#include <linux/slab.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
-#include <linux/sysdev.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/dmar.h>
#define DOMAIN_MAX_ADDR(gaw) ((((u64)1) << gaw) - 1)
+#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
+#define DMA_32BIT_PFN IOVA_PFN(DMA_32BIT_MASK)
+#define DMA_64BIT_PFN IOVA_PFN(DMA_64BIT_MASK)
+
+/* global iommu list, set NULL for ignored DMAR units */
+static struct intel_iommu **g_iommus;
+
+/*
+ * 0: Present
+ * 1-11: Reserved
+ * 12-63: Context Ptr (12 - (haw-1))
+ * 64-127: Reserved
+ */
+struct root_entry {
+ u64 val;
+ u64 rsvd1;
+};
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
+static inline bool root_present(struct root_entry *root)
+{
+ return (root->val & 1);
+}
+static inline void set_root_present(struct root_entry *root)
+{
+ root->val |= 1;
+}
+static inline void set_root_value(struct root_entry *root, unsigned long value)
+{
+ root->val |= value & VTD_PAGE_MASK;
+}
+
+static inline struct context_entry *
+get_context_addr_from_root(struct root_entry *root)
+{
+ return (struct context_entry *)
+ (root_present(root)?phys_to_virt(
+ root->val & VTD_PAGE_MASK) :
+ NULL);
+}
+
+/*
+ * low 64 bits:
+ * 0: present
+ * 1: fault processing disable
+ * 2-3: translation type
+ * 12-63: address space root
+ * high 64 bits:
+ * 0-2: address width
+ * 3-6: aval
+ * 8-23: domain id
+ */
+struct context_entry {
+ u64 lo;
+ u64 hi;
+};
+
+static inline bool context_present(struct context_entry *context)
+{
+ return (context->lo & 1);
+}
+static inline void context_set_present(struct context_entry *context)
+{
+ context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+ context->lo &= (((u64)-1) << 2) | 1;
+}
+
+#define CONTEXT_TT_MULTI_LEVEL 0
+
+static inline void context_set_translation_type(struct context_entry *context,
+ unsigned long value)
+{
+ context->lo &= (((u64)-1) << 4) | 3;
+ context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+ unsigned long value)
+{
+ context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+ unsigned long value)
+{
+ context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+ unsigned long value)
+{
+ context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+ context->lo = 0;
+ context->hi = 0;
+}
+
+/*
+ * 0: readable
+ * 1: writable
+ * 2-6: reserved
+ * 7: super page
+ * 8-11: available
+ * 12-63: Host physcial address
+ */
+struct dma_pte {
+ u64 val;
+};
+
+static inline void dma_clear_pte(struct dma_pte *pte)
+{
+ pte->val = 0;
+}
+
+static inline void dma_set_pte_readable(struct dma_pte *pte)
+{
+ pte->val |= DMA_PTE_READ;
+}
+
+static inline void dma_set_pte_writable(struct dma_pte *pte)
+{
+ pte->val |= DMA_PTE_WRITE;
+}
+
+static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot)
+{
+ pte->val = (pte->val & ~3) | (prot & 3);
+}
+
+static inline u64 dma_pte_addr(struct dma_pte *pte)
+{
+ return (pte->val & VTD_PAGE_MASK);
+}
+
+static inline void dma_set_pte_addr(struct dma_pte *pte, u64 addr)
+{
+ pte->val |= (addr & VTD_PAGE_MASK);
+}
+
+static inline bool dma_pte_present(struct dma_pte *pte)
+{
+ return (pte->val & 3) != 0;
+}
+
+/* devices under the same p2p bridge are owned in one domain */
+#define DOMAIN_FLAG_P2P_MULTIPLE_DEVICES (1 < 0)
+
+struct dmar_domain {
+ int id; /* domain id */
+ unsigned long iommu_bmp; /* bitmap of iommus this domain uses*/
