From: Tony Luck <tony.luck@intel.com> To: Ingo Molnar <mingo@kernel.org> Cc: Borislav Petkov <bp@alien8.de>, Andrew Morton <akpm@linux-foundation.org>, Andy Lutomirski <luto@kernel.org>, Dan Williams <dan.j.williams@intel.com>, <elliott@hpe.com>, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-nvdimm@ml01.01.org, x86@kernel.org Subject: [PATCHV4 3/3] x86, ras: Add __mcsafe_copy() function to recover from machine checks Date: Tue, 15 Dec 2015 17:30:49 -0800 [thread overview] Message-ID: <a27752f2ac16e47b1a365c5c3cc870bd87ff0366.1450990481.git.tony.luck@intel.com> (raw) In-Reply-To: <cover.1450990481.git.tony.luck@intel.com> Using __copy_user_nocache() as inspiration create a memory copy routine for use by kernel code with annotations to allow for recovery from machine checks. Notes: 1) We align the source address rather than the destination. This means we never have to deal with a memory read that spans two cache lines ... so we can provide a precise indication of where the error occurred without having to re-execute at a byte-by-byte level to find the exact spot like the original did. 2) We 'or' BIT(63) into the return because this is the first in a series of machine check safe functions. Some will copy from user addresses, so may need to indicate an invalid user address instead of a machine check. 3) This code doesn't play any cache games. Future functions can use non-temporal loads/stores to meet needs of different callers. 4) Provide helpful macros to decode the return value. Signed-off-by: Tony Luck <tony.luck@intel.com> --- arch/x86/include/asm/string_64.h | 8 +++ arch/x86/kernel/x8664_ksyms_64.c | 4 ++ arch/x86/lib/memcpy_64.S | 133 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 145 insertions(+) diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index ff8b9a17dc4b..4359ebb86b86 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -78,6 +78,14 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +#ifdef CONFIG_MCE_KERNEL_RECOVERY +u64 __mcsafe_copy(void *dst, const void __user *src, unsigned size); + +#define COPY_MCHECK_ERRBIT BIT(63) +#define COPY_HAD_MCHECK(ret) ((ret) & COPY_MCHECK_ERRBIT) +#define COPY_MCHECK_REMAIN(ret) ((ret) & ~COPY_MCHECK_ERRBIT) +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a0695be19864..3d42d0ef3333 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -37,6 +37,10 @@ EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); +#ifdef CONFIG_MCE_KERNEL_RECOVERY +EXPORT_SYMBOL(__mcsafe_copy); +#endif + EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 16698bba87de..bef21b18f6f5 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -177,3 +177,136 @@ ENTRY(memcpy_orig) .Lend: retq ENDPROC(memcpy_orig) + +#ifdef CONFIG_MCE_KERNEL_RECOVERY +/* + * __mcsafe_copy - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(__mcsafe_copy) + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + + /* check for bad alignment of source */ + movl %esi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +0: movb (%rsi),%al + movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 0b +102: + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 + mov %r8,(%rdi) + mov %r9,1*8(%rdi) + mov %r10,2*8(%rdi) + mov %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 + mov %r8,4*8(%rdi) + mov %r9,5*8(%rdi) + mov %r10,6*8(%rdi) + mov %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %ecx + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 + mov %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al + movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xorl %eax,%eax + sfence + ret + + .section .fixup,"ax" +30: + addl %ecx,%edx + jmp 100f +31: + shll $6,%ecx + addl %ecx,%edx + jmp 100f +32: + shll $6,%ecx + leal -8(%ecx,%edx),%edx + jmp 100f +33: + shll $6,%ecx + leal -16(%ecx,%edx),%edx + jmp 100f +34: + shll $6,%ecx + leal -24(%ecx,%edx),%edx + jmp 100f +35: + shll $6,%ecx + leal -32(%ecx,%edx),%edx + jmp 