diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-12 10:14:38 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-12 10:14:38 -0700 |
commit | ca1b66922a702316734bcd5ea2100e5fb8f3caa3 (patch) | |
tree | 47c14ba23f855d71d72568dd0ae6007013167a7c /arch/x86/include/asm/mce.h | |
parent | a9a4b7d9a6380ae4e1df2c9b90fef6c427229aab (diff) | |
parent | b3149ffcdb31a8eb854cc442a389ae0b539bf28a (diff) |
Merge tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RAS updates from Borislav Petkov:
- Extend the recovery from MCE in kernel space also to processes which
encounter an MCE in kernel space but while copying from user memory
by sending them a SIGBUS on return to user space and umapping the
faulty memory, by Tony Luck and Youquan Song.
- memcpy_mcsafe() rework by splitting the functionality into
copy_mc_to_user() and copy_mc_to_kernel(). This, as a result, enables
support for new hardware which can recover from a machine check
encountered during a fast string copy and makes that the default and
lets the older hardware which does not support that advance recovery,
opt in to use the old, fragile, slow variant, by Dan Williams.
- New AMD hw enablement, by Yazen Ghannam and Akshay Gupta.
- Do not use MSR-tracing accessors in #MC context and flag any fault
while accessing MCA architectural MSRs as an architectural violation
with the hope that such hw/fw misdesigns are caught early during the
hw eval phase and they don't make it into production.
- Misc fixes, improvements and cleanups, as always.
* tag 'ras_updates_for_v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mce: Allow for copy_mc_fragile symbol checksum to be generated
x86/mce: Decode a kernel instruction to determine if it is copying from user
x86/mce: Recover from poison found while copying from user space
x86/mce: Avoid tail copy when machine check terminated a copy from user
x86/mce: Add _ASM_EXTABLE_CPY for copy user access
x86/mce: Provide method to find out the type of an exception handler
x86/mce: Pass pointer to saved pt_regs to severity calculation routines
x86/copy_mc: Introduce copy_mc_enhanced_fast_string()
x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()
x86/mce: Drop AMD-specific "DEFERRED" case from Intel severity rule list
x86/mce: Add Skylake quirk for patrol scrub reported errors
RAS/CEC: Convert to DEFINE_SHOW_ATTRIBUTE()
x86/mce: Annotate mce_rd/wrmsrl() with noinstr
x86/mce/dev-mcelog: Do not update kflags on AMD systems
x86/mce: Stop mce_reign() from re-computing severity for every CPU
x86/mce: Make mce_rdmsrl() panic on an inaccessible MSR
x86/mce: Increase maximum number of banks to 64
x86/mce: Delay clearing IA32_MCG_STATUS to the end of do_machine_check()
x86/MCE/AMD, EDAC/mce_amd: Remove struct smca_hwid.xec_bitmap
RAS/CEC: Fix cec_init() prototype
Diffstat (limited to 'arch/x86/include/asm/mce.h')
-rw-r--r-- | arch/x86/include/asm/mce.h | 33 |
1 files changed, 26 insertions, 7 deletions
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cf503824529c..a0f147893a04 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -136,9 +136,24 @@ #define MCE_HANDLED_NFIT BIT_ULL(3) #define MCE_HANDLED_EDAC BIT_ULL(4) #define MCE_HANDLED_MCELOG BIT_ULL(5) + +/* + * Indicates an MCE which has happened in kernel space but from + * which the kernel can recover simply by executing fixup_exception() + * so that an error is returned to the caller of the function that + * hit the machine check. + */ #define MCE_IN_KERNEL_RECOV BIT_ULL(6) /* + * Indicates an MCE that happened in kernel space while copying data + * from user. In this case fixup_exception() gets the kernel to the + * error exit for the copy function. Machine check handler can then + * treat it like a fault taken in user mode. + */ +#define MCE_IN_KERNEL_COPYIN BIT_ULL(7) + +/* * This structure contains all data related to the MCE log. Also * carries a signature to make it easier to find from external * debugging tools. Each entry is only valid when its finished flag @@ -174,6 +189,15 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb); extern int mce_p5_enabled; +#ifdef CONFIG_ARCH_HAS_COPY_MC +extern void enable_copy_mc_fragile(void); +unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt); +#else +static inline void enable_copy_mc_fragile(void) +{ +} +#endif + #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); @@ -200,12 +224,8 @@ void mce_setup(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct device *, mce_device); -/* - * Maximum banks number. - * This is the limit of the current register layout on - * Intel CPUs. - */ -#define MAX_NR_BANKS 32 +/* Maximum number of MCA banks per CPU. */ +#define MAX_NR_BANKS 64 #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); @@ -328,7 +348,6 @@ enum smca_bank_types { struct smca_hwid { unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ u32 hwid_mcatype; /* (hwid,mcatype) tuple */ - u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ u8 count; /* Number of instances. */ }; |