Commit-ID: cf302bfdf3039853fce812ae1ffd0ac24f5b468f
Gitweb: http://git.kernel.org/tip/cf302bfdf3039853fce812ae1ffd0ac24f5b468f
Author: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
AuthorDate: Tue, 21 Apr 2015 16:16:15 +0300
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 27 May 2015 09:17:47 +0200
perf/x86/intel/pt: Document pt_buffer_reset_markers()
The comments in the driver don't make it absolutely clear as to what
exactly is the calling order and other possible constraints of buffer
management functions.
Document constraints and calling order for the buffer configuration
functions. While at it, replace a redundant check in
pt_buffer_reset_markers() with an explanation why it is not needed.
Signed-off-by: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: acme@xxxxxxxxxxxxx
Cc: adrian.hunter@xxxxxxxxx
Cc: hpa@xxxxxxxxx
Link: http://lkml.kernel.org/r/1429622177-22843-4-git-send-email-alexander.shishkin@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/kernel/cpu/perf_event_intel_pt.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 8a45956..b2746ea 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -609,7 +609,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
* @handle: Current output handle.
*
* Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
*/
static int pt_buffer_reset_markers(struct pt_buffer *buf,
struct perf_output_handle *handle)
@@ -618,9 +623,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
unsigned long head = local64_read(&buf->head);
unsigned long idx, npages, wakeup;
- if (buf->snapshot)
- return 0;
-
/* can't stop in the middle of an output region */
if (buf->output_off + handle->size + 1 <
sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
@@ -901,6 +903,7 @@ void intel_pt_interrupt(void)
}
pt_buffer_reset_offsets(buf, pt->handle.head);
+ /* snapshot counters don't use PMI, so it's safe */
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
perf_aux_output_end(&pt->handle, 0, true);
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|