summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/intel-iommu.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu/intel-iommu.c')
-rw-r--r--drivers/iommu/intel-iommu.c887
1 files changed, 734 insertions, 153 deletions
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 12d094d08c0a..9dc37672bf89 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -41,9 +41,11 @@
#include <linux/dma-direct.h>
#include <linux/crash_dump.h>
#include <linux/numa.h>
+#include <linux/swiotlb.h>
#include <asm/irq_remapping.h>
#include <asm/cacheflush.h>
#include <asm/iommu.h>
+#include <trace/events/intel_iommu.h>
#include "irq_remapping.h"
#include "intel-pasid.h"
@@ -305,6 +307,20 @@ static int hw_pass_through = 1;
*/
#define DOMAIN_FLAG_LOSE_CHILDREN BIT(1)
+/*
+ * When VT-d works in the scalable mode, it allows DMA translation to
+ * happen through either first level or second level page table. This
+ * bit marks that the DMA translation for the domain goes through the
+ * first level page table, otherwise, it goes through the second level.
+ */
+#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(2)
+
+/*
+ * Domain represents a virtual machine which demands iommu nested
+ * translation mode support.
+ */
+#define DOMAIN_FLAG_NESTING_MODE BIT(3)
+
#define for_each_domain_iommu(idx, domain) \
for (idx = 0; idx < g_num_of_iommus; idx++) \
if (domain->iommu_refcnt[idx])
@@ -339,19 +355,28 @@ static void domain_exit(struct dmar_domain *domain);
static void domain_remove_dev_info(struct dmar_domain *domain);
static void dmar_remove_one_dev_info(struct device *dev);
static void __dmar_remove_one_dev_info(struct device_domain_info *info);
+static void domain_context_clear(struct intel_iommu *iommu,
+ struct device *dev);
static int domain_detach_iommu(struct dmar_domain *domain,
struct intel_iommu *iommu);
static bool device_is_rmrr_locked(struct device *dev);
static int intel_iommu_attach_device(struct iommu_domain *domain,
struct device *dev);
+static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
+ dma_addr_t iova);
#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
int dmar_disabled = 0;
#else
int dmar_disabled = 1;
-#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+#endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */
+#ifdef INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+int intel_iommu_sm = 1;
+#else
int intel_iommu_sm;
+#endif /* INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
+
int intel_iommu_enabled = 0;
EXPORT_SYMBOL_GPL(intel_iommu_enabled);
@@ -360,8 +385,8 @@ static int dmar_forcedac;
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
static int iommu_identity_mapping;
+static int intel_no_bounce;
-#define IDENTMAP_ALL 1
#define IDENTMAP_GFX 2
#define IDENTMAP_AZALIA 4
@@ -370,9 +395,12 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
#define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
-static DEFINE_SPINLOCK(device_domain_lock);
+DEFINE_SPINLOCK(device_domain_lock);
static LIST_HEAD(device_domain_list);
+#define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) && \
+ to_pci_dev(d)->untrusted)
+
/*
* Iterate over elements in device_domain_list and call the specified
* callback @fn against each element.
@@ -455,6 +483,9 @@ static int __init intel_iommu_setup(char *str)
printk(KERN_INFO
"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
intel_iommu_tboot_noforce = 1;
+ } else if (!strncmp(str, "nobounce", 8)) {
+ pr_info("Intel-IOMMU: No bounce buffer. This could expose security risks of DMA attacks\n");
+ intel_no_bounce = 1;
}
str += strcspn(str, ",");
@@ -539,6 +570,11 @@ static inline int domain_type_is_si(struct dmar_domain *domain)
return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
}
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+ return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
static inline int domain_pfn_supported(struct dmar_domain *domain,
unsigned long pfn)
{
@@ -648,11 +684,12 @@ static int domain_update_iommu_snooping(struct intel_iommu *skip)
return ret;
}
-static int domain_update_iommu_superpage(struct intel_iommu *skip)
+static int domain_update_iommu_superpage(struct dmar_domain *domain,
+ struct intel_iommu *skip)
{
struct dmar_drhd_unit *drhd;
struct intel_iommu *iommu;
- int mask = 0xf;
+ int mask = 0x3;
if (!intel_iommu_superpage) {
return 0;
@@ -662,7 +699,13 @@ static int domain_update_iommu_superpage(struct intel_iommu *skip)
rcu_read_lock();
for_each_active_iommu(iommu, drhd) {
if (iommu != skip) {
- mask &= cap_super_page_val(iommu->cap);
+ if (domain && domain_use_first_level(domain)) {
+ if (!cap_fl1gp_support(iommu->cap))
+ mask = 0x1;
+ } else {
+ mask &= cap_super_page_val(iommu->cap);
+ }
+
if (!mask)
break;
}
@@ -677,7 +720,7 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
{
domain_update_iommu_coherency(domain);
domain->iommu_snooping = domain_update_iommu_snooping(NULL);
- domain->iommu_superpage = domain_update_iommu_superpage(NULL);
+ domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
}
struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -761,13 +804,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
if (dev_is_pci(dev)) {
struct pci_dev *pf_pdev;
- pdev = to_pci_dev(dev);
-
-#ifdef CONFIG_X86
- /* VMD child devices currently cannot be handled individually */
- if (is_vmd(pdev->bus))
- return NULL;
-#endif
+ pdev = pci_real_dma_dev(to_pci_dev(dev));
/* VFs aren't listed in scope tables; we need to look up
* the PF instead to find the IOMMU. */
@@ -900,6 +937,8 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+ if (domain_use_first_level(domain))
+ pteval |= DMA_FL_PTE_XD;
if (cmpxchg64(&pte->val, 0ULL, pteval))
/* Someone else set it while we were thinking; use theirs. */
free_pgtable_page(tmp_page);
@@ -1470,6 +1509,20 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
spin_unlock_irqrestore(&device_domain_lock, flags);
}
+static void domain_flush_piotlb(struct intel_iommu *iommu,
+ struct dmar_domain *domain,
+ u64 addr, unsigned long npages, bool ih)
+{
+ u16 did = domain->iommu_did[iommu->seq_id];
+
+ if (domain->default_pasid)
+ qi_flush_piotlb(iommu, did, domain->default_pasid,
+ addr, npages, ih);
+
+ if (!list_empty(&domain->devices))
+ qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, npages, ih);
+}
+
static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
struct dmar_domain *domain,
unsigned long pfn, unsigned int pages,
@@ -1483,18 +1536,23 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
if (ih)
ih = 1 << 6;
- /*
- * Fallback to domain selective flush if no PSI support or the size is
- * too big.
