diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/selftest_hangcheck.c')
-rw-r--r-- | drivers/gpu/drm/i915/gt/selftest_hangcheck.c | 1919 |
1 files changed, 1919 insertions, 0 deletions
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c new file mode 100644 index 000000000000..acd33aa46068 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -0,0 +1,1919 @@ +/* + * Copyright © 2016 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#include <linux/kthread.h> + +#include "i915_selftest.h" +#include "selftests/i915_random.h" +#include "selftests/igt_flush_test.h" +#include "selftests/igt_reset.h" +#include "selftests/igt_wedge_me.h" + +#include "selftests/mock_context.h" +#include "selftests/mock_drm.h" + +#define IGT_IDLE_TIMEOUT 50 /* ms; time to wait after flushing between tests */ + +struct hang { + struct drm_i915_private *i915; + struct drm_i915_gem_object *hws; + struct drm_i915_gem_object *obj; + struct i915_gem_context *ctx; + u32 *seqno; + u32 *batch; +}; + +static int hang_init(struct hang *h, struct drm_i915_private *i915) +{ + void *vaddr; + int err; + + memset(h, 0, sizeof(*h)); + h->i915 = i915; + + h->ctx = kernel_context(i915); + if (IS_ERR(h->ctx)) + return PTR_ERR(h->ctx); + + GEM_BUG_ON(i915_gem_context_is_bannable(h->ctx)); + + h->hws = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(h->hws)) { + err = PTR_ERR(h->hws); + goto err_ctx; + } + + h->obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(h->obj)) { + err = PTR_ERR(h->obj); + goto err_hws; + } + + i915_gem_object_set_cache_coherency(h->hws, I915_CACHE_LLC); + vaddr = i915_gem_object_pin_map(h->hws, I915_MAP_WB); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto err_obj; + } + h->seqno = memset(vaddr, 0xff, PAGE_SIZE); + + vaddr = i915_gem_object_pin_map(h->obj, + i915_coherent_map_type(i915)); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto err_unpin_hws; + } + h->batch = vaddr; + + return 0; + +err_unpin_hws: + i915_gem_object_unpin_map(h->hws); +err_obj: + i915_gem_object_put(h->obj); +err_hws: + i915_gem_object_put(h->hws); +err_ctx: + kernel_context_close(h->ctx); + return err; +} + +static u64 hws_address(const struct i915_vma *hws, + const struct i915_request *rq) +{ + return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context); +} + +static int move_to_active(struct i915_vma *vma, + struct i915_request *rq, + unsigned int flags) +{ + int err; + + err = i915_vma_move_to_active(vma, rq, flags); + if (err) + return err; + + if (!i915_gem_object_has_active_reference(vma->obj)) { + i915_gem_object_get(vma->obj); + i915_gem_object_set_active_reference(vma->obj); + } + + return 0; +} + +static struct i915_request * +hang_create_request(struct hang *h, struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = h->i915; + struct i915_address_space *vm = + h->ctx->ppgtt ? &h->ctx->ppgtt->vm : &i915->ggtt.vm; + struct i915_request *rq = NULL; + struct i915_vma *hws, *vma; + unsigned int flags; + u32 *batch; + int err; + + if (i915_gem_object_is_active(h->obj)) { + struct drm_i915_gem_object *obj; + void *vaddr; + + obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + vaddr = i915_gem_object_pin_map(obj, + i915_coherent_map_type(h->i915)); + if (IS_ERR(vaddr)) { + i915_gem_object_put(obj); + return ERR_CAST(vaddr); + } + + i915_gem_object_unpin_map(h->obj); + i915_gem_object_put(h->obj); + + h->obj = obj; + h->batch = vaddr; + } + + vma = i915_vma_instance(h->obj, vm, NULL); + if (IS_ERR(vma)) + return ERR_CAST(vma); + + hws = i915_vma_instance(h->hws, vm, NULL); + if (IS_ERR(hws)) + return ERR_CAST(hws); + + err = i915_vma_pin(vma, 0, 0, PIN_USER); + if (err) + return ERR_PTR(err); + + err = i915_vma_pin(hws, 0, 0, PIN_USER); + if (err) + goto unpin_vma; + + rq = i915_request_alloc(engine, h->ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto unpin_hws; + } + + err = move_to_active(vma, rq, 0); + if (err) + goto cancel_rq; + + err = move_to_active(hws, rq, 0); + if (err) + goto cancel_rq; + + batch = h->batch; + if (INTEL_GEN(i915) >= 8) { + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = lower_32_bits(hws_address(hws, rq)); + *batch++ = upper_32_bits(hws_address(hws, rq)); + *batch++ = rq->fence.seqno; + *batch++ = MI_ARB_CHECK; + + memset(batch, 0, 1024); + batch += 1024 / sizeof(*batch); + + *batch++ = MI_ARB_CHECK; + *batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1; + *batch++ = lower_32_bits(vma->node.start); + *batch++ = upper_32_bits(vma->node.start); + } else if (INTEL_GEN(i915) >= 6) { + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = 0; + *batch++ = lower_32_bits(hws_address(hws, rq)); + *batch++ = rq->fence.seqno; + *batch++ = MI_ARB_CHECK; + + memset(batch, 0, 1024); + batch += 1024 / sizeof(*batch); + + *batch++ = MI_ARB_CHECK; + *batch++ = MI_BATCH_BUFFER_START | 1 << 8; + *batch++ = lower_32_bits(vma->node.start); + } else if (INTEL_GEN(i915) >= 4) { + *batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *batch++ = 0; + *batch++ = lower_32_bits(hws_address(hws, rq)); + *batch++ = rq->fence.seqno; + *batch++ = MI_ARB_CHECK; + + memset(batch, 0, 1024); + batch += 1024 / sizeof(*batch); + + *batch++ = MI_ARB_CHECK; + *batch++ = MI_BATCH_BUFFER_START | 2 << 6; + *batch++ = lower_32_bits(vma->node.start); + } else { + *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; + *batch++ = lower_32_bits(hws_address(hws, rq)); + *batch++ = rq->fence.seqno; + *batch++ = MI_ARB_CHECK; + + memset(batch, 0, 1024); + batch += 1024 / sizeof(*batch); + + *batch++ = MI_ARB_CHECK; + *batch++ = MI_BATCH_BUFFER_START | 2 << 6; + *batch++ = lower_32_bits(vma->node.start); + } + *batch++ = MI_BATCH_BUFFER_END; /* not reached */ + i915_gem_chipset_flush(h->i915); + + if (rq->engine->emit_init_breadcrumb) { + err = rq->engine->emit_init_breadcrumb(rq); + if (err) + goto cancel_rq; + } + + flags = 0; + if (INTEL_GEN(vm->i915) <= 5) + flags |= I915_DISPATCH_SECURE; + + err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags); + +cancel_rq: + if (err) { + i915_request_skip(rq, err); + i915_request_add(rq); + } +unpin_hws: + i915_vma_unpin(hws); +unpin_vma: + i915_vma_unpin(vma); + return err ? ERR_PTR(err) : rq; +} + +static u32 hws_seqno(const struct hang *h, const struct i915_request *rq) +{ + return READ_ONCE(h->seqno[rq->fence.context % (PAGE_SIZE/sizeof(u32))]); +} + +static void hang_fini(struct hang *h) +{ + *h->batch = MI_BATCH_BUFFER_END; + i915_gem_chipset_flush(h->i915); + + i915_gem_object_unpin_map(h->obj); + i915_gem_object_put(h->obj); + + i915_gem_object_unpin_map(h->hws); + i915_gem_object_put(h->hws); + + kernel_context_close(h->ctx); + + igt_flush_test(h->i915, I915_WAIT_LOCKED); +} + +static bool wait_until_running(struct hang *h, struct i915_request *rq) +{ + return !(wait_for_us(i915_seqno_passed(hws_seqno(h, rq), + rq->fence.seqno), + 10) && + wait_for(i915_seqno_passed(hws_seqno(h, rq), + rq->fence.seqno), + 1000)); +} + +static int igt_hang_sanitycheck(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_request *rq; + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct hang h; + int err; + + /* Basic check that we can execute our hanging batch */ + + mutex_lock(&i915->drm.struct_mutex); + err = hang_init(&h, i915); + if (err) + goto unlock; + + for_each_engine(engine, i915, id) { + struct igt_wedge_me w; + long timeout; + + if (!intel_engine_can_store_dword(engine)) + continue; + + rq = hang_create_request(&h, engine); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + pr_err("Failed to create request for %s, err=%d\n", + engine->name, err); + goto fini; + } + + i915_request_get(rq); + + *h.batch = MI_BATCH_BUFFER_END; + i915_gem_chipset_flush(i915); + + i915_request_add(rq); + + timeout = 0; + igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/) + timeout = i915_request_wait(rq, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + if (i915_reset_failed(i915)) + timeout = -EIO; + + i915_request_put(rq); + + if (timeout < 0) { + err = timeout; + pr_err("Wait for request failed on %s, err=%d\n", + engine->name, err); + goto fini; + } + } + +fini: + hang_fini(&h); +unlock: + mutex_unlock(&i915->drm.struct_mutex); + return err; +} + +static int igt_global_reset(void *arg) +{ + struct drm_i915_private *i915 = arg; + unsigned int reset_count; + int err = 0; + + /* Check that we can issue a global GPU reset */ + + igt_global_reset_lock(i915); + + reset_count = i915_reset_count(&i915->gpu_error); + + i915_reset(i915, ALL_ENGINES, NULL); + + if (i915_reset_count(&i915->gpu_error) == reset_count) { + pr_err("No GPU reset recorded!\n"); + err = -EINVAL; + } + + igt_global_reset_unlock(i915); + + if (i915_reset_failed(i915)) + err = -EIO; + + return err; +} + +static int igt_wedged_reset(void *arg) +{ + struct drm_i915_private *i915 = arg; + intel_wakeref_t wakeref; + + /* Check that we can recover a wedged device with a GPU reset */ + + igt_global_reset_lock(i915); + wakeref = intel_runtime_pm_get(i915); + + i915_gem_set_wedged(i915); + + GEM_BUG_ON(!i915_reset_failed(i915)); + i915_reset(i915, ALL_ENGINES, NULL); + + intel_runtime_pm_put(i915, wakeref); + igt_global_reset_unlock(i915); + + return i915_reset_failed(i915) ? -EIO : 0; +} + +static bool wait_for_idle(struct intel_engine_cs *engine) +{ + return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; +} + +static int igt_reset_nop(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + unsigned int reset_count, count; + enum intel_engine_id id; + intel_wakeref_t wakeref; + struct drm_file *file; + IGT_TIMEOUT(end_time); + int err = 0; + + /* Check that we can reset during non-user portions of requests */ + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&i915->drm.struct_mutex); + ctx = live_context(i915, file); + mutex_unlock(&i915->drm.struct_mutex); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + + i915_gem_context_clear_bannable(ctx); + wakeref = intel_runtime_pm_get(i915); + reset_count = i915_reset_count(&i915->gpu_error); + count = 0; + do { + mutex_lock(&i915->drm.struct_mutex); + for_each_engine(engine, i915, id) { + int i; + + for (i = 0; i < 16; i++) { + struct i915_request *rq; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + break; + } + + i915_request_add(rq); + } + } + mutex_unlock(&i915->drm.struct_mutex); + + igt_global_reset_lock(i915); + i915_reset(i915, ALL_ENGINES, NULL); + igt_global_reset_unlock(i915); + if (i915_reset_failed(i915)) { + err = -EIO; + break; + } + + if (i915_reset_count(&i915->gpu_error) != + reset_count + ++count) { + pr_err("Full GPU reset not recorded!\n"); + err = -EINVAL; + break; + } + + if (!i915_reset_flush(i915)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("%s failed to idle after reset\n", + engine->name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } + + err = igt_flush_test(i915, 0); + if (err) + break; + } while (time_before(jiffies, end_time)); + pr_info("%s: %d resets\n", __func__, count); + + mutex_lock(&i915->drm.struct_mutex); + err = igt_flush_test(i915, I915_WAIT_LOCKED); + mutex_unlock(&i915->drm.struct_mutex); + + intel_runtime_pm_put(i915, wakeref); + +out: + mock_file_free(i915, file); + if (i915_reset_failed(i915)) + err = -EIO; + return err; +} + +static int igt_reset_nop_engine(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + enum intel_engine_id id; + intel_wakeref_t wakeref; + struct drm_file *file; + int err = 0; + + /* Check that we can engine-reset during non-user portions */ + + if (!intel_has_reset_engine(i915)) + return 0; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&i915->drm.struct_mutex); + ctx = live_context(i915, file); + mutex_unlock(&i915->drm.struct_mutex); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } + + i915_gem_context_clear_bannable(ctx); + wakeref = intel_runtime_pm_get(i915); + for_each_engine(engine, i915, id) { + unsigned int reset_count, reset_engine_count; + unsigned int count; + IGT_TIMEOUT(end_time); + + reset_count = i915_reset_count(&i915->gpu_error); + reset_engine_count = i915_reset_engine_count(&i915->gpu_error, + engine); + count = 0; + + set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + do { + int i; + + if (!wait_for_idle(engine)) { + pr_err("%s failed to idle before reset\n", + engine->name); + err = -EIO; + break; + } + + mutex_lock(&i915->drm.struct_mutex); + for (i = 0; i < 16; i++) { + struct i915_request *rq; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + break; + } + + i915_request_add(rq); + } + mutex_unlock(&i915->drm.struct_mutex); + + err = i915_reset_engine(engine, NULL); + if (err) { + pr_err("i915_reset_engine failed\n"); + break; + } + + if (i915_reset_count(&i915->gpu_error) != reset_count) { + pr_err("Full GPU reset recorded! (engine reset expected)\n"); + err = -EINVAL; + break; + } + + if (i915_reset_engine_count(&i915->gpu_error, engine) != + reset_engine_count + ++count) { + pr_err("%s engine reset not recorded!\n", + engine->name); + err = -EINVAL; + break; + } + + if (!i915_reset_flush(i915)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("%s failed to idle after reset\n", + engine->name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } + } while (time_before(jiffies, end_time)); + clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + pr_info("%s(%s): %d resets\n", __func__, engine->name, count); + + if (err) + break; + + err = igt_flush_test(i915, 0); + if (err) + break; + } + + mutex_lock(&i915->drm.struct_mutex); + err = igt_flush_test(i915, I915_WAIT_LOCKED); + mutex_unlock(&i915->drm.struct_mutex); + + intel_runtime_pm_put(i915, wakeref); +out: + mock_file_free(i915, file); + if (i915_reset_failed(i915)) + err = -EIO; + return err; +} + +static int __igt_reset_engine(struct drm_i915_private *i915, bool active) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + struct hang h; + int err = 0; + + /* Check that we can issue an engine reset on an idle engine (no-op) */ + + if (!intel_has_reset_engine(i915)) + return 0; + + if (active) { + mutex_lock(&i915->drm.struct_mutex); + err = hang_init(&h, i915); + mutex_unlock(&i915->drm.struct_mutex); + if (err) + return err; + } + + for_each_engine(engine, i915, id) { + unsigned int reset_count, reset_engine_count; + IGT_TIMEOUT(end_time); + + if (active && !intel_engine_can_store_dword(engine)) + continue; + + if (!wait_for_idle(engine)) { + pr_err("%s failed to idle before reset\n", + engine->name); + err = -EIO; + break; + } + + reset_count = i915_reset_count(&i915->gpu_error); + reset_engine_count = i915_reset_engine_count(&i915->gpu_error, + engine); + + set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + do { + if (active) { + struct i915_request *rq; + + mutex_lock(&i915->drm.struct_mutex); + rq = hang_create_request(&h, engine); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + mutex_unlock(&i915->drm.struct_mutex); + break; + } + + i915_request_get(rq); + i915_request_add(rq); + mutex_unlock(&i915->drm.struct_mutex); + + if (!wait_until_running(&h, rq)) { + struct drm_printer p = drm_info_printer(i915->drm.dev); + + pr_err("%s: Failed to start request %llx, at %x\n", + __func__, rq->fence.seqno, hws_seqno(&h, rq)); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + i915_request_put(rq); + err = -EIO; + break; + } + + i915_request_put(rq); + } + + err = i915_reset_engine(engine, NULL); + if (err) { + pr_err("i915_reset_engine failed\n"); + break; + } + + if (i915_reset_count(&i915->gpu_error) != reset_count) { + pr_err("Full GPU reset recorded! (engine reset expected)\n"); + err = -EINVAL; + break; + } + + if (i915_reset_engine_count(&i915->gpu_error, engine) != + ++reset_engine_count) { + pr_err("%s engine reset not recorded!