Merge branch 'for-next/iommu/svm' into for-next/iommu/core

More steps along the way to Shared Virtual {Addressing, Memory} support
for Arm's SMMUv3, including the addition of a helper library that can be
shared amongst other IOMMU implementations wishing to support this
feature.

* for-next/iommu/svm:
  iommu/arm-smmu-v3: Hook up ATC invalidation to mm ops
  iommu/arm-smmu-v3: Implement iommu_sva_bind/unbind()
  iommu/sva: Add PASID helpers
  iommu/ioasid: Add ioasid references

3 files changed, 312 insertions, 12 deletions

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 9255c9600fb8..e13b092e6004 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -5,11 +5,35 @@
 
 #include <linux/mm.h>
 #include <linux/mmu_context.h>
+#include <linux/mmu_notifier.h>
 #include <linux/slab.h>
 
 #include "arm-smmu-v3.h"
+#include "../../iommu-sva-lib.h"
 #include "../../io-pgtable-arm.h"
 
+struct arm_smmu_mmu_notifier {
+	struct mmu_notifier		mn;
+	struct arm_smmu_ctx_desc	*cd;
+	bool				cleared;
+	refcount_t			refs;
+	struct list_head		list;
+	struct arm_smmu_domain		*domain;
+};
+
+#define mn_to_smmu(mn) container_of(mn, struct arm_smmu_mmu_notifier, mn)
+
+struct arm_smmu_bond {
+	struct iommu_sva		sva;
+	struct mm_struct		*mm;
+	struct arm_smmu_mmu_notifier	*smmu_mn;
+	struct list_head		list;
+	refcount_t			refs;
+};
+
+#define sva_to_bond(handle) \
+	container_of(handle, struct arm_smmu_bond, sva)
+
 static DEFINE_MUTEX(sva_lock);
 
 /*
@@ -64,7 +88,6 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
 	return NULL;
 }
 
-__maybe_unused
 static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
 {
 	u16 asid;
@@ -145,7 +168,6 @@ out_put_context:
 	return err < 0 ? ERR_PTR(err) : ret;
 }
 
-__maybe_unused
 static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
 {
 	if (arm_smmu_free_asid(cd)) {
@@ -155,6 +177,215 @@ static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
 	}
 }
 
