[Intel-gfx] [PATCH 03/28] drm/i915: Track unbound pages
Chris Wilson
chris at chris-wilson.co.uk
Tue Apr 24 16:47:32 CEST 2012
When dealing with a working set larger than the GATT, or even the
mappable aperture when touching through the GTT, we end up with evicting
objects only to rebind them at a new offset again later. Moving an
object into and out of the GTT requires clflushing the pages, thus
causing a double-clflush penalty for rebinding.
To avoid having to clflush on rebinding, we can track the pages as they
are evicted from the GTT and only relinquish those pages on memory
pressure.
As usual, if it were not for the handling of out-of-memory condition and
having to manually shrink our own bo caches, it would be a net reduction
of code. Alas.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_debugfs.c | 5 +
drivers/gpu/drm/i915/i915_drv.h | 9 +-
drivers/gpu/drm/i915/i915_gem.c | 444 ++++++++++++++++------------
drivers/gpu/drm/i915/i915_gem_evict.c | 13 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +-
drivers/gpu/drm/i915/i915_trace.h | 10 +-
6 files changed, 272 insertions(+), 218 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 120db46..de7c65e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -247,6 +247,11 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
seq_printf(m, " %u [%u] inactive objects, %zu [%zu] bytes\n",
count, mappable_count, size, mappable_size);
+ size = count = 0;
+ list_for_each_entry(obj, &dev_priv->mm.unbound_list, mm_list)
+ size += obj->base.size, ++count;
+ seq_printf(m, "%u unbound objects, %zu bytes\n", count, size);
+
size = count = mappable_size = mappable_count = 0;
list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
if (obj->fault_mappable) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 21127af..866b280 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -689,6 +689,13 @@ typedef struct drm_i915_private {
*/
struct list_head inactive_list;
+ /**
+ * List of objects which are not bound to the GTT (thus
+ * are idle and not used by the GPU) but still have
+ * (presumably uncached) pages still attached.
+ */
+ struct list_head unbound_list;
+
/** LRU list of objects with fence regs on them. */
struct list_head fence_list;
@@ -1356,7 +1363,7 @@ void i915_gem_init_global_gtt(struct drm_device *dev,
/* i915_gem_evict.c */
int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
unsigned alignment, bool mappable);
-int i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only);
+int i915_gem_evict_everything(struct drm_device *dev);
/* i915_gem_tiling.c */
void i915_gem_detect_bit_6_swizzle(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9bf11c8..761af95 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -55,6 +55,8 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
static int i915_gem_inactive_shrink(struct shrinker *shrinker,
struct shrink_control *sc);
+static long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
+static void i915_gem_shrink_all(struct drm_i915_private *dev_priv);
static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
@@ -413,9 +415,11 @@ i915_gem_shmem_pread(struct drm_device *dev,
* anyway again before the next pread happens. */
if (obj->cache_level == I915_CACHE_NONE)
needs_clflush = 1;
- ret = i915_gem_object_set_to_gtt_domain(obj, false);
- if (ret)
- return ret;
+ if (obj->gtt_space) {
+ ret = i915_gem_object_set_to_gtt_domain(obj, false);
+ if (ret)
+ return ret;
+ }
}
offset = args->offset;
@@ -733,9 +737,11 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
* right away and we therefore have to clflush anyway. */
if (obj->cache_level == I915_CACHE_NONE)
needs_clflush_after = 1;
- ret = i915_gem_object_set_to_gtt_domain(obj, true);
- if (ret)
- return ret;
+ if (obj->gtt_space) {
+ ret = i915_gem_object_set_to_gtt_domain(obj, true);
+ if (ret)
+ return ret;
+ }
}
/* Same trick applies for invalidate partially written cachelines before
* writing. */
@@ -1318,59 +1324,56 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
}
-
-static int
-i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj,
- gfp_t gfpmask)
+/* Immediately discard the backing storage */
+static void
+i915_gem_object_truncate(struct drm_i915_gem_object *obj)
{
- int page_count, i;
- struct address_space *mapping;
struct inode *inode;
- struct page *page;
- /* Get the list of pages out of our struct file. They'll be pinned
- * at this point until we release them.
