Merge branches 'arm/rockchip', 'arm/exynos', 'arm/smmu', 'x86/vt-d', 'x86/amd', 'default-domains' and 'core' into next
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
new file mode 100644
index 0000000..c03eec1
--- /dev/null
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
@@ -0,0 +1,37 @@
+* ARM SMMUv3 Architecture Implementation
+
+The SMMUv3 architecture is a significant deparature from previous
+revisions, replacing the MMIO register interface with in-memory command
+and event queues and adding support for the ATS and PRI components of
+the PCIe specification.
+
+** SMMUv3 required properties:
+
+- compatible : Should include:
+
+ * "arm,smmu-v3" for any SMMUv3 compliant
+ implementation. This entry should be last in the
+ compatible list.
+
+- reg : Base address and size of the SMMU.
+
+- interrupts : Non-secure interrupt list describing the wired
+ interrupt sources corresponding to entries in
+ interrupt-names. If no wired interrupts are
+ present then this property may be omitted.
+
+- interrupt-names : When the interrupts property is present, should
+ include the following:
+ * "eventq" - Event Queue not empty
+ * "priq" - PRI Queue not empty
+ * "cmdq-sync" - CMD_SYNC complete
+ * "gerror" - Global Error activated
+
+** SMMUv3 optional properties:
+
+- dma-coherent : Present if DMA operations made by the SMMU (page
+ table walks, stream table accesses etc) are cache
+ coherent with the CPU.
+
+ NOTE: this only applies to the SMMU itself, not
+ masters connected upstream of the SMMU.
diff --git a/MAINTAINERS b/MAINTAINERS
index d8afd29..82a8de8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1634,11 +1634,12 @@
F: drivers/mmc/host/sdhci-of-arasan.c
F: drivers/edac/synopsys_edac.c
-ARM SMMU DRIVER
+ARM SMMU DRIVERS
M: Will Deacon <will.deacon@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: drivers/iommu/arm-smmu.c
+F: drivers/iommu/arm-smmu-v3.c
F: drivers/iommu/io-pgtable-arm.c
ARM64 PORT (AARCH64 ARCHITECTURE)
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 1ae4e54..40f37a2 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -339,6 +339,7 @@
Enables bits of IOMMU API required by VFIO. The iommu_ops
is not implemented as it is not necessary for VFIO.
+# ARM IOMMU support
config ARM_SMMU
bool "ARM Ltd. System MMU (SMMU) Support"
depends on (ARM64 || ARM) && MMU
@@ -352,4 +353,16 @@
Say Y here if your SoC includes an IOMMU device implementing
the ARM SMMU architecture.
+config ARM_SMMU_V3
+ bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
+ depends on ARM64 && PCI
+ select IOMMU_API
+ select IOMMU_IO_PGTABLE_LPAE
+ help
+ Support for implementations of the ARM System MMU architecture
+ version 3 providing translation support to a PCIe root complex.
+
+ Say Y here if your system includes an IOMMU device implementing
+ the ARM SMMUv3 architecture.
+
endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 080ffab..c6dcc51 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -9,6 +9,7 @@
obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
+obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e1c7e9e..c5677ed 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -64,10 +64,6 @@
static DEFINE_RWLOCK(amd_iommu_devtable_lock);
-/* A list of preallocated protection domains */
-static LIST_HEAD(iommu_pd_list);
-static DEFINE_SPINLOCK(iommu_pd_list_lock);
-
/* List of all available dev_data structures */
static LIST_HEAD(dev_data_list);
static DEFINE_SPINLOCK(dev_data_list_lock);
@@ -119,7 +115,7 @@
struct kmem_cache *amd_iommu_irq_cache;
static void update_domain(struct protection_domain *domain);
-static int __init alloc_passthrough_domain(void);
+static int alloc_passthrough_domain(void);
/****************************************************************************
*
@@ -234,31 +230,38 @@
}
/*
- * In this function the list of preallocated protection domains is traversed to
- * find the domain for a specific device
+ * This function actually applies the mapping to the page table of the
+ * dma_ops domain.
*/
-static struct dma_ops_domain *find_protection_domain(u16 devid)
+static void alloc_unity_mapping(struct dma_ops_domain *dma_dom,
+ struct unity_map_entry *e)
{
- struct dma_ops_domain *entry, *ret = NULL;
- unsigned long flags;
- u16 alias = amd_iommu_alias_table[devid];
+ u64 addr;
- if (list_empty(&iommu_pd_list))
- return NULL;
-
- spin_lock_irqsave(&iommu_pd_list_lock, flags);
-
- list_for_each_entry(entry, &iommu_pd_list, list) {
- if (entry->target_dev == devid ||
- entry->target_dev == alias) {
- ret = entry;
- break;
- }
+ for (addr = e->address_start; addr < e->address_end;
+ addr += PAGE_SIZE) {
+ if (addr < dma_dom->aperture_size)
+ __set_bit(addr >> PAGE_SHIFT,
+ dma_dom->aperture[0]->bitmap);
}
+}
- spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+/*
+ * Inits the unity mappings required for a specific device
+ */
+static void init_unity_mappings_for_device(struct device *dev,
+ struct dma_ops_domain *dma_dom)
+{
+ struct unity_map_entry *e;
+ u16 devid;
- return ret;
+ devid = get_device_id(dev);
+
+ list_for_each_entry(e, &amd_iommu_unity_map, list) {
+ if (!(devid >= e->devid_start && devid <= e->devid_end))
+ continue;
+ alloc_unity_mapping(dma_dom, e);
+ }
}
/*
@@ -290,11 +293,23 @@
static void init_iommu_group(struct device *dev)
{
+ struct dma_ops_domain *dma_domain;
+ struct iommu_domain *domain;
struct iommu_group *group;
group = iommu_group_get_for_dev(dev);
- if (!IS_ERR(group))
- iommu_group_put(group);
+ if (IS_ERR(group))
+ return;
+
+ domain = iommu_group_default_domain(group);
+ if (!domain)
+ goto out;
+
+ dma_domain = to_pdomain(domain)->priv;
+
+ init_unity_mappings_for_device(dev, dma_domain);
+out:
+ iommu_group_put(group);
}
static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -434,64 +449,15 @@
/* Unlink from alias, it may change if another device is re-plugged */
dev_data->alias_data = NULL;
+ /* Remove dma-ops */
+ dev->archdata.dma_ops = NULL;
+
/*
* We keep dev_data around for unplugged devices and reuse it when the
* device is re-plugged - not doing so would introduce a ton of races.
*/
}
-void __init amd_iommu_uninit_devices(void)
-{
- struct iommu_dev_data *dev_data, *n;
- struct pci_dev *pdev = NULL;
-
- for_each_pci_dev(pdev) {
-
- if (!check_device(&pdev->dev))
- continue;
-
- iommu_uninit_device(&pdev->dev);
- }
-
- /* Free all of our dev_data structures */
- list_for_each_entry_safe(dev_data, n, &dev_data_list, dev_data_list)
- free_dev_data(dev_data);
-}
-
-int __init amd_iommu_init_devices(void)
-{
- struct pci_dev *pdev = NULL;
- int ret = 0;
-
- for_each_pci_dev(pdev) {
-
- if (!check_device(&pdev->dev))
- continue;
-
- ret = iommu_init_device(&pdev->dev);
- if (ret == -ENOTSUPP)
- iommu_ignore_device(&pdev->dev);
- else if (ret)
- goto out_free;
- }
-
- /*
- * Initialize IOMMU groups only after iommu_init_device() has
- * had a chance to populate any IVRS defined aliases.
- */
- for_each_pci_dev(pdev) {
- if (check_device(&pdev->dev))
- init_iommu_group(&pdev->dev);
- }
-
- return 0;
-
-out_free:
-
- amd_iommu_uninit_devices();
-
- return ret;
-}
#ifdef CONFIG_AMD_IOMMU_STATS
/*
@@ -1463,94 +1429,6 @@
return unmapped;
}
-/*
- * This function checks if a specific unity mapping entry is needed for
- * this specific IOMMU.
- */
-static int iommu_for_unity_map(struct amd_iommu *iommu,
- struct unity_map_entry *entry)
-{
- u16 bdf, i;
-
- for (i = entry->devid_start; i <= entry->devid_end; ++i) {
- bdf = amd_iommu_alias_table[i];
- if (amd_iommu_rlookup_table[bdf] == iommu)
- return 1;
- }
-
- return 0;
-}
-
-/*
- * This function actually applies the mapping to the page table of the
- * dma_ops domain.
- */
-static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
- struct unity_map_entry *e)
-{
- u64 addr;
- int ret;
-
- for (addr = e->address_start; addr < e->address_end;
- addr += PAGE_SIZE) {
- ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot,
- PAGE_SIZE);
- if (ret)
- return ret;
- /*
- * if unity mapping is in aperture range mark the page
- * as allocated in the aperture
- */
- if (addr < dma_dom->aperture_size)
- __set_bit(addr >> PAGE_SHIFT,
- dma_dom->aperture[0]->bitmap);
- }
-
- return 0;
-}
-
-/*
- * Init the unity mappings for a specific IOMMU in the system
- *
- * Basically iterates over all unity mapping entries and applies them to
- * the default domain DMA of that IOMMU if necessary.
- */
-static int iommu_init_unity_mappings(struct amd_iommu *iommu)
-{
- struct unity_map_entry *entry;
- int ret;
-
- list_for_each_entry(entry, &amd_iommu_unity_map, list) {
- if (!iommu_for_unity_map(iommu, entry))
- continue;
- ret = dma_ops_unity_map(iommu->default_dom, entry);
- if (ret)
- return ret;
- }
-
- return 0;
-}
-
-/*
- * Inits the unity mappings required for a specific device
- */
-static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
- u16 devid)
-{
- struct unity_map_entry *e;
- int ret;
-
- list_for_each_entry(e, &amd_iommu_unity_map, list) {
- if (!(devid >= e->devid_start && devid <= e->devid_end))
- continue;
- ret = dma_ops_unity_map(dma_dom, e);
- if (ret)
- return ret;
- }
-
- return 0;
-}
-
/****************************************************************************
*
* The next functions belong to the address allocator for the dma_ops
@@ -1704,14 +1582,16 @@
unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
int i = start >> APERTURE_RANGE_SHIFT;
- unsigned long boundary_size;
+ unsigned long boundary_size, mask;
unsigned long address = -1;
unsigned long limit;
next_bit >>= PAGE_SHIFT;
- boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
- PAGE_SIZE) >> PAGE_SHIFT;
+ mask = dma_get_seg_boundary(dev);
+
+ boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
+ 1UL << (BITS_PER_LONG - PAGE_SHIFT);
for (;i < max_index; ++i) {
unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
@@ -1869,9 +1749,15 @@
pt = (u64 *)__pt; \
\
for (i = 0; i < 512; ++i) { \
+ /* PTE present? */ \
if (!IOMMU_PTE_PRESENT(pt[i])) \
continue; \
\
+ /* Large PTE? */ \
+ if (PM_PTE_LEVEL(pt[i]) == 0 || \
+ PM_PTE_LEVEL(pt[i]) == 7) \
+ continue; \
+ \
p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
FN(p); \
} \
@@ -2008,7 +1894,6 @@
goto free_dma_dom;
dma_dom->need_flush = false;
- dma_dom->target_dev = 0xffff;
add_domain_to_list(&dma_dom->domain);
@@ -2373,110 +2258,67 @@
dev_data->ats.enabled = false;
}
-/*
- * Find out the protection domain structure for a given PCI device. This
- * will give us the pointer to the page table root for example.
- */
-static struct protection_domain *domain_for_device(struct device *dev)
+static int amd_iommu_add_device(struct device *dev)
{
struct iommu_dev_data *dev_data;
- struct protection_domain *dom = NULL;
- unsigned long flags;
-
- dev_data = get_dev_data(dev);
-
- if (dev_data->domain)
- return dev_data->domain;
-
- if (dev_data->alias_data != NULL) {
- struct iommu_dev_data *alias_data = dev_data->alias_data;
-
- read_lock_irqsave(&amd_iommu_devtable_lock, flags);
- if (alias_data->domain != NULL) {
- __attach_device(dev_data, alias_data->domain);
- dom = alias_data->domain;
- }
- read_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
- }
-
- return dom;
-}
-
-static int device_change_notifier(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct dma_ops_domain *dma_domain;
- struct protection_domain *domain;
- struct iommu_dev_data *dev_data;
- struct device *dev = data;
+ struct iommu_domain *domain;
struct amd_iommu *iommu;
- unsigned long flags;
u16 devid;
+ int ret;
- if (!check_device(dev))
+ if (!check_device(dev) || get_dev_data(dev))
return 0;
- devid = get_device_id(dev);
- iommu = amd_iommu_rlookup_table[devid];
- dev_data = get_dev_data(dev);
+ devid = get_device_id(dev);
+ iommu = amd_iommu_rlookup_table[devid];
- switch (action) {
- case BUS_NOTIFY_ADD_DEVICE:
+ ret = iommu_init_device(dev);
+ if (ret) {
+ if (ret != -ENOTSUPP)
+ pr_err("Failed to initialize device %s - trying to proceed anyway\n",
+ dev_name(dev));
- iommu_init_device(dev);
- init_iommu_group(dev);
-
- /*
- * dev_data is still NULL and
- * got initialized in iommu_init_device
- */
- dev_data = get_dev_data(dev);
-
- if (iommu_pass_through || dev_data->iommu_v2) {
- dev_data->passthrough = true;
- attach_device(dev, pt_domain);
- break;
- }
-
- domain = domain_for_device(dev);
-
- /* allocate a protection domain if a device is added */
- dma_domain = find_protection_domain(devid);
- if (!dma_domain) {
- dma_domain = dma_ops_domain_alloc();
- if (!dma_domain)
- goto out;
- dma_domain->target_dev = devid;
-
- spin_lock_irqsave(&iommu_pd_list_lock, flags);
- list_add_tail(&dma_domain->list, &iommu_pd_list);
- spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
- }
-
- dev->archdata.dma_ops = &amd_iommu_dma_ops;
-
- break;
- case BUS_NOTIFY_REMOVED_DEVICE:
-
- iommu_uninit_device(dev);
-
- default:
+ iommu_ignore_device(dev);
+ dev->archdata.dma_ops = &nommu_dma_ops;
goto out;
}
+ init_iommu_group(dev);
- iommu_completion_wait(iommu);
+ dev_data = get_dev_data(dev);
+
+ BUG_ON(!dev_data);
+
+ if (dev_data->iommu_v2)
+ iommu_request_dm_for_dev(dev);
+
+ /* Domains are initialized for this device - have a look what we ended up with */
+ domain = iommu_get_domain_for_dev(dev);
+ if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+ dev_data->passthrough = true;
+ dev->archdata.dma_ops = &nommu_dma_ops;
+ } else {
+ dev->archdata.dma_ops = &amd_iommu_dma_ops;
+ }
out:
+ iommu_completion_wait(iommu);
+
return 0;
}
-static struct notifier_block device_nb = {
- .notifier_call = device_change_notifier,
-};
-
-void amd_iommu_init_notifier(void)
+static void amd_iommu_remove_device(struct device *dev)
{
- bus_register_notifier(&pci_bus_type, &device_nb);
+ struct amd_iommu *iommu;
+ u16 devid;
+
+ if (!check_device(dev))
+ return;
+
+ devid = get_device_id(dev);
+ iommu = amd_iommu_rlookup_table[devid];
+
+ iommu_uninit_device(dev);
+ iommu_completion_wait(iommu);
}
/*****************************************************************************
@@ -2495,28 +2337,20 @@
static struct protection_domain *get_domain(struct device *dev)
{
struct protection_domain *domain;
- struct dma_ops_domain *dma_dom;
- u16 devid = get_device_id(dev);
+ struct iommu_domain *io_domain;
if (!check_device(dev))
return ERR_PTR(-EINVAL);
- domain = domain_for_device(dev);
- if (domain != NULL && !dma_ops_domain(domain))
+ io_domain = iommu_get_domain_for_dev(dev);
+ if (!io_domain)
+ return NULL;
+
+ domain = to_pdomain(io_domain);
+ if (!dma_ops_domain(domain))
return ERR_PTR(-EBUSY);
- if (domain != NULL)
- return domain;
-
- /* Device not bound yet - bind it */
- dma_dom = find_protection_domain(devid);
- if (!dma_dom)
- dma_dom = amd_iommu_rlookup_table[devid]->default_dom;
- attach_device(dev, &dma_dom->domain);
- DUMP_printk("Using protection domain %d for device %s\n",
- dma_dom->domain.id, dev_name(dev));
-
- return &dma_dom->domain;
+ return domain;
}
static void update_device_table(struct protection_domain *domain)
@@ -3012,54 +2846,6 @@
return check_device(dev);
}
-/*
- * The function for pre-allocating protection domains.
- *
- * If the driver core informs the DMA layer if a driver grabs a device
- * we don't need to preallocate the protection domains anymore.
- * For now we have to.
- */
-static void __init prealloc_protection_domains(void)
-{
- struct iommu_dev_data *dev_data;
- struct dma_ops_domain *dma_dom;
- struct pci_dev *dev = NULL;
- u16 devid;
-
- for_each_pci_dev(dev) {
-
- /* Do we handle this device? */
- if (!check_device(&dev->dev))
- continue;
-
- dev_data = get_dev_data(&dev->dev);
- if (!amd_iommu_force_isolation && dev_data->iommu_v2) {
- /* Make sure passthrough domain is allocated */
- alloc_passthrough_domain();
- dev_data->passthrough = true;
- attach_device(&dev->dev, pt_domain);
- pr_info("AMD-Vi: Using passthrough domain for device %s\n",
- dev_name(&dev->dev));
- }
-
- /* Is there already any domain for it? */
- if (domain_for_device(&dev->dev))
- continue;
-
- devid = get_device_id(&dev->dev);
-
- dma_dom = dma_ops_domain_alloc();
- if (!dma_dom)
- continue;
- init_unity_mappings_for_device(dma_dom, devid);
- dma_dom->target_dev = devid;
-
- attach_device(&dev->dev, &dma_dom->domain);
-
- list_add_tail(&dma_dom->list, &iommu_pd_list);
- }
-}
-
static struct dma_map_ops amd_iommu_dma_ops = {
.alloc = alloc_coherent,
.free = free_coherent,
@@ -3070,76 +2856,16 @@
.dma_supported = amd_iommu_dma_supported,
};
-static unsigned device_dma_ops_init(void)
+int __init amd_iommu_init_api(void)
{
- struct iommu_dev_data *dev_data;
- struct pci_dev *pdev = NULL;
- unsigned unhandled = 0;
-
- for_each_pci_dev(pdev) {
- if (!check_device(&pdev->dev)) {
-
- iommu_ignore_device(&pdev->dev);
-
- unhandled += 1;
- continue;
- }
-
- dev_data = get_dev_data(&pdev->dev);
-
- if (!dev_data->passthrough)
- pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
- else
- pdev->dev.archdata.dma_ops = &nommu_dma_ops;
- }
-
- return unhandled;
-}
-
-/*
- * The function which clues the AMD IOMMU driver into dma_ops.
