xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drm/i915: Make request allocation caches global

Browse Source 
As kmem_caches share the same properties (size, allocation/free behaviour)
for all potential devices, we can use global caches. While this
potential has worse fragmentation behaviour (one can argue that
different devices would have different activity lifetimes, but you can
also argue that activity is temporal across the system) it is the
default behaviour of the system at large to amalgamate matching caches.

The benefit for us is much reduced pointer dancing along the frequent
allocation paths.

v2: Defer shrinking until after a global grace period for futureproofing
multiple consumers of the slab caches, similar to the current strategy
for avoiding shrinking too early.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190228102035.5857-1-chris@chris-wilson.co.uk
This commit is contained in:
Chris Wilson
2019-02-28 10:20:33 +00:00
parent bd2be14186
commit 32eb6bcfdd
19 changed files with 312 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
drivers/gpu/drm/i915/i915_request.c
View File

@@ -32,6 +32,11 @@
#include "i915_active.h"
#include "i915_reset.h"
static struct i915_global_request {
struct kmem_cache *slab_requests;
struct kmem_cache *slab_dependencies;
} global;
static const char *i915_fence_get_driver_name(struct dma_fence *fence)
{
return "i915";
@@ -86,7 +91,7 @@ static void i915_fence_release(struct dma_fence *fence)
*/
i915_sw_fence_fini(&rq->submit);
kmem_cache_free(rq->i915->requests, rq);
kmem_cache_free(global.slab_requests, rq);
}
const struct dma_fence_ops i915_fence_ops = {
@@ -292,7 +297,7 @@ static void i915_request_retire(struct i915_request *request)
unreserve_gt(request->i915);
i915_sched_node_fini(request->i915, &request->sched);
i915_sched_node_fini(&request->sched);
i915_request_put(request);
}
@@ -491,7 +496,7 @@ i915_request_alloc_slow(struct intel_context *ce)
ring_retire_requests(ring);
out:
return kmem_cache_alloc(ce->gem_context->i915->requests, GFP_KERNEL);
return kmem_cache_alloc(global.slab_requests, GFP_KERNEL);
}
static int add_timeline_barrier(struct i915_request *rq)
@@ -579,7 +584,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
*
* Do not use kmem_cache_zalloc() here!
*/
rq = kmem_cache_alloc(i915->requests,
rq = kmem_cache_alloc(global.slab_requests,
GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
if (unlikely(!rq)) {
rq = i915_request_alloc_slow(ce);
@@ -666,7 +671,7 @@ err_unwind:
GEM_BUG_ON(!list_empty(&rq->sched.signalers_list));
GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
kmem_cache_free(i915->requests, rq);
kmem_cache_free(global.slab_requests, rq);
err_unreserve:
unreserve_gt(i915);
intel_context_unpin(ce);
@@ -685,9 +690,7 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
return 0;
if (to->engine->schedule) {
ret = i915_sched_node_add_dependency(to->i915,
&to->sched,
&from->sched);
ret = i915_sched_node_add_dependency(&to->sched, &from->sched);
if (ret < 0)
return ret;
}
@@ -1175,3 +1178,37 @@ void i915_retire_requests(struct drm_i915_private *i915)
#include "selftests/mock_request.c"
#include "selftests/i915_request.c"
#endif
int __init i915_global_request_init(void)
{
global.slab_requests = KMEM_CACHE(i915_request,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_TYPESAFE_BY_RCU);
if (!global.slab_requests)
return -ENOMEM;
global.slab_dependencies = KMEM_CACHE(i915_dependency,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT);
if (!global.slab_dependencies)
goto err_requests;
return 0;
err_requests:
kmem_cache_destroy(global.slab_requests);
return -ENOMEM;
}
void i915_global_request_shrink(void)
{
kmem_cache_shrink(global.slab_dependencies);
kmem_cache_shrink(global.slab_requests);
}
void i915_global_request_exit(void)
{
kmem_cache_destroy(global.slab_dependencies);
kmem_cache_destroy(global.slab_requests);
}