Merge tag 'iommu-updates-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - Conversion of the AMD IOMMU driver to use the dma-iommu code for
   imlementing the DMA-API. This gets rid of quite some code in the
   driver itself, but also has some potential for regressions (non are
   known at the moment).

 - Support for the Qualcomm SMMUv2 implementation in the SDM845 SoC.
   This also includes some firmware interface changes, but those are
   acked by the respective maintainers.

 - Preparatory work to support two distinct page-tables per domain in
   the ARM-SMMU driver

 - Power management improvements for the ARM SMMUv2

 - Custom PASID allocator support

 - Multiple PCI DMA alias support for the AMD IOMMU driver

 - Adaption of the Mediatek driver to the changed IO/TLB flush interface
   of the IOMMU core code.

 - Preparatory patches for the Renesas IOMMU driver to support future
   hardware.

* tag 'iommu-updates-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (62 commits)
  iommu/rockchip: Don't provoke WARN for harmless IRQs
  iommu/vt-d: Turn off translations at shutdown
  iommu/vt-d: Check VT-d RMRR region in BIOS is reported as reserved
  iommu/arm-smmu: Remove duplicate error message
  iommu/arm-smmu-v3: Don't display an error when IRQ lines are missing
  iommu/ipmmu-vmsa: Add utlb_offset_base
  iommu/ipmmu-vmsa: Add helper functions for "uTLB" registers
  iommu/ipmmu-vmsa: Calculate context registers' offset instead of a macro
  iommu/ipmmu-vmsa: Add helper functions for MMU "context" registers
  iommu/ipmmu-vmsa: tidyup register definitions
  iommu/ipmmu-vmsa: Remove all unused register definitions
  iommu/mediatek: Reduce the tlb flush timeout value
  iommu/mediatek: Get rid of the pgtlock
  iommu/mediatek: Move the tlb_sync into tlb_flush
  iommu/mediatek: Delete the leaf in the tlb_flush
  iommu/mediatek: Use gather to achieve the tlb range flush
  iommu/mediatek: Add a new tlb_lock for tlb_flush
  iommu/mediatek: Correct the flush_iotlb_all callback
  iommu/io-pgtable-arm: Rename IOMMU_QCOM_SYS_CACHE and improve doc
  iommu/io-pgtable-arm: Rationalise MAIR handling
  ...

6 files changed, 310 insertions, 6 deletions

diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index a7cf3599d9a1..f64ca27dc210 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -129,6 +129,7 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
+extern void intel_iommu_shutdown(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg);
@@ -137,6 +138,7 @@ extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
+static inline void intel_iommu_shutdown(void) { }
 
 #define	dmar_parse_one_rmrr		dmar_res_noop
 #define	dmar_parse_one_atsr		dmar_res_noop
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ec7a13405f10..ee21eedafe98 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -102,7 +102,7 @@ struct io_pgtable_cfg {
 		struct {
 			u64	ttbr[2];
 			u64	tcr;
-			u64	mair[2];
+			u64	mair;
 		} arm_lpae_s1_cfg;
 
 		struct {
diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h
new file mode 100644
index 000000000000..6f000d7a0ddc
--- /dev/null
+++ b/include/linux/ioasid.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_IOASID_H
+#define __LINUX_IOASID_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+
+#define INVALID_IOASID ((ioasid_t)-1)
+typedef unsigned int ioasid_t;
+typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data);
+typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data);
+
+struct ioasid_set {
+	int dummy;
+};
+
+/**
+ * struct ioasid_allocator_ops - IOASID allocator helper functions and data
+ *
+ * @alloc:	helper function to allocate IOASID
+ * @free:	helper function to free IOASID
+ * @list:	for tracking ops that share helper functions but not data
+ * @pdata:	data belong to the allocator, provided when calling alloc()
+ */
+struct ioasid_allocator_ops {
+	ioasid_alloc_fn_t alloc;
+	ioasid_free_fn_t free;
+	struct list_head list;
+	void *pdata;
+};
+
+#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 }
+
+#if IS_ENABLED(CONFIG_IOASID)
+ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
+		      void *private);
+void ioasid_free(ioasid_t ioasid);
+void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+		  bool (*getter)(void *));
+int ioasid_register_allocator(struct ioasid_allocator_ops *allocator);
+void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator);
+int ioasid_set_data(ioasid_t ioasid, void *data);
+
+#else /* !CONFIG_IOASID */
+static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min,
+				    ioasid_t max, void *private)
+{
+	return INVALID_IOASID;
+}
+
+static inline void ioasid_free(ioasid_t ioasid)
+{
+}
+
+static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+				bool (*getter)(void *))
+{
+	return NULL;
+}
+
+static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator)
+{
+}
+
+static inline int ioasid_set_data(ioasid_t ioasid, void *data)
+{
+	return -ENOTSUPP;
+}
+
+#endif /* CONFIG_IOASID */
+#endif /* __LINUX_IOASID_H */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 29bac5345563..f2223cbb5fd5 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/of.h>
+#include <linux/ioasid.h>
 #include <uapi/linux/iommu.h>
 
