1 files changed, 257 insertions, 50 deletions

diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 4145c04cb1c6..6ea7bbe26b19 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -22,6 +22,7 @@
 #include <linux/bitfield.h>
 #include <linux/xarray.h>
 #include <linux/perf_event.h>
+#include <linux/pci.h>
 
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
@@ -35,6 +36,8 @@
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
+
 #define VTD_STRIDE_SHIFT        (9)
 #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
 
@@ -47,7 +50,6 @@
 #define DMA_FL_PTE_US		BIT_ULL(2)
 #define DMA_FL_PTE_ACCESS	BIT_ULL(5)
 #define DMA_FL_PTE_DIRTY	BIT_ULL(6)
-#define DMA_FL_PTE_XD		BIT_ULL(63)
 
 #define DMA_SL_PTE_DIRTY_BIT	9
 #define DMA_SL_PTE_DIRTY	BIT_ULL(DMA_SL_PTE_DIRTY_BIT)
@@ -455,7 +457,6 @@ enum {
 
 /* Page group response descriptor QW0 */
 #define QI_PGRP_PASID_P(p)	(((u64)(p)) << 4)
-#define QI_PGRP_PDP(p)		(((u64)(p)) << 5)
 #define QI_PGRP_RESP_CODE(res)	(((u64)(res)) << 12)
 #define QI_PGRP_DID(rid)	(((u64)(rid)) << 16)
 #define QI_PGRP_PASID(pasid)	(((u64)(pasid)) << 32)
@@ -584,11 +585,23 @@ struct iommu_domain_info {
 					 * to VT-d spec, section 9.3 */
 };
 
+/*
+ * We start simply by using a fixed size for the batched descriptors. This
+ * size is currently sufficient for our needs. Future improvements could
+ * involve dynamically allocating the batch buffer based on actual demand,
+ * allowing us to adjust the batch size for optimal performance in different
+ * scenarios.
+ */
+#define QI_MAX_BATCHED_DESC_COUNT 16
+struct qi_batch {
+	struct qi_desc descs[QI_MAX_BATCHED_DESC_COUNT];
+	unsigned int index;
+};
+
 struct dmar_domain {
 	int	nid;			/* node id */
 	struct xarray iommu_array;	/* Attached IOMMU array */
 
-	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
 	u8 set_pte_snp:1;
@@ -607,6 +620,10 @@ struct dmar_domain {
 	struct list_head devices;	/* all devices' list */
 	struct list_head dev_pasids;	/* all attached pasids */
 
+	spinlock_t cache_lock;		/* Protect the cache tag list */
+	struct list_head cache_tags;	/* Cache tag list */
+	struct qi_batch *qi_batch;	/* Batched QI descriptors */
+
 	int		iommu_superpage;/* Level of superpages supported:
 					   0 == 4KiB (no superpages), 1 == 2MiB,
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
@@ -637,13 +654,16 @@ struct dmar_domain {
 		struct {
 			/* parent page table which the user domain is nested on */
 			struct dmar_domain *s2_domain;
-			/* user page table pointer (in GPA) */
-			unsigned long s1_pgtbl;
 			/* page table attributes */
 			struct iommu_hwpt_vtd_s1 s1_cfg;
 			/* link to parent domain siblings */
 			struct list_head s2_link;
 		};
+
+		/* SVA domain */
+		struct {
+			struct mmu_notifier notifier;
+		};
 	};
 
 	struct iommu_domain domain;	/* generic domain data structure for
@@ -679,8 +699,6 @@ struct iommu_pmu {
 	DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX);
 	struct perf_event	*event_list[IOMMU_PMU_IDX_MAX];
 	unsigned char		irq_name[16];
-	struct hlist_node	cpuhp_node;
-	int			cpu;
 };
 
 #define IOMMU_IRQ_ID_OFFSET_PRQ		(DMAR_UNITS_SUPPORTED)
@@ -701,7 +719,7 @@ struct intel_iommu {
 	int		msagaw; /* max sagaw of this iommu */
 	unsigned int	irq, pr_irq, perf_irq;
 	u16		segment;     /* PCI segment# */
-	unsigned char 	name[13];    /* Device Name */
+	unsigned char	name[16];    /* Device Name */
 
