All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.william.auld@gmail.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Juergen Gross <jgross@suse.com>,
	Stefano Stabellini <sstabellini@kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	ML dri-devel <dri-devel@lists.freedesktop.org>,
	linux-mm@kvack.org, Peter Zijlstra <peterz@infradead.org>,
	kernel list <linux-kernel@vger.kernel.org>,
	Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
	x86@kernel.org, Chris Wilson <chris@chris-wilson.co.uk>,
	Minchan Kim <minchan@kernel.org>,
	Matthew Auld <matthew.auld@intel.com>,
	xen-devel@lists.xenproject.org,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Nitin Gupta <ngupta@vflare.org>
Subject: Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
Date: Fri, 25 Sep 2020 15:08:59 +0100	[thread overview]
Message-ID: <CAM0jSHPaqpX2A5T4iybfLF+F=cBX05GW8u54cUe7AG0QKDJt2g@mail.gmail.com> (raw)
In-Reply-To: <20200924135853.875294-9-hch@lst.de>

On Thu, 24 Sep 2020 at 14:59, Christoph Hellwig <hch@lst.de> 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 <hch@lst.de>
> ---
>  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 {
> -               resource_size_t iomap;
> -               struct sgt_iter iter;
> -               pte_t **ptes = mem;
> -               dma_addr_t addr;
> +       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;
> +}
>
> -               iomap = obj->mm.region->iomap.base;
> -               iomap -= obj->mm.region->region.start;
> +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
> +               enum i915_map_type type)
> +{
> +       resource_size_t iomap = obj->mm.region->iomap.base -
> +               obj->mm.region->region.start;
> +       unsigned long n_pfn = obj->base.size >> PAGE_SHIFT;
> +       unsigned long stack[32], *pfns = stack, i;
> +       struct sgt_iter iter;
> +       dma_addr_t addr;
> +       void *vaddr;
> +
> +       if (type != I915_MAP_WC)
> +               return NULL;
>
> -               for_each_sgt_daddr(addr, iter, sgt)
> -                       **ptes++ = iomap_pte(iomap, addr, pgprot);
> +       if (n_pfn > ARRAY_SIZE(stack)) {
> +               /* Too big for stack -- allocate temporary array instead */
> +               pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
> +               if (!pfns)
> +                       return NULL;
>         }
>
> -       if (mem != stack)
> -               kvfree(mem);
> -
> -       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?

> +       vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
> +       if (pfns != stack)
> +               kvfree(pfns);
> +       return vaddr;
>  }
>
>  /* get, pin, and map the pages of the object into kernel space */
> @@ -383,7 +367,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
>         }
>
>         if (!ptr) {
> -               ptr = i915_gem_object_map(obj, type);
> +               if (GEM_WARN_ON(type == I915_MAP_WC &&
> +                               !static_cpu_has(X86_FEATURE_PAT)))
> +                       ptr = NULL;
> +               else if (i915_gem_object_has_struct_page(obj))
> +                       ptr = i915_gem_object_map_page(obj, type);
> +               else
> +                       ptr = i915_gem_object_map_pfn(obj, type);
>                 if (!ptr) {
>                         err = -ENOMEM;
>                         goto err_unpin;
> --
> 2.28.0
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx

WARNING: multiple messages have this Message-ID
From: Matthew Auld <matthew.william.auld@gmail.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Juergen Gross <jgross@suse.com>,
	Stefano Stabellini <sstabellini@kernel.org>,
	Minchan Kim <minchan@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
	x86@kernel.org, kernel list <linux-kernel@vger.kernel.org>,
	ML dri-devel <dri-devel@lists.freedesktop.org>,
	Chris Wilson <chris@chris-wilson.co.uk>,
	linux-mm@kvack.org, Matthew Wilcox <willy@infradead.org>,
	xen-devel@lists.xenproject.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Nitin Gupta <ngupta@vflare.org>,
	Matthew Auld <matthew.auld@intel.com>
Subject: Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
Date: Fri, 25 Sep 2020 15:08:59 +0100	[thread overview]
Message-ID: <CAM0jSHPaqpX2A5T4iybfLF+F=cBX05GW8u54cUe7AG0QKDJt2g@mail.gmail.com> (raw)
In-Reply-To: <20200924135853.875294-9-hch@lst.de>

On Thu, 24 Sep 2020 at 14:59, Christoph Hellwig <hch@lst.de> 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 <hch@lst.de>
> ---
>  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 {
> -               resource_size_t iomap;
> -               struct sgt_iter iter;
> -               pte_t **ptes = mem;
> -               dma_addr_t addr;
> +       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;
> +}
>
> -               iomap = obj->mm.region->iomap.base;
> -               iomap -= obj->mm.region->region.start;
> +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
> +               enum i915_map_type type)
> +{
> +       resource_size_t iomap = obj->mm.region->iomap.base -
> +               obj->mm.region->region.start;
> +       unsigned long n_pfn = obj->base.size >> PAGE_SHIFT;
> +       unsigned long stack[32], *pfns = stack, i;
> +       struct sgt_iter iter;
> +       dma_addr_t addr;
> +       void *vaddr;
> +
> +       if (type != I915_MAP_WC)
> +               return NULL;
>
> -               for_each_sgt_daddr(addr, iter, sgt)
> -                       **ptes++ = iomap_pte(iomap, addr, pgprot);
> +       if (n_pfn > ARRAY_SIZE(stack)) {
> +               /* Too big for stack -- allocate temporary array instead */
> +               pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
> +               if (!pfns)
> +                       return NULL;
>         }
>
> -       if (mem != stack)
> -               kvfree(mem);
> -
> -       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?

