Merge tag 'iommu-updates-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Consolidate iommu_map/unmap functions.

   There have been blocking and atomic variants so far, but that was
   problematic as this approach does not scale with required new
   variants which just differ in the GFP flags used. So Jason
   consolidated this back into single functions that take a GFP
   parameter.

 - Retire the detach_dev() call-back in iommu_ops

 - Arm SMMU updates from Will:
     - Device-tree binding updates:
         - Cater for three power domains on SM6375
         - Document existing compatible strings for Qualcomm SoCs
         - Tighten up clocks description for platform-specific
           compatible strings
     - Enable Qualcomm workarounds for some additional platforms that
       need them

 - Intel VT-d updates from Lu Baolu:
     - Add Intel IOMMU performance monitoring support
     - Set No Execute Enable bit in PASID table entry
     - Two performance optimizations
     - Fix PASID directory pointer coherency
     - Fix missed rollbacks in error path
     - Cleanups

 - Apple t8110 DART support

 - Exynos IOMMU:
     - Implement better fault handling
     - Error handling fixes

 - Renesas IPMMU:
     - Add device tree bindings for r8a779g0

 - AMD IOMMU:
     - Various fixes for handling on SNP-enabled systems and
       handling of faults with unknown request-ids
     - Cleanups and other small fixes

 - Various other smaller fixes and cleanups

* tag 'iommu-updates-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (71 commits)
  iommu/amd: Skip attach device domain is same as new domain
  iommu: Attach device group to old domain in error path
  iommu/vt-d: Allow to use flush-queue when first level is default
  iommu/vt-d: Fix PASID directory pointer coherency
  iommu/vt-d: Avoid superfluous IOTLB tracking in lazy mode
  iommu/vt-d: Fix error handling in sva enable/disable paths
  iommu/amd: Improve page fault error reporting
  iommu/amd: Do not identity map v2 capable device when snp is enabled
  iommu: Fix error unwind in iommu_group_alloc()
  iommu/of: mark an unused function as __maybe_unused
  iommu: dart: DART_T8110_ERROR range should be 0 to 5
  iommu/vt-d: Enable IOMMU perfmon support
  iommu/vt-d: Add IOMMU perfmon overflow handler support
  iommu/vt-d: Support cpumask for IOMMU perfmon
  iommu/vt-d: Add IOMMU perfmon support
  iommu/vt-d: Support Enhanced Command Interface
  iommu/vt-d: Retrieve IOMMU perfmon capability information
  iommu/vt-d: Support size of the register set in DRHD
  iommu/vt-d: Set No Execute Enable bit in PASID table entry
  iommu/vt-d: Remove sva from intel_svm_dev
  ...

3 files changed, 27 insertions, 20 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c135f6e37a00..8bc01071474a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -984,7 +984,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 
 		len = (j - i) << PAGE_SHIFT;
 		ret = iommu_map(mapping->domain, iova, phys, len,
-				__dma_info_to_prot(DMA_BIDIRECTIONAL, attrs));
+				__dma_info_to_prot(DMA_BIDIRECTIONAL, attrs),
+				GFP_KERNEL);
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1207,7 +1208,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 
 		prot = __dma_info_to_prot(dir, attrs);
 
-		ret = iommu_map(mapping->domain, iova, phys, len, prot);
+		ret = iommu_map(mapping->domain, iova, phys, len, prot,
+				GFP_KERNEL);
 		if (ret < 0)
 			goto fail;
 		count += len >> PAGE_SHIFT;
@@ -1379,7 +1381,8 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 
 	prot = __dma_info_to_prot(dir, attrs);
 
-	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
+	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len,
+			prot, GFP_KERNEL);
 	if (ret < 0)
 		goto fail;
 
@@ -1443,7 +1446,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
 
-	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot);
+	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL);
 	if (ret < 0)
 		goto fail;
 
diff --git a/arch/s390/include/asm/pci_dma.h b/arch/s390/include/asm/pci_dma.h
index 91e63426bdc5..7119c04c51c5 100644
--- a/arch/s390/include/asm/pci_dma.h
+++ b/arch/s390/include/asm/pci_dma.h
@@ -186,9 +186,10 @@ static inline unsigned long *get_st_pto(unsigned long entry)
 
 /* Prototypes */
 void dma_free_seg_table(unsigned long);
-unsigned long *dma_alloc_cpu_table(void);
+unsigned long *dma_alloc_cpu_table(gfp_t gfp);
 void dma_cleanup_tables(unsigned long *);
-unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr);
+unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr,
+				  gfp_t gfp);
 void dma_update_cpu_trans(unsigned long *entry, phys_addr_t page_addr, int flags);
 
 extern const struct dma_map_ops s390_pci_dma_ops;
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index ea478d11fbd1..2d9b01d7ca4c 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -27,11 +27,11 @@ static int zpci_refresh_global(struct zpci_dev *zdev)
 				  zdev->iommu_pages * PAGE_SIZE);
 }
 
