From 559fdc3c1b624edb1933a875022fe7e27934d11c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 16 Nov 2009 12:45:14 +0100 Subject: [PATCH] perf_event: Optimize perf_output_lock() The purpose of perf_output_{un,}lock() is to: 1) avoid publishing incomplete data [ possible when publishing a head that is ahead of an entry that is still being written ] 2) guarantee fwd progress [ a simple refcount on pending writers doesn't need to drop to 0, making it so would end up implementing something like forced quiecent states of RCU ] To satisfy the above without undue complexity it serializes between CPUs, this means that a pending writer can only be the same cpu in a nested context, and since (under normal operation) a cpu always makes progress we're good -- if the head is only published when the bottom most writer completes. Now we don't need to disable IRQs in order to serialize between CPUs, disabling preemption ought to be sufficient, esp since we already deal with nesting due to NMIs. This avoids potentially expensive (and needless) local IRQ disable/enable ops. Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <1258373161.26714.254.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 - kernel/perf_event.c | 21 +++++++++++---------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index df4e73e3377..7f87563c848 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -714,7 +714,6 @@ struct perf_output_handle { int nmi; int sample; int locked; - unsigned long flags; }; #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 6f4ed3b4cd7..3256e36ad25 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2674,20 +2674,21 @@ static void perf_output_wakeup(struct perf_output_handle *handle) static void perf_output_lock(struct perf_output_handle *handle) { struct perf_mmap_data *data = handle->data; - int cpu; + int cur, cpu = get_cpu(); handle->locked = 0; - local_irq_save(handle->flags); - cpu = smp_processor_id(); + for (;;) { + cur = atomic_cmpxchg(&data->lock, -1, cpu); + if (cur == -1) { + handle->locked = 1; + break; + } + if (cur == cpu) + break; - if (in_nmi() && atomic_read(&data->lock) == cpu) - return; - - while (atomic_cmpxchg(&data->lock, -1, cpu) != -1) cpu_relax(); - - handle->locked = 1; + } } static void perf_output_unlock(struct perf_output_handle *handle) @@ -2733,7 +2734,7 @@ again: if (atomic_xchg(&data->wakeup, 0)) perf_output_wakeup(handle); out: - local_irq_restore(handle->flags); + put_cpu(); } void perf_output_copy(struct perf_output_handle *handle,