vmap consolidation to obj->mapping

vmap consolidation to obj->mapping

[Chris Wilson]

Now with a new lick of paint, I introduce the cached obj->mapping pointer
for all your contiguous accesses!

Enjoy,
-Chris

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

[PATCH v2 1/6] drm/i915/dmabuf: Tighten struct_mutex for unmap_dma_buf

[Chris Wilson]

We only need the struct_mutex to manipulate the pages_pin_count on the
object, we do not need to hold our BKL when freeing the exported
scatterlist.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_dmabuf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 0506016e18e0..b7d46800c49f 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -95,14 +95,12 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment,
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
 
-	mutex_lock(&obj->base.dev->struct_mutex);
-
 	dma_unmap_sg(attachment->dev, sg->sgl, sg->nents, dir);
 	sg_free_table(sg);
 	kfree(sg);
 
+	mutex_lock(&obj->base.dev->struct_mutex);
 	i915_gem_object_unpin_pages(obj);
-
 	mutex_unlock(&obj->base.dev->struct_mutex);
 }
 
-- 
2.8.0.rc3

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

[PATCH v2 2/6] drm/i915: Consolidate common error handling in intel_pin_and_map_ringbuffer_obj

[Chris Wilson]

After we pin the ringbuffer into the GGTT, all error paths need to unpin
it again. Move this common step into one block, and make the unable to
iomap error code consistent (i.e. treat it as out of memory to avoid
confusing it with a invalid argument).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6b4952031e30..600ccc403b1f 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2121,15 +2121,13 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return ret;
 
 		ret = i915_gem_object_set_to_cpu_domain(obj, true);
-		if (ret) {
-			i915_gem_object_ggtt_unpin(obj);
-			return ret;
-		}
+		if (ret)
+			goto err_unpin;
 
 		ringbuf->virtual_start = vmap_obj(obj);
 		if (ringbuf->virtual_start == NULL) {
-			i915_gem_object_ggtt_unpin(obj);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_unpin;
 		}
 	} else {
 		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
@@ -2137,10 +2135,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return ret;
 
 		ret = i915_gem_object_set_to_gtt_domain(obj, true);
-		if (ret) {
-			i915_gem_object_ggtt_unpin(obj);
-			return ret;
-		}
+		if (ret)
+			goto err_unpin;
 
 		/* Access through the GTT requires the device to be awake. */
 		assert_rpm_wakelock_held(dev_priv);
@@ -2148,14 +2144,17 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 		ringbuf->virtual_start = ioremap_wc(ggtt->mappable_base +
 						    i915_gem_obj_ggtt_offset(obj), ringbuf->size);
 		if (ringbuf->virtual_start == NULL) {
-			i915_gem_object_ggtt_unpin(obj);
-			return -EINVAL;
+			ret = -ENOMEM;
+			goto err_unpin;
 		}
 	}
 
 	ringbuf->vma = i915_gem_obj_to_ggtt(obj);
-
 	return 0;
+
+err_unpin:
+	i915_gem_object_ggtt_unpin(obj);
+	return ret;
 }
 
 static void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
-- 
2.8.0.rc3

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

[PATCH v2 3/6] drm/i915: Refactor duplicate object vmap functions

[Chris Wilson]

We now have two implementations for vmapping a whole object, one for
dma-buf and one for the ringbuffer. If we couple the mapping into the
obj->pages lifetime, then we can reuse an obj->mapping for both and at
the same time couple it into the shrinker. There is a third vmapping
routine in the cmdparser that maps only a range within the object, for
the time being that is left alone, but will eventually use these routines
in order to cache the mapping between invocations.

v2: Mark the failable kmalloc() as __GFP_NOWARN (vsyrjala)
v3: Call unpin_vmap from the right dmabuf unmapper

v4: Rename vmap to map as we don't wish to imply the type of mapping
involved, just that it contiguously maps the object into kernel space.
Add kerneldoc and lockdep annotations

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Dave Gordon <david.s.gordon@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         | 37 ++++++++++++++++++++++---
 drivers/gpu/drm/i915/i915_gem.c         | 44 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_dmabuf.c  | 49 ++++-----------------------------
 drivers/gpu/drm/i915/intel_ringbuffer.c | 26 ++---------------
 4 files changed, 84 insertions(+), 72 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a93e5dd4fa9a..eda4218e2ede 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2169,10 +2169,7 @@ struct drm_i915_gem_object {
 		struct scatterlist *sg;
 		int last;
 	} get_page;
-
-	/* prime dma-buf support */
-	void *dma_buf_vmapping;
-	int vmapping_count;
+	void *mapping;
 
 	/** Breadcrumb of last rendering to the buffer.
 	 * There can only be one writer, but we allow for multiple readers.
@@ -2988,12 +2985,44 @@ static inline void i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
 	BUG_ON(obj->pages == NULL);
 	obj->pages_pin_count++;
 }
+
 static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 {
 	BUG_ON(obj->pages_pin_count == 0);
 	obj->pages_pin_count--;
 }
 
