[PATCH RFC v2 7/8] dma-iommu: Support DMA sync batch mode for IOVA link and unlink

[Barry Song <21cnbao@gmail.com>]

From: Barry Song <baohua@kernel.org>

Apply batched DMA synchronization to __dma_iova_link() and
iommu_dma_iova_unlink_range_slow(). For multiple
sync_dma_for_device() and sync_dma_for_cpu() calls, we only
need to wait once for the completion of all sync operations,
rather than waiting for each one individually.

I do not have the hardware to test this, so it is marked as
RFC. I would greatly appreciate it if someone could test it.

Suggested-by: Marek Szyprowski <m.szyprowski@samsung.com>
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: 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: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Signed-off-by: Barry Song <baohua@kernel.org>
---
 drivers/iommu/dma-iommu.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 6827763a3877..ffa940bdbbaf 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1849,10 +1849,8 @@ static int __dma_iova_link(struct device *dev, dma_addr_t addr,
 	bool coherent = dev_is_dma_coherent(dev);
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 
-	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
+	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		arch_sync_dma_for_device(phys, size, dir);
-		arch_sync_dma_flush();
-	}
 
 	return iommu_map_nosync(iommu_get_dma_domain(dev), addr, phys, size,
 			prot, GFP_ATOMIC);
@@ -1995,6 +1993,8 @@ int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
 	dma_addr_t addr = state->addr + offset;
 	size_t iova_start_pad = iova_offset(iovad, addr);
 
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_flush();
 	return iommu_sync_map(domain, addr - iova_start_pad,
 		      iova_align(iovad, size + iova_start_pad));
 }
@@ -2008,6 +2008,8 @@ static void iommu_dma_iova_unlink_range_slow(struct device *dev,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_start_pad = iova_offset(iovad, addr);
+	bool need_sync_dma = !dev_is_dma_coherent(dev) &&
+			!(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO));
 	dma_addr_t end = addr + size;
 
 	do {
@@ -2023,16 +2025,17 @@ static void iommu_dma_iova_unlink_range_slow(struct device *dev,
 			end - addr, iovad->granule - iova_start_pad);
 
 		if (!dev_is_dma_coherent(dev) &&
-		    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
+		    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 			arch_sync_dma_for_cpu(phys, len, dir);
-			arch_sync_dma_flush();
-		}
 
 		swiotlb_tbl_unmap_single(dev, phys, len, dir, attrs);
 
 		addr += len;
 		iova_start_pad = 0;
 	} while (addr < end);
+
+	if (need_sync_dma)
+		arch_sync_dma_flush();
 }
 
 static void __iommu_dma_iova_unlink(struct device *dev,
-- 
2.43.0