#include <linux/dma-buf.h>
static void i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj);
-static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj);
-static __must_check int i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
- unsigned alignment,
- bool map_and_fenceable,
- bool nonblocking);
+static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+ bool force);
+static __must_check int
+i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm,
+ unsigned alignment,
+ bool map_and_fenceable,
+ bool nonblocking);
static int i915_gem_phys_pwrite(struct drm_device *dev,
struct drm_i915_gem_object *obj,
struct drm_i915_gem_pwrite *args,
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 bool cpu_cache_is_coherent(struct drm_device *dev,
+ enum i915_cache_level level)
+{
+ return HAS_LLC(dev) || level != I915_CACHE_NONE;
+}
+
+static bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
+{
+ if (!cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
+ return true;
+
+ return obj->pin_display;
+}
+
static inline void i915_gem_object_fence_lost(struct drm_i915_gem_object *obj)
{
if (obj->tiling_mode)
static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv,
size_t size)
{
+ spin_lock(&dev_priv->mm.object_stat_lock);
dev_priv->mm.object_count++;
dev_priv->mm.object_memory += size;
+ spin_unlock(&dev_priv->mm.object_stat_lock);
}
static void i915_gem_info_remove_obj(struct drm_i915_private *dev_priv,
size_t size)
{
+ spin_lock(&dev_priv->mm.object_stat_lock);
dev_priv->mm.object_count--;
dev_priv->mm.object_memory -= size;
+ spin_unlock(&dev_priv->mm.object_stat_lock);
}
static int
static inline bool
i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
{
- return i915_gem_obj_ggtt_bound(obj) && !obj->active;
+ return i915_gem_obj_bound_any(obj) && !obj->active;
}
int
return -ENOMEM;
ret = drm_gem_handle_create(file, &obj->base, &handle);
- if (ret) {
- drm_gem_object_release(&obj->base);
- i915_gem_info_remove_obj(dev->dev_private, obj->base.size);
- i915_gem_object_free(obj);
- return ret;
- }
-
/* drop reference from allocate - handle holds it now */
- drm_gem_object_unreference(&obj->base);
- trace_i915_gem_object_create(obj);
+ drm_gem_object_unreference_unlocked(&obj->base);
+ if (ret)
+ return ret;
*handle_p = handle;
return 0;
* read domain and manually flush cachelines (if required). This
* optimizes for the case when the gpu will dirty the data
* anyway again before the next pread happens. */
- if (obj->cache_level == I915_CACHE_NONE)
- needs_clflush = 1;
- if (i915_gem_obj_ggtt_bound(obj)) {
+ needs_clflush = !cpu_cache_is_coherent(dev, obj->cache_level);
+ if (i915_gem_obj_bound_any(obj)) {
ret = i915_gem_object_set_to_gtt_domain(obj, false);
if (ret)
return ret;
mutex_unlock(&dev->struct_mutex);
- if (!prefaulted) {
+ if (likely(!i915_prefault_disable) && !prefaulted) {
ret = fault_in_multipages_writeable(user_data, remain);
/* Userspace is tricking us, but we've already clobbered
* its pages with the prefault and promised to write the
char __user *user_data;
int page_offset, page_length, ret;
- ret = i915_gem_object_pin(obj, 0, true, true);
+ ret = i915_gem_obj_ggtt_pin(obj, 0, true, true);
if (ret)
goto out;
* write domain and manually flush cachelines (if required). This
* optimizes for the case when the gpu will use the data
* right away and we therefore have to clflush anyway. */
- if (obj->cache_level == I915_CACHE_NONE)
- needs_clflush_after = 1;
- if (i915_gem_obj_ggtt_bound(obj)) {
+ needs_clflush_after = cpu_write_needs_clflush(obj);
+ if (i915_gem_obj_bound_any(obj)) {
ret = i915_gem_object_set_to_gtt_domain(obj, true);
if (ret)
return ret;
}
}
- /* Same trick applies for invalidate partially written cachelines before
- * writing. */
- if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)
- && obj->cache_level == I915_CACHE_NONE)
- needs_clflush_before = 1;
+ /* Same trick applies to invalidate partially written cachelines read
+ * before writing. */
+ if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0)
+ needs_clflush_before =
+ !cpu_cache_is_coherent(dev, obj->cache_level);
ret = i915_gem_object_get_pages(obj);
if (ret)
*/
if (!needs_clflush_after &&
obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
