From patchwork Tue Mar 14 15:20:36 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [1/8] drm/i915/gt: introduce vm->scratch_range callback From: Andi Shyti X-Patchwork-Id: 526780 Message-Id: <20230314152043.402262-1-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:36 +0100 From: Andrzej Hajda The callback will be responsible for setting scratch page PTEs for specified range. In contrast to clear_range it cannot be optimized to nop. It will be used by code adding guard pages. Signed-off-by: Andrzej Hajda --- drivers/gpu/drm/i915/gt/intel_ggtt.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c | 1 + drivers/gpu/drm/i915/gt/intel_gtt.h | 2 ++ 3 files changed, 26 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 842e69c7b21e4..38e6f0b207fe0 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -291,6 +291,27 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, ggtt->invalidate(ggtt); } +static void gen8_ggtt_clear_range(struct i915_address_space *vm, + u64 start, u64 length) +{ + struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); + unsigned int first_entry = start / I915_GTT_PAGE_SIZE; + unsigned int num_entries = length / I915_GTT_PAGE_SIZE; + const gen8_pte_t scratch_pte = vm->scratch[0]->encode; + gen8_pte_t __iomem *gtt_base = + (gen8_pte_t __iomem *)ggtt->gsm + first_entry; + const int max_entries = ggtt_total_entries(ggtt) - first_entry; + int i; + + if (WARN(num_entries > max_entries, + "First entry = %d; Num entries = %d (max=%d)\n", + first_entry, num_entries, max_entries)) + num_entries = max_entries; + + for (i = 0; i < num_entries; i++) + gen8_set_pte(>t_base[i], scratch_pte); +} + static void gen6_ggtt_insert_page(struct i915_address_space *vm, dma_addr_t addr, u64 offset, @@ -919,6 +940,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.cleanup = gen6_gmch_remove; ggtt->vm.insert_page = gen8_ggtt_insert_page; ggtt->vm.clear_range = nop_clear_range; + ggtt->vm.scratch_range = gen8_ggtt_clear_range; ggtt->vm.insert_entries = gen8_ggtt_insert_entries; @@ -1082,6 +1104,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.clear_range = nop_clear_range; if (!HAS_FULL_PPGTT(i915)) ggtt->vm.clear_range = gen6_ggtt_clear_range; + ggtt->vm.scratch_range = gen6_ggtt_clear_range; ggtt->vm.insert_page = gen6_ggtt_insert_page; ggtt->vm.insert_entries = gen6_ggtt_insert_entries; ggtt->vm.cleanup = gen6_gmch_remove; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c index 77c793812eb46..d6a74ae2527bd 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_gmch.c @@ -102,6 +102,7 @@ int intel_ggtt_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.insert_page = gmch_ggtt_insert_page; ggtt->vm.insert_entries = gmch_ggtt_insert_entries; ggtt->vm.clear_range = gmch_ggtt_clear_range; + ggtt->vm.scratch_range = gmch_ggtt_clear_range; ggtt->vm.cleanup = gmch_ggtt_remove; ggtt->invalidate = gmch_ggtt_invalidate; diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 5a775310d3fcb..69ce55f517f56 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -298,6 +298,8 @@ struct i915_address_space { u64 start, u64 length); void (*clear_range)(struct i915_address_space *vm, u64 start, u64 length); + void (*scratch_range)(struct i915_address_space *vm, + u64 start, u64 length); void (*insert_page)(struct i915_address_space *vm, dma_addr_t addr, u64 offset, From patchwork Tue Mar 14 15:20:37 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [2/8] drm/i915: add guard page to ggtt->error_capture From: Andi Shyti X-Patchwork-Id: 526781 Message-Id: <20230314152043.402262-2-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:37 +0100 From: Andrzej Hajda Write-combining memory allows speculative reads by CPU. ggtt->error_capture is WC mapped to CPU, so CPU/MMU can try to prefetch memory beyond the error_capture, ie it tries to read memory pointed by next PTE in GGTT. If this PTE points to invalid address DMAR errors will occur. This behaviour was observed on ADL and RPL platforms. To avoid it, guard scratch page should be added after error_capture. The patch fixes the most annoying issue