Merge tag 'perf-urgent-for-mingo-4.17-20180406' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

- Show group details on the title line in the annotate browser
  and 'perf annotate --stdio2' output, so that the per-event
  columns can have headers (Arnaldo Carvalho de Melo)

- Fixup vertical line separating metrics from instructions and
  cleaning unused lines at the bottom, both in the annotate TUI
  browser (Arnaldo Carvalho de Melo)

- Remove duplicated 'samples' in lost samples warning in
  'perf report' (Arnaldo Carvalho de Melo)

- Synchronize i915_drm.h, silencing the perf build process,
  automagically adding support for the new DRM_I915_QUERY
  ioctl (Arnaldo Carvalho de Melo)

- Make auxtrace_queues__add_buffer() allocate struct buffer,
  from a patchkit already applied (Adrian Hunter)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/include/uapi/drm/i915_drm.h

@@ -318,6 +318,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_OPEN		0x36
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
+#define DRM_I915_QUERY			0x39
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -375,6 +376,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
 #define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
 #define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -1358,7 +1360,9 @@ struct drm_intel_overlay_attrs {
  * active on a given plane.
  */
 
-#define I915_SET_COLORKEY_NONE		(1<<0) /* disable color key matching */
+#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
+						* flags==0 to disable colorkeying.
+						*/
 #define I915_SET_COLORKEY_DESTINATION	(1<<1)
 #define I915_SET_COLORKEY_SOURCE	(1<<2)
 struct drm_intel_sprite_colorkey {
@@ -1604,15 +1608,115 @@ struct drm_i915_perf_oa_config {
 	__u32 n_flex_regs;
 
 	/*
-	 * These fields are pointers to tuples of u32 values (register
-	 * address, value). For example the expected length of the buffer
-	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 * These fields are pointers to tuples of u32 values (register address,
+	 * value). For example the expected length of the buffer pointed by
+	 * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
 	 */
 	__u64 mux_regs_ptr;
 	__u64 boolean_regs_ptr;
 	__u64 flex_regs_ptr;
 };
 
+struct drm_i915_query_item {
+	__u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO    1
+
+	/*
+	 * When set to zero by userspace, this is filled with the size of the
+	 * data to be written at the data_ptr pointer. The kernel sets this
+	 * value to a negative value to signal an error on a particular query
+	 * item.
+	 */
+	__s32 length;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Data will be written at the location pointed by data_ptr when the
+	 * value of length matches the length of the data to be written by the
+	 * kernel.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_query {
+	__u32 num_items;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * This points to an array of num_items drm_i915_query_item structures.
+	 */
+	__u64 items_ptr;
+};
+
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
+ *
+ * data: contains the 3 pieces of information :
+ *
+ * - the slice mask with one bit per slice telling whether a slice is
+ *   available. The availability of slice X can be queried with the following
+ *   formula :
+ *
+ *           (data[X / 8] >> (X % 8)) & 1
+ *
+ * - the subslice mask for each slice with one bit per subslice telling
+ *   whether a subslice is available. The availability of subslice Y in slice
+ *   X can be queried with the following formula :
+ *
+ *           (data[subslice_offset +
+ *                 X * subslice_stride +
+ *                 Y / 8] >> (Y % 8)) & 1
+ *
+ * - the EU mask for each subslice in each slice with one bit per EU telling
+ *   whether an EU is available. The availability of EU Z in subslice Y in
+ *   slice X can be queried with the following formula :
+ *
+ *           (data[eu_offset +
+ *                 (X * max_subslices + Y) * eu_stride +
+ *                 Z / 8] >> (Z % 8)) & 1
+ */
+struct drm_i915_query_topology_info {
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u16 flags;
+
+	__u16 max_slices;
+	__u16 max_subslices;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Offset in data[] at which the subslice masks are stored.
+	 */
+	__u16 subslice_offset;
+
+	/*
+	 * Stride at which each of the subslice masks for each slice are
+	 * stored.
+	 */
+	__u16 subslice_stride;
+
+	/*
+	 * Offset in data[] at which the EU masks are stored.
+	 */
+	__u16 eu_offset;
+
+	/*
+	 * Stride at which each of the EU masks for each subslice are stored.
+	 */
+	__u16 eu_stride;
+
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif

tools/perf/ui/browser.c

@@ -343,8 +343,8 @@ static int __ui_browser__refresh(struct ui_browser *browser)
 	else
 		width += 1;
 
