@@ -1275,8 +1275,12 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
u32 *cmd;
int err;
+
if (!pool) {
- pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE);
+ pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE,
+ cache->has_llc ?
+ I915_MAP_WB :
+ I915_MAP_WC);
if (IS_ERR(pool))
return PTR_ERR(pool);
}
@@ -1286,10 +1290,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
if (err)
goto err_pool;
- cmd = i915_gem_object_pin_map(pool->obj,
- cache->has_llc ?
- I915_MAP_FORCE_WB :
- I915_MAP_FORCE_WC);
+ cmd = i915_gem_object_pin_map(pool->obj, pool->type);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto err_pool;
@@ -2458,7 +2459,8 @@ static int eb_parse(struct i915_execbuffer *eb)
return -EINVAL;
if (!pool) {
- pool = intel_gt_get_buffer_pool(eb->engine->gt, len);
+ pool = intel_gt_get_buffer_pool(eb->engine->gt, len,
+ I915_MAP_WB);
if (IS_ERR(pool))
return PTR_ERR(pool);
eb->batch_pool = pool;
@@ -35,7 +35,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
count = div_u64(round_up(vma->size, block_size), block_size);
size = (1 + 8 * count) * sizeof(u32);
size = round_up(size, PAGE_SIZE);
- pool = intel_gt_get_buffer_pool(ce->engine->gt, size);
+ pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
if (IS_ERR(pool)) {
err = PTR_ERR(pool);
goto out_pm;
@@ -55,7 +55,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
if (unlikely(err))
goto out_put;
- cmd = i915_gem_object_pin_map(pool->obj, I915_MAP_WC);
+ cmd = i915_gem_object_pin_map(pool->obj, pool->type);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto out_unpin;
@@ -257,7 +257,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
count = div_u64(round_up(dst->size, block_size), block_size);
size = (1 + 11 * count) * sizeof(u32);
size = round_up(size, PAGE_SIZE);
- pool = intel_gt_get_buffer_pool(ce->engine->gt, size);
+ pool = intel_gt_get_buffer_pool(ce->engine->gt, size, I915_MAP_WC);
if (IS_ERR(pool)) {
err = PTR_ERR(pool);
goto out_pm;
@@ -277,7 +277,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
if (unlikely(err))
goto out_put;
- cmd = i915_gem_object_pin_map(pool->obj, I915_MAP_WC);
+ cmd = i915_gem_object_pin_map(pool->obj, pool->type);
if (IS_ERR(cmd)) {
err = PTR_ERR(cmd);
goto out_unpin;
@@ -145,7 +145,8 @@ static void pool_retire(struct i915_active *ref)
}
static struct intel_gt_buffer_pool_node *
-node_create(struct intel_gt_buffer_pool *pool, size_t sz)
+node_create(struct intel_gt_buffer_pool *pool, size_t sz,
+ enum i915_map_type type)
{
struct intel_gt *gt = to_gt(pool);
struct intel_gt_buffer_pool_node *node;
@@ -169,12 +170,14 @@ node_create(struct intel_gt_buffer_pool *pool, size_t sz)
i915_gem_object_set_readonly(obj);
+ node->type = type;
node->obj = obj;
return node;
}
struct intel_gt_buffer_pool_node *
-intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size)
+intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size,
+ enum i915_map_type type)
{
struct intel_gt_buffer_pool *pool = >->buffer_pool;
struct intel_gt_buffer_pool_node *node;
@@ -191,6 +194,9 @@ intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size)
if (node->obj->base.size < size)
continue;
+ if (node->type != type)
+ continue;
+
age = READ_ONCE(node->age);
if (!age)
continue;
@@ -205,7 +211,7 @@ intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size)
rcu_read_unlock();
if (&node->link == list) {
- node = node_create(pool, size);
+ node = node_create(pool, size, type);
if (IS_ERR(node))
return node;
}
@@ -15,7 +15,8 @@ struct intel_gt;
struct i915_request;
struct intel_gt_buffer_pool_node *
-intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size);
+intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size,
+ enum i915_map_type type);
static inline int
intel_gt_buffer_pool_mark_active(struct intel_gt_buffer_pool_node *node,
@@ -11,10 +11,9 @@
#include <linux/spinlock.h>
#include <linux/workqueue.h>
+#include "gem/i915_gem_object.h"
#include "i915_active_types.h"
-struct drm_i915_gem_object;
-
struct intel_gt_buffer_pool {
spinlock_t lock;
struct list_head cache_list[4];
@@ -31,6 +30,7 @@ struct intel_gt_buffer_pool_node {
struct rcu_head rcu;
};
unsigned long age;
+ enum i915_map_type type;
};
#endif /* INTEL_GT_BUFFER_POOL_TYPES_H */
@@ -1143,7 +1143,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
void *dst, *src;
int ret;
- dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB);
+ dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB);
if (IS_ERR(dst))
return dst;
In a few places we always end up mapping the pool object with the FORCE constraint(to prevent hitting -EBUSY) which will destroy the cached mapping if it has a different type. As a simple first step, make the mapping type part of the pool interface, where the behaviour is to only give out pool objects which match the requested mapping type. Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Matthew Auld <matthew.auld@intel.com> --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 14 ++++++++------ drivers/gpu/drm/i915/gem/i915_gem_object_blt.c | 8 ++++---- drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c | 12 +++++++++--- drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h | 3 ++- .../gpu/drm/i915/gt/intel_gt_buffer_pool_types.h | 4 ++-- drivers/gpu/drm/i915/i915_cmd_parser.c | 2 +- 6 files changed, 26 insertions(+), 17 deletions(-)