode)) { + /* + * Return an error if there is no memory to update the + * page-table. + */ + if (!increase_address_space(domain, address, gfp)) + return NULL; + + /* Read new values to check if update was successful */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + } + + + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -1536,16 +1591,19 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address, unsigned long *page_size) { + struct domain_pgtable pgtable; int level; u64 *pte; *page_size = 0; - if (address > PM_LEVEL_SIZE(domain->mode)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address > PM_LEVEL_SIZE(pgtable.mode)) return NULL; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -1660,7 +1718,13 @@ out: unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - update_domain(dom); + /* + * Flush domain TLB(s) and wait for completion. Any Device-Table + * Updates and flushing already happened in + * increase_address_space(). + */ + domain_flush_tlb_pde(dom); + domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -1806,6 +1870,7 @@ static void dma_ops_domain_free(struct protection_domain *domain) static struct protection_domain *dma_ops_domain_alloc(void) { struct protection_domain *domain; + u64 *pt_root, root; domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL); if (!domain) @@ -1814,12 +1879,14 @@ static struct protection_domain *dma_ops_domain_alloc(void) if (protection_domain_init(domain)) goto free_domain; - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - domain->flags = PD_DMA_OPS_MASK; - if (!domain->pt_root) + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) goto free_domain; + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&domain->pt_root, root); + domain->flags = PD_DMA_OPS_MASK; + if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM) goto free_domain; @@ -1841,16 +1908,17 @@ static bool dma_ops_domain(struct protection_domain *domain) } static void set_dte_entry(u16 devid, struct protection_domain *domain, + struct domain_pgtable *pgtable, bool ats, bool ppr) { u64 pte_root = 0; u64 flags = 0; u32 old_domid; - if (domain->mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->pt_root); + if (pgtable->mode != PAGE_MODE_NONE) + pte_root = iommu_virt_to_phys(pgtable->root); - pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK) + pte_root |= (pgtable->mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV; @@ -1923,6 +1991,7 @@ static void clear_dte_entry(u16 devid) static void do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { + struct domain_pgtable pgtable; struct amd_iommu *iommu; bool ats; @@ -1938,7 +2007,9 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_cnt += 1; /* Update device table */ - set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2); + amd_iommu_domain_get_pgtable(domain, &pgtable); + set_dte_entry(dev_data->devid, domain, &pgtable, + ats, dev_data->iommu_v2); clone_aliases(dev_data->pdev); device_flush_dte(dev_data); @@ -2249,23 +2320,36 @@ static int amd_iommu_domain_get_attr(struct iommu_domain *domain, * *****************************************************************************/ -static void update_device_table(struct protection_domain *domain) +static void update_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) { struct iommu_dev_data *dev_data; list_for_each_entry(dev_data, &domain->dev_list, list) { - set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled, - dev_data->iommu_v2); + set_dte_entry(dev_data->devid, domain, pgtable, + dev_data->ats.enabled, dev_data->iommu_v2); clone_aliases(dev_data->pdev); } } +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + update_device_table(domain, pgtable); + domain_flush_devices(domain); +} + static void update_domain(struct protection_domain *domain) { - update_device_table(domain); + struct domain_pgtable pgtable; - domain_flush_devices(domain); + /* Update device table */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + update_and_flush_device_table(domain, &pgtable); + + /* Flush domain TLB(s) and wait for completion */ domain_flush_tlb_pde(domain); + domain_flush_complete(domain); } int __init amd_iommu_init_api(void) @@ -2375,6 +2459,7 @@ out_err: static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *pdomain; + u64 *pt_root, root; switch (type) { case IOMMU_DOMAIN_UNMANAGED: @@ -2382,13 +2467,15 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_3_LEVEL; - pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!pdomain->pt_root) { + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) { protection_domain_free(pdomain); return NULL; } + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&pdomain->pt_root, root); + pdomain->domain.geometry.aperture_start = 0; pdomain->domain.geometry.aperture_end = ~0ULL; pdomain->domain.geometry.force_aperture = true; @@ -2406,7 +2493,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_NONE; + atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE); break; default: return NULL; @@ -2418,6 +2505,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) static void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain; + struct domain_pgtable pgtable; domain = to_pdomain(dom); @@ -2435,7 +2523,9 @@ static void amd_iommu_domain_free(struct iommu_domain *dom) dma_ops_domain_free(domain); break; default: - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (pgtable.mode != PAGE_MODE_NONE) free_pagetable(domain); if (domain->flags & PD_IOMMUV2_MASK) @@ -2518,10 +2608,12 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; int prot = 0; int ret; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return -EINVAL; if (iommu_prot & IOMMU_READ) @@ -2541,8 +2633,10 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, struct iommu_iotlb_gather *gather) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return 0; return iommu_unmap_page(domain, iova, page_size); @@ -2553,9 +2647,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, { struct protection_domain *domain = to_pdomain(dom); unsigned long offset_mask, pte_pgsize; + struct domain_pgtable pgtable; u64 *pte, __pte; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return iova; pte = fetch_pte(domain, iova, &pte_pgsize); @@ -2708,16 +2804,26 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); void amd_iommu_domain_direct_map(struct iommu_domain *dom) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; unsigned long flags; + u64 pt_root; spin_lock_irqsave(&domain->lock, flags); + /* First save pgtable configuration*/ + amd_iommu_domain_get_pgtable(domain, &pgtable); + /* Update data structure */ - domain->mode = PAGE_MODE_NONE; + pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE); + atomic64_set(&domain->pt_root, pt_root); /* Make changes visible to IOMMUs */ update_domain(domain); + /* Restore old pgtable in domain->ptroot to free page-table */ + pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode); + atomic64_set(&domain->pt_root, pt_root); + /* Page-table is not visible to IOMMU anymore, so free it */ free_pagetable(domain); @@ -2908,9 +3014,11 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc) static int __set_gcr3(struct protection_domain *domain, int pasid, unsigned long cr3) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true); @@ -2924,9 +3032,11 @@ static int __set_gcr3(struct protection_domain *domain, int pasid, static int __clear_gcr3(struct protection_domain *domain, int pasid) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 6be3853a5d97..2b9a67ecc6ac 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -2936,7 +2936,7 @@ static int __init parse_amd_iommu_intr(char *str) { for (; *str; ++str) { if (strncmp(str, "legacy", 6) == 0) { - amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA; break; } if (strncmp(str, "vapic", 5) == 0) { diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index ca8c4522045b..7a8fdec138bd 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -468,8 +468,7 @@ struct protection_domain { iommu core code */ spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ - int mode; /* paging mode (0-6 levels) */ - u64 *pt_root; /* page table root pointer */ + atomic64_t pt_root; /* pgtable root and pgtable mode */ int glx; /* Number of levels for GCR3 table */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ @@ -477,6 +476,12 @@ struct protection_domain { unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ }; +/* For decocded pt_root */ +struct domain_pgtable { + int mode; + u64 *root; +}; + /* * Structure where we save information about one hardware AMD IOMMU in the * system. diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ef0a5246700e..0182cff2c7ac 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -371,11 +371,11 @@ int dmar_disabled = 0; int dmar_disabled = 1; #endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */ -#ifdef INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON +#ifdef CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON int intel_iommu_sm = 1; #else int intel_iommu_sm; -#endif /* INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */ +#endif /* CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */ int intel_iommu_enabled = 0; EXPORT_SYMBOL_GPL(intel_iommu_enabled); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 2b471419e26c..7b375421afba 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -170,6 +170,7 @@ static struct dev_iommu *dev_iommu_get(struct device *dev) static void dev_iommu_free(struct device *dev) { + iommu_fwspec_free(dev); kfree(dev->iommu); dev->iommu = NULL; } @@ -1428,7 +1429,7 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev) return group; } -EXPORT_SYMBOL(iommu_group_get_for_dev); +EXPORT_SYMBOL_GPL(iommu_group_get_for_dev); struct iommu_domain *iommu_group_default_domain(struct iommu_group *group) { diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index 0e2a96467767..5b3b270972f8 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -824,8 +824,11 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) qcom_iommu->dev = dev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) + if (res) { qcom_iommu->local_base = devm_ioremap_resource(dev, res); + if (IS_ERR(qcom_iommu->local_base)) + return PTR_ERR(qcom_iommu->local_base); + } qcom_iommu->iface_clk = devm_clk_get(dev, "iface"); if (IS_ERR(qcom_iommu->iface_clk)) { diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index d5cac4f46ca5..4e1d11af23c8 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -453,7 +453,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, if (!region) return -ENOMEM; - list_add(&vdev->resv_regions, ®ion->list); + list_add(®ion->list, &vdev->resv_regions); return 0; } diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 58fd137b6ae1..3e500098132f 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -585,10 +585,12 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) /* Do we need to select a new pgpath? */ pgpath = READ_ONCE(m->current_pgpath); - queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); - if (!pgpath || !queue_io) + if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) pgpath = choose_pgpath(m, bio->bi_iter.bi_size); + /* MPATHF_QUEUE_IO might have been cleared by choose_pgpath. */ + queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags); + if ((pgpath && queue_io) || (!pgpath && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))) { /* Queue for the daemon to resubmit */ diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 49147e634046..fb41b4f23c48 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -435,7 +435,7 @@ int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, fio->level++; if (type == DM_VERITY_BLOCK_TYPE_METADATA) - block += v->data_blocks; + block = block - v->hash_start + v->data_blocks; /* * For RS(M, N), the continuous FEC data is divided into blocks of N diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 114927da9cc9..613c171b1b6d 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -931,6 +931,24 @@ static int writecache_alloc_entries(struct dm_writecache *wc) return 0; } +static int writecache_read_metadata(struct dm_writecache *wc, sector_t n_sectors) +{ + struct dm_io_region region; + struct dm_io_request req; + + region.bdev = wc->ssd_dev->bdev; + region.sector = wc->start_sector; + region.count = n_sectors; + req.bi_op = REQ_OP_READ; + req.bi_op_flags = REQ_SYNC; + req.mem.type = DM_IO_VMA; + req.mem.ptr.vma = (char *)wc->memory_map; + req.client = wc->dm_io; + req.notify.fn = NULL; + + return dm_io(&req, 1, ®ion, NULL); +} + static void writecache_resume(struct dm_target *ti) { struct dm_writecache *wc = ti->private; @@ -941,8 +959,18 @@ static void writecache_resume(struct dm_target *ti) wc_lock(wc); - if (WC_MODE_PMEM(wc)) + if (WC_MODE_PMEM(wc)) { persistent_memory_invalidate_cache(wc->memory_map, wc->memory_map_size); + } else { + r = writecache_read_metadata(wc, wc->metadata_sectors); + if (r) { + size_t sb_entries_offset; + writecache_error(wc, r, "unable to read metadata: %d", r); + sb_entries_offset = offsetof(struct wc_memory_superblock, entries); + memset((char *)wc->memory_map + sb_entries_offset, -1, + (wc->metadata_sectors << SECTOR_SHIFT) - sb_entries_offset); + } + } wc->tree = RB_ROOT; INIT_LIST_HEAD(&wc->lru); @@ -2102,6 +2130,12 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->error = "Invalid block size"; goto bad; } + if (wc->block_size < bdev_logical_block_size(wc->dev->bdev) || + wc->block_size < bdev_logical_block_size(wc->ssd_dev->bdev)) { + r = -EINVAL; + ti->error = "Block size is smaller than device logical block size"; + goto bad; + } wc->block_size_bits = __ffs(wc->block_size); wc->max_writeback_jobs = MAX_WRITEBACK_JOBS; @@ -2200,8 +2234,6 @@ invalid_optional: goto bad; } } else { - struct dm_io_region region; - struct dm_io_request req; size_t n_blocks, n_metadata_blocks; uint64_t n_bitmap_bits; @@ -2258,19 +2290,9 @@ invalid_optional: goto bad; } - region.bdev = wc->ssd_dev->bdev; - region.sector = wc->start_sector; - region.count = wc->metadata_sectors; - req.bi_op = REQ_OP_READ; - req.bi_op_flags = REQ_SYNC; - req.mem.type = DM_IO_VMA; - req.mem.ptr.vma = (char *)wc->memory_map; - req.client = wc->dm_io; - req.notify.fn = NULL; - - r = dm_io(&req, 1, ®ion, NULL); + r = writecache_read_metadata(wc, wc->block_size >> SECTOR_SHIFT); if (r) { - ti->error = "Unable to read metadata"; + ti->error = "Unable to read first block of metadata"; goto bad; } } diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 668418d7ea77..f620442addf5 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1465,6 +1465,13 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; +/* LBG with quirk for SPS Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS, +}; + /* Tiger Lake and newer devices */ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_PCH8_HFS, @@ -1487,6 +1494,7 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, }; diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index 4a8d4dcd5a91..b6b94e211464 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -80,6 +80,9 @@ struct mei_me_hw { * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer * @MEI_ME_NUM_CFG: Upper Sentinel. */ @@ -93,6 +96,7 @@ enum mei_cfg_idx { MEI_ME_PCH8_CFG, MEI_ME_PCH8_SPS_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_CFG, MEI_ME_PCH15_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 0c390fe421ad..a1ed375fed37 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -70,7 +70,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 5bd0ab8b236a..baa6314f69b4 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -878,7 +878,7 @@ static int mmc_send_hpi_cmd(struct mmc_card *card) * Issued High Priority Interrupt, and check for card status * until out-of prg-state. */ -int mmc_interrupt_hpi(struct mmc_card *card) +static int mmc_interrupt_hpi(struct mmc_card *card) { int err; u32 status; diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c index c2239ee2c0ef..75934f3c117e 100644 --- a/drivers/mmc/host/cqhci.c +++ b/drivers/mmc/host/cqhci.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -349,12 +350,16 @@ static int cqhci_enable(struct mmc_host *mmc, struct mmc_card *card) /* CQHCI is idle and should halt immediately, so set a small timeout */ #define CQHCI_OFF_TIMEOUT 100 +static u32 cqhci_read_ctl(struct cqhci_host *cq_host) +{ + return cqhci_readl(cq_host, CQHCI_CTL); +} + static void cqhci_off(struct mmc_host *mmc) { struct cqhci_host *cq_host = mmc->cqe_private; - ktime_t timeout; - bool timed_out; u32 reg; + int err; if (!cq_host->enabled || !mmc->cqe_on || cq_host->recovery_halt) return; @@ -364,15 +369,9 @@ static void cqhci_off(struct mmc_host *mmc) cqhci_writel(cq_host, CQHCI_HALT, CQHCI_CTL); - timeout = ktime_add_us(ktime_get(), CQHCI_OFF_TIMEOUT); - while (1) { - timed_out = ktime_compare(ktime_get(), timeout) > 0; - reg = cqhci_readl(cq_host, CQHCI_CTL); - if ((reg & CQHCI_HALT) || timed_out) - break; - } - - if (timed_out) + err = readx_poll_timeout(cqhci_read_ctl, cq_host, reg, + reg & CQHCI_HALT, 0, CQHCI_OFF_TIMEOUT); + if (err < 0) pr_err("%s: cqhci: CQE stuck on\n", mmc_hostname(mmc)); else pr_debug("%s: cqhci: CQE off\n", mmc_hostname(mmc)); diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 8b038e7b2cd3..2e58743d83bb 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -357,14 +357,6 @@ static void meson_mx_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) meson_mx_mmc_start_cmd(mmc, mrq->cmd); } -static int meson_mx_mmc_card_busy(struct mmc_host *mmc) -{ - struct meson_mx_mmc_host *host = mmc_priv(mmc); - u32 irqc = readl(host->base + MESON_MX_SDIO_IRQC); - - return !!(irqc & MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK); -} - static void meson_mx_mmc_read_response(struct mmc_host *mmc, struct mmc_command *cmd) { @@ -506,7 +498,6 @@ static void meson_mx_mmc_timeout(struct timer_list *t) static struct mmc_host_ops meson_mx_mmc_ops = { .request = meson_mx_mmc_request, .set_ios = meson_mx_mmc_set_ios, - .card_busy = meson_mx_mmc_card_busy, .get_cd = mmc_gpio_get_cd, .get_ro = mmc_gpio_get_ro, }; @@ -570,7 +561,7 @@ static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host) mmc->f_max = clk_round_rate(host->cfg_div_clk, clk_get_rate(host->parent_clk)); - mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23; + mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_WAIT_WHILE_BUSY; mmc->ops = &meson_mx_mmc_ops; ret = mmc_of_parse(mmc); diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 09ff7315eb5e..a8bcb3f16aa4 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2087,6 +2087,8 @@ static int sdhci_msm_probe(struct platform_device *pdev) goto clk_disable; } + msm_host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_NEED_RSP_BUSY; + pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 525de2454a4d..2527244c2ae1 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -601,6 +601,9 @@ static int intel_select_drive_strength(struct mmc_card *card, struct sdhci_pci_slot *slot = sdhci_priv(host); struct intel_host *intel_host = sdhci_pci_priv(slot); + if (!(mmc_driver_type_mask(intel_host->drv_strength) & card_drv)) + return 0; + return intel_host->drv_strength; } diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 1dea1ba66f7b..4703cd540c7f 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -235,6 +235,16 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); + + /* + * For some reason the controller's Host Control2 register reports + * the bit representing 1.8V signaling as 0 when read after it was + * written as 1. Subsequent read reports 1. + * + * Since this may cause some issues, do an empty read of the Host + * Control2 register here to circumvent this. + */ + sdhci_readw(host, SDHCI_HOST_CONTROL2); } static const struct sdhci_ops sdhci_xenon_ops = { diff --git a/drivers/most/core.c b/drivers/most/core.c index 06426fc5c990..f781c46cd4af 100644 --- a/drivers/most/core.c +++ b/drivers/most/core.c @@ -1483,7 +1483,7 @@ static void __exit most_exit(void) ida_destroy(&mdev_id); } -module_init(most_init); +subsys_initcall(most_init); module_exit(most_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Christian Gromm "); diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 6435020d690d..51185e4d7d15 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -24,8 +24,8 @@ config NET_DSA_MV88E6XXX_PTP bool "PTP support for Marvell 88E6xxx" default n depends on NET_DSA_MV88E6XXX_GLOBAL2 + depends on PTP_1588_CLOCK imply NETWORK_PHY_TIMESTAMPING - imply PTP_1588_CLOCK help Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch chips that support it. diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index dd8a5666a584..2b4a723c8306 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3962,7 +3962,6 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390_phylink_validate, }; @@ -4021,7 +4020,6 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390x_phylink_validate, }; @@ -4079,7 +4077,6 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, .phylink_validate = mv88e6390_phylink_validate, @@ -4235,7 +4232,6 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index d0a3764ff0cf..e2c6bf0e430e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -400,6 +400,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) ocelot->stats_layout = felix->info->stats_layout; ocelot->num_stats = felix->info->num_stats; ocelot->shared_queue_sz = felix->info->shared_queue_sz; + ocelot->num_mact_rows = felix->info->num_mact_rows; ocelot->vcap_is2_keys = felix->info->vcap_is2_keys; ocelot->vcap_is2_actions= felix->info->vcap_is2_actions; ocelot->vcap = felix->info->vcap; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 82d46f260041..9af106513e53 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -15,6 +15,7 @@ struct felix_info { const u32 *const *map; const struct ocelot_ops *ops; int shared_queue_sz; + int num_mact_rows; const struct ocelot_stat_layout *stats_layout; unsigned int num_stats; int num_ports; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index b4078f3c5c38..8bf395f12b47 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1220,6 +1220,7 @@ struct felix_info felix_info_vsc9959 = { .vcap_is2_actions = vsc9959_vcap_is2_actions, .vcap = vsc9959_vcap_props, .shared_queue_sz = 128 * 1024, + .num_mact_rows = 2048, .num_ports = 6, .switch_pci_bar = 4, .imdio_pci_bar = 0, diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 0fe1ae173aa1..68c3086af9af 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -20,6 +20,7 @@ tristate "NXP SJA1105 Ethernet switch family support" config NET_DSA_SJA1105_PTP bool "Support for the PTP clock on the NXP SJA1105 Ethernet switch" depends on NET_DSA_SJA1105 + depends on PTP_1588_CLOCK help This enables support for timestamping and PTP clock manipulations in the SJA1105 DSA driver. diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index a22f8e3fc06b..bc0e47c1dbb9 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -16,14 +16,15 @@ /* PTPSYNCTS has no interrupt or update mechanism, because the intended * hardware use case is for the timestamp to be collected synchronously, - * immediately after the CAS_MASTER SJA1105 switch has triggered a CASSYNC - * pulse on the PTP_CLK pin. When used as a generic extts source, it needs - * polling and a comparison with the old value. The polling interval is just - * the Nyquist rate of a canonical PPS input (e.g. from a GPS module). - * Anything of higher frequency than 1 Hz will be lost, since there is no - * timestamp FIFO. + * immediately after the CAS_MASTER SJA1105 switch has performed a CASSYNC + * one-shot toggle (no return to level) on the PTP_CLK pin. When used as a + * generic extts source, the PTPSYNCTS register needs polling and a comparison + * with the old value. The polling interval is configured as the Nyquist rate + * of a signal with 50% duty cycle and 1Hz frequency, which is sadly all that + * this hardware can do (but may be enough for some setups). Anything of higher + * frequency than 1 Hz will be lost, since there is no timestamp FIFO. */ -#define SJA1105_EXTTS_INTERVAL (HZ / 2) +#define SJA1105_EXTTS_INTERVAL (HZ / 4) /* This range is actually +/- SJA1105_MAX_ADJ_PPB * divided by 1000 (ppb -> ppm) and with a 16-bit @@ -754,7 +755,16 @@ static int sja1105_extts_enable(struct sja1105_private *priv, return -EOPNOTSUPP; /* Reject requests with unsupported flags */ - if (extts->flags) + if (extts->flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* We can only enable time stamping on both edges, sadly. */ + if ((extts->flags & PTP_STRICT_FLAGS) && + (extts->flags & PTP_ENABLE_FEATURE) && + (extts->flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) return -EOPNOTSUPP; rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_EXTTS); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 97dfd0c67e84..9e1860d81908 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -69,7 +69,7 @@ * 16kB. */ #if PAGE_SIZE > SZ_16K -#define ENA_PAGE_SIZE SZ_16K +#define ENA_PAGE_SIZE (_AC(SZ_16K, UL)) #else #define ENA_PAGE_SIZE PAGE_SIZE #endif diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 2edf137a7030..8a70ffe1d326 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -57,7 +57,7 @@ static const struct aq_board_revision_s hw_atl_boards[] = { { AQ_DEVICE_ID_D108, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_D109, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc109, }, - { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, + { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc100, }, { AQ_DEVICE_ID_AQC107, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, { AQ_DEVICE_ID_AQC108, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_AQC109, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc109, }, diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index a5d1a6cb9ce3..6795b6d95f54 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,6 +172,7 @@ static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; + struct resource *regs; const u8 *mac_addr; bgmac = bgmac_alloc(&pdev->dev); @@ -206,16 +207,21 @@ static int bgmac_probe(struct platform_device *pdev) if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base); - bgmac->plat.idm_base = - devm_platform_ioremap_resource_byname(pdev, "idm_base"); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + } - bgmac->plat.nicpm_base = - devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); + if (regs) { + bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, + regs); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); + } bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fead64f1ad90..d1a83716d934 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6642,7 +6642,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp, int rc; if (!mem_size) - return 0; + return -EINVAL; ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE); if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) { @@ -9780,6 +9780,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, netdev_features_t features) { struct bnxt *bp = netdev_priv(dev); + netdev_features_t vlan_features; if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; @@ -9796,12 +9797,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) != - (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) { + vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); + if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) features &= ~(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); - else + else if (vlan_features) features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; } @@ -12212,12 +12215,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) bnxt_ulp_start(bp, err); } - if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) - dev_close(netdev); + if (result != PCI_ERS_RESULT_RECOVERED) { + if (netif_running(netdev)) + dev_close(netdev); + pci_disable_device(pdev); + } rtnl_unlock(); - return PCI_ERS_RESULT_RECOVERED; + return result; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f2caa2756f5b..f6a3250ef1c5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1066,7 +1066,6 @@ struct bnxt_vf_info { #define BNXT_VF_LINK_FORCED 0x4 #define BNXT_VF_LINK_UP 0x8 #define BNXT_VF_TRUST 0x10 - u32 func_flags; /* func cfg flags */ u32 min_tx_rate; u32 max_tx_rate; void *hwrm_cmd_req_addr; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 95f893f2a74d..d5c8bd49383a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -43,7 +43,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) #define BNXT_NVM_CFG_VER_BITS 24 #define BNXT_NVM_CFG_VER_BYTES 4 -#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MAX 512 #define BNXT_MSIX_VEC_MIN_MAX 128 enum bnxt_nvm_dir_type { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 6ea3df6da18c..cea2f9958a1d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) if (old_setting == setting) return 0; - func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ @@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { - vf->func_flags = func_flags; if (setting) vf->flags |= BNXT_VF_SPOOFCHK; else @@ -228,7 +226,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -266,7 +263,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -305,7 +301,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW); @@ -477,7 +472,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id) vf = &bp->pf.vf[vf_id]; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); if (is_valid_ether_addr(vf->mac_addr)) { req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index 53b50c24d9c9..2c4c12b03502 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -35,8 +35,8 @@ config MACB config MACB_USE_HWSTAMP bool "Use IEEE 1588 hwstamp" depends on MACB + depends on PTP_1588_CLOCK default y - imply PTP_1588_CLOCK ---help--- Enable IEEE 1588 Precision Time Protocol (PTP) support for MACB. diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index a0e8c5bbabc0..36290a8e2a84 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -334,8 +334,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -386,8 +388,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -3816,8 +3820,10 @@ static int at91ether_open(struct net_device *dev) int ret; ret = pm_runtime_get_sync(&lp->pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&lp->pdev->dev); return ret; + } /* Clear internal statistics */ ctl = macb_readl(lp, NCR); @@ -4172,15 +4178,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk, static int fu540_c000_init(struct platform_device *pdev) { - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res) - return -ENODEV; - - mgmt->reg = ioremap(res->start, resource_size(res)); - if (!mgmt->reg) - return -ENOMEM; + mgmt->reg = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(mgmt->reg)) + return PTR_ERR(mgmt->reg); return macb_init(pdev); } diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 6a700d34019e..4520e7ee00fe 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,7 @@ config THUNDER_NIC_RGX config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index f5dd34db4b54..6516c45864b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2207,6 +2207,9 @@ static void ethofld_hard_xmit(struct net_device *dev, if (unlikely(skip_eotx_wr)) { start = (u64 *)wr; eosw_txq->state = next_state; + eosw_txq->cred -= wrlen16; + eosw_txq->ncompl++; + eosw_txq->last_compl = 0; goto write_wr_headers; } @@ -2365,6 +2368,34 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) return cxgb4_eth_xmit(skb, dev); } +static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq) +{ + int pktcount = eosw_txq->pidx - eosw_txq->last_pidx; + int pidx = eosw_txq->pidx; + struct sk_buff *skb; + + if (!pktcount) + return; + + if (pktcount < 0) + pktcount += eosw_txq->ndesc; + + while (pktcount--) { + pidx--; + if (pidx < 0) + pidx += eosw_txq->ndesc; + + skb = eosw_txq->desc[pidx].skb; + if (skb) { + dev_consume_skb_any(skb); + eosw_txq->desc[pidx].skb = NULL; + eosw_txq->inuse--; + } + } + + eosw_txq->pidx = eosw_txq->last_pidx + 1; +} + /** * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc. * @dev - netdevice @@ -2440,9 +2471,11 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc) FW_FLOWC_MNEM_EOSTATE_CLOSING : FW_FLOWC_MNEM_EOSTATE_ESTABLISHED); - eosw_txq->cred -= len16; - eosw_txq->ncompl++; - eosw_txq->last_compl = 0; + /* Free up any pending skbs to ensure there's room for + * termination FLOWC. + */ + if (tc == FW_SCHED_CLS_NONE) + eosw_txq_flush_pending_skbs(eosw_txq); ret = eosw_txq_enqueue(eosw_txq, skb); if (ret) { @@ -2695,6 +2728,7 @@ static void ofldtxq_stop(struct sge_uld_txq *q, struct fw_wr_hdr *wr) * is ever running at a time ... */ static void service_ofldq(struct sge_uld_txq *q) + __must_hold(&q->sendq.lock) { u64 *pos, *before, *end; int credits; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c index ebc635f8a4cc..15f37c5b8dc1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -74,8 +74,8 @@ err_pci_mem_reg: pci_disable_device(pdev); err_pci_enable: err_mdiobus_alloc: - iounmap(port_regs); err_hw_alloc: + iounmap(port_regs); err_ioremap: return err; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4bd33245bad6..3de549c6c693 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2189,7 +2189,8 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } - } else { + } else if (!