@@ -1479,6 +1479,65 @@ static int igt_ppgtt_sanity_check(void *arg)
return err;
}
+static int igt_ppgtt_compact(void *arg)
+{
+ struct drm_i915_private *i915 = arg;
+ struct drm_i915_gem_object *obj;
+ int err;
+
+ /*
+ * Simple test to catch issues with compact 64K pages -- since the pt is
+ * compacted to 256B that gives us 32 entries per pt, however since the
+ * backing page for the pt is 4K, any extra entries we might incorrectly
+ * write out should be ignored by the HW. If ever hit such a case this
+ * test should catch it since some of our writes would land in scratch.
+ */
+
+ if (!HAS_64K_PAGES(i915)) {
+ pr_info("device lacks compact 64K page support, skipping\n");
+ return 0;
+ }
+
+ if (!HAS_LMEM(i915)) {
+ pr_info("device lacks LMEM support, skipping\n");
+ return 0;
+ }
+
+ /* We want the range to cover multiple page-table boundaries. */
+ obj = i915_gem_object_create_lmem(i915, SZ_4M, 0);
+ if (IS_ERR(obj))
+ return PTR_ERR(obj);
+
+ err = i915_gem_object_pin_pages_unlocked(obj);
+ if (err)
+ goto out_put;
+
+ if (obj->mm.page_sizes.phys < I915_GTT_PAGE_SIZE_64K) {
+ pr_info("LMEM compact unable to allocate huge-page(s)\n");
+ goto out_unpin;
+ }
+
+ /*
+ * Disable 2M GTT pages by forcing the page-size to 64K for the GTT
+ * insertion.
+ */
+ obj->mm.page_sizes.sg = I915_GTT_PAGE_SIZE_64K;
+
+ err = igt_write_huge(i915, obj);
+ if (err)
+ pr_err("LMEM compact write-huge failed\n");
+
+out_unpin:
+ i915_gem_object_unpin_pages(obj);
+out_put:
+ i915_gem_object_put(obj);
+
+ if (err == -ENOMEM)
+ err = 0;
+
+ return err;
+}
+
static int igt_tmpfs_fallback(void *arg)
{
struct drm_i915_private *i915 = arg;
@@ -1736,6 +1795,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
SUBTEST(igt_tmpfs_fallback),
SUBTEST(igt_ppgtt_smoke_huge),
SUBTEST(igt_ppgtt_sanity_check),
+ SUBTEST(igt_ppgtt_compact),
};
if (!HAS_PPGTT(i915)) {
@@ -233,6 +233,8 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
start, end, lvl);
} else {
unsigned int count;
+ unsigned int pte = gen8_pd_index(start, 0);
+ unsigned int num_ptes;
u64 *vaddr;
count = gen8_pt_count(start, end);
@@ -242,10 +244,18 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
atomic_read(&pt->used));
GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
+ num_ptes = count;
+ if (pt->is_compact) {
+ GEM_BUG_ON(num_ptes % 16);
+ GEM_BUG_ON(pte % 16);
+ num_ptes /= 16;
+ pte /= 16;
+ }
+
vaddr = px_vaddr(pt);
- memset64(vaddr + gen8_pd_index(start, 0),
+ memset64(vaddr + pte,
vm->scratch[0]->encode,
- count);
+ num_ptes);
atomic_sub(count, &pt->used);
start += count;
@@ -453,6 +463,95 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
return idx;
}
+static void
+xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
+ struct i915_vma_resource *vma_res,
+ struct sgt_dma *iter,
+ enum i915_cache_level cache_level,
+ u32 flags)
+{
+ const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags);
+ unsigned int rem = sg_dma_len(iter->sg);
+ u64 start = vma_res->start;
+
+ GEM_BUG_ON(!i915_vm_is_4lvl(vm));
+
+ do {
+ struct i915_page_directory * const pdp =
+ gen8_pdp_for_page_address(vm, start);
+ struct i915_page_directory * const pd =
+ i915_pd_entry(pdp, __gen8_pte_index(start, 2));
+ struct i915_page_table *pt =
+ i915_pt_entry(pd, __gen8_pte_index(start, 1));
+ gen8_pte_t encode = pte_encode;
+ unsigned int page_size;
+ gen8_pte_t *vaddr;
+ u16 index, max;
+
+ max = I915_PDES;
+
+ if (vma_res->bi.page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
+ IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
+ rem >= I915_GTT_PAGE_SIZE_2M &&
+ !__gen8_pte_index(start, 0)) {
+ index = __gen8_pte_index(start, 1);
+ encode |= GEN8_PDE_PS_2M;
+ page_size = I915_GTT_PAGE_SIZE_2M;
+
+ vaddr = px_vaddr(pd);
+ } else {
+ if (encode & GEN12_PPGTT_PTE_LM) {
+ GEM_BUG_ON(__gen8_pte_index(start, 0) % 16);
+ GEM_BUG_ON(rem < I915_GTT_PAGE_SIZE_64K);
+ GEM_BUG_ON(!IS_ALIGNED(iter->dma,
+ I915_GTT_PAGE_SIZE_64K));
+
+ index = __gen8_pte_index(start, 0) / 16;
+ page_size = I915_GTT_PAGE_SIZE_64K;
+
+ max /= 16;
+
+ vaddr = px_vaddr(pd);
+ vaddr[__gen8_pte_index(start, 1)] |= GEN12_PDE_64K;
+
+ pt->is_compact = true;
+ } else {
+ GEM_BUG_ON(pt->is_compact);
+ index = __gen8_pte_index(start, 0);
+ page_size = I915_GTT_PAGE_SIZE;
+ }
+
+ vaddr = px_vaddr(pt);
+ }
+
+ do {
+ GEM_BUG_ON(rem < 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 = sg_dma_len(iter->sg);
+ if (!rem)
+ break;
+
+ 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);
+
+ vma_res->page_sizes_gtt |= page_size;
+ } while (iter->sg && sg_dma_len(iter->sg));
+}
+
static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
struct i915_vma_resource *vma_res,
struct sgt_dma *iter,
@@ -586,7 +685,10 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
struct sgt_dma iter = sgt_dma(vma_res);
if (vma_res->bi.page_sizes.sg > I915_GTT_PAGE_SIZE) {
- gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
+ if (HAS_64K_PAGES(vm->i915))
+ xehpsdv_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
+ else
+ gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
} else {
u64 idx = vma_res->start >> GEN8_PTE_SHIFT;
@@ -92,6 +92,8 @@ typedef u64 gen8_pte_t;
#define GEN12_GGTT_PTE_LM BIT_ULL(1)
+#define GEN12_PDE_64K BIT(6)
+
/*
* Cacheability Control is a 4-bit value. The low three bits are stored in bits
* 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
@@ -160,6 +162,7 @@ struct i915_page_table {
atomic_t used;
struct i915_page_table *stash;
};
+ bool is_compact;
};
struct i915_page_directory {
@@ -26,6 +26,7 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm)
return ERR_PTR(-ENOMEM);
}
+ pt->is_compact = false;
atomic_set(&pt->used, 0);
return pt;
}