- */
-
-void __init amd_iommu_init_api(void)
-{
- bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
+ return bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
}
int __init amd_iommu_init_dma_ops(void)
{
- struct amd_iommu *iommu;
- int ret, unhandled;
-
- /*
- * first allocate a default protection domain for every IOMMU we
- * found in the system. Devices not assigned to any other
- * protection domain will be assigned to the default one.
- */
- for_each_iommu(iommu) {
- iommu->default_dom = dma_ops_domain_alloc();
- if (iommu->default_dom == NULL)
- return -ENOMEM;
- iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
- ret = iommu_init_unity_mappings(iommu);
- if (ret)
- goto free_domains;
- }
-
- /*
- * Pre-allocate the protection domains for each device.
- */
- prealloc_protection_domains();
-
iommu_detected = 1;
swiotlb = 0;
- /* Make the driver finally visible to the drivers */
- unhandled = device_dma_ops_init();
- if (unhandled && max_pfn > MAX_DMA32_PFN) {
- /* There are unhandled devices - initialize swiotlb for them */
- swiotlb = 1;
- }
-
amd_iommu_stats_init();
if (amd_iommu_unmap_flush)
@@ -3148,14 +2874,6 @@
pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n");
return 0;
-
-free_domains:
-
- for_each_iommu(iommu) {
- dma_ops_domain_free(iommu->default_dom);
- }
-
- return ret;
}
/*****************************************************************************
@@ -3222,7 +2940,7 @@
return NULL;
}
-static int __init alloc_passthrough_domain(void)
+static int alloc_passthrough_domain(void)
{
if (pt_domain != NULL)
return 0;
@@ -3240,30 +2958,46 @@
static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
{
struct protection_domain *pdomain;
+ struct dma_ops_domain *dma_domain;
- /* We only support unmanaged domains for now */
- if (type != IOMMU_DOMAIN_UNMANAGED)
+ switch (type) {
+ case IOMMU_DOMAIN_UNMANAGED:
+ pdomain = protection_domain_alloc();
+ if (!pdomain)
+ return NULL;
+
+ pdomain->mode = PAGE_MODE_3_LEVEL;
+ pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!pdomain->pt_root) {
+ protection_domain_free(pdomain);
+ return NULL;
+ }
+
+ pdomain->domain.geometry.aperture_start = 0;
+ pdomain->domain.geometry.aperture_end = ~0ULL;
+ pdomain->domain.geometry.force_aperture = true;
+
+ break;
+ case IOMMU_DOMAIN_DMA:
+ dma_domain = dma_ops_domain_alloc();
+ if (!dma_domain) {
+ pr_err("AMD-Vi: Failed to allocate\n");
+ return NULL;
+ }
+ pdomain = &dma_domain->domain;
+ break;
+ case IOMMU_DOMAIN_IDENTITY:
+ pdomain = protection_domain_alloc();
+ if (!pdomain)
+ return NULL;
+
+ pdomain->mode = PAGE_MODE_NONE;
+ break;
+ default:
return NULL;
-
- pdomain = protection_domain_alloc();
- if (!pdomain)
- goto out_free;
-
- pdomain->mode = PAGE_MODE_3_LEVEL;
- pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
- if (!pdomain->pt_root)
- goto out_free;
-
- pdomain->domain.geometry.aperture_start = 0;
- pdomain->domain.geometry.aperture_end = ~0ULL;
- pdomain->domain.geometry.force_aperture = true;
+ }
return &pdomain->domain;
-
-out_free:
- protection_domain_free(pdomain);
-
- return NULL;
}
static void amd_iommu_domain_free(struct iommu_domain *dom)
@@ -3413,6 +3147,47 @@
return false;
}
+static void amd_iommu_get_dm_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct unity_map_entry *entry;
+ u16 devid;
+
+ devid = get_device_id(dev);
+
+ list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+ struct iommu_dm_region *region;
+
+ if (devid < entry->devid_start || devid > entry->devid_end)
+ continue;
+
+ region = kzalloc(sizeof(*region), GFP_KERNEL);
+ if (!region) {
+ pr_err("Out of memory allocating dm-regions for %s\n",
+ dev_name(dev));
+ return;
+ }
+
+ region->start = entry->address_start;
+ region->length = entry->address_end - entry->address_start;
+ if (entry->prot & IOMMU_PROT_IR)
+ region->prot |= IOMMU_READ;
+ if (entry->prot & IOMMU_PROT_IW)
+ region->prot |= IOMMU_WRITE;
+
+ list_add_tail(®ion->list, head);
+ }
+}
+
+static void amd_iommu_put_dm_regions(struct device *dev,
+ struct list_head *head)
+{
+ struct iommu_dm_region *entry, *next;
+
+ list_for_each_entry_safe(entry, next, head, list)
+ kfree(entry);
+}
+
static const struct iommu_ops amd_iommu_ops = {
.capable = amd_iommu_capable,
.domain_alloc = amd_iommu_domain_alloc,
@@ -3423,6 +3198,10 @@
.unmap = amd_iommu_unmap,
.map_sg = default_iommu_map_sg,
.iova_to_phys = amd_iommu_iova_to_phys,
+ .add_device = amd_iommu_add_device,
+ .remove_device = amd_iommu_remove_device,
+ .get_dm_regions = amd_iommu_get_dm_regions,
+ .put_dm_regions = amd_iommu_put_dm_regions,
.pgsize_bitmap = AMD_IOMMU_PGSIZES,
};
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 450ef50..dbac49c 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -226,6 +226,7 @@
static int amd_iommu_enable_interrupts(void);
static int __init iommu_go_to_state(enum iommu_init_state state);
+static void init_device_table_dma(void);
static inline void update_last_devid(u16 devid)
{
@@ -1385,9 +1386,15 @@
break;
}
- ret = amd_iommu_init_devices();
+ init_device_table_dma();
- print_iommu_info();
+ for_each_iommu(iommu)
+ iommu_flush_all_caches(iommu);
+
+ ret = amd_iommu_init_api();
+
+ if (!ret)
+ print_iommu_info();
return ret;
}
@@ -1825,8 +1832,6 @@
static void __init free_dma_resources(void)
{
- amd_iommu_uninit_devices();
-
free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
get_order(MAX_DOMAIN_ID/8));
@@ -2019,27 +2024,10 @@
static int amd_iommu_init_dma(void)
{
- struct amd_iommu *iommu;
- int ret;
-
if (iommu_pass_through)
- ret = amd_iommu_init_passthrough();
+ return amd_iommu_init_passthrough();
else
- ret = amd_iommu_init_dma_ops();
-
- if (ret)
- return ret;
-
- init_device_table_dma();
-
- for_each_iommu(iommu)
- iommu_flush_all_caches(iommu);
-
- amd_iommu_init_api();
-
- amd_iommu_init_notifier();
-
- return 0;
+ return amd_iommu_init_dma_ops();
}
/****************************************************************************
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 72b0fd4..9ed1c43 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -30,7 +30,7 @@
extern int amd_iommu_init_devices(void);
extern void amd_iommu_uninit_devices(void);
extern void amd_iommu_init_notifier(void);
-extern void amd_iommu_init_api(void);
+extern int amd_iommu_init_api(void);
/* Needed for interrupt remapping */
extern int amd_iommu_prepare(void);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 05030e5..bb56560 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -446,8 +446,6 @@
* Data container for a dma_ops specific protection domain
*/
struct dma_ops_domain {
- struct list_head list;
-
/* generic protection domain information */
struct protection_domain domain;
@@ -462,12 +460,6 @@
/* This will be set to true when TLB needs to be flushed */
bool need_flush;
-
- /*
- * if this is a preallocated domain, keep the device for which it was
- * preallocated in this variable
- */
- u16 target_dev;
};
/*
@@ -552,9 +544,6 @@
/* if one, we need to send a completion wait command */
bool need_sync;
- /* default dma_ops domain for that IOMMU */
- struct dma_ops_domain *default_dom;
-
/* IOMMU sysfs device */
struct device *iommu_dev;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
new file mode 100644
index 0000000..f141301
--- /dev/null
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -0,0 +1,2670 @@
+/*
+ * IOMMU API for ARM architected SMMUv3 implementations.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver is powered by bad coffee and bombay mix.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include "io-pgtable.h"
+
+/* MMIO registers */
+#define ARM_SMMU_IDR0 0x0
+#define IDR0_ST_LVL_SHIFT 27
+#define IDR0_ST_LVL_MASK 0x3
+#define IDR0_ST_LVL_2LVL (1 << IDR0_ST_LVL_SHIFT)
+#define IDR0_STALL_MODEL (3 << 24)
+#define IDR0_TTENDIAN_SHIFT 21
+#define IDR0_TTENDIAN_MASK 0x3
+#define IDR0_TTENDIAN_LE (2 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_BE (3 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_MIXED (0 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_CD2L (1 << 19)
+#define IDR0_VMID16 (1 << 18)
+#define IDR0_PRI (1 << 16)
+#define IDR0_SEV (1 << 14)
+#define IDR0_MSI (1 << 13)
+#define IDR0_ASID16 (1 << 12)
+#define IDR0_ATS (1 << 10)
+#define IDR0_HYP (1 << 9)
+#define IDR0_COHACC (1 << 4)
+#define IDR0_TTF_SHIFT 2
+#define IDR0_TTF_MASK 0x3
+#define IDR0_TTF_AARCH64 (2 << IDR0_TTF_SHIFT)
+#define IDR0_S1P (1 << 1)
+#define IDR0_S2P (1 << 0)
+
+#define ARM_SMMU_IDR1 0x4
+#define IDR1_TABLES_PRESET (1 << 30)
+#define IDR1_QUEUES_PRESET (1 << 29)
+#define IDR1_REL (1 << 28)
+#define IDR1_CMDQ_SHIFT 21
+#define IDR1_CMDQ_MASK 0x1f
+#define IDR1_EVTQ_SHIFT 16
+#define IDR1_EVTQ_MASK 0x1f
+#define IDR1_PRIQ_SHIFT 11
+#define IDR1_PRIQ_MASK 0x1f
+#define IDR1_SSID_SHIFT 6
+#define IDR1_SSID_MASK 0x1f
+#define IDR1_SID_SHIFT 0
+#define IDR1_SID_MASK 0x3f
+
+#define ARM_SMMU_IDR5 0x14
+#define IDR5_STALL_MAX_SHIFT 16
+#define IDR5_STALL_MAX_MASK 0xffff
+#define IDR5_GRAN64K (1 << 6)
+#define IDR5_GRAN16K (1 << 5)
+#define IDR5_GRAN4K (1 << 4)
+#define IDR5_OAS_SHIFT 0
+#define IDR5_OAS_MASK 0x7
+#define IDR5_OAS_32_BIT (0 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_36_BIT (1 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_40_BIT (2 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_42_BIT (3 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_44_BIT (4 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_48_BIT (5 << IDR5_OAS_SHIFT)
+
+#define ARM_SMMU_CR0 0x20
+#define CR0_CMDQEN (1 << 3)
+#define CR0_EVTQEN (1 << 2)
+#define CR0_PRIQEN (1 << 1)
+#define CR0_SMMUEN (1 << 0)
+
+#define ARM_SMMU_CR0ACK 0x24
+
+#define ARM_SMMU_CR1 0x28
+#define CR1_SH_NSH 0
+#define CR1_SH_OSH 2
+#define CR1_SH_ISH 3
+#define CR1_CACHE_NC 0
+#define CR1_CACHE_WB 1
+#define CR1_CACHE_WT 2
+#define CR1_TABLE_SH_SHIFT 10
+#define CR1_TABLE_OC_SHIFT 8
+#define CR1_TABLE_IC_SHIFT 6
+#define CR1_QUEUE_SH_SHIFT 4
+#define CR1_QUEUE_OC_SHIFT 2
+#define CR1_QUEUE_IC_SHIFT 0
+
+#define ARM_SMMU_CR2 0x2c
+#define CR2_PTM (1 << 2)
+#define CR2_RECINVSID (1 << 1)
+#define CR2_E2H (1 << 0)
+
+#define ARM_SMMU_IRQ_CTRL 0x50
+#define IRQ_CTRL_EVTQ_IRQEN (1 << 2)
+#define IRQ_CTRL_GERROR_IRQEN (1 << 0)
+
+#define ARM_SMMU_IRQ_CTRLACK 0x54
+
+#define ARM_SMMU_GERROR 0x60
+#define GERROR_SFM_ERR (1 << 8)
+#define GERROR_MSI_GERROR_ABT_ERR (1 << 7)
+#define GERROR_MSI_PRIQ_ABT_ERR (1 << 6)
+#define GERROR_MSI_EVTQ_ABT_ERR (1 << 5)
+#define GERROR_MSI_CMDQ_ABT_ERR (1 << 4)
+#define GERROR_PRIQ_ABT_ERR (1 << 3)
+#define GERROR_EVTQ_ABT_ERR (1 << 2)
+#define GERROR_CMDQ_ERR (1 << 0)
+#define GERROR_ERR_MASK 0xfd
+
+#define ARM_SMMU_GERRORN 0x64
+
+#define ARM_SMMU_GERROR_IRQ_CFG0 0x68
+#define ARM_SMMU_GERROR_IRQ_CFG1 0x70
+#define ARM_SMMU_GERROR_IRQ_CFG2 0x74
+
+#define ARM_SMMU_STRTAB_BASE 0x80
+#define STRTAB_BASE_RA (1UL << 62)
+#define STRTAB_BASE_ADDR_SHIFT 6
+#define STRTAB_BASE_ADDR_MASK 0x3ffffffffffUL
+
+#define ARM_SMMU_STRTAB_BASE_CFG 0x88
+#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT 0
+#define STRTAB_BASE_CFG_LOG2SIZE_MASK 0x3f
+#define STRTAB_BASE_CFG_SPLIT_SHIFT 6
+#define STRTAB_BASE_CFG_SPLIT_MASK 0x1f
+#define STRTAB_BASE_CFG_FMT_SHIFT 16
+#define STRTAB_BASE_CFG_FMT_MASK 0x3
+#define STRTAB_BASE_CFG_FMT_LINEAR (0 << STRTAB_BASE_CFG_FMT_SHIFT)
+#define STRTAB_BASE_CFG_FMT_2LVL (1 << STRTAB_BASE_CFG_FMT_SHIFT)
+
+#define ARM_SMMU_CMDQ_BASE 0x90
+#define ARM_SMMU_CMDQ_PROD 0x98
+#define ARM_SMMU_CMDQ_CONS 0x9c
+
+#define ARM_SMMU_EVTQ_BASE 0xa0
+#define ARM_SMMU_EVTQ_PROD 0x100a8
+#define ARM_SMMU_EVTQ_CONS 0x100ac
+#define ARM_SMMU_EVTQ_IRQ_CFG0 0xb0
+#define ARM_SMMU_EVTQ_IRQ_CFG1 0xb8
+#define ARM_SMMU_EVTQ_IRQ_CFG2 0xbc
+
+#define ARM_SMMU_PRIQ_BASE 0xc0
+#define ARM_SMMU_PRIQ_PROD 0x100c8
+#define ARM_SMMU_PRIQ_CONS 0x100cc
+#define ARM_SMMU_PRIQ_IRQ_CFG0 0xd0
+#define ARM_SMMU_PRIQ_IRQ_CFG1 0xd8
+#define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc
+
+/* Common MSI config fields */
+#define MSI_CFG0_SH_SHIFT 60
+#define MSI_CFG0_SH_NSH (0UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_OSH (2UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_ISH (3UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_MEMATTR_SHIFT 56
+#define MSI_CFG0_MEMATTR_DEVICE_nGnRE (0x1 << MSI_CFG0_MEMATTR_SHIFT)
+#define MSI_CFG0_ADDR_SHIFT 2
+#define MSI_CFG0_ADDR_MASK 0x3fffffffffffUL
+
+#define Q_IDX(q, p) ((p) & ((1 << (q)->max_n_shift) - 1))
+#define Q_WRP(q, p) ((p) & (1 << (q)->max_n_shift))
+#define Q_OVERFLOW_FLAG (1 << 31)
+#define Q_OVF(q, p) ((p) & Q_OVERFLOW_FLAG)
+#define Q_ENT(q, p) ((q)->base + \
+ Q_IDX(q, p) * (q)->ent_dwords)
+
+#define Q_BASE_RWA (1UL << 62)
+#define Q_BASE_ADDR_SHIFT 5
+#define Q_BASE_ADDR_MASK 0xfffffffffffUL
+#define Q_BASE_LOG2SIZE_SHIFT 0
+#define Q_BASE_LOG2SIZE_MASK 0x1fUL
+
+/*
+ * Stream table.
