[PATCH v7 3/7] drm,i915: introduce drm_malloc_gfp()

[PATCH v7 3/7] drm,i915: introduce drm_malloc_gfp()

[Dave Gordon]

From: Chris Wilson <chris@chris-wilson.co.uk>

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>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
---
 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    | 15 ++++-----------
 include/drm/drm_mem_util.h                 | 19 +++++++++++++++++++
 4 files changed, 29 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1328bc5..f734b3c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1775,11 +1775,9 @@ static bool only_mappable_for_reloc(unsigned int flags)
 		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(sizeof(*exec2_list),
+				    args->buffer_count,
+				    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 49e4f26..6af2462 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3416,8 +3416,9 @@ struct i915_vma *
 	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 4b09c84..4c98c8c 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -494,10 +494,7 @@ struct get_pages_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 +631,10 @@ struct get_pages_work {
 	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 e42495a..741ce75 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);
-- 
1.9.1

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

[PATCH v7 7/7] drm: add parameter-order checking to drm memory allocators

[Dave Gordon]

After the recent addition of drm_malloc_gfp(), it was noticed that
some callers of these functions has swapped the parameters in the
call - it's supposed to be 'number of members' and 'sizeof(element)',
but a few callers had got the size first and the count second. This
isn't otherwise detected because they're both type 'size_t', and
the implementation at present just multiplies them anyway, so the
result is still right. But some future implementation might treat
them differently (e.g. allowing 0 elements but not zero size), so
let's add some compile-time checks and complain if the second (size)
parameter isn't a sizeof() expression, or at least a compile-time
constant.

This patch also fixes those callers where the order was wrong.

v6: removed duplicate BUILD_BUG_ON_MSG(); avoided renaming functions
    by shadowing them with #defines and then calling the function
    (non-recursively!) from inside the #define [Chris Wilson]

Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>Cc: dri-
Cc: dri-devel@lists.freedesktop.org
---
 drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c |  2 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c   |  8 ++++----
 include/drm/drm_mem_util.h                   | 27 ++++++++++++++++++++++++---
 3 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 1aba01a..9ae4a71 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -340,7 +340,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 */
 	bos = drm_malloc_ab(args->nr_bos, sizeof(*bos));
 	relocs = drm_malloc_ab(args->nr_relocs, sizeof(*relocs));
-	stream = drm_malloc_ab(1, args->stream_size);
+	stream = drm_malloc_ab(args->stream_size, sizeof(*stream));
 	cmdbuf = etnaviv_gpu_cmdbuf_new(gpu, ALIGN(args->stream_size, 8) + 8,
 					args->nr_bos);
 	if (!bos || !relocs || !stream || !cmdbuf) {
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f734b3c..1a136d9 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1686,8 +1686,8 @@ static bool only_mappable_for_reloc(unsigned int flags)
 	}
 
 	/* Copy in the exec list from userland */
-	exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count);
-	exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count);
+	exec_list = drm_malloc_ab(args->buffer_count, sizeof(*exec_list));
+	exec2_list = drm_malloc_ab(args->buffer_count, sizeof(*exec2_list));
 	if (exec_list == NULL || exec2_list == NULL) {
 		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
 			  args->buffer_count);
@@ -1775,8 +1775,8 @@ static bool only_mappable_for_reloc(unsigned int flags)
 		return -EINVAL;
 	}
 
-	exec2_list = drm_malloc_gfp(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",
diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h
index 741ce75..5b0111c 100644
--- a/include/drm/drm_mem_util.h
+++ b/include/drm/drm_mem_util.h
@@ -29,7 +29,7 @@
 
 #include <linux/vmalloc.h>
 
-static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
+static __inline__ void *drm_calloc_large(size_t nmemb, const size_t size)
 {
 	if (size != 0 && nmemb > SIZE_MAX / size)
 		return NULL;
@@ -41,8 +41,15 @@ static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
 			 GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
 }
 
+#define	drm_calloc_large(nmemb, size)					\
+({									\
+	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
+		"Non-constant 'size' - check argument ordering?");	\
+	(drm_calloc_large)(nmemb, size);				\
+})
+
 /* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */
-static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size)
+static __inline__ void *drm_malloc_ab(size_t nmemb, const size_t size)
 {
 	if (size != 0 && nmemb > SIZE_MAX / size)
 		return NULL;
@@ -54,7 +61,14 @@ 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)
+#define	drm_malloc_ab(nmemb, size)					\
+({									\
+	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
+		"Non-constant 'size' - check argument ordering?");	\
+	(drm_malloc_ab)(nmemb, size);					\
+})
+
+static __inline__ void *drm_malloc_gfp(size_t nmemb, const size_t size, gfp_t gfp)
 {
 	if (size != 0 && nmemb > SIZE_MAX / size)
 		return NULL;
@@ -73,6 +87,13 @@ static __inline__ void *drm_malloc_gfp(size_t nmemb, size_t size, gfp_t gfp)
 			 gfp | __GFP_HIGHMEM, PAGE_KERNEL);
 }
 
+#define	drm_malloc_gfp(nmemb, size, gfp)				\
+({									\
+	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
+		"Non-constant 'size' - check argument ordering?");	\
+	(drm_malloc_gfp)(nmemb, size, gfp);				\
+})
+
 static __inline void drm_free_large(void *ptr)
 {
 	kvfree(ptr);
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v7 7/7] drm: add parameter-order checking to drm memory allocators

