diff options
Diffstat (limited to 'drivers/gpu/drm/i915/selftests')
-rw-r--r-- | drivers/gpu/drm/i915/selftests/huge_pages.c | 13 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_gem.c | 221 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_gem_coherency.c | 40 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_gem_context.c | 202 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_gem_object.c | 5 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_live_selftests.h | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_request.c | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_sw_fence.c | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/intel_guc.c | 42 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 101 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/intel_lrc.c | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/intel_workarounds.c | 5 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/mock_context.c | 11 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/mock_gtt.c | 2 |
14 files changed, 612 insertions, 55 deletions
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 7efb326badcd..8d03f64eabd7 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -235,6 +235,8 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj) sg = sg_next(sg); } while (1); + i915_sg_trim(st); + obj->mm.madv = I915_MADV_DONTNEED; __i915_gem_object_set_pages(obj, st, sg_page_sizes); @@ -906,7 +908,11 @@ gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val) if (IS_ERR(obj)) return ERR_CAST(obj); - cmd = i915_gem_object_pin_map(obj, I915_MAP_WB); + err = i915_gem_object_set_to_wc_domain(obj, true); + if (err) + goto err; + + cmd = i915_gem_object_pin_map(obj, I915_MAP_WC); if (IS_ERR(cmd)) { err = PTR_ERR(cmd); goto err; @@ -936,13 +942,10 @@ gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val) } *cmd = MI_BATCH_BUFFER_END; + i915_gem_chipset_flush(i915); i915_gem_object_unpin_map(obj); - err = i915_gem_object_set_to_gtt_domain(obj, false); - if (err) - goto err; - batch = i915_vma_instance(obj, vma->vm, NULL); if (IS_ERR(batch)) { err = PTR_ERR(batch); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c new file mode 100644 index 000000000000..d0aa19d17653 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -0,0 +1,221 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#include <linux/random.h> + +#include "../i915_selftest.h" + +#include "mock_context.h" +#include "igt_flush_test.h" + +static int switch_to_context(struct drm_i915_private *i915, + struct i915_gem_context *ctx) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + int err = 0; + + intel_runtime_pm_get(i915); + + for_each_engine(engine, i915, id) { + struct i915_request *rq; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + break; + } + + i915_request_add(rq); + } + + intel_runtime_pm_put(i915); + + return err; +} + +static void trash_stolen(struct drm_i915_private *i915) +{ + struct i915_ggtt *ggtt = &i915->ggtt; + const u64 slot = ggtt->error_capture.start; + const resource_size_t size = resource_size(&i915->dsm); + unsigned long page; + u32 prng = 0x12345678; + + for (page = 0; page < size; page += PAGE_SIZE) { + const dma_addr_t dma = i915->dsm.start + page; + u32 __iomem *s; + int x; + + ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0); + + s = io_mapping_map_atomic_wc(&ggtt->iomap, slot); + for (x = 0; x < PAGE_SIZE / sizeof(u32); x++) { + prng = next_pseudo_random32(prng); + iowrite32(prng, &s[x]); + } + io_mapping_unmap_atomic(s); + } + + ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE); +} + +static void simulate_hibernate(struct drm_i915_private *i915) +{ + intel_runtime_pm_get(i915); + + /* + * As a final sting in the tail, invalidate stolen. Under a real S4, + * stolen is lost and needs to be refilled on resume. However, under + * CI we merely do S4-device testing (as full S4 is too unreliable + * for automated testing across a cluster), so to