Re: [Intel-gfx] [PATCH 03/16] drm/i915: stop using drm_pci_alloc
On Fri, Jun 14, 2019 at 03:47:13PM +0200, Christoph Hellwig wrote:
> Remove usage of the legacy drm PCI DMA wrappers, and with that the
> incorrect usage cocktail of __GFP_COMP, virt_to_page on DMA allocation
> and SetPageReserved.
>
> Signed-off-by: Christoph Hellwig
> ---
> drivers/gpu/drm/i915/i915_gem.c| 30 +-
> drivers/gpu/drm/i915/i915_gem_object.h | 3 ++-
> drivers/gpu/drm/i915/intel_display.c | 2 +-
> 3 files changed, 18 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index ad01c92aaf74..8f2053c91aff 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -228,7 +228,6 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void
> *data,
> static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
> {
> struct address_space *mapping = obj->base.filp->f_mapping;
> - drm_dma_handle_t *phys;
> struct sg_table *st;
> struct scatterlist *sg;
> char *vaddr;
> @@ -242,13 +241,13 @@ static int i915_gem_object_get_pages_phys(struct
> drm_i915_gem_object *obj)
>* to handle all possible callers, and given typical object sizes,
>* the alignment of the buddy allocation will naturally match.
>*/
> - phys = drm_pci_alloc(obj->base.dev,
> - roundup_pow_of_two(obj->base.size),
> - roundup_pow_of_two(obj->base.size));
> - if (!phys)
> + obj->phys_vaddr = dma_alloc_coherent(>base.dev->pdev->dev,
> + roundup_pow_of_two(obj->base.size),
> + >phys_handle, GFP_KERNEL);
> + if (!obj->phys_vaddr)
> return -ENOMEM;
>
> - vaddr = phys->vaddr;
> + vaddr = obj->phys_vaddr;
> for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
> struct page *page;
> char *src;
> @@ -286,18 +285,17 @@ static int i915_gem_object_get_pages_phys(struct
> drm_i915_gem_object *obj)
> sg->offset = 0;
> sg->length = obj->base.size;
>
> - sg_dma_address(sg) = phys->busaddr;
> + sg_dma_address(sg) = obj->phys_handle;
> sg_dma_len(sg) = obj->base.size;
>
> - obj->phys_handle = phys;
> -
> __i915_gem_object_set_pages(obj, st, sg->length);
>
> return 0;
>
> err_phys:
> - drm_pci_free(obj->base.dev, phys);
> -
> + dma_free_coherent(>base.dev->pdev->dev,
> + roundup_pow_of_two(obj->base.size), obj->phys_vaddr,
> + obj->phys_handle);
Need to undo the damage to obj->phys_vaddr here since
i915_gem_pwrite_ioctl() will now use that to determine if it's
dealing with a phys obj.
> return err;
> }
>
> @@ -335,7 +333,7 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object
> *obj,
>
> if (obj->mm.dirty) {
> struct address_space *mapping = obj->base.filp->f_mapping;
> - char *vaddr = obj->phys_handle->vaddr;
> + char *vaddr = obj->phys_vaddr;
> int i;
>
> for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
> @@ -363,7 +361,9 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object
> *obj,
> sg_free_table(pages);
> kfree(pages);
>
> - drm_pci_free(obj->base.dev, obj->phys_handle);
> + dma_free_coherent(>base.dev->pdev->dev,
> + roundup_pow_of_two(obj->base.size), obj->phys_vaddr,
> + obj->phys_handle);
This one is fine I think since the object remains a phys obj once
turned into one. At least the current code isn't clearing
phys_handle here. But my memory is a bit hazy on the details. Chris?
Also maybe s/phys_handle/phys_busaddr/ all over?
> }
>
> static void
> @@ -603,7 +603,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
>struct drm_i915_gem_pwrite *args,
>struct drm_file *file)
> {
> - void *vaddr = obj->phys_handle->vaddr + args->offset;
> + void *vaddr = obj->phys_vaddr + args->offset;
> char __user *user_data = u64_to_user_ptr(args->data_ptr);
>
> /* We manually control the domain here and pretend that it
> @@ -1431,7 +1431,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void
> *data,
> ret = i915_gem_gtt_pwrite_fast(obj, args);
>
> if (ret == -EFAULT || ret == -ENOSPC) {
> - if (obj->phys_handle)
> + if (obj->phys_vaddr)
> ret = i915_gem_phys_pwrite(obj, args, file);
> else
> ret = i915_gem_shmem_pwrite(obj, args);
> diff --git a/drivers/gpu/drm/i915/i915_gem_object.h
> b/drivers/gpu/drm/i915/i915_gem_object.h
> index ca93a40c0c87..14bd2d61d0f6 100644
> --- a/drivers/gpu/drm/i915/i915_gem_object.h
> +++ b/drivers/gpu/drm/i915/i915_gem_object.h
> @@ -290,7 +290,8 @@ struct drm_i915_gem_object {
> };
>
> /** for phys allocated objects
[PATCH 03/16] drm/i915: stop using drm_pci_alloc
Remove usage of the legacy drm PCI DMA wrappers, and with that the
incorrect usage cocktail of __GFP_COMP, virt_to_page on DMA allocation
and SetPageReserved.
