From: Nitin Gote Date: Tue, 17 Dec 2024 06:35:32 +0000 (+0530) Subject: drm/i915/gt: Increase a time to retry RING_HEAD reset X-Git-Tag: block-6.14-20240131~40^2~4^2~8 X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=512eadb33489fac4245abdede396cbda17e79a8b;p=linux-block.git drm/i915/gt: Increase a time to retry RING_HEAD reset Issue seen again where engine resets fails because the engine resumes from an incorrect RING_HEAD. HEAD is still not 0 even after writing into it. This seems to be timing issue and we experimented different values from 5ms to 50ms and found out that 50ms works best based on testing. So, if write doesn't succeed at first then retry again. v2: add a comment (Andi Shyti) Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12806 Signed-off-by: Nitin Gote Reviewed-by: Andi Shyti Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20241217063532.2729031-1-nitin.r.gote@intel.com --- diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 32f3b52a183a..d56410863f26 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -230,8 +230,13 @@ static int xcs_resume(struct intel_engine_cs *engine) set_pp_dir(engine); - /* First wake the ring up to an empty/idle ring */ - for ((kt) = ktime_get() + (2 * NSEC_PER_MSEC); + /* + * First wake the ring up to an empty/idle ring. + * Use 50ms of delay to let the engine write successfully + * for all platforms. Experimented with different values and + * determined that 50ms works best based on testing. + */ + for ((kt) = ktime_get() + (50 * NSEC_PER_MSEC); ktime_before(ktime_get(), (kt)); cpu_relax()) { /* * In case of resets fails because engine resumes from