From f406c8e4b770ca3b0df84a17349e13f2b6b07d10 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 7 May 2024 13:20:21 +0200 Subject: dma: avoid redundant calls for sync operations Quite often, devices do not need dma_sync operations on x86_64 at least. Indeed, when dev_is_dma_coherent(dev) is true and dev_use_swiotlb(dev) is false, iommu_dma_sync_single_for_cpu() and friends do nothing. However, indirectly calling them when CONFIG_RETPOLINE=y consumes about 10% of cycles on a cpu receiving packets from softirq at ~100Gbit rate. Even if/when CONFIG_RETPOLINE is not set, there is a cost of about 3%. Add dev->need_dma_sync boolean and turn it off during the device initialization (dma_set_mask()) depending on the setup: dev_is_dma_coherent() for the direct DMA, !(sync_single_for_device || sync_single_for_cpu) or the new dma_map_ops flag, %DMA_F_CAN_SKIP_SYNC, advertised for non-NULL DMA ops. Then later, if/when swiotlb is used for the first time, the flag is reset back to on, from swiotlb_tbl_map_single(). On iavf, the UDP trafficgen with XDP_DROP in skb mode test shows +3-5% increase for direct DMA. Suggested-by: Christoph Hellwig # direct DMA shortcut Co-developed-by: Eric Dumazet Signed-off-by: Eric Dumazet Signed-off-by: Alexander Lobakin Signed-off-by: Christoph Hellwig --- include/linux/device.h | 4 ++++ include/linux/dma-map-ops.h | 12 ++++++++++ include/linux/dma-mapping.h | 53 ++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 64 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index b9f5464f44ed..ed95b829f05b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -691,6 +691,7 @@ struct device_physical_location { * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. + * @dma_need_sync: The device needs performing DMA sync operations. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -803,6 +804,9 @@ struct device { #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif +#ifdef CONFIG_DMA_NEED_SYNC + bool dma_need_sync:1; +#endif }; /** diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..4893cb89cb52 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -18,8 +18,11 @@ struct iommu_ops; * * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. + * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is + * coherent and it's not an SWIOTLB buffer. */ #define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) +#define DMA_F_CAN_SKIP_SYNC (1 << 1) struct dma_map_ops { unsigned int flags; @@ -273,6 +276,15 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +static inline void dma_reset_need_sync(struct device *dev) +{ +#ifdef CONFIG_DMA_NEED_SYNC + /* Reset it only once so that the function can be called on hotpath */ + if (unlikely(!dev->dma_need_sync)) + dev->dma_need_sync = true; +#endif +} + /* * Check whether potential kmalloc() buffers are safe for non-coherent DMA. */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index a569b56b25e2..eb4e15893b6c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -282,16 +282,59 @@ static inline int dma_mmap_noncontiguous(struct device *dev, #endif /* CONFIG_HAS_DMA */ #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +static inline bool dma_dev_need_sync(const struct device *dev) +{ + /* Always call DMA sync operations when debugging is enabled */ + return dev->dma_need_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); +} + +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_cpu(dev, addr, size, dir); +} + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_device(dev, addr, size, dir); +} + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_cpu(dev, sg, nelems, dir); +} + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_device(dev, sg, nelems, dir); +} + +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false; +} #else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ +static inline bool dma_dev_need_sync(const struct device *dev) +{ + return false; +} static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { -- cgit