Merge tag 'iommu-updates-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - SMMU Updates from Will Deacon:

     - SMMUv3:
        - Support stalling faults for platform devices
        - Decrease defaults sizes for the event and PRI queues
     - SMMUv2:
        - Support for a new '->probe_finalize' hook, needed by Nvidia
        - Even more Qualcomm compatible strings
        - Avoid Adreno TTBR1 quirk for DB820C platform

 - Intel VT-d updates from Lu Baolu:

     - Convert Intel IOMMU to use sva_lib helpers in iommu core
     - ftrace and debugfs supports for page fault handling
     - Support asynchronous nested capabilities
     - Various misc cleanups

 - Support for new VIOT ACPI table to make the VirtIO IOMMU
   available on x86

 - Add the amd_iommu=force_enable command line option to enable
   the IOMMU on platforms where they are known to cause problems

 - Support for version 2 of the Rockchip IOMMU

 - Various smaller fixes, cleanups and refactorings

* tag 'iommu-updates-v5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (66 commits)
  iommu/virtio: Enable x86 support
  iommu/dma: Pass address limit rather than size to iommu_setup_dma_ops()
  ACPI: Add driver for the VIOT table
  ACPI: Move IOMMU setup code out of IORT
  ACPI: arm64: Move DMA setup operations out of IORT
  iommu/vt-d: Fix dereference of pointer info before it is null checked
  iommu: Update "iommu.strict" documentation
  iommu/arm-smmu: Check smmu->impl pointer before dereferencing
  iommu/arm-smmu-v3: Remove unnecessary oom message
  iommu/arm-smmu: Fix arm_smmu_device refcount leak in address translation
  iommu/arm-smmu: Fix arm_smmu_device refcount leak when arm_smmu_rpm_get fails
  iommu/vt-d: Fix linker error on 32-bit
  iommu/vt-d: No need to typecast
  iommu/vt-d: Define counter explicitly as unsigned int
  iommu/vt-d: Remove unnecessary braces
  iommu/vt-d: Removed unused iommu_count in dmar domain
  iommu/vt-d: Use bitfields for DMAR capabilities
  iommu/vt-d: Use DEVICE_ATTR_RO macro
  iommu/vt-d: Fix out-bounds-warning in intel/svm.c
  iommu/vt-d: Add PRQ handling latency sampling
  ...

8 files changed, 110 insertions, 31 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c6bd4f9a80ba..1ae993fee4a5 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -592,6 +592,9 @@ struct acpi_pci_root {
 
 bool acpi_dma_supported(const struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
+int acpi_iommu_fwspec_init(struct device *dev, u32 id,
+			   struct fwnode_handle *fwnode,
+			   const struct iommu_ops *ops);
 int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
 		       u64 *size);
 int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index b338613fb536..6bb36fd6ba31 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -260,9 +260,12 @@ void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
 
 #ifdef CONFIG_ARM64
 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
+void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size);
 #else
 static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
+static inline void
+acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { }
 #endif
 
 int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 1a12baa58e40..f1f0842a2cb2 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -34,9 +34,8 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
 void acpi_configure_pmsi_domain(struct device *dev);
 int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 /* IOMMU interface */
-void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
-const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
-						const u32 *id_in);
+int iort_dma_get_ranges(struct device *dev, u64 *size);
+int iort_iommu_configure_id(struct device *dev, const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 phys_addr_t acpi_iort_dma_get_max_cpu_address(void);
 #else
@@ -48,11 +47,10 @@ static inline struct irq_domain *iort_get_device_domain(
 { return NULL; }
 static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
-static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
-				  u64 *size) { }
-static inline const struct iommu_ops *iort_iommu_configure_id(
-				      struct device *dev, const u32 *id_in)
-{ return NULL; }
+static inline int iort_dma_get_ranges(struct device *dev, u64 *size)
+{ return -ENODEV; }
+static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in)
+{ return -ENODEV; }
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
 { return 0; }
diff --git a/include/linux/acpi_viot.h b/include/linux/acpi_viot.h
new file mode 100644
index 000000000000..1eb8ee5b0e5f
--- /dev/null
+++ b/include/linux/acpi_viot.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ACPI_VIOT_H__
+#define __ACPI_VIOT_H__
+
+#include <linux/acpi.h>
+
+#ifdef CONFIG_ACPI_VIOT
+void __init acpi_viot_init(void);
+int viot_iommu_configure(struct device *dev);
+#else
+static inline void acpi_viot_init(void) {}
+static inline int viot_iommu_configure(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* __ACPI_VIOT_H__ */
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 6e75a2d689b4..758ca4694257 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -19,7 +19,7 @@ int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 void iommu_put_dma_cookie(struct iommu_domain *domain);
 
