Following a GPU hang, we break out of the request loop in order to
unlock the struct_mutex for use by the GPU reset. However, if we retire
all the requests at that moment, we cannot identify the guilty request
after performing the reset.
Fixes: f4457ae71fd6 ("drm/i915: Prevent leaking of -EIO from i915_wait_request()")
Testcase: igt/gem_reset_stats
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Daniel Vetter <daniel.vetter@xxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 474c027..b1a33fe9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1462,7 +1462,10 @@ i915_wait_request(struct drm_i915_gem_request *req)
if (ret)
return ret;
- __i915_gem_request_retire__upto(req);
+ /* If the GPU hung, we want to keep the requests to find the guilty. */
+ if (req->reset_counter == i915_reset_counter(&dev_priv->gpu_error))
+ __i915_gem_request_retire__upto(req);
+
return 0;
}
@@ -1519,7 +1522,8 @@ i915_gem_object_retire_request(struct drm_i915_gem_object *obj,
else if (obj->last_write_req == req)
i915_gem_object_retire__write(obj);
- __i915_gem_request_retire__upto(req);
+ if (req->reset_counter == i915_reset_counter(&req->i915->gpu_error))
+ __i915_gem_request_retire__upto(req);
}
/* A nonblocking variant of the above wait. This is a highly dangerous routine
--
2.8.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
