[PATCH 36/48] drm/i915: Get context early in execbuf

[Ben Widawsky <benjamin.widawsky@intel.com>]

From: Ben Widawsky <ben@bwidawsk.net>

We need to have the address space when reserving space for the objects.
Since the address space and context are tied together, and reserve
occurs before context switch (for good reason), we must lookup our
context earlier in the process.

This leaves some room for optimizations where we no longer need to use
ctx_id in certain places. This will be addressed in a subsequent patch.

Important tricky bit:
Because slow relocations during execbuffer drop struct_mutex

Perhaps it would be best to acquire the reference when we get the
context, but I'll save that for another day (note I have written the
patch before, and I found the changes required to be uglier than this).

Note that since we currently access everything via context id, and not
the data structure this is fine, though not desirable. The next change
attempts to get the context only once via the context ID idr lookup, and
as such, the following can happen:

CTX-A is created, refcount = 1
CTX-A execbuf, mutex dropped
close IOCTL called on CTX-A, refcount = 0
CTX-A resumes in execbuf.

v2: Rebased on top of
commit b6359918b885da7c7b58c050674278dbd06020ab
Author: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date:   Wed Oct 30 15:44:16 2013 +0200

    drm/i915: add i915_get_reset_stats_ioctl

v3: Rebased on top of
commit 25b3dfc87bff80317d67ddd2cd4cfb91e6fe7d79
Author: Mika Westerberg <mika.westerberg@linux.intel.com>
Date:   Tue Nov 12 11:57:30 2013 +0200

Author: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date:   Tue Nov 26 16:14:33 2013 +0200

    drm/i915: check context reset stats before relocations

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_drv.h            |  8 ++----
 drivers/gpu/drm/i915/i915_gem.c            |  2 +-
 drivers/gpu/drm/i915/i915_gem_context.c    | 32 ++++------------------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 44 ++++++++++++++++++------------
 drivers/gpu/drm/i915/intel_uncore.c        |  8 ++++--
 5 files changed, 41 insertions(+), 53 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b071b00..ff30f3f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2236,7 +2236,9 @@ int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
 int i915_gem_context_enable(struct drm_i915_private *dev_priv);
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
 int i915_switch_context(struct intel_ring_buffer *ring,
-			struct drm_file *file, int to_id);
+			struct drm_file *file, struct i915_hw_context *to);
+struct i915_hw_context *
+i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
 void i915_gem_context_free(struct kref *ctx_ref);
 static inline void i915_gem_context_reference(struct i915_hw_context *ctx)
 {
@@ -2250,10 +2252,6 @@ static inline void i915_gem_context_unreference(struct i915_hw_context *ctx)
 		kref_put(&ctx->ref, i915_gem_context_free);
 }
 
-struct i915_ctx_hang_stats * __must_check
-i915_gem_context_get_hang_stats(struct drm_device *dev,
-				struct drm_file *file,
-				u32 id);
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file);
 int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3a80d0f..ed52108 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2799,7 +2799,7 @@ int i915_gpu_idle(struct drm_device *dev)
 
 	/* Flush everything onto the inactive list. */
 	for_each_ring(ring, dev_priv, i) {
-		ret = i915_switch_context(ring, NULL, DEFAULT_CONTEXT_ID);
+		ret = i915_switch_context(ring, NULL, ring->default_context);
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 362de0d..165a5c7 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -96,8 +96,6 @@
 #define GEN6_CONTEXT_ALIGN (64<<10)
 #define GEN7_CONTEXT_ALIGN 4096
 
-static struct i915_hw_context *
-i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
 static int do_switch(struct intel_ring_buffer *ring,
 		     struct i915_hw_context *to);
 
@@ -485,20 +483,6 @@ static int context_idr_cleanup(int id, void *p, void *data)
 	return 0;
 }
 
-struct i915_ctx_hang_stats *
-i915_gem_context_get_hang_stats(struct drm_device *dev,
-				struct drm_file *file,
-				u32 id)
-{
-	struct i915_hw_context *ctx;
-
-	ctx = i915_gem_context_get(file->driver_priv, id);
-	if (ctx == NULL)
-		return ERR_PTR(-ENOENT);
-
-	return &ctx->hang_stats;
-}
-
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
@@ -541,9 +525,12 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 	idr_destroy(&file_priv->context_idr);
 }
 
-static struct i915_hw_context *
+struct i915_hw_context *
 i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
 {
+	if (!HAS_HW_CONTEXTS(file_priv->dev_priv->dev))
+		return file_priv->private_default_ctx;
+
 	return (struct i915_hw_context *)idr_find(&file_priv->context_idr, id);
 }
 
@@ -716,20 +703,13 @@ done:
  */
 int i915_switch_context(struct intel_ring_buffer *ring,
 			struct drm_file *file,
-			int to_id)
+			struct i915_hw_context *to)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	struct i915_hw_context *to;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
 
