From 5bd00f6db012f75b42434d39b7fec98b95c1afcc Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Tue, 9 May 2023 08:31:23 +1000 Subject: [PATCH 1/2] smp: Reduce logging due to dump_stack of CSD waiters If a waiter is waiting for CSD lock, its call stack will not change between first and subsequent hang detection for the same CSD lock. Therefore, do dump_stack only for first-time detection for a given waiter. This avoids excessive logging on systems with hundreds of CPUs where repetitive dump_stack from hundreds of CPUs would otherwise flood the console. Signed-off-by: Imran Khan Cc: Peter Zijlstra Cc: Juergen Gross Cc: Valentin Schneider Cc: Yury Norov Signed-off-by: Paul E. McKenney --- kernel/smp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/smp.c b/kernel/smp.c index 385179dae360..1d41a0cb54f1 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -259,7 +259,8 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * arch_send_call_function_single_ipi(cpu); } } - dump_stack(); + if (firsttime) + dump_stack(); *ts1 = ts2; return false; From 0d3a00b370424f5f1b9fd037bc8a4a3e7cbf0939 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Tue, 9 May 2023 08:31:24 +1000 Subject: [PATCH 2/2] smp: Reduce NMI traffic from CSD waiters to CSD destination On systems with hundreds of CPUs, if most of the CPUs detect a CSD hang, then all of these waiting CPUs send an NMI to the destination CPU in order to dump its backtrace. Given enough NMIs, the destination CPU will spent much of its time producing backtraces, thus further delaying that CPU's response to the original CSD IPI. In the worst case, by the time destination CPU is done producing all of these backtrace NMIs, the CSD wait timeout will have elapsed so that the waiters resend their backtrace NMIs again, further delaying forward progress. Therefore, to avoid these delays, issue the backtrace NMI only from the first waiter. The destination CPU's other waiters can make use of backtrace obtained from the first waiter's NMI. Signed-off-by: Imran Khan Cc: Peter Zijlstra Cc: Juergen Gross Cc: Valentin Schneider Cc: Yury Norov Signed-off-by: Paul E. McKenney --- kernel/smp.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/smp.c b/kernel/smp.c index 1d41a0cb54f1..8455a53465af 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -46,6 +46,8 @@ static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); +static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); + static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) @@ -253,7 +255,8 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { - dump_cpu_task(cpu); + if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) + dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); @@ -434,9 +437,14 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) struct llist_node *entry, *prev; struct llist_head *head; static bool warned; + atomic_t *tbt; lockdep_assert_irqs_disabled(); + /* Allow waiters to send backtrace NMI from here onwards */ + tbt = this_cpu_ptr(&trigger_backtrace); + atomic_set_release(tbt, 1); + head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry);