From: Barry Song <baohua@kernel.org>

Leon suggested extending a flush argument to
dma_direct_unmap_phys(), dma_direct_map_phys(), and
dma_direct_sync_single_for_cpu(). For single-buffer cases, this
would use flush=true, 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: Leon Romanovsky <leon@kernel.org>
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>
Signed-off-by: Barry Song <baohua@kernel.org>
---
 kernel/dma/direct.c  | 17 +++++++++++++----
 kernel/dma/direct.h  | 16 ++++++++++------
 kernel/dma/mapping.c |  6 +++---
 3 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 98bacf562ca1..550a1a13148d 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -447,14 +447,19 @@ 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
 
@@ -464,6 +469,7 @@ 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))) {
@@ -475,8 +481,9 @@ 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;
@@ -495,6 +502,8 @@ 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 a69326eed266..d4ad79828090 100644
--- 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();
 	}
 
@@ -85,7 +87,7 @@ 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;
 
@@ -114,7 +116,8 @@ 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;
 
@@ -127,7 +130,8 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev,
 }
 
 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;
 
@@ -137,7 +141,7 @@ 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 37163eb49f9f..d8cfa56a3cbb 100644
--- 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)
-- 
2.43.0

On Sat, Dec 27, 2025 at 11:52:46AM +1300, Barry Song wrote:
> From: Barry Song <baohua@kernel.org>
> 
> Leon suggested extending a flush argument to

Let's move this sentence out of the commit message and place it in the
changelog instead.

> dma_direct_unmap_phys(), dma_direct_map_phys(), and
> dma_direct_sync_single_for_cpu(). For single-buffer cases, this
> would use flush=true, 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: Leon Romanovsky <leon@kernel.org>
> 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>
> Signed-off-by: Barry Song <baohua@kernel.org>
> ---
>  kernel/dma/direct.c  | 17 +++++++++++++----
>  kernel/dma/direct.h  | 16 ++++++++++------
>  kernel/dma/mapping.c |  6 +++---
>  3 files changed, 26 insertions(+), 13 deletions(-)

Thanks,
Reviewed-by: Leon Romanovsky <leon@kernel.org>