[Intel-gfx] [PATCH] drm/i915: Move flags describing VMA mappings into the VMA
Tvrtko Ursulin
tvrtko.ursulin at linux.intel.com
Fri Oct 24 13:42:33 CEST 2014
From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
If these flags are on the object level it will be more difficult to allow
for multiple VMAs per object.
v2: Simplification and cleanup after code review comments (Chris Wilson).
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_debugfs.c | 2 +-
drivers/gpu/drm/i915/i915_drv.h | 2 --
drivers/gpu/drm/i915/i915_gem.c | 4 ++--
drivers/gpu/drm/i915/i915_gem_context.c | 10 +++++-----
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +++------
drivers/gpu/drm/i915/i915_gem_gtt.c | 24 ++++++++++++------------
drivers/gpu/drm/i915/i915_gem_gtt.h | 8 ++++++--
drivers/gpu/drm/i915/i915_gem_stolen.c | 2 +-
drivers/gpu/drm/i915/i915_gpu_error.c | 10 ++++++----
9 files changed, 36 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d8d08fc..6a15fb6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -118,7 +118,7 @@ static const char *get_tiling_flag(struct drm_i915_gem_object *obj)
static inline const char *get_global_flag(struct drm_i915_gem_object *obj)
{
- return obj->has_global_gtt_mapping ? "g" : " ";
+ return i915_gem_obj_to_ggtt(obj) ? "g" : " ";
}
static void
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ce3f01f..a830b85 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1965,8 +1965,6 @@ struct drm_i915_gem_object {
unsigned long gt_ro:1;
unsigned int cache_level:3;
- unsigned int has_aliasing_ppgtt_mapping:1;
- unsigned int has_global_gtt_mapping:1;
unsigned int has_dma_mapping:1;
unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index edab8f1..255a431 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3700,7 +3700,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
list_for_each_entry(vma, &obj->vma_list, vma_link)
if (drm_mm_node_allocated(&vma->node))
vma->bind_vma(vma, cache_level,
- obj->has_global_gtt_mapping ? GLOBAL_BIND : 0);
+ vma->bound & GLOBAL_BIND);
}
list_for_each_entry(vma, &obj->vma_list, vma_link)
@@ -4096,7 +4096,7 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
return PTR_ERR(vma);
}
- if (flags & PIN_GLOBAL && !obj->has_global_gtt_mapping)
+ if (flags & PIN_GLOBAL && !(vma->bound & GLOBAL_BIND))
vma->bind_vma(vma, obj->cache_level, GLOBAL_BIND);
vma->pin_count++;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index bf41f41..5ff6e94 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -525,6 +525,7 @@ static int do_switch(struct intel_engine_cs *ring,
struct intel_context *from = ring->last_context;
u32 hw_flags = 0;
bool uninitialized = false;
+ struct i915_vma *vma;
int ret, i;
if (from != NULL && ring == &dev_priv->ring[RCS]) {
@@ -574,11 +575,10 @@ static int do_switch(struct intel_engine_cs *ring,
if (ret)
goto unpin_out;
- if (!to->legacy_hw_ctx.rcs_state->has_global_gtt_mapping) {
- struct i915_vma *vma = i915_gem_obj_to_vma(to->legacy_hw_ctx.rcs_state,
- &dev_priv->gtt.base);
- vma->bind_vma(vma, to->legacy_hw_ctx.rcs_state->cache_level, GLOBAL_BIND);
- }
+ vma = i915_gem_obj_to_ggtt(to->legacy_hw_ctx.rcs_state);
+ if (!(vma->bound & GLOBAL_BIND))
+ vma->bind_vma(vma, to->legacy_hw_ctx.rcs_state->cache_level,
+ GLOBAL_BIND);
if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
hw_flags |= MI_RESTORE_INHIBIT;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f8cc935..8d56d5b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -357,12 +357,9 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
* through the ppgtt for non_secure batchbuffers. */
if (unlikely(IS_GEN6(dev) &&
reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
- !target_i915_obj->has_global_gtt_mapping)) {
- struct i915_vma *vma =
- list_first_entry(&target_i915_obj->vma_list,
- typeof(*vma), vma_link);
- vma->bind_vma(vma, target_i915_obj->cache_level, GLOBAL_BIND);
- }
+ !(target_vma->bound & GLOBAL_BIND)))
+ target_vma->bind_vma(target_vma, target_i915_obj->cache_level,
+ GLOBAL_BIND);
/* Validate that the target is in a valid r/w GPU domain */
if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b80ab86..814a805 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1324,7 +1324,7 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
* Unfortunately above, we've just wiped out the mappings
* without telling our object about it. So we need to fake it.