\n", + engine->name); + err = -EINVAL; + break; + } + + if (!i915_reset_flush(i915)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("%s failed to idle after reset\n", + engine->name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } + } while (time_before(jiffies, end_time)); + clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + + if (err) + break; + + err = igt_flush_test(i915, 0); + if (err) + break; + } + + if (i915_reset_failed(i915)) + err = -EIO; + + if (active) { + mutex_lock(&i915->drm.struct_mutex); + hang_fini(&h); + mutex_unlock(&i915->drm.struct_mutex); + } + + return err; +} + +static int igt_reset_idle_engine(void *arg) +{ + return __igt_reset_engine(arg, false); +} + +static int igt_reset_active_engine(void *arg) +{ + return __igt_reset_engine(arg, true); +} + +struct active_engine { + struct task_struct *task; + struct intel_engine_cs *engine; + unsigned long resets; + unsigned int flags; +}; + +#define TEST_ACTIVE BIT(0) +#define TEST_OTHERS BIT(1) +#define TEST_SELF BIT(2) +#define TEST_PRIORITY BIT(3) + +static int active_request_put(struct i915_request *rq) +{ + int err = 0; + + if (!rq) + return 0; + + if (i915_request_wait(rq, 0, 5 * HZ) < 0) { + GEM_TRACE("%s timed out waiting for completion of fence %llx:%lld\n", + rq->engine->name, + rq->fence.context, + rq->fence.seqno); + GEM_TRACE_DUMP(); + + i915_gem_set_wedged(rq->i915); + err = -EIO; + } + + i915_request_put(rq); + + return err; +} + +static int active_engine(void *data) +{ + I915_RND_STATE(prng); + struct active_engine *arg = data; + struct intel_engine_cs *engine = arg->engine; + struct i915_request *rq[8] = {}; + struct i915_gem_context *ctx[ARRAY_SIZE(rq)]; + struct drm_file *file; + unsigned long count = 0; + int err = 0; + + file = mock_file(engine->i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + for (count = 0; count < ARRAY_SIZE(ctx); count++) { + mutex_lock(&engine->i915->drm.struct_mutex); + ctx[count] = live_context(engine->i915, file); + mutex_unlock(&engine->i915->drm.struct_mutex); + if (IS_ERR(ctx[count])) { + err = PTR_ERR(ctx[count]); + while (--count) + i915_gem_context_put(ctx[count]); + goto err_file; + } + } + + while (!kthread_should_stop()) { + unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1); + struct i915_request *old = rq[idx]; + struct i915_request *new; + + mutex_lock(&engine->i915->drm.struct_mutex); + new = i915_request_alloc(engine, ctx[idx]); + if (IS_ERR(new)) { + mutex_unlock(&engine->i915->drm.struct_mutex); + err = PTR_ERR(new); + break; + } + + if (arg->flags & TEST_PRIORITY) + ctx[idx]->sched.priority = + i915_prandom_u32_max_state(512, &prng); + + rq[idx] = i915_request_get(new); + i915_request_add(new); + mutex_unlock(&engine->i915->drm.struct_mutex); + + err = active_request_put(old); + if (err) + break; + + cond_resched(); + } + + for (count = 0; count < ARRAY_SIZE(rq); count++) { + int err__ = active_request_put(rq[count]); + + /* Keep the first error */ + if (!err) + err = err__; + } + +err_file: + mock_file_free(engine->i915, file); + return err; +} + +static int __igt_reset_engines(struct drm_i915_private *i915, + const char *test_name, + unsigned int flags) +{ + struct intel_engine_cs *engine, *other; + enum intel_engine_id id, tmp; + struct hang h; + int err = 0; + + /* Check that issuing a reset on one engine does not interfere + * with any other engine. + */ + + if (!intel_has_reset_engine(i915)) + return 0; + + if (flags & TEST_ACTIVE) { + mutex_lock(&i915->drm.struct_mutex); + err = hang_init(&h, i915); + mutex_unlock(&i915->drm.struct_mutex); + if (err) + return err; + + if (flags & TEST_PRIORITY) + h.ctx->sched.priority = 1024; + } + + for_each_engine(engine, i915, id) { + struct