with error capture but since WC reads are used also in other places there is a risk similar problem can affect them as well. v2: - modified commit message (I hope the diagnosis is correct), - added bug checks to ensure scratch is initialized on gen3 platforms. CI produces strange stacktrace for it suggesting scratch[0] is NULL, to be removed after resolving the issue with gen3 platforms. v3: - removed bug checks, replaced with gen check. v4: - change code for scratch page insertion to support all platforms, - add info in commit message there could be more similar issues v5: - check for nop_clear_range instead of gen8 (Tvrtko), - re-insert scratch pages on resume (Tvrtko) v6: - use scratch_range callback to set scratch pages (Chris) Signed-off-by: Andrzej Hajda Reviewed-by: Andi Shyti --- drivers/gpu/drm/i915/gt/intel_ggtt.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 38e6f0b207fe0..5ef7e03b11c8e 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -572,8 +572,12 @@ static int init_ggtt(struct i915_ggtt *ggtt) * paths, and we trust that 0 will remain reserved. However, * the only likely reason for failure to insert is a driver * bug, which we expect to cause other failures... + * + * Since CPU can perform speculative reads on error capture + * (write-combining allows it) add scratch page after error + * capture to avoid DMAR errors. */ - ggtt->error_capture.size = I915_GTT_PAGE_SIZE; + ggtt->error_capture.size = 2 * I915_GTT_PAGE_SIZE; ggtt->error_capture.color = I915_COLOR_UNEVICTABLE; if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture)) drm_mm_insert_node_in_range(&ggtt->vm.mm, @@ -583,11 +587,15 @@ static int init_ggtt(struct i915_ggtt *ggtt) 0, ggtt->mappable_end, DRM_MM_INSERT_LOW); } - if (drm_mm_node_allocated(&ggtt->error_capture)) + if (drm_mm_node_allocated(&ggtt->error_capture)) { + u64 start = ggtt->error_capture.start; + u64 size = ggtt->error_capture.size; + + ggtt->vm.scratch_range(&ggtt->vm, start, size); drm_dbg(&ggtt->vm.i915->drm, "Reserved GGTT:[%llx, %llx] for use by error capture\n", - ggtt->error_capture.start, - ggtt->error_capture.start + ggtt->error_capture.size); + start, start + size); + } /* * The upper portion of the GuC address space has a sizeable hole @@ -1280,6 +1288,10 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt) flush = i915_ggtt_resume_vm(&ggtt->vm); + if (drm_mm_node_allocated(&ggtt->error_capture)) + ggtt->vm.scratch_range(&ggtt->vm, ggtt->error_capture.start, + ggtt->error_capture.size); + ggtt->invalidate(ggtt); if (flush) From patchwork Tue Mar 14 15:20:38 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [3/8] drm/i915: Throttle for ringspace prior to taking the timeline mutex From: Andi Shyti X-Patchwork-Id: 526782 Message-Id: <20230314152043.402262-3-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:38 +0100 From: Chris Wilson Before taking exclusive ownership of the ring for emitting the request, wait for space in the ring to become available. This allows others to take the timeline->mutex to make forward progresses while userspace is blocked. In particular, this allows regular clients to issue requests on the kernel context, potentially filling the ring, but allow the higher priority heartbeats and pulses to still be submitted without being blocked by the less critical work. Signed-off-by: Chris Wilson Cc: Maciej Patelczyk Cc: stable@vger.kernel.org Signed-off-by: Andi Shyti --- drivers/gpu/drm/i915/gt/intel_context.c | 41 +++++++++++++++++++++++++ drivers/gpu/drm/i915/gt/intel_context.h | 2 ++ drivers/gpu/drm/i915/i915_request.c | 3 ++ 3 files changed, 46 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 2aa63ec521b89..59cd612a23561 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -626,6 +626,47 @@ bool intel_context_revoke(struct intel_context *ce) return ret; } +int intel_context_throttle(const struct intel_context *ce) +{ + const struct intel_ring *ring = ce->ring; + const struct intel_timeline *tl = ce->timeline; + struct i915_request *rq; + int err = 0; + + if (READ_ONCE(ring->space) >= SZ_1K) + return 