> +       vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
> +       if (pfns != stack)
> +               kvfree(pfns);
> +       return vaddr;
>  }
>
>  /* get, pin, and map the pages of the object into kernel space */
> @@ -383,7 +367,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
>         }
>
>         if (!ptr) {
> -               ptr = i915_gem_object_map(obj, type);
> +               if (GEM_WARN_ON(type == I915_MAP_WC &&
> +                               !static_cpu_has(X86_FEATURE_PAT)))
> +                       ptr = NULL;
> +               else if (i915_gem_object_has_struct_page(obj))
> +                       ptr = i915_gem_object_map_page(obj, type);
> +               else
> +                       ptr = i915_gem_object_map_pfn(obj, type);
>                 if (!ptr) {
>                         err = -ENOMEM;
>                         goto err_unpin;
> --
> 2.28.0
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

WARNING: multiple messages have this Message-ID
From: Matthew Auld <matthew.william.auld@gmail.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Juergen Gross <jgross@suse.com>,
	Stefano Stabellini <sstabellini@kernel.org>,
	Minchan Kim <minchan@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
	x86@kernel.org, kernel list <linux-kernel@vger.kernel.org>,
	ML dri-devel <dri-devel@lists.freedesktop.org>,
	Chris Wilson <chris@chris-wilson.co.uk>,
	linux-mm@kvack.org, Matthew Wilcox <willy@infradead.org>,
	xen-devel@lists.xenproject.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Nitin Gupta <ngupta@vflare.org>,
	Matthew Auld <matthew.auld@intel.com>
Subject: Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map
Date: Fri, 25 Sep 2020 15:08:59 +0100	[thread overview]
Message-ID: <CAM0jSHPaqpX2A5T4iybfLF+F=cBX05GW8u54cUe7AG0QKDJt2g@mail.gmail.com> (raw)
In-Reply-To: <20200924135853.875294-9-hch@lst.de>

On Thu, 24 Sep 2020 at 14:59, Christoph Hellwig <hch@lst.de> 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 <hch@lst.de>
> ---
>  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 {
> -               resource_size_t iomap;
> -               struct sgt_iter iter;
> -               pte_t **ptes = mem;
> -               dma_addr_t addr;
> +       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;
> +}
>
> -               iomap = obj->mm.region->iomap.base;
> -               iomap -= obj->mm.region->region.start;
> +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
> +               enum i915_map_type type)
> +{
> +       resource_size_t iomap = obj->mm.region->iomap.base -
> +               obj->mm.region->region.start;
> +       unsigned long n_pfn = obj->base.size >> PAGE_SHIFT;
> +       unsigned long stack[32], *pfns = stack, i;
> +       struct sgt_iter iter;
> +       dma_addr_t addr;
> +       void *vaddr;
> +
> +       if (type != I915_MAP_WC)
> +               return NULL;
>
> -               for_each_sgt_daddr(addr, iter, sgt)
> -                       **ptes++ = iomap_pte(iomap, addr, pgprot);
> +       if (n_pfn > ARRAY_SIZE(stack)) {
> +               /* Too big for stack -- allocate temporary array instead */
> +               pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
> +               if (!pfns)
> +                       return NULL;
>         }
>
> -       if (mem != stack)
> -               kvfree(mem);
> -
> -       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?

