const struct intel_engine_cs *engine,
const struct intel_ring *ring,
bool close);
+static void
+__execlists_update_reg_state(const struct intel_context *ce,
+ const struct intel_engine_cs *engine);
static void mark_eio(struct i915_request *rq)
{
i915_request_mark_complete(rq);
}
+static struct i915_request *active_request(struct i915_request *rq)
+{
+ const struct intel_context * const ce = rq->hw_context;
+ struct i915_request *active = NULL;
+ struct list_head *list;
+
+ if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+ return rq;
+
+ rcu_read_lock();
+ list = &rcu_dereference(rq->timeline)->requests;
+ list_for_each_entry_from_reverse(rq, list, link) {
+ if (i915_request_completed(rq))
+ break;
+
+ if (rq->hw_context != ce)
+ break;
+
+ active = rq;
+ }
+ rcu_read_unlock();
+
+ return active;
+}
+
static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
{
return (i915_ggtt_offset(engine->status_page.vma) +
tasklet_schedule(&ve->base.execlists.tasklet);
}
+static void restore_default_state(struct intel_context *ce,
+ struct intel_engine_cs *engine)
+{
+ u32 *regs = ce->lrc_reg_state;
+
+ if (engine->pinned_default_state)
+ memcpy(regs, /* skip restoring the vanilla PPHWSP */
+ engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
+ engine->context_size - PAGE_SIZE);
+
+ execlists_init_reg_state(regs, ce, engine, ce->ring, false);
+}
+
+static void reset_active(struct i915_request *rq,
+ struct intel_engine_cs *engine)
+{
+ struct intel_context * const ce = rq->hw_context;
+
+ /*
+ * The executing context has been cancelled. We want to prevent
+ * further execution along this context and propagate the error on
+ * to anything depending on its results.
+ *
+ * In __i915_request_submit(), we apply the -EIO and remove the
+ * requests' payloads for any banned requests. But first, we must
+ * rewind the context back to the start of the incomplete request so
+ * that we do not jump back into the middle of the batch.
+ *
+ * We preserve the breadcrumbs and semaphores of the incomplete
+ * requests so that inter-timeline dependencies (i.e other timelines)
+ * remain correctly ordered. And we defer to __i915_request_submit()
+ * so that all asynchronous waits are correctly handled.
+ */
+ GEM_TRACE("%s(%s): { rq=%llx:%lld }\n",
+ __func__, engine->name, rq->fence.context, rq->fence.seqno);
+
+ /* On resubmission of the active request, payload will be scrubbed */
+ rq = active_request(rq);
+ if (rq)
+ ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
+ else
+ ce->ring->head = ce->ring->tail;
+ intel_ring_update_space(ce->ring);
+
+ /* Scrub the context image to prevent replaying the previous batch */
+ restore_default_state(ce, engine);
+ __execlists_update_reg_state(ce, engine);
+
+ /* We've switched away, so this should be a no-op, but intent matters */
+ ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+}
+
static inline void
__execlists_schedule_out(struct i915_request *rq,
struct intel_engine_cs * const engine)
execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
intel_gt_pm_put(engine->gt);
+ if (unlikely(i915_gem_context_is_banned(ce->gem_context)))
+ reset_active(rq, engine);
+
/*
* If this is part of a virtual engine, its next request may
* have been blocked waiting for access to the active context.
if (!rq)
return 0;
+ /* Force a fast reset for terminated contexts (ignoring sysfs!) */
+ if (unlikely(i915_gem_context_is_banned(rq->gem_context)))
+ return 1;
+
return READ_ONCE(engine->props.preempt_timeout_ms);
}
&execlists->csb_status[reset_value]);
}
-static struct i915_request *active_request(struct i915_request *rq)
-{
- const struct intel_context * const ce = rq->hw_context;
- struct i915_request *active = NULL;
- struct list_head *list;
-
- if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
- return rq;
-
- list = &i915_request_active_timeline(rq)->requests;
- list_for_each_entry_from_reverse(rq, list, link) {
- if (i915_request_completed(rq))
- break;
-
- if (rq->hw_context != ce)
- break;
-
- active = rq;
- }
-
- return active;
-}
-
static void __execlists_reset_reg_state(const struct intel_context *ce,
const struct intel_engine_cs *engine)
{
struct intel_engine_execlists * const execlists = &engine->execlists;
struct intel_context *ce;
struct i915_request *rq;
- u32 *regs;
mb(); /* paranoia: read the CSB pointers from after the reset */
clflush(execlists->csb_write);
* to recreate its own state.