- i915_gem_clflush_object(obj);
+ i915_gem_clflush_object(obj, obj->pin_display);
i915_gem_chipset_flush(dev);
}
}
args->size))
return -EFAULT;
- ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
- args->size);
- if (ret)
- return -EFAULT;
+ if (likely(!i915_prefault_disable)) {
+ ret = fault_in_multipages_readable(to_user_ptr(args->data_ptr),
+ args->size);
+ if (ret)
+ return -EFAULT;
+ }
ret = i915_mutex_lock_interruptible(dev);
if (ret)
goto out;
}
- if (obj->cache_level == I915_CACHE_NONE &&
- obj->tiling_mode == I915_TILING_NONE &&
- obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+ if (obj->tiling_mode == I915_TILING_NONE &&
+ obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
+ cpu_write_needs_clflush(obj)) {
ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);
/* Note that the gtt paths might fail with non-page-backed user
* pointers (e.g. gtt mappings when moving data between
}
/* Pinned buffers may be scanout, so flush the cache */
- if (obj->pin_count)
- i915_gem_object_flush_cpu_write_domain(obj);
+ if (obj->pin_display)
+ i915_gem_object_flush_cpu_write_domain(obj, true);
drm_gem_object_unreference(&obj->base);
unlock:
}
/* Now bind it into the GTT if needed */
- ret = i915_gem_object_pin(obj, 0, true, false);
+ ret = i915_gem_obj_ggtt_pin(obj, 0, true, false);
if (ret)
goto unlock;
* hope for the best.
*/
WARN_ON(ret != -EIO);
- i915_gem_clflush_object(obj);
+ i915_gem_clflush_object(obj, true);
obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
}
if (obj->pages == NULL)
return 0;
- BUG_ON(i915_gem_obj_ggtt_bound(obj));
-
if (obj->pages_pin_count)
return -EBUSY;
+ BUG_ON(i915_gem_obj_bound_any(obj));
+
/* ->put_pages might need to allocate memory for the bit17 swizzle
* array, hence protect them from being reaped by removing them from gtt
* lists early. */
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,
}
}
- 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) {
+ list_for_each_entry_safe(obj, next, &dev_priv->mm.bound_list,
+ global_list) {
+ struct i915_vma *vma, *v;
+
+ if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+ continue;
+
+ list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
+ if (i915_vma_unbind(vma))
+ break;
+
+ if (!i915_gem_object_put_pages(obj)) {
count += obj->base.size >> PAGE_SHIFT;
if (count >= target)
return count;
{
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);
+ if (obj->ring != ring && obj->last_write_seqno) {
+ /* Keep the seqno relative to the current ring */
+ obj->last_write_seqno = seqno;
+ }
obj->ring = ring;
/* Add a reference if we're newly entering the active list. */
obj->active = 1;
}
- /* Move from whatever list we were on to the tail of execution. */
- list_move_tail(&obj->mm_list, &vm->active_list);
list_move_tail(&obj->ring_list, &ring->active_list);
obj->last_read_seqno = seqno;
static void
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;
+ struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+ struct i915_address_space *ggtt_vm = &dev_priv->gtt.base;
+ struct i915_vma *vma = i915_gem_obj_to_vma(obj, ggtt_vm);
BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS);
BUG_ON(!obj->active);
- list_move_tail(&obj->mm_list, &vm->inactive_list);
+ list_move_tail(&vma->mm_list, &ggtt_vm->inactive_list);
list_del_init(&obj->ring_list);
obj->ring = NULL;
spin_unlock(&file_priv->mm.lock);
}
-static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj)
+static bool i915_head_inside_object(u32 acthd, struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm)
{
- if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
- acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
+ if (acthd >= i915_gem_obj_offset(obj, vm) &&
+ acthd < i915_gem_obj_offset(obj, vm) + obj->base.size)
return true;
return false;
return false;
}
+static struct i915_address_space *
+request_to_vm(struct drm_i915_gem_request *request)
+{
+ struct drm_i915_private *dev_priv = request->ring->dev->dev_private;
+ struct i915_address_space *vm;
+
+ vm = &dev_priv->gtt.base;
+
+ return vm;
+}
+
static bool i915_request_guilty(struct drm_i915_gem_request *request,
const u32 acthd, bool *inside)
{
* pointing inside the ring, matches the batch_obj address range.
* However this is extremely unlikely.
