From 2ab00456ea8a0d79acb1390659b98416111880b2 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 21 Jun 2013 08:51:35 -0700 Subject: [PATCH] x86: Warn when NMI handlers take large amounts of time I have a system which is causing all kinds of problems. It has 8 NUMA nodes, and lots of cores that can fight over cachelines. If things are not working _perfectly_, then NMIs can take longer than expected. If we get too many of them backed up to each other, we can easily end up in a situation where we are doing nothing *but* running NMIs. The biggest problem, though, is that this happens _silently_. You might be lucky to get an hrtimer warning, but most of the time system simply hangs. This patch should at least give us some warning before we fall off the cliff. the warnings look like this: nmi_handle: perf_event_nmi_handler() took: 26095071 ns The message is triggered whenever we notice the longest NMI we've seen to date. You can always view and reset this value via the debugfs interface if you like. Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra Cc: paulus@samba.org Cc: acme@ghostprotocols.net Cc: Dave Hansen Signed-off-by: Ingo Molnar --- arch/x86/kernel/nmi.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 60308053fdb2..e9bae4c2f2dd 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -82,6 +83,15 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) +static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; +static int __init nmi_warning_debugfs(void) +{ + debugfs_create_u64("nmi_longest_ns", 0644, + arch_debugfs_dir, &nmi_longest_ns); + return 0; +} +fs_initcall(nmi_warning_debugfs); + static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); @@ -96,8 +106,25 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * can be latched at any given time. Walk the whole list * to handle those situations. */ - list_for_each_entry_rcu(a, &desc->head, list) + list_for_each_entry_rcu(a, &desc->head, list) { + u64 before, delta, whole_msecs; + int decimal_msecs; + + before = local_clock(); handled += a->handler(type, regs); + delta = local_clock() - before; + + if (delta < nmi_longest_ns) + continue; + + nmi_longest_ns = delta; + whole_msecs = do_div(delta, (1000 * 1000)); + decimal_msecs = do_div(delta, 1000) % 1000; + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: " + "%lld.%03d msecs\n", a->handler, whole_msecs, + decimal_msecs); + } rcu_read_unlock(); -- 2.20.1