+/**
+ * i915_gem_object_pin_map - return a contiguous mapping of the entire object
+ * @obj - the object to map into kernel address space
+ *
+ * Calls i915_gem_object_pin_pages() to prevent reaping of the object's
+ * pages and then returns a contiguous mapping of the backing storage into
+ * the kernel address space.
+ *
+ * The caller must hold the struct_mutex.
+ *
+ * Returns the pointer through which to access the backing storage.
+ */
+void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj);
+
+/**
+ * i915_gem_object_unpin_map - releases an earlier mapping
+ * @obj - the object to unmap
+ *
+ * After pinning the object and mapping its pages, once you are finished
+ * with your access, call i915_gem_object_unpin_map() to release the pin
+ * upon the mapping. Once the pin count reaches zero, that mapping may be
+ * removed.
+ *
+ * The caller must hold the struct_mutex.
+ */
+static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj)
+{
+	lockdep_assert_held(&obj->base.dev->struct_mutex);
+	i915_gem_object_unpin_pages(obj);
+}
+
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
 int i915_gem_object_sync(struct drm_i915_gem_object *obj,
 			 struct intel_engine_cs *to,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5a65a7663b88..fcbd47d36dcf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2232,6 +2232,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	 * lists early. */
 	list_del(&obj->global_list);
 
+	if (obj->mapping) {
+		vunmap(obj->mapping);
+		obj->mapping = NULL;
+	}
+
 	ops->put_pages(obj);
 	obj->pages = NULL;
 
@@ -2400,6 +2405,45 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
+void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
+{
+	int ret;
+
+	lockdep_assert_held(&obj->base.dev->struct_mutex);
+
+	ret = i915_gem_object_get_pages(obj);
+	if (ret)
+		return ERR_PTR(ret);
+
+	i915_gem_object_pin_pages(obj);
+
+	if (obj->mapping == NULL) {
+		struct sg_page_iter sg_iter;
+		struct page **pages;
+		int n;
+
+		n = obj->base.size >> PAGE_SHIFT;
+		pages = kmalloc(n*sizeof(*pages), GFP_TEMPORARY | __GFP_NOWARN);
+		if (pages == NULL)
+			pages = drm_malloc_ab(n, sizeof(*pages));
+		if (pages != NULL) {
+			n = 0;
+			for_each_sg_page(obj->pages->sgl, &sg_iter,
+					 obj->pages->nents, 0)
+				pages[n++] = sg_page_iter_page(&sg_iter);
+
+			obj->mapping = vmap(pages, n, 0, PAGE_KERNEL);
+			drm_free_large(pages);
+		}
+		if (obj->mapping == NULL) {
+			i915_gem_object_unpin_pages(obj);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	return obj->mapping;
+}
+
 void i915_vma_move_to_active(struct i915_vma *vma,
 			     struct drm_i915_gem_request *req)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index b7d46800c49f..80bbe43a2e92 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -108,51 +108,17 @@ static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
-	struct sg_page_iter sg_iter;
-	struct page **pages;
-	int ret, i;
+	void *addr;
+	int ret;
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (obj->dma_buf_vmapping) {
-		obj->vmapping_count++;
-		goto out_unlock;
-	}
-
-	ret = i915_gem_object_get_pages(obj);
-	if (ret)
-		goto err;
-
-	i915_gem_object_pin_pages(obj);
-
-	ret = -ENOMEM;
-
-	pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
-	if (pages == NULL)
-		goto err_unpin;
-
-	i = 0;
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0)
-		pages[i++] = sg_page_iter_page(&sg_iter);
-
-	obj->dma_buf_vmapping = vmap(pages, i, 0, PAGE_KERNEL);
-	drm_free_large(pages);
-
-	if (!obj->dma_buf_vmapping)
-		goto err_unpin;
-
-	obj->vmapping_count = 1;
-out_unlock:
+	addr = i915_gem_object_pin_map(obj);
 	mutex_unlock(&dev->struct_mutex);
-	return obj->dma_buf_vmapping;
 
-err_unpin:
-	i915_gem_object_unpin_pages(obj);
-err:
-	mutex_unlock(&dev->struct_mutex);
-	return ERR_PTR(ret);
+	return addr;
 }
 
 static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
@@ -161,12 +127,7 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	struct drm_device *dev = obj->base.dev;
 
 	mutex_lock(&dev->struct_mutex);
-	if (--obj->vmapping_count == 0) {
-		vunmap(obj->dma_buf_vmapping);
-		obj->dma_buf_vmapping = NULL;
-
-		i915_gem_object_unpin_pages(obj);
-	}
+	i915_gem_object_unpin_map(obj);
 	mutex_unlock(&dev->struct_mutex);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 600ccc403b1f..83536c39b9ca 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2078,35 +2078,13 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 {
 	if (HAS_LLC(ringbuf->obj->base.dev) && !ringbuf->obj->stolen)
-		vunmap(ringbuf->virtual_start);
+		i915_gem_object_unpin_map(ringbuf->obj);
 	else
 		iounmap(ringbuf->virtual_start);
-	ringbuf->virtual_start = NULL;
 	ringbuf->vma = NULL;
 	i915_gem_object_ggtt_unpin(ringbuf->obj);
 }
 
