* This driver is powered by bad coffee and bombay mix.
*/
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/err.h>
#define STRTAB_STE_1_SHCFG_INCOMING 1UL
#define STRTAB_STE_1_SHCFG_SHIFT 44
-#define STRTAB_STE_1_PRIVCFG_UNPRIV 2UL
-#define STRTAB_STE_1_PRIVCFG_SHIFT 48
-
#define STRTAB_STE_2_S2VMID_SHIFT 0
#define STRTAB_STE_2_S2VMID_MASK 0xffffUL
#define STRTAB_STE_2_VTCR_SHIFT 32
/* High-level queue structures */
#define ARM_SMMU_POLL_TIMEOUT_US 100
+#define MSI_IOVA_BASE 0x8000000
+#define MSI_IOVA_LENGTH 0x100000
+
static bool disable_bypass;
module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
MODULE_PARM_DESC(disable_bypass,
unsigned int sid_bits;
struct arm_smmu_strtab_cfg strtab_cfg;
+
+ /* IOMMU core code handle */
+ struct iommu_device iommu;
};
/* SMMU private data for each master */
}
}
- /* Nuke the existing Config, as we're going to rewrite it */
- val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
-
- if (ste->valid)
- val |= STRTAB_STE_0_V;
- else
- val &= ~STRTAB_STE_0_V;
+ /* Nuke the existing STE_0 value, as we're going to rewrite it */
+ val = ste->valid ? STRTAB_STE_0_V : 0;
if (ste->bypass) {
val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
#ifdef CONFIG_PCI_ATS
STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
#endif
- STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT |
- STRTAB_STE_1_PRIVCFG_UNPRIV <<
- STRTAB_STE_1_PRIVCFG_SHIFT);
+ STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
if (smmu->features & ARM_SMMU_FEAT_STALLS)
dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
<< STRTAB_STE_0_S1CTXPTR_SHIFT) |
STRTAB_STE_0_CFG_S1_TRANS;
-
}
if (ste->s2_cfg) {
} while (size -= granule);
}
-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,
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
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;
}
master = fwspec->iommu_priv;
smmu = master->smmu;
} else {
- smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode));
+ smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
if (!smmu)
return -ENODEV;
master = kzalloc(sizeof(*master), GFP_KERNEL);
}
group = iommu_group_get_for_dev(dev);
- if (!IS_ERR(group))
+ if (!IS_ERR(group)) {
iommu_group_put(group);
+ iommu_device_link(&smmu->iommu, dev);
+ }
return PTR_ERR_OR_ZERO(group);
}
{
struct iommu_fwspec *fwspec = dev->iommu_fwspec;
struct arm_smmu_master_data *master;
+ struct arm_smmu_device *smmu;
if (!fwspec || fwspec->ops != &arm_smmu_ops)
return;
master = fwspec->iommu_priv;
+ smmu = master->smmu;
if (master && master->ste.valid)
arm_smmu_detach_dev(dev);
iommu_group_remove_device(dev);
+ iommu_device_unlink(&smmu->iommu, dev);
kfree(master);
iommu_fwspec_free(dev);
}
return iommu_fwspec_add_ids(dev, args->args, 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 */
};
u32 size, l1size;
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
- /*
- * If we can resolve everything with a single L2 table, then we
- * just need a single L1 descriptor. Otherwise, calculate the L1
- * size, capped to the SIDSIZE.
- */
- if (smmu->sid_bits < STRTAB_SPLIT) {
- size = 0;
- } else {
- size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
- size = min(size, smmu->sid_bits - STRTAB_SPLIT);
- }
+ /* Calculate the L1 size, capped to the SIDSIZE. */
+ size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
+ size = min(size, smmu->sid_bits - STRTAB_SPLIT);
cfg->num_l1_ents = 1 << size;
size += STRTAB_SPLIT;
return 0;
}
-static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
+static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
{
u32 reg;
- bool coherent;
+ bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
/* IDR0 */
reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
smmu->features |= ARM_SMMU_FEAT_HYP;
/*
- * The dma-coherent property is used in preference to the ID
+ * The coherency feature as set by FW is used in preference to the ID
* register, but warn on mismatch.
