drm/i915/selftest: Always cancel semaphore on error

Ensure that we always signal the semaphore when timing out, so that if it
happens to be stuck waiting for the semaphore we will quickly recover
without having to wait for a reset.

Reported-by: CQ Tang <cq.tang@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: CQ Tang <cq.tang@intel.com>
cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Signed-off-by: Karolina Drobnik <karolina.drobnik@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/8b7781f7dbaf2791156491b76d5faa7852e5cbbb.1663081418.git.karolina.drobnik@intel.com

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 8320eab..71e664f 100644 (file)
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1460,18 +1460,17 @@ static int __lrc_isolation(struct intel_engine_cs *engine, u32 poison)
        }
 
        err = poison_registers(B, poison, sema);
-       if (err) {
-               WRITE_ONCE(*sema, -1);
-               i915_request_put(rq);
-               goto err_result1;
-       }
-
-       if (i915_request_wait(rq, 0, HZ / 2) < 0) {
-               i915_request_put(rq);
+       if (err == 0 && i915_request_wait(rq, 0, HZ / 2) < 0) {
+               pr_err("%s(%s): wait for results timed out\n",
+                      __func__, engine->name);
                err = -ETIME;
-               goto err_result1;
        }
+
+       /* Always cancel the semaphore wait, just in case the GPU gets stuck */
+       WRITE_ONCE(*sema, -1);
        i915_request_put(rq);
+       if (err)
+               goto err_result1;
 
        err = compare_isolation(engine, ref, result, A, poison);