simulate the effect + * of stolen being trashed across S4, we trash it ourselves. + */ + trash_stolen(i915); + + intel_runtime_pm_put(i915); +} + +static int pm_prepare(struct drm_i915_private *i915) +{ + int err = 0; + + if (i915_gem_suspend(i915)) { + pr_err("i915_gem_suspend failed\n"); + err = -EINVAL; + } + + return err; +} + +static void pm_suspend(struct drm_i915_private *i915) +{ + intel_runtime_pm_get(i915); + + i915_gem_suspend_gtt_mappings(i915); + i915_gem_suspend_late(i915); + + intel_runtime_pm_put(i915); +} + +static void pm_hibernate(struct drm_i915_private *i915) +{ + intel_runtime_pm_get(i915); + + i915_gem_suspend_gtt_mappings(i915); + + i915_gem_freeze(i915); + i915_gem_freeze_late(i915); + + intel_runtime_pm_put(i915); +} + +static void pm_resume(struct drm_i915_private *i915) +{ + /* + * Both suspend and hibernate follow the same wakeup path and assume + * that runtime-pm just works. + */ + intel_runtime_pm_get(i915); + + intel_engines_sanitize(i915); + i915_gem_sanitize(i915); + i915_gem_resume(i915); + + intel_runtime_pm_put(i915); +} + +static int igt_gem_suspend(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_gem_context *ctx; + struct drm_file *file; + int err; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + err = -ENOMEM; + mutex_lock(&i915->drm.struct_mutex); + ctx = live_context(i915, file); + if (!IS_ERR(ctx)) + err = switch_to_context(i915, ctx); + mutex_unlock(&i915->drm.struct_mutex); + if (err) + goto out; + + err = pm_prepare(i915); + if (err) + goto out; + + pm_suspend(i915); + + /* Here be dragons! Note that with S3RST any S3 may become S4! */ + simulate_hibernate(i915); + + pm_resume(i915); + + mutex_lock(&i915->drm.struct_mutex); + err = switch_to_context(i915, ctx); + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; + mutex_unlock(&i915->drm.struct_mutex); +out: + mock_file_free(i915, file); + return err; +} + +static int igt_gem_hibernate(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_gem_context *ctx; + struct drm_file *file; + int err; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + err = -ENOMEM; + mutex_lock(&i915->drm.struct_mutex); + ctx = live_context(i915, file); + if (!IS_ERR(ctx)) + err = switch_to_context(i915, ctx); + mutex_unlock(&i915->drm.struct_mutex); + if (err) + goto out; + + err = pm_prepare(i915); + if (err) + goto out; + + pm_hibernate(i915); + + /* Here be dragons! */ + simulate_hibernate(i915); + + pm_resume(i915); + + mutex_lock(&i915->drm.struct_mutex); + err = switch_to_context(i915, ctx); + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + err = -EIO; + mutex_unlock(&i915->drm.struct_mutex); +out: + mock_file_free(i915, file); + return err; +} + +int i915_gem_live_selftests(struct drm_i915_private *i915) +{ + static const struct i915_subtest tests[] = { + SUBTEST(igt_gem_suspend), + SUBTEST(igt_gem_hibernate), + }; + + return i915_subtests(tests, i915); +} diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c index 3a095c37c120..f7392c1ffe75 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c @@ -33,7 +33,8 @@ static int cpu_set(struct drm_i915_gem_object *obj, { unsigned int needs_clflush; struct page *page; - u32 *map; + void *map; + u32 *cpu; int err; err = i915_gem_obj_prepare_shmem_write(obj, &needs_clflush); @@ -42,24 +43,19 @@ static int cpu_set(struct drm_i915_gem_object *obj, page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT); map = kmap_atomic(page); + cpu = map + offset_in_page(offset); - if (needs_clflush & CLFLUSH_BEFORE) { - mb(); - clflush(map+offset_in_page(offset) / sizeof(*map)); - mb(); - } + if (needs_clflush & CLFLUSH_BEFORE) + drm_clflush_virt_range(cpu, sizeof(*cpu)); - map[offset_in_page(offset) / sizeof(*map)] = v; + *cpu = v; - if (needs_clflush & CLFLUSH_AFTER) { - mb(); - clflush(map+offset_in_page(offset) / sizeof(*map)); - mb(); - } + if (needs_clflush & CLFLUSH_AFTER) + drm_clflush_virt_range(cpu, sizeof(*cpu)); kunmap_atomic(map); - i915_gem_obj_finish_shmem_access(obj); + return 