+ /* Our goal here is to return as much of the memory as
+ * is possible back to the system as we are called from OOM.
+ * To do this we must instruct the shmfs to drop all of its
+ * backing pages, *now*.
*/
- page_count = obj->base.size / PAGE_SIZE;
- BUG_ON(obj->pages != NULL);
- obj->pages = drm_malloc_ab(page_count, sizeof(struct page *));
- if (obj->pages == NULL)
- return -ENOMEM;
-
inode = obj->base.filp->f_path.dentry->d_inode;
- mapping = inode->i_mapping;
- gfpmask |= mapping_gfp_mask(mapping);
-
- for (i = 0; i < page_count; i++) {
- page = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
- if (IS_ERR(page))
- goto err_pages;
-
- obj->pages[i] = page;
- }
-
- if (i915_gem_object_needs_bit17_swizzle(obj))
- i915_gem_object_do_bit_17_swizzle(obj);
+ shmem_truncate_range(inode, 0, (loff_t)-1);
- return 0;
+ if (obj->base.map_list.map)
+ drm_gem_free_mmap_offset(&obj->base);
-err_pages:
- while (i--)
- page_cache_release(obj->pages[i]);
+ obj->madv = __I915_MADV_PURGED;
+}
- drm_free_large(obj->pages);
- obj->pages = NULL;
- return PTR_ERR(page);
+static inline int
+i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
+{
+ return obj->madv == I915_MADV_DONTNEED;
}
-static void
+static int
i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
{
int page_count = obj->base.size / PAGE_SIZE;
- int i;
+ int ret, i;
+
+ if (obj->pages == NULL)
+ return 0;
+ BUG_ON(obj->gtt_space);
BUG_ON(obj->madv == __I915_MADV_PURGED);
+ ret = i915_gem_object_set_to_cpu_domain(obj, 0);
+ if (ret && ret != -EIO)
+ return ret;
+
+ if (ret) {
+ /* In the event of a disaster, abandon all caches and
+ * hope for the best.
+ */
+ i915_gem_clflush_object(obj);
+ obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+ }
+
if (i915_gem_object_needs_bit17_swizzle(obj))
i915_gem_object_save_bit_17_swizzle(obj);
@@ -1390,6 +1393,181 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
drm_free_large(obj->pages);
obj->pages = NULL;
+
+ list_del(&obj->mm_list);
+
+ if (i915_gem_object_is_purgeable(obj))
+ i915_gem_object_truncate(obj);
+
+ return 0;
+}
+
+static long
+i915_gem_purge(struct drm_i915_private *dev_priv, long target)
+{
+ struct drm_i915_gem_object *obj, *next;
+ long count = 0;
+
+ list_for_each_entry_safe(obj, next,
+ &dev_priv->mm.unbound_list,
+ mm_list) {
+ if (i915_gem_object_is_purgeable(obj) &&
+ i915_gem_object_put_pages_gtt(obj) == 0) {
+ count += obj->base.size >> PAGE_SHIFT;
+ if (count >= target)
+ return count;
+ }
+ }
+
+ list_for_each_entry_safe(obj, next,
+ &dev_priv->mm.inactive_list,
+ mm_list) {
+ if (i915_gem_object_is_purgeable(obj) &&
+ i915_gem_object_unbind(obj) == 0 &&
+ i915_gem_object_put_pages_gtt(obj) == 0) {
+ count += obj->base.size >> PAGE_SHIFT;
+ if (count >= target)
+ return count;
+ }
+ }
+
+ return count;
+}
+
+inline static struct drm_i915_gem_object *
+first_unbound_bo(struct drm_i915_private *dev_priv)
+{
+ return list_first_entry(&dev_priv->mm.unbound_list,
+ struct drm_i915_gem_object,
+ mm_list);
+}
+
+static void
+i915_gem_shrink_all(struct drm_i915_private *dev_priv)
+{
+ i915_gem_evict_everything(dev_priv->dev);
+ while (!list_empty(&dev_priv->mm.unbound_list))
+ i915_gem_object_put_pages_gtt(first_unbound_bo(dev_priv));
+}
+
+/* Try to allocate some memory under the struct_mutex by purging some
+ * of our own buffers if necessary.
