From 4f75d8412792777a314ac5c1393a9ed43d695fd1 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 23 Dec 2013 18:05:02 +0100 Subject: [PATCH] x86, mce: Fix mce_start_timer semantics So mce_start_timer() has a 'cpu' argument which is supposed to mean to start a timer on that cpu. However, the code currently starts a timer on the *current* cpu the function runs on and causes the sanity-check in mce_timer_fn to fire: WARNING: CPU: 0 PID: 0 at arch/x86/kernel/cpu/mcheck/mce.c:1286 mce_timer_fn because it is running on the wrong cpu. This was triggered by Prarit Bhargava by offlining all the cpus in succession. Then, we were fiddling with the CMCI storm settings when starting the timer whereas there's no need for that - if there's storm happening on this newly restarted cpu, we're going to be in normal CMCI mode initially and then when the CMCI interrupt starts firing, we're going to go to the polling mode with the timer real soon. Signed-off-by: Borislav Petkov Tested-by: Prarit Bhargava Cc: Tony Luck Reviewed-by: Chen, Gong Link: http://lkml.kernel.org/r/1387722156-5511-1-git-send-email-prarit@redhat.com --- arch/x86/kernel/cpu/mcheck/mce.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a389c1d..4d5419b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1638,15 +1638,15 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) static void mce_start_timer(unsigned int cpu, struct timer_list *t) { - unsigned long iv = mce_adjust_timer(check_interval * HZ); - - __this_cpu_write(mce_next_interval, iv); + unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; + per_cpu(mce_next_interval, cpu) = iv; + t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, smp_processor_id()); + add_timer_on(t, cpu); } static void __mcheck_cpu_init_timer(void) -- 2.7.4