 /* Setup call for arch DMA mapping code */
-void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size);
+void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit);
 
 /* The DMA API isn't _quite_ the whole story, though... */
 /*
@@ -50,7 +50,7 @@ struct msi_msg;
 struct device;
 
 static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size)
+				       u64 dma_limit)
 {
 }
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 03faf20a6817..d0fa0b31994d 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -537,7 +537,7 @@ struct context_entry {
 struct dmar_domain {
 	int	nid;			/* node id */
 
-	unsigned	iommu_refcnt[DMAR_UNITS_SUPPORTED];
+	unsigned int iommu_refcnt[DMAR_UNITS_SUPPORTED];
 					/* Refcount of devices per iommu */
 
 
@@ -546,7 +546,10 @@ struct dmar_domain {
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
 
-	bool has_iotlb_device;
+	u8 has_iotlb_device: 1;
+	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
+	u8 iommu_snooping: 1;		/* indicate snooping control feature */
+
 	struct list_head devices;	/* all devices' list */
 	struct list_head subdevices;	/* all subdevices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
@@ -558,10 +561,6 @@ struct dmar_domain {
 	int		agaw;
 
 	int		flags;		/* flags to find out type of domain */
-
-	int		iommu_coherency;/* indicate coherency of iommu access */
-	int		iommu_snooping; /* indicate snooping control feature*/
-	int		iommu_count;	/* reference count of iommu */
 	int		iommu_superpage;/* Level of superpages supported:
 					   0 == 4KiB (no superpages), 1 == 2MiB,
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
@@ -606,6 +605,8 @@ struct intel_iommu {
 	struct completion prq_complete;
 	struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */
 #endif
+	struct iopf_queue *iopf_queue;
+	unsigned char iopfq_name[16];
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 *iommu_state; /* Store iommu states between suspend and resume.*/
 
@@ -619,6 +620,7 @@ struct intel_iommu {
 	u32		flags;      /* Software defined flags */
 
 	struct dmar_drhd_unit *drhd;
+	void *perf_statistic;
 };
 
 /* Per subdevice private data */
@@ -776,6 +778,7 @@ struct intel_svm_dev {
 	struct device *dev;
 	struct intel_iommu *iommu;
 	struct iommu_sva sva;
+	unsigned long prq_seq_number;
 	u32 pasid;
 	int users;
 	u16 did;
@@ -791,7 +794,6 @@ struct intel_svm {
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
-	struct list_head list;
 };
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
@@ -827,4 +829,32 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
 #define intel_iommu_enabled (0)
 #endif
 
