On Mon, Nov 28, 2011 at 09:35:31PM +0100, Daniel Vetter wrote:
> This adds support to bind/unbind objects and wires it up. Objects are
> only put into the ppgtt when necessary, i.e. at execbuf time.
>
> Objects are still unconditionally put into the global gtt.
>
> v2: Kill the quick hack and explicitly pass cache_level to ppgtt_bind
> like for the global gtt function. Noticed by Chris Wilson.
>
> Signed-off-by: Daniel Vetter <daniel.vetter at ffwll.ch>
> ---
> diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> index c918124..9c81cda 100644
> --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
> @@ -513,6 +513,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
> struct drm_file *file,
> struct list_head *objects)
> {
> + drm_i915_private_t *dev_priv = ring->dev->dev_private;
> struct drm_i915_gem_object *obj;
> int ret, retry;
> bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4;
> @@ -621,6 +622,14 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
> }
>
> i915_gem_object_unpin(obj);
> +
> + /* ... and ensure ppgtt mapping exist if needed. */
> + if (dev_priv->mm.aliasing_ppgtt && !obj->has_aliasing_ppgtt_mapping) {
> + i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt,
> + obj, obj->cache_level);
> +
> + obj->has_aliasing_ppgtt_mapping = 1;
> + }
> }
>
> if (ret != -ENOSPC || retry > 1)
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index bd9b520..061ae12 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -34,22 +34,31 @@ static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
> unsigned first_entry,
> unsigned num_entries)
> {
> - int i, j;
> uint32_t *pt_vaddr;
> uint32_t scratch_pte;
> + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
> + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
> + unsigned last_pte, i;
>
> scratch_pte = GEN6_PTE_ADDR_ENCODE(ppgtt->scratch_page_dma_addr);
> scratch_pte |= GEN6_PTE_VALID | GEN6_PTE_CACHE_LLC;
>
> - for (i = 0; i < ppgtt->num_pd_entries; i++) {
> - pt_vaddr = kmap_atomic(ppgtt->pt_pages[i]);
> + while (num_entries) {
> + last_pte = first_pte + num_entries;
> + if (last_pte > I915_PPGTT_PT_ENTRIES)
> + last_pte = I915_PPGTT_PT_ENTRIES;
> +
> + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
>
> - for (j = 0; j < I915_PPGTT_PT_ENTRIES; j++)
> - pt_vaddr[j] = scratch_pte;
> + for (i = first_pte; i < last_pte; i++)
> + pt_vaddr[i] = scratch_pte;
>
> kunmap_atomic(pt_vaddr);
> - }
>
> + num_entries -= last_pte - first_pte;
> + first_pte = 0;
> + act_pd++;
> + }
> }
>
> int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
> @@ -162,6 +171,131 @@ void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
> kfree(ppgtt);
> }
>
> +static void i915_ppgtt_insert_sg_entries(struct i915_hw_ppgtt *ppgtt,
> + struct scatterlist *sg_list,
> + unsigned sg_len,
> + unsigned first_entry,
> + uint32_t pte_flags)
> +{
> + uint32_t *pt_vaddr, pte;
> + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
> + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
> + unsigned i, j, m, segment_len;
> + dma_addr_t page_addr;
> + struct scatterlist *sg;
> +
> + /* init sg walking */
> + sg = sg_list;
> + i = 0;
> + segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
> + m = 0;
> +
> + while (i < sg_len) {
> + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
> +
> + for (j = first_pte; j < I915_PPGTT_PT_ENTRIES; j++) {
> + page_addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
> + pte = GEN6_PTE_ADDR_ENCODE(page_addr);
> + pt_vaddr[j] = pte | pte_flags;
> +
> + /* grab the next page */
> + m++;
> + if (m == segment_len) {
> + sg = sg_next(sg);
> + i++;
> + if (i == sg_len)
> + break;
> +
> + segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
> + m = 0;
> + }
> + }
> +
> + kunmap_atomic(pt_vaddr);
> +
> + first_pte = 0;
> + act_pd++;
> + }
> +}
> +
> +static void i915_ppgtt_insert_pages(struct i915_hw_ppgtt *ppgtt,
> + unsigned first_entry, unsigned num_entries,
> + struct page **pages, uint32_t pte_flags)
> +{
> + uint32_t *pt_vaddr, pte;
> + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
> + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
> + unsigned last_pte, i;
> + dma_addr_t page_addr;
> +
> + while (num_entries) {
> + last_pte = first_pte + num_entries;
> + last_pte = min_t(unsigned, last_pte, I915_PPGTT_PT_ENTRIES);
> +
> + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
> +
> + for (i = first_pte; i < last_pte; i++) {
> + page_addr = page_to_phys(*pages);
> + pte = GEN6_PTE_ADDR_ENCODE(page_addr);
> + pt_vaddr[i] = pte | pte_flags;
> +
> + pages++;
> + }
> +
> + kunmap_atomic(pt_vaddr);
> +
> + num_entries -= last_pte - first_pte;
> + first_pte = 0;
> + act_pd++;
> + }
> +}
Same comment as 3/11 on these... don't we need a clflush?