+static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn,
+					 struct mm_struct *mm,
+					 unsigned long start, unsigned long end)
+{
+	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+
+	arm_smmu_atc_inv_domain(smmu_mn->domain, mm->pasid, start,
+				end - start + 1);
+}
+
+static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn);
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+
+	mutex_lock(&sva_lock);
+	if (smmu_mn->cleared) {
+		mutex_unlock(&sva_lock);
+		return;
+	}
+
+	/*
+	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
+	 * but disable translation.
+	 */
+	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, &quiet_cd);
+
+	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
+	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+
+	smmu_mn->cleared = true;
+	mutex_unlock(&sva_lock);
+}
+
+static void arm_smmu_mmu_notifier_free(struct mmu_notifier *mn)
+{
+	kfree(mn_to_smmu(mn));
+}
+
+static struct mmu_notifier_ops arm_smmu_mmu_notifier_ops = {
+	.invalidate_range	= arm_smmu_mm_invalidate_range,
+	.release		= arm_smmu_mm_release,
+	.free_notifier		= arm_smmu_mmu_notifier_free,
+};
+
+/* Allocate or get existing MMU notifier for this {domain, mm} pair */
+static struct arm_smmu_mmu_notifier *
+arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
+			  struct mm_struct *mm)
+{
+	int ret;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_mmu_notifier *smmu_mn;
+
+	list_for_each_entry(smmu_mn, &smmu_domain->mmu_notifiers, list) {
+		if (smmu_mn->mn.mm == mm) {
+			refcount_inc(&smmu_mn->refs);
+			return smmu_mn;
+		}
+	}
+
+	cd = arm_smmu_alloc_shared_cd(mm);
+	if (IS_ERR(cd))
+		return ERR_CAST(cd);
+
+	smmu_mn = kzalloc(sizeof(*smmu_mn), GFP_KERNEL);
+	if (!smmu_mn) {
+		ret = -ENOMEM;
+		goto err_free_cd;
+	}
+
+	refcount_set(&smmu_mn->refs, 1);
+	smmu_mn->cd = cd;
+	smmu_mn->domain = smmu_domain;
+	smmu_mn->mn.ops = &arm_smmu_mmu_notifier_ops;
+
+	ret = mmu_notifier_register(&smmu_mn->mn, mm);
+	if (ret) {
+		kfree(smmu_mn);
+		goto err_free_cd;
+	}
+
+	ret = arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, cd);
+	if (ret)
+		goto err_put_notifier;
+
+	list_add(&smmu_mn->list, &smmu_domain->mmu_notifiers);
+	return smmu_mn;
+
+err_put_notifier:
+	/* Frees smmu_mn */
+	mmu_notifier_put(&smmu_mn->mn);
+err_free_cd:
+	arm_smmu_free_shared_cd(cd);
+	return ERR_PTR(ret);
+}
+
+static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
+{
+	struct mm_struct *mm = smmu_mn->mn.mm;
+	struct arm_smmu_ctx_desc *cd = smmu_mn->cd;
+	struct arm_smmu_domain *smmu_domain = smmu_mn->domain;
+
+	if (!refcount_dec_and_test(&smmu_mn->refs))
+		return;
+
+	list_del(&smmu_mn->list);
+	arm_smmu_write_ctx_desc(smmu_domain, mm->pasid, NULL);
+
+	/*
+	 * If we went through clear(), we've already invalidated, and no
+	 * new TLB entry can have been formed.
+	 */
+	if (!smmu_mn->cleared) {
+		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
+		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	}
+
+	/* Frees smmu_mn */
+	mmu_notifier_put(&smmu_mn->mn);
+	arm_smmu_free_shared_cd(cd);
+}
+
+static struct iommu_sva *
+__arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm)
+{
+	int ret;
+	struct arm_smmu_bond *bond;
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (!master || !master->sva_enabled)
+		return ERR_PTR(-ENODEV);
+
+	/* If bind() was already called for this {dev, mm} pair, reuse it. */
+	list_for_each_entry(bond, &master->bonds, list) {
+		if (bond->mm == mm) {
+			refcount_inc(&bond->refs);
+			return &bond->sva;
+		}
+	}
+
+	bond = kzalloc(sizeof(*bond), GFP_KERNEL);
+	if (!bond)
+		return ERR_PTR(-ENOMEM);
+
+	/* Allocate a PASID for this mm if necessary */
+	ret = iommu_sva_alloc_pasid(mm, 1, (1U << master->ssid_bits) - 1);
+	if (ret)
+		goto err_free_bond;
+
+	bond->mm = mm;
+	bond->sva.dev = dev;
+	refcount_set(&bond->refs, 1);
+
+	bond->smmu_mn = arm_smmu_mmu_notifier_get(smmu_domain, mm);
+	if (IS_ERR(bond->smmu_mn)) {
+		ret = PTR_ERR(bond->smmu_mn);
+		goto err_free_pasid;
+	}
+
+	list_add(&bond->list, &master->bonds);
+	return &bond->sva;
+
+err_free_pasid:
+	iommu_sva_free_pasid(mm);
+err_free_bond:
+	kfree(bond);
+	return ERR_PTR(ret);
+}
+
+struct iommu_sva *
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct iommu_sva *handle;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->stage != ARM_SMMU_DOMAIN_S1)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&sva_lock);
+	handle = __arm_smmu_sva_bind(dev, mm);
+	mutex_unlock(&sva_lock);
+	return handle;
+}
+
+void arm_smmu_sva_unbind(struct iommu_sva *handle)
+{
+	struct arm_smmu_bond *bond = sva_to_bond(handle);
+
+	mutex_lock(&sva_lock);
+	if (refcount_dec_and_test(&bond->refs)) {
+		list_del(&bond->list);
+		arm_smmu_mmu_notifier_put(bond->smmu_mn);
+		iommu_sva_free_pasid(bond->mm);
+		kfree(bond);
+	}
+	mutex_unlock(&sva_lock);
+}
+
+u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
+{
+	struct arm_smmu_bond *bond = sva_to_bond(handle);
+
+	return bond->mm->pasid;
+}
+
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 {
 	unsigned long reg, fld;
@@ -246,3 +477,12 @@ int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
 
 	return 0;
 }
+
+void arm_smmu_sva_notifier_synchronize(void)
+{
+	/*
+	 * Some MMU notifiers may still be waiting to be freed, using
+	 * arm_smmu_mmu_notifier_free(). Wait for them.
+	 */
+	mmu_notifier_synchronize();
+}
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index c9cafce51835..2ddf5ecc75f8 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -76,6 +76,12 @@ struct arm_smmu_option_prop {
 DEFINE_XARRAY_ALLOC1(arm_smmu_asid_xa);
 DEFINE_MUTEX(arm_smmu_asid_lock);
 
+/*
+ * Special value used by SVA when a process dies, to quiesce a CD without
+ * disabling it.
+ */
+struct arm_smmu_ctx_desc quiet_cd = { 0 };
+
 static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
 	{ ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"},
@@ -91,11 +97,6 @@ static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset,
 	return smmu->base + offset;
 }
 
-static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
-{
-	return container_of(dom, struct arm_smmu_domain, domain);
-}
-
 static void parse_driver_options(struct arm_smmu_device *smmu)
 {
 	int i = 0;
@@ -983,7 +984,9 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 	 * (2) Install a secondary CD, for SID+SSID traffic.
 	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
 	 *     CD, then invalidate the old entry and mappings.
-	 * (4) Remove a secondary CD.
+	 * (4) Quiesce the context without clearing the valid bit. Disable
+	 *     translation, and ignore any translation fault.
+	 * (5) Remove a secondary CD.
 	 */
 	u64 val;
 	bool cd_live;
@@ -1000,8 +1003,10 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 	val = le64_to_cpu(cdptr[0]);
 	cd_live = !!(val & CTXDESC_CD_0_V);
 