0; } @@ -69,7 +65,8 @@ static int cpu_get(struct drm_i915_gem_object *obj, { unsigned int needs_clflush; struct page *page; - u32 *map; + void *map; + u32 *cpu; int err; err = i915_gem_obj_prepare_shmem_read(obj, &needs_clflush); @@ -78,17 +75,16 @@ static int cpu_get(struct drm_i915_gem_object *obj, page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT); map = kmap_atomic(page); + cpu = map + offset_in_page(offset); - if (needs_clflush & CLFLUSH_BEFORE) { - mb(); - clflush(map+offset_in_page(offset) / sizeof(*map)); - mb(); - } + if (needs_clflush & CLFLUSH_BEFORE) + drm_clflush_virt_range(cpu, sizeof(*cpu)); - *v = map[offset_in_page(offset) / sizeof(*map)]; - kunmap_atomic(map); + *v = *cpu; + kunmap_atomic(map); i915_gem_obj_finish_shmem_access(obj); + return 0; } @@ -302,6 +298,7 @@ static int igt_gem_coherency(void *arg) values = offsets + ncachelines; mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); for (over = igt_coherency_mode; over->name; over++) { if (!over->set) continue; @@ -379,6 +376,7 @@ static int igt_gem_coherency(void *arg) } } unlock: + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); kfree(offsets); return err; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index 1c92560d35da..76df25aa90c9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -22,6 +22,8 @@ * */ +#include <linux/prime_numbers.h> + #include "../i915_selftest.h" #include "i915_random.h" #include "igt_flush_test.h" @@ -32,6 +34,200 @@ #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32)) +struct live_test { + struct drm_i915_private *i915; + const char *func; + const char *name; + + unsigned int reset_count; +}; + +static int begin_live_test(struct live_test *t, + struct drm_i915_private *i915, + const char *func, + const char *name) +{ + int err; + + t->i915 = i915; + t->func = func; + t->name = name; + + err = i915_gem_wait_for_idle(i915, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + if (err) { + pr_err("%s(%s): failed to idle before, with err=%d!", + func, name, err); + return err; + } + + i915->gpu_error.missed_irq_rings = 0; + t->reset_count = i915_reset_count(&i915->gpu_error); + + return 0; +} + +static int end_live_test(struct live_test *t) +{ + struct drm_i915_private *i915 = t->i915; + + if (igt_flush_test(i915, I915_WAIT_LOCKED)) + return -EIO; + + if (t->reset_count != i915_reset_count(&i915->gpu_error)) { + pr_err("%s(%s): GPU was reset %d times!\n", + t->func, t->name, + i915_reset_count(&i915->gpu_error) - t->reset_count); + return -EIO; + } + + if (i915->gpu_error.missed_irq_rings) { + pr_err("%s(%s): Missed interrupts on engines %lx\n", + t->func, t->name, i915->gpu_error.missed_irq_rings); + return -EIO; + } + + return 0; +} + +static int live_nop_switch(void *arg) +{ + const unsigned int nctx = 1024; + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context **ctx; + enum intel_engine_id id; + struct drm_file *file; + struct live_test t; + unsigned long n; + int err = -ENODEV; + + /* + * Create as many contexts as we can feasibly get away with + * and check we can switch between them rapidly. + * + * Serves as very simple stress test for submission and HW switching + * between contexts. + */ + + if (!DRIVER_CAPS(i915)->has_logical_contexts) + return 0; + + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + + mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); + + ctx = kcalloc(nctx, sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + err = -ENOMEM; + goto out_unlock; + } + + for (n = 0; n < nctx; n++) { + ctx[n] = i915_gem_create_context(i915, file->driver_priv); + if (IS_ERR(ctx[n])) { + err = PTR_ERR(ctx[n]); + goto out_unlock; + } + } + + for_each_engine(engine, i915, id) { + struct i915_request *rq; + unsigned long end_time, prime; + ktime_t times[2] = {}; + + times[0] = ktime_get_raw(); + for (n = 0; n < nctx; n++) { + rq = i915_request_alloc(engine, ctx[n]); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_unlock; + } + i915_request_add(rq); + } + if (i915_request_wait(rq, + I915_WAIT_LOCKED, + HZ / 5) < 0) { + pr_err("Failed to populated %d contexts\n", nctx); + i915_gem_set_wedged(i915); + err = -EIO; + goto out_unlock; + } + + times[1] = ktime_get_raw(); + + pr_info("Populated %d contexts on %s in %lluns\n", + nctx, engine->name, ktime_to_ns(times[1] - times[0])); + + err = begin_live_test(&t, i915, __func__, engine->name); + if (err) + goto out_unlock; + + end_time = jiffies + i915_selftest.timeout_jiffies; + for_each_prime_number_from(prime, 2, 8192) { + times[1] = ktime_get_raw(); + + for (n = 0; n < prime; n++) { + rq = i915_request_alloc(engine, ctx[n % nctx]); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out_unlock; + } + + /* + * This space is left intentionally blank. + * + * We do not actually want to perform any + * action with this request, we just want + * to measure the latency in allocation + * and submission of our breadcrumbs - + * ensuring that the bare request is sufficient + * for the system to work (i.e. proper HEAD + * tracking of the rings, interrupt handling, + * etc). It also gives us the lowest bounds + * for latency. + */ + + i915_request_add(rq); + } + if (i915_request_wait(rq, + I915_WAIT_LOCKED, + HZ / 5) < 0) { + pr_err("Switching between %ld contexts timed out\n", + prime); + i915_gem_set_wedged(i915); + break; + } + + times[1] = ktime_sub(ktime_get_raw(), times[1]); + if (prime == 2) + times[0] = times[1]; + + if (__igt_timeout(end_time, NULL)) + break; + } + + err = end_live_test(&t); + if (err) + goto out_unlock; + + pr_info("Switch latencies on %s: 1 = %lluns, %lu = %lluns\n", + engine->name, + ktime_to_ns(times[0]), + prime - 1, div64_u64(ktime_to_ns(times[1]), prime - 1)); + } + +out_unlock: + intel_runtime_pm_put(i915); + mutex_unlock(&i915->drm.struct_mutex); + mock_file_free(i915, file); + return err; +} + static struct i915_vma * gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value) { @@ -195,6 +391,7 @@ err_request: i915_request_add(rq); err_batch: i915_vma_unpin(batch); + i915_vma_put(batch); err_vma: i915_vma_unpin(vma); return err; @@ -636,6 +833,8 @@ static int igt_switch_to_kernel_context(void *arg) */ mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); + ctx = kernel_context(i915); if (IS_ERR(ctx)) { mutex_unlock(&i915->drm.struct_mutex); @@ -658,6 +857,8 @@ out_unlock: GEM_TRACE_DUMP_ON(err); if (igt_flush_test(i915, I915_WAIT_LOCKED)) err = -EIO; + + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); kernel_context_close(ctx); @@ -713,6 +914,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv) { static const struct i915_subtest tests[] = { SUBTEST(igt_switch_to_kernel_context), + SUBTEST(live_nop_switch), SUBTEST(igt_ctx_exec), SUBTEST(igt_ctx_readonly), }; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index ba4f322d56b8..c3999dd2021e 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -282,7 +282,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, view.partial.offset, view.partial.size, vma->size >> PAGE_SHIFT, - tile_row_pages(obj), + tile->tiling ? tile_row_pages(obj) : 0, vma->fence ? vma->fence->id : -1, tile->tiling, tile->stride, offset >> PAGE_SHIFT, (unsigned int)offset_in_page(offset), @@ -501,6 +501,8 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, static void disable_retire_worker(struct drm_i915_private *i915) { + i915_gem_shrinker_unregister(i915); + mutex_lock(&i915->drm.struct_mutex); if (!i915->gt.active_requests++) { intel_runtime_pm_get(i915); @@ -613,6 +615,7 @@ out_park: else queue_delayed_work(i915->wq, &i915->gt.idle_work, 0); mutex_unlock(&i915->drm.struct_mutex); + i915_gem_shrinker_register(i915); return err; err_obj: i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h index a00e2bd08bce..a15713cae3b3 100644 --- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h +++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h @@ -17,6 +17,7 @@ selftest(objects, i915_gem_object_live_selftests) selftest(dmabuf, i915_gem_dmabuf_live_selftests) selftest(coherency, i915_gem_coherency_live_selftests) selftest(gtt, i915_gem_gtt_live_selftests) +selftest(gem, i915_gem_live_selftests) selftest(evict, i915_gem_evict_live_selftests) selftest(hugepages, i915_gem_huge_page_live_selftests) selftest(contexts, i915_gem_context_live_selftests) diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index c4aac6141e04..07e557815308 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -342,6 +342,7 @@ static int live_nop_request(void *arg) */ mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); for_each_engine(engine, i915, id) { struct i915_request *request = NULL; @@ -402,6 +403,7 @@ static int live_nop_request(void *arg) } out_unlock: + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -487,6 +489,7 @@ static int live_empty_request(void *arg) */ mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); batch = empty_batch(i915); if (IS_ERR(batch)) { @@ -550,6 +553,7 @@ out_batch: i915_vma_unpin(batch); i915_vma_put(batch); out_unlock: + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -644,6 +648,7 @@ static int live_all_engines(void *arg) */ mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); err = begin_live_test(&t, i915, __func__, ""); if (err) @@ -726,6 +731,7 @@ out_request: i915_vma_unpin(batch); i915_vma_put(batch); out_unlock: + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -747,6 +753,7 @@ static int live_sequential_engines(void *arg) */ mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); err = begin_live_test(&t, i915, __func__, ""); if (err) @@ -853,6 +860,7 @@ out_request: i915_request_put(request[id]); } out_unlock: + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } diff --git a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c index 570e325af93e..cdbc8f134e5e 100644 --- a/drivers/gpu/drm/i915/selftests/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/selftests/i915_sw_fence.c @@ -611,17 +611,9 @@ static const char *mock_name(struct dma_fence *fence) return "mock"; } -static bool mock_enable_signaling(struct dma_fence *fence) -{ - return true; -} - static const struct dma_fence_ops mock_fence_ops = { .get_driver_name = mock_name, .get_timeline_name = mock_name, - .enable_signaling = mock_enable_signaling, - .wait = dma_fence_default_wait, - .release = dma_fence_free, }; static DEFINE_SPINLOCK(mock_fence_lock); diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c index 407c98fb9170..0c0ab82b6228 100644 --- a/drivers/gpu/drm/i915/selftests/intel_guc.c +++ b/drivers/gpu/drm/i915/selftests/intel_guc.c @@ -65,6 +65,40 @@ static int check_all_doorbells(struct intel_guc *guc) return 0; } +static int ring_doorbell_nop(struct intel_guc_client *client) +{ + struct guc_process_desc *desc = __get_process_desc(client); + int err; + + client->use_nop_wqi = true; + + spin_lock_irq(&client->wq_lock); + + guc_wq_item_append(client, 0, 0, 0, 0); + guc_ring_doorbell(client); + + spin_unlock_irq(&client->wq_lock); + + client->use_nop_wqi = false; + + /* if there are no issues GuC will update the WQ head and keep the + * WQ in active status + */ + err = wait_for(READ_ONCE(desc->head) == READ_ONCE(desc->tail), 10); + if (err) { + pr_err("doorbell %u ring failed!\n", client->doorbell_id); + return -EIO; + } + + if (desc->wq_status != WQ_STATUS_ACTIVE) { + pr_err("doorbell %u ring put WQ in bad state (%u)!