* - v7/v8 long-descriptor format
* - Non-secure access to the SMMU
* - Context fault reporting
+ * - Extended Stream ID (16 bit)
*/
#define pr_fmt(fmt) "arm-smmu: " fmt
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
#include <linux/atomic.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#define sCR0_CLIENTPD (1 << 0)
#define sCR0_GFRE (1 << 1)
#define sCR0_GFIE (1 << 2)
+#define sCR0_EXIDENABLE (1 << 3)
#define sCR0_GCFGFRE (1 << 4)
#define sCR0_GCFGFIE (1 << 5)
#define sCR0_USFCFG (1 << 10)
#define ID0_NUMIRPT_MASK 0xff
#define ID0_NUMSIDB_SHIFT 9
#define ID0_NUMSIDB_MASK 0xf
+#define ID0_EXIDS (1 << 8)
#define ID0_NUMSMRG_SHIFT 0
#define ID0_NUMSMRG_MASK 0xff
#define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2))
#define S2CR_CBNDX_SHIFT 0
#define S2CR_CBNDX_MASK 0xff
+#define S2CR_EXIDVALID (1 << 10)
#define S2CR_TYPE_SHIFT 16
#define S2CR_TYPE_MASK 0x3
enum arm_smmu_s2cr_type {
#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)
#define TTBCR2_SEP_SHIFT 15
#define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT)
+#define TTBCR2_AS (1 << 4)
#define TTBRn_ASID_SHIFT 48
#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,
#define INVALID_SMENDX -1
#define __fwspec_cfg(fw) ((struct arm_smmu_master_cfg *)fw->iommu_priv)
#define fwspec_smmu(fw) (__fwspec_cfg(fw)->smmu)
+#define fwspec_smendx(fw, i) \
+ (i >= fw->num_ids ? INVALID_SMENDX : __fwspec_cfg(fw)->smendx[i])
#define for_each_cfg_sme(fw, i, idx) \
- for (i = 0; idx = __fwspec_cfg(fw)->smendx[i], i < fw->num_ids; ++i)
+ for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i)
struct arm_smmu_device {
struct device *dev;
#define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9)
#define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10)
#define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11)
+#define ARM_SMMU_FEAT_EXIDS (1 << 12)
u32 features;
#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
unsigned int *irqs;
u32 cavium_id_base; /* Specific to Cavium */
+
+ /* IOMMU core code handle */
+ struct iommu_device iommu;
};
enum arm_smmu_context_fmt {
}
}
-static struct iommu_gather_ops arm_smmu_gather_ops = {
+static const struct iommu_gather_ops arm_smmu_gather_ops = {
.tlb_flush_all = arm_smmu_tlb_inv_context,
.tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
.tlb_sync = arm_smmu_tlb_sync,
reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
reg2 = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
reg2 |= TTBCR2_SEP_UPSTREAM;
+ if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+ reg2 |= TTBCR2_AS;
}
if (smmu->version > ARM_SMMU_V1)
writel_relaxed(reg2, cb_base + ARM_SMMU_CB_TTBCR2);
struct arm_smmu_smr *smr = smmu->smrs + idx;
u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT;
- if (smr->valid)
+ if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
reg |= SMR_VALID;
writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx));
}
(s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT |
(s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT;
+ if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
+ smmu->smrs[idx].valid)
+ reg |= S2CR_EXIDVALID;
writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx));
}
arm_smmu_write_smr(smmu, idx);
}
+/*
+ * The width of SMR's mask field depends on sCR0_EXIDENABLE, so this function
+ * should be called after sCR0 is written.
+ */
+static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
+{
+ void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+ u32 smr;
+
+ if (!smmu->smrs)
+ return;
+
+ /*
+ * SMR.ID bits may not be preserved if the corresponding MASK
+ * bits are set, so check each one separately. We can reject
+ * masters later if they try to claim IDs outside these masks.
+ */
+ smr = smmu->streamid_mask << SMR_ID_SHIFT;
+ writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+ smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+ smmu->streamid_mask = smr >> SMR_ID_SHIFT;
+
+ smr = smmu->streamid_mask << SMR_MASK_SHIFT;
+ writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+ smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+ smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
+}
+
static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
{
struct arm_smmu_smr *smrs = smmu->smrs;
continue;
s2cr[idx].type = type;
- s2cr[idx].privcfg = S2CR_PRIVCFG_UNPRIV;
+ s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
s2cr[idx].cbndx = cbndx;
arm_smmu_write_s2cr(smmu, idx);
}
return -ENXIO;
}
+ /*
+ * FIXME: The arch/arm DMA API code tries to attach devices to its own
+ * domains between of_xlate() and add_device() - we have no way to cope
+ * with that, so until ARM gets converted to rely on groups and default
+ * domains, just say no (but more politely than by dereferencing NULL).
+ * This should be at least a WARN_ON once that's sorted.
