Commit ff0dac08 authored by Jonathan Cavitt's avatar Jonathan Cavitt Committed by Andi Shyti
Browse files

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: default avatarJohn Harrison <john.c.harrison@intel.com>
Signed-off-by: default avatarJonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: default avatarAndi Shyti <andi.shyti@linux.intel.com>
Acked-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: default avatarNirmoy Das <nirmoy.das@intel.com>
Reviewed-by: default avatarJohn Harrison <john.c.harrison@intel.com>
Signed-off-by: default avatarAndi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231017180806.3054290-3-jonathan.cavitt@intel.com
parent 29e66833

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

+27 −0
Original line number Diff line number Diff line
@@ -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);

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h

+2 −0
Original line number Diff line number Diff line
@@ -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);