Merge branches 'x86/amd', 'x86/vt-d', 'arm/rockchip', 'arm/omap', 'arm/mediatek', 'arm/exynos', 'arm/renesas', 'arm/smmu' and 'core' into next
diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
index 1fd5d696..ffadb7c 100644
--- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
+++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt
@@ -11,6 +11,8 @@
the device is compatible with the R-Car Gen2 VMSA-compatible IPMMU.
- "renesas,ipmmu-r8a73a4" for the R8A73A4 (R-Mobile APE6) IPMMU.
+ - "renesas,ipmmu-r8a7743" for the R8A7743 (RZ/G1M) IPMMU.
+ - "renesas,ipmmu-r8a7745" for the R8A7745 (RZ/G1E) IPMMU.
- "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU.
- "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU.
- "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.
@@ -19,7 +21,8 @@
- "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU.
- "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU.
- "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU.
- - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU.
+ - "renesas,ipmmu-vmsa" for generic R-Car Gen2 or RZ/G1 VMSA-compatible
+ IPMMU.
- reg: Base address and size of the IPMMU registers.
- interrupts: Specifiers for the MMU fault interrupts. For instances that
diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt b/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt
index 2098f77..6ecefea 100644
--- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt
+++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt
@@ -14,6 +14,11 @@
"single-master" device, and needs no additional information
to associate with its master device. See:
Documentation/devicetree/bindings/iommu/iommu.txt
+- clocks : A list of clocks required for the IOMMU to be accessible by
+ the host CPU.
+- clock-names : Should contain the following:
+ "iface" - Main peripheral bus clock (PCLK/HCL) (required)
+ "aclk" - AXI bus clock (required)
Optional properties:
- rockchip,disable-mmu-reset : Don't use the mmu reset operation.
@@ -27,5 +32,7 @@
reg = <0xff940300 0x100>;
interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "vopl_mmu";
+ clocks = <&cru ACLK_VOP1>, <&cru HCLK_VOP1>;
+ clock-names = "aclk", "iface";
#iommu-cells = <0>;
};
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 95255ec..e2f7bdd 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -39,6 +39,7 @@
struct iort_its_msi_chip {
struct list_head list;
struct fwnode_handle *fw_node;
+ phys_addr_t base_addr;
u32 translation_id;
};
@@ -161,14 +162,16 @@ static LIST_HEAD(iort_msi_chip_list);
static DEFINE_SPINLOCK(iort_msi_chip_lock);
/**
- * iort_register_domain_token() - register domain token and related ITS ID
- * to the list from where we can get it back later on.
+ * iort_register_domain_token() - register domain token along with related
+ * ITS ID and base address to the list from where we can get it back later on.
* @trans_id: ITS ID.
+ * @base: ITS base address.
* @fw_node: Domain token.
*
* Returns: 0 on success, -ENOMEM if no memory when allocating list element
*/
-int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
+int iort_register_domain_token(int trans_id, phys_addr_t base,
+ struct fwnode_handle *fw_node)
{
struct iort_its_msi_chip *its_msi_chip;
@@ -178,6 +181,7 @@ int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node)
its_msi_chip->fw_node = fw_node;
its_msi_chip->translation_id = trans_id;
+ its_msi_chip->base_addr = base;
spin_lock(&iort_msi_chip_lock);
list_add(&its_msi_chip->list, &iort_msi_chip_list);
@@ -581,6 +585,24 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
return -ENODEV;
}
+static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base)
+{
+ struct iort_its_msi_chip *its_msi_chip;
+ int ret = -ENODEV;
+
+ spin_lock(&iort_msi_chip_lock);
+ list_for_each_entry(its_msi_chip, &iort_msi_chip_list, list) {
+ if (its_msi_chip->translation_id == its_id) {
+ *base = its_msi_chip->base_addr;
+ ret = 0;
+ break;
+ }
+ }
+ spin_unlock(&iort_msi_chip_lock);
+
+ return ret;
+}
+
/**
* iort_dev_find_its_id() - Find the ITS identifier for a device
* @dev: The device.
@@ -766,6 +788,24 @@ static inline bool iort_iommu_driver_enabled(u8 type)
}
#ifdef CONFIG_IOMMU_API
+static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev)
+{
+ struct acpi_iort_node *iommu;
+ struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+
+ iommu = iort_get_iort_node(fwspec->iommu_fwnode);
+
+ if (iommu && (iommu->type == ACPI_IORT_NODE_SMMU_V3)) {
+ struct acpi_iort_smmu_v3 *smmu;
+
+ smmu = (struct acpi_iort_smmu_v3 *)iommu->node_data;
+ if (smmu->model == ACPI_IORT_SMMU_V3_HISILICON_HI161X)
+ return iommu;
+ }
+
+ return NULL;
+}
+
static inline const struct iommu_ops *iort_fwspec_iommu_ops(
struct iommu_fwspec *fwspec)
{
@@ -782,6 +822,69 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops,
return err;
}
+
+/**
+ * iort_iommu_msi_get_resv_regions - Reserved region driver helper
+ * @dev: Device from iommu_get_resv_regions()
+ * @head: Reserved region list from iommu_get_resv_regions()
+ *
+ * Returns: Number of msi reserved regions on success (0 if platform
+ * doesn't require the reservation or no associated msi regions),
+ * appropriate error value otherwise. The ITS interrupt translation
+ * spaces (ITS_base + SZ_64K, SZ_64K) associated with the device
+ * are the msi reserved regions.
+ */
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{
+ struct acpi_iort_its_group *its;
+ struct acpi_iort_node *iommu_node, *its_node = NULL;
+ int i, resv = 0;
+
+ iommu_node = iort_get_msi_resv_iommu(dev);
+ if (!iommu_node)
+ return 0;
+
+ /*
+ * Current logic to reserve ITS regions relies on HW topologies
+ * where a given PCI or named component maps its IDs to only one
+ * ITS group; if a PCI or named component can map its IDs to
+ * different ITS groups through IORT mappings this function has
+ * to be reworked to ensure we reserve regions for all ITS groups
+ * a given PCI or named component may map IDs to.
