From 18807ddb7f88d4ac3797302bafb18143d573e66f Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Tue, 15 Nov 2016 15:13:53 -0600 Subject: x86/mce/AMD: Reset Threshold Limit after logging error The error count field in MCA_MISC does not get reset by hardware when the threshold has been reached. Software is expected to reset it. Currently, the threshold limit only gets reset during init or when a user writes to sysfs. If the user is not monitoring threshold interrupts and resetting the limit then the user will only see 1 interrupt when the limit is first hit. So if, for example, the limit is set to 10 then only 1 interrupt will be recorded after 10 errors even if 100 errors have occurred. The user may then assume that only 10 errors have occurred. Signed-off-by: Yazen Ghannam Cc: Aravind Gopalakrishnan Cc: linux-edac Cc: x86-ml Link: http://lkml.kernel.org/r/1479244433-69267-1-git-send-email-Yazen.Ghannam@amd.com Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/mcheck/mce_amd.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/kernel/cpu/mcheck/mce_amd.c') diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index e68a305ff666..5b33702ca86e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -665,6 +665,7 @@ static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; unsigned int bank, block, cpu = smp_processor_id(); + struct thresh_restart tr; /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { @@ -701,6 +702,11 @@ static void amd_threshold_interrupt(void) log: __log_error(bank, false, true, ((u64)high << 32) | low); + + /* Reset threshold block after logging error. */ + memset(&tr, 0, sizeof(tr)); + tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; + threshold_restart_bank(&tr); } /* -- cgit