From 6298c512bc1007c3ff5c9ce20e6996781651cc45 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 9 Apr 2009 12:28:22 +0200 Subject: x86, mce: make polling timer interval per CPU The polling timer while running per CPU still uses a global next_interval variable, which lead to some CPUs either polling too fast or too slow. This was not a serious problem because all errors get picked up eventually, but it's still better to avoid it. Turn next_interval into a per cpu variable. v2: Fix check_interval == 0 case (Hidetoshi Seto) [ Impact: minor bug fix ] Signed-off-by: Andi Kleen Reviewed-by: Hidetoshi Seto Signed-off-by: H. Peter Anvin diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 863f895..82614f1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -452,13 +452,14 @@ void mce_log_therm_throt_event(__u64 status) */ static int check_interval = 5 * 60; /* 5 minutes */ -static int next_interval; /* in jiffies */ +static DEFINE_PER_CPU(int, next_interval); /* in jiffies */ static void mcheck_timer(unsigned long); static DEFINE_PER_CPU(struct timer_list, mce_timer); static void mcheck_timer(unsigned long data) { struct timer_list *t = &per_cpu(mce_timer, data); + int *n; WARN_ON(smp_processor_id() != data); @@ -470,14 +471,14 @@ static void mcheck_timer(unsigned long data) * Alert userspace if needed. If we logged an MCE, reduce the * polling interval, otherwise increase the polling interval. */ + n = &__get_cpu_var(next_interval); if (mce_notify_user()) { - next_interval = max(next_interval/2, HZ/100); + *n = max(*n/2, HZ/100); } else { - next_interval = min(next_interval * 2, - (int)round_jiffies_relative(check_interval*HZ)); + *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ)); } - t->expires = jiffies + next_interval; + t->expires = jiffies + *n; add_timer(t); } @@ -632,14 +633,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c) static void mce_init_timer(void) { struct timer_list *t = &__get_cpu_var(mce_timer); + int *n = &__get_cpu_var(next_interval); - /* data race harmless because everyone sets to the same value */ - if (!next_interval) - next_interval = check_interval * HZ; - if (!next_interval) + *n = check_interval * HZ; + if (!*n) return; setup_timer(t, mcheck_timer, smp_processor_id()); - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + *n); add_timer(t); } @@ -907,7 +907,6 @@ static void mce_cpu_restart(void *data) /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { - next_interval = check_interval * HZ; on_each_cpu(mce_cpu_restart, NULL, 1); } @@ -1110,7 +1109,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb, break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - t->expires = round_jiffies(jiffies + next_interval); + t->expires = round_jiffies(jiffies + + __get_cpu_var(next_interval)); add_timer_on(t, cpu); smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; -- cgit v0.10.2 From 5679af4c1625a1534a4321e1ecc3c48a1cf65eb8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 7 Apr 2009 17:06:55 +0200 Subject: x86, mce: fix boot logging logic The earlier patch to change the poller to a separate function subtly broke the boot logging logic. This could lead to machine checks getting logged at boot even when disabled or defaulting to off on some systems. Fix that. [ Impact: bug fix - avoid spurious MCE in log ] Signed-off-by: Andi Kleen Reviewed-by: Hidetoshi Seto Signed-off-by: H. Peter Anvin diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 563933e..4f8c199 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { MCP_TIMESTAMP = (1 << 0), /* log time stamp */ MCP_UC = (1 << 1), /* log uncorrected errors */ + MCP_DONTLOG = (1 << 2), /* only clear, don't log */ }; extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index 82614f1..6fb0b35 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - - mce_log(&m); - add_taint(TAINT_MACHINE_CHECK); + if (!(flags & MCP_DONTLOG)) { + mce_log(&m); + add_taint(TAINT_MACHINE_CHECK); + } /* * Clear state for this bank. @@ -585,7 +586,7 @@ static void mce_init(void *dummy) * Log the machine checks left over from the previous reset. */ bitmap_fill(all_banks, MAX_NR_BANKS); - machine_check_poll(MCP_UC, &all_banks); + machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks); set_in_cr4(X86_CR4_MCE); -- cgit v0.10.2