+ */
+
+ for (i = 0; i < dev->iommu_fwspec->num_ids; i++) {
+ its_node = iort_node_map_id(iommu_node,
+ dev->iommu_fwspec->ids[i],
+ NULL, IORT_MSI_TYPE);
+ if (its_node)
+ break;
+ }
+
+ if (!its_node)
+ return 0;
+
+ /* Move to ITS specific data */
+ its = (struct acpi_iort_its_group *)its_node->node_data;
+
+ for (i = 0; i < its->its_count; i++) {
+ phys_addr_t base;
+
+ if (!iort_find_its_base(its->identifiers[i], &base)) {
+ int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+ struct iommu_resv_region *region;
+
+ region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K,
+ prot, IOMMU_RESV_MSI);
+ if (region) {
+ list_add_tail(®ion->list, head);
+ resv++;
+ }
+ }
+ }
+
+ return (resv == its->its_count) ? resv : -ENODEV;
+}
#else
static inline const struct iommu_ops *iort_fwspec_iommu_ops(
struct iommu_fwspec *fwspec)
@@ -789,6 +892,8 @@ static inline const struct iommu_ops *iort_fwspec_iommu_ops(
static inline int iort_add_device_replay(const struct iommu_ops *ops,
struct device *dev)
{ return 0; }
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{ return 0; }
#endif
static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 74788fd..8c469b5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -80,11 +80,12 @@
*/
#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38))
-static DEFINE_RWLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(pd_bitmap_lock);
+static DEFINE_SPINLOCK(iommu_table_lock);
/* List of all available dev_data structures */
-static LIST_HEAD(dev_data_list);
-static DEFINE_SPINLOCK(dev_data_list_lock);
+static LLIST_HEAD(dev_data_list);
LIST_HEAD(ioapic_map);
LIST_HEAD(hpet_map);
@@ -203,40 +204,33 @@ static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain
static struct iommu_dev_data *alloc_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
- unsigned long flags;
dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
if (!dev_data)
return NULL;
dev_data->devid = devid;
-
- spin_lock_irqsave(&dev_data_list_lock, flags);
- list_add_tail(&dev_data->dev_data_list, &dev_data_list);
- spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
ratelimit_default_init(&dev_data->rs);
+ llist_add(&dev_data->dev_data_list, &dev_data_list);
return dev_data;
}
static struct iommu_dev_data *search_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
- unsigned long flags;
+ struct llist_node *node;
- spin_lock_irqsave(&dev_data_list_lock, flags);
- list_for_each_entry(dev_data, &dev_data_list, dev_data_list) {
+ if (llist_empty(&dev_data_list))
+ return NULL;
+
+ node = dev_data_list.first;
+ llist_for_each_entry(dev_data, node, dev_data_list) {
if (dev_data->devid == devid)
- goto out_unlock;
+ return dev_data;
}
- dev_data = NULL;
-
-out_unlock:
- spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
- return dev_data;
+ return NULL;
}
static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -310,6 +304,8 @@ static struct iommu_dev_data *find_dev_data(u16 devid)
if (dev_data == NULL) {
dev_data = alloc_dev_data(devid);
+ if (!dev_data)
+ return NULL;
if (translation_pre_enabled(iommu))
dev_data->defer_attach = true;
@@ -547,6 +543,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
{
+ struct device *dev = iommu->iommu.dev;
int type, devid, domid, flags;
volatile u32 *event = __evt;
int count = 0;
@@ -573,53 +570,53 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
amd_iommu_report_page_fault(devid, domid, address, flags);
return;
} else {
- printk(KERN_ERR "AMD-Vi: Event logged [");
+ dev_err(dev, "AMD-Vi: Event logged [");
}
switch (type) {
case EVENT_TYPE_ILL_DEV:
- printk("ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
- "address=0x%016llx flags=0x%04x]\n",
- PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
- address, flags);
+ dev_err(dev, "ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x "
+ "address=0x%016llx flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ address, flags);
dump_dte_entry(devid);
break;
case EVENT_TYPE_DEV_TAB_ERR:
- printk("DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
- "address=0x%016llx flags=0x%04x]\n",
- PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
- address, flags);
+ dev_err(dev, "DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
+ "address=0x%016llx flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ address, flags);
break;
case EVENT_TYPE_PAGE_TAB_ERR:
- printk("PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
- "domain=0x%04x address=0x%016llx flags=0x%04x]\n",
- PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
- domid, address, flags);
+ dev_err(dev, "PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
+ "domain=0x%04x address=0x%016llx flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ domid, address, flags);
break;
case EVENT_TYPE_ILL_CMD:
- printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
+ dev_err(dev, "ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address);
dump_command(address);
break;
case EVENT_TYPE_CMD_HARD_ERR:
- printk("COMMAND_HARDWARE_ERROR address=0x%016llx "
- "flags=0x%04x]\n", address, flags);
+ dev_err(dev, "COMMAND_HARDWARE_ERROR address=0x%016llx "
+ "flags=0x%04x]\n", address, flags);
break;
case EVENT_TYPE_IOTLB_INV_TO:
- printk("IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
- "address=0x%016llx]\n",
- PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
- address);
+ dev_err(dev, "IOTLB_INV_TIMEOUT device=%02x:%02x.%x "
+ "address=0x%016llx]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ address);
break;
case EVENT_TYPE_INV_DEV_REQ:
- printk("INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
- "address=0x%016llx flags=0x%04x]\n",
- PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
- address, flags);
+ dev_err(dev, "INVALID_DEVICE_REQUEST device=%02x:%02x.%x "
+ "address=0x%016llx flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ address, flags);
break;
default:
- printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x "
- "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
- type, event[0], event[1], event[2], event[3]);
+ dev_err(dev, KERN_ERR "UNKNOWN event[0]=0x%08x event[1]=0x%08x "
+ "event[2]=0x%08x event[3]=0x%08x\n",
+ event[0], event[1], event[2], event[3]);
}
memset(__evt, 0, 4 * sizeof(u32));
@@ -1056,9 +1053,9 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
unsigned long flags;
int ret;
- spin_lock_irqsave(&iommu->lock, flags);
+ raw_spin_lock_irqsave(&iommu->lock, flags);
ret = __iommu_queue_command_sync(iommu, cmd, sync);
- spin_unlock_irqrestore(&iommu->lock, flags);
+ raw_spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
}
@@ -1084,7 +1081,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
- spin_lock_irqsave(&iommu->lock, flags);
+ raw_spin_lock_irqsave(&iommu->lock, flags);
iommu->cmd_sem = 0;
@@ -1095,7 +1092,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
ret = wait_on_sem(&iommu->cmd_sem);
out_unlock:
- spin_unlock_irqrestore(&iommu->lock, flags);
+ raw_spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
}
@@ -1605,29 +1602,26 @@ static void del_domain_from_list(struct protection_domain *domain)
static u16 domain_id_alloc(void)
{
- unsigned long flags;
int id;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock(&pd_bitmap_lock);
id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
BUG_ON(id == 0);
if (id > 0 && id < MAX_DOMAIN_ID)
__set_bit(id, amd_iommu_pd_alloc_bitmap);
else
id = 0;
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock(&pd_bitmap_lock);
return id;
}
static void domain_id_free(int id)
{
- unsigned long flags;
-
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock(&pd_bitmap_lock);
if (id > 0 && id < MAX_DOMAIN_ID)
__clear_bit(id, amd_iommu_pd_alloc_bitmap);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock(&pd_bitmap_lock);
}
#define DEFINE_FREE_PT_FN(LVL, FN) \
@@ -2103,9 +2097,9 @@ static int attach_device(struct device *dev,
}
skip_ats_check:
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
ret = __attach_device(dev_data, domain);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
/*
* We might boot into a crash-kernel here. The crashed kernel
@@ -2155,9 +2149,9 @@ static void detach_device(struct device *dev)
domain = dev_data->domain;
/* lock device table */
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
__detach_device(dev_data);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
if (!dev_is_pci(dev))
return;
@@ -2820,7 +2814,7 @@ static void cleanup_domain(struct protection_domain *domain)
struct iommu_dev_data *entry;
unsigned long flags;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
while (!list_empty(&domain->dev_list)) {
entry = list_first_entry(&domain->dev_list,
@@ -2828,7 +2822,7 @@ static void cleanup_domain(struct protection_domain *domain)
__detach_device(entry);
}
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
}
static void protection_domain_free(struct protection_domain *domain)
@@ -3050,15 +3044,12 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
size_t unmap_size;
if (domain->mode == PAGE_MODE_NONE)
- return -EINVAL;
+ return 0;
mutex_lock(&domain->api_lock);
unmap_size = iommu_unmap_page(domain, iova, page_size);
mutex_unlock(&domain->api_lock);
- domain_flush_tlb_pde(domain);
- domain_flush_complete(domain);
-
return unmap_size;
}
@@ -3176,6 +3167,19 @@ static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
return dev_data->defer_attach;
}
+static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+ struct protection_domain *dom = to_pdomain(domain);
+
+ domain_flush_tlb_pde(dom);
+ domain_flush_complete(dom);
+}
+
+static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
+ unsigned long iova, size_t size)
+{
+}
+
const struct iommu_ops amd_iommu_ops = {
.capable = amd_iommu_capable,
.domain_alloc = amd_iommu_domain_alloc,