-static u32 *vmap_obj(struct drm_i915_gem_object *obj)
-{
-	struct sg_page_iter sg_iter;
-	struct page **pages;
-	void *addr;
-	int i;
-
-	pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
-	if (pages == NULL)
-		return NULL;
-
-	i = 0;
-	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0)
-		pages[i++] = sg_page_iter_page(&sg_iter);
-
-	addr = vmap(pages, i, 0, PAGE_KERNEL);
-	drm_free_large(pages);
-
-	return addr;
-}
-
 int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 				     struct intel_ringbuffer *ringbuf)
 {
@@ -2124,7 +2102,7 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 		if (ret)
 			goto err_unpin;
 
-		ringbuf->virtual_start = vmap_obj(obj);
+		ringbuf->virtual_start = i915_gem_object_pin_map(obj);
 		if (ringbuf->virtual_start == NULL) {
 			ret = -ENOMEM;
 			goto err_unpin;
-- 
2.8.0.rc3

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

Re: [PATCH v2 3/6] drm/i915: Refactor duplicate object vmap functions

[Tvrtko Ursulin]

On 08/04/16 12:11, Chris Wilson wrote:
> We now have two implementations for vmapping a whole object, one for
> dma-buf and one for the ringbuffer. If we couple the mapping into the
> obj->pages lifetime, then we can reuse an obj->mapping for both and at
> the same time couple it into the shrinker. There is a third vmapping
> routine in the cmdparser that maps only a range within the object, for
> the time being that is left alone, but will eventually use these routines
> in order to cache the mapping between invocations.
>
> v2: Mark the failable kmalloc() as __GFP_NOWARN (vsyrjala)
> v3: Call unpin_vmap from the right dmabuf unmapper
>
> v4: Rename vmap to map as we don't wish to imply the type of mapping
> involved, just that it contiguously maps the object into kernel space.
> Add kerneldoc and lockdep annotations
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> Cc: Dave Gordon <david.s.gordon@intel.com>
> ---
>   drivers/gpu/drm/i915/i915_drv.h         | 37 ++++++++++++++++++++++---
>   drivers/gpu/drm/i915/i915_gem.c         | 44 +++++++++++++++++++++++++++++
>   drivers/gpu/drm/i915/i915_gem_dmabuf.c  | 49 ++++-----------------------------
>   drivers/gpu/drm/i915/intel_ringbuffer.c | 26 ++---------------
>   4 files changed, 84 insertions(+), 72 deletions(-)