-	if (file == NULL)
-		to = ring->default_context;
-	else
-		to = i915_gem_context_get(file->driver_priv, to_id);
-
-	if (to == NULL)
-		return -ENOENT;
+	BUG_ON(file && to == NULL);
 
 	/* We have the fake context, but don't supports switching. */
 	if (!HAS_HW_CONTEXTS(ring->dev))
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 2b8863d..7a34fc4 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -895,22 +895,24 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 	return 0;
 }
 
-static int
+static struct i915_hw_context *
 i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 			  const u32 ctx_id)
 {
+	struct i915_hw_context *ctx = NULL;
 	struct i915_ctx_hang_stats *hs;
 
-	hs = i915_gem_context_get_hang_stats(dev, file, ctx_id);
-	if (IS_ERR(hs))
-		return PTR_ERR(hs);
+	ctx = i915_gem_context_get(file->driver_priv, ctx_id);
+	if (IS_ERR_OR_NULL(ctx))
+		return ctx;
 
+	hs = &ctx->hang_stats;
 	if (hs->banned) {
 		DRM_DEBUG("Context %u tried to submit while banned\n", ctx_id);
-		return -EIO;
+		return ERR_PTR(-EIO);
 	}
 
-	return 0;
+	return ctx;
 }
 
 static void
@@ -986,14 +988,15 @@ static int
 i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct i915_address_space *vm)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct eb_vmas *eb;
 	struct drm_i915_gem_object *batch_obj;
 	struct drm_clip_rect *cliprects = NULL;
 	struct intel_ring_buffer *ring;
+	struct i915_hw_context *ctx;
+	struct i915_address_space *vm;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
 	u32 exec_start, exec_len;
 	u32 mask, flags;
@@ -1107,11 +1110,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		goto pre_mutex_err;
 	}
 
-	ret = i915_gem_validate_context(dev, file, ctx_id);
-	if (ret) {
+	ctx = i915_gem_validate_context(dev, file, ctx_id);
+	if (IS_ERR_OR_NULL(ctx)) {
 		mutex_unlock(&dev->struct_mutex);
+		ret = PTR_ERR(ctx);
 		goto pre_mutex_err;
-	}
+	} 
+
+	i915_gem_context_reference(ctx);
+
+	/* HACK until we have full PPGTT */
+	/* vm = ctx->vm; */
+	vm = &dev_priv->gtt.base;
 
 	eb = eb_create(args);
 	if (eb == NULL) {
@@ -1171,7 +1181,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (ret)
 		goto err;
 
-	ret = i915_switch_context(ring, file, ctx_id);
+	ret = i915_switch_context(ring, file, ctx);
 	if (ret)
 		goto err;
 
@@ -1226,6 +1236,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj);
 
 err:
+	/* the request owns the ref now */
+	i915_gem_context_unreference(ctx);
 	eb_destroy(eb);
 
 	mutex_unlock(&dev->struct_mutex);
@@ -1243,7 +1255,6 @@ int
 i915_gem_execbuffer(struct drm_device *dev, void *data,
 		    struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer *args = data;
 	struct drm_i915_gem_execbuffer2 exec2;
 	struct drm_i915_gem_exec_object *exec_list = NULL;
@@ -1299,8 +1310,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	exec2.flags = I915_EXEC_RENDER;
 	i915_execbuffer2_set_context_id(exec2, 0);
 
-	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list,
-				     &dev_priv->gtt.base);
+	ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		for (i = 0; i < args->buffer_count; i++)
@@ -1326,7 +1336,6 @@ int
 i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		     struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list = NULL;
 	int ret;
@@ -1357,8 +1366,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list,
-				     &dev_priv->gtt.base);
+	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
 		ret = copy_to_user(to_user_ptr(args->buffers_ptr),
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index feb2d66..e52fcce 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -836,6 +836,7 @@ int i915_get_reset_stats_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_reset_stats *args = data;
 	struct i915_ctx_hang_stats *hs;
+	struct i915_hw_context *ctx;
 	int ret;
 
 	if (args->flags || args->pad)
@@ -848,11 +849,12 @@ int i915_get_reset_stats_ioctl(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	hs = i915_gem_context_get_hang_stats(dev, file, args->ctx_id);
-	if (IS_ERR(hs)) {
+	ctx = i915_gem_context_get(file->driver_priv, args->ctx_id);
+	if (IS_ERR(ctx)) {
 		mutex_unlock(&dev->struct_mutex);
-		return PTR_ERR(hs);
+		return PTR_ERR(ctx);
 	}
+	hs = &ctx->hang_stats;
 
 	if (capable(CAP_SYS_ADMIN))
 		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
-- 
1.8.4.2