+
+ struct list_head devices; /* all devices' list */
+ struct iova_domain iovad; /* iova's that belong to this domain */
+
+ struct dma_pte *pgd; /* virtual address */
+ spinlock_t mapping_lock; /* page table lock */
+ int gaw; /* max guest address width */
+
+ /* adjusted guest address width, 0 is level 2 30-bit */
+ int agaw;
+
+ int flags; /* flags to find out type of domain */
+};
+
+/* PCI domain-device relationship */
+struct device_domain_info {
+ struct list_head link; /* link to domain siblings */
+ struct list_head global; /* link to global list */
+ u8 bus; /* PCI bus numer */
+ u8 devfn; /* PCI devfn number */
+ struct pci_dev *dev; /* it's NULL for PCIE-to-PCI bridge */
+ struct dmar_domain *domain; /* pointer to domain */
+};
static void flush_unmaps_timeout(unsigned long data);
kmem_cache_free(iommu_iova_cache, iova);
}
+/* in native case, each domain is related to only one iommu */
+static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
+{
+ int iommu_id;
+
+ iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
+ if (iommu_id < 0 || iommu_id >= g_num_of_iommus)
+ return NULL;
+
+ return g_iommus[iommu_id];
+}
+
/* Gets context entry for a given bus and devfn */
static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
u8 bus, u8 devfn)
ret = 0;
goto out;
}
- ret = context_present(context[devfn]);
+ ret = context_present(&context[devfn]);
out:
spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
root = &iommu->root_entry[bus];
context = get_context_addr_from_root(root);
if (context) {
- context_clear_entry(context[devfn]);
+ context_clear_entry(&context[devfn]);
__iommu_flush_cache(iommu, &context[devfn], \
sizeof(*context));
}
int level = agaw_to_level(domain->agaw);
int offset;
unsigned long flags;
+ struct intel_iommu *iommu = domain_get_iommu(domain);
BUG_ON(!domain->pgd);
if (level == 1)
break;
- if (!dma_pte_present(*pte)) {
+ if (!dma_pte_present(pte)) {
tmp_page = alloc_pgtable_page();
if (!tmp_page) {
flags);
return NULL;
}
- __iommu_flush_cache(domain->iommu, tmp_page,
+ __iommu_flush_cache(iommu, tmp_page,
PAGE_SIZE);
- dma_set_pte_addr(*pte, virt_to_phys(tmp_page));
+ dma_set_pte_addr(pte, virt_to_phys(tmp_page));
/*
* high level table always sets r/w, last level page
* table control read/write
*/
- dma_set_pte_readable(*pte);
- dma_set_pte_writable(*pte);
- __iommu_flush_cache(domain->iommu, pte, sizeof(*pte));
+ dma_set_pte_readable(pte);
+ dma_set_pte_writable(pte);
+ __iommu_flush_cache(iommu, pte, sizeof(*pte));
}
- parent = phys_to_virt(dma_pte_addr(*pte));
+ parent = phys_to_virt(dma_pte_addr(pte));
level--;
}
if (level == total)
return pte;
- if (!dma_pte_present(*pte))
+ if (!dma_pte_present(pte))
break;
- parent = phys_to_virt(dma_pte_addr(*pte));
+ parent = phys_to_virt(dma_pte_addr(pte));
total--;
}
return NULL;
static void dma_pte_clear_one(struct dmar_domain *domain, u64 addr)
{
struct dma_pte *pte = NULL;
+ struct intel_iommu *iommu = domain_get_iommu(domain);
/* get last level pte */
pte = dma_addr_level_pte(domain, addr, 1);
if (pte) {
- dma_clear_pte(*pte);
- __iommu_flush_cache(domain->iommu, pte, sizeof(*pte));
+ dma_clear_pte(pte);
+ __iommu_flush_cache(iommu, pte, sizeof(*pte));
}
}
int total = agaw_to_level(domain->agaw);
int level;
u64 tmp;
+ struct intel_iommu *iommu = domain_get_iommu(domain);
