[Intel-gfx] [PATCH 01/29] drm/i915: Track unbound pages
Chris Wilson
chris at chris-wilson.co.uk
Sat Aug 11 16:41:00 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 | 14 +-
drivers/gpu/drm/i915/i915_drv.h | 13 +-
drivers/gpu/drm/i915/i915_gem.c | 397 ++++++++++++++--------------
drivers/gpu/drm/i915/i915_gem_dmabuf.c | 20 +-
drivers/gpu/drm/i915/i915_gem_evict.c | 13 +-
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +-
drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
drivers/gpu/drm/i915/i915_irq.c | 4 +-
drivers/gpu/drm/i915/i915_trace.h | 10 +-
9 files changed, 240 insertions(+), 242 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0e8f14d..a7eb093 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -211,7 +211,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
dev_priv->mm.object_memory);
size = count = mappable_size = mappable_count = 0;
- count_objects(&dev_priv->mm.gtt_list, gtt_list);
+ count_objects(&dev_priv->mm.bound_list, gtt_list);
seq_printf(m, "%u [%u] objects, %zu [%zu] bytes in gtt\n",
count, mappable_count, size, mappable_size);
@@ -225,8 +225,13 @@ 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, gtt_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) {
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
if (obj->fault_mappable) {
size += obj->gtt_space->size;
++count;
@@ -264,7 +269,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void* data)
return ret;
total_obj_size = total_gtt_size = count = 0;
- list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
if (list == PINNED_LIST && obj->pin_count == 0)
continue;
@@ -526,7 +531,8 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_gem_object *obj = dev_priv->fence_regs[i].obj;
- seq_printf(m, "Fenced object[%2d] = ", i);
+ seq_printf(m, "Fence %d, pin count = %d, object = ",
+ i, dev_priv->fence_regs[i].pin_count);
if (obj == NULL)
seq_printf(m, "unused");
else
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 261fe21..e252947 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -692,7 +692,13 @@ typedef struct drm_i915_private {
struct drm_mm gtt_space;
/** List of all objects in gtt_space. Used to restore gtt
* mappings on resume */
- struct list_head gtt_list;
+ struct list_head bound_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;
/** Usable portion of the GTT for GEM */
unsigned long gtt_start;
@@ -1307,8 +1313,7 @@ int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj);
void i915_gem_release_mmap(struct drm_i915_gem_object *obj);
void i915_gem_lastclose(struct drm_device *dev);
-int i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj,
- gfp_t gfpmask);
+int __must_check i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj);
int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
int i915_gem_object_sync(struct drm_i915_gem_object *obj,
struct intel_ring_buffer *to);
@@ -1450,7 +1455,7 @@ int __must_check i915_gem_evict_something(struct drm_device *dev, int min_size,
unsigned alignment,
unsigned cache_level,
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_stolen.c */
int i915_gem_init_stolen(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0514593..3a7ac38 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)
@@ -140,7 +142,7 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
static inline bool
i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
{
- return !obj->active;
+ return obj->gtt_space && !obj->active;
}
int
@@ -179,7 +181,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
pinned = 0;
mutex_lock(&dev->struct_mutex);
- list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list)
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
if (obj->pin_count)
pinned += obj->gtt_space->size;
mutex_unlock(&dev->struct_mutex);
@@ -423,9 +425,11 @@ 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;
@@ -751,9 +755,11 @@ 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. */
@@ -1340,64 +1346,54 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
}
-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;
-
- if (obj->pages || obj->sg_table)
- return 0;
- /* 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)
- return;
+ 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, true);
+ if (ret) {
+ /* In the event of a disaster, abandon all caches and
+ * hope for the best.
