[Intel-gfx] [PATCH v4 21/24] drm/i915/bdw: Split out mappings
Michel Thierry
michel.thierry at intel.com
Thu Jan 22 09:01:43 PST 2015
From: Ben Widawsky <benjamin.widawsky at intel.com>
When we do dynamic page table allocations for gen8, we'll need to have
more control over how and when we map page tables, similar to gen6.
In particular, DMA mappings for page directories/tables occur at allocation
time.
This patch adds the functionality and calls it at init, which should
have no functional change.
The PDPEs are still a special case for now. We'll need a function for
that in the future as well.
v2: Handle renamed unmap_and_free_page functions.
v3: Updated after teardown_va logic was removed.
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com> (v2+)
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 177 ++++++++++++++----------------------
1 file changed, 69 insertions(+), 108 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 66c2a9d..e662039 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -413,17 +413,20 @@ err_out:
return ret;
}
-static void unmap_and_free_pd(struct i915_page_directory_entry *pd)
+static void unmap_and_free_pd(struct i915_page_directory_entry *pd,
+ struct drm_device *dev)
{
if (pd->page) {
+ i915_dma_unmap_single(pd, dev);
__free_page(pd->page);
kfree(pd);
}
}
-static struct i915_page_directory_entry *alloc_pd_single(void)
+static struct i915_page_directory_entry *alloc_pd_single(struct drm_device *dev)
{
struct i915_page_directory_entry *pd;
+ int ret;
pd = kzalloc(sizeof(*pd), GFP_KERNEL);
if (!pd)
@@ -435,6 +438,13 @@ static struct i915_page_directory_entry *alloc_pd_single(void)
return ERR_PTR(-ENOMEM);
}
+ ret = i915_dma_map_px_single(pd, dev);
+ if (ret) {
+ __free_page(pd->page);
+ kfree(pd);
+ return ERR_PTR(ret);
+ }
+
return pd;
}
@@ -589,6 +599,36 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
}
}
+static void __gen8_do_map_pt(gen8_ppgtt_pde_t *pde,
+ struct i915_page_table_entry *pt,
+ struct drm_device *dev)
+{
+ gen8_ppgtt_pde_t entry =
+ gen8_pde_encode(dev, pt->daddr, I915_CACHE_LLC);
+ *pde = entry;
+}
+
+/* It's likely we'll map more than one pagetable at a time. This function will
+ * save us unnecessary kmap calls, but do no more functionally than multiple
+ * calls to map_pt. */
+static void gen8_map_pagetable_range(struct i915_page_directory_entry *pd,
+ uint64_t start,
+ uint64_t length,
+ struct drm_device *dev)
+{
+ gen8_ppgtt_pde_t *page_directory = kmap_atomic(pd->page);
+ struct i915_page_table_entry *pt;
+ uint64_t temp, pde;
+
+ gen8_for_each_pde(pt, pd, start, length, temp, pde)
+ __gen8_do_map_pt(page_directory + pde, pt, dev);
+
+ if (!HAS_LLC(dev))
+ drm_clflush_virt_range(page_directory, PAGE_SIZE);
+
+ kunmap_atomic(page_directory);
+}
+
static void gen8_free_page_tables(struct i915_page_directory_entry *pd, struct drm_device *dev)
{
int i;
@@ -644,7 +684,7 @@ static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
continue;
gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
- unmap_and_free_pd(ppgtt->pdp.page_directory[i]);
+ unmap_and_free_pd(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
}
}
@@ -684,7 +724,8 @@ unwind_out:
static int gen8_ppgtt_alloc_page_directories(struct i915_page_directory_pointer_entry *pdp,
uint64_t start,
- uint64_t length)
+ uint64_t length,
+ struct drm_device *dev)
{
struct i915_page_directory_entry *unused;
uint64_t temp;
@@ -695,7 +736,7 @@ 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();
+ pdp->page_directory[pdpe] = alloc_pd_single(dev);
if (IS_ERR(pdp->page_directory[pdpe]))
goto unwind_out;
}
@@ -704,21 +745,24 @@ static int gen8_ppgtt_alloc_page_directories(struct i915_page_directory_pointer_
unwind_out:
while (pdpe--)
- unmap_and_free_pd(pdp->page_directory[pdpe]);
+ unmap_and_free_pd(pdp->page_directory[pdpe], dev);
return -ENOMEM;
}
-static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
- uint64_t start,
- uint64_t length)
+static int gen8_alloc_va_range(struct i915_address_space *vm,
+ uint64_t start,
+ uint64_t length)
{
+ struct i915_hw_ppgtt *ppgtt =
+ container_of(vm, struct i915_hw_ppgtt, base);
struct i915_page_directory_entry *pd;
uint64_t temp;
uint32_t pdpe;
int ret;
- ret = gen8_ppgtt_alloc_page_directories(&ppgtt->pdp, start, length);
+ ret = gen8_ppgtt_alloc_page_directories(&ppgtt->pdp, start, length,
+ ppgtt->base.dev);
if (ret)
return ret;
@@ -731,134 +775,51 @@ static int gen8_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt,
return 0;
- /* TODO: Check this for all cases */
err_out:
gen8_ppgtt_free(ppgtt);
return ret;
}
-static int gen8_ppgtt_setup_page_directories(struct i915_hw_ppgtt *ppgtt,
- const int pd)
-{
- dma_addr_t pd_addr;
- int ret;
-
- pd_addr = pci_map_page(ppgtt->base.dev->pdev,
- ppgtt->pdp.page_directory[pd]->page, 0,
- PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-
- ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
- if (ret)
- return ret;
-
- ppgtt->pdp.page_directory[pd]->daddr = pd_addr;
-
- return 0;
-}
-
-static int gen8_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt,
- const int pd,
- const int pt)
-{
- dma_addr_t pt_addr;
- struct i915_page_directory_entry *pdir = ppgtt->pdp.page_directory[pd];
- struct i915_page_table_entry *ptab = pdir->page_tables[pt];
- struct page *p = ptab->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;
-
- ptab->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
* PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
* space.
