From afce0cc9ad8aa510650e781a51e43c26e2a34cf6 Mon Sep 17 00:00:00 2001 From: Julien Grall Date: Tue, 14 Aug 2018 11:33:32 +0100 Subject: [PATCH 1/4] Documentation/arm64/sve: Couple of improvements and typos - Fix mismatch between SVE registers (Z) and FPSIMD register (V) - Don't prefix the path for [3] with Linux to stay consistent with [1] and [2]. Signed-off-by: Julien Grall Signed-off-by: Will Deacon --- Documentation/arm64/sve.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt index f128f736b4a5..7169a0ec41d8 100644 --- a/Documentation/arm64/sve.txt +++ b/Documentation/arm64/sve.txt @@ -200,7 +200,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg) thread. * Changing the vector length causes all of P0..P15, FFR and all bits of - Z0..V31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become unspecified. Calling PR_SVE_SET_VL with vl equal to the thread's current vector length, or calling PR_SVE_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. @@ -500,7 +500,7 @@ References [2] arch/arm64/include/uapi/asm/ptrace.h AArch64 Linux ptrace ABI definitions -[3] linux/Documentation/arm64/cpu-feature-registers.txt +[3] Documentation/arm64/cpu-feature-registers.txt [4] ARM IHI0055C http://infocenter.arm.com/help/topic/com.arm.doc.ihi0055c/IHI0055C_beta_aapcs64.pdf From 1d8f574708a3fb6f18c85486d0c5217df893c0cf Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 24 Aug 2018 15:08:29 +0100 Subject: [PATCH 2/4] arm/arm64: smccc-1.1: Make return values unsigned long An unfortunate consequence of having a strong typing for the input values to the SMC call is that it also affects the type of the return values, limiting r0 to 32 bits and r{1,2,3} to whatever was passed as an input. Let's turn everything into "unsigned long", which satisfies the requirements of both architectures, and allows for the full range of return values. Reported-by: Julien Grall Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index ca1d2cc2cdfa..5a91ff33720b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -199,31 +199,31 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __declare_arg_0(a0, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ + register unsigned long r0 asm("r0") = (u32)a0; \ register unsigned long r1 asm("r1"); \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_1(a0, a1, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_2(a0, a1, a2, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ + register unsigned long r2 asm("r2") = a2; \ register unsigned long r3 asm("r3") #define __declare_arg_3(a0, a1, a2, a3, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ - register typeof(a3) r3 asm("r3") = a3 + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = a1; \ + register unsigned long r2 asm("r2") = a2; \ + register unsigned long r3 asm("r3") = a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ __declare_arg_3(a0, a1, a2, a3, res); \ From 755a8bf5579d22eb5636685c516d8dede799e27b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 24 Aug 2018 15:08:30 +0100 Subject: [PATCH 3/4] arm/arm64: smccc-1.1: Handle function result as parameters If someone has the silly idea to write something along those lines: extern u64 foo(void); void bar(struct arm_smccc_res *res) { arm_smccc_1_1_smc(0xbad, foo(), res); } they are in for a surprise, as this gets compiled as: 0000000000000588 : 588: a9be7bfd stp x29, x30, [sp, #-32]! 58c: 910003fd mov x29, sp 590: f9000bf3 str x19, [sp, #16] 594: aa0003f3 mov x19, x0 598: aa1e03e0 mov x0, x30 59c: 94000000 bl 0 <_mcount> 5a0: 94000000 bl 0 5a4: aa0003e1 mov x1, x0 5a8: d4000003 smc #0x0 5ac: b4000073 cbz x19, 5b8 5b0: a9000660 stp x0, x1, [x19] 5b4: a9010e62 stp x2, x3, [x19, #16] 5b8: f9400bf3 ldr x19, [sp, #16] 5bc: a8c27bfd ldp x29, x30, [sp], #32 5c0: d65f03c0 ret 5c4: d503201f nop The call to foo "overwrites" the x0 register for the return value, and we end up calling the wrong secure service. A solution is to evaluate all the parameters before assigning anything to specific registers, leading to the expected result: 0000000000000588 : 588: a9be7bfd stp x29, x30, [sp, #-32]! 58c: 910003fd mov x29, sp 590: f9000bf3 str x19, [sp, #16] 594: aa0003f3 mov x19, x0 598: aa1e03e0 mov x0, x30 59c: 94000000 bl 0 <_mcount> 5a0: 94000000 bl 0 5a4: aa0003e1 mov x1, x0 5a8: d28175a0 mov x0, #0xbad 5ac: d4000003 smc #0x0 5b0: b4000073 cbz x19, 5bc 5b4: a9000660 stp x0, x1, [x19] 5b8: a9010e62 stp x2, x3, [x19, #16] 5bc: f9400bf3 ldr x19, [sp, #16] 5c0: a8c27bfd ldp x29, x30, [sp], #32 5c4: d65f03c0 ret Reported-by: Julien Grall Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 5a91ff33720b..18863d56273c 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -205,41 +205,51 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3") #define __declare_arg_1(a0, a1, res) \ + typeof(a1) __a1 = a1; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ + register unsigned long r1 