Merge tag 'iommu-updates-v6.7' of git://git.kernel.org/pub/scm/linux/…

…kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - Make default-domains mandatory for all IOMMU drivers
   - Remove group refcounting
   - Add generic_single_device_group() helper and consolidate drivers
   - Cleanup map/unmap ops
   - Scaling improvements for the IOVA rcache depot
   - Convert dart & iommufd to the new domain_alloc_paging()

  ARM-SMMU:
   - Device-tree binding update:
       - Add qcom,sm7150-smmu-v2 for Adreno on SM7150 SoC
   - SMMUv2:
       - Support for Qualcomm SDM670 (MDSS) and SM7150 SoCs
   - SMMUv3:
       - Large refactoring of the context descriptor code to move the CD
         table into the master, paving the way for '->set_dev_pasid()'
         support on non-SVA domains
   - Minor cleanups to the SVA code

  Intel VT-d:
   - Enable debugfs to dump domain attached to a pasid
   - Remove an unnecessary inline function

  AMD IOMMU:
   - Initial patches for SVA support (not complete yet)

  S390 IOMMU:
   - DMA-API conversion and optimized IOTLB flushing

  And some smaller fixes and improvements"

* tag 'iommu-updates-v6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (102 commits)
  iommu/dart: Remove the force_bypass variable
  iommu/dart: Call apple_dart_finalize_domain() as part of alloc_paging()
  iommu/dart: Convert to domain_alloc_paging()
  iommu/dart: Move the blocked domain support to a global static
  iommu/dart: Use static global identity domains
  iommufd: Convert to alloc_domain_paging()
  iommu/vt-d: Use ops->blocked_domain
  iommu/vt-d: Update the definition of the blocking domain
  iommu: Move IOMMU_DOMAIN_BLOCKED global statics to ops->blocked_domain
  Revert "iommu/vt-d: Remove unused function"
  iommu/amd: Remove DMA_FQ type from domain allocation path
  iommu: change iommu_map_sgtable to return signed values
  iommu/virtio: Add __counted_by for struct viommu_request and use struct_size()
  iommu/vt-d: debugfs: Support dumping a specified page table
  iommu/vt-d: debugfs: Create/remove debugfs file per {device, pasid}
  iommu/vt-d: debugfs: Dump entry pointing to huge page
  iommu/vt-d: Remove unused function
  iommu/arm-smmu-v3-sva: Remove bond refcount
  iommu/arm-smmu-v3-sva: Remove unused iommu_sva handle
  iommu/arm-smmu-v3: Rename cdcfg to cd_table
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -2227,7 +2227,7 @@
 			  forcing Dual Address Cycle for PCI cards supporting
 			  greater than 32-bit addressing.
 
-	iommu.strict=	[ARM64, X86] Configure TLB invalidation behaviour
+	iommu.strict=	[ARM64, X86, S390] Configure TLB invalidation behaviour
 			Format: { "0" | "1" }
 			0 - Lazy mode.
 			  Request that DMA unmap operations use deferred
@@ -5694,9 +5694,10 @@
 	s390_iommu=	[HW,S390]
 			Set s390 IOTLB flushing mode
 		strict
-			With strict flushing every unmap operation will result in
-			an IOTLB flush. Default is lazy flushing before reuse,
-			which is faster.
+			With strict flushing every unmap operation will result
+			in an IOTLB flush. Default is lazy flushing before
+			reuse, which is faster. Deprecated, equivalent to
+			iommu.strict=1.
 
 	s390_iommu_aperture=	[KNL,S390]
 			Specifies the size of the per device DMA address space

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -110,6 +110,7 @@ properties:
               - qcom,sdm630-smmu-v2
               - qcom,sdm845-smmu-v2
               - qcom,sm6350-smmu-v2
+              - qcom,sm7150-smmu-v2
           - const: qcom,adreno-smmu
           - const: qcom,smmu-v2
       - description: Qcom Adreno GPUs on Google Cheza platform
@@ -409,6 +410,7 @@ allOf:
           contains:
             enum:
               - qcom,sm6350-smmu-v2
+              - qcom,sm7150-smmu-v2
               - qcom,sm8150-smmu-500
               - qcom,sm8250-smmu-500
     then:

arch/arm/configs/multi_v7_defconfig

@@ -1076,7 +1076,6 @@ CONFIG_QCOM_IPCC=y
 CONFIG_OMAP_IOMMU=y
 CONFIG_OMAP_IOMMU_DEBUG=y
 CONFIG_ROCKCHIP_IOMMU=y
-CONFIG_TEGRA_IOMMU_GART=y
 CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_EXYNOS_IOMMU=y
 CONFIG_QCOM_IOMMU=y

