AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-02 10:36:45 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity

drm/i915: Track GEN6 page table usage

Browse Source 
Instead of implementing the full tracking + dynamic allocation, this
patch does a bit less than half of the work, by tracking and warning on
unexpected conditions. The tracking itself follows which PTEs within a
page table are currently being used for objects. The next patch will
modify this to actually allocate the page tables only when necessary.

With the current patch there isn't much in the way of making a gen
agnostic range allocation function. However, in the next patch we'll add
more specificity which makes having separate functions a bit easier to
manage.

One important change introduced here is that DMA mappings are
created/destroyed at the same page directories/tables are
allocated/deallocated.

Notice that aliasing PPGTT is not managed here. The patch which actually
begins dynamic allocation/teardown explains the reasoning for this.

v2: s/pdp.page_directory/pdp.page_directories
Make a scratch page allocation helper

v3: Rebase and expand commit message.

v4: Allocate required pagetables only when it is needed, _bind_to_vm
instead of bind_vma (Daniel).

v5: Rebased to remove the unnecessary noise in the diff, also:
 - PDE mask is GEN agnostic, renamed GEN6_PDE_MASK to I915_PDE_MASK.
 - Removed unnecessary checks in gen6_alloc_va_range.
 - Changed map/unmap_px_single macros to use dma functions directly and
   be part of a static inline function instead.
 - Moved drm_device plumbing through page tables operation to its own
   patch.
 - Moved allocate/teardown_va_range calls until they are fully
   implemented (in subsequent patch).
 - Merged pt and scratch_pt unmap_and_free path.
 - Moved scratch page allocator helper to the patch that will use it.

v6: Reduce complexity by not tearing down pagetables dynamically, the
same can be achieved while freeing empty vms. (Daniel)

v7: s/i915_dma_map_px_single/i915_dma_map_single
s/gen6_write_pdes/gen6_write_pde
Prevent a NULL case when only GGTT is available. (Mika)

v8: Rebased after s/page_tables/page_table/.

v9: Reworked i915_pte_index and i915_pte_count.
Also exercise bitmap allocation here (gen6_alloc_va_range) and fix
incorrect write_page_range in i915_gem_restore_gtt_mappings (Mika).

Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v3+)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This commit is contained in:
Ben Widawsky 2015-03-16 16:00:56 +00:00 committed by Daniel Vetter
parent 317b4e9036
commit 678d96fbb3
3 changed files with 219 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
drivers/gpu/drm/i915/i915_gem.c
View File

@ -3510,6 +3510,15 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
if (ret)
goto err_remove_node;
/* allocate before insert / bind */
if (vma->vm->allocate_va_range) {
ret = vma->vm->allocate_va_range(vma->vm,
vma->node.start,
vma->node.size);
if (ret)
goto err_remove_node;
}
trace_i915_vma_bind(vma, flags);
ret = i915_vma_bind(vma, obj->cache_level,
flags & PIN_GLOBAL ? GLOBAL_BIND : 0);