- * PSI requires page size to be 2 ^ x, and the base address is naturally
- * aligned to the size
- */
- if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
- iommu->flush.flush_iotlb(iommu, did, 0, 0,
- DMA_TLB_DSI_FLUSH);
- else
- iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
- DMA_TLB_PSI_FLUSH);
+
+ if (domain_use_first_level(domain)) {
+ domain_flush_piotlb(iommu, domain, addr, pages, ih);
+ } else {
+ /*
+ * Fallback to domain selective flush if no PSI support or
+ * the size is too big. PSI requires page size to be 2 ^ x,
+ * and the base address is naturally aligned to the size.
+ */
+ if (!cap_pgsel_inv(iommu->cap) ||
+ mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+ DMA_TLB_PSI_FLUSH);
+ }
/*
* In caching mode, changes of pages from non-present to present require
@@ -1509,8 +1567,11 @@ static inline void __mapping_notify_one(struct intel_iommu *iommu,
struct dmar_domain *domain,
unsigned long pfn, unsigned int pages)
{
- /* It's a non-present to present mapping. Only flush if caching mode */
- if (cap_caching_mode(iommu->cap))
+ /*
+ * It's a non-present to present mapping. Only flush if caching mode
+ * and second level.
+ */
+ if (cap_caching_mode(iommu->cap) && !domain_use_first_level(domain))
iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
else
iommu_flush_write_buffer(iommu);
@@ -1527,7 +1588,11 @@ static void iommu_flush_iova(struct iova_domain *iovad)
struct intel_iommu *iommu = g_iommus[idx];
u16 did = domain->iommu_did[iommu->seq_id];
- iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+ if (domain_use_first_level(domain))
+ domain_flush_piotlb(iommu, domain, 0, -1, 0);
+ else
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
if (!cap_caching_mode(iommu->cap))
iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
@@ -1696,6 +1761,33 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
#endif
}
+/*
+ * Check and return whether first level is used by default for
+ * DMA translation.
+ */
+static bool first_level_by_default(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ static int first_level_support = -1;
+
+ if (likely(first_level_support != -1))
+ return first_level_support;
+
+ first_level_support = 1;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) {
+ first_level_support = 0;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return first_level_support;
+}
+
static struct dmar_domain *alloc_domain(int flags)
{
struct dmar_domain *domain;
@@ -1707,6 +1799,8 @@ static struct dmar_domain *alloc_domain(int flags)
memset(domain, 0, sizeof(*domain));
domain->nid = NUMA_NO_NODE;
domain->flags = flags;
+ if (first_level_by_default())
+ domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
domain->has_iotlb_device = false;
INIT_LIST_HEAD(&domain->devices);
@@ -1836,14 +1930,16 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
{
int adjust_width, agaw;
unsigned long sagaw;
- int err;
+ int ret;
init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
- err = init_iova_flush_queue(&domain->iovad,
- iommu_flush_iova, iova_entry_free);
- if (err)
- return err;
+ if (!intel_iommu_strict) {
+ ret = init_iova_flush_queue(&domain->iovad,
+ iommu_flush_iova, iova_entry_free);
+ if (ret)
+ pr_info("iova flush queue initialization failed\n");
+ }
domain_reserve_special_ranges(domain);
@@ -2105,9 +2201,26 @@ out_unlock:
return ret;
}
+struct domain_context_mapping_data {
+ struct dmar_domain *domain;
+ struct intel_iommu *iommu;
+ struct pasid_table *table;
+};
+
+static int domain_context_mapping_cb(struct pci_dev *pdev,
+ u16 alias, void *opaque)
+{
+ struct domain_context_mapping_data *data = opaque;
+
+ return domain_context_mapping_one(data->domain, data->iommu,
+ data->table, PCI_BUS_NUM(alias),
+ alias & 0xff);
+}
+
static int
domain_context_mapping(struct dmar_domain *domain, struct device *dev)
{
+ struct domain_context_mapping_data data;
struct pasid_table *table;
struct intel_iommu *iommu;
u8 bus, devfn;
@@ -2117,7 +2230,17 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
return -ENODEV;
table = intel_pasid_get_table(dev);
- return domain_context_mapping_one(domain, iommu, table, bus, devfn);
+
+ if (!dev_is_pci(dev))
+ return domain_context_mapping_one(domain, iommu, table,
+ bus, devfn);
+
+ data.domain = domain;
+ data.iommu = iommu;
+ data.table = table;
+
+ return pci_for_each_dma_alias(to_pci_dev(dev),
+ &domain_context_mapping_cb, &data);
}
static int domain_context_mapped_cb(struct pci_dev *pdev,
@@ -2189,17 +2312,20 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
unsigned long sg_res = 0;
unsigned int largepage_lvl = 0;
unsigned long lvl_pages = 0;
+ u64 attr;
BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
return -EINVAL;
- prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+ attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+ if (domain_use_first_level(domain))
+ attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
if (!sg) {
sg_res = nr_pages;
- pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+ pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
}
while (nr_pages > 0) {
@@ -2211,7 +2337,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
sg_res = aligned_nrpages(sg->offset, sg->length);
sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + pgoff;
sg->dma_length = sg->length;
- pteval = (sg_phys(sg) - pgoff) | prot;
+ pteval = (sg_phys(sg) - pgoff) | attr;
phys_pfn = pteval >> VTD_PAGE_SHIFT;
}
@@ -2380,14 +2506,27 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
spin_unlock_irqrestore(&device_domain_lock, flags);
}
-/*
- * find_domain
- * Note: we use struct device->archdata.iommu stores the info
- */
-static struct dmar_domain *find_domain(struct device *dev)
+struct dmar_domain *find_domain(struct device *dev)
{
struct device_domain_info *info;
+ if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
+ dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+ return NULL;
+
+ if (dev_is_pci(dev))
+ dev = &pci_real_dma_dev(to_pci_dev(dev))->dev;
+
+ /* No lock here, assumes no domain exit in normal case */
+ info = dev->archdata.iommu;
+ if (likely(info))
+ return info->domain;
+
+ return NULL;
+}
+
+static struct dmar_domain *deferred_attach_domain(struct device *dev)
+{
if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
struct iommu_domain *domain;
@@ -2397,12 +2536,7 @@ static struct dmar_domain *find_domain(struct device *dev)
intel_iommu_attach_device(domain, dev);
}
- /* No lock here, assumes no domain exit in normal case */
- info = dev->archdata.iommu;
-
- if (likely(info))
- return info->domain;
- return NULL;
+ return find_domain(dev);
}
static inline struct device_domain_info *
@@ -2418,6 +2552,36 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
return NULL;
}
+static int domain_setup_first_level(struct intel_iommu *iommu,
+ struct dmar_domain *domain,
+ struct device *dev,
+ int pasid)
+{
+ int flags = PASID_FLAG_SUPERVISOR_MODE;
+ struct dma_pte *pgd = domain->pgd;
+ int agaw, level;
+
+ /*
+ * Skip top levels of page tables for iommu which has
+ * less agaw than default. Unnecessary for PT mode.
+ */
+ for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+ pgd = phys_to_virt(dma_pte_addr(pgd));
+ if (!dma_pte_present(pgd))
+ return -ENOMEM;
+ }
+
+ level = agaw_to_level(agaw);
+ if (level != 4 && level != 5)
+ return -EINVAL;
+
+ flags |= (level == 5) ? PASID_FLAG_FL5LP : 0;
+
+ return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+ domain->iommu_did[iommu->seq_id],
+ flags);
+}
+
static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
int bus, int devfn,
struct device *dev,
@@ -2517,6 +2681,9 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
if (hw_pass_through && domain_type_is_si(domain))
ret = intel_pasid_setup_pass_through(iommu, domain,
dev, PASID_RID2PASID);
+ else if (domain_use_first_level(domain))
+ ret = domain_setup_first_level(iommu, domain, dev,
+ PASID_RID2PASID);
else
ret = intel_pasid_setup_second_level(iommu, domain,
dev, PASID_RID2PASID);
@@ -2722,10 +2889,8 @@ static int __init si_domain_init(int hw)
}
/*
- * Normally we use DMA domains for devices which have RMRRs. But we
- * loose this requirement for graphic and usb devices. Identity map
- * the RMRRs for graphic and USB devices so that they could use the
- * si_domain.
+ * Identity map the RMRRs so that devices with RMRRs could also use
+ * the si_domain.
*/
for_each_rmrr_units(rmrr) {
for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
@@ -2733,9 +2898,6 @@ static int __init si_domain_init(int hw)
unsigned long long start = rmrr->base_address;
unsigned long long end = rmrr->end_address;
- if (device_is_rmrr_locked(dev))
- continue;
-
if (WARN_ON(end < start ||
end >> agaw_to_width(si_domain->agaw)))
continue;
@@ -2754,7 +2916,7 @@ static int identity_mapping(struct device *dev)
struct device_domain_info *info;
info = dev->archdata.iommu;
- if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+ if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
return (info->domain == si_domain);
return 0;
@@ -2874,9 +3036,6 @@ static int device_def_domain_type(struct device *dev)
if (dev_is_pci(dev)) {
struct pci_dev *pdev = to_pci_dev(dev);
- if (device_is_rmrr_locked(dev))
- return IOMMU_DOMAIN_DMA;
-
/*
* Prevent any device marked as untrusted from getting
* placed into the statically identity mapping domain.
@@ -2914,13 +3073,9 @@ static int device_def_domain_type(struct device *dev)
return IOMMU_DOMAIN_DMA;
} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
return IOMMU_DOMAIN_DMA;
- } else {
- if (device_has_rmrr(dev))
- return IOMMU_DOMAIN_DMA;
}
- return (iommu_identity_mapping & IDENTMAP_ALL) ?
