From ff0dac080a8555eb3e95573c5ccaec4ac3ca63de Mon Sep 17 00:00:00 2001 From: Jonathan Cavitt Date: Tue, 17 Oct 2023 11:08:01 -0700 Subject: [PATCH] drm/i915/guc: Add CT size delay helper As of now, there is no mechanism for tracking a given request's progress through the queue. Instead, add a helper that returns an estimated maximum time the queue should take to drain if completely full. Suggested-by: John Harrison Signed-off-by: Jonathan Cavitt Reviewed-by: Andi Shyti Acked-by: Tvrtko Ursulin Reviewed-by: Nirmoy Das Reviewed-by: John Harrison Signed-off-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20231017180806.3054290-3-jonathan.cavitt@intel.com --- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 27 +++++++++++++++++++++++ drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h | 2 ++ 2 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index c33210ead1ef..03b616ba4ebb 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -103,6 +103,33 @@ enum { CTB_SEND = 0, CTB_RECV = 1 }; enum { CTB_OWNER_HOST = 0 }; +/* + * Some H2G commands involve a synchronous response that the driver needs + * to wait for. In such cases, a timeout is required to prevent the driver + * from waiting forever in the case of an error (either no error response + * is defined in the protocol or something has died and requires a reset). + * The specific command may be defined as having a time bound response but + * the CT is a queue and that time guarantee only starts from the point + * when the command reaches the head of the queue and is processed by GuC. + * + * Ideally there would be a helper to report the progress of a given + * command through the CT. However, that would require a significant + * amount of work in the CT layer. In the meantime, provide a reasonable + * estimation of the worst case latency it should take for the entire + * queue to drain. And therefore, how long a caller should wait before + * giving up on their request. The current estimate is based on empirical + * measurement of a test that fills the buffer with context creation and + * destruction requests as they seem to be the slowest operation. + */ +long intel_guc_ct_max_queue_time_jiffies(void) +{ + /* + * A 4KB buffer full of context destroy commands takes a little + * over a second to process so bump that to 2s to be super safe. + */ + return (CTB_H2G_BUFFER_SIZE * HZ) / SZ_2K; +} + static void ct_receive_tasklet_func(struct tasklet_struct *t); static void ct_incoming_request_worker_func(struct work_struct *w); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h index 58e42901ff49..2c4bb9a941be 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h @@ -104,6 +104,8 @@ struct intel_guc_ct { #endif }; +long intel_guc_ct_max_queue_time_jiffies(void); + void intel_guc_ct_init_early(struct intel_guc_ct *ct); int intel_guc_ct_init(struct intel_guc_ct *ct); void intel_guc_ct_fini(struct intel_guc_ct *ct);