Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 26 ++++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
2 files changed, 27 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 03c35097ef39..9b89ec10f333 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -937,6 +937,7 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
struct i915_page_table *pt = pd->page_table[idx.pde];
dma_addr_t rem = iter->max - iter->dma;
unsigned int page_size;
+ bool maybe_64K = false;
gen8_pte_t encode = pte_encode;
gen8_pte_t *vaddr;
u16 index, max;
@@ -962,9 +963,17 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
index = idx.pte;
max = GEN8_PTES;
page_size = I915_GTT_PAGE_SIZE;
+
+ if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K && !idx.pte)
+ maybe_64K = true;
}
do {
+ if (maybe_64K && (index % 16 == 0) &&
+ (!IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) ||
+ rem < I915_GTT_PAGE_SIZE_64K))
+ maybe_64K = false;
+
vaddr[index++] = encode | iter->dma;
start += page_size;
@@ -986,6 +995,23 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
kunmap_atomic(vaddr);
+
+ /* Is it safe to mark the 2M block as 64K? -- Either we have
+ * filled whole page-table with 64K entries, or filled part of
+ * it and have reached the end of the sg table and we have
+ * enough padding.
+ */
+ if (maybe_64K) {
+ if (index == max ||
+ (!iter->sg && IS_ALIGNED(vma->node.start +
+ vma->node.size,
+ I915_GTT_PAGE_SIZE_2M))) {
+ vaddr = kmap_atomic_px(pd);
+ vaddr[idx.pde] |= GEN8_PDE_IPS_64K;
+ kunmap_atomic(vaddr);
+ }
+ }
+
} while (iter->sg);
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index e9ec75b92f85..41df07e5e37a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -149,6 +149,7 @@ typedef u64 gen8_ppgtt_pml4e_t;
#define GEN8_PPAT_ELLC_OVERRIDE (0<<2)
#define GEN8_PPAT(i, x) ((u64)(x) << ((i) * 8))
+#define GEN8_PDE_IPS_64K BIT(11)
#define GEN8_PDE_PS_2M BIT(7)
#define GEN8_PDPE_PS_1G BIT(7)
--
2.9.4
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
