drm/i915: If the GPU hangs twice within 5 seconds, declare it wedged.

The issue is that we may become stuck executing a long running shader
and continually attempt to reset the GPU. (Or maybe we tickle some bug
and need to break the vicious cycle.) So if we are detect a second hang
within 5 seconds, give up trying to programme the GPU and report it
wedged.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f3243a3abc379671b46b70b39c14693163446a7f..c3decb2fef4ba8b80d7b95114a58cf25e35a7b59 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -383,6 +383,11 @@ static int i965_do_reset(struct drm_device *dev, u8 flags)
 {
        u8 gdrst;
 
+       /*
+        * Set the domains we want to reset (GRDOM/bits 2 and 3) as
+        * well as the reset bit (GR/bit 0).  Setting the GR bit
+        * triggers the reset; when done, the hardware will clear it.
+        */
        pci_read_config_byte(dev->pdev, I965_GDRST, &gdrst);
        pci_write_config_byte(dev->pdev, I965_GDRST, gdrst | flags | 0x1);
 
@@ -427,13 +432,10 @@ int i915_reset(struct drm_device *dev, u8 flags)
 
        i915_gem_reset(dev);
 
-       /*
-        * Set the domains we want to reset (GRDOM/bits 2 and 3) as
-        * well as the reset bit (GR/bit 0).  Setting the GR bit
-        * triggers the reset; when done, the hardware will clear it.
-        */
        ret = -ENODEV;
-       switch (INTEL_INFO(dev)->gen) {
+       if (get_seconds() - dev_priv->last_gpu_reset < 5) {
+               DRM_ERROR("GPU hanging too fast, declaring wedged!\n");
+       } else switch (INTEL_INFO(dev)->gen) {
        case 5:
                ret = ironlake_do_reset(dev, flags);
                break;
@@ -444,6 +446,7 @@ int i915_reset(struct drm_device *dev, u8 flags)
                ret = i8xx_do_reset(dev, flags);
                break;
        }
+       dev_priv->last_gpu_reset = get_seconds();
        if (ret) {
                DRM_ERROR("Failed to reset chip.\n");
                mutex_unlock(&dev->struct_mutex);

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d19a26af3f8e4250aed07e21a71ad5130ee10894..73ad8bff2c2a7ab833dbad13156453e5d9c2569d 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -699,6 +699,8 @@ typedef struct drm_i915_private {
        struct drm_mm_node *compressed_fb;
        struct drm_mm_node *compressed_llb;
 
+       unsigned long last_gpu_reset;
+
        /* list of fbdev register on this device */
        struct intel_fbdev *fbdev;
 } drm_i915_private_t;