+ *
+ * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
+ * 2lvl: 8k L1 entries, 256 lazy entries per table (each table covers a PCI bus)
+ */
+#define STRTAB_L1_SZ_SHIFT 16
+#define STRTAB_SPLIT 8
+
+#define STRTAB_L1_DESC_DWORDS 1
+#define STRTAB_L1_DESC_SPAN_SHIFT 0
+#define STRTAB_L1_DESC_SPAN_MASK 0x1fUL
+#define STRTAB_L1_DESC_L2PTR_SHIFT 6
+#define STRTAB_L1_DESC_L2PTR_MASK 0x3ffffffffffUL
+
+#define STRTAB_STE_DWORDS 8
+#define STRTAB_STE_0_V (1UL << 0)
+#define STRTAB_STE_0_CFG_SHIFT 1
+#define STRTAB_STE_0_CFG_MASK 0x7UL
+#define STRTAB_STE_0_CFG_ABORT (0UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_BYPASS (4UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S1_TRANS (5UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S2_TRANS (6UL << STRTAB_STE_0_CFG_SHIFT)
+
+#define STRTAB_STE_0_S1FMT_SHIFT 4
+#define STRTAB_STE_0_S1FMT_LINEAR (0UL << STRTAB_STE_0_S1FMT_SHIFT)
+#define STRTAB_STE_0_S1CTXPTR_SHIFT 6
+#define STRTAB_STE_0_S1CTXPTR_MASK 0x3ffffffffffUL
+#define STRTAB_STE_0_S1CDMAX_SHIFT 59
+#define STRTAB_STE_0_S1CDMAX_MASK 0x1fUL
+
+#define STRTAB_STE_1_S1C_CACHE_NC 0UL
+#define STRTAB_STE_1_S1C_CACHE_WBRA 1UL
+#define STRTAB_STE_1_S1C_CACHE_WT 2UL
+#define STRTAB_STE_1_S1C_CACHE_WB 3UL
+#define STRTAB_STE_1_S1C_SH_NSH 0UL
+#define STRTAB_STE_1_S1C_SH_OSH 2UL
+#define STRTAB_STE_1_S1C_SH_ISH 3UL
+#define STRTAB_STE_1_S1CIR_SHIFT 2
+#define STRTAB_STE_1_S1COR_SHIFT 4
+#define STRTAB_STE_1_S1CSH_SHIFT 6
+
+#define STRTAB_STE_1_S1STALLD (1UL << 27)
+
+#define STRTAB_STE_1_EATS_ABT 0UL
+#define STRTAB_STE_1_EATS_TRANS 1UL
+#define STRTAB_STE_1_EATS_S1CHK 2UL
+#define STRTAB_STE_1_EATS_SHIFT 28
+
+#define STRTAB_STE_1_STRW_NSEL1 0UL
+#define STRTAB_STE_1_STRW_EL2 2UL
+#define STRTAB_STE_1_STRW_SHIFT 30
+
+#define STRTAB_STE_2_S2VMID_SHIFT 0
+#define STRTAB_STE_2_S2VMID_MASK 0xffffUL
+#define STRTAB_STE_2_VTCR_SHIFT 32
+#define STRTAB_STE_2_VTCR_MASK 0x7ffffUL
+#define STRTAB_STE_2_S2AA64 (1UL << 51)
+#define STRTAB_STE_2_S2ENDI (1UL << 52)
+#define STRTAB_STE_2_S2PTW (1UL << 54)
+#define STRTAB_STE_2_S2R (1UL << 58)
+
+#define STRTAB_STE_3_S2TTB_SHIFT 4
+#define STRTAB_STE_3_S2TTB_MASK 0xfffffffffffUL
+
+/* Context descriptor (stage-1 only) */
+#define CTXDESC_CD_DWORDS 8
+#define CTXDESC_CD_0_TCR_T0SZ_SHIFT 0
+#define ARM64_TCR_T0SZ_SHIFT 0
+#define ARM64_TCR_T0SZ_MASK 0x1fUL
+#define CTXDESC_CD_0_TCR_TG0_SHIFT 6
+#define ARM64_TCR_TG0_SHIFT 14
+#define ARM64_TCR_TG0_MASK 0x3UL
+#define CTXDESC_CD_0_TCR_IRGN0_SHIFT 8
+#define ARM64_TCR_IRGN0_SHIFT 24
+#define ARM64_TCR_IRGN0_MASK 0x3UL
+#define CTXDESC_CD_0_TCR_ORGN0_SHIFT 10
+#define ARM64_TCR_ORGN0_SHIFT 26
+#define ARM64_TCR_ORGN0_MASK 0x3UL
+#define CTXDESC_CD_0_TCR_SH0_SHIFT 12
+#define ARM64_TCR_SH0_SHIFT 12
+#define ARM64_TCR_SH0_MASK 0x3UL
+#define CTXDESC_CD_0_TCR_EPD0_SHIFT 14
+#define ARM64_TCR_EPD0_SHIFT 7
+#define ARM64_TCR_EPD0_MASK 0x1UL
+#define CTXDESC_CD_0_TCR_EPD1_SHIFT 30
+#define ARM64_TCR_EPD1_SHIFT 23
+#define ARM64_TCR_EPD1_MASK 0x1UL
+
+#define CTXDESC_CD_0_ENDI (1UL << 15)
+#define CTXDESC_CD_0_V (1UL << 31)
+
+#define CTXDESC_CD_0_TCR_IPS_SHIFT 32
+#define ARM64_TCR_IPS_SHIFT 32
+#define ARM64_TCR_IPS_MASK 0x7UL
+#define CTXDESC_CD_0_TCR_TBI0_SHIFT 38
+#define ARM64_TCR_TBI0_SHIFT 37
+#define ARM64_TCR_TBI0_MASK 0x1UL
+
+#define CTXDESC_CD_0_AA64 (1UL << 41)
+#define CTXDESC_CD_0_R (1UL << 45)
+#define CTXDESC_CD_0_A (1UL << 46)
+#define CTXDESC_CD_0_ASET_SHIFT 47
+#define CTXDESC_CD_0_ASET_SHARED (0UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASET_PRIVATE (1UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASID_SHIFT 48
+#define CTXDESC_CD_0_ASID_MASK 0xffffUL
+
+#define CTXDESC_CD_1_TTB0_SHIFT 4
+#define CTXDESC_CD_1_TTB0_MASK 0xfffffffffffUL
+
+#define CTXDESC_CD_3_MAIR_SHIFT 0
+
+/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
+#define ARM_SMMU_TCR2CD(tcr, fld) \
+ (((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK) \
+ << CTXDESC_CD_0_TCR_##fld##_SHIFT)
+
+/* Command queue */
+#define CMDQ_ENT_DWORDS 2
+#define CMDQ_MAX_SZ_SHIFT 8
+
+#define CMDQ_ERR_SHIFT 24
+#define CMDQ_ERR_MASK 0x7f
+#define CMDQ_ERR_CERROR_NONE_IDX 0
+#define CMDQ_ERR_CERROR_ILL_IDX 1
+#define CMDQ_ERR_CERROR_ABT_IDX 2
+
+#define CMDQ_0_OP_SHIFT 0
+#define CMDQ_0_OP_MASK 0xffUL
+#define CMDQ_0_SSV (1UL << 11)
+
+#define CMDQ_PREFETCH_0_SID_SHIFT 32
+#define CMDQ_PREFETCH_1_SIZE_SHIFT 0
+#define CMDQ_PREFETCH_1_ADDR_MASK ~0xfffUL
+
+#define CMDQ_CFGI_0_SID_SHIFT 32
+#define CMDQ_CFGI_0_SID_MASK 0xffffffffUL
+#define CMDQ_CFGI_1_LEAF (1UL << 0)
+#define CMDQ_CFGI_1_RANGE_SHIFT 0
+#define CMDQ_CFGI_1_RANGE_MASK 0x1fUL
+
+#define CMDQ_TLBI_0_VMID_SHIFT 32
+#define CMDQ_TLBI_0_ASID_SHIFT 48
+#define CMDQ_TLBI_1_LEAF (1UL << 0)
+#define CMDQ_TLBI_1_ADDR_MASK ~0xfffUL
+
+#define CMDQ_PRI_0_SSID_SHIFT 12
+#define CMDQ_PRI_0_SSID_MASK 0xfffffUL
+#define CMDQ_PRI_0_SID_SHIFT 32
+#define CMDQ_PRI_0_SID_MASK 0xffffffffUL
+#define CMDQ_PRI_1_GRPID_SHIFT 0
+#define CMDQ_PRI_1_GRPID_MASK 0x1ffUL
+#define CMDQ_PRI_1_RESP_SHIFT 12
+#define CMDQ_PRI_1_RESP_DENY (0UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_FAIL (1UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_SUCC (2UL << CMDQ_PRI_1_RESP_SHIFT)
+
+#define CMDQ_SYNC_0_CS_SHIFT 12
+#define CMDQ_SYNC_0_CS_NONE (0UL << CMDQ_SYNC_0_CS_SHIFT)
+#define CMDQ_SYNC_0_CS_SEV (2UL << CMDQ_SYNC_0_CS_SHIFT)
+
+/* Event queue */
+#define EVTQ_ENT_DWORDS 4
+#define EVTQ_MAX_SZ_SHIFT 7
+
+#define EVTQ_0_ID_SHIFT 0
+#define EVTQ_0_ID_MASK 0xffUL
+
+/* PRI queue */
+#define PRIQ_ENT_DWORDS 2
+#define PRIQ_MAX_SZ_SHIFT 8
+
+#define PRIQ_0_SID_SHIFT 0
+#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)
+#define PRIQ_0_PERM_WRITE (1UL << 61)
+#define PRIQ_0_PRG_LAST (1UL << 62)
+#define PRIQ_0_SSID_V (1UL << 63)
+
+#define PRIQ_1_PRG_IDX_SHIFT 0
+#define PRIQ_1_PRG_IDX_MASK 0x1ffUL
+#define PRIQ_1_ADDR_SHIFT 12
+#define PRIQ_1_ADDR_MASK 0xfffffffffffffUL
+
+/* High-level queue structures */
+#define ARM_SMMU_POLL_TIMEOUT_US 100
+
+static bool disable_bypass;
+module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_bypass,
+ "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
+
+enum pri_resp {
+ PRI_RESP_DENY,
+ PRI_RESP_FAIL,
+ PRI_RESP_SUCC,
+};
+
+struct arm_smmu_cmdq_ent {
+ /* Common fields */
+ u8 opcode;
+ bool substream_valid;
+
+ /* Command-specific fields */
+ union {
+ #define CMDQ_OP_PREFETCH_CFG 0x1
+ struct {
+ u32 sid;
+ u8 size;
+ u64 addr;
+ } prefetch;
+
+ #define CMDQ_OP_CFGI_STE 0x3
+ #define CMDQ_OP_CFGI_ALL 0x4
+ struct {
+ u32 sid;
+ union {
+ bool leaf;
+ u8 span;
+ };
+ } cfgi;
+
+ #define CMDQ_OP_TLBI_NH_ASID 0x11
+ #define CMDQ_OP_TLBI_NH_VA 0x12
+ #define CMDQ_OP_TLBI_EL2_ALL 0x20
+ #define CMDQ_OP_TLBI_S12_VMALL 0x28
+ #define CMDQ_OP_TLBI_S2_IPA 0x2a
+ #define CMDQ_OP_TLBI_NSNH_ALL 0x30
+ struct {
+ u16 asid;
+ u16 vmid;
+ bool leaf;
+ u64 addr;
+ } tlbi;
+
+ #define CMDQ_OP_PRI_RESP 0x41
+ struct {
+ u32 sid;
+ u32 ssid;
+ u16 grpid;
+ enum pri_resp resp;
+ } pri;
+
+ #define CMDQ_OP_CMD_SYNC 0x46
+ };
+};
+
+struct arm_smmu_queue {
+ int irq; /* Wired interrupt */
+
+ __le64 *base;
+ dma_addr_t base_dma;
+ u64 q_base;
+
+ size_t ent_dwords;
+ u32 max_n_shift;
+ u32 prod;
+ u32 cons;
+
+ u32 __iomem *prod_reg;
+ u32 __iomem *cons_reg;
+};
+
+struct arm_smmu_cmdq {
+ struct arm_smmu_queue q;
+ spinlock_t lock;
+};
+
+struct arm_smmu_evtq {
+ struct arm_smmu_queue q;
+ u32 max_stalls;
+};
+
+struct arm_smmu_priq {
+ struct arm_smmu_queue q;
+};
+
+/* High-level stream table and context descriptor structures */
+struct arm_smmu_strtab_l1_desc {
+ u8 span;
+
+ __le64 *l2ptr;
+ dma_addr_t l2ptr_dma;
+};
+
+struct arm_smmu_s1_cfg {
+ __le64 *cdptr;
+ dma_addr_t cdptr_dma;
+
+ struct arm_smmu_ctx_desc {
+ u16 asid;
+ u64 ttbr;
+ u64 tcr;
+ u64 mair;
+ } cd;
+};
+
+struct arm_smmu_s2_cfg {
+ u16 vmid;
+ u64 vttbr;
+ u64 vtcr;
+};
+
+struct arm_smmu_strtab_ent {
+ bool valid;
+
+ bool bypass; /* Overrides s1/s2 config */
+ struct arm_smmu_s1_cfg *s1_cfg;
+ struct arm_smmu_s2_cfg *s2_cfg;
+};
+
+struct arm_smmu_strtab_cfg {
+ __le64 *strtab;
+ dma_addr_t strtab_dma;
+ struct arm_smmu_strtab_l1_desc *l1_desc;
+ unsigned int num_l1_ents;
+
+ u64 strtab_base;
+ u32 strtab_base_cfg;
+};
+
+/* An SMMUv3 instance */
+struct arm_smmu_device {
+ struct device *dev;
+ void __iomem *base;
+
+#define ARM_SMMU_FEAT_2_LVL_STRTAB (1 << 0)
+#define ARM_SMMU_FEAT_2_LVL_CDTAB (1 << 1)
+#define ARM_SMMU_FEAT_TT_LE (1 << 2)
+#define ARM_SMMU_FEAT_TT_BE (1 << 3)
+#define ARM_SMMU_FEAT_PRI (1 << 4)
+#define ARM_SMMU_FEAT_ATS (1 << 5)
+#define ARM_SMMU_FEAT_SEV (1 << 6)
+#define ARM_SMMU_FEAT_MSI (1 << 7)
+#define ARM_SMMU_FEAT_COHERENCY (1 << 8)
+#define ARM_SMMU_FEAT_TRANS_S1 (1 << 9)
+#define ARM_SMMU_FEAT_TRANS_S2 (1 << 10)
+#define ARM_SMMU_FEAT_STALLS (1 << 11)
+#define ARM_SMMU_FEAT_HYP (1 << 12)
+ u32 features;
+
+ struct arm_smmu_cmdq cmdq;
+ struct arm_smmu_evtq evtq;
+ struct arm_smmu_priq priq;
+
+ int gerr_irq;
+
+ unsigned long ias; /* IPA */
+ unsigned long oas; /* PA */
+
+#define ARM_SMMU_MAX_ASIDS (1 << 16)
+ unsigned int asid_bits;
+ DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS);
+
+#define ARM_SMMU_MAX_VMIDS (1 << 16)
+ unsigned int vmid_bits;
+ DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+
+ unsigned int ssid_bits;
+ unsigned int sid_bits;
+
+ struct arm_smmu_strtab_cfg strtab_cfg;
+ struct list_head list;
+};
+
+/* SMMU private data for an IOMMU group */
+struct arm_smmu_group {
+ struct arm_smmu_device *smmu;
+ struct arm_smmu_domain *domain;
+ int num_sids;
+ u32 *sids;
+ struct arm_smmu_strtab_ent ste;
+};
+
+/* SMMU private data for an IOMMU domain */
+enum arm_smmu_domain_stage {
+ ARM_SMMU_DOMAIN_S1 = 0,
+ ARM_SMMU_DOMAIN_S2,
+ ARM_SMMU_DOMAIN_NESTED,
+};
+
+struct arm_smmu_domain {
+ struct arm_smmu_device *smmu;
+ struct mutex init_mutex; /* Protects smmu pointer */
+
+ struct io_pgtable_ops *pgtbl_ops;
+ spinlock_t pgtbl_lock;
+
+ enum arm_smmu_domain_stage stage;
+ union {
+ struct arm_smmu_s1_cfg s1_cfg;
+ struct arm_smmu_s2_cfg s2_cfg;
+ };
+
+ struct iommu_domain domain;
+};
+
+/* Our list of SMMU instances */
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+ return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+/* Low-level queue manipulation functions */
+static bool queue_full(struct arm_smmu_queue *q)
+{
+ return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+ Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
+}
+
+static bool queue_empty(struct arm_smmu_queue *q)
+{
+ return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+ Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
+}
+
+static void queue_sync_cons(struct arm_smmu_queue *q)
+{
+ q->cons = readl_relaxed(q->cons_reg);
+}
+
+static void queue_inc_cons(struct arm_smmu_queue *q)
+{
+ u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+
+ q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
+ writel(q->cons, q->cons_reg);
+}
+
+static int queue_sync_prod(struct arm_smmu_queue *q)
+{
+ int ret = 0;
+ u32 prod = readl_relaxed(q->prod_reg);
+
+ if (Q_OVF(q, prod) != Q_OVF(q, q->prod))
+ ret = -EOVERFLOW;
+
+ q->prod = prod;
+ return ret;
+}
+
+static void queue_inc_prod(struct arm_smmu_queue *q)
+{
+ u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;
+
+ q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
+ writel(q->prod, q->prod_reg);
+}
+
+static bool __queue_cons_before(struct arm_smmu_queue *q, u32 until)
+{
+ if (Q_WRP(q, q->cons) == Q_WRP(q, until))
+ return Q_IDX(q, q->cons) < Q_IDX(q, until);
+
+ return Q_IDX(q, q->cons) >= Q_IDX(q, until);
+}
+
+static int queue_poll_cons(struct arm_smmu_queue *q, u32 until, bool wfe)
+{
+ ktime_t timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+
+ while (queue_sync_cons(q), __queue_cons_before(q, until)) {
+ if (ktime_compare(ktime_get(), timeout) > 0)
+ return -ETIMEDOUT;
+
+ if (wfe) {
+ wfe();
+ } else {
+ cpu_relax();
+ udelay(1);
+ }
+ }
+
+ return 0;
+}
+
+static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
+{
+ int i;
+
+ for (i = 0; i < n_dwords; ++i)
+ *dst++ = cpu_to_le64(*src++);
+}
+
+static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+ if (queue_full(q))
+ return -ENOSPC;
+
+ queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
+ queue_inc_prod(q);
+ return 0;
+}
+
+static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
+{
+ int i;
+
+ for (i = 0; i < n_dwords; ++i)
+ *dst++ = le64_to_cpu(*src++);
+}
+
+static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+ if (queue_empty(q))
+ return -EAGAIN;
+
+ queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
+ queue_inc_cons(q);
+ return 0;
+}
+
+/* High-level queue accessors */
+static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
+{
+ memset(cmd, 0, CMDQ_ENT_DWORDS << 3);
+ cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT;
+
+ switch (ent->opcode) {
+ case CMDQ_OP_TLBI_EL2_ALL:
+ case CMDQ_OP_TLBI_NSNH_ALL:
+ break;
+ case CMDQ_OP_PREFETCH_CFG:
+ cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT;
+ cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT;
+ cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
+ break;
+ case CMDQ_OP_CFGI_STE:
+ cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT;
+ cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0;
+ break;
+ case CMDQ_OP_CFGI_ALL:
+ /* Cover the entire SID range */
+ cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT;
+ break;
+ case CMDQ_OP_TLBI_NH_VA:
+ cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+ /* Fallthrough */
+ case CMDQ_OP_TLBI_S2_IPA:
+ cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+ cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
+ cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK;
+ break;
+ case CMDQ_OP_TLBI_NH_ASID:
+ cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+ /* Fallthrough */
+ case CMDQ_OP_TLBI_S12_VMALL:
+ cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+ break;
+ case CMDQ_OP_PRI_RESP:
+ cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0;
+ cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT;
+ cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT;
+ cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT;
+ switch (ent->pri.resp) {
+ case PRI_RESP_DENY:
+ cmd[1] |= CMDQ_PRI_1_RESP_DENY;
+ break;
+ case PRI_RESP_FAIL:
+ cmd[1] |= CMDQ_PRI_1_RESP_FAIL;
+ break;
+ case PRI_RESP_SUCC:
+ cmd[1] |= CMDQ_PRI_1_RESP_SUCC;
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case CMDQ_OP_CMD_SYNC:
+ cmd[0] |= CMDQ_SYNC_0_CS_SEV;
+ break;
+ default:
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
+static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
+{
+ static const char *cerror_str[] = {
+ [CMDQ_ERR_CERROR_NONE_IDX] = "No error",
+ [CMDQ_ERR_CERROR_ILL_IDX] = "Illegal command",
+ [CMDQ_ERR_CERROR_ABT_IDX] = "Abort on command fetch",
+ };
+
+ int i;
+ u64 cmd[CMDQ_ENT_DWORDS];
+ struct arm_smmu_queue *q = &smmu->cmdq.q;
+ u32 cons = readl_relaxed(q->cons_reg);
+ u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK;
+ struct arm_smmu_cmdq_ent cmd_sync = {
+ .opcode = CMDQ_OP_CMD_SYNC,
+ };
+
+ dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
+ cerror_str[idx]);
+
+ 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;
+ }
+
+ /*
+ * We may have concurrent producers, so we need to be careful
+ * not to touch any of the shadow cmdq state.