0; + + rcu_read_lock(); + list_for_each_entry_reverse(rq, &tl->requests, link) { + if (__i915_request_is_complete(rq)) + break; + + if (rq->ring != ring) + continue; + + /* Wait until there will be enough space following that rq */ + if (__intel_ring_space(rq->postfix, + ring->emit, + ring->size) < ring->size / 2) { + if (i915_request_get_rcu(rq)) { + rcu_read_unlock(); + + if (i915_request_wait(rq, + I915_WAIT_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT) < 0) + err = -EINTR; + + rcu_read_lock(); + i915_request_put(rq); + } + break; + } + } + rcu_read_unlock(); + + return err; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_context.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 0a8d553da3f43..f919a66cebf5b 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -226,6 +226,8 @@ static inline void intel_context_exit(struct intel_context *ce) ce->ops->exit(ce); } +int intel_context_throttle(const struct intel_context *ce); + static inline struct intel_context *intel_context_get(struct intel_context *ce) { kref_get(&ce->ref); diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 630a732aaecca..72aed544f8714 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1034,6 +1034,9 @@ i915_request_create(struct intel_context *ce) struct i915_request *rq; struct intel_timeline *tl; + if (intel_context_throttle(ce)) + return ERR_PTR(-EINTR); + tl = intel_context_timeline_lock(ce); if (IS_ERR(tl)) return ERR_CAST(tl); From patchwork Tue Mar 14 15:20:39 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [4/8] drm/i915/gt: Add intel_context_timeline_is_locked helper From: Andi Shyti X-Patchwork-Id: 526783 Message-Id: <20230314152043.402262-4-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:39 +0100 We have: - intel_context_timeline_lock() - intel_context_timeline_unlock() In the next patches we will also need: - intel_context_timeline_is_locked() Add it. Signed-off-by: Andi Shyti Cc: stable@vger.kernel.org --- drivers/gpu/drm/i915/gt/intel_context.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index f919a66cebf5b..87d5e2d60b6db 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -265,6 +265,12 @@ static inline void intel_context_timeline_unlock(struct intel_timeline *tl) mutex_unlock(&tl->mutex); } +static inline void intel_context_assert_timeline_is_locked(struct intel_timeline *tl) + __must_hold(&tl->mutex) +{ + lockdep_assert_held(&tl->mutex); +} + int intel_context_prepare_remote_request(struct intel_context *ce, struct i915_request *rq); From patchwork Tue Mar 14 15:20:40 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [5/8] drm/i915: Create the locked version of the request create From: Andi Shyti X-Patchwork-Id: 526784 Message-Id: <20230314152043.402262-5-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:40 +0100 Make version of the request creation that doesn't hold any lock. Signed-off-by: Andi Shyti Cc: stable@vger.kernel.org --- drivers/gpu/drm/i915/i915_request.c | 43 +++++++++++++++++++---------- drivers/gpu/drm/i915/i915_request.h | 2 ++ 2 files changed, 31 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 72aed544f8714..5ddb0e02b06b7 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1028,18 +1028,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) return ERR_PTR(ret); } -struct i915_request * -i915_request_create(struct intel_context *ce) +static struct i915_request * +__i915_request_create_locked(struct intel_context *ce) { struct i915_request *rq; - struct intel_timeline *tl; - - if (intel_context_throttle(ce)) - return ERR_PTR(-EINTR); - - tl = intel_context_timeline_lock(ce); - if (IS_ERR(tl)) - return ERR_CAST(tl); + struct intel_timeline *tl = ce->timeline; /* Move our oldest request to the slab-cache (if not in use!) */ rq = list_first_entry(&tl->requests, typeof(*rq), link); @@ -1049,16 +1042,38 @@ i915_request_create(struct intel_context *ce) intel_context_enter(ce); rq = __i915_request_create(ce, GFP_KERNEL); intel_context_exit(ce); /* active reference transferred to request */ - if (IS_ERR(rq)) - goto err_unlock; /* Check that we do not