100f +36: + shll $6,%ecx + leal -40(%ecx,%edx),%edx + jmp 100f +37: + shll $6,%ecx + leal -48(%ecx,%edx),%edx + jmp 100f +38: + shll $6,%ecx + leal -56(%ecx,%edx),%edx + jmp 100f +39: + lea (%rdx,%rcx,8),%rdx + jmp 100f +40: + mov %ecx,%edx +100: + sfence + mov %edx,%eax + bts $63,%rax + ret + .previous + + _ASM_MCEXTABLE(0b,30b) + _ASM_MCEXTABLE(1b,31b) + _ASM_MCEXTABLE(2b,32b) + _ASM_MCEXTABLE(3b,33b) + _ASM_MCEXTABLE(4b,34b) + _ASM_MCEXTABLE(9b,35b) + _ASM_MCEXTABLE(10b,36b) + _ASM_MCEXTABLE(11b,37b) + _ASM_MCEXTABLE(12b,38b) + _ASM_MCEXTABLE(18b,39b) + _ASM_MCEXTABLE(21b,40b) +ENDPROC(__mcsafe_copy) +#endif -- 2.1.4
WARNING: multiple messages have this Message-ID (diff)
From: Tony Luck <tony.luck@intel.com> To: Ingo Molnar <mingo@kernel.org> Cc: Borislav Petkov <bp@alien8.de>, Andrew Morton <akpm@linux-foundation.org>, Andy Lutomirski <luto@kernel.org>, Dan Williams <dan.j.williams@intel.com>, elliott@hpe.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-nvdimm@ml01.01.org, x86@kernel.org Subject: [PATCHV4 3/3] x86, ras: Add __mcsafe_copy() function to recover from machine checks Date: Tue, 15 Dec 2015 17:30:49 -0800 [thread overview] Message-ID: <a27752f2ac16e47b1a365c5c3cc870bd87ff0366.1450990481.git.tony.luck@intel.com> (raw) In-Reply-To: <cover.1450990481.git.tony.luck@intel.com> Using __copy_user_nocache() as inspiration create a memory copy routine for use by kernel code with annotations to allow for recovery from machine checks. Notes: 1) We align the source address rather than the destination. This means we never have to deal with a memory read that spans two cache lines ... so we can provide a precise indication of where the error occurred without having to re-execute at a byte-by-byte level to find the exact spot like the original did. 2) We 'or' BIT(63) into the return because this is the first in a series of machine check safe functions. Some will copy from user addresses, so may need to indicate an invalid user address instead of a machine check. 3) This code doesn't play any cache games. Future functions can use non-temporal loads/stores to meet needs of different callers. 4) Provide helpful macros to decode the return value. Signed-off-by: Tony Luck <tony.luck@intel.com> --- arch/x86/include/asm/string_64.h | 8 +++ arch/x86/kernel/x8664_ksyms_64.c | 4 ++ arch/x86/lib/memcpy_64.S | 133 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 145 insertions(+) diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index ff8b9a17dc4b..4359ebb86b86 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -78,6 +78,14 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +#ifdef CONFIG_MCE_KERNEL_RECOVERY +u64 __mcsafe_copy(void *dst, const void __user *src, unsigned size); + +#define COPY_MCHECK_ERRBIT BIT(63) +#define COPY_HAD_MCHECK(ret) ((ret) & COPY_MCHECK_ERRBIT) +#define COPY_MCHECK_REMAIN(ret) ((ret) & ~COPY_MCHECK_ERRBIT) +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a0695be19864..3d42d0ef3333 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -37,6 +37,10 @@ EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); +#ifdef CONFIG_MCE_KERNEL_RECOVERY +EXPORT_SYMBOL(__mcsafe_copy); +#endif + EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 16698bba87de..bef21b18f6f5 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -177,3 +177,136 @@ ENTRY(memcpy_orig) .Lend: retq ENDPROC(memcpy_orig) + +#ifdef CONFIG_MCE_KERNEL_RECOVERY +/* + * __mcsafe_copy - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(__mcsafe_copy) + cmpl $8,%edx + jb 20f /* less then 8 bytes, go to byte copy loop */ + + /* check for bad alignment of source */ + movl %esi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +0: movb (%rsi),%al + movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 0b +102: + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz 17f +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 + mov %r8,(%rdi) + mov %r9,1*8(%rdi) + mov %r10,2*8(%rdi) + mov %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 + mov %r8,4*8(%rdi) + mov %r9,5*8(%rdi) + mov %r10,6*8(%rdi) + mov %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %ecx + jnz 1b +17: movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz 20f +18: movq (%rsi),%r8 + mov %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +20: andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al + movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xorl %eax,%eax + sfence + ret + + .section .fixup,"ax" +30: + addl %ecx,%edx + jmp 100f +31: + shll $6,%ecx + addl %ecx,%edx + jmp 100f +32: + shll $6,%ecx + leal -8(%ecx,%edx),%edx + jmp 100f +33: + shll $6,%ecx + leal -16(%ecx,%edx),%edx + jmp 100f +34: + shll $6,%ecx + leal -24(%ecx,%edx),%edx + jmp 100f +35: + shll $6,%ecx + leal -32(%ecx,%edx),%edx + jmp 100f +36: + shll $6,%ecx + leal -40(%ecx,%edx),%edx + jmp 100f +37: + shll $6,%ecx + leal -48(%ecx,%edx),%edx + jmp 100f +38: + shll $6,%ecx + leal -56(%ecx,%edx),%edx + jmp 100f +39: + lea (%rdx,%rcx,8),%rdx + jmp 100f +40: + mov %ecx,%edx +100: + sfence + mov %edx,%eax + bts $63,%rax + ret + .previous + + _ASM_MCEXTABLE(0b,30b) + _ASM_MCEXTABLE(1b,31b) + _ASM_MCEXTABLE(2b,32b) + _ASM_MCEXTABLE(3b,33b) + _ASM_MCEXTABLE(4b,34b) + _ASM_MCEXTABLE(9b,35b) + _ASM_MCEXTABLE(10b,36b) + _ASM_MCEXTABLE(11b,37b) + _ASM_MCEXTABLE(12b,38b) + _ASM_MCEXTABLE(18b,39b) + _ASM_MCEXTABLE(21b,40b) +ENDPROC(__mcsafe_copy) +#endif -- 2.1.4 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-12-24 21:10 UTC|newest] Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-12-24 20:54 [PATCHV4 0/3] Machine check recovery when kernel accesses poison Tony Luck 2015-12-24 20:54 ` Tony Luck 2015-12-16 1:29 ` [PATCHV4 1/3] x86, ras: Add new infrastructure for machine check fixup tables Tony Luck 2015-12-16 1:29 ` Tony Luck 2015-12-16 1:29 ` [PATCHV4 2/3] x86, ras: Extend machine check recovery code to annotated ring0 areas Tony Luck 2015-12-16 1:29 ` Tony Luck 2015-12-16 1:30 ` Tony Luck [this message] 2015-12-16 1:30 ` [PATCHV4 3/3] x86, ras: Add __mcsafe_copy() function to recover from machine checks Tony Luck 2015-12-24 21:46 ` Borislav Petkov 2015-12-16 1:30 ` [PATCHV5 " Tony Luck 2015-12-16 1:30 ` Tony Luck 2015-12-25 11:49 ` Borislav Petkov 2015-12-25 20:05 ` Luck, Tony 2015-12-25 20:05 ` Luck, Tony 2015-12-26 10:32 ` Borislav Petkov 2015-12-26 14:54 ` Andy Lutomirski 2015-12-26 14:54 ` Andy Lutomirski 2015-12-27 2:08 ` Tony Luck 2015-12-27 2:08 ` Tony Luck 2015-12-27 2:15 ` Andy Lutomirski 2015-12-27 2:15 ` Andy Lutomirski 2015-12-27 2:16 ` Andy Lutomirski 2015-12-27 2:16 ` Andy Lutomirski 2015-12-27 6:57 ` Tony Luck 2015-12-27 6:57 ` Tony Luck 2015-12-27 10:09 ` Borislav Petkov 2015-12-27 12:19 ` Andy Lutomirski 2015-12-27 12:19 ` Andy Lutomirski 2015-12-27 13:17 ` Boris Petkov 2015-12-27 13:25 ` Andy Lutomirski 2015-12-27 13:25 ` Andy Lutomirski 2015-12-27 13:33 ` Borislav Petkov 2015-12-27 13:40 ` Andy Lutomirski 2015-12-27 13:40 ` Andy Lutomirski 2015-12-27 19:04 ` Dan Williams 2015-12-27 19:04 ` Dan Williams 2015-12-27 12:18 ` Andy Lutomirski 2015-12-27 12:18 ` Andy Lutomirski 2015-12-30 23:32 ` Tony Luck 2015-12-30 23:32 ` Tony Luck 2015-12-31 20:30 ` Tony Luck 2015-12-31 20:30 ` Tony Luck 2015-12-31 21:22 ` Andy Lutomirski 2015-12-31 21:22 ` Andy Lutomirski 2016-01-01 22:19 ` Tony Luck 2016-01-01 22:19 ` Tony Luck 2016-01-03 3:40 ` Andy Lutomirski 2016-01-03 3:40 ` Andy Lutomirski
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=a27752f2ac16e47b1a365c5c3cc870bd87ff0366.1450990481.git.tony.luck@intel.com \ --to=tony.luck@intel.com \ --cc=akpm@linux-foundation.org \ --cc=bp@alien8.de \ --cc=dan.j.williams@intel.com \ --cc=elliott@hpe.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=linux-nvdimm@ml01.01.org \ --cc=luto@kernel.org \ --cc=mingo@kernel.org \ --cc=x86@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.