Commit f3a964b9 authored by Ben Widawsky's avatar Ben Widawsky Committed by Daniel Vetter

drm/i915/bdw: Reorganize PPGTT init

Create 3 clear stages in PPGTT init. This will help with upcoming
changes be more readable. The 3 stages are, allocation, dma mapping, and
writing the P[DT]Es

One nice benefit to the patches is that it makes 2 very clear error
points, allocation, and mapping, and avoids having to do any handling
after writing PTEs (something which was likely buggy before). This
simplified error handling I suspect will be helpful when we move to
deferred/dynamic page table allocation and mapping.

The patches also attempts to break up some of the steps into more
logical reviewable chunks, particularly when we free.

v2: Don't call cleanup on the error path since that takes down the
drm_mm and list entry, which aren't setup at this point.

v3: Fixes addressing Imre's comments from:
<1392821989.19792.13.camel@intelbox>

Don't do dynamic allocation for the page table DMA addresses. I can't
remember why I did it in the first place. This addresses one of Imre's
other issues.

Fix error path leak of page tables.

v4: Fix the fix of the error path leak. Original fix still leaked page
tables. (Imre)
Reviewed-by: default avatarImre Deak <imre.deak@intel.com>
Signed-off-by: default avatarBen Widawsky <ben@bwidawsk.net>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
parent b18b6bde
...@@ -332,6 +332,7 @@ static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt) ...@@ -332,6 +332,7 @@ static void gen8_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt) static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
{ {
struct pci_dev *hwdev = ppgtt->base.dev->pdev;
int i, j; int i, j;
for (i = 0; i < ppgtt->num_pd_pages; i++) { for (i = 0; i < ppgtt->num_pd_pages; i++) {
...@@ -340,18 +341,14 @@ static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt) ...@@ -340,18 +341,14 @@ static void gen8_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
if (!ppgtt->pd_dma_addr[i]) if (!ppgtt->pd_dma_addr[i])
continue; continue;
pci_unmap_page(ppgtt->base.dev->pdev, pci_unmap_page(hwdev, ppgtt->pd_dma_addr[i], PAGE_SIZE,
ppgtt->pd_dma_addr[i], PCI_DMA_BIDIRECTIONAL);
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
for (j = 0; j < GEN8_PDES_PER_PAGE; j++) { for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j]; dma_addr_t addr = ppgtt->gen8_pt_dma_addr[i][j];
if (addr) if (addr)
pci_unmap_page(ppgtt->base.dev->pdev, pci_unmap_page(hwdev, addr, PAGE_SIZE,
addr,
PAGE_SIZE,
PCI_DMA_BIDIRECTIONAL); PCI_DMA_BIDIRECTIONAL);
} }
} }
} }
...@@ -369,27 +366,27 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) ...@@ -369,27 +366,27 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
} }
/** /**
* GEN8 legacy ppgtt programming is accomplished through 4 PDP registers with a * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
* net effect resembling a 2-level page table in normal x86 terms. Each PDP * with a net effect resembling a 2-level page table in normal x86 terms. Each
* represents 1GB of memory * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
* 4 * 512 * 512 * 4096 = 4GB legacy 32b address space. * 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 * TODO: Do something with the size parameter
**/ */
static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
{ {
struct page *pt_pages; struct page *pt_pages;
int i, j, ret = -ENOMEM;
const int max_pdp = DIV_ROUND_UP(size, 1 << 30); const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp; const int num_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
struct pci_dev *hwdev = ppgtt->base.dev->pdev;
int i, j, ret;
if (size % (1<<30)) if (size % (1<<30))
DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size); DRM_INFO("Pages will be wasted unless GTT size (%llu) is divisible by 1GB\n", size);
/* FIXME: split allocation into smaller pieces. For now we only ever do /* 1. Do all our allocations for page directories and page tables */
* this once, but with full PPGTT, the multiple contiguous allocations
* will be bad.
*/
ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT)); ppgtt->pd_pages = alloc_pages(GFP_KERNEL, get_order(max_pdp << PAGE_SHIFT));
if (!ppgtt->pd_pages) if (!ppgtt->pd_pages)
return -ENOMEM; return -ENOMEM;
...@@ -404,52 +401,56 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ...@@ -404,52 +401,56 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT); ppgtt->num_pd_pages = 1 << get_order(max_pdp << PAGE_SHIFT);
ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT); ppgtt->num_pt_pages = 1 << get_order(num_pt_pages << PAGE_SHIFT);
ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE; ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
ppgtt->enable = gen8_ppgtt_enable;
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;
ppgtt->base.start = 0;
ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE;
BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS); BUG_ON(ppgtt->num_pd_pages > GEN8_LEGACY_PDPS);
for (i = 0; i < max_pdp; i++) {
ppgtt->gen8_pt_dma_addr[i] = kcalloc(GEN8_PDES_PER_PAGE,
sizeof(dma_addr_t),
GFP_KERNEL);
if (!ppgtt->gen8_pt_dma_addr[i]) {
ret = -ENOMEM;
goto bail;
}
}
/* /*
* - Create a mapping for the page directories. * 2. Create all the DMA mappings for the page directories and page
* - For each page directory: * tables
* allocate space for page table mappings.
* map each page table
*/ */
for (i = 0; i < max_pdp; i++) { for (i = 0; i < max_pdp; i++) {
dma_addr_t temp; dma_addr_t pd_addr, pt_addr;
temp = pci_map_page(ppgtt->base.dev->pdev,
&ppgtt->pd_pages[i], 0,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp))
goto err_out;
ppgtt->pd_dma_addr[i] = temp; /* Get the page directory mappings */
pd_addr = pci_map_page(hwdev, &ppgtt->pd_pages[i], 0,
PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
ret = pci_dma_mapping_error(ppgtt->base.dev->pdev, pd_addr);
if (ret)
goto bail;
ppgtt->gen8_pt_dma_addr[i] = kmalloc(sizeof(dma_addr_t) * GEN8_PDES_PER_PAGE, GFP_KERNEL); ppgtt->pd_dma_addr[i] = pd_addr;
if (!ppgtt->gen8_pt_dma_addr[i])
goto err_out;
/* And the page table mappings per page directory */
for (j = 0; j < GEN8_PDES_PER_PAGE; j++) { for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
struct page *p = &pt_pages[i * GEN8_PDES_PER_PAGE + j]; struct page *p = &pt_pages[i * GEN8_PDES_PER_PAGE + j];
temp = pci_map_page(ppgtt->base.dev->pdev,
p, 0, PAGE_SIZE,
PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(ppgtt->base.dev->pdev, temp)) pt_addr = pci_map_page(hwdev, p, 0, PAGE_SIZE,
goto err_out; PCI_DMA_BIDIRECTIONAL);
ret = pci_dma_mapping_error(hwdev, pt_addr);
if (ret)
goto bail;
ppgtt->gen8_pt_dma_addr[i][j] = temp; ppgtt->gen8_pt_dma_addr[i][j] = pt_addr;
} }
} }
/* For now, the PPGTT helper functions all require that the PDEs are /*
* 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 * plugged in correctly. So we do that now/here. For aliasing PPGTT, we
* will never need to touch the PDEs again */ * will never need to touch the PDEs again.
*/
for (i = 0; i < max_pdp; i++) { for (i = 0; i < max_pdp; i++) {
gen8_ppgtt_pde_t *pd_vaddr; gen8_ppgtt_pde_t *pd_vaddr;
pd_vaddr = kmap_atomic(&ppgtt->pd_pages[i]); pd_vaddr = kmap_atomic(&ppgtt->pd_pages[i]);
...@@ -461,6 +462,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ...@@ -461,6 +462,14 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
kunmap_atomic(pd_vaddr); kunmap_atomic(pd_vaddr);
} }
ppgtt->enable = gen8_ppgtt_enable;
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;
ppgtt->base.start = 0;
ppgtt->base.total = ppgtt->num_pt_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE;
ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.clear_range(&ppgtt->base, 0,
ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE, ppgtt->num_pd_entries * GEN8_PTES_PER_PAGE,
true); true);
...@@ -473,8 +482,9 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) ...@@ -473,8 +482,9 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
size % (1<<30)); size % (1<<30));
return 0; return 0;
err_out: bail:
ppgtt->base.cleanup(&ppgtt->base); gen8_ppgtt_unmap_pages(ppgtt);
gen8_ppgtt_free(ppgtt);
return ret; return ret;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment