#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/module.h>
+#include <linux/msi.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_platform.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#define STRTAB_STE_1_STRW_EL2 2UL
#define STRTAB_STE_1_STRW_SHIFT 30
+#define STRTAB_STE_1_SHCFG_INCOMING 1UL
+#define STRTAB_STE_1_SHCFG_SHIFT 44
+
#define STRTAB_STE_2_S2VMID_SHIFT 0
#define STRTAB_STE_2_S2VMID_MASK 0xffffUL
#define STRTAB_STE_2_VTCR_SHIFT 32
#define PRIQ_0_SID_MASK 0xffffffffUL
#define PRIQ_0_SSID_SHIFT 32
#define PRIQ_0_SSID_MASK 0xfffffUL
-#define PRIQ_0_OF (1UL << 57)
#define PRIQ_0_PERM_PRIV (1UL << 58)
#define PRIQ_0_PERM_EXEC (1UL << 59)
#define PRIQ_0_PERM_READ (1UL << 60)
PRI_RESP_SUCC,
};
+enum arm_smmu_msi_index {
+ EVTQ_MSI_INDEX,
+ GERROR_MSI_INDEX,
+ PRIQ_MSI_INDEX,
+ ARM_SMMU_MAX_MSIS,
+};
+
+static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
+ [EVTQ_MSI_INDEX] = {
+ ARM_SMMU_EVTQ_IRQ_CFG0,
+ ARM_SMMU_EVTQ_IRQ_CFG1,
+ ARM_SMMU_EVTQ_IRQ_CFG2,
+ },
+ [GERROR_MSI_INDEX] = {
+ ARM_SMMU_GERROR_IRQ_CFG0,
+ ARM_SMMU_GERROR_IRQ_CFG1,
+ ARM_SMMU_GERROR_IRQ_CFG2,
+ },
+ [PRIQ_MSI_INDEX] = {
+ ARM_SMMU_PRIQ_IRQ_CFG0,
+ ARM_SMMU_PRIQ_IRQ_CFG1,
+ ARM_SMMU_PRIQ_IRQ_CFG2,
+ },
+};
+
struct arm_smmu_cmdq_ent {
/* Common fields */
u8 opcode;
unsigned int sid_bits;
struct arm_smmu_strtab_cfg strtab_cfg;
- struct list_head list;
};
/* SMMU private data for an IOMMU group */
struct iommu_domain domain;
};
-/* Our list of SMMU instances */
-static DEFINE_SPINLOCK(arm_smmu_devices_lock);
-static LIST_HEAD(arm_smmu_devices);
-
struct arm_smmu_option_prop {
u32 opt;
const char *prop;
};
dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
- cerror_str[idx]);
+ idx < ARRAY_SIZE(cerror_str) ? cerror_str[idx] : "Unknown");
switch (idx) {
- case CMDQ_ERR_CERROR_ILL_IDX:
- break;
case CMDQ_ERR_CERROR_ABT_IDX:
dev_err(smmu->dev, "retrying command fetch\n");
case CMDQ_ERR_CERROR_NONE_IDX:
return;
+ case CMDQ_ERR_CERROR_ILL_IDX:
+ /* Fallthrough */
+ default:
+ break;
}
/*
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);
dst[2] = 0; /* Nuke the VMID */
if (ste_live)
arm_smmu_sync_ste_for_sid(smmu, sid);
strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
desc->span = STRTAB_SPLIT + 1;
- desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
- GFP_KERNEL);
+ desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!desc->l2ptr) {
dev_err(smmu->dev,
"failed to allocate l2 stream table for SID %u\n",
struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
if (cfg->cdptr) {
- dma_free_coherent(smmu_domain->smmu->dev,
- CTXDESC_CD_DWORDS << 3,
- cfg->cdptr,
- cfg->cdptr_dma);
+ dmam_free_coherent(smmu_domain->smmu->dev,
+ CTXDESC_CD_DWORDS << 3,
+ cfg->cdptr,
+ cfg->cdptr_dma);
arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
}
struct io_pgtable_cfg *pgtbl_cfg)
{
int ret;
- u16 asid;
+ int asid;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
if (IS_ERR_VALUE(asid))
return asid;
- cfg->cdptr = dma_zalloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
- &cfg->cdptr_dma, GFP_KERNEL);
+ cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
+ &cfg->cdptr_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!cfg->cdptr) {
dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+ ret = -ENOMEM;
goto out_free_asid;
}
- cfg->cd.asid = asid;
+ cfg->cd.asid = (u16)asid;
cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
cfg->cd.tcr = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
struct io_pgtable_cfg *pgtbl_cfg)
{
- u16 vmid;
+ int vmid;
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
if (IS_ERR_VALUE(vmid))
return vmid;
- cfg->vmid = vmid;
+ cfg->vmid = (u16)vmid;
cfg->vttbr = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
cfg->vtcr = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
return 0;
static struct arm_smmu_device *arm_smmu_get_for_pci_dev(struct pci_dev *pdev)
{
struct device_node *of_node;
- struct arm_smmu_device *curr, *smmu = NULL;
+ struct platform_device *smmu_pdev;
+ struct arm_smmu_device *smmu = NULL;
struct pci_bus *bus = pdev->bus;
/* Walk up to the root bus */
return NULL;
/* See if we can find an SMMU corresponding to the phandle */
- spin_lock(&arm_smmu_devices_lock);
- list_for_each_entry(curr, &arm_smmu_devices, list) {
- if (curr->dev->of_node == of_node) {
- smmu = curr;
- break;
- }
- }
- spin_unlock(&arm_smmu_devices_lock);
+ smmu_pdev = of_find_device_by_node(of_node);
+ if (smmu_pdev)