arch/arm/configs/tegra_defconfig

@@ -292,7 +292,6 @@ CONFIG_CHROME_PLATFORMS=y
 CONFIG_CROS_EC=y
 CONFIG_CROS_EC_I2C=m
 CONFIG_CROS_EC_SPI=m
-CONFIG_TEGRA_IOMMU_GART=y
 CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_ARCH_TEGRA_2x_SOC=y
 CONFIG_ARCH_TEGRA_3x_SOC=y

arch/powerpc/kernel/iommu.c

@@ -1280,13 +1280,19 @@ struct iommu_table_group_ops spapr_tce_table_group_ops = {
 /*
  * A simple iommu_ops to allow less cruft in generic VFIO code.
  */
-static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom,
-					       struct device *dev)
+static int
+spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
+				    struct device *dev)
 {
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_group *grp = iommu_group_get(dev);
 	struct iommu_table_group *table_group;
 	int ret = -EINVAL;
 
+	/* At first attach the ownership is already set */
+	if (!domain)
+		return 0;
+
 	if (!grp)
 		return -ENODEV;
 
@@ -1297,17 +1303,22 @@ static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom,
 	return ret;
 }
 
-static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev)
-{
-	struct iommu_group *grp = iommu_group_get(dev);
-	struct iommu_table_group *table_group;
+static const struct iommu_domain_ops spapr_tce_platform_domain_ops = {
+	.attach_dev = spapr_tce_platform_iommu_attach_dev,
+};
 
-	table_group = iommu_group_get_iommudata(grp);
-	table_group->ops->release_ownership(table_group);
-}
+static struct iommu_domain spapr_tce_platform_domain = {
+	.type = IOMMU_DOMAIN_PLATFORM,
+	.ops = &spapr_tce_platform_domain_ops,
+};
 
-static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = {
-	.attach_dev = spapr_tce_blocking_iommu_attach_dev,
+static struct iommu_domain spapr_tce_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	/*
+	 * FIXME: SPAPR mixes blocked and platform behaviors, the blocked domain
+	 * also sets the dma_api ops
+	 */
+	.ops = &spapr_tce_platform_domain_ops,
 };
 
 static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
@@ -1322,22 +1333,6 @@ static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap)
 	return false;
 }
 
-static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type)
-{
-	struct iommu_domain *dom;
-
-	if (type != IOMMU_DOMAIN_BLOCKED)
-		return NULL;
-
-	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
-	if (!dom)
-		return NULL;
-
-	dom->ops = &spapr_tce_blocking_domain_ops;
-
-	return dom;
-}
-
 static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
 {
 	struct pci_dev *pdev;
@@ -1371,12 +1366,12 @@ static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev)
 }
 
 static const struct iommu_ops spapr_tce_iommu_ops = {
+	.default_domain = &spapr_tce_platform_domain,
+	.blocked_domain = &spapr_tce_blocked_domain,
 	.capable = spapr_tce_iommu_capable,
-	.domain_alloc = spapr_tce_iommu_domain_alloc,
 	.probe_device = spapr_tce_iommu_probe_device,
 	.release_device = spapr_tce_iommu_release_device,
 	.device_group = spapr_tce_iommu_device_group,
-	.set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma,
 };
 
 static struct attribute *spapr_tce_iommu_attrs[] = {

arch/s390/include/asm/pci.h

@@ -159,13 +159,6 @@ struct zpci_dev {
 	unsigned long	*dma_table;
 	int		tlb_refresh;
 
-	spinlock_t	iommu_bitmap_lock;
-	unsigned long	*iommu_bitmap;
-	unsigned long	*lazy_bitmap;
-	unsigned long	iommu_size;
-	unsigned long	iommu_pages;
-	unsigned int	next_bit;
-
 	struct iommu_device iommu_dev;  /* IOMMU core handle */
 
 	char res_name[16];
@@ -180,10 +173,6 @@ struct zpci_dev {
 	struct zpci_fmb *fmb;
 	u16		fmb_update;	/* update interval */
 	u16		fmb_length;
-	/* software counters */
-	atomic64_t allocated_pages;
-	atomic64_t mapped_pages;
-	atomic64_t unmapped_pages;
 
 	u8		version;
 	enum pci_bus_speed max_bus_speed;

arch/s390/include/asm/pci_clp.h

@@ -50,6 +50,9 @@ struct clp_fh_list_entry {
 #define CLP_UTIL_STR_LEN	64
 #define CLP_PFIP_NR_SEGMENTS	4
 
+/* PCI function type numbers */
+#define PCI_FUNC_TYPE_ISM	0x5	/* ISM device */
+
 extern bool zpci_unique_uid;
 
 struct clp_rsp_slpc_pci {

arch/s390/include/asm/pci_dma.h

@@ -82,117 +82,16 @@ enum zpci_ioat_dtype {
 #define ZPCI_TABLE_VALID_MASK		0x20
 #define ZPCI_TABLE_PROT_MASK		0x200
 
-static inline unsigned int calc_rtx(dma_addr_t ptr)
-{
-	return ((unsigned long) ptr >> ZPCI_RT_SHIFT) & ZPCI_INDEX_MASK;
-}
-
-static inline unsigned int calc_sx(dma_addr_t ptr)
-{
-	return ((unsigned long) ptr >> ZPCI_ST_SHIFT) & ZPCI_INDEX_MASK;
-}
-
-static inline unsigned int calc_px(dma_addr_t ptr)
-{
-	return ((unsigned long) ptr >> PAGE_SHIFT) & ZPCI_PT_MASK;
-}
-
-static inline void set_pt_pfaa(unsigned long *entry, phys_addr_t pfaa)
-{
-	*entry &= ZPCI_PTE_FLAG_MASK;
-	*entry |= (pfaa & ZPCI_PTE_ADDR_MASK);
-}
-
-static inline void set_rt_sto(unsigned long *entry, phys_addr_t sto)
-{
-	*entry &= ZPCI_RTE_FLAG_MASK;
-	*entry |= (sto & ZPCI_RTE_ADDR_MASK);
-	*entry |= ZPCI_TABLE_TYPE_RTX;
-}
-
-static inline void set_st_pto(unsigned long *entry, phys_addr_t pto)
-{
-	*entry &= ZPCI_STE_FLAG_MASK;
-	*entry |= (pto & ZPCI_STE_ADDR_MASK);
-	*entry |= ZPCI_TABLE_TYPE_SX;
-}
-
-static inline void validate_rt_entry(unsigned long *entry)
-{
-	*entry &= ~ZPCI_TABLE_VALID_MASK;
-	*entry &= ~ZPCI_TABLE_OFFSET_MASK;
-	*entry |= ZPCI_TABLE_VALID;
-	*entry |= ZPCI_TABLE_LEN_RTX;
-}
-
-static inline void validate_st_entry(unsigned long *entry)
-{
-	*entry &= ~ZPCI_TABLE_VALID_MASK;
-	*entry |= ZPCI_TABLE_VALID;
-}
-
-static inline void invalidate_pt_entry(unsigned long *entry)
-{
-	WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_INVALID);
-	*entry &= ~ZPCI_PTE_VALID_MASK;
-	*entry |= ZPCI_PTE_INVALID;
-}
-
-static inline void validate_pt_entry(unsigned long *entry)
-{
-	WARN_ON_ONCE((*entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID);
-	*entry &= ~ZPCI_PTE_VALID_MASK;
-	*entry |= ZPCI_PTE_VALID;
-}
-
-static inline void entry_set_protected(unsigned long *entry)
-{
-	*entry &= ~ZPCI_TABLE_PROT_MASK;
-	*entry |= ZPCI_TABLE_PROTECTED;
-}
-
-static inline void entry_clr_protected(unsigned long *entry)
-{
-	*entry &= ~ZPCI_TABLE_PROT_MASK;
-	*entry |= ZPCI_TABLE_UNPROTECTED;
-}
-
-static inline int reg_entry_isvalid(unsigned long entry)
-{
-	return (entry & ZPCI_TABLE_VALID_MASK) == ZPCI_TABLE_VALID;
-}
-
-static inline int pt_entry_isvalid(unsigned long entry)
-{
-	return (entry & ZPCI_PTE_VALID_MASK) == ZPCI_PTE_VALID;
-}
-
-static inline unsigned long *get_rt_sto(unsigned long entry)
-{
-	if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_RTX)
-		return phys_to_virt(entry & ZPCI_RTE_ADDR_MASK);
-	else
-		return NULL;
-
-}
-
-static inline unsigned long *get_st_pto(unsigned long entry)
-{
-	if ((entry & ZPCI_TABLE_TYPE_MASK) == ZPCI_TABLE_TYPE_SX)
-		return phys_to_virt(entry & ZPCI_STE_ADDR_MASK);
-	else
-		return NULL;
-}
-
-/* Prototypes */
-void dma_free_seg_table(unsigned long);
-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,
-				  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;
+struct zpci_iommu_ctrs {
+	atomic64_t		mapped_pages;
+	atomic64_t		unmapped_pages;
+	atomic64_t		global_rpcits;
+	atomic64_t		sync_map_rpcits;
+	atomic64_t		sync_rpcits;
+};
+
+struct zpci_dev;
 
+struct zpci_iommu_ctrs *zpci_get_iommu_ctrs(struct zpci_dev *zdev);
 
 #endif

arch/s390/pci/Makefile

@@ -3,7 +3,7 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
+obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o \
 			   pci_bus.o pci_kvm_hook.o
 obj-$(CONFIG_PCI_IOV)	+= pci_iov.o