(rwi->reset_reason == VNIC_RESET_FATAL && + adapter->from_passive_init)) { rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 8972cdd559e8..7352244c5e68 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1428,6 +1428,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port, struct mvpp2_ethtool_fs *efs; int ret; + if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW) + return -EINVAL; + efs = port->rfs_rules[info->fs.location]; if (!efs) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 1fa60e985b43..2b5dad2ec650 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4329,6 +4329,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, if (!mvpp22_rss_is_supported()) return -EOPNOTSUPP; + if (rss_context >= MVPP22_N_RSS_TABLES) + return -EINVAL; if (hfunc) *hfunc = ETH_RSS_HASH_CRC32; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5716c3d2bb86..c72c4e1ea383 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; + err = 0; } else if (err == -ENOENT) { err = 0; continue; @@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) *idx = get_param_l(&out_param); - + if (WARN_ON(err == -ENOSPC)) + err = -EINVAL; return err; } return __mlx4_counter_alloc(dev, idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 34cba97f7bf4..cede5bdfd598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work) } cmd->ent_arr[ent->idx] = ent; - set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work) if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ if (pci_channel_offline(dev->pdev) || @@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + /* no doorbell, no need to keep the entry */ + free_ent(cmd, ent->idx); + if (ent->callback) + free_cmd(ent); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 55457f268495..f372e94948fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1773,19 +1773,14 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv) { - int err = mlx5e_init_rep_rx(priv); - - if (err) - return err; - mlx5e_create_q_counters(priv); - return 0; + return mlx5e_init_rep_rx(priv); } static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv) { - mlx5e_destroy_q_counters(priv); mlx5e_cleanup_rep_rx(priv); + mlx5e_destroy_q_counters(priv); } static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b2e38e0cde97..5d9def18ae3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1550,9 +1550,9 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw) MLX5_FLOW_NAMESPACE_KERNEL, 1, modact); if (IS_ERR(mod_hdr)) { + err = PTR_ERR(mod_hdr); esw_warn(dev, "Failed to create restore mod header, err: %d\n", err); - err = PTR_ERR(mod_hdr); goto err_mod_hdr; } @@ -2219,10 +2219,12 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev); memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); + mutex_init(&esw->fdb_table.offloads.vports.lock); + hash_init(esw->fdb_table.offloads.vports.table); err = esw_create_uplink_offloads_acl_tables(esw); if (err) - return err; + goto create_acl_err; err = esw_create_offloads_table(esw, total_vports); if (err) @@ -2240,9 +2242,6 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_fg_err; - mutex_init(&esw->fdb_table.offloads.vports.lock); - hash_init(esw->fdb_table.offloads.vports.table); - return 0; create_fg_err: @@ -2253,18 +2252,19 @@ create_restore_err: esw_destroy_offloads_table(esw); create_offloads_err: esw_destroy_uplink_offloads_acl_tables(esw); - +create_acl_err: + mutex_destroy(&esw->fdb_table.offloads.vports.lock); return err; } static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) { - mutex_destroy(&esw->fdb_table.offloads.vports.lock); esw_destroy_vport_rx_group(esw); esw_destroy_offloads_fdb_tables(esw); esw_destroy_restore_table(esw); esw_destroy_offloads_table(esw); esw_destroy_uplink_offloads_acl_tables(esw); + mutex_destroy(&esw->fdb_table.offloads.vports.lock); } static void @@ -2377,9 +2377,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) err_vports: esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); err_uplink: - esw_set_passing_vport_metadata(esw, false); -err_steering_init: esw_offloads_steering_cleanup(esw); +err_steering_init: + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index c0ab9cf74929..18719acb7e54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -695,6 +695,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq, pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); } +static void dr_cq_complete(struct mlx5_core_cq *mcq, + struct mlx5_eqe *eqe) +{ + pr_err("CQ completion CQ: #%u\n", mcq->cqn); +} + static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -756,6 +762,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); cq->mcq.event = dr_cq_event; + cq->mcq.comp = dr_cq_complete; err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); @@ -767,7 +774,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cq->mcq.set_ci_db = cq->wq_ctrl.db.db; cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; *cq->mcq.set_ci_db = 0; - *cq->mcq.arm_db = 0; + + /* set no-zero value, in order to avoid the HW to run db-recovery on + * CQ that used in polling mode. + */ + *cq->mcq.arm_db = cpu_to_be32(2 << 28); + cq->mcq.vector = 0; cq->mcq.irqn = irqn; cq->mcq.uar = uar; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 430da69003d8..a6e30e020b5c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, unsigned int priority, struct mlxsw_afk_element_usage *elusage) { + struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2; struct mlxsw_sp_acl_tcam_vregion *vregion; - struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct list_head *pos; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) @@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion); - list_add_tail(&vchunk->list, &vregion->vchunk_list); + + /* Position the vchunk inside the list according to priority */ + list_for_each(pos, &vregion->vchunk_list) { + vchunk2 = list_entry(pos, typeof(*vchunk2), list); + if (vchunk2->priority > priority) + break; + } + list_add_tail(&vchunk->list, pos); mutex_unlock(&vregion->lock); return vchunk; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 51117a5a6bbf..890b078851c9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -36,7 +36,8 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack); if (err) return err; - } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED) { + } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED && + act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) { NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index e1651756bf9d..f70bb81e1ed6 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -564,7 +564,7 @@ static int moxart_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); unregister_netdev(ndev); - free_irq(ndev->irq, ndev); + devm_free_irq(&pdev->dev, ndev->irq, ndev); moxart_mac_free_memory(ndev); free_netdev(ndev); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index a8c48a4a708f..02350c3d9d01 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1031,10 +1031,8 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, { int i, j; - /* Loop through all the mac tables entries. There are 1024 rows of 4 - * entries. - */ - for (i = 0; i < 1024; i++) { + /* Loop through all the mac tables entries. */ + for (i = 0; i < ocelot->num_mact_rows; i++) { for (j = 0; j < 4; j++) { struct ocelot_mact_entry entry; bool is_static; @@ -1453,8 +1451,15 @@ static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port, void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs) { - ocelot_write(ocelot, ANA_AUTOAGE_AGE_PERIOD(msecs / 2), - ANA_AUTOAGE); + unsigned int age_period = ANA_AUTOAGE_AGE_PERIOD(msecs / 2000); + + /* Setting AGE_PERIOD to zero effectively disables automatic aging, + * which is clearly not what our intention is. So avoid that. + */ + if (!age_period) + age_period = 1; + + ocelot_rmw(ocelot, age_period, ANA_AUTOAGE_AGE_PERIOD_M, ANA_AUTOAGE); } EXPORT_SYMBOL(ocelot_set_ageing_time); diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index b88b5899b227..7d4fd1b6adda 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -431,6 +431,7 @@ int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) ocelot->stats_layout = ocelot_stats_layout; ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout); ocelot->shared_queue_sz = 224 * 1024; + ocelot->num_mact_rows = 1024; ocelot->ops = ops; ret = ocelot_regfields_init(ocelot, ocelot_regfields); diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index bfa0c0d39600..8b018ed37b1b 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -208,11 +208,13 @@ static int jazz_sonic_probe(struct platform_device *pdev) err = register_netdev(dev); if (err) - goto out1; + goto undo_probe1; return 0; -out1: +undo_probe1: + dma_free_coherent(lp->device, SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), + lp->descriptors, lp->descriptors_laddr); release_mem_region(dev->base_addr, SONIC_MEM_SIZE); out: free_netdev(dev); diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 9183b3e85d21..354efffac0f9 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, if (!nfp_nsp_has_hwinfo_lookup(nsp)) { nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n"); eth_hw_addr_random(nn->dp.netdev); + nfp_nsp_close(nsp); return; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 5f8fc58d42b3..11621ccc1faf 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -170,8 +170,7 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa); debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs); debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size); - debugfs_create_u8("done_color", 0400, cq_dentry, - (u8 *)&cq->done_color); + debugfs_create_bool("done_color", 0400, cq_dentry, &cq->done_color); debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5acf4f46c268..d5293bfded29 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2101,6 +2101,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) ionic_txrx_free(lif); } ionic_lifs_deinit(ionic); + ionic_reset(ionic); ionic_qcqs_free(lif); dev_info(ionic->dev, "FW Down: LIFs stopped\n"); @@ -2116,6 +2117,7 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) dev_info(ionic->dev, "FW Up: restarting LIFs\n"); + ionic_init_devinfo(ionic); err = ionic_qcqs_alloc(lif); if (err) goto err_out; @@ -2549,8 +2551,6 @@ int ionic_lifs_register(struct ionic *ionic) dev_err(ionic->dev, "Cannot register net device, aborting\n"); return err; } - - ionic_link_status_check_request(ionic->master_lif); ionic->master_lif->registered = true; return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 494c859b4ade..67ba67ed0cb9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -624,7 +624,7 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, total_offset += offset; } - total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000; + total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL; total_ctr += total_offset; ctr_low = do_div(total_ctr, 1000000000); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 565da6498c84..a999d6b33a64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4060,7 +4060,7 @@ static int stmmac_set_features(struct net_device *netdev, /** * stmmac_interrupt - main ISR * @irq: interrupt number. - * @dev_id: to pass the net device pointer. + * @dev_id: to pass the net device pointer (must be valid). * Description: this is the main driver interrupt service routine. * It can call: * o DMA service routine (to manage incoming frame reception and transmission @@ -4084,11 +4084,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (priv->irq_wake) pm_wakeup_event(priv->device, 0); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -4991,7 +4986,7 @@ int stmmac_dvr_probe(struct device *device, priv->plat->bsp_priv); if (ret < 0) - return ret; + goto error_serdes_powerup; } #ifdef CONFIG_DEBUG_FS @@ -5000,6 +4995,8 @@ int stmmac_dvr_probe(struct device *device, return ret; +error_serdes_powerup: + unregister_netdev(ndev); error_netdev_register: phylink_destroy(priv->phylink); error_phy_setup: diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 89cec778cf2d..8e348780efb6 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -90,9 +90,8 @@ config TI_CPTS config TI_CPTS_MOD tristate depends on TI_CPTS + depends on PTP_1588_CLOCK default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y - select NET_PTP_CLASSIFY - imply PTP_1588_CLOCK default m config TI_K3_AM65_CPSW_NUSS diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2bf56733ba94..2517ffba8178 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1719,7 +1719,8 @@ static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, tx_chn->irq, am65_cpsw_nuss_tx_irq, - 0, tx_chn->tx_chn_name, tx_chn); + IRQF_TRIGGER_HIGH, + tx_chn->tx_chn_name, tx_chn); if (ret) { dev_err(dev, "failure requesting tx%u irq %u, %d\n", tx_chn->id, tx_chn->irq, ret); @@ -1744,7 +1745,7 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, common->rx_chns.irq, am65_cpsw_nuss_rx_irq, - 0, dev_name(dev), common); + IRQF_TRIGGER_HIGH, dev_name(dev), common); if (ret) { dev_err(dev, "failure requesting rx irq %u, %d\n", common->rx_chns.irq, ret); diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index b50c3ec3495b..6bcda20ed7e7 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -643,7 +643,7 @@ static int tc_mii_probe(struct net_device *dev) linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask); } - linkmode_and(phydev->supported, phydev->supported, mask); + linkmode_andnot(phydev->supported, phydev->supported, mask); linkmode_copy(phydev->advertising, phydev->supported); lp->link = 0; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 672cd2caf2fb..21640a035d7d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1169,11 +1169,11 @@ out_unlock: static struct genl_family gtp_genl_family; static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, - u32 type, struct pdp_ctx *pctx) + int flags, u32 type, struct pdp_ctx *pctx) { void *genlh; - genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, 0, + genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, type); if (genlh == NULL) goto nlmsg_failure; @@ -1227,8 +1227,8 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) goto err_unlock; } - err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, - info->snd_seq, info->nlhdr->nlmsg_type, pctx); + err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq, + 0, info->nlhdr->nlmsg_type, pctx); if (err < 0) goto err_unlock_free; @@ -1271,6 +1271,7 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, gtp_genl_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; cb->args[1] = j; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d8e86bdbfba1..ebcfbae05690 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -707,7 +707,8 @@ no_memory: goto drop; } -static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb, + struct net_device *ndev) { return netvsc_xmit(skb, ndev, false); } diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 845478a19a4f..b671bea0aa7c 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1041,6 +1041,7 @@ static void gsi_isr_gp_int1(struct gsi *gsi) complete(&gsi->completion); } + /* Inter-EE interrupt handler */ static void gsi_isr_glob_ee(struct gsi *gsi) { @@ -1493,6 +1494,12 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, struct completion *completion = &gsi->completion; u32 val; + /* First zero the result code field */ + val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + val &= ~GENERIC_EE_RESULT_FMASK; + iowrite32(val, gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + + /* Now issue the command */ val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK); val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK); val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK); @@ -1798,9 +1805,9 @@ static int gsi_channel_init_one(struct gsi *gsi, /* Worst case we need an event for every outstanding TRE */ if (data->channel.tre_count > data->channel.event_count) { - dev_warn(gsi->dev, "channel %u limited to %u TREs\n", - data->channel_id, data->channel.tre_count); tre_count = data->channel.event_count; + dev_warn(gsi->dev, "channel %u limited to %u TREs\n", + data->channel_id, tre_count); } else { tre_count = data->channel.tre_count; } diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index 7613b9cc7cf6..acc9e744c67d 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -410,6 +410,8 @@ #define INTER_EE_RESULT_FMASK GENMASK(2, 0) #define GENERIC_EE_RESULT_FMASK GENMASK(7, 5) #define GENERIC_EE_SUCCESS_FVAL 1 +#define GENERIC_EE_INCORRECT_DIRECTION_FVAL 3 +#define GENERIC_EE_INCORRECT_CHANNEL_FVAL 5 #define GENERIC_EE_NO_RESOURCES_FVAL 7 #define USB_MAX_PACKET_FMASK GENMASK(15, 15) /* 0: HS; 1: SS */ #define MHI_BASE_CHANNEL_FMASK GENMASK(31, 24) diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 6de03be28784..a21534f1462f 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1283,7 +1283,7 @@ static int ipa_endpoint_stop_rx_dma(struct ipa *ipa) */ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) { - u32 retries = endpoint->toward_ipa ? 0 : IPA_ENDPOINT_STOP_RX_RETRIES; + u32 retries = IPA_ENDPOINT_STOP_RX_RETRIES; int ret; do { @@ -1291,12 +1291,9 @@ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) struct gsi *gsi = &ipa->gsi; ret = gsi_channel_stop(gsi, endpoint->channel_id); - if (ret != -EAGAIN) + if (ret != -EAGAIN || endpoint->toward_ipa) break; - if (endpoint->toward_ipa) - continue; - /* For IPA v3.5.1, send a DMA read task and check again */ if (ipa->version == IPA_VERSION_3_5_1) { ret = ipa_endpoint_stop_rx_dma(ipa); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 758baf7cb8a1..d0d31cb99180 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1305,7 +1305,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + /* Pick a sync gcm(aes) cipher to ensure order is preserved. */ + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -2640,11 +2641,12 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) if (ret) goto rollback; - rtnl_unlock(); /* Force features update, since they are different for SW MACSec and * HW offloading cases. */ netdev_update_features(dev); + + rtnl_unlock(); return 0; rollback: diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 415c27310982..ecbd5e0d685c 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1120,7 +1120,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus) goto out; } dp83640_clock_init(clock, bus); - list_add_tail(&phyter_clocks, &clock->list); + list_add_tail(&clock->list, &phyter_clocks); out: mutex_unlock(&phyter_clocks_lock); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index fe9aa3ad52a7..1dd19d0cb269 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -137,19 +137,18 @@ static int dp83822_set_wol(struct phy_device *phydev, value &= ~DP83822_WOL_SECURE_ON; } - value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | - DP83822_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); - } else { - value = phy_read_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_WOL_CFG); - value &= ~DP83822_WOL_EN; - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); - } + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83822_MISR2); - return 0; + value |= DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | + DP83822_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); + } else { + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, DP83822_WOL_EN); + } } static void dp83822_get_wol(struct phy_device *phydev, @@ -258,12 +257,11 @@ static int dp83822_config_intr(struct phy_device *phydev) static int dp83822_config_init(struct phy_device *phydev) { - int value; + int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN | + DP83822_WOL_SECURE_ON; - value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; - - return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); } static int dp83822_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 06f08832ebcd..d73725312c7c 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -139,16 +139,19 @@ static int dp83811_set_wol(struct phy_device *phydev, value &= ~DP83811_WOL_SECURE_ON; } - value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | - DP83811_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83811_INT_STAT1); + + value |= DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | + DP83811_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, value); } else { - phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - DP83811_WOL_EN); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, DP83811_WOL_EN); } - return 0; } static void dp83811_get_wol(struct phy_device *phydev, @@ -292,8 +295,8 @@ static int dp83811_config_init(struct phy_device *phydev) value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN; - return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); } static int dp83811_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ff12492771ab..1f1a01c98e44 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -66,6 +66,9 @@ enum { MV_PCS_CSSR1_SPD2_2500 = 0x0004, MV_PCS_CSSR1_SPD2_10000 = 0x0000, + /* Temperature read register (88E2110 only) */ + MV_PCS_TEMP = 0x8042, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -77,6 +80,7 @@ enum { MV_V2_PORT_CTRL = 0xf001, MV_V2_PORT_CTRL_SWRST = BIT(15), MV_V2_PORT_CTRL_PWRDOWN = BIT(11), + /* Temperature control/read registers (88X3310 only) */ MV_V2_TEMP_CTRL = 0xf08a, MV_V2_TEMP_CTRL_MASK = 0xc000, MV_V2_TEMP_CTRL_SAMPLE = 0x0000, @@ -104,6 +108,24 @@ static umode_t mv3310_hwmon_is_visible(const void *data, return 0; } +static int mv3310_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); +} + +static int mv2110_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_TEMP); +} + +static int mv10g_hwmon_read_temp_reg(struct phy_device *phydev) +{ + if (phydev->drv->phy_id == MARVELL_PHY_ID_88X3310) + return mv3310_hwmon_read_temp_reg(phydev); + else /* MARVELL_PHY_ID_88E2110 */ + return mv2110_hwmon_read_temp_reg(phydev); +} + static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *value) { @@ -116,7 +138,7 @@ static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, } if (type == hwmon_temp && attr == hwmon_temp_input) { - temp = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); + temp = mv10g_hwmon_read_temp_reg(phydev); if (temp < 0) return temp; @@ -169,6 +191,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) u16 val; int ret; + if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310) + return 0; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP, MV_V2_TEMP_UNKNOWN); if (ret < 0) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6c738a271257..4bb8552a00d3 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81cc, 8)}, /* Dell Wireless 5816e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 5c964fcb994e..71b8e80b58e1 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, if (multicore) { queue->worker = wg_packet_percpu_multicore_worker_alloc( function, queue); - if (!queue->worker) + if (!queue->worker) { + ptr_ring_cleanup(&queue->ring, NULL); return -ENOMEM; + } } else { INIT_WORK(&queue->work, function); } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index da3b782ab7d3..3bb5b9ae7cd1 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker(struct work_struct *work) static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; if (peer->sent_lastminute_handshake) return; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, + REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT); rcu_read_unlock_bh(); - if (send) { + if (unlikely(send)) { peer->sent_lastminute_handshake = true; wg_packet_send_queued_handshake_initiation(peer, false); } @@ -393,13 +392,11 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) goto dishonest_packet_size; - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP_ECN_set_ce(ip_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos); } else if (skb->protocol == htons(ETH_P_IPV6)) { len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP6_ECN_set_ce(skb, ipv6_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb))); } else { goto dishonest_packet_type; } @@ -518,6 +515,8 @@ void wg_packet_decrypt_worker(struct work_struct *work) &PACKET_CB(skb)->keypair->receiving)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; wg_queue_enqueue_per_peer_napi(skb, state); + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c index bcd6462e4540..007cd4457c5f 100644 --- a/drivers/net/wireguard/selftest/ratelimiter.c +++ b/drivers/net/wireguard/selftest/ratelimiter.c @@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void) enum { TRIALS_BEFORE_GIVING_UP = 5000 }; bool success = false; int test = 0, trials; - struct sk_buff *skb4, *skb6; + struct sk_buff *skb4, *skb6 = NULL; struct iphdr *hdr4; - struct ipv6hdr *hdr6; + struct ipv6hdr *hdr6 = NULL; if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) return true; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 7348c10cbae3..6687db699803 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(struct wg_device *wg, static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - (unlikely(atomic64_read(&keypair->sending.counter.counter) > - REKEY_AFTER_MESSAGES) || - (keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REKEY_AFTER_TIME))))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES || + (keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); - if (send) + if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } @@ -281,6 +278,8 @@ void wg_packet_tx_worker(struct work_struct *work) wg_noise_keypair_put(keypair, false); wg_peer_put(peer); + if (need_resched()) + cond_resched(); } } @@ -304,7 +303,8 @@ void wg_packet_encrypt_worker(struct work_struct *work) } wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, state); - + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index b0d6541582d3..f9018027fc13 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(rt->dst.dev == skb->dev)) { - ip_rt_put(rt); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip4(cache, &rt->dst, fl.saddr); @@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(dst->dev == skb->dev)) { - dst_release(dst); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip6(cache, dst, &fl.saddr); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 91c1bd659947..f3c037f5a9ba 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1110,7 +1110,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, * Don't treat an error as fatal, as we potentially already * have a NGUID or EUI-64. */ - if (status > 0) + if (status > 0 && !