> +       vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
> +       if (pfns != stack)
> +               kvfree(pfns);
> +       return vaddr;
>  }
>
>  /* get, pin, and map the pages of the object into kernel space */
> @@ -383,7 +367,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
>         }
>
>         if (!ptr) {
> -               ptr = i915_gem_object_map(obj, type);
> +               if (GEM_WARN_ON(type == I915_MAP_WC &&
> +                               !static_cpu_has(X86_FEATURE_PAT)))
> +                       ptr = NULL;
> +               else if (i915_gem_object_has_struct_page(obj))
> +                       ptr = i915_gem_object_map_page(obj, type);
> +               else
> +                       ptr = i915_gem_object_map_pfn(obj, type);
>                 if (!ptr) {
>                         err = -ENOMEM;
>                         goto err_unpin;
> --
> 2.28.0
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2020-09-25 14:09 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-24 13:58 remove alloc_vm_area v2 Christoph Hellwig
2020-09-24 13:58 ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 01/11] mm: update the documentation for vfree Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 02/11] mm: add a VM_MAP_PUT_PAGES flag for vmap Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 03/11] mm: add a vmap_pfn function Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 04/11] mm: allow a NULL fn callback in apply_to_page_range Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 05/11] zsmalloc: switch from alloc_vm_area to get_vm_area Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 06/11] drm/i915: use vmap in shmem_pin_map Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-25 13:05   ` Tvrtko Ursulin
2020-09-25 13:05     ` [Intel-gfx] " Tvrtko Ursulin
2020-09-25 13:05     ` Tvrtko Ursulin
2020-09-24 13:58 ` [PATCH 07/11] drm/i915: stop using kmap in i915_gem_object_map Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-25 13:01   ` Tvrtko Ursulin
2020-09-25 13:01     ` [Intel-gfx] " Tvrtko Ursulin
2020-09-25 13:01     ` Tvrtko Ursulin
2020-09-24 13:58 ` [PATCH 08/11] drm/i915: use vmap " Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-25 13:11   ` Tvrtko Ursulin
2020-09-25 13:11     ` [Intel-gfx] " Tvrtko Ursulin
2020-09-25 13:11     ` Tvrtko Ursulin
2020-09-25 14:08   ` Matthew Auld [this message]
2020-09-25 14:08     ` [Intel-gfx] " Matthew Auld
2020-09-25 14:08     ` Matthew Auld
2020-09-25 14:08     ` Matthew Auld
2020-09-25 14:08     ` Matthew Auld
2020-09-25 16:02     ` Christoph Hellwig
2020-09-25 16:02       ` Christoph Hellwig
2020-09-25 16:09   ` [PATCH 08/11, fixed] " Christoph Hellwig
2020-09-25 16:09     ` [Intel-gfx] " Christoph Hellwig
2020-09-24 13:58 ` [PATCH 09/11] xen/xenbus: use apply_to_page_range directly in xenbus_map_ring_pv Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 23:42   ` boris.ostrovsky
2020-09-24 23:42     ` [Intel-gfx] " boris.ostrovsky
2020-09-24 23:42     ` boris.ostrovsky
2020-09-24 13:58 ` [PATCH 10/11] x86/xen: open code alloc_vm_area in arch_gnttab_valloc Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 23:43   ` boris.ostrovsky
2020-09-24 23:43     ` [Intel-gfx] " boris.ostrovsky
2020-09-24 23:43     ` boris.ostrovsky
2020-09-24 13:58 ` [PATCH 11/11] mm: remove alloc_vm_area Christoph Hellwig
2020-09-24 13:58   ` [Intel-gfx] " Christoph Hellwig
2020-09-24 15:09 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/11] mm: update the documentation for vfree Patchwork
2020-09-24 15:34 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-09-24 20:44 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2020-09-25 16:50 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [01/11] mm: update the documentation for vfree (rev2) Patchwork
2020-09-26  0:08 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
2020-09-26  2:43 ` remove alloc_vm_area v2 Andrew Morton
2020-09-26  2:43   ` [Intel-gfx] " Andrew Morton
2020-09-26  2:43   ` Andrew Morton
2020-09-26  6:29   ` Christoph Hellwig
2020-09-26  6:29     ` [Intel-gfx] " Christoph Hellwig
2020-09-28 10:13     ` Joonas Lahtinen
2020-09-28 10:13       ` [Intel-gfx] " Joonas Lahtinen
2020-09-28 10:13       ` Joonas Lahtinen
2020-09-28 12:37       ` Christoph Hellwig
2020-09-28 12:37         ` [Intel-gfx] " Christoph Hellwig
2020-09-29 12:43         ` Joonas Lahtinen
2020-09-29 12:43           ` [Intel-gfx] " Joonas Lahtinen
2020-09-29 12:43           ` Joonas Lahtinen
2020-09-30 14:48           ` Christoph Hellwig
2020-09-30 14:48             ` [Intel-gfx] " Christoph Hellwig
2020-09-30 18:37             ` Daniel Vetter
2020-09-30 18:37               ` [Intel-gfx] " Daniel Vetter
2020-09-30 18:37               ` Daniel Vetter
2020-09-30 18:37               ` Daniel Vetter
2020-10-02 12:21 remove alloc_vm_area v4 Christoph Hellwig
2020-10-02 12:22 ` [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAM0jSHPaqpX2A5T4iybfLF+F=cBX05GW8u54cUe7AG0QKDJt2g@mail.gmail.com' \
    --to=matthew.william.auld@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=boris.ostrovsky@oracle.com \
    --cc=chris@chris-wilson.co.uk \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hch@lst.de \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jgross@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=matthew.auld@intel.com \
    --cc=minchan@kernel.org \
    --cc=ngupta@vflare.org \
    --cc=peterz@infradead.org \
    --cc=sstabellini@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [Intel-gfx] [PATCH 08/11] drm/i915: use vmap in i915_gem_object_map' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.