*
- * FIXME: split allocation into smaller pieces. For now we only ever do this
- * once, but with full PPGTT, the multiple contiguous allocations will be bad.
- * TODO: Do something with the size parameter
*/
static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
{
- const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
- int i, j, ret;
-
- if (size % (1<<30))
- DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
+ struct i915_page_directory_entry *pd;
+ uint64_t temp, start = 0;
+ const uint64_t orig_length = size;
+ uint32_t pdpe;
+ int ret;
ppgtt->base.start = 0;
ppgtt->base.total = size;
+ ppgtt->base.clear_range = gen8_ppgtt_clear_range;
+ ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
+ ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+ ppgtt->switch_mm = gen8_mm_switch;
ppgtt->scratch_pd = alloc_pt_scratch(ppgtt->base.dev);
if (IS_ERR(ppgtt->scratch_pd))
return PTR_ERR(ppgtt->scratch_pd);
- /* 1. Do all our allocations for page directories and page tables. */
- ret = gen8_ppgtt_alloc(ppgtt, ppgtt->base.start, ppgtt->base.total);
+ ret = gen8_alloc_va_range(&ppgtt->base, start, size);
if (ret) {
unmap_and_free_pt(ppgtt->scratch_pd, ppgtt->base.dev);
return ret;
}
- /*
- * 2. Create DMA mappings for the page directories and page tables.
- */
- for (i = 0; i < max_pdp; i++) {
- ret = gen8_ppgtt_setup_page_directories(ppgtt, i);
- if (ret)
- goto bail;
+ start = 0;
+ size = orig_length;
- for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
- ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
- if (ret)
- goto bail;
- }
- }
-
- /*
- * 3. Map all the page directory entires to point to the page tables
- * we've allocated.
- *
- * For now, the PPGTT helper functions all require that the PDEs are
- * plugged in correctly. So we do that now/here. For aliasing PPGTT, we
- * will never need to touch the PDEs again.
- */
- for (i = 0; i < max_pdp; i++) {
- struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
- gen8_ppgtt_pde_t *pd_vaddr;
- pd_vaddr = kmap_atomic(ppgtt->pdp.page_directory[i]->page);
- for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
- struct i915_page_table_entry *pt = pd->page_tables[j];
- dma_addr_t addr = pt->daddr;
- pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr,
- I915_CACHE_LLC);
- }
- if (!HAS_LLC(ppgtt->base.dev))
- drm_clflush_virt_range(pd_vaddr, PAGE_SIZE);
- kunmap_atomic(pd_vaddr);
- }
-
- ppgtt->switch_mm = gen8_mm_switch;
- ppgtt->base.clear_range = gen8_ppgtt_clear_range;
- ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
- ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+ gen8_for_each_pdpe(pd, &ppgtt->pdp, start, size, temp, pdpe)
+ gen8_map_pagetable_range(pd, start, size, ppgtt->base.dev);
ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
return 0;
-
-bail:
- gen8_ppgtt_unmap_pages(ppgtt);
- gen8_ppgtt_free(ppgtt);
- return ret;
}
static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
@@ -1265,7 +1226,7 @@ static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
}
unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
- unmap_and_free_pd(&ppgtt->pd);
+ unmap_and_free_pd(&ppgtt->pd, ppgtt->base.dev);
}
static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
--
2.1.1
More information about the Intel-gfx
mailing list