[Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
i915_gem_object_map implements fairly low-level vmap functionality in
a driver. Split it into two helpers, one for remapping kernel memory
which can use vmap, and one for I/O memory that uses vmap_pfn.
The only practical difference is that alloc_vm_area prefeaults the
vmalloc area PTEs, which doesn't seem to be required here for the
kernel memory case (and could be added to vmap using a flag if actually
required).
Signed-off-by: Christoph Hellwig
Reviewed-by: Tvrtko Ursulin
---
drivers/gpu/drm/i915/Kconfig | 1 +
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 127 ++
2 files changed, 60 insertions(+), 68 deletions(-)
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 9afa5c4a6bf006..1e1cb245fca778 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -25,6 +25,7 @@ config DRM_I915
select CRC32
select SND_HDA_I915 if SND_HDA_CORE
select CEC_CORE if CEC_NOTIFIER
+ select VMAP_PFN
help
Choose this option if you have a system that has "Intel Graphics
Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 6550c0bc824ea2..f60ca6dc911f29 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct
drm_i915_gem_object *obj)
return err;
}
-static inline pte_t iomap_pte(resource_size_t base,
- dma_addr_t offset,
- pgprot_t prot)
-{
- return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
-}
-
/* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
-enum i915_map_type type)
+static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
+ enum i915_map_type type)
{
- unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
- struct sg_table *sgt = obj->mm.pages;
- pte_t *stack[32], **mem;
- struct vm_struct *area;
+ unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
+ struct page *stack[32], **pages = stack, *page;
+ struct sgt_iter iter;
pgprot_t pgprot;
+ void *vaddr;
- if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
- return NULL;
-
- if (GEM_WARN_ON(type == I915_MAP_WC &&
- !static_cpu_has(X86_FEATURE_PAT)))
- return NULL;
-
- /* A single page can always be kmapped */
- if (n_pte == 1 && type == I915_MAP_WB) {
- struct page *page = sg_page(sgt->sgl);
-
+ switch (type) {
+ default:
+ MISSING_CASE(type);
+ fallthrough;/* to use PAGE_KERNEL anyway */
+ case I915_MAP_WB:
/*
* On 32b, highmem using a finite set of indirect PTE (i.e.
* vmap) to provide virtual mappings of the high pages.
@@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
* So if the page is beyond the 32b boundary, make an explicit
* vmap.
*/
- if (!PageHighMem(page))
- return page_address(page);
- }
-
- mem = stack;
- if (n_pte > ARRAY_SIZE(stack)) {
- /* Too big for stack -- allocate temporary array instead */
- mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
- if (!mem)
- return NULL;
- }
-
- area = alloc_vm_area(obj->base.size, mem);
- if (!area) {
- if (mem != stack)
- kvfree(mem);
- return NULL;
- }
-
- switch (type) {
- default:
- MISSING_CASE(type);
- fallthrough;/* to use PAGE_KERNEL anyway */
- case I915_MAP_WB:
+ if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl)))
+ return page_address(sg_page(obj->mm.pages->sgl));
pgprot = PAGE_KERNEL;
break;
case I915_MAP_WC:
@@ -308,30 +273,50 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
break;
}
- if (i915_gem_object_has_struct_page(obj)) {
- struct sgt_iter iter;
- struct page *page;
- pte_t **ptes = mem;
+ if (n_pages > ARRAY_SIZE(stack)) {
+ /* Too big for stack -- allocate temporary array instead */
+ pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+ }
- for_each_sgt_page(page, iter, sgt)
- **ptes++ = mk_pte(p
Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
On Fri, Sep 25, 2020 at 03:08:59PM +0100, Matthew Auld wrote: > > + i = 0; > > + for_each_sgt_page(page, iter, obj->mm.pages) > > + pages[i++] = page; > > + vaddr = vmap(pages, n_pages, 0, pgprot); > > + if (pages != stack) > > + kvfree(pages); > > + return vaddr; > > +} > > - return area->addr; > > + for_each_sgt_daddr(addr, iter, obj->mm.pages) > > + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; > > Missing the i = 0 fix from Dan? Yeah, looks like I only managed to apply the one in the page based version above. ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
On Thu, 24 Sep 2020 at 14:59, Christoph Hellwig wrote:
>
> i915_gem_object_map implements fairly low-level vmap functionality in
> a driver. Split it into two helpers, one for remapping kernel memory
> which can use vmap, and one for I/O memory that uses vmap_pfn.
