[PATCH RFC 6/6] dma-iommu: Allow DMA sync batching for IOVA link/unlink

[Barry Song]

From: Barry Song <v-songbaohua at oppo.com>

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 at samsung.com>
Cc: Robin Murphy <robin.murphy at arm.com>
Cc: Joerg Roedel <joro at 8bytes.org>
Cc: Will Deacon <will at kernel.org>
Signed-off-by: Barry Song <v-songbaohua at oppo.com>
---
 drivers/iommu/dma-iommu.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c92088855450..95432bdc364f 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1837,7 +1837,7 @@ static int __dma_iova_link(struct device *dev, dma_addr_t addr,
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 
 	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
-		arch_sync_dma_for_device(phys, size, dir);
+		arch_sync_dma_for_device_batch_add(phys, size, dir);
 
 	return iommu_map_nosync(iommu_get_dma_domain(dev), addr, phys, size,
 			prot, GFP_ATOMIC);
@@ -1980,6 +1980,8 @@ 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_batch_flush();
 	return iommu_sync_map(domain, addr - iova_start_pad,
 		      iova_align(iovad, size + iova_start_pad));
 }
@@ -1993,6 +1995,8 @@ 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 {
@@ -2007,8 +2011,7 @@ static void iommu_dma_iova_unlink_range_slow(struct device *dev,
 		len = min_t(size_t,
 			end - addr, iovad->granule - iova_start_pad);
 
-		if (!dev_is_dma_coherent(dev) &&
-		    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
+		if (need_sync_dma)
 			arch_sync_dma_for_cpu(phys, len, dir);
 
 		swiotlb_tbl_unmap_single(dev, phys, len, dir, attrs);
@@ -2016,6 +2019,9 @@ static void iommu_dma_iova_unlink_range_slow(struct device *dev,
 		addr += len;
 		iova_start_pad = 0;
 	} while (addr < end);
+
+	if (need_sync_dma)
+		arch_sync_dma_batch_flush();
 }
 
 static void __iommu_dma_iova_unlink(struct device *dev,
-- 
2.39.3 (Apple Git-146)