(status & NVME_SC_DNR)) status = 0; goto free_data; } @@ -3642,6 +3642,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) return; out_put_disk: + /* prevent double queue cleanup */ + ns->disk->queue = NULL; put_disk(ns->disk); out_unlink_ns: mutex_lock(&ctrl->subsys->lock); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4e79e412b276..e13c370de830 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + u16 tmp = nvmeq->cq_head + 1; + + if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; nvmeq->cq_phase ^= 1; + } else { + nvmeq->cq_head = tmp; } } diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index 3708d43b7508..393011a05b48 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -815,6 +815,13 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { }, { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, + }, { + /* + * Deprecated. Only here to support legacy device + * trees that didn't include "qcom,qusb2-v2-phy" + */ + .compatible = "qcom,sdm845-qusb2-phy", + .data = &qusb2_v2_phy_cfg, }, { .compatible = "qcom,qusb2-v2-phy", .data = &qusb2_v2_phy_cfg, diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c index d998e65c89c8..a52a9bf13b75 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c @@ -160,18 +160,11 @@ static int qcom_snps_hsphy_power_on(struct phy *phy) ret = regulator_bulk_enable(VREG_NUM, priv->vregs); if (ret) return ret; - ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); - if (ret) - goto err_disable_regulator; + qcom_snps_hsphy_disable_hv_interrupts(priv); qcom_snps_hsphy_exit_retention(priv); return 0; - -err_disable_regulator: - regulator_bulk_disable(VREG_NUM, priv->vregs); - - return ret; } static int qcom_snps_hsphy_power_off(struct phy *phy) @@ -180,7 +173,6 @@ static int qcom_snps_hsphy_power_off(struct phy *phy) qcom_snps_hsphy_enter_retention(priv); qcom_snps_hsphy_enable_hv_interrupts(priv); - clk_bulk_disable_unprepare(priv->num_clks, priv->clks); regulator_bulk_disable(VREG_NUM, priv->vregs); return 0; @@ -266,21 +258,39 @@ static int qcom_snps_hsphy_init(struct phy *phy) struct hsphy_priv *priv = phy_get_drvdata(phy); int ret; - ret = qcom_snps_hsphy_reset(priv); + ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); if (ret) return ret; + ret = qcom_snps_hsphy_reset(priv); + if (ret) + goto disable_clocks; + qcom_snps_hsphy_init_sequence(priv); ret = qcom_snps_hsphy_por_reset(priv); if (ret) - return ret; + goto disable_clocks; + + return 0; + +disable_clocks: + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); + return ret; +} + +static int qcom_snps_hsphy_exit(struct phy *phy) +{ + struct hsphy_priv *priv = phy_get_drvdata(phy); + + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); return 0; } static const struct phy_ops qcom_snps_hsphy_ops = { .init = qcom_snps_hsphy_init, + .exit = qcom_snps_hsphy_exit, .power_on = qcom_snps_hsphy_power_on, .power_off = qcom_snps_hsphy_power_off, .set_mode = qcom_snps_hsphy_set_mode, diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c index b7f2c00db5e1..9c4af76a9956 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub.c +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -52,28 +52,15 @@ static int cros_ec_sensorhub_register(struct device *dev, int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; struct cros_ec_command *msg = sensorhub->msg; struct cros_ec_dev *ec = sensorhub->ec; - int ret, i, sensor_num; + int ret, i; char *name; - sensor_num = cros_ec_get_sensor_count(ec); - if (sensor_num < 0) { - dev_err(dev, - "Unable to retrieve sensor information (err:%d)\n", - sensor_num); - return sensor_num; - } - - sensorhub->sensor_num = sensor_num; - if (sensor_num == 0) { - dev_err(dev, "Zero sensors reported.\n"); - return -EINVAL; - } msg->version = 1; msg->insize = sizeof(struct ec_response_motion_sense); msg->outsize = sizeof(struct ec_params_motion_sense); - for (i = 0; i < sensor_num; i++) { + for (i = 0; i < sensorhub->sensor_num; i++) { sensorhub->params->cmd = MOTIONSENSE_CMD_INFO; sensorhub->params->info.sensor_num = i; @@ -140,8 +127,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct cros_ec_sensorhub *data; struct cros_ec_command *msg; - int ret; - int i; + int ret, i, sensor_num; msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) + max((u16)sizeof(struct ec_params_motion_sense), @@ -166,10 +152,52 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) dev_set_drvdata(dev, data); /* Check whether this EC is a sensor hub. */ - if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) { + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) { + sensor_num = cros_ec_get_sensor_count(ec); + if (sensor_num < 0) { + dev_err(dev, + "Unable to retrieve sensor information (err:%d)\n", + sensor_num); + return sensor_num; + } + if (sensor_num == 0) { + dev_err(dev, "Zero sensors reported.\n"); + return -EINVAL; + } + data->sensor_num = sensor_num; + + /* + * Prepare the ring handler before enumering the + * sensors. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_allocate(data); + if (ret) + return ret; + } + + /* Enumerate the sensors.*/ ret = cros_ec_sensorhub_register(dev, data); if (ret) return ret; + + /* + * When the EC does not have a FIFO, the sensors will query + * their data themselves via sysfs or a software trigger. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_add(data); + if (ret) + return ret; + /* + * The msg and its data is not under the control of the + * ring handler. + */ + return devm_add_action_or_reset(dev, + cros_ec_sensorhub_ring_remove, + data); + } + } else { /* * If the device has sensors but does not claim to @@ -184,22 +212,6 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) } } - /* - * If the EC does not have a FIFO, the sensors will query their data - * themselves via sysfs or a software trigger. - */ - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { - ret = cros_ec_sensorhub_ring_add(data); - if (ret) - return ret; - /* - * The msg and its data is not under the control of the ring - * handler. - */ - return devm_add_action_or_reset(dev, - cros_ec_sensorhub_ring_remove, - data); - } return 0; } diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index c48e5b38a441..24e48d96ed76 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -956,6 +956,53 @@ static int cros_ec_sensorhub_event(struct notifier_block *nb, return NOTIFY_OK; } +/** + * cros_ec_sensorhub_ring_allocate() - Prepare the FIFO functionality if the EC + * supports it. + * + * @sensorhub : Sensor Hub object. + * + * Return: 0 on success. + */ +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub) +{ + int fifo_info_length = + sizeof(struct ec_response_motion_sense_fifo_info) + + sizeof(u16) * sensorhub->sensor_num; + + /* Allocate the array for lost events. */ + sensorhub->fifo_info = devm_kzalloc(sensorhub->dev, fifo_info_length, + GFP_KERNEL); + if (!sensorhub->fifo_info) + return -ENOMEM; + + /* + * Allocate the callback area based on the number of sensors. + * Add one for the sensor ring. + */ + sensorhub->push_data = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->push_data), + GFP_KERNEL); + if (!sensorhub->push_data) + return -ENOMEM; + + sensorhub->tight_timestamps = cros_ec_check_features( + sensorhub->ec, + EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); + + if (sensorhub->tight_timestamps) { + sensorhub->batch_state = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->batch_state), + GFP_KERNEL); + if (!sensorhub->batch_state) + return -ENOMEM; + } + + return 0; +} + /** * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC * supports it. @@ -972,12 +1019,6 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) sizeof(struct ec_response_motion_sense_fifo_info) + sizeof(u16) * sensorhub->sensor_num; - /* Allocate the array for lost events. */ - sensorhub->fifo_info = devm_kzalloc(sensorhub->dev, fifo_info_length, - GFP_KERNEL); - if (!sensorhub->fifo_info) - return -ENOMEM; - /* Retrieve FIFO information */ sensorhub->msg->version = 2; sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO; @@ -998,31 +1039,9 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) if (!sensorhub->ring) return -ENOMEM; - /* - * Allocate the callback area based on the number of sensors. - */ - sensorhub->push_data = devm_kcalloc( - sensorhub->dev, sensorhub->sensor_num, - sizeof(*sensorhub->push_data), - GFP_KERNEL); - if (!sensorhub->push_data) - return -ENOMEM; - sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] = cros_ec_get_time_ns(); - sensorhub->tight_timestamps = cros_ec_check_features( - ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); - - if (sensorhub->tight_timestamps) { - sensorhub->batch_state = devm_kcalloc(sensorhub->dev, - sensorhub->sensor_num, - sizeof(*sensorhub->batch_state), - GFP_KERNEL); - if (!sensorhub->batch_state) - return -ENOMEM; - } - /* Register the notifier that will act as a top half interrupt. */ sensorhub->notifier.notifier_call = cros_ec_sensorhub_event; ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 6f12747a359a..c4404d9c1de4 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -515,9 +515,33 @@ static struct asus_wmi_driver asus_nb_wmi_driver = { .detect_quirks = asus_nb_wmi_quirks, }; +static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = { + { + /* + * asus-nb-wm adds no functionality. The T100TA has a detachable + * USB kbd, so no hotkeys and it has no WMI rfkill; and loading + * asus-nb-wm causes the camera LED to turn and _stay_ on. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + }, + }, + { + /* The Asus T200TA has the same issue as the T100TA */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + }, + {} /* Terminating entry */ +}; static int __init asus_nb_wmi_init(void) { + if (dmi_check_system(asus_nb_wmi_blacklist)) + return -ENODEV; + return asus_wmi_register_driver(&asus_nb_wmi_driver); } diff --git a/drivers/platform/x86/intel-uncore-frequency.c b/drivers/platform/x86/intel-uncore-frequency.c index b96d172eb2c1..12d5ab7e1f5d 100644 --- a/drivers/platform/x86/intel-uncore-frequency.c +++ b/drivers/platform/x86/intel-uncore-frequency.c @@ -53,7 +53,7 @@ static int uncore_max_entries __read_mostly; /* Storage for uncore data for all instances */ static struct uncore_data *uncore_instances; /* Root of the all uncore sysfs kobjs */ -struct kobject *uncore_root_kobj; +static struct kobject *uncore_root_kobj; /* Stores the CPU mask of the target CPUs to use during uncore read/write */ static cpumask_t uncore_cpu_mask; /* CPU online callback register instance */ diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index d2a5d4c36715..7c8bdab078cf 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -255,7 +255,7 @@ static const struct pmc_bit_map *ext_cnp_pfear_map[] = { }; static const struct pmc_bit_map icl_pfear_map[] = { - /* Ice Lake generation onwards only */ + /* Ice Lake and Jasper Lake generation onwards only */ {"RES_65", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -274,7 +274,7 @@ static const struct pmc_bit_map *ext_icl_pfear_map[] = { }; static const struct pmc_bit_map tgl_pfear_map[] = { - /* Tiger Lake, Elkhart Lake and Jasper Lake generation onwards only */ + /* Tiger Lake and Elkhart Lake generation onwards only */ {"PSF9", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -692,7 +692,6 @@ static void pmc_core_lpm_display(struct pmc_dev *pmcdev, struct device *dev, kfree(lpm_regs); } -#if IS_ENABLED(CONFIG_DEBUG_FS) static bool slps0_dbg_latch; static inline u8 pmc_core_reg_read_byte(struct pmc_dev *pmcdev, int offset) @@ -1133,15 +1132,6 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) &pmc_core_substate_l_sts_regs_fops); } } -#else -static inline void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) -{ -} - -static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) -{ -} -#endif /* CONFIG_DEBUG_FS */ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &spt_reg_map), @@ -1156,7 +1146,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &tgl_reg_map), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &tgl_reg_map), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &icl_reg_map), {} }; @@ -1260,13 +1250,11 @@ static int pmc_core_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP - static bool warn_on_s0ix_failures; module_param(warn_on_s0ix_failures, bool, 0644); MODULE_PARM_DESC(warn_on_s0ix_failures, "Check and warn for S0ix failures"); -static int pmc_core_suspend(struct device *dev) +static __maybe_unused int pmc_core_suspend(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); @@ -1318,7 +1306,7 @@ static inline bool pmc_core_is_s0ix_failed(struct pmc_dev *pmcdev) return false; } -static int pmc_core_resume(struct device *dev) +static __maybe_unused int pmc_core_resume(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); const struct pmc_bit_map **maps = pmcdev->map->lpm_sts; @@ -1348,8 +1336,6 @@ static int pmc_core_resume(struct device *dev) return 0; } -#endif - static const struct dev_pm_ops pmc_core_pm_ops = { SET_LATE_SYSTEM_SLEEP_PM_OPS(pmc_core_suspend, pmc_core_resume) }; diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h index 0d50b2402abe..5eae55d80226 100644 --- a/drivers/platform/x86/intel_pmc_core.h +++ b/drivers/platform/x86/intel_pmc_core.h @@ -282,9 +282,7 @@ struct pmc_dev { u32 base_addr; void __iomem *regbase; const struct pmc_reg_map *map; -#if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; -#endif /* CONFIG_DEBUG_FS */ int pmc_xram_read_bit; struct mutex lock; /* generic mutex lock for PMC Core */ diff --git a/drivers/platform/x86/surface3_power.c b/drivers/platform/x86/surface3_power.c index 946ac2dc08ae..cc4f9cba6856 100644 --- a/drivers/platform/x86/surface3_power.c +++ b/drivers/platform/x86/surface3_power.c @@ -522,8 +522,8 @@ static int mshw0011_probe(struct i2c_client *client) strlcpy(board_info.type, "MSHW0011-bat0", I2C_NAME_SIZE); bat0 = i2c_acpi_new_device(dev, 1, &board_info); - if (!bat0) - return -ENOMEM; + if (IS_ERR(bat0)) + return PTR_ERR(bat0); data->bat0 = bat0; i2c_set_clientdata(bat0, data); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 8eaadbaf8ffa..0f704484ae1d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9548,7 +9548,7 @@ static ssize_t tpacpi_battery_store(int what, if (!battery_info.batteries[battery].start_support) return -ENODEV; /* valid values are [0, 99] */ - if (value < 0 || value > 99) + if (value > 99) return -EINVAL; if (value > battery_info.batteries[battery].charge_stop) return -EINVAL; diff --git a/drivers/platform/x86/xiaomi-wmi.c b/drivers/platform/x86/xiaomi-wmi.c index 601cbb282f54..54a2546bb93b 100644 --- a/drivers/platform/x86/xiaomi-wmi.c +++ b/drivers/platform/x86/xiaomi-wmi.c @@ -23,7 +23,7 @@ struct xiaomi_wmi { unsigned int key_code; }; -int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) +static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) { struct xiaomi_wmi *data; @@ -48,7 +48,7 @@ int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) return input_register_device(data->input_dev); } -void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) +static void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) { struct xiaomi_wmi *data; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c340505150b6..7486f6e4e613 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5754,10 +5754,6 @@ static DECLARE_DELAYED_WORK(regulator_init_complete_work, static int __init regulator_init_complete(void) { - int delay = driver_deferred_probe_timeout; - - if (delay < 0) - delay = 0; /* * Since DT doesn't provide an idiomatic mechanism for * enabling full constraints and since it's much more natural @@ -5768,17 +5764,18 @@ static int __init regulator_init_complete(void) has_full_constraints = true; /* - * If driver_deferred_probe_timeout is set, we punt - * completion for that many seconds since systems like - * distros will load many drivers from userspace so consumers - * might not always be ready yet, this is particularly an - * issue with laptops where this might bounce the display off - * then on. Ideally we'd get a notification from userspace - * when this happens but we don't so just wait a bit and hope - * we waited long enough. It'd be better if we'd only do - * this on systems that need it. + * We punt completion for an arbitrary amount of time since + * systems like distros will load many drivers from userspace + * so consumers might not always be ready yet, this is + * particularly an issue with laptops where this might bounce + * the display off then on. Ideally we'd get a notification + * from userspace when this happens but we don't so just wait + * a bit and hope we waited long enough. It'd be better if + * we'd only do this on systems that need it, and a kernel + * command line option might be useful. */ - schedule_delayed_work(®ulator_init_complete_work, delay * HZ); + schedule_delayed_work(®ulator_init_complete_work, + msecs_to_jiffies(30000)); return 0; } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f7689461c242..569966bdc513 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -6717,17 +6717,17 @@ int qeth_stop(struct net_device *dev) unsigned int i; /* Quiesce the NAPI instances: */ - qeth_for_each_output_queue(card, queue, i) { + qeth_for_each_output_queue(card, queue, i) napi_disable(&queue->napi); - del_timer_sync(&queue->timer); - } /* Stop .ndo_start_xmit, might still access queue->napi. */ netif_tx_disable(dev); - /* Queues may get re-allocated, so remove the NAPIs here. */ - qeth_for_each_output_queue(card, queue, i) + qeth_for_each_output_queue(card, queue, i) { + del_timer_sync(&queue->timer); + /* Queues may get re-allocated, so remove the NAPIs. */ netif_napi_del(&queue->napi); + } } else { netif_tx_disable(dev); } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 7da9e060b270..635f6f9cffc4 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt) struct ibmvfc_host *vhost = tgt->vhost; struct ibmvfc_event *evt; + if (!vhost->logged_in) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); + return; + } + if (vhost->discovery_threads >= disc_threads) return; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 7f66a7783209..59f0f1030c54 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2320,16 +2320,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - unsigned long flags; srp_remove_host(hostdata->host); scsi_remove_host(hostdata->host); purge_requests(hostdata, DID_ERROR); - - spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); - spin_unlock_irqrestore(hostdata->host->host_lock, flags); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 97cabd7e0014..33255968f03a 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3031,11 +3031,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); - qla_nvme_delete(vha); qla24xx_disable_vp(vha); qla2x00_wait_for_sess_deletion(vha); + qla_nvme_delete(vha); vha->flags.delete_progress = 1; qlt_remove_target(ha, vha); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4ed90437e8c4..d6c991bd1bde 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3153,7 +3153,7 @@ qla24xx_abort_command(srb_t *sp) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c, "Entered %s.\n", __func__); - if (vha->flags.qpairs_available && sp->qpair) + if (sp->qpair) req = sp->qpair->req; else return QLA_FUNCTION_FAILED; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index d190db5ea7d9..1d9a4866f9a7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -3732,6 +3732,13 @@ qla2x00_remove_one(struct pci_dev *pdev) } qla2x00_wait_for_hba_ready(base_vha); + /* + * if UNLOADING flag is already set, then continue unload, + * where it was set first. + */ + if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags)) + return; + if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) { if (ha->flags.fw_started) @@ -3750,15 +3757,6 @@ qla2x00_remove_one(struct pci_dev *pdev) qla2x00_wait_for_sess_deletion(base_vha); - /* - * if UNLOAD flag is already set, then continue unload, - * where it was set first. - */ - if (test_bit(UNLOADING, &base_vha->dpc_flags)) - return; - - set_bit(UNLOADING, &base_vha->dpc_flags); - qla_nvme_delete(base_vha); dma_free_coherent(&ha->pdev->dev, @@ -4864,6 +4862,9 @@ qla2x00_alloc_work(struct scsi_qla_host *vha, enum qla_work_type type) struct qla_work_evt *e; uint8_t bail; + if (test_bit(UNLOADING, &vha->dpc_flags)) + return NULL; + QLA_VHA_MARK_BUSY(vha, bail); if (bail) return NULL; @@ -6628,13 +6629,6 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work) struct pci_dev *pdev = ha->pdev; scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev); - /* - * if UNLOAD flag is already set, then continue unload, - * where it was set first. - */ - if (test_bit(UNLOADING, &base_vha->dpc_flags)) - return; - ql_log(ql_log_warn, base_vha, 0x015b, "Disabling adapter.\n"); @@ -6645,9 +6639,14 @@ qla2x00_disable_board_on_pci_error(struct work_struct *work) return; } - qla2x00_wait_for_sess_deletion(base_vha); + /* + * if UNLOADING flag is already set, then continue unload, + * where it was set first. + */ + if (test_and_set_bit(UNLOADING, &base_vha->dpc_flags)) + return; - set_bit(UNLOADING, &base_vha->dpc_flags); + qla2x00_wait_for_sess_deletion(base_vha); qla2x00_delete_all_vps(ha, base_vha); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 47835c4b4ee0..06c260f6cdae 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2284,6 +2284,7 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state) switch (oldstate) { case SDEV_RUNNING: case SDEV_CREATED_BLOCK: + case SDEV_QUIESCE: case SDEV_OFFLINE: break; default: diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 8e0575fcb4c8..67325fbaf760 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -925,6 +925,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma, gasket_get_bar_index(gasket_dev, (vma->vm_pgoff << PAGE_SHIFT) + driver_desc->legacy_mmap_address_offset); + + if (bar_index < 0) + return DO_MAP_REGION_INVALID; + phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset; while (mapped_bytes < map_length) { /* diff --git a/drivers/staging/ks7010/TODO b/drivers/staging/ks7010/TODO index 87a6dac4890d..ab6f39175d99 100644 --- a/drivers/staging/ks7010/TODO +++ b/drivers/staging/ks7010/TODO @@ -30,5 +30,4 @@ Now the TODOs: Please send any patches to: Greg Kroah-Hartman -Wolfram Sang Linux Driver Project Developer List diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 51ffd5c002de..1c181d31f4c8 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -432,7 +432,7 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd) target_to_linux_sector(dev, cmd->t_task_lba), target_to_linux_sector(dev, sbc_get_write_same_sectors(cmd)), - GFP_KERNEL, false); + GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); if (ret) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 3d084cec136f..50c7534ba31e 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -182,6 +182,9 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status) return ret; ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_26, 1); + if (ret) + return ret; + if (val & ROUTER_CS_26_ONS) return -EOPNOTSUPP; diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig index 31b7e1b03749..d1b27b0522a3 100644 --- a/drivers/tty/hvc/Kconfig +++ b/drivers/tty/hvc/Kconfig @@ -88,7 +88,7 @@ config HVC_DCC config HVC_RISCV_SBI bool "RISC-V SBI console support" - depends on RISCV_SBI + depends on RISCV_SBI_V01 select HVC_DRIVER help This enables support for console output via RISC-V SBI calls, which diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 4b0a7b98f8c7..a3cd1cc64c1e 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -86,7 +86,7 @@ config SERIAL_EARLYCON_ARM_SEMIHOST config SERIAL_EARLYCON_RISCV_SBI bool "Early console using RISC-V SBI" - depends on RISCV_SBI + depends on RISCV_SBI_V01 select SERIAL_CORE select SERIAL_CORE_CONSOLE select SERIAL_EARLYCON diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index ed0aa5c0d9b7..5674da2b76f0 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -843,10 +843,8 @@ static int bcm_uart_probe(struct platform_device *pdev) if (IS_ERR(clk) && pdev->dev.of_node) clk = of_clk_get(pdev->dev.of_node, 0); - if (IS_ERR(clk)) { - clk_put(clk); + if (IS_ERR(clk)) return -ENODEV; - } port->iotype = UPIO_MEM; port->irq = res_irq->start; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index 672cfa075e28..b9d672af8b65 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1465,6 +1465,7 @@ static int cdns_uart_probe(struct platform_device *pdev) cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS; #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE cdns_uart_uart_driver.cons = &cdns_uart_console; + cdns_uart_console.index = id; #endif rc = uart_register_driver(&cdns_uart_uart_driver); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e5ffed795e4c..48a8199f7845 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -365,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) return uniscr; } +static void vc_uniscr_free(struct uni_screen *uniscr) +{ + vfree(uniscr); +} + static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) { - vfree(vc->vc_uni_screen); + vc_uniscr_free(vc->vc_uni_screen); vc->vc_uni_screen = new_uniscr; } @@ -1230,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, err = resize_screen(vc, new_cols, new_rows, user); if (err) { kfree(newscreen); - kfree(new_uniscr); + vc_uniscr_free(new_uniscr); return err; } diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6833c918abce..b9db9812d6c5 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -217,6 +217,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) { struct usb_memory *usbm = NULL; struct usb_dev_state *ps = file->private_data; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; @@ -250,9 +251,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (remap_pfn_range(vma, vma->vm_start, - virt_to_phys(usbm->mem) >> PAGE_SHIFT, - size, vma->vm_page_prot) < 0) { + if (dma_mmap_coherent(hcd->self.sysdev, vma, mem, dma_handle, size)) { dec_usb_memory_use_count(usbm, &usbm->vma_use_count); return -EAGAIN; } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index a48678a0c83a..6197938dcc2d 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1144,11 +1144,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, if (usb_endpoint_out(epaddr)) { ep = dev->ep_out[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_out[epnum] = NULL; } else { ep = dev->ep_in[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_in[epnum] = NULL; } if (ep) { diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c index ffd984142171..d63072fee099 100644 --- a/drivers/usb/serial/garmin_gps.c +++ b/drivers/usb/serial/garmin_gps.c @@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p, send it directly to the tty port */ if (garmin_data_p->flags & FLAGS_QUEUING) { pkt_add(garmin_data_p, data, data_length); - } else if (bulk_data || - getLayerId(data) == GARMIN_LAYERID_APPL) { + } else if (bulk_data || (data_length >= sizeof(u32) && + getLayerId(data) == GARMIN_LAYERID_APPL)) { spin_lock_irqsave(&garmin_data_p->lock, flags); garmin_data_p->flags |= APP_RESP_SEEN; diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 613f91add03d..ce0401d3137f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1b23741036ee..37157ed9a881 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list */ +/* Reported-by: Julian Groß */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index f5c5e0aef66f..67c5139cfa0d 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -157,6 +157,10 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) req.mode_data |= (state->mode - TYPEC_STATE_MODAL) << PMC_USB_ALTMODE_DP_MODE_SHIFT; + if (data->status & DP_STATUS_HPD_STATE) + req.mode_data |= PMC_USB_DP_HPD_LVL << + PMC_USB_ALTMODE_DP_MODE_SHIFT; + return pmc_usb_command(port, (void *)&req, sizeof(req)); } @@ -298,11 +302,11 @@ static int pmc_usb_register_port(struct pmc_usb *pmc, int index, struct typec_mux_desc mux_desc = { }; int ret; - ret = fwnode_property_read_u8(fwnode, "usb2-port", &port->usb2_port); + ret = fwnode_property_read_u8(fwnode, "usb2-port-number", &port->usb2_port); if (ret) return ret; - ret = fwnode_property_read_u8(fwnode, "usb3-port", &port->usb3_port); + ret = fwnode_property_read_u8(fwnode, "usb3-port-number", &port->usb3_port); if (ret) return ret; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 85b32c325282..cc1d64765ce7 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -342,8 +342,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, vma = find_vma_intersection(mm, vaddr, vaddr + 1); if (vma && vma->vm_flags & VM_PFNMAP) { - *pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - if (is_invalid_reserved_pfn(*pfn)) + if (!follow_pfn(vma, vaddr, pfn) && + is_invalid_reserved_pfn(*pfn)) ret = 0; } done: @@ -555,7 +555,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, continue; } - remote_vaddr = dma->vaddr + iova - dma->iova; + remote_vaddr = dma->vaddr + (iova - dma->iova); ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i], do_accounting); if (ret) @@ -2345,10 +2345,10 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, vaddr = dma->vaddr + offset; if (write) - *copied = __copy_to_user((void __user *)vaddr, data, + *copied = copy_to_user((void __user *)vaddr, data, count) ? 