On Sat, Jun 26, 2021 at 07:01:24PM +0800, Zhen Lei wrote:
> 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, function arm_smmu_cmdq_issue_cmd_with_sync() is added to insert
> the 'cmd+sync' commands at a time.
> 
> Signed-off-by: Zhen Lei <[email protected]>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 33 +++++++++++++--------
>  1 file changed, 21 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c 
> b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index 2433d3c29b49ff2..a5361153ca1d6a4 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -858,11 +858,25 @@ static int arm_smmu_cmdq_issue_cmd(struct 
> arm_smmu_device *smmu,
>       return arm_smmu_cmdq_issue_cmdlist(smmu, cmd, 1, false);
>  }
>  
> -static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
> +static int __maybe_unused arm_smmu_cmdq_issue_sync(struct arm_smmu_device 
> *smmu)
>  {
>       return arm_smmu_cmdq_issue_cmdlist(smmu, NULL, 0, true);
>  }
>  
> +static int arm_smmu_cmdq_issue_cmd_with_sync(struct arm_smmu_device *smmu,
> +                                          struct arm_smmu_cmdq_ent *ent)
> +{
> +     u64 cmd[CMDQ_ENT_DWORDS];
> +
> +     if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
> +             dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
> +                      ent->opcode);
> +             return -EINVAL;
> +     }
> +
> +     return arm_smmu_cmdq_issue_cmdlist(smmu, cmd, 1, true);
> +}

This function is almost identical to arm_smmu_cmdq_issue_cmd(). How about
moving the guts out into a helper:

        static int __arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
                                             struct arm_smmu_cmdq_ent *ent,
                                             bool sync);

and then having arm_smmu_cmdq_issue_cmd_with_sync() and
arm_smmu_cmdq_issue_cmd() wrap that?

Will
_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Reply via email to