Map and unmap are common operations across all generations for
pagetables. With a simple helper, we can get a nice net code reduction
as well as simplified complexity.
There is some room for optimization here, for instance with the multiple
page mapping, that can be done in one pci_map operation. In that case
however, the max value we'll ever see there is 512, and so I believe the
simpler code makes this a worthwhile trade-off. Also, the range mapping
functions are place holders to help transition the code. Eventually,
mapping will only occur during a page allocation which will always be a
discrete operation.
Signed-off-by: Ben Widawsky <b...@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 147 +++++++++++++++++++++---------------
1 file changed, 85 insertions(+), 62 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c
b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 35acccb..92e03dd 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -183,6 +183,76 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
return pte;
}
+#define dma_unmap_pt_single(pt, dev) do { \
+ pci_unmap_page((dev)->pdev, (pt)->daddr, 4096, PCI_DMA_BIDIRECTIONAL); \
+} while (0);
+
+
+static void dma_unmap_pt_range(struct i915_pagedir *pd,
+ unsigned pde, size_t n,
+ struct drm_device *dev)
+{
+ if (WARN_ON(pde + n > I915_PDES_PER_PD))
+ n = I915_PDES_PER_PD - pde;
+
+ n += pde;
+
+ for (; pde < n; pde++)
+ dma_unmap_pt_single(pd->page_tables[pde], dev);
+}
+
+/**
+ * dma_map_pt_single() - Create a dma mapping for a page table
+ * @pt: Page table to get a DMA map for
+ * @dev: drm device
+ *
+ * Page table allocations are unified across all gens. They always require a
+ * single 4k allocation, as well as a DMA mapping.
+ *
+ * Return: 0 if success.
+ */
+static int dma_map_pt_single(struct i915_pagetab *pt, struct drm_device *dev)
+{
+ struct page *page;
+ dma_addr_t pt_addr;
+ int ret;
+
+ page = pt->page;
+ pt_addr = pci_map_page(dev->pdev, page, 0, 4096,
+ PCI_DMA_BIDIRECTIONAL);
+
+ ret = pci_dma_mapping_error(dev->pdev, pt_addr);
+ if (ret)
+ return ret;
+
+ pt->daddr = pt_addr;
+
+ return 0;
+}
+
+static int dma_map_pt_range(struct i915_pagedir *pd,
+ unsigned pde, size_t n,
+ struct drm_device *dev)
+{
+ const int first = pde;
+
+ if (WARN_ON(pde + n > I915_PDES_PER_PD))
+ n = I915_PDES_PER_PD - pde;
+
+ n += pde;
+
+ for (; pde < n; pde++) {
+ int ret;
+ ret = dma_map_pt_single(pd->page_tables[pde], dev);
+ if (ret) {
+ dma_unmap_pt_range(pd, first, pde, dev);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
static void free_pt_single(struct i915_pagetab *pt)
{
if (WARN_ON(!pt->page))
@@ -191,7 +261,7 @@ static void free_pt_single(struct i915_pagetab *pt)
kfree(pt);
}
-static struct i915_pagetab *alloc_pt_single(void)
+static struct i915_pagetab *alloc_pt_single(struct drm_device *dev)
{
struct i915_pagetab *pt;
@@ -214,6 +284,7 @@ static struct i915_pagetab *alloc_pt_single(void)
* available to point to the allocated page tables.
* @pde: First page directory entry for which we are allocating.
* @count: Number of pages to allocate.
+ * @dev DRM device used for DMA mapping.
*
* Allocates multiple page table pages and sets the appropriate entries in the
* page table structure within the page directory. Function cleans up after
@@ -221,7 +292,8 @@ static struct i915_pagetab *alloc_pt_single(void)
*
* Return: 0 if allocation succeeded.