0 : count; else - *copied = __copy_from_user(data, (void __user *)vaddr, + *copied = copy_from_user(data, (void __user *)vaddr, count) ? 0 : count; if (kthread) unuse_mm(mm); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e36aaf9ba7bd..fb4e944c4d0d 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -181,14 +181,14 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); - added = true; - - /* Deliver to monitoring devices all correctly transmitted - * packets. + /* Deliver to monitoring devices all packets that we + * will transmit. */ virtio_transport_deliver_tap_pkt(pkt); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); + added = true; + pkt->off += payload_len; total_len += payload_len; @@ -196,6 +196,12 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * to send it with the next available buffer. */ if (pkt->off < pkt->len) { + /* We are queueing the same virtio_vsock_pkt to handle + * the remaining bytes, and we want to deliver it + * to monitoring devices in the next iteration. + */ + pkt->tap_delivered = false; + spin_lock_bh(&vsock->send_pkt_list_lock); list_add(&pkt->list, &vsock->send_pkt_list); spin_unlock_bh(&vsock->send_pkt_list_lock); @@ -543,6 +549,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) mutex_unlock(&vq->mutex); } + /* Some packets may have been queued before the device was started, + * let's kick the send worker to send them. + */ + vhost_work_queue(&vsock->dev, &vsock->send_pkt_work); + mutex_unlock(&vsock->dev.mutex); return 0; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 9c380e7edf62..0cc02577577b 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -391,7 +391,7 @@ static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr) struct rb_node **p = &preftrees->direct.root.rb_root.rb_node; struct rb_node *parent = NULL; struct prelim_ref *ref = NULL; - struct prelim_ref target = {0}; + struct prelim_ref target = {}; int result; target.parent = bytenr; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 47f66c6a7d7f..696f47103cfc 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out; + goto out_put_group; } /* @@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); - goto out; + goto out_put_group; } clear_nlink(inode); /* One for the block groups ref */ @@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) - goto out; + goto out_put_group; if (ret > 0) btrfs_release_path(path); if (ret == 0) { ret = btrfs_del_item(trans, tree_root, path); if (ret) - goto out; + goto out_put_group; btrfs_release_path(path); } @@ -1102,9 +1102,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = remove_block_group_free_space(trans, block_group); if (ret) - goto out; + goto out_put_group; - btrfs_put_block_group(block_group); + /* Once for the block groups rbtree */ btrfs_put_block_group(block_group); ret = btrfs_search_slot(trans, root, &key, path, -1, 1); @@ -1127,6 +1127,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, /* once for the tree */ free_extent_map(em); } + +out_put_group: + /* Once for the lookup reference */ + btrfs_put_block_group(block_group); out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); @@ -1288,11 +1292,15 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans, if (ret) goto err; mutex_unlock(&fs_info->unused_bg_unpin_mutex); + if (prev_trans) + btrfs_put_transaction(prev_trans); return true; err: mutex_unlock(&fs_info->unused_bg_unpin_mutex); + if (prev_trans) + btrfs_put_transaction(prev_trans); btrfs_dec_block_group_ro(bg); return false; } diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h index 21a15776dac4..353228d62f5a 100644 --- a/fs/btrfs/discard.h +++ b/fs/btrfs/discard.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_DISCARD_H #define BTRFS_DISCARD_H diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a6cb5cbbdb9f..d10c7be10f3b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2036,9 +2036,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info) for (i = 0; i < ret; i++) btrfs_drop_and_free_fs_root(fs_info, gang[i]); } - - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - btrfs_free_log_root_tree(NULL, fs_info); } static void btrfs_init_scrub(struct btrfs_fs_info *fs_info) @@ -3888,7 +3885,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, spin_unlock(&fs_info->fs_roots_radix_lock); if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { - btrfs_free_log(NULL, root); + ASSERT(root->log_root == NULL); if (root->reloc_root) { btrfs_put_root(root->reloc_root); root->reloc_root = NULL; @@ -4211,6 +4208,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) up_write(&fs_info->cleanup_work_sem); } +static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + u64 root_objectid = 0; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix, + (void **)gang, root_objectid, + ARRAY_SIZE(gang))) != 0) { + int i; + + for (i = 0; i < ret; i++) + gang[i] = btrfs_grab_root(gang[i]); + spin_unlock(&fs_info->fs_roots_radix_lock); + + for (i = 0; i < ret; i++) { + if (!gang[i]) + continue; + root_objectid = gang[i]->root_key.objectid; + btrfs_free_log(NULL, gang[i]); + btrfs_put_root(gang[i]); + } + root_objectid++; + spin_lock(&fs_info->fs_roots_radix_lock); + } + spin_unlock(&fs_info->fs_roots_radix_lock); + btrfs_free_log_root_tree(NULL, fs_info); +} + static void btrfs_destroy_ordered_extents(struct btrfs_root *root) { struct btrfs_ordered_extent *ordered; @@ -4603,6 +4630,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) btrfs_destroy_delayed_inodes(fs_info); btrfs_assert_delayed_root_empty(fs_info); btrfs_destroy_all_delalloc_inodes(fs_info); + btrfs_drop_all_logs(fs_info); mutex_unlock(&fs_info->transaction_kthread_mutex); return 0; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d35936c934ab..03bc7134e8cb 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4559,6 +4559,7 @@ int btrfs_recover_relocation(struct btrfs_root *root) if (IS_ERR(fs_root)) { err = PTR_ERR(fs_root); list_add_tail(&reloc_root->root_list, &reloc_roots); + btrfs_end_transaction(trans); goto out_unset; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8cede6eb9843..2d5498136e5e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -662,10 +662,19 @@ again: } got_it: - btrfs_record_root_in_trans(h, root); - if (!current->journal_info) current->journal_info = h; + + /* + * btrfs_record_root_in_trans() needs to alloc new extents, and may + * call btrfs_join_transaction() while we're also starting a + * transaction. + * + * Thus it need to be called after current->journal_info initialized, + * or we can deadlock. + */ + btrfs_record_root_in_trans(h, root); + return h; join_fail: diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ec36a7c6ba3d..02ebdd9edc19 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4226,6 +4226,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, const u64 ino = btrfs_ino(inode); struct btrfs_path *dst_path = NULL; bool dropped_extents = false; + u64 truncate_offset = i_size; + struct extent_buffer *leaf; + int slot; int ins_nr = 0; int start_slot; int ret; @@ -4240,9 +4243,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, if (ret < 0) goto out; + /* + * We must check if there is a prealloc extent that starts before the + * i_size and crosses the i_size boundary. This is to ensure later we + * truncate down to the end of that extent and not to the i_size, as + * otherwise we end up losing part of the prealloc extent after a log + * replay and with an implicit hole if there is another prealloc extent + * that starts at an offset beyond i_size. + */ + ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); + if (ret < 0) + goto out; + + if (ret == 0) { + struct btrfs_file_extent_item *ei; + + leaf = path->nodes[0]; + slot = path->slots[0]; + ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == + BTRFS_FILE_EXTENT_PREALLOC) { + u64 extent_end; + + btrfs_item_key_to_cpu(leaf, &key, slot); + extent_end = key.offset + + btrfs_file_extent_num_bytes(leaf, ei); + + if (extent_end > i_size) + truncate_offset = extent_end; + } + } else { + ret = 0; + } + while (true) { - struct extent_buffer *leaf = path->nodes[0]; - int slot = path->slots[0]; + leaf = path->nodes[0]; + slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { if (ins_nr > 0) { @@ -4280,7 +4317,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, ret = btrfs_truncate_inode_items(trans, root->log_root, &inode->vfs_inode, - i_size, + truncate_offset, BTRFS_EXTENT_DATA_KEY); } while (ret == -EAGAIN); if (ret) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 185db76300b3..5f3aa4d607de 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN) + if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) ret = 0; return ret; } @@ -3746,6 +3746,7 @@ retry: WARN_ON(1); tsession = NULL; target = -1; + mutex_lock(&session->s_mutex); } goto retry; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 481ac97b4d25..dcaed75de9e6 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) &congestion_kb_fops); snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->sb->s_bdi->dev)); + bdi_dev_name(fsc->sb->s_bdi)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 486f91f9685b..7c63abf5bea9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session, void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; u32 op; - u64 seq; - unsigned long features = 0; + u64 seq, features = 0; int wake = 0; bool blacklisted = false; @@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - memcpy(&features, p, min_t(size_t, len, sizeof(features))); - p += len; + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); } mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index de56dee60540..19507e2fdb57 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, } if (IS_ERR(in)) { - pr_warn("Can't lookup inode %llx (err: %ld)\n", - realm->ino, PTR_ERR(in)); + dout("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ } else { qri->timeout = 0; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cf7b7e1d5bd7..cb733652ecca 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) spin_lock(&configfs_dirent_lock); configfs_detach_rollback(dentry); spin_unlock(&configfs_dirent_lock); + config_item_put(parent_item); return -EINTR; } frag->frag_dead = true; diff --git a/fs/coredump.c b/fs/coredump.c index 408418e6aa13..478a0d810136 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (displaced) put_files_struct(displaced); if (!dump_interrupted()) { + /* + * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would + * have this set to NULL. + */ + if (!cprm.file) { + pr_info("Core dump to |%s disabled\n", cn.corename); + goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8c596641a72b..aba03ee749f8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; @@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (epi->next == EP_UNACTIVE_PTR && - chain_epi_lockless(epi)) + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); - goto out_unlock; - } - - /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(epi) && - list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) { - ep_pm_stay_awake_rcu(epi); } /* @@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1867,21 +1866,23 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); - + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); - } - for (;;) { /* * We don't want to sleep if the ep_poll_callback() sends us * a wakeup in between. That's why we set the task state @@ -1911,10 +1912,20 @@ fetch_events: timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: /* * Try to transfer events to user space. In case we get 0 events and @@ -1925,12 +1936,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } diff --git a/fs/io_uring.c b/fs/io_uring.c index c687f57fb651..979d9f977409 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -524,6 +524,7 @@ enum { REQ_F_OVERFLOW_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, + REQ_F_NO_FILE_TABLE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -577,6 +578,8 @@ enum { REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT), + /* doesn't need file table for this request */ + REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT), }; struct async_poll { @@ -677,8 +680,6 @@ struct io_op_def { unsigned needs_mm : 1; /* needs req->file assigned */ unsigned needs_file : 1; - /* needs req->file assigned IFF fd is >= 0 */ - unsigned fd_non_neg : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -781,8 +782,6 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, }, [IORING_OP_OPENAT] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -796,9 +795,8 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_STATX] = { .needs_mm = 1, - .needs_file = 1, - .fd_non_neg = 1, .needs_fs = 1, + .file_table = 1, }, [IORING_OP_READ] = { .needs_mm = 1, @@ -833,8 +831,6 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, }, [IORING_OP_OPENAT2] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -1291,7 +1287,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx) struct io_kiocb *req; req = ctx->fallback_req; - if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req)) + if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req)) return req; return NULL; @@ -1378,7 +1374,7 @@ static void __io_free_req(struct io_kiocb *req) if (likely(!io_is_fallback_req(req))) kmem_cache_free(req_cachep, req); else - clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req); + clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req); } struct req_batch { @@ -2034,7 +2030,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd) * any file. For now, just ensure that anything potentially problematic is done * inline. */ -static bool io_file_supports_async(struct file *file) +static bool io_file_supports_async(struct file *file, int rw) { umode_t mode = file_inode(file)->i_mode; @@ -2043,7 +2039,13 @@ static bool io_file_supports_async(struct file *file) if (S_ISREG(mode) && file->f_op != &io_uring_fops) return true; - return false; + if (!(file->f_mode & FMODE_NOWAIT)) + return false; + + if (rw == READ) + return file->f_op->read_iter != NULL; + + return file->f_op->write_iter != NULL; } static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, @@ -2571,7 +2573,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock) * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so * we know to async punt it even if it was opened O_NONBLOCK */ - if (force_nonblock && !io_file_supports_async(req->file)) + if (force_nonblock && !io_file_supports_async(req->file, READ)) goto copy_iov; iov_count = iov_iter_count(&iter); @@ -2594,7 +2596,8 @@ copy_iov: if (ret) goto out_free; /* any defer here is final, must blocking retry */ - if (!(req->flags & REQ_F_NOWAIT)) + if (!(req->flags & REQ_F_NOWAIT) && + !file_can_poll(req->file)) req->flags |= REQ_F_MUST_PUNT; return -EAGAIN; } @@ -2662,7 +2665,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock) * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so * we know to async punt it even if it was opened O_NONBLOCK */ - if (force_nonblock && !io_file_supports_async(req->file)) + if (force_nonblock && !io_file_supports_async(req->file, WRITE)) goto copy_iov; /* file path doesn't support NOWAIT for non-direct_IO */ @@ -2716,7 +2719,8 @@ copy_iov: if (ret) goto out_free; /* any defer here is final, must blocking retry */ - req->flags |= REQ_F_MUST_PUNT; + if (!file_can_poll(req->file)) + req->flags |= REQ_F_MUST_PUNT; return -EAGAIN; } } @@ -2756,15 +2760,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } -static bool io_splice_punt(struct file *file) -{ - if (get_pipe_info(file)) - return false; - if (!io_file_supports_async(file)) - return true; - return !(file->f_flags & O_NONBLOCK); -} - static int io_splice(struct io_kiocb *req, bool force_nonblock) { struct io_splice *sp = &req->splice; @@ -2774,11 +2769,8 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) loff_t *poff_in, *poff_out; long ret; - if (force_nonblock) { - if (io_splice_punt(in) || io_splice_punt(out)) - return -EAGAIN; - flags |= SPLICE_F_NONBLOCK; - } + if (force_nonblock) + return -EAGAIN; poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -3355,8 +3347,12 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock) struct kstat stat; int ret; - if (force_nonblock) + if (force_nonblock) { + /* only need file table for an actual valid fd */ + if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD) + req->flags |= REQ_F_NO_FILE_TABLE; return -EAGAIN; + } if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags)) return -EINVAL; @@ -3502,7 +3498,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr) if (io_req_cancelled(req)) return; __io_sync_file_range(req); - io_put_req(req); /* put submission ref */ + io_steal_work(req, workptr); } static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock) @@ -5015,7 +5011,7 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe) int ret; /* Still need defer if there is pending req in defer list. */ - if (!req_need_defer(req) && list_empty(&ctx->defer_list)) + if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list)) return 0; if (!req->io && io_alloc_async_ctx(req)) @@ -5364,15 +5360,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) io_steal_work(req, workptr); } -static int io_req_needs_file(struct io_kiocb *req, int fd) -{ - if (!io_op_defs[req->opcode].needs_file) - return 0; - if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg) - return 0; - return 1; -} - static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { @@ -5410,14 +5397,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd, unsigned int flags) + int fd) { bool fixed; - if (!io_req_needs_file(req, fd)) - return 0; - - fixed = (flags & IOSQE_FIXED_FILE); + fixed = (req->flags & REQ_F_FIXED_FILE) != 0; if (unlikely(!fixed && req->needs_fixed_file)) return -EBADF; @@ -5429,7 +5413,7 @@ static int io_grab_files(struct io_kiocb *req) int ret = -EBADF; struct io_ring_ctx *ctx = req->ctx; - if (req->work.files) + if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE)) return 0; if (!ctx->ring_file) return -EBADF; @@ -5794,7 +5778,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, struct io_submit_state *state, bool async) { unsigned int sqe_flags; - int id, fd; + int id; /* * All io need record the previous position, if LINK vs DARIN, @@ -5846,8 +5830,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, IOSQE_ASYNC | IOSQE_FIXED_FILE | IOSQE_BUFFER_SELECT | IOSQE_IO_LINK); - fd = READ_ONCE(sqe->fd); - return io_req_set_file(state, req, fd, sqe_flags); + if (!io_op_defs[req->opcode].needs_file) + return 0; + + return io_req_set_file(state, req, READ_ONCE(sqe->fd)); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, @@ -7327,7 +7313,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) * it could cause shutdown to hang. */ while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait)) - cpu_relax(); + cond_resched(); io_kill_timeouts(ctx); io_poll_remove_all(ctx); @@ -7356,11 +7342,9 @@ static int io_uring_release(struct inode *inode, struct file *file) static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { - struct io_kiocb *req; - DEFINE_WAIT(wait); - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_kiocb *cancel_req = NULL; + struct io_kiocb *cancel_req = NULL, *req; + DEFINE_WAIT(wait); spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { @@ -7400,6 +7384,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, */ if (refcount_sub_and_test(2, &cancel_req->refs)) { io_put_req(cancel_req); + finish_wait(&ctx->inflight_wait, &wait); continue; } } @@ -7407,8 +7392,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_wq_cancel_work(ctx->io_wq, &cancel_req->work); io_put_req(cancel_req); schedule(); + finish_wait(&ctx->inflight_wait, &wait); } - finish_wait(&ctx->inflight_wait, &wait); } static int io_uring_flush(struct file *file, void *data) @@ -7757,7 +7742,8 @@ err: return ret; } -static int io_uring_create(unsigned entries, struct io_uring_params *p) +static int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) { struct user_struct *user = NULL; struct io_ring_ctx *ctx; @@ -7849,6 +7835,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup @@ -7857,9 +7851,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: @@ -7875,7 +7866,6 @@ err: static long io_uring_setup(u32 entries, struct io_uring_params __user *params) { struct io_uring_params p; - long ret; int i; if (copy_from_user(&p, params, sizeof(p))) @@ -7890,14 +7880,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) return -EINVAL; - ret = io_uring_create(entries, &p); - if (ret < 0) - return ret; - - if (copy_to_user(params, &p, sizeof(p))) - return -EFAULT; - - return ret; + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, diff --git a/fs/ioctl.c b/fs/ioctl.c index 282d45be6f45..5e80b40bc1b5 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -55,6 +55,7 @@ EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); + struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; @@ -71,6 +72,13 @@ static int ioctl_fibmap(struct file *filp, int __user *p) block = ur_block; error = bmap(inode, &block); + if (block > INT_MAX) { + error = -ERANGE; + pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", + current->comm, task_pid_nr(current), + sb->s_id, filp); + } + if (error) ur_block = 0; else diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index bccf305ea9ce..d55e8f491a5e 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -117,10 +117,7 @@ iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length, if (iomap->type == IOMAP_MAPPED) { addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits; - if (addr > INT_MAX) - WARN(1, "would truncate bmap result\n"); - else - *bno = addr; + *bno = addr; } return 0; } diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index c5c3fc6e6c60..26c94b32d6f4 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type) { - struct posix_acl *alloc = NULL, *dfacl = NULL; + struct posix_acl *orig = acl, *dfacl = NULL, *alloc; int status; if (S_ISDIR(inode->i_mode)) { switch(type) { case ACL_TYPE_ACCESS: - alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT); + alloc = get_acl(inode, ACL_TYPE_DEFAULT); if (IS_ERR(alloc)) goto fail; + dfacl = alloc; break; case ACL_TYPE_DEFAULT: - dfacl = acl; - alloc = acl = get_acl(inode, ACL_TYPE_ACCESS); + alloc = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(alloc)) goto fail; + dfacl = acl; + acl = alloc; break; } } if (acl == NULL) { - alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); + alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); if (IS_ERR(alloc)) goto fail; + acl = alloc; } status = __nfs3_proc_setacls(inode, acl, dfacl); - posix_acl_release(alloc); +out: + if (acl != orig) + posix_acl_release(acl); + if (dfacl != orig) + posix_acl_release(dfacl); return status; fail: - return PTR_ERR(alloc); + status = PTR_ERR(alloc); + goto out; } const struct xattr_handler *nfs3_xattr_handlers[] = { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 512afb1c7867..a0c1e653a935 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7891,6 +7891,7 @@ static void nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) { struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp; + struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp; struct nfs_client *clp = args->client; switch (task->tk_status) { @@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); } + if (args->dir == NFS4_CDFC4_FORE_OR_BOTH && + res->dir != NFS4_CDFS4_BOTH) { + rpc_task_close_connection(task); + if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES) + rpc_restart_call(task); + } } static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = { @@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt, struct nfs41_bind_conn_to_session_args args = { .client = clp, .dir = NFS4_CDFC4_FORE_OR_BOTH, + .retries = 0, }; struct nfs41_bind_conn_to_session_res res; struct rpc_message msg = { @@ -9191,8 +9199,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - return ERR_CAST(task); + status = rpc_wait_for_completion_task(task); if (status != 0) goto out; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b8d78f393365..dd2e14f5875d 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1332,13 +1332,15 @@ _pnfs_return_layout(struct inode *ino) !valid_layout) { spin_unlock(&ino->i_lock); dprintk("NFS: %s no layout segments to return\n", __func__); - goto out_put_layout_hdr; + goto out_wait_layoutreturn; } send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL); spin_unlock(&ino->i_lock); if (send) status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true); +out_wait_layoutreturn: + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE); out_put_layout_hdr: pnfs_free_lseg_list(&tmp_list); pnfs_put_layout_hdr(lo); @@ -1456,18 +1458,15 @@ retry: /* lo ref dropped in pnfs_roc_release() */ layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode); /* If the creds don't match, we can't compound the layoutreturn */ - if (!layoutreturn) + if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0) goto out_noroc; - if (cred_fscmp(cred, lc_cred) != 0) - goto out_noroc_put_cred; roc = layoutreturn; pnfs_init_layoutreturn_args(args, lo, &stateid, iomode); res->lrs_present = 0; layoutreturn = false; - -out_noroc_put_cred: put_cred(lc_cred); + out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 59ef3b13ccca..bdb6d0c2e755 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -185,7 +185,7 @@ static int __nfs_list_for_each_server(struct list_head *head, rcu_read_lock(); list_for_each_entry_rcu(server, head, client_link) { - if (!nfs_sb_active(server->super)) + if (!(server->super && nfs_sb_active(server->super))) continue; rcu_read_unlock(); if (last) diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 8e4f1ace467c..1de77f1a600b 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -275,7 +275,6 @@ static ssize_t dlmfs_file_write(struct file *filp, loff_t *ppos) { int bytes_left; - ssize_t writelen; char *lvb_buf; struct inode *inode = file_inode(filp); @@ -285,32 +284,30 @@ static ssize_t dlmfs_file_write(struct file *filp, if (*ppos >= i_size_read(inode)) return -ENOSPC; + /* don't write past the lvb */ + if (count > i_size_read(inode) - *ppos) + count = i_size_read(inode) - *ppos; + if (!count) return 0; if (!access_ok(buf, count)) return -EFAULT; - /* don't write past the lvb */ - if ((count + *ppos) > i_size_read(inode)) - writelen = i_size_read(inode) - *ppos; - else - writelen = count - *ppos; - - lvb_buf = kmalloc(writelen, GFP_NOFS); + lvb_buf = kmalloc(count, GFP_NOFS); if (!lvb_buf) return -ENOMEM; - bytes_left = copy_from_user(lvb_buf, buf, writelen); - writelen -= bytes_left; - if (writelen) - user_dlm_write_lvb(inode, lvb_buf, writelen); + bytes_left = copy_from_user(lvb_buf, buf, count); + count -= bytes_left; + if (count) + user_dlm_write_lvb(inode, lvb_buf, count); kfree(lvb_buf); - *ppos = *ppos + writelen; - mlog(0, "wrote %zd bytes\n", writelen); - return writelen; + *ppos = *ppos + count; + mlog(0, "wrote %zu bytes\n", count); + return count; } static void dlmfs_init_once(void *foo) diff --git a/fs/pnode.c b/fs/pnode.c index 49f6d7ff2139..1106137c747a 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -261,14 +261,13 @@ static int propagate_one(struct mount *m) child = copy_tree(last_source, last_source->mnt.mnt_root, type); if (IS_ERR(child)) return PTR_ERR(child); + read_seqlock_excl(&mount_lock); mnt_set_mountpoint(m, mp, child); + if (m->mnt_master != dest_master) + SET_MNT_MARK(m->mnt_master); + read_sequnlock_excl(&mount_lock); last_dest = m; last_source = child; - if (m->mnt_master != dest_master) { - read_seqlock_excl(&mount_lock); - SET_MNT_MARK(m->mnt_master); - read_sequnlock_excl(&mount_lock); - } hlist_add_head(&child->mnt_hash, list); return count_mounts(m->mnt_ns, child); } diff --git a/fs/splice.c b/fs/splice.c index 4735defc46ee..fd0a1e7e5959 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in, loff_t offset; long ret; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + ipipe = get_pipe_info(in); opipe = get_pipe_info(out); @@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in, if (off_in || off_out) return -ESPIPE; - if (!