- IOMMU_DOMAIN_IDENTITY : 0;
+ return 0;
}
static void intel_iommu_init_qi(struct intel_iommu *iommu)
@@ -3249,10 +3404,7 @@ static int __init init_dmars(void)
if (!ecap_pass_through(iommu->ecap))
hw_pass_through = 0;
-#ifdef CONFIG_INTEL_IOMMU_SVM
- if (pasid_supported(iommu))
- intel_svm_init(iommu);
-#endif
+ intel_svm_check(iommu);
}
/*
@@ -3267,9 +3419,6 @@ static int __init init_dmars(void)
iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}
- if (iommu_pass_through)
- iommu_identity_mapping |= IDENTMAP_ALL;
-
#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
dmar_map_gfx = 0;
#endif
@@ -3342,8 +3491,21 @@ static unsigned long intel_alloc_iova(struct device *dev,
{
unsigned long iova_pfn;
- /* Restrict dma_mask to the width that the iommu can handle */
- dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+ /*
+ * Restrict dma_mask to the width that the iommu can handle.
+ * First-level translation restricts the input-address to a
+ * canonical address (i.e., address bits 63:N have the same
+ * value as address bit [N-1], where N is 48-bits with 4-level
+ * paging and 57-bits with 5-level paging). Hence, skip bit
+ * [N-1].
+ */
+ if (domain_use_first_level(domain))
+ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw - 1),
+ dma_mask);
+ else
+ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw),
+ dma_mask);
+
/* Ensure we reserve the whole size-aligned region */
nrpages = __roundup_pow_of_two(nrpages);
@@ -3361,7 +3523,8 @@ static unsigned long intel_alloc_iova(struct device *dev,
iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
IOVA_PFN(dma_mask), true);
if (unlikely(!iova_pfn)) {
- dev_err(dev, "Allocating %ld-page iova failed", nrpages);
+ dev_err_once(dev, "Allocating %ld-page iova failed\n",
+ nrpages);
return 0;
}
@@ -3431,7 +3594,7 @@ static bool iommu_need_mapping(struct device *dev)
if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
dma_mask = dev->coherent_dma_mask;
- if (dma_mask >= dma_get_required_mask(dev))
+ if (dma_mask >= dma_direct_get_required_mask(dev))
return false;
/*
@@ -3472,7 +3635,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
BUG_ON(dir == DMA_NONE);
- domain = find_domain(dev);
+ domain = deferred_attach_domain(dev);
if (!domain)
return DMA_MAPPING_ERROR;
@@ -3505,6 +3668,9 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT;
start_paddr += paddr & ~PAGE_MASK;
+
+ trace_map_single(dev, start_paddr, paddr, size << VTD_PAGE_SHIFT);
+
return start_paddr;
error:
@@ -3560,10 +3726,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
if (dev_is_pci(dev))
pdev = to_pci_dev(dev);
- dev_dbg(dev, "Device unmapping: pfn %lx-%lx\n", start_pfn, last_pfn);
-
freelist = domain_unmap(domain, start_pfn, last_pfn);
-
if (intel_iommu_strict || (pdev && pdev->untrusted) ||
!has_iova_flush_queue(&domain->iovad)) {
iommu_flush_iotlb_psi(iommu, domain, start_pfn,
@@ -3579,6 +3742,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
* cpu used up by the iotlb flush operation...
*/
}
+
+ trace_unmap_single(dev, dev_addr, size);
}
static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
@@ -3669,6 +3834,8 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
}
intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
+
+ trace_unmap_sg(dev, startaddr, nrpages << VTD_PAGE_SHIFT);
}
static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
@@ -3688,7 +3855,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
if (!iommu_need_mapping(dev))
return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
- domain = find_domain(dev);
+ domain = deferred_attach_domain(dev);
if (!domain)
return 0;
@@ -3725,9 +3892,19 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
return 0;
}
+ for_each_sg(sglist, sg, nelems, i)
+ trace_map_sg(dev, i + 1, nelems, sg);
+
return nelems;
}
+static u64 intel_get_required_mask(struct device *dev)
+{
+ if (!iommu_need_mapping(dev))
+ return dma_direct_get_required_mask(dev);
+ return DMA_BIT_MASK(32);
+}
+
static const struct dma_map_ops intel_dma_ops = {
.alloc = intel_alloc_coherent,
.free = intel_free_coherent,
@@ -3738,6 +3915,258 @@ static const struct dma_map_ops intel_dma_ops = {
.map_resource = intel_map_resource,
.unmap_resource = intel_unmap_resource,
.dma_supported = dma_direct_supported,
+ .mmap = dma_common_mmap,
+ .get_sgtable = dma_common_get_sgtable,
+ .get_required_mask = intel_get_required_mask,
+};
+
+static void
+bounce_sync_single(struct device *dev, dma_addr_t addr, size_t size,
+ enum dma_data_direction dir, enum dma_sync_target target)
+{
+ struct dmar_domain *domain;
+ phys_addr_t tlb_addr;
+
+ domain = find_domain(dev);
+ if (WARN_ON(!domain))
+ return;
+
+ tlb_addr = intel_iommu_iova_to_phys(&domain->domain, addr);
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_sync_single(dev, tlb_addr, size, dir, target);
+}
+
+static dma_addr_t
+bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs,
+ u64 dma_mask)
+{
+ size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE);
+ struct dmar_domain *domain;
+ struct intel_iommu *iommu;
+ unsigned long iova_pfn;
+ unsigned long nrpages;
+ phys_addr_t tlb_addr;
+ int prot = 0;
+ int ret;
+
+ domain = deferred_attach_domain(dev);
+ if (WARN_ON(dir == DMA_NONE || !domain))
+ return DMA_MAPPING_ERROR;
+
+ iommu = domain_get_iommu(domain);
+ if (WARN_ON(!iommu))
+ return DMA_MAPPING_ERROR;
+
+ nrpages = aligned_nrpages(0, size);
+ iova_pfn = intel_alloc_iova(dev, domain,
+ dma_to_mm_pfn(nrpages), dma_mask);
+ if (!iova_pfn)
+ return DMA_MAPPING_ERROR;
+
+ /*
+ * Check if DMAR supports zero-length reads on write only
+ * mappings..
