diff options
author | Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> | 2013-07-01 21:08:47 +0530 |
---|---|---|
committer | Tony Luck <tony.luck@intel.com> | 2013-07-08 11:53:01 -0700 |
commit | c3d1fb567a634dcdff4c6f6095b2053260988336 (patch) | |
tree | be2b0f39a3b489c4aa4b39d6c527be0c63146b92 /arch/x86/kernel/cpu/mcheck/mce.c | |
parent | 8bb495e3f02401ee6f76d1b1d77f3ac9f079e376 (diff) |
mce: acpi/apei: Honour Firmware First for MCA banks listed in APEI HEST CMC
The Corrected Machine Check structure (CMC) in HEST has a flag which can be
set by the firmware to indicate to the OS that it prefers to process the
corrected error events first. In this scenario, the OS is expected to not
monitor for corrected errors (through CMCI/polling). Instead, the firmware
notifies the OS on corrected error events through GHES.
Linux already has support for GHES. This patch adds support for parsing CMC
structure and to disable CMCI/polling if the firmware first flag is set.
Further, the list of machine check bank structures at the end of CMC is used
to determine which MCA banks function in FF mode, so that we continue to
monitor error events on the other banks.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck/mce.c')
-rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 28 |
1 files changed, 28 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9239504b41c..5bf32c70a9c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -94,6 +94,15 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL }; +/* + * MCA banks controlled through firmware first for corrected errors. + * This is a global list of banks for which we won't enable CMCI and we + * won't poll. Firmware controls these banks and is responsible for + * reporting corrected errors through GHES. Uncorrected/recoverable + * errors are still notified through a machine check. + */ +mce_banks_t mce_banks_ce_disabled; + static DEFINE_PER_CPU(struct work_struct, mce_work); static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); @@ -1932,6 +1941,25 @@ static struct miscdevice mce_chrdev_device = { &mce_chrdev_ops, }; +static void __mce_disable_bank(void *arg) +{ + int bank = *((int *)arg); + __clear_bit(bank, __get_cpu_var(mce_poll_banks)); + cmci_disable_bank(bank); +} + +void mce_disable_bank(int bank) +{ + if (bank >= mca_cfg.banks) { + pr_warn(FW_BUG + "Ignoring request to disable invalid MCA bank %d.\n", + bank); + return; + } + set_bit(bank, mce_banks_ce_disabled); + on_each_cpu(__mce_disable_bank, &bank, 1); +} + /* * mce=off Disables machine check * mce=no_cmci Disables CMCI |