Merge tag 'iommu-updates-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - iova_magazine_alloc() optimization
   - Make flush-queue an IOMMU driver capability
   - Consolidate the error handling around device attachment

  AMD IOMMU changes:
   - AVIC Interrupt Remapping Improvements
   - Some minor fixes and cleanups

  Intel VT-d changes from Lu Baolu:
   - Small and misc cleanups

  ARM-SMMU changes from Will Deacon:
   - Device-tree binding updates:
      - Add missing clocks for SC8280XP and SA8775 Adreno SMMUs
      - Add two new Qualcomm SMMUs in SDX75 and SM6375
   - Workarounds for Arm MMU-700 errata:
      - 1076982: Avoid use of SEV-based cmdq wakeup
      - 2812531: Terminate command batches with a CMD_SYNC
      - Enforce single-stage translation to avoid nesting-related errata
   - Set the correct level hint for range TLB invalidation on teardown

  .. and some other minor fixes and cleanups (including Freescale PAMU
  and virtio-iommu changes)"

* tag 'iommu-updates-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (50 commits)
  iommu/vt-d: Remove commented-out code
  iommu/vt-d: Remove two WARN_ON in domain_context_mapping_one()
  iommu/vt-d: Handle the failure case of dmar_reenable_qi()
  iommu/vt-d: Remove unnecessary (void*) conversions
  iommu/amd: Remove extern from function prototypes
  iommu/amd: Use BIT/BIT_ULL macro to define bit fields
  iommu/amd: Fix DTE_IRQ_PHYS_ADDR_MASK macro
  iommu/amd: Fix compile error for unused function
  iommu/amd: Improving Interrupt Remapping Table Invalidation
  iommu/amd: Do not Invalidate IRT when IRTE caching is disabled
  iommu/amd: Introduce Disable IRTE Caching Support
  iommu/amd: Remove the unused struct amd_ir_data.ref
  iommu/amd: Switch amd_iommu_update_ga() to use modify_irte_ga()
  iommu/arm-smmu-v3: Set TTL invalidation hint better
  iommu/arm-smmu-v3: Document nesting-related errata
  iommu/arm-smmu-v3: Add explicit feature for nesting
  iommu/arm-smmu-v3: Document MMU-700 erratum 2812531
  iommu/arm-smmu-v3: Work around MMU-600 erratum 1076982
  dt-bindings: arm-smmu: Add SDX75 SMMU compatible
  dt-bindings: arm-smmu: Add SM6375 GPU SMMU
  ...

Author: torvalds

.clang-format

@@ -254,6 +254,7 @@ ForEachMacros:
   - 'for_each_free_mem_range'
   - 'for_each_free_mem_range_reverse'
   - 'for_each_func_rsrc'
+  - 'for_each_group_device'
   - 'for_each_group_evsel'
   - 'for_each_group_member'
   - 'for_each_hstate'

Documentation/admin-guide/kernel-parameters.txt

@@ -323,6 +323,7 @@
 				       option with care.
 			pgtbl_v1     - Use v1 page table for DMA-API (Default).
 			pgtbl_v2     - Use v2 page table for DMA-API.
+			irtcachedis  - Disable Interrupt Remapping Table (IRT) caching.
 
 	amd_iommu_dump=	[HW,X86-64]
 			Enable AMD IOMMU driver option to dump the ACPI table

Documentation/arch/arm64/silicon-errata.rst

@@ -140,6 +140,10 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | MMU-600         | #1076982,1209401| N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
+| ARM            | MMU-700         | #2268618,2812531| N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
 +----------------+-----------------+-----------------+-----------------------------+

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

@@ -29,6 +29,7 @@ properties:
               - qcom,msm8996-smmu-v2
               - qcom,msm8998-smmu-v2
               - qcom,sdm630-smmu-v2
+              - qcom,sm6375-smmu-v2
           - const: qcom,smmu-v2
 
