iommu/arm-smmu-v3: Introduce an RCU-protected invalidation array

index ae23aacc38402..5c0b38595d209 100644
@@ -858,6 +858,7 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_SVA,
 };
 
 struct arm_smmu_domain {

index 59a480974d80f..6097f1f540d87 100644
@@ -346,6 +346,7 @@ struct iommu_domain *arm_smmu_sva_domain_alloc(struct device *dev,
 	 * ARM_SMMU_FEAT_RANGE_INV is present
 	 */
 	smmu_domain->domain.pgsize_bitmap = PAGE_SIZE;
+	smmu_domain->stage = ARM_SMMU_DOMAIN_SVA;
 	smmu_domain->smmu = smmu;
 
 	ret = xa_alloc(&arm_smmu_asid_xa, &asid, smmu_domain,

index 2a8b46b948f05..0312bb79f1247 100644
@@ -3064,6 +3064,9 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		arm_smmu_install_ste_for_dev(master, &target);
 		arm_smmu_clear_cd(master, IOMMU_NO_PASID);
 		break;
+	default:
+		WARN_ON(true);
+		break;
 	}
 
 	arm_smmu_attach_commit(&state);

index 5c0b38595d209..96a23ca633cb6 100644
@@ -954,6 +954,11 @@ extern struct mutex arm_smmu_asid_lock;
 
 struct arm_smmu_domain *arm_smmu_domain_alloc(void);
 
+static inline void arm_smmu_domain_free(struct arm_smmu_domain *smmu_domain)
+{
+	kfree(smmu_domain);
+}
+
 void arm_smmu_clear_cd(struct arm_smmu_master *master, ioasid_t ssid);
 struct arm_smmu_cd *arm_smmu_get_cd_ptr(struct arm_smmu_master *master,
 					u32 ssid);

index 6097f1f540d87..fc601b494e0af 100644
@@ -365,6 +365,6 @@ struct iommu_domain *arm_smmu_sva_domain_alloc(struct device *dev,
 err_asid:
 	xa_erase(&arm_smmu_asid_xa, smmu_domain->cd.asid);
 err_free:
-	kfree(smmu_domain);
+	arm_smmu_domain_free(smmu_domain);
 	return ERR_PTR(ret);
 }

index 0312bb79f1247..00d43080efaa8 100644
@@ -2492,7 +2492,7 @@ static void arm_smmu_domain_free_paging(struct iommu_domain *domain)
 			ida_free(&smmu->vmid_map, cfg->vmid);
 	}
 
-	kfree(smmu_domain);
+	arm_smmu_domain_free(smmu_domain);
 }
 
 static int arm_smmu_domain_finalise_s1(struct arm_smmu_device *smmu,

@@ -3353,7 +3353,7 @@ arm_smmu_domain_alloc_paging_flags(struct device *dev, u32 flags,
 	return &smmu_domain->domain;
 
 err_free:
-	kfree(smmu_domain);
+	arm_smmu_domain_free(smmu_domain);
 	return ERR_PTR(ret);
 }
 

index 96a23ca633cb6..43df0ae89d96f 100644
@@ -649,6 +649,85 @@ struct arm_smmu_cmdq_batch {
 	int				num;
 };
 