>
> The only practical difference is that alloc_vm_area prefeaults the
> vmalloc area PTEs, which doesn't seem to be required here for the
> kernel memory case (and could be added to vmap using a flag if actually
> required).
>
> Signed-off-by: Christoph Hellwig
> ---
> drivers/gpu/drm/i915/Kconfig | 1 +
> drivers/gpu/drm/i915/gem/i915_gem_pages.c | 126 ++
> 2 files changed, 59 insertions(+), 68 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
> index 9afa5c4a6bf006..1e1cb245fca778 100644
> --- a/drivers/gpu/drm/i915/Kconfig
> +++ b/drivers/gpu/drm/i915/Kconfig
> @@ -25,6 +25,7 @@ config DRM_I915
> select CRC32
> select SND_HDA_I915 if SND_HDA_CORE
> select CEC_CORE if CEC_NOTIFIER
> + select VMAP_PFN
> help
> Choose this option if you have a system that has "Intel Graphics
> Media Accelerator" or "HD Graphics" integrated graphics,
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> index 6550c0bc824ea2..b519417667eb4b 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> @@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct
> drm_i915_gem_object *obj)
> return err;
> }
>
> -static inline pte_t iomap_pte(resource_size_t base,
> - dma_addr_t offset,
> - pgprot_t prot)
> -{
> - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
> -}
> -
> /* The 'mapping' part of i915_gem_object_pin_map() below */
> -static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
> -enum i915_map_type type)
> +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
> + enum i915_map_type type)
> {
> - unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
> - struct sg_table *sgt = obj->mm.pages;
> - pte_t *stack[32], **mem;
> - struct vm_struct *area;
> + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
> + struct page *stack[32], **pages = stack, *page;
> + struct sgt_iter iter;
> pgprot_t pgprot;
> + void *vaddr;
>
> - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
> - return NULL;
> -
> - if (GEM_WARN_ON(type == I915_MAP_WC &&
> - !static_cpu_has(X86_FEATURE_PAT)))
> - return NULL;
> -
> - /* A single page can always be kmapped */
> - if (n_pte == 1 && type == I915_MAP_WB) {
> - struct page *page = sg_page(sgt->sgl);
> -
> + switch (type) {
> + default:
> + MISSING_CASE(type);
> + fallthrough;/* to use PAGE_KERNEL anyway */
> + case I915_MAP_WB:
> /*
> * On 32b, highmem using a finite set of indirect PTE (i.e.
> * vmap) to provide virtual mappings of the high pages.
> @@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct
> drm_i915_gem_object *obj,
> * So if the page is beyond the 32b boundary, make an explicit
> * vmap.