(in->f_mode & FMODE_READ)) - return -EBADF; - - if (!(out->f_mode & FMODE_WRITE)) - return -EBADF; - /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; @@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in, offset = out->f_pos; } - if (unlikely(!(out->f_mode & FMODE_WRITE))) - return -EBADF; - if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; @@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, error = -EBADF; in = fdget(fd_in); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - out = fdget(fd_out); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_splice(in.file, off_in, - out.file, off_out, - len, flags); - fdput(out); - } + out = fdget(fd_out); + if (out.file) { + error = do_splice(in.file, off_in, out.file, off_out, + len, flags); + fdput(out); } fdput(in); } @@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len, struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + /* * Duplicate the contents of ipipe to opipe without actually * copying the data. @@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len, SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { - struct fd in; + struct fd in, out; int error; if (unlikely(flags & ~SPLICE_F_ALL)) @@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) error = -EBADF; in = fdget(fdin); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - struct fd out = fdget(fdout); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_tee(in.file, out.file, - len, flags); - fdput(out); - } + out = fdget(fdout); + if (out.file) { + error = do_tee(in.file, out.file, len, flags); + fdput(out); } fdput(in); } diff --git a/fs/super.c b/fs/super.c index cd352530eca9..a288cd60d2ae 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1302,8 +1302,8 @@ int get_tree_bdev(struct fs_context *fc, mutex_lock(&bdev->bd_fsfreeze_mutex); if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); - blkdev_put(bdev, mode); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); + blkdev_put(bdev, mode); return -EBUSY; } diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 675e26989376..8fe03b4a0d2b 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_free; } - err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id); if (err) goto fail_free; diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 26f0ecf401ea..0bbfd647f5c6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -65,6 +65,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct device_dma_parameters dma_parms; unsigned int periphid; unsigned int cid; struct amba_cs_uci_id uci; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ee577a83cfe6..7367150f962a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -219,6 +219,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } -extern const char *bdi_unknown_name; - -static inline const char *bdi_dev_name(struct backing_dev_info *bdi) -{ - if (!bdi || !bdi->dev) - return bdi_unknown_name; - return dev_name(bdi->dev); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1ade486fc2bb..57bcef6f988a 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -329,13 +329,12 @@ struct dma_buf { /** * struct dma_buf_attach_ops - importer operations for an attachment - * @move_notify: [optional] notification that the DMA-buf is moving * * Attachment operations implemented by the importer. */ struct dma_buf_attach_ops { /** - * @move_notify + * @move_notify: [optional] notification that the DMA-buf is moving * * If this callback is provided the framework can avoid pinning the * backing store while mappings exists. diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 21065c04c4ac..e1c03339918f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -83,9 +83,9 @@ enum dma_transfer_direction { /** * Interleaved Transfer Request * ---------------------------- - * A chunk is collection of contiguous bytes to be transfered. + * A chunk is collection of contiguous bytes to be transferred. * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG). - * ICGs may or maynot change between chunks. + * ICGs may or may not change between chunks. * A FRAME is the smallest series of contiguous {chunk,icg} pairs, * that when repeated an integral number of times, specifies the transfer. * A transfer template is specification of a Frame, the number of times @@ -341,13 +341,11 @@ struct dma_chan { * @chan: driver channel device * @device: sysfs device * @dev_id: parent dma_device dev_id - * @idr_ref: reference count to gate release of dma_device dev_id */ struct dma_chan_dev { struct dma_chan *chan; struct device device; int dev_id; - atomic_t *idr_ref; }; /** @@ -835,6 +833,8 @@ struct dma_device { int dev_id; struct device *dev; struct module *owner; + struct ida chan_ida; + struct mutex chan_mutex; /* to protect chan_ida */ u32 src_addr_widths; u32 dst_addr_widths; @@ -1069,7 +1069,7 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan) * dmaengine_synchronize() needs to be called before it is safe to free * any memory that is accessed by previously submitted descriptors or before * freeing any resources accessed from within the completion callback of any - * perviously submitted descriptors. + * previously submitted descriptors. * * This function can be called from atomic context as well as from within a * complete callback of a descriptor submitted on the same channel. @@ -1091,7 +1091,7 @@ static inline int dmaengine_terminate_async(struct dma_chan *chan) * * Synchronizes to the DMA channel termination to the current context. When this * function returns it is guaranteed that all transfers for previously issued - * descriptors have stopped and and it is safe to free the memory assoicated + * descriptors have stopped and it is safe to free the memory associated * with them. Furthermore it is guaranteed that all complete callback functions * for a previously submitted descriptor have finished running and it is safe to * free resources accessed from within the complete callbacks. diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f6f59b4f22a..45cc10cdf6dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -983,7 +983,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..1bdd027766d4 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) -LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, +LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..3d7c3c26eeb9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -53,9 +53,9 @@ enum mhi_callback { * @MHI_CHAIN: Linked transfer */ enum mhi_flags { - MHI_EOB, - MHI_EOT, - MHI_CHAIN, + MHI_EOB = BIT(0), + MHI_EOT = BIT(1), + MHI_CHAIN = BIT(2), }; /** @@ -335,14 +335,15 @@ struct mhi_controller_config { * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) - * @link_status: CB function to query link status of the device (required) * @wake_get: CB function to assert device wake (optional) * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) * @runtime_get: CB function to controller runtime resume (required) - * @runtimet_put: CB function to decrement pm usage (required) + * @runtime_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer + * @read_reg: Read a MHI register via the physical link (required) + * @write_reg: Write a MHI register via the physical link (required) * @buffer_len: Bounce buffer length * @bounce_buf: Use of bounce buffer * @fbc_download: MHI host needs to do complete image transfer (optional) @@ -417,7 +418,6 @@ struct mhi_controller { void (*status_cb)(struct mhi_controller *mhi_cntrl, enum mhi_callback cb); - int (*link_status)(struct mhi_controller *mhi_cntrl); void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_toggle)(struct mhi_controller *mhi_cntrl); @@ -427,6 +427,10 @@ struct mhi_controller { struct mhi_buf_info *buf); void (*unmap_single)(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf); + int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 *out); + void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 val); size_t buffer_len; bool bounce_buf; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 440230488025..e5f3e7d8d3d5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1317,11 +1317,13 @@ struct nfs41_impl_id { struct nfstime4 date; }; +#define MAX_BIND_CONN_TO_SESSION_RETRIES 3 struct nfs41_bind_conn_to_session_args { struct nfs_client *client; struct nfs4_sessionid sessionid; u32 dir; bool use_conn_in_rdma_mode; + int retries; }; struct nfs41_bind_conn_to_session_res { diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index c588be843f61..0ecce6aa69d5 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub, void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub, u8 sensor_num); +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub); int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub); void cros_ec_sensorhub_ring_remove(void *arg); int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index bdc35753ef7c..77a2aada106d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -25,6 +25,7 @@ struct platform_device { bool id_auto; struct device dev; u64 platform_dma_mask; + struct device_dma_parameters dma_parms; u32 num_resources; struct resource *resource; diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ca7e108248e2..02e7a5863d28 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -71,7 +71,13 @@ struct rpc_clnt { #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *cl_debugfs; /* debugfs directory */ #endif - struct rpc_xprt_iter cl_xpi; + /* cl_work is only needed after cl_xpi is no longer used, + * and that are of similar size + */ + union { + struct rpc_xprt_iter cl_xpi; + struct work_struct cl_work; + }; const struct cred *cl_cred; }; @@ -236,4 +242,9 @@ static inline int rpc_reply_expected(struct rpc_task *task) (task->tk_msg.rpc_proc->p_decode != NULL); } +static inline void rpc_task_close_connection(struct rpc_task *task) +{ + if (task->tk_xprt) + xprt_force_disconnect(task->tk_xprt); +} #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..4f8159e90ce1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -78,47 +78,6 @@ struct tcp_sack_block { #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ -#if IS_ENABLED(CONFIG_MPTCP) -struct mptcp_options_received { - u64 sndr_key; - u64 rcvr_key; - u64 data_ack; - u64 data_seq; - u32 subflow_seq; - u16 data_len; - u16 mp_capable : 1, - mp_join : 1, - dss : 1, - add_addr : 1, - rm_addr : 1, - family : 4, - echo : 1, - backup : 1; - u32 token; - u32 nonce; - u64 thmac; - u8 hmac[20]; - u8 join_id; - u8 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - __unused:2; - u8 addr_id; - u8 rm_id; - union { - struct in_addr addr; -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - struct in6_addr addr6; -#endif - }; - u64 ahmac; - u16 port; -}; -#endif - struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ @@ -136,9 +95,6 @@ struct tcp_options_received { u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ -#if IS_ENABLED(CONFIG_MPTCP) - struct mptcp_options_received mptcp; -#endif }; static inline void tcp_clear_options(struct tcp_options_received *rx_opt) @@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif -#if IS_ENABLED(CONFIG_MPTCP) - rx_opt->mptcp.mp_capable = 0; - rx_opt->mptcp.mp_join = 0; - rx_opt->mptcp.add_addr = 0; - rx_opt->mptcp.rm_addr = 0; - rx_opt->mptcp.dss = 0; -#endif } /* This is the max number of SACKS that we'll generate and process. It's safe diff --git a/include/linux/tty.h b/include/linux/tty.h index bd5fe0e907e8..a99e9b8e4e31 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ struct tty_buffer { int read; int flags; /* Data points here */ - unsigned long data[0]; + unsigned long data[]; }; /* Values for .flags field of tty_buffer */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 0d1fe9297ac6..6f6ade63b04c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include +#include +#include #include static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, @@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int gso_type = 0; + unsigned int thlen = 0; + unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); break; default: return -EINVAL; @@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + + if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { + struct flow_keys_basic keys; + if (!skb->protocol) virtio_net_hdr_set_proto(skb, hdr); retry: - skb_probe_transport_header(skb); - if (!skb_transport_header_was_set(skb)) { + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { @@ -75,6 +91,12 @@ retry: } return -EINVAL; } + + if (keys.control.thoff + thlen > skb_headlen(skb) || + keys.basic.ip_proto != ip_proto) + return -EINVAL; + + skb_set_transport_header(skb, keys.control.thoff); } } diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 71c81e0dc8f2..dc636b727179 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,7 @@ struct virtio_vsock_pkt { u32 len; u32 off; bool reply; + bool tap_delivered; }; struct virtio_vsock_pkt_info { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 3619c6acf60f..efc8350b42fb 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -166,15 +166,18 @@ enum flow_action_mangle_base { enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, + FLOW_ACTION_HW_STATS_DISABLED_BIT, }; enum flow_action_hw_stats { - FLOW_ACTION_HW_STATS_DISABLED = 0, + FLOW_ACTION_HW_STATS_DONT_CARE = 0, FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE | FLOW_ACTION_HW_STATS_DELAYED, + FLOW_ACTION_HW_STATS_DISABLED = + BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), }; typedef void (*action_destr)(void *priv); @@ -325,7 +328,11 @@ __flow_action_hw_stats_check(const struct flow_action *action, return true; if (!flow_action_mixed_hw_stats_check(action, extack)) return false; + action_entry = flow_action_first_entry_get(action); + if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE) + return true; + if (!check_allow_bit && action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index c8e2bebd8d93..0f0d1efe06dd 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph) return 1; } +static inline int IP_ECN_set_ect1(struct iphdr *iph) +{ + u32 check = (__force u32)iph->check; + + if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + check += (__force u16)htons(0x100); + + iph->check = (__force __sum16)(check + (check>=0xFFFF)); + iph->tos ^= INET_ECN_MASK; + return 1; +} + static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; @@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) return 1; } +static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + from = *(__be32 *)iph; + to = from ^ htonl(INET_ECN_MASK << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; @@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int INET_ECN_set_ect1(struct sk_buff *skb) +{ + switch (skb->protocol) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ect1(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant @@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb, int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); - if (!rc && set_ce) - INET_ECN_set_ce(skb); + if (!rc) { + if (set_ce) + INET_ECN_set_ce(skb); + else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) + INET_ECN_set_ect1(skb); + } return rc; } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 80262d2980f5..1d98828c6649 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -203,6 +203,7 @@ struct fib6_info { struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; + int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; @@ -291,6 +292,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt) struct fib6_info *from; u32 cookie = 0; + if (rt->sernum) + return rt->sernum; + rcu_read_lock(); from = rcu_dereference(rt->from); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0e7c5471010b..3bce2019e4da 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -68,11 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return tcp_rsk(req)->is_mptcp; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); -void mptcp_rcv_synsent(struct sock *sk); bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, struct mptcp_out_options *opts); bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ab96fb59131c..8e001e049497 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -437,6 +437,13 @@ static inline int rt_genid_ipv4(const struct net *net) return atomic_read(&net->ipv4.rt_genid); } +#if IS_ENABLED(CONFIG_IPV6) +static inline int rt_genid_ipv6(const struct net *net) +{ + return atomic_read(&net->ipv6.fib6_sernum); +} +#endif + static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 25d2ec4c8f00..8428aa614265 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -407,6 +407,7 @@ struct tcf_block { struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ + u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6d6a3947c8b7..efc8b613d486 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -502,6 +502,7 @@ struct ocelot { unsigned int num_stats; int shared_queue_sz; + int num_mact_rows; struct net_device *hw_bridge_dev; u16 bridge_mask; diff --git a/include/trace/events/gpu_mem.h b/include/trace/events/gpu_mem.h index 1897822a9150..26d871f96e94 100644 --- a/include/trace/events/gpu_mem.h +++ b/include/trace/events/gpu_mem.h @@ -24,7 +24,7 @@ * * @pid: Put 0 for global total, while positive pid for process total. * - * @size: Virtual size of the allocation in bytes. + * @size: Size of the allocation in bytes. * */ TRACE_EVENT(gpu_mem_total, diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 596e0a803477..132c3c778a43 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -692,11 +692,10 @@ TRACE_EVENT(xprtrdma_prepsend_failed, TRACE_EVENT(xprtrdma_post_send, TP_PROTO( - const struct rpcrdma_req *req, - int status + const struct rpcrdma_req *req ), - TP_ARGS(req, status), + TP_ARGS(req), TP_STRUCT__entry( __field(const void *, req) @@ -705,7 +704,6 @@ TRACE_EVENT(xprtrdma_post_send, __field(unsigned int, client_id) __field(int, num_sge) __field(int, signaled) - __field(int, status) ), TP_fast_assign( @@ -718,15 +716,13 @@ TRACE_EVENT(xprtrdma_post_send, __entry->sc = req->rl_sendctx; __entry->num_sge = req->rl_wr.num_sge; __entry->signaled = req->rl_wr.send_flags & IB_SEND_SIGNALED; - __entry->status = status; ), - TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %sstatus=%d", + TP_printk("task:%u@%u req=%p sc=%p (%d SGE%s) %s", __entry->task_id, __entry->client_id, __entry->req, __entry->sc, __entry->num_sge, (__entry->num_sge == 1 ? "" : "s"), - (__entry->signaled ? "signaled " : ""), - __entry->status + (__entry->signaled ? "signaled" : "") ) ); diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index 784814160197..9c66e59d859c 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; @@ -68,7 +68,7 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; @@ -141,7 +141,7 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 65f69723cbdc..d28b4ce744d5 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -346,6 +346,10 @@ struct drm_amdgpu_gem_userptr { #define AMDGPU_TILING_DCC_PITCH_MAX_MASK 0x3FFF #define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT 43 #define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK 0x1 +#define AMDGPU_TILING_DCC_INDEPENDENT_128B_SHIFT 44 +#define AMDGPU_TILING_DCC_INDEPENDENT_128B_MASK 0x1 +#define AMDGPU_TILING_SCANOUT_SHIFT 63 +#define AMDGPU_TILING_SCANOUT_MASK 0x1 /* Set/Get helpers for tiling flags. */ #define AMDGPU_TILING_SET(field, value) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bbf1b65be10..f9b7fdd951e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index e83954c69fff..f880d2831160 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[]; + char name[0]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[]; + char name[0]; }; struct dlm_purge_params { diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index dbc7092e04b5..7f30393b92c3 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -39,6 +39,12 @@ struct dma_buf_sync { #define DMA_BUF_BASE 'b' #define DMA_BUF_IOCTL_SYNC _IOW(DMA_BUF_BASE, 0, struct dma_buf_sync) + +/* 32/64bitness of this uapi was botched in android, there's no difference + * between them in actual uapi, they're just different numbers. + */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) #endif diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 7a900b2377b6..8c0bc24d5d95 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index 991b2b7ada7a..8f24404ad04f 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -119,8 +119,8 @@ enum hv_fcopy_op { struct hv_fcopy_hdr { __u32 operation; - uuid_le service_id0; /* currently unused */ - uuid_le service_id1; /* currently unused */ + __u8 service_id0[16]; /* currently unused */ + __u8 service_id1[16]; /* currently unused */ } __attribute__((packed)); #define OVER_WRITE 0x1 diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index b122cfac7128..683878036d76 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -60,7 +60,7 @@ struct arc_rfc1201 { __u8 proto; /* protocol ID field - varies */ __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - __u8 payload[]; /* space remaining in packet (504 bytes)*/ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -69,7 +69,7 @@ struct arc_rfc1201 { */ struct arc_rfc1051 { __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[]; /* 507 bytes */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -80,7 +80,7 @@ struct arc_rfc1051 { struct arc_eth_encap { __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[]; /* 493 bytes */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 98e29e7f54ac..00c08120f3ba 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -57,7 +57,7 @@ struct mmc_ioc_cmd { */ struct mmc_ioc_multi_cmd { __u64 num_of_cmds; - struct mmc_ioc_cmd cmds[]; + struct mmc_ioc_cmd cmds[0]; }; #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 67e31f329190..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -29,12 +29,12 @@ struct net_dm_config_entry { struct net_dm_config_msg { __u32 entries; - struct net_dm_config_entry options[]; + struct net_dm_config_entry options[0]; }; struct net_dm_alert_msg { __u32 entries; - struct net_dm_drop_point points[]; + struct net_dm_drop_point points[0]; }; struct net_dm_user_msg { diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index 73b26a280c4f..9acf757bc1f7 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple { struct ebt_mac_wormhash { int table[257]; int poolsize; - struct ebt_mac_wormhash_tuple pool[]; + struct ebt_mac_wormhash_tuple pool[0]; }; #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \ diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 7f5930801f72..3ae65e93235c 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -209,7 +209,7 @@ struct fc_bsg_host_vendor { __u64 vendor_id; /* start of vendor command area */ - __u32 vendor_cmd[]; + __u32 vendor_cmd[0]; }; /* Response: diff --git a/init/Kconfig b/init/Kconfig index 9e22ee8fbd75..9278a603d399 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -39,22 +39,6 @@ config TOOLS_SUPPORT_RELR config CC_HAS_ASM_INLINE def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null) -config CC_HAS_WARN_MAYBE_UNINITIALIZED - def_bool $(cc-option,-Wmaybe-uninitialized) - help - GCC >= 4.7 supports this option. - -config CC_DISABLE_WARN_MAYBE_UNINITIALIZED - bool - depends on CC_HAS_WARN_MAYBE_UNINITIALIZED - default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9 - help - GCC's -Wmaybe-uninitialized is not reliable by definition. - Lots of false positive warnings are produced in some cases. - - If this option is enabled, -Wno-maybe-uninitialzed is passed - to the compiler to suppress maybe-uninitialized warnings. - config CONSTRUCTORS bool depends on !UML @@ -1257,14 +1241,12 @@ config CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE_O3 bool "Optimize more for performance (-O3)" depends on ARC - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-O3" to your compiler to optimize the kernel yet more for performance. config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size (-Os)" - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-Os" to your compiler resulting in a smaller kernel. diff --git a/init/initramfs.c b/init/initramfs.c index 8ec1be4d7d51..7a38012e1af7 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -542,7 +542,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end) } #ifdef CONFIG_KEXEC_CORE -static bool kexec_free_initrd(void) +static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); diff --git a/init/main.c b/init/main.c index a48617f2e5e5..1a5da2c2660c 100644 --- a/init/main.c +++ b/init/main.c @@ -257,6 +257,47 @@ static int __init loglevel(char *str) early_param("loglevel", loglevel); +#ifdef CONFIG_BLK_DEV_INITRD +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + u32 size, csum; + char *data; + u32 *hdr; + + if (!initrd_end) + return NULL; + + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + return NULL; + + hdr = (u32 *)(data - 8); + size = hdr[0]; + csum = hdr[1]; + + data = ((void *)hdr) - size; + if ((unsigned long)data < initrd_start) { + pr_err("bootconfig size %d is greater than initrd size %ld\n", + size, initrd_end - initrd_start); + return NULL; + } + + /* Remove bootconfig from initramfs/initrd */ + initrd_end = (unsigned long)data; + if (_size) + *_size = size; + if (_csum) + *_csum = csum; + + return data; +} +#else +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + return NULL; +} +#endif + #ifdef CONFIG_BOOT_CONFIG char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; @@ -357,9 +398,12 @@ static void __init setup_boot_config(const char *cmdline) int pos; u32 size, csum; char *data, *copy; - u32 *hdr; int ret; + data = get_boot_config_from_initrd(&size, &csum); + if (!data) + goto not_found; + strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, bootconfig_params); @@ -367,27 +411,12 @@ static void __init setup_boot_config(const char *cmdline) if (!bootconfig_found) return; - if (!initrd_end) - goto not_found; - - data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - goto not_found; - - hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; - if (size >= XBC_DATA_MAX) { pr_err("bootconfig size %d greater than max size %d\n", size, XBC_DATA_MAX); return; } - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) - goto not_found; - if (boot_config_checksum((unsigned char *)data, size) != csum) { pr_err("bootconfig checksum failed\n"); return; @@ -420,8 +449,14 @@ static void __init setup_boot_config(const char *cmdline) not_found: pr_err("'bootconfig' found on command line, but no bootconfig found\n"); } + #else -#define setup_boot_config(cmdline) do { } while (0) + +static void __init setup_boot_config(const char *cmdline) +{ + /* Remove bootconfig data from initrd */ + get_boot_config_from_initrd(NULL, NULL); +} static int __init warn_bootconfig(char *str) { diff --git a/ipc/mqueue.c b/ipc/mqueue.c index dc8307bf2d74..beff0cfcd1e8 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -142,6 +142,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid *notify_owner; + u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; @@ -773,28 +774,44 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; - case SIGEV_SIGNAL: - /* sends signal */ + case SIGEV_SIGNAL: { + struct kernel_siginfo sig_i; + struct task_struct *task; + + /* do_mq_notify() accepts sigev_signo == 0, why?? */ + if (!info->notify.sigev_signo) + break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - /* map current pid/uid into info->owner's namespaces */ rcu_read_lock(); + /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, + current_uid()); + /* + * We can't use kill_pid_info(), this signal should + * bypass check_kill_permission(). It is from kernel + * but si_fromuser() can't know this. + * We do check the self_exec_id, to avoid sending + * signals to programs that don't expect them. + */ + task = pid_task(info->notify_owner, PIDTYPE_TGID); + if (task && task->self_exec_id == + info->notify_self_exec_id) { + do_send_sig_info(info->notify.sigev_signo, + &sig_i, task, PIDTYPE_TGID); + } rcu_read_unlock(); - - kill_pid_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); break; + } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); @@ -1383,6 +1400,7 @@ retry: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_self_exec_id = current->self_exec_id; break; } diff --git a/kernel/kcov.c b/kernel/kcov.c index f50354202dbe..8accc9722a81 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = { * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an * arbitrary 4-byte non-zero number as the instance id). This common handle * then gets saved into the task_struct of the process that issued the - * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn - * kernel threads, the common handle must be retrived via kcov_common_handle() + * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn + * kernel threads, the common handle must be retrieved via kcov_common_handle() * and passed to the spawned threads via custom annotations. Those kernel * threads must in turn be annotated with kcov_remote_start(common_handle) and * kcov_remote_stop(). All of the threads that are spawned by the same process diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 86aba8706b16..30bd28d1d418 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -898,6 +898,13 @@ static int software_resume(void) error = freeze_processes(); if (error) goto Close_Finish; + + error = freeze_kernel_threads(); + if (error) { + thaw_processes(); + goto Close_Finish; + } + error = load_image_and_restore(); thaw_processes(); Finish: diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 402eef84c859..743647005f64 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -466,7 +466,6 @@ config PROFILE_ANNOTATED_BRANCHES config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss. diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index 31c0fad4cb9e..c4c86de63cf9 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -113,22 +113,42 @@ static int preemptirq_delay_run(void *data) for (i = 0; i < s; i++) (testfuncs[i])(i); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + __set_current_state(TASK_RUNNING); + return 0; } -static struct task_struct *preemptirq_start_test(void) +static int preemptirq_run_test(void) { + struct task_struct *task; + char task_name[50]; snprintf(task_name, sizeof(task_name), "%s_test", test_mode); - return kthread_run(preemptirq_delay_run, NULL, task_name); + task = kthread_run(preemptirq_delay_run, NULL, task_name); + if (IS_ERR(task)) + return PTR_ERR(task); + if (task) + kthread_stop(task); + return 0; } static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - preemptirq_start_test(); + ssize_t ret; + + ret = preemptirq_run_test(); + if (ret) + return ret; return count; } @@ -148,11 +168,9 @@ static struct kobject *preemptirq_delay_kobj; static int __init preemptirq_delay_init(void) { - struct task_struct *test_task; int retval; - test_task = preemptirq_start_test(); - retval = PTR_ERR_OR_ZERO(test_task); + retval = preemptirq_run_test(); if (retval != 0) return retval; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8d2b98812625..29615f15a820 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 06d7feb5255f..9de29bb45a27 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -95,23 +95,19 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) struct xbc_node *anode; char buf[MAX_BUF_LEN]; const char *val; - int ret; - - kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); - - ret = kprobe_event_gen_cmd_start(&cmd, event, NULL); - if (ret) - return ret; + int ret = 0; xbc_node_for_each_array_value(node, "probes", anode, val) { - ret = kprobe_event_add_field(&cmd, val); - if (ret) - return ret; - } + kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); - ret = kprobe_event_gen_cmd_end(&cmd); - if (ret) - pr_err("Failed to add probe: %s\n", buf); + ret = kprobe_event_gen_cmd_start(&cmd, event, val); + if (ret) + break; + + ret = kprobe_event_gen_cmd_end(&cmd); + if (ret) + pr_err("Failed to add probe: %s\n", buf); + } return ret; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d0568af4a0ef..35989383ae11 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr) static bool within_notrace_func(struct trace_kprobe *tk) { - unsigned long addr = addr = trace_kprobe_address(tk); + unsigned long addr = trace_kprobe_address(tk); char symname[KSYM_NAME_LEN], *p; if (!__within_notrace_func(addr)) @@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init); * complete command or only the first part of it; in the latter case, * kprobe_event_add_fields() can be used to add more fields following this. * + * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This + * returns -EINVAL if @loc == NULL. + * * Return: 0 if successful, error otherwise. */ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, @@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, if (cmd->type != DYNEVENT_TYPE_KPROBE) return -EINVAL; + if (!loc) + return -EINVAL; + if (kretprobe) snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name); else diff --git a/kernel/umh.c b/kernel/umh.c index 7f255b5a8845..11bf5eea474c 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,6 +544,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 48469c95d78e..929211039bac 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -60,17 +60,14 @@ config UBSAN_SANITIZE_ALL Enabling this option will get kernel image size increased significantly. -config UBSAN_NO_ALIGNMENT - bool "Disable checking of pointers alignment" - default y if HAVE_EFFICIENT_UNALIGNED_ACCESS - help - This option disables the check of unaligned memory accesses. - This option should be used when building allmodconfig. - Disabling this option on architectures that support unaligned - accesses may produce a lot of false positives. - config UBSAN_ALIGNMENT - def_bool !UBSAN_NO_ALIGNMENT + bool "Enable checks for pointers alignment" + default !HAVE_EFFICIENT_UNALIGNED_ACCESS + depends on !X86 || !COMPILE_TEST + help + This option enables the check of unaligned memory accesses. + Enabling this option on architectures that support unaligned + accesses may produce a lot of false positives. config TEST_UBSAN tristate "Module for testing for undefined behavior detection" diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 7a6430a7fca0..ccb2ffad8dcf 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -93,7 +93,7 @@ static void kunit_print_ok_not_ok(void *test_or_suite, * representation. */ if (suite) - pr_info("%s %zd - %s", + pr_info("%s %zd - %s\n", kunit_status_to_string(is_ok), test_number, description); else diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c81b4f3a7268..efc5b83acd2d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = { EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; -const char *bdi_unknown_name = "(unknown)"; +static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU @@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5beea03dd58a..a3b97f103966 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void) unsigned int size; int node; int __maybe_unused i; + long error = -ENOMEM; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(error); memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); - if (memcg->id.id < 0) + if (memcg->id.id < 0) { + error = memcg->id.id; goto fail; + } memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_local) @@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref @@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) long error = -ENOMEM; memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; @@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) fail: mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69827d4fa052..13cc653122b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone) if (!watermark_boost_factor) return; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); diff --git a/mm/percpu.c b/mm/percpu.c index d7e3bc649f4e..7da7d7737dab 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { - /* whitelisted flags that can be passed to the backing allocators */ - gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; - bool do_warn = !(gfp & __GFP_NOWARN); + gfp_t pcpu_gfp; + bool is_atomic; + bool do_warn; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; @@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, void __percpu *ptr; size_t bits, bit_align; + gfp = current_gfp_context(gfp); + /* whitelisted flags that can be passed to the backing allocators */ + pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + do_warn = !(gfp & __GFP_NOWARN); + /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. diff --git a/mm/slub.c b/mm/slub.c index 9bf44955c4f1..b762450fc9f0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -3587,6 +3597,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/vmscan.c b/mm/vmscan.c index b06868fc4926..a37c87b5aee2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session - * @mode: One of the LRU isolation modes * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. diff --git a/net/atm/common.c b/net/atm/common.c index 0ce530af534d..8575f5d52087 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -177,18 +177,18 @@ static void vcc_destroy_socket(struct sock *sk) set_bit(ATM_VF_CLOSE, &vcc->flags); clear_bit(ATM_VF_READY, &vcc->flags); - if (vcc->dev) { - if (vcc->dev->ops->close) - vcc->dev->ops->close(vcc); - if (vcc->push) - vcc->push(vcc, NULL); /* atmarpd has no push */ - module_put(vcc->owner); + if (vcc->dev && vcc->dev->ops->close) + vcc->dev->ops->close(vcc); + if (vcc->push) + vcc->push(vcc, NULL); /* atmarpd has no push */ + module_put(vcc->owner); - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - } + while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + atm_return(vcc, skb->truesize); + kfree_skb(skb); + } + if (vcc->dev && vcc->dev->ops->owner) { module_put(vcc->dev->ops->owner); atm_dev_put(vcc->dev); } diff --git a/net/atm/lec.c b/net/atm/lec.c index 25fa3a7b72bd..ca37f5a71f5e 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1264,6 +1264,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 969466218999..80b87b1f4e3a 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -893,7 +893,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) - return; + goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 8f0717c3f7b5..b0469d15da0e 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index c45962d8527b..0f962dcd239e 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1150,7 +1150,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out; old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override) @@ -1190,6 +1190,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj, tp_override = atomic_read(&hard_iface->bat_v.throughput_override); + batadv_hardif_put(hard_iface); return sprintf(buff, "%u.%u MBit\n", tp_override / 10, tp_override % 10); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 43dab4066f91..a0f5dbee8f9c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -612,6 +612,7 @@ int br_process_vlan_info(struct net_bridge *br, v - 1, rtm_cmd); v_change_start = 0; } + cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) diff --git a/net/core/devlink.c b/net/core/devlink.c index 80f97722f31f..899edcee7dab 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4283,6 +4283,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); dump = false; + + if (start_offset == end_offset) { + err = 0; + goto nla_put_failure; + } } err = devlink_nl_region_read_snapshot_fill(skb, devlink, @@ -5363,6 +5368,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; /* write a log message of the current error */ WARN_ON(!msg); @@ -5373,10 +5379,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 8e33cec9fc4e..2ee7bc4c9e03 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -213,6 +213,7 @@ static void sched_send_work(struct timer_list *t) static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; + struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; @@ -231,11 +232,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); + point = msg->points; for (i = 0; i < msg->entries; i++) { - if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { - msg->points[i].count++; + if (!memcmp(&location, &point->pc, sizeof(void *))) { + point->count++; goto out; } + point++; } if (msg->entries == dm_hit_limit) goto out; @@ -244,8 +247,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); - memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); - msg->points[msg->entries].count = 1; + memcpy(point->pc, &location, sizeof(void *)); + point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 39d37d0ef575..116139233d57 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1956,6 +1956,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } + if (protocol) + neigh->protocol = protocol; + if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; @@ -1969,9 +1972,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (protocol) - neigh->protocol = protocol; - neigh_release(neigh); out: diff --git a/net/core/sock.c b/net/core/sock.c index 90509c37d291..b714162213ae 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2364,7 +2364,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -/* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9a271a58a41d..d90665b465b8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -459,7 +459,7 @@ 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) - goto teardown; + continue; } return 0; diff --git a/net/dsa/master.c b/net/dsa/master.c index b5c535af63a3..a621367c6e8c 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -289,7 +289,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; - dev->netdev_ops = cpu_dp->orig_ndo_ops; + if (cpu_dp->orig_ndo_ops) + dev->netdev_ops = cpu_dp->orig_ndo_ops; cpu_dp->orig_ndo_ops = NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d1068803cd11..62f4ee3da172 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -856,20 +856,18 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, struct dsa_port *to_dp; int err; - act = &cls->rule->action.entries[0]; - if (!ds->ops->port_mirror_add) return -EOPNOTSUPP; - if (!act->dev) - return -EINVAL; - if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; + if (!act->dev) + return -EINVAL; + if (!dsa_slave_dev_check(act->dev)) return -EOPNOTSUPP; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index f4b9f7a3ce51..25b6ffba26cd 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -18,7 +18,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; - u16 protocol; + __be16 protocol; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bf4ced9273e8..b996dc1069c5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net, */ break; #endif - case TCPOPT_MPTCP: - mptcp_parse_option(skb, ptr, opsize, opt_rx); - break; - case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -5990,9 +5986,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); - if (sk_is_mptcp(sk)) - mptcp_rcv_synsent(sk); - /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 310cbddaa533..8d418038fe32 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1385,9 +1385,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; + + if (f6i->nh) + pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); + return pcpu_rt; } +static bool rt6_is_valid(const struct rt6_info *rt6) +{ + return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); +} + /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { @@ -1395,6 +1404,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); + if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { + struct rt6_info *prev, **p; + + p = this_cpu_ptr(res->nh->rt6i_pcpu); + prev = xchg(p, NULL); + if (prev) { + dst_dev_put(&prev->dst); + dst_release(&prev->dst); + } + + pcpu_rt = NULL; + } + return pcpu_rt; } @@ -2593,6 +2615,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = container_of(dst, struct rt6_info, dst); + if (rt->sernum) + return rt6_is_valid(rt) ? dst : NULL; + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 4c7e0a27fa9c..37b434293bda 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -27,8 +27,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) { - int trailing; unsigned int tlv_offset; + int max_last_entry; + int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; @@ -36,7 +37,12 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) if (((srh->hdrlen + 1) << 3) != len) return false; - if (srh->segments_left > srh->first_segment) + max_last_entry = (srh->hdrlen / 2) - 1; + + if (srh->first_segment > max_last_entry) + return false; + + if (srh->segments_left > srh->first_segment + 1) return false; tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4a7c467b99db..45497af23906 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -16,10 +16,10 @@ static bool mptcp_cap_flag_sha256(u8 flags) return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx) +static void mptcp_parse_option(const struct sk_buff *skb, + const unsigned char *ptr, int opsize, + struct mptcp_options_received *mp_opt) { - struct mptcp_options_received *mp_opt = &opt_rx->mptcp; u8 subtype = *ptr >> 4; int expected_opsize; u8 version; @@ -283,12 +283,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, } void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx) + struct mptcp_options_received *mp_opt) { - const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); - int length = (th->doff * 4) - sizeof(struct tcphdr); + const unsigned char *ptr; + int length; + /* initialize option status */ + mp_opt->mp_capable = 0; + mp_opt->mp_join = 0; + mp_opt->add_addr = 0; + mp_opt->rm_addr = 0; + mp_opt->dss = 0; + + length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); while (length > 0) { @@ -308,7 +316,7 @@ void mptcp_get_options(const struct sk_buff *skb, if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_MPTCP) - mptcp_parse_option(skb, ptr, opsize, opt_rx); + mptcp_parse_option(skb, ptr, opsize, mp_opt); ptr += opsize - 2; length -= opsize; } @@ -344,28 +352,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -void mptcp_rcv_synsent(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct tcp_sock *tp = tcp_sk(sk); - - if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) { - subflow->mp_capable = 1; - subflow->can_ack = 1; - subflow->remote_key = tp->rx_opt.mptcp.sndr_key; - pr_debug("subflow=%p, remote_key=%llu", subflow, - subflow->remote_key); - } else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) { - subflow->mp_join = 1; - subflow->thmac = tp->rx_opt.mptcp.thmac; - subflow->remote_nonce = tp->rx_opt.mptcp.nonce; - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, - subflow->thmac, subflow->remote_nonce); - } else if (subflow->request_mptcp) { - tcp_sk(sk)->is_mptcp = 0; - } -} - /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions @@ -709,7 +695,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) return subflow->mp_capable; - if (mp_opt->use_ack) { + if (mp_opt->dss && mp_opt->use_ack) { /* subflows are fully established as soon as we get any * additional ack. */ @@ -717,8 +703,6 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, goto fully_established; } - WARN_ON_ONCE(subflow->can_ack); - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP */ @@ -728,6 +712,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, return false; } + if (unlikely(!READ_ONCE(msk->pm.server_side))) + pr_warn_once("bogus mpc option on established client sk"); subflow->fully_established = 1; subflow->remote_key = mp_opt->sndr_key; subflow->can_ack = 1; @@ -819,41 +805,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - struct mptcp_options_received *mp_opt; + struct mptcp_options_received mp_opt; struct mptcp_ext *mpext; - mp_opt = &opt_rx->mptcp; - if (!check_fully_established(msk, sk, subflow, skb, mp_opt)) + mptcp_get_options(skb, &mp_opt); + if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; - if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) { + if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) { struct mptcp_addr_info addr; - addr.port = htons(mp_opt->port); - addr.id = mp_opt->addr_id; - if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) { + addr.port = htons(mp_opt.port); + addr.id = mp_opt.addr_id; + if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) { addr.family = AF_INET; - addr.addr = mp_opt->addr; + addr.addr = mp_opt.addr; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) - else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) { + else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) { addr.family = AF_INET6; - addr.addr6 = mp_opt->addr6; + addr.addr6 = mp_opt.addr6; } #endif - if (!mp_opt->echo) + if (!mp_opt.echo) mptcp_pm_add_addr_received(msk, &addr); - mp_opt->add_addr = 0; + mp_opt.add_addr = 0; } - if (!mp_opt->dss) + if (!mp_opt.dss) return; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck */ - if (mp_opt->use_ack) - update_una(msk, mp_opt); + if (mp_opt.use_ack) + update_una(msk, &mp_opt); mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) @@ -861,8 +847,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, memset(mpext, 0, sizeof(*mpext)); - if (mp_opt->use_map) { - if (mp_opt->mpc_map) { + if (mp_opt.use_map) { + if (mp_opt.mpc_map) { /* this is an MP_CAPABLE carrying MPTCP data * we know this map the first chunk of data */ @@ -872,13 +858,14 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, mpext->subflow_seq = 1; mpext->dsn64 = 1; mpext->mpc_map = 1; + mpext->data_fin = 0; } else { - mpext->data_seq = mp_opt->data_seq; - mpext->subflow_seq = mp_opt->subflow_seq; - mpext->dsn64 = mp_opt->dsn64; - mpext->data_fin = mp_opt->data_fin; + mpext->data_seq = mp_opt.data_seq; + mpext->subflow_seq = mp_opt.subflow_seq; + mpext->dsn64 = mp_opt.dsn64; + mpext->data_fin = mp_opt.data_fin; } - mpext->data_len = mp_opt->data_len; + mpext->data_len = mp_opt.data_len; mpext->use_map = 1; } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b22a63ba2348..e1f23016ed3f 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1316,11 +1316,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) static int mptcp_disconnect(struct sock *sk, int flags) { - lock_sock(sk); - __mptcp_clear_xmit(sk); - release_sock(sk); - mptcp_cancel_work(sk); - return tcp_disconnect(sk, flags); + /* Should never be called. + * inet_stream_connect() calls ->disconnect, but that + * refers to the subflow socket, not the mptcp one. + */ + WARN_ON_ONCE(1); + return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1333,7 +1334,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); @@ -1372,9 +1373,9 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); - if (opt_rx->mptcp.mp_capable) { + if (mp_opt->mp_capable) { msk->can_ack = true; - msk->remote_key = opt_rx->mptcp.sndr_key; + msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; msk->ack_seq = ack_seq; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a2b3048037d0..e4ca6320ce76 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -91,6 +91,45 @@ #define MPTCP_WORK_RTX 2 #define MPTCP_WORK_EOF 3 +struct mptcp_options_received { + u64 sndr_key; + u64 rcvr_key; + u64 data_ack; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + u16 mp_capable : 1, + mp_join : 1, + dss : 1, + add_addr : 1, + rm_addr : 1, + family : 4, + echo : 1, + backup : 1; + u32 token; + u32 nonce; + u64 thmac; + u8 hmac[20]; + u8 join_id; + u8 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + __unused:2; + u8 addr_id; + u8 rm_id; + union { + struct in_addr addr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + struct in6_addr addr6; +#endif + }; + u64 ahmac; + u16 port; +}; + static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) { return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) | @@ -331,10 +370,10 @@ int mptcp_proto_v6_init(void); #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx); + struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fabd06f2ff45..67a4e35d4838 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -124,12 +124,11 @@ static void subflow_init_req(struct request_sock *req, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - struct tcp_options_received rx_opt; + struct mptcp_options_received mp_opt; pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); - memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp)); - mptcp_get_options(skb, &rx_opt); + mptcp_get_options(skb, &mp_opt); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; @@ -142,16 +141,16 @@ static void subflow_init_req(struct request_sock *req, return; #endif - if (rx_opt.mptcp.mp_capable) { + if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); - if (rx_opt.mptcp.mp_join) + if (mp_opt.mp_join) return; - } else if (rx_opt.mptcp.mp_join) { + } else if (mp_opt.mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); } - if (rx_opt.mptcp.mp_capable && listener->request_mptcp) { + if (mp_opt.mp_capable && listener->request_mptcp) { int err; err = mptcp_token_new_request(req); @@ -159,13 +158,13 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; - } else if (rx_opt.mptcp.mp_join && listener->request_mptcp) { + } else if (mp_opt.mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; - subflow_req->backup = rx_opt.mptcp.backup; - subflow_req->remote_id = rx_opt.mptcp.join_id; - subflow_req->token = rx_opt.mptcp.token; - subflow_req->remote_nonce = rx_opt.mptcp.nonce; + subflow_req->backup = mp_opt.backup; + subflow_req->remote_id = mp_opt.join_id; + subflow_req->token = mp_opt.token; + subflow_req->remote_nonce = mp_opt.nonce; pr_debug("token=%u, remote_nonce=%u", subflow_req->token, subflow_req->remote_nonce); if (!subflow_token_join_request(req, skb)) { @@ -221,23 +220,47 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; + struct tcp_sock *tp = tcp_sk(sk); subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) != TCP_ESTABLISHED) { + if (inet_sk_state_load(parent) == TCP_SYN_SENT) { inet_sk_state_store(parent, TCP_ESTABLISHED); parent->sk_state_change(parent); } - if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp) + /* be sure no special action on any packet other than syn-ack */ + if (subflow->conn_finished) + return; + + subflow->conn_finished = 1; + + mptcp_get_options(skb, &mp_opt); + if (subflow->request_mptcp && mp_opt.mp_capable) { + subflow->mp_capable = 1; + subflow->can_ack = 1; + subflow->remote_key = mp_opt.sndr_key; + pr_debug("subflow=%p, remote_key=%llu", subflow, + subflow->remote_key); + } else if (subflow->request_join && mp_opt.mp_join) { + subflow->mp_join = 1; + subflow->thmac = mp_opt.thmac; + subflow->remote_nonce = mp_opt.nonce; + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, + subflow->thmac, subflow->remote_nonce); + } else if (subflow->request_mptcp) { + tp->is_mptcp = 0; + } + + if (!tp->is_mptcp) return; if (subflow->mp_capable) { pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk), subflow->remote_key); mptcp_finish_connect(sk); - subflow->conn_finished = 1; if (skb) { pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq); @@ -264,7 +287,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (!mptcp_finish_join(sk)) goto do_reset; - subflow->conn_finished = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); } else { do_reset: @@ -322,7 +344,7 @@ drop: /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, - const struct tcp_options_received *rx_opt) + const struct mptcp_options_received *mp_opt) { const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[MPTCPOPT_HMAC_LEN]; @@ -339,7 +361,7 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req->local_nonce, hmac); ret = true; - if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac))) + if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac))) ret = false; sock_put((struct sock *)msk); @@ -395,7 +417,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; - struct tcp_options_received opt_rx; + struct mptcp_options_received mp_opt; bool fallback_is_fatal = false; struct sock *new_msk = NULL; bool fallback = false; @@ -403,7 +425,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - opt_rx.mptcp.mp_capable = 0; + /* we need later a valid 'mp_capable' value even when options are not + * parsed + */ + mp_opt.mp_capable = 0; if (tcp_rsk(req)->is_mptcp == 0) goto create_child; @@ -418,22 +443,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, goto create_msk; } - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_capable) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_capable) { fallback = true; goto create_child; } create_msk: - new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req); + new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req); if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { fallback_is_fatal = true; - opt_rx.mptcp.mp_join = 0; - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_join || - !subflow_hmac_valid(req, &opt_rx)) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_join || + !