[PATCH 20/44] drm/i915/gem: Move the 'cached' info to i915_execbuffer
Chris Wilson
chris at chris-wilson.co.uk
Fri Jul 31 13:34:16 UTC 2020
The reloc_cache contains some details that are used outside of the
relocation handling, so lift those out of the embeddded struct into the
principle struct i915_execbuffer.
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 61 +++++++++++--------
.../i915/gem/selftests/i915_gem_execbuffer.c | 6 +-
2 files changed, 37 insertions(+), 30 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 87f1d6760ce1..6044aad3fc3c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -253,11 +253,6 @@ struct i915_execbuffer {
*/
struct reloc_cache {
struct drm_mm_node node; /** temporary GTT binding */
- unsigned int gen; /** Cached value of INTEL_GEN */
- bool use_64bit_reloc : 1;
- bool has_llc : 1;
- bool has_fence : 1;
- bool needs_unfenced : 1;
struct intel_context *ce;
@@ -275,6 +270,12 @@ struct i915_execbuffer {
u32 batch_len; /** Length of batch within object */
u32 batch_flags; /** Flags composed for emit_bb_start() */
+ unsigned int gen; /** Cached value of INTEL_GEN */
+ bool use_64bit_reloc : 1;
+ bool has_llc : 1;
+ bool has_fence : 1;
+ bool needs_unfenced : 1;
+
/**
* Indicate either the size of the hastable used to resolve
* relocation handles, or if negative that we are using a direct
@@ -529,11 +530,11 @@ eb_validate_vma(struct i915_execbuffer *eb,
*/
entry->offset = gen8_noncanonical_addr(entry->offset);
- if (!eb->reloc_cache.has_fence) {
+ if (!eb->has_fence) {
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
} else {
if ((entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
- eb->reloc_cache.needs_unfenced) &&
+ eb->needs_unfenced) &&
i915_gem_object_is_tiled(vma->obj))
entry->flags |= EXEC_OBJECT_NEEDS_GTT | __EXEC_OBJECT_NEEDS_MAP;
}
@@ -581,7 +582,7 @@ eb_add_vma(struct i915_execbuffer *eb,
if (entry->relocation_count &&
!(ev->flags & EXEC_OBJECT_PINNED))
ev->flags |= __EXEC_OBJECT_NEEDS_BIAS;
- if (eb->reloc_cache.has_fence)
+ if (eb->has_fence)
ev->flags |= EXEC_OBJECT_NEEDS_FENCE;
eb->batch = ev;
@@ -984,15 +985,19 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
return gen8_canonical_addr((int)reloc->delta + target->node.start);
}
-static void reloc_cache_init(struct reloc_cache *cache,
- struct drm_i915_private *i915)
+static void eb_info_init(struct i915_execbuffer *eb,
+ struct drm_i915_private *i915)
{
/* Must be a variable in the struct to allow GCC to unroll. */
- cache->gen = INTEL_GEN(i915);
- cache->has_llc = HAS_LLC(i915);
- cache->use_64bit_reloc = HAS_64BIT_RELOC(i915);
- cache->has_fence = cache->gen < 4;
- cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
+ eb->gen = INTEL_GEN(i915);
+ eb->has_llc = HAS_LLC(i915);
+ eb->use_64bit_reloc = HAS_64BIT_RELOC(i915);
+ eb->has_fence = eb->gen < 4;
+ eb->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
+}
+
+static void reloc_cache_init(struct reloc_cache *cache)
+{
cache->node.flags = 0;
cache->rq = NULL;
cache->target = NULL;
@@ -1000,8 +1005,9 @@ static void reloc_cache_init(struct reloc_cache *cache,
#define RELOC_TAIL 4
-static int reloc_gpu_chain(struct reloc_cache *cache)
+static int reloc_gpu_chain(struct i915_execbuffer *eb)
{
+ struct reloc_cache *cache = &eb->reloc_cache;
struct intel_gt_buffer_pool_node *pool;
struct i915_request *rq = cache->rq;
struct i915_vma *batch;
@@ -1025,9 +1031,9 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
GEM_BUG_ON(cache->rq_size + RELOC_TAIL > PAGE_SIZE / sizeof(u32));
cmd = cache->rq_cmd + cache->rq_size;
*cmd++ = MI_ARB_CHECK;
- if (cache->gen >= 8)
+ if (eb->gen >= 8)
*cmd++ = MI_BATCH_BUFFER_START_GEN8;
- else if (cache->gen >= 6)
+ else if (eb->gen >= 6)
*cmd++ = MI_BATCH_BUFFER_START;
else
*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
@@ -1050,7 +1056,7 @@ static int reloc_gpu_chain(struct reloc_cache *cache)
goto out_pool;
cmd = i915_gem_object_pin_map(batch->obj,
- cache->has_llc ?
