Module: Mesa
Branch: main
Commit: 5aae8a05264c354aa93017d323ce238858f68227
URL:    
http://cgit.freedesktop.org/mesa/mesa/commit/?id=5aae8a05264c354aa93017d323ce238858f68227

Author: Kai-Heng Feng <[email protected]>
Date:   Thu Dec 29 13:43:27 2022 +0800

iris: Retry DRM_IOCTL_I915_GEM_EXECBUFFER2 on ENOMEM

We are seeing endless DRM_IOCTL_SYNCOBJ_WAIT ioctl when system memory is
under pressured.

Commit f9d8d9acbb6a ("iris: Avoid abort() if kernel can't allocate
memory") avoids the abort() on ENOMEM by resetting the batch. However,
when there's an ongoing OpenGL query, resetting the batch will make the
snapshots_landed never be flipped, so iris_get_query_result() gets stuck
in the while loop forever.

Since there's no guarantee that the next batch after resetting won't hit
ENOMEM, so instead of resetting the batch, be patient and wait until kernel has
enough memory. Once the batch is submiited and snapshots_landed gets
flipped, iris_get_query_result() can proceed normally.

Reviewed-by: José Roberto de Souza <[email protected]>
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6851
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20449>

---

 src/gallium/drivers/iris/iris_batch.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/src/gallium/drivers/iris/iris_batch.c 
b/src/gallium/drivers/iris/iris_batch.c
index 3ad32323a93..8f46bd581b2 100644
--- a/src/gallium/drivers/iris/iris_batch.c
+++ b/src/gallium/drivers/iris/iris_batch.c
@@ -982,9 +982,14 @@ submit_batch(struct iris_batch *batch)
    }
 
    int ret = 0;
-   if (!batch->screen->devinfo->no_hw &&
-       intel_ioctl(batch->screen->fd, DRM_IOCTL_I915_GEM_EXECBUFFER2, 
&execbuf))
-      ret = -errno;
+   if (!batch->screen->devinfo->no_hw) {
+      do {
+         ret = intel_ioctl(batch->screen->fd, DRM_IOCTL_I915_GEM_EXECBUFFER2, 
&execbuf);
+      } while (ret && errno == ENOMEM);
+
+      if (ret)
+        ret = -errno;
+   }
 
    simple_mtx_unlock(bo_deps_lock);
 

Reply via email to