interrupt ourselves with a new request */ rq->cookie = lockdep_pin_lock(&tl->mutex); return rq; +} + +struct i915_request * +i915_request_create_locked(struct intel_context *ce) +{ + intel_context_assert_timeline_is_locked(ce->timeline); + + if (intel_context_throttle(ce)) + return ERR_PTR(-EINTR); + + return __i915_request_create_locked(ce); +} + +struct i915_request * +i915_request_create(struct intel_context *ce) +{ + struct i915_request *rq; + struct intel_timeline *tl; + + tl = intel_context_timeline_lock(ce); + if (IS_ERR(tl)) + return ERR_CAST(tl); + + rq = __i915_request_create_locked(ce); + if (IS_ERR(rq)) + intel_context_timeline_unlock(tl); -err_unlock: - intel_context_timeline_unlock(tl); return rq; } diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index f5e1bb5e857aa..bb48bd4605c03 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -374,6 +374,8 @@ struct i915_request * __must_check __i915_request_create(struct intel_context *ce, gfp_t gfp); struct i915_request * __must_check i915_request_create(struct intel_context *ce); +struct i915_request * __must_check +i915_request_create_locked(struct intel_context *ce); void __i915_request_skip(struct i915_request *rq); bool i915_request_set_error_once(struct i915_request *rq, int error); From patchwork Tue Mar 14 15:20:41 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [6/8] drm/i915: Create the locked version of the request add From: Andi Shyti X-Patchwork-Id: 526785 Message-Id: <20230314152043.402262-6-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:41 +0100 i915_request_add() assumes that the timeline is locked whtn the function is called. Before exiting it releases the lock. But in the next commit we have one case where releasing the timeline mutex is not necessary and we don't want that. Make a new i915_request_add_locked() version of the function where the lock is not released. Signed-off-by: Andi Shyti Cc: stable@vger.kernel.org --- drivers/gpu/drm/i915/i915_request.c | 14 +++++++++++--- drivers/gpu/drm/i915/i915_request.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 5ddb0e02b06b7..a4af16e25d966 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1852,13 +1852,13 @@ void __i915_request_queue(struct i915_request *rq, local_bh_enable(); /* kick tasklets */ } -void i915_request_add(struct i915_request *rq) +void i915_request_add_locked(struct i915_request *rq) { struct intel_timeline * const tl = i915_request_timeline(rq); struct i915_sched_attr attr = {}; struct i915_gem_context *ctx; - lockdep_assert_held(&tl->mutex); + intel_context_assert_timeline_is_locked(tl); lockdep_unpin_lock(&tl->mutex, rq->cookie); trace_i915_request_add(rq); @@ -1873,7 +1873,15 @@ void i915_request_add(struct i915_request *rq) __i915_request_queue(rq, &attr); - mutex_unlock(&tl->mutex); +} + +void i915_request_add(struct i915_request *rq) +{ + struct intel_timeline * const tl = i915_request_timeline(rq); + + i915_request_add_locked(rq); + + intel_context_timeline_unlock(tl); } static unsigned long local_clock_ns(unsigned int *cpu) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index bb48bd4605c03..29e3a37c300a7 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -425,6 +425,7 @@ int i915_request_await_deps(struct i915_request *rq, const struct i915_deps *dep int i915_request_await_execution(struct i915_request *rq, struct dma_fence *fence); +void i915_request_add_locked(struct i915_request *rq); void i915_request_add(struct i915_request *rq); bool __i915_request_submit(struct i915_request *request); From patchwork Tue Mar 14 15:20:42 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [7/8] drm/i915/gt: Make sure that errors are propagated through request chains From: Andi Shyti X-Patchwork-Id: 526786 Message-Id: <20230314152043.402262-7-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:42 +0100 Currently, when we perform operations such as clearing or copying large blocks of memory, we generate multiple requests that are executed in a chain. However, if one of these requests fails, we may not realize it unless it happens