 #ifdef CONFIG_INTEL_IOMMU
 	unsigned long 	*domain_ids; /* bitmap of domains */
@@ -711,17 +729,22 @@ struct intel_iommu {
 
 	struct iommu_flush flush;
 #endif
-#ifdef CONFIG_INTEL_IOMMU_SVM
 	struct page_req_dsc *prq;
 	unsigned char prq_name[16];    /* Name for PRQ interrupt */
 	unsigned long prq_seq_number;
 	struct completion prq_complete;
-#endif
 	struct iopf_queue *iopf_queue;
 	unsigned char iopfq_name[16];
+	/* Synchronization between fault report and iommu device release. */
+	struct mutex iopf_lock;
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/
 
+	/* rb tree for all probed devices */
+	struct rb_root device_rbtree;
+	/* protect the device_rbtree */
+	spinlock_t device_rbtree_lock;
+
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
 	struct irq_domain *ir_domain;
@@ -755,6 +778,8 @@ struct device_domain_info {
 	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct dmar_domain *domain; /* pointer to domain */
 	struct pasid_table *pasid_table; /* pasid table */
+	/* device tracking node(lookup by PCI RID) */
+	struct rb_node node;
 #ifdef CONFIG_INTEL_IOMMU_DEBUGFS
 	struct dentry *debugfs_dentry; /* pointer to device directory dentry */
 #endif
@@ -782,6 +807,13 @@ static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
 	return container_of(dom, struct dmar_domain, domain);
 }
 
+/*
+ * Domain ID reserved for pasid entries programmed for first-level
+ * only and pass-through transfer modes.
+ */
+#define FLPT_DEFAULT_DID		1
+#define NUM_RESERVED_DID		2
+
 /* Retrieve the domain ID which has allocated to the domain */
 static inline u16
 domain_id_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
@@ -792,6 +824,21 @@ domain_id_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	return info->did;
 }
 
+static inline u16
+iommu_domain_did(struct iommu_domain *domain, struct intel_iommu *iommu)
+{
+	if (domain->type == IOMMU_DOMAIN_SVA ||
+	    domain->type == IOMMU_DOMAIN_IDENTITY)
+		return FLPT_DEFAULT_DID;
+	return domain_id_iommu(to_dmar_domain(domain), iommu);
+}
+
+static inline bool dev_is_real_dma_subdevice(struct device *dev)
+{
+	return dev && dev_is_pci(dev) &&
+	       pci_real_dma_dev(to_pci_dev(dev)) != to_pci_dev(dev);
+}
+
 /*
  * 0: readable
  * 1: writable
@@ -813,11 +860,10 @@ static inline void dma_clear_pte(struct dma_pte *pte)
 static inline u64 dma_pte_addr(struct dma_pte *pte)
 {
 #ifdef CONFIG_64BIT
-	return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
+	return pte->val & VTD_PAGE_MASK;
 #else
 	/* Must have a full atomic 64-bit read */
-	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) &
-			VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
 #endif
 }
 
@@ -1029,6 +1075,137 @@ static inline void context_set_sm_pre(struct context_entry *context)
 	context->lo |= BIT_ULL(4);
 }
 