-	if (!cd) { /* (4) */
+	if (!cd) { /* (5) */
 		val = 0;
+	} else if (cd == &quiet_cd) { /* (4) */
+		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
 		val |= FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid);
@@ -1519,6 +1524,20 @@ arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size,
 	size_t inval_grain_shift = 12;
 	unsigned long page_start, page_end;
 
+	/*
+	 * ATS and PASID:
+	 *
+	 * If substream_valid is clear, the PCIe TLP is sent without a PASID
+	 * prefix. In that case all ATC entries within the address range are
+	 * invalidated, including those that were requested with a PASID! There
+	 * is no way to invalidate only entries without PASID.
+	 *
+	 * When using STRTAB_STE_1_S1DSS_SSID0 (reserving CD 0 for non-PASID
+	 * traffic), translation requests without PASID create ATC entries
+	 * without PASID, which must be invalidated with substream_valid clear.
+	 * This has the unpleasant side-effect of invalidating all PASID-tagged
+	 * ATC entries within the address range.
+	 */
 	*cmd = (struct arm_smmu_cmdq_ent) {
 		.opcode			= CMDQ_OP_ATC_INV,
 		.substream_valid	= !!ssid,
@@ -1577,8 +1596,8 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_master *master)
 	return arm_smmu_cmdq_issue_sync(master->smmu);
 }
 
-static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
-				   int ssid, unsigned long iova, size_t size)
+int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
+			    unsigned long iova, size_t size)
 {
 	int i;
 	unsigned long flags;
@@ -1794,6 +1813,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 	mutex_init(&smmu_domain->init_mutex);
 	INIT_LIST_HEAD(&smmu_domain->devices);
 	spin_lock_init(&smmu_domain->devices_lock);
+	INIT_LIST_HEAD(&smmu_domain->mmu_notifiers);
 
 	return &smmu_domain->domain;
 }
@@ -2589,6 +2609,9 @@ static struct iommu_ops arm_smmu_ops = {
 	.dev_feat_enabled	= arm_smmu_dev_feature_enabled,
 	.dev_enable_feat	= arm_smmu_dev_enable_feature,
 	.dev_disable_feat	= arm_smmu_dev_disable_feature,
+	.sva_bind		= arm_smmu_sva_bind,
+	.sva_unbind		= arm_smmu_sva_unbind,
+	.sva_get_pasid		= arm_smmu_sva_get_pasid,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -3611,6 +3634,12 @@ static const struct of_device_id arm_smmu_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
+static void arm_smmu_driver_unregister(struct platform_driver *drv)
+{
+	arm_smmu_sva_notifier_synchronize();
+	platform_driver_unregister(drv);
+}
+
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.name			= "arm-smmu-v3",
@@ -3621,7 +3650,8 @@ static struct platform_driver arm_smmu_driver = {
 	.remove	= arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
-module_platform_driver(arm_smmu_driver);
+module_driver(arm_smmu_driver, platform_driver_register,
+	      arm_smmu_driver_unregister);
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
 MODULE_AUTHOR("Will Deacon <will@kernel.org>");
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index d4b7f40ccb02..96c2e9565e00 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -678,15 +678,25 @@ struct arm_smmu_domain {
 
 	struct list_head		devices;
 	spinlock_t			devices_lock;
+
+	struct list_head		mmu_notifiers;
 };
 
+static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
 extern struct xarray arm_smmu_asid_xa;
 extern struct mutex arm_smmu_asid_lock;
+extern struct arm_smmu_ctx_desc quiet_cd;
 
 int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 			    struct arm_smmu_ctx_desc *cd);
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
 bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
+int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
+			    unsigned long iova, size_t size);
 
 #ifdef CONFIG_ARM_SMMU_V3_SVA
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
@@ -694,6 +704,11 @@ bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);
 bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
+struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
+				    void *drvdata);
+void arm_smmu_sva_unbind(struct iommu_sva *handle);
+u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle);
+void arm_smmu_sva_notifier_synchronize(void);
 #else /* CONFIG_ARM_SMMU_V3_SVA */
 static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 {
@@ -719,5 +734,20 @@ static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
 {
 	return -ENODEV;
 }
+
+static inline struct iommu_sva *
+arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void arm_smmu_sva_unbind(struct iommu_sva *handle) {}
+
+static inline u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle)
+{
+	return IOMMU_PASID_INVALID;
+}
+
+static inline void arm_smmu_sva_notifier_synchronize(void) {}
 #endif /* CONFIG_ARM_SMMU_V3_SVA */
 #endif /* _ARM_SMMU_V3_H */