*/
-
if (request->batch_obj) {
- if (i915_head_inside_object(acthd, request->batch_obj)) {
+ if (i915_head_inside_object(acthd, request->batch_obj,
+ request_to_vm(request))) {
*inside = true;
return true;
}
{
struct i915_ctx_hang_stats *hs = NULL;
bool inside, guilty;
+ unsigned long offset = 0;
/* Innocent until proven guilty */
guilty = false;
+ if (request->batch_obj)
+ offset = i915_gem_obj_offset(request->batch_obj,
+ request_to_vm(request));
+
if (ring->hangcheck.action != wait &&
i915_request_guilty(request, acthd, &inside)) {
DRM_ERROR("%s hung %s bo (0x%lx ctx %d) at 0x%x\n",
ring->name,
inside ? "inside" : "flushing",
- request->batch_obj ?
- i915_gem_obj_ggtt_offset(request->batch_obj) : 0,
+ offset,
request->ctx ? request->ctx->id : 0,
acthd);
}
}
-static void i915_gem_reset_fences(struct drm_device *dev)
+void i915_gem_restore_fences(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int i;
for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
- if (reg->obj)
- i915_gem_object_fence_lost(reg->obj);
-
- i915_gem_write_fence(dev, i, NULL);
-
- reg->pin_count = 0;
- reg->obj = NULL;
- INIT_LIST_HEAD(®->lru_list);
+ /*
+ * Commit delayed tiling changes if we have an object still
+ * attached to the fence, otherwise just clear the fence.
+ */
+ if (reg->obj) {
+ i915_gem_object_update_fence(reg->obj, reg,
+ reg->obj->tiling_mode);
+ } else {
+ i915_gem_write_fence(dev, i, NULL);
+ }
}
-
- INIT_LIST_HEAD(&dev_priv->mm.fence_list);
}
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;
for_each_ring(ring, dev_priv, i)
i915_gem_reset_ring_lists(dev_priv, ring);
- /* Move everything out of the GPU domains to ensure we do any
- * necessary invalidation upon reuse.
- */
- list_for_each_entry(obj, &vm->inactive_list, mm_list)
- obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
-
- /* The fence registers are invalidated so clear them out */
- i915_gem_reset_fences(dev);
+ i915_gem_restore_fences(dev);
}
/**
old_write_domain);
}
-/**
- * Unbinds an object from the GTT aperture.
- */
-int
-i915_gem_object_unbind(struct drm_i915_gem_object *obj)
+int i915_vma_unbind(struct i915_vma *vma)
{
+ struct drm_i915_gem_object *obj = vma->obj;
drm_i915_private_t *dev_priv = obj->base.dev->dev_private;
int ret;
- if (!i915_gem_obj_ggtt_bound(obj))
+ if (list_empty(&vma->vma_link))
return 0;
if (obj->pin_count)
if (ret)
return ret;
- trace_i915_gem_object_unbind(obj);
+ trace_i915_vma_unbind(vma);
if (obj->has_global_gtt_mapping)
i915_gem_gtt_unbind_object(obj);
i915_gem_gtt_finish_object(obj);
i915_gem_object_unpin_pages(obj);
- list_del(&obj->mm_list);
- list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
+ list_del(&vma->mm_list);
/* Avoid an unnecessary call to unbind on rebind. */
- obj->map_and_fenceable = true;
+ if (i915_is_ggtt(vma->vm))
+ obj->map_and_fenceable = true;
- drm_mm_remove_node(&obj->gtt_space);
+ drm_mm_remove_node(&vma->node);
+ i915_gem_vma_destroy(vma);
+
+ /* Since the unbound list is global, only move to that list if
+ * no more VMAs exist.
+ * NB: Until we have real VMAs there will only ever be one */
+ WARN_ON(!list_empty(&obj->vma_list));
+ if (list_empty(&obj->vma_list))
+ list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
return 0;
}
+/**
+ * Unbinds an object from the global GTT aperture.
+ */
+int
+i915_gem_object_ggtt_unbind(struct drm_i915_gem_object *obj)
+{
+ struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+ struct i915_address_space *ggtt = &dev_priv->gtt.base;
+
+ if (!i915_gem_obj_ggtt_bound(obj))
+ return 0;
+
+ if (obj->pin_count)
+ return -EBUSY;
+
+ BUG_ON(obj->pages == NULL);
+
+ return i915_vma_unbind(i915_gem_obj_to_vma(obj, ggtt));
+}
+
int i915_gpu_idle(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
drm_i915_private_t *dev_priv = dev->dev_private;
int fence_reg;
int fence_pitch_shift;
- uint64_t val;
if (INTEL_INFO(dev)->gen >= 6) {
fence_reg = FENCE_REG_SANDYBRIDGE_0;
fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
}
+ fence_reg += reg * 8;
+
+ /* To w/a incoherency with non-atomic 64-bit register updates,
+ * we split the 64-bit update into two 32-bit writes. In order
+ * for a partial fence not to be evaluated between writes, we
+ * precede the update with write to turn off the fence register,
+ * and only enable the fence as the last step.
