Merge tag 'iommu-updates-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - Debugfs support for the Intel VT-d driver.

   When enabled, it now also exposes some of its internal data
   structures to user-space for debugging purposes.

 - ARM-SMMU driver now uses the generic deferred flushing and fast-path
   iova allocation code.

   This is expected to be a major performance improvement, as this
   allocation path scales a lot better.

 - Support for r8a7744 in the Renesas iommu driver

 - Couple of minor fixes and improvements all over the place

* tag 'iommu-updates-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (39 commits)
  iommu/arm-smmu-v3: Remove unnecessary wrapper function
  iommu/arm-smmu-v3: Add SPDX header
  iommu/amd: Add default branch in amd_iommu_capable()
  dt-bindings: iommu: ipmmu-vmsa: Add r8a7744 support
  iommu/amd: Move iommu_init_pci() to .init section
  iommu/arm-smmu: Support non-strict mode
  iommu/io-pgtable-arm-v7s: Add support for non-strict mode
  iommu/arm-smmu-v3: Add support for non-strict mode
  iommu/io-pgtable-arm: Add support for non-strict mode
  iommu: Add "iommu.strict" command line option
  iommu/dma: Add support for non-strict mode
  iommu/arm-smmu: Ensure that page-table updates are visible before TLBI
  iommu/arm-smmu-v3: Implement flush_iotlb_all hook
  iommu/arm-smmu-v3: Avoid back-to-back CMD_SYNC operations
  iommu/arm-smmu-v3: Fix unexpected CMD_SYNC timeout
  iommu/io-pgtable-arm: Fix race handling in split_blk_unmap()
  iommu/arm-smmu-v3: Fix a couple of minor comment typos
  iommu: Fix a typo
  iommu: Remove .domain_{get,set}_windows
  iommu: Tidy up window attributes
  ...

2 files changed, 11 insertions, 6 deletions

diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index 8cb78dd99672..90c0faf8579f 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -148,6 +148,7 @@
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
+		dma-ranges = <0x0 0x0 0x0 0x0 0x10000 0x00000000>;
 
 		clockgen: clocking@1300000 {
 			compatible = "fsl,ls2080a-clockgen";
@@ -321,6 +322,8 @@
 			reg = <0x00000008 0x0c000000 0 0x40>,	 /* MC portal base */
 			      <0x00000000 0x08340000 0 0x40000>; /* MC control reg */
 			msi-parent = <&its>;
+			iommu-map = <0 &smmu 0 0>;	/* This is fixed-up by u-boot */
+			dma-coherent;
 			#address-cells = <3>;
 			#size-cells = <1>;
 
@@ -424,6 +427,9 @@
 			compatible = "arm,mmu-500";
 			reg = <0 0x5000000 0 0x800000>;
 			#global-interrupts = <12>;
+			#iommu-cells = <1>;
+			stream-match-mask = <0x7C00>;
+			dma-coherent;
 			interrupts = <0 13 4>, /* global secure fault */
 				     <0 14 4>, /* combined secure interrupt */
 				     <0 15 4>, /* global non-secure fault */
@@ -466,7 +472,6 @@
 				     <0 204 4>, <0 205 4>,
 				     <0 206 4>, <0 207 4>,
 				     <0 208 4>, <0 209 4>;
-			mmu-masters = <&fsl_mc 0x300 0>;
 		};
 
 		dspi: dspi@2100000 {
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 072c51fb07d7..cf017c5bb5e7 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -712,7 +712,7 @@ static void __iommu_sync_single_for_cpu(struct device *dev,
 	if (is_device_dma_coherent(dev))
 		return;
 
-	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
 	__dma_unmap_area(phys_to_virt(phys), size, dir);
 }
 
@@ -725,7 +725,7 @@ static void __iommu_sync_single_for_device(struct device *dev,
 	if (is_device_dma_coherent(dev))
 		return;
 
-	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
 	__dma_map_area(phys_to_virt(phys), size, dir);
 }
 
@@ -738,9 +738,9 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
 
-	if (!iommu_dma_mapping_error(dev, dev_addr) &&
-	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
-		__iommu_sync_single_for_device(dev, dev_addr, size, dir);
+	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    !iommu_dma_mapping_error(dev, dev_addr))
+		__dma_map_area(page_address(page) + offset, size, dir);
 
 	return dev_addr;
 }