start &= (((u64)1) << addr_width) - 1;
end &= (((u64)1) << addr_width) - 1;
pte = dma_addr_level_pte(domain, tmp, level);
if (pte) {
free_pgtable_page(
- phys_to_virt(dma_pte_addr(*pte)));
- dma_clear_pte(*pte);
- __iommu_flush_cache(domain->iommu,
+ phys_to_virt(dma_pte_addr(pte)));
+ dma_clear_pte(pte);
+ __iommu_flush_cache(iommu,
pte, sizeof(*pte));
}
tmp += level_size(level);
kfree(iommu->domains);
kfree(iommu->domain_ids);
+ g_iommus[iommu->seq_id] = NULL;
+
+ /* if all iommus are freed, free g_iommus */
+ for (i = 0; i < g_num_of_iommus; i++) {
+ if (g_iommus[i])
+ break;
+ }
+
+ if (i == g_num_of_iommus)
+ kfree(g_iommus);
+
/* free context mapping */
free_context_table(iommu);
}
set_bit(num, iommu->domain_ids);
domain->id = num;
- domain->iommu = iommu;
+ memset(&domain->iommu_bmp, 0, sizeof(unsigned long));
+ set_bit(iommu->seq_id, &domain->iommu_bmp);
+ domain->flags = 0;
iommu->domains[num] = domain;
spin_unlock_irqrestore(&iommu->lock, flags);
static void iommu_free_domain(struct dmar_domain *domain)
{
unsigned long flags;
+ struct intel_iommu *iommu;
- spin_lock_irqsave(&domain->iommu->lock, flags);
- clear_bit(domain->id, domain->iommu->domain_ids);
- spin_unlock_irqrestore(&domain->iommu->lock, flags);
+ iommu = domain_get_iommu(domain);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+ clear_bit(domain->id, iommu->domain_ids);
+ spin_unlock_irqrestore(&iommu->lock, flags);
}
static struct iova_domain reserved_iova_list;
domain_reserve_special_ranges(domain);
/* calculate AGAW */
- iommu = domain->iommu;
+ iommu = domain_get_iommu(domain);
if (guest_width > cap_mgaw(iommu->cap))
guest_width = cap_mgaw(iommu->cap);
domain->gaw = guest_width;
u8 bus, u8 devfn)
{
struct context_entry *context;
- struct intel_iommu *iommu = domain->iommu;
+ struct intel_iommu *iommu = domain_get_iommu(domain);
unsigned long flags;
pr_debug("Set context mapping for %02x:%02x.%d\n",
if (!context)
return -ENOMEM;
spin_lock_irqsave(&iommu->lock, flags);
- if (context_present(*context)) {
+ if (context_present(context)) {
spin_unlock_irqrestore(&iommu->lock, flags);
return 0;
}
- context_set_domain_id(*context, domain->id);
- context_set_address_width(*context, domain->agaw);
- context_set_address_root(*context, virt_to_phys(domain->pgd));
- context_set_translation_type(*context, CONTEXT_TT_MULTI_LEVEL);
- context_set_fault_enable(*context);
- context_set_present(*context);
+ context_set_domain_id(context, domain->id);
+ context_set_address_width(context, domain->agaw);
+ context_set_address_root(context, virt_to_phys(domain->pgd));
+ context_set_translation_type(context, CONTEXT_TT_MULTI_LEVEL);
+ context_set_fault_enable(context);
+ context_set_present(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
/* it's a non-present to present mapping */
{
int ret;
struct pci_dev *tmp, *parent;
+ struct intel_iommu *iommu = domain_get_iommu(domain);
- ret = device_context_mapped(domain->iommu,
+ ret = device_context_mapped(iommu,
pdev->bus->number, pdev->devfn);
if (!ret)
return ret;
/* Secondary interface's bus number and devfn 0 */
parent = pdev->bus->self;
while (parent != tmp) {
- ret = device_context_mapped(domain->iommu, parent->bus->number,
+ ret = device_context_mapped(iommu, parent->bus->number,
parent->devfn);
if (!ret)
return ret;
parent = parent->bus->self;
}
if (tmp->is_pcie)