+ */
+ queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+ dev_err(smmu->dev, "skipping command in error state:\n");
+ for (i = 0; i < ARRAY_SIZE(cmd); ++i)
+ dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
+
+ /* Convert the erroneous command into a CMD_SYNC */
+ if (arm_smmu_cmdq_build_cmd(cmd, &cmd_sync)) {
+ dev_err(smmu->dev, "failed to convert to CMD_SYNC\n");
+ return;
+ }
+
+ queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+}
+
+static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+ struct arm_smmu_cmdq_ent *ent)
+{
+ u32 until;
+ u64 cmd[CMDQ_ENT_DWORDS];
+ bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+ struct arm_smmu_queue *q = &smmu->cmdq.q;
+
+ if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
+ dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+ ent->opcode);
+ return;
+ }
+
+ spin_lock(&smmu->cmdq.lock);
+ while (until = q->prod + 1, queue_insert_raw(q, cmd) == -ENOSPC) {
+ /*
+ * Keep the queue locked, otherwise the producer could wrap
+ * twice and we could see a future consumer pointer that looks
+ * like it's behind us.
+ */
+ if (queue_poll_cons(q, until, wfe))
+ dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+ }
+
+ if (ent->opcode == CMDQ_OP_CMD_SYNC && queue_poll_cons(q, until, wfe))
+ dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
+ spin_unlock(&smmu->cmdq.lock);
+}
+
+/* Context descriptor manipulation functions */
+static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
+{
+ u64 val = 0;
+
+ /* Repack the TCR. Just care about TTBR0 for now */
+ val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
+ val |= ARM_SMMU_TCR2CD(tcr, TG0);
+ val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
+ val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
+ val |= ARM_SMMU_TCR2CD(tcr, SH0);
+ val |= ARM_SMMU_TCR2CD(tcr, EPD0);
+ val |= ARM_SMMU_TCR2CD(tcr, EPD1);
+ val |= ARM_SMMU_TCR2CD(tcr, IPS);
+ val |= ARM_SMMU_TCR2CD(tcr, TBI0);
+
+ return val;
+}
+
+static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
+ struct arm_smmu_s1_cfg *cfg)
+{
+ u64 val;
+
+ /*
+ * We don't need to issue any invalidation here, as we'll invalidate
+ * the STE when installing the new entry anyway.
+ */
+ val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+#ifdef __BIG_ENDIAN
+ CTXDESC_CD_0_ENDI |
+#endif
+ CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE |
+ CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT |
+ CTXDESC_CD_0_V;
+ cfg->cdptr[0] = cpu_to_le64(val);
+
+ val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT;
+ cfg->cdptr[1] = cpu_to_le64(val);
+
+ cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT);
+}
+
+/* Stream table manipulation functions */
+static void
+arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
+{
+ u64 val = 0;
+
+ val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK)
+ << STRTAB_L1_DESC_SPAN_SHIFT;
+ val |= desc->l2ptr_dma &
+ STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT;
+
+ *dst = cpu_to_le64(val);
+}
+
+static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+ struct arm_smmu_cmdq_ent cmd = {
+ .opcode = CMDQ_OP_CFGI_STE,
+ .cfgi = {
+ .sid = sid,
+ .leaf = true,
+ },
+ };
+
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ cmd.opcode = CMDQ_OP_CMD_SYNC;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
+ __le64 *dst, struct arm_smmu_strtab_ent *ste)
+{
+ /*
+ * This is hideously complicated, but we only really care about
+ * three cases at the moment:
+ *
+ * 1. Invalid (all zero) -> bypass (init)
+ * 2. Bypass -> translation (attach)
+ * 3. Translation -> bypass (detach)
+ *
+ * Given that we can't update the STE atomically and the SMMU
+ * doesn't read the thing in a defined order, that leaves us
+ * with the following maintenance requirements:
+ *
+ * 1. Update Config, return (init time STEs aren't live)
+ * 2. Write everything apart from dword 0, sync, write dword 0, sync
+ * 3. Update Config, sync
+ */
+ u64 val = le64_to_cpu(dst[0]);
+ bool ste_live = false;
+ struct arm_smmu_cmdq_ent prefetch_cmd = {
+ .opcode = CMDQ_OP_PREFETCH_CFG,
+ .prefetch = {
+ .sid = sid,
+ },
+ };
+
+ if (val & STRTAB_STE_0_V) {
+ u64 cfg;
+
+ cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT;
+ switch (cfg) {
+ case STRTAB_STE_0_CFG_BYPASS:
+ break;
+ case STRTAB_STE_0_CFG_S1_TRANS:
+ case STRTAB_STE_0_CFG_S2_TRANS:
+ ste_live = true;
+ break;
+ default:
+ BUG(); /* STE corruption */
+ }
+ }
+
+ /* 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;
+
+ if (ste->bypass) {
+ val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
+ : STRTAB_STE_0_CFG_BYPASS;
+ dst[0] = cpu_to_le64(val);
+ dst[2] = 0; /* Nuke the VMID */
+ if (ste_live)
+ arm_smmu_sync_ste_for_sid(smmu, sid);
+ return;
+ }
+
+ if (ste->s1_cfg) {
+ BUG_ON(ste_live);
+ dst[1] = cpu_to_le64(
+ STRTAB_STE_1_S1C_CACHE_WBRA
+ << STRTAB_STE_1_S1CIR_SHIFT |
+ STRTAB_STE_1_S1C_CACHE_WBRA
+ << STRTAB_STE_1_S1COR_SHIFT |
+ STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT |
+ STRTAB_STE_1_S1STALLD |
+#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);
+
+ 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) {
+ BUG_ON(ste_live);
+ dst[2] = cpu_to_le64(
+ ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT |
+ (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK)
+ << STRTAB_STE_2_VTCR_SHIFT |
+#ifdef __BIG_ENDIAN
+ STRTAB_STE_2_S2ENDI |
+#endif
+ STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
+ STRTAB_STE_2_S2R);
+
+ dst[3] = cpu_to_le64(ste->s2_cfg->vttbr &
+ STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT);
+
+ val |= STRTAB_STE_0_CFG_S2_TRANS;
+ }
+
+ arm_smmu_sync_ste_for_sid(smmu, sid);
+ dst[0] = cpu_to_le64(val);
+ arm_smmu_sync_ste_for_sid(smmu, sid);
+
+ /* It's likely that we'll want to use the new STE soon */
+ arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+}
+
+static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
+{
+ unsigned int i;
+ struct arm_smmu_strtab_ent ste = {
+ .valid = true,
+ .bypass = true,
+ };
+
+ for (i = 0; i < nent; ++i) {
+ arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
+ strtab += STRTAB_STE_DWORDS;
+ }
+}
+
+static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+ size_t size;
+ void *strtab;
+ struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+ struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];
+
+ if (desc->l2ptr)
+ return 0;
+
+ size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
+ 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);
+ if (!desc->l2ptr) {
+ dev_err(smmu->dev,
+ "failed to allocate l2 stream table for SID %u\n",
+ sid);
+ return -ENOMEM;
+ }
+
+ arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
+ arm_smmu_write_strtab_l1_desc(strtab, desc);
+ return 0;
+}
+
+/* IRQ and event handlers */
+static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
+{
+ int i;
+ struct arm_smmu_device *smmu = dev;
+ struct arm_smmu_queue *q = &smmu->evtq.q;
+ u64 evt[EVTQ_ENT_DWORDS];
+
+ while (!queue_remove_raw(q, evt)) {
+ u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK;
+
+ dev_info(smmu->dev, "event 0x%02x received:\n", id);
+ for (i = 0; i < ARRAY_SIZE(evt); ++i)
+ dev_info(smmu->dev, "\t0x%016llx\n",
+ (unsigned long long)evt[i]);
+ }
+
+ /* Sync our overflow flag, as we believe we're up to speed */
+ q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_evtq_handler(int irq, void *dev)
+{
+ irqreturn_t ret = IRQ_WAKE_THREAD;
+ struct arm_smmu_device *smmu = dev;
+ struct arm_smmu_queue *q = &smmu->evtq.q;
+
+ /*
+ * Not much we can do on overflow, so scream and pretend we're
+ * trying harder.
+ */
+ if (queue_sync_prod(q) == -EOVERFLOW)
+ dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
+ else if (queue_empty(q))
+ ret = IRQ_NONE;
+
+ return ret;
+}
+
+static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
+{
+ struct arm_smmu_device *smmu = dev;
+ struct arm_smmu_queue *q = &smmu->priq.q;
+ u64 evt[PRIQ_ENT_DWORDS];
+
+ while (!queue_remove_raw(q, evt)) {
+ u32 sid, ssid;
+ u16 grpid;
+ bool ssv, last;
+
+ sid = evt[0] >> PRIQ_0_SID_SHIFT & PRIQ_0_SID_MASK;
+ ssv = evt[0] & PRIQ_0_SSID_V;
+ ssid = ssv ? evt[0] >> PRIQ_0_SSID_SHIFT & PRIQ_0_SSID_MASK : 0;
+ last = evt[0] & PRIQ_0_PRG_LAST;
+ grpid = evt[1] >> PRIQ_1_PRG_IDX_SHIFT & PRIQ_1_PRG_IDX_MASK;
+
+ dev_info(smmu->dev, "unexpected PRI request received:\n");
+ dev_info(smmu->dev,
+ "\tsid 0x%08x.0x%05x: [%u%s] %sprivileged %s%s%s access at iova 0x%016llx\n",
+ sid, ssid, grpid, last ? "L" : "",
+ evt[0] & PRIQ_0_PERM_PRIV ? "" : "un",
+ evt[0] & PRIQ_0_PERM_READ ? "R" : "",
+ evt[0] & PRIQ_0_PERM_WRITE ? "W" : "",
+ evt[0] & PRIQ_0_PERM_EXEC ? "X" : "",
+ evt[1] & PRIQ_1_ADDR_MASK << PRIQ_1_ADDR_SHIFT);
+
+ if (last) {
+ struct arm_smmu_cmdq_ent cmd = {
+ .opcode = CMDQ_OP_PRI_RESP,
+ .substream_valid = ssv,
+ .pri = {
+ .sid = sid,
+ .ssid = ssid,
+ .grpid = grpid,
+ .resp = PRI_RESP_DENY,
+ },
+ };
+
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ }
+ }
+
+ /* Sync our overflow flag, as we believe we're up to speed */
+ q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_priq_handler(int irq, void *dev)
+{
+ irqreturn_t ret = IRQ_WAKE_THREAD;
+ struct arm_smmu_device *smmu = dev;
+ struct arm_smmu_queue *q = &smmu->priq.q;
+
+ /* PRIQ overflow indicates a programming error */
+ if (queue_sync_prod(q) == -EOVERFLOW)
+ dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
+ else if (queue_empty(q))
+ ret = IRQ_NONE;
+
+ return ret;
+}
+
+static irqreturn_t arm_smmu_cmdq_sync_handler(int irq, void *dev)
+{
+ /* We don't actually use CMD_SYNC interrupts for anything */
+ return IRQ_HANDLED;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
+
+static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
+{
+ u32 gerror, gerrorn;
+ struct arm_smmu_device *smmu = dev;
+
+ gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
+ gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
+
+ gerror ^= gerrorn;
+ if (!(gerror & GERROR_ERR_MASK))
+ return IRQ_NONE; /* No errors pending */
+
+ dev_warn(smmu->dev,
+ "unexpected global error reported (0x%08x), this could be serious\n",
+ gerror);
+
+ if (gerror & GERROR_SFM_ERR) {
+ dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
+ arm_smmu_device_disable(smmu);
+ }
+
+ if (gerror & GERROR_MSI_GERROR_ABT_ERR)
+ dev_warn(smmu->dev, "GERROR MSI write aborted\n");
+
+ if (gerror & GERROR_MSI_PRIQ_ABT_ERR) {
+ dev_warn(smmu->dev, "PRIQ MSI write aborted\n");
+ arm_smmu_priq_handler(irq, smmu->dev);
+ }
+
+ if (gerror & GERROR_MSI_EVTQ_ABT_ERR) {
+ dev_warn(smmu->dev, "EVTQ MSI write aborted\n");
+ arm_smmu_evtq_handler(irq, smmu->dev);
+ }
+
+ if (gerror & GERROR_MSI_CMDQ_ABT_ERR) {
+ dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
+ arm_smmu_cmdq_sync_handler(irq, smmu->dev);
+ }
+
+ if (gerror & GERROR_PRIQ_ABT_ERR)
+ dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");
+
+ if (gerror & GERROR_EVTQ_ABT_ERR)
+ dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n");
+
+ if (gerror & GERROR_CMDQ_ERR)
+ arm_smmu_cmdq_skip_err(smmu);
+
+ writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+ return IRQ_HANDLED;
+}
+
+/* IO_PGTABLE API */
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+{
+ struct arm_smmu_cmdq_ent cmd;
+
+ cmd.opcode = CMDQ_OP_CMD_SYNC;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_tlb_sync(void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ __arm_smmu_tlb_sync(smmu_domain->smmu);
+}
+
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ struct arm_smmu_cmdq_ent cmd;
+
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+ cmd.opcode = CMDQ_OP_TLBI_NH_ASID;
+ cmd.tlbi.asid = smmu_domain->s1_cfg.cd.asid;
+ cmd.tlbi.vmid = 0;
+ } else {
+ cmd.opcode = CMDQ_OP_TLBI_S12_VMALL;
+ cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
+ }
+
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ __arm_smmu_tlb_sync(smmu);
+}
+
+static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
+ bool leaf, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ struct arm_smmu_cmdq_ent cmd = {
+ .tlbi = {
+ .leaf = leaf,
+ .addr = iova,
+ },
+ };
+
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+ cmd.opcode = CMDQ_OP_TLBI_NH_VA;
+ cmd.tlbi.asid = smmu_domain->s1_cfg.cd.asid;
+ } else {
+ cmd.opcode = CMDQ_OP_TLBI_S2_IPA;
+ cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
+ }
+
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+ if (smmu->features & ARM_SMMU_FEAT_COHERENCY) {
+ dsb(ishst);
+ } else {
+ dma_addr_t dma_addr;
+ struct device *dev = smmu->dev;
+
+ dma_addr = dma_map_page(dev, virt_to_page(addr), offset, size,
+ DMA_TO_DEVICE);
+
+ if (dma_mapping_error(dev, dma_addr))
+ dev_err(dev, "failed to flush pgtable at %p\n", addr);
+ else
+ dma_unmap_page(dev, dma_addr, size, DMA_TO_DEVICE);
+ }
+}
+
+static 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,
+ .flush_pgtable = arm_smmu_flush_pgtable,
+};
+
+/* IOMMU API */
+static bool arm_smmu_capable(enum iommu_cap cap)
+{
+ 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:
+ return false;
+ }
+}
+
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+{
+ struct arm_smmu_domain *smmu_domain;
+
+ if (type != IOMMU_DOMAIN_UNMANAGED)
+ return NULL;
+
+ /*
+ * Allocate the domain and initialise some of its data structures.
+ * We can't really do anything meaningful until we've added a
+ * master.
