[PATCH OLK-6.6 0/1] iommu: set the default iommu-dma mode as non-strict
driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8292 ---------------------------------------------------------------------- The non-strict smmu mode has significant performance gains and can resolve the nvme soft lockup problem. We enable it by default. Currently, many peripherals are faster than before. For example, the top speed of the older netcard is 10Gb/s, and now it's more than 25Gb/s. But when iommu page-table mapping enabled, it's hard to reach the top speed in strict mode, because of frequently map and unmap operations. In order to keep abreast of the times, I think it's better to set non-strict as default. Below it's our iperf performance data of 25Gb netcard: strict mode: 18-20 Gb/s non-strict mode: 23.5 Gb/s Qinxin Xia (1): iommu: set the default iommu-dma mode as non-strict Documentation/admin-guide/kernel-parameters.txt | 2 +- arch/arm64/configs/openeuler_defconfig | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) -- 2.33.0
driver inclusion category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8292 ---------------------------------------------------------------------- The non-strict smmu mode has significant performance gains and can resolve the nvme soft lockup problem. We enable it by default. Currently, many peripherals are faster than before. For example, the top speed of the older netcard is 10Gb/s, and now it's more than 25Gb/s. But when iommu page-table mapping enabled, it's hard to reach the top speed in strict mode, because of frequently map and unmap operations. In order to keep abreast of the times, I think it's better to set non-strict as default. Below it's our iperf performance data of 25Gb netcard: strict mode: 18-20 Gb/s non-strict mode: 23.5 Gb/s Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com> Signed-off-by: Xie Xiuqi <xiexiuqi@huawei.com> --- Documentation/admin-guide/kernel-parameters.txt | 2 +- arch/arm64/configs/openeuler_defconfig | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 90aae84c850a..d72ab64a69b9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2294,7 +2294,7 @@ iommu.strict= [ARM64, X86, S390] Configure TLB invalidation behaviour Format: { "0" | "1" } - 0 - Lazy mode. + 0 - Lazy mode (default). Request that DMA unmap operations use deferred invalidation of hardware TLBs, for increased throughput at the cost of reduced device isolation. diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index d4237341e76d..e25613346942 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -6673,8 +6673,8 @@ CONFIG_IOMMU_IO_PGTABLE_LPAE=y # end of Generic IOMMU Pagetable Support # CONFIG_IOMMU_DEBUGFS is not set -CONFIG_IOMMU_DEFAULT_DMA_STRICT=y -# CONFIG_IOMMU_DEFAULT_DMA_LAZY is not set +# CONFIG_IOMMU_DEFAULT_DMA_STRICT is not set +CONFIG_IOMMU_DEFAULT_DMA_LAZY=y # CONFIG_IOMMU_DEFAULT_PASSTHROUGH is not set CONFIG_OF_IOMMU=y CONFIG_IOMMU_DMA=y -- 2.33.0
反馈: 您发送到kernel@openeuler.org的补丁/补丁集,已成功转换为PR! PR链接地址: https://atomgit.com/openeuler/kernel/merge_requests/19793 邮件列表地址:https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/4FX... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://atomgit.com/openeuler/kernel/merge_requests/19793 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/4FX...
participants (2)
-
patchwork bot -
Qinxin Xia