- return device_context_mapped(domain->iommu,
+ return device_context_mapped(iommu,
tmp->subordinate->number, 0);
else
- return device_context_mapped(domain->iommu,
+ return device_context_mapped(iommu,
tmp->bus->number, tmp->devfn);
}
struct dma_pte *pte;
int index;
int addr_width = agaw_to_width(domain->agaw);
+ struct intel_iommu *iommu = domain_get_iommu(domain);
hpa &= (((u64)1) << addr_width) - 1;
/* We don't need lock here, nobody else
* touches the iova range
*/
- BUG_ON(dma_pte_addr(*pte));
- dma_set_pte_addr(*pte, start_pfn << VTD_PAGE_SHIFT);
- dma_set_pte_prot(*pte, prot);
- __iommu_flush_cache(domain->iommu, pte, sizeof(*pte));
+ BUG_ON(dma_pte_addr(pte));
+ dma_set_pte_addr(pte, start_pfn << VTD_PAGE_SHIFT);
+ dma_set_pte_prot(pte, prot);
+ __iommu_flush_cache(iommu, pte, sizeof(*pte));
start_pfn++;
index++;
}
static void detach_domain_for_dev(struct dmar_domain *domain, u8 bus, u8 devfn)
{
- clear_context_table(domain->iommu, bus, devfn);
- domain->iommu->flush.flush_context(domain->iommu, 0, 0, 0,
+ struct intel_iommu *iommu = domain_get_iommu(domain);
+
+ clear_context_table(iommu, bus, devfn);
+ iommu->flush.flush_context(iommu, 0, 0, 0,
DMA_CCMD_GLOBAL_INVL, 0);
- domain->iommu->flush.flush_iotlb(domain->iommu, 0, 0, 0,
+ iommu->flush.flush_iotlb(iommu, 0, 0, 0,
DMA_TLB_GLOBAL_FLUSH, 0);
}
info->dev = NULL;
info->domain = domain;
/* This domain is shared by devices under p2p bridge */
- domain->flags |= DOMAIN_FLAG_MULTIPLE_DEVICES;
+ domain->flags |= DOMAIN_FLAG_P2P_MULTIPLE_DEVICES;
/* pcie-to-pci bridge already has a domain, uses it */
found = NULL;
printk(KERN_ERR "IOMMU: mapping reserved region failed\n");
}
}
+#else /* !CONFIG_DMAR_GFX_WA */
+static inline void iommu_prepare_gfx_mapping(void)
+{
+ return;
+}
#endif
#ifdef CONFIG_DMAR_FLOPPY_WA
}
#endif /* !CONFIG_DMAR_FLPY_WA */
-int __init init_dmars(void)
+static int __init init_dmars(void)
{
struct dmar_drhd_unit *drhd;
struct dmar_rmrr_unit *rmrr;
*/
}
+ g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
+ GFP_KERNEL);
+ if (!g_iommus) {
+ printk(KERN_ERR "Allocating global iommu array failed\n");
+ ret = -ENOMEM;
+ goto error;
+ }
+
deferred_flush = kzalloc(g_num_of_iommus *
sizeof(struct deferred_flush_tables), GFP_KERNEL);
if (!deferred_flush) {
+ kfree(g_iommus);
ret = -ENOMEM;
goto error;
}
continue;
iommu = drhd->iommu;
+ g_iommus[iommu->seq_id] = iommu;
ret = iommu_init_domains(iommu);
if (ret)
iommu->flush.flush_context = __iommu_flush_context;
iommu->flush.flush_iotlb = __iommu_flush_iotlb;
printk(KERN_INFO "IOMMU 0x%Lx: using Register based "
- "invalidation\n", drhd->reg_base_addr);
+ "invalidation\n",
+ (unsigned long long)drhd->reg_base_addr);
} else {
iommu->flush.flush_context = qi_flush_context;
iommu->flush.flush_iotlb = qi_flush_iotlb;
printk(KERN_INFO "IOMMU 0x%Lx: using Queued "
- "invalidation\n", drhd->reg_base_addr);
+ "invalidation\n",
+ (unsigned long long)drhd->reg_base_addr);
}
}
iommu = drhd->iommu;
free_iommu(iommu);
}
+ kfree(g_iommus);
return ret;
}
struct iova *iova;
int prot = 0;
int ret;
+ struct intel_iommu *iommu;
BUG_ON(dir == DMA_NONE);
if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
if (!domain)
return 0;
+ iommu = domain_get_iommu(domain);
size = aligned_size((u64)paddr, size);
iova = __intel_alloc_iova(hwdev, domain, size, pdev->dma_mask);
* mappings..