+/*
+ * Clear the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_clear_sm_pre(struct context_entry *context)
+{
+	context->lo &= ~BIT_ULL(4);
+}
+
+/* Returns a number of VTD pages, but aligned to MM page size */
+static inline unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
+{
+	host_addr &= ~PAGE_MASK;
+	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
+}
+
+/* Return a size from number of VTD pages. */
+static inline unsigned long nrpages_to_size(unsigned long npages)
+{
+	return npages << VTD_PAGE_SHIFT;
+}
+
+static inline void qi_desc_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+				 unsigned int size_order, u64 type,
+				 struct qi_desc *desc)
+{
+	u8 dw = 0, dr = 0;
+	int ih = 0;
+
+	if (cap_write_drain(iommu->cap))
+		dw = 1;
+
+	if (cap_read_drain(iommu->cap))
+		dr = 1;
+
+	desc->qw0 = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
+	desc->qw1 = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+		| QI_IOTLB_AM(size_order);
+	desc->qw2 = 0;
+	desc->qw3 = 0;
+}
+
+static inline void qi_desc_dev_iotlb(u16 sid, u16 pfsid, u16 qdep, u64 addr,
+				     unsigned int mask, struct qi_desc *desc)
+{
+	if (mask) {
+		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
+		desc->qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+	} else {
+		desc->qw1 = QI_DEV_IOTLB_ADDR(addr);
+	}
+
+	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
+		qdep = 0;
+
+	desc->qw0 = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+		   QI_DIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid);
+	desc->qw2 = 0;
+	desc->qw3 = 0;
+}
+
+static inline void qi_desc_piotlb(u16 did, u32 pasid, u64 addr,
+				  unsigned long npages, bool ih,
+				  struct qi_desc *desc)
+{
+	if (npages == -1) {
+		desc->qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+				QI_EIOTLB_TYPE;
+		desc->qw1 = 0;
+	} else {
+		int mask = ilog2(__roundup_pow_of_two(npages));
+		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
+
+		if (WARN_ON_ONCE(!IS_ALIGNED(addr, align)))
+			addr = ALIGN_DOWN(addr, align);
+
+		desc->qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
+				QI_EIOTLB_TYPE;
+		desc->qw1 = QI_EIOTLB_ADDR(addr) |
+				QI_EIOTLB_IH(ih) |
+				QI_EIOTLB_AM(mask);
+	}
+}
+
+static inline void qi_desc_dev_iotlb_pasid(u16 sid, u16 pfsid, u32 pasid,
+					   u16 qdep, u64 addr,
+					   unsigned int size_order,
+					   struct qi_desc *desc)
+{
+	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
+
+	desc->qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
+		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
+		QI_DEV_IOTLB_PFSID(pfsid);
+
+	/*
+	 * If S bit is 0, we only flush a single page. If S bit is set,
+	 * The least significant zero bit indicates the invalidation address
+	 * range. VT-d spec 6.5.2.6.
+	 * e.g. address bit 12[0] indicates 8KB, 13[0] indicates 16KB.
+	 * size order = 0 is PAGE_SIZE 4KB
+	 * Max Invs Pending (MIP) is set to 0 for now until we have DIT in
+	 * ECAP.
+	 */
+	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order))
+		pr_warn_ratelimited("Invalidate non-aligned address %llx, order %d\n",
+				    addr, size_order);
+
+	/* Take page address */
+	desc->qw1 = QI_DEV_EIOTLB_ADDR(addr);
+
+	if (size_order) {
+		/*
+		 * Existing 0s in address below size_order may be the least
+		 * significant bit, we must set them to 1s to avoid having
+		 * smaller size than desired.
+		 */
+		desc->qw1 |= GENMASK_ULL(size_order + VTD_PAGE_SHIFT - 1,
+					VTD_PAGE_SHIFT);
+		/* Clear size_order bit to indicate size */
+		desc->qw1 &= ~mask;
+		/* Set the S bit to indicate flushing more than 1 page */
+		desc->qw1 |= QI_DEV_EIOTLB_SIZE;
+	}
+}
+
 /* Convert value to context PASID directory size field coding. */
 #define context_pdts(pds)	(((pds) & 0x7) << 9)
 
@@ -1060,63 +1237,93 @@ void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
 
 int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 		   unsigned int count, unsigned long options);
+
+void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+			 unsigned int size_order, u64 type);
 /*
  * Options used in qi_submit_sync:
  * QI_OPT_WAIT_DRAIN - Wait for PRQ drain completion, spec 6.5.2.8.
  */
 #define QI_OPT_WAIT_DRAIN		BIT(0)
 