*/
GEM_BUG_ON(!intel_context_is_pinned(ce));
- regs = ce->lrc_reg_state;
- if (engine->pinned_default_state) {
- memcpy(regs, /* skip restoring the vanilla PPHWSP */
- engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
- engine->context_size - PAGE_SIZE);
- }
- execlists_init_reg_state(regs, ce, engine, ce->ring, false);
+ restore_default_state(ce, engine);
out_replay:
GEM_TRACE("%s replay {head:%04x, tail:%04x\n",
* future request will be after userspace has had the opportunity
* to recreate its own state.
*/
- if (scrub) {
- u32 *regs = ce->lrc_reg_state;
-
- if (engine->pinned_default_state) {
- memcpy(regs, /* skip restoring the vanilla PPHWSP */
- engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
- engine->context_size - PAGE_SIZE);
- }
- execlists_init_reg_state(regs, ce, engine, ce->ring, false);
- }
+ if (scrub)
+ restore_default_state(ce, engine);
/* Rerun the request; its payload has been neutered (if guilty). */
ce->ring->head = head;
#include <linux/prime_numbers.h>
#include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_heartbeat.h"
#include "gt/intel_reset.h"
#include "i915_selftest.h"
goto err_client_b;
}
+struct live_preempt_cancel {
+ struct intel_engine_cs *engine;
+ struct preempt_client a, b;
+};
+
+static int __cancel_active0(struct live_preempt_cancel *arg)
+{
+ struct i915_request *rq;
+ struct igt_live_test t;
+ int err;
+
+ /* Preempt cancel of ELSP0 */
+ GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+ if (igt_live_test_begin(&t, arg->engine->i915,
+ __func__, arg->engine->name))
+ return -EIO;
+
+ clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+ rq = spinner_create_request(&arg->a.spin,
+ arg->a.ctx, arg->engine,
+ MI_ARB_CHECK);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+
+ i915_request_get(rq);
+ i915_request_add(rq);
+ if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
+ err = -EIO;
+ goto out;
+ }
+
+ i915_gem_context_set_banned(arg->a.ctx);
+ err = intel_engine_pulse(arg->engine);
+ if (err)
+ goto out;
+
+ if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+ err = -EIO;
+ goto out;
+ }
+
+ if (rq->fence.error != -EIO) {
+ pr_err("Cancelled inflight0 request did not report -EIO\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+out:
+ i915_request_put(rq);
+ if (igt_live_test_end(&t))
+ err = -EIO;
+ return err;
+}
+
+static int __cancel_active1(struct live_preempt_cancel *arg)
+{
+ struct i915_request *rq[2] = {};
+ struct igt_live_test t;
+ int err;
+
+ /* Preempt cancel of ELSP1 */
+ GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+ if (igt_live_test_begin(&t, arg->engine->i915,
+ __func__, arg->engine->name))
+ return -EIO;
+
+ clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+ rq[0] = spinner_create_request(&arg->a.spin,
+ arg->a.ctx, arg->engine,
+ MI_NOOP); /* no preemption */
+ if (IS_ERR(rq[0]))
+ return PTR_ERR(rq[0]);
+
+ i915_request_get(rq[0]);
+ i915_request_add(rq[0]);
+ if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
+ err = -EIO;
+ goto out;
+ }
+
+ clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
+ rq[1] = spinner_create_request(&arg->b.spin,
+ arg->b.ctx, arg->engine,
+ MI_ARB_CHECK);
+ if (IS_ERR(rq[1])) {
+ err = PTR_ERR(rq[1]);
+ goto out;
+ }
+
+ i915_request_get(rq[1]);
+ err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
+ i915_request_add(rq[1]);
+ if (err)
+ goto out;
+
+ i915_gem_context_set_banned(arg->b.ctx);
+ err = intel_engine_pulse(arg->engine);
+ if (err)
+ goto out;
+
+ igt_spinner_end(&arg->a.spin);
+ if (i915_request_wait(rq[1], 0, HZ / 5) < 0) {
+ err = -EIO;
+ goto out;
+ }
+
+ if (rq[0]->fence.error != 0) {
+ pr_err("Normal inflight0 request did not complete\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (rq[1]->fence.error != -EIO) {
+ pr_err("Cancelled inflight1 request did not report -EIO\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+out:
+ i915_request_put(rq[1]);
+ i915_request_put(rq[0]);
+ if (igt_live_test_end(&t))
+ err = -EIO;
+ return err;
+}
+
+static int __cancel_queued(struct live_preempt_cancel *arg)
+{
+ struct i915_request *rq[3] = {};
+ struct igt_live_test t;
+ int err;
+
+ /* Full ELSP and one in the wings */
+ GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+ if (igt_live_test_begin(&t, arg->engine->i915,
