[Intel-gfx] [PATCH 08/21] drm/i915/gtt: Introduce struct i915_page_dma
Michel Thierry
michel.thierry at intel.com
Mon Jun 22 07:05:09 PDT 2015
On 6/11/2015 6:48 PM, Mika Kuoppala wrote:
> All our paging structures have struct page and dma address
> for that page.
>
> Add struct for page/dma address pairs and use it to make
> the setup and teardown for different paging structures
> identical.
>
> Include the page directory offset also in the struct for legacy
> gens. Rename it to clearly point out that it is offset into the
> ggtt.
>
> v2: Add comment about ggtt_offset (Michel)
>
Reviewed-by: Michel Thierry <michel.thierry at intel.com>
> Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
> ---
> drivers/gpu/drm/i915/i915_debugfs.c | 2 +-
> drivers/gpu/drm/i915/i915_gem_gtt.c | 120 ++++++++++++++----------------------
> drivers/gpu/drm/i915/i915_gem_gtt.h | 25 +++++---
> 3 files changed, 64 insertions(+), 83 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 14f5d16..5a7a20a 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -2248,7 +2248,7 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
> struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
>
> seq_puts(m, "aliasing PPGTT:\n");
> - seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.pd_offset);
> + seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.base.ggtt_offset);
>
> ppgtt->debug_dump(ppgtt, m);
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index 5832f53..65ee92f 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -301,52 +301,39 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
> return pte;
> }
>
> -#define i915_dma_unmap_single(px, dev) \
> - __i915_dma_unmap_single((px)->daddr, dev)
> -
> -static void __i915_dma_unmap_single(dma_addr_t daddr,
> - struct drm_device *dev)
> +static int setup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
> {
> struct device *device = &dev->pdev->dev;
>
> - dma_unmap_page(device, daddr, 4096, PCI_DMA_BIDIRECTIONAL);
> -}
> -
> -/**
> - * i915_dma_map_single() - Create a dma mapping for a page table/dir/etc.
> - * @px: Page table/dir/etc to get a DMA map for
> - * @dev: drm device
> - *
> - * Page table allocations are unified across all gens. They always require a
> - * single 4k allocation, as well as a DMA mapping. If we keep the structs
> - * symmetric here, the simple macro covers us for every page table type.
> - *
> - * Return: 0 if success.
> - */
> -#define i915_dma_map_single(px, dev) \
> - i915_dma_map_page_single((px)->page, (dev), &(px)->daddr)
> + p->page = alloc_page(GFP_KERNEL);
> + if (!p->page)
> + return -ENOMEM;
>
> -static int i915_dma_map_page_single(struct page *page,
> - struct drm_device *dev,
> - dma_addr_t *daddr)
> -{
> - struct device *device = &dev->pdev->dev;
> + p->daddr = dma_map_page(device,
> + p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
>
> - *daddr = dma_map_page(device, page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
> - if (dma_mapping_error(device, *daddr))
> - return -ENOMEM;
> + if (dma_mapping_error(device, p->daddr)) {
> + __free_page(p->page);
> + return -EINVAL;
> + }
>
> return 0;
> }
>
> -static void unmap_and_free_pt(struct i915_page_table *pt,
> - struct drm_device *dev)
> +static void cleanup_page_dma(struct drm_device *dev, struct i915_page_dma *p)
> {
> - if (WARN_ON(!pt->page))
> + if (WARN_ON(!p->page))
> return;
>
> - i915_dma_unmap_single(pt, dev);
> - __free_page(pt->page);
> + dma_unmap_page(&dev->pdev->dev, p->daddr, 4096, PCI_DMA_BIDIRECTIONAL);
> + __free_page(p->page);
> + memset(p, 0, sizeof(*p));
> +}
> +
> +static void unmap_and_free_pt(struct i915_page_table *pt,
> + struct drm_device *dev)
> +{
> + cleanup_page_dma(dev, &pt->base);
> kfree(pt->used_ptes);
> kfree(pt);
> }
> @@ -357,7 +344,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
> gen8_pte_t *pt_vaddr, scratch_pte;
> int i;
>
> - pt_vaddr = kmap_atomic(pt->page);
> + pt_vaddr = kmap_atomic(pt->base.page);
