iommu/arm-smmu-v3: Use command queue batching helpers to improve performance
authorZhen Lei <thunder.leizhen@huawei.com>
Wed, 11 Aug 2021 11:48:49 +0000 (19:48 +0800)
committerWill Deacon <will@kernel.org>
Fri, 13 Aug 2021 13:17:16 +0000 (14:17 +0100)
commiteff19474b1bd60286213e5052ccf246b6a6c7199
treeb5ca08d6dd777adf63eca88bd40c98abf6c9c114
parentef75702d6d65a1993dc0d6dd423fefaa08901f24
iommu/arm-smmu-v3: Use command queue batching helpers to improve performance

The obvious key to the performance optimization of commit 587e6c10a7ce
("iommu/arm-smmu-v3: Reduce contention during command-queue insertion") is
to allow multiple cores to insert commands in parallel after a brief mutex
contention.

Obviously, inserting as many commands at a time as possible can reduce the
number of times the mutex contention participates, thereby improving the
overall performance. At least it reduces the number of calls to function
arm_smmu_cmdq_issue_cmdlist().

Therefore, use command queue batching helpers to insert multiple commands
at a time.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Link: https://lore.kernel.org/r/20210811114852.2429-2-thunder.leizhen@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c