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko

>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index a93e5dd4fa9a..eda4218e2ede 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2169,10 +2169,7 @@ struct drm_i915_gem_object {
>   		struct scatterlist *sg;
>   		int last;
>   	} get_page;
> -
> -	/* prime dma-buf support */
> -	void *dma_buf_vmapping;
> -	int vmapping_count;
> +	void *mapping;
>
>   	/** Breadcrumb of last rendering to the buffer.
>   	 * There can only be one writer, but we allow for multiple readers.
> @@ -2988,12 +2985,44 @@ static inline void i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
>   	BUG_ON(obj->pages == NULL);
>   	obj->pages_pin_count++;
>   }
> +
>   static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
>   {
>   	BUG_ON(obj->pages_pin_count == 0);
>   	obj->pages_pin_count--;
>   }
>
> +/**
> + * i915_gem_object_pin_map - return a contiguous mapping of the entire object
> + * @obj - the object to map into kernel address space
> + *
> + * Calls i915_gem_object_pin_pages() to prevent reaping of the object's
> + * pages and then returns a contiguous mapping of the backing storage into
> + * the kernel address space.
> + *
> + * The caller must hold the struct_mutex.
> + *
> + * Returns the pointer through which to access the backing storage.
> + */
> +void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj);
> +
> +/**
> + * i915_gem_object_unpin_map - releases an earlier mapping
> + * @obj - the object to unmap
> + *
> + * After pinning the object and mapping its pages, once you are finished
> + * with your access, call i915_gem_object_unpin_map() to release the pin
> + * upon the mapping. Once the pin count reaches zero, that mapping may be
> + * removed.
> + *
> + * The caller must hold the struct_mutex.
> + */
> +static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj)
> +{
> +	lockdep_assert_held(&obj->base.dev->struct_mutex);
> +	i915_gem_object_unpin_pages(obj);
> +}
> +
>   int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
>   int i915_gem_object_sync(struct drm_i915_gem_object *obj,
>   			 struct intel_engine_cs *to,
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 5a65a7663b88..fcbd47d36dcf 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2232,6 +2232,11 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
>   	 * lists early. */
>   	list_del(&obj->global_list);
>
> +	if (obj->mapping) {
> +		vunmap(obj->mapping);
> +		obj->mapping = NULL;
> +	}
> +
>   	ops->put_pages(obj);
>   	obj->pages = NULL;
>
> @@ -2400,6 +2405,45 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
>   	return 0;
>   }
>
> +void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
> +{
> +	int ret;
> +
> +	lockdep_assert_held(&obj->base.dev->struct_mutex);
> +
> +	ret = i915_gem_object_get_pages(obj);
> +	if (ret)
> +		return ERR_PTR(ret);
> +
> +	i915_gem_object_pin_pages(obj);
> +
> +	if (obj->mapping == NULL) {
> +		struct sg_page_iter sg_iter;
> +		struct page **pages;
> +		int n;
> +
> +		n = obj->base.size >> PAGE_SHIFT;
> +		pages = kmalloc(n*sizeof(*pages), GFP_TEMPORARY | __GFP_NOWARN);
> +		if (pages == NULL)
> +			pages = drm_malloc_ab(n, sizeof(*pages));
> +		if (pages != NULL) {
> +			n = 0;
> +			for_each_sg_page(obj->pages->sgl, &sg_iter,
> +					 obj->pages->nents, 0)
> +				pages[n++] = sg_page_iter_page(&sg_iter);
> +
> +			obj->mapping = vmap(pages, n, 0, PAGE_KERNEL);
> +			drm_free_large(pages);
> +		}
> +		if (obj->mapping == NULL) {
> +			i915_gem_object_unpin_pages(obj);
> +			return ERR_PTR(-ENOMEM);
> +		}
> +	}
> +
> +	return obj->mapping;
> +}
> +
>   void i915_vma_move_to_active(struct i915_vma *vma,
>   			     struct drm_i915_gem_request *req)
>   {
> diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> index b7d46800c49f..80bbe43a2e92 100644
> --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
> @@ -108,51 +108,17 @@ static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
>   {
>   	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
>   	struct drm_device *dev = obj->base.dev;
> -	struct sg_page_iter sg_iter;
> -	struct page **pages;
> -	int ret, i;
> +	void *addr;
> +	int ret;
>
>   	ret = i915_mutex_lock_interruptible(dev);
>   	if (ret)
>   		return ERR_PTR(ret);
>
> -	if (obj->dma_buf_vmapping) {
> -		obj->vmapping_count++;
> -		goto out_unlock;
> -	}
> -
> -	ret = i915_gem_object_get_pages(obj);
> -	if (ret)
> -		goto err;
> -
> -	i915_gem_object_pin_pages(obj);
> -
> -	ret = -ENOMEM;
> -
> -	pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
> -	if (pages == NULL)
> -		goto err_unpin;
> -
> -	i = 0;
> -	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0)
> -		pages[i++] = sg_page_iter_page(&sg_iter);
> -
> -	obj->dma_buf_vmapping = vmap(pages, i, 0, PAGE_KERNEL);
> -	drm_free_large(pages);
> -
> -	if (!obj->dma_buf_vmapping)
> -		goto err_unpin;
> -
> -	obj->vmapping_count = 1;
> -out_unlock:
> +	addr = i915_gem_object_pin_map(obj);
>   	mutex_unlock(&dev->struct_mutex);
> -	return obj->dma_buf_vmapping;
>
> -err_unpin:
> -	i915_gem_object_unpin_pages(obj);
> -err:
> -	mutex_unlock(&dev->struct_mutex);
> -	return ERR_PTR(ret);
> +	return addr;
>   }
>
>   static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
> @@ -161,12 +127,7 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
>   	struct drm_device *dev = obj->base.dev;
>
>   	mutex_lock(&dev->struct_mutex);
> -	if (--obj->vmapping_count == 0) {
> -		vunmap(obj->dma_buf_vmapping);
> -		obj->dma_buf_vmapping = NULL;
> -
> -		i915_gem_object_unpin_pages(obj);
> -	}
> +	i915_gem_object_unpin_map(obj);
>   	mutex_unlock(&dev->struct_mutex);
>   }
>
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 600ccc403b1f..83536c39b9ca 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -2078,35 +2078,13 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
>   void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
>   {
>   	if (HAS_LLC(ringbuf->obj->base.dev) && !ringbuf->obj->stolen)
> -		vunmap(ringbuf->virtual_start);
> +		i915_gem_object_unpin_map(ringbuf->obj);
>   	else
>   		iounmap(ringbuf->virtual_start);
> -	ringbuf->virtual_start = NULL;
>   	ringbuf->vma = NULL;
>   	i915_gem_object_ggtt_unpin(ringbuf->obj);
>   }
>
> -static u32 *vmap_obj(struct drm_i915_gem_object *obj)
> -{
> -	struct sg_page_iter sg_iter;
> -	struct page **pages;
> -	void *addr;
> -	int i;
> -
> -	pages = drm_malloc_ab(obj->base.size >> PAGE_SHIFT, sizeof(*pages));
> -	if (pages == NULL)
> -		return NULL;
> -
> -	i = 0;
> -	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0)
> -		pages[i++] = sg_page_iter_page(&sg_iter);
> -
> -	addr = vmap(pages, i, 0, PAGE_KERNEL);
> -	drm_free_large(pages);
> -
> -	return addr;
> -}
> -
>   int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
>   				     struct intel_ringbuffer *ringbuf)
>   {
> @@ -2124,7 +2102,7 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
>   		if (ret)
>   			goto err_unpin;
>
> -		ringbuf->virtual_start = vmap_obj(obj);
> +		ringbuf->virtual_start = i915_gem_object_pin_map(obj);
>   		if (ringbuf->virtual_start == NULL) {
>   			ret = -ENOMEM;
>   			goto err_unpin;
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Chris Wilson]