+ __func__, arg->engine->name))
+ return -EIO;
+
+ clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+ rq[0] = spinner_create_request(&arg->a.spin,
+ arg->a.ctx, arg->engine,
+ MI_ARB_CHECK);
+ if (IS_ERR(rq[0]))
+ return PTR_ERR(rq[0]);
+
+ i915_request_get(rq[0]);
+ i915_request_add(rq[0]);
+ if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
+ err = -EIO;
+ goto out;
+ }
+
+ clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
+ rq[1] = igt_request_alloc(arg->b.ctx, arg->engine);
+ if (IS_ERR(rq[1])) {
+ err = PTR_ERR(rq[1]);
+ goto out;
+ }
+
+ i915_request_get(rq[1]);
+ err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
+ i915_request_add(rq[1]);
+ if (err)
+ goto out;
+
+ rq[2] = spinner_create_request(&arg->b.spin,
+ arg->a.ctx, arg->engine,
+ MI_ARB_CHECK);
+ if (IS_ERR(rq[2])) {
+ err = PTR_ERR(rq[2]);
+ goto out;
+ }
+
+ i915_request_get(rq[2]);
+ err = i915_request_await_dma_fence(rq[2], &rq[1]->fence);
+ i915_request_add(rq[2]);
+ if (err)
+ goto out;
+
+ i915_gem_context_set_banned(arg->a.ctx);
+ err = intel_engine_pulse(arg->engine);
+ if (err)
+ goto out;
+
+ if (i915_request_wait(rq[2], 0, HZ / 5) < 0) {
+ err = -EIO;
+ goto out;
+ }
+
+ if (rq[0]->fence.error != -EIO) {
+ pr_err("Cancelled inflight0 request did not report -EIO\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (rq[1]->fence.error != 0) {
+ pr_err("Normal inflight1 request did not complete\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (rq[2]->fence.error != -EIO) {
+ pr_err("Cancelled queued request did not report -EIO\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+out:
+ i915_request_put(rq[2]);
+ i915_request_put(rq[1]);
+ i915_request_put(rq[0]);
+ if (igt_live_test_end(&t))
+ err = -EIO;
+ return err;
+}
+
+static int __cancel_hostile(struct live_preempt_cancel *arg)
+{
+ struct i915_request *rq;
+ int err;
+
+ /* Preempt cancel non-preemptible spinner in ELSP0 */
+ if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT)
+ return 0;
+
+ GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+ clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+ rq = spinner_create_request(&arg->a.spin,
+ arg->a.ctx, arg->engine,
+ MI_NOOP); /* preemption disabled */
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+
+ i915_request_get(rq);
+ i915_request_add(rq);
+ if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
+ err = -EIO;
+ goto out;
+ }
+
+ i915_gem_context_set_banned(arg->a.ctx);
+ err = intel_engine_pulse(arg->engine); /* force reset */
+ if (err)
+ goto out;
+
+ if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+ err = -EIO;
+ goto out;
+ }
+
+ if (rq->fence.error != -EIO) {
+ pr_err("Cancelled inflight0 request did not report -EIO\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+out:
+ i915_request_put(rq);
+ if (igt_flush_test(arg->engine->i915))
+ err = -EIO;
+ return err;
+}
+
+static int live_preempt_cancel(void *arg)
+{
+ struct intel_gt *gt = arg;
+ struct live_preempt_cancel data;
+ enum intel_engine_id id;
+ int err = -ENOMEM;
+
+ /*
+ * To cancel an inflight context, we need to first remove it from the
+ * GPU. That sounds like preemption! Plus a little bit of bookkeeping.
+ */
+
+ if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+ return 0;
+
+ if (preempt_client_init(gt, &data.a))
+ return -ENOMEM;
+ if (preempt_client_init(gt, &data.b))
+ goto err_client_a;
+
+ for_each_engine(data.engine, gt, id) {
+ if (!intel_engine_has_preemption(data.engine))
+ continue;
+
+ err = __cancel_active0(&data);
+ if (err)
+ goto err_wedged;
+
+ err = __cancel_active1(&data);
+ if (err)
+ goto err_wedged;
+
+ err = __cancel_queued(&data);
+ if (err)
+ goto err_wedged;
+
+ err = __cancel_hostile(&data);
+ if (err)
+ goto err_wedged;
+ }
+
+ err = 0;
+err_client_b:
+ preempt_client_fini(&data.b);
+err_client_a:
+ preempt_client_fini(&data.a);
+ return err;
+
+err_wedged:
+ GEM_TRACE_DUMP();
+ igt_spinner_end(&data.b.spin);
+ igt_spinner_end(&data.a.spin);
+ intel_gt_set_wedged(gt);
+ goto err_client_b;
+}
+
static int live_suppress_self_preempt(void *arg)
{
struct intel_gt *gt = arg;
SUBTEST(live_preempt),
SUBTEST(live_late_preempt),
SUBTEST(live_nopreempt),
+ SUBTEST(live_preempt_cancel),
SUBTEST(live_suppress_self_preempt),
SUBTEST(live_suppress_wait_preempt),
SUBTEST(live_chain_preempt),