+ */
+ if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL ||
+ !cap_zlr(iommu->cap))
+ prot |= DMA_PTE_READ;
+ if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+ prot |= DMA_PTE_WRITE;
+
+ /*
+ * If both the physical buffer start address and size are
+ * page aligned, we don't need to use a bounce page.
+ */
+ if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
+ tlb_addr = swiotlb_tbl_map_single(dev,
+ __phys_to_dma(dev, io_tlb_start),
+ paddr, size, aligned_size, dir, attrs);
+ if (tlb_addr == DMA_MAPPING_ERROR) {
+ goto swiotlb_error;
+ } else {
+ /* Cleanup the padding area. */
+ void *padding_start = phys_to_virt(tlb_addr);
+ size_t padding_size = aligned_size;
+
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ (dir == DMA_TO_DEVICE ||
+ dir == DMA_BIDIRECTIONAL)) {
+ padding_start += size;
+ padding_size -= size;
+ }
+
+ memset(padding_start, 0, padding_size);
+ }
+ } else {
+ tlb_addr = paddr;
+ }
+
+ ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn),
+ tlb_addr >> VTD_PAGE_SHIFT, nrpages, prot);
+ if (ret)
+ goto mapping_error;
+
+ trace_bounce_map_single(dev, iova_pfn << PAGE_SHIFT, paddr, size);
+
+ return (phys_addr_t)iova_pfn << PAGE_SHIFT;
+
+mapping_error:
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_unmap_single(dev, tlb_addr, size,
+ aligned_size, dir, attrs);
+swiotlb_error:
+ free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
+ dev_err(dev, "Device bounce map: %zx@%llx dir %d --- failed\n",
+ size, (unsigned long long)paddr, dir);
+
+ return DMA_MAPPING_ERROR;
+}
+
+static void
+bounce_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE);
+ struct dmar_domain *domain;
+ phys_addr_t tlb_addr;
+
+ domain = find_domain(dev);
+ if (WARN_ON(!domain))
+ return;
+
+ tlb_addr = intel_iommu_iova_to_phys(&domain->domain, dev_addr);
+ if (WARN_ON(!tlb_addr))
+ return;
+
+ intel_unmap(dev, dev_addr, size);
+ if (is_swiotlb_buffer(tlb_addr))
+ swiotlb_tbl_unmap_single(dev, tlb_addr, size,
+ aligned_size, dir, attrs);
+
+ trace_bounce_unmap_single(dev, dev_addr, size);
+}
+
+static dma_addr_t
+bounce_map_page(struct device *dev, struct page *page, unsigned long offset,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ return bounce_map_single(dev, page_to_phys(page) + offset,
+ size, dir, attrs, *dev->dma_mask);
+}
+
+static dma_addr_t
+bounce_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ return bounce_map_single(dev, phys_addr, size,
+ dir, attrs, *dev->dma_mask);
+}
+
+static void
+bounce_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ bounce_unmap_single(dev, dev_addr, size, dir, attrs);
+}
+
+static void
+bounce_unmap_resource(struct device *dev, dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ bounce_unmap_single(dev, dev_addr, size, dir, attrs);
+}
+
+static void
+bounce_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_unmap_page(dev, sg->dma_address,
+ sg_dma_len(sg), dir, attrs);
+}
+
+static int
+bounce_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sglist, sg, nelems, i) {
+ sg->dma_address = bounce_map_page(dev, sg_page(sg),
+ sg->offset, sg->length,
+ dir, attrs);
+ if (sg->dma_address == DMA_MAPPING_ERROR)
+ goto out_unmap;
+ sg_dma_len(sg) = sg->length;
+ }
+
+ for_each_sg(sglist, sg, nelems, i)
+ trace_bounce_map_sg(dev, i + 1, nelems, sg);
+
+ return nelems;
+
+out_unmap:
+ bounce_unmap_sg(dev, sglist, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+ return 0;
+}
+
+static void
+bounce_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
+{
+ bounce_sync_single(dev, addr, size, dir, SYNC_FOR_CPU);
+}
+
+static void
+bounce_sync_single_for_device(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir)
+{
+ bounce_sync_single(dev, addr, size, dir, SYNC_FOR_DEVICE);
+}
+
+static void
+bounce_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_sync_single(dev, sg_dma_address(sg),
+ sg_dma_len(sg), dir, SYNC_FOR_CPU);
+}
+
+static void
+bounce_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+ int nelems, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sglist, sg, nelems, i)
+ bounce_sync_single(dev, sg_dma_address(sg),
+ sg_dma_len(sg), dir, SYNC_FOR_DEVICE);
+}
+
+static const struct dma_map_ops bounce_dma_ops = {
+ .alloc = intel_alloc_coherent,
+ .free = intel_free_coherent,
+ .map_sg = bounce_map_sg,
+ .unmap_sg = bounce_unmap_sg,
+ .map_page = bounce_map_page,
+ .unmap_page = bounce_unmap_page,
+ .sync_single_for_cpu = bounce_sync_single_for_cpu,
+ .sync_single_for_device = bounce_sync_single_for_device,
+ .sync_sg_for_cpu = bounce_sync_sg_for_cpu,
+ .sync_sg_for_device = bounce_sync_sg_for_device,