\n", + client->doorbell_id, desc->wq_status); + return -EIO; + } + + return 0; +} + /* * Basic client sanity check, handy to validate create_clients. */ @@ -108,6 +142,7 @@ static int igt_guc_clients(void *args) GEM_BUG_ON(!HAS_GUC(dev_priv)); mutex_lock(&dev_priv->drm.struct_mutex); + intel_runtime_pm_get(dev_priv); guc = &dev_priv->guc; if (!guc) { @@ -235,6 +270,7 @@ out: guc_clients_create(guc); guc_clients_doorbell_init(guc); unlock: + intel_runtime_pm_put(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); return err; } @@ -253,6 +289,7 @@ static int igt_guc_doorbells(void *arg) GEM_BUG_ON(!HAS_GUC(dev_priv)); mutex_lock(&dev_priv->drm.struct_mutex); + intel_runtime_pm_get(dev_priv); guc = &dev_priv->guc; if (!guc) { @@ -332,6 +369,10 @@ static int igt_guc_doorbells(void *arg) err = check_all_doorbells(guc); if (err) goto out; + + err = ring_doorbell_nop(clients[i]); + if (err) + goto out; } out: @@ -341,6 +382,7 @@ out: guc_client_free(clients[i]); } unlock: + intel_runtime_pm_put(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); return err; } diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index 65d66cdedd26..db378226ac10 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -1018,8 +1018,41 @@ static int evict_vma(void *data) 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); + + return err; +} + static int __igt_reset_evict_vma(struct drm_i915_private *i915, - struct i915_address_space *vm) + struct i915_address_space *vm, + int (*fn)(void *), + unsigned int flags) { struct drm_i915_gem_object *obj; struct task_struct *tsk = NULL; @@ -1040,12 +1073,20 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915, if (err) goto unlock; - obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + obj = i915_gem_object_create_internal(i915, SZ_1M); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto fini; } + if (flags & EXEC_OBJECT_NEEDS_FENCE) { + err = i915_gem_object_set_tiling(obj, I915_TILING_X, 512); + if (err) { + pr_err("Invalid X-tiling settings; err:%d\n", err); + goto out_obj; + } + } + arg.vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(arg.vma)) { err = PTR_ERR(arg.vma); @@ -1059,11 +1100,28 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915, } err = i915_vma_pin(arg.vma, 0, 0, - i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER); - if (err) + i915_vma_is_ggtt(arg.vma) ? + PIN_GLOBAL | PIN_MAPPABLE : + PIN_USER); + if (err) { + i915_request_add(rq); goto out_obj; + } + + if (flags & EXEC_OBJECT_NEEDS_FENCE) { + err = i915_vma_pin_fence(arg.vma); + if (err) { + pr_err("Unable to pin X-tiled fence; err:%d\n", err); + i915_vma_unpin(arg.vma); + i915_request_add(rq); + goto out_obj; + } + } + + err = i915_vma_move_to_active(arg.vma, rq, flags); - err = i915_vma_move_to_active(arg.vma, rq, EXEC_OBJECT_WRITE); + if (flags & EXEC_OBJECT_NEEDS_FENCE) + i915_vma_unpin_fence(arg.vma); i915_vma_unpin(arg.vma); i915_request_get(rq); @@ -1086,7 +1144,7 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915, init_completion(&arg.completion); - tsk = kthread_run(evict_vma, &arg, "igt/evict_vma"); + tsk = kthread_run(fn, &arg, "igt/evict_vma"); if (IS_ERR(tsk)) { err = PTR_ERR(tsk); tsk = NULL; @@ -1137,29 +1195,47 @@ static int igt_reset_evict_ggtt(void *arg) { struct drm_i915_private *i915 = arg; - return __igt_reset_evict_vma(i915, &i915->ggtt.vm); + return __igt_reset_evict_vma(i915, &i915->ggtt.vm, + evict_vma, EXEC_OBJECT_WRITE); } static int igt_reset_evict_ppgtt(void *arg) { struct drm_i915_private *i915 = arg; struct i915_gem_context *ctx; + struct drm_file *file; int err; + file = mock_file(i915); + if (IS_ERR(file)) + return PTR_ERR(file); + mutex_lock(&i915->drm.struct_mutex); - ctx = kernel_context(i915); + ctx = live_context(i915, file); mutex_unlock(&i915->drm.struct_mutex); - if (IS_ERR(ctx)) - return PTR_ERR(ctx); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto out; + } err = 0; if (ctx->ppgtt) /* aliasing == global gtt locking, covered above */ - err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm); + err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm, + evict_vma, EXEC_OBJECT_WRITE); - kernel_context_close(ctx); +out: + mock_file_free(i915, file); return err; } +static int igt_reset_evict_fence(void *arg) +{ + struct drm_i915_private *i915 = arg; + + return __igt_reset_evict_vma(i915, &i915->ggtt.vm, + evict_fence, EXEC_OBJECT_NEEDS_FENCE); +} + static int wait_for_others(struct