       - description: Qcom SoCs implementing "qcom,smmu-500" and "arm,mmu-500"
@@ -45,6 +46,7 @@ properties:
               - qcom,sdm845-smmu-500
               - qcom,sdx55-smmu-500
               - qcom,sdx65-smmu-500
+              - qcom,sdx75-smmu-500
               - qcom,sm6115-smmu-500
               - qcom,sm6125-smmu-500
               - qcom,sm6350-smmu-500
@@ -79,7 +81,9 @@ properties:
       - description: Qcom Adreno GPUs implementing "qcom,smmu-500" and "arm,mmu-500"
         items:
           - enum:
+              - qcom,sa8775p-smmu-500
               - qcom,sc7280-smmu-500
+              - qcom,sc8280xp-smmu-500
               - qcom,sm6115-smmu-500
               - qcom,sm6125-smmu-500
               - qcom,sm8150-smmu-500
@@ -267,6 +271,7 @@ allOf:
             enum:
               - qcom,msm8998-smmu-v2
               - qcom,sdm630-smmu-v2
+              - qcom,sm6375-smmu-v2
     then:
       anyOf:
         - properties:
@@ -331,7 +336,10 @@ allOf:
       properties:
         compatible:
           contains:
-            const: qcom,sc7280-smmu-500
+            enum:
+              - qcom,sa8775p-smmu-500
+              - qcom,sc7280-smmu-500
+              - qcom,sc8280xp-smmu-500
     then:
       properties:
         clock-names:
@@ -413,10 +421,8 @@ allOf:
               - nvidia,smmu-500
               - qcom,qcm2290-smmu-500
               - qcom,qdu1000-smmu-500
-              - qcom,sa8775p-smmu-500
               - qcom,sc7180-smmu-500
               - qcom,sc8180x-smmu-500
-              - qcom,sc8280xp-smmu-500
               - qcom,sdm670-smmu-500
               - qcom,sdm845-smmu-500
               - qcom,sdx55-smmu-500

arch/powerpc/sysdev/fsl_pci.c

@@ -1353,6 +1353,7 @@ static struct platform_driver fsl_pci_driver = {
 		.of_match_table = pci_ids,
 	},
 	.probe = fsl_pci_probe,
+	.driver_managed_dma = true,
 };
 
 static int __init fsl_pci_init(void)

drivers/iommu/amd/amd_iommu.h

@@ -11,12 +11,15 @@
 
 #include "amd_iommu_types.h"
 
-extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
-extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid);
-extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
-extern void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
-extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
+irqreturn_t amd_iommu_int_thread(int irq, void *data);
+irqreturn_t amd_iommu_int_handler(int irq, void *data);
+void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid);
+void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
+void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
+int amd_iommu_init_devices(void);
+void amd_iommu_uninit_devices(void);
+void amd_iommu_init_notifier(void);
+void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
@@ -25,45 +28,44 @@ static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {}
 #endif
 
 /* Needed for interrupt remapping */
-extern int amd_iommu_prepare(void);
-extern int amd_iommu_enable(void);
-extern void amd_iommu_disable(void);
-extern int amd_iommu_reenable(int);
-extern int amd_iommu_enable_faulting(void);
+int amd_iommu_prepare(void);
+int amd_iommu_enable(void);
+void amd_iommu_disable(void);
+int amd_iommu_reenable(int mode);
+int amd_iommu_enable_faulting(void);
 extern int amd_iommu_guest_ir;
 extern enum io_pgtable_fmt amd_iommu_pgtable;
 extern int amd_iommu_gpt_level;
 
 /* IOMMUv2 specific functions */
 struct iommu_domain;
 
-extern bool amd_iommu_v2_supported(void);
-extern struct amd_iommu *get_amd_iommu(unsigned int idx);
-extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
-extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
-extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
-				u8 fxn, u64 *value);
-extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
-				u8 fxn, u64 *value);
-
-extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
-extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
-extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
-extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
-extern int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
-				u64 address);
-extern void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
-extern void amd_iommu_domain_update(struct protection_domain *domain);
-extern void amd_iommu_domain_flush_complete(struct protection_domain *domain);
-extern void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
-extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
-extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
-				     unsigned long cr3);
-extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
+bool amd_iommu_v2_supported(void);
+struct amd_iommu *get_amd_iommu(unsigned int idx);
+u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+bool amd_iommu_pc_supported(void);
+u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+			 u8 fxn, u64 *value);
+int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+			 u8 fxn, u64 *value);
+
+int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
+int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
+void amd_iommu_domain_direct_map(struct iommu_domain *dom);
+int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address);
+void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
+void amd_iommu_domain_update(struct protection_domain *domain);
+void amd_iommu_domain_flush_complete(struct protection_domain *domain);
+void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
+			      unsigned long cr3);
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
 
 #ifdef CONFIG_IRQ_REMAP
-extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
 #else
 static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 {
@@ -75,8 +77,8 @@ static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf
 
-extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
-				  int status, int tag);
+int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
+			   int status, int tag);
 
 static inline bool is_rd890_iommu(struct pci_dev *pdev)
 {
@@ -129,20 +131,19 @@ static inline void *alloc_pgtable_page(int nid, gfp_t gfp)
 	return page ? page_address(page) : NULL;
 }
 