+ .map_resource = bounce_map_resource,
+ .unmap_resource = bounce_unmap_resource,
+ .dma_supported = dma_direct_supported,
};
static inline int iommu_domain_cache_init(void)
@@ -4007,17 +4436,38 @@ static void __init init_iommu_pm_ops(void)
static inline void init_iommu_pm_ops(void) {}
#endif /* CONFIG_PM */
+static int rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+ if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
+ !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
+ rmrr->end_address <= rmrr->base_address ||
+ arch_rmrr_sanity_check(rmrr))
+ return -EINVAL;
+
+ return 0;
+}
+
int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
{
struct acpi_dmar_reserved_memory *rmrr;
struct dmar_rmrr_unit *rmrru;
+ rmrr = (struct acpi_dmar_reserved_memory *)header;
+ if (rmrr_sanity_check(rmrr))
+ WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+ "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
+ "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+ rmrr->base_address, rmrr->end_address,
+ dmi_get_system_info(DMI_BIOS_VENDOR),
+ dmi_get_system_info(DMI_BIOS_VERSION),
+ dmi_get_system_info(DMI_PRODUCT_VERSION));
+
rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
if (!rmrru)
goto out;
rmrru->hdr = header;
- rmrr = (struct acpi_dmar_reserved_memory *)header;
+
rmrru->base_address = rmrr->base_address;
rmrru->end_address = rmrr->end_address;
@@ -4156,7 +4606,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
iommu->name);
return -ENXIO;
}
- sp = domain_update_iommu_superpage(iommu) - 1;
+ sp = domain_update_iommu_superpage(NULL, iommu) - 1;
if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
pr_warn("%s: Doesn't support large page.\n",
iommu->name);
@@ -4176,10 +4626,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
if (ret)
goto out;
-#ifdef CONFIG_INTEL_IOMMU_SVM
- if (pasid_supported(iommu))
- intel_svm_init(iommu);
-#endif
+ intel_svm_check(iommu);
if (dmaru->ignored) {
/*
@@ -4456,6 +4903,26 @@ static void intel_disable_iommus(void)
iommu_disable_translation(iommu);
}
+void intel_iommu_shutdown(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu = NULL;
+
+ if (no_iommu || dmar_disabled)
+ return;
+
+ down_write(&dmar_global_lock);
+
+ /* Disable PMRs explicitly here. */
+ for_each_iommu(iommu, drhd)
+ iommu_disable_protect_mem_regions(iommu);
+
+ /* Make sure the IOMMUs are switched off */
+ intel_disable_iommus();
+
+ up_write(&dmar_global_lock);
+}
+
static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
{
struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
@@ -4540,22 +5007,20 @@ const struct attribute_group *intel_iommu_groups[] = {
NULL,
};
-static int __init platform_optin_force_iommu(void)
+static inline bool has_untrusted_dev(void)
{
struct pci_dev *pdev = NULL;
- bool has_untrusted_dev = false;
- if (!dmar_platform_optin() || no_platform_optin)
- return 0;
+ for_each_pci_dev(pdev)
+ if (pdev->untrusted)
+ return true;
- for_each_pci_dev(pdev) {
- if (pdev->untrusted) {
- has_untrusted_dev = true;
- break;
- }
- }
+ return false;
+}
- if (!has_untrusted_dev)
+static int __init platform_optin_force_iommu(void)
+{
+ if (!dmar_platform_optin() || no_platform_optin || !has_untrusted_dev())
return 0;
if (no_iommu || dmar_disabled)
@@ -4566,12 +5031,9 @@ static int __init platform_optin_force_iommu(void)
* map for all devices except those marked as being untrusted.
*/
if (dmar_disabled)
- iommu_identity_mapping |= IDENTMAP_ALL;
+ iommu_set_default_passthrough(false);
dmar_disabled = 0;
-#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB)
- swiotlb = 0;
-#endif
no_iommu = 0;
return 1;
@@ -4711,7 +5173,14 @@ int __init intel_iommu_init(void)
up_write(&dmar_global_lock);
#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB)
- swiotlb = 0;
+ /*
+ * If the system has no untrusted device or the user has decided
+ * to disable the bounce page mechanisms, we don't need swiotlb.
+ * Mark this and the pre-allocated bounce pages will be released
+ * later.
+ */
+ if (!has_untrusted_dev() || intel_no_bounce)
+ swiotlb = 0;
#endif
dma_ops = &intel_dma_ops;
@@ -4759,6 +5228,28 @@ out_free_dmar:
return ret;
}
+static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
+{
+ struct intel_iommu *iommu = opaque;
+
+ domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff);
+ return 0;
+}
+
+/*
+ * NB - intel-iommu lacks any sort of reference counting for the users of
+ * dependent devices. If multiple endpoints have intersecting dependent
+ * devices, unbinding the driver from any one of them will possibly leave
+ * the others unable to operate.
