Shamelessly manipulated out of Daniel :-)
"When moving the lists around explain that the active/inactive stuff is
used by eviction when we run out of address space, so needs to be
per-vma and per-address space. Bound/unbound otoh is used by the
shrinker which only cares about the amount of memory used and not one
bit about in which address space this memory is all used in. Of course
to actual kick out an object we need to unbind it from every address
space, but for that we have the per-object list of vmas."
v2: Leave the bound list as a global one. (Chris, indirectly)
v3: Rebased with no i915_gtt_vm. In most places I added a new *vm local,
since it will eventually be replaces by a vm argument.
Put comment back inline, since it no longer makes sense to do otherwise.
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
drivers/gpu/drm/i915/i915_debugfs.c | 16 +++++++-----
drivers/gpu/drm/i915/i915_drv.h | 46 +++++++++++++++++-----------------
drivers/gpu/drm/i915/i915_gem.c | 33 ++++++++++++------------
drivers/gpu/drm/i915/i915_gem_debug.c | 2 +-
drivers/gpu/drm/i915/i915_gem_evict.c | 18 ++++++-------
drivers/gpu/drm/i915/i915_gem_stolen.c | 3 ++-
drivers/gpu/drm/i915/i915_irq.c | 8 +++---
7 files changed, 67 insertions(+), 59 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d870f27..16b2aaf 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -146,7 +146,8 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
uintptr_t list = (uintptr_t) node->info_ent->data;
struct list_head *head;
struct drm_device *dev = node->minor->dev;
- drm_i915_private_t *dev_priv = dev->dev_private;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_i915_gem_object *obj;
size_t total_obj_size, total_gtt_size;
int count, ret;
@@ -158,11 +159,11 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
switch (list) {
case ACTIVE_LIST:
seq_puts(m, "Active:\n");
- head = &dev_priv->mm.active_list;
+ head = &vm->active_list;
break;
case INACTIVE_LIST:
seq_puts(m, "Inactive:\n");
- head = &dev_priv->mm.inactive_list;
+ head = &vm->inactive_list;
break;
default:
mutex_unlock(&dev->struct_mutex);
@@ -230,6 +231,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
u32 count, mappable_count, purgeable_count;
size_t size, mappable_size, purgeable_size;
struct drm_i915_gem_object *obj;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_file *file;
int ret;
@@ -247,12 +249,12 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
count, mappable_count, size, mappable_size);
size = count = mappable_size = mappable_count = 0;
- count_objects(&dev_priv->mm.active_list, mm_list);
+ count_objects(&vm->active_list, mm_list);
seq_printf(m, " %u [%u] active objects, %zu [%zu] bytes\n",
count, mappable_count, size, mappable_size);
size = count = mappable_size = mappable_count = 0;
- count_objects(&dev_priv->mm.inactive_list, mm_list);
+ count_objects(&vm->inactive_list, mm_list);
seq_printf(m, " %u [%u] inactive objects, %zu [%zu] bytes\n",
count, mappable_count, size, mappable_size);
@@ -2025,6 +2027,7 @@ i915_drop_caches_set(void *data, u64 val)
struct drm_device *dev = data;
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj, *next;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
int ret;
DRM_DEBUG_DRIVER("Dropping caches: 0x%08llx\n", val);
@@ -2045,7 +2048,8 @@ i915_drop_caches_set(void *data, u64 val)
i915_gem_retire_requests(dev);
if (val & DROP_BOUND) {
- list_for_each_entry_safe(obj, next, &dev_priv->mm.inactive_list, mm_list)
+ list_for_each_entry_safe(obj, next, &vm->inactive_list,
+ mm_list)
if (obj->pin_count == 0) {
ret = i915_gem_object_unbind(obj);
if (ret)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 997c9a5..3759c09 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -458,6 +458,29 @@ struct i915_address_space {
struct page *page;
} scratch;
+ /**
+ * List of objects currently involved in rendering.
+ *
+ * Includes buffers having the contents of their GPU caches
+ * flushed, not necessarily primitives. last_rendering_seqno
+ * represents when the rendering involved will be completed.
+ *
+ * A reference is held on the buffer while on this list.
+ */
+ struct list_head active_list;
+
+ /**
+ * LRU list of objects which are not in the ringbuffer and
+ * are ready to unbind, but are still in the GTT.
+ *
+ * last_rendering_seqno is 0 while an object is in this list.
+ *
+ * A reference is not held on the buffer while on this list,
+ * as merely being GTT-bound shouldn't prevent its being
+ * freed, and we'll pull it off the list in the free path.
