]> git.ipfire.org Git - thirdparty/kernel/linux.git/commit
drm/xe/migrate: Configure migration queue as low latency
authorFrancois Dugast <francois.dugast@intel.com>
Tue, 23 Dec 2025 11:53:27 +0000 (12:53 +0100)
committerRodrigo Vivi <rodrigo.vivi@intel.com>
Tue, 23 Dec 2025 15:03:48 +0000 (10:03 -0500)
commit15e096960a7fe6b0163d0f35d908cc08d4ca83e8
tree956e2b19cfff93c96e3eb68394e831a15e5b4e49
parent0620837490e0401cb4e9965a1e0c462dbff1c97b
drm/xe/migrate: Configure migration queue as low latency

Commit 5488bec96bcc ("drm/xe/uapi: Use hint for guc to set GT frequency")
introduced low latency hint for use by user space when creating an exec
queue. This instructs SLPC to ramp the GT frequency aggressively.

SVM relies on an internal exec queue to migrate memory upon page faults.
This change creates this exec queue with the low latency hint to speed up
migration.

This should not impact systems where GT frequency is set over sysfs, or
with long running workloads which give enough time for the frequency to
ramp up. An example of memory access pattern that shows an improvement of
SVM performance is running hundreds of times IGT eu-fault-2m-once-device
in xe_exec_system_allocator. The copy duration provided by GT stats in
svm_2M_device_copy_us shows per GPU page fault:
    ~ 165 μs without low latency hint
    ~ 130 μs with low latency hint

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Link: https://patch.msgid.link/20251223115327.49555-1-francois.dugast@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
drivers/gpu/drm/xe/xe_migrate.c