active_engine threads[I915_NUM_ENGINES] = {}; + unsigned long global = i915_reset_count(&i915->gpu_error); + unsigned long count = 0, reported; + IGT_TIMEOUT(end_time); + + if (flags & TEST_ACTIVE && + !intel_engine_can_store_dword(engine)) + continue; + + if (!wait_for_idle(engine)) { + pr_err("i915_reset_engine(%s:%s): failed to idle before reset\n", + engine->name, test_name); + err = -EIO; + break; + } + + memset(threads, 0, sizeof(threads)); + for_each_engine(other, i915, tmp) { + struct task_struct *tsk; + + threads[tmp].resets = + i915_reset_engine_count(&i915->gpu_error, + other); + + if (!(flags & TEST_OTHERS)) + continue; + + if (other == engine && !(flags & TEST_SELF)) + continue; + + threads[tmp].engine = other; + threads[tmp].flags = flags; + + tsk = kthread_run(active_engine, &threads[tmp], + "igt/%s", other->name); + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + goto unwind; + } + + threads[tmp].task = tsk; + get_task_struct(tsk); + } + + set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + do { + struct i915_request *rq = NULL; + + if (flags & TEST_ACTIVE) { + mutex_lock(&i915->drm.struct_mutex); + rq = hang_create_request(&h, engine); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + mutex_unlock(&i915->drm.struct_mutex); + break; + } + + i915_request_get(rq); + i915_request_add(rq); + mutex_unlock(&i915->drm.struct_mutex); + + if (!wait_until_running(&h, rq)) { + struct drm_printer p = drm_info_printer(i915->drm.dev); + + pr_err("%s: Failed to start request %llx, at %x\n", + __func__, rq->fence.seqno, hws_seqno(&h, rq)); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + i915_request_put(rq); + err = -EIO; + break; + } + } + + err = i915_reset_engine(engine, NULL); + if (err) { + pr_err("i915_reset_engine(%s:%s): failed, err=%d\n", + engine->name, test_name, err); + break; + } + + count++; + + if (rq) { + if (i915_request_wait(rq, 0, HZ / 5) < 0) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("i915_reset_engine(%s:%s):" + " failed to complete request after reset\n", + engine->name, test_name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + i915_request_put(rq); + + GEM_TRACE_DUMP(); + i915_gem_set_wedged(i915); + err = -EIO; + break; + } + + i915_request_put(rq); + } + + if (!(flags & TEST_SELF) && !wait_for_idle(engine)) { + struct drm_printer p = + drm_info_printer(i915->drm.dev); + + pr_err("i915_reset_engine(%s:%s):" + " failed to idle after reset\n", + engine->name, test_name); + intel_engine_dump(engine, &p, + "%s\n", engine->name); + + err = -EIO; + break; + } + } while (time_before(jiffies, end_time)); + clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + pr_info("i915_reset_engine(%s:%s): %lu resets\n", + engine->name, test_name, count); + + reported = i915_reset_engine_count(&i915->gpu_error, engine); + reported -= threads[engine->id].resets; + if (reported != count) { + pr_err("i915_reset_engine(%s:%s): reset %lu times, but reported %lu\n", + engine->name, test_name, count, reported); + if (!err) + err = -EINVAL; + } + +unwind: + for_each_engine(other, i915, tmp) { + int ret; + + if (!threads[tmp].task) + continue; + + ret = kthread_stop(threads[tmp].task); + if (ret) { + pr_err("kthread for other engine %s failed, err=%d\n", + other->name, ret); + if (!err) + err = ret; + } + put_task_struct(threads[tmp].task); + + if (other != engine && + threads[tmp].resets != + i915_reset_engine_count(&i915->gpu_error, other)) { + pr_err("Innocent engine %s was reset (count=%ld)\n", + other->name, + i915_reset_engine_count(&i915->gpu_error, + other) - + threads[tmp].resets); + if (!err) + err = -EINVAL; + } + } + + if (global != i915_reset_count(&i915->gpu_error)) { + pr_err("Global reset (count=%ld)!