+ */
+static void *i915_malloc(struct drm_i915_private *dev_priv,
+ unsigned long size)
+{
+ gfp_t gfp;
+ void *ptr;
+
+ gfp = GFP_KERNEL;
+ gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
+ gfp &= ~(__GFP_IO | __GFP_WAIT);
+
+ ptr = kmalloc(size, gfp);
+ if (ptr)
+ return ptr;
+
+ if (size <= 2*PAGE_SIZE) {
+ i915_gem_purge(dev_priv, (size >> PAGE_SHIFT) + 1);
+ ptr = kmalloc(size, gfp);
+ if (ptr)
+ return ptr;
+
+ i915_gem_shrink_all(dev_priv);
+
+ gfp &= ~(__GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD);
+ gfp |= __GFP_IO | __GFP_WAIT;
+ return kmalloc(size, gfp);
+ } else {
+ gfp |= __GFP_HIGHMEM;
+ ptr = __vmalloc(size, gfp, PAGE_KERNEL);
+ if (ptr)
+ return ptr;
+
+ i915_gem_purge(dev_priv, (size >> PAGE_SHIFT) + 1);
+ ptr = __vmalloc(size, gfp, PAGE_KERNEL);
+ if (ptr)
+ return ptr;
+
+ i915_gem_shrink_all(dev_priv);
+
+ gfp &= ~(__GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD);
+ gfp |= __GFP_IO | __GFP_WAIT;
+ return __vmalloc(size, gfp, PAGE_KERNEL);
+ }
+}
+
+static int
+i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
+{
+ struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+ int page_count, i;
+ struct address_space *mapping;
+ struct page *page;
+ gfp_t gfp;
+
+ if (obj->pages)
+ return 0;
+
+ /* Assert that the object is not currently in any GPU domain. As it
+ * wasn't in the GTT, there shouldn't be any way it could have been in
+ * a GPU cache
+ */
+ BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
+ BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);
+
+ /* Get the list of pages out of our struct file. They'll be pinned
+ * at this point until we release them.
+ */
+ page_count = obj->base.size / PAGE_SIZE;
+ obj->pages = i915_malloc(dev_priv, page_count*sizeof(struct page *));
+ if (obj->pages == NULL)
+ return -ENOMEM;
+
+ /* Fail silently without starting the shrinker */
+ mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping;
+ gfp = mapping_gfp_mask(mapping);
+ gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
+ gfp &= ~(__GFP_IO | __GFP_WAIT);
+ for (i = 0; i < page_count; i++) {
+ page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+ if (IS_ERR(page)) {
+ i915_gem_purge(dev_priv, page_count);
+ page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+ }
+ if (IS_ERR(page)) {
+ /* We've tried hard to allocate the memory by reaping
+ * our own buffer, now let the real VM do its job and
+ * go down in flames if truly OOM.
+ */
+ gfp &= ~(__GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD);
+ gfp |= __GFP_IO | __GFP_WAIT;
+
+ i915_gem_shrink_all(dev_priv);
+ page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+ if (IS_ERR(page))
+ goto err_pages;
+
+ gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
+ gfp &= ~(__GFP_IO | __GFP_WAIT);
+ }
+
+ obj->pages[i] = page;
+ }
+
+ if (i915_gem_object_needs_bit17_swizzle(obj))
+ i915_gem_object_do_bit_17_swizzle(obj);
+
+ list_add_tail(&obj->mm_list, &dev_priv->mm.unbound_list);
+ return 0;
+
+err_pages:
+ while (i--)
+ page_cache_release(obj->pages[i]);
+
+ drm_free_large(obj->pages);
+ obj->pages = NULL;
+ return PTR_ERR(page);
}
void
@@ -1471,32 +1649,6 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
WARN_ON(i915_verify_lists(dev));
}
-/* Immediately discard the backing storage */
-static void
-i915_gem_object_truncate(struct drm_i915_gem_object *obj)
-{
- struct inode *inode;
-
- /* Our goal here is to return as much of the memory as
- * is possible back to the system as we are called from OOM.