+ */
+ smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
+ if (!smmu_domain)
+ return NULL;
+
+ mutex_init(&smmu_domain->init_mutex);
+ spin_lock_init(&smmu_domain->pgtbl_lock);
+ return &smmu_domain->domain;
+}
+
+static int arm_smmu_bitmap_alloc(unsigned long *map, int span)
+{
+ int idx, size = 1 << span;
+
+ do {
+ idx = find_first_zero_bit(map, size);
+ if (idx == size)
+ return -ENOSPC;
+ } while (test_and_set_bit(idx, map));
+
+ return idx;
+}
+
+static void arm_smmu_bitmap_free(unsigned long *map, int idx)
+{
+ clear_bit(idx, map);
+}
+
+static void arm_smmu_domain_free(struct iommu_domain *domain)
+{
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+ if (smmu_domain->pgtbl_ops)
+ free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+
+ /* Free the CD and ASID, if we allocated them */
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+ 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);
+
+ arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
+ }
+ } else {
+ struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+ if (cfg->vmid)
+ arm_smmu_bitmap_free(smmu->vmid_map, cfg->vmid);
+ }
+
+ kfree(smmu_domain);
+}
+
+static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
+ struct io_pgtable_cfg *pgtbl_cfg)
+{
+ int ret;
+ u16 asid;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+
+ asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
+ if (IS_ERR_VALUE(asid))
+ return asid;
+
+ cfg->cdptr = dma_zalloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
+ &cfg->cdptr_dma, GFP_KERNEL);
+ if (!cfg->cdptr) {
+ dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+ goto out_free_asid;
+ }
+
+ cfg->cd.asid = 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];
+ return 0;
+
+out_free_asid:
+ arm_smmu_bitmap_free(smmu->asid_map, asid);
+ return ret;
+}
+
+static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
+ struct io_pgtable_cfg *pgtbl_cfg)
+{
+ u16 vmid;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+
+ vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
+ if (IS_ERR_VALUE(vmid))
+ return vmid;
+
+ cfg->vmid = vmid;
+ cfg->vttbr = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+ cfg->vtcr = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+ return 0;
+}
+
+static struct iommu_ops arm_smmu_ops;
+
+static int arm_smmu_domain_finalise(struct iommu_domain *domain)
+{
+ int ret;
+ unsigned long ias, oas;
+ enum io_pgtable_fmt fmt;
+ struct io_pgtable_cfg pgtbl_cfg;
+ struct io_pgtable_ops *pgtbl_ops;
+ int (*finalise_stage_fn)(struct arm_smmu_domain *,
+ struct io_pgtable_cfg *);
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+ /* Restrict the stage to what we can actually support */
+ if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
+ smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
+ if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+ smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+ switch (smmu_domain->stage) {
+ case ARM_SMMU_DOMAIN_S1:
+ ias = VA_BITS;
+ oas = smmu->ias;
+ fmt = ARM_64_LPAE_S1;
+ finalise_stage_fn = arm_smmu_domain_finalise_s1;
+ break;
+ case ARM_SMMU_DOMAIN_NESTED:
+ case ARM_SMMU_DOMAIN_S2:
+ ias = smmu->ias;
+ oas = smmu->oas;
+ fmt = ARM_64_LPAE_S2;
+ finalise_stage_fn = arm_smmu_domain_finalise_s2;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ pgtbl_cfg = (struct io_pgtable_cfg) {
+ .pgsize_bitmap = arm_smmu_ops.pgsize_bitmap,
+ .ias = ias,
+ .oas = oas,
+ .tlb = &arm_smmu_gather_ops,
+ };
+
+ pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+ if (!pgtbl_ops)
+ return -ENOMEM;
+
+ arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+ smmu_domain->pgtbl_ops = pgtbl_ops;
+
+ ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
+ if (IS_ERR_VALUE(ret))
+ free_io_pgtable_ops(pgtbl_ops);
+
+ return ret;
+}
+
+static struct arm_smmu_group *arm_smmu_group_get(struct device *dev)
+{
+ struct iommu_group *group;
+ struct arm_smmu_group *smmu_group;
+
+ group = iommu_group_get(dev);
+ if (!group)
+ return NULL;
+
+ smmu_group = iommu_group_get_iommudata(group);
+ iommu_group_put(group);
+ return smmu_group;
+}
+
+static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+ __le64 *step;
+ struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+ if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+ struct arm_smmu_strtab_l1_desc *l1_desc;
+ int idx;
+
+ /* Two-level walk */
+ idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+ l1_desc = &cfg->l1_desc[idx];
+ idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
+ step = &l1_desc->l2ptr[idx];
+ } else {
+ /* Simple linear lookup */
+ step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+ }
+
+ return step;
+}
+
+static int arm_smmu_install_ste_for_group(struct arm_smmu_group *smmu_group)
+{
+ int i;
+ struct arm_smmu_domain *smmu_domain = smmu_group->domain;
+ struct arm_smmu_strtab_ent *ste = &smmu_group->ste;
+ struct arm_smmu_device *smmu = smmu_group->smmu;
+
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+ ste->s1_cfg = &smmu_domain->s1_cfg;
+ ste->s2_cfg = NULL;
+ arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
+ } else {
+ ste->s1_cfg = NULL;
+ ste->s2_cfg = &smmu_domain->s2_cfg;
+ }
+
+ for (i = 0; i < smmu_group->num_sids; ++i) {
+ u32 sid = smmu_group->sids[i];
+ __le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+
+ arm_smmu_write_strtab_ent(smmu, sid, step, ste);
+ }
+
+ return 0;
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+ int ret = 0;
+ struct arm_smmu_device *smmu;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_group *smmu_group = arm_smmu_group_get(dev);
+
+ if (!smmu_group)
+ return -ENOENT;
+
+ /* Already attached to a different domain? */
+ if (smmu_group->domain && smmu_group->domain != smmu_domain)
+ return -EEXIST;
+
+ smmu = smmu_group->smmu;
+ mutex_lock(&smmu_domain->init_mutex);
+
+ if (!smmu_domain->smmu) {
+ smmu_domain->smmu = smmu;
+ ret = arm_smmu_domain_finalise(domain);
+ if (ret) {
+ smmu_domain->smmu = NULL;
+ goto out_unlock;
+ }
+ } else if (smmu_domain->smmu != smmu) {
+ dev_err(dev,
+ "cannot attach to SMMU %s (upstream of %s)\n",
+ dev_name(smmu_domain->smmu->dev),
+ dev_name(smmu->dev));
+ ret = -ENXIO;
+ goto out_unlock;
+ }
+
+ /* Group already attached to this domain? */
+ if (smmu_group->domain)
+ goto out_unlock;
+
+ smmu_group->domain = smmu_domain;
+ smmu_group->ste.bypass = false;
+
+ ret = arm_smmu_install_ste_for_group(smmu_group);
+ if (IS_ERR_VALUE(ret))
+ smmu_group->domain = NULL;
+
+out_unlock:
+ mutex_unlock(&smmu_domain->init_mutex);
+ return ret;
+}
+
+static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_group *smmu_group = arm_smmu_group_get(dev);
+
+ BUG_ON(!smmu_domain);
+ BUG_ON(!smmu_group);
+
+ mutex_lock(&smmu_domain->init_mutex);
+ BUG_ON(smmu_group->domain != smmu_domain);
+
+ smmu_group->ste.bypass = true;
+ if (IS_ERR_VALUE(arm_smmu_install_ste_for_group(smmu_group)))
+ dev_warn(dev, "failed to install bypass STE\n");
+
+ smmu_group->domain = NULL;
+ mutex_unlock(&smmu_domain->init_mutex);
+}
+
+static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
+ phys_addr_t paddr, size_t size, int prot)
+{
+ int ret;
+ unsigned long flags;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+ if (!ops)
+ return -ENODEV;
+
+ spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+ ret = ops->map(ops, iova, paddr, size, prot);
+ spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+ return ret;
+}
+
+static size_t
+arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
+{
+ size_t ret;
+ unsigned long flags;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+ if (!ops)
+ return 0;
+
+ spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+ ret = ops->unmap(ops, iova, size);
+ spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+ return ret;
+}
+
+static phys_addr_t
+arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+ phys_addr_t ret;
+ unsigned long flags;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+ if (!ops)
+ return 0;
+
+ spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+ ret = ops->iova_to_phys(ops, iova);
+ spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+
+ return ret;
+}
+
+static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *sidp)
+{
+ *(u32 *)sidp = alias;
+ return 0; /* Continue walking */
+}
+
+static void __arm_smmu_release_pci_iommudata(void *data)
+{
+ kfree(data);
+}
+
+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 pci_bus *bus = pdev->bus;
+
+ /* Walk up to the root bus */
+ while (!pci_is_root_bus(bus))
+ bus = bus->parent;
+
+ /* Follow the "iommus" phandle from the host controller */
+ of_node = of_parse_phandle(bus->bridge->parent->of_node, "iommus", 0);
+ if (!of_node)
+ 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);
+ of_node_put(of_node);
+ return smmu;
+}
+
+static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
+{
+ unsigned long limit = smmu->strtab_cfg.num_l1_ents;
+
+ if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+ limit *= 1UL << STRTAB_SPLIT;
+
+ return sid < limit;
+}
+
+static int arm_smmu_add_device(struct device *dev)
+{
+ int i, ret;
+ u32 sid, *sids;
+ struct pci_dev *pdev;
+ struct iommu_group *group;
+ struct arm_smmu_group *smmu_group;
+ struct arm_smmu_device *smmu;
+
+ /* We only support PCI, for now */
+ if (!dev_is_pci(dev))
+ return -ENODEV;
+
+ pdev = to_pci_dev(dev);
+ group = iommu_group_get_for_dev(dev);
+ if (IS_ERR(group))
+ return PTR_ERR(group);
+
+ smmu_group = iommu_group_get_iommudata(group);
+ if (!smmu_group) {
+ smmu = arm_smmu_get_for_pci_dev(pdev);
+ if (!smmu) {
+ ret = -ENOENT;
+ goto out_put_group;
+ }
+
+ smmu_group = kzalloc(sizeof(*smmu_group), GFP_KERNEL);
+ if (!smmu_group) {
+ ret = -ENOMEM;
+ goto out_put_group;
+ }
+
+ smmu_group->ste.valid = true;
+ smmu_group->smmu = smmu;
+ iommu_group_set_iommudata(group, smmu_group,
+ __arm_smmu_release_pci_iommudata);
+ } else {
+ smmu = smmu_group->smmu;
+ }
+
+ /* Assume SID == RID until firmware tells us otherwise */
+ pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid);
+ 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;
+ }
+
+ /* 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;
+ }
+
+ /* 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;
+ }
+
+ /* Resize the SID array for the group */
+ smmu_group->num_sids++;
+ sids = krealloc(smmu_group->sids, smmu_group->num_sids * sizeof(*sids),
+ GFP_KERNEL);
+ if (!sids) {
+ smmu_group->num_sids--;
+ ret = -ENOMEM;
+ goto out_put_group;
+ }
+
+ /* 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 ret;
+}
+
+static void arm_smmu_remove_device(struct device *dev)
+{
+ iommu_group_remove_device(dev);
+}
+
+static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
+ enum iommu_attr attr, void *data)
+{
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+ switch (attr) {
+ case DOMAIN_ATTR_NESTING:
+ *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+ return 0;
+ default:
+ return -ENODEV;
+ }
+}
+
+static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
+ enum iommu_attr attr, void *data)
+{
+ int ret = 0;
+ struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+ mutex_lock(&smmu_domain->init_mutex);
+
+ switch (attr) {
+ case DOMAIN_ATTR_NESTING:
+ if (smmu_domain->smmu) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ if (*(int *)data)
+ smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+ else
+ smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+ break;
+ default:
+ ret = -ENODEV;
+ }
+
+out_unlock:
+ mutex_unlock(&smmu_domain->init_mutex);
+ return ret;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+ .capable = arm_smmu_capable,
+ .domain_alloc = arm_smmu_domain_alloc,
+ .domain_free = arm_smmu_domain_free,
+ .attach_dev = arm_smmu_attach_dev,
+ .detach_dev = arm_smmu_detach_dev,
+ .map = arm_smmu_map,
+ .unmap = arm_smmu_unmap,
+ .iova_to_phys = arm_smmu_iova_to_phys,
+ .add_device = arm_smmu_add_device,
+ .remove_device = arm_smmu_remove_device,
+ .domain_get_attr = arm_smmu_domain_get_attr,
+ .domain_set_attr = arm_smmu_domain_set_attr,
+ .pgsize_bitmap = -1UL, /* Restricted during device attach */
+};
+
+/* Probing and initialisation functions */
+static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
+ struct arm_smmu_queue *q,
+ unsigned long prod_off,
+ unsigned long cons_off,
+ size_t dwords)
+{
+ size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;
+
+ q->base = dma_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 -ENOMEM;
+ }
+
+ q->prod_reg = smmu->base + prod_off;
+ q->cons_reg = smmu->base + cons_off;
+ q->ent_dwords = dwords;
+
+ q->q_base = Q_BASE_RWA;
+ q->q_base |= q->base_dma & Q_BASE_ADDR_MASK << Q_BASE_ADDR_SHIFT;
+ q->q_base |= (q->max_n_shift & Q_BASE_LOG2SIZE_MASK)
+ << Q_BASE_LOG2SIZE_SHIFT;
+
+ q->prod = q->cons = 0;
+ 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;
+
+ /* cmdq */
+ spin_lock_init(&smmu->cmdq.lock);
+ 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;
+
+ /* 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;
+
+ /* 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);
+ }
+}
+
+static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
+{
+ unsigned int i;
+ struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+ size_t size = sizeof(*cfg->l1_desc) * cfg->num_l1_ents;
+ void *strtab = smmu->strtab_cfg.strtab;
+
+ cfg->l1_desc = devm_kzalloc(smmu->dev, size, GFP_KERNEL);
+ if (!cfg->l1_desc) {
+ dev_err(smmu->dev, "failed to allocate l1 stream table desc\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < cfg->num_l1_ents; ++i) {
+ arm_smmu_write_strtab_l1_desc(strtab, &cfg->l1_desc[i]);
+ strtab += STRTAB_L1_DESC_DWORDS << 3;
+ }
+
+ return 0;
+}
+
+static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
+{
+ void *strtab;
+ u64 reg;
+ u32 size;
+ int ret;
+ struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+ /* 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);
+ if (size + STRTAB_SPLIT < smmu->sid_bits)
+ dev_warn(smmu->dev,
+ "2-level strtab only covers %u/%u bits of SID\n",
+ size + STRTAB_SPLIT, smmu->sid_bits);
+
+ cfg->num_l1_ents = 1 << size;
+ size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
+ strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+ GFP_KERNEL);
+ if (!strtab) {
+ dev_err(smmu->dev,
+ "failed to allocate l1 stream table (%u bytes)\n",
+ size);
+ return -ENOMEM;
+ }
+ cfg->strtab = strtab;
+
+ /* Configure strtab_base_cfg for 2 levels */
+ reg = STRTAB_BASE_CFG_FMT_2LVL;
+ reg |= (size & STRTAB_BASE_CFG_LOG2SIZE_MASK)
+ << STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
+ reg |= (STRTAB_SPLIT & STRTAB_BASE_CFG_SPLIT_MASK)
+ << STRTAB_BASE_CFG_SPLIT_SHIFT;
+ cfg->strtab_base_cfg = reg;
+
+ ret = arm_smmu_init_l1_strtab(smmu);
+ if (ret)
+ dma_free_coherent(smmu->dev,
+ cfg->num_l1_ents *
+ (STRTAB_L1_DESC_DWORDS << 3),
+ strtab,
+ cfg->strtab_dma);
+ return ret;
+}
+
+static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
+{
+ void *strtab;
+ u64 reg;
+ u32 size;
+ 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);
+ if (!strtab) {
+ dev_err(smmu->dev,
+ "failed to allocate linear stream table (%u bytes)\n",
+ size);
+ return -ENOMEM;
+ }
+ cfg->strtab = strtab;
+ cfg->num_l1_ents = 1 << smmu->sid_bits;
+
+ /* Configure strtab_base_cfg for a linear table covering all SIDs */
+ reg = STRTAB_BASE_CFG_FMT_LINEAR;
+ reg |= (smmu->sid_bits & STRTAB_BASE_CFG_LOG2SIZE_MASK)
+ << STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
+ cfg->strtab_base_cfg = reg;
+
+ arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents);
+ return 0;
+}
+
+static int arm_smmu_init_strtab(struct arm_smmu_device *smmu)
+{
+ u64 reg;
+ int ret;
+
+ if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+ ret = arm_smmu_init_strtab_2lvl(smmu);
+ else
+ ret = arm_smmu_init_strtab_linear(smmu);
+
+ if (ret)
+ return ret;
+
+ /* Set the strtab base address */
+ reg = smmu->strtab_cfg.strtab_dma &
+ STRTAB_BASE_ADDR_MASK << STRTAB_BASE_ADDR_SHIFT;
+ reg |= STRTAB_BASE_RA;
+ smmu->strtab_cfg.strtab_base = reg;
+
+ /* Allocate the first VMID for stage-2 bypass STEs */
+ set_bit(0, smmu->vmid_map);
+ 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;
+
+ ret = arm_smmu_init_queues(smmu);
+ 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);
+}
+
+static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
+ unsigned int reg_off, unsigned int ack_off)
+{
+ u32 reg;
+
+ writel_relaxed(val, smmu->base + reg_off);
+ return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
+ 1, ARM_SMMU_POLL_TIMEOUT_US);
+}
+
+static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
+{
+ int ret, irq;
+
+ /* Disable IRQs first */
+ ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
+ ARM_SMMU_IRQ_CTRLACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to disable irqs\n");
+ 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);
+
+ /* Request wired interrupt lines */
+ irq = smmu->evtq.q.irq;
+ if (irq) {
+ ret = devm_request_threaded_irq(smmu->dev, irq,
+ arm_smmu_evtq_handler,
+ arm_smmu_evtq_thread,
+ 0, "arm-smmu-v3-evtq", smmu);
+ if (IS_ERR_VALUE(ret))
+ dev_warn(smmu->dev, "failed to enable evtq irq\n");
+ }
+
+ irq = smmu->cmdq.q.irq;
+ if (irq) {
+ ret = devm_request_irq(smmu->dev, irq,
+ arm_smmu_cmdq_sync_handler, 0,
+ "arm-smmu-v3-cmdq-sync", smmu);
+ if (IS_ERR_VALUE(ret))
+ dev_warn(smmu->dev, "failed to enable cmdq-sync irq\n");
+ }
+
+ irq = smmu->gerr_irq;
+ if (irq) {
+ ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
+ 0, "arm-smmu-v3-gerror", smmu);
+ if (IS_ERR_VALUE(ret))
+ dev_warn(smmu->dev, "failed to enable gerror irq\n");
+ }
+
+ 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,
+ arm_smmu_priq_handler,
+ arm_smmu_priq_thread,
+ 0, "arm-smmu-v3-priq",
+ smmu);
+ if (IS_ERR_VALUE(ret))
+ dev_warn(smmu->dev,
+ "failed to enable priq irq\n");
+ }
+ }
+
+ /* Enable interrupt generation on the SMMU */
+ ret = arm_smmu_write_reg_sync(smmu,
+ IRQ_CTRL_EVTQ_IRQEN |
+ IRQ_CTRL_GERROR_IRQEN,
+ ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
+ if (ret)
+ dev_warn(smmu->dev, "failed to enable irqs\n");
+
+ return 0;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
+{
+ int ret;
+
+ ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
+ if (ret)
+ dev_err(smmu->dev, "failed to clear cr0\n");
+
+ return ret;
+}
+
+static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
+{
+ int ret;
+ u32 reg, enables;
+ struct arm_smmu_cmdq_ent cmd;
+
+ /* Clear CR0 and sync (disables SMMU and queue processing) */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
+ if (reg & CR0_SMMUEN)
+ dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
+
+ ret = arm_smmu_device_disable(smmu);
+ if (ret)
+ return ret;
+
+ /* CR1 (table and queue memory attributes) */
+ reg = (CR1_SH_ISH << CR1_TABLE_SH_SHIFT) |
+ (CR1_CACHE_WB << CR1_TABLE_OC_SHIFT) |
+ (CR1_CACHE_WB << CR1_TABLE_IC_SHIFT) |
+ (CR1_SH_ISH << CR1_QUEUE_SH_SHIFT) |
+ (CR1_CACHE_WB << CR1_QUEUE_OC_SHIFT) |
+ (CR1_CACHE_WB << CR1_QUEUE_IC_SHIFT);
+ writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
+
+ /* CR2 (random crap) */
+ reg = CR2_PTM | CR2_RECINVSID | CR2_E2H;
+ writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
+
+ /* Stream table */
+ writeq_relaxed(smmu->strtab_cfg.strtab_base,
+ smmu->base + ARM_SMMU_STRTAB_BASE);
+ writel_relaxed(smmu->strtab_cfg.strtab_base_cfg,
+ smmu->base + ARM_SMMU_STRTAB_BASE_CFG);
+
+ /* Command queue */
+ writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
+ writel_relaxed(smmu->cmdq.q.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
+ writel_relaxed(smmu->cmdq.q.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
+
+ enables = CR0_CMDQEN;
+ ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to enable command queue\n");
+ return ret;
+ }
+
+ /* Invalidate any cached configuration */
+ cmd.opcode = CMDQ_OP_CFGI_ALL;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ cmd.opcode = CMDQ_OP_CMD_SYNC;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+
+ /* Invalidate any stale TLB entries */
+ if (smmu->features & ARM_SMMU_FEAT_HYP) {
+ cmd.opcode = CMDQ_OP_TLBI_EL2_ALL;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ }
+
+ cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+ cmd.opcode = CMDQ_OP_CMD_SYNC;
+ arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+
+ /* Event queue */
+ writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
+ writel_relaxed(smmu->evtq.q.prod, smmu->base + ARM_SMMU_EVTQ_PROD);
+ writel_relaxed(smmu->evtq.q.cons, smmu->base + ARM_SMMU_EVTQ_CONS);
+
+ enables |= CR0_EVTQEN;
+ ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to enable event queue\n");
+ return ret;
+ }
+
+ /* PRI queue */
+ if (smmu->features & ARM_SMMU_FEAT_PRI) {
+ writeq_relaxed(smmu->priq.q.q_base,
+ smmu->base + ARM_SMMU_PRIQ_BASE);
+ writel_relaxed(smmu->priq.q.prod,
+ smmu->base + ARM_SMMU_PRIQ_PROD);
+ writel_relaxed(smmu->priq.q.cons,
+ smmu->base + ARM_SMMU_PRIQ_CONS);
+
+ enables |= CR0_PRIQEN;
+ ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to enable PRI queue\n");
+ return ret;
+ }
+ }
+
+ ret = arm_smmu_setup_irqs(smmu);
+ if (ret) {
+ dev_err(smmu->dev, "failed to setup irqs\n");
+ return ret;
+ }
+
+ /* Enable the SMMU interface */
+ enables |= CR0_SMMUEN;
+ ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+ ARM_SMMU_CR0ACK);
+ if (ret) {
+ dev_err(smmu->dev, "failed to enable SMMU interface\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
+{
+ u32 reg;
+ bool coherent;
+ unsigned long pgsize_bitmap = 0;
+
+ /* IDR0 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
+
+ /* 2-level structures */
+ if ((reg & IDR0_ST_LVL_MASK << IDR0_ST_LVL_SHIFT) == IDR0_ST_LVL_2LVL)
+ smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;
+
+ if (reg & IDR0_CD2L)
+ smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;
+
+ /*
+ * Translation table endianness.