*/
- obj->has_global_gtt_mapping = 0;
+ vma->bound &= ~GLOBAL_BIND;
vma->bind_vma(vma, obj->cache_level, GLOBAL_BIND);
}
@@ -1521,7 +1521,7 @@ static void i915_ggtt_bind_vma(struct i915_vma *vma,
BUG_ON(!i915_is_ggtt(vma->vm));
intel_gtt_insert_sg_entries(vma->obj->pages, entry, flags);
- vma->obj->has_global_gtt_mapping = 1;
+ vma->bound = GLOBAL_BIND;
}
static void i915_ggtt_clear_range(struct i915_address_space *vm,
@@ -1540,7 +1540,7 @@ static void i915_ggtt_unbind_vma(struct i915_vma *vma)
const unsigned int size = vma->obj->base.size >> PAGE_SHIFT;
BUG_ON(!i915_is_ggtt(vma->vm));
- vma->obj->has_global_gtt_mapping = 0;
+ vma->bound = 0;
intel_gtt_clear_range(first, size);
}
@@ -1568,24 +1568,24 @@ static void ggtt_bind_vma(struct i915_vma *vma,
* flags. At all other times, the GPU will use the aliasing PPGTT.
*/
if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
- if (!obj->has_global_gtt_mapping ||
+ if (!(vma->bound & GLOBAL_BIND) ||
(cache_level != obj->cache_level)) {
vma->vm->insert_entries(vma->vm, obj->pages,
vma->node.start,
cache_level, flags);
- obj->has_global_gtt_mapping = 1;
+ vma->bound |= GLOBAL_BIND;
}
}
if (dev_priv->mm.aliasing_ppgtt &&
- (!obj->has_aliasing_ppgtt_mapping ||
+ (!(vma->bound & LOCAL_BIND) ||
(cache_level != obj->cache_level))) {
struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
appgtt->base.insert_entries(&appgtt->base,
vma->obj->pages,
vma->node.start,
cache_level, flags);
- vma->obj->has_aliasing_ppgtt_mapping = 1;
+ vma->bound |= LOCAL_BIND;
}
}
@@ -1595,21 +1595,21 @@ static void ggtt_unbind_vma(struct i915_vma *vma)
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj = vma->obj;
- if (obj->has_global_gtt_mapping) {
+ if (vma->bound & GLOBAL_BIND) {
vma->vm->clear_range(vma->vm,
vma->node.start,
obj->base.size,
true);
- obj->has_global_gtt_mapping = 0;
+ vma->bound &= ~GLOBAL_BIND;
}
- if (obj->has_aliasing_ppgtt_mapping) {
+ if (vma->bound & LOCAL_BIND) {
struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
appgtt->base.clear_range(&appgtt->base,
vma->node.start,
obj->base.size,
true);
- obj->has_aliasing_ppgtt_mapping = 0;
+ vma->bound &= ~LOCAL_BIND;
}
}
@@ -1687,7 +1687,7 @@ int i915_gem_setup_global_gtt(struct drm_device *dev,
DRM_DEBUG_KMS("Reservation failed: %i\n", ret);
return ret;
}
- obj->has_global_gtt_mapping = 1;
+ vma->bound |= GLOBAL_BIND;
}
dev_priv->gtt.base.start = start;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d5c14af..d0562d0 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -123,6 +123,12 @@ struct i915_vma {
struct drm_i915_gem_object *obj;
struct i915_address_space *vm;
+ /** Flags and address space this VMA is bound to */
+#define GLOBAL_BIND (1<<0)
+#define LOCAL_BIND (1<<1)
+#define PTE_READ_ONLY (1<<2)
+ unsigned int bound : 4;
+
/** This object's place on the active/inactive lists */
struct list_head mm_list;
@@ -155,8 +161,6 @@ struct i915_vma {
* setting the valid PTE entries to a reserved scratch page. */
void (*unbind_vma)(struct i915_vma *vma);
/* Map an object into an address space with the given cache flags. */
-#define GLOBAL_BIND (1<<0)
-#define PTE_READ_ONLY (1<<1)
void (*bind_vma)(struct i915_vma *vma,
enum i915_cache_level cache_level,
u32 flags);
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 85fda6b..c388918 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -533,7 +533,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
}
}
- obj->has_global_gtt_mapping = 1;
+ vma->bound |= GLOBAL_BIND;
list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
list_add_tail(&vma->mm_list, &ggtt->inactive_list);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 053d99e..80f0c80 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -567,6 +567,7 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
struct i915_address_space *vm)
{
struct drm_i915_error_object *dst;
+ struct i915_vma *vma = NULL;
int num_pages;
bool use_ggtt;
int i = 0;
@@ -587,16 +588,17 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
dst->gtt_offset = -1;
reloc_offset = dst->gtt_offset;
+ if (i915_is_ggtt(vm))
+ vma = i915_gem_obj_to_ggtt(src);
use_ggtt = (src->cache_level == I915_CACHE_NONE &&
- i915_is_ggtt(vm) &&
- src->has_global_gtt_mapping &&
- reloc_offset + num_pages * PAGE_SIZE <= dev_priv->gtt.mappable_end);
+ vma && (vma->bound & GLOBAL_BIND) &&
+ reloc_offset + num_pages * PAGE_SIZE <= dev_priv->gtt.mappable_end);
/* Cannot access stolen address directly, try to use the aperture */
if (src->stolen) {
use_ggtt = true;
- if (!src->has_global_gtt_mapping)
+ if (!(vma && vma->bound & GLOBAL_BIND))
goto unwind;
reloc_offset = i915_gem_obj_ggtt_offset(src);
--
2.1.1
More information about the Intel-gfx
mailing list