+ *
+ * For extra levels of paranoia, we make sure each step lands
+ * before applying the next step.
+ */
+ I915_WRITE(fence_reg, 0);
+ POSTING_READ(fence_reg);
+
if (obj) {
u32 size = i915_gem_obj_ggtt_size(obj);
+ uint64_t val;
val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
0xfffff000) << 32;
if (obj->tiling_mode == I915_TILING_Y)
val |= 1 << I965_FENCE_TILING_Y_SHIFT;
val |= I965_FENCE_REG_VALID;
- } else
- val = 0;
- fence_reg += reg * 8;
- I915_WRITE64(fence_reg, val);
- POSTING_READ(fence_reg);
+ I915_WRITE(fence_reg + 4, val >> 32);
+ POSTING_READ(fence_reg + 4);
+
+ I915_WRITE(fence_reg + 0, val);
+ POSTING_READ(fence_reg);
+ } else {
+ I915_WRITE(fence_reg + 4, 0);
+ POSTING_READ(fence_reg + 4);
+ }
}
static void i915_write_fence_reg(struct drm_device *dev, int reg,
if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj))
mb();
+ WARN(obj && (!obj->stride || !obj->tiling_mode),
+ "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
+ obj->stride, obj->tiling_mode);
+
switch (INTEL_INFO(dev)->gen) {
case 7:
case 6:
return fence - dev_priv->fence_regs;
}
-struct write_fence {
- struct drm_device *dev;
- struct drm_i915_gem_object *obj;
- int fence;
-};
-
-static void i915_gem_write_fence__ipi(void *data)
-{
- struct write_fence *args = data;
-
- /* Required for SNB+ with LLC */
- wbinvd();
-
- /* Required for VLV */
- i915_gem_write_fence(args->dev, args->fence, args->obj);
-}
-
static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
struct drm_i915_fence_reg *fence,
bool enable)
{
struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
- struct write_fence args = {
- .dev = obj->base.dev,
- .fence = fence_number(dev_priv, fence),
- .obj = enable ? obj : NULL,
- };
-
- /* In order to fully serialize access to the fenced region and
- * the update to the fence register we need to take extreme
- * measures on SNB+. In theory, the write to the fence register
- * flushes all memory transactions before, and coupled with the
- * mb() placed around the register write we serialise all memory
- * operations with respect to the changes in the tiler. Yet, on
- * SNB+ we need to take a step further and emit an explicit wbinvd()
- * on each processor in order to manually flush all memory
- * transactions before updating the fence register.
- *
- * However, Valleyview complicates matter. There the wbinvd is
- * insufficient and unlike SNB/IVB requires the serialising
- * register write. (Note that that register write by itself is
- * conversely not sufficient for SNB+.) To compromise, we do both.
- */
- if (INTEL_INFO(args.dev)->gen >= 6)
- on_each_cpu(i915_gem_write_fence__ipi, &args, 1);
- else
- i915_gem_write_fence(args.dev, args.fence, args.obj);
+ int reg = fence_number(dev_priv, fence);
+
+ i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);
if (enable) {
- obj->fence_reg = args.fence;
+ obj->fence_reg = reg;
fence->obj = obj;
list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
} else {
fence->obj = NULL;
list_del_init(&fence->lru_list);
}
+ obj->fence_dirty = false;
}
static int
return 0;
i915_gem_object_update_fence(obj, reg, enable);
- obj->fence_dirty = false;
return 0;
}
* Finds free space in the GTT aperture and binds the object there.
*/
static int
-i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
- unsigned alignment,
- bool map_and_fenceable,
- bool nonblocking)
+i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm,
+ unsigned alignment,
+ bool map_and_fenceable,
+ bool nonblocking)
{
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 ?