+ */
+static void domain_context_clear(struct intel_iommu *iommu, struct device *dev)
+{
+ if (!iommu || !dev || !dev_is_pci(dev))
+ return;
+
+ pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu);
+}
+
static void __dmar_remove_one_dev_info(struct device_domain_info *info)
{
struct dmar_domain *domain;
@@ -4779,7 +5270,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
PASID_RID2PASID);
iommu_disable_dev_iotlb(info);
- domain_context_clear_one(iommu, info->bus, info->devfn);
+ domain_context_clear(iommu, info->dev);
intel_pasid_free_table(info->dev);
}
@@ -4805,7 +5296,8 @@ static void dmar_remove_one_dev_info(struct device *dev)
spin_lock_irqsave(&device_domain_lock, flags);
info = dev->archdata.iommu;
- if (info)
+ if (info && info != DEFER_DEVICE_DOMAIN_INFO
+ && info != DUMMY_DEVICE_DOMAIN_INFO)
__dmar_remove_one_dev_info(info);
spin_unlock_irqrestore(&device_domain_lock, flags);
}
@@ -4839,6 +5331,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
{
struct dmar_domain *dmar_domain;
struct iommu_domain *domain;
+ int ret;
switch (type) {
case IOMMU_DOMAIN_DMA:
@@ -4855,11 +5348,12 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
return NULL;
}
- if (type == IOMMU_DOMAIN_DMA &&
- init_iova_flush_queue(&dmar_domain->iovad,
- iommu_flush_iova, iova_entry_free)) {
- pr_warn("iova flush queue initialization failed\n");
- intel_iommu_strict = 1;
+ if (!intel_iommu_strict && type == IOMMU_DOMAIN_DMA) {
+ ret = init_iova_flush_queue(&dmar_domain->iovad,
+ iommu_flush_iova,
+ iova_entry_free);
+ if (ret)
+ pr_info("iova flush queue initialization failed\n");
}
domain_update_iommu_cap(dmar_domain);
@@ -4925,7 +5419,7 @@ static void auxiliary_unlink_device(struct dmar_domain *domain,
domain->auxd_refcnt--;
if (!domain->auxd_refcnt && domain->default_pasid > 0)
- intel_pasid_free_id(domain->default_pasid);
+ ioasid_free(domain->default_pasid);
}
static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4943,10 +5437,11 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
if (domain->default_pasid <= 0) {
int pasid;
- pasid = intel_pasid_alloc_id(domain, PASID_MIN,
- pci_max_pasids(to_pci_dev(dev)),
- GFP_KERNEL);
- if (pasid <= 0) {
+ /* No private data needed for the default pasid */
+ pasid = ioasid_alloc(NULL, PASID_MIN,
+ pci_max_pasids(to_pci_dev(dev)) - 1,
+ NULL);
+ if (pasid == INVALID_IOASID) {
pr_err("Can't allocate default pasid\n");
return -ENODEV;
}
@@ -4964,8 +5459,12 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
goto attach_failed;
/* Setup the PASID entry for mediated devices: */
- ret = intel_pasid_setup_second_level(iommu, domain, dev,
- domain->default_pasid);
+ if (domain_use_first_level(domain))
+ ret = domain_setup_first_level(iommu, domain, dev,
+ domain->default_pasid);
+ else
+ ret = intel_pasid_setup_second_level(iommu, domain, dev,
+ domain->default_pasid);
if (ret)
goto table_failed;
spin_unlock(&iommu->lock);
@@ -4982,7 +5481,7 @@ attach_failed:
spin_unlock(&iommu->lock);
spin_unlock_irqrestore(&device_domain_lock, flags);
if (!domain->auxd_refcnt && domain->default_pasid > 0)
- intel_pasid_free_id(domain->default_pasid);
+ ioasid_free(domain->default_pasid);
return ret;
}
@@ -5113,16 +5612,13 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
static int intel_iommu_map(struct iommu_domain *domain,
unsigned long iova, phys_addr_t hpa,
- size_t size, int iommu_prot)
+ size_t size, int iommu_prot, gfp_t gfp)
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
u64 max_addr;
int prot = 0;
int ret;
- if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
- return -EINVAL;
-
if (iommu_prot & IOMMU_READ)
prot |= DMA_PTE_READ;
if (iommu_prot & IOMMU_WRITE)
@@ -5153,7 +5649,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
}
static size_t intel_iommu_unmap(struct iommu_domain *domain,
- unsigned long iova, size_t size)
+ unsigned long iova, size_t size,
+ struct iommu_iotlb_gather *gather)
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
struct page *freelist = NULL;
@@ -5164,8 +5661,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
/* Cope with horrid API which requires us to unmap more than the
size argument if it happens to be a large-page mapping. */
BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level));
- if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
- return 0;
if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
size = VTD_PAGE_SIZE << level_to_offset_bits(level);
@@ -5197,9 +5692,6 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
int level = 0;
u64 phys = 0;
- if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
- return 0;
-
pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
if (pte)
phys = dma_pte_addr(pte);
@@ -5243,6 +5735,24 @@ static inline bool iommu_pasid_support(void)
return ret;
}
+static inline bool nested_mode_support(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ bool ret = true;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!sm_supported(iommu) || !ecap_nest(iommu->ecap)) {
+ ret = false;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
static bool intel_iommu_capable(enum iommu_cap cap)
{
if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -5273,8 +5783,10 @@ static int intel_iommu_add_device(struct device *dev)