- * To do this we must instruct the shmfs to drop all of its
- * backing pages, *now*.
- */
- inode = obj->base.filp->f_path.dentry->d_inode;
- shmem_truncate_range(inode, 0, (loff_t)-1);
-
- if (obj->base.map_list.map)
- drm_gem_free_mmap_offset(&obj->base);
-
- obj->madv = __I915_MADV_PURGED;
-}
-
-static inline int
-i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
-{
- return obj->madv == I915_MADV_DONTNEED;
-}
-
static void
i915_gem_process_flushing_list(struct intel_ring_buffer *ring,
uint32_t flush_domains)
@@ -1700,6 +1852,9 @@ void i915_gem_reset(struct drm_device *dev)
obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
}
+ while (!list_empty(&dev_priv->mm.unbound_list))
+ i915_gem_object_put_pages_gtt(first_unbound_bo(dev_priv));
+
/* The fence registers are invalidated so clear them out */
i915_gem_reset_fences(dev);
}
@@ -2046,10 +2201,8 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
if (obj->gtt_space == NULL)
return 0;
- if (obj->pin_count != 0) {
- DRM_ERROR("Attempting to unbind pinned buffer\n");
+ if (obj->pin_count != 0)
return -EINVAL;
- }
ret = i915_gem_object_finish_gpu(obj);
if (ret)
@@ -2061,22 +2214,6 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
i915_gem_object_finish_gtt(obj);
- /* Move the object to the CPU domain to ensure that
- * any possible CPU writes while it's not in the GTT
- * are flushed when we go to remap it.
- */
- if (ret == 0)
- ret = i915_gem_object_set_to_cpu_domain(obj, 1);
- if (ret == -ERESTARTSYS)
- return ret;
- if (ret) {
- /* In the event of a disaster, abandon all caches and
- * hope for the best.
- */
- i915_gem_clflush_object(obj);
- obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
- }
-
/* release the fence reg _after_ flushing */
ret = i915_gem_object_put_fence(obj);
if (ret)
@@ -2092,10 +2229,8 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
}
i915_gem_gtt_finish_object(obj);
- i915_gem_object_put_pages_gtt(obj);
-
list_del_init(&obj->gtt_list);
- list_del_init(&obj->mm_list);
+ list_move_tail(&obj->mm_list, &dev_priv->mm.unbound_list);
/* Avoid an unnecessary call to unbind on rebind. */
obj->map_and_fenceable = true;
@@ -2103,10 +2238,10 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
obj->gtt_space = NULL;
obj->gtt_offset = 0;
- if (i915_gem_object_is_purgeable(obj))
- i915_gem_object_truncate(obj);
+ if (obj->base.read_domains & I915_GEM_DOMAIN_CPU)
+ i915_gem_object_put_pages_gtt(obj);
- return ret;
+ return 0;
}
int
@@ -2490,7 +2625,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
struct drm_device *dev = obj->base.dev;
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_mm_node *free_space;
- gfp_t gfpmask = __GFP_NORETRY | __GFP_NOWARN;
u32 size, fence_size, fence_alignment, unfenced_alignment;
bool mappable, fenceable;
int ret;
@@ -2530,6 +2664,10 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
return -E2BIG;
}
+ ret = i915_gem_object_get_pages_gtt(obj);
+ if (ret)
+ return ret;
+
search_free:
if (map_and_fenceable)
free_space =
@@ -2553,9 +2691,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
drm_mm_get_block(free_space, size, alignment);
}
if (obj->gtt_space == NULL) {
- /* If the gtt is empty and we're still having trouble
- * fitting our object in, we're out of memory.