- dev_priv->gtt.mappable_end : dev_priv->gtt.base.total;
+ size_t gtt_max =
+ map_and_fenceable ? dev_priv->gtt.mappable_end : vm->total;
+ struct i915_vma *vma;
int ret;
+ if (WARN_ON(!list_empty(&obj->vma_list)))
+ return -EBUSY;
+
fence_size = i915_gem_get_gtt_size(dev,
obj->base.size,
obj->tiling_mode);
i915_gem_object_pin_pages(obj);
+ /* FIXME: For now we only ever use 1 VMA per object */
+ BUG_ON(!i915_is_ggtt(vm));
+ WARN_ON(!list_empty(&obj->vma_list));
+
+ vma = i915_gem_vma_create(obj, vm);
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto err_unpin;
+ }
+
search_free:
- ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm,
- &obj->gtt_space,
+ ret = drm_mm_insert_node_in_range_generic(&vm->mm, &vma->node,
size, alignment,
obj->cache_level, 0, gtt_max);
if (ret) {
- ret = i915_gem_evict_something(dev, size, alignment,
+ ret = i915_gem_evict_something(dev, vm, size, alignment,
obj->cache_level,
map_and_fenceable,
nonblocking);
if (ret == 0)
goto search_free;
- i915_gem_object_unpin_pages(obj);
- return ret;
+ goto err_free_vma;
}
- if (WARN_ON(!i915_gem_valid_gtt_space(dev, &obj->gtt_space,
+ if (WARN_ON(!i915_gem_valid_gtt_space(dev, &vma->node,
obj->cache_level))) {
- i915_gem_object_unpin_pages(obj);
- drm_mm_remove_node(&obj->gtt_space);
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_remove_node;
}
ret = i915_gem_gtt_prepare_object(obj);
- if (ret) {
- i915_gem_object_unpin_pages(obj);
- drm_mm_remove_node(&obj->gtt_space);
- return ret;
- }
+ if (ret)
+ goto err_remove_node;
list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
- list_add_tail(&obj->mm_list, &vm->inactive_list);
+ list_add_tail(&vma->mm_list, &vm->inactive_list);
fenceable =
+ i915_is_ggtt(vm) &&
i915_gem_obj_ggtt_size(obj) == fence_size &&
(i915_gem_obj_ggtt_offset(obj) & (fence_alignment - 1)) == 0;
- mappable = i915_gem_obj_ggtt_offset(obj) + obj->base.size <=
- dev_priv->gtt.mappable_end;
+ mappable =
+ i915_is_ggtt(vm) &&
+ vma->node.start + obj->base.size <= dev_priv->gtt.mappable_end;
- obj->map_and_fenceable = mappable && fenceable;
+ /* Map and fenceable only changes if the VM is the global GGTT */
+ if (i915_is_ggtt(vm))
+ obj->map_and_fenceable = mappable && fenceable;
- trace_i915_gem_object_bind(obj, map_and_fenceable);
+ trace_i915_vma_bind(vma, map_and_fenceable);
i915_gem_verify_gtt(dev);
return 0;
+
+err_remove_node:
+ drm_mm_remove_node(&vma->node);
+err_free_vma:
+ i915_gem_vma_destroy(vma);
+err_unpin:
+ i915_gem_object_unpin_pages(obj);
+ return ret;
}
void
-i915_gem_clflush_object(struct drm_i915_gem_object *obj)
+i915_gem_clflush_object(struct drm_i915_gem_object *obj,
+ bool force)
{
/* If we don't have a page list set up, then we're not pinned
* to GPU, and we can ignore the cache flush because it'll happen
* snooping behaviour occurs naturally as the result of our domain
* tracking.