+ */
+ if (!fwspec->iommu_priv)
+ return -ENODEV;
+
smmu = fwspec_smmu(fwspec);
/* Ensure that the domain is finalised */
ret = arm_smmu_init_domain_context(domain, smmu);
* requests.
*/
return true;
- case IOMMU_CAP_INTR_REMAP:
- return true; /* MSIs are just memory writes */
case IOMMU_CAP_NOEXEC:
return true;
default:
static int arm_smmu_match_node(struct device *dev, void *data)
{
- return dev->of_node == data;
+ return dev->fwnode == data;
}
-static struct arm_smmu_device *arm_smmu_get_by_node(struct device_node *np)
+static
+struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
{
struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL,
- np, arm_smmu_match_node);
+ fwnode, arm_smmu_match_node);
put_device(dev);
return dev ? dev_get_drvdata(dev) : NULL;
}
fwspec = dev->iommu_fwspec;
if (ret)
goto out_free;
- } else if (fwspec) {
- smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
+ } else if (fwspec && fwspec->ops == &arm_smmu_ops) {
+ smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
} else {
return -ENODEV;
}
if (ret)
goto out_free;
+ iommu_device_link(&smmu->iommu, dev);
+
return 0;
out_free:
static void arm_smmu_remove_device(struct device *dev)
{
struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+ struct arm_smmu_master_cfg *cfg;
+ struct arm_smmu_device *smmu;
+
if (!fwspec || fwspec->ops != &arm_smmu_ops)
return;
+ cfg = fwspec->iommu_priv;
+ smmu = cfg->smmu;
+
+ iommu_device_unlink(&smmu->iommu, dev);
arm_smmu_master_free_smes(fwspec);
iommu_group_remove_device(dev);
kfree(fwspec->iommu_priv);
}
if (group)
- return group;
+ return iommu_group_ref_get(group);
if (dev_is_pci(dev))
group = pci_device_group(dev);
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_MSI);
+ if (!region)
+ return;
+
+ list_add_tail(®ion->list, 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,
.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 */
};
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);
}
if (smmu->features & ARM_SMMU_FEAT_VMID16)
reg |= sCR0_VMID16EN;
+ if (smmu->features & ARM_SMMU_FEAT_EXIDS)
+ reg |= sCR0_EXIDENABLE;
+
/* Push the button */
__arm_smmu_tlb_sync(smmu);
writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
unsigned long size;
void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
u32 id;
- bool cttw_dt, cttw_reg;
+ bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
int i;
dev_notice(smmu->dev, "probing hardware configuration...\n");
/*
* In order for DMA API calls to work properly, we must defer to what
- * the DT says about coherency, regardless of what the hardware claims.
+ * the FW says about coherency, regardless of what the hardware claims.
* Fortunately, this also opens up a workaround for systems where the
* ID register value has ended up configured incorrectly.
*/
- cttw_dt = of_dma_is_coherent(smmu->dev->of_node);
cttw_reg = !!(id & ID0_CTTW);
- if (cttw_dt)
- smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
- if (cttw_dt || cttw_reg)
+ if (cttw_fw || cttw_reg)
dev_notice(smmu->dev, "\t%scoherent table walk\n",
- cttw_dt ? "" : "non-");
- if (cttw_dt != cttw_reg)
+ cttw_fw ? "" : "non-");
+ if (cttw_fw != cttw_reg)
dev_notice(smmu->dev,
- "\t(IDR0.CTTW overridden by dma-coherent property)\n");
+ "\t(IDR0.CTTW overridden by FW configuration)\n");
/* Max. number of entries we have for stream matching/indexing */
- size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+ if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+ smmu->features |= ARM_SMMU_FEAT_EXIDS;
+ size = 1 << 16;
+ } else {
+ size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+ }
smmu->streamid_mask = size - 1;
if (id & ID0_SMS) {
- u32 smr;
-
smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK;
if (size == 0) {
return -ENODEV;
}
- /*
- * SMR.ID bits may not be preserved if the corresponding MASK
- * bits are set, so check each one separately. We can reject
- * masters later if they try to claim IDs outside these masks.
