@@ -40,7 +40,7 @@ struct ring_buffer {
/* AUX area */
long aux_head;
local_t aux_nest;
- long aux_wakeup;
+ long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */
unsigned long aux_pgoff;
int aux_nr_pages;
int aux_overwrite;
@@ -454,7 +454,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
rb->user_page->aux_head = rb->aux_head;
if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
wakeup = true;
- rb->aux_wakeup += rb->aux_watermark;
+ rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
}
if (wakeup) {
@@ -488,7 +488,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
rb->user_page->aux_head = rb->aux_head;
if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
perf_output_wakeup(handle);
- rb->aux_wakeup += rb->aux_watermark;
+ rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
}
The aux_watermark member of struct ring_buffer represents the period (in terms of bytes) at which wakeup events should be generated when data is written to the aux buffer in non-snapshot mode. On hardware that cannot generate an interrupt when the aux_head reaches an arbitrary wakeup index (such as ARM SPE), the aux_head sampled from handle->head in perf_aux_output_{skip,end} may in fact be past the wakeup index. This can lead to wakeup slowly falling behind the head. For example, consider the case where hardware can only generate an interrupt on a page-boundary and the aux buffer is initialised as follows: // Buffer size is 2 * PAGE_SIZE rb->aux_head = rb->aux_wakeup = 0 rb->aux_watermark = PAGE_SIZE / 2 following the first perf_aux_output_begin call, the handle is initialised with: handle->head = 0 handle->size = 2 * PAGE_SIZE handle->wakeup = PAGE_SIZE / 2 and the hardware will be programmed to generate an interrupt at PAGE_SIZE. When the interrupt is raised, the hardware head will be at PAGE_SIZE, so calling perf_aux_output_end(handle, PAGE_SIZE) puts the ring buffer into the following state: rb->aux_head = PAGE_SIZE rb->aux_wakeup = PAGE_SIZE / 2 rb->aux_watermark = PAGE_SIZE / 2 and then the next call to perf_aux_output_begin will result in: handle->head = handle->wakeup = PAGE_SIZE for which the semantics are unclear and, for a smaller aux_watermark (e.g. PAGE_SIZE / 4), then the wakeup would in fact be behind head at this point. This patch fixes the problem by rounding down the aux_head (as sampled from the handle) to the nearest aux_watermark boundary when updating rb->aux_wakeup, therefore taking into account any overruns by the hardware. Cc: Peter Zijlstra <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Reported-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com> --- kernel/events/internal.h | 2 +- kernel/events/ring_buffer.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-)