*/
- if (obj->cache_level != I915_CACHE_NONE)
+ if (!force && cpu_cache_is_coherent(obj->base.dev, obj->cache_level))
return;
trace_i915_gem_object_clflush(obj);
/** Flushes the CPU write domain for the object if it's dirty. */
static void
-i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj)
+i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
+ bool force)
{
uint32_t old_write_domain;
if (obj->base.write_domain != I915_GEM_DOMAIN_CPU)
return;
- i915_gem_clflush_object(obj);
+ i915_gem_clflush_object(obj, force);
i915_gem_chipset_flush(obj->base.dev);
old_write_domain = obj->base.write_domain;
obj->base.write_domain = 0;
int ret;
/* Not valid to be called on unbound objects. */
- if (!i915_gem_obj_ggtt_bound(obj))
+ if (!i915_gem_obj_bound_any(obj))
return -EINVAL;
if (obj->base.write_domain == I915_GEM_DOMAIN_GTT)
if (ret)
return ret;
- i915_gem_object_flush_cpu_write_domain(obj);
+ i915_gem_object_flush_cpu_write_domain(obj, false);
/* Serialise direct access to this object with the barriers for
* coherent writes from the GPU, by effectively invalidating the
old_write_domain);
/* And bump the LRU for this access */
- if (i915_gem_object_is_inactive(obj))
- list_move_tail(&obj->mm_list,
- &dev_priv->gtt.base.inactive_list);
+ if (i915_gem_object_is_inactive(obj)) {
+ struct i915_vma *vma = i915_gem_obj_to_vma(obj,
+ &dev_priv->gtt.base);
+ if (vma)
+ list_move_tail(&vma->mm_list,
+ &dev_priv->gtt.base.inactive_list);
+
+ }
return 0;
}
{
struct drm_device *dev = obj->base.dev;
drm_i915_private_t *dev_priv = dev->dev_private;
+ struct i915_vma *vma;
int ret;
if (obj->cache_level == cache_level)
return -EBUSY;
}
- if (!i915_gem_valid_gtt_space(dev, &obj->gtt_space, cache_level)) {
- ret = i915_gem_object_unbind(obj);
- if (ret)
- return ret;
+ list_for_each_entry(vma, &obj->vma_list, vma_link) {
+ if (!i915_gem_valid_gtt_space(dev, &vma->node, cache_level)) {
+ ret = i915_vma_unbind(vma);
+ if (ret)
+ return ret;
+
+ break;
+ }
}
- if (i915_gem_obj_ggtt_bound(obj)) {
+ if (i915_gem_obj_bound_any(obj)) {
ret = i915_gem_object_finish_gpu(obj);
if (ret)
return ret;
if (obj->has_aliasing_ppgtt_mapping)
i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt,
obj, cache_level);
-
- i915_gem_obj_ggtt_set_color(obj, cache_level);
}
- if (cache_level == I915_CACHE_NONE) {
+ list_for_each_entry(vma, &obj->vma_list, vma_link)
+ vma->node.color = cache_level;
+ obj->cache_level = cache_level;
+
+ if (cpu_write_needs_clflush(obj)) {
u32 old_read_domains, old_write_domain;
/* If we're coming from LLC cached, then we haven't
old_write_domain);
}
- obj->cache_level = cache_level;
i915_gem_verify_gtt(dev);
return 0;
}
return ret;
}
+static bool is_pin_display(struct drm_i915_gem_object *obj)
+{
+ /* There are 3 sources that pin objects:
+ * 1. The display engine (scanouts, sprites, cursors);
+ * 2. Reservations for execbuffer;
+ * 3. The user.
+ *
+ * We can ignore reservations as we hold the struct_mutex and
+ * are only called outside of the reservation path. The user
+ * can only increment pin_count once, and so if after
+ * subtracting the potential reference by the user, any pin_count
+ * remains, it must be due to another use by the display engine.
+ */
+ return obj->pin_count - !!obj->user_pin_count;
+}
+
/*
* Prepare buffer for display plane (scanout, cursors, etc).
* Can be called from an uninterruptible phase (modesetting) and allows
return ret;
}
+ /* Mark the pin_display early so that we account for the
+ * display coherency whilst setting up the cache domains.
+ */
+ obj->pin_display = true;
+
/* The display engine is not coherent with the LLC cache on gen6. As
* a result, we make sure that the pinning that is about to occur is
* done with uncached PTEs. This is lowest common denominator for all
*/
ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
if (ret)
- return ret;
+ goto err_unpin_display;
/* As the user may map the buffer once pinned in the display plane
* (e.g. libkms for the bootup splash), we have to ensure that we
* always use map_and_fenceable for all scanout buffers.