When called because we have run out of vmap address space, we only need
to recover objects that have vmappings and not all.

v2: Start using is_vmalloc_addr()

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h          |  1 +
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index eda4218e2ede..4061a11e4234 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3338,6 +3338,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
 #define I915_SHRINK_UNBOUND 0x2
 #define I915_SHRINK_BOUND 0x4
 #define I915_SHRINK_ACTIVE 0x8
+#define I915_SHRINK_VMAPS 0x10
 unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
 void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
 void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 39943793edcc..d46388f25e04 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -167,6 +167,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			    obj->madv != I915_MADV_DONTNEED)
 				continue;
 
+			if (flags & I915_SHRINK_VMAPS &&
+			    !is_vmalloc_addr(obj->mapping))
+				continue;
+
 			if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active)
 				continue;
 
@@ -388,7 +392,11 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 	if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
 		return NOTIFY_DONE;
 
-	freed_pages = i915_gem_shrink_all(dev_priv);
+	freed_pages = i915_gem_shrink(dev_priv, -1UL,
+				      I915_SHRINK_BOUND |
+				      I915_SHRINK_UNBOUND |
+				      I915_SHRINK_ACTIVE |
+				      I915_SHRINK_VMAPS);
 
 	i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu);
 
-- 
2.8.0.rc3

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

Re: [PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Tvrtko Ursulin]

On 08/04/16 12:11, Chris Wilson wrote:
> When called because we have run out of vmap address space, we only need
> to recover objects that have vmappings and not all.
>
> v2: Start using is_vmalloc_addr()
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> ---
>   drivers/gpu/drm/i915/i915_drv.h          |  1 +
>   drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
>   2 files changed, 10 insertions(+), 1 deletion(-)

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko

>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index eda4218e2ede..4061a11e4234 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -3338,6 +3338,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
>   #define I915_SHRINK_UNBOUND 0x2
>   #define I915_SHRINK_BOUND 0x4
>   #define I915_SHRINK_ACTIVE 0x8
> +#define I915_SHRINK_VMAPS 0x10
>   unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
>   void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
>   void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv);
> diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
> index 39943793edcc..d46388f25e04 100644
> --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
> +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
> @@ -167,6 +167,10 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
>   			    obj->madv != I915_MADV_DONTNEED)
>   				continue;
>
> +			if (flags & I915_SHRINK_VMAPS &&
> +			    !is_vmalloc_addr(obj->mapping))
> +				continue;
> +
>   			if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active)
>   				continue;
>
> @@ -388,7 +392,11 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
>   	if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
>   		return NOTIFY_DONE;
>
> -	freed_pages = i915_gem_shrink_all(dev_priv);
> +	freed_pages = i915_gem_shrink(dev_priv, -1UL,
> +				      I915_SHRINK_BOUND |
> +				      I915_SHRINK_UNBOUND |
> +				      I915_SHRINK_ACTIVE |
> +				      I915_SHRINK_VMAPS);
>
>   	i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu);
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Chris Wilson]

On Mon, Apr 11, 2016 at 03:25:41PM +0100, Tvrtko Ursulin wrote:
> 
> On 08/04/16 12:11, Chris Wilson wrote:
> >When called because we have run out of vmap address space, we only need
> >to recover objects that have vmappings and not all.
> >
> >v2: Start using is_vmalloc_addr()
> >
> >Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> >Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> >---
> >  drivers/gpu/drm/i915/i915_drv.h          |  1 +
> >  drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
> >  2 files changed, 10 insertions(+), 1 deletion(-)
> 
> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Having started to use the obj->mapping cache in anger, do you think there
is any left before pushing this part of the puzzle? I'm hitting an
interesting scaling problem with vmalloc's lazy free list (that's a
patch for later!).
-Chris


-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Tvrtko Ursulin]

On 11/04/16 15:44, Chris Wilson wrote:
> On Mon, Apr 11, 2016 at 03:25:41PM +0100, Tvrtko Ursulin wrote:
>>
>> On 08/04/16 12:11, Chris Wilson wrote:
>>> When called because we have run out of vmap address space, we only need
>>> to recover objects that have vmappings and not all.
>>>
>>> v2: Start using is_vmalloc_addr()
>>>
>>> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>>> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
>>> ---
>>>   drivers/gpu/drm/i915/i915_drv.h          |  1 +
>>>   drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
>>>   2 files changed, 10 insertions(+), 1 deletion(-)
>>
>> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>
> Having started to use the obj->mapping cache in anger, do you think there
> is any left before pushing this part of the puzzle? I'm hitting an
> interesting scaling problem with vmalloc's lazy free list (that's a
> patch for later!).