to be the last request in the chain. This is because errors are not properly propagated. For this we need to keep propagating the chain of fence notification in order to always reach the final fence associated to the final request. To address this issue, we need to ensure that the chain of fence notifications is always propagated so that we can reach the final fence associated with the last request. By doing so, we will be able to detect any memory operation failures and determine whether the memory is still invalid. On copy and clear migration signal fences upon completion. On copy and clear migration, signal fences upon request completion to ensure that we have a reliable perpetuation of the operation outcome. Fixes: cf586021642d80 ("drm/i915/gt: Pipelined page migration") Reported-by: Matthew Auld Suggested-by: Chris Wilson Signed-off-by: Andi Shyti Cc: stable@vger.kernel.org Reviewed-by: Matthew Auld --- drivers/gpu/drm/i915/gt/intel_migrate.c | 51 +++++++++++++++++++------ 1 file changed, 39 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index 3f638f1987968..668c95af8cbcf 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -742,13 +742,19 @@ intel_context_migrate_copy(struct intel_context *ce, dst_offset = 2 * CHUNK_SZ; } + /* + * While building the chain of requests, we need to ensure + * that no one can sneak into the timeline unnoticed. + */ + mutex_lock(&ce->timeline->mutex); + do { int len; - rq = i915_request_create(ce); + rq = i915_request_create_locked(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); - goto out_ce; + break; } if (deps) { @@ -878,10 +884,14 @@ intel_context_migrate_copy(struct intel_context *ce, /* Arbitration is re-enabled between requests. */ out_rq: - if (*out) + i915_sw_fence_await(&rq->submit); + i915_request_get(rq); + i915_request_add_locked(rq); + if (*out) { + i915_sw_fence_complete(&(*out)->submit); i915_request_put(*out); - *out = i915_request_get(rq); - i915_request_add(rq); + } + *out = rq; if (err) break; @@ -905,7 +915,10 @@ intel_context_migrate_copy(struct intel_context *ce, cond_resched(); } while (1); -out_ce: + mutex_unlock(&ce->timeline->mutex); + + if (*out) + i915_sw_fence_complete(&(*out)->submit); return err; } @@ -999,13 +1012,19 @@ intel_context_migrate_clear(struct intel_context *ce, if (HAS_64K_PAGES(i915) && is_lmem) offset = CHUNK_SZ; + /* + * While building the chain of requests, we need to ensure + * that no one can sneak into the timeline unnoticed. + */ + mutex_lock(&ce->timeline->mutex); + do { int len; - rq = i915_request_create(ce); + rq = i915_request_create_locked(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); - goto out_ce; + break; } if (deps) { @@ -1056,17 +1075,25 @@ intel_context_migrate_clear(struct intel_context *ce, /* Arbitration is re-enabled between requests. */ out_rq: - if (*out) + i915_sw_fence_await(&rq->submit); + i915_request_get(rq); + i915_request_add_locked(rq); + if (*out) { + i915_sw_fence_complete(&(*out)->submit); i915_request_put(*out); - *out = i915_request_get(rq); - i915_request_add(rq); + } + *out = rq; + if (err || !it.sg || !sg_dma_len(it.sg)) break; cond_resched(); } while (1); -out_ce: + mutex_unlock(&ce->timeline->mutex); + + if (*out) + i915_sw_fence_complete(&(*out)->submit); return err; } From patchwork Tue Mar 14 15:20:43 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [8/8] some fixes From: Andi Shyti X-Patchwork-Id: 526787 Message-Id: <20230314152043.402262-8-andi.shyti@linux.intel.com> To: intel-gfx-trybot@lists.freedesktop.org Date: Tue, 14 Mar 2023 16:20:43 +0100 --- drivers/gpu/drm/i915/i915_request.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index a4af16e25d966..08c158b5724e2 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1043,6 +1043,9 @@ __i915_request_create_locked(struct intel_context *ce) rq = __i915_request_create(ce, GFP_KERNEL); intel_context_exit(ce); /* active reference transferred to request */ + if (IS_ERR(rq)) + return rq; + /* Check that we do not interrupt ourselves with a new request */ rq->cookie = lockdep_pin_lock(&tl->mutex);