- */
ret = i915_gem_evict_something(dev, size, alignment,
map_and_fenceable);
if (ret)
@@ -2564,54 +2699,19 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
goto search_free;
}
- ret = i915_gem_object_get_pages_gtt(obj, gfpmask);
- if (ret) {
- drm_mm_put_block(obj->gtt_space);
- obj->gtt_space = NULL;
-
- if (ret == -ENOMEM) {
- /* first try to reclaim some memory by clearing the GTT */
- ret = i915_gem_evict_everything(dev, false);
- if (ret) {
- /* now try to shrink everyone else */
- if (gfpmask) {
- gfpmask = 0;
- goto search_free;
- }
-
- return -ENOMEM;
- }
-
- goto search_free;
- }
-
- return ret;
- }
ret = i915_gem_gtt_prepare_object(obj);
if (ret) {
- i915_gem_object_put_pages_gtt(obj);
drm_mm_put_block(obj->gtt_space);
obj->gtt_space = NULL;
-
- if (i915_gem_evict_everything(dev, false))
- return ret;
-
- goto search_free;
+ return ret;
}
if (!dev_priv->mm.aliasing_ppgtt)
i915_gem_gtt_bind_object(obj, obj->cache_level);
list_add_tail(&obj->gtt_list, &dev_priv->mm.gtt_list);
- list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
-
- /* Assert that the object is not currently in any GPU domain. As it
- * wasn't in the GTT, there shouldn't be any way it could have been in
- * a GPU cache
- */
- BUG_ON(obj->base.read_domains & I915_GEM_GPU_DOMAINS);
- BUG_ON(obj->base.write_domain & I915_GEM_GPU_DOMAINS);
+ list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
obj->gtt_offset = obj->gtt_space->start;
@@ -3286,9 +3386,8 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
if (obj->madv != __I915_MADV_PURGED)
obj->madv = args->madv;
- /* if the object is no longer bound, discard its backing storage */
- if (i915_gem_object_is_purgeable(obj) &&
- obj->gtt_space == NULL)
+ /* if the object is no longer attached, discard its backing storage */
+ if (i915_gem_object_is_purgeable(obj) && obj->pages == NULL)
i915_gem_object_truncate(obj);
args->retained = obj->madv != __I915_MADV_PURGED;
@@ -3385,6 +3484,7 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
dev_priv->mm.interruptible = was_interruptible;
}
+ i915_gem_object_put_pages_gtt(obj);
if (obj->base.map_list.map)
drm_gem_free_mmap_offset(&obj->base);
@@ -3416,7 +3516,7 @@ i915_gem_idle(struct drm_device *dev)
/* Under UMS, be paranoid and evict. */
if (!drm_core_check_feature(dev, DRIVER_MODESET))
- i915_gem_evict_everything(dev, false);
+ i915_gem_evict_everything(dev);
i915_gem_reset_fences(dev);
@@ -3659,6 +3759,7 @@ i915_gem_load(struct drm_device *dev)
INIT_LIST_HEAD(&dev_priv->mm.active_list);
INIT_LIST_HEAD(&dev_priv->mm.flushing_list);
INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
+ INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
INIT_LIST_HEAD(&dev_priv->mm.fence_list);
INIT_LIST_HEAD(&dev_priv->mm.gtt_list);
for (i = 0; i < I915_NUM_RINGS; i++)
@@ -3909,18 +4010,6 @@ void i915_gem_release(struct drm_device *dev, struct drm_file *file)
}
static int
-i915_gpu_is_active(struct drm_device *dev)
-{
- drm_i915_private_t *dev_priv = dev->dev_private;
- int lists_empty;
-
- lists_empty = list_empty(&dev_priv->mm.flushing_list) &&
- list_empty(&dev_priv->mm.active_list);
-
- return !lists_empty;
-}
-
-static int
i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
@@ -3928,60 +4017,25 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
struct drm_i915_private,
mm.inactive_shrinker);
struct drm_device *dev = dev_priv->dev;
- struct drm_i915_gem_object *obj, *next;
+ struct drm_i915_gem_object *obj;
int nr_to_scan = sc->nr_to_scan;
int cnt;
if (!mutex_trylock(&dev->struct_mutex))
return 0;
- /* "fast-path" to count number of available objects */
- if (nr_to_scan == 0) {
- cnt = 0;
- list_for_each_entry(obj,
- &dev_priv->mm.inactive_list,
- mm_list)