- */
- smr = smmu->streamid_mask << SMR_ID_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->streamid_mask = smr >> SMR_ID_SHIFT;
-
- smr = smmu->streamid_mask << SMR_MASK_SHIFT;
- writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
- smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
- smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
-
/* Zero-initialised to mark as invalid */
smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs),
GFP_KERNEL);
return -ENOMEM;
dev_notice(smmu->dev,
- "\tstream matching with %lu register groups, mask 0x%x",
- size, smmu->smr_mask_mask);
+ "\tstream matching with %lu register groups", size);
}
/* s2cr->type == 0 means translation, so initialise explicitly */
smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
};
MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
-static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+#ifdef CONFIG_ACPI
+static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
+{
+ int ret = 0;
+
+ switch (model) {
+ case ACPI_IORT_SMMU_V1:
+ case ACPI_IORT_SMMU_CORELINK_MMU400:
+ smmu->version = ARM_SMMU_V1;
+ smmu->model = GENERIC_SMMU;
+ break;
+ case ACPI_IORT_SMMU_V2:
+ smmu->version = ARM_SMMU_V2;
+ smmu->model = GENERIC_SMMU;
+ break;
+ case ACPI_IORT_SMMU_CORELINK_MMU500:
+ smmu->version = ARM_SMMU_V2;
+ smmu->model = ARM_MMU500;
+ break;
+ default:
+ ret = -ENODEV;
+ }
+
+ return ret;
+}
+
+static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+ struct arm_smmu_device *smmu)
+{
+ struct device *dev = smmu->dev;
+ struct acpi_iort_node *node =
+ *(struct acpi_iort_node **)dev_get_platdata(dev);
+ struct acpi_iort_smmu *iort_smmu;
+ int ret;
+
+ /* Retrieve SMMU1/2 specific data */
+ iort_smmu = (struct acpi_iort_smmu *)node->node_data;
+
+ ret = acpi_smmu_get_data(iort_smmu->model, smmu);
+ if (ret < 0)
+ return ret;
+
+ /* Ignore the configuration access interrupt */
+ smmu->num_global_irqs = 1;
+
+ if (iort_smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK)
+ smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+ return 0;
+}
+#else
+static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+ struct arm_smmu_device *smmu)
+{
+ return -ENODEV;
+}
+#endif
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev,
+ struct arm_smmu_device *smmu)
{
const struct arm_smmu_match_data *data;
- struct resource *res;
- struct arm_smmu_device *smmu;
struct device *dev = &pdev->dev;
- int num_irqs, i, err;
bool legacy_binding;
+ if (of_property_read_u32(dev->of_node, "#global-interrupts",
+ &smmu->num_global_irqs)) {
+ dev_err(dev, "missing #global-interrupts property\n");
+ return -ENODEV;
+ }
+
+ data = of_device_get_match_data(dev);
+ smmu->version = data->version;
+ smmu->model = data->model;
+
+ parse_driver_options(smmu);
+
legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL);
if (legacy_binding && !using_generic_binding) {
if (!using_legacy_binding)
return -ENODEV;
}
+ if (of_dma_is_coherent(dev->of_node))
+ smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
+
+ return 0;
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ resource_size_t ioaddr;
+ struct arm_smmu_device *smmu;
+ struct device *dev = &pdev->dev;
+ int num_irqs, i, err;
+
smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
if (!smmu) {
dev_err(dev, "failed to allocate arm_smmu_device\n");
}
smmu->dev = dev;
- data = of_device_get_match_data(dev);
- smmu->version = data->version;
- smmu->model = data->model;
+ if (dev->of_node)
+ err = arm_smmu_device_dt_probe(pdev, smmu);
+ else
+ err = arm_smmu_device_acpi_probe(pdev, smmu);
+
+ if (err)
+ return err;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ ioaddr = res->start;
smmu->base = devm_ioremap_resource(dev, res);
if (IS_ERR(smmu->base))
return PTR_ERR(smmu->base);
smmu->size = resource_size(res);
- if (of_property_read_u32(dev->of_node, "#global-interrupts",
- &smmu->num_global_irqs)) {
- dev_err(dev, "missing #global-interrupts property\n");
- return -ENODEV;
- }
-
num_irqs = 0;
while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
num_irqs++;
if (err)
return err;
- parse_driver_options(smmu);
-
if (smmu->version == ARM_SMMU_V2 &&
smmu->num_context_banks != smmu->num_context_irqs) {
dev_err(dev,
}
}
- of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
+ err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
+ "smmu.%pa", &ioaddr);
+ if (err) {
+ dev_err(dev, "Failed to register iommu in sysfs\n");
+ return err;
+ }
+
+ iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+ iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+ err = iommu_device_register(&smmu->iommu);
+ if (err) {
+ dev_err(dev, "Failed to register iommu\n");
+ return err;
+ }
+
platform_set_drvdata(pdev, smmu);
arm_smmu_device_reset(smmu);
+ arm_smmu_test_smr_masks(smmu);
/* Oh, for a proper bus abstraction */
if (!iommu_present(&platform_bus_type))
.name = "arm-smmu",
.of_match_table = of_match_ptr(arm_smmu_of_match),
},
- .probe = arm_smmu_device_dt_probe,
+ .probe = arm_smmu_device_probe,
.remove = arm_smmu_device_remove,
};
IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", arm_smmu_of_init);
IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", arm_smmu_of_init);
+#ifdef CONFIG_ACPI
+static int __init arm_smmu_acpi_init(struct acpi_table_header *table)
+{
+ if (iort_node_match(ACPI_IORT_NODE_SMMU))
+ return arm_smmu_init();
+
+ return 0;
+}
+IORT_ACPI_DECLARE(arm_smmu, ACPI_SIG_IORT, arm_smmu_acpi_init);
+#endif
+
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
MODULE_LICENSE("GPL v2");