lwn.git/arch/x86/include/asm/mce.h, branch docs-5.10-3

x86/mce: Add _ASM_EXTABLE_CPY for copy user access

2020-10-07T09:19:11+00:00

_ASM_EXTABLE_UA is a general exception entry to record the exception fixup for all exception spots between kernel and user space access. To enable recovery from machine checks while coping data from user addresses it is necessary to be able to distinguish the places that are looping copying data from those that copy a single byte/word/etc. Add a new macro _ASM_EXTABLE_CPY and use it in place of _ASM_EXTABLE_UA in the copy functions. Record the exception reason number to regs->ax at ex_handler_uaccess which is used to check MCE triggered. The new fixup routine ex_handler_copy() is almost an exact copy of ex_handler_uaccess() The difference is that it sets regs->ax to the trap number. Following patches use this to avoid trying to copy remaining bytes from the tail of the copy and possibly hitting the poison again. New mce.kflags bit MCE_IN_KERNEL_COPYIN will be used by mce_severity() calculation to indicate that a machine check is recoverable because the kernel was copying from user space. Signed-off-by: Youquan Song Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20201006210910.21062-4-tony.luck@intel.com

x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()

2020-10-06T09:18:04+00:00

In reaction to a proposal to introduce a memcpy_mcsafe_fast() implementation Linus points out that memcpy_mcsafe() is poorly named relative to communicating the scope of the interface. Specifically what addresses are valid to pass as source, destination, and what faults / exceptions are handled. Of particular concern is that even though x86 might be able to handle the semantics of copy_mc_to_user() with its common copy_user_generic() implementation other archs likely need / want an explicit path for this case: On Fri, May 1, 2020 at 11:28 AM Linus Torvalds wrote: > > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams wrote: > > > > However now I see that copy_user_generic() works for the wrong reason. > > It works because the exception on the source address due to poison > > looks no different than a write fault on the user address to the > > caller, it's still just a short copy. So it makes copy_to_user() work > > for the wrong reason relative to the name. > > Right. > > And it won't work that way on other architectures. On x86, we have a > generic function that can take faults on either side, and we use it > for both cases (and for the "in_user" case too), but that's an > artifact of the architecture oddity. > > In fact, it's probably wrong even on x86 - because it can hide bugs - > but writing those things is painful enough that everybody prefers > having just one function. Replace a single top-level memcpy_mcsafe() with either copy_mc_to_user(), or copy_mc_to_kernel(). Introduce an x86 copy_mc_fragile() name as the rename for the low-level x86 implementation formerly named memcpy_mcsafe(). It is used as the slow / careful backend that is supplanted by a fast copy_mc_generic() in a follow-on patch. One side-effect of this reorganization is that separating copy_mc_64.S to its own file means that perf no longer needs to track dependencies for its memcpy_64.S benchmarks. [ bp: Massage a bit. ] Signed-off-by: Dan Williams Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Acked-by: Michael Ellerman Cc: Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com

x86/mce: Increase maximum number of banks to 64

2020-09-04T15:17:27+00:00

...because future AMD systems will support up to 64 MCA banks per CPU. MAX_NR_BANKS is used to allocate a number of data structures, and it is used as a ceiling for values read from MCG_CAP[Count]. Therefore, this change will have no functional effect on existing systems with 32 or fewer MCA banks per CPU. However, this will increase the size of the following structures: Global bitmaps: - core.c / mce_banks_ce_disabled - core.c / all_banks - core.c / valid_banks - core.c / toclear - Total: 32 new bits * 4 bitmaps = 16 new bytes Per-CPU bitmaps: - core.c / mce_poll_banks - intel.c / mce_banks_owned - Total: 32 new bits * 2 bitmaps = 8 new bytes The bitmaps are arrays of longs. So this change will only affect 32-bit execution, since there will be one additional long used. There will be no additional memory use on 64-bit execution, because the size of long is 64 bits. Global structs: - amd.c / struct smca_bank smca_banks[]: 16 bytes per bank - core.c / struct mce_bank_dev mce_bank_devs[]: 56 bytes per bank - Total: 32 new banks * (16 + 56) bytes = 2304 new bytes Per-CPU structs: - core.c / struct mce_bank mce_banks_array[]: 16 bytes per bank - Total: 32 new banks * 16 bytes = 512 new bytes 32-bit Total global size increase: 2320 bytes Total per-CPU size increase: 520 bytes 64-bit Total global size increase: 2304 bytes Total per-CPU size increase: 512 bytes This additional memory should still fit within the existing .data section of the kernel binary. However, in the case where it doesn't fit, an additional page (4kB) of memory will be added to the binary to accommodate the extra data which will be the maximum size increase of vmlinux. Signed-off-by: Akshay Gupta [ Adjust commit message and code comment. ] Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200828192412.320052-1-Yazen.Ghannam@amd.com