 #define IOMMU_READ	(1 << 0)
@@ -31,11 +32,11 @@
  */
 #define IOMMU_PRIV	(1 << 5)
 /*
- * Non-coherent masters on few Qualcomm SoCs can use this page protection flag
- * to set correct cacheability attributes to use an outer level of cache -
- * last level cache, aka system cache.
+ * Non-coherent masters can use this page protection flag to set cacheable
+ * memory attributes for only a transparent outer level of cache, also known as
+ * the last-level or system cache.
  */
-#define IOMMU_QCOM_SYS_CACHE	(1 << 6)
+#define IOMMU_SYS_CACHE_ONLY	(1 << 6)
 
 struct iommu_ops;
 struct iommu_group;
@@ -244,7 +245,10 @@ struct iommu_iotlb_gather {
  * @sva_unbind: Unbind process address space from device
  * @sva_get_pasid: Get PASID associated to a SVA handle
  * @page_response: handle page request response
+ * @cache_invalidate: invalidate translation caches
  * @pgsize_bitmap: bitmap of all possible supported page sizes
+ * @sva_bind_gpasid: bind guest pasid and mm
+ * @sva_unbind_gpasid: unbind guest pasid and mm
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -256,7 +260,7 @@ struct iommu_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
+		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
@@ -306,6 +310,12 @@ struct iommu_ops {
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
 			     struct iommu_page_response *msg);
+	int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info);
+	int (*sva_bind_gpasid)(struct iommu_domain *domain,
+			struct device *dev, struct iommu_gpasid_bind_data *data);
+
+	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
 
 	unsigned long pgsize_bitmap;
 };
@@ -417,10 +427,19 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
+extern int iommu_cache_invalidate(struct iommu_domain *domain,
+				  struct device *dev,
+				  struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+		struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot);
+extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
@@ -428,6 +447,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain,
 			       struct iommu_iotlb_gather *iotlb_gather);
 extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			   struct scatterlist *sg,unsigned int nents, int prot);
+extern size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
@@ -662,6 +684,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return -ENODEV;
 }
 
+static inline int iommu_map_atomic(struct iommu_domain *domain,
+				   unsigned long iova, phys_addr_t paddr,
+				   size_t size, int prot)
+{
+	return -ENODEV;
+}
+
 static inline size_t iommu_unmap(struct iommu_domain *domain,
 				 unsigned long iova, size_t size)
 {
@@ -682,6 +711,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain,
 	return 0;
 }
 
+static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot)
+{
+	return 0;
+}
+
 static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
@@ -1005,6 +1041,25 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
+static inline int
+iommu_cache_invalidate(struct iommu_domain *domain,
+		       struct device *dev,
+		       struct iommu_cache_invalidate_info *inv_info)
+{
+	return -ENODEV;
+}
+static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+				struct device *dev, struct iommu_gpasid_bind_data *data)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					   struct device *dev, int pasid)
+{
+	return -ENODEV;
+}
+
 #endif /* CONFIG_IOMMU_API */
 
 #ifdef CONFIG_IOMMU_DEBUGFS
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 2d5eff506e13..ffd72b3b14ee 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -58,6 +58,7 @@ extern int qcom_scm_set_remote_state(u32 state, u32 id);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
+extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
 extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val);
 extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val);
 #else
@@ -97,6 +98,7 @@ qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; }
 static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; }
+static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; }
 static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return -ENODEV; }
 static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) { return -ENODEV; }
 #endif
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index fc00c5d4741b..4ad3496e5c43 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -152,4 +152,173 @@ struct iommu_page_response {
 	__u32	code;
 };
 