-extern bool translation_pre_enabled(struct amd_iommu *iommu);
-extern bool amd_iommu_is_attach_deferred(struct device *dev);
-extern int __init add_special_device(u8 type, u8 id, u32 *devid,
-				     bool cmd_line);
+bool translation_pre_enabled(struct amd_iommu *iommu);
+bool amd_iommu_is_attach_deferred(struct device *dev);
+int __init add_special_device(u8 type, u8 id, u32 *devid, bool cmd_line);
 
 #ifdef CONFIG_DMI
 void amd_iommu_apply_ivrs_quirks(void);
 #else
 static inline void amd_iommu_apply_ivrs_quirks(void) { }
 #endif
 
-extern void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
-					 u64 *root, int mode);
-extern struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
+void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+				  u64 *root, int mode);
+struct dev_table_entry *get_dev_table(struct amd_iommu *iommu);
 
 extern u64 amd_iommu_efr;
 extern u64 amd_iommu_efr2;

drivers/iommu/amd/amd_iommu_types.h

@@ -84,21 +84,21 @@
 
 
 /* Extended Feature Bits */
-#define FEATURE_PREFETCH	(1ULL<<0)
-#define FEATURE_PPR		(1ULL<<1)
-#define FEATURE_X2APIC		(1ULL<<2)
-#define FEATURE_NX		(1ULL<<3)
-#define FEATURE_GT		(1ULL<<4)
-#define FEATURE_IA		(1ULL<<6)
-#define FEATURE_GA		(1ULL<<7)
-#define FEATURE_HE		(1ULL<<8)
-#define FEATURE_PC		(1ULL<<9)
+#define FEATURE_PREFETCH	BIT_ULL(0)
+#define FEATURE_PPR		BIT_ULL(1)
+#define FEATURE_X2APIC		BIT_ULL(2)
+#define FEATURE_NX		BIT_ULL(3)
+#define FEATURE_GT		BIT_ULL(4)
+#define FEATURE_IA		BIT_ULL(6)
+#define FEATURE_GA		BIT_ULL(7)
+#define FEATURE_HE		BIT_ULL(8)
+#define FEATURE_PC		BIT_ULL(9)
 #define FEATURE_GATS_SHIFT	(12)
 #define FEATURE_GATS_MASK	(3ULL)
-#define FEATURE_GAM_VAPIC	(1ULL<<21)
-#define FEATURE_GIOSUP		(1ULL<<48)
-#define FEATURE_EPHSUP		(1ULL<<50)
-#define FEATURE_SNP		(1ULL<<63)
+#define FEATURE_GAM_VAPIC	BIT_ULL(21)
+#define FEATURE_GIOSUP		BIT_ULL(48)
+#define FEATURE_EPHSUP		BIT_ULL(50)
+#define FEATURE_SNP		BIT_ULL(63)
 
 #define FEATURE_PASID_SHIFT	32
 #define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
@@ -120,13 +120,13 @@
 #define PASID_MASK		0x0000ffff
 
 /* MMIO status bits */
-#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK	(1 << 0)
-#define MMIO_STATUS_EVT_INT_MASK	(1 << 1)
-#define MMIO_STATUS_COM_WAIT_INT_MASK	(1 << 2)
-#define MMIO_STATUS_PPR_INT_MASK	(1 << 6)
-#define MMIO_STATUS_GALOG_RUN_MASK	(1 << 8)
-#define MMIO_STATUS_GALOG_OVERFLOW_MASK	(1 << 9)
-#define MMIO_STATUS_GALOG_INT_MASK	(1 << 10)
+#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK	BIT(0)
+#define MMIO_STATUS_EVT_INT_MASK		BIT(1)
+#define MMIO_STATUS_COM_WAIT_INT_MASK		BIT(2)
+#define MMIO_STATUS_PPR_INT_MASK		BIT(6)
+#define MMIO_STATUS_GALOG_RUN_MASK		BIT(8)
+#define MMIO_STATUS_GALOG_OVERFLOW_MASK		BIT(9)
+#define MMIO_STATUS_GALOG_INT_MASK		BIT(10)
 
 /* event logging constants */
 #define EVENT_ENTRY_SIZE	0x10
@@ -174,6 +174,7 @@
 #define CONTROL_GAINT_EN	29
 #define CONTROL_XT_EN		50
 #define CONTROL_INTCAPXT_EN	51
+#define CONTROL_IRTCACHEDIS	59
 #define CONTROL_SNPAVIC_EN	61
 