Looks ready and useful to me so I vote for merging it.

I can follow up with the LRC reg state when it is in.

Regards,

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

Re: [PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Chris Wilson]

On Mon, Apr 11, 2016 at 03:57:21PM +0100, Tvrtko Ursulin wrote:
> 
> On 11/04/16 15:44, Chris Wilson wrote:
> >On Mon, Apr 11, 2016 at 03:25:41PM +0100, Tvrtko Ursulin wrote:
> >>
> >>On 08/04/16 12:11, Chris Wilson wrote:
> >>>When called because we have run out of vmap address space, we only need
> >>>to recover objects that have vmappings and not all.
> >>>
> >>>v2: Start using is_vmalloc_addr()
> >>>
> >>>Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> >>>Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> >>>---
> >>>  drivers/gpu/drm/i915/i915_drv.h          |  1 +
> >>>  drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
> >>>  2 files changed, 10 insertions(+), 1 deletion(-)
> >>
> >>Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> >
> >Having started to use the obj->mapping cache in anger, do you think there
> >is any left before pushing this part of the puzzle? I'm hitting an
> >interesting scaling problem with vmalloc's lazy free list (that's a
> >patch for later!).
> 
> Looks ready and useful to me so I vote for merging it.

Done. Hopefully I can make some headway on bugfixes and then start
chasing some of the more interesting improvements.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH v2 4/6] drm/i915/shrinker: Restrict vmap purge to objects with vmaps

[Dave Gordon]

On 11/04/16 17:40, Chris Wilson wrote:
> On Mon, Apr 11, 2016 at 03:57:21PM +0100, Tvrtko Ursulin wrote:
>>
>> On 11/04/16 15:44, Chris Wilson wrote:
>>> On Mon, Apr 11, 2016 at 03:25:41PM +0100, Tvrtko Ursulin wrote:
>>>>
>>>> On 08/04/16 12:11, Chris Wilson wrote:
>>>>> When called because we have run out of vmap address space, we only need
>>>>> to recover objects that have vmappings and not all.
>>>>>
>>>>> v2: Start using is_vmalloc_addr()
>>>>>
>>>>> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
>>>>> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
>>>>> ---
>>>>>   drivers/gpu/drm/i915/i915_drv.h          |  1 +
>>>>>   drivers/gpu/drm/i915/i915_gem_shrinker.c | 10 +++++++++-
>>>>>   2 files changed, 10 insertions(+), 1 deletion(-)
>>>>
>>>> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>>
>>> Having started to use the obj->mapping cache in anger, do you think there
>>> is any left before pushing this part of the puzzle? I'm hitting an
>>> interesting scaling problem with vmalloc's lazy free list (that's a
>>> patch for later!).
>>
>> Looks ready and useful to me so I vote for merging it.
>
> Done. Hopefully I can make some headway on bugfixes and then start
> chasing some of the more interesting improvements.
> -Chris

Yay! Now we'll try using it for the various GuC objects that could do 
with a long-term mapping rather than repeated kmap_atomic() :)

.Dave.

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

[PATCH v2 5/6] drm,i915: Introduce drm_malloc_gfp()

[Chris Wilson]

I have instances where I want to use drm_malloc_ab() but with a custom
gfp mask. And with those, where I want a temporary allocation, I want to
try a high-order kmalloc() before using a vmalloc().

So refactor my usage into drm_malloc_gfp().

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: dri-devel@lists.freedesktop.org
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/i915/i915_gem.c            |  4 +---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  8 +++-----
 drivers/gpu/drm/i915/i915_gem_gtt.c        |  5 +++--
 drivers/gpu/drm/i915/i915_gem_userptr.c    | 16 +++++-----------
 include/drm/drm_mem_util.h                 | 19 +++++++++++++++++++
 5 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fcbd47d36dcf..fa810226bd8b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2423,9 +2423,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
 		int n;
 
 		n = obj->base.size >> PAGE_SHIFT;
-		pages = kmalloc(n*sizeof(*pages), GFP_TEMPORARY | __GFP_NOWARN);
-		if (pages == NULL)
-			pages = drm_malloc_ab(n, sizeof(*pages));
+		pages = drm_malloc_gfp(n, sizeof(*pages), GFP_TEMPORARY);
 		if (pages != NULL) {
 			n = 0;
 			for_each_sg_page(obj->pages->sgl, &sg_iter,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 0ee61fd014df..6ee4f00f620c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1783,11 +1783,9 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count,
-			     GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
-	if (exec2_list == NULL)
-		exec2_list = drm_malloc_ab(sizeof(*exec2_list),
-					   args->buffer_count);
+	exec2_list = drm_malloc_gfp(args->buffer_count,
+				    sizeof(*exec2_list),
+				    GFP_TEMPORARY);
 	if (exec2_list == NULL) {
 		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
 			  args->buffer_count);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index da6e3a533095..c5cb04907525 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3401,8 +3401,9 @@ intel_rotate_fb_obj_pages(struct intel_rotation_info *rot_info,
 	int ret = -ENOMEM;
 