*/
if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
- !cap_zlr(domain->iommu->cap))
+ !cap_zlr(iommu->cap))
prot |= DMA_PTE_READ;
if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
prot |= DMA_PTE_WRITE;
goto error;
/* it's a non-present to present mapping */
- ret = iommu_flush_iotlb_psi(domain->iommu, domain->id,
+ ret = iommu_flush_iotlb_psi(iommu, domain->id,
start_paddr, size >> VTD_PAGE_SHIFT, 1);
if (ret)
- iommu_flush_write_buffer(domain->iommu);
+ iommu_flush_write_buffer(iommu);
return start_paddr + ((u64)paddr & (~PAGE_MASK));
/* just flush them all */
for (i = 0; i < g_num_of_iommus; i++) {
- if (deferred_flush[i].next) {
- struct intel_iommu *iommu =
- deferred_flush[i].domain[0]->iommu;
+ struct intel_iommu *iommu = g_iommus[i];
+ if (!iommu)
+ continue;
+ if (deferred_flush[i].next) {
iommu->flush.flush_iotlb(iommu, 0, 0, 0,
DMA_TLB_GLOBAL_FLUSH, 0);
for (j = 0; j < deferred_flush[i].next; j++) {
{
unsigned long flags;
int next, iommu_id;
+ struct intel_iommu *iommu;
spin_lock_irqsave(&async_umap_flush_lock, flags);
if (list_size == HIGH_WATER_MARK)
flush_unmaps();
- iommu_id = dom->iommu->seq_id;
+ iommu = domain_get_iommu(dom);
+ iommu_id = iommu->seq_id;
next = deferred_flush[iommu_id].next;
deferred_flush[iommu_id].domain[next] = dom;
struct dmar_domain *domain;
unsigned long start_addr;
struct iova *iova;
+ struct intel_iommu *iommu;
if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
return;
domain = find_domain(pdev);
BUG_ON(!domain);
+ iommu = domain_get_iommu(domain);
+
iova = find_iova(&domain->iovad, IOVA_PFN(dev_addr));
if (!iova)
return;
/* free page tables */
dma_pte_free_pagetable(domain, start_addr, start_addr + size);
if (intel_iommu_strict) {
- if (iommu_flush_iotlb_psi(domain->iommu,
+ if (iommu_flush_iotlb_psi(iommu,
domain->id, start_addr, size >> VTD_PAGE_SHIFT, 0))
- iommu_flush_write_buffer(domain->iommu);
+ iommu_flush_write_buffer(iommu);
/* free iova */
__free_iova(&domain->iovad, iova);
} else {
size_t size = 0;
void *addr;
struct scatterlist *sg;
+ struct intel_iommu *iommu;
if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
return;
domain = find_domain(pdev);
+ BUG_ON(!domain);
+
+ iommu = domain_get_iommu(domain);
iova = find_iova(&domain->iovad, IOVA_PFN(sglist[0].dma_address));
if (!iova)
/* free page tables */
dma_pte_free_pagetable(domain, start_addr, start_addr + size);
- if (iommu_flush_iotlb_psi(domain->iommu, domain->id, start_addr,
+ if (iommu_flush_iotlb_psi(iommu, domain->id, start_addr,
size >> VTD_PAGE_SHIFT, 0))
- iommu_flush_write_buffer(domain->iommu);
+ iommu_flush_write_buffer(iommu);
/* free iova */
__free_iova(&domain->iovad, iova);
int ret;
struct scatterlist *sg;
unsigned long start_addr;
+ struct intel_iommu *iommu;
BUG_ON(dir == DMA_NONE);
if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
if (!domain)
return 0;
+ iommu = domain_get_iommu(domain);
+
for_each_sg(sglist, sg, nelems, i) {
addr = SG_ENT_VIRT_ADDRESS(sg);
addr = (void *)virt_to_phys(addr);
* mappings..
*/
if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || \
- !cap_zlr(domain->iommu->cap))
+ !cap_zlr(iommu->cap))
prot |= DMA_PTE_READ;
if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
prot |= DMA_PTE_WRITE;
}
/* it's a non-present to present mapping */
- if (iommu_flush_iotlb_psi(domain->iommu, domain->id,
+ if (iommu_flush_iotlb_psi(iommu, domain->id,
start_addr, offset >> VTD_PAGE_SHIFT, 1))
- iommu_flush_write_buffer(domain->iommu);
+ iommu_flush_write_buffer(iommu);
return nelems;
}
pte = addr_to_dma_pte(domain, iova);
if (pte)
- pfn = dma_pte_addr(*pte);
+ pfn = dma_pte_addr(pte);
return pfn >> VTD_PAGE_SHIFT;
}