[5.15-velinux] Backported IOMMU PCI Multi segment patches for velinux-5.15 kernel

drivers/iommu/amd/amd_iommu.h

@@ -13,14 +13,15 @@
 
 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(u16 devid);
+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_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
 extern void amd_iommu_uninit_devices(void);
 extern void amd_iommu_init_notifier(void);
 extern int amd_iommu_init_api(void);
+extern 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);
@@ -116,11 +117,18 @@ void amd_iommu_domain_clr_pt_root(struct protection_domain *domain)
 	amd_iommu_domain_set_pt_root(domain, 0);
 }
 
+static inline int get_pci_sbdf_id(struct pci_dev *pdev)
+{
+	int seg = pci_domain_nr(pdev->bus);
+	u16 devid = pci_dev_id(pdev);
+
+	return PCI_SEG_DEVID_TO_SBDF(seg, devid);
+}
 
 extern bool translation_pre_enabled(struct amd_iommu *iommu);
 extern bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
 					 struct device *dev);
-extern int __init add_special_device(u8 type, u8 id, u16 *devid,
+extern int __init add_special_device(u8 type, u8 id, u32 *devid,
 				     bool cmd_line);
 
 #ifdef CONFIG_DMI
@@ -131,4 +139,5 @@ static inline void amd_iommu_apply_ivrs_quirks(void) { }
 
 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);
 #endif

drivers/iommu/amd/amd_iommu_types.h

@@ -443,14 +443,22 @@ struct irq_remap_table {
 	u32 *table;
 };
 
-extern struct irq_remap_table **irq_lookup_table;
-
 /* Interrupt remapping feature used? */
 extern bool amd_iommu_irq_remap;
 
 /* kmem_cache to get tables with 128 byte alignement */
 extern struct kmem_cache *amd_iommu_irq_cache;
 
+#define PCI_SBDF_TO_SEGID(sbdf)		(((sbdf) >> 16) & 0xffff)
+#define PCI_SBDF_TO_DEVID(sbdf)		((sbdf) & 0xffff)
+#define PCI_SEG_DEVID_TO_SBDF(seg, devid)	((((u32)(seg) & 0xffff) << 16) | \
+						 ((devid) & 0xffff))
+
+/* Make iterating over all pci segment easier */
+#define for_each_pci_segment(pci_seg) \
+	list_for_each_entry((pci_seg), &amd_iommu_pci_seg_list, list)
+#define for_each_pci_segment_safe(pci_seg, next) \
+	list_for_each_entry_safe((pci_seg), (next), &amd_iommu_pci_seg_list, list)
 /*
  * Make iterating over all IOMMUs easier
  */
@@ -473,13 +481,14 @@ extern struct kmem_cache *amd_iommu_irq_cache;
 struct amd_iommu_fault {
 	u64 address;    /* IO virtual address of the fault*/
 	u32 pasid;      /* Address space identifier */
-	u16 device_id;  /* Originating PCI device id */
+	u32 sbdf;	/* Originating PCI device id */
 	u16 tag;        /* PPR tag */
 	u16 flags;      /* Fault flags */
 
 };
 
 
+struct amd_iommu;
 struct iommu_domain;
 struct irq_domain;
 struct amd_irte_ops;
@@ -525,6 +534,75 @@ struct protection_domain {
 	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
 };
 
+/*
+ * This structure contains information about one PCI segment in the system.
+ */
+struct amd_iommu_pci_seg {
+	/* List with all PCI segments in the system */
+	struct list_head list;
+
+	/* List of all available dev_data structures */
+	struct llist_head dev_data_list;
+
+	/* PCI segment number */
+	u16 id;
+
+	/* Largest PCI device id we expect translation requests for */
+	u16 last_bdf;
+
+	/* Size of the device table */
+	u32 dev_table_size;
+
+	/* Size of the alias table */
+	u32 alias_table_size;
+
+	/* Size of the rlookup table */
+	u32 rlookup_table_size;
+
+	/*
+	 * device table virtual address
+	 *
+	 * Pointer to the per PCI segment device table.
+	 * It is indexed by the PCI device id or the HT unit id and contains
+	 * information about the domain the device belongs to as well as the
+	 * page table root pointer.
+	 */
+	struct dev_table_entry *dev_table;
+
+	/*
+	 * The rlookup iommu table is used to find the IOMMU which is
+	 * responsible for a specific device. It is indexed by the PCI
+	 * device id.
+	 */
+	struct amd_iommu **rlookup_table;
+
+	/*
+	 * This table is used to find the irq remapping table for a given
+	 * device id quickly.
+	 */
+	struct irq_remap_table **irq_lookup_table;
+
+	/*
+	 * Pointer to a device table which the content of old device table
+	 * will be copied to. It's only be used in kdump kernel.
+	 */
+	struct dev_table_entry *old_dev_tbl_cpy;
+
+	/*
+	 * The alias table is a driver specific data structure which contains the
+	 * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
+	 * More than one device can share the same requestor id.
+	 */
+	u16 *alias_table;
+
+	/*
+	 * A list of required unity mappings we find in ACPI. It is not locked
+	 * because as runtime it is only read. It is created at ACPI table
+	 * parsing time.
+	 */
+	struct list_head unity_map;
+};
+
 /*
  * Structure where we save information about one hardware AMD IOMMU in the
  * system.
@@ -576,7 +654,7 @@ struct amd_iommu {
 	u16 cap_ptr;
 