 	/* Allocate a temporary list of source pages for random access. */
-	page_addr_list = drm_malloc_ab(obj->base.size / PAGE_SIZE,
-				       sizeof(dma_addr_t));
+	page_addr_list = drm_malloc_gfp(obj->base.size / PAGE_SIZE,
+					sizeof(dma_addr_t),
+					GFP_TEMPORARY);
 	if (!page_addr_list)
 		return ERR_PTR(ret);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 962cb4c507cb..0f94b6c5c9cc 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -494,10 +494,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	ret = -ENOMEM;
 	pinned = 0;
 
-	pvec = kmalloc(npages*sizeof(struct page *),
-		       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
-	if (pvec == NULL)
-		pvec = drm_malloc_ab(npages, sizeof(struct page *));
+	pvec = drm_malloc_gfp(npages, sizeof(struct page *), GFP_TEMPORARY);
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
@@ -634,14 +631,11 @@ i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	pvec = NULL;
 	pinned = 0;
 	if (obj->userptr.mm->mm == current->mm) {
-		pvec = kmalloc(num_pages*sizeof(struct page *),
-			       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
+		pvec = drm_malloc_gfp(num_pages, sizeof(struct page *),
+				      GFP_TEMPORARY);
 		if (pvec == NULL) {
-			pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
-			if (pvec == NULL) {
-				__i915_gem_userptr_set_active(obj, false);
-				return -ENOMEM;
-			}
+			__i915_gem_userptr_set_active(obj, false);
+			return -ENOMEM;
 		}
 
 		pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages,
diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h
index e42495ad8136..741ce75a72b4 100644
--- a/include/drm/drm_mem_util.h
+++ b/include/drm/drm_mem_util.h
@@ -54,6 +54,25 @@ static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size)
 			 GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
 }
 
+static __inline__ void *drm_malloc_gfp(size_t nmemb, size_t size, gfp_t gfp)
+{
+	if (size != 0 && nmemb > SIZE_MAX / size)
+		return NULL;
+
+	if (size * nmemb <= PAGE_SIZE)
+	    return kmalloc(nmemb * size, gfp);
+
+	if (gfp & __GFP_RECLAIMABLE) {
+		void *ptr = kmalloc(nmemb * size,
+				    gfp | __GFP_NOWARN | __GFP_NORETRY);
+		if (ptr)
+			return ptr;
+	}
+
+	return __vmalloc(size * nmemb,
+			 gfp | __GFP_HIGHMEM, PAGE_KERNEL);
+}
+
 static __inline void drm_free_large(void *ptr)
 {
 	kvfree(ptr);
-- 
2.8.0.rc3

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

[PATCH v2 6/6] drm/i915: Avoid allocating a vmap arena for a single page

[Chris Wilson]

If we want a contiguous mapping of a single page sized object, we can
forgo using vmap() and just use a regular kmap(). Note that this is only
suitable if the desired pgprot_t is compatible.

v2: Use is_vmalloc_addr()

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Dave Gordon <david.s.gordon@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fa810226bd8b..b37ffea8b458 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2233,7 +2233,10 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	list_del(&obj->global_list);
 
 	if (obj->mapping) {
-		vunmap(obj->mapping);
+		if (is_vmalloc_addr(obj->mapping))
+			vunmap(obj->mapping);
+		else
+			kunmap(kmap_to_page(obj->mapping));
 		obj->mapping = NULL;
 	}
 
@@ -2418,13 +2421,19 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
 	i915_gem_object_pin_pages(obj);
 
 	if (obj->mapping == NULL) {
-		struct sg_page_iter sg_iter;
 		struct page **pages;
-		int n;
 
-		n = obj->base.size >> PAGE_SHIFT;
-		pages = drm_malloc_gfp(n, sizeof(*pages), GFP_TEMPORARY);
+		pages = NULL;
+		if (obj->base.size == PAGE_SIZE)
+			obj->mapping = kmap(sg_page(obj->pages->sgl));
+		else
+			pages = drm_malloc_gfp(obj->base.size >> PAGE_SHIFT,
+					       sizeof(*pages),
+					       GFP_TEMPORARY);
 		if (pages != NULL) {
+			struct sg_page_iter sg_iter;
+			int n;
+
 			n = 0;
 			for_each_sg_page(obj->pages->sgl, &sg_iter,
 					 obj->pages->nents, 0)
-- 
2.8.0.rc3

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

Re: [PATCH v2 6/6] drm/i915: Avoid allocating a vmap arena for a single page

[Tvrtko Ursulin]

On 08/04/16 12:11, Chris Wilson wrote:
> If we want a contiguous mapping of a single page sized object, we can
> forgo using vmap() and just use a regular kmap(). Note that this is only
> suitable if the desired pgprot_t is compatible.
>
> v2: Use is_vmalloc_addr()
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> Cc: Dave Gordon <david.s.gordon@intel.com>
> ---
>   drivers/gpu/drm/i915/i915_gem.c | 19 ++++++++++++++-----
>   1 file changed, 14 insertions(+), 5 deletions(-)

