Commit f4c0b0aa authored by Will Deacon's avatar Will Deacon Committed by Ingo Molnar

perf/core: Keep AUX flags in the output handle

In preparation for adding more flags to perf AUX records, introduce a
separate API for setting the flags for a session, rather than appending
more bool arguments to perf_aux_output_end. This allows to set each
flag at the time a corresponding condition is detected, instead of
tracking it in each driver's private state.
Signed-off-by: default avatarWill Deacon <will.deacon@arm.com>
Signed-off-by: default avatarAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20170220133352.17995-3-alexander.shishkin@linux.intel.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent ed827adb
......@@ -63,7 +63,6 @@ struct bts_buffer {
unsigned int cur_buf;
bool snapshot;
local_t data_size;
local_t lost;
local_t head;
unsigned long end;
void **data_pages;
......@@ -199,7 +198,8 @@ static void bts_update(struct bts_ctx *bts)
return;
if (ds->bts_index >= ds->bts_absolute_maximum)
local_inc(&buf->lost);
perf_aux_output_flag(&bts->handle,
PERF_AUX_FLAG_TRUNCATED);
/*
* old and head are always in the same physical buffer, so we
......@@ -276,7 +276,7 @@ static void bts_event_start(struct perf_event *event, int flags)
return;
fail_end_stop:
perf_aux_output_end(&bts->handle, 0, false);
perf_aux_output_end(&bts->handle, 0);
fail_stop:
event->hw.state = PERF_HES_STOPPED;
......@@ -319,9 +319,8 @@ static void bts_event_stop(struct perf_event *event, int flags)
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
perf_aux_output_end(&bts->handle,
local_xchg(&buf->data_size, 0));
}
cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
......@@ -484,8 +483,7 @@ int intel_bts_interrupt(void)
if (old_head == local_read(&buf->head))
return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
buf = perf_aux_output_begin(&bts->handle, event);
if (buf)
......@@ -500,7 +498,7 @@ int intel_bts_interrupt(void)
* cleared handle::event
*/
barrier();
perf_aux_output_end(&bts->handle, 0, false);
perf_aux_output_end(&bts->handle, 0);
}
}
......
......@@ -753,7 +753,8 @@ static void pt_handle_status(struct pt *pt)
*/
if (!pt_cap_get(PT_CAP_topa_multiple_entries) ||
buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
local_inc(&buf->lost);
perf_aux_output_flag(&pt->handle,
PERF_AUX_FLAG_TRUNCATED);
advance++;
}
}
......@@ -846,8 +847,10 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
/* 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))
sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
return -EINVAL;
}
/* single entry ToPA is handled by marking all regions STOP=1 INT=1 */
......@@ -1192,8 +1195,7 @@ void intel_pt_interrupt(void)
pt_update_head(pt);
perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
local_xchg(&buf->lost, 0));
perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
if (!event->hw.state) {
int ret;
......@@ -1208,7 +1210,7 @@ void intel_pt_interrupt(void)
/* 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);
perf_aux_output_end(&pt->handle, 0);
return;
}
......@@ -1280,7 +1282,7 @@ static void pt_event_start(struct perf_event *event, int mode)
return;
fail_end_stop:
perf_aux_output_end(&pt->handle, 0, true);
perf_aux_output_end(&pt->handle, 0);
fail_stop:
hwc->state = PERF_HES_STOPPED;
}
......@@ -1321,8 +1323,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
pt->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
local_xchg(&buf->lost, 0));
perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
}
}
......
......@@ -143,7 +143,6 @@ struct pt_buffer {
size_t output_off;
unsigned long nr_pages;
local_t data_size;
local_t lost;
local64_t head;
bool snapshot;
unsigned long stop_pos, intr_pos;
......
......@@ -321,7 +321,7 @@ static int etb_set_buffer(struct coresight_device *csdev,
static unsigned long etb_reset_buffer(struct coresight_device *csdev,
struct perf_output_handle *handle,
void *sink_config, bool *lost)
void *sink_config)
{
unsigned long size = 0;
struct cs_buffers *buf = sink_config;
......@@ -343,7 +343,6 @@ static unsigned long etb_reset_buffer(struct coresight_device *csdev,
* resetting parameters here and squaring off with the ring
* buffer API in the tracer PMU is fine.
*/
*lost = !!local_xchg(&buf->lost, 0);
size = local_xchg(&buf->data_size, 0);
}
......@@ -385,7 +384,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
(unsigned long)write_ptr);
write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
local_inc(&buf->lost);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
/*
......@@ -396,7 +395,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
*/
status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
if (status & ETB_STATUS_RAM_FULL) {
local_inc(&buf->lost);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
to_read = capacity;
read_ptr = write_ptr;
} else {
......@@ -429,7 +428,7 @@ static void etb_update_buffer(struct coresight_device *csdev,
if (read_ptr > (drvdata->buffer_depth - 1))
read_ptr -= drvdata->buffer_depth;
/* let the decoder know we've skipped ahead */
local_inc(&buf->lost);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
/* finally tell HW where we want to start reading from */
......