-	SLsmg_fill_region(browser->y + row, browser->x,
-			  browser->height - row, width, ' ');
+	SLsmg_fill_region(browser->y + row + browser->extra_title_lines, browser->x,
+			  browser->rows - row, width, ' ');
 
 	return 0;
 }

tools/perf/ui/browsers/annotate.c

@@ -218,7 +218,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
-	__ui_browser__vline(browser, pcnt_width, 0, browser->height - 1);
+	__ui_browser__vline(browser, pcnt_width, 0, browser->rows - 1);
 	return ret;
 }
 

tools/perf/util/annotate.c

@@ -2600,7 +2600,7 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   bool show_freq)
 {
 	const char *ev_name = perf_evsel__name(evsel);
-	char ref[30] = " show reference callgraph, ";
+	char buf[1024], ref[30] = " show reference callgraph, ";
 	char sample_freq_str[64] = "";
 	unsigned long nr_samples = 0;
 	int nr_members = 1;
@@ -2609,8 +2609,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
 	char unit;
 	int i;
 
-	if (perf_evsel__is_group_event(evsel))
+	if (perf_evsel__is_group_event(evsel)) {
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		ev_name = buf;
                 nr_members = evsel->nr_members;
+	}
 
 	for (i = 0; i < nr_members; i++) {
 		struct sym_hist *ah = annotation__histogram(notes, evsel->idx + i);

tools/perf/util/auxtrace.c

@@ -308,7 +308,11 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 				       struct auxtrace_buffer *buffer,
 				       struct auxtrace_buffer **buffer_ptr)
 {
-	int err;
+	int err = -ENOMEM;
+
+	buffer = memdup(buffer, sizeof(*buffer));
+	if (!buffer)
+		return -ENOMEM;
 
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
@@ -316,24 +320,28 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 	} else if (perf_data__is_pipe(session->data)) {
 		buffer->data = auxtrace_copy_data(buffer->size, session);
 		if (!buffer->data)
-			return -ENOMEM;
+			goto out_free;
 		buffer->data_needs_freeing = true;
 	} else if (BITS_PER_LONG == 32 &&
 		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
 		err = auxtrace_queues__split_buffer(queues, idx, buffer);
 		if (err)
-			return err;
+			goto out_free;
 	}
 
 	err = auxtrace_queues__queue_buffer(queues, idx, buffer);
 	if (err)
-		return err;
+		goto out_free;
 
 	/* FIXME: Doesn't work for split buffer */
 	if (buffer_ptr)
 		*buffer_ptr = buffer;
 
 	return 0;
+
+out_free:
+	auxtrace_buffer__free(buffer);
+	return err;
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)
@@ -348,36 +356,22 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 			       union perf_event *event, off_t data_offset,
 			       struct auxtrace_buffer **buffer_ptr)
 {
-	struct auxtrace_buffer *buffer;
-	unsigned int idx;
-	int err;
+	struct auxtrace_buffer buffer = {
+		.pid = -1,
+		.tid = event->auxtrace.tid,
+		.cpu = event->auxtrace.cpu,
+		.data_offset = data_offset,
+		.offset = event->auxtrace.offset,
+		.reference = event->auxtrace.reference,
+		.size = event->auxtrace.size,
+	};
+	unsigned int idx = event->auxtrace.idx;
 
 	if (filter_cpu(session, event->auxtrace.cpu))
 		return 0;
 
-	buffer = zalloc(sizeof(struct auxtrace_buffer));
-	if (!buffer)
-		return -ENOMEM;
-
-	buffer->pid = -1;
-	buffer->tid = event->auxtrace.tid;
-	buffer->cpu = event->auxtrace.cpu;
-	buffer->data_offset = data_offset;
-	buffer->offset = event->auxtrace.offset;
-	buffer->reference = event->auxtrace.reference;
-	buffer->size = event->auxtrace.size;
-	idx = event->auxtrace.idx;
-
-	err = auxtrace_queues__add_buffer(queues, session, idx, buffer,
-					  buffer_ptr);
-	if (err)
-		goto out_err;
-
-	return 0;
-
-out_err:
-	auxtrace_buffer__free(buffer);
-	return err;
+	return auxtrace_queues__add_buffer(queues, session, idx, &buffer,
+					   buffer_ptr);
 }
 
 static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,

tools/perf/util/session.c

@@ -1591,7 +1591,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		drop_rate = (double)stats->total_lost_samples /
 			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
 		if (drop_rate > 0.05) {
-			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%%!\n\n",
 				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
 				    drop_rate * 100.0);
 		}