+/*
+ * The order here also determines the sequence in which commands are sent to the
+ * command queue. E.g. TLBI must be done before ATC_INV.
+ */
+enum arm_smmu_inv_type {
+	INV_TYPE_S1_ASID,
+	INV_TYPE_S2_VMID,
+	INV_TYPE_S2_VMID_S1_CLEAR,
+	INV_TYPE_ATS,
+	INV_TYPE_ATS_FULL,
+};
+
+struct arm_smmu_inv {
+	struct arm_smmu_device *smmu;
+	u8 type;
+	u8 size_opcode;
+	u8 nsize_opcode;
+	u32 id; /* ASID or VMID or SID */
+	union {
+		size_t pgsize; /* ARM_SMMU_FEAT_RANGE_INV */
+		u32 ssid; /* INV_TYPE_ATS */
+	};
+
+	refcount_t users; /* users=0 to mark as a trash to be purged */
+};
+
+static inline bool arm_smmu_inv_is_ats(struct arm_smmu_inv *inv)
+{
+	return inv->type == INV_TYPE_ATS || inv->type == INV_TYPE_ATS_FULL;
+}
+
+/**
+ * struct arm_smmu_invs - Per-domain invalidation array
+ * @num_invs: number of invalidations in the flexible array
+ * @rwlock: optional rwlock to fench ATS operations
+ * @has_ats: flag if the array contains an INV_TYPE_ATS or INV_TYPE_ATS_FULL
+ * @rcu: rcu head for kfree_rcu()
+ * @inv: flexible invalidation array
+ *
+ * The arm_smmu_invs is an RCU data structure. During a ->attach_dev callback,
+ * arm_smmu_invs_merge(), arm_smmu_invs_unref() and arm_smmu_invs_purge() will
+ * be used to allocate a new copy of an old array for addition and deletion in
+ * the old domain's and new domain's invs arrays.
+ *
+ * The arm_smmu_invs_unref() mutates a given array, by internally reducing the
+ * users counts of some given entries. This exists to support a no-fail routine
+ * like attaching to an IOMMU_DOMAIN_BLOCKED. And it could pair with a followup
+ * arm_smmu_invs_purge() call to generate a new clean array.
+ *
+ * Concurrent invalidation thread will push every invalidation described in the
+ * array into the command queue for each invalidation event. It is designed like
+ * this to optimize the invalidation fast path by avoiding locks.
+ *
+ * A domain can be shared across SMMU instances. When an instance gets removed,
+ * it would delete all the entries that belong to that SMMU instance. Then, a
+ * synchronize_rcu() would have to be called to sync the array, to prevent any
+ * concurrent invalidation thread accessing the old array from issuing commands
+ * to the command queue of a removed SMMU instance.
+ */
+struct arm_smmu_invs {
+	size_t num_invs;
+	rwlock_t rwlock;
+	bool has_ats;
+	struct rcu_head rcu;
+	struct arm_smmu_inv inv[];
+};
+
+static inline struct arm_smmu_invs *arm_smmu_invs_alloc(size_t num_invs)
+{
+	struct arm_smmu_invs *new_invs;
+
+	new_invs = kzalloc(struct_size(new_invs, inv, num_invs), GFP_KERNEL);
+	if (!new_invs)
+		return ERR_PTR(-ENOMEM);
+	rwlock_init(&new_invs->rwlock);
+	new_invs->num_invs = num_invs;
+	return new_invs;
+}
+
 struct arm_smmu_evtq {
 	struct arm_smmu_queue		q;
 	struct iopf_queue		*iopf;

@@ -875,6 +954,8 @@ struct arm_smmu_domain {
 
 	struct iommu_domain		domain;
 
+	struct arm_smmu_invs __rcu	*invs;
+
 	/* List of struct arm_smmu_master_domain */
 	struct list_head		devices;
 	spinlock_t			devices_lock;

@@ -923,6 +1004,14 @@ void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target,
 void arm_smmu_make_sva_cd(struct arm_smmu_cd *target,
 			  struct arm_smmu_master *master, struct mm_struct *mm,
 			  u16 asid);
+
+struct arm_smmu_invs *arm_smmu_invs_merge(struct arm_smmu_invs *invs,
+					  struct arm_smmu_invs *to_merge);
+size_t arm_smmu_invs_unref(struct arm_smmu_invs *invs,
+			   struct arm_smmu_invs *to_unref,
+			   void (*flush_fn)(struct arm_smmu_inv *inv));
+struct arm_smmu_invs *arm_smmu_invs_purge(struct arm_smmu_invs *invs,
+					  size_t num_trashes);
 #endif
 
 struct arm_smmu_master_domain {

@@ -956,6 +1045,7 @@ struct arm_smmu_domain *arm_smmu_domain_alloc(void);
 
 static inline void arm_smmu_domain_free(struct arm_smmu_domain *smmu_domain)
 {
+	kfree_rcu(rcu_dereference_protected(smmu_domain->invs, true), rcu);
 	kfree(smmu_domain);
 }
 