+ eb->has_llc ?
I915_MAP_FORCE_WB :
I915_MAP_FORCE_WC);
if (IS_ERR(cmd)) {
@@ -1098,9 +1104,9 @@ static void __i915_request_add(struct i915_request *rq,
__i915_request_queue(rq, attr);
}
-static unsigned int reloc_bb_flags(const struct reloc_cache *cache)
+static unsigned int reloc_bb_flags(const struct i915_execbuffer *eb)
{
- return cache->gen > 5 ? 0 : I915_DISPATCH_SECURE;
+ return eb->gen > 5 ? 0 : I915_DISPATCH_SECURE;
}
static int reloc_gpu_flush(struct i915_execbuffer *eb)
@@ -1131,7 +1137,7 @@ static int reloc_gpu_flush(struct i915_execbuffer *eb)
err = rq->engine->emit_bb_start(rq,
rq->batch->node.start,
PAGE_SIZE,
- reloc_bb_flags(cache));
+ reloc_bb_flags(eb));
if (err)
i915_request_set_error_once(rq, err);
@@ -1179,7 +1185,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
return PTR_ERR(pool);
cmd = i915_gem_object_pin_map(pool->obj,
- cache->has_llc ?
+ eb->has_llc ?
I915_MAP_FORCE_WB :
I915_MAP_FORCE_WC);
if (IS_ERR(cmd)) {
@@ -1273,7 +1279,7 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
if (unlikely(cache->rq_size + len >
PAGE_SIZE / sizeof(u32) - RELOC_TAIL)) {
- err = reloc_gpu_chain(cache);
+ err = reloc_gpu_chain(eb);
if (unlikely(err)) {
i915_request_set_error_once(cache->rq, err);
return ERR_PTR(err);
@@ -1306,7 +1312,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
u64 offset,
u64 target_addr)
{
- const unsigned int gen = eb->reloc_cache.gen;
+ const unsigned int gen = eb->gen;
unsigned int len;
u32 *batch;
u64 addr;
@@ -1453,7 +1459,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
/* Check that the relocation address is valid... */
if (unlikely(reloc->offset >
- ev->vma->size - (eb->reloc_cache.use_64bit_reloc ? 8 : 4))) {
+ ev->vma->size - (eb->use_64bit_reloc ? 8 : 4))) {
drm_dbg(&i915->drm, "Relocation beyond object bounds: "
"target %d offset %d size %d.\n",
reloc->target_handle,
@@ -2481,7 +2487,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
eb.exec = exec;
eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;
- reloc_cache_init(&eb.reloc_cache, eb.i915);
+ eb_info_init(&eb, eb.i915);
+ reloc_cache_init(&eb.reloc_cache);
eb.buffer_count = args->buffer_count;
eb.batch_start_offset = args->batch_start_offset;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 992d46db1b33..023900de9f03 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -23,8 +23,7 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
struct drm_i915_gem_object *obj)
{
const unsigned int offsets[] = { 8, 3, 0 };
- const u64 mask =
- GENMASK_ULL(eb->reloc_cache.use_64bit_reloc ? 63 : 31, 0);
+ const u64 mask = GENMASK_ULL(eb->use_64bit_reloc ? 63 : 31, 0);
const u32 *map = page_mask_bits(obj->mm.mapping);
struct i915_request *rq;
struct i915_vma *vma;
@@ -126,8 +125,9 @@ static int igt_gpu_reloc(void *arg)
goto err_scratch;
}
+ eb_info_init(&eb, eb.i915);
for_each_uabi_engine(eb.engine, eb.i915) {
- reloc_cache_init(&eb.reloc_cache, eb.i915);
+ reloc_cache_init(&eb.reloc_cache);
memset(map, POISON_INUSE, 4096);
intel_engine_pm_get(eb.engine);
--
2.20.1
More information about the Intel-gfx-trybot
mailing list