@@ -3194,6 +3198,9 @@ const struct iommu_ops amd_iommu_ops = {
.apply_resv_region = amd_iommu_apply_resv_region,
.is_attach_deferred = amd_iommu_is_attach_deferred,
.pgsize_bitmap = AMD_IOMMU_PGSIZES,
+ .flush_iotlb_all = amd_iommu_flush_iotlb_all,
+ .iotlb_range_add = amd_iommu_iotlb_range_add,
+ .iotlb_sync = amd_iommu_flush_iotlb_all,
};
/*****************************************************************************
@@ -3595,14 +3602,62 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
amd_iommu_dev_table[devid].data[2] = dte;
}
-static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
+static struct irq_remap_table *get_irq_table(u16 devid)
+{
+ struct irq_remap_table *table;
+
+ if (WARN_ONCE(!amd_iommu_rlookup_table[devid],
+ "%s: no iommu for devid %x\n", __func__, devid))
+ return NULL;
+
+ table = irq_lookup_table[devid];
+ if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid))
+ return NULL;
+
+ return table;
+}
+
+static struct irq_remap_table *__alloc_irq_table(void)
+{
+ struct irq_remap_table *table;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return NULL;
+
+ table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL);
+ if (!table->table) {
+ kfree(table);
+ return NULL;
+ }
+ raw_spin_lock_init(&table->lock);
+
+ if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+ memset(table->table, 0,
+ MAX_IRQS_PER_TABLE * sizeof(u32));
+ else
+ memset(table->table, 0,
+ (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+ return table;
+}
+
+static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
+ struct irq_remap_table *table)
+{
+ irq_lookup_table[devid] = table;
+ set_dte_irq_entry(devid, table);
+ iommu_flush_dte(iommu, devid);
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid)
{
struct irq_remap_table *table = NULL;
+ struct irq_remap_table *new_table = NULL;
struct amd_iommu *iommu;
unsigned long flags;
u16 alias;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&iommu_table_lock, flags);
iommu = amd_iommu_rlookup_table[devid];
if (!iommu)
@@ -3615,60 +3670,45 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
alias = amd_iommu_alias_table[devid];
table = irq_lookup_table[alias];
if (table) {
- irq_lookup_table[devid] = table;
- set_dte_irq_entry(devid, table);
- iommu_flush_dte(iommu, devid);
- goto out;
+ set_remap_table_entry(iommu, devid, table);
+ goto out_wait;
}
+ spin_unlock_irqrestore(&iommu_table_lock, flags);
/* Nothing there yet, allocate new irq remapping table */
- table = kzalloc(sizeof(*table), GFP_ATOMIC);
- if (!table)
+ new_table = __alloc_irq_table();
+ if (!new_table)
+ return NULL;
+
+ spin_lock_irqsave(&iommu_table_lock, flags);
+
+ table = irq_lookup_table[devid];
+ if (table)
goto out_unlock;
- /* Initialize table spin-lock */
- spin_lock_init(&table->lock);
-
- if (ioapic)
- /* Keep the first 32 indexes free for IOAPIC interrupts */
- table->min_index = 32;
-
- table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC);
- if (!table->table) {
- kfree(table);
- table = NULL;
- goto out_unlock;
+ table = irq_lookup_table[alias];
+ if (table) {
+ set_remap_table_entry(iommu, devid, table);
+ goto out_wait;
}
- if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
- memset(table->table, 0,
- MAX_IRQS_PER_TABLE * sizeof(u32));
- else
- memset(table->table, 0,
- (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+ table = new_table;
+ new_table = NULL;
- if (ioapic) {
- int i;
+ set_remap_table_entry(iommu, devid, table);
+ if (devid != alias)
+ set_remap_table_entry(iommu, alias, table);
- for (i = 0; i < 32; ++i)
- iommu->irte_ops->set_allocated(table, i);
- }
-
- irq_lookup_table[devid] = table;
- set_dte_irq_entry(devid, table);
- iommu_flush_dte(iommu, devid);
- if (devid != alias) {
- irq_lookup_table[alias] = table;
- set_dte_irq_entry(alias, table);
- iommu_flush_dte(iommu, alias);
- }
-
-out:
+out_wait:
iommu_completion_wait(iommu);
out_unlock:
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&iommu_table_lock, flags);
+ if (new_table) {
+ kmem_cache_free(amd_iommu_irq_cache, new_table->table);
+ kfree(new_table);
+ }
return table;
}
@@ -3682,14 +3722,14 @@ static int alloc_irq_index(u16 devid, int count, bool align)
if (!iommu)
return -ENODEV;
- table = get_irq_table(devid, false);
+ table = alloc_irq_table(devid);
if (!table)
return -ENODEV;
if (align)
alignment = roundup_pow_of_two(count);
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
/* Scan table for free entries */
for (index = ALIGN(table->min_index, alignment), c = 0;
@@ -3716,7 +3756,7 @@ static int alloc_irq_index(u16 devid, int count, bool align)
index = -ENOSPC;
out:
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
return index;
}
@@ -3733,11 +3773,11 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
if (iommu == NULL)
return -EINVAL;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return -ENOMEM;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
entry = (struct irte_ga *)table->table;
entry = &entry[index];
@@ -3748,7 +3788,7 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
if (data)
data->ref = entry;
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3766,13 +3806,13 @@ static int modify_irte(u16 devid, int index, union irte *irte)
if (iommu == NULL)
return -EINVAL;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return -ENOMEM;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
table->table[index] = irte->val;
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3790,13 +3830,13 @@ static void free_irte(u16 devid, int index)
if (iommu == NULL)
return;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
iommu->irte_ops->clear_allocated(table, index);
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3877,10 +3917,8 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
u8 vector, u32 dest_apicid)
{
struct irte_ga *irte = (struct irte_ga *) entry;
- struct iommu_dev_data *dev_data = search_dev_data(devid);
- if (!dev_data || !dev_data->use_vapic ||
- !irte->lo.fields_remap.guest_mode) {
+ if (!irte->lo.fields_remap.guest_mode) {
irte->hi.fields.vector = vector;
irte->lo.fields_remap.destination = dest_apicid;
modify_irte_ga(devid, index, irte, NULL);
@@ -4086,7 +4124,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
struct amd_ir_data *data = NULL;
struct irq_cfg *cfg;
int i, ret, devid;
- int index = -1;
+ int index;
if (!info)
return -EINVAL;
@@ -4110,10 +4148,26 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
return ret;
if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
- if (get_irq_table(devid, true))
+ struct irq_remap_table *table;
+ struct amd_iommu *iommu;
+
+ table = alloc_irq_table(devid);
+ if (table) {
+ if (!table->min_index) {
+ /*
+ * Keep the first 32 indexes free for IOAPIC
+ * interrupts.
+ */
+ table->min_index = 32;
+ iommu = amd_iommu_rlookup_table[devid];
+ for (i = 0; i < 32; ++i)
+ iommu->irte_ops->set_allocated(table, i);
+ }
+ WARN_ON(table->min_index != 32);
index = info->ioapic_pin;
- else
- ret = -ENOMEM;
+ } else {
+ index = -ENOMEM;
+ }
} else {
bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
@@ -4379,7 +4433,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
{
unsigned long flags;
struct amd_iommu *iommu;
- struct irq_remap_table *irt;
+ struct irq_remap_table *table;
struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
int devid = ir_data->irq_2_irte.devid;
struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -4393,11 +4447,11 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
if (!iommu)
return -ENODEV;
- irt = get_irq_table(devid, false);
- if (!irt)
+ table = get_irq_table(devid);
+ if (!table)
return -ENODEV;
- spin_lock_irqsave(&irt->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
if (ref->lo.fields_vapic.guest_mode) {
if (cpu >= 0)
@@ -4406,7 +4460,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
barrier();
}
- spin_unlock_irqrestore(&irt->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 4e4a615..904c575 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1474,7 +1474,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
{
int ret;
- spin_lock_init(&iommu->lock);
+ raw_spin_lock_init(&iommu->lock);
/* Add IOMMU to internal data structures */
list_add_tail(&iommu->list, &amd_iommu_list);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 6a877eb..1c9b0802 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -408,7 +408,7 @@ extern bool amd_iommu_iotlb_sup;
#define IRQ_TABLE_ALIGNMENT 128
struct irq_remap_table {
- spinlock_t lock;
+ raw_spinlock_t lock;
unsigned min_index;
u32 *table;
};
@@ -490,7 +490,7 @@ struct amd_iommu {
int index;
/* locks the accesses to the hardware */
- spinlock_t lock;
+ raw_spinlock_t lock;
/* Pointer to PCI device of this IOMMU */
struct pci_dev *dev;
@@ -627,7 +627,7 @@ struct devid_map {
*/
struct iommu_dev_data {
struct list_head list; /* For domain->dev_list */
- struct list_head dev_data_list; /* For global dev_data_list */
+ struct llist_node dev_data_list; /* For global dev_data_list */
struct protection_domain *domain; /* Domain the device is bound to */
u16 devid; /* PCI Device ID */
u16 alias; /* Alias Device ID */
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 25914d3..f05f3cf 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -19,6 +19,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi_iort.h>
#include <linux/device.h>
#include <linux/dma-iommu.h>
#include <linux/gfp.h>
@@ -167,13 +168,18 @@ EXPORT_SYMBOL(iommu_put_dma_cookie);
*
* IOMMU drivers can use this to implement their .get_resv_regions callback
* for general non-IOMMU-specific reservations. Currently, this covers host
- * bridge windows for PCI devices.
+ * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI
+ * based ARM platforms that may require HW MSI reservation.