 	/* pci domain of this IOMMU */
-	u16 pci_seg;
+	struct amd_iommu_pci_seg *pci_seg;
 
 	/* start of exclusion range of that IOMMU */
 	u64 exclusion_start;
@@ -664,16 +742,16 @@ struct acpihid_map_entry {
 	struct list_head list;
 	u8 uid[ACPIHID_UID_LEN];
 	u8 hid[ACPIHID_HID_LEN];
-	u16 devid;
-	u16 root_devid;
+	u32 devid;
+	u32 root_devid;
 	bool cmd_line;
 	struct iommu_group *group;
 };
 
 struct devid_map {
 	struct list_head list;
 	u8 id;
-	u16 devid;
+	u32 devid;
 	bool cmd_line;
 };
 
@@ -687,7 +765,7 @@ struct iommu_dev_data {
 	struct list_head list;		  /* For domain->dev_list */
 	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
-	struct pci_dev *pdev;
+	struct device *dev;
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	struct {
@@ -707,6 +785,12 @@ extern struct list_head ioapic_map;
 extern struct list_head hpet_map;
 extern struct list_head acpihid_map;
 
+/*
+ * List with all PCI segments in the system. This list is not locked because
+ * it is only written at driver initialization time
+ */
+extern struct list_head amd_iommu_pci_seg_list;
+
 /*
  * List with all IOMMUs in the system. This list is not locked because it is
  * only written and read at driver initialization or suspend time
@@ -746,39 +830,13 @@ struct unity_map_entry {
 	int prot;
 };
 
-/*
- * List of all unity mappings. It is not locked because as runtime it is only
- * read. It is created at ACPI table parsing time.
- */
-extern struct list_head amd_iommu_unity_map;
-
 /*
  * Data structures for device handling
  */
 
-/*
- * Device table used by hardware. Read and write accesses by software are
- * locked with the amd_iommu_pd_table lock.
- */
-extern struct dev_table_entry *amd_iommu_dev_table;
-
-/*
- * Alias table to find requestor ids to device ids. Not locked because only
- * read on runtime.
- */
-extern u16 *amd_iommu_alias_table;
-
-/*
- * Reverse lookup table to find the IOMMU which translates a specific device.
- */
-extern struct amd_iommu **amd_iommu_rlookup_table;
-
 /* size of the dma_ops aperture as power of 2 */
 extern unsigned amd_iommu_aperture_order;
 
-/* largest PCI device id we expect translation requests for */
-extern u16 amd_iommu_last_bdf;
-
 /* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
@@ -911,6 +969,7 @@ struct irq_2_irte {
 
 struct amd_ir_data {
 	u32 cached_ga_tag;
+	struct amd_iommu *iommu;
 	struct irq_2_irte irq_2_irte;
 	struct msi_msg msi_entry;
 	void *entry;    /* Pointer to union irte or struct irte_ga */
@@ -927,9 +986,9 @@ struct amd_ir_data {
 
 struct amd_irte_ops {
 	void (*prepare)(void *, u32, bool, u8, u32, int);
-	void (*activate)(void *, u16, u16);
-	void (*deactivate)(void *, u16, u16);
-	void (*set_affinity)(void *, u16, u16, u8, u32);
+	void (*activate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*deactivate)(struct amd_iommu *iommu, void *, u16, u16);
+	void (*set_affinity)(struct amd_iommu *iommu, void *, u16, u16, u8, u32);
 	void *(*get)(struct irq_remap_table *, int);
 	void (*set_allocated)(struct irq_remap_table *, int);
 	bool (*is_allocated)(struct irq_remap_table *, int);