drm_i915_private *i915, struct intel_engine_cs *exclude) { @@ -1409,6 +1485,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_reset_wait), SUBTEST(igt_reset_evict_ggtt), SUBTEST(igt_reset_evict_ppgtt), + SUBTEST(igt_reset_evict_fence), SUBTEST(igt_handle_error), }; bool saved_hangcheck; diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 582566faef09..1aea7a8f2224 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -221,6 +221,7 @@ static int live_sanitycheck(void *arg) return 0; mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); if (spinner_init(&spin, i915)) goto err_unlock; @@ -261,6 +262,7 @@ err_spin: spinner_fini(&spin); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -278,6 +280,7 @@ static int live_preempt(void *arg) return 0; mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); if (spinner_init(&spin_hi, i915)) goto err_unlock; @@ -350,6 +353,7 @@ err_spin_hi: spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } @@ -368,6 +372,7 @@ static int live_late_preempt(void *arg) return 0; mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); if (spinner_init(&spin_hi, i915)) goto err_unlock; @@ -440,6 +445,7 @@ err_spin_hi: spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; @@ -467,6 +473,7 @@ static int live_preempt_hang(void *arg) return 0; mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); if (spinner_init(&spin_hi, i915)) goto err_unlock; @@ -561,6 +568,7 @@ err_spin_hi: spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); + intel_runtime_pm_put(i915); mutex_unlock(&i915->drm.struct_mutex); return err; } diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c index 0d39b3bf0c0d..d1a0923d2f38 100644 --- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c @@ -44,7 +44,9 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine) if (err) goto err_obj; + intel_runtime_pm_get(engine->i915); rq = i915_request_alloc(engine, ctx); + intel_runtime_pm_put(engine->i915); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto err_pin; @@ -175,7 +177,10 @@ static int switch_to_scratch_context(struct intel_engine_cs *engine) if (IS_ERR(ctx)) return PTR_ERR(ctx); + intel_runtime_pm_get(engine->i915); rq = i915_request_alloc(engine, ctx); + intel_runtime_pm_put(engine->i915); + kernel_context_close(ctx); if (IS_ERR(rq)) return PTR_ERR(rq); diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c index 8904f1ce64e3..d937bdff26f9 100644 --- a/drivers/gpu/drm/i915/selftests/mock_context.c +++ b/drivers/gpu/drm/i915/selftests/mock_context.c @@ -43,6 +43,7 @@ mock_context(struct drm_i915_private *i915, INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL); INIT_LIST_HEAD(&ctx->handles_list); + INIT_LIST_HEAD(&ctx->hw_id_link); for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { struct intel_context *ce = &ctx->__engine[n]; @@ -50,11 +51,9 @@ mock_context(struct drm_i915_private *i915, ce->gem_context = ctx; } - ret = ida_simple_get(&i915->contexts.hw_ida, - 0, MAX_CONTEXT_HW_ID, GFP_KERNEL); + ret = i915_gem_context_pin_hw_id(ctx); if (ret < 0) goto err_handles; - ctx->hw_id = ret; if (name) { ctx->name = kstrdup(name, GFP_KERNEL); @@ -85,11 +84,7 @@ void mock_context_close(struct i915_gem_context *ctx) void mock_init_contexts(struct drm_i915_private *i915) { - INIT_LIST_HEAD(&i915->contexts.list); - ida_init(&i915->contexts.hw_ida); - - INIT_WORK(&i915->contexts.free_work, contexts_free_worker); - init_llist_head(&i915->contexts.free_list); + init_contexts(i915); } struct i915_gem_context * diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c index a140ea5c3a7c..6ae418c76015 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gtt.c +++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c @@ -118,6 +118,8 @@ void mock_init_ggtt(struct drm_i915_private *i915) ggtt->vm.vma_ops.clear_pages = clear_pages; i915_address_space_init(&ggtt->vm, i915); + + ggtt->vm.is_ggtt = true; } void mock_fini_ggtt(struct drm_i915_private *i915) |