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); return NULL; } @@ -473,9 +497,9 @@ create_child: /* with OoO packets we can reach here without ingress * mpc option */ - ctx->remote_key = opt_rx.mptcp.sndr_key; - ctx->fully_established = opt_rx.mptcp.mp_capable; - ctx->can_ack = opt_rx.mptcp.mp_capable; + ctx->remote_key = mp_opt.sndr_key; + ctx->fully_established = mp_opt.mp_capable; + ctx->can_ack = mp_opt.mp_capable; } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -499,7 +523,7 @@ out: /* check for expected invariant - should never trigger, just help * catching eariler subtle bugs */ - WARN_ON_ONCE(*own_req && child && tcp_sk(child)->is_mptcp && + WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || !mptcp_subflow_ctx(child)->conn)); return child; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 3d816a1e5442..59151dc07fdc 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; - bool do_csum; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); - do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); - __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 9f5dea0064ea..916a3c7f9eaf 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -165,12 +165,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb, static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, - unsigned char *opts) + unsigned char *opts, + struct tcphdr *_tcph) { const struct tcphdr *tcp; - struct tcphdr _tcph; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; @@ -205,10 +205,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; @@ -265,10 +266,11 @@ bool nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 55bd1429678f..0a7ecc292bd3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2070,6 +2070,7 @@ replay: err = PTR_ERR(block); goto errout; } + block->classid = parent; chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { @@ -2612,12 +2613,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; parent = tcm->tcm_parent; - if (!parent) { + if (!parent) q = dev->qdisc; - parent = q->handle; - } else { + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } if (!q) goto out; cops = q->ops->cl_ops; @@ -2633,6 +2632,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl, NULL); if (!block) goto out; + parent = block->classid; if (tcf_block_shared(block)) q = NULL; } @@ -3523,6 +3523,16 @@ static void tcf_sample_get_group(struct flow_action_entry *entry, #endif } +static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) +{ + if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) + return FLOW_ACTION_HW_STATS_DONT_CARE; + else if (!hw_stats) + return FLOW_ACTION_HW_STATS_DISABLED; + + return hw_stats; +} + int tc_setup_flow_action(struct flow_action *flow_action, const struct tcf_exts *exts) { @@ -3546,7 +3556,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, if (err) goto err_out_locked; - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; @@ -3614,7 +3624,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mangle.mask = tcf_pedit_mask(act, k); entry->mangle.val = tcf_pedit_val(act, k); entry->mangle.offset = tcf_pedit_offset(act, k); - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); entry = &flow_action->entries[++j]; } } else if (is_tcf_csum(act)) { diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index a36974e9c601..1bcf8fbfd40e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch) sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 968519ff36e9..436160be9c18 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -416,7 +416,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c787d4d46017..5a6def5e4e6d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + /* slot->allot is a short, make sure quantum is not too big. */ + if (ctl->quantum) { + unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum); + + if (scaled <= 0 || scaled > SHRT_MAX) + return -EINVAL; + } + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog)) return -EINVAL; diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 0fb10abf7579..7a5e4c454715 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, { struct tc_skbprio_qopt *ctl = nla_data(opt); + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + sch->limit = ctl->limit; return 0; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 325a0858700f..8350d3a2e9a7 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -880,6 +880,20 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); /* * Free an RPC client */ +static void rpc_free_client_work(struct work_struct *work) +{ + struct rpc_clnt *clnt = container_of(work, struct rpc_clnt, cl_work); + + /* These might block on processes that might allocate memory, + * so they cannot be called in rpciod, so they are handled separately + * here. + */ + rpc_clnt_debugfs_unregister(clnt); + rpc_clnt_remove_pipedir(clnt); + + kfree(clnt); + rpciod_down(); +} static struct rpc_clnt * rpc_free_client(struct rpc_clnt *clnt) { @@ -890,17 +904,16 @@ rpc_free_client(struct rpc_clnt *clnt) rcu_dereference(clnt->cl_xprt)->servername); if (clnt->cl_parent != clnt) parent = clnt->cl_parent; - rpc_clnt_debugfs_unregister(clnt); - rpc_clnt_remove_pipedir(clnt); rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); clnt->cl_metrics = NULL; xprt_put(rcu_dereference_raw(clnt->cl_xprt)); xprt_iter_destroy(&clnt->cl_xpi); - rpciod_down(); put_cred(clnt->cl_cred); rpc_free_clid(clnt); - kfree(clnt); + + INIT_WORK(&clnt->cl_work, rpc_free_client_work); + schedule_work(&clnt->cl_work); return parent; } @@ -2808,8 +2821,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, task = rpc_call_null_helper(clnt, xprt, NULL, RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS, &rpc_cb_add_xprt_call_ops, data); - if (IS_ERR(task)) - return PTR_ERR(task); + rpc_put_task(task); success: return 1; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 4a81e6995d3e..3c627dc685cc 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -388,7 +388,9 @@ static int rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, } while (nsegs); done: - return xdr_stream_encode_item_absent(xdr); + if (xdr_stream_encode_item_absent(xdr) < 0) + return -EMSGSIZE; + return 0; } /* Register and XDR encode the Write list. Supports encoding a list @@ -454,7 +456,9 @@ static int rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, *segcount = cpu_to_be32(nchunks); done: - return xdr_stream_encode_item_absent(xdr); + if (xdr_stream_encode_item_absent(xdr) < 0) + return -EMSGSIZE; + return 0; } /* Register and XDR encode the Reply chunk. Supports encoding an array @@ -480,8 +484,11 @@ static int rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, int nsegs, nchunks; __be32 *segcount; - if (wtype != rpcrdma_replych) - return xdr_stream_encode_item_absent(xdr); + if (wtype != rpcrdma_replych) { + if (xdr_stream_encode_item_absent(xdr) < 0) + return -EMSGSIZE; + return 0; + } seg = req->rl_segments; nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index cdd84c09df10..05c4d3a9cda2 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -289,6 +289,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: ep->re_connect_status = -ECONNABORTED; disconnected: + xprt_force_disconnect(xprt); return rpcrdma_ep_destroy(ep); default: break; @@ -1355,8 +1356,8 @@ int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) --ep->re_send_count; } + trace_xprtrdma_post_send(req); rc = frwr_send(r_xprt, req); - trace_xprtrdma_post_send(req, rc); if (rc) return -ENOTCONN; return 0; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 3a12fc18239b..73dbed0c4b6b 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -402,10 +402,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); + if (!ret) + return 0; } - if (ret < 0) - tipc_conn_close(con); + tipc_conn_close(con); return ret; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c98e602a1a2d..e23f94a5549b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -800,6 +800,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } + if (psock) + sk_psock_put(sk, psock); return err; } more_data: @@ -2081,8 +2083,9 @@ static void tls_data_ready(struct sock *sk) strp_data_ready(&ctx->strp); psock = sk_psock_get(sk); - if (psock && !list_empty(&psock->ingress_msg)) { - ctx->saved_data_ready(sk); + if (psock) { + if (!list_empty(&psock->ingress_msg)) + ctx->saved_data_ready(sk); sk_psock_put(sk, psock); } } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 709038a4783e..69efc891885f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -157,7 +157,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) { + if (pkt->tap_delivered) + return; + vsock_deliver_tap(virtio_transport_build_skb, pkt); + pkt->tap_delivered = true; } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h index 80b4a70315b6..13a35f7cbe66 100644 --- a/samples/trace_events/trace-events-sample.h +++ b/samples/trace_events/trace-events-sample.h @@ -416,7 +416,7 @@ TRACE_EVENT_FN(foo_bar_with_fn, * Note, TRACE_EVENT() itself is simply defined as: * * #define TRACE_EVENT(name, proto, args, tstruct, assign, printk) \ - * DEFINE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ + * DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ * DEFINE_EVENT(name, name, proto, args) * * The DEFINE_EVENT() also can be declared with conditions and reg functions: diff --git a/scripts/decodecode b/scripts/decodecode index ba8b8d5834e6..fbdb325cdf4f 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo | cut -d" " -f1) - \ faultline=`cat $T.dis | head -1 | cut -d":" -f2-` faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'` -cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" +cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" echo cat $T.aa cleanup diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index f22858b2c3d6..80f354289eeb 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -4,6 +4,7 @@ GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin) HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat +HOST_EXTRACXXFLAGS += -Wno-format-diag $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h quiet_cmd_create_randomize_layout_seed = GENSEED $@ diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 17f06079a712..9ad76b7f3f10 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -35,7 +35,9 @@ #include "ggc.h" #include "timevar.h" +#if BUILDING_GCC_VERSION < 10000 #include "params.h" +#endif #if BUILDING_GCC_VERSION <= 4009 #include "pointer-set.h" @@ -847,6 +849,7 @@ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree l return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT); } +#if BUILDING_GCC_VERSION < 10000 template <> template <> inline bool is_a_helper::test(const_gimple gs) @@ -860,6 +863,7 @@ inline bool is_a_helper::test(const_gimple gs) { return gs->code == GIMPLE_RETURN; } +#endif static inline gasm *as_a_gasm(gimple stmt) { diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index dbd37460c573..cc75eeba0be1 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -51,7 +51,6 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) gimple stmt; gcall *stackleak_track_stack; cgraph_node_ptr node; - int frequency; basic_block bb; /* Insert call to void stackleak_track_stack(void) */ @@ -68,9 +67,9 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) bb = gimple_bb(stackleak_track_stack); node = cgraph_get_create_node(track_function_decl); gcc_assert(node); - frequency = compute_call_stmt_bb_frequency(current_function_decl, bb); cgraph_create_edge(cgraph_get_node(current_function_decl), node, - stackleak_track_stack, bb->count, frequency); + stackleak_track_stack, bb->count, + compute_call_stmt_bb_frequency(current_function_decl, bb)); } static bool is_alloca(gimple stmt) diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py index 39db889b874c..c4b991607917 100644 --- a/scripts/gdb/linux/rbtree.py +++ b/scripts/gdb/linux/rbtree.py @@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node") def rb_first(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) @@ -28,7 +28,7 @@ def rb_first(root): def rb_last(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 3e8dea6e0a95..6dc3078649fa 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -34,7 +34,7 @@ struct sym_entry { unsigned int len; unsigned int start_pos; unsigned int percpu_absolute; - unsigned char sym[0]; + unsigned char sym[]; }; struct addr_range { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 0b4e32161b77..4c037c2545c1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5842,40 +5842,60 @@ static unsigned int selinux_ipv6_postroute(void *priv, static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { - int err = 0; - u32 perm; + int rc = 0; + unsigned int msg_len; + unsigned int data_len = skb->len; + unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security; + u16 sclass = sksec->sclass; + u32 perm; - if (skb->len < NLMSG_HDRLEN) { - err = -EINVAL; - goto out; - } - nlh = nlmsg_hdr(skb); + while (data_len >= nlmsg_total_size(0)) { + nlh = (struct nlmsghdr *)data; - err = selinux_nlmsg_lookup(sksec->sclass, nlh->nlmsg_type, &perm); - if (err) { - if (err == -EINVAL) { + /* NOTE: the nlmsg_len field isn't reliably set by some netlink + * users which means we can't reject skb's with bogus + * length fields; our solution is to follow what + * netlink_rcv_skb() does and simply skip processing at + * messages with length fields that are clearly junk + */ + if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) + return 0; + + rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); + if (rc == 0) { + rc = sock_has_perm(sk, perm); + if (rc) + return rc; + } else if (rc == -EINVAL) { + /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" - " message: protocol=%hu nlmsg_type=%hu sclass=%s" - " pid=%d comm=%s\n", - sk->sk_protocol, nlh->nlmsg_type, - secclass_map[sksec->sclass - 1].name, - task_pid_nr(current), current->comm); - if (!enforcing_enabled(&selinux_state) || - security_get_allow_unknown(&selinux_state)) - err = 0; + " message: protocol=%hu nlmsg_type=%hu sclass=%s" + " pid=%d comm=%s\n", + sk->sk_protocol, nlh->nlmsg_type, + secclass_map[sclass - 1].name, + task_pid_nr(current), current->comm); + if (enforcing_enabled(&selinux_state) && + !security_get_allow_unknown(&selinux_state)) + return rc; + rc = 0; + } else if (rc == -ENOENT) { + /* -ENOENT is a missing socket/class mapping, ignore */ + rc = 0; + } else { + return rc; } - /* Ignore */ - if (err == -ENOENT) - err = 0; - goto out; + /* move to the next message after applying netlink padding */ + msg_len = NLMSG_ALIGN(nlh->nlmsg_len); + if (msg_len >= data_len) + return 0; + data_len -= msg_len; + data += msg_len; } - err = sock_has_perm(sk, perm); -out: - return err; + return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 939a74fd8fb4..da94a1b4bfda 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -429,7 +429,7 @@ int cond_read_list(struct policydb *p, void *fp) p->cond_list = kcalloc(len, sizeof(*p->cond_list), GFP_KERNEL); if (!p->cond_list) - return rc; + return -ENOMEM; rc = avtab_alloc(&(p->te_cond_avtab), p->te_avtab.nel); if (rc) diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c index 59d62f05658f..1545f8fdb4db 100644 --- a/sound/core/oss/pcm_plugin.c +++ b/sound/core/oss/pcm_plugin.c @@ -205,13 +205,14 @@ static snd_pcm_sframes_t calc_dst_frames(struct snd_pcm_substream *plug, plugin = snd_pcm_plug_first(plug); while (plugin && frames > 0) { plugin_next = plugin->next; + if (check_size && plugin->buf_frames && + frames > plugin->buf_frames) + frames = plugin->buf_frames; if (plugin->dst_frames) { frames = plugin->dst_frames(plugin, frames); if (frames < 0) return frames; } - if (check_size && frames > plugin->buf_frames) - frames = plugin->buf_frames; plugin = plugin_next; } return frames; @@ -225,14 +226,15 @@ static snd_pcm_sframes_t calc_src_frames(struct snd_pcm_substream *plug, plugin = snd_pcm_plug_last(plug); while (plugin && frames > 0) { - if (check_size && frames > plugin->buf_frames) - frames = plugin->buf_frames; plugin_prev = plugin->prev; if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames); if (frames < 0) return frames; } + if (check_size && plugin->buf_frames && + frames > plugin->buf_frames) + frames = plugin->buf_frames; plugin = plugin_prev; } return frames; diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c index e764816a8f7a..b039429e6871 100644 --- a/sound/isa/opti9xx/miro.c +++ b/sound/isa/opti9xx/miro.c @@ -867,10 +867,13 @@ static void snd_miro_write(struct snd_miro *chip, unsigned char reg, spin_unlock_irqrestore(&chip->lock, flags); } +static inline void snd_miro_write_mask(struct snd_miro *chip, + unsigned char reg, unsigned char value, unsigned char mask) +{ + unsigned char oldval = snd_miro_read(chip, reg); -#define snd_miro_write_mask(chip, reg, value, mask) \ - snd_miro_write(chip, reg, \ - (snd_miro_read(chip, reg) & ~(mask)) | ((value) & (mask))) + snd_miro_write(chip, reg, (oldval & ~mask) | (value & mask)); +} /* * Proc Interface diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c index d06b29693c85..0e6d20e49158 100644 --- a/sound/isa/opti9xx/opti92x-ad1848.c +++ b/sound/isa/opti9xx/opti92x-ad1848.c @@ -317,10 +317,13 @@ static void snd_opti9xx_write(struct snd_opti9xx *chip, unsigned char reg, } -#define snd_opti9xx_write_mask(chip, reg, value, mask) \ - snd_opti9xx_write(chip, reg, \ - (snd_opti9xx_read(chip, reg) & ~(mask)) | ((value) & (mask))) +static inline void snd_opti9xx_write_mask(struct snd_opti9xx *chip, + unsigned char reg, unsigned char value, unsigned char mask) +{ + unsigned char oldval = snd_opti9xx_read(chip, reg); + snd_opti9xx_write(chip, reg, (oldval & ~mask) | (value & mask)); +} static int snd_opti9xx_configure(struct snd_opti9xx *chip, long port, diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 457a2c065485..0310193ea1bd 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2078,9 +2078,10 @@ static void pcm_mmap_prepare(struct snd_pcm_substream *substream, * some HD-audio PCI entries are exposed without any codecs, and such devices * should be ignored from the beginning. */ -static const struct snd_pci_quirk driver_blacklist[] = { - SND_PCI_QUIRK(0x1462, 0xcb59, "MSI TRX40 Creator", 0), - SND_PCI_QUIRK(0x1462, 0xcb60, "MSI TRX40", 0), +static const struct pci_device_id driver_blacklist[] = { + { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */ + { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */ + { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */ {} }; @@ -2100,7 +2101,7 @@ static int azx_probe(struct pci_dev *pci, bool schedule_probe; int err; - if (snd_pci_quirk_lookup(pci, driver_blacklist)) { + if (pci_match_id(driver_blacklist, pci)) { dev_info(&pci->dev, "Skipping the blacklisted device\n"); return -ENODEV; } diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 4eff16053bd5..93760a3564cf 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1848,8 +1848,10 @@ static bool check_non_pcm_per_cvt(struct hda_codec *codec, hda_nid_t cvt_nid) /* Add sanity check to pass klockwork check. * This should never happen. */ - if (WARN_ON(spdif == NULL)) + if (WARN_ON(spdif == NULL)) { + mutex_unlock(&codec->spdif_mutex); return true; + } non_pcm = !!(spdif->status & IEC958_AES0_NONAUDIO); mutex_unlock(&codec->spdif_mutex); return non_pcm; @@ -2198,7 +2200,9 @@ static int generic_hdmi_build_controls(struct hda_codec *codec) for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) { struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx); + struct hdmi_eld *pin_eld = &per_pin->sink_eld; + pin_eld->eld_valid = false; hdmi_present_sense(per_pin, 0); } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c1a85c8f7b69..c16f63957c5a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7420,6 +7420,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index d37db32ecd3b..e39dc85c355a 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -21,8 +21,7 @@ enum { LINE6_PODHD300, LINE6_PODHD400, - LINE6_PODHD500_0, - LINE6_PODHD500_1, + LINE6_PODHD500, LINE6_PODX3, LINE6_PODX3LIVE, LINE6_PODHD500X, @@ -318,8 +317,7 @@ static const struct usb_device_id podhd_id_table[] = { /* TODO: no need to alloc data interfaces when only audio is used */ { LINE6_DEVICE(0x5057), .driver_info = LINE6_PODHD300 }, { LINE6_DEVICE(0x5058), .driver_info = LINE6_PODHD400 }, - { LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500_0 }, - { LINE6_IF_NUM(0x414D, 1), .driver_info = LINE6_PODHD500_1 }, + { LINE6_IF_NUM(0x414D, 0), .driver_info = LINE6_PODHD500 }, { LINE6_IF_NUM(0x414A, 0), .driver_info = LINE6_PODX3 }, { LINE6_IF_NUM(0x414B, 0), .driver_info = LINE6_PODX3LIVE }, { LINE6_IF_NUM(0x4159, 0), .driver_info = LINE6_PODHD500X }, @@ -352,23 +350,13 @@ static const struct line6_properties podhd_properties_table[] = { .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, - [LINE6_PODHD500_0] = { + [LINE6_PODHD500] = { .id = "PODHD500", .name = "POD HD500", - .capabilities = LINE6_CAP_PCM + .capabilities = LINE6_CAP_PCM | LINE6_CAP_CONTROL | LINE6_CAP_HWMON, .altsetting = 1, - .ep_ctrl_r = 0x81, - .ep_ctrl_w = 0x01, - .ep_audio_r = 0x86, - .ep_audio_w = 0x02, - }, - [LINE6_PODHD500_1] = { - .id = "PODHD500", - .name = "POD HD500", - .capabilities = LINE6_CAP_PCM - | LINE6_CAP_HWMON, - .altsetting = 0, + .ctrl_if = 1, .ep_ctrl_r = 0x81, .ep_ctrl_w = 0x01, .ep_audio_r = 0x86, diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 351ba214a9d3..848a4cc25bed 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1687,7 +1687,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */ case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */ - case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */ + case USB_ID(0x16d0, 0x06b2): /* NuPrime DAC-10 */ case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */ case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */ diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 16b9a420e6fd..001076c51712 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -314,6 +314,7 @@ int apply_xbc(const char *path, const char *xbc_path) ret = delete_xbc(path); if (ret < 0) { pr_err("Failed to delete previous boot config: %d\n", ret); + free(data); return ret; } @@ -321,24 +322,26 @@ int apply_xbc(const char *path, const char *xbc_path) fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { pr_err("Failed to open %s: %d\n", path, fd); + free(data); return fd; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); if (ret < 0) { pr_err("Failed to apply a boot config: %d\n", ret); - return ret; + goto out; } /* Write a magic word of the bootconfig */ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); if (ret < 0) { pr_err("Failed to apply a boot config magic: %d\n", ret); - return ret; + goto out; } +out: close(fd); free(data); - return 0; + return ret; } int usage(void) diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 7427a5ee761b..9d8e9613008a 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -159,7 +159,12 @@ class IocgStat: else: self.inflight_pct = 0 - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + # vdebt used to be an atomic64_t and is now u64, support both + try: + self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + except: + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + self.use_delay = blkg.use_delay.counter.value_() self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4b170fd08a28..3c6da70e6084 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -72,6 +72,17 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, return find_insn(file, func->cfunc->sec, func->cfunc->offset); } +static struct instruction *prev_insn_same_sym(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *prev = list_prev_entry(insn, list); + + if (&prev->list != &file->insn_list && prev->func == insn->func) + return prev; + + return NULL; +} + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn; \ @@ -1050,8 +1061,8 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; - insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + insn && insn->func && insn->func->pfunc == func; + insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) break; @@ -1449,7 +1460,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op; - if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0; /* push */ diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 0b79c2353a21..12e01ac190ec 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -87,9 +87,10 @@ struct elf { #define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) #define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ _offset += OFFSET_STRIDE) static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 11eee0b60040..d979ff14775a 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include #include +#include #include #include #include @@ -3136,4 +3137,149 @@ TEST(epoll59) close(ctx.sfd[0]); } +enum { + EPOLL60_EVENTS_NR = 10, +}; + +struct epoll60_ctx { + volatile int stopped; + int ready; + int waiters; + int epfd; + int evfd[EPOLL60_EVENTS_NR]; +}; + +static void *epoll60_wait_thread(void *ctx_) +{ + struct epoll60_ctx *ctx = ctx_; + struct epoll_event e; + sigset_t sigmask; + uint64_t v; + int ret; + + /* Block SIGUSR1 */ + sigemptyset(&sigmask); + sigaddset(&sigmask, SIGUSR1); + sigprocmask(SIG_SETMASK, &sigmask, NULL); + + /* Prepare empty mask for epoll_pwait() */ + sigemptyset(&sigmask); + + while (!ctx->stopped) { + /* Mark we are ready */ + __atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE); + + /* Start when all are ready */ + while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) && + !ctx->stopped); + + /* Account this waiter */ + __atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE); + + ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask); + if (ret != 1) { + /* We expect only signal delivery on stop */ + assert(ret < 0 && errno == EINTR && "Lost wakeup!