......@@ -302,7 +302,8 @@ static void etm_event_start(struct perf_event *event, int flags)
return;
fail_end_stop:
perf_aux_output_end(handle, 0, true);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
perf_aux_output_end(handle, 0);
fail:
event->hw.state = PERF_HES_STOPPED;
goto out;
......@@ -310,7 +311,6 @@ static void etm_event_start(struct perf_event *event, int flags)
static void etm_event_stop(struct perf_event *event, int mode)
{
bool lost;
int cpu = smp_processor_id();
unsigned long size;
struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
......@@ -348,10 +348,9 @@ static void etm_event_stop(struct perf_event *event, int mode)
return;
size = sink_ops(sink)->reset_buffer(sink, handle,
event_data->snk_config,
&lost);
event_data->snk_config);
perf_aux_output_end(handle, size, lost);
perf_aux_output_end(handle, size);
}
/* Disabling the path make its elements available to other sessions */
......
......@@ -76,7 +76,6 @@ enum cs_mode {
* @nr_pages: max number of pages granted to us
* @offset: offset within the current buffer
* @data_size: how much we collected in this run
* @lost: other than zero if we had a HW buffer wrap around
* @snapshot: is this run in snapshot mode
* @data_pages: a handle the ring buffer
*/
......@@ -85,7 +84,6 @@ struct cs_buffers {
unsigned int nr_pages;
unsigned long offset;
local_t data_size;
local_t lost;
bool snapshot;
void **data_pages;
};
......
......@@ -329,7 +329,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev,
static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
struct perf_output_handle *handle,
void *sink_config, bool *lost)
void *sink_config)
{
long size = 0;
struct cs_buffers *buf = sink_config;
......@@ -350,7 +350,6 @@ static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
* resetting parameters here and squaring off with the ring
* buffer API in the tracer PMU is fine.
*/
*lost = !!local_xchg(&buf->lost, 0);
size = local_xchg(&buf->data_size, 0);
}
......@@ -389,7 +388,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
*/
status = readl_relaxed(drvdata->base + TMC_STS);
if (status & TMC_STS_FULL) {
local_inc(&buf->lost);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
to_read = drvdata->size;
} else {
to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);
......@@ -434,7 +433,7 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev,
read_ptr -= drvdata->size;
/* Tell the HW */
writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
local_inc(&buf->lost);
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
cur = buf->cur;
......
......@@ -201,7 +201,7 @@ struct coresight_ops_sink {
void *sink_config);
unsigned long (*reset_buffer)(struct coresight_device *csdev,
struct perf_output_handle *handle,
void *sink_config, bool *lost);
void *sink_config);
void (*update_buffer)(struct coresight_device *csdev,
struct perf_output_handle *handle,
void *sink_config);
......
......@@ -801,6 +801,7 @@ struct perf_output_handle {
struct ring_buffer *rb;
unsigned long wakeup;
unsigned long size;
u64 aux_flags;
union {
void *addr;
unsigned long head;
......@@ -849,10 +850,11 @@ perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
extern void *perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event);
extern void perf_aux_output_end(struct perf_output_handle *handle,
unsigned long size, bool truncated);
unsigned long size);
extern int perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size);
extern void *perf_get_aux(struct perf_output_handle *handle);
extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
......@@ -1268,8 +1270,8 @@ static inline void *
perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event) { return NULL; }
static inline void
perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
bool truncated) { }
perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{ }
static inline int
perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size) { return -EINVAL; }
......
......@@ -297,6 +297,19 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
rb->paused = 1;
}
void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
{
/*
* OVERWRITE is determined by perf_aux_output_end() and can't
* be passed in directly.
*/
if (WARN_ON_ONCE(flags & PERF_AUX_FLAG_OVERWRITE))
return;
handle->aux_flags |= flags;
}
EXPORT_SYMBOL_GPL(perf_aux_output_flag);
/*
* This is called before hardware starts writing to the AUX area to
* obtain an output handle and make sure there's room in the buffer.
......@@ -360,6 +373,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
handle->event = event;
handle->head = aux_head;
handle->size = 0;
handle->aux_flags = 0;
/*
* In overwrite mode, AUX data stores do not depend on aux_tail,
......@@ -408,34 +422,32 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
* of the AUX buffer management code is that after pmu::stop(), the AUX
* transaction must be stopped and therefore drop the AUX reference count.
*/
void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
bool truncated)
void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{
struct ring_buffer *rb = handle->rb;
bool wakeup = truncated;
bool wakeup = !!handle->aux_flags;
unsigned long aux_head;
u64 flags = 0;
if (truncated)
flags |= PERF_AUX_FLAG_TRUNCATED;
/* in overwrite mode, driver provides aux_head via handle */
if (rb->aux_overwrite) {
flags |= PERF_AUX_FLAG_OVERWRITE;
handle->aux_flags |= PERF_AUX_FLAG_OVERWRITE;
aux_head = handle->head;
local_set(&rb->aux_head, aux_head);
} else {
handle->aux_flags &= ~PERF_AUX_FLAG_OVERWRITE;
aux_head = local_read(&rb->aux_head);
local_add(size, &rb->aux_head);
}
if (size || flags) {
if (size || handle->aux_flags) {
/*
* Only send RECORD_AUX if we have something useful to communicate
*/
perf_event_aux_event(handle->event, aux_head, size, flags);
perf_event_aux_event(handle->event, aux_head, size,
handle->aux_flags);
}
aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
......@@ -446,7 +458,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
}
if (wakeup) {
if (truncated)
if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
handle->event->pending_disable = 1;
perf_output_wakeup(handle);
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment