diff mbox

[RFC,5/8] drm/i915: Add support for forwarding ring id in sample metadata through perf

Message ID 1438754144-20435-6-git-send-email-sourab.gupta@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

sourab.gupta@intel.com Aug. 5, 2015, 5:55 a.m. UTC
From: Sourab Gupta <sourab.gupta@intel.com>

This patch introduces flags and adds support for having ring id output with
the timestamp samples and forwarding them through perf.

When the userspace expresses its interest in listening to the ring id
through a gen pmu attr field during event init, the samples generated would
have an additional field appended with the ring id information. This patch
enables this framework, which can be expanded upon to introduce further
fields in the gen pmu attr through which additional metadata information
can be appended to samples.

Signed-off-by: Sourab Gupta <sourab.gupta@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h     |  3 ++
 drivers/gpu/drm/i915/i915_oa_perf.c | 98 +++++++++++++++++++++++++++++++++++--
 include/uapi/drm/i915_drm.h         | 13 +++++
 3 files changed, 111 insertions(+), 3 deletions(-)

Comments

Chris Wilson Aug. 5, 2015, 9:26 a.m. UTC | #1
On Wed, Aug 05, 2015 at 11:25:41AM +0530, sourab.gupta@intel.com wrote:
> @@ -542,18 +548,27 @@ static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
>  	struct perf_sample_data data;
>  	struct perf_event *event = dev_priv->gen_pmu.exclusive_event;
>  	int snapshot_size;
> -	u8 *snapshot;
> +	u8 *snapshot, *current_ptr;
>  	struct drm_i915_ts_node_ctx_id *ctx_info;
> +	struct drm_i915_ts_node_ring_id *ring_info;
>  	struct perf_raw_record raw;
>  
> -	BUILD_BUG_ON(TS_DATA_SIZE != 8);
> -	BUILD_BUG_ON(CTX_INFO_SIZE != 8);
> +	BUILD_BUG_ON((TS_DATA_SIZE != 8) || (CTX_INFO_SIZE != 8) ||
> +			(RING_INFO_SIZE != 8));
>  
>  	snapshot = dev_priv->gen_pmu.buffer.addr + node->offset;
>  	snapshot_size = TS_DATA_SIZE + CTX_INFO_SIZE;
>  
>  	ctx_info = (struct drm_i915_ts_node_ctx_id *)(snapshot + TS_DATA_SIZE);
>  	ctx_info->ctx_id = node->ctx_id;
> +	current_ptr = snapshot + snapshot_size;
> +
> +	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING) {
> +		ring_info = (struct drm_i915_ts_node_ring_id *)current_ptr;
> +		ring_info->ring = node->ring;

Stylewise I would be move familar with current_ptr = ring_info + 1, and
make current_ptr void*. snapshot_size is then redundant.

> +		snapshot_size += RING_INFO_SIZE;
> +		current_ptr = snapshot + snapshot_size;
> +	}
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 46ece85..70f1bd6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1683,6 +1683,7 @@  struct i915_gen_pmu_node {
 	u32 offset;
 	bool discard;
 	u32 ctx_id;
+	u32 ring;
 };
 
 extern const struct i915_oa_reg i915_oa_3d_mux_config_hsw[];
@@ -2016,6 +2017,8 @@  struct drm_i915_private {
 		struct list_head node_list;
 		struct work_struct forward_work;
 		struct work_struct event_destroy_work;
+#define I915_GEN_PMU_SAMPLE_RING		(1<<0)
+		int sample_info_flags;
 	} gen_pmu;
 
 	void (*emit_profiling_data[I915_PROFILE_MAX])
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index 2cf7f1b..41e2407 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -13,6 +13,7 @@ 
 
 #define TS_DATA_SIZE sizeof(struct drm_i915_ts_data)
 #define CTX_INFO_SIZE sizeof(struct drm_i915_ts_node_ctx_id)
+#define RING_INFO_SIZE sizeof(struct drm_i915_ts_node_ring_id)
 
 static u32 i915_oa_event_paranoid = true;
 
@@ -113,6 +114,9 @@  static void i915_oa_emit_perf_report(struct drm_i915_gem_request *req,
 	i915_vma_move_to_active(dev_priv->oa_pmu.oa_rcs_buffer.vma, ring);
 }
 
