From: Mika Kuoppala Date: Tue, 25 Feb 2014 15:11:25 +0000 (+0200) Subject: drm/i915: Add error code into error state X-Git-Tag: firefly_0821_release~176^2~3773^2~63^2~280 X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=cb38300215dc24886347bfc6400ccfed806dac21;p=firefly-linux-kernel-4.4.55.git drm/i915: Add error code into error state commit 011cf577b2531dfbd2254bd9ec147ad71471abaf Author: Ben Widawsky Date: Tue Feb 4 12:18:55 2014 +0000 drm/i915: Generate a hang error code added error code debug into dmesg. Store this also with error state to make matching dmesg logs and error states easier. As we need to have full ring state for error code generation, do full capture always, print hang message into log and then decide if we need to keep the error state. Signed-off-by: Mika Kuoppala Reviewed-by: Chris Wilson Signed-off-by: Daniel Vetter --- diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 826fcaef25c1..7db735c1e764 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -303,6 +303,8 @@ struct drm_i915_error_state { struct kref ref; struct timeval time; + char error_msg[128]; + /* Generic register state */ u32 eir; u32 pgtbl_er; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8b02498ee963..75dd0562bb4a 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -329,6 +329,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, goto out; } + err_printf(m, "%s\n", error->error_msg); err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec, error->time.tv_usec); err_printf(m, "Kernel: " UTS_RELEASE "\n"); @@ -689,7 +690,8 @@ static u32 capture_pinned_bo(struct drm_i915_error_buffer *err, * It's only a small step better than a random number in its current form. */ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv, - struct drm_i915_error_state *error) + struct drm_i915_error_state *error, + int *ring_id) { uint32_t error_code = 0; int i; @@ -699,9 +701,14 @@ static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv, * synchronization commands which almost always appear in the case * strictly a client bug. Use instdone to differentiate those some. */ - for (i = 0; i < I915_NUM_RINGS; i++) - if (error->ring[i].hangcheck_action == HANGCHECK_HUNG) + for (i = 0; i < I915_NUM_RINGS; i++) { + if (error->ring[i].hangcheck_action == HANGCHECK_HUNG) { + if (ring_id) + *ring_id = i; + return error->ring[i].ipehr ^ error->ring[i].instdone; + } + } return error_code; } @@ -1086,6 +1093,19 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv, i915_get_extra_instdone(dev, error->extra_instdone); } +static void i915_error_capture_msg(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 ecode; + int ring_id = -1; + + ecode = i915_error_generate_code(dev_priv, error, &ring_id); + + scnprintf(error->error_msg, sizeof(error->error_msg), + "GPU HANG: ecode %d:0x%08x", ring_id, ecode); +} + /** * i915_capture_error_state - capture an error record for later analysis * @dev: drm device @@ -1101,13 +1121,6 @@ void i915_capture_error_state(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_error_state *error; unsigned long flags; - uint32_t ecode; - - spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); - error = dev_priv->gpu_error.first_error; - spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); - if (error) - return; /* Account for pipe specific data like PIPE*STAT */ error = kzalloc(sizeof(*error), GFP_ATOMIC); @@ -1116,30 +1129,21 @@ void i915_capture_error_state(struct drm_device *dev) return; } - DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n", - dev->primary->index); kref_init(&error->ref); i915_capture_reg_state(dev_priv, error); i915_gem_capture_buffers(dev_priv, error); i915_gem_record_fences(dev, error); i915_gem_record_rings(dev, error); - ecode = i915_error_generate_code(dev_priv, error); - - if (!warned) { - DRM_INFO("GPU HANG [%x]\n", ecode); - DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n"); - DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n"); - DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n"); - DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n"); - warned = true; - } do_gettimeofday(&error->time); error->overlay = intel_overlay_capture_error_state(dev); error->display = intel_display_capture_error_state(dev); + i915_error_capture_msg(dev, error); + DRM_INFO("%s\n", error->error_msg); + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); if (dev_priv->gpu_error.first_error == NULL) { dev_priv->gpu_error.first_error = error; @@ -1147,8 +1151,19 @@ void i915_capture_error_state(struct drm_device *dev) } spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); - if (error) + if (error) { i915_error_state_free(&error->ref); + return; + } + + if (!warned) { + DRM_INFO("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n"); + DRM_INFO("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n"); + DRM_INFO("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n"); + DRM_INFO("The gpu crash dump is required to analyze gpu hangs, so please always attach it.\n"); + DRM_INFO("GPU crash dump saved to /sys/class/drm/card%d/error\n", dev->primary->index); + warned = true; + } } void i915_error_state_get(struct drm_device *dev,