*/
void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
{
struct pci_host_bridge *bridge;
struct resource_entry *window;
+ if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) &&
+ iort_iommu_msi_get_resv_regions(dev, list) < 0)
+ return;
+
if (!dev_is_pci(dev))
return;
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9a7ffd1..accf5838 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -806,7 +806,7 @@ int __init dmar_dev_scope_init(void)
return dmar_dev_scope_status;
}
-void dmar_register_bus_notifier(void)
+void __init dmar_register_bus_notifier(void)
{
bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
}
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 2138102..210715f 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -1238,17 +1238,6 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
return phys;
}
-static struct iommu_group *get_device_iommu_group(struct device *dev)
-{
- struct iommu_group *group;
-
- group = iommu_group_get(dev);
- if (!group)
- group = iommu_group_alloc();
-
- return group;
-}
-
static int exynos_iommu_add_device(struct device *dev)
{
struct exynos_iommu_owner *owner = dev->archdata.iommu;
@@ -1344,7 +1333,7 @@ static const struct iommu_ops exynos_iommu_ops = {
.unmap = exynos_iommu_unmap,
.map_sg = default_iommu_map_sg,
.iova_to_phys = exynos_iommu_iova_to_phys,
- .device_group = get_device_iommu_group,
+ .device_group = generic_device_group,
.add_device = exynos_iommu_add_device,
.remove_device = exynos_iommu_remove_device,
.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 582fd01..d49e0d3 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -5072,7 +5072,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
struct page *freelist = NULL;
- struct intel_iommu *iommu;
unsigned long start_pfn, last_pfn;
unsigned int npages;
int iommu_id, level = 0;
@@ -5091,12 +5090,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
npages = last_pfn - start_pfn + 1;
- for_each_domain_iommu(iommu_id, dmar_domain) {
- iommu = g_iommus[iommu_id];
-
+ for_each_domain_iommu(iommu_id, dmar_domain)
iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
start_pfn, npages, !freelist, 0);
- }
dma_free_pagelist(freelist);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 99bc9bd..e8cd984 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -396,6 +396,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
pasid_max - 1, GFP_KERNEL);
if (ret < 0) {
kfree(svm);
+ kfree(sdev);
goto out;
}
svm->pasid = ret;
@@ -422,17 +423,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
iommu->pasid_table[svm->pasid].val = pasid_entry_val;
wmb();
- /* In caching mode, we still have to flush with PASID 0 when
- * a PASID table entry becomes present. Not entirely clear
- * *why* that would be the case — surely we could just issue
- * a flush with the PASID value that we've changed? The PASID
- * is the index into the table, after all. It's not like domain
- * IDs in the case of the equivalent context-entry change in
- * caching mode. And for that matter it's not entirely clear why
- * a VMM would be in the business of caching the PASID table
- * anyway. Surely that can be left entirely to the guest? */
+
+ /*
+ * Flush PASID cache when a PASID table entry becomes
+ * present.
+ */
if (cap_caching_mode(iommu->cap))
- intel_flush_pasid_dev(svm, sdev, 0);
+ intel_flush_pasid_dev(svm, sdev, svm->pasid);
}
list_add_rcu(&sdev->list, &svm->devs);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 2ca08dc..10e4a3d 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -357,8 +357,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl)
return false;
}
-static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
- size_t, int, arm_v7s_iopte *);
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long,
+ size_t, int, arm_v7s_iopte *);
static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data,
unsigned long iova, phys_addr_t paddr, int prot,
@@ -541,9 +541,10 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data,
return pte;
}
-static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
- unsigned long iova, size_t size,
- arm_v7s_iopte blk_pte, arm_v7s_iopte *ptep)
+static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
+ unsigned long iova, size_t size,
+ arm_v7s_iopte blk_pte,
+ arm_v7s_iopte *ptep)
{
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_v7s_iopte pte, *tablep;
@@ -584,9 +585,9 @@ static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
return size;
}
-static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
- unsigned long iova, size_t size, int lvl,
- arm_v7s_iopte *ptep)
+static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
+ unsigned long iova, size_t size, int lvl,
+ arm_v7s_iopte *ptep)
{
arm_v7s_iopte pte[ARM_V7S_CONT_PAGES];
struct io_pgtable *iop = &data->iop;
@@ -656,8 +657,8 @@ static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep);
}
-static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size)
+static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+ size_t size)
{
struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 47b64d3..39c2a05 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -285,9 +285,9 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
__arm_lpae_sync_pte(ptep, cfg);
}
-static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
- unsigned long iova, size_t size, int lvl,
- arm_lpae_iopte *ptep);
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+ unsigned long iova, size_t size, int lvl,
+ arm_lpae_iopte *ptep);
static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
phys_addr_t paddr, arm_lpae_iopte prot,
@@ -523,10 +523,10 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop)
kfree(data);
}
-static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
- unsigned long iova, size_t size,
- arm_lpae_iopte blk_pte, int lvl,
- arm_lpae_iopte *ptep)
+static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
+ unsigned long iova, size_t size,
+ arm_lpae_iopte blk_pte, int lvl,
+ arm_lpae_iopte *ptep)
{
struct io_pgtable_cfg *cfg = &data->iop.cfg;
arm_lpae_iopte pte, *tablep;
@@ -577,9 +577,9 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
return size;
}
-static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
- unsigned long iova, size_t size, int lvl,
- arm_lpae_iopte *ptep)
+static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
+ unsigned long iova, size_t size, int lvl,
+ arm_lpae_iopte *ptep)
{
arm_lpae_iopte pte;
struct io_pgtable *iop = &data->iop;
@@ -623,8 +623,8 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep);
}
-static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size)
+static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
+ size_t size)
{
struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
arm_lpae_iopte *ptep = data->pgd;
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
index cd2e1ea..2df7909 100644
--- a/drivers/iommu/io-pgtable.h
+++ b/drivers/iommu/io-pgtable.h
@@ -119,8 +119,8 @@ struct io_pgtable_cfg {
struct io_pgtable_ops {
int (*map)(struct io_pgtable_ops *ops, unsigned long iova,
phys_addr_t paddr, size_t size, int prot);
- int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
- size_t size);
+ size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova,
+ size_t size);
phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
unsigned long iova);
};
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 69fef99..d2aa2320 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1573,10 +1573,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
if (unlikely(ops->unmap == NULL ||
domain->pgsize_bitmap == 0UL))
- return -ENODEV;
+ return 0;
if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING)))
- return -EINVAL;
+ return 0;
/* find out the minimum page size supported */
min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
@@ -1589,7 +1589,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
if (!IS_ALIGNED(iova | size, min_pagesz)) {
pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n",
iova, size, min_pagesz);
- return -EINVAL;
+ return 0;
}
pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index f227d73..f2832a1 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -60,7 +60,7 @@
(((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data))
#define REG_MMU_IVRP_PADDR 0x114
-#define F_MMU_IVRP_PA_SET(pa, ext) (((pa) >> 1) | ((!!(ext)) << 31))
+
#define REG_MMU_VLD_PA_RNG 0x118
#define F_MMU_VLD_PA_RNG(EA, SA) (((EA) << 8) | (SA))
@@ -539,8 +539,13 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
- writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
- data->base + REG_MMU_IVRP_PADDR);
+ if (data->m4u_plat == M4U_MT8173)
+ regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
+ else
+ regval = lower_32_bits(data->protect_base) |
+ upper_32_bits(data->protect_base);
+ writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);
+
if (data->enable_4GB && data->m4u_plat != M4U_MT8173) {
/*
* If 4GB mode is enabled, the validate PA range is from
@@ -695,6 +700,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev)
reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
+ reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
clk_disable_unprepare(data->bclk);
return 0;
}
@@ -717,8 +723,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
- writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB),
- base + REG_MMU_IVRP_PADDR);
+ writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
if (data->m4u_dom)
writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0],
base + REG_MMU_PT_BASE_ADDR);
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index b4451a1..778498b 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -32,6 +32,7 @@ struct mtk_iommu_suspend_reg {
u32 ctrl_reg;
u32 int_control0;
u32 int_main_control;
+ u32 ivrp_paddr;
};
enum mtk_iommu_plat {
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 542930c..1b1b7759 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -418,20 +418,12 @@ static int mtk_iommu_create_mapping(struct device *dev,
m4udev->archdata.iommu = mtk_mapping;
}
- ret = arm_iommu_attach_device(dev, mtk_mapping);
- if (ret)
- goto err_release_mapping;
-
return 0;
-
-err_release_mapping:
- arm_iommu_release_mapping(mtk_mapping);
- m4udev->archdata.iommu = NULL;
- return ret;
}
static int mtk_iommu_add_device(struct device *dev)
{
+ struct dma_iommu_mapping *mtk_mapping;
struct of_phandle_args iommu_spec;
struct of_phandle_iterator it;
struct mtk_iommu_data *data;
@@ -452,15 +444,30 @@ static int mtk_iommu_add_device(struct device *dev)
if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
return -ENODEV; /* Not a iommu client device */
- data = dev->iommu_fwspec->iommu_priv;
- iommu_device_link(&data->iommu, dev);
-
- group = iommu_group_get_for_dev(dev);
+ /*
+ * This is a short-term bodge because the ARM DMA code doesn't
+ * understand multi-device groups, but we have to call into it
+ * successfully (and not just rely on a normal IOMMU API attach
+ * here) in order to set the correct DMA API ops on @dev.