+static inline const char *decode_prq_descriptor(char *str, size_t size,
+		u64 dw0, u64 dw1, u64 dw2, u64 dw3)
+{
+	char *buf = str;
+	int bytes;
+
+	bytes = snprintf(buf, size,
+			 "rid=0x%llx addr=0x%llx %c%c%c%c%c pasid=0x%llx index=0x%llx",
+			 FIELD_GET(GENMASK_ULL(31, 16), dw0),
+			 FIELD_GET(GENMASK_ULL(63, 12), dw1),
+			 dw1 & BIT_ULL(0) ? 'r' : '-',
+			 dw1 & BIT_ULL(1) ? 'w' : '-',
+			 dw0 & BIT_ULL(52) ? 'x' : '-',
+			 dw0 & BIT_ULL(53) ? 'p' : '-',
+			 dw1 & BIT_ULL(2) ? 'l' : '-',
+			 FIELD_GET(GENMASK_ULL(51, 32), dw0),
+			 FIELD_GET(GENMASK_ULL(11, 3), dw1));
+
+	/* Private Data */
+	if (dw0 & BIT_ULL(9)) {
+		size -= bytes;
+		buf += bytes;
+		snprintf(buf, size, " private=0x%llx/0x%llx\n", dw2, dw3);
+	}
+
+	return str;
+}
+
 #endif
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 16f4b3e87f20..55c1eb300a86 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -2,29 +2,18 @@
 #ifndef __OF_IOMMU_H
 #define __OF_IOMMU_H
 
-#include <linux/device.h>
-#include <linux/iommu.h>
-#include <linux/of.h>
+struct device;
+struct device_node;
+struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern int of_get_dma_window(struct device_node *dn, const char *prefix,
-			     int index, unsigned long *busno, dma_addr_t *addr,
-			     size_t *size);
-
 extern const struct iommu_ops *of_iommu_configure(struct device *dev,
 					struct device_node *master_np,
 					const u32 *id);
 
 #else
 
-static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
-			    int index, unsigned long *busno, dma_addr_t *addr,
-			    size_t *size)
-{
-	return -EINVAL;
-}
-
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 					 struct device_node *master_np,
 					 const u32 *id)
diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h
index d233f2916584..e5c1ca6d16ee 100644
--- a/include/trace/events/intel_iommu.h
+++ b/include/trace/events/intel_iommu.h
@@ -15,6 +15,8 @@
 #include <linux/tracepoint.h>
 #include <linux/intel-iommu.h>
 
+#define MSG_MAX		256
+
 TRACE_EVENT(qi_submit,
 	TP_PROTO(struct intel_iommu *iommu, u64 qw0, u64 qw1, u64 qw2, u64 qw3),
 
@@ -51,6 +53,41 @@ TRACE_EVENT(qi_submit,
 		__entry->qw0, __entry->qw1, __entry->qw2, __entry->qw3
 	)
 );
+
+TRACE_EVENT(prq_report,
+	TP_PROTO(struct intel_iommu *iommu, struct device *dev,
+		 u64 dw0, u64 dw1, u64 dw2, u64 dw3,
+		 unsigned long seq),
+
+	TP_ARGS(iommu, dev, dw0, dw1, dw2, dw3, seq),
+
+	TP_STRUCT__entry(
+		__field(u64, dw0)
+		__field(u64, dw1)
+		__field(u64, dw2)
+		__field(u64, dw3)
+		__field(unsigned long, seq)
+		__string(iommu, iommu->name)
+		__string(dev, dev_name(dev))
+		__dynamic_array(char, buff, MSG_MAX)
+	),
+
+	TP_fast_assign(
+		__entry->dw0 = dw0;
+		__entry->dw1 = dw1;
+		__entry->dw2 = dw2;
+		__entry->dw3 = dw3;
+		__entry->seq = seq;
+		__assign_str(iommu, iommu->name);
+		__assign_str(dev, dev_name(dev));
+	),
+
+	TP_printk("%s/%s seq# %ld: %s",
+		__get_str(iommu), __get_str(dev), __entry->seq,
+		decode_prq_descriptor(__get_str(buff), MSG_MAX, __entry->dw0,
+				      __entry->dw1, __entry->dw2, __entry->dw3)
+	)
+);
 #endif /* _TRACE_INTEL_IOMMU_H */
 
 /* This part must be outside protection */