+ * We currently require the same endianness as the CPU, but this
+ * could be changed later by adding a new IO_PGTABLE_QUIRK.
+ */
+ switch (reg & IDR0_TTENDIAN_MASK << IDR0_TTENDIAN_SHIFT) {
+ case IDR0_TTENDIAN_MIXED:
+ smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
+ break;
+#ifdef __BIG_ENDIAN
+ case IDR0_TTENDIAN_BE:
+ smmu->features |= ARM_SMMU_FEAT_TT_BE;
+ break;
+#else
+ case IDR0_TTENDIAN_LE:
+ smmu->features |= ARM_SMMU_FEAT_TT_LE;
+ break;
+#endif
+ default:
+ dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
+ return -ENXIO;
+ }
+
+ /* Boolean feature flags */
+ if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
+ smmu->features |= ARM_SMMU_FEAT_PRI;
+
+ if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
+ smmu->features |= ARM_SMMU_FEAT_ATS;
+
+ if (reg & IDR0_SEV)
+ smmu->features |= ARM_SMMU_FEAT_SEV;
+
+ if (reg & IDR0_MSI)
+ smmu->features |= ARM_SMMU_FEAT_MSI;
+
+ if (reg & IDR0_HYP)
+ smmu->features |= ARM_SMMU_FEAT_HYP;
+
+ /*
+ * The dma-coherent property 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");
+
+ if (reg & IDR0_STALL_MODEL)
+ smmu->features |= ARM_SMMU_FEAT_STALLS;
+
+ if (reg & IDR0_S1P)
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+
+ if (reg & IDR0_S2P)
+ smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+
+ if (!(reg & (IDR0_S1P | IDR0_S2P))) {
+ dev_err(smmu->dev, "no translation support!\n");
+ return -ENXIO;
+ }
+
+ /* We only support the AArch64 table format at present */
+ if ((reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) < IDR0_TTF_AARCH64) {
+ dev_err(smmu->dev, "AArch64 table format not supported!\n");
+ return -ENXIO;
+ }
+
+ /* ASID/VMID sizes */
+ smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
+ smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;
+
+ /* IDR1 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
+ if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
+ dev_err(smmu->dev, "embedded implementation not supported\n");
+ return -ENXIO;
+ }
+
+ /* Queue sizes, capped at 4k */
+ smmu->cmdq.q.max_n_shift = min((u32)CMDQ_MAX_SZ_SHIFT,
+ reg >> IDR1_CMDQ_SHIFT & IDR1_CMDQ_MASK);
+ if (!smmu->cmdq.q.max_n_shift) {
+ /* Odd alignment restrictions on the base, so ignore for now */
+ dev_err(smmu->dev, "unit-length command queue not supported\n");
+ return -ENXIO;
+ }
+
+ smmu->evtq.q.max_n_shift = min((u32)EVTQ_MAX_SZ_SHIFT,
+ reg >> IDR1_EVTQ_SHIFT & IDR1_EVTQ_MASK);
+ smmu->priq.q.max_n_shift = min((u32)PRIQ_MAX_SZ_SHIFT,
+ reg >> IDR1_PRIQ_SHIFT & IDR1_PRIQ_MASK);
+
+ /* SID/SSID sizes */
+ smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
+ smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
+
+ /* IDR5 */
+ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
+
+ /* Maximum number of outstanding stalls */
+ smmu->evtq.max_stalls = reg >> IDR5_STALL_MAX_SHIFT
+ & IDR5_STALL_MAX_MASK;
+
+ /* Page sizes */
+ if (reg & IDR5_GRAN64K)
+ pgsize_bitmap |= SZ_64K | SZ_512M;
+ if (reg & IDR5_GRAN16K)
+ pgsize_bitmap |= SZ_16K | SZ_32M;
+ if (reg & IDR5_GRAN4K)
+ pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+
+ arm_smmu_ops.pgsize_bitmap &= pgsize_bitmap;
+
+ /* Output address size */
+ switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) {
+ case IDR5_OAS_32_BIT:
+ smmu->oas = 32;
+ break;
+ case IDR5_OAS_36_BIT:
+ smmu->oas = 36;
+ break;
+ case IDR5_OAS_40_BIT:
+ smmu->oas = 40;
+ break;
+ case IDR5_OAS_42_BIT:
+ smmu->oas = 42;
+ break;
+ case IDR5_OAS_44_BIT:
+ smmu->oas = 44;
+ break;
+ case IDR5_OAS_48_BIT:
+ smmu->oas = 48;
+ break;
+ default:
+ dev_err(smmu->dev, "unknown output address size!\n");
+ return -ENXIO;
+ }
+
+ /* Set the DMA mask for our table walker */
+ if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
+ dev_warn(smmu->dev,
+ "failed to set DMA mask for table walker\n");
+
+ if (!smmu->ias)
+ smmu->ias = smmu->oas;
+
+ dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
+ smmu->ias, smmu->oas, smmu->features);
+ return 0;
+}
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+{
+ int irq, ret;
+ struct resource *res;
+ struct arm_smmu_device *smmu;
+ struct device *dev = &pdev->dev;
+
+ smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+ if (!smmu) {
+ dev_err(dev, "failed to allocate arm_smmu_device\n");
+ return -ENOMEM;
+ }
+ smmu->dev = dev;
+
+ /* Base address */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (resource_size(res) + 1 < SZ_128K) {
+ dev_err(dev, "MMIO region too small (%pr)\n", res);
+ return -EINVAL;
+ }
+
+ smmu->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(smmu->base))
+ return PTR_ERR(smmu->base);
+
+ /* Interrupt lines */
+ irq = platform_get_irq_byname(pdev, "eventq");
+ if (irq > 0)
+ smmu->evtq.q.irq = irq;
+
+ irq = platform_get_irq_byname(pdev, "priq");
+ if (irq > 0)
+ smmu->priq.q.irq = irq;
+
+ irq = platform_get_irq_byname(pdev, "cmdq-sync");
+ if (irq > 0)
+ smmu->cmdq.q.irq = irq;
+
+ irq = platform_get_irq_byname(pdev, "gerror");
+ if (irq > 0)
+ smmu->gerr_irq = irq;
+
+ /* Probe the h/w */
+ ret = arm_smmu_device_probe(smmu);
+ if (ret)
+ return ret;
+
+ /* Initialise in-memory data structures */
+ ret = arm_smmu_init_structures(smmu);
+ 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;
+
+out_free_structures:
+ arm_smmu_free_structures(smmu);
+ return ret;
+}
+
+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;
+
+ arm_smmu_device_disable(smmu);
+ arm_smmu_free_structures(smmu);
+ return 0;
+}
+
+static struct of_device_id arm_smmu_of_match[] = {
+ { .compatible = "arm,smmu-v3", },
+ { },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
+static struct platform_driver arm_smmu_driver = {
+ .driver = {
+ .name = "arm-smmu-v3",
+ .of_match_table = of_match_ptr(arm_smmu_of_match),
+ },
+ .probe = arm_smmu_device_dt_probe,
+ .remove = arm_smmu_device_remove,
+};
+
+static int __init arm_smmu_init(void)
+{
+ struct device_node *np;
+ int ret;
+
+ np = of_find_matching_node(NULL, arm_smmu_of_match);
+ if (!np)
+ return 0;
+
+ of_node_put(np);
+
+ ret = platform_driver_register(&arm_smmu_driver);
+ if (ret)
+ return ret;
+
+ return bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+}
+
+static void __exit arm_smmu_exit(void)
+{
+ return platform_driver_unregister(&arm_smmu_driver);
+}
+
+subsys_initcall(arm_smmu_init);
+module_exit(arm_smmu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 66a803b..dce041b 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -202,8 +202,7 @@
#define ARM_SMMU_CB_S1_TLBIVAL 0x620
#define ARM_SMMU_CB_S2_TLBIIPAS2 0x630
#define ARM_SMMU_CB_S2_TLBIIPAS2L 0x638
-#define ARM_SMMU_CB_ATS1PR_LO 0x800
-#define ARM_SMMU_CB_ATS1PR_HI 0x804
+#define ARM_SMMU_CB_ATS1PR 0x800
#define ARM_SMMU_CB_ATSR 0x8f0
#define SCTLR_S1_ASIDPNE (1 << 12)
@@ -247,7 +246,7 @@
#define FSYNR0_WNR (1 << 4)
static int force_stage;
-module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+module_param_named(force_stage, force_stage, int, S_IRUGO);
MODULE_PARM_DESC(force_stage,
"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
@@ -1229,18 +1228,18 @@
void __iomem *cb_base;
u32 tmp;
u64 phys;
+ unsigned long va;
cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
- if (smmu->version == 1) {
- u32 reg = iova & ~0xfff;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
- } else {
- u32 reg = iova & ~0xfff;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
- reg = ((u64)iova & ~0xfff) >> 32;
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_HI);
- }
+ /* ATS1 registers can only be written atomically */
+ va = iova & ~0xfffUL;
+#ifdef CONFIG_64BIT
+ if (smmu->version == ARM_SMMU_V2)
+ writeq_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
+ else
+#endif
+ writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
!(tmp & ATSR_ACTIVE), 5, 50)) {
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 3e89850..97c41b8 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -12,21 +12,22 @@
#define DEBUG
#endif
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/pm_runtime.h>
#include <linux/clk.h>
+#include <linux/dma-mapping.h>
#include <linux/err.h>
-#include <linux/mm.h>
+#include <linux/io.h>
#include <linux/iommu.h>
-#include <linux/errno.h>
+#include <linux/interrupt.h>
#include <linux/list.h>
-#include <linux/memblock.h>
-#include <linux/export.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 <asm/cacheflush.h>
+#include <asm/dma-iommu.h>
#include <asm/pgtable.h>
typedef u32 sysmmu_iova_t;
@@ -184,35 +185,50 @@
"UNKNOWN FAULT"
};
-/* attached to dev.archdata.iommu of the master device */
+/*
+ * This structure is attached to dev.archdata.iommu of the master device
+ * on device add, contains a list of SYSMMU controllers defined by device tree,
+ * which are bound to given master device. It is usually referenced by 'owner'
+ * pointer.
+*/
struct exynos_iommu_owner {
- struct list_head client; /* entry of exynos_iommu_domain.clients */
- struct device *dev;
- struct device *sysmmu;
- struct iommu_domain *domain;
- void *vmm_data; /* IO virtual memory manager's data */
- spinlock_t lock; /* Lock to preserve consistency of System MMU */
+ struct list_head controllers; /* list of sysmmu_drvdata.owner_node */
};
+/*
+ * This structure exynos specific generalization of struct iommu_domain.
+ * It contains list of SYSMMU controllers from all master devices, which has
+ * been attached to this domain and page tables of IO address space defined by
+ * it. It is usually referenced by 'domain' pointer.
+ */
struct exynos_iommu_domain {
- struct list_head clients; /* list of sysmmu_drvdata.node */
- sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */
- short *lv2entcnt; /* free lv2 entry counter for each section */
- spinlock_t lock; /* lock for this structure */
- spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
+ struct list_head clients; /* list of sysmmu_drvdata.domain_node */
+ sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */
+ short *lv2entcnt; /* free lv2 entry counter for each section */
+ spinlock_t lock; /* lock for modyfying list of clients */
+ spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
struct iommu_domain domain; /* generic domain data structure */
};
+/*
+ * This structure hold all data of a single SYSMMU controller, this includes
+ * hw resources like registers and clocks, pointers and list nodes to connect
+ * it to all other structures, internal state and parameters read from device
+ * tree. It is usually referenced by 'data' pointer.
+ */
struct sysmmu_drvdata {
- struct device *sysmmu; /* System MMU's device descriptor */
- struct device *master; /* Owner of system MMU */
- void __iomem *sfrbase;
- struct clk *clk;
- struct clk *clk_master;
- int activations;
- spinlock_t lock;
- struct iommu_domain *domain;
- phys_addr_t pgtable;
+ struct device *sysmmu; /* SYSMMU controller device */
+ struct device *master; /* master device (owner) */
+ void __iomem *sfrbase; /* our registers */
+ struct clk *clk; /* SYSMMU's clock */
+ struct clk *clk_master; /* master's device clock */
+ int activations; /* number of calls to sysmmu_enable */
+ spinlock_t lock; /* lock for modyfying state */
+ struct exynos_iommu_domain *domain; /* domain we belong to */
+ struct list_head domain_node; /* node for domain clients list */
+ struct list_head owner_node; /* node for owner controllers list */
+ phys_addr_t pgtable; /* assigned page table structure */
+ unsigned int version; /* our version */
};
static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
@@ -244,11 +260,6 @@
__raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL);
}
-static unsigned int __raw_sysmmu_version(struct sysmmu_drvdata *data)
-{
- return MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
-}
-
static bool sysmmu_block(void __iomem *sfrbase)
{
int i = 120;
@@ -345,7 +356,7 @@
show_fault_information(dev_name(data->sysmmu),
itype, base, addr);
if (data->domain)
- ret = report_iommu_fault(data->domain,
+ ret = report_iommu_fault(&data->domain->domain,
data->master, addr, itype);
}
@@ -408,7 +419,7 @@
unsigned int cfg = CFG_LRU | CFG_QOS(15);
unsigned int ver;
- ver = __raw_sysmmu_version(data);
+ ver = MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
if (MMU_MAJ_VER(ver) == 3) {
if (MMU_MIN_VER(ver) >= 2) {
cfg |= CFG_FLPDCACHE;
@@ -422,6 +433,7 @@
}
__raw_writel(cfg, data->sfrbase + REG_MMU_CFG);
+ data->version = ver;
}
static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
@@ -442,8 +454,8 @@
clk_disable(data->clk_master);
}
-static int __sysmmu_enable(struct sysmmu_drvdata *data,
- phys_addr_t pgtable, struct iommu_domain *domain)
+static int __sysmmu_enable(struct sysmmu_drvdata *data, phys_addr_t pgtable,
+ struct exynos_iommu_domain *domain)
{
int ret = 0;
unsigned long flags;
@@ -470,77 +482,17 @@
return ret;
}
-/* __exynos_sysmmu_enable: Enables System MMU
- *
- * returns -error if an error occurred and System MMU is not enabled,
- * 0 if the System MMU has been just enabled and 1 if System MMU was already
- * enabled before.
- */
-static int __exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable,
- struct iommu_domain *domain)
-{
- int ret = 0;
- unsigned long flags;
- struct exynos_iommu_owner *owner = dev->archdata.iommu;
- struct sysmmu_drvdata *data;
-
- BUG_ON(!has_sysmmu(dev));
-
- spin_lock_irqsave(&owner->lock, flags);
-
- data = dev_get_drvdata(owner->sysmmu);
-
- ret = __sysmmu_enable(data, pgtable, domain);
- if (ret >= 0)
- data->master = dev;
-
- spin_unlock_irqrestore(&owner->lock, flags);
-
- return ret;
-}
-
-int exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable)
-{
- BUG_ON(!memblock_is_memory(pgtable));
-
- return __exynos_sysmmu_enable(dev, pgtable, NULL);
-}
-
-static bool exynos_sysmmu_disable(struct device *dev)
-{
- unsigned long flags;
- bool disabled = true;
- struct exynos_iommu_owner *owner = dev->archdata.iommu;
- struct sysmmu_drvdata *data;
-
- BUG_ON(!has_sysmmu(dev));
-
- spin_lock_irqsave(&owner->lock, flags);
-
- data = dev_get_drvdata(owner->sysmmu);
-
- disabled = __sysmmu_disable(data);
- if (disabled)
- data->master = NULL;
-
- spin_unlock_irqrestore(&owner->lock, flags);
-
- return disabled;
-}
-
static void __sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
sysmmu_iova_t iova)
{
- if (__raw_sysmmu_version(data) == MAKE_MMU_VER(3, 3))
+ if (data->version == MAKE_MMU_VER(3, 3))
__raw_writel(iova | 0x1, data->sfrbase + REG_MMU_FLUSH_ENTRY);
}
-static void sysmmu_tlb_invalidate_flpdcache(struct device *dev,
+static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
sysmmu_iova_t iova)
{
unsigned long flags;
- struct exynos_iommu_owner *owner = dev->archdata.iommu;
- struct sysmmu_drvdata *data = dev_get_drvdata(owner->sysmmu);
if (!IS_ERR(data->clk_master))
clk_enable(data->clk_master);
@@ -554,14 +506,10 @@
clk_disable(data->clk_master);
}
-static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
- size_t size)
+static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
+ sysmmu_iova_t iova, size_t size)
{
- struct exynos_iommu_owner *owner = dev->archdata.iommu;
unsigned long flags;
- struct sysmmu_drvdata *data;
-
- data = dev_get_drvdata(owner->sysmmu);
spin_lock_irqsave(&data->lock, flags);
if (is_sysmmu_active(data)) {
@@ -580,7 +528,7 @@
* 1MB page can be cached in one of all sets.
* 64KB page can be one of 16 consecutive sets.
