On Sat, 22 Jan 2022 at 00:14, Matthew Brost matthew.brost@intel.com wrote:
Using more guc_ids in the stealing guc id test has no real benefit. Tearing down lots of contexts all at the same time takes a bit of time due to the H2G / G2H ping-pong with the GuC. On some slower platforms this can cause timeous when flushing the test as the GT isn't idle when this ping-pong is happening. Reduce the number of guc ids to speed up the flushing of the test.
Link: https://gitlab.freedesktop.org/drm/intel/-/issues/4821 Signed-off-by: Matthew Brost matthew.brost@intel.com
This also appears to make the test pass on systems with a small LMEM BAR(256M), where before it was just running out of memory, Reviewed-by: Matthew Auld matthew.auld@intel.com
drivers/gpu/drm/i915/gt/uc/selftest_guc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c index d3327b802b761..a115894d5896e 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c @@ -157,7 +157,7 @@ static int intel_guc_steal_guc_ids(void *arg) wakeref = intel_runtime_pm_get(gt->uncore->rpm); engine = intel_selftest_find_any_engine(gt); sv = guc->submission_state.num_guc_ids;
guc->submission_state.num_guc_ids = 4096;
guc->submission_state.num_guc_ids = 512; /* Create spinner to block requests in below loop */ ce[context_index] = intel_context_create(engine);-- 2.34.1