From 4c113a5b28bfd589e2010b5fc8867578b0135ed7 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 24 Jun 2025 14:15:56 +0000 Subject: [PATCH 1/5] x86/mce: Don't remove sysfs if thresholding sysfs init fails Currently, the MCE subsystem sysfs interface will be removed if the thresholding sysfs interface fails to be created. A common failure is due to new MCA bank types that are not recognized and don't have a short name set. The MCA thresholding feature is optional and should not break the common MCE sysfs interface. Also, new MCA bank types are occasionally introduced, and updates will be needed to recognize them. But likewise, this should not break the common sysfs interface. Keep the MCE sysfs interface regardless of the status of the thresholding sysfs interface. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Qiuxu Zhuo Reviewed-by: Tony Luck Tested-by: Tony Luck Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-1-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/core.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index e9b3c5d4a52e..07d61937427f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2801,15 +2801,9 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { struct timer_list *t = this_cpu_ptr(&mce_timer); - int ret; mce_device_create(cpu); - - ret = mce_threshold_create_device(cpu); - if (ret) { - mce_device_remove(cpu); - return ret; - } + mce_threshold_create_device(cpu); mce_reenable_cpu(); mce_start_timer(t); return 0; From 00c092de6f28ebd32208aef83b02d61af2229b60 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 24 Jun 2025 14:15:57 +0000 Subject: [PATCH 2/5] x86/mce: Ensure user polling settings are honored when restarting timer Users can disable MCA polling by setting the "ignore_ce" parameter or by setting "check_interval=0". This tells the kernel to *not* start the MCE timer on a CPU. If the user did not disable CMCI, then storms can occur. When these happen, the MCE timer will be started with a fixed interval. After the storm subsides, the timer's next interval is set to check_interval. This disregards the user's input through "ignore_ce" and "check_interval". Furthermore, if "check_interval=0", then the new timer will run faster than expected. Create a new helper to check these conditions and use it when a CMCI storm ends. [ bp: Massage. ] Fixes: 7eae17c4add5 ("x86/mce: Add per-bank CMCI storm mitigation") Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-2-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/core.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 07d61937427f..4da4eab56c81 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1740,6 +1740,11 @@ static void mc_poll_banks_default(void) void (*mc_poll_banks)(void) = mc_poll_banks_default; +static bool should_enable_timer(unsigned long iv) +{ + return !mca_cfg.ignore_ce && iv; +} + static void mce_timer_fn(struct timer_list *t) { struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); @@ -1763,7 +1768,7 @@ static void mce_timer_fn(struct timer_list *t) if (mce_get_storm_mode()) { __start_timer(t, HZ); - } else { + } else if (should_enable_timer(iv)) { __this_cpu_write(mce_next_interval, iv); __start_timer(t, iv); } @@ -2156,11 +2161,10 @@ static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; - if (mca_cfg.ignore_ce || !iv) - return; - - this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (should_enable_timer(iv)) { + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } static void __mcheck_cpu_setup_timer(void) From d66e1e90b16055d2f0ee76e5384e3f119c3c2773 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 24 Jun 2025 14:15:58 +0000 Subject: [PATCH 3/5] x86/mce/amd: Add default names for MCA banks and blocks Ensure that sysfs init doesn't fail for new/unrecognized bank types or if a bank has additional blocks available. Most MCA banks have a single thresholding block, so the block takes the same name as the bank. Unified Memory Controllers (UMCs) are a special case where there are two blocks and each has a unique name. However, the microarchitecture allows for five blocks. Any new MCA bank types with more than one block will be missing names for the extra blocks. The MCE sysfs will fail to initialize in this case. Fixes: 87a6d4091bd7 ("x86/mce/AMD: Update sysfs bank names for SMCA systems") Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-3-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 9d852c3b2cb5..6820ebce5d46 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1113,13 +1113,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol } bank_type = smca_get_bank_type(cpu, bank); - if (bank_type >= N_SMCA_BANK_TYPES) - return NULL; if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; - return NULL; + } + + if (b && b->block) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block); + return buf_mcatype; + } + + if (bank_type >= N_SMCA_BANK_TYPES) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank); + return buf_mcatype; } if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1) From 5f6e3b720694ad771911f637a51930f511427ce1 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 24 Jun 2025 14:15:59 +0000 Subject: [PATCH 4/5] x86/mce/amd: Fix threshold limit reset The MCA threshold limit must be reset after servicing the interrupt. Currently, the restart function doesn't have an explicit check for this. It makes some assumptions based on the current limit and what's in the registers. These assumptions don't always hold, so the limit won't be reset in some cases. Make the reset condition explicit. Either an interrupt/overflow has occurred or the bank is being initialized. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-4-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6820ebce5d46..5c4eb28c3ac9 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) struct thresh_restart { struct threshold_block *b; - int reset; int set_lvt_off; int lvt_off; u16 old_limit; @@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr) rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) - tr->reset = 1; /* limit cannot be lower than err count */ - - if (tr->reset) { /* reset err count and overflow bit */ - hi = - (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | - (THRESHOLD_MAX - tr->b->threshold_limit); + /* + * Reset error count and overflow bit. + * This is done during init or after handling an interrupt. + */ + if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) { + hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI); + hi |= THRESHOLD_MAX - tr->b->threshold_limit; } else if (tr->old_limit) { /* change limit w/o reset */ int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit); From 30ad231a5029bfa16e46ce868497b1a5cdd3c24d Mon Sep 17 00:00:00 2001 From: JP Kobryn Date: Fri, 27 Jun 2025 10:49:35 -0700 Subject: [PATCH 5/5] x86/mce: Make sure CMCI banks are cleared during shutdown on Intel CMCI banks are not cleared during shutdown on Intel CPUs. As a side effect, when a kexec is performed, CPUs coming back online are unable to rediscover/claim these occupied banks which breaks MCE reporting. Clear the CPU ownership during shutdown via cmci_clear() so the banks can be reclaimed and MCE reporting will become functional once more. [ bp: Massage commit message. ] Reported-by: Aijay Adams Signed-off-by: JP Kobryn Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Tony Luck Reviewed-by: Qiuxu Zhuo Cc: Link: https://lore.kernel.org/20250627174935.95194-1-inwardvessel@gmail.com --- arch/x86/kernel/cpu/mce/intel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index efcf21e9552e..9b149b9c4109 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -478,6 +478,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c) void mce_intel_feature_clear(struct cpuinfo_x86 *c) { intel_clear_lmce(); + cmci_clear(); } bool intel_filter_mce(struct mce *m)