Inside the error capture itself, we refer to not only the hardware engine, its ringbuffer but also the capture state. Finding clear names for each whilst avoiding mixing ring/intel_engine_cs is tricky. As a compromise we keep using ering for the error capture. Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Link: http://patchwork.freedesktop.org/patch/msgid/1469432687-22756-8-git-send-email-chris@xxxxxxxxxxxxxxxxxx --- drivers/gpu/drm/i915/i915_drv.h | 6 +- drivers/gpu/drm/i915/i915_gpu_error.c | 255 +++++++++++++++++----------------- 2 files changed, 134 insertions(+), 127 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 97f827979a66..11c0204aac23 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -512,7 +512,7 @@ struct drm_i915_error_state { struct intel_display_error_state *display; struct drm_i915_error_object *semaphore_obj; - struct drm_i915_error_ring { + struct drm_i915_error_engine { bool valid; /* Software tracked state */ bool waiting; @@ -578,7 +578,7 @@ struct drm_i915_error_state { pid_t pid; char comm[TASK_COMM_LEN]; - } ring[I915_NUM_ENGINES]; + } engine[I915_NUM_ENGINES]; struct drm_i915_error_buffer { u32 size; @@ -593,7 +593,7 @@ struct drm_i915_error_state { u32 dirty:1; u32 purgeable:1; u32 userptr:1; - s32 ring:4; + s32 engine:4; u32 cache_level:3; } **active_bo, **pinned_bo; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 4d39c7284605..0ec917fa115d 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -30,9 +30,9 @@ #include <generated/utsrelease.h> #include "i915_drv.h" -static const char *ring_str(int ring) +static const char *engine_str(int engine) { - switch (ring) { + switch (engine) { case RCS: return "render"; case VCS: return "bsd"; case BCS: return "blt"; @@ -207,8 +207,8 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m, err_puts(m, dirty_flag(err->dirty)); err_puts(m, purgeable_flag(err->purgeable)); err_puts(m, err->userptr ? " userptr" : ""); - err_puts(m, err->ring != -1 ? " " : ""); - err_puts(m, ring_str(err->ring)); + err_puts(m, err->engine != -1 ? " " : ""); + err_puts(m, engine_str(err->engine)); err_puts(m, i915_cache_level_str(m->i915, err->cache_level)); if (err->name) @@ -240,69 +240,71 @@ static const char *hangcheck_action_to_str(enum intel_ring_hangcheck_action a) } static void i915_ring_error_state(struct drm_i915_error_state_buf *m, - struct drm_device *dev, - struct drm_i915_error_state *error, - int ring_idx) + struct drm_device *dev, + struct drm_i915_error_state *error, + int engine_idx) { - struct drm_i915_error_ring *ring = &error->ring[ring_idx]; + struct drm_i915_error_engine *ering = &error->engine[engine_idx]; - if (!ring->valid) + if (!ering->valid) return; - err_printf(m, "%s command stream:\n", ring_str(ring_idx)); - err_printf(m, " START: 0x%08x\n", ring->start); - err_printf(m, " HEAD: 0x%08x\n", ring->head); - err_printf(m, " TAIL: 0x%08x\n", ring->tail); - err_printf(m, " CTL: 0x%08x\n", ring->ctl); - err_printf(m, " HWS: 0x%08x\n", ring->hws); - err_printf(m, " ACTHD: 0x%08x %08x\n", (u32)(ring->acthd>>32), (u32)ring->acthd); - err_printf(m, " IPEIR: 0x%08x\n", ring->ipeir); - err_printf(m, " IPEHR: 0x%08x\n", ring->ipehr); - err_printf(m, " INSTDONE: 0x%08x\n", ring->instdone); + err_printf(m, "%s command stream:\n", engine_str(engine_idx)); + err_printf(m, " START: 0x%08x\n", ering->start); + err_printf(m, " HEAD: 0x%08x\n", ering->head); + err_printf(m, " TAIL: 0x%08x\n", ering->tail); + err_printf(m, " CTL: 0x%08x\n", ering->ctl); + err_printf(m, " HWS: 0x%08x\n", ering->hws); + err_printf(m, " ACTHD: 0x%08x %08x\n", + (u32)(ering->acthd>>32), (u32)ering->acthd); + err_printf(m, " IPEIR: 0x%08x\n", ering->ipeir); + err_printf(m, " IPEHR: 0x%08x\n", ering->ipehr); + err_printf(m, " INSTDONE: 0x%08x\n", ering->instdone); if (INTEL_INFO(dev)->gen >= 4) { - err_printf(m, " BBADDR: 0x%08x %08x\n", (u32)(ring->bbaddr>>32), (u32)ring->bbaddr); - err_printf(m, " BB_STATE: 0x%08x\n", ring->bbstate); - err_printf(m, " INSTPS: 0x%08x\n", ring->instps); + err_printf(m, " BBADDR: 0x%08x %08x\n", + (u32)(ering->bbaddr>>32), (u32)ering->bbaddr); + err_printf(m, " BB_STATE: 0x%08x\n", ering->bbstate); + err_printf(m, " INSTPS: 0x%08x\n", ering->instps); } - err_printf(m, " INSTPM: 0x%08x\n", ring->instpm); - err_printf(m, " FADDR: 0x%08x %08x\n", upper_32_bits(ring->faddr), - lower_32_bits(ring->faddr)); + err_printf(m, " INSTPM: 0x%08x\n", ering->instpm); + err_printf(m, " FADDR: 0x%08x %08x\n", upper_32_bits(ering->faddr), + lower_32_bits(ering->faddr)); if (INTEL_INFO(dev)->gen >= 6) { - err_printf(m, " RC PSMI: 0x%08x\n", ring->rc_psmi); - err_printf(m, " FAULT_REG: 0x%08x\n", ring->fault_reg); + err_printf(m, " RC PSMI: 0x%08x\n", ering->rc_psmi); + err_printf(m, " FAULT_REG: 0x%08x\n", ering->fault_reg); err_printf(m, " SYNC_0: 0x%08x [last synced 0x%08x]\n", - ring->semaphore_mboxes[0], - ring->semaphore_seqno[0]); + ering->semaphore_mboxes[0], + ering->semaphore_seqno[0]); err_printf(m, " SYNC_1: 0x%08x [last synced 0x%08x]\n", - ring->semaphore_mboxes[1], - ring->semaphore_seqno[1]); + ering->semaphore_mboxes[1], + ering->semaphore_seqno[1]); if (HAS_VEBOX(dev)) { err_printf(m, " SYNC_2: 0x%08x [last synced 0x%08x]\n", - ring->semaphore_mboxes[2], - ring->semaphore_seqno[2]); + ering->semaphore_mboxes[2], + ering->semaphore_seqno[2]); } } if (USES_PPGTT(dev)) { - err_printf(m, " GFX_MODE: 0x%08x\n", ring->vm_info.gfx_mode); + err_printf(m, " GFX_MODE: 0x%08x\n", ering->vm_info.gfx_mode); if (INTEL_INFO(dev)->gen >= 8) { int i; for (i = 0; i < 4; i++) err_printf(m, " PDP%d: 0x%016llx\n", - i, ring->vm_info.pdp[i]); + i, ering->vm_info.pdp[i]); } else { err_printf(m, " PP_DIR_BASE: 0x%08x\n", - ring->vm_info.pp_dir_base); + ering->vm_info.pp_dir_base); } } - err_printf(m, " seqno: 0x%08x\n", ring->seqno); - err_printf(m, " last_seqno: 0x%08x\n", ring->last_seqno); - err_printf(m, " waiting: %s\n", yesno(ring->waiting)); - err_printf(m, " ring->head: 0x%08x\n", ring->cpu_ring_head); - err_printf(m, " ring->tail: 0x%08x\n", ring->cpu_ring_tail); + err_printf(m, " seqno: 0x%08x\n", ering->seqno); + err_printf(m, " last_seqno: 0x%08x\n", ering->last_seqno); + err_printf(m, " waiting: %s\n", yesno(ering->waiting)); + err_printf(m, " ring->head: 0x%08x\n", ering->cpu_ring_head); + err_printf(m, " ring->tail: 0x%08x\n", ering->cpu_ring_tail); err_printf(m, " hangcheck: %s [%d]\n", - hangcheck_action_to_str(ring->hangcheck_action), - ring->hangcheck_score); + hangcheck_action_to_str(ering->hangcheck_action), + ering->hangcheck_score); } void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) @@ -348,17 +350,17 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, error->time.tv_usec); err_printf(m, "Kernel: " UTS_RELEASE "\n"); max_hangcheck_score = 0; - for (i = 0; i < ARRAY_SIZE(error->ring); i++) { - if (error->ring[i].hangcheck_score > max_hangcheck_score) - max_hangcheck_score = error->ring[i].hangcheck_score; + for (i = 0; i < ARRAY_SIZE(error->engine); i++) { + if (error->engine[i].hangcheck_score > max_hangcheck_score) + max_hangcheck_score = error->engine[i].hangcheck_score; } - for (i = 0; i < ARRAY_SIZE(error->ring); i++) { - if (error->ring[i].hangcheck_score == max_hangcheck_score && - error->ring[i].pid != -1) { + for (i = 0; i < ARRAY_SIZE(error->engine); i++) { + if (error->engine[i].hangcheck_score == max_hangcheck_score && + error->engine[i].pid != -1) { err_printf(m, "Active process (on ring %s): %s [%d]\n", - ring_str(i), - error->ring[i].comm, - error->ring[i].pid); + engine_str(i), + error->engine[i].comm, + error->engine[i].pid); } } err_printf(m, "Reset count: %u\n", error->reset_count); @@ -414,7 +416,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, if (IS_GEN7(dev)) err_printf(m, "ERR_INT: 0x%08x\n", error->err_int); - for (i = 0; i < ARRAY_SIZE(error->ring); i++) + for (i = 0; i < ARRAY_SIZE(error->engine); i++) i915_ring_error_state(m, dev, error, i); for (i = 0; i < error->vm_count; i++) { @@ -429,21 +431,23 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, error->pinned_bo_count[i]); } - for (i = 0; i < ARRAY_SIZE(error->ring); i++) { - obj = error->ring[i].batchbuffer; + for (i = 0; i < ARRAY_SIZE(error->engine); i++) { + struct drm_i915_error_engine *ering = &error->engine[i]; + + obj = ering->batchbuffer; if (obj) { err_puts(m, dev_priv->engine[i].name); - if (error->ring[i].pid != -1) + if (ering->pid != -1) err_printf(m, " (submitted by %s [%d])", - error->ring[i].comm, - error->ring[i].pid); + ering->comm, + ering->pid); err_printf(m, " --- gtt_offset = 0x%08x %08x\n", upper_32_bits(obj->gtt_offset), lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } - obj = error->ring[i].wa_batchbuffer; + obj = ering->wa_batchbuffer; if (obj) { err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n", dev_priv->engine[i].name, @@ -451,38 +455,38 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, print_error_obj(m, obj); } - if (error->ring[i].num_requests) { + if (ering->num_requests) { err_printf(m, "%s --- %d requests\n", dev_priv->engine[i].name, - error->ring[i].num_requests); - for (j = 0; j < error->ring[i].num_requests; j++) { + ering->num_requests); + for (j = 0; j < ering->num_requests; j++) { err_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n", - error->ring[i].requests[j].seqno, - error->ring[i].requests[j].jiffies, - error->ring[i].requests[j].tail); + ering->requests[j].seqno, + ering->requests[j].jiffies, + ering->requests[j].tail); } } - if (error->ring[i].num_waiters) { + if (ering->num_waiters) { err_printf(m, "%s --- %d waiters\n", dev_priv->engine[i].name, - error->ring[i].num_waiters); - for (j = 0; j < error->ring[i].num_waiters; j++) { + ering->num_waiters); + for (j = 0; j < ering->num_waiters; j++) { err_printf(m, " seqno 0x%08x for %s [%d]\n", - error->ring[i].waiters[j].seqno, - error->ring[i].waiters[j].comm, - error->ring[i].waiters[j].pid); + ering->waiters[j].seqno, + ering->waiters[j].comm, + ering->waiters[j].pid); } } - if ((obj = error->ring[i].ringbuffer)) { + if ((obj = ering->ringbuffer)) { err_printf(m, "%s --- ringbuffer = 0x%08x\n", dev_priv->engine[i].name, lower_32_bits(obj->gtt_offset)); print_error_obj(m, obj); } - if ((obj = error->ring[i].hws_page)) { + if ((obj = ering->hws_page)) { u64 hws_offset = obj->gtt_offset; u32 *hws_page = &obj->pages[0][0]; @@ -504,7 +508,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, } } - obj = error->ring[i].wa_ctx; + obj = ering->wa_ctx; if (obj) { u64 wa_ctx_offset = obj->gtt_offset; u32 *wa_ctx_page = &obj->pages[0][0]; @@ -526,7 +530,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, } } - if ((obj = error->ring[i].ctx)) { + if ((obj = ering->ctx)) { err_printf(m, "%s --- HW Context = 0x%08x\n", dev_priv->engine[i].name, lower_32_bits(obj->gtt_offset)); @@ -611,15 +615,18 @@ static void i915_error_state_free(struct kref *error_ref) typeof(*error), ref); int i; - for (i = 0; i < ARRAY_SIZE(error->ring); i++) { - i915_error_object_free(error->ring[i].batchbuffer); - i915_error_object_free(error->ring[i].wa_batchbuffer); - i915_error_object_free(error->ring[i].ringbuffer); - i915_error_object_free(error->ring[i].hws_page); - i915_error_object_free(error->ring[i].ctx); - i915_error_object_free(error->ring[i].wa_ctx); - kfree(error->ring[i].requests); - kfree(error->ring[i].waiters); + for (i = 0; i < ARRAY_SIZE(error->engine); i++) { + struct drm_i915_error_engine *ering = &error->engine[i]; + + i915_error_object_free(ering->batchbuffer); + i915_error_object_free(ering->wa_batchbuffer); + i915_error_object_free(ering->ringbuffer); + i915_error_object_free(ering->hws_page); + i915_error_object_free(ering->ctx); + i915_error_object_free(ering->wa_ctx); + + kfree(ering->requests); + kfree(ering->waiters); } i915_error_object_free(error->semaphore_obj); @@ -762,8 +769,8 @@ static void capture_bo(struct drm_i915_error_buffer *err, err->dirty = obj->dirty; err->purgeable = obj->madv != I915_MADV_WILLNEED; err->userptr = obj->userptr.mm != NULL; - err->ring = obj->last_write_req ? - i915_gem_request_get_engine(obj->last_write_req)->id : -1; + err->engine = obj->last_write_req ? + i915_gem_request_get_engine(obj->last_write_req)->id : -1; err->cache_level = obj->cache_level; } @@ -815,7 +822,7 @@ static u32 capture_pinned_bo(struct drm_i915_error_buffer *err, */ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv, struct drm_i915_error_state *error, - int *ring_id) + int *engine_id) { uint32_t error_code = 0; int i; @@ -826,11 +833,11 @@ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv, * strictly a client bug. Use instdone to differentiate those some. */ for (i = 0; i < I915_NUM_ENGINES; i++) { - if (error->ring[i].hangcheck_action == HANGCHECK_HUNG) { - if (ring_id) - *ring_id = i; + if (error->engine[i].hangcheck_action == HANGCHECK_HUNG) { + if (engine_id) + *engine_id = i; - return error->ring[i].ipehr ^ error->ring[i].instdone; + return error->engine[i].ipehr ^ error->engine[i].instdone; } } @@ -858,7 +865,7 @@ static void i915_gem_record_fences(struct drm_i915_private *dev_priv, static void gen8_record_semaphore_state(struct drm_i915_private *dev_priv, struct drm_i915_error_state *error, struct intel_engine_cs *engine, - struct drm_i915_error_ring *ering) + struct drm_i915_error_engine *ering) { struct intel_engine_cs *to; enum intel_engine_id id; @@ -891,7 +898,7 @@ static void gen8_record_semaphore_state(struct drm_i915_private *dev_priv, static void gen6_record_semaphore_state(struct drm_i915_private *dev_priv, struct intel_engine_cs *engine, - struct drm_i915_error_ring *ering) + struct drm_i915_error_engine *ering) { ering->semaphore_mboxes[0] = I915_READ(RING_SYNC_0(engine->mmio_base)); ering->semaphore_mboxes[1] = I915_READ(RING_SYNC_1(engine->mmio_base)); @@ -906,7 +913,7 @@ static void gen6_record_semaphore_state(struct drm_i915_private *dev_priv, } static void engine_record_waiters(struct intel_engine_cs *engine, - struct drm_i915_error_ring *ering) + struct drm_i915_error_engine *ering) { struct intel_breadcrumbs *b = &engine->breadcrumbs; struct drm_i915_error_waiter *waiter; @@ -950,7 +957,7 @@ static void engine_record_waiters(struct intel_engine_cs *engine, static void i915_record_ring_state(struct drm_i915_private *dev_priv, struct drm_i915_error_state *error, struct intel_engine_cs *engine, - struct drm_i915_error_ring *ering) + struct drm_i915_error_engine *ering) { if (INTEL_GEN(dev_priv) >= 6) { ering->rc_psmi = I915_READ(RING_PSMI_CTL(engine->mmio_base)); @@ -1048,7 +1055,7 @@ static void i915_record_ring_state(struct drm_i915_private *dev_priv, static void i915_gem_record_active_context(struct intel_engine_cs *engine, struct drm_i915_error_state *error, - struct drm_i915_error_ring *ering) + struct drm_i915_error_engine *ering) { struct drm_i915_private *dev_priv = engine->i915; struct drm_i915_gem_object *obj; @@ -1077,16 +1084,17 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, for (i = 0; i < I915_NUM_ENGINES; i++) { struct intel_engine_cs *engine = &dev_priv->engine[i]; + struct drm_i915_error_engine *ering = &error->engine[i]; - error->ring[i].pid = -1; + ering->pid = -1; if (!intel_engine_initialized(engine)) continue; - error->ring[i].valid = true; + ering->valid = true; - i915_record_ring_state(dev_priv, error, engine, &error->ring[i]); - engine_record_waiters(engine, &error->ring[i]); + i915_record_ring_state(dev_priv, error, engine, ering); + engine_record_waiters(engine, ering); request = i915_gem_find_active_request(engine); if (request) { @@ -1100,13 +1108,13 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, * as the simplest method to avoid being overwritten * by userspace. */ - error->ring[i].batchbuffer = + ering->batchbuffer = i915_error_object_create(dev_priv, request->batch_obj, vm); if (HAS_BROKEN_CS_TLB(dev_priv)) - error->ring[i].wa_batchbuffer = + ering->wa_batchbuffer = i915_error_ggtt_object_create(dev_priv, engine->scratch.obj); @@ -1116,8 +1124,8 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, rcu_read_lock(); task = pid_task(request->pid, PIDTYPE_PID); if (task) { - strcpy(error->ring[i].comm, task->comm); - error->ring[i].pid = task->pid; + strcpy(ering->comm, task->comm); + ering->pid = task->pid; } rcu_read_unlock(); } @@ -1126,35 +1134,34 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, request->ctx->flags & CONTEXT_NO_ERROR_CAPTURE; rb = request->ringbuf; - error->ring[i].cpu_ring_head = rb->head; - error->ring[i].cpu_ring_tail = rb->tail; - error->ring[i].ringbuffer = + ering->cpu_ring_head = rb->head; + ering->cpu_ring_tail = rb->tail; + ering->ringbuffer = i915_error_ggtt_object_create(dev_priv, rb->obj); } - error->ring[i].hws_page = + ering->hws_page = i915_error_ggtt_object_create(dev_priv, engine->status_page.obj); if (engine->wa_ctx.obj) { - error->ring[i].wa_ctx = + ering->wa_ctx = i915_error_ggtt_object_create(dev_priv, engine->wa_ctx.obj); } - i915_gem_record_active_context(engine, error, &error->ring[i]); + i915_gem_record_active_context(engine, error, ering); count = 0; list_for_each_entry(request, &engine->request_list, list) count++; - error->ring[i].num_requests = count; - error->ring[i].requests = - kcalloc(count, sizeof(*error->ring[i].requests), - GFP_ATOMIC); - if (error->ring[i].requests == NULL) { - error->ring[i].num_requests = 0; + ering->num_requests = count; + ering->requests = + kcalloc(count, sizeof(*ering->requests), GFP_ATOMIC); + if (!ering->requests) { + ering->num_requests = 0; continue; } @@ -1162,7 +1169,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, list_for_each_entry(request, &engine->request_list, list) { struct drm_i915_error_request *erq; - if (count >= error->ring[i].num_requests) { + if (count >= ering->num_requests) { /* * If the ring request list was changed in * between the point where the error request @@ -1181,7 +1188,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv, break; } - erq = &error->ring[i].requests[count++]; + erq = &ering->requests[count++]; erq->seqno = request->fence.seqno; erq->jiffies = request->emitted_jiffies; erq->tail = request->postfix; @@ -1352,20 +1359,20 @@ static void i915_error_capture_msg(struct drm_i915_private *dev_priv, const char *error_msg) { u32 ecode; - int ring_id = -1, len; + int engine_id = -1, len; - ecode = i915_error_generate_code(dev_priv, error, &ring_id); + ecode = i915_error_generate_code(dev_priv, error, &engine_id); len = scnprintf(error->error_msg, sizeof(error->error_msg), "GPU HANG: ecode %d:%d:0x%08x", - INTEL_GEN(dev_priv), ring_id, ecode); + INTEL_GEN(dev_priv), engine_id, ecode); - if (ring_id != -1 && error->ring[ring_id].pid != -1) + if (engine_id != -1 && error->engine[engine_id].pid != -1) len += scnprintf(error->error_msg + len, sizeof(error->error_msg) - len, ", in %s [%d]", - error->ring[ring_id].comm, - error->ring[ring_id].pid); + error->engine[engine_id].comm, + error->engine[engine_id].pid); scnprintf(error->error_msg + len, sizeof(error->error_msg) - len, ", reason: %s, action: %s", -- 2.8.1 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