-unsigned long *dma_alloc_cpu_table(void)
+unsigned long *dma_alloc_cpu_table(gfp_t gfp)
 {
 	unsigned long *table, *entry;
 
-	table = kmem_cache_alloc(dma_region_table_cache, GFP_ATOMIC);
+	table = kmem_cache_alloc(dma_region_table_cache, gfp);
 	if (!table)
 		return NULL;
 
@@ -45,11 +45,11 @@ static void dma_free_cpu_table(void *table)
 	kmem_cache_free(dma_region_table_cache, table);
 }
 
-static unsigned long *dma_alloc_page_table(void)
+static unsigned long *dma_alloc_page_table(gfp_t gfp)
 {
 	unsigned long *table, *entry;
 
-	table = kmem_cache_alloc(dma_page_table_cache, GFP_ATOMIC);
+	table = kmem_cache_alloc(dma_page_table_cache, gfp);
 	if (!table)
 		return NULL;
 
@@ -63,7 +63,7 @@ static void dma_free_page_table(void *table)
 	kmem_cache_free(dma_page_table_cache, table);
 }
 
-static unsigned long *dma_get_seg_table_origin(unsigned long *rtep)
+static unsigned long *dma_get_seg_table_origin(unsigned long *rtep, gfp_t gfp)
 {
 	unsigned long old_rte, rte;
 	unsigned long *sto;
@@ -72,7 +72,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep)
 	if (reg_entry_isvalid(rte)) {
 		sto = get_rt_sto(rte);
 	} else {
-		sto = dma_alloc_cpu_table();
+		sto = dma_alloc_cpu_table(gfp);
 		if (!sto)
 			return NULL;
 
@@ -90,7 +90,7 @@ static unsigned long *dma_get_seg_table_origin(unsigned long *rtep)
 	return sto;
 }
 
-static unsigned long *dma_get_page_table_origin(unsigned long *step)
+static unsigned long *dma_get_page_table_origin(unsigned long *step, gfp_t gfp)
 {
 	unsigned long old_ste, ste;
 	unsigned long *pto;
@@ -99,7 +99,7 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step)
 	if (reg_entry_isvalid(ste)) {
 		pto = get_st_pto(ste);
 	} else {
-		pto = dma_alloc_page_table();
+		pto = dma_alloc_page_table(gfp);
 		if (!pto)
 			return NULL;
 		set_st_pto(&ste, virt_to_phys(pto));
@@ -116,18 +116,19 @@ static unsigned long *dma_get_page_table_origin(unsigned long *step)
 	return pto;
 }
 
-unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr)
+unsigned long *dma_walk_cpu_trans(unsigned long *rto, dma_addr_t dma_addr,
+				  gfp_t gfp)
 {
 	unsigned long *sto, *pto;
 	unsigned int rtx, sx, px;
 
 	rtx = calc_rtx(dma_addr);
-	sto = dma_get_seg_table_origin(&rto[rtx]);
+	sto = dma_get_seg_table_origin(&rto[rtx], gfp);
 	if (!sto)
 		return NULL;
 
 	sx = calc_sx(dma_addr);
-	pto = dma_get_page_table_origin(&sto[sx]);
+	pto = dma_get_page_table_origin(&sto[sx], gfp);
 	if (!pto)
 		return NULL;
 
@@ -170,7 +171,8 @@ static int __dma_update_trans(struct zpci_dev *zdev, phys_addr_t pa,
 		return -EINVAL;
 
 	for (i = 0; i < nr_pages; i++) {
-		entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+		entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr,
+					   GFP_ATOMIC);
 		if (!entry) {
 			rc = -ENOMEM;
 			goto undo_cpu_trans;
@@ -186,7 +188,8 @@ undo_cpu_trans:
 		while (i-- > 0) {
 			page_addr -= PAGE_SIZE;
 			dma_addr -= PAGE_SIZE;
-			entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr);
+			entry = dma_walk_cpu_trans(zdev->dma_table, dma_addr,
+						   GFP_ATOMIC);
 			if (!entry)
 				break;
 			dma_update_cpu_trans(entry, page_addr, flags);
@@ -576,7 +579,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
 
 	spin_lock_init(&zdev->iommu_bitmap_lock);
 
-	zdev->dma_table = dma_alloc_cpu_table();
+	zdev->dma_table = dma_alloc_cpu_table(GFP_KERNEL);
 	if (!zdev->dma_table) {
 		rc = -ENOMEM;
 		goto out;