+ */
+ group = iommu_group_alloc();
if (IS_ERR(group))
return PTR_ERR(group);
+ err = iommu_group_add_device(group, dev);
iommu_group_put(group);
- return 0;
+ if (err)
+ return err;
+
+ data = dev->iommu_fwspec->iommu_priv;
+ mtk_mapping = data->dev->archdata.iommu;
+ err = arm_iommu_attach_device(dev, mtk_mapping);
+ if (err) {
+ iommu_group_remove_device(dev);
+ return err;
+ }
+
+ return iommu_device_link(&data->iommu, dev);;
}
static void mtk_iommu_remove_device(struct device *dev)
@@ -477,24 +484,6 @@ static void mtk_iommu_remove_device(struct device *dev)
iommu_fwspec_free(dev);
}
-static struct iommu_group *mtk_iommu_device_group(struct device *dev)
-{
- struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv;
-
- if (!data)
- return ERR_PTR(-ENODEV);
-
- /* All the client devices are in the same m4u iommu-group */
- if (!data->m4u_group) {
- data->m4u_group = iommu_group_alloc();
- if (IS_ERR(data->m4u_group))
- dev_err(dev, "Failed to allocate M4U IOMMU group\n");
- } else {
- iommu_group_ref_get(data->m4u_group);
- }
- return data->m4u_group;
-}
-
static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
{
u32 regval;
@@ -547,7 +536,6 @@ static struct iommu_ops mtk_iommu_ops = {
.iova_to_phys = mtk_iommu_iova_to_phys,
.add_device = mtk_iommu_add_device,
.remove_device = mtk_iommu_remove_device,
- .device_group = mtk_iommu_device_group,
.pgsize_bitmap = ~0UL << MT2701_IOMMU_PAGE_SHIFT,
};
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index e135ab8..c33b7b10 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1536,7 +1536,7 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev)
struct iommu_group *group = ERR_PTR(-EINVAL);
if (arch_data->iommu_dev)
- group = arch_data->iommu_dev->group;
+ group = iommu_group_ref_get(arch_data->iommu_dev->group);
return group;
}
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 9d991c2..5fc8656 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -4,6 +4,7 @@
* published by the Free Software Foundation.
*/
+#include <linux/clk.h>
#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/device.h>
@@ -13,13 +14,15 @@
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
-#include <linux/jiffies.h>
+#include <linux/iopoll.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_iommu.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
@@ -36,7 +39,10 @@
#define RK_MMU_AUTO_GATING 0x24
#define DTE_ADDR_DUMMY 0xCAFEBABE
-#define FORCE_RESET_TIMEOUT 100 /* ms */
+
+#define RK_MMU_POLL_PERIOD_US 100
+#define RK_MMU_FORCE_RESET_TIMEOUT_US 100000
+#define RK_MMU_POLL_TIMEOUT_US 1000
/* RK_MMU_STATUS fields */
#define RK_MMU_STATUS_PAGING_ENABLED BIT(0)
@@ -73,11 +79,8 @@
*/
#define RK_IOMMU_PGSIZE_BITMAP 0x007ff000
-#define IOMMU_REG_POLL_COUNT_FAST 1000
-
struct rk_iommu_domain {
struct list_head iommus;
- struct platform_device *pdev;
u32 *dt; /* page directory table */
dma_addr_t dt_dma;
spinlock_t iommus_lock; /* lock for iommus list */
@@ -86,24 +89,37 @@ struct rk_iommu_domain {
struct iommu_domain domain;
};
+/* list of clocks required by IOMMU */
+static const char * const rk_iommu_clocks[] = {
+ "aclk", "iface",
+};
+
struct rk_iommu {
struct device *dev;
void __iomem **bases;
int num_mmu;
- int *irq;
- int num_irq;
+ struct clk_bulk_data *clocks;
+ int num_clocks;
bool reset_disabled;
struct iommu_device iommu;
struct list_head node; /* entry in rk_iommu_domain.iommus */
struct iommu_domain *domain; /* domain to which iommu is attached */
+ struct iommu_group *group;
};
+struct rk_iommudata {
+ struct device_link *link; /* runtime PM link from IOMMU to master */
+ struct rk_iommu *iommu;
+};
+
+static struct device *dma_dev;
+
static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma,
unsigned int count)
{
size_t size = count * sizeof(u32); /* count of u32 entry */
- dma_sync_single_for_device(&dom->pdev->dev, dma, size, DMA_TO_DEVICE);
+ dma_sync_single_for_device(dma_dev, dma, size, DMA_TO_DEVICE);
}
static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
@@ -111,27 +127,6 @@ static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
return container_of(dom, struct rk_iommu_domain, domain);
}
-/**
- * Inspired by _wait_for in intel_drv.h
- * This is NOT safe for use in interrupt context.
- *
- * Note that it's important that we check the condition again after having
- * timed out, since the timeout could be due to preemption or similar and
- * we've never had a chance to check the condition before the timeout.
- */
-#define rk_wait_for(COND, MS) ({ \
- unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1; \
- int ret__ = 0; \
- while (!(COND)) { \
- if (time_after(jiffies, timeout__)) { \
- ret__ = (COND) ? 0 : -ETIMEDOUT; \
- break; \
- } \
- usleep_range(50, 100); \
- } \
- ret__; \
-})
-
/*
* The Rockchip rk3288 iommu uses a 2-level page table.
* The first level is the "Directory Table" (DT).
@@ -296,19 +291,21 @@ static void rk_iommu_base_command(void __iomem *base, u32 command)
{
writel(command, base + RK_MMU_COMMAND);
}
-static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova,
+static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova_start,
size_t size)
{
int i;
-
- dma_addr_t iova_end = iova + size;
+ dma_addr_t iova_end = iova_start + size;
/*
* TODO(djkurtz): Figure out when it is more efficient to shootdown the
* entire iotlb rather than iterate over individual iovas.