+ */
+ struct list_head inactive_list;
+
/* FIXME: Need a more generic return type */
gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
enum i915_cache_level level);
@@ -840,29 +863,6 @@ struct i915_gem_mm {
struct shrinker inactive_shrinker;
bool shrinker_no_lock_stealing;
- /**
- * List of objects currently involved in rendering.
- *
- * Includes buffers having the contents of their GPU caches
- * flushed, not necessarily primitives. last_rendering_seqno
- * represents when the rendering involved will be completed.
- *
- * A reference is held on the buffer while on this list.
- */
- struct list_head active_list;
-
- /**
- * LRU list of objects which are not in the ringbuffer and
- * are ready to unbind, but are still in the GTT.
- *
- * last_rendering_seqno is 0 while an object is in this list.
- *
- * A reference is not held on the buffer while on this list,
- * as merely being GTT-bound shouldn't prevent its being
- * freed, and we'll pull it off the list in the free path.
- */
- struct list_head inactive_list;
-
/** LRU list of objects with fence regs on them. */
struct list_head fence_list;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ad763e3..525aa8f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1692,6 +1692,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
bool purgeable_only)
{
struct drm_i915_gem_object *obj, *next;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
long count = 0;
list_for_each_entry_safe(obj, next,
@@ -1705,9 +1706,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
}
}
- list_for_each_entry_safe(obj, next,
- &dev_priv->mm.inactive_list,
- mm_list) {
+ list_for_each_entry_safe(obj, next, &vm->inactive_list, mm_list) {
if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
i915_gem_object_unbind(obj) == 0 &&
i915_gem_object_put_pages(obj) == 0) {
@@ -1878,6 +1877,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
{
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
u32 seqno = intel_ring_get_seqno(ring);
BUG_ON(ring == NULL);
@@ -1890,7 +1890,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
}
/* Move from whatever list we were on to the tail of execution. */
- list_move_tail(&obj->mm_list, &dev_priv->mm.active_list);
+ list_move_tail(&obj->mm_list, &vm->active_list);
list_move_tail(&obj->ring_list, &ring->active_list);
obj->last_read_seqno = seqno;
@@ -1914,11 +1914,12 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
{
struct drm_device *dev = obj->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS);
BUG_ON(!obj->active);
- list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+ list_move_tail(&obj->mm_list, &vm->inactive_list);
list_del_init(&obj->ring_list);
obj->ring = NULL;
@@ -2262,6 +2263,7 @@ void i915_gem_restore_fences(struct drm_device *dev)
void i915_gem_reset(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_i915_gem_object *obj;
struct intel_ring_buffer *ring;
int i;
@@ -2272,12 +2274,8 @@ void i915_gem_reset(struct drm_device *dev)
/* Move everything out of the GPU domains to ensure we do any
* necessary invalidation upon reuse.
*/
- list_for_each_entry(obj,
- &dev_priv->mm.inactive_list,
- mm_list)
- {
+ list_for_each_entry(obj, &vm->inactive_list, mm_list)
obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
- }
i915_gem_restore_fences(dev);
}
@@ -3067,6 +3065,7 @@ 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 i915_address_space *vm = &dev_priv->gtt.base;
u32 size, fence_size, fence_alignment, unfenced_alignment;
bool mappable, fenceable;
size_t gtt_max = map_and_fenceable ?
