[RFC 8/8] drm/i915: Add support to add execbuffer tags to OA counter reports

[sourab.gupta@intel.com]

From: Sourab Gupta <sourab.gupta@intel.com>

This patch enables userspace to specify tags (per workload), provided via
execbuffer ioctl, which could be added to OA reports, to help associate
reports with the corresponding workloads.

There may be multiple stages within a single context, from a userspace
perspective. An ability is needed to individually associate the OA reports
with their corresponding workloads(execbuffers), which may not be possible
solely with ctx_id or pid information. This patch enables such a mechanism.

In this patch, rsvd2 field of execbuffer arguments is being utilized for
passing the tag. A new bitfield in execbuffer flags is introduced in order
to inform kernel of the tag being passed in execbuffer arguments.

Signed-off-by: Sourab Gupta <sourab.gupta@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h            |  9 ++++++---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  8 ++++++--
 drivers/gpu/drm/i915/i915_oa_perf.c        | 23 ++++++++++++++++++++---
 include/uapi/drm/i915_drm.h                | 21 ++++++++++++++++++---
 4 files changed, 50 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 337a721..9409b4a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1672,6 +1672,7 @@ struct i915_oa_rcs_node {
 	bool discard;
 	u32 ctx_id;
 	u32 pid;
+	u32 tag;
 };
 
 extern const struct i915_oa_reg i915_oa_3d_mux_config_hsw[];
@@ -1980,11 +1981,12 @@ struct drm_i915_private {
 		struct work_struct work_timer;
 		struct work_struct work_event_destroy;
 #define I915_OA_SAMPLE_PID		(1<<0)
+#define I915_OA_SAMPLE_TAG		(1<<1)
 		int sample_info_flags;
 	} oa_pmu;
 
 	void (*insert_profile_cmd[I915_PROFILE_MAX])
-		(struct intel_ringbuffer *ringbuf, u32 ctx_id);
+		(struct intel_ringbuffer *ringbuf, u32 ctx_id, int tag);
 #endif
 
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
@@ -3165,7 +3167,8 @@ void i915_oa_context_pin_notify(struct drm_i915_private *dev_priv,
 				struct intel_context *context);
 void i915_oa_context_unpin_notify(struct drm_i915_private *dev_priv,
 				  struct intel_context *context);
-void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id);
+void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id,
+				int tag);
 #else
 static inline void
 i915_oa_context_pin_notify(struct drm_i915_private *dev_priv,
@@ -3174,7 +3177,7 @@ static inline void
 i915_oa_context_unpin_notify(struct drm_i915_private *dev_priv,
 			     struct intel_context *context) {}
 void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf,
-				u32 ctx_id) {};
+				u32 ctx_id, int tag) {};
 #endif
 
 /* i915_gem_evict.c */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 2f8971b..53d228c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1203,6 +1203,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 	u64 exec_len;
 	int instp_mode;
 	u32 instp_mask;
+	u32 tag = 0;
 	int i, ret = 0;
 
 	if (args->num_cliprects != 0) {
@@ -1317,8 +1318,11 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 			goto error;
 	}
 
+	if (args->flags & I915_EXEC_TAG)
+		tag = i915_execbuffer2_get_tag(*args);
+
 	i915_insert_profiling_cmd(ring->buffer,
-		i915_execbuffer2_get_context_id(*args));
+		i915_execbuffer2_get_context_id(*args), tag);
 
 	exec_len = args->batch_len;
 	if (cliprects) {
@@ -1343,7 +1347,7 @@ i915_gem_ringbuffer_submission(struct drm_device *dev, struct drm_file *file,
 	}
 
 	i915_insert_profiling_cmd(ring->buffer,
-		i915_execbuffer2_get_context_id(*args));
+		i915_execbuffer2_get_context_id(*args), tag);
 
 	trace_i915_gem_ring_dispatch(intel_ring_get_request(ring), dispatch_flags);
 
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index 15920d1291..839ebb4 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -25,7 +25,8 @@ static int hsw_perf_format_sizes[] = {
 	64   /* C4_B8_HSW */
 };
 
-void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id)
+void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id,
+				int tag)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -33,11 +34,11 @@ void i915_insert_profiling_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id)
 
 	for (i = I915_PROFILE_OA; i < I915_PROFILE_MAX; i++) {
 		if (dev_priv->insert_profile_cmd[i])
-			dev_priv->insert_profile_cmd[i](ringbuf, ctx_id);
+			dev_priv->insert_profile_cmd[i](ringbuf, ctx_id, tag);
 	}
 }
 
