intel_context_timeline_lock can return can error if interrupted by a user when trying to lock the timeline mutex. Check the return value of intel_context_timeline_lock in eb_pin_timeline (execbuf IOCTL).
Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf") Signed-off-by: Matthew Brost matthew.brost@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index e9541244027a..65a078945b00 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2517,6 +2517,9 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce, i915_request_put(rq);
tl = intel_context_timeline_lock(ce); + if (IS_ERR(tl)) + return PTR_ERR(tl); + intel_context_exit(ce); intel_context_timeline_unlock(tl);
On 1/4/2022 09:31, Matthew Brost wrote:
intel_context_timeline_lock can return can error if interrupted by a user when trying to lock the timeline mutex. Check the return value of intel_context_timeline_lock in eb_pin_timeline (execbuf IOCTL).
Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf") Signed-off-by: Matthew Brost matthew.brost@intel.com
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index e9541244027a..65a078945b00 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2517,6 +2517,9 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce, i915_request_put(rq);
tl = intel_context_timeline_lock(ce);
if (IS_ERR(tl))return PTR_ERR(tl);intel_context_exit(ce);
Won't this leak the stuff acquired by the intel_context_enter() above if the _exit() is now skipped?
John.
intel_context_timeline_unlock(tl);
On Tue, Jan 04, 2022 at 03:05:03PM -0800, John Harrison wrote:
On 1/4/2022 09:31, Matthew Brost wrote:
intel_context_timeline_lock can return can error if interrupted by a user when trying to lock the timeline mutex. Check the return value of intel_context_timeline_lock in eb_pin_timeline (execbuf IOCTL).
Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf") Signed-off-by: Matthew Brost matthew.brost@intel.com
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index e9541244027a..65a078945b00 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2517,6 +2517,9 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce, i915_request_put(rq); tl = intel_context_timeline_lock(ce);
if (IS_ERR(tl))return PTR_ERR(tl);intel_context_exit(ce);Won't this leak the stuff acquired by the intel_context_enter() above if the _exit() is now skipped?
Yep, this isn't right. I think should just call mutex_lock / mutex_unlock directly on the timeline mutex.
Matt
John.
intel_context_timeline_unlock(tl);
dri-devel@lists.freedesktop.org
-
John Harrison -
Matthew Brost