asm("r1") = __a1; \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_2(a0, a1, a2, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ - register unsigned long r2 asm("r2") = a2; \ + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ register unsigned long r3 asm("r3") #define __declare_arg_3(a0, a1, a2, a3, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ + typeof(a3) __a3 = a3; \ struct arm_smccc_res *___res = res; \ register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = a1; \ - register unsigned long r2 asm("r2") = a2; \ - register unsigned long r3 asm("r3") = a3 + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ + register unsigned long r3 asm("r3") = __a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ + typeof(a4) __a4 = a4; \ __declare_arg_3(a0, a1, a2, a3, res); \ - register typeof(a4) r4 asm("r4") = a4 + register unsigned long r4 asm("r4") = __a4 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ + typeof(a5) __a5 = a5; \ __declare_arg_4(a0, a1, a2, a3, a4, res); \ - register typeof(a5) r5 asm("r5") = a5 + register unsigned long r5 asm("r5") = __a5 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ + typeof(a6) __a6 = a6; \ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ - register typeof(a6) r6 asm("r6") = a6 + register unsigned long r6 asm("r6") = __a6 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ + typeof(a7) __a7 = a7; \ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ - register typeof(a7) r7 asm("r7") = a7 + register unsigned long r7 asm("r7") = __a7 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) #define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) From f52bb98f5aded4c43e52f5ce19fb83f7261e9e73 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 30 Aug 2018 16:05:32 +0100 Subject: [PATCH 4/4] arm64: mm: always enable CONFIG_HOLES_IN_ZONE Commit 6d526ee26ccd ("arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA") only enabled HOLES_IN_ZONE for NUMA systems because the NUMA code was choking on the missing zone for nomap pages. This problem doesn't just apply to NUMA systems. If the architecture doesn't set HAVE_ARCH_PFN_VALID, pfn_valid() will return true if the pfn is part of a valid sparsemem section. When working with multiple pages, the mm code uses pfn_valid_within() to test each page it uses within the sparsemem section is valid. On most systems memory comes in MAX_ORDER_NR_PAGES chunks which all have valid/initialised struct pages. In this case pfn_valid_within() is optimised out. Systems where this isn't true (e.g. due to nomap) should set HOLES_IN_ZONE and provide HAVE_ARCH_PFN_VALID so that mm tests each page as it works with it. Currently non-NUMA arm64 systems can't enable HOLES_IN_ZONE, leading to a VM_BUG_ON(): | page:fffffdff802e1780 is uninitialized and poisoned | raw: ffffffffffffffff ffffffffffffffff ffffffffffffffff ffffffffffffffff | raw: ffffffffffffffff ffffffffffffffff ffffffffffffffff ffffffffffffffff | page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) | ------------[ cut here ]------------ | kernel BUG at include/linux/mm.h:978! | Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [...] | CPU: 1 PID: 25236 Comm: dd Not tainted 4.18.0 #7 | Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 | pstate: 40000085 (nZcv daIf -PAN -UAO) | pc : move_freepages_block+0x144/0x248 | lr : move_freepages_block+0x144/0x248 | sp : fffffe0071177680 [...] | Process dd (pid: 25236, stack limit = 0x0000000094cc07fb) | Call trace: | move_freepages_block+0x144/0x248 | steal_suitable_fallback+0x100/0x16c | get_page_from_freelist+0x440/0xb20 | __alloc_pages_nodemask+0xe8/0x838 | new_slab+0xd4/0x418 | ___slab_alloc.constprop.27+0x380/0x4a8 | __slab_alloc.isra.21.constprop.26+0x24/0x34 | kmem_cache_alloc+0xa8/0x180 | alloc_buffer_head+0x1c/0x90 | alloc_page_buffers+0x68/0xb0 | create_empty_buffers+0x20/0x1ec | create_page_buffers+0xb0/0xf0 | __block_write_begin_int+0xc4/0x564 | __block_write_begin+0x10/0x18 | block_write_begin+0x48/0xd0 | blkdev_write_begin+0x28/0x30 | generic_perform_write+0x98/0x16c | __generic_file_write_iter+0x138/0x168 | blkdev_write_iter+0x80/0xf0 | __vfs_write+0xe4/0x10c | vfs_write+0xb4/0x168 | ksys_write+0x44/0x88 | sys_write+0xc/0x14 | el0_svc_naked+0x30/0x34 | Code: aa1303e0 90001a01 91296421 94008902 (d4210000) | ---[ end trace 1601ba47f6e883fe ]--- Remove the NUMA dependency. Link: https://www.spinics.net/lists/arm-kernel/msg671851.html Cc: Cc: Ard Biesheuvel Reported-by: Mikulas Patocka Reviewed-by: Pavel Tatashin Tested-by: Mikulas Patocka Signed-off-by: James Morse Signed-off-by: Will Deacon --- arch/arm64/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 29e75b47becd..1b1a0e95c751 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -763,7 +763,6 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK config HOLES_IN_ZONE def_bool y - depends on NUMA source kernel/Kconfig.hz