+/* Returns the ring's ID mask (i.e. I915_EXEC_<ring>) */
+#define ring_id_mask(ring) ((ring)->id + 1)
+
 /*
  * Emits the commands to capture timestamps, into the CS
  */
@@ -139,6 +143,8 @@  static void i915_gen_emit_ts_data(struct drm_i915_gem_request *req,
 	}
 
 	entry->ctx_id = global_ctx_id;
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING)
+		entry->ring = ring_id_mask(ring);
 	i915_gem_request_assign(&entry->req, ring->outstanding_lazy_request);
 
 	spin_lock(&dev_priv->gen_pmu.lock);
@@ -542,18 +548,27 @@  static void forward_one_gen_pmu_sample(struct drm_i915_private *dev_priv,
 	struct perf_sample_data data;
 	struct perf_event *event = dev_priv->gen_pmu.exclusive_event;
 	int snapshot_size;
-	u8 *snapshot;
+	u8 *snapshot, *current_ptr;
 	struct drm_i915_ts_node_ctx_id *ctx_info;
+	struct drm_i915_ts_node_ring_id *ring_info;
 	struct perf_raw_record raw;
 
-	BUILD_BUG_ON(TS_DATA_SIZE != 8);
-	BUILD_BUG_ON(CTX_INFO_SIZE != 8);
+	BUILD_BUG_ON((TS_DATA_SIZE != 8) || (CTX_INFO_SIZE != 8) ||
+			(RING_INFO_SIZE != 8));
 
 	snapshot = dev_priv->gen_pmu.buffer.addr + node->offset;
 	snapshot_size = TS_DATA_SIZE + CTX_INFO_SIZE;
 
 	ctx_info = (struct drm_i915_ts_node_ctx_id *)(snapshot + TS_DATA_SIZE);
 	ctx_info->ctx_id = node->ctx_id;
+	current_ptr = snapshot + snapshot_size;
+
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING) {
+		ring_info = (struct drm_i915_ts_node_ring_id *)current_ptr;
+		ring_info->ring = node->ring;
+		snapshot_size += RING_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.
@@ -999,6 +1014,9 @@  static int init_gen_pmu_buffer(struct perf_event *event)
 
 	node_size = TS_DATA_SIZE + CTX_INFO_SIZE;
 
+	if (dev_priv->gen_pmu.sample_info_flags & I915_GEN_PMU_SAMPLE_RING)
+		node_size += RING_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;
@@ -1533,16 +1551,90 @@  static int i915_oa_event_event_idx(struct perf_event *event)
 	return 0;
 }
 
+static int i915_gen_pmu_copy_attr(struct drm_i915_gen_pmu_attr __user *uattr,
+			     struct drm_i915_gen_pmu_attr *attr)
+{
+	u32 size;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, I915_GEN_PMU_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * zero the full structure, so that a short copy will be nice.
+	 */
+	memset(attr, 0, sizeof(*attr));
+
+	ret = get_user(size, &uattr->size);
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (size < I915_GEN_PMU_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+		size = sizeof(*attr);
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
 static int i915_gen_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(event->pmu, typeof(*dev_priv), gen_pmu.pmu);
+	struct drm_i915_gen_pmu_attr gen_attr;
 	unsigned long lock_flags;
 	int ret = 0;
 
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
+	BUILD_BUG_ON(sizeof(struct drm_i915_gen_pmu_attr) !=
+			I915_GEN_PMU_ATTR_SIZE_VER0);
+
+	ret = i915_gen_pmu_copy_attr(to_user_ptr(event->attr.config),
+				&gen_attr);
+	if (ret)
+		return ret;
+
+	if (gen_attr.sample_ring)
+		dev_priv->gen_pmu.sample_info_flags |=
+				I915_GEN_PMU_SAMPLE_RING;
+
 	/* 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 4a19c9b..5b484fb 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -81,6 +81,8 @@ 
 
 #define I915_OA_ATTR_SIZE_VER0		32  /* sizeof first published struct */
 
+#define I915_GEN_PMU_ATTR_SIZE_VER0	8  /* sizeof first published struct */
+
 typedef struct _drm_i915_oa_attr {
 	__u32 size;
 
@@ -98,6 +100,12 @@  typedef struct _drm_i915_oa_attr {
 		__reserved_1:60;
 } drm_i915_oa_attr_t;
 
+struct drm_i915_gen_pmu_attr {
+	__u32 size;
+	__u32 sample_ring:1,
+		__reserved_1:31;
+};
+
 /* Header for PERF_RECORD_DEVICE type events */
 typedef struct _drm_i915_oa_event_header {
 	__u32 type;
@@ -150,6 +158,11 @@  struct drm_i915_ts_node_ctx_id {
 	__u32 pad;
 };
 
+struct drm_i915_ts_node_ring_id {
+	__u32 ring;
+	__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