+ smmu = platform_get_drvdata(smmu_pdev);
+
of_node_put(of_node);
return smmu;
}
smmu = arm_smmu_get_for_pci_dev(pdev);
if (!smmu) {
ret = -ENOENT;
- goto out_put_group;
+ goto out_remove_dev;
}
smmu_group = kzalloc(sizeof(*smmu_group), GFP_KERNEL);
if (!smmu_group) {
ret = -ENOMEM;
- goto out_put_group;
+ goto out_remove_dev;
}
smmu_group->ste.valid = true;
for (i = 0; i < smmu_group->num_sids; ++i) {
/* If we already know about this SID, then we're done */
if (smmu_group->sids[i] == sid)
- return 0;
+ goto out_put_group;
}
/* Check the SID is in range of the SMMU and our stream table */
if (!arm_smmu_sid_in_range(smmu, sid)) {
ret = -ERANGE;
- goto out_put_group;
+ goto out_remove_dev;
}
/* Ensure l2 strtab is initialised */
if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
ret = arm_smmu_init_l2_strtab(smmu, sid);
if (ret)
- goto out_put_group;
+ goto out_remove_dev;
}
/* Resize the SID array for the group */
if (!sids) {
smmu_group->num_sids--;
ret = -ENOMEM;
- goto out_put_group;
+ goto out_remove_dev;
}
/* Add the new SID */
sids[smmu_group->num_sids - 1] = sid;
smmu_group->sids = sids;
- return 0;
out_put_group:
+ iommu_group_put(group);
+ return 0;
+
+out_remove_dev:
+ iommu_group_remove_device(dev);
iommu_group_put(group);
return ret;
}
.iova_to_phys = arm_smmu_iova_to_phys,
.add_device = arm_smmu_add_device,
.remove_device = arm_smmu_remove_device,
+ .device_group = pci_device_group,
.domain_get_attr = arm_smmu_domain_get_attr,
.domain_set_attr = arm_smmu_domain_set_attr,
.pgsize_bitmap = -1UL, /* Restricted during device attach */
{
size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;
- q->base = dma_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
+ q->base = dmam_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
if (!q->base) {
dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n",
qsz);
return 0;
}
-static void arm_smmu_free_one_queue(struct arm_smmu_device *smmu,
- struct arm_smmu_queue *q)
-{
- size_t qsz = ((1 << q->max_n_shift) * q->ent_dwords) << 3;
-
- dma_free_coherent(smmu->dev, qsz, q->base, q->base_dma);
-}
-
-static void arm_smmu_free_queues(struct arm_smmu_device *smmu)
-{
- arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
- arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
-
- if (smmu->features & ARM_SMMU_FEAT_PRI)
- arm_smmu_free_one_queue(smmu, &smmu->priq.q);
-}
-
static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
{
int ret;
ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
if (ret)
- goto out;
+ return ret;
/* evtq */
ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
if (ret)
- goto out_free_cmdq;
+ return ret;
/* priq */
if (!(smmu->features & ARM_SMMU_FEAT_PRI))
return 0;
- ret = arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
- ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
- if (ret)
- goto out_free_evtq;
-
- return 0;
-
-out_free_evtq:
- arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
-out_free_cmdq:
- arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
-out:
- return ret;
-}
-
-static void arm_smmu_free_l2_strtab(struct arm_smmu_device *smmu)
-{
- int i;
- size_t size;
- struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
-
- size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
- for (i = 0; i < cfg->num_l1_ents; ++i) {
- struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[i];
-
- if (!desc->l2ptr)
- continue;
-
- dma_free_coherent(smmu->dev, size, desc->l2ptr,
- desc->l2ptr_dma);
- }
+ return arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
+ ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
}
static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
void *strtab;
u64 reg;
u32 size, l1size;
- int ret;
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
/*
size, smmu->sid_bits);
l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
- strtab = dma_zalloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
- GFP_KERNEL);
+ strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!strtab) {
dev_err(smmu->dev,
"failed to allocate l1 stream table (%u bytes)\n",
<< STRTAB_BASE_CFG_SPLIT_SHIFT;
cfg->strtab_base_cfg = reg;
- ret = arm_smmu_init_l1_strtab(smmu);
- if (ret)
- dma_free_coherent(smmu->dev,
- l1size,
- strtab,
- cfg->strtab_dma);
- return ret;
+ return arm_smmu_init_l1_strtab(smmu);
}
static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
- strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
- GFP_KERNEL);
+ strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+ GFP_KERNEL | __GFP_ZERO);
if (!strtab) {
dev_err(smmu->dev,
"failed to allocate linear stream table (%u bytes)\n",
return 0;
}
-static void arm_smmu_free_strtab(struct arm_smmu_device *smmu)
-{
- struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
- u32 size = cfg->num_l1_ents;
-
- if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
- arm_smmu_free_l2_strtab(smmu);
- size *= STRTAB_L1_DESC_DWORDS << 3;
- } else {
- size *= STRTAB_STE_DWORDS * 3;
- }
-
- dma_free_coherent(smmu->dev, size, cfg->strtab, cfg->strtab_dma);
-}
-
static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
{
int ret;
if (ret)
return ret;
- ret = arm_smmu_init_strtab(smmu);
- if (ret)
- goto out_free_queues;
-
- return 0;
-
-out_free_queues:
- arm_smmu_free_queues(smmu);
- return ret;
-}
-
-static void arm_smmu_free_structures(struct arm_smmu_device *smmu)
-{
- arm_smmu_free_strtab(smmu);
- arm_smmu_free_queues(smmu);
+ return arm_smmu_init_strtab(smmu);
}
static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
1, ARM_SMMU_POLL_TIMEOUT_US);
}
+static void arm_smmu_free_msis(void *data)
+{
+ struct device *dev = data;
+ platform_msi_domain_free_irqs(dev);
+}
+
+static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+ phys_addr_t doorbell;
+ struct device *dev = msi_desc_to_dev(desc);
+ struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+ phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index];
+
+ doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+ doorbell &= MSI_CFG0_ADDR_MASK << MSI_CFG0_ADDR_SHIFT;
+
+ writeq_relaxed(doorbell, smmu->base + cfg[0]);
+ writel_relaxed(msg->data, smmu->base + cfg[1]);
+ writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]);
+}
+
+static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
+{
+ struct msi_desc *desc;
+ int ret, nvec = ARM_SMMU_MAX_MSIS;
+ struct device *dev = smmu->dev;
+
+ /* Clear the MSI address regs */
+ writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
+ writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
+
+ if (smmu->features & ARM_SMMU_FEAT_PRI)
+ writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
+ else
+ nvec--;
+
+ if (!(smmu->features & ARM_SMMU_FEAT_MSI))
+ return;
+
+ /* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */
+ ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg);
+ if (ret) {
+ dev_warn(dev, "failed to allocate MSIs\n");
+ return;
+ }
+
+ for_each_msi_entry(desc, dev) {
+ switch (desc->platform.msi_index) {
+ case EVTQ_MSI_INDEX:
+ smmu->evtq.q.irq = desc->irq;
+ break;
+ case GERROR_MSI_INDEX:
+ smmu->gerr_irq = desc->irq;
+ break;
+ case PRIQ_MSI_INDEX:
+ smmu->priq.q.irq = desc->irq;
+ break;
+ default: /* Unknown */
+ continue;
+ }
+ }
+
+ /* Add callback to free MSIs on teardown */
+ devm_add_action(dev, arm_smmu_free_msis, dev);
+}
+
static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
{
int ret, irq;
return ret;
}
- /* Clear the MSI address regs */
- writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
- writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
+ arm_smmu_setup_msis(smmu);
- /* Request wired interrupt lines */
+ /* Request interrupt lines */
irq = smmu->evtq.q.irq;
if (irq) {
ret = devm_request_threaded_irq(smmu->dev, irq,
}
if (smmu->features & ARM_SMMU_FEAT_PRI) {
- writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
-
irq = smmu->priq.q.irq;
if (irq) {
ret = devm_request_threaded_irq(smmu->dev, irq,
if (ret)
return ret;
- /* Reset the device */
- ret = arm_smmu_device_reset(smmu);
- if (ret)
- goto out_free_structures;
-
/* Record our private device structure */
- INIT_LIST_HEAD(&smmu->list);
- spin_lock(&arm_smmu_devices_lock);
- list_add(&smmu->list, &arm_smmu_devices);
- spin_unlock(&arm_smmu_devices_lock);
- return 0;
+ platform_set_drvdata(pdev, smmu);
-out_free_structures:
- arm_smmu_free_structures(smmu);
- return ret;
+ /* Reset the device */
+ return arm_smmu_device_reset(smmu);
}
static int arm_smmu_device_remove(struct platform_device *pdev)
{
- struct arm_smmu_device *curr, *smmu = NULL;
- struct device *dev = &pdev->dev;
-
- spin_lock(&arm_smmu_devices_lock);
- list_for_each_entry(curr, &arm_smmu_devices, list) {
- if (curr->dev == dev) {
- smmu = curr;
- list_del(&smmu->list);
- break;
- }
- }
- spin_unlock(&arm_smmu_devices_lock);
-
- if (!smmu)
- return -ENODEV;
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
arm_smmu_device_disable(smmu);
- arm_smmu_free_structures(smmu);
return 0;
}