\n"); + assert(ctx->stopped); + break; + } + + ret = read(e.data.fd, &v, sizeof(v)); + /* Since we are on ET mode, thus each thread gets its own fd. */ + assert(ret == sizeof(v)); + + __atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE); + } + + return NULL; +} + +static inline unsigned long long msecs(void) +{ + struct timespec ts; + unsigned long long msecs; + + clock_gettime(CLOCK_REALTIME, &ts); + msecs = ts.tv_sec * 1000ull; + msecs += ts.tv_nsec / 1000000ull; + + return msecs; +} + +static inline int count_waiters(struct epoll60_ctx *ctx) +{ + return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE); +} + +TEST(epoll60) +{ + struct epoll60_ctx ctx = { 0 }; + pthread_t waiters[ARRAY_SIZE(ctx.evfd)]; + struct epoll_event e; + int i, n, ret; + + signal(SIGUSR1, signal_handler); + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + + /* Create event fds */ + for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) { + ctx.evfd[i] = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd[i], 0); + + e.events = EPOLLIN | EPOLLET; + e.data.fd = ctx.evfd[i]; + ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0); + } + + /* Create waiter threads */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ASSERT_EQ(pthread_create(&waiters[i], NULL, + epoll60_wait_thread, &ctx), 0); + + for (i = 0; i < 300; i++) { + uint64_t v = 1, ms; + + /* Wait for all to be ready */ + while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) != + ARRAY_SIZE(ctx.evfd)) + ; + + /* Steady, go */ + __atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd), + __ATOMIC_ACQUIRE); + + /* Wait all have gone to kernel */ + while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd)) + ; + + /* 1ms should be enough to schedule away */ + usleep(1000); + + /* Quickly signal all handles at once */ + for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) { + ret = write(ctx.evfd[n], &v, sizeof(v)); + ASSERT_EQ(ret, sizeof(v)); + } + + /* Busy loop for 1s and wait for all waiters to wake up */ + ms = msecs(); + while (count_waiters(&ctx) && msecs() < ms + 1000) + ; + + ASSERT_EQ(count_waiters(&ctx), 0); + } + ctx.stopped = 1; + /* Stop waiters */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ret = pthread_kill(waiters[i], SIGUSR1); + for (i = 0; i < ARRAY_SIZE(waiters); i++) + pthread_join(waiters[i], NULL); + + for (i = 0; i < ARRAY_SIZE(waiters); i++) + close(ctx.evfd[i]); + close(ctx.epfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 063ecb290a5a..a4605b5ee66d 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -17,6 +17,7 @@ echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" echo " --fail-unsupported Treat UNSUPPORTED as a failure" +echo " --fail-unresolved Treat UNRESOLVED as a failure" echo " -d|--debug Debug mode (trace all shell commands)" echo " -l|--logdir Save logs on the " echo " If is -, all logs output in console only" @@ -29,8 +30,25 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# cgroup RT scheduling prevents chrt commands from succeeding, which +# induces failures in test wakeup tests. Disable for the duration of +# the tests. + +readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us + +sched_rt_runtime_orig=$(cat $sched_rt_runtime) + +setup() { + echo -1 > $sched_rt_runtime +} + +cleanup() { + echo $sched_rt_runtime_orig > $sched_rt_runtime +} + errexit() { # message echo "Error: $1" 1>&2 + cleanup exit $err_ret } @@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then errexit "this must be run by root user" fi +setup + # Utilities absdir() { # file_path (cd `dirname $1`; pwd) @@ -93,6 +113,10 @@ parse_opts() { # opts UNSUPPORTED_RESULT=1 shift 1 ;; + --fail-unresolved) + UNRESOLVED_RESULT=1 + shift 1 + ;; --logdir|-l) LOG_DIR=$2 shift 2 @@ -157,6 +181,7 @@ KEEP_LOG=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 +UNRESOLVED_RESULT=0 STOP_FAILURE=0 # Parse command-line options parse_opts $* @@ -235,6 +260,7 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 + testcase() { # testfile CASENO=$((CASENO+1)) desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` @@ -260,7 +286,7 @@ eval_result() { # sigval $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" - return 1 # this is a kind of bug.. something happened. + return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" @@ -273,7 +299,7 @@ eval_result() { # sigval return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) - prlog " [${color_red}XFAIL${color_reset}]" + prlog " [${color_green}XFAIL${color_reset}]" XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; @@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +cleanup + # if no error, return 0 exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc index aefab0c66d54..f59853857ad2 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter-stack.tc @@ -10,10 +10,7 @@ if ! grep -q function_graph available_tracers; then exit_unsupported fi -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is dynamic ftrace not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter do_reset() { if [ -e /proc/sys/kernel/stack_tracer_enabled ]; then diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc index c8a5209f2119..d610f47edd90 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-filter.tc @@ -9,6 +9,8 @@ if ! grep -q function_graph available_tracers; then exit_unsupported fi +check_filter_file set_ftrace_filter + fail() { # msg echo $1 exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index f4e92afab14b..28936f434ee5 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -9,6 +9,8 @@ if ! grep -q function available_tracers; then exit_unsupported fi +check_filter_file set_ftrace_filter + disable_tracing clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc index 8aa46a2ea133..71db68a7975f 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc @@ -15,10 +15,7 @@ if [ ! -f set_ftrace_notrace_pid ]; then exit_unsupported fi -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is function tracer not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter do_function_fork=1 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index f2ee1e889e13..d58403c4b7cd 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -16,10 +16,7 @@ if [ ! -f set_ftrace_pid ]; then exit_unsupported fi -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is function tracer not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter do_function_fork=1 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc index 1a52f2883fe0..b2aff786c1a2 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc @@ -3,7 +3,7 @@ # description: ftrace - stacktrace filter command # flags: instance -[ ! -f set_ftrace_filter ] && exit_unsupported +check_filter_file set_ftrace_filter echo _do_fork:stacktrace >> set_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc index ca2ffd7957f9..e9b1fd534e96 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -11,10 +11,7 @@ # # The triggers are set within the set_ftrace_filter file -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is dynamic ftrace not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter do_reset() { reset_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc index 9330c873f9fe..1a4b4a442d33 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_mod_trace.tc @@ -2,7 +2,7 @@ # SPDX-License-Identifier: GPL-2.0 # description: ftrace - function trace on module -[ ! -f set_ftrace_filter ] && exit_unsupported +check_filter_file set_ftrace_filter : "mod: allows to filter a non exist function" echo 'non_exist_func:mod:non_exist_module' > set_ftrace_filter diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc index dfbae637c60c..a3dadb6b93b4 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_profiler.tc @@ -18,10 +18,7 @@ if ! grep -q function_graph available_tracers; then exit_unsupported; fi -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is dynamic ftrace not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter if [ ! -f function_profile_enabled ]; then echo "function_profile_enabled not found, function profiling enabled?" diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index 51f6e6146bd9..70bad441fa7d 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -10,10 +10,7 @@ # # The triggers are set within the set_ftrace_filter file -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is dynamic ftrace not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter fail() { # mesg echo $1 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc index b414f0e3c646..51e9e80bc0e6 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_stack_tracer.tc @@ -8,6 +8,8 @@ if [ ! -f stack_trace ]; then exit_unsupported fi +check_filter_file stack_trace_filter + echo > stack_trace_filter echo 0 > stack_max_size echo 1 > /proc/sys/kernel/stack_tracer_enabled diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc index 1947387fe976..3ed173f2944a 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -11,10 +11,7 @@ # # The triggers are set within the set_ftrace_filter file -if [ ! -f set_ftrace_filter ]; then - echo "set_ftrace_filter not found? Is dynamic ftrace not set?" - exit_unsupported -fi +check_filter_file set_ftrace_filter fail() { # mesg echo $1 diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 5d4550591ff9..61a3c7e2634d 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -1,3 +1,9 @@ +check_filter_file() { # check filter file introduced by dynamic ftrace + if [ ! -f "$1" ]; then + echo "$1 not found? Is dynamic ftrace not set?" + exit_unsupported + fi +} clear_trace() { # reset trace output echo > trace diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc index 1bcb67dcae26..81490ecaaa92 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc @@ -38,7 +38,7 @@ for width in 64 32 16 8; do echo 0 > events/kprobes/testprobe/enable : "Confirm the arguments is recorded in given types correctly" - ARGS=`grep "testprobe" trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'` + ARGS=`grep "testprobe" trace | head -n 1 | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'` check_types $ARGS $width : "Clear event for next loop" diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc index 7650a82db3f5..df5072815b87 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc @@ -5,6 +5,8 @@ [ -f kprobe_events ] || exit_unsupported # this is configurable grep "function" available_tracers || exit_unsupported # this is configurable +check_filter_file set_ftrace_filter + # prepare echo nop > current_tracer echo _do_fork > set_ftrace_filter diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 0bb80619db58..32bdc978a711 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -1,13 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 -MOUNT_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null) -MOUNT_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null) -ifeq ($(MOUNT_LDLIBS),) -MOUNT_LDLIBS := -lmount -I/usr/include/libmount +VAR_CFLAGS := $(shell pkg-config --cflags mount 2>/dev/null) +VAR_LDLIBS := $(shell pkg-config --libs mount 2>/dev/null) +ifeq ($(VAR_LDLIBS),) +VAR_LDLIBS := -lmount -I/usr/include/libmount endif -CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(MOUNT_CFLAGS) -LDLIBS += $(MOUNT_LDLIBS) +CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ $(VAR_CFLAGS) +LDLIBS += $(VAR_LDLIBS) TEST_PROGS := gpio-mockup.sh TEST_FILES := gpio-mockup-sysfs.sh diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 7340fd6a9a9f..39f0fa2a8fd6 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE -LDLIBS := $(LDLIBS) -lm +LDLIBS += -lm uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) diff --git a/tools/testing/selftests/kselftest_deps.sh b/tools/testing/selftests/kselftest_deps.sh new file mode 100755 index 000000000000..bbc04646346b --- /dev/null +++ b/tools/testing/selftests/kselftest_deps.sh @@ -0,0 +1,272 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# kselftest_deps.sh +# +# Checks for kselftest build dependencies on the build system. +# Copyright (c) 2020 Shuah Khan +# +# + +usage() +{ + +echo -e "Usage: $0 -[p] [test_name]\n" +echo -e "\tkselftest_deps.sh [-p] gcc" +echo -e "\tkselftest_deps.sh [-p] gcc vm" +echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc" +echo -e "\tkselftest_deps.sh [-p] aarch64-linux-gnu-gcc vm\n" +echo "- Should be run in selftests directory in the kernel repo." +echo "- Checks if Kselftests can be built/cross-built on a system." +echo "- Parses all test/sub-test Makefile to find library dependencies." +echo "- Runs compile test on a trivial C file with LDLIBS specified" +echo " in the test Makefiles to identify missing library dependencies." +echo "- Prints suggested target list for a system filtering out tests" +echo " failed the build dependency check from the TARGETS in Selftests" +echo " main Makefile when optional -p is specified." +echo "- Prints pass/fail dependency check for each tests/sub-test." +echo "- Prints pass/fail targets and libraries." +echo "- Default: runs dependency checks on all tests." +echo "- Optional test name can be specified to check dependencies for it." +exit 1 + +} + +# Start main() +main() +{ + +base_dir=`pwd` +# Make sure we're in the selftests top-level directory. +if [ $(basename "$base_dir") != "selftests" ]; then + echo -e "\tPlease run $0 in" + echo -e "\ttools/testing/selftests directory ..." + exit 1 +fi + +print_targets=0 + +while getopts "p" arg; do + case $arg in + p) + print_targets=1 + shift;; + esac +done + +if [ $# -eq 0 ] +then + usage +fi + +# Compiler +CC=$1 + +tmp_file=$(mktemp).c +trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT +#echo $tmp_file + +pass=$(mktemp).out +trap "rm -f $pass" EXIT +#echo $pass + +fail=$(mktemp).out +trap "rm -f $fail" EXIT +#echo $fail + +# Generate tmp source fire for compile test +cat << "EOF" > $tmp_file +int main() +{ +} +EOF + +# Save results +total_cnt=0 +fail_trgts=() +fail_libs=() +fail_cnt=0 +pass_trgts=() +pass_libs=() +pass_cnt=0 + +# Get all TARGETS from selftests Makefile +targets=$(egrep "^TARGETS +|^TARGETS =" Makefile | cut -d "=" -f2) + +# Single test case +if [ $# -eq 2 ] +then + test=$2/Makefile + + l1_test $test + l2_test $test + l3_test $test + + print_results $1 $2 + exit $? +fi + +# Level 1: LDLIBS set static. +# +# Find all LDLIBS set statically for all executables built by a Makefile +# and filter out VAR_LDLIBS to discard the following: +# gpio/Makefile:LDLIBS += $(VAR_LDLIBS) +# Append space at the end of the list to append more tests. + +l1_tests=$(grep -r --include=Makefile "^LDLIBS" | \ + grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + +# Level 2: LDLIBS set dynamically. +# +# Level 2 +# Some tests have multiple valid LDLIBS lines for individual sub-tests +# that need dependency checks. Find them and append them to the tests +# e.g: vm/Makefile:$(OUTPUT)/userfaultfd: LDLIBS += -lpthread +# Filter out VAR_LDLIBS to discard the following: +# memfd/Makefile:$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) +# Append space at the end of the list to append more tests. + +l2_tests=$(grep -r --include=Makefile ": LDLIBS" | \ + grep -v "VAR_LDLIBS" | awk -F: '{print $1}') + +# Level 3 +# gpio, memfd and others use pkg-config to find mount and fuse libs +# respectively and save it in VAR_LDLIBS. If pkg-config doesn't find +# any, VAR_LDLIBS set to default. +# Use the default value and filter out pkg-config for dependency check. +# e.g: +# gpio/Makefile +# VAR_LDLIBS := $(shell pkg-config --libs mount) 2>/dev/null) +# memfd/Makefile +# VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null) + +l3_tests=$(grep -r --include=Makefile "^VAR_LDLIBS" | \ + grep -v "pkg-config" | awk -F: '{print $1}') + +#echo $l1_tests +#echo $l2_1_tests +#echo $l3_tests + +all_tests +print_results $1 $2 + +exit $? +} +# end main() + +all_tests() +{ + for test in $l1_tests; do + l1_test $test + done + + for test in $l2_tests; do + l2_test $test + done + + for test in $l3_tests; do + l3_test $test + done +} + +# Use same parsing used for l1_tests and pick libraries this time. +l1_test() +{ + test_libs=$(grep --include=Makefile "^LDLIBS" $test | \ + grep -v "VAR_LDLIBS" | \ + sed -e 's/\:/ /' | \ + sed -e 's/+/ /' | cut -d "=" -f 2) + + check_libs $test $test_libs +} + +# Use same parsing used for l2__tests and pick libraries this time. +l2_test() +{ + test_libs=$(grep --include=Makefile ": LDLIBS" $test | \ + grep -v "VAR_LDLIBS" | \ + sed -e 's/\:/ /' | sed -e 's/+/ /' | \ + cut -d "=" -f 2) + + check_libs $test $test_libs +} + +l3_test() +{ + test_libs=$(grep --include=Makefile "^VAR_LDLIBS" $test | \ + grep -v "pkg-config" | sed -e 's/\:/ /' | + sed -e 's/+/ /' | cut -d "=" -f 2) + + check_libs $test $test_libs +} + +check_libs() +{ + +if [[ ! -z "${test_libs// }" ]] +then + + #echo $test_libs + + for lib in $test_libs; do + + let total_cnt+=1 + $CC -o $tmp_file.bin $lib $tmp_file > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "FAIL: $test dependency check: $lib" >> $fail + let fail_cnt+=1 + fail_libs+="$lib " + fail_target=$(echo "$test" | cut -d "/" -f1) + fail_trgts+="$fail_target " + targets=$(echo "$targets" | grep -v "$fail_target") + else + echo "PASS: $test dependency check passed $lib" >> $pass + let pass_cnt+=1 + pass_libs+="$lib " + pass_trgts+="$(echo "$test" | cut -d "/" -f1) " + fi + + done +fi +} + +print_results() +{ + echo -e "========================================================"; + echo -e "Kselftest Dependency Check for [$0 $1 $2] results..." + + if [ $print_targets -ne 0 ] + then + echo -e "Suggested Selftest Targets for your configuration:" + echo -e "$targets"; + fi + + echo -e "========================================================"; + echo -e "Checked tests defining LDLIBS dependencies" + echo -e "--------------------------------------------------------"; + echo -e "Total tests with Dependencies:" + echo -e "$total_cnt Pass: $pass_cnt Fail: $fail_cnt"; + + if [ $pass_cnt -ne 0 ]; then + echo -e "--------------------------------------------------------"; + cat $pass + echo -e "--------------------------------------------------------"; + echo -e "Targets passed build dependency check on system:" + echo -e "$(echo "$pass_trgts" | xargs -n1 | sort -u | xargs)" + fi + + if [ $fail_cnt -ne 0 ]; then + echo -e "--------------------------------------------------------"; + cat $fail + echo -e "--------------------------------------------------------"; + echo -e "Targets failed build dependency check on system:" + echo -e "$(echo "$fail_trgts" | xargs -n1 | sort -u | xargs)" + echo -e "--------------------------------------------------------"; + echo -e "Missing libraries system" + echo -e "$(echo "$fail_libs" | xargs -n1 | sort -u | xargs)" + fi + + echo -e "--------------------------------------------------------"; + echo -e "========================================================"; +} + +main "$@" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 712a2ddd2a27..b728c0a0f9b2 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -5,8 +5,34 @@ all: top_srcdir = ../../../.. KSFT_KHDR_INSTALL := 1 + +# For cross-builds to work, UNAME_M has to map to ARCH and arch specific +# directories and targets in this Makefile. "uname -m" doesn't map to +# arch specific sub-directory names. +# +# UNAME_M variable to used to run the compiles pointing to the right arch +# directories and build the right targets for these supported architectures. +# +# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. +# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. +# +# x86_64 targets are named to include x86_64 as a suffix and directories +# for includes are in x86_64 sub-directory. s390x and aarch64 follow the +# same convention. "uname -m" doesn't result in the correct mapping for +# s390x and aarch64. +# +# No change necessary for x86_64 UNAME_M := $(shell uname -m) +# Set UNAME_M for arm64 compile/install to work +ifeq ($(ARCH),arm64) + UNAME_M := aarch64 +endif +# Set UNAME_M s390x compile/install to work +ifeq ($(ARCH),s390) + UNAME_M := s390x +endif + LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c @@ -53,7 +79,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ @@ -84,6 +110,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ +x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index d8f4d6bfe05d..a034438b6266 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -219,8 +219,8 @@ struct hv_enlightened_vmcs { #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) -struct hv_enlightened_vmcs *current_evmcs; -struct hv_vp_assist_page *current_vp_assist; +extern struct hv_enlightened_vmcs *current_evmcs; +extern struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 6f17f69394be..4ae104f6ce69 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -17,6 +17,9 @@ bool enable_evmcs; +struct hv_enlightened_vmcs *current_evmcs; +struct hv_vp_assist_page *current_vp_assist; + struct eptPageTableEntry { uint64_t readable:1; uint64_t writable:1; diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index 187b14cad00c..4da8b565fa32 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -8,11 +8,21 @@ TEST_GEN_PROGS := memfd_test TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh TEST_GEN_FILES := fuse_test fuse_mnt -fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) +VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null) +ifeq ($(VAR_CFLAGS),) +VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse +endif + +VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null) +ifeq ($(VAR_LDLIBS),) +VAR_LDLIBS := -lfuse -pthread +endif + +fuse_mnt.o: CFLAGS += $(VAR_CFLAGS) include ../lib.mk -$(OUTPUT)/fuse_mnt: LDLIBS += $(shell pkg-config fuse --libs) +$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) $(OUTPUT)/memfd_test: memfd_test.c common.c $(OUTPUT)/fuse_test: fuse_test.c common.c diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 35505b31e5cc..4555f88252ba 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -165,9 +165,10 @@ void *child_thread(void *arg) socklen_t zc_len = sizeof(zc); int res; + memset(&zc, 0, sizeof(zc)); zc.address = (__u64)((unsigned long)addr); zc.length = chunk_size; - zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, &zc, &zc_len); if (res == -1) @@ -281,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr, static void do_accept(int fdlisten) { pthread_attr_t attr; + int rcvlowat; pthread_attr_init(&attr); pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + rcvlowat = chunk_size; if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, - &chunk_size, sizeof(chunk_size)) == -1) { + &rcvlowat, sizeof(rcvlowat)) == -1) { perror("setsockopt SO_RCVLOWAT"); } diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 936e1ca9410e..17a1f53ceba0 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -48,8 +48,11 @@ cleanup() { exec 2>/dev/null printf "$orig_message_cost" > /proc/sys/net/core/message_cost ip0 link del dev wg0 + ip0 link del dev wg1 ip1 link del dev wg0 + ip1 link del dev wg1 ip2 link del dev wg0 + ip2 link del dev wg1 local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" [[ -n $to_kill ]] && kill $to_kill pp ip netns del $netns1 @@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2 key1="$(pp wg genkey)" key2="$(pp wg genkey)" key3="$(pp wg genkey)" +key4="$(pp wg genkey)" pub1="$(pp wg pubkey <<<"$key1")" pub2="$(pp wg pubkey <<<"$key2")" pub3="$(pp wg pubkey <<<"$key3")" +pub4="$(pp wg pubkey <<<"$key4")" psk="$(pp wg genpsk)" [[ -n $key1 && -n $key2 && -n $psk ]] configure_peers() { ip1 addr add 192.168.241.1/24 dev wg0 - ip1 addr add fd00::1/24 dev wg0 + ip1 addr add fd00::1/112 dev wg0 ip2 addr add 192.168.241.2/24 dev wg0 - ip2 addr add fd00::2/24 dev wg0 + ip2 addr add fd00::2/112 dev wg0 n1 wg set wg0 \ private-key <(echo "$key1") \ @@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 private-key <(echo "$key3") n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove n1 ping -W 1 -c 1 192.168.241.2 +n2 wg set wg0 peer "$pub3" remove -ip1 link del wg0 +# Test that we can route wg through wg +ip1 addr flush dev wg0 +ip2 addr flush dev wg0 +ip1 addr add fd00::5:1/112 dev wg0 +ip2 addr add fd00::5:2/112 dev wg0 +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998 +ip1 link add wg1 type wireguard +ip2 link add wg1 type wireguard +ip1 addr add 192.168.241.1/24 dev wg1 +ip1 addr add fd00::1/112 dev wg1 +ip2 addr add 192.168.241.2/24 dev wg1 +ip2 addr add fd00::2/112 dev wg1 +ip1 link set mtu 1340 up dev wg1 +ip2 link set mtu 1340 up dev wg1 +n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5 +n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5 +tests +# Try to set up a routing loop between the two namespaces +ip1 link set netns $netns0 dev wg1 +ip0 addr add 192.168.241.1/24 dev wg1 +ip0 link set up dev wg1 +n0 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 ip2 link del wg0 +ip2 link del wg1 +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel + +ip0 link del wg1 +ip1 link del wg0 # Test using NAT. We now change the topology to this: # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ @@ -282,6 +316,20 @@ pp sleep 3 n2 ping -W 1 -c 1 192.168.241.1 n1 wg set wg0 peer "$pub2" persistent-keepalive 0 +# Test that onion routing works, even when it loops +n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 +ip1 addr add 192.168.242.1/24 dev wg0 +ip2 link add wg1 type wireguard +ip2 addr add 192.168.242.2/24 dev wg1 +n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32 +ip2 link set wg1 up +n1 ping -W 1 -c 1 192.168.242.2 +ip2 link del wg1 +n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5 +! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel +n1 wg set wg0 peer "$pub3" remove +ip1 addr del 192.168.242.1/24 dev wg0 + # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. ip1 -6 addr add fc00::9/96 dev vethc ip1 -6 route add default via fc00::1 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config index 990c510a9cfa..f52f1e2bc7f6 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 +CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 5909e7ef2a5c..9803dbb54181 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -25,7 +25,6 @@ CONFIG_KASAN=y CONFIG_KASAN_INLINE=y CONFIG_UBSAN=y CONFIG_UBSAN_SANITIZE_ALL=y -CONFIG_UBSAN_NO_ALIGNMENT=y CONFIG_UBSAN_NULL=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 14a162e295a9..ae364716ee40 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -186,6 +186,33 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); } +static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) +{ + int i; + + /* + * Zero the input registers' upper 32 bits. They will be fully + * zeroed on exit, so we're fine changing them in place. + */ + for (i = 1; i < 4; i++) + vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); +} + +static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) +{ + switch(fn) { + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN64_AFFINITY_INFO: + /* Disallow these functions for 32bit guests */ + if (vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; + break; + } + + return 0; +} + static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; @@ -193,6 +220,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) + goto out; + switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -210,12 +241,16 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_CPU_ON: mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; @@ -256,6 +291,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } +out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -273,6 +309,10 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) break; case PSCI_1_0_FN_PSCI_FEATURES: feature = smccc_get_arg1(vcpu); + val = kvm_psci_check_allowed_function(vcpu, feature); + if (val) + break; + switch(feature) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index a963b9d766b7..32e32d67a127 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -294,8 +294,15 @@ int vgic_init(struct kvm *kvm) } } - if (vgic_has_its(kvm)) { + if (vgic_has_its(kvm)) vgic_lpi_translation_cache_init(kvm); + + /* + * If we have GICv4.1 enabled, unconditionnaly request enable the + * v4 support so that we get HW-accelerated vSGIs. Otherwise, only + * enable it if we present a virtual ITS to the guest. + */ + if (vgic_supports_direct_msis(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; @@ -348,6 +355,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); } @@ -359,10 +372,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm) vgic_debug_destroy(kvm); - kvm_vgic_dist_destroy(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); } void kvm_vgic_destroy(struct kvm *kvm) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index d53d34a33e35..c012a52b19f5 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -96,14 +96,21 @@ out_unlock: * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } return irq; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 5945f062d749..a016f07adc28 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -409,24 +409,28 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { NULL, vgic_mmio_uaccess_write_v2_group, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index e72dcc454247..89a14ec8b33b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -50,7 +50,8 @@ bool vgic_has_its(struct kvm *kvm) bool vgic_supports_direct_msis(struct kvm *kvm) { - return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm); + return (kvm_vgic_global_state.has_gicv4_1 || + (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); } /* @@ -538,10 +539,12 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -553,11 +556,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, @@ -609,11 +612,13 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_senable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_cenable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -625,12 +630,12 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 2199302597fa..b2d73fc0d1ef 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -184,6 +184,48 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, } } +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -219,17 +261,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->pending_latch = true; - vgic_irq_set_phys_active(irq, true); -} - static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && @@ -240,7 +271,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -270,22 +300,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, continue; } + irq->pending_latch = true; if (irq->hw) - vgic_hw_irq_spending(vcpu, irq, is_uaccess); - else - irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (is_uaccess) - return; + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ irq->pending_latch = false; /* @@ -308,7 +364,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -339,7 +394,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; @@ -348,8 +403,68 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } } -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -359,6 +474,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ if (irq->active) value |= (1U << i); @@ -368,6 +487,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) @@ -426,36 +568,6 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts, we have to stop all the VCPUs because interrupts can - * be migrated while we don't hold the IRQ locks and we don't want to be - * chasing moving targets. - * - * For private interrupts we don't have to do anything because userspace - * accesses to the VGIC state already require all VCPUs to be stopped, and - * only the VCPU itself can modify its private interrupts active state, which - * guarantees that the VCPU is not running. - */ -static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} - -/* See vgic_change_active_prepare */ -static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); -} - static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) @@ -477,11 +589,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } @@ -514,11 +626,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 5af2aefad435..fefcca2b14dc 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -138,6 +138,14 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); @@ -149,9 +157,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val);