From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 07/11] drm/i915/gem: Add all GPU reloc awaits/signals en masse
Date: Thu, 28 May 2020 08:41:05 +0100 [thread overview]
Message-ID: <20200528074109.28235-7-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200528074109.28235-1-chris@chris-wilson.co.uk>
Asynchronous waits and signaling form a traditional semaphore with all
the usual ordering problems with taking multiple locks. If we want to
add more than one wait on a shared resource by the GPU, we must ensure
that all the associated timelines are advanced atomically, ergo we must
lock all the timelines en masse.
Testcase: igt/gem_exec_reloc/basic-concurrent16
Fixes: 0e97fbb08055 ("drm/i915/gem: Use a single chained reloc batches for a single execbuf")
References: https://gitlab.freedesktop.org/drm/intel/-/issues/1889
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 110 ++++++++++++------
.../i915/gem/selftests/i915_gem_execbuffer.c | 24 ++--
2 files changed, 89 insertions(+), 45 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d48f42567f75..3fb76d222610 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -259,7 +259,6 @@ struct i915_execbuffer {
bool has_fence : 1;
bool needs_unfenced : 1;
- struct i915_vma *target;
struct i915_request *rq;
struct i915_vma *rq_vma;
u32 *rq_cmd;
@@ -924,7 +923,6 @@ static void reloc_cache_init(struct reloc_cache *cache,
cache->has_fence = cache->gen < 4;
cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
cache->node.flags = 0;
- cache->target = NULL;
}
static inline void *unmask_page(unsigned long p)
@@ -1054,26 +1052,6 @@ static int reloc_gpu_flush(struct reloc_cache *cache)
return err;
}
-static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
-{
- struct drm_i915_gem_object *obj = vma->obj;
- int err;
-
- i915_vma_lock(vma);
-
- if (obj->cache_dirty & ~obj->cache_coherent)
- i915_gem_clflush_object(obj, 0);
- obj->write_domain = 0;
-
- err = i915_request_await_object(rq, vma->obj, true);
- if (err == 0)
- err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-
- i915_vma_unlock(vma);
-
- return err;
-}
-
static int
__reloc_gpu_alloc(struct i915_execbuffer *eb, struct intel_engine_cs *engine)
{
@@ -1165,24 +1143,12 @@ __reloc_gpu_alloc(struct i915_execbuffer *eb, struct intel_engine_cs *engine)
return err;
}
-static u32 *reloc_batch_grow(struct i915_execbuffer *eb,
- struct i915_vma *vma,
- unsigned int len)
+static u32 *reloc_batch_grow(struct i915_execbuffer *eb, unsigned int len)
{
struct reloc_cache *cache = &eb->reloc_cache;
u32 *cmd;
int err;
- if (vma != cache->target) {
- err = reloc_move_to_gpu(cache->rq, vma);
- if (unlikely(err)) {
- i915_request_set_error_once(cache->rq, err);
- return ERR_PTR(err);
- }
-
- cache->target = vma;
- }
-
if (unlikely(cache->rq_size + len >
PAGE_SIZE / sizeof(u32) - RELOC_TAIL)) {
err = reloc_gpu_chain(cache);
@@ -1230,7 +1196,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
else
len = 3;
- batch = reloc_batch_grow(eb, vma, len);
+ batch = reloc_batch_grow(eb, len);
if (IS_ERR(batch))
return PTR_ERR(batch);
@@ -1550,6 +1516,74 @@ static long eb_reloc_vma_validate(struct i915_execbuffer *eb, struct eb_vma *ev)
return required;
}
+static int reloc_move_to_gpu(struct reloc_cache *cache, struct eb_vma *ev)
+{
+ struct i915_request *rq = cache->rq;
+ struct i915_vma *vma = ev->vma;
+ struct drm_i915_gem_object *obj = vma->obj;
+ int err;
+
+ if (obj->cache_dirty & ~obj->cache_coherent)
+ i915_gem_clflush_object(obj, 0);
+
+ obj->write_domain = I915_GEM_DOMAIN_RENDER;
+ obj->read_domains = I915_GEM_DOMAIN_RENDER;
+
+ err = i915_request_await_object(rq, obj, true);
+ if (err == 0) {
+ dma_resv_add_excl_fence(vma->resv, &rq->fence);
+ err = __i915_vma_move_to_active(vma, rq);
+ }
+
+ return err;
+}
+
+static int
+lock_relocs(struct i915_execbuffer *eb)
+{
+ struct ww_acquire_ctx acquire;
+ struct eb_vma *ev;
+ int err = 0;
+
+ ww_acquire_init(&acquire, &reservation_ww_class);
+
+ list_for_each_entry(ev, &eb->relocs, reloc_link) {
+ struct i915_vma *vma = ev->vma;
+
+ err = ww_mutex_lock_interruptible(&vma->resv->lock, &acquire);
+ if (err == -EDEADLK) {
+ struct eb_vma *unlock = ev, *en;
+
+ list_for_each_entry_safe_continue_reverse(unlock, en,
+ &eb->relocs,
+ reloc_link) {
+ ww_mutex_unlock(&unlock->vma->resv->lock);
+ list_move_tail(&unlock->reloc_link,
