There are some allocations that must be only referenced by 32bit
offsets. To limit the chances of having the first 4GB already full,
objects not requiring this workaround use DRM_MM_SEARCH_BELOW/
DRM_MM_CREATE_TOP flags
User must pass I915_EXEC_SUPPORTS_48BADDRESS flag to indicate it can
be allocated above the 32b address range.
The flag is ignored in 32b PPGTT.
v2: Changed flag logic from neeeds_32b, to supports_48b.
Signed-off-by: Michel Thierry <michel.thierry@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_drv.h | 1 +
drivers/gpu/drm/i915/i915_gem.c | 19 ++++++++++++++--
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 36 +++++++++++++++++++++---------
include/uapi/drm/i915_drm.h | 4 +++-
4 files changed, 47 insertions(+), 13 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 95f59d3..d73dddb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2714,6 +2714,7 @@ void i915_gem_vma_destroy(struct i915_vma *vma);
#define PIN_OFFSET_BIAS (1<<3)
#define PIN_USER (1<<4)
#define PIN_UPDATE (1<<5)
+#define PIN_FULL_RANGE (1<<6)
#define PIN_OFFSET_MASK (~4095)
int __must_check
i915_gem_object_pin(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 35690ef..e6325a4a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3672,6 +3672,8 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
struct drm_i915_private *dev_priv = dev->dev_private;
u32 fence_alignment, unfenced_alignment;
u64 size, fence_size;
+ u32 search_flag = DRM_MM_SEARCH_DEFAULT;
+ u32 alloc_flag = DRM_MM_CREATE_DEFAULT;
u64 start =
flags & PIN_OFFSET_BIAS ? flags & PIN_OFFSET_MASK : 0;
u64 end =
@@ -3713,6 +3715,19 @@ i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
obj->tiling_mode,
false);
size = flags & PIN_MAPPABLE ? fence_size : obj->base.size;
+
+ /* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
+ * limit address to 4GB-1 for objects requiring this wa; for
+ * others, set alloc flag to TOP.
+ */
+ if (USES_FULL_48BIT_PPGTT(dev)) {
+ if (flags & PIN_FULL_RANGE) {
+ search_flag = DRM_MM_SEARCH_BELOW;
+ alloc_flag = DRM_MM_CREATE_TOP;
+ } else {
+ end = ((4ULL << GEN8_PDPE_SHIFT) - 1);
+ }
+ }
}
if (alignment == 0)
@@ -3755,8 +3770,8 @@ search_free:
size, alignment,
obj->cache_level,
start, end,
- DRM_MM_SEARCH_DEFAULT,
- DRM_MM_CREATE_DEFAULT);
+ search_flag,
+ alloc_flag);
if (ret) {
ret = i915_gem_evict_something(dev, vm, size, alignment,
obj->cache_level,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index bd0e4bd..04af62b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -577,7 +577,8 @@ static bool only_mappable_for_reloc(unsigned int flags)
static int
i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
struct intel_engine_cs *ring,
- bool *need_reloc)
+ bool *need_reloc,
+ bool support_48baddr)
{
struct drm_i915_gem_object *obj = vma->obj;
struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
@@ -588,6 +589,9 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
flags |= PIN_GLOBAL;
+ if (support_48baddr)
+ flags |= PIN_FULL_RANGE;
+
if (!drm_mm_node_allocated(&vma->node)) {
if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
flags |= PIN_GLOBAL | PIN_MAPPABLE;
@@ -650,7 +654,7 @@ need_reloc_mappable(struct i915_vma *vma)
}
static bool
-eb_vma_misplaced(struct i915_vma *vma)
+eb_vma_misplaced(struct i915_vma *vma, bool support_48baddr)
{
struct drm_i915_gem_exec_object2 *entry = vma->exec_entry;
struct drm_i915_gem_object *obj = vma->obj;
@@ -670,13 +674,18 @@ eb_vma_misplaced(struct i915_vma *vma)
if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
return !only_mappable_for_reloc(entry->flags);
+ if (!support_48baddr &&
+ vma->node.start >= (1ULL << 32))
+ return true;
+
return false;
}
static int
i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
struct list_head *vmas,
- bool *need_relocs)
+ bool *need_relocs,
+ bool support_48baddr)
{
struct drm_i915_gem_object *obj;
struct i915_vma *vma;
@@ -737,10 +746,11 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
if (!drm_mm_node_allocated(&vma->node))
continue;
- if (eb_vma_misplaced(vma))
+ if (eb_vma_misplaced(vma, support_48baddr))
ret = i915_vma_unbind(vma);
else
- ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
+ ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs,
+ support_48baddr);
if (ret)
goto err;
}
@@ -750,7 +760,9 @@ i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
if (drm_mm_node_allocated(&vma->node))
continue;
- ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs);
+ ret = i915_gem_execbuffer_reserve_vma(vma, ring,
+ need_relocs,
+ support_48baddr);
if (ret)
goto err;
}
@@ -780,7 +792,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
struct drm_i915_gem_relocation_entry *reloc;
struct i915_address_space *vm;
struct i915_vma *vma;
- bool need_relocs;
+ bool need_relocs, support_48baddr;
int *reloc_offset;
int i, total, ret;
unsigned count = args->buffer_count;
@@ -861,7 +873,9 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
goto err;
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+ support_48baddr = (args->flags & I915_EXEC_SUPPORT_48BADDRESS);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs,
+ support_48baddr);
if (ret)
goto err;
@@ -1411,7 +1425,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
u64 exec_start = args->batch_start_offset;
u32 dispatch_flags;
int ret;
- bool need_relocs;
+ bool need_relocs, support_48baddr;
if (!i915_gem_check_execbuffer(args))
return -EINVAL;
@@ -1519,7 +1533,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
/* Move the objects en-masse into the GTT, evicting if necessary. */
need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0;
- ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs);
+ support_48baddr = (args->flags & I915_EXEC_SUPPORT_48BADDRESS);
+ ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs,
+ support_48baddr);
if (ret)
goto err;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 4851d66..18df34a 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -760,7 +760,9 @@ struct drm_i915_gem_execbuffer2 {
#define I915_EXEC_BSD_RING1 (1<<13)
#define I915_EXEC_BSD_RING2 (2<<13)
-#define __I915_EXEC_UNKNOWN_FLAGS -(1<<15)
+#define I915_EXEC_SUPPORT_48BADDRESS (1<<15)
+
+#define __I915_EXEC_UNKNOWN_FLAGS -(1<<16)
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
--
2.4.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