-void domain_update_iotlb(struct dmar_domain *domain);
 int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu);
 void device_block_translation(struct device *dev);
-int prepare_domain_attach_device(struct iommu_domain *domain,
-				 struct device *dev);
-void domain_update_iommu_cap(struct dmar_domain *domain);
+int paging_domain_compatible(struct iommu_domain *domain, struct device *dev);
+
+struct dev_pasid_info *
+domain_add_dev_pasid(struct iommu_domain *domain,
+		     struct device *dev, ioasid_t pasid);
+void domain_remove_dev_pasid(struct iommu_domain *domain,
+			     struct device *dev, ioasid_t pasid);
+
+int __domain_setup_first_level(struct intel_iommu *iommu,
+			       struct device *dev, ioasid_t pasid,
+			       u16 did, pgd_t *pgd, int flags,
+			       struct iommu_domain *old);
 
 int dmar_ir_support(void);
 
-void *alloc_pgtable_page(int node, gfp_t gfp);
-void free_pgtable_page(void *vaddr);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
-					       const struct iommu_user_data *user_data);
+struct iommu_domain *
+intel_iommu_domain_alloc_nested(struct device *dev, struct iommu_domain *parent,
+				u32 flags,
+				const struct iommu_user_data *user_data);
+struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid);
+
+enum cache_tag_type {
+	CACHE_TAG_IOTLB,
+	CACHE_TAG_DEVTLB,
+	CACHE_TAG_NESTING_IOTLB,
+	CACHE_TAG_NESTING_DEVTLB,
+};
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
-void intel_svm_check(struct intel_iommu *iommu);
-int intel_svm_enable_prq(struct intel_iommu *iommu);
-int intel_svm_finish_prq(struct intel_iommu *iommu);
-int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
-			    struct iommu_page_response *msg);
-struct iommu_domain *intel_svm_domain_alloc(void);
-void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid);
-void intel_drain_pasid_prq(struct device *dev, u32 pasid);
-
-struct intel_svm_dev {
-	struct list_head list;
-	struct rcu_head rcu;
-	struct device *dev;
+struct cache_tag {
+	struct list_head node;
+	enum cache_tag_type type;
 	struct intel_iommu *iommu;
-	u16 did;
-	u16 sid, qdep;
+	/*
+	 * The @dev field represents the location of the cache. For IOTLB, it
+	 * resides on the IOMMU hardware. @dev stores the device pointer to
+	 * the IOMMU hardware. For DevTLB, it locates in the PCIe endpoint.
+	 * @dev stores the device pointer to that endpoint.
+	 */
+	struct device *dev;
+	u16 domain_id;
+	ioasid_t pasid;
+	unsigned int users;
 };
 
-struct intel_svm {
-	struct mmu_notifier notifier;
-	struct mm_struct *mm;
-	u32 pasid;
-	struct list_head devs;
-};
+int cache_tag_assign_domain(struct dmar_domain *domain,
+			    struct device *dev, ioasid_t pasid);
+void cache_tag_unassign_domain(struct dmar_domain *domain,
+			       struct device *dev, ioasid_t pasid);
+void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
+			   unsigned long end, int ih);
+void cache_tag_flush_all(struct dmar_domain *domain);
+void cache_tag_flush_range_np(struct dmar_domain *domain, unsigned long start,
+			      unsigned long end);
+
+void intel_context_flush_present(struct device_domain_info *info,
+				 struct context_entry *context,
+				 u16 did, bool affect_domains);
+
+int intel_iommu_enable_prq(struct intel_iommu *iommu);
+int intel_iommu_finish_prq(struct intel_iommu *iommu);
+void intel_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			       struct iommu_page_response *msg);
+void intel_iommu_drain_pasid_prq(struct device *dev, u32 pasid);
+
+#ifdef CONFIG_INTEL_IOMMU_SVM
+void intel_svm_check(struct intel_iommu *iommu);
+struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
+					    struct mm_struct *mm);
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
-static inline void intel_drain_pasid_prq(struct device *dev, u32 pasid) {}
-static inline struct iommu_domain *intel_svm_domain_alloc(void)
-{
-	return NULL;
-}
-
-static inline void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid)
+static inline struct iommu_domain *intel_svm_domain_alloc(struct device *dev,
+							  struct mm_struct *mm)
 {
+	return ERR_PTR(-ENODEV);
 }
 #endif