Support inserting 1G gtt pages into the 48b PPGTT.
v2: sanity check sg->length against page_size
v3: don't recalculate rem on each loop
whitespace breakup
Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 78 +++++++++++++++++++++++++++++++++++--
drivers/gpu/drm/i915/i915_gem_gtt.h | 2 +
2 files changed, 76 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 43e076083ef8..c750770e75a1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -950,6 +950,71 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
cache_level);
}
+static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
+ struct i915_page_directory_pointer **pdps,
+ struct sgt_dma *iter,
+ enum i915_cache_level cache_level)
+{
+ const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+ u64 start = vma->node.start;
+ dma_addr_t rem = iter->sg->length;
+
+ do {
+ struct gen8_insert_pte idx = gen8_insert_pte(start);
+ struct i915_page_directory_pointer *pdp = pdps[idx.pml4e];
+ struct i915_page_directory *pd = pdp->page_directory[idx.pdpe];
+ unsigned int page_size;
+ gen8_pte_t encode = pte_encode;
+ gen8_pte_t *vaddr;
+ u16 index, max;
+
+ if (unlikely(vma->page_sizes.sg & I915_GTT_PAGE_SIZE_1G) &&
+ IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_1G) &&
+ rem >= I915_GTT_PAGE_SIZE_1G && !(idx.pte | idx.pde)) {
+ index = idx.pdpe;
+ max = GEN8_PML4ES_PER_PML4;
+ page_size = I915_GTT_PAGE_SIZE_1G;
+
+ encode |= GEN8_PDPE_PS_1G;
+
+ vaddr = kmap_atomic_px(pdp);
+ } else {
+ struct i915_page_table *pt = pd->page_table[idx.pde];
+
+ index = idx.pte;
+ max = GEN8_PTES;
+ page_size = I915_GTT_PAGE_SIZE;
+
+ vaddr = kmap_atomic_px(pt);
+ }
+
+ do {
+ GEM_BUG_ON(iter->sg->length < page_size);
+ vaddr[index++] = encode | iter->dma;
+
+ start += page_size;
+ iter->dma += page_size;
+ rem -= page_size;
+ if (iter->dma >= iter->max) {
+ iter->sg = __sg_next(iter->sg);
+ if (!iter->sg)
+ break;
+
+ rem = iter->sg->length;
+ iter->dma = sg_dma_address(iter->sg);
+ iter->max = iter->dma + rem;
+
+ if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
+ break;
+ }
+
+ } while (rem >= page_size && index < max);
+
+ kunmap_atomic(vaddr);
+
+ } while (iter->sg);
+}
+
static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
struct i915_vma *vma,
enum i915_cache_level cache_level,
@@ -962,11 +1027,16 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
.max = iter.dma + iter.sg->length,
};
struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
- struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
- while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], &iter,
- &idx, cache_level))
- GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
+ if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+ gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level);
+ } else {
+ struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
+
+ while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++],
+ &iter, &idx, cache_level))
+ GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
+ }
}
static void gen8_free_page_tables(struct i915_address_space *vm,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 57738a61ea6e..e46f05f0cfd9 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -149,6 +149,8 @@ typedef u64 gen8_ppgtt_pml4e_t;
#define GEN8_PPAT_ELLC_OVERRIDE (0<<2)
#define GEN8_PPAT(i, x) ((u64)(x) << ((i) * 8))
+#define GEN8_PDPE_PS_1G BIT(7)
+
struct sg_table;
struct intel_rotation_info {
--
2.13.4
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
