[GIT PULL] perf fixes
From: Ingo Molnar
Date: Fri Nov 01 2013 - 05:57:04 EST
Linus,
Please pull the latest perf-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus
# HEAD: e8a923cc1fff6e627f906655ad52ee694ef2f6d7 perf/x86: Fix NMI measurements
Two fixes:
- Fix 'NMI handler took too long to run' false positives. [ Genuine
NMI overhead speedups will come for v3.13, this commit only fixes
a measurement bug. ]
- Fix perf ring-buffer missed barrier causing (rare) ring-buffer
data corruption on ppc64.
Thanks,
Ingo
------------------>
Peter Zijlstra (2):
perf: Fix perf ring buffer memory ordering
perf/x86: Fix NMI measurements
arch/x86/kernel/cpu/perf_event.c | 6 +++---
arch/x86/kernel/nmi.c | 4 ++--
include/uapi/linux/perf_event.h | 12 +++++++-----
kernel/events/ring_buffer.c | 31 +++++++++++++++++++++++++++----
4 files changed, 39 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9d84491..8a87a32 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void)
static int __kprobes
perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
- int ret;
u64 start_clock;
u64 finish_clock;
+ int ret;
if (!atomic_read(&active_events))
return NMI_DONE;
- start_clock = local_clock();
+ start_clock = sched_clock();
ret = x86_pmu.handle_irq(regs);
- finish_clock = local_clock();
+ finish_clock = sched_clock();
perf_sample_event_took(finish_clock - start_clock);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ba77ebc..6fcb49c 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
u64 before, delta, whole_msecs;
int remainder_ns, decimal_msecs, thishandled;
- before = local_clock();
+ before = sched_clock();
thishandled = a->handler(type, regs);
handled += thishandled;
- delta = local_clock() - before;
+ delta = sched_clock() - before;
trace_nmi_handler(a->handler, (int)delta, thishandled);
if (delta < nmi_longest_ns)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 009a655..2fc1602 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -456,13 +456,15 @@ struct perf_event_mmap_page {
/*
* Control data for the mmap() data buffer.
*
- * User-space reading the @data_head value should issue an rmb(), on
- * SMP capable platforms, after reading this value -- see
- * perf_event_wakeup().
+ * User-space reading the @data_head value should issue an smp_rmb(),
+ * after reading this value.
*
* When the mapping is PROT_WRITE the @data_tail value should be
- * written by userspace to reflect the last read data. In this case
- * the kernel will not over-write unread data.
+ * written by userspace to reflect the last read data, after issueing
+ * an smp_mb() to separate the data read from the ->data_tail store.
+ * In this case the kernel will not over-write unread data.
+ *
+ * See perf_output_put_handle() for the data ordering.
*/
__u64 data_head; /* head in the data section */
__u64 data_tail; /* user-space written tail */
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index cd55144..9c2ddfb 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -87,10 +87,31 @@ again:
goto out;
/*
- * Publish the known good head. Rely on the full barrier implied
- * by atomic_dec_and_test() order the rb->head read and this
- * write.
+ * Since the mmap() consumer (userspace) can run on a different CPU:
+ *
+ * kernel user
+ *
+ * READ ->data_tail READ ->data_head
+ * smp_mb() (A) smp_rmb() (C)
+ * WRITE $data READ $data
+ * smp_wmb() (B) smp_mb() (D)
+ * STORE ->data_head WRITE ->data_tail
+ *
+ * Where A pairs with D, and B pairs with C.
+ *
+ * I don't think A needs to be a full barrier because we won't in fact
+ * write data until we see the store from userspace. So we simply don't
+ * issue the data WRITE until we observe it. Be conservative for now.
+ *
+ * OTOH, D needs to be a full barrier since it separates the data READ
+ * from the tail WRITE.
+ *
+ * For B a WMB is sufficient since it separates two WRITEs, and for C
+ * an RMB is sufficient since it separates two READs.
+ *
+ * See perf_output_begin().
*/
+ smp_wmb();
rb->user_page->data_head = head;
/*
@@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle,
* Userspace could choose to issue a mb() before updating the
* tail pointer. So that all reads will be completed before the
* write is issued.
+ *
+ * See perf_output_put_handle().
*/
tail = ACCESS_ONCE(rb->user_page->data_tail);
- smp_rmb();
+ smp_mb();
offset = head = local_read(&rb->head);
head += size;
if (unlikely(!perf_output_space(rb, tail, offset, head)))
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/