linux-dev/arch/x86/kernel/cpu/mce/internal.h, branch linus/master

x86/mce: Remove the tolerance level control

2022-02-23T10:09:25Z

This is pretty much unused and not really useful. What is more, all relevant MCA hardware has recoverable machine checks support so there's no real need to tweak MCA tolerance levels in order to *maybe* extend machine lifetime. So rip it out. Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/YcDq8PxvKtTENl/e@zn.tnic

x86/mce: Work around an erratum on fast string copy instructions

2022-02-19T13:26:42Z

A rare kernel panic scenario can happen when the following conditions are met due to an erratum on fast string copy instructions: 1) An uncorrected error. 2) That error must be in first cache line of a page. 3) Kernel must execute page_copy from the page immediately before that page. The fast string copy instructions ("REP; MOVS*") could consume an uncorrectable memory error in the cache line _right after_ the desired region to copy and raise an MCE. Bit 0 of MSR_IA32_MISC_ENABLE can be cleared to disable fast string copy and will avoid such spurious machine checks. However, that is less preferable due to the permanent performance impact. Considering memory poison is rare, it's desirable to keep fast string copy enabled until an MCE is seen. Intel has confirmed the following: 1. The CPU erratum of fast string copy only applies to Skylake, Cascade Lake and Cooper Lake generations. Directly return from the MCE handler: 2. Will result in complete execution of the "REP; MOVS*" with no data loss or corruption. 3. Will not result in another MCE firing on the next poisoned cache line due to "REP; MOVS*". 4. Will resume execution from a correct point in code. 5. Will result in the same instruction that triggered the MCE firing a second MCE immediately for any other software recoverable data fetch errors. 6. Is not safe without disabling the fast string copy, as the next fast string copy of the same buffer on the same CPU would result in a PANIC MCE. This should mitigate the erratum completely with the only caveat that the fast string copy is disabled on the affected hyper thread thus performance degradation. This is still better than the OS crashing on MCEs raised on an irrelevant process due to "REP; MOVS*' accesses in a kernel context, e.g., copy_page. Tested: Injected errors on 1st cache line of 8 anonymous pages of process 'proc1' and observed MCE consumption from 'proc2' with no panic (directly returned). Without the fix, the host panicked within a few minutes on a random 'proc2' process due to kernel access from copy_page. [ bp: Fix comment style + touch ups, zap an unlikely(), improve the quirk function's readability. ] Signed-off-by: Jue Wang Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lore.kernel.org/r/20220218013209.2436006-1-juew@google.com

x86/mce: Use arch atomic and bit helpers

2022-02-13T21:08:27Z

The arch helpers do not have explicit KASAN instrumentation. Use them in noinstr code. Inline a couple more functions with single call sites, while at it: mce_severity_amd_smca() has a single call-site which is noinstr so force the inlining and fix: vmlinux.o: warning: objtool: mce_severity_amd.constprop.0()+0xca: call to \ mce_severity_amd_smca() leaves .noinstr.text section Always inline mca_msr_reg(): text data bss dec hex filename 16065240 128031326 36405368 180501934 ac23dae vmlinux.before 16065240 128031294 36405368 180501902 ac23d8e vmlinux.after and mce_no_way_out() as the latter one is used only once, to fix: vmlinux.o: warning: objtool: mce_read_aux()+0x53: call to mca_msr_reg() leaves .noinstr.text section vmlinux.o: warning: objtool: do_machine_check()+0xc9: call to mce_no_way_out() leaves .noinstr.text section Signed-off-by: Borislav Petkov Acked-by: Marco Elver Link: https://lore.kernel.org/r/20220204083015.17317-4-bp@alien8.de

x86/mce: Use mce_rdmsrl() in severity checking code

2021-12-13T13:12:08Z

MCA has its own special MSR accessors. Use them. No functional changes. Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20211208111343.8130-4-bp@alien8.de

Merge tag 'ras_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2021-11-01T22:12:04Z

Pull RAS updates from Borislav Petkov: - Get rid of a bunch of function pointers used in MCA land in favor of normal functions. This is in preparation of making the MCA code noinstr-aware - When the kernel copies data from user addresses and it encounters a machine check, a SIGBUS is sent to that process. Change this action to either an -EFAULT which is returned to the user or a short write, making the recovery action a lot more user-friendly * tag 'ras_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mce: Sort mca_config members to get rid of unnecessary padding x86/mce: Get rid of the ->quirk_no_way_out() indirect call x86/mce: Get rid of msr_ops x86/mce: Get rid of machine_check_vector x86/mce: Get rid of the mce_severity function pointer x86/mce: Drop copyin special case for #MC x86/mce: Change to not send SIGBUS error during copy from user

x86/mce: Sort mca_config members to get rid of unnecessary padding

2021-09-23T09:38:04Z

$ pahole -C mca_config arch/x86/kernel/cpu/mce/core.o before: /* size: 40, cachelines: 1, members: 16 */ /* sum members: 21, holes: 1, sum holes: 3 */ /* sum bitfield members: 64 bits, bit holes: 2, sum bit holes: 32 bits */ /* padding: 4 */ /* last cacheline: 40 bytes */ after: /* size: 32, cachelines: 1, members: 16 */ /* padding: 3 */ /* last cacheline: 32 bytes */ No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-6-bp@alien8.de

x86/mce: Get rid of the ->quirk_no_way_out() indirect call

2021-09-23T09:34:49Z

Use a flag setting to call the only quirk function for that. No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-5-bp@alien8.de

x86/mce: Get rid of msr_ops

2021-09-23T09:20:20Z

Avoid having indirect calls and use a normal function which returns the proper MSR address based on ->smca setting. No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-4-bp@alien8.de

x86/mce: Get rid of machine_check_vector

2021-09-23T09:15:49Z

Get rid of the indirect function pointer and use flags settings instead to steer execution. Now that it is not an indirect call any longer, drop the instrumentation annotation for objtool too. No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-3-bp@alien8.de

x86/mce: Get rid of the mce_severity function pointer

2021-09-23T09:03:51Z

Turn it into a normal function which calls an AMD- or Intel-specific variant depending on the CPU it runs on. No functional changes. Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Link: https://lkml.kernel.org/r/20210922165101.18951-2-bp@alien8.de