Add a cancel request selftest that results in an engine reset to cancel the request as it is non-preemptable. Also insert a NOP request after the cancelled request and confirm that it completes successfully.

v2: (Tvrtko) - Skip test if preemption timeout compiled out - Skip test if engine reset isn't supported - Update debug prints to be more descriptive v3: - Add comment explaining test v4: (John Harrison) - Fix typos in comment explaining test - goto out_rq is NOP creation fails

Signed-off-by: Matthew Brost matthew.brost@intel.com

--- drivers/gpu/drm/i915/selftests/i915_request.c | 117 ++++++++++++++++++ 1 file changed, 117 insertions(+) --- drivers/gpu/drm/i915/selftests/i915_request.c | 117 ++++++++++++++++++ 1 file changed, 117 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 7f66f6d299b26..2a99dd7c2fe8a 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -782,6 +782,115 @@ static int __cancel_completed(struct intel_engine_cs *engine) return err; }

+/* + * Test to prove a non-preemptable request can be cancelled and a subsequent + * request on the same context can successfully complete after cancellation. + * + * Testing methodology is to create a non-preemptible request and submit it, + * wait for spinner to start, create a NOP request and submit it, cancel the + * spinner, wait for spinner to complete and verify it failed with an error, + * finally wait for NOP request to complete verify it succeeded without an + * error. Preemption timeout also reduced / restored so test runs in a timely + * maner. + */ +static int __cancel_reset(struct drm_i915_private *i915, + struct intel_engine_cs *engine) +{ + struct intel_context *ce; + struct igt_spinner spin; + struct i915_request *rq, *nop; + unsigned long preempt_timeout_ms; + int err = 0; + + if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT || + !intel_has_reset_engine(engine->gt)) + return 0; + + preempt_timeout_ms = engine->props.preempt_timeout_ms; + engine->props.preempt_timeout_ms = 100; + + if (igt_spinner_init(&spin, engine->gt)) + goto out_restore; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + goto out_spin; + } + + rq = igt_spinner_create_request(&spin, ce, MI_NOOP); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_ce; + } + + pr_debug("%s: Cancelling active non-preemptable request\n", + engine->name); + i915_request_get(rq); + i915_request_add(rq); + if (!igt_wait_for_spinner(&spin, rq)) { + struct drm_printer p = drm_info_printer(engine->i915->drm.dev); + + pr_err("Failed to start spinner on %s\n", engine->name); + intel_engine_dump(engine, &p, "%s\n", engine->name); + err = -ETIME; + goto out_rq; + } + + nop = intel_context_create_request(ce); + if (IS_ERR(nop)) + goto out_rq; + i915_request_get(nop); + i915_request_add(nop); + + i915_request_cancel(rq, -EINTR); + + if (i915_request_wait(rq, 0, HZ) < 0) { + struct drm_printer p = drm_info_printer(engine->i915->drm.dev); + + pr_err("%s: Failed to cancel hung request\n", engine->name); + intel_engine_dump(engine, &p, "%s\n", engine->name); + err = -ETIME; + goto out_nop; + } + + if (rq->fence.error != -EINTR) { + pr_err("%s: fence not cancelled (%u)\n", + engine->name, rq->fence.error); + err = -EINVAL; + goto out_nop; + } + + if (i915_request_wait(nop, 0, HZ) < 0) { + struct drm_printer p = drm_info_printer(engine->i915->drm.dev); + + pr_err("%s: Failed to complete nop request\n", engine->name); + intel_engine_dump(engine, &p, "%s\n", engine->name); + err = -ETIME; + goto out_nop; + } + + if (nop->fence.error != 0) { + pr_err("%s: Nop request errored (%u)\n", + engine->name, nop->fence.error); + err = -EINVAL; + } + +out_nop: + i915_request_put(nop); +out_rq: + i915_request_put(rq); +out_ce: + intel_context_put(ce); +out_spin: + igt_spinner_fini(&spin); +out_restore: + engine->props.preempt_timeout_ms = preempt_timeout_ms; + if (err) + pr_err("%s: %s error %d\n", __func__, engine->name, err); + return err; +} + static int live_cancel_request(void *arg) { struct drm_i915_private *i915 = arg; @@ -814,6 +923,14 @@ static int live_cancel_request(void *arg) return err; if (err2) return err2; + + /* Expects reset so call outside of igt_live_test_* */ + err = __cancel_reset(i915, engine); + if (err) + return err; + + if (igt_flush_test(i915)) + return -EIO; }

return 0;

In the i915 there are several hacks in place to make request cancellation work with an old version of the GuC which delivered the G2H indicating schedule disable is done before G2H indicating a context reset. Version 69 fixes this, so we can remove these hacks.

v2: (Checkpatch) - s/cancelation/cancellation

Reviewed-by: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com --- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 30 ++----------------- 1 file changed, 2 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 23a40f10d376d..3918f1be114fa 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1533,7 +1533,6 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) unsigned long flags; u32 head; int i, number_children = ce->parallel.number_children; - bool skip = false; struct intel_context *parent = ce;

GEM_BUG_ON(intel_context_is_child(ce)); @@ -1544,23 +1543,10 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) * GuC will implicitly mark the context as non-schedulable when it sends * the reset notification. Make sure our state reflects this change. The * context will be marked enabled on resubmission. - * - * XXX: If the context is reset as a result of the request cancellation - * this G2H is received after the schedule disable complete G2H which is - * wrong as this creates a race between the request cancellation code - * re-submitting the context and this G2H handler. This is a bug in the - * GuC but can be worked around in the meantime but converting this to a - * NOP if a pending enable is in flight as this indicates that a request - * cancellation has occurred. */ spin_lock_irqsave(&ce->guc_state.lock, flags); - if (likely(!context_pending_enable(ce))) - clr_context_enabled(ce); - else - skip = true; + clr_context_enabled(ce); spin_unlock_irqrestore(&ce->guc_state.lock, flags); - if (unlikely(skip)) - goto out_put;

/* * For each context in the relationship find the hanging request @@ -1592,7 +1578,6 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled) }

__unwind_incomplete_requests(parent); -out_put: intel_context_put(parent); }

@@ -2531,12 +2516,6 @@ static void guc_context_cancel_request(struct intel_context *ce, true); }

- /* - * XXX: Racey if context is reset, see comment in - * __guc_reset_context(). - */ - flush_work(&ce_to_guc(ce)->ct.requests.worker); - guc_context_unblock(block_context); intel_context_put(ce); } @@ -3971,12 +3950,7 @@ static void guc_handle_context_reset(struct intel_guc *guc, { trace_intel_context_reset(ce);

- /* - * XXX: Racey if request cancellation has occurred, see comment in - * __guc_reset_context(). - */ - if (likely(!intel_context_is_banned(ce) && - !context_blocked(ce))) { + if (likely(!intel_context_is_banned(ce))) { capture_error_state(guc, ce); guc_context_replay(ce); } else {