From: Ben Widawsky <benjamin.widawsky@xxxxxxxxx>
Like with gen6/7, we can enable bitmap tracking with all the
preallocations to make sure things actually don't blow up.
v2: Rebased to match changes from previous patches.
Signed-off-by: Ben Widawsky <ben@xxxxxxxxxxxx>
Signed-off-by: Michel Thierry <michel.thierry@xxxxxxxxx> (v2)
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 121 +++++++++++++++++++++++++-----------
drivers/gpu/drm/i915/i915_gem_gtt.h | 24 +++++++
2 files changed, 108 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3ce9f83..82b72a1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -424,8 +424,12 @@ static void unmap_and_free_pd(struct i915_page_directory_entry *pd,
struct drm_device *dev)
{
if (pd->page) {
+ WARN(!bitmap_empty(pd->used_pdes, GEN8_PDES_PER_PAGE),
+ "Free page directory with %d used pages\n",
+ bitmap_weight(pd->used_pdes, GEN8_PDES_PER_PAGE));
i915_dma_unmap_single(pd, dev);
__free_page(pd->page);
+ kfree(pd->used_pdes);
kfree(pd);
}
}
@@ -433,26 +437,35 @@ static void unmap_and_free_pd(struct i915_page_directory_entry *pd,
static struct i915_page_directory_entry *alloc_pd_single(struct drm_device *dev)
{
struct i915_page_directory_entry *pd;
- int ret;
+ int ret = -ENOMEM;
pd = kzalloc(sizeof(*pd), GFP_KERNEL);
if (!pd)
return ERR_PTR(-ENOMEM);
+ pd->used_pdes = kcalloc(BITS_TO_LONGS(GEN8_PDES_PER_PAGE),
+ sizeof(*pd->used_pdes), GFP_KERNEL);
+ if (!pd->used_pdes)
+ goto free_pd;
+
pd->page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!pd->page) {
- kfree(pd);
- return ERR_PTR(-ENOMEM);
- }
+ if (!pd->page)
+ goto free_bitmap;
ret = i915_dma_map_px_single(pd, dev);
- if (ret) {
- __free_page(pd->page);
- kfree(pd);
- return ERR_PTR(ret);
- }
+ if (ret)
+ goto free_page;
return pd;
+
+free_page:
+ __free_page(pd->page);
+free_bitmap:
+ kfree(pd->used_pdes);
+free_pd:
+ kfree(pd);
+
+ return ERR_PTR(ret);
}
/* Broadwell Page Directory Pointer Descriptors */
@@ -634,36 +647,47 @@ static void gen8_teardown_va_range(struct i915_address_space *vm,
gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
uint64_t pd_len = gen8_clamp_pd(start, length);
uint64_t pd_start = start;
- gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) {
- unmap_and_free_pt(pt, vm->dev);
- pd->page_tables[pde] = NULL;
- }
- unmap_and_free_pd(pd, vm->dev);
- ppgtt->pdp.page_directory[pdpe] = NULL;
- }
-}
-static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
-{
- struct pci_dev *hwdev = ppgtt->base.dev->pdev;
- int i, j;
-
- for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
- /* TODO: In the future we'll support sparse mappings, so this
- * will have to change. */
- if (!ppgtt->pdp.page_directory[i]->daddr)
+ /* Page directories might not be present since the macro rounds
+ * down, and up.
