Merge tag 'perf-urgent-for-mingo-5.5-20191205' of...

Merge tag 'perf-urgent-for-mingo-5.5-20191205' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

 into perf/urgent

Pull perf fixes from Arnaldo Carvalho de Melo:

perf inject:

  Adrian Hunter:

  - Fix processing of ID index for injected instruction tracing

perf report:

  Ravi Bangoria:

  - Replace pr_err() with ui__error(), so that we can see the output
    in the TUI mode instead of showing and immediately restoring the
    screen to the state before perf was started.

  - Don't start --mem-mode/--branch-mode mode if required samples are not
    available.

tools headers UAPI:

  Arnaldo Carvalho de Melo:

  - Sync drm/i915_drm.h with the kernel sources

  - Update tools's copy of drm.h headers.

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

tools/include/uapi/drm/drm.h

@@ -778,11 +778,12 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */
 struct drm_syncobj_timeline_array {
 	__u64 handles;
 	__u64 points;
 	__u32 count_handles;
-	__u32 pad;
+	__u32 flags;
 };
 
 

tools/include/uapi/drm/i915_drm.h

@@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait {
  * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
  */
 #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION	54
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1565,6 +1572,21 @@ struct drm_i915_gem_context_param {
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
+
+/*
+ * I915_CONTEXT_PARAM_PERSISTENCE:
+ *
+ * Allow the context and active rendering to survive the process until
+ * completion. Persistence allows fire-and-forget clients to queue up a
+ * bunch of work, hand the output over to a display server and then quit.
+ * If the context is marked as not persistent, upon closing (either via
+ * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
+ * or process termination), the context and any outstanding requests will be
+ * cancelled (and exported fences for cancelled requests marked as -EIO).
+ *
+ * By default, new contexts allow persistence.
+ */
+#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -1844,23 +1866,31 @@ enum drm_i915_perf_property_id {
 	 * Open the stream for a specific context handle (as used with
 	 * execbuffer2). A stream opened for a specific context this way
 	 * won't typically require root privileges.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
 
 	/**
 	 * A value of 1 requests the inclusion of raw OA unit reports as
 	 * part of stream samples.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_SAMPLE_OA,
 
 	/**
 	 * The value specifies which set of OA unit metrics should be
 	 * be configured, defining the contents of any OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_METRICS_SET,
 
 	/**
 	 * The value specifies the size and layout of OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_FORMAT,
 
@@ -1870,9 +1900,22 @@ enum drm_i915_perf_property_id {
 	 * from this exponent as follows:
 	 *
 	 *   80ns * 2^(period_exponent + 1)
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
+	/**
+	 * Specifying this property is only valid when specify a context to
+	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+	 * will hold preemption of the particular context we want to gather
+	 * performance data about. The execbuf2 submissions must include a
+	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+	 *
+	 * This property is available in perf revision 3.
+	 */
+	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
@@ -1901,6 +1944,8 @@ struct drm_i915_perf_open_param {
  * to close and re-open a stream with the same configuration.
  *
  * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
 
@@ -1908,9 +1953,24 @@ struct drm_i915_perf_open_param {
  * Disable data capture for a stream.
  *
  * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
+/**
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
+
 /**
  * Common to all i915 perf records
  */
@@ -1984,6 +2044,7 @@ struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
 #define DRM_I915_QUERY_ENGINE_INFO	2
+#define DRM_I915_QUERY_PERF_CONFIG      3
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -1995,9 +2056,18 @@ struct drm_i915_query_item {
 	__s32 length;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 *
+	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * following :
+	 *         - DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *         - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *         - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
 	 */
 	__u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
 