105 lines not on this page · raw message

266 lines not on this page · raw message

index 43df0ae89d96f..b8a4bda12b571 100644
@@ -922,6 +922,14 @@ struct arm_smmu_master {
 	struct arm_smmu_device		*smmu;
 	struct device			*dev;
 	struct arm_smmu_stream		*streams;
+	/*
+	 * Scratch memory for a to_merge or to_unref array to build a per-domain
+	 * invalidation array. It'll be pre-allocated with enough enries for all
+	 * possible build scenarios. It can be used by only one caller at a time
+	 * until the arm_smmu_invs_merge/unref() finishes. Must be locked by the
+	 * iommu_group mutex.
+	 */
+	struct arm_smmu_invs		*build_invs;
 	struct arm_smmu_vmaster		*vmaster; /* use smmu->streams_mutex */
 	/* Locked by the iommu core using the group mutex */
 	struct arm_smmu_ctx_desc_cfg	cd_table;

index cc266b47810b0..f01c2a6b40cd5 100644
@@ -3686,12 +3686,22 @@ static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
 	return 0;
 }
 
+static int arm_smmu_ids_cmp(const void *_l, const void *_r)
+{
+	const typeof_member(struct iommu_fwspec, ids[0]) *l = _l;
+	const typeof_member(struct iommu_fwspec, ids[0]) *r = _r;
+
+	return cmp_int(*l, *r);
+}
+
 static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 				  struct arm_smmu_master *master)
 {
 	int i;
 	int ret = 0;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+	bool ats_supported = dev_is_pci(master->dev) &&
+			     pci_ats_supported(to_pci_dev(master->dev));
 
 	master->streams = kcalloc(fwspec->num_ids, sizeof(*master->streams),
 				  GFP_KERNEL);

@@ -3699,6 +3709,21 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 		return -ENOMEM;
 	master->num_streams = fwspec->num_ids;
 
+	if (!ats_supported) {
+		/* Base case has 1 ASID entry or maximum 2 VMID entries */
+		master->build_invs = arm_smmu_invs_alloc(2);
+	} else {
+		/* Put the ids into order for sorted to_merge/to_unref arrays */
+		sort_nonatomic(fwspec->ids, fwspec->num_ids,
+			       sizeof(fwspec->ids[0]), arm_smmu_ids_cmp, NULL);
+		/* ATS case adds num_ids of entries, on top of the base case */
+		master->build_invs = arm_smmu_invs_alloc(2 + fwspec->num_ids);
+	}
+	if (IS_ERR(master->build_invs)) {
+		kfree(master->streams);
+		return PTR_ERR(master->build_invs);
+	}
+
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0; i < fwspec->num_ids; i++) {
 		struct arm_smmu_stream *new_stream = &master->streams[i];

@@ -3736,6 +3761,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 		for (i--; i >= 0; i--)
 			rb_erase(&master->streams[i].node, &smmu->streams);
 		kfree(master->streams);
+		kfree(master->build_invs);
 	}
 	mutex_unlock(&smmu->streams_mutex);
 

@@ -3757,6 +3783,7 @@ static void arm_smmu_remove_master(struct arm_smmu_master *master)
 	mutex_unlock(&smmu->streams_mutex);
 
 	kfree(master->streams);
+	kfree(master->build_invs);
 }
 
 static struct iommu_device *arm_smmu_probe_device(struct device *dev)

index b8a4bda12b571..b0dd9ff846f75 100644
@@ -1093,6 +1093,21 @@ static inline bool arm_smmu_master_canwbs(struct arm_smmu_master *master)
 	       IOMMU_FWSPEC_PCI_RC_CANWBS;
 }
 
+/**
+ * struct arm_smmu_inv_state - Per-domain invalidation array state
+ * @invs_ptr: points to the domain->invs (unwinding nesting/etc.) or is NULL if
+ *            no change should be made
+ * @old_invs: the original invs array
+ * @new_invs: for new domain, this is the new invs array to update domin->invs;
+ *            for old domain, this is the master->build_invs to pass in as the
+ *            to_unref argument to an arm_smmu_invs_unref() call
+ */
+struct arm_smmu_inv_state {
+	struct arm_smmu_invs __rcu **invs_ptr;
+	struct arm_smmu_invs *old_invs;
+	struct arm_smmu_invs *new_invs;
+};
+
 struct arm_smmu_attach_state {
 	/* Inputs */
 	struct iommu_domain *old_domain;