*/
- for (i = 0; i < iommu->num_mmu; i++)
- for (; iova < iova_end; iova += SPAGE_SIZE)
+ for (i = 0; i < iommu->num_mmu; i++) {
+ dma_addr_t iova;
+
+ for (iova = iova_start; iova < iova_end; iova += SPAGE_SIZE)
rk_iommu_write(iommu->bases[i], RK_MMU_ZAP_ONE_LINE, iova);
+ }
}
static bool rk_iommu_is_stall_active(struct rk_iommu *iommu)
@@ -335,9 +332,21 @@ static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu)
return enable;
}
+static bool rk_iommu_is_reset_done(struct rk_iommu *iommu)
+{
+ bool done = true;
+ int i;
+
+ for (i = 0; i < iommu->num_mmu; i++)
+ done &= rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0;
+
+ return done;
+}
+
static int rk_iommu_enable_stall(struct rk_iommu *iommu)
{
int ret, i;
+ bool val;
if (rk_iommu_is_stall_active(iommu))
return 0;
@@ -348,7 +357,9 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu)
rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL);
- ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1);
+ ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
+ val, RK_MMU_POLL_PERIOD_US,
+ RK_MMU_POLL_TIMEOUT_US);
if (ret)
for (i = 0; i < iommu->num_mmu; i++)
dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n",
@@ -360,13 +371,16 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu)
static int rk_iommu_disable_stall(struct rk_iommu *iommu)
{
int ret, i;
+ bool val;
if (!rk_iommu_is_stall_active(iommu))
return 0;
rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL);
- ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1);
+ ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
+ !val, RK_MMU_POLL_PERIOD_US,
+ RK_MMU_POLL_TIMEOUT_US);
if (ret)
for (i = 0; i < iommu->num_mmu; i++)
dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n",
@@ -378,13 +392,16 @@ static int rk_iommu_disable_stall(struct rk_iommu *iommu)
static int rk_iommu_enable_paging(struct rk_iommu *iommu)
{
int ret, i;
+ bool val;
if (rk_iommu_is_paging_enabled(iommu))
return 0;
rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING);
- ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1);
+ ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
+ val, RK_MMU_POLL_PERIOD_US,
+ RK_MMU_POLL_TIMEOUT_US);
if (ret)
for (i = 0; i < iommu->num_mmu; i++)
dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n",
@@ -396,13 +413,16 @@ static int rk_iommu_enable_paging(struct rk_iommu *iommu)
static int rk_iommu_disable_paging(struct rk_iommu *iommu)
{
int ret, i;
+ bool val;
if (!rk_iommu_is_paging_enabled(iommu))
return 0;
rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING);
- ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1);
+ ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
+ !val, RK_MMU_POLL_PERIOD_US,
+ RK_MMU_POLL_TIMEOUT_US);
if (ret)
for (i = 0; i < iommu->num_mmu; i++)
dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n",
@@ -415,6 +435,7 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu)
{
int ret, i;
u32 dte_addr;
+ bool val;
if (iommu->reset_disabled)
return 0;
@@ -435,13 +456,12 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu)
rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET);
- for (i = 0; i < iommu->num_mmu; i++) {
- ret = rk_wait_for(rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0x00000000,
- FORCE_RESET_TIMEOUT);
- if (ret) {
- dev_err(iommu->dev, "FORCE_RESET command timed out\n");
- return ret;
- }
+ ret = readx_poll_timeout(rk_iommu_is_reset_done, iommu, val,
+ val, RK_MMU_FORCE_RESET_TIMEOUT_US,
+ RK_MMU_POLL_TIMEOUT_US);
+ if (ret) {
+ dev_err(iommu->dev, "FORCE_RESET command timed out\n");
+ return ret;
}
return 0;
@@ -503,6 +523,12 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
irqreturn_t ret = IRQ_NONE;
int i;
+ if (WARN_ON(!pm_runtime_get_if_in_use(iommu->dev)))
+ return 0;
+
+ if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)))
+ goto out;
+
for (i = 0; i < iommu->num_mmu; i++) {
int_status = rk_iommu_read(iommu->bases[i], RK_MMU_INT_STATUS);
if (int_status == 0)
@@ -549,6 +575,10 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
rk_iommu_write(iommu->bases[i], RK_MMU_INT_CLEAR, int_status);
}
+ clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+
+out:
+ pm_runtime_put(iommu->dev);
return ret;
}
@@ -590,8 +620,17 @@ static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain,
spin_lock_irqsave(&rk_domain->iommus_lock, flags);
list_for_each(pos, &rk_domain->iommus) {
struct rk_iommu *iommu;
+
iommu = list_entry(pos, struct rk_iommu, node);
- rk_iommu_zap_lines(iommu, iova, size);
+
+ /* Only zap TLBs of IOMMUs that are powered on. */
+ if (pm_runtime_get_if_in_use(iommu->dev)) {
+ WARN_ON(clk_bulk_enable(iommu->num_clocks,
+ iommu->clocks));
+ rk_iommu_zap_lines(iommu, iova, size);
+ clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+ pm_runtime_put(iommu->dev);
+ }
}
spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
}
@@ -608,7 +647,6 @@ static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
dma_addr_t iova)
{
- struct device *dev = &rk_domain->pdev->dev;
u32 *page_table, *dte_addr;
u32 dte_index, dte;
phys_addr_t pt_phys;
@@ -626,9 +664,9 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
if (!page_table)
return ERR_PTR(-ENOMEM);
- pt_dma = dma_map_single(dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
- if (dma_mapping_error(dev, pt_dma)) {
- dev_err(dev, "DMA mapping error while allocating page table\n");
+ pt_dma = dma_map_single(dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
+ if (dma_mapping_error(dma_dev, pt_dma)) {
+ dev_err(dma_dev, "DMA mapping error while allocating page table\n");
free_page((unsigned long)page_table);
return ERR_PTR(-ENOMEM);
}
@@ -790,52 +828,46 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
static struct rk_iommu *rk_iommu_from_dev(struct device *dev)
{
- struct iommu_group *group;
- struct device *iommu_dev;
- struct rk_iommu *rk_iommu;
+ struct rk_iommudata *data = dev->archdata.iommu;
- group = iommu_group_get(dev);
- if (!group)
- return NULL;
- iommu_dev = iommu_group_get_iommudata(group);
- rk_iommu = dev_get_drvdata(iommu_dev);
- iommu_group_put(group);
-
- return rk_iommu;
+ return data ? data->iommu : NULL;
}
-static int rk_iommu_attach_device(struct iommu_domain *domain,
- struct device *dev)
+/* Must be called with iommu powered on and attached */
+static void rk_iommu_disable(struct rk_iommu *iommu)
{
- struct rk_iommu *iommu;
+ int i;
+
+ /* Ignore error while disabling, just keep going */
+ WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks));
+ rk_iommu_enable_stall(iommu);
+ rk_iommu_disable_paging(iommu);
+ for (i = 0; i < iommu->num_mmu; i++) {
+ rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0);
+ rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0);
+ }
+ rk_iommu_disable_stall(iommu);
+ clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+}
+
+/* Must be called with iommu powered on and attached */
+static int rk_iommu_enable(struct rk_iommu *iommu)
+{
+ struct iommu_domain *domain = iommu->domain;
struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
- unsigned long flags;
int ret, i;
- /*
- * Allow 'virtual devices' (e.g., drm) to attach to domain.
- * Such a device does not belong to an iommu group.
- */
- iommu = rk_iommu_from_dev(dev);
- if (!iommu)
- return 0;
+ ret = clk_bulk_enable(iommu->num_clocks, iommu->clocks);
+ if (ret)
+ return ret;
ret = rk_iommu_enable_stall(iommu);
if (ret)
- return ret;
+ goto out_disable_clocks;
ret = rk_iommu_force_reset(iommu);
if (ret)
- return ret;
-
- iommu->domain = domain;
-
- for (i = 0; i < iommu->num_irq; i++) {
- ret = devm_request_irq(iommu->dev, iommu->irq[i], rk_iommu_irq,
- IRQF_SHARED, dev_name(dev), iommu);
- if (ret)
- return ret;
- }
+ goto out_disable_stall;
for (i = 0; i < iommu->num_mmu; i++) {
rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
@@ -845,18 +877,12 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
}
ret = rk_iommu_enable_paging(iommu);
- if (ret)
- return ret;
- spin_lock_irqsave(&rk_domain->iommus_lock, flags);
- list_add_tail(&iommu->node, &rk_domain->iommus);
- spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
-
- dev_dbg(dev, "Attached to iommu domain\n");
-
+out_disable_stall:
rk_iommu_disable_stall(iommu);
-
- return 0;
+out_disable_clocks:
+ clk_bulk_disable(iommu->num_clocks, iommu->clocks);
+ return ret;
}
static void rk_iommu_detach_device(struct iommu_domain *domain,
@@ -865,60 +891,90 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
struct rk_iommu *iommu;
struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
unsigned long flags;
- int i;
/* Allow 'virtual devices' (eg drm) to detach from domain */
iommu = rk_iommu_from_dev(dev);
if (!iommu)
return;
+ dev_dbg(dev, "Detaching from iommu domain\n");
+
+ /* iommu already detached */
+ if (iommu->domain != domain)
+ return;
+
+ iommu->domain = NULL;
+
spin_lock_irqsave(&rk_domain->iommus_lock, flags);
list_del_init(&iommu->node);
spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
- /* Ignore error while disabling, just keep going */
- rk_iommu_enable_stall(iommu);
- rk_iommu_disable_paging(iommu);
- for (i = 0; i < iommu->num_mmu; i++) {
- rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0);
- rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0);
+ if (pm_runtime_get_if_in_use(iommu->dev)) {
+ rk_iommu_disable(iommu);
+ pm_runtime_put(iommu->dev);
}
- rk_iommu_disable_stall(iommu);
+}
- for (i = 0; i < iommu->num_irq; i++)
- devm_free_irq(iommu->dev, iommu->irq[i], iommu);
+static int rk_iommu_attach_device(struct iommu_domain *domain,
+ struct device *dev)
+{
+ struct rk_iommu *iommu;
+ struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
+ unsigned long flags;
+ int ret;
- iommu->domain = NULL;
+ /*
+ * Allow 'virtual devices' (e.g., drm) to attach to domain.
+ * Such a device does not belong to an iommu group.
