Merge branch 'for-joerg/arm-smmu/updates' of...

Merge branch 'for-joerg/arm-smmu/updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Documentation/admin-guide/kernel-parameters.txt

@@ -1644,6 +1644,12 @@
 		nobypass	[PPC/POWERNV]
 			Disable IOMMU bypass, using IOMMU for PCI devices.
 
+	iommu.passthrough=
+			[ARM64] Configure DMA to bypass the IOMMU by default.
+			Format: { "0" | "1" }
+			0 - Use IOMMU translation for DMA.
+			1 - Bypass the IOMMU for DMA.
+			unset - Use IOMMU translation for DMA.
 
 	io7=		[HW] IO7 for Marvel based alpha systems
 			See comment before marvel_specify_io7 in

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

@@ -60,6 +60,17 @@ conditions.
                   aliases of secure registers have to be used during
                   SMMU configuration.
 
+- stream-match-mask : For SMMUs supporting stream matching and using
+                  #iommu-cells = <1>, specifies a mask of bits to ignore
+		  when matching stream IDs (e.g. this may be programmed
+		  into the SMRn.MASK field of every stream match register
+		  used). For cases where it is desirable to ignore some
+                  portion of every Stream ID (e.g. for certain MMU-500
+                  configurations given globally unique input IDs). This
+                  property is not valid for SMMUs using stream indexing,
+                  or using stream matching with #iommu-cells = <2>, and
+                  may be ignored if present in such cases.
+
 ** Deprecated properties:
 
 - mmu-masters (deprecated in favour of the generic "iommus" binding) :
@@ -109,3 +120,20 @@ conditions.
         master3 {
                 iommus = <&smmu2 1 0x30>;
         };
+
+
+        /* ARM MMU-500 with 10-bit stream ID input configuration */
+        smmu3: iommu {
+                compatible = "arm,mmu-500", "arm,smmu-v2";
+                ...
+                #iommu-cells = <1>;
+                /* always ignore appended 5-bit TBU number */
+                stream-match-mask = 0x7c00;
+        };
+
+        bus {
+                /* bus whose child devices emit one unique 10-bit stream
+                   ID each, but may master through multiple SMMU TBUs */
+                iommu-map = <0 &smmu3 0 0x400>;
+                ...
+        };

drivers/iommu/arm-smmu-v3.c

@@ -554,9 +554,14 @@ struct arm_smmu_s2_cfg {
 };
 
 struct arm_smmu_strtab_ent {
-	bool				valid;
-
-	bool				bypass;	/* Overrides s1/s2 config */
+	/*
+	 * An STE is "assigned" if the master emitting the corresponding SID
+	 * is attached to a domain. The behaviour of an unassigned STE is
+	 * determined by the disable_bypass parameter, whereas an assigned
+	 * STE behaves according to s1_cfg/s2_cfg, which themselves are
+	 * configured according to the domain type.
+	 */
+	bool				assigned;
 	struct arm_smmu_s1_cfg		*s1_cfg;
 	struct arm_smmu_s2_cfg		*s2_cfg;
 };
@@ -632,6 +637,7 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
+	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {
@@ -1005,9 +1011,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	 * This is hideously complicated, but we only really care about
 	 * three cases at the moment:
 	 *
-	 * 1. Invalid (all zero) -> bypass  (init)
-	 * 2. Bypass -> translation (attach)
-	 * 3. Translation -> bypass (detach)
+	 * 1. Invalid (all zero) -> bypass/fault (init)
+	 * 2. Bypass/fault -> translation/bypass (attach)
+	 * 3. Translation/bypass -> bypass/fault (detach)
 	 *
 	 * Given that we can't update the STE atomically and the SMMU
 	 * doesn't read the thing in a defined order, that leaves us
@@ -1046,11 +1052,15 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 	}
 
 	/* Nuke the existing STE_0 value, as we're going to rewrite it */
-	val = ste->valid ? STRTAB_STE_0_V : 0;
+	val = STRTAB_STE_0_V;
+
+	/* Bypass/fault */
+	if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
+		if (!ste->assigned && disable_bypass)
+			val |= STRTAB_STE_0_CFG_ABORT;
+		else
+			val |= STRTAB_STE_0_CFG_BYPASS;
 
-	if (ste->bypass) {
-		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
-				      : STRTAB_STE_0_CFG_BYPASS;
 		dst[0] = cpu_to_le64(val);
 		dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
 			 << STRTAB_STE_1_SHCFG_SHIFT);
@@ -1111,10 +1121,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
 {
 	unsigned int i;
-	struct arm_smmu_strtab_ent ste = {
-		.valid	= true,
-		.bypass	= true,
-	};
+	struct arm_smmu_strtab_ent ste = { .assigned = false };
 
 	for (i = 0; i < nent; ++i) {
 		arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
@@ -1378,7 +1385,9 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+	if (type != IOMMU_DOMAIN_UNMANAGED &&
+	    type != IOMMU_DOMAIN_DMA &&
+	    type != IOMMU_DOMAIN_IDENTITY)
 		return NULL;
 