*/
- if (MMU_MAJ_VER(__raw_sysmmu_version(data)) == 2)
+ if (MMU_MAJ_VER(data->version) == 2)
num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);
if (sysmmu_block(data->sfrbase)) {
@@ -591,32 +539,8 @@
if (!IS_ERR(data->clk_master))
clk_disable(data->clk_master);
} else {
- dev_dbg(dev, "disabled. Skipping TLB invalidation @ %#x\n",
- iova);
- }
- spin_unlock_irqrestore(&data->lock, flags);
-}
-
-void exynos_sysmmu_tlb_invalidate(struct device *dev)
-{
- struct exynos_iommu_owner *owner = dev->archdata.iommu;
- unsigned long flags;
- struct sysmmu_drvdata *data;
-
- data = dev_get_drvdata(owner->sysmmu);
-
- spin_lock_irqsave(&data->lock, flags);
- if (is_sysmmu_active(data)) {
- if (!IS_ERR(data->clk_master))
- clk_enable(data->clk_master);
- if (sysmmu_block(data->sfrbase)) {
- __sysmmu_tlb_invalidate(data->sfrbase);
- sysmmu_unblock(data->sfrbase);
- }
- if (!IS_ERR(data->clk_master))
- clk_disable(data->clk_master);
- } else {
- dev_dbg(dev, "disabled. Skipping TLB invalidation\n");
+ dev_dbg(data->master,
+ "disabled. Skipping TLB invalidation @ %#x\n", iova);
}
spin_unlock_irqrestore(&data->lock, flags);
}
@@ -682,6 +606,36 @@
return 0;
}
+#ifdef CONFIG_PM_SLEEP
+static int exynos_sysmmu_suspend(struct device *dev)
+{
+ struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+
+ dev_dbg(dev, "suspend\n");
+ if (is_sysmmu_active(data)) {
+ __sysmmu_disable_nocount(data);
+ pm_runtime_put(dev);
+ }
+ return 0;
+}
+
+static int exynos_sysmmu_resume(struct device *dev)
+{
+ struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+
+ dev_dbg(dev, "resume\n");
+ if (is_sysmmu_active(data)) {
+ pm_runtime_get_sync(dev);
+ __sysmmu_enable_nocount(data);
+ }
+ return 0;
+}
+#endif
+
+static const struct dev_pm_ops sysmmu_pm_ops = {
+ SET_LATE_SYSTEM_SLEEP_PM_OPS(exynos_sysmmu_suspend, exynos_sysmmu_resume)
+};
+
static const struct of_device_id sysmmu_of_match[] __initconst = {
{ .compatible = "samsung,exynos-sysmmu", },
{ },
@@ -692,6 +646,7 @@
.driver = {
.name = "exynos-sysmmu",
.of_match_table = sysmmu_of_match,
+ .pm = &sysmmu_pm_ops,
}
};
@@ -704,105 +659,109 @@
static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
{
- struct exynos_iommu_domain *exynos_domain;
+ struct exynos_iommu_domain *domain;
int i;
if (type != IOMMU_DOMAIN_UNMANAGED)
return NULL;
- exynos_domain = kzalloc(sizeof(*exynos_domain), GFP_KERNEL);
- if (!exynos_domain)
+ domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+ if (!domain)
return NULL;
- exynos_domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
- if (!exynos_domain->pgtable)
+ domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
+ if (!domain->pgtable)
goto err_pgtable;
- exynos_domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
- if (!exynos_domain->lv2entcnt)
+ domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+ if (!domain->lv2entcnt)
goto err_counter;
/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
- exynos_domain->pgtable[i + 0] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 1] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 2] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 3] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 4] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 5] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 6] = ZERO_LV2LINK;
- exynos_domain->pgtable[i + 7] = ZERO_LV2LINK;
+ domain->pgtable[i + 0] = ZERO_LV2LINK;
+ domain->pgtable[i + 1] = ZERO_LV2LINK;
+ domain->pgtable[i + 2] = ZERO_LV2LINK;
+ domain->pgtable[i + 3] = ZERO_LV2LINK;
+ domain->pgtable[i + 4] = ZERO_LV2LINK;
+ domain->pgtable[i + 5] = ZERO_LV2LINK;
+ domain->pgtable[i + 6] = ZERO_LV2LINK;
+ domain->pgtable[i + 7] = ZERO_LV2LINK;
}
- pgtable_flush(exynos_domain->pgtable, exynos_domain->pgtable + NUM_LV1ENTRIES);
+ pgtable_flush(domain->pgtable, domain->pgtable + NUM_LV1ENTRIES);
- spin_lock_init(&exynos_domain->lock);
- spin_lock_init(&exynos_domain->pgtablelock);
- INIT_LIST_HEAD(&exynos_domain->clients);
+ spin_lock_init(&domain->lock);
+ spin_lock_init(&domain->pgtablelock);
+ INIT_LIST_HEAD(&domain->clients);
- exynos_domain->domain.geometry.aperture_start = 0;
- exynos_domain->domain.geometry.aperture_end = ~0UL;
- exynos_domain->domain.geometry.force_aperture = true;
+ domain->domain.geometry.aperture_start = 0;
+ domain->domain.geometry.aperture_end = ~0UL;
+ domain->domain.geometry.force_aperture = true;
- return &exynos_domain->domain;
+ return &domain->domain;
err_counter:
- free_pages((unsigned long)exynos_domain->pgtable, 2);
+ free_pages((unsigned long)domain->pgtable, 2);
err_pgtable:
- kfree(exynos_domain);
+ kfree(domain);
return NULL;
}
-static void exynos_iommu_domain_free(struct iommu_domain *domain)
+static void exynos_iommu_domain_free(struct iommu_domain *iommu_domain)
{
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
- struct exynos_iommu_owner *owner;
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+ struct sysmmu_drvdata *data, *next;
unsigned long flags;
int i;
- WARN_ON(!list_empty(&priv->clients));
+ WARN_ON(!list_empty(&domain->clients));
- spin_lock_irqsave(&priv->lock, flags);
+ spin_lock_irqsave(&domain->lock, flags);
- list_for_each_entry(owner, &priv->clients, client) {
- while (!exynos_sysmmu_disable(owner->dev))
- ; /* until System MMU is actually disabled */
+ list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+ if (__sysmmu_disable(data))
+ data->master = NULL;
+ list_del_init(&data->domain_node);
}
- while (!list_empty(&priv->clients))
- list_del_init(priv->clients.next);
-
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&domain->lock, flags);
for (i = 0; i < NUM_LV1ENTRIES; i++)
- if (lv1ent_page(priv->pgtable + i))
+ if (lv1ent_page(domain->pgtable + i))
kmem_cache_free(lv2table_kmem_cache,
- phys_to_virt(lv2table_base(priv->pgtable + i)));
+ phys_to_virt(lv2table_base(domain->pgtable + i)));
- free_pages((unsigned long)priv->pgtable, 2);
- free_pages((unsigned long)priv->lv2entcnt, 1);
- kfree(priv);
+ free_pages((unsigned long)domain->pgtable, 2);
+ free_pages((unsigned long)domain->lv2entcnt, 1);
+ kfree(domain);
}
-static int exynos_iommu_attach_device(struct iommu_domain *domain,
+static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
struct device *dev)
{
struct exynos_iommu_owner *owner = dev->archdata.iommu;
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
- phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+ struct sysmmu_drvdata *data;
+ phys_addr_t pagetable = virt_to_phys(domain->pgtable);
unsigned long flags;
- int ret;
+ int ret = -ENODEV;
- spin_lock_irqsave(&priv->lock, flags);
+ if (!has_sysmmu(dev))
+ return -ENODEV;
- ret = __exynos_sysmmu_enable(dev, pagetable, domain);
- if (ret == 0) {
- list_add_tail(&owner->client, &priv->clients);
- owner->domain = domain;
+ list_for_each_entry(data, &owner->controllers, owner_node) {
+ pm_runtime_get_sync(data->sysmmu);
+ ret = __sysmmu_enable(data, pagetable, domain);
+ if (ret >= 0) {
+ data->master = dev;
+
+ spin_lock_irqsave(&domain->lock, flags);
+ list_add_tail(&data->domain_node, &domain->clients);
+ spin_unlock_irqrestore(&domain->lock, flags);
+ }
}
- spin_unlock_irqrestore(&priv->lock, flags);
-
if (ret < 0) {
dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
__func__, &pagetable);
@@ -815,36 +774,39 @@
return ret;
}
-static void exynos_iommu_detach_device(struct iommu_domain *domain,
+static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain,
struct device *dev)
{
- struct exynos_iommu_owner *owner;
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
- phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+ phys_addr_t pagetable = virt_to_phys(domain->pgtable);
+ struct sysmmu_drvdata *data, *next;
unsigned long flags;
+ bool found = false;
- spin_lock_irqsave(&priv->lock, flags);
+ if (!has_sysmmu(dev))
+ return;
- list_for_each_entry(owner, &priv->clients, client) {
- if (owner == dev->archdata.iommu) {
- if (exynos_sysmmu_disable(dev)) {
- list_del_init(&owner->client);
- owner->domain = NULL;
+ spin_lock_irqsave(&domain->lock, flags);
+ list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+ if (data->master == dev) {
+ if (__sysmmu_disable(data)) {
+ data->master = NULL;
+ list_del_init(&data->domain_node);
}
- break;
+ pm_runtime_put(data->sysmmu);
+ found = true;
}
}
+ spin_unlock_irqrestore(&domain->lock, flags);
- spin_unlock_irqrestore(&priv->lock, flags);
-
- if (owner == dev->archdata.iommu)
+ if (found)
dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
__func__, &pagetable);
else
dev_err(dev, "%s: No IOMMU is attached\n", __func__);
}
-static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
+static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
sysmmu_pte_t *sent, sysmmu_iova_t iova, short *pgcounter)
{
if (lv1ent_section(sent)) {
@@ -862,6 +824,7 @@
return ERR_PTR(-ENOMEM);
*sent = mk_lv1ent_page(virt_to_phys(pent));
+ kmemleak_ignore(pent);
*pgcounter = NUM_LV2ENTRIES;
pgtable_flush(pent, pent + NUM_LV2ENTRIES);
pgtable_flush(sent, sent + 1);
@@ -884,20 +847,19 @@
* not currently mapped.
*/
if (need_flush_flpd_cache) {
- struct exynos_iommu_owner *owner;
+ struct sysmmu_drvdata *data;
- spin_lock(&priv->lock);
- list_for_each_entry(owner, &priv->clients, client)
- sysmmu_tlb_invalidate_flpdcache(
- owner->dev, iova);
- spin_unlock(&priv->lock);
+ spin_lock(&domain->lock);
+ list_for_each_entry(data, &domain->clients, domain_node)
+ sysmmu_tlb_invalidate_flpdcache(data, iova);
+ spin_unlock(&domain->lock);
}
}
return page_entry(sent, iova);
}
-static int lv1set_section(struct exynos_iommu_domain *priv,
+static int lv1set_section(struct exynos_iommu_domain *domain,
sysmmu_pte_t *sent, sysmmu_iova_t iova,
phys_addr_t paddr, short *pgcnt)
{
@@ -922,17 +884,17 @@
pgtable_flush(sent, sent + 1);
- spin_lock(&priv->lock);
+ spin_lock(&domain->lock);
if (lv1ent_page_zero(sent)) {
- struct exynos_iommu_owner *owner;
+ struct sysmmu_drvdata *data;
/*
* Flushing FLPD cache in System MMU v3.3 that may cache a FLPD
* entry by speculative prefetch of SLPD which has no mapping.
*/
- list_for_each_entry(owner, &priv->clients, client)
- sysmmu_tlb_invalidate_flpdcache(owner->dev, iova);
+ list_for_each_entry(data, &domain->clients, domain_node)
+ sysmmu_tlb_invalidate_flpdcache(data, iova);
}
- spin_unlock(&priv->lock);
+ spin_unlock(&domain->lock);
return 0;
}
@@ -992,74 +954,75 @@
* than or equal to 128KiB.
* - Start address of an I/O virtual region must be aligned by 128KiB.
*/
-static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
- phys_addr_t paddr, size_t size, int prot)
+static int exynos_iommu_map(struct iommu_domain *iommu_domain,
+ unsigned long l_iova, phys_addr_t paddr, size_t size,
+ int prot)
{
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
sysmmu_pte_t *entry;
sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
unsigned long flags;
int ret = -ENOMEM;
- BUG_ON(priv->pgtable == NULL);
+ BUG_ON(domain->pgtable == NULL);
- spin_lock_irqsave(&priv->pgtablelock, flags);
+ spin_lock_irqsave(&domain->pgtablelock, flags);
- entry = section_entry(priv->pgtable, iova);
+ entry = section_entry(domain->pgtable, iova);
if (size == SECT_SIZE) {
- ret = lv1set_section(priv, entry, iova, paddr,
- &priv->lv2entcnt[lv1ent_offset(iova)]);
+ ret = lv1set_section(domain, entry, iova, paddr,
+ &domain->lv2entcnt[lv1ent_offset(iova)]);
} else {
sysmmu_pte_t *pent;
- pent = alloc_lv2entry(priv, entry, iova,
- &priv->lv2entcnt[lv1ent_offset(iova)]);
+ pent = alloc_lv2entry(domain, entry, iova,
+ &domain->lv2entcnt[lv1ent_offset(iova)]);
if (IS_ERR(pent))
ret = PTR_ERR(pent);
else
ret = lv2set_page(pent, paddr, size,
- &priv->lv2entcnt[lv1ent_offset(iova)]);
+ &domain->lv2entcnt[lv1ent_offset(iova)]);
}
if (ret)
pr_err("%s: Failed(%d) to map %#zx bytes @ %#x\n",
__func__, ret, size, iova);
- spin_unlock_irqrestore(&priv->pgtablelock, flags);
+ spin_unlock_irqrestore(&domain->pgtablelock, flags);
return ret;
}
-static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv,
- sysmmu_iova_t iova, size_t size)
+static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain,
+ sysmmu_iova_t iova, size_t size)
{
- struct exynos_iommu_owner *owner;
+ struct sysmmu_drvdata *data;
unsigned long flags;
- spin_lock_irqsave(&priv->lock, flags);
+ spin_lock_irqsave(&domain->lock, flags);
- list_for_each_entry(owner, &priv->clients, client)
- sysmmu_tlb_invalidate_entry(owner->dev, iova, size);
+ list_for_each_entry(data, &domain->clients, domain_node)
+ sysmmu_tlb_invalidate_entry(data, iova, size);
- spin_unlock_irqrestore(&priv->lock, flags);
+ spin_unlock_irqrestore(&domain->lock, flags);
}
-static size_t exynos_iommu_unmap(struct iommu_domain *domain,
- unsigned long l_iova, size_t size)
+static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
+ unsigned long l_iova, size_t size)
{
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
sysmmu_pte_t *ent;
size_t err_pgsize;
unsigned long flags;
- BUG_ON(priv->pgtable == NULL);
+ BUG_ON(domain->pgtable == NULL);
- spin_lock_irqsave(&priv->pgtablelock, flags);
+ spin_lock_irqsave(&domain->pgtablelock, flags);
- ent = section_entry(priv->pgtable, iova);
+ ent = section_entry(domain->pgtable, iova);
if (lv1ent_section(ent)) {
if (WARN_ON(size < SECT_SIZE)) {
@@ -1093,7 +1056,7 @@
*ent = 0;
size = SPAGE_SIZE;
pgtable_flush(ent, ent + 1);
- priv->lv2entcnt[lv1ent_offset(iova)] += 1;
+ domain->lv2entcnt[lv1ent_offset(iova)] += 1;
goto done;
}
@@ -1107,15 +1070,15 @@
pgtable_flush(ent, ent + SPAGES_PER_LPAGE);
size = LPAGE_SIZE;
- priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
+ domain->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
done:
- spin_unlock_irqrestore(&priv->pgtablelock, flags);
+ spin_unlock_irqrestore(&domain->pgtablelock, flags);
- exynos_iommu_tlb_invalidate_entry(priv, iova, size);
+ exynos_iommu_tlb_invalidate_entry(domain, iova, size);
return size;
err:
- spin_unlock_irqrestore(&priv->pgtablelock, flags);
+ spin_unlock_irqrestore(&domain->pgtablelock, flags);
pr_err("%s: Failed: size(%#zx) @ %#x is smaller than page size %#zx\n",
__func__, size, iova, err_pgsize);
@@ -1123,17 +1086,17 @@
return 0;
}
-static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
+static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
dma_addr_t iova)
{
- struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+ struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
sysmmu_pte_t *entry;
unsigned long flags;
phys_addr_t phys = 0;
- spin_lock_irqsave(&priv->pgtablelock, flags);
+ spin_lock_irqsave(&domain->pgtablelock, flags);
- entry = section_entry(priv->pgtable, iova);
+ entry = section_entry(domain->pgtable, iova);
if (lv1ent_section(entry)) {
phys = section_phys(entry) + section_offs(iova);
@@ -1146,7 +1109,7 @@
phys = spage_phys(entry) + spage_offs(iova);
}
- spin_unlock_irqrestore(&priv->pgtablelock, flags);
+ spin_unlock_irqrestore(&domain->pgtablelock, flags);
return phys;
}
@@ -1156,6 +1119,9 @@
struct iommu_group *group;
int ret;
+ if (!has_sysmmu(dev))
+ return -ENODEV;
+
group = iommu_group_get(dev);
if (!group) {
@@ -1174,10 +1140,40 @@
static void exynos_iommu_remove_device(struct device *dev)
{
+ if (!has_sysmmu(dev))
+ return;
+
iommu_group_remove_device(dev);
}
-static const struct iommu_ops exynos_iommu_ops = {
+static int exynos_iommu_of_xlate(struct device *dev,
+ struct of_phandle_args *spec)
+{
+ struct exynos_iommu_owner *owner = dev->archdata.iommu;
+ struct platform_device *sysmmu = of_find_device_by_node(spec->np);
+ struct sysmmu_drvdata *data;
+
+ if (!sysmmu)
+ return -ENODEV;
+
+ data = platform_get_drvdata(sysmmu);
+ if (!data)
+ return -ENODEV;
+
+ if (!owner) {
+ owner = kzalloc(sizeof(*owner), GFP_KERNEL);
+ if (!owner)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&owner->controllers);
+ dev->archdata.iommu = owner;
+ }
+
+ list_add_tail(&data->owner_node, &owner->controllers);
+ return 0;
+}
+
+static struct iommu_ops exynos_iommu_ops = {
.domain_alloc = exynos_iommu_domain_alloc,
.domain_free = exynos_iommu_domain_free,
.attach_dev = exynos_iommu_attach_device,
@@ -1189,19 +1185,15 @@
.add_device = exynos_iommu_add_device,
.remove_device = exynos_iommu_remove_device,
.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
+ .of_xlate = exynos_iommu_of_xlate,
};
+static bool init_done;
+
static int __init exynos_iommu_init(void)
{
- struct device_node *np;
int ret;
- np = of_find_matching_node(NULL, sysmmu_of_match);
- if (!np)
- return 0;
-
- of_node_put(np);
-
lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
if (!lv2table_kmem_cache) {
@@ -1230,6 +1222,8 @@
goto err_set_iommu;
}
+ init_done = true;
+
return 0;
err_set_iommu:
kmem_cache_free(lv2table_kmem_cache, zero_lv2_table);
@@ -1239,4 +1233,21 @@
kmem_cache_destroy(lv2table_kmem_cache);
return ret;
}
-subsys_initcall(exynos_iommu_init);
+
+static int __init exynos_iommu_of_setup(struct device_node *np)
+{
+ struct platform_device *pdev;
+
+ if (!init_done)
+ exynos_iommu_init();
+
+ pdev = of_platform_device_create(np, NULL, platform_bus_type.dev_root);
+ if (IS_ERR(pdev))
+ return PTR_ERR(pdev);
+
+ of_iommu_set_ops(np, &exynos_iommu_ops);
+ return 0;
+}
+
+IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu",
+ exynos_iommu_of_setup);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d4f527e..49e7542 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -16,7 +16,7 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#define pr_fmt(fmt) "%s: " fmt, __func__
+#define pr_fmt(fmt) "iommu: " fmt
#include <linux/device.h>
#include <linux/kernel.h>
@@ -51,6 +51,8 @@
void (*iommu_data_release)(void *iommu_data);
char *name;
int id;
+ struct iommu_domain *default_domain;
+ struct iommu_domain *domain;
};
struct iommu_device {
@@ -75,6 +77,15 @@
#define to_iommu_group(_kobj) \
container_of(_kobj, struct iommu_group, kobj)
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+ unsigned type);
+static int __iommu_attach_device(struct iommu_domain *domain,
+ struct device *dev);
+static int __iommu_attach_group(struct iommu_domain *domain,
+ struct iommu_group *group);
+static void __iommu_detach_group(struct iommu_domain *domain,
+ struct iommu_group *group);
+
static ssize_t iommu_group_attr_show(struct kobject *kobj,
struct attribute *__attr, char *buf)
{
@@ -128,6 +139,8 @@
{
struct iommu_group *group = to_iommu_group(kobj);
+ pr_debug("Releasing group %d\n", group->id);
+
if (group->iommu_data_release)
group->iommu_data_release(group->iommu_data);
@@ -135,6 +148,9 @@
ida_remove(&iommu_group_ida, group->id);
mutex_unlock(&iommu_group_mutex);
+ if (group->default_domain)
+ iommu_domain_free(group->default_domain);
+
kfree(group->name);
kfree(group);
}
@@ -207,6 +223,8 @@
*/
kobject_put(&group->kobj);
+ pr_debug("Allocated group %d\n", group->id);
+
return group;
}
EXPORT_SYMBOL_GPL(iommu_group_alloc);
@@ -307,6 +325,52 @@
}
EXPORT_SYMBOL_GPL(iommu_group_set_name);
+static int iommu_group_create_direct_mappings(struct iommu_group *group,
+ struct device *dev)
+{
+ struct iommu_domain *domain = group->default_domain;
+ struct iommu_dm_region *entry;
+ struct list_head mappings;
+ unsigned long pg_size;
+ int ret = 0;
+
+ if (!domain || domain->type != IOMMU_DOMAIN_DMA)
+ return 0;
+
+ BUG_ON(!domain->ops->pgsize_bitmap);
+
+ pg_size = 1UL << __ffs(domain->ops->pgsize_bitmap);
+ INIT_LIST_HEAD(&mappings);
+
+ iommu_get_dm_regions(dev, &mappings);
+
+ /* We need to consider overlapping regions for different devices */
+ list_for_each_entry(entry, &mappings, list) {
+ dma_addr_t start, end, addr;
+
+ start = ALIGN(entry->start, pg_size);
+ end = ALIGN(entry->start + entry->length, pg_size);
+
+ for (addr = start; addr < end; addr += pg_size) {
+ phys_addr_t phys_addr;
+
+ phys_addr = iommu_iova_to_phys(domain, addr);
+ if (phys_addr)
+ continue;
+
+ ret = iommu_map(domain, addr, addr, pg_size, entry->prot);
+ if (ret)
+ goto out;
+ }
+
+ }
+
+out:
+ iommu_put_dm_regions(dev, &mappings);
+
+ return ret;
+}
+
/**
* iommu_group_add_device - add a device to an iommu group
* @group: the group into which to add the device (reference should be held)
@@ -363,8 +427,12 @@
dev->iommu_group = group;
+ iommu_group_create_direct_mappings(group, dev);
+
mutex_lock(&group->mutex);
list_add_tail(&device->list, &group->devices);
+ if (group->domain)
+ __iommu_attach_device(group->domain, dev);
mutex_unlock(&group->mutex);
/* Notify any listeners about change to group. */
@@ -372,6 +440,9 @@
IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
trace_add_device_to_group(group->id, dev);
+
+ pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
+
return 0;
}
EXPORT_SYMBOL_GPL(iommu_group_add_device);
@@ -388,6 +459,8 @@
struct iommu_group *group = dev->iommu_group;
struct iommu_device *tmp_device, *device = NULL;
+ pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);
+
/* Pre-notify listeners that a device is being removed. */
blocking_notifier_call_chain(&group->notifier,
IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);
@@ -417,6 +490,17 @@
}
EXPORT_SYMBOL_GPL(iommu_group_remove_device);
+static int iommu_group_device_count(struct iommu_group *group)
+{
+ struct iommu_device *entry;
+ int ret = 0;
+
+ list_for_each_entry(entry, &group->devices, list)
+ ret++;
+
+ return ret;
+}
+
/**
* iommu_group_for_each_dev - iterate over each device in the group
* @group: the group
@@ -428,19 +512,30 @@
* The group->mutex is held across callbacks, which will block calls to
* iommu_group_add/remove_device.