+ */
+ iommu = rk_iommu_from_dev(dev);
+ if (!iommu)
+ return 0;
- dev_dbg(dev, "Detached from iommu domain\n");
+ dev_dbg(dev, "Attaching to iommu domain\n");
+
+ /* iommu already attached */
+ if (iommu->domain == domain)
+ return 0;
+
+ if (iommu->domain)
+ rk_iommu_detach_device(iommu->domain, dev);
+
+ iommu->domain = domain;
+
+ spin_lock_irqsave(&rk_domain->iommus_lock, flags);
+ list_add_tail(&iommu->node, &rk_domain->iommus);
+ spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
+
+ if (!pm_runtime_get_if_in_use(iommu->dev))
+ return 0;
+
+ ret = rk_iommu_enable(iommu);
+ if (ret)
+ rk_iommu_detach_device(iommu->domain, dev);
+
+ pm_runtime_put(iommu->dev);
+
+ return ret;
}
static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
{
struct rk_iommu_domain *rk_domain;
- struct platform_device *pdev;
- struct device *iommu_dev;
if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
return NULL;
- /* Register a pdev per domain, so DMA API can base on this *dev
- * even some virtual master doesn't have an iommu slave
- */
- pdev = platform_device_register_simple("rk_iommu_domain",
- PLATFORM_DEVID_AUTO, NULL, 0);
- if (IS_ERR(pdev))
+ if (!dma_dev)
return NULL;
- rk_domain = devm_kzalloc(&pdev->dev, sizeof(*rk_domain), GFP_KERNEL);
+ rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL);
if (!rk_domain)
- goto err_unreg_pdev;
-
- rk_domain->pdev = pdev;
+ return NULL;
if (type == IOMMU_DOMAIN_DMA &&
iommu_get_dma_cookie(&rk_domain->domain))
- goto err_unreg_pdev;
+ return NULL;
/*
* rk32xx iommus use a 2 level pagetable.
@@ -929,11 +985,10 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
if (!rk_domain->dt)
goto err_put_cookie;
- iommu_dev = &pdev->dev;
- rk_domain->dt_dma = dma_map_single(iommu_dev, rk_domain->dt,
+ rk_domain->dt_dma = dma_map_single(dma_dev, rk_domain->dt,
SPAGE_SIZE, DMA_TO_DEVICE);
- if (dma_mapping_error(iommu_dev, rk_domain->dt_dma)) {
- dev_err(iommu_dev, "DMA map error for DT\n");
+ if (dma_mapping_error(dma_dev, rk_domain->dt_dma)) {
+ dev_err(dma_dev, "DMA map error for DT\n");
goto err_free_dt;
}
@@ -954,8 +1009,6 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
err_put_cookie:
if (type == IOMMU_DOMAIN_DMA)
iommu_put_dma_cookie(&rk_domain->domain);
-err_unreg_pdev:
- platform_device_unregister(pdev);
return NULL;
}
@@ -972,128 +1025,84 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
if (rk_dte_is_pt_valid(dte)) {
phys_addr_t pt_phys = rk_dte_pt_address(dte);
u32 *page_table = phys_to_virt(pt_phys);
- dma_unmap_single(&rk_domain->pdev->dev, pt_phys,
+ dma_unmap_single(dma_dev, pt_phys,
SPAGE_SIZE, DMA_TO_DEVICE);
free_page((unsigned long)page_table);
}
}
- dma_unmap_single(&rk_domain->pdev->dev, rk_domain->dt_dma,
+ dma_unmap_single(dma_dev, rk_domain->dt_dma,
SPAGE_SIZE, DMA_TO_DEVICE);
free_page((unsigned long)rk_domain->dt);
if (domain->type == IOMMU_DOMAIN_DMA)
iommu_put_dma_cookie(&rk_domain->domain);
-
- platform_device_unregister(rk_domain->pdev);
-}
-
-static bool rk_iommu_is_dev_iommu_master(struct device *dev)
-{
- struct device_node *np = dev->of_node;
- int ret;
-
- /*
- * An iommu master has an iommus property containing a list of phandles
- * to iommu nodes, each with an #iommu-cells property with value 0.
- */
- ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells");
- return (ret > 0);
-}
-
-static int rk_iommu_group_set_iommudata(struct iommu_group *group,
- struct device *dev)
-{
- struct device_node *np = dev->of_node;
- struct platform_device *pd;
- int ret;
- struct of_phandle_args args;
-
- /*
- * An iommu master has an iommus property containing a list of phandles
- * to iommu nodes, each with an #iommu-cells property with value 0.
- */
- ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0,
- &args);
- if (ret) {
- dev_err(dev, "of_parse_phandle_with_args(%pOF) => %d\n",
- np, ret);
- return ret;
- }
- if (args.args_count != 0) {
- dev_err(dev, "incorrect number of iommu params found for %pOF (found %d, expected 0)\n",
- args.np, args.args_count);
- return -EINVAL;
- }
-
- pd = of_find_device_by_node(args.np);
- of_node_put(args.np);
- if (!pd) {
- dev_err(dev, "iommu %pOF not found\n", args.np);
- return -EPROBE_DEFER;
- }
-
- /* TODO(djkurtz): handle multiple slave iommus for a single master */
- iommu_group_set_iommudata(group, &pd->dev, NULL);
-
- return 0;
}
static int rk_iommu_add_device(struct device *dev)
{
struct iommu_group *group;
struct rk_iommu *iommu;
- int ret;
+ struct rk_iommudata *data;
- if (!rk_iommu_is_dev_iommu_master(dev))
+ data = dev->archdata.iommu;
+ if (!data)
return -ENODEV;
- group = iommu_group_get(dev);
- if (!group) {
- group = iommu_group_alloc();
- if (IS_ERR(group)) {
- dev_err(dev, "Failed to allocate IOMMU group\n");
- return PTR_ERR(group);
- }
- }
-
- ret = iommu_group_add_device(group, dev);
- if (ret)
- goto err_put_group;
-
- ret = rk_iommu_group_set_iommudata(group, dev);
- if (ret)
- goto err_remove_device;
-
iommu = rk_iommu_from_dev(dev);
- if (iommu)
- iommu_device_link(&iommu->iommu, dev);
+ group = iommu_group_get_for_dev(dev);
+ if (IS_ERR(group))
+ return PTR_ERR(group);
iommu_group_put(group);
+ iommu_device_link(&iommu->iommu, dev);
+ data->link = device_link_add(dev, iommu->dev, DL_FLAG_PM_RUNTIME);
+
return 0;
-
-err_remove_device:
- iommu_group_remove_device(dev);
-err_put_group:
- iommu_group_put(group);
- return ret;
}
static void rk_iommu_remove_device(struct device *dev)
{
struct rk_iommu *iommu;
-
- if (!rk_iommu_is_dev_iommu_master(dev))
- return;
+ struct rk_iommudata *data = dev->archdata.iommu;
iommu = rk_iommu_from_dev(dev);
- if (iommu)
- iommu_device_unlink(&iommu->iommu, dev);
+ device_link_del(data->link);
+ iommu_device_unlink(&iommu->iommu, dev);
iommu_group_remove_device(dev);
}
+static struct iommu_group *rk_iommu_device_group(struct device *dev)
+{
+ struct rk_iommu *iommu;
+
+ iommu = rk_iommu_from_dev(dev);
+
+ return iommu_group_ref_get(iommu->group);
+}
+
+static int rk_iommu_of_xlate(struct device *dev,
+ struct of_phandle_args *args)
+{
+ struct platform_device *iommu_dev;
+ struct rk_iommudata *data;
+
+ data = devm_kzalloc(dma_dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ iommu_dev = of_find_device_by_node(args->np);
+
+ data->iommu = platform_get_drvdata(iommu_dev);
+ dev->archdata.iommu = data;
+
+ of_dev_put(iommu_dev);
+
+ return 0;
+}
+
static const struct iommu_ops rk_iommu_ops = {
.domain_alloc = rk_iommu_domain_alloc,
.domain_free = rk_iommu_domain_free,
@@ -1105,31 +1114,9 @@ static const struct iommu_ops rk_iommu_ops = {
.add_device = rk_iommu_add_device,
.remove_device = rk_iommu_remove_device,
.iova_to_phys = rk_iommu_iova_to_phys,
+ .device_group = rk_iommu_device_group,
.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
-};
-
-static int rk_iommu_domain_probe(struct platform_device *pdev)
-{
- struct device *dev = &pdev->dev;
-
- dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL);
- if (!dev->dma_parms)
- return -ENOMEM;
-
- /* Set dma_ops for dev, otherwise it would be dummy_dma_ops */
- arch_setup_dma_ops(dev, 0, DMA_BIT_MASK(32), NULL, false);
-
- dma_set_max_seg_size(dev, DMA_BIT_MASK(32));
- dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
-
- return 0;
-}
-
-static struct platform_driver rk_iommu_domain_driver = {
- .probe = rk_iommu_domain_probe,
- .driver = {
- .name = "rk_iommu_domain",
- },
+ .of_xlate = rk_iommu_of_xlate,
};
static int rk_iommu_probe(struct platform_device *pdev)
@@ -1138,7 +1125,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
struct rk_iommu *iommu;
struct resource *res;
int num_res = pdev->num_resources;
- int err, i;
+ int err, i, irq;
iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
if (!iommu)
@@ -1165,50 +1152,108 @@ static int rk_iommu_probe(struct platform_device *pdev)
if (iommu->num_mmu == 0)
return PTR_ERR(iommu->bases[0]);
- iommu->num_irq = platform_irq_count(pdev);
- if (iommu->num_irq < 0)
- return iommu->num_irq;
- if (iommu->num_irq == 0)
- return -ENXIO;
+ i = 0;
+ while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) {
+ if (irq < 0)
+ return irq;
- iommu->irq = devm_kcalloc(dev, iommu->num_irq, sizeof(*iommu->irq),
- GFP_KERNEL);
- if (!iommu->irq)
- return -ENOMEM;
-
- for (i = 0; i < iommu->num_irq; i++) {
- iommu->irq[i] = platform_get_irq(pdev, i);
- if (iommu->irq[i] < 0) {
- dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq[i]);
- return -ENXIO;
- }
+ err = devm_request_irq(iommu->dev, irq, rk_iommu_irq,
+ IRQF_SHARED, dev_name(dev), iommu);
+ if (err)
+ return err;
}
iommu->reset_disabled = device_property_read_bool(dev,
"rockchip,disable-mmu-reset");
- err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
+ iommu->num_clocks = ARRAY_SIZE(rk_iommu_clocks);
+ iommu->clocks = devm_kcalloc(iommu->dev, iommu->num_clocks,
+ sizeof(*iommu->clocks), GFP_KERNEL);
+ if (!iommu->clocks)
+ return -ENOMEM;
+
+ for (i = 0; i < iommu->num_clocks; ++i)
+ iommu->clocks[i].id = rk_iommu_clocks[i];
+
+ err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
if (err)
return err;
- iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops);
- err = iommu_device_register(&iommu->iommu);
+ err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
+ if (err)
+ return err;
+ iommu->group = iommu_group_alloc();
+ if (IS_ERR(iommu->group)) {
+ err = PTR_ERR(iommu->group);
+ goto err_unprepare_clocks;
+ }
+
+ err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
+ if (err)
+ goto err_put_group;
+
+ iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops);
+ iommu_device_set_fwnode(&iommu->iommu, &dev->of_node->fwnode);
+
+ err = iommu_device_register(&iommu->iommu);
+ if (err)
+ goto err_remove_sysfs;
+
+ /*
+ * Use the first registered IOMMU device for domain to use with DMA
+ * API, since a domain might not physically correspond to a single
+ * IOMMU device..