> scratch_pte = gen8_pte_encode(vm->scratch.addr,
> I915_CACHE_LLC, true);
>
> @@ -386,19 +373,13 @@ static struct i915_page_table *alloc_pt(struct drm_device *dev)
> if (!pt->used_ptes)
> goto fail_bitmap;
>
> - pt->page = alloc_page(GFP_KERNEL);
> - if (!pt->page)
> - goto fail_page;
> -
> - ret = i915_dma_map_single(pt, dev);
> + ret = setup_page_dma(dev, &pt->base);
> if (ret)
> - goto fail_dma;
> + goto fail_page_m;
>
> return pt;
>
> -fail_dma:
> - __free_page(pt->page);
> -fail_page:
> +fail_page_m:
> kfree(pt->used_ptes);
> fail_bitmap:
> kfree(pt);
> @@ -409,9 +390,8 @@ fail_bitmap:
> static void unmap_and_free_pd(struct i915_page_directory *pd,
> struct drm_device *dev)
> {
> - if (pd->page) {
> - i915_dma_unmap_single(pd, dev);
> - __free_page(pd->page);
> + if (pd->base.page) {
> + cleanup_page_dma(dev, &pd->base);
> kfree(pd->used_pdes);
> kfree(pd);
> }
> @@ -431,18 +411,12 @@ static struct i915_page_directory *alloc_pd(struct drm_device *dev)
> if (!pd->used_pdes)
> goto free_pd;
>
> - pd->page = alloc_page(GFP_KERNEL);
> - if (!pd->page)
> - goto free_bitmap;
> -
> - ret = i915_dma_map_single(pd, dev);
> + ret = setup_page_dma(dev, &pd->base);
> if (ret)
> - goto free_page;
> + goto free_bitmap;
>
> return pd;
>
> -free_page:
> - __free_page(pd->page);
> free_bitmap:
> kfree(pd->used_pdes);
> free_pd:
> @@ -523,10 +497,10 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
>
> pt = pd->page_table[pde];
>
> - if (WARN_ON(!pt->page))
> + if (WARN_ON(!pt->base.page))
> continue;
>
> - page_table = pt->page;
> + page_table = pt->base.page;
>
> last_pte = pte + num_entries;
> if (last_pte > GEN8_PTES)
> @@ -573,7 +547,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
> if (pt_vaddr == NULL) {
> struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe];
> struct i915_page_table *pt = pd->page_table[pde];
> - struct page *page_table = pt->page;
> + struct page *page_table = pt->base.page;
>
> pt_vaddr = kmap_atomic(page_table);
> }
> @@ -605,7 +579,7 @@ static void __gen8_do_map_pt(gen8_pde_t * const pde,
> struct drm_device *dev)
> {
> gen8_pde_t entry =
> - gen8_pde_encode(dev, pt->daddr, I915_CACHE_LLC);
> + gen8_pde_encode(dev, pt->base.daddr, I915_CACHE_LLC);
> *pde = entry;
> }
>
> @@ -618,7 +592,7 @@ static void gen8_initialize_pd(struct i915_address_space *vm,
> struct i915_page_table *pt;
> int i;
>
> - page_directory = kmap_atomic(pd->page);
> + page_directory = kmap_atomic(pd->base.page);
> pt = ppgtt->scratch_pt;
> for (i = 0; i < I915_PDES; i++)
> /* Map the PDE to the page table */
> @@ -633,7 +607,7 @@ static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_dev
> {
> int i;
>
> - if (!pd->page)
> + if (!pd->base.page)
> return;
>
> for_each_set_bit(i, pd->used_pdes, I915_PDES) {
> @@ -884,7 +858,7 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
> /* Allocations have completed successfully, so set the bitmaps, and do
> * the mappings. */
> gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
> - gen8_pde_t *const page_directory = kmap_atomic(pd->page);
> + gen8_pde_t *const page_directory = kmap_atomic(pd->base.page);
> struct i915_page_table *pt;
> uint64_t pd_len = gen8_clamp_pd(start, length);
> uint64_t pd_start = start;
> @@ -995,7 +969,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
> gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde) {
> u32 expected;
> gen6_pte_t *pt_vaddr;
> - dma_addr_t pt_addr = ppgtt->pd.page_table[pde]->daddr;
> + dma_addr_t pt_addr = ppgtt->pd.page_table[pde]->base.daddr;
> pd_entry = readl(ppgtt->pd_addr + pde);
> expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
>
> @@ -1006,7 +980,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
> expected);
> seq_printf(m, "\tPDE: %x\n", pd_entry);
>
> - pt_vaddr = kmap_atomic(ppgtt->pd.page_table[pde]->page);
> + pt_vaddr = kmap_atomic(ppgtt->pd.page_table[pde]->base.page);
> for (pte = 0; pte < GEN6_PTES; pte+=4) {
> unsigned long va =
> (pde * PAGE_SIZE * GEN6_PTES) +