*/
-int iommu_group_for_each_dev(struct iommu_group *group, void *data,
- int (*fn)(struct device *, void *))
+static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
+ int (*fn)(struct device *, void *))
{
struct iommu_device *device;
int ret = 0;
- mutex_lock(&group->mutex);
list_for_each_entry(device, &group->devices, list) {
ret = fn(device->dev, data);
if (ret)
break;
}
+ return ret;
+}
+
+
+int iommu_group_for_each_dev(struct iommu_group *group, void *data,
+ int (*fn)(struct device *, void *))
+{
+ int ret;
+
+ mutex_lock(&group->mutex);
+ ret = __iommu_group_for_each_dev(group, data, fn);
mutex_unlock(&group->mutex);
+
return ret;
}
EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);
@@ -692,7 +787,19 @@
return group;
/* No shared group found, allocate new */
- return iommu_group_alloc();
+ group = iommu_group_alloc();
+ if (IS_ERR(group))
+ return NULL;
+
+ /*
+ * Try to allocate a default domain - needs support from the
+ * IOMMU driver.
+ */
+ group->default_domain = __iommu_domain_alloc(pdev->dev.bus,
+ IOMMU_DOMAIN_DMA);
+ group->domain = group->default_domain;
+
+ return group;
}
/**
@@ -731,6 +838,11 @@
return group;
}
+struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
+{
+ return group->default_domain;
+}
+
static int add_iommu_group(struct device *dev, void *data)
{
struct iommu_callback_data *cb = data;
@@ -741,7 +853,16 @@
WARN_ON(dev->iommu_group);
- ops->add_device(dev);
+ return ops->add_device(dev);
+}
+
+static int remove_iommu_group(struct device *dev, void *data)
+{
+ struct iommu_callback_data *cb = data;
+ const struct iommu_ops *ops = cb->ops;
+
+ if (ops->remove_device && dev->iommu_group)
+ ops->remove_device(dev);
return 0;
}
@@ -761,7 +882,7 @@
if (action == BUS_NOTIFY_ADD_DEVICE) {
if (ops->add_device)
return ops->add_device(dev);
- } else if (action == BUS_NOTIFY_DEL_DEVICE) {
+ } else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
if (ops->remove_device && dev->iommu_group) {
ops->remove_device(dev);
return 0;
@@ -814,19 +935,25 @@
nb->notifier_call = iommu_bus_notifier;
err = bus_register_notifier(bus, nb);
- if (err) {
- kfree(nb);
- return err;
- }
+ if (err)
+ goto out_free;
err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
- if (err) {
- bus_unregister_notifier(bus, nb);
- kfree(nb);
- return err;
- }
+ if (err)
+ goto out_err;
+
return 0;
+
+out_err:
+ /* Clean up */
+ bus_for_each_dev(bus, NULL, &cb, remove_iommu_group);
+ bus_unregister_notifier(bus, nb);
+
+out_free:
+ kfree(nb);
+
+ return err;
}
/**
@@ -898,22 +1025,28 @@
}
EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
-struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+ unsigned type)
{
struct iommu_domain *domain;
if (bus == NULL || bus->iommu_ops == NULL)
return NULL;
- domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
+ domain = bus->iommu_ops->domain_alloc(type);
if (!domain)
return NULL;
domain->ops = bus->iommu_ops;
- domain->type = IOMMU_DOMAIN_UNMANAGED;
+ domain->type = type;
return domain;
}
+
+struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+{
+ return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
+}
EXPORT_SYMBOL_GPL(iommu_domain_alloc);
void iommu_domain_free(struct iommu_domain *domain)
@@ -922,7 +1055,8 @@
}
EXPORT_SYMBOL_GPL(iommu_domain_free);
-int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+static int __iommu_attach_device(struct iommu_domain *domain,
+ struct device *dev)
{
int ret;
if (unlikely(domain->ops->attach_dev == NULL))
@@ -933,9 +1067,38 @@
trace_attach_device_to_domain(dev);
return ret;
}
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+ struct iommu_group *group;
+ int ret;
+
+ group = iommu_group_get(dev);
+ /* FIXME: Remove this when groups a mandatory for iommu drivers */
+ if (group == NULL)
+ return __iommu_attach_device(domain, dev);
+
+ /*
+ * We have a group - lock it to make sure the device-count doesn't
+ * change while we are attaching
+ */
+ mutex_lock(&group->mutex);
+ ret = -EINVAL;
+ if (iommu_group_device_count(group) != 1)
+ goto out_unlock;
+
+ ret = __iommu_attach_group(domain, group);
+
+out_unlock:
+ mutex_unlock(&group->mutex);
+ iommu_group_put(group);
+
+ return ret;
+}
EXPORT_SYMBOL_GPL(iommu_attach_device);
-void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+static void __iommu_detach_device(struct iommu_domain *domain,
+ struct device *dev)
{
if (unlikely(domain->ops->detach_dev == NULL))
return;
@@ -943,8 +1106,48 @@
domain->ops->detach_dev(domain, dev);
trace_detach_device_from_domain(dev);
}
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+ struct iommu_group *group;
+
+ group = iommu_group_get(dev);
+ /* FIXME: Remove this when groups a mandatory for iommu drivers */
+ if (group == NULL)
+ return __iommu_detach_device(domain, dev);
+
+ mutex_lock(&group->mutex);
+ if (iommu_group_device_count(group) != 1) {
+ WARN_ON(1);
+ goto out_unlock;
+ }
+
+ __iommu_detach_group(domain, group);
+
+out_unlock:
+ mutex_unlock(&group->mutex);
+ iommu_group_put(group);
+}
EXPORT_SYMBOL_GPL(iommu_detach_device);
+struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
+{
+ struct iommu_domain *domain;
+ struct iommu_group *group;
+
+ group = iommu_group_get(dev);
+ /* FIXME: Remove this when groups a mandatory for iommu drivers */
+ if (group == NULL)
+ return NULL;
+
+ domain = group->domain;
+
+ iommu_group_put(group);
+
+ return domain;
+}
+EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
+
/*
* IOMMU groups are really the natrual working unit of the IOMMU, but
* the IOMMU API works on domains and devices. Bridge that gap by
@@ -959,13 +1162,34 @@
{
struct iommu_domain *domain = data;
- return iommu_attach_device(domain, dev);
+ return __iommu_attach_device(domain, dev);
+}
+
+static int __iommu_attach_group(struct iommu_domain *domain,
+ struct iommu_group *group)
+{
+ int ret;
+
+ if (group->default_domain && group->domain != group->default_domain)
+ return -EBUSY;
+
+ ret = __iommu_group_for_each_dev(group, domain,
+ iommu_group_do_attach_device);
+ if (ret == 0)
+ group->domain = domain;
+
+ return ret;
}
int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
{
- return iommu_group_for_each_dev(group, domain,
- iommu_group_do_attach_device);
+ int ret;
+
+ mutex_lock(&group->mutex);
+ ret = __iommu_attach_group(domain, group);
+ mutex_unlock(&group->mutex);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(iommu_attach_group);
@@ -973,14 +1197,40 @@
{
struct iommu_domain *domain = data;
- iommu_detach_device(domain, dev);
+ __iommu_detach_device(domain, dev);
return 0;
}
+static void __iommu_detach_group(struct iommu_domain *domain,
+ struct iommu_group *group)
+{
+ int ret;
+
+ if (!group->default_domain) {
+ __iommu_group_for_each_dev(group, domain,
+ iommu_group_do_detach_device);
+ group->domain = NULL;
+ return;
+ }
+
+ if (group->domain == group->default_domain)
+ return;
+
+ /* Detach by re-attaching to the default domain */
+ ret = __iommu_group_for_each_dev(group, group->default_domain,
+ iommu_group_do_attach_device);
+ if (ret != 0)
+ WARN_ON(1);
+ else
+ group->domain = group->default_domain;
+}
+
void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
{
- iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device);
+ mutex_lock(&group->mutex);
+ __iommu_detach_group(domain, group);
+ mutex_unlock(&group->mutex);
}
EXPORT_SYMBOL_GPL(iommu_detach_group);
@@ -1207,7 +1457,7 @@
return 0;
}
-arch_initcall(iommu_init);
+core_initcall(iommu_init);
int iommu_domain_get_attr(struct iommu_domain *domain,
enum iommu_attr attr, void *data)
@@ -1273,3 +1523,72 @@
return ret;
}
EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
+
+void iommu_get_dm_regions(struct device *dev, struct list_head *list)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->get_dm_regions)
+ ops->get_dm_regions(dev, list);
+}
+
+void iommu_put_dm_regions(struct device *dev, struct list_head *list)
+{
+ const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+ if (ops && ops->put_dm_regions)
+ ops->put_dm_regions(dev, list);
+}
+
+/* Request that a device is direct mapped by the IOMMU */
+int iommu_request_dm_for_dev(struct device *dev)
+{
+ struct iommu_domain *dm_domain;
+ struct iommu_group *group;
+ int ret;
+
+ /* Device must already be in a group before calling this function */
+ group = iommu_group_get_for_dev(dev);
+ if (IS_ERR(group))
+ return PTR_ERR(group);
+
+ mutex_lock(&group->mutex);
+
+ /* Check if the default domain is already direct mapped */
+ ret = 0;
+ if (group->default_domain &&
+ group->default_domain->type == IOMMU_DOMAIN_IDENTITY)
+ goto out;
+
+ /* Don't change mappings of existing devices */
+ ret = -EBUSY;
+ if (iommu_group_device_count(group) != 1)
+ goto out;
+
+ /* Allocate a direct mapped domain */
+ ret = -ENOMEM;
+ dm_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_IDENTITY);
+ if (!dm_domain)
+ goto out;
+
+ /* Attach the device to the domain */
+ ret = __iommu_attach_group(dm_domain, group);
+ if (ret) {
+ iommu_domain_free(dm_domain);
+ goto out;
+ }
+
+ /* Make the direct mapped domain the default for this group */
+ if (group->default_domain)
+ iommu_domain_free(group->default_domain);
+ group->default_domain = dm_domain;
+
+ pr_info("Using direct mapping for device %s\n", dev_name(dev));
+
+ ret = 0;
+out:
+ mutex_unlock(&group->mutex);
+ iommu_group_put(group);
+
+ return ret;
+}
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 9dd8208..b7c3d92 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -227,6 +227,7 @@
/* Figure out where to put new node */
while (*new) {
struct iova *this = container_of(*new, struct iova, node);
+
parent = *new;
if (iova->pfn_lo < this->pfn_lo)
@@ -350,6 +351,7 @@
free_iova(struct iova_domain *iovad, unsigned long pfn)
{
struct iova *iova = find_iova(iovad, pfn);
+
if (iova)
__free_iova(iovad, iova);
@@ -369,6 +371,7 @@
node = rb_first(&iovad->rbroot);
while (node) {
struct iova *iova = container_of(node, struct iova, node);
+
rb_erase(node, &iovad->rbroot);
free_iova_mem(iova);
node = rb_first(&iovad->rbroot);
@@ -482,6 +485,7 @@
for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
struct iova *iova = container_of(node, struct iova, node);
struct iova *new_iova;
+
new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
if (!new_iova)
printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index cab2145..ebf0adb 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -551,6 +551,15 @@
spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
}
+static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
+ dma_addr_t iova, size_t size)
+{
+ rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
+ if (size > SPAGE_SIZE)
+ rk_iommu_zap_iova(rk_domain, iova + size - SPAGE_SIZE,
+ SPAGE_SIZE);
+}
+
static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
dma_addr_t iova)
{
@@ -575,12 +584,6 @@
rk_table_flush(page_table, NUM_PT_ENTRIES);
rk_table_flush(dte_addr, 1);
- /*
- * Zap the first iova of newly allocated page table so iommu evicts
- * old cached value of new dte from the iotlb.
- */
- rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
-
done:
pt_phys = rk_dte_pt_address(dte);
return (u32 *)phys_to_virt(pt_phys);
@@ -630,6 +633,14 @@
rk_table_flush(pte_addr, pte_count);
+ /*
+ * Zap the first and last iova to evict from iotlb any previously
+ * mapped cachelines holding stale values for its dte and pte.
+ * We only zap the first and last iova, since only they could have
+ * dte or pte shared with an existing mapping.
+ */
+ rk_iommu_zap_iova_first_last(rk_domain, iova, size);
+
return 0;
unwind:
/* Unmap the range of iovas that we just mapped */
@@ -774,7 +785,7 @@
list_add_tail(&iommu->node, &rk_domain->iommus);
spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
- dev_info(dev, "Attached to iommu domain\n");
+ dev_dbg(dev, "Attached to iommu domain\n");
rk_iommu_disable_stall(iommu);
@@ -808,7 +819,7 @@
iommu->domain = NULL;
- dev_info(dev, "Detached from iommu domain\n");
+ dev_dbg(dev, "Detached from iommu domain\n");
}
static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 7d092dd..4540179 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -21,7 +21,7 @@
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
depends on IOMMU_API
- select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU)
+ select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM_SMMU || ARM_SMMU_V3)
select VFIO_IOMMU_SPAPR_TCE if (PPC_POWERNV || PPC_PSERIES)
select VFIO_SPAPR_EEH if (PPC_POWERNV || PPC_PSERIES)
select ANON_INODES
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 0546b87..dc767f7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -114,6 +114,20 @@
DOMAIN_ATTR_MAX,
};
+/**
+ * struct iommu_dm_region - descriptor for a direct mapped memory region
+ * @list: Linked list pointers
+ * @start: System physical start address of the region
+ * @length: Length of the region in bytes
+ * @prot: IOMMU Protection flags (READ/WRITE/...)
+ */
+struct iommu_dm_region {
+ struct list_head list;
+ phys_addr_t start;
+ size_t length;
+ int prot;
+};
+
#ifdef CONFIG_IOMMU_API
/**
@@ -159,6 +173,10 @@
int (*domain_set_attr)(struct iommu_domain *domain,
enum iommu_attr attr, void *data);
+ /* Request/Free a list of direct mapping requirements for a device */
+ void (*get_dm_regions)(struct device *dev, struct list_head *list);
+ void (*put_dm_regions)(struct device *dev, struct list_head *list);
+
/* Window handling functions */
int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
phys_addr_t paddr, u64 size, int prot);
@@ -193,6 +211,7 @@
struct device *dev);
extern void iommu_detach_device(struct iommu_domain *domain,
struct device *dev);
+extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot);
extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
@@ -204,6 +223,10 @@
extern void iommu_set_fault_handler(struct iommu_domain *domain,
iommu_fault_handler_t handler, void *token);
+extern void iommu_get_dm_regions(struct device *dev, struct list_head *list);
+extern void iommu_put_dm_regions(struct device *dev, struct list_head *list);
+extern int iommu_request_dm_for_dev(struct device *dev);
+
extern int iommu_attach_group(struct iommu_domain *domain,
struct iommu_group *group);
extern void iommu_detach_group(struct iommu_domain *domain,
@@ -227,6 +250,7 @@
struct notifier_block *nb);
extern int iommu_group_id(struct iommu_group *group);
extern struct iommu_group *iommu_group_get_for_dev(struct device *dev);
+extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *);
extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
void *data);
@@ -332,6 +356,11 @@
{
}
+static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
+{
+ return NULL;
+}
+
static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, int gfp_order, int prot)
{
@@ -373,6 +402,21 @@
{
}
+static inline void iommu_get_dm_regions(struct device *dev,
+ struct list_head *list)
+{
+}
+
+static inline void iommu_put_dm_regions(struct device *dev,
+ struct list_head *list)
+{
+}
+
+static inline int iommu_request_dm_for_dev(struct device *dev)
+{
+ return -ENODEV;
+}
+
static inline int iommu_attach_group(struct iommu_domain *domain,
struct iommu_group *group)
{