\n", + i915_reset_count(&i915->gpu_error) - global); + if (!err) + err = -EINVAL; + } + + if (err) + break; + + err = igt_flush_test(i915, 0); + if (err) + break; + } + + if (i915_reset_failed(i915)) + err = -EIO; + + if (flags & TEST_ACTIVE) { + mutex_lock(&i915->drm.struct_mutex); + hang_fini(&h); + mutex_unlock(&i915->drm.struct_mutex); + } + + return err; +} + +static int igt_reset_engines(void *arg) +{ + static const struct { + const char *name; + unsigned int flags; + } phases[] = { + { "idle", 0 }, + { "active", TEST_ACTIVE }, + { "others-idle", TEST_OTHERS }, + { "others-active", TEST_OTHERS | TEST_ACTIVE }, + { + "others-priority", + TEST_OTHERS | TEST_ACTIVE | TEST_PRIORITY + }, + { + "self-priority", + TEST_OTHERS | TEST_ACTIVE | TEST_PRIORITY | TEST_SELF, + }, + { } + }; + struct drm_i915_private *i915 = arg; + typeof(*phases) *p; + int err; + + for (p = phases; p->name; p++) { + if (p->flags & TEST_PRIORITY) { + if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY)) + continue; + } + + err = __igt_reset_engines(arg, p->name, p->flags); + if (err) + return err; + } + + return 0; +} + +static u32 fake_hangcheck(struct drm_i915_private *i915, + intel_engine_mask_t mask) +{ + u32 count = i915_reset_count(&i915->gpu_error); + + i915_reset(i915, mask, NULL); + + return count; +} + +static int igt_reset_wait(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_request *rq; + unsigned int reset_count; + struct hang h; + long timeout; + int err; + + if (!intel_engine_can_store_dword(i915->engine[RCS0])) + return 0; + + /* Check that we detect a stuck waiter and issue a reset */ + + igt_global_reset_lock(i915); + + mutex_lock(&i915->drm.struct_mutex); + err = hang_init(&h, i915); + if (err) + goto unlock; + + rq = hang_create_request(&h, i915->engine[RCS0]); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto fini; + } + + i915_request_get(rq); + i915_request_add(rq); + + if (!wait_until_running(&h, rq)) { + struct drm_printer p = drm_info_printer(i915->drm.dev); + + pr_err("%s: Failed to start request %llx, at %x\n", + __func__, rq->fence.seqno, hws_seqno(&h, rq)); + intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name); + + i915_gem_set_wedged(i915); + + err = -EIO; + goto out_rq; + } + + reset_count = fake_hangcheck(i915, ALL_ENGINES); + + timeout = i915_request_wait(rq, I915_WAIT_LOCKED, 10); + if (timeout < 0) { + pr_err("i915_request_wait failed on a stuck request: err=%ld\n", + timeout); + err = timeout; + goto out_rq; + } + + if (i915_reset_count(&i915->gpu_error) == reset_count) { + pr_err("No GPU reset recorded!\n"); + err = -EINVAL; + goto out_rq; + } + +out_rq: + i915_request_put(rq); +fini: + hang_fini(&h); +unlock: + mutex_unlock(&i915->drm.struct_mutex); + igt_global_reset_unlock(i915); + + if (i915_reset_failed(i915)) + return -EIO; + + return err; +} + +struct evict_vma { + struct completion completion; + struct i915_vma *vma; +}; + +static int evict_vma(void *data) +{ + struct evict_vma *arg = data; + struct i915_address_space *vm = arg->vma->vm; + struct drm_i915_private *i915 = vm->i915; + struct drm_mm_node evict = arg->vma->node; + int err; + + complete(&arg->completion); + + mutex_lock(&i915->drm.struct_mutex); + err = i915_gem_evict_for_node(vm, &evict, 0); + mutex_unlock(&i915->drm.struct_mutex); + + return err; +} + +static int evict_fence(void *data) +{ + struct evict_vma *arg = data; + struct drm_i915_private *i915 = arg->vma->vm->i915; + int err; + + complete(&arg->completion); + + mutex_lock(&i915->drm.struct_mutex); + + /* Mark the fence register as dirty to force the mmio update. */ + err = i915_gem_object_set_tiling(arg->vma->obj, I915_TILING_Y, 512); + if (err) { + pr_err("Invalid Y-tiling settings; err:%d\n", err); + goto out_unlock; + } + + err = i915_vma_pin_fence(arg->vma); + if (err) { + pr_err("Unable to pin Y-tiled fence; err:%d\n", err); + goto out_unlock; + } + + i915_vma_unpin_fence(arg->vma); + +out_unlock: + mutex_unlock(&i915->drm.struct_mutex) |