+/* defines the granularity of the invalidation */
+enum iommu_inv_granularity {
+	IOMMU_INV_GRANU_DOMAIN,	/* domain-selective invalidation */
+	IOMMU_INV_GRANU_PASID,	/* PASID-selective invalidation */
+	IOMMU_INV_GRANU_ADDR,	/* page-selective invalidation */
+	IOMMU_INV_GRANU_NR,	/* number of invalidation granularities */
+};
+
+/**
+ * struct iommu_inv_addr_info - Address Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the address-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If ARCHID bit is set, @archid is populated and the invalidation relates
+ *   to cache entries tagged with this architecture specific ID and matching
+ *   the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - If neither PASID or ARCHID is set, global addr invalidation applies.
+ * - The LEAF flag indicates whether only the leaf PTE caching needs to be
+ *   invalidated and other paging structure caches can be preserved.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ * @addr: first stage/level input address
+ * @granule_size: page/block size of the mapping in bytes
+ * @nb_granules: number of contiguous granules to be invalidated
+ */
+struct iommu_inv_addr_info {
+#define IOMMU_INV_ADDR_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_ADDR_FLAGS_ARCHID	(1 << 1)
+#define IOMMU_INV_ADDR_FLAGS_LEAF	(1 << 2)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+	__u64	addr;
+	__u64	granule_size;
+	__u64	nb_granules;
+};
+
+/**
+ * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the PASID-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If the ARCHID bit is set, the @archid is populated and the invalidation
+ *   relates to cache entries tagged with this architecture specific ID and
+ *   matching the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - At least one of PASID or ARCHID must be set.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ */
+struct iommu_inv_pasid_info {
+#define IOMMU_INV_PASID_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_PASID_FLAGS_ARCHID	(1 << 1)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+};
+
+/**
+ * struct iommu_cache_invalidate_info - First level/stage invalidation
+ *     information
+ * @version: API version of this structure
+ * @cache: bitfield that allows to select which caches to invalidate
+ * @granularity: defines the lowest granularity used for the invalidation:
+ *     domain > PASID > addr
+ * @padding: reserved for future use (should be zero)
+ * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID
+ * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR
+ *
+ * Not all the combinations of cache/granularity are valid:
+ *
+ * +--------------+---------------+---------------+---------------+
+ * | type /       |   DEV_IOTLB   |     IOTLB     |      PASID    |
+ * | granularity  |               |               |      cache    |
+ * +==============+===============+===============+===============+
+ * | DOMAIN       |       N/A     |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | PASID        |       Y       |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | ADDR         |       Y       |       Y       |       N/A     |
+ * +--------------+---------------+---------------+---------------+
+ *
+ * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than
+ * @version and @cache.
+ *
+ * If multiple cache types are invalidated simultaneously, they all
+ * must support the used granularity.
+ */
+struct iommu_cache_invalidate_info {
+#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+/* IOMMU paging structure cache */
+#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
+#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
+#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
+#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[2];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	};
+};
+
+/**
+ * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest
+ * SVA binding.
+ *
+ * @flags:	VT-d PASID table entry attributes
+ * @pat:	Page attribute table data to compute effective memory type
+ * @emt:	Extended memory type
+ *
+ * Only guest vIOMMU selectable and effective options are passed down to
+ * the host IOMMU.
+ */
+struct iommu_gpasid_bind_data_vtd {
+#define IOMMU_SVA_VTD_GPASID_SRE	(1 << 0) /* supervisor request */
+#define IOMMU_SVA_VTD_GPASID_EAFE	(1 << 1) /* extended access enable */
+#define IOMMU_SVA_VTD_GPASID_PCD	(1 << 2) /* page-level cache disable */
+#define IOMMU_SVA_VTD_GPASID_PWT	(1 << 3) /* page-level write through */
+#define IOMMU_SVA_VTD_GPASID_EMTE	(1 << 4) /* extended mem type enable */
+#define IOMMU_SVA_VTD_GPASID_CD		(1 << 5) /* PASID-level cache disable */
+	__u64 flags;
+	__u32 pat;
+	__u32 emt;
+};
+
+/**
+ * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
+ * @version:	Version of this data structure
+ * @format:	PASID table entry format
+ * @flags:	Additional information on guest bind request
+ * @gpgd:	Guest page directory base of the guest mm to bind
+ * @hpasid:	Process address space ID used for the guest mm in host IOMMU
+ * @gpasid:	Process address space ID used for the guest mm in guest IOMMU
+ * @addr_width:	Guest virtual address width
+ * @padding:	Reserved for future use (should be zero)
+ * @vtd:	Intel VT-d specific data
+ *
+ * Guest to host PASID mapping can be an identity or non-identity, where guest
+ * has its own PASID space. For non-identify mapping, guest to host PASID lookup
+ * is needed when VM programs guest PASID into an assigned device. VMM may
+ * trap such PASID programming then request host IOMMU driver to convert guest
+ * PASID to host PASID based on this bind data.
+ */
+struct iommu_gpasid_bind_data {
+#define IOMMU_GPASID_BIND_VERSION_1	1
+	__u32 version;
+#define IOMMU_PASID_FORMAT_INTEL_VTD	1
+	__u32 format;
+#define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
+	__u64 flags;
+	__u64 gpgd;
+	__u64 hpasid;
+	__u64 gpasid;
+	__u32 addr_width;
+	__u8  padding[12];
+	/* Vendor specific data */
+	union {
+		struct iommu_gpasid_bind_data_vtd vtd;
+	};
+};
+
 #endif /* _UAPI_IOMMU_H */