drm/xe: Fix exec IOCTL long running exec queue ring full condition

The intent is to return -EWOULDBLOCK to the user if a long running exec
queue is full during the exec IOCTL. -EWOULDBLOCK aliases to -EAGAIN
which results in the exec IOCTL doing a retry loop. Fix this by ensuring
the retry loop is broken when returning -EWOULDBLOCK.

Fixes: 8ae8a2e8dd21 ("drm/xe: Long running job update")
Reported-by: Sai Gowtham Ch <sai.gowtham.ch@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Brian Welty <brian.welty@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 0c78a37..9db1867 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -154,7 +154,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
        struct xe_sched_job *job;
        struct dma_fence *rebind_fence;
        struct xe_vm *vm;
-       bool write_locked;
+       bool write_locked, skip_retry = false;
        ktime_t end = 0;
        int err = 0;
 
@@ -265,7 +265,8 @@ retry:
        }
 
        if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
-               err = -EWOULDBLOCK;
+               err = -EWOULDBLOCK;     /* Aliased to -EAGAIN */
+               skip_retry = true;
                goto err_exec;
        }
 
@@ -375,7 +376,7 @@ err_unlock_list:
                up_write(&vm->lock);
        else
                up_read(&vm->lock);
-       if (err == -EAGAIN)
+       if (err == -EAGAIN && !skip_retry)
                goto retry;
 err_syncs:
        for (i = 0; i < num_syncs; i++)