diff options
author | Thomas Hellström <thomas.hellstrom@linux.intel.com> | 2021-11-29 21:22:45 +0100 |
---|---|---|
committer | Thomas Hellström <thomas.hellstrom@linux.intel.com> | 2021-12-01 16:53:22 +0100 |
commit | ff20afc4cee7b65f752b1da6d5da4c0bea1431b9 (patch) | |
tree | 680b6da2c53baf47e8f146d27e1ed1ae19f53fce /drivers/gpu/drm/i915/i915_request.c | |
parent | 49a8bf50caa2fb0fb2eb1c89923ea61192227c32 (diff) |
drm/i915: Update error capture code to avoid using the current vma state
With asynchronous migrations, the vma state may be several migrations
ahead of the state that matches the request we're capturing.
Address that by introducing an i915_vma_snapshot structure that
can be used to snapshot relevant state at request submission.
In order to make sure we access the correct memory, the snapshots take
references on relevant sg-tables and memory regions.
Also move the capture list allocation out of the fence signaling
critical path and use the CONFIG_DRM_I915_CAPTURE_ERROR define to
avoid compiling in members and functions used for error capture
when they're not used.
Finally, Introduce lockdep annotation.
v4:
- Break out the capture allocation mode change to a separate patch.
v5:
- Fix compilation error in the !CONFIG_DRM_I915_CAPTURE_ERROR case
(kernel test robot)
v6:
- Use #if IS_ENABLED() instead of #ifdef to match driver style.
- Move yet another change of allocation mode to the separate patch.
- Commit message rework due to patch reordering.
v7:
- Adjust for removal of region refcounting.
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211129202245.472043-1-thomas.hellstrom@linux.intel.com
Diffstat (limited to 'drivers/gpu/drm/i915/i915_request.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_request.c | 63 |
1 files changed, 46 insertions, 17 deletions
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 825a94b18c78..471cde0e9883 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -113,6 +113,10 @@ static void i915_fence_release(struct dma_fence *fence) GEM_BUG_ON(rq->guc_prio != GUC_PRIO_INIT && rq->guc_prio != GUC_PRIO_FINI); + i915_request_free_capture_list(fetch_and_zero(&rq->capture_list)); + if (i915_vma_snapshot_present(&rq->batch_snapshot)) + i915_vma_snapshot_put_onstack(&rq->batch_snapshot); + /* * The request is put onto a RCU freelist (i.e. the address * is immediately reused), mark the fences as being freed now. @@ -186,19 +190,6 @@ void i915_request_notify_execute_cb_imm(struct i915_request *rq) __notify_execute_cb(rq, irq_work_imm); } -static void free_capture_list(struct i915_request *request) -{ - struct i915_capture_list *capture; - - capture = fetch_and_zero(&request->capture_list); - while (capture) { - struct i915_capture_list *next = capture->next; - - kfree(capture); - capture = next; - } -} - static void __i915_request_fill(struct i915_request *rq, u8 val) { void *vaddr = rq->ring->vaddr; @@ -303,6 +294,37 @@ static void __rq_cancel_watchdog(struct i915_request *rq) i915_request_put(rq); } +#if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) + +/** + * i915_request_free_capture_list - Free a capture list + * @capture: Pointer to the first list item or NULL + * + */ +void i915_request_free_capture_list(struct i915_capture_list *capture) +{ + while (capture) { + struct i915_capture_list *next = capture->next; + + i915_vma_snapshot_put(capture->vma_snapshot); + capture = next; + } +} + +#define assert_capture_list_is_null(_rq) GEM_BUG_ON((_rq)->capture_list) + +#define clear_capture_list(_rq) ((_rq)->capture_list = NULL) + +#else + +#define i915_request_free_capture_list(_a) do {} while (0) + +#define assert_capture_list_is_null(_a) do {} while (0) + +#define clear_capture_list(_rq) do {} while (0) + +#endif + bool i915_request_retire(struct i915_request *rq) { if (!__i915_request_is_complete(rq)) @@ -359,7 +381,6 @@ bool i915_request_retire(struct i915_request *rq) intel_context_exit(rq->context); intel_context_unpin(rq->context); - free_capture_list(rq); i915_sched_node_fini(&rq->sched); i915_request_put(rq); @@ -829,11 +850,18 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); - rq->capture_list = NULL; + clear_capture_list(rq); + rq->batch_snapshot.present = false; init_llist_head(&rq->execute_cb); } +#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +#define clear_batch_ptr(_rq) ((_rq)->batch = NULL) +#else +#define clear_batch_ptr(_a) do {} while (0) +#endif + struct i915_request * __i915_request_create(struct intel_context *ce, gfp_t gfp) { @@ -925,10 +953,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) i915_sched_node_reinit(&rq->sched); /* No zalloc, everything must be cleared after use */ - rq->batch = NULL; + clear_batch_ptr(rq); __rq_init_watchdog(rq); - GEM_BUG_ON(rq->capture_list); + assert_capture_list_is_null(rq); GEM_BUG_ON(!llist_empty(&rq->execute_cb)); + GEM_BUG_ON(i915_vma_snapshot_present(&rq->batch_snapshot)); /* * Reserve space in the ring buffer for all the commands required to |