1 files changed, 84 insertions, 16 deletions

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 5a9a441..382a1d3 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -49,6 +49,7 @@
 #include <linux/spinlock.h>
 
 #include <linux/amba/bus.h>
+#include "../staging/fsl-mc/include/mc-bus.h"
 
 #include "io-pgtable.h"
 
@@ -247,6 +248,7 @@ enum arm_smmu_s2cr_privcfg {
 #define ARM_MMU500_ACTLR_CPRE		(1 << 1)
 
 #define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
+#define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
 
 #define CB_PAR_F			(1 << 0)
 
@@ -278,6 +280,9 @@ enum arm_smmu_s2cr_privcfg {
 
 #define FSYNR0_WNR			(1 << 4)
 
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
 static int force_stage;
 module_param(force_stage, int, S_IRUGO);
 MODULE_PARM_DESC(force_stage,
@@ -401,6 +406,7 @@ 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 {
@@ -821,6 +827,12 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+		smmu_domain->smmu = smmu;
+		goto out_unlock;
+	}
+
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -981,7 +993,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	void __iomem *cb_base;
 	int irq;
 
-	if (!smmu)
+	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
 		return;
 
 	/*
@@ -1004,7 +1016,9 @@ 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;
 	/*
 	 * Allocate the domain and initialise some of its data structures.
@@ -1202,10 +1216,15 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 {
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
-	enum arm_smmu_s2cr_type type = S2CR_TYPE_TRANS;
 	u8 cbndx = smmu_domain->cfg.cbndx;
+	enum arm_smmu_s2cr_type type;
 	int i, idx;
 
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
+		type = S2CR_TYPE_BYPASS;
+	else
+		type = S2CR_TYPE_TRANS;
+
 	for_each_cfg_sme(fwspec, i, idx) {
 		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
 			continue;
@@ -1343,6 +1362,9 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
+		return iova;
+
 	if (!ops)
 		return 0;
 
@@ -1368,8 +1390,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 		 * requests.
 		 */
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true; /* MSIs are just memory writes */
 	case IOMMU_CAP_NOEXEC:
 		return true;
 	default:
@@ -1478,10 +1498,12 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	}
 
 	if (group)
-		return group;
+		return iommu_group_ref_get(group);
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
+	else if (dev_is_fsl_mc(dev))
+		group = fsl_mc_device_group(dev);
 	else
 		group = generic_device_group(dev);
 
@@ -1493,6 +1515,9 @@ 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);
@@ -1508,6 +1533,9 @@ 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) {
@@ -1534,17 +1562,44 @@ out_unlock:
 
 static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 {
-	u32 fwid = 0;
+	u32 mask, fwid = 0;
 
 	if (args->args_count > 0)
 		fwid |= (u16)args->args[0];
 
 	if (args->args_count > 1)
 		fwid |= (u16)args->args[1] << SMR_MASK_SHIFT;
+	else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
+		fwid |= (u16)mask << SMR_MASK_SHIFT;
 
 	return iommu_fwspec_add_ids(dev, &fwid, 1);
 }
 
+static void arm_smmu_get_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					 prot, IOMMU_RESV_SW_MSI);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+
+	iommu_dma_get_resv_regions(dev, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1560,6 +1615,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -1581,16 +1638,22 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	for (i = 0; i < smmu->num_mapping_groups; ++i)
 		arm_smmu_write_sme(smmu, i);
 
-	/*
-	 * Before clearing ARM_MMU500_ACTLR_CPRE, need to
-	 * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK
-	 * bit is only present in MMU-500r2 onwards.
-	 */
-	reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7);
-	major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK;
-	if ((smmu->model == ARM_MMU500) && (major >= 2)) {
+	if (smmu->model == ARM_MMU500) {
+		/*
+		 * Before clearing ARM_MMU500_ACTLR_CPRE, need to
+		 * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK
+		 * bit is only present in MMU-500r2 onwards.
+		 */
+		reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7);
+		major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK;
 		reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sACR);
-		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+		if (major >= 2)
+			reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+		/*
+		 * Allow unmatched Stream IDs to allocate bypass
+		 * TLB entries for reduced latency.
+		 */
+		reg |= ARM_MMU500_ACR_SMTNMB_TLBEN;
 		writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR);
 	}
 
@@ -2024,6 +2087,11 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev)
 		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
 	}
 #endif
+#ifdef CONFIG_FSL_MC_BUS
+	if (!iommu_present(&fsl_mc_bus_type))
+		bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops);
+#endif
+
 	return 0;
 }