+ */
+ WARN_ON(ret != -EIO);
+ 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);
@@ -1417,6 +1413,129 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj)
drm_free_large(obj->pages);
obj->pages = NULL;
+
+ list_del(&obj->gtt_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,
+ gtt_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;
+}
+
+static void
+i915_gem_shrink_all(struct drm_i915_private *dev_priv)
+{
+ struct drm_i915_gem_object *obj, *next;
+
+ i915_gem_evict_everything(dev_priv->dev);
+
+ list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+ i915_gem_object_put_pages_gtt(obj);
+}
+
+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 || obj->sg_table)
+ 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 = kmalloc(page_count*sizeof(struct page *), GFP_KERNEL);
+ 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->gtt_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
@@ -1486,32 +1605,6 @@ 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 u32
i915_gem_get_seqno(struct drm_device *dev)
{
@@ -1681,7 +1774,7 @@ static void i915_gem_reset_fences(struct drm_device *dev)
void i915_gem_reset(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct drm_i915_gem_object *obj;
+ struct drm_i915_gem_object *obj, *next;
struct intel_ring_buffer *ring;
int i;
@@ -1698,6 +1791,10 @@ void i915_gem_reset(struct drm_device *dev)
obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
}
+
+ list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+ i915_gem_object_put_pages_gtt(obj);
+
/* The fence registers are invalidated so clear them out */
i915_gem_reset_fences(dev);
}
@@ -2209,22 +2306,6 @@ 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)
@@ -2240,10 +2321,8 @@ 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_del(&obj->mm_list);
+ list_move_tail(&obj->gtt_list, &dev_priv->mm.unbound_list);
/* Avoid an unnecessary call to unbind on rebind. */
obj->map_and_fenceable = true;
@@ -2251,10 +2330,7 @@ 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);
-
- return ret;
+ return 0;
}
static int i915_ring_idle(struct intel_ring_buffer *ring)
@@ -2667,7 +2743,6 @@ 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;
@@ -2707,6 +2782,10 @@ 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 =
@@ -2733,9 +2812,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
false);
}
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,
obj->cache_level,
map_and_fenceable);
@@ -2752,55 +2828,20 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
return -EINVAL;
}
- 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_move_tail(&obj->gtt_list, &dev_priv->mm.bound_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);
-
obj->gtt_offset = obj->gtt_space->start;
fenceable =
@@ -3464,9 +3505,8 @@ 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;
@@ -3573,6 +3613,7 @@ 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);
@@ -3605,7 +3646,7 @@ 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);
@@ -3963,8 +4004,9 @@ i915_gem_load(struct drm_device *dev)
INIT_LIST_HEAD(&dev_priv->mm.active_list);
INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
+ INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
+ INIT_LIST_HEAD(&dev_priv->mm.bound_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++)
init_ring_lists(&dev_priv->ring[i]);
for (i = 0; i < I915_MAX_NUM_FENCES; i++)
@@ -4209,13 +4251,6 @@ 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;
- return !list_empty(&dev_priv->mm.active_list);
-}
-
-static int
i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
@@ -4223,60 +4258,26 @@ 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, gtt_list)
+ cnt += obj->base.size >> PAGE_SHIFT;
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
+ if (obj->pin_count == 0)
+ 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) == 0)
- goto rescan;
- }
mutex_unlock(&dev->struct_mutex);
- return cnt / 100 * sysctl_vfs_cache_pressure;
+ return cnt;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index aa308e1..e5f0375 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -33,7 +33,7 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
struct drm_i915_gem_object *obj = attachment->dmabuf->priv;
struct drm_device *dev = obj->base.dev;
int npages = obj->base.size / PAGE_SIZE;
- struct sg_table *sg = NULL;
+ struct sg_table *sg;
int ret;
int nents;
@@ -41,10 +41,10 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
if (ret)
return ERR_PTR(ret);
- if (!obj->pages) {
- ret = i915_gem_object_get_pages_gtt(obj, __GFP_NORETRY | __GFP_NOWARN);
- if (ret)
- goto out;
+ ret = i915_gem_object_get_pages_gtt(obj);
+ if (ret) {
+ sg = ERR_PTR(ret);
+ goto out;
}
/* link the pages into an SG then map the sg */
@@ -89,12 +89,10 @@ static void *i915_gem_dmabuf_vmap(struct dma_buf *dma_buf)
goto out_unlock;
}
- if (!obj->pages) {
- ret = i915_gem_object_get_pages_gtt(obj, __GFP_NORETRY | __GFP_NOWARN);
- if (ret) {
- mutex_unlock(&dev->struct_mutex);
- return ERR_PTR(ret);
- }
+ ret = i915_gem_object_get_pages_gtt(obj);
+ if (ret) {
+ mutex_unlock(&dev->struct_mutex);
+ return ERR_PTR(ret);
}
obj->dma_buf_vmapping = vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 7279c31..74635da 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -148,7 +148,7 @@ 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;
@@ -160,7 +160,7 @@ 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);
/* The gpu_idle will flush everything in the write domain to the
* active list. Then we must move everything off the active list
@@ -174,12 +174,9 @@ 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 0;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 25b2c54..50b07a1 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -502,17 +502,12 @@ 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_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 4584f7f..3c36d3b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -348,7 +348,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
intel_gtt_clear_range(dev_priv->mm.gtt_start / PAGE_SIZE,
(dev_priv->mm.gtt_end - dev_priv->mm.gtt_start) / PAGE_SIZE);
- list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list) {
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) {
i915_gem_clflush_object(obj);
i915_gem_gtt_bind_object(obj, obj->cache_level);
}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0c37101..4153c75 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1222,7 +1222,7 @@ static void i915_capture_error_state(struct drm_device *dev)
list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list)
i++;
error->active_bo_count = i;
- list_for_each_entry(obj, &dev_priv->mm.gtt_list, gtt_list)
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list)
if (obj->pin_count)
i++;
error->pinned_bo_count = i - error->active_bo_count;
@@ -1247,7 +1247,7 @@ static void i915_capture_error_state(struct drm_device *dev)
error->pinned_bo_count =
capture_pinned_bo(error->pinned_bo,
error->pinned_bo_count,
- &dev_priv->mm.gtt_list);
+ &dev_priv->mm.bound_list);
do_gettimeofday(&error->time);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index fe90b3a..3c4093d 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,
--
1.7.10.4
More information about the Intel-gfx
mailing list