199
drivers/gpu/drm/i915/i915_gem_gtt.c
View File

@ -279,29 +279,88 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
return pte;
}
static void unmap_and_free_pt(struct i915_page_table_entry *pt, struct drm_device *dev)
#define i915_dma_unmap_single(px, dev) \
__i915_dma_unmap_single((px)->daddr, dev)
static inline void __i915_dma_unmap_single(dma_addr_t daddr,
struct drm_device *dev)
{
struct device *device = &dev->pdev->dev;
dma_unmap_page(device, daddr, 4096, PCI_DMA_BIDIRECTIONAL);
}
/**
* i915_dma_map_single() - Create a dma mapping for a page table/dir/etc.
* @px: Page table/dir/etc 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. If we keep the structs
* symmetric here, the simple macro covers us for every page table type.
*
* Return: 0 if success.
*/
#define i915_dma_map_single(px, dev) \
i915_dma_map_page_single((px)->page, (dev), &(px)->daddr)
static inline int i915_dma_map_page_single(struct page *page,
struct drm_device *dev,
dma_addr_t *daddr)
{
struct device *device = &dev->pdev->dev;
*daddr = dma_map_page(device, page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
return dma_mapping_error(device, *daddr);
}
static void unmap_and_free_pt(struct i915_page_table_entry *pt,
struct drm_device *dev)
{
if (WARN_ON(!pt->page))
return;
i915_dma_unmap_single(pt, dev);
__free_page(pt->page);
kfree(pt->used_ptes);
kfree(pt);
}
static struct i915_page_table_entry *alloc_pt_single(struct drm_device *dev)
{
struct i915_page_table_entry *pt;
const size_t count = INTEL_INFO(dev)->gen >= 8 ?
GEN8_PTES : GEN6_PTES;
int ret = -ENOMEM;
pt = kzalloc(sizeof(*pt), GFP_KERNEL);
if (!pt)
return ERR_PTR(-ENOMEM);
pt->used_ptes = kcalloc(BITS_TO_LONGS(count), sizeof(*pt->used_ptes),
GFP_KERNEL);
if (!pt->used_ptes)
goto fail_bitmap;
pt->page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!pt->page) {
kfree(pt);
return ERR_PTR(-ENOMEM);
}
if (!pt->page)
goto fail_page;
ret = i915_dma_map_single(pt, dev);
if (ret)
goto fail_dma;
return pt;
fail_dma:
__free_page(pt->page);
fail_page:
kfree(pt->used_ptes);
fail_bitmap:
kfree(pt);
return ERR_PTR(ret);
}
/**
@ -848,26 +907,36 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
}
}
static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
/* Write pde (index) from the page directory @pd to the page table @pt */
static void gen6_write_pde(struct i915_page_directory_entry *pd,
const int pde, struct i915_page_table_entry *pt)
{
struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
gen6_pte_t __iomem *pd_addr;
uint32_t pd_entry;
int i;
/* Caller needs to make sure the write completes if necessary */
struct i915_hw_ppgtt *ppgtt =
container_of(pd, struct i915_hw_ppgtt, pd);
u32 pd_entry;
WARN_ON(ppgtt->pd.pd_offset & 0x3f);
pd_addr = (gen6_pte_t __iomem*)dev_priv->gtt.gsm +
ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
for (i = 0; i < ppgtt->num_pd_entries; i++) {
dma_addr_t pt_addr;
pd_entry = GEN6_PDE_ADDR_ENCODE(pt->daddr);
pd_entry |= GEN6_PDE_VALID;
pt_addr = ppgtt->pd.page_table[i]->daddr;
pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
pd_entry |= GEN6_PDE_VALID;
writel(pd_entry, ppgtt->pd_addr + pde);
}
writel(pd_entry, pd_addr + i);
}
readl(pd_addr);
/* Write all the page tables found in the ppgtt structure to incrementing page
* directories. */
static void gen6_write_page_range(struct drm_i915_private *dev_priv,
struct i915_page_directory_entry *pd,
uint32_t start, uint32_t length)
{
struct i915_page_table_entry *pt;
uint32_t pde, temp;
gen6_for_each_pde(pt, pd, start, length, temp, pde)
gen6_write_pde(pd, pde, pt);
/* Make sure write is complete before other code can use this page
* table. Also require for WC mapped PTEs */
readl(dev_priv->gtt.gsm);
}
static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
@ -1093,6 +1162,28 @@ static void gen6_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
4096, PCI_DMA_BIDIRECTIONAL);
}
static int gen6_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_table_entry *pt;
uint32_t pde, temp;
gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
DECLARE_BITMAP(tmp_bitmap, GEN6_PTES);
bitmap_zero(tmp_bitmap, GEN6_PTES);
bitmap_set(tmp_bitmap, gen6_pte_index(start),
gen6_pte_count(start, length));
bitmap_or(pt->used_ptes, pt->used_ptes, tmp_bitmap,
GEN6_PTES);
}
return 0;
}
static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
{
int i;
@ -1139,20 +1230,24 @@ static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
0, dev_priv->gtt.base.total,
0);
if (ret)
return ret;
goto err_out;
retried = true;
goto alloc;
}
if (ret)
return ret;
goto err_out;
if (ppgtt->node.start < dev_priv->gtt.mappable_end)
DRM_DEBUG("Forced to use aperture for PDEs\n");
ppgtt->num_pd_entries = I915_PDES;
return 0;
err_out:
return ret;
}
static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
@ -1174,30 +1269,6 @@ 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_table[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_unmap_pages(ppgtt);
return -EIO;
}
ppgtt->pd.page_table[i]->daddr = pt_addr;
}
return 0;
}
static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
{
struct drm_device *dev = ppgtt->base.dev;
@ -1221,12 +1292,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
if (ret)
return ret;
ret = gen6_ppgtt_setup_page_tables(ppgtt);
if (ret) {
gen6_ppgtt_free(ppgtt);
return ret;
}
ppgtt->base.allocate_va_range = gen6_alloc_va_range;
ppgtt->base.clear_range = gen6_ppgtt_clear_range;
ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
ppgtt->base.cleanup = gen6_ppgtt_cleanup;
@ -1237,13 +1303,17 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
ppgtt->pd.pd_offset =
ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
ppgtt->pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
gen6_write_page_range(dev_priv, &ppgtt->pd, 0, ppgtt->base.total);
DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
ppgtt->node.size >> 20,
ppgtt->node.start / PAGE_SIZE);
gen6_write_pdes(ppgtt);
DRM_DEBUG("Adding PPGTT at offset %x\n",
ppgtt->pd.pd_offset << 10);
@ -1514,15 +1584,20 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
return;
}
list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
/* TODO: Perhaps it shouldn't be gen6 specific */
if (i915_is_ggtt(vm)) {
if (dev_priv->mm.aliasing_ppgtt)
gen6_write_pdes(dev_priv->mm.aliasing_ppgtt);
continue;
}
if (USES_PPGTT(dev)) {
list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
/* TODO: Perhaps it shouldn't be gen6 specific */
gen6_write_pdes(container_of(vm, struct i915_hw_ppgtt, base));
struct i915_hw_ppgtt *ppgtt =
container_of(vm, struct i915_hw_ppgtt,
base);
if (i915_is_ggtt(vm))
ppgtt = dev_priv->mm.aliasing_ppgtt;
gen6_write_page_range(dev_priv, &ppgtt->pd,
0, ppgtt->base.total);
}
}
i915_ggtt_flush(dev_priv);

73
drivers/gpu/drm/i915/i915_gem_gtt.h
View File

@ -55,10 +55,12 @@ typedef uint64_t gen8_pde_t;
#define I915_PTE_MASK(pte_len) (I915_PTES(pte_len) - 1)
#define I915_PDES 512
#define I915_PDE_MASK (I915_PDES - 1)
#define NUM_PTE(pde_shift) (1 << (pde_shift - PAGE_SHIFT))
#define GEN6_PTES I915_PTES(sizeof(gen6_pte_t))
#define GEN6_PD_SIZE (I915_PDES * PAGE_SIZE)
#define GEN6_PD_ALIGN (PAGE_SIZE * 16)
#define GEN6_PDE_SHIFT 22
#define GEN6_PDE_VALID (1 << 0)
#define GEN7_PTE_CACHE_L3_LLC (3 << 1)
@ -194,6 +196,8 @@ struct i915_vma {
struct i915_page_table_entry {
struct page *page;
dma_addr_t daddr;
unsigned long *used_ptes;
};
struct i915_page_directory_entry {
@ -250,6 +254,9 @@ struct i915_address_space {
gen6_pte_t (*pte_encode)(dma_addr_t addr,
enum i915_cache_level level,
bool valid, u32 flags); /* Create a valid PTE */
int (*allocate_va_range)(struct i915_address_space *vm,
uint64_t start,
uint64_t length);
void (*clear_range)(struct i915_address_space *vm,
uint64_t start,
uint64_t length,
@ -302,12 +309,78 @@ struct i915_hw_ppgtt {
struct drm_i915_file_private *file_priv;
gen6_pte_t __iomem *pd_addr;
int (*enable)(struct i915_hw_ppgtt *ppgtt);
int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
struct intel_engine_cs *ring);
void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
};
/* For each pde iterates over every pde between from start until start + length.
* If start, and start+length are not perfectly divisible, the macro will round
* down, and up as needed. The macro modifies pde, start, and length. Dev is
* only used to differentiate shift values. Temp is temp. On gen6/7, start = 0,
* and length = 2G effectively iterates over every PDE in the system.
*
* XXX: temp is not actually needed, but it saves doing the ALIGN operation.
*/
#define gen6_for_each_pde(pt, pd, start, length, temp, iter) \
for (iter = gen6_pde_index(start), pt = (pd)->page_table[iter]; \
length > 0 && iter < I915_PDES; \
pt = (pd)->page_table[++iter], \
temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \
temp = min_t(unsigned, temp, length), \
start += temp, length -= temp)
static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift)
{
const uint32_t mask = NUM_PTE(pde_shift) - 1;
return (address >> PAGE_SHIFT) & mask;
}
/* Helper to counts the number of PTEs within the given length. This count
* does not cross a page table boundary, so the max value would be
* GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
*/
static inline uint32_t i915_pte_count(uint64_t addr, size_t length,
uint32_t pde_shift)
{
const uint64_t mask = ~((1 << pde_shift) - 1);
uint64_t end;
WARN_ON(length == 0);
WARN_ON(offset_in_page(addr|length));
end = addr + length;
if ((addr & mask) != (end & mask))
return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
}
static inline uint32_t i915_pde_index(uint64_t addr, uint32_t shift)
{
return (addr >> shift) & I915_PDE_MASK;
}
static inline uint32_t gen6_pte_index(uint32_t addr)
{
return i915_pte_index(addr, GEN6_PDE_SHIFT);
}
static inline size_t gen6_pte_count(uint32_t addr, uint32_t length)
{
return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
}
static inline uint32_t gen6_pde_index(uint32_t addr)
{
return i915_pde_index(addr, GEN6_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);