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/i915/i915_gem.c| 30 +-
drivers/gpu/drm/i915/i915_gem_object.h | 3 ++-
drivers/gpu/drm/i915/intel_display.c | 2 +-
3 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ad01c92aaf74..8f2053c91aff 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -228,7 +228,6 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void
*data,
static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
{
struct address_space *mapping = obj->base.filp->f_mapping;
- drm_dma_handle_t *phys;
struct sg_table *st;
struct scatterlist *sg;
char *vaddr;
@@ -242,13 +241,13 @@ static int i915_gem_object_get_pages_phys(struct
drm_i915_gem_object *obj)
* to handle all possible callers, and given typical object sizes,
* the alignment of the buddy allocation will naturally match.
*/
- phys = drm_pci_alloc(obj->base.dev,
-roundup_pow_of_two(obj->base.size),
-roundup_pow_of_two(obj->base.size));
- if (!phys)
+ obj->phys_vaddr = dma_alloc_coherent(>base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size),
+ >phys_handle, GFP_KERNEL);
+ if (!obj->phys_vaddr)
return -ENOMEM;
- vaddr = phys->vaddr;
+ vaddr = obj->phys_vaddr;
for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
struct page *page;
char *src;
@@ -286,18 +285,17 @@ static int i915_gem_object_get_pages_phys(struct
drm_i915_gem_object *obj)
sg->offset = 0;
sg->length = obj->base.size;
- sg_dma_address(sg) = phys->busaddr;
+ sg_dma_address(sg) = obj->phys_handle;
sg_dma_len(sg) = obj->base.size;
- obj->phys_handle = phys;
-
__i915_gem_object_set_pages(obj, st, sg->length);
return 0;
err_phys:
- drm_pci_free(obj->base.dev, phys);
-
+ dma_free_coherent(>base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size), obj->phys_vaddr,
+ obj->phys_handle);
return err;
}
@@ -335,7 +333,7 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object
*obj,
if (obj->mm.dirty) {
struct address_space *mapping = obj->base.filp->f_mapping;
- char *vaddr = obj->phys_handle->vaddr;
+ char *vaddr = obj->phys_vaddr;
int i;
for (i = 0; i < obj->base.size / PAGE_SIZE; i++) {
@@ -363,7 +361,9 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object
*obj,
sg_free_table(pages);
kfree(pages);
- drm_pci_free(obj->base.dev, obj->phys_handle);
+ dma_free_coherent(>base.dev->pdev->dev,
+ roundup_pow_of_two(obj->base.size), obj->phys_vaddr,
+ obj->phys_handle);
}
static void
@@ -603,7 +603,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
struct drm_i915_gem_pwrite *args,
struct drm_file *file)
{
- void *vaddr = obj->phys_handle->vaddr + args->offset;
+ void *vaddr = obj->phys_vaddr + args->offset;
char __user *user_data = u64_to_user_ptr(args->data_ptr);
/* We manually control the domain here and pretend that it
@@ -1431,7 +1431,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
ret = i915_gem_gtt_pwrite_fast(obj, args);
if (ret == -EFAULT || ret == -ENOSPC) {
- if (obj->phys_handle)
+ if (obj->phys_vaddr)
ret = i915_gem_phys_pwrite(obj, args, file);
else
ret = i915_gem_shmem_pwrite(obj, args);
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h
b/drivers/gpu/drm/i915/i915_gem_object.h
index ca93a40c0c87..14bd2d61d0f6 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -290,7 +290,8 @@ struct drm_i915_gem_object {
};
/** for phys allocated objects */
- struct drm_dma_handle *phys_handle;
+ dma_addr_t phys_handle;
+ void *phys_vaddr;
struct reservation_object __builtin_resv;
};
diff --git a/drivers/gpu/drm/i915/intel_display.c
b/drivers/gpu/drm/i915/intel_display.c
index 5098228f1302..4f8b368ac4e2 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10066,7 +10066,7 @@ static u32 intel_cursor_base(const struct
intel_plane_state *plane_state)
u32 base;
if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
-