- cnt++;
- mutex_unlock(&dev->struct_mutex);
- return cnt / 100 * sysctl_vfs_cache_pressure;
- }
-
-rescan:
- /* first scan for clean buffers */
- i915_gem_retire_requests(dev);
-
- list_for_each_entry_safe(obj, next,
- &dev_priv->mm.inactive_list,
- mm_list) {
- if (i915_gem_object_is_purgeable(obj)) {
- if (i915_gem_object_unbind(obj) == 0 &&
- --nr_to_scan == 0)
- break;
- }
+ if (nr_to_scan) {
+ nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
+ if (nr_to_scan > 0)
+ i915_gem_shrink_all(dev_priv);
}
- /* second pass, evict/count anything still on the inactive list */
cnt = 0;
- list_for_each_entry_safe(obj, next,
- &dev_priv->mm.inactive_list,
- mm_list) {
- if (nr_to_scan &&
- i915_gem_object_unbind(obj) == 0)
- nr_to_scan--;
- else
- cnt++;
- }
+ list_for_each_entry(obj, &dev_priv->mm.unbound_list, mm_list)
+ cnt += obj->base.size >> PAGE_SHIFT;
+ list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
+ cnt += obj->base.size >> PAGE_SHIFT;
- if (nr_to_scan && i915_gpu_is_active(dev)) {
- /*
- * We are desperate for pages, so as a last resort, wait
- * for the GPU to finish and discard whatever we can.
- * This has a dramatic impact to reduce the number of
- * OOM-killer events whilst running the GPU aggressively.
- */
- if (i915_gpu_idle(dev, true) == 0)
- goto rescan;
- }
mutex_unlock(&dev->struct_mutex);
return cnt / 100 * sysctl_vfs_cache_pressure;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 91ebb94..99e7696 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -163,7 +163,7 @@ found:
}
int
-i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
+i915_gem_evict_everything(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj, *next;
@@ -176,7 +176,7 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
if (lists_empty)
return -ENOSPC;
- trace_i915_gem_evict_everything(dev, purgeable_only);
+ trace_i915_gem_evict_everything(dev);
/* Flush everything (on to the inactive lists) and evict */
ret = i915_gpu_idle(dev, true);
@@ -187,12 +187,9 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only)
/* Having flushed everything, unbind() should never raise an error */
list_for_each_entry_safe(obj, next,
- &dev_priv->mm.inactive_list, mm_list) {
- if (!purgeable_only || obj->madv != I915_MADV_WILLNEED) {
- if (obj->pin_count == 0)
- WARN_ON(i915_gem_object_unbind(obj));
- }
- }
+ &dev_priv->mm.inactive_list, mm_list)
+ if (obj->pin_count == 0)
+ WARN_ON(i915_gem_object_unbind(obj));
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 68ec013..2091c86 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -675,17 +675,12 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
}
}
- if (ret != -ENOSPC || retry > 1)
+ if (ret != -ENOSPC || retry++)
return ret;
- /* First attempt, just clear anything that is purgeable.
- * Second attempt, clear the entire GTT.
- */
- ret = i915_gem_evict_everything(ring->dev, retry == 0);
+ ret = i915_gem_evict_everything(ring->dev);
if (ret)
return ret;
-
- retry++;
} while (1);
err:
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index dac7bba..b6ce36a 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -214,22 +214,18 @@ TRACE_EVENT(i915_gem_evict,
);
TRACE_EVENT(i915_gem_evict_everything,
- TP_PROTO(struct drm_device *dev, bool purgeable),
- TP_ARGS(dev, purgeable),
+ TP_PROTO(struct drm_device *dev),
+ TP_ARGS(dev),
TP_STRUCT__entry(
__field(u32, dev)
- __field(bool, purgeable)
),
TP_fast_assign(
__entry->dev = dev->primary->index;
- __entry->purgeable = purgeable;
),
- TP_printk("dev=%d%s",
- __entry->dev,
- __entry->purgeable ? ", purgeable only" : "")
+ TP_printk("dev=%d", __entry->dev)
);
TRACE_EVENT(i915_gem_ring_dispatch,
--
1.7.10
More information about the Intel-gfx
mailing list