UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/i915: Require the vm mutex for i915_vma_bind() 

Protect updates of struct i915_vma flags and async binding / unbinding
with the vm::mutex. This means that i915_vma_bind() needs to assert
vm::mutex held. In order to make that possible drop the caching of
kmap_atomic() maps around i915_vma_bind().

An alternative would be to use kmap_local() but since we block cpu
unplugging during sleeps inside kmap_local() sections this may have
unwanted side-effects. Particularly since we might wait for gpu while
holding the vm mutex.

This change may theoretically increase execbuf cpu-usage on snb, but
at least on non-highmem systems that increase should be very small.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211221200050.436316-5-thomas.hellstrom@linux.intel.com
This commit is contained in:
Thomas Hellström 2021-12-21 21:00:50 +01:00
parent 63cf4cad73
commit c2ea703dca
2 changed files with 50 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
View File

@ -1098,6 +1098,47 @@ static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache)
return &i915->ggtt;
}
static void reloc_cache_unmap(struct reloc_cache *cache)
{
void *vaddr;
if (!cache->vaddr)
return;
vaddr = unmask_page(cache->vaddr);
if (cache->vaddr & KMAP)
kunmap_atomic(vaddr);
else
io_mapping_unmap_atomic((void __iomem *)vaddr);
}
static void reloc_cache_remap(struct reloc_cache *cache,
struct drm_i915_gem_object *obj)
{
void *vaddr;
if (!cache->vaddr)
return;
if (cache->vaddr & KMAP) {
struct page *page = i915_gem_object_get_page(obj, cache->page);
vaddr = kmap_atomic(page);
cache->vaddr = unmask_flags(cache->vaddr) |
(unsigned long)vaddr;
} else {
struct i915_ggtt *ggtt = cache_to_ggtt(cache);
unsigned long offset;
offset = cache->node.start;
if (!drm_mm_node_allocated(&cache->node))
offset += cache->page << PAGE_SHIFT;
cache->vaddr = (unsigned long)
io_mapping_map_atomic_wc(&ggtt->iomap, offset);
}
}
static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb)
{
void *vaddr;
@ -1362,10 +1403,17 @@ eb_relocate_entry(struct i915_execbuffer *eb,
* batchbuffers.
*/
if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
GRAPHICS_VER(eb->i915) == 6) {
GRAPHICS_VER(eb->i915) == 6 &&
!i915_vma_is_bound(target->vma, I915_VMA_GLOBAL_BIND)) {
struct i915_vma *vma = target->vma;
reloc_cache_unmap(&eb->reloc_cache);
mutex_lock(&vma->vm->mutex);
err = i915_vma_bind(target->vma,
target->vma->obj->cache_level,
PIN_GLOBAL, NULL);
mutex_unlock(&vma->vm->mutex);
reloc_cache_remap(&eb->reloc_cache, ev->vma->obj);
if (err)
return err;
}

1
drivers/gpu/drm/i915/i915_vma.c
View File

@ -393,6 +393,7 @@ int i915_vma_bind(struct i915_vma *vma,
u32 bind_flags;
u32 vma_flags;
lockdep_assert_held(&vma->vm->mutex);
GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
GEM_BUG_ON(vma->size > vma->node.size);