 #define CTRL_INV_TO_MASK	(7 << CONTROL_INV_TIMEOUT)
@@ -283,7 +284,7 @@
 #define AMD_IOMMU_PGSIZES_V2	(PAGE_SIZE | (1ULL << 21) | (1ULL << 30))
 
 /* Bit value definition for dte irq remapping fields*/
-#define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
+#define DTE_IRQ_PHYS_ADDR_MASK		GENMASK_ULL(51, 6)
 #define DTE_IRQ_REMAP_INTCTL_MASK	(0x3ULL << 60)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
 #define DTE_IRQ_REMAP_ENABLE    1ULL
@@ -369,23 +370,23 @@
 /*
  * Bit value definition for I/O PTE fields
  */
-#define IOMMU_PTE_PR (1ULL << 0)
-#define IOMMU_PTE_U  (1ULL << 59)
-#define IOMMU_PTE_FC (1ULL << 60)
-#define IOMMU_PTE_IR (1ULL << 61)
-#define IOMMU_PTE_IW (1ULL << 62)
+#define IOMMU_PTE_PR	BIT_ULL(0)
+#define IOMMU_PTE_U	BIT_ULL(59)
+#define IOMMU_PTE_FC	BIT_ULL(60)
+#define IOMMU_PTE_IR	BIT_ULL(61)
+#define IOMMU_PTE_IW	BIT_ULL(62)
 
 /*
  * Bit value definition for DTE fields
  */
-#define DTE_FLAG_V  (1ULL << 0)
-#define DTE_FLAG_TV (1ULL << 1)
-#define DTE_FLAG_IR (1ULL << 61)
-#define DTE_FLAG_IW (1ULL << 62)
-
-#define DTE_FLAG_IOTLB	(1ULL << 32)
-#define DTE_FLAG_GIOV	(1ULL << 54)
-#define DTE_FLAG_GV	(1ULL << 55)
+#define DTE_FLAG_V	BIT_ULL(0)
+#define DTE_FLAG_TV	BIT_ULL(1)
+#define DTE_FLAG_IR	BIT_ULL(61)
+#define DTE_FLAG_IW	BIT_ULL(62)
+
+#define DTE_FLAG_IOTLB	BIT_ULL(32)
+#define DTE_FLAG_GIOV	BIT_ULL(54)
+#define DTE_FLAG_GV	BIT_ULL(55)
 #define DTE_FLAG_MASK	(0x3ffULL << 32)
 #define DTE_GLX_SHIFT	(56)
 #define DTE_GLX_MASK	(3)
@@ -439,13 +440,13 @@
 #define MAX_DOMAIN_ID 65536
 
 /* Protection domain flags */
-#define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
-#define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
+#define PD_DMA_OPS_MASK		BIT(0) /* domain used for dma_ops */
+#define PD_DEFAULT_MASK		BIT(1) /* domain is a default dma_ops
 					      domain for an IOMMU */
-#define PD_PASSTHROUGH_MASK	(1UL << 2) /* domain has no page
+#define PD_PASSTHROUGH_MASK	BIT(2) /* domain has no page
 					      translation */
-#define PD_IOMMUV2_MASK		(1UL << 3) /* domain has gcr3 table */
-#define PD_GIOV_MASK		(1UL << 4) /* domain enable GIOV support */
+#define PD_IOMMUV2_MASK		BIT(3) /* domain has gcr3 table */
+#define PD_GIOV_MASK		BIT(4) /* domain enable GIOV support */
 
 extern bool amd_iommu_dump;
 #define DUMP_printk(format, arg...)				\
@@ -716,6 +717,9 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
+	/* true if disable irte caching */
+	bool irtcachedis_enabled;
+
 	/* Handle for IOMMU core code */
 	struct iommu_device iommu;
 
@@ -748,7 +752,7 @@ struct amd_iommu {
 
 	u32 flags;
 	volatile u64 *cmd_sem;
-	u64 cmd_sem_val;
+	atomic64_t cmd_sem_val;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
@@ -882,7 +886,7 @@ extern int amd_iommu_max_glx_val;
  * This function flushes all internal caches of
  * the IOMMU used by this driver.
  */
-extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+void iommu_flush_all_caches(struct amd_iommu *iommu);
 
 static inline int get_ioapic_devid(int id)
 {
@@ -1006,7 +1010,6 @@ struct amd_ir_data {
 	struct irq_2_irte irq_2_irte;
 	struct msi_msg msi_entry;
 	void *entry;    /* Pointer to union irte or struct irte_ga */
-	void *ref;      /* Pointer to the actual irte */
 
 	/**
 	 * Store information for activate/de-activate