+ */
+ if (!pd) {
+ WARN(test_bit(pdpe, ppgtt->pdp.used_pdpes),
+ "PDPE %d is not allocated, but is reserved (%p)\n",
+ pdpe, vm);
continue;
+ } else {
+ WARN(!test_bit(pdpe, ppgtt->pdp.used_pdpes),
+ "PDPE %d not reserved, but is allocated (%p)",
+ pdpe, vm);
+ }
- pci_unmap_page(hwdev, ppgtt->pdp.page_directory[i]->daddr, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
+ gen8_for_each_pde(pt, pd, pd_start, pd_len, temp, pde) {
+ if (!pt) {
+ WARN(test_bit(pde, pd->used_pdes),
+ "PDE %d is not allocated, but is reserved (%p)\n",
+ pde, vm);
+ continue;
+ } else
+ WARN(!test_bit(pde, pd->used_pdes),
+ "PDE %d not reserved, but is allocated (%p)",
+ pde, vm);
+
+ bitmap_clear(pt->used_ptes,
+ gen8_pte_index(pd_start),
+ gen8_pte_count(pd_start, pd_len));
+
+ if (bitmap_empty(pt->used_ptes, GEN8_PTES_PER_PAGE)) {
+ unmap_and_free_pt(pt, vm->dev);
+ pd->page_tables[pde] = NULL;
+ WARN_ON(!test_and_clear_bit(pde, pd->used_pdes));
+ }
+ }
- for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
- struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
- struct i915_page_table_entry *pt = pd->page_tables[j];
- dma_addr_t addr = pt->daddr;
- if (addr)
- pci_unmap_page(hwdev, addr, PAGE_SIZE,
- PCI_DMA_BIDIRECTIONAL);
+ if (bitmap_empty(pd->used_pdes, GEN8_PDES_PER_PAGE)) {
+ unmap_and_free_pd(pd, vm->dev);
+ ppgtt->pdp.page_directory[pdpe] = NULL;
+ WARN_ON(!test_and_clear_bit(pdpe, ppgtt->pdp.used_pdpes));
}
}
}
@@ -679,7 +703,6 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt, base);
- gen8_ppgtt_unmap_pages(ppgtt);
gen8_ppgtt_free(ppgtt);
}
@@ -708,6 +731,7 @@ unwind_out:
return -ENOMEM;
}
+/* bitmap of new page_directories */
static int gen8_ppgtt_alloc_page_directories(struct i915_page_directory_pointer_entry *pdp,
uint64_t start,
uint64_t length,
@@ -723,6 +747,7 @@ static int gen8_ppgtt_alloc_page_directories(struct i915_page_directory_pointer_
gen8_for_each_pdpe(unused, pdp, start, length, temp, pdpe) {
BUG_ON(unused);
pdp->page_directory[pdpe] = alloc_pd_single(dev);
+
if (IS_ERR(pdp->page_directory[pdpe]))
goto unwind_out;
}
@@ -744,10 +769,12 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
container_of(vm, struct i915_hw_ppgtt, base);
struct i915_page_directory_entry *pd;
const uint64_t orig_start = start;
+ const uint64_t orig_length = length;
uint64_t temp;
uint32_t pdpe;
int ret;
+ /* Do the allocations first so we can easily bail out */
ret = gen8_ppgtt_alloc_page_directories(&ppgtt->pdp, start, length,
ppgtt->base.dev);
if (ret)
@@ -760,6 +787,26 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
goto err_out;
}
+ /* Now mark everything we've touched as used. This doesn't allow for
+ * robust error checking, but it makes the code a hell of a lot simpler.
+ */
+ start = orig_start;
+ length = orig_length;
+
+ gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
+ struct i915_page_table_entry *pt;
+ uint64_t pd_len = gen8_clamp_pd(start, length);
+ uint64_t pd_start = start;
+ uint32_t pde;
+ gen8_for_each_pde(pt, &ppgtt->pd, pd_start, pd_len, temp, pde) {
+ bitmap_set(pd->page_tables[pde]->used_ptes,
+ gen8_pte_index(start),
+ gen8_pte_count(start, length));
+ set_bit(pde, pd->used_pdes);
+ }
+ set_bit(pdpe, ppgtt->pdp.used_pdpes);
+ }
+
return 0;
err_out:
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 4a3371a..c755617 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -205,11 +205,13 @@ struct i915_page_directory_entry {
dma_addr_t daddr;
};
+ unsigned long *used_pdes;
struct i915_page_table_entry *page_tables[GEN6_PPGTT_PD_ENTRIES]; /* PDEs */
};
struct i915_page_directory_pointer_entry {
/* struct page *page; */
+ DECLARE_BITMAP(used_pdpes, GEN8_LEGACY_PDPES);
struct i915_page_directory_entry *page_directory[GEN8_LEGACY_PDPES];
};
@@ -447,6 +449,28 @@ static inline uint32_t gen8_pml4e_index(uint64_t address)
BUG(); /* For 64B */
}
+static inline size_t gen8_pte_count(uint64_t addr, uint64_t length)
+{
+ return i915_pte_count(addr, length, GEN8_PDE_SHIFT);
+}
+
+static inline size_t gen8_pde_count(uint64_t addr, uint64_t length)
+{
+ const uint32_t pdp_shift = GEN8_PDE_SHIFT + 9;
+ const uint64_t mask = ~((1 << pdp_shift) - 1);
+ uint64_t end;
+
+ BUG_ON(length == 0);
+ BUG_ON(offset_in_page(addr|length));
+
+ end = addr + length;
+
+ if ((addr & mask) != (end & mask))
+ return GEN8_PDES_PER_PAGE - i915_pde_index(addr, GEN8_PDE_SHIFT);
+
+ return i915_pde_index(end, GEN8_PDE_SHIFT) - i915_pde_index(addr, GEN8_PDE_SHIFT);
+}
+
int i915_gem_gtt_init(struct drm_device *dev);
void i915_gem_init_global_gtt(struct drm_device *dev);
void i915_global_gtt_cleanup(struct drm_device *dev);
--
2.1.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