+ */
+ if (!dma_dev)
+ dma_dev = &pdev->dev;
+
+ bus_set_iommu(&platform_bus_type, &rk_iommu_ops);
+
+ pm_runtime_enable(dev);
+
+ return 0;
+err_remove_sysfs:
+ iommu_device_sysfs_remove(&iommu->iommu);
+err_put_group:
+ iommu_group_put(iommu->group);
+err_unprepare_clocks:
+ clk_bulk_unprepare(iommu->num_clocks, iommu->clocks);
return err;
}
-static int rk_iommu_remove(struct platform_device *pdev)
+static void rk_iommu_shutdown(struct platform_device *pdev)
{
- struct rk_iommu *iommu = platform_get_drvdata(pdev);
+ pm_runtime_force_suspend(&pdev->dev);
+}
- if (iommu) {
- iommu_device_sysfs_remove(&iommu->iommu);
- iommu_device_unregister(&iommu->iommu);
- }
+static int __maybe_unused rk_iommu_suspend(struct device *dev)
+{
+ struct rk_iommu *iommu = dev_get_drvdata(dev);
+ if (!iommu->domain)
+ return 0;
+
+ rk_iommu_disable(iommu);
return 0;
}
+static int __maybe_unused rk_iommu_resume(struct device *dev)
+{
+ struct rk_iommu *iommu = dev_get_drvdata(dev);
+
+ if (!iommu->domain)
+ return 0;
+
+ return rk_iommu_enable(iommu);
+}
+
+static const struct dev_pm_ops rk_iommu_pm_ops = {
+ SET_RUNTIME_PM_OPS(rk_iommu_suspend, rk_iommu_resume, NULL)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
+};
+
static const struct of_device_id rk_iommu_dt_ids[] = {
{ .compatible = "rockchip,iommu" },
{ /* sentinel */ }
@@ -1217,45 +1262,22 @@ MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids);
static struct platform_driver rk_iommu_driver = {
.probe = rk_iommu_probe,
- .remove = rk_iommu_remove,
+ .shutdown = rk_iommu_shutdown,
.driver = {
.name = "rk_iommu",
.of_match_table = rk_iommu_dt_ids,
+ .pm = &rk_iommu_pm_ops,
+ .suppress_bind_attrs = true,
},
};
static int __init rk_iommu_init(void)
{
- struct device_node *np;
- int ret;
-
- np = of_find_matching_node(NULL, rk_iommu_dt_ids);
- if (!np)
- return 0;
-
- of_node_put(np);
-
- ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops);
- if (ret)
- return ret;
-
- ret = platform_driver_register(&rk_iommu_domain_driver);
- if (ret)
- return ret;
-
- ret = platform_driver_register(&rk_iommu_driver);
- if (ret)
- platform_driver_unregister(&rk_iommu_domain_driver);
- return ret;
+ return platform_driver_register(&rk_iommu_driver);
}
-static void __exit rk_iommu_exit(void)
-{
- platform_driver_unregister(&rk_iommu_driver);
- platform_driver_unregister(&rk_iommu_domain_driver);
-}
-
subsys_initcall(rk_iommu_init);
-module_exit(rk_iommu_exit);
+
+IOMMU_OF_DECLARE(rk_iommu_of, "rockchip,iommu");
MODULE_DESCRIPTION("IOMMU API for Rockchip");
MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>");
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 2cbb19c..b84bbcd 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3451,7 +3451,8 @@ static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header,
return -ENOMEM;
}
- err = iort_register_domain_token(its_entry->translation_id, dom_handle);
+ err = iort_register_domain_token(its_entry->translation_id, res.start,
+ dom_handle);
if (err) {
pr_err("ITS@%pa: Unable to register GICv3 ITS domain token (ITS ID %d) to IORT\n",
&res.start, its_entry->translation_id);
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 2f7a292..38cd77b 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -26,7 +26,8 @@
#define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL)
#define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL)
-int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node);
+int iort_register_domain_token(int trans_id, phys_addr_t base,
+ struct fwnode_handle *fw_node);
void iort_deregister_domain_token(int trans_id);
struct fwnode_handle *iort_find_domain_token(int trans_id);
#ifdef CONFIG_ACPI_IORT
@@ -38,6 +39,7 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
/* IOMMU interface */
void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
const struct iommu_ops *iort_iommu_configure(struct device *dev);
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
#else
static inline void acpi_iort_init(void) { }
static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
@@ -52,6 +54,9 @@ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
static inline const struct iommu_ops *iort_iommu_configure(
struct device *dev)
{ return NULL; }
+static inline
+int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
+{ return 0; }
#endif
#endif /* __ACPI_IORT_H__ */
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 8dad3dd..ef169d6 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -209,12 +209,12 @@
#define DMA_FECTL_IM (((u32)1) << 31)
/* FSTS_REG */
-#define DMA_FSTS_PPF ((u32)2)
-#define DMA_FSTS_PFO ((u32)1)
-#define DMA_FSTS_IQE (1 << 4)
-#define DMA_FSTS_ICE (1 << 5)
-#define DMA_FSTS_ITE (1 << 6)
-#define DMA_FSTS_PRO (1 << 7)
+#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */
+#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */
+#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */
+#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */
+#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */
+#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */
#define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff)
/* FRCD_REG, 32 bits access */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 41b8c57..19938ee 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -465,23 +465,23 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
return -ENODEV;
}
-static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
- size_t size)
+static inline size_t iommu_unmap(struct iommu_domain *domain,
+ unsigned long iova, size_t size)
{
- return -ENODEV;
+ return 0;
}
-static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova,
- int gfp_order)
+static inline size_t iommu_unmap_fast(struct iommu_domain *domain,
+ unsigned long iova, int gfp_order)
{
- return -ENODEV;
+ return 0;
}
static inline size_t iommu_map_sg(struct iommu_domain *domain,
unsigned long iova, struct scatterlist *sg,
unsigned int nents, int prot)
{
- return -ENODEV;
+ return 0;
}
static inline void iommu_flush_tlb_all(struct iommu_domain *domain)