*/
- ret = i915_gem_object_pin(obj, alignment, true, false);
+ ret = i915_gem_obj_ggtt_pin(obj, alignment, true, false);
if (ret)
- return ret;
+ goto err_unpin_display;
- i915_gem_object_flush_cpu_write_domain(obj);
+ i915_gem_object_flush_cpu_write_domain(obj, true);
old_write_domain = obj->base.write_domain;
old_read_domains = obj->base.read_domains;
old_write_domain);
return 0;
+
+err_unpin_display:
+ obj->pin_display = is_pin_display(obj);
+ return ret;
+}
+
+void
+i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj)
+{
+ i915_gem_object_unpin(obj);
+ obj->pin_display = is_pin_display(obj);
}
int
/* Flush the CPU cache if it's still invalid. */
if ((obj->base.read_domains & I915_GEM_DOMAIN_CPU) == 0) {
- i915_gem_clflush_object(obj);
+ i915_gem_clflush_object(obj, false);
obj->base.read_domains |= I915_GEM_DOMAIN_CPU;
}
int
i915_gem_object_pin(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm,
uint32_t alignment,
bool map_and_fenceable,
bool nonblocking)
{
+ struct i915_vma *vma;
int ret;
if (WARN_ON(obj->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
return -EBUSY;
- if (i915_gem_obj_ggtt_bound(obj)) {
- if ((alignment && i915_gem_obj_ggtt_offset(obj) & (alignment - 1)) ||
+ WARN_ON(map_and_fenceable && !i915_is_ggtt(vm));
+
+ vma = i915_gem_obj_to_vma(obj, vm);
+
+ if (vma) {
+ if ((alignment &&
+ vma->node.start & (alignment - 1)) ||
(map_and_fenceable && !obj->map_and_fenceable)) {
WARN(obj->pin_count,
"bo is already pinned with incorrect alignment:"
" offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
" obj->map_and_fenceable=%d\n",
- i915_gem_obj_ggtt_offset(obj), alignment,
+ i915_gem_obj_offset(obj, vm), alignment,
map_and_fenceable,
obj->map_and_fenceable);
- ret = i915_gem_object_unbind(obj);
+ ret = i915_vma_unbind(vma);
if (ret)
return ret;
}
}
- if (!i915_gem_obj_ggtt_bound(obj)) {
+ if (!i915_gem_obj_bound(obj, vm)) {
struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
- ret = i915_gem_object_bind_to_gtt(obj, alignment,
- map_and_fenceable,
- nonblocking);
+ ret = i915_gem_object_bind_to_vm(obj, vm, alignment,
+ map_and_fenceable,
+ nonblocking);
if (ret)
return ret;
i915_gem_object_unpin(struct drm_i915_gem_object *obj)
{
BUG_ON(obj->pin_count == 0);
- BUG_ON(!i915_gem_obj_ggtt_bound(obj));
+ BUG_ON(!i915_gem_obj_bound_any(obj));
if (--obj->pin_count == 0)
obj->pin_mappable = false;
}
if (obj->user_pin_count == 0) {
- ret = i915_gem_object_pin(obj, args->alignment, true, false);
+ ret = i915_gem_obj_ggtt_pin(obj, args->alignment, true, false);
if (ret)
goto out;
}
obj->user_pin_count++;
obj->pin_filp = file;
- /* XXX - flush the CPU caches for pinned objects
- * as the X server doesn't manage domains yet
- */
- i915_gem_object_flush_cpu_write_domain(obj);
args->offset = i915_gem_obj_ggtt_offset(obj);
out:
drm_gem_object_unreference(&obj->base);
void i915_gem_object_init(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_object_ops *ops)
{
- INIT_LIST_HEAD(&obj->mm_list);
INIT_LIST_HEAD(&obj->global_list);
INIT_LIST_HEAD(&obj->ring_list);
INIT_LIST_HEAD(&obj->exec_list);
+ INIT_LIST_HEAD(&obj->vma_list);
obj->ops = ops;
} else
obj->cache_level = I915_CACHE_NONE;
+ trace_i915_gem_object_create(obj);
+
return obj;
}
struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
struct drm_device *dev = obj->base.dev;
drm_i915_private_t *dev_priv = dev->dev_private;
+ struct i915_vma *vma, *next;
trace_i915_gem_object_destroy(obj);
i915_gem_detach_phys_object(dev, obj);
obj->pin_count = 0;
- if (WARN_ON(i915_gem_object_unbind(obj) == -ERESTARTSYS)) {
- bool was_interruptible;
+ /* NB: 0 or 1 elements */
+ WARN_ON(!list_empty(&obj->vma_list) &&
+ !list_is_singular(&obj->vma_list));
+ list_for_each_entry_safe(vma, next, &obj->vma_list, vma_link) {
+ int ret = i915_vma_unbind(vma);
+ if (WARN_ON(ret == -ERESTARTSYS)) {
+ bool was_interruptible;
- was_interruptible = dev_priv->mm.interruptible;
- dev_priv->mm.interruptible = false;
+ was_interruptible = dev_priv->mm.interruptible;
+ dev_priv->mm.interruptible = false;
- WARN_ON(i915_gem_object_unbind(obj));