*/
-static int alloc_pt_range(struct i915_pagedir *pd, uint16_t pde, size_t count)
+static int alloc_pt_range(struct i915_pagedir *pd, uint16_t pde, size_t count,
+ struct drm_device *dev)
{
int i, ret;
@@ -231,7 +303,7 @@ static int alloc_pt_range(struct i915_pagedir *pd, uint16_t
pde, size_t count)
BUG_ON(pde + count > I915_PDES_PER_PD);
for (i = pde; i < pde + count; i++) {
- struct i915_pagetab *pt = alloc_pt_single();
+ struct i915_pagetab *pt = alloc_pt_single(dev);
if (IS_ERR(pt)) {
ret = PTR_ERR(pt);
goto err_out;
@@ -480,7 +552,7 @@ static int gen8_ppgtt_allocate_page_tables(struct
i915_hw_ppgtt *ppgtt)
for (i = 0; i < ppgtt->num_pd_pages; i++) {
ret = alloc_pt_range(ppgtt->pdp.pagedir[i],
- 0, I915_PDES_PER_PD);
+ 0, I915_PDES_PER_PD, ppgtt->base.dev);
if (ret)
goto unwind_out;
}
@@ -559,27 +631,6 @@ static int gen8_ppgtt_setup_page_directories(struct
i915_hw_ppgtt *ppgtt,
return 0;
}
-static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
- const int pdpe,
- const int pde)
-{
- dma_addr_t pt_addr;
- struct i915_pagedir *pd = ppgtt->pdp.pagedir[pdpe];
- struct i915_pagetab *pt = pd->page_tables[pde];
- struct page *p = pt->page;
- int ret;
-
- pt_addr = pci_map_page(ppgtt->base.dev->pdev,
- p, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
- ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pt_addr);
- if (ret)
- return ret;
-
- pt->daddr = pt_addr;
-
- return 0;
-}
-
/**
* GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
* with a net effect resembling a 2-level page table in normal x86 terms. Each
@@ -608,12 +659,15 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
uint64_t size)
* 2. Create DMA mappings for the page directories and page tables.
*/
for (i = 0; i < max_pdp; i++) {
+ struct i915_pagedir *pd;
ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
if (ret)
goto bail;
+ pd = ppgtt->pdp.pagedir[i];
+
for (j = 0; j < I915_PDES_PER_PD; j++) {
- ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
+ ret = dma_map_pt_single(pd->page_tables[j],
ppgtt->base.dev);
if (ret)
goto bail;
}
@@ -1029,16 +1083,6 @@ static void gen6_ppgtt_insert_entries(struct
i915_address_space *vm,
kunmap_atomic(pt_vaddr);
}
-static void gen6_ppgtt_dma_unmap_pages(struct i915_hw_ppgtt *ppgtt)
-{
- int i;
-
- for (i = 0; i < ppgtt->num_pd_entries; i++)
- pci_unmap_page(ppgtt->base.dev->pdev,
- ppgtt->pd.page_tables[i]->daddr,
- 4096, PCI_DMA_BIDIRECTIONAL);
-}
-
static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
{
int i;
@@ -1058,7 +1102,7 @@ static void gen6_ppgtt_cleanup(struct i915_address_space
*vm)
drm_mm_takedown(&ppgtt->base.mm);
drm_mm_remove_node(&ppgtt->node);
- gen6_ppgtt_dma_unmap_pages(ppgtt);
+ dma_unmap_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries, vm->dev);
gen6_ppgtt_free(ppgtt);
}
@@ -1111,7 +1155,8 @@ static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
if (ret)
return ret;
- ret = alloc_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries);
+ ret = alloc_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries,
+ ppgtt->base.dev);
if (ret) {
drm_mm_remove_node(&ppgtt->node);
return ret;
@@ -1120,29 +1165,6 @@ static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
return 0;
}
-static int gen6_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt)
-{
- struct drm_device *dev = ppgtt->base.dev;
- int i;
-
- for (i = 0; i < ppgtt->num_pd_entries; i++) {
- struct page *page;
- dma_addr_t pt_addr;
-
- page = ppgtt->pd.page_tables[i]->page;
- pt_addr = pci_map_page(dev->pdev, page, 0, 4096,
- PCI_DMA_BIDIRECTIONAL);
-
- if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
- gen6_ppgtt_dma_unmap_pages(ppgtt);
- return -EIO;
- }
-
- ppgtt->pd.page_tables[i]->daddr = pt_addr;
- }
-
- return 0;
-}
static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
@@ -1167,7 +1189,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
if (ret)
return ret;
- ret = gen6_ppgtt_setup_page_tables(ppgtt);
+ ret = dma_map_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries,
+ ppgtt->base.dev);
if (ret) {
gen6_ppgtt_free(ppgtt);
return ret;
--
1.9.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