*/
- coherent = of_dma_is_coherent(smmu->dev->of_node);
- if (coherent)
- smmu->features |= ARM_SMMU_FEAT_COHERENCY;
-
if (!!(reg & IDR0_COHACC) != coherent)
dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
coherent ? "true" : "false");
smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
+ /*
+ * If the SMMU supports fewer bits than would fill a single L2 stream
+ * table, use a linear table instead.
+ */
+ if (smmu->sid_bits <= STRTAB_SPLIT)
+ smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;
+
/* IDR5 */
reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
return 0;
}
-static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+#ifdef CONFIG_ACPI
+static int arm_smmu_device_acpi_probe(struct platform_device *pdev,
+ struct arm_smmu_device *smmu)
+{
+ struct acpi_iort_smmu_v3 *iort_smmu;
+ struct device *dev = smmu->dev;
+ struct acpi_iort_node *node;
+
+ node = *(struct acpi_iort_node **)dev_get_platdata(dev);
+
+ /* Retrieve SMMUv3 specific data */
+ iort_smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
+
+ if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE)
+ smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+ 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)
{
- int irq, ret;
- struct resource *res;
- struct arm_smmu_device *smmu;
struct device *dev = &pdev->dev;
- bool bypass = true;
u32 cells;
+ int ret = -EINVAL;
if (of_property_read_u32(dev->of_node, "#iommu-cells", &cells))
dev_err(dev, "missing #iommu-cells property\n");
else if (cells != 1)
dev_err(dev, "invalid #iommu-cells value (%d)\n", cells);
else
- bypass = false;
+ ret = 0;
+
+ parse_driver_options(smmu);
+
+ if (of_dma_is_coherent(dev->of_node))
+ smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+ return ret;
+}
+
+static int arm_smmu_device_probe(struct platform_device *pdev)
+{
+ int irq, ret;
+ struct resource *res;
+ resource_size_t ioaddr;
+ struct arm_smmu_device *smmu;
+ struct device *dev = &pdev->dev;
+ bool bypass;
smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
if (!smmu) {
dev_err(dev, "MMIO region too small (%pr)\n", res);
return -EINVAL;
}
+ ioaddr = res->start;
smmu->base = devm_ioremap_resource(dev, res);
if (IS_ERR(smmu->base))
if (irq > 0)
smmu->gerr_irq = irq;
- parse_driver_options(smmu);
+ if (dev->of_node) {
+ ret = arm_smmu_device_dt_probe(pdev, smmu);
+ } else {
+ ret = arm_smmu_device_acpi_probe(pdev, smmu);
+ if (ret == -ENODEV)
+ return ret;
+ }
+
+ /* Set bypass mode according to firmware probing result */
+ bypass = !!ret;
/* Probe the h/w */
- ret = arm_smmu_device_probe(smmu);
+ ret = arm_smmu_device_hw_probe(smmu);
if (ret)
return ret;
return ret;
/* And we're up. Go go go! */
- of_iommu_set_ops(dev->of_node, &arm_smmu_ops);
+ ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
+ "smmu3.%pa", &ioaddr);
+ if (ret)
+ return ret;
+
+ iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+ iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+ ret = iommu_device_register(&smmu->iommu);
+
#ifdef CONFIG_PCI
if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
pci_request_acs();
.name = "arm-smmu-v3",
.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_smmuv3, "arm,smmu-v3", arm_smmu_of_init);
+#ifdef CONFIG_ACPI
+static int __init acpi_smmu_v3_init(struct acpi_table_header *table)
+{
+ if (iort_node_match(ACPI_IORT_NODE_SMMU_V3))
+ return arm_smmu_init();
+
+ return 0;
+}
+IORT_ACPI_DECLARE(arm_smmu_v3, ACPI_SIG_IORT, acpi_smmu_v3_init);
+#endif
+
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
MODULE_LICENSE("GPL v2");
projects / linux.git / blobdiff