+ WARN_ON(i915_vma_unbind(vma));
- dev_priv->mm.interruptible = was_interruptible;
+ dev_priv->mm.interruptible = was_interruptible;
+ }
}
/* Stolen objects don't hold a ref, but do hold pin count. Fix that up
i915_gem_object_free(obj);
}
+struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm)
+{
+ struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL);
+ if (vma == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&vma->vma_link);
+ INIT_LIST_HEAD(&vma->mm_list);
+ vma->vm = vm;
+ vma->obj = obj;
+
+ /* Keep GGTT vmas first to make debug easier */
+ if (i915_is_ggtt(vm))
+ list_add(&vma->vma_link, &obj->vma_list);
+ else
+ list_add_tail(&vma->vma_link, &obj->vma_list);
+
+ return vma;
+}
+
+void i915_gem_vma_destroy(struct i915_vma *vma)
+{
+ WARN_ON(vma->node.allocated);
+ list_del(&vma->vma_link);
+ kfree(vma);
+}
+
int
i915_gem_idle(struct drm_device *dev)
{
if (!drm_core_check_feature(dev, DRIVER_MODESET))
i915_gem_evict_everything(dev);
- i915_gem_reset_fences(dev);
-
del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
i915_kernel_lost_context(dev);
INIT_LIST_HEAD(&ring->request_list);
}
+static void i915_init_vm(struct drm_i915_private *dev_priv,
+ struct i915_address_space *vm)
+{
+ vm->dev = dev_priv->dev;
+ INIT_LIST_HEAD(&vm->active_list);
+ INIT_LIST_HEAD(&vm->inactive_list);
+ INIT_LIST_HEAD(&vm->global_link);
+ list_add(&vm->global_link, &dev_priv->vm_list);
+}
+
void
i915_gem_load(struct drm_device *dev)
{
SLAB_HWCACHE_ALIGN,
NULL);
- INIT_LIST_HEAD(&dev_priv->gtt.base.active_list);
- INIT_LIST_HEAD(&dev_priv->gtt.base.inactive_list);
+ INIT_LIST_HEAD(&dev_priv->vm_list);
+ i915_init_vm(dev_priv, &dev_priv->gtt.base);
+
INIT_LIST_HEAD(&dev_priv->mm.unbound_list);
INIT_LIST_HEAD(&dev_priv->mm.bound_list);
INIT_LIST_HEAD(&dev_priv->mm.fence_list);
dev_priv->num_fence_regs = 8;
/* Initialize fence registers to zero */
- i915_gem_reset_fences(dev);
+ INIT_LIST_HEAD(&dev_priv->mm.fence_list);
+ i915_gem_restore_fences(dev);
i915_gem_detect_bit_6_swizzle(dev);
init_waitqueue_head(&dev_priv->pending_flip_queue);
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;
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, &vm->inactive_list, global_list)
+
+ list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+ if (obj->active)
+ continue;
+
if (obj->pin_count == 0 && obj->pages_pin_count == 0)
cnt += obj->base.size >> PAGE_SHIFT;
+ }
if (unlock)
mutex_unlock(&dev->struct_mutex);
return cnt;
}
+
+/* All the new VM stuff */
+unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
+ struct i915_address_space *vm)
+{
+ struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+ struct i915_vma *vma;
+
+ if (vm == &dev_priv->mm.aliasing_ppgtt->base)
+ vm = &dev_priv->gtt.base;
+
+ BUG_ON(list_empty(&o->vma_list));
+ list_for_each_entry(vma, &o->vma_list, vma_link) {
+ if (vma->vm == vm)
+ return vma->node.start;
+
+ }
+ return -1;
+}
+
+bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
+ struct i915_address_space *vm)
+{
+ struct i915_vma *vma;
+
+ list_for_each_entry(vma, &o->vma_list, vma_link)
+ if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
+ return true;
+
+ return false;
+}
+
+bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o)
+{
+ struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+ struct i915_address_space *vm;
+
+ list_for_each_entry(vm, &dev_priv->vm_list, global_link)
+ if (i915_gem_obj_bound(o, vm))
+ return true;
+
+ return false;
+}
+
+unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
+ struct i915_address_space *vm)
+{
+ struct drm_i915_private *dev_priv = o->base.dev->dev_private;
+ struct i915_vma *vma;
+
+ if (vm == &dev_priv->mm.aliasing_ppgtt->base)
+ vm = &dev_priv->gtt.base;
+
+ BUG_ON(list_empty(&o->vma_list));
+
+ list_for_each_entry(vma, &o->vma_list, vma_link)
+ if (vma->vm == vm)
+ return vma->node.size;
+
+ return 0;
+}
+
+struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+ struct i915_address_space *vm)
+{
+ struct i915_vma *vma;
+ list_for_each_entry(vma, &obj->vma_list, vma_link)
+ if (vma->vm == vm)
+ return vma;
+
+ return NULL;
+}