group = iommu_group_get_for_dev(dev);
- if (IS_ERR(group))
- return PTR_ERR(group);
+ if (IS_ERR(group)) {
+ ret = PTR_ERR(group);
+ goto unlink;
+ }
iommu_group_put(group);
@@ -5300,7 +5812,8 @@ static int intel_iommu_add_device(struct device *dev)
if (!get_private_domain_for_dev(dev)) {
dev_warn(dev,
"Failed to get a private domain.\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto unlink;
}
dev_info(dev,
@@ -5309,7 +5822,16 @@ static int intel_iommu_add_device(struct device *dev)
}
}
+ if (device_needs_bounce(dev)) {
+ dev_info(dev, "Use Intel IOMMU bounce page dma_ops\n");
+ set_dma_ops(dev, &bounce_dma_ops);
+ }
+
return 0;
+
+unlink:
+ iommu_device_unlink(&iommu->iommu, dev);
+ return ret;
}
static void intel_iommu_remove_device(struct device *dev)
@@ -5326,6 +5848,9 @@ static void intel_iommu_remove_device(struct device *dev)
iommu_group_remove_device(dev);
iommu_device_unlink(&iommu->iommu, dev);
+
+ if (device_needs_bounce(dev))
+ set_dma_ops(dev, NULL);
}
static void intel_iommu_get_resv_regions(struct device *device,
@@ -5369,8 +5894,8 @@ static void intel_iommu_get_resv_regions(struct device *device,
struct pci_dev *pdev = to_pci_dev(device);
if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) {
- reg = iommu_alloc_resv_region(0, 1UL << 24, 0,
- IOMMU_RESV_DIRECT);
+ reg = iommu_alloc_resv_region(0, 1UL << 24, prot,
+ IOMMU_RESV_DIRECT_RELAXABLE);
if (reg)
list_add_tail(&reg->list, head);
}
@@ -5385,15 +5910,6 @@ static void intel_iommu_get_resv_regions(struct device *device,
list_add_tail(&reg->list, head);
}
-static void intel_iommu_put_resv_regions(struct device *dev,
- struct list_head *head)
-{
- struct iommu_resv_region *entry, *next;
-
- list_for_each_entry_safe(entry, next, head, list)
- kfree(entry);
-}
-
int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
{
struct device_domain_info *info;
@@ -5458,6 +5974,13 @@ static void intel_iommu_apply_resv_region(struct device *dev,
WARN_ON_ONCE(!reserve_iova(&dmar_domain->iovad, start, end));
}
+static struct iommu_group *intel_iommu_device_group(struct device *dev)
+{
+ if (dev_is_pci(dev))
+ return pci_device_group(dev);
+ return generic_device_group(dev);
+}
+
#ifdef CONFIG_INTEL_IOMMU_SVM
struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
{
@@ -5613,10 +6136,42 @@ static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
}
+static int
+intel_iommu_domain_set_attr(struct iommu_domain *domain,
+ enum iommu_attr attr, void *data)
+{
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+ unsigned long flags;
+ int ret = 0;
+
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
+ switch (attr) {
+ case DOMAIN_ATTR_NESTING:
+ spin_lock_irqsave(&device_domain_lock, flags);
+ if (nested_mode_support() &&
+ list_empty(&dmar_domain->devices)) {
+ dmar_domain->flags |= DOMAIN_FLAG_NESTING_MODE;
+ dmar_domain->flags &= ~DOMAIN_FLAG_USE_FIRST_LEVEL;
+ } else {
+ ret = -ENODEV;
+ }
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
const struct iommu_ops intel_iommu_ops = {
.capable = intel_iommu_capable,
.domain_alloc = intel_iommu_domain_alloc,
.domain_free = intel_iommu_domain_free,
+ .domain_set_attr = intel_iommu_domain_set_attr,
.attach_dev = intel_iommu_attach_device,
.detach_dev = intel_iommu_detach_device,
.aux_attach_dev = intel_iommu_aux_attach_device,
@@ -5628,9 +6183,9 @@ const struct iommu_ops intel_iommu_ops = {
.add_device = intel_iommu_add_device,
.remove_device = intel_iommu_remove_device,
.get_resv_regions = intel_iommu_get_resv_regions,
- .put_resv_regions = intel_iommu_put_resv_regions,
+ .put_resv_regions = generic_iommu_put_resv_regions,
.apply_resv_region = intel_iommu_apply_resv_region,
- .device_group = pci_device_group,
+ .device_group = intel_iommu_device_group,
.dev_has_feat = intel_iommu_dev_has_feat,
.dev_feat_enabled = intel_iommu_dev_feat_enabled,
.dev_enable_feat = intel_iommu_dev_enable_feat,
@@ -5639,20 +6194,46 @@ const struct iommu_ops intel_iommu_ops = {
.pgsize_bitmap = INTEL_IOMMU_PGSIZES,
};
-static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
+static void quirk_iommu_igfx(struct pci_dev *dev)
{
- /* G4x/GM45 integrated gfx dmar support is totally busted. */
pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
dmar_map_gfx = 0;
}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx);
+/* G4x/GM45 integrated gfx dmar support is totally busted. */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);
+
+/* Broadwell igfx malfunctions with dmar */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1602, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1616, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1612, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1626, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1622, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162D, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1636, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163B, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163E, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx);
static void quirk_iommu_rwbf(struct pci_dev *dev)
{
OpenPOWER on IntegriCloud