 	/*
@@ -1509,6 +1518,11 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+		return 0;
+	}
+
 	/* Restrict the stage to what we can actually support */
 	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
 		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
@@ -1579,7 +1593,7 @@ static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 	return step;
 }
 
-static int arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
+static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
 {
 	int i;
 	struct arm_smmu_master_data *master = fwspec->iommu_priv;
@@ -1591,17 +1605,14 @@ static int arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
 
 		arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste);
 	}
-
-	return 0;
 }
 
 static void arm_smmu_detach_dev(struct device *dev)
 {
 	struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv;
 
-	master->ste.bypass = true;
-	if (arm_smmu_install_ste_for_dev(dev->iommu_fwspec) < 0)
-		dev_warn(dev, "failed to install bypass STE\n");
+	master->ste.assigned = false;
+	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1620,7 +1631,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	ste = &master->ste;
 
 	/* Already attached to a different domain? */
-	if (!ste->bypass)
+	if (ste->assigned)
 		arm_smmu_detach_dev(dev);
 
 	mutex_lock(&smmu_domain->init_mutex);
@@ -1641,10 +1652,12 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		goto out_unlock;
 	}
 
-	ste->bypass = false;
-	ste->valid = true;
+	ste->assigned = true;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) {
+		ste->s1_cfg = NULL;
+		ste->s2_cfg = NULL;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		ste->s1_cfg = &smmu_domain->s1_cfg;
 		ste->s2_cfg = NULL;
 		arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
@@ -1653,10 +1666,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		ste->s2_cfg = &smmu_domain->s2_cfg;
 	}
 
-	ret = arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
-	if (ret < 0)
-		ste->valid = false;
-
+	arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
 	return ret;
@@ -1807,7 +1817,7 @@ static void arm_smmu_remove_device(struct device *dev)
 
 	master = fwspec->iommu_priv;
 	smmu = master->smmu;
-	if (master && master->ste.valid)
+	if (master && master->ste.assigned)
 		arm_smmu_detach_dev(dev);
 	iommu_group_remove_device(dev);
 	iommu_device_unlink(&smmu->iommu, dev);
@@ -1837,6 +1847,9 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	switch (attr) {
 	case DOMAIN_ATTR_NESTING:
 		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
@@ -1852,6 +1865,9 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 	int ret = 0;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	mutex_lock(&smmu_domain->init_mutex);
 
 	switch (attr) {

drivers/iommu/io-pgtable-arm.c

@@ -74,7 +74,7 @@
 
 /* Calculate the block/page mapping size at level l for pagetable in d. */
 #define ARM_LPAE_BLOCK_SIZE(l,d)					\
-	(1 << (ilog2(sizeof(arm_lpae_iopte)) +				\
+	(1ULL << (ilog2(sizeof(arm_lpae_iopte)) +			\
 		((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
 
 /* Page table bits */

drivers/iommu/iommu.c

@@ -36,6 +36,7 @@
 
 static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
+static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
 
 struct iommu_callback_data {
 	const struct iommu_ops *ops;
@@ -112,6 +113,18 @@ static int __iommu_attach_group(struct iommu_domain *domain,
 static void __iommu_detach_group(struct iommu_domain *domain,
 				 struct iommu_group *group);
 
+static int __init iommu_set_def_domain_type(char *str)
+{
+	bool pt;
+
+	if (!str || strtobool(str, &pt))
+		return -EINVAL;
+
+	iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
+	return 0;
+}
+early_param("iommu.passthrough", iommu_set_def_domain_type);
+
 static ssize_t iommu_group_attr_show(struct kobject *kobj,
 				     struct attribute *__attr, char *buf)
 {
@@ -1015,10 +1028,19 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	 * IOMMU driver.
 	 */
 	if (!group->default_domain) {
-		group->default_domain = __iommu_domain_alloc(dev->bus,
-							     IOMMU_DOMAIN_DMA);
+		struct iommu_domain *dom;
+
+		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
+		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
+			dev_warn(dev,
+				 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+				 iommu_def_domain_type);
+			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+		}
+
+		group->default_domain = dom;
 		if (!group->domain)
-			group->domain = group->default_domain;
+			group->domain = dom;
 	}
 
 	ret = iommu_group_add_device(group, dev);

include/linux/iommu.h

@@ -32,10 +32,13 @@
 #define IOMMU_NOEXEC	(1 << 3)
 #define IOMMU_MMIO	(1 << 4) /* e.g. things like MSI doorbells */
 /*
- * This is to make the IOMMU API setup privileged
- * mapppings accessible by the master only at higher
- * privileged execution level and inaccessible at
- * less privileged levels.
+ * Where the bus hardware includes a privilege level as part of its access type
+ * markings, and certain devices are capable of issuing transactions marked as
+ * either 'supervisor' or 'user', the IOMMU_PRIV flag requests that the other
+ * given permission flags only apply to accesses at the higher privilege level,
+ * and that unprivileged transactions should have as little access as possible.
+ * This would usually imply the same permissions as kernel mappings on the CPU,
+ * if the IOMMU page table format is equivalent.
  */
 #define IOMMU_PRIV	(1 << 5)