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

Regards,

Tvrtko

> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index fa810226bd8b..b37ffea8b458 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2233,7 +2233,10 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
>   	list_del(&obj->global_list);
>
>   	if (obj->mapping) {
> -		vunmap(obj->mapping);
> +		if (is_vmalloc_addr(obj->mapping))
> +			vunmap(obj->mapping);
> +		else
> +			kunmap(kmap_to_page(obj->mapping));
>   		obj->mapping = NULL;
>   	}
>
> @@ -2418,13 +2421,19 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj)
>   	i915_gem_object_pin_pages(obj);
>
>   	if (obj->mapping == NULL) {
> -		struct sg_page_iter sg_iter;
>   		struct page **pages;
> -		int n;
>
> -		n = obj->base.size >> PAGE_SHIFT;
> -		pages = drm_malloc_gfp(n, sizeof(*pages), GFP_TEMPORARY);
> +		pages = NULL;
> +		if (obj->base.size == PAGE_SIZE)
> +			obj->mapping = kmap(sg_page(obj->pages->sgl));
> +		else
> +			pages = drm_malloc_gfp(obj->base.size >> PAGE_SHIFT,
> +					       sizeof(*pages),
> +					       GFP_TEMPORARY);
>   		if (pages != NULL) {
> +			struct sg_page_iter sg_iter;
> +			int n;
> +
>   			n = 0;
>   			for_each_sg_page(obj->pages->sgl, &sg_iter,
>   					 obj->pages->nents, 0)
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Fi.CI.BAT: warning for series starting with [v2,1/6] drm/i915/dmabuf: Tighten struct_mutex for unmap_dma_buf

[Patchwork]

== Series Details ==

Series: series starting with [v2,1/6] drm/i915/dmabuf: Tighten struct_mutex for unmap_dma_buf
URL   : https://patchwork.freedesktop.org/series/5454/
State : warning

== Summary ==

Series 5454v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/5454/revisions/1/mbox/

Test gem_exec_basic:
        Subgroup basic-bsd:
                dmesg-warn -> PASS       (bsw-nuc-2)
Test gem_exec_suspend:
        Subgroup basic-s3:
                dmesg-warn -> PASS       (bsw-nuc-2)
Test gem_sync:
        Subgroup basic-bsd:
                dmesg-warn -> PASS       (bsw-nuc-2)
Test kms_flip:
        Subgroup basic-flip-vs-modeset:
                pass       -> DMESG-WARN (skl-i7k-2)
Test kms_force_connector_basic:
        Subgroup prune-stale-modes:
                pass       -> SKIP       (snb-x220t)
Test pm_rpm:
        Subgroup basic-rte:
                dmesg-warn -> PASS       (bsw-nuc-2)

bdw-ultra        total:196  pass:175  dwarn:0   dfail:0   fail:0   skip:21 
bsw-nuc-2        total:196  pass:159  dwarn:0   dfail:0   fail:0   skip:37 
byt-nuc          total:196  pass:161  dwarn:0   dfail:0   fail:0   skip:35 
hsw-brixbox      total:196  pass:174  dwarn:0   dfail:0   fail:0   skip:22 
hsw-gt2          total:196  pass:179  dwarn:0   dfail:0   fail:0   skip:17 
ilk-hp8440p      total:196  pass:132  dwarn:0   dfail:0   fail:0   skip:64 
ivb-t430s        total:196  pass:171  dwarn:0   dfail:0   fail:0   skip:25 
skl-i7k-2        total:196  pass:172  dwarn:1   dfail:0   fail:0   skip:23 
skl-nuci5        total:196  pass:185  dwarn:0   dfail:0   fail:0   skip:11 
snb-dellxps      total:196  pass:162  dwarn:0   dfail:0   fail:0   skip:34 
snb-x220t        total:196  pass:161  dwarn:0   dfail:0   fail:1   skip:34 

Results at /archive/results/CI_IGT_test/Patchwork_1842/

949884a57b51aa158e3ae9afe1f08130cdb7a3ef drm-intel-nightly: 2016y-04m-08d-10h-45m-28s UTC integration manifest
8d7c7c27f5609b0ba9af71fa1fd4cfeeff632757 drm/i915: Avoid allocating a vmap arena for a single page
4485414d9cff3cac069b328a526c64f7bc615c8f drm,i915: Introduce drm_malloc_gfp()
b8c857a26ca887a36535fb1d107c41333419921f drm/i915/shrinker: Restrict vmap purge to objects with vmaps
94e5014d54ccbb1fef06141c0ae801f6e7631b55 drm/i915: Refactor duplicate object vmap functions
1c7d13206cd237ef9f1b34edebefae80592f74a3 drm/i915: Consolidate common error handling in intel_pin_and_map_ringbuffer_obj
d94080d534d0b0f0054ca3aa7550fcdfe7cf4780 drm/i915/dmabuf: Tighten struct_mutex for unmap_dma_buf

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