korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2025-01-25 23:34:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

- Fix the APEI MCE callback handler to consult the hardware about the

Browse Source 
granularity of the memory error instead of hard-coding it
 
 - Offline memory pages on Intel machines after 2 errors reported per page
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmM7+ZAACgkQEsHwGGHe
 VUp3Rg/9HkwMcl8HOEShQoN1HvhDh68DeR0pgZpFjooBgilqFuPopWn7rwOsebza
 b6Z1XYg3pmWwkG35ztHedFP8WkRb8aZDJV7czpGxiaxtRUCuXpGZJk45CFzU+3l8
 FD9XKryDf6rPSKmg6w/63FUPVXJXpM8+pAlEso9BVrb6xmUb3n6ul5A/kt3Z4OBZ
 beNDI54s7pfKXmCYze7VbK2nqyEM9fmDuPAhaicB/qhVEqxSWMNKDYDhHs1wt/Um
 dOlLC2paqcc9EaRhV/L/9Pvi1zasy7Q0+jSIXhgbag7EQmZRYQn3Pe0xqUJNhK2H
 ulm65Dy+AZ3y15+qBkBOgoNF/By5eMwJ+C9bucC6FWkPG0XMjDVGiphf+DPZmAHk
 msYSvyp++WidNYn/bXhbQv0epjheLoHj22lTvlHwLquI+eISuDV24DIcBQQpFFed
 S/8sMw3RqoOgAd3LHr1NGcd/7eF+b/Lc1mtUx7qhg/W0V2cYVTGIcNJMAJ8USHMy
 IxFiB+8x7ps0lRJGlaApylLQOGAhS9WxpH2UUIKIoURrmCi9Pf8OaHzfIA5jYK+t
 xEQTzZE5ZUB0V5mvNhAWTm9HvlaW1WNbokt0vElAEJ9WAjRfMVYKya7shlAK2MYI
 nrM3eqlUwOqTGLGCA7IhCS9Re7M5ZKZk5nsLygnYsadntqCmN0c=
 =5tV9
 -----END PGP SIGNATURE-----

Merge tag 'ras_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Borislav Petkov:

 - Fix the APEI MCE callback handler to consult the hardware about the
   granularity of the memory error instead of hard-coding it

 - Offline memory pages on Intel machines after 2 errors reported per
   page

* tag 'ras_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Retrieve poison range from hardware
  RAS/CEC: Reduce offline page threshold for Intel systems
This commit is contained in:
Linus Torvalds 2022-10-04 09:33:12 -07:00
commit 51eaa866a5
2 changed files with 20 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
arch/x86/kernel/cpu/mce/apei.c
View File

@ -29,15 +29,26 @@
void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
{
struct mce m;
int lsb;
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
/*
* Even if the ->validation_bits are set for address mask,
* to be extra safe, check and reject an error radius '0',
* and fall back to the default page size.
*/
if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT);
else
lsb = PAGE_SHIFT;
mce_setup(&m);
m.bank = -1;
/* Fake a memory read error with unknown channel */
m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f;
m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT;
m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb;
if (severity >= GHES_SEV_RECOVERABLE)
m.status |= MCI_STATUS_UC;

8
drivers/ras/cec.c
View File

@ -556,6 +556,14 @@ static int __init cec_init(void)
if (ce_arr.disabled)
return -ENODEV;
/*
* Intel systems may avoid uncorrectable errors
* if pages with corrected errors are aggressively
* taken offline.
*/
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
action_threshold = 2;
ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
if (!ce_arr.array) {
pr_err("Error allocating CE array page!\n");