 	/*
 	 * Data will be written at the location pointed by data_ptr when the
@@ -2033,8 +2103,10 @@ struct drm_i915_query {
  *           (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 :
+ *   whether a subslice is available. Gen12 has dual-subslices, which are
+ *   similar to two gen11 subslices. For gen12, this array represents dual-
+ *   subslices. The availability of subslice Y in slice X can be queried
+ *   with the following formula :
  *
  *           (data[subslice_offset +
  *                 X * subslice_stride +
@@ -2123,6 +2195,56 @@ struct drm_i915_query_engine_info {
 	struct drm_i915_engine_info engines[];
 };
 
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
+ */
+struct drm_i915_query_perf_config {
+	union {
+		/*
+		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
+		 * this fields to the number of configurations available.
+		 */
+		__u64 n_configs;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 */
+		__u64 config;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 *
+		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
+		 */
+		char uuid[36];
+	};
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
+	 * write an array of __u64 of configuration identifiers.
+	 *
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
+	 * write a struct drm_i915_perf_oa_config. If the following fields of
+	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
+	 * the associated pointers the values of submitted when the
+	 * configuration was created :
+	 *
+	 *         - n_mux_regs
+	 *         - n_boolean_regs
+	 *         - n_flex_regs
+	 */
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif

tools/perf/builtin-inject.c

@@ -403,17 +403,6 @@ static int perf_event__repipe_tracing_data(struct perf_session *session,
 	return err;
 }
 
-static int perf_event__repipe_id_index(struct perf_session *session,
-				       union perf_event *event)
-{
-	int err;
-
-	perf_event__repipe_synth(session->tool, event);
-	err = perf_event__process_id_index(session, event);
-
-	return err;
-}
-
 static int dso__read_build_id(struct dso *dso)
 {
 	if (dso->has_build_id)
@@ -651,7 +640,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.comm	    = perf_event__repipe_comm;
 		inject->tool.namespaces	    = perf_event__repipe_namespaces;
 		inject->tool.exit	    = perf_event__repipe_exit;
-		inject->tool.id_index	    = perf_event__repipe_id_index;
+		inject->tool.id_index	    = perf_event__process_id_index;
 		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
 		inject->tool.auxtrace	    = perf_event__process_auxtrace;
 		inject->tool.aux	    = perf_event__drop_aux;

tools/perf/builtin-report.c

@@ -388,6 +388,14 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
+	if (sort__mode == SORT_MODE__MEMORY) {
+		if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) {
+			ui__error("Selected --mem-mode but no mem data. "
+				  "Did you call perf record without -d?\n");
+			return -1;
+		}
+	}
+
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
 		    (sample_type & PERF_SAMPLE_STACK_USER)) {

tools/perf/util/sort.c

@@ -2681,12 +2681,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
 				if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
-					pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
+					ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
 				else
-					pr_err("Invalid --sort key: `%s'", tok);
+					ui__error("Invalid --sort key: `%s'", tok);
 				break;
 			} else if (ret == -ESRCH) {
-				pr_err("Unknown --sort key: `%s'", tok);
+				ui__error("Unknown --sort key: `%s'", tok);
 				break;
 			}
 		}
@@ -2743,7 +2743,7 @@ static int setup_sort_order(struct evlist *evlist)
 		return 0;
 
 	if (sort_order[1] == '\0') {
-		pr_err("Invalid --sort key: `+'");
+		ui__error("Invalid --sort key: `+'");
 		return -EINVAL;
 	}
 
@@ -2959,6 +2959,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
+		if (sort__mode != SORT_MODE__MEMORY)
+			return -EINVAL;
+
 		return __sort_dimension__add_output(list, sd);
 	}
 
@@ -2968,6 +2971,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
+		if (sort__mode != SORT_MODE__BRANCH)
+			return -EINVAL;
+
 		return __sort_dimension__add_output(list, sd);
 	}
 
@@ -3034,7 +3040,7 @@ static int __setup_output_field(void)
 		strp++;
 
 	if (!strlen(strp)) {
-		pr_err("Invalid --fields key: `+'");
+		ui__error("Invalid --fields key: `+'");
 		goto out;
 	}