@@ -3142,7 +3141,7 @@ search_free:
}
list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
- list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+ list_add_tail(&obj->mm_list, &vm->inactive_list);
fenceable =
i915_gem_obj_ggtt_size(obj) == fence_size &&
@@ -3290,7 +3289,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
/* And bump the LRU for this access */
if (i915_gem_object_is_inactive(obj))
- list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+ list_move_tail(&obj->mm_list,
+ &dev_priv->gtt.base.inactive_list);
return 0;
}
@@ -4240,7 +4240,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
return ret;
}
- BUG_ON(!list_empty(&dev_priv->mm.active_list));
+ BUG_ON(!list_empty(&dev_priv->gtt.base.active_list));
mutex_unlock(&dev->struct_mutex);
ret = drm_irq_install(dev);
@@ -4301,8 +4301,8 @@ i915_gem_load(struct drm_device *dev)
SLAB_HWCACHE_ALIGN,
NULL);
- INIT_LIST_HEAD(&dev_priv->mm.active_list);
- INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
+ INIT_LIST_HEAD(&dev_priv->gtt.base.active_list);
+ INIT_LIST_HEAD(&dev_priv->gtt.base.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);
@@ -4573,6 +4573,7 @@ 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 i915_address_space *vm = &dev_priv->gtt.base;
struct drm_i915_gem_object *obj;
int nr_to_scan = sc->nr_to_scan;
bool unlock = true;
@@ -4601,7 +4602,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
if (obj->pages_pin_count == 0)
cnt += obj->base.size >> PAGE_SHIFT;
- list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
+ list_for_each_entry(obj, &vm->inactive_list, mm_list)
if (obj->pin_count == 0 && obj->pages_pin_count == 0)
cnt += obj->base.size >> PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c
index 582e6a5..bf945a3 100644
--- a/drivers/gpu/drm/i915/i915_gem_debug.c
+++ b/drivers/gpu/drm/i915/i915_gem_debug.c
@@ -97,7 +97,7 @@ i915_verify_lists(struct drm_device *dev)
}
}
- list_for_each_entry(obj, &dev_priv->mm.inactive_list, list) {
+ list_for_each_entry(obj, &i915_gtt_vm->inactive_list, list) {
if (obj->base.dev != dev ||
!atomic_read(&obj->base.refcount.refcount)) {
DRM_ERROR("freed inactive %p\n", obj);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index f1c9ab0..43b8235 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -47,6 +47,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
bool mappable, bool nonblocking)
{
drm_i915_private_t *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct list_head eviction_list, unwind_list;
struct drm_i915_gem_object *obj;
int ret = 0;
@@ -78,15 +79,14 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
INIT_LIST_HEAD(&unwind_list);
if (mappable)
- drm_mm_init_scan_with_range(&dev_priv->gtt.base.mm, min_size,
+ drm_mm_init_scan_with_range(&vm->mm, min_size,
alignment, cache_level, 0,
dev_priv->gtt.mappable_end);
else
- drm_mm_init_scan(&dev_priv->gtt.base.mm, min_size, alignment,
- cache_level);
+ drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level);
/* First see if there is a large enough contiguous idle region... */
- list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list) {
+ list_for_each_entry(obj, &vm->inactive_list, mm_list) {
if (mark_free(obj, &unwind_list))
goto found;
}
@@ -95,7 +95,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size,
goto none;
/* Now merge in the soon-to-be-expired objects... */
- list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
+ list_for_each_entry(obj, &vm->active_list, mm_list) {
if (mark_free(obj, &unwind_list))
goto found;
}
@@ -154,12 +154,13 @@ int
i915_gem_evict_everything(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_i915_gem_object *obj, *next;
bool lists_empty;
int ret;
- lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
- list_empty(&dev_priv->mm.active_list));
+ lists_empty = (list_empty(&vm->inactive_list) &&
+ list_empty(&vm->active_list));
if (lists_empty)
return -ENOSPC;
@@ -176,8 +177,7 @@ i915_gem_evict_everything(struct drm_device *dev)
i915_gem_retire_requests(dev);
/* Having flushed everything, unbind() should never raise an error */
- list_for_each_entry_safe(obj, next,
- &dev_priv->mm.inactive_list, mm_list)
+ list_for_each_entry_safe(obj, next, &vm->inactive_list, mm_list)
if (obj->pin_count == 0)
WARN_ON(i915_gem_object_unbind(obj));
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index c201321..a4c3136 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -348,6 +348,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
u32 size)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
struct drm_i915_gem_object *obj;
struct drm_mm_node *stolen;
int ret;
@@ -408,7 +409,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
obj->has_global_gtt_mapping = 1;
list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
- list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
+ list_add_tail(&obj->mm_list, &vm->inactive_list);
return obj;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 56199ef..79fbb17 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1707,6 +1707,7 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
struct intel_ring_buffer *ring)
{
struct drm_i915_gem_object *obj;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
u32 seqno;
if (!ring->get_seqno)
@@ -1725,7 +1726,7 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
}
seqno = ring->get_seqno(ring, false);
- list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) {
+ list_for_each_entry(obj, &vm->active_list, mm_list) {
if (obj->ring != ring)
continue;
@@ -1858,10 +1859,11 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
struct drm_i915_error_state *error)
{
struct drm_i915_gem_object *obj;
+ struct i915_address_space *vm = &dev_priv->gtt.base;
int i;
i = 0;
- list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list)
+ list_for_each_entry(obj, &vm->active_list, mm_list)
i++;
error->active_bo_count = i;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
@@ -1881,7 +1883,7 @@ static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
error->active_bo_count =
capture_active_bo(error->active_bo,
error->active_bo_count,
- &dev_priv->mm.active_list);
+ &vm->active_list);
if (error->pinned_bo)
error->pinned_bo_count =
--
1.8.3.2