[Tvrtko Ursulin]

On 01/03/16 16:33, Dave Gordon wrote:
> After the recent addition of drm_malloc_gfp(), it was noticed that
> some callers of these functions has swapped the parameters in the
> call - it's supposed to be 'number of members' and 'sizeof(element)',
> but a few callers had got the size first and the count second. This
> isn't otherwise detected because they're both type 'size_t', and
> the implementation at present just multiplies them anyway, so the
> result is still right. But some future implementation might treat
> them differently (e.g. allowing 0 elements but not zero size), so
> let's add some compile-time checks and complain if the second (size)
> parameter isn't a sizeof() expression, or at least a compile-time
> constant.
>
> This patch also fixes those callers where the order was wrong.
>
> v6: removed duplicate BUILD_BUG_ON_MSG(); avoided renaming functions
>      by shadowing them with #defines and then calling the function
>      (non-recursively!) from inside the #define [Chris Wilson]
>
> Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
> Cc: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>Cc: dri-
> Cc: dri-devel@lists.freedesktop.org

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

Daniel, there are two DRM core patches in this series and only thing 
missing is convincing Chris that 6/7 does bring some improvement, 
especially looking forward to following GuC refactoring it will enable.

Assuming that gets resolved, I assume because of the core DRM bits I 
will need to ping you to pickup the series?

Regards,

Tvrtko

> ---
>   drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c |  2 +-
>   drivers/gpu/drm/i915/i915_gem_execbuffer.c   |  8 ++++----
>   include/drm/drm_mem_util.h                   | 27 ++++++++++++++++++++++++---
>   3 files changed, 29 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
> index 1aba01a..9ae4a71 100644
> --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
> +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
> @@ -340,7 +340,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
>   	 */
>   	bos = drm_malloc_ab(args->nr_bos, sizeof(*bos));
>   	relocs = drm_malloc_ab(args->nr_relocs, sizeof(*relocs));
> -	stream = drm_malloc_ab(1, args->stream_size);
> +	stream = drm_malloc_ab(args->stream_size, sizeof(*stream));
>   	cmdbuf = etnaviv_gpu_cmdbuf_new(gpu, ALIGN(args->stream_size, 8) + 8,
>   					args->nr_bos);
>   	if (!bos || !relocs || !stream || !cmdbuf) {
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index f734b3c..1a136d9 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -1686,8 +1686,8 @@ static bool only_mappable_for_reloc(unsigned int flags)
>   	}
>
>   	/* Copy in the exec list from userland */
> -	exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count);
> -	exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count);
> +	exec_list = drm_malloc_ab(args->buffer_count, sizeof(*exec_list));
> +	exec2_list = drm_malloc_ab(args->buffer_count, sizeof(*exec2_list));
>   	if (exec_list == NULL || exec2_list == NULL) {
>   		DRM_DEBUG("Failed to allocate exec list for %d buffers\n",
>   			  args->buffer_count);
> @@ -1775,8 +1775,8 @@ static bool only_mappable_for_reloc(unsigned int flags)
>   		return -EINVAL;
>   	}
>
> -	exec2_list = drm_malloc_gfp(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",
> diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h
> index 741ce75..5b0111c 100644
> --- a/include/drm/drm_mem_util.h
> +++ b/include/drm/drm_mem_util.h
> @@ -29,7 +29,7 @@
>
>   #include <linux/vmalloc.h>
>
> -static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
> +static __inline__ void *drm_calloc_large(size_t nmemb, const size_t size)
>   {
>   	if (size != 0 && nmemb > SIZE_MAX / size)
>   		return NULL;
> @@ -41,8 +41,15 @@ static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
>   			 GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
>   }
>
> +#define	drm_calloc_large(nmemb, size)					\
> +({									\
> +	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
> +		"Non-constant 'size' - check argument ordering?");	\
> +	(drm_calloc_large)(nmemb, size);				\
> +})
> +
>   /* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */
> -static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size)
> +static __inline__ void *drm_malloc_ab(size_t nmemb, const size_t size)
>   {
>   	if (size != 0 && nmemb > SIZE_MAX / size)
>   		return NULL;
> @@ -54,7 +61,14 @@ 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)
> +#define	drm_malloc_ab(nmemb, size)					\
> +({									\
> +	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
> +		"Non-constant 'size' - check argument ordering?");	\
> +	(drm_malloc_ab)(nmemb, size);					\
> +})
> +
> +static __inline__ void *drm_malloc_gfp(size_t nmemb, const size_t size, gfp_t gfp)
>   {
>   	if (size != 0 && nmemb > SIZE_MAX / size)
>   		return NULL;
> @@ -73,6 +87,13 @@ static __inline__ void *drm_malloc_gfp(size_t nmemb, size_t size, gfp_t gfp)
>   			 gfp | __GFP_HIGHMEM, PAGE_KERNEL);
>   }
>
> +#define	drm_malloc_gfp(nmemb, size, gfp)				\
> +({									\
> +	BUILD_BUG_ON_MSG(!__builtin_constant_p(size),			\
> +		"Non-constant 'size' - check argument ordering?");	\
> +	(drm_malloc_gfp)(nmemb, size, gfp);				\
> +})
> +
>   static __inline void drm_free_large(void *ptr)
>   {
>   	kvfree(ptr);
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx