[Intel-gfx] [RFC 7/8] drm/i915: Add support for forwarding execbuffer tags in timestamp sample metadata

[sourab.gupta at intel.com]

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

This patch enables userspace to specify tags (per workload), provided via
execbuffer ioctl, which could be added to timestamps samples, to help
associate samples 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 samples
with their corresponding workloads(execbuffers), which may not be possible
solely with ctx_id or pid information.
This patch enables this mechanism.

Signed-off-by: Sourab Gupta <sourab.gupta at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h     |  2 ++
 drivers/gpu/drm/i915/i915_oa_perf.c | 20 +++++++++++++++++++-
 include/uapi/drm/i915_drm.h         |  8 +++++++-
 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f46687a..c3e823f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1685,6 +1685,7 @@ struct i915_gen_pmu_node {
 	u32 ctx_id;
 	u32 ring;
 	u32 pid;
+	u32 tag;
 };
 
 extern const struct i915_oa_reg i915_oa_3d_mux_config_hsw[];
@@ -2020,6 +2021,7 @@ struct drm_i915_private {
 		struct work_struct event_destroy_work;
 #define I915_GEN_PMU_SAMPLE_RING		(1<<0)
 #define I915_GEN_PMU_SAMPLE_PID			(1<<1)
+#define I915_GEN_PMU_SAMPLE_TAG			(1<<2)
 		int sample_info_flags;
 	} gen_pmu;
 
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index f73d23c..e065e06 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -15,6 +15,7 @@
 #define CTX_INFO_SIZE sizeof(struct drm_i915_ts_node_ctx_id)
 #define RING_INFO_SIZE sizeof(struct drm_i915_ts_node_ring_id)
 #define PID_INFO_SIZE sizeof(struct drm_i915_ts_node_pid)
+#define TAG_INFO_SIZE sizeof(struct drm_i915_ts_node_tag)
 
 static u32 i915_oa_event_paranoid = true;
 
@@ -148,6 +149,8 @@ static void i915_gen_emit_ts_data(struct drm_i915_gem_request *req,
 		entry->ring = ring_id_mask(ring);
 	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_PID)
 		entry->pid = current->pid;
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_TAG)
+		entry->tag = tag;
 	i915_gem_request_assign(&entry->req, ring->outstanding_lazy_request);
 
 	spin_lock(&dev_priv->gen_pmu.lock);
@@ -555,10 +558,12 @@ static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
 	struct drm_i915_ts_node_ctx_id *ctx_info;
 	struct drm_i915_ts_node_ring_id *ring_info;
 	struct drm_i915_ts_node_pid *pid_info;
+	struct drm_i915_ts_node_tag *tag_info;
 	struct perf_raw_record raw;
 
 	BUILD_BUG_ON((TS_DATA_SIZE != 8) || (CTX_INFO_SIZE != 8) ||
-			(RING_INFO_SIZE != 8) || (PID_INFO_SIZE != 8));
+			(RING_INFO_SIZE != 8) || (PID_INFO_SIZE != 8) ||
+			(TAG_INFO_SIZE != 8));
 
 	snapshot = dev_priv->gen_pmu.buffer.addr + node->offset;
 	snapshot_size = TS_DATA_SIZE + CTX_INFO_SIZE;
@@ -581,6 +586,13 @@ static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
 		current_ptr = snapshot + snapshot_size;
 	}
 
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_TAG) {
+		tag_info = (struct drm_i915_ts_node_tag *)current_ptr;
+		tag_info->tag = node->tag;
+		snapshot_size += TAG_INFO_SIZE;
+		current_ptr = snapshot + snapshot_size;
+	}
+
 	/* Note: the raw sample consists of a u32 size member and raw data. The
 	 * combined size of these two fields is required to be 8 byte aligned.
 	 * The size of raw data field is assumed to be 8 byte aligned already.
@@ -1031,6 +1043,9 @@ static int init_gen_pmu_buffer(struct perf_event *event)
 	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_PID)
 		node_size += PID_INFO_SIZE;
 
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_TAG)
+		node_size += TAG_INFO_SIZE;
+
 	/* size has to be aligned to 8 bytes */
 	node_size = ALIGN(node_size, 8);
 	dev_priv->gen_pmu.buffer.node_size = node_size;
@@ -1652,6 +1667,9 @@ static int i915_gen_event_init(struct perf_event *event)
 	if (gen_attr.sample_pid)
 		dev_priv->gen_pmu.sample_info_flags |= I915_GEN_PMU_SAMPLE_PID;
 
+	if (gen_attr.sample_tag)
+		dev_priv->gen_pmu.sample_info_flags |= I915_GEN_PMU_SAMPLE_TAG;
+
 	/* To avoid the complexity of having to accurately filter
 	 * data and marshal to the appropriate client
 	 * we currently only allow exclusive access */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 3dcc862..db91098 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -104,7 +104,8 @@ struct drm_i915_gen_pmu_attr {
 	__u32 size;
 	__u32 sample_ring:1,
 		sample_pid:1,
-		__reserved_1:30;
+		sample_tag:1,
+		__reserved_1:29;
 };
 
 /* Header for PERF_RECORD_DEVICE type events */
@@ -169,6 +170,11 @@ struct drm_i915_ts_node_pid {
 	__u32 pad;
 };
 
+struct drm_i915_ts_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
-- 
1.8.5.1