> */
> - if (!PageHighMem(page))
> - return page_address(page);
> - }
> -
> - mem = stack;
> - if (n_pte > ARRAY_SIZE(stack)) {
> - /* Too big for stack -- allocate temporary array instead */
> - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
> - if (!mem)
> - return NULL;
> - }
> -
> - area = alloc_vm_area(obj->base.size, mem);
> - if (!area) {
> - if (mem != stack)
> - kvfree(mem);
> - return NULL;
> - }
> -
> - switch (type) {
> - default:
> - MISSING_CASE(type);
> - fallthrough;/* to use PAGE_KERNEL anyway */
> - case I915_MAP_WB:
> + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl)))
> + return page_address(sg_page(obj->mm.pages->sgl));
> pgprot = PAGE_KERNEL;
> break;
> case I915_MAP_WC:
> @@ -308,30 +273,49 @@ static void *i915_gem_object_map(struct
> drm_i915_gem_object *obj,
> break;
> }
>
> - if (i915_gem_object_has_struct_page(obj)) {
> - struct sgt_iter iter;
> - struct page *page;
> - pte_t **ptes = mem;
> + if (n_pages > ARRAY_SIZE(stack)) {
> + /* Too big for stack -- allocate tempora
Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
On 24/09/2020 14:58, Christoph Hellwig wrote:
i915_gem_object_map implements fairly low-level vmap functionality in
a driver. Split it into two helpers, one for remapping kernel memory
which can use vmap, and one for I/O memory that uses vmap_pfn.
The only practical difference is that alloc_vm_area prefeaults the
vmalloc area PTEs, which doesn't seem to be required here for the
kernel memory case (and could be added to vmap using a flag if actually
required).
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/i915/Kconfig | 1 +
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 126 ++
2 files changed, 59 insertions(+), 68 deletions(-)
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 9afa5c4a6bf006..1e1cb245fca778 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -25,6 +25,7 @@ config DRM_I915
select CRC32
select SND_HDA_I915 if SND_HDA_CORE
select CEC_CORE if CEC_NOTIFIER
+ select VMAP_PFN
help
Choose this option if you have a system that has "Intel Graphics
Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 6550c0bc824ea2..b519417667eb4b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct
drm_i915_gem_object *obj)
return err;
}
-static inline pte_t iomap_pte(resource_size_t base,
- dma_addr_t offset,
- pgprot_t prot)
-{
- return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
-}
-
/* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
-enum i915_map_type type)
+static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
+ enum i915_map_type type)
{
- unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
- struct sg_table *sgt = obj->mm.pages;
- pte_t *stack[32], **mem;
- struct vm_struct *area;
+ unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
+ struct page *stack[32], **pages = stack, *page;
+ struct sgt_iter iter;
pgprot_t pgprot;
+ void *vaddr;
- if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
- return NULL;
-
- if (GEM_WARN_ON(type == I915_MAP_WC &&
- !static_cpu_has(X86_FEATURE_PAT)))
- return NULL;
-
- /* A single page can always be kmapped */
- if (n_pte == 1 && type == I915_MAP_WB) {
- struct page *page = sg_page(sgt->sgl);
-
+ switch (type) {
+ default:
+ MISSING_CASE(type);
+ fallthrough;/* to use PAGE_KERNEL anyway */
+ case I915_MAP_WB:
/*
* On 32b, highmem using a finite set of indirect PTE (i.e.
* vmap) to provide virtual mappings of the high pages.
@@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
* So if the page is beyond the 32b boundary, make an explicit
* vmap.
*/
- if (!PageHighMem(page))
- return page_address(page);
- }
-
- mem = stack;
- if (n_pte > ARRAY_SIZE(stack)) {
- /* Too big for stack -- allocate temporary array instead */
- mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
- if (!mem)
- return NULL;
- }
-
- area = alloc_vm_area(obj->base.size, mem);
- if (!area) {
- if (mem != stack)
- kvfree(mem);
- return NULL;
- }
-
- switch (type) {
- default:
- MISSING_CASE(type);
- fallthrough;/* to use PAGE_KERNEL anyway */
- case I915_MAP_WB:
+ if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl)))
+ return page_address(sg_page(obj->mm.pages->sgl));
pgprot = PAGE_KERNEL;
break;
case I915_MAP_WC:
@@ -308,30 +273,49 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
break;
}
- if (i915_gem_object_has_struct_page(obj)) {
- struct sgt_iter iter;
- struct page *page;
- pte_t **ptes = mem;
+ if (n_pages > ARRAY_SIZE(stack)) {
+ /* Too big for stack -- allocate temporary array instead */
+ pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+ }
- for_each_sgt_page(page, iter, sgt)
- **ptes++
[Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
i915_gem_object_map implements fairly low-level vmap functionality in
a driver. Split it into two helpers, one for remapping kernel memory
which can use vmap, and one for I/O memory that uses vmap_pfn.
The only practical difference is that alloc_vm_area prefeaults the
vmalloc area PTEs, which doesn't seem to be required here for the
kernel memory case (and could be added to vmap using a flag if actually
required).
Signed-off-by: Christoph Hellwig
---
drivers/gpu/drm/i915/Kconfig | 1 +
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 126 ++
2 files changed, 59 insertions(+), 68 deletions(-)
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 9afa5c4a6bf006..1e1cb245fca778 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -25,6 +25,7 @@ config DRM_I915
select CRC32
select SND_HDA_I915 if SND_HDA_CORE
select CEC_CORE if CEC_NOTIFIER
+ select VMAP_PFN
help
Choose this option if you have a system that has "Intel Graphics
Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 6550c0bc824ea2..b519417667eb4b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -232,34 +232,21 @@ int __i915_gem_object_put_pages(struct
drm_i915_gem_object *obj)
return err;
}
-static inline pte_t iomap_pte(resource_size_t base,
- dma_addr_t offset,
- pgprot_t prot)
-{
- return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
-}
-
/* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
-enum i915_map_type type)
+static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
+ enum i915_map_type type)
{
- unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
- struct sg_table *sgt = obj->mm.pages;
- pte_t *stack[32], **mem;
- struct vm_struct *area;
+ unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
+ struct page *stack[32], **pages = stack, *page;
+ struct sgt_iter iter;
pgprot_t pgprot;
+ void *vaddr;
- if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
- return NULL;
-
- if (GEM_WARN_ON(type == I915_MAP_WC &&
- !static_cpu_has(X86_FEATURE_PAT)))
- return NULL;
-
- /* A single page can always be kmapped */
- if (n_pte == 1 && type == I915_MAP_WB) {
- struct page *page = sg_page(sgt->sgl);
-
+ switch (type) {
+ default:
+ MISSING_CASE(type);
+ fallthrough;/* to use PAGE_KERNEL anyway */
+ case I915_MAP_WB:
/*
* On 32b, highmem using a finite set of indirect PTE (i.e.
* vmap) to provide virtual mappings of the high pages.
@@ -277,30 +264,8 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
* So if the page is beyond the 32b boundary, make an explicit
* vmap.
*/
- if (!PageHighMem(page))
- return page_address(page);
- }
-
- mem = stack;
- if (n_pte > ARRAY_SIZE(stack)) {
- /* Too big for stack -- allocate temporary array instead */
- mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
- if (!mem)
- return NULL;
- }
-
- area = alloc_vm_area(obj->base.size, mem);
- if (!area) {
- if (mem != stack)
- kvfree(mem);
- return NULL;
- }
-
- switch (type) {
- default:
- MISSING_CASE(type);
- fallthrough;/* to use PAGE_KERNEL anyway */
- case I915_MAP_WB:
+ if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl)))
+ return page_address(sg_page(obj->mm.pages->sgl));
pgprot = PAGE_KERNEL;
break;
case I915_MAP_WC:
@@ -308,30 +273,49 @@ static void *i915_gem_object_map(struct
drm_i915_gem_object *obj,
break;
}
- if (i915_gem_object_has_struct_page(obj)) {
- struct sgt_iter iter;
- struct page *page;
- pte_t **ptes = mem;
+ if (n_pages > ARRAY_SIZE(stack)) {
+ /* Too big for stack -- allocate temporary array instead */
+ pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+ }
- for_each_sgt_page(page, iter, sgt)
- **ptes++ = mk_pte(page, pgprot);
- } else