x86/MCE/AMD, EDAC/mce_amd: Remove struct smca_hwid.xec_bitmap

2020-08-20T08:34:38+00:00

The Extended Error Code Bitmap (xec_bitmap) for a Scalable MCA bank type was intended to be used by the kernel to filter out invalid error codes on a system. However, this is unnecessary after a few product releases because the hardware will only report valid error codes. Thus, there's no need for it with future systems. Remove the xec_bitmap field and all references to it. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20200720145353.43924-1-Yazen.Ghannam@amd.com

Merge branch 'x86/entry' into ras/core

2020-06-11T13:17:57+00:00

to fixup conflicts in arch/x86/kernel/cpu/mce/core.c so MCE specific follow up patches can be applied without creating a horrible merge conflict afterwards.

x86/entry: Convert Machine Check to IDTENTRY_IST

2020-06-11T13:14:57+00:00

Convert #MC to IDTENTRY_MCE: - Implement the C entry points with DEFINE_IDTENTRY_MCE - Emit the ASM stub with DECLARE_IDTENTRY_MCE - Remove the ASM idtentry in 64bit - Remove the open coded ASM entry code in 32bit - Fixup the XEN/PV code - Remove the old prototypes - Remove the error code from *machine_check_vector() as it is always 0 and not used by any of the functions it can point to. Fixup all the functions as well. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Alexandre Chartre Acked-by: Peter Zijlstra Acked-by: Andy Lutomirski Link: https://lkml.kernel.org/r/20200505135314.334980426@linutronix.de

x86/mce: Fixup exception only for the correct MCEs

2020-04-14T14:01:49+00:00

The severity grading code returns IN_KERNEL_RECOV error context for errors which have happened in kernel space but from which the kernel can recover. Whether the recovery can happen is determined by the exception table entry having as handler ex_handler_fault() and which has been declared at build time using _ASM_EXTABLE_FAULT(). IN_KERNEL_RECOV is used in mce_severity_intel() to lookup the corresponding error severity in the severities table. However, the mapping back from error severity to whether the error is IN_KERNEL_RECOV is ambiguous and in the very paranoid case - which might not be possible right now - but be better safe than sorry later, an exception fixup could be attempted for another MCE whose address is in the exception table and has the proper severity. Which would be unfortunate, to say the least. Therefore, mark such MCEs explicitly as MCE_IN_KERNEL_RECOV so that the recovery attempt is done only for them. Document the whole handling, while at it, as it is not trivial. Reported-by: Thomas Gleixner Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200407163414.18058-10-bp@alien8.de

x86/mce: Add a struct mce.kflags field

2020-04-14T13:58:43+00:00

There can be many different subsystems register on the mce handler chain. Add a new bitmask field and define values so that handlers can indicate whether they took any action to log or otherwise handle an error. The default handler at the end of the chain can use this information to decide whether to print to the console log. Boris suggested a generic name and leaving plenty of spare bits for possible future use. [ bp: Move flag bits to the internal mce.h header and use BIT_ULL(). ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200214222720.13168-4-tony.luck@intel.com

x86/mce: Rename "first" function as "early"

2020-04-14T13:55:01+00:00

It isn't going to be first on the notifier chain when the CEC is moved to be a normal user of the notifier chain. Fix the enum for the MCE_PRIO symbols to list them in reverse order so that the compiler can give them numbers from low to high priority. Add an entry for MCE_PRIO_CEC as the highest priority. [ bp: Use passive voice, add comments. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200214222720.13168-2-tony.luck@intel.com

x86/mce/amd, edac: Remove report_gart_errors

2020-04-14T13:53:46+00:00

... because no one should be interested in spurious MCEs anyway. Make the filtering unconditional and move it to amd_filter_mce(). Signed-off-by: Borislav Petkov Tested-by: Tony Luck Link: https://lkml.kernel.org/r/20200407163414.18058-2-bp@alien8.de