diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-12 14:51:56 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-12 14:51:56 -0800 |
commit | 9196a0ba9f0ebe168c7b186f63cf7cab02e55778 (patch) | |
tree | 0d2f4b95543b23d9323dec7ffa0066706c42e654 | |
parent | 7adcadb98405cb4ef56b2518164026c1069d8669 (diff) | |
parent | 50865c14f34edbd03f8113147fac069b39f4e390 (diff) | |
download | linux-9196a0ba9f0ebe168c7b186f63cf7cab02e55778.tar.bz2 |
Merge tag 'ras_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 RAS updates from Borislav Petkov:
- Fix confusing output from /sys/kernel/debug/ras/daemon_active
- Add another MCE severity error case to the Intel error severity table
to promote UC and AR errors to panic severity and remove the
corresponding code condition doing that.
- Make sure the thresholding and deferred error interrupts on AMD SMCA
systems clear the all registers reporting an error so that there are
no multiple errors logged for the same event
* tag 'ras_core_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
RAS: Fix return value from show_trace()
x86/mce: Use severity table to handle uncorrected errors in kernel
x86/MCE/AMD: Clear DFR errors found in THR handler
-rw-r--r-- | arch/x86/kernel/cpu/mce/amd.c | 33 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/severity.c | 8 | ||||
-rw-r--r-- | drivers/ras/debugfs.c | 2 |
3 files changed, 26 insertions, 17 deletions
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 1c87501e0fa3..10fb5b5c9efa 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -788,6 +788,24 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) return status & MCI_STATUS_DEFERRED; } +static bool _log_error_deferred(unsigned int bank, u32 misc) +{ + if (!_log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), misc)) + return false; + + /* + * Non-SMCA systems don't have MCA_DESTAT/MCA_DEADDR registers. + * Return true here to avoid accessing these registers. + */ + if (!mce_flags.smca) + return true; + + /* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */ + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return true; +} + /* * We have three scenarios for checking for Deferred errors: * @@ -799,19 +817,8 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) */ static void log_error_deferred(unsigned int bank) { - bool defrd; - - defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), - mca_msr_reg(bank, MCA_ADDR), 0); - - if (!mce_flags.smca) - return; - - /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ - if (defrd) { - wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + if (_log_error_deferred(bank, 0)) return; - } /* * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check @@ -832,7 +839,7 @@ static void amd_deferred_error_interrupt(void) static void log_error_thresholding(unsigned int bank, u64 misc) { - _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc); + _log_error_deferred(bank, misc); } static void log_and_reset_block(struct threshold_block *block) diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 00483d1c27e4..c4477162c07d 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -203,6 +203,11 @@ static struct severity { BITSET(MCI_STATUS_OVER|MCI_STATUS_UC) ), MCESEV( + PANIC, "Uncorrected in kernel", + BITSET(MCI_STATUS_UC), + KERNEL + ), + MCESEV( UC, "Uncorrected", BITSET(MCI_STATUS_UC) ), @@ -391,9 +396,6 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char *msg = s->msg; s->covered = 1; - if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) - return MCE_PANIC_SEVERITY; - return s->sev; } } diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c index 0d4f985afbf3..f0a6391b1146 100644 --- a/drivers/ras/debugfs.c +++ b/drivers/ras/debugfs.c @@ -15,7 +15,7 @@ EXPORT_SYMBOL_GPL(ras_userspace_consumers); static int trace_show(struct seq_file *m, void *v) { - return atomic_read(&trace_count); + return 0; } static int trace_open(struct inode *inode, struct file *file) |