> @@ -1041,7 +1015,7 @@ static void gen6_write_pde(struct i915_page_directory *pd,
> container_of(pd, struct i915_hw_ppgtt, pd);
> u32 pd_entry;
>
> - pd_entry = GEN6_PDE_ADDR_ENCODE(pt->daddr);
> + pd_entry = GEN6_PDE_ADDR_ENCODE(pt->base.daddr);
> pd_entry |= GEN6_PDE_VALID;
>
> writel(pd_entry, ppgtt->pd_addr + pde);
> @@ -1066,9 +1040,9 @@ static void gen6_write_page_range(struct drm_i915_private *dev_priv,
>
> static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
> {
> - BUG_ON(ppgtt->pd.pd_offset & 0x3f);
> + BUG_ON(ppgtt->pd.base.ggtt_offset & 0x3f);
>
> - return (ppgtt->pd.pd_offset / 64) << 16;
> + return (ppgtt->pd.base.ggtt_offset / 64) << 16;
> }
>
> static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
> @@ -1231,7 +1205,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
> if (last_pte > GEN6_PTES)
> last_pte = GEN6_PTES;
>
> - pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->page);
> + pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->base.page);
>
> for (i = first_pte; i < last_pte; i++)
> pt_vaddr[i] = scratch_pte;
> @@ -1260,7 +1234,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
> pt_vaddr = NULL;
> for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
> if (pt_vaddr == NULL)
> - pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->page);
> + pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->base.page);
>
> pt_vaddr[act_pte] =
> vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
> @@ -1288,7 +1262,7 @@ static void gen6_initialize_pt(struct i915_address_space *vm,
> scratch_pte = vm->pte_encode(vm->scratch.addr,
> I915_CACHE_LLC, true, 0);
>
> - pt_vaddr = kmap_atomic(pt->page);
> + pt_vaddr = kmap_atomic(pt->base.page);
>
> for (i = 0; i < GEN6_PTES; i++)
> pt_vaddr[i] = scratch_pte;
> @@ -1504,11 +1478,11 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
> ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
> ppgtt->debug_dump = gen6_dump_ppgtt;
>
> - ppgtt->pd.pd_offset =
> + ppgtt->pd.base.ggtt_offset =
> ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
>
> ppgtt->pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
> - ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
> + ppgtt->pd.base.ggtt_offset / sizeof(gen6_pte_t);
>
> gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);
>
> @@ -1519,7 +1493,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
> ppgtt->node.start / PAGE_SIZE);
>
> DRM_DEBUG("Adding PPGTT at offset %x\n",
> - ppgtt->pd.pd_offset << 10);
> + ppgtt->pd.base.ggtt_offset << 10);
>
> return 0;
> }
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
> index da67542..0ccdf54 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.h
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
> @@ -205,19 +205,26 @@ struct i915_vma {
> #define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf
> };
>
> -struct i915_page_table {
> +struct i915_page_dma {
> struct page *page;
> - dma_addr_t daddr;
> + union {
> + dma_addr_t daddr;
> +
> + /* For gen6/gen7 only. This is the offset in the GGTT
> + * where the page directory entries for PPGTT begin
> + */
> + uint32_t ggtt_offset;
> + };
> +};
> +
> +struct i915_page_table {
> + struct i915_page_dma base;
>
> unsigned long *used_ptes;
> };
>
> struct i915_page_directory {
> - struct page *page; /* NULL for GEN6-GEN7 */
> - union {
> - uint32_t pd_offset;
> - dma_addr_t daddr;
> - };
> + struct i915_page_dma base;
>
> unsigned long *used_pdes;
> struct i915_page_table *page_table[I915_PDES]; /* PDEs */
> @@ -472,8 +479,8 @@ static inline dma_addr_t
> i915_page_dir_dma_addr(const struct i915_hw_ppgtt *ppgtt, const unsigned n)
> {
> return test_bit(n, ppgtt->pdp.used_pdpes) ?
> - ppgtt->pdp.page_directory[n]->daddr :
> - ppgtt->scratch_pd->daddr;
> + ppgtt->pdp.page_directory[n]->base.daddr :
> + ppgtt->scratch_pd->base.daddr;
> }
>
> int i915_gem_gtt_init(struct drm_device *dev);
>
More information about the Intel-gfx
mailing list