@@ -1102,6 +1117,8 @@ struct arm_smmu_attach_state {
 	ioasid_t ssid;
 	/* Resulting state */
 	struct arm_smmu_vmaster *vmaster;
+	struct arm_smmu_inv_state old_domain_invst;
+	struct arm_smmu_inv_state new_domain_invst;
 	bool ats_enabled;
 };
 

283 lines not on this page · raw message

index b0dd9ff846f75..b85ab564943cf 100644
@@ -1078,6 +1078,15 @@ void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
 int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
 			    unsigned long iova, size_t size);
 
+void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
+			       unsigned long iova, size_t size,
+			       unsigned int granule, bool leaf);
+
+static inline void arm_smmu_domain_inv(struct arm_smmu_domain *smmu_domain)
+{
+	arm_smmu_domain_inv_range(smmu_domain, 0, 0, 0, false);
+}
+
 void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
 			      struct arm_smmu_cmdq *cmdq);
 int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,

258 lines not on this page · raw message

index b85ab564943cf..501fcfc74f45d 100644
@@ -1071,13 +1071,6 @@ int arm_smmu_set_pasid(struct arm_smmu_master *master,
 		       struct arm_smmu_domain *smmu_domain, ioasid_t pasid,
 		       struct arm_smmu_cd *cd, struct iommu_domain *old);
 
-void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
-void arm_smmu_tlb_inv_range_asid(unsigned long iova, size_t size, int asid,
-				 size_t granule, bool leaf,
-				 struct arm_smmu_domain *smmu_domain);
-int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
-			    unsigned long iova, size_t size);
-
 void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
 			       unsigned long iova, size_t size,
 			       unsigned int granule, bool leaf);

index fc601b494e0af..048b53f79b144 100644
@@ -122,15 +122,6 @@ void arm_smmu_make_sva_cd(struct arm_smmu_cd *target,
 }
 EXPORT_SYMBOL_IF_KUNIT(arm_smmu_make_sva_cd);
 
-/*
- * Cloned from the MAX_TLBI_OPS in arch/arm64/include/asm/tlbflush.h, this
- * is used as a threshold to replace per-page TLBI commands to issue in the
- * command queue with an address-space TLBI command, when SMMU w/o a range
- * invalidation feature handles too many per-page TLBI commands, which will
- * otherwise result in a soft lockup.
- */
-#define CMDQ_MAX_TLBI_OPS		(1 << (PAGE_SHIFT - 3))
-
 static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						struct mm_struct *mm,
 						unsigned long start,

@@ -146,21 +137,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 	 * range. So do a simple translation here by calculating size correctly.
 	 */
 	size = end - start;
-	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_RANGE_INV)) {
-		if (size >= CMDQ_MAX_TLBI_OPS * PAGE_SIZE)
-			size = 0;
-	} else {
-		if (size == ULONG_MAX)
-			size = 0;
-	}
-
-	if (!size)
-		arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_domain->cd.asid);
-	else
-		arm_smmu_tlb_inv_range_asid(start, size, smmu_domain->cd.asid,
-					    PAGE_SIZE, false, smmu_domain);
 
-	arm_smmu_atc_inv_domain(smmu_domain, start, size);
+	arm_smmu_domain_inv_range(smmu_domain, start, size, PAGE_SIZE, false);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)

@@ -191,8 +169,7 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	}
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
-	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_domain->cd.asid);
-	arm_smmu_atc_inv_domain(smmu_domain, 0, 0);
+	arm_smmu_domain_inv(smmu_domain);
 }
 
 static void arm_smmu_mmu_notifier_free(struct mmu_notifier *mn)

@@ -301,7 +278,7 @@ static void arm_smmu_sva_domain_free(struct iommu_domain *domain)
 	/*
 	 * Ensure the ASID is empty in the iommu cache before allowing reuse.
 	 */
-	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_domain->cd.asid);
+	arm_smmu_domain_inv(smmu_domain);
 
 	/*
 	 * Notice that the arm_smmu_mm_arch_invalidate_secondary_tlbs op can

211 lines not on this page · raw message