drm/i915: Move debug only per-request pid tracking from request to ctx

Since contexts are not currently shared between userspace processes, we
have an exact correspondence between context creator and guilty batch
submitter. Therefore we can save some per-batch work by inspecting the
context->pid upon error instead. Note that we take the context's
creator's pid rather than the file's pid in order to better track fd
passed over sockets.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471254551-25805-29-git-send-email-chris@chris-wilson.co.uk

6 files changed, 32 insertions, 21 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 019df75be5ac..1b4de447ae9f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -460,6 +460,8 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	print_context_stats(m, dev_priv);
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct file_stats stats;
+		struct drm_i915_file_private *file_priv = file->driver_priv;
+		struct drm_i915_gem_request *request;
 		struct task_struct *task;
 
 		memset(&stats, 0, sizeof(stats));
@@ -473,10 +475,17 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		 * still alive (e.g. get_pid(current) => fork() => exit()).
 		 * Therefore, we need to protect this ->comm access using RCU.
 		 */
+		mutex_lock(&dev->struct_mutex);
+		request = list_first_entry_or_null(&file_priv->mm.request_list,
+						   struct drm_i915_gem_request,
+						   client_list);
 		rcu_read_lock();
-		task = pid_task(file->pid, PIDTYPE_PID);
+		task = pid_task(request && request->ctx->pid ?
+				request->ctx->pid : file->pid,
+				PIDTYPE_PID);
 		print_file_stats(m, task ? task->comm : "<unknown>", stats);
 		rcu_read_unlock();
+		mutex_unlock(&dev->struct_mutex);
 	}
 	mutex_unlock(&dev->filelist_mutex);
 
@@ -658,12 +667,11 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 
 		seq_printf(m, "%s requests: %d\n", engine->name, count);
 		list_for_each_entry(req, &engine->request_list, link) {
+			struct pid *pid = req->ctx->pid;
 			struct task_struct *task;
 
 			rcu_read_lock();
-			task = NULL;
-			if (req->pid)
-				task = pid_task(req->pid, PIDTYPE_PID);
+			task = pid ? pid_task(pid, PIDTYPE_PID) : NULL;
 			seq_printf(m, "    %x @ %d: %s [%d]\n",
 				   req->fence.seqno,
 				   (int) (jiffies - req->emitted_jiffies),
@@ -1952,18 +1960,17 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_printf(m, "HW context %u ", ctx->hw_id);
-		if (IS_ERR(ctx->file_priv)) {
-			seq_puts(m, "(deleted) ");
-		} else if (ctx->file_priv) {
-			struct pid *pid = ctx->file_priv->file->pid;
+		if (ctx->pid) {
 			struct task_struct *task;
 
-			task = get_pid_task(pid, PIDTYPE_PID);
+			task = get_pid_task(ctx->pid, PIDTYPE_PID);
 			if (task) {
 				seq_printf(m, "(%s [%d]) ",
 					   task->comm, task->pid);
 				put_task_struct(task);
 			}
+		} else if (IS_ERR(ctx->file_priv)) {
+			seq_puts(m, "(deleted) ");
 		} else {
 			seq_puts(m, "(kernel) ");
 		}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bd58878de77b..d9f29244bafb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -782,6 +782,7 @@ struct drm_i915_error_state {
 
 		struct drm_i915_error_request {
 			long jiffies;
+			pid_t pid;
 			u32 seqno;
 			u32 head;
 			u32 tail;
@@ -880,6 +881,7 @@ struct i915_gem_context {
 	struct drm_i915_private *i915;
 	struct drm_i915_file_private *file_priv;
 	struct i915_hw_ppgtt *ppgtt;
+	struct pid *pid;
 
 	struct i915_ctx_hang_stats hang_stats;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 98d2956f91f4..35950ee46a1d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -158,6 +158,7 @@ void i915_gem_context_free(struct kref *ctx_ref)
 		i915_vma_put(ce->state);
 	}
 
+	put_pid(ctx->pid);
 	list_del(&ctx->link);
 
 	ida_simple_remove(&ctx->i915->context_hw_ida, ctx->hw_id);
@@ -311,6 +312,9 @@ __create_hw_context(struct drm_device *dev,
 		ret = DEFAULT_CONTEXT_HANDLE;
 
 	ctx->file_priv = file_priv;
+	if (file_priv)
+		ctx->pid = get_task_pid(current, PIDTYPE_PID);
+
 	ctx->user_handle = ret;
 	/* NB: Mark all slices as needing a remap so that when the context first
 	 * loads it will restore whatever remap state already exists. If there
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index a0756b553a19..1a215320cefb 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -137,8 +137,6 @@ int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
 	list_add_tail(&req->client_list, &file_priv->mm.request_list);
 	spin_unlock(&file_priv->mm.lock);
 
-	req->pid = get_pid(task_pid(current));
-
 	return 0;
 }
 
@@ -154,9 +152,6 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 	list_del(&request->client_list);
 	request->file_priv = NULL;
 	spin_unlock(&file_priv->mm.lock);
-
-	put_pid(request->pid);
-	request->pid = NULL;
 }
 
 void i915_gem_retire_noop(struct i915_gem_active *active,
@@ -407,7 +402,6 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	req->previous_context = NULL;
 	req->file_priv = NULL;
 	req->batch = NULL;
-	req->pid = NULL;
 	req->elsp_submitted = 0;
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index a66243a6f791..6c72bd8d9423 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -134,9 +134,6 @@ struct drm_i915_gem_request {
 	/** file_priv list entry for this request */
 	struct list_head client_list;
 
-	/** process identifier submitting this request */
-	struct pid *pid;
-
 	/**
 	 * The ELSP only accepts two elements at a time, so we queue
 	 * context/tail pairs on a given queue (ring->execlist_queue) until the
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 8fc21a9c0abd..638664f78dd5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -470,7 +470,8 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				   dev_priv->engine[i].name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++) {
-				err_printf(m, "  seqno 0x%08x, emitted %ld, head 0x%08x, tail 0x%08x\n",
+				err_printf(m, "  pid %d, seqno 0x%08x, emitted %ld, head 0x%08x, tail 0x%08x\n",
+					   ee->requests[j].pid,
 					   ee->requests[j].seqno,
 					   ee->requests[j].jiffies,
 					   ee->requests[j].head,
@@ -1076,6 +1077,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 		request = i915_gem_find_active_request(engine);
 		if (request) {
 			struct intel_ring *ring;
+			struct pid *pid;
 
 			ee->vm = request->ctx->ppgtt ?
 				&request->ctx->ppgtt->base : &ggtt->base;
@@ -1097,11 +1099,12 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				i915_error_object_create(dev_priv,
 							 request->ctx->engine[i].state);
 
-			if (request->pid) {
+			pid = request->ctx->pid;
+			if (pid) {
 				struct task_struct *task;
 
 				rcu_read_lock();
-				task = pid_task(request->pid, PIDTYPE_PID);
+				task = pid_task(pid, PIDTYPE_PID);
 				if (task) {
 					strcpy(ee->comm, task->comm);
 					ee->pid = task->pid;
@@ -1166,6 +1169,10 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			erq->jiffies = request->emitted_jiffies;
 			erq->head = request->head;
 			erq->tail = request->tail;
+
+			rcu_read_lock();
+			erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
+			rcu_read_unlock();
 		}
 	}
 }