+ &eb->relocs);
+ }
+
+ GEM_BUG_ON(!list_is_first(&ev->reloc_link,
+ &eb->relocs));
+ err = ww_mutex_lock_slow_interruptible(&vma->resv->lock,
+ &acquire);
+ }
+ if (err)
+ break;
+ }
+
+ ww_acquire_done(&acquire);
+
+ list_for_each_entry_continue_reverse(ev, &eb->relocs, reloc_link) {
+ if (err == 0)
+ err = reloc_move_to_gpu(&eb->reloc_cache, ev);
+ ww_mutex_unlock(&ev->vma->resv->lock);
+ }
+
+ ww_acquire_fini(&acquire);
+
+ return err;
+}
+
static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
{
return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
@@ -1578,6 +1612,10 @@ static int reloc_gpu(struct i915_execbuffer *eb)
return err;
GEM_BUG_ON(!eb->reloc_cache.rq);
+ err = lock_relocs(eb);
+ if (err)
+ goto out;
+
list_for_each_entry(ev, &eb->relocs, reloc_link) {
err = eb_relocate_vma(eb, ev);
if (err)
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 50fe22d87ae1..d5c1be86b1e6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -24,15 +24,15 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
GENMASK_ULL(eb->reloc_cache.use_64bit_reloc ? 63 : 31, 0);
const u32 *map = page_mask_bits(obj->mm.mapping);
struct i915_request *rq;
- struct i915_vma *vma;
+ struct eb_vma ev;
int err;
int i;
- vma = i915_vma_instance(obj, eb->context->vm, NULL);
- if (IS_ERR(vma))
- return PTR_ERR(vma);
+ ev.vma = i915_vma_instance(obj, eb->context->vm, NULL);
+ if (IS_ERR(ev.vma))
+ return PTR_ERR(ev.vma);
- err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH);
+ err = i915_vma_pin(ev.vma, 0, 0, PIN_USER | PIN_HIGH);
if (err)
return err;
@@ -40,13 +40,19 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
if (err)
goto unpin_vma;
+ i915_vma_lock(ev.vma);
+ err = reloc_move_to_gpu(&eb->reloc_cache, &ev);
+ i915_vma_unlock(ev.vma);
+ if (err)
+ goto unpin_vma;
+
/* 8-Byte aligned */
- err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
+ err = __reloc_entry_gpu(eb, ev.vma, offsets[0] * sizeof(u32), 0);
if (err)
goto unpin_vma;
/* !8-Byte aligned */
- err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1);
+ err = __reloc_entry_gpu(eb, ev.vma, offsets[1] * sizeof(u32), 1);
if (err)
goto unpin_vma;
@@ -58,7 +64,7 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
eb->reloc_cache.rq_size += i;
/* Force batch chaining */
- err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2);
+ err = __reloc_entry_gpu(eb, ev.vma, offsets[2] * sizeof(u32), 2);
if (err)
goto unpin_vma;
@@ -95,7 +101,7 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
put_rq:
i915_request_put(rq);
unpin_vma:
- i915_vma_unpin(vma);
+ i915_vma_unpin(ev.vma);
return err;
}
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-05-28 7:41 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-28 7:40 [Intel-gfx] [PATCH 01/11] drm/i915/gt: Prevent timeslicing into unpreemptable requests Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 02/11] drm/i915/gt: Don't declare hangs if engine is stalled Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 03/11] drm/i915/gem: Async GPU relocations only Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 04/11] drm/i915: Add list_for_each_entry_safe_continue_reverse Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 05/11] drm/i915/gem: Separate reloc validation into an earlier step Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 06/11] drm/i915/gem: Lift GPU relocation allocation Chris Wilson
2020-05-28 7:41 ` Chris Wilson [this message]
2020-05-28 7:41 ` [Intel-gfx] [PATCH 08/11] drm/i915/gem: Build the reloc request first Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 09/11] dma-buf: Proxy fence, an unsignaled fence placeholder Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 10/11] drm/i915: Unpeel awaits on a proxy fence Chris Wilson
2020-05-28 7:41 ` [Intel-gfx] [PATCH 11/11] drm/i915/gem: Make relocations atomic within execbuf Chris Wilson
2020-05-28 7:54 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/11] drm/i915/gt: Prevent timeslicing into unpreemptable requests Patchwork
2020-05-28 7:55 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-05-28 8:16 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-05-28 10:38 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200528074109.28235-7-chris@chris-wilson.co.uk \
--to=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.