dma-mapping: Support batch mode for dma_direct_{map,unmap}_sg

Extending these APIs with a flush argument:
dma_direct_unmap_phys(), dma_direct_map_phys(), and
dma_direct_sync_single_for_cpu(). For single-buffer cases, flush=true
would be used, while for SG cases flush=false would be used, followed
by a single flush after all cache operations are issued in
dma_direct_{map,unmap}_sg().

This ultimately benefits dma_map_sg() and dma_unmap_sg().

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Reviewed-by: Leon Romanovsky <leon@kernel.org>
Tested-by: Xueyuan Chen <xueyuan.chen21@gmail.com>
Signed-off-by: Barry Song <baohua@kernel.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260228221337.59951-1-21cnbao@gmail.com

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index c7666e5d5e7c12baedd837c6a1f5156c61a261f8..ec887f443741835d8bae31df223862268a562dd8 100644 (file)
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -444,14 +444,19 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 {
        struct scatterlist *sg;
        int i;
+       bool need_sync = false;
 
        for_each_sg(sgl,  sg, nents, i) {
-               if (sg_dma_is_bus_address(sg))
+               if (sg_dma_is_bus_address(sg)) {
                        sg_dma_unmark_bus_address(sg);
-               else
+               } else {
+                       need_sync = true;
                        dma_direct_unmap_phys(dev, sg->dma_address,
-                                             sg_dma_len(sg), dir, attrs);
+                                             sg_dma_len(sg), dir, attrs, false);
+               }
        }
+       if (need_sync && !dev_is_dma_coherent(dev))
+               arch_sync_dma_flush();
 }
 #endif
 
@@ -461,6 +466,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
        struct pci_p2pdma_map_state p2pdma_state = {};
        struct scatterlist *sg;
        int i, ret;
+       bool need_sync = false;
 
        for_each_sg(sgl, sg, nents, i) {
                switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(sg))) {
@@ -472,8 +478,9 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
                         */
                        break;
                case PCI_P2PDMA_MAP_NONE:
+                       need_sync = true;
                        sg->dma_address = dma_direct_map_phys(dev, sg_phys(sg),
-                                       sg->length, dir, attrs);
+                                       sg->length, dir, attrs, false);
                        if (sg->dma_address == DMA_MAPPING_ERROR) {
                                ret = -EIO;
                                goto out_unmap;
@@ -492,6 +499,8 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
                sg_dma_len(sg) = sg->length;
        }
 
+       if (need_sync && !dev_is_dma_coherent(dev))
+               arch_sync_dma_flush();
        return nents;
 
 out_unmap:

diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
index f925a7e8b000f078e22d406a01922fdf243ff70c..52b361e667008c99f0643995ef698efda282c853 100644 (file)
--- a/kernel/dma/direct.h
+++ b/kernel/dma/direct.h
@@ -67,13 +67,15 @@ static inline void dma_direct_sync_single_for_device(struct device *dev,
 }
 
 static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-               dma_addr_t addr, size_t size, enum dma_data_direction dir)
+               dma_addr_t addr, size_t size, enum dma_data_direction dir,
+               bool flush)
 {
        phys_addr_t paddr = dma_to_phys(dev, addr);
 
        if (!dev_is_dma_coherent(dev)) {
                arch_sync_dma_for_cpu(paddr, size, dir);
-               arch_sync_dma_flush();
+               if (flush)
+                       arch_sync_dma_flush();
                arch_sync_dma_for_cpu_all();
        }
 
@@ -82,7 +84,7 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 
 static inline dma_addr_t dma_direct_map_phys(struct device *dev,
                phys_addr_t phys, size_t size, enum dma_data_direction dir,
-               unsigned long attrs)
+               unsigned long attrs, bool flush)
 {
        dma_addr_t dma_addr;
 
@@ -111,7 +113,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
        if (!dev_is_dma_coherent(dev) &&
            !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
                arch_sync_dma_for_device(phys, size, dir);
-               arch_sync_dma_flush();
+               if (flush)
+                       arch_sync_dma_flush();
        }
        return dma_addr;
 
@@ -124,7 +127,8 @@ err_overflow:
 }
 
 static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
-               size_t size, enum dma_data_direction dir, unsigned long attrs)
+               size_t size, enum dma_data_direction dir, unsigned long attrs,
+               bool flush)
 {
        phys_addr_t phys;
 
@@ -134,7 +138,7 @@ static inline void dma_direct_unmap_phys(struct device *dev, dma_addr_t addr,
 
        phys = dma_to_phys(dev, addr);
        if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-               dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+               dma_direct_sync_single_for_cpu(dev, addr, size, dir, flush);
 
        swiotlb_tbl_unmap_single(dev, phys, size, dir,
                                         attrs | DMA_ATTR_SKIP_CPU_SYNC);

diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 3928a509c44c285e7b45874d876e6e56809c212b..78d8b4039c3e6aeb2f6025b6923ee1912a3f945d 100644 (file)
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -166,7 +166,7 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 
        if (dma_map_direct(dev, ops) ||
            (!is_mmio && arch_dma_map_phys_direct(dev, phys + size)))
-               addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
+               addr = dma_direct_map_phys(dev, phys, size, dir, attrs, true);
        else if (use_dma_iommu(dev))
                addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
        else if (ops->map_phys)
@@ -207,7 +207,7 @@ void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
        BUG_ON(!valid_dma_direction(dir));
        if (dma_map_direct(dev, ops) ||
            (!is_mmio && arch_dma_unmap_phys_direct(dev, addr + size)))
-               dma_direct_unmap_phys(dev, addr, size, dir, attrs);
+               dma_direct_unmap_phys(dev, addr, size, dir, attrs, true);
        else if (use_dma_iommu(dev))
                iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
        else if (ops->unmap_phys)
@@ -373,7 +373,7 @@ void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
 
        BUG_ON(!valid_dma_direction(dir));
        if (dma_map_direct(dev, ops))
-               dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+               dma_direct_sync_single_for_cpu(dev, addr, size, dir, true);
        else if (use_dma_iommu(dev))
                iommu_dma_sync_single_for_cpu(dev, addr, size, dir);
        else if (ops->sync_single_for_cpu)