-void i915_oa_insert_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id)
+void i915_oa_insert_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id, int tag)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -59,6 +60,8 @@ void i915_oa_insert_cmd(struct intel_ringbuffer *ringbuf, u32 ctx_id)
 	entry->ctx_id = ctx_id;
 	if (dev_priv->oa_pmu.sample_info_flags & I915_OA_SAMPLE_PID)
 		entry->pid = current->pid;
+	if (dev_priv->oa_pmu.sample_info_flags & I915_OA_SAMPLE_TAG)
+		entry->tag = tag;
 	i915_gem_request_assign(&entry->req, ring->outstanding_lazy_request);
 
 	spin_lock_irqsave(&dev_priv->oa_pmu.lock, lock_flags);
@@ -320,6 +323,7 @@ static void forward_one_oa_rcs_sample(struct drm_i915_private *dev_priv,
 	u8 *snapshot, *current_ptr;
 	struct drm_i915_oa_node_ctx_id *ctx_info;
 	struct drm_i915_oa_node_pid *pid_info;
+	struct drm_i915_oa_node_tag *tag_info;
 	struct perf_raw_record raw;
 	u64 snapshot_ts;
 
@@ -338,6 +342,13 @@ static void forward_one_oa_rcs_sample(struct drm_i915_private *dev_priv,
 		current_ptr = snapshot + snapshot_size;
 	}
 
+	if (dev_priv->oa_pmu.sample_info_flags & I915_OA_SAMPLE_TAG) {
+		tag_info = (struct drm_i915_oa_node_tag *)current_ptr;
+		tag_info->tag = node->tag;
+		snapshot_size += sizeof(*tag_info);
+		current_ptr = snapshot + snapshot_size;
+	}
+
 	/* Flush the periodic snapshots till the ts of this OA report */
 	snapshot_ts = *(u64 *)(snapshot + 4);
 	flush_oa_snapshots(dev_priv, true, snapshot_ts);
@@ -694,6 +705,9 @@ static int init_oa_rcs_buffer(struct perf_event *event)
 	if (dev_priv->oa_pmu.sample_info_flags & I915_OA_SAMPLE_PID)
 		node_size += sizeof(struct drm_i915_oa_node_pid);
 
+	if (dev_priv->oa_pmu.sample_info_flags & I915_OA_SAMPLE_TAG)
+		node_size += sizeof(struct drm_i915_oa_node_tag);
+
 	/* node size has to be aligned to 64 bytes, since only 64 byte aligned
 	 * addresses can be given to OA unit for dumping OA reports */
 	node_size = ALIGN(node_size, 64);
@@ -850,6 +864,9 @@ static int i915_oa_event_init(struct perf_event *event)
 		if (oa_attr.sample_pid)
 			dev_priv->oa_pmu.sample_info_flags |=
 					I915_OA_SAMPLE_PID;
+		if (oa_attr.sample_tag)
+			dev_priv->oa_pmu.sample_info_flags |=
+					I915_OA_SAMPLE_TAG;
 	}
 
 	report_format = oa_attr.format;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 65e8297..1084178 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -94,7 +94,8 @@ typedef struct _drm_i915_oa_attr {
 	__u64 single_context : 1,
 		multiple_context_mode:1,
 		sample_pid:1,
-		__reserved_1:61;
+		sample_tag:1,
+		__reserved_1:60;
 } drm_i915_oa_attr_t;
 
 /* Header for PERF_RECORD_DEVICE type events */
@@ -134,6 +135,11 @@ struct drm_i915_oa_node_pid {
 	__u32 pad;
 };
 
+struct drm_i915_oa_node_tag {
+	__u32 tag;
+	__u32 pad;
+};
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
@@ -802,7 +808,7 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
 	__u64 flags;
 	__u64 rsvd1; /* now used for context info */
-	__u64 rsvd2;
+	__u64 rsvd2; /* used for tag */
 };
 
 /** Resets the SO write offset registers for transform feedback on gen7. */
@@ -840,7 +846,12 @@ struct drm_i915_gem_execbuffer2 {
 #define I915_EXEC_BSD_RING1		(1<<13)
 #define I915_EXEC_BSD_RING2		(2<<13)
 
-#define __I915_EXEC_UNKNOWN_FLAGS -(1<<15)
+/** Inform the kernel that tag is passed through rsvd2 field of
+ * execbuffer args
+ */
+#define I915_EXEC_TAG			(1<<15)
+
+#define __I915_EXEC_UNKNOWN_FLAGS -(1<<16)
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -848,6 +859,10 @@ struct drm_i915_gem_execbuffer2 {
 #define i915_execbuffer2_get_context_id(eb2) \
 	((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
 
+#define I915_EXEC_TAG_MASK		(0xffffffff)
+#define i915_execbuffer2_get_tag(eb2) \
+	((eb2).rsvd2 & I915_EXEC_TAG_MASK)
+
 struct drm_i915_gem_pin {
 	/** Handle of the buffer to be pinned. */
 	__u32 handle;
-- 
1.8.5.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx