drm/i915: Skip the ERR_PTR error state

Although commit fb6f0b64e455 ("drm/i915: Prevent machine hang from
Broxton's vtd w/a and error capture") applied cleanly after a 24 month
hiatus, the code had moved on with new methods for peeking and fetching
the captured gpu info. Make sure we catch all uses of the stashed error
state and avoid dereferencing the error pointer.

v2: Move error pointer determination into i915_gpu_capture_state
v3: Restore early check to avoid capturing and then throwing away
subsequent GPU error states.

Fixes: fb6f0b64e455 ("drm/i915: Prevent machine hang from Broxton's vtd w/a and error capture")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181207110554.19897-1-chris@chris-wilson.co.uk
(cherry picked from commit e6154e4cb8b0d3692f84ca0d66b4e1ba0389b134)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 38dcee1ca062483272948bce3a7d9af2b4c83a7d..40a61ef9aac18bdee413df26a9ac6eb9b6a257aa 100644 (file)
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -984,8 +984,8 @@ static int i915_gpu_info_open(struct inode *inode, struct file *file)
        intel_runtime_pm_get(i915);
        gpu = i915_capture_gpu_state(i915);
        intel_runtime_pm_put(i915);
-       if (!gpu)
-               return -ENOMEM;
+       if (IS_ERR(gpu))
+               return PTR_ERR(gpu);
 
        file->private_data = gpu;
        return 0;
@@ -1018,7 +1018,13 @@ i915_error_state_write(struct file *filp,
 
 static int i915_error_state_open(struct inode *inode, struct file *file)
 {
-       file->private_data = i915_first_error_state(inode->i_private);
+       struct i915_gpu_state *error;
+
+       error = i915_first_error_state(inode->i_private);
+       if (IS_ERR(error))
+               return PTR_ERR(error);
+
+       file->private_data  = error;
        return 0;
 }
 

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 07465123c1663c61818fc1b63c1c04cab782ba06..3f9ce403c755961946d10c0ecb7c932dc569f914 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1907,9 +1907,16 @@ i915_capture_gpu_state(struct drm_i915_private *i915)
 {
        struct i915_gpu_state *error;
 
+       /* Check if GPU capture has been disabled */
+       error = READ_ONCE(i915->gpu_error.first_error);
+       if (IS_ERR(error))
+               return error;
+
        error = kzalloc(sizeof(*error), GFP_ATOMIC);
-       if (!error)
-               return NULL;
+       if (!error) {
+               i915_disable_error_state(i915, -ENOMEM);
+               return ERR_PTR(-ENOMEM);
+       }
 
        kref_init(&error->ref);
        error->i915 = i915;
@@ -1945,11 +1952,8 @@ void i915_capture_error_state(struct drm_i915_private *i915,
                return;
 
        error = i915_capture_gpu_state(i915);
-       if (!error) {
-               DRM_DEBUG_DRIVER("out of memory, not capturing error state\n");
-               i915_disable_error_state(i915, -ENOMEM);
+       if (IS_ERR(error))
                return;
-       }
 
        i915_error_capture_msg(i915, error, engine_mask, error_msg);
        DRM_INFO("%s\n", error->error_msg);
@@ -1987,7 +1991,7 @@ i915_first_error_state(struct drm_i915_private *i915)
 
        spin_lock_irq(&i915->gpu_error.lock);
        error = i915->gpu_error.first_error;
-       if (error)
+       if (!IS_ERR_OR_NULL(error))
                i915_gpu_state_get(error);
        spin_unlock_irq(&i915->gpu_error.lock);
 
@@ -2000,10 +2004,11 @@ void i915_reset_error_state(struct drm_i915_private *i915)
 
        spin_lock_irq(&i915->gpu_error.lock);
        error = i915->gpu_error.first_error;
-       i915->gpu_error.first_error = NULL;
+       if (error != ERR_PTR(-ENODEV)) /* if disabled, always disabled */
+               i915->gpu_error.first_error = NULL;
        spin_unlock_irq(&i915->gpu_error.lock);
 
-       if (!IS_ERR(error))
+       if (!IS_ERR_OR_NULL(error))
                i915_gpu_state_put(error);
 }
 

diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 535caebd9813af5d82701b1d7e47b987563cd608..c0cfe7ae2ba5aecbe3daaf8bccce3eee362753a8 100644 (file)
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -521,7 +521,9 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
        ssize_t ret;
 
        gpu = i915_first_error_state(i915);
-       if (gpu) {
+       if (IS_ERR(gpu)) {
+               ret = PTR_ERR(gpu);
+       } else if (gpu) {
                ret = i915_gpu_state_copy_to_buffer(gpu, buf, off, count);
                i915_gpu_state_put(gpu);
        } else {