aboutsummaryrefslogtreecommitdiff
path: root/drivers/iommu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu')
-rw-r--r--drivers/iommu/amd_iommu.c40
-rw-r--r--drivers/iommu/arm-smmu-v3.c4
-rw-r--r--drivers/iommu/dma-iommu.c28
-rw-r--r--drivers/iommu/intel-iommu-debugfs.c2
-rw-r--r--drivers/iommu/intel-iommu.c66
-rw-r--r--drivers/iommu/intel-svm.c36
6 files changed, 132 insertions, 44 deletions
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b607a92791d3..61de81965c44 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1143,6 +1143,17 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
iommu_completion_wait(iommu);
}
+static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
+{
+ struct iommu_cmd cmd;
+
+ build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+ dom_id, 1);
+ iommu_queue_command(iommu, &cmd);
+
+ iommu_completion_wait(iommu);
+}
+
static void amd_iommu_flush_all(struct amd_iommu *iommu)
{
struct iommu_cmd cmd;
@@ -1424,18 +1435,21 @@ static void free_pagetable(struct protection_domain *domain)
* another level increases the size of the address space by 9 bits to a size up
* to 64 bits.
*/
-static bool increase_address_space(struct protection_domain *domain,
+static void increase_address_space(struct protection_domain *domain,
gfp_t gfp)
{
+ unsigned long flags;
u64 *pte;
- if (domain->mode == PAGE_MODE_6_LEVEL)
+ spin_lock_irqsave(&domain->lock, flags);
+
+ if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
/* address space already 64 bit large */
- return false;
+ goto out;
pte = (void *)get_zeroed_page(gfp);
if (!pte)
- return false;
+ goto out;
*pte = PM_LEVEL_PDE(domain->mode,
iommu_virt_to_phys(domain->pt_root));
@@ -1443,7 +1457,10 @@ static bool increase_address_space(struct protection_domain *domain,
domain->mode += 1;
domain->updated = true;
- return true;
+out:
+ spin_unlock_irqrestore(&domain->lock, flags);
+
+ return;
}
static u64 *alloc_pte(struct protection_domain *domain,
@@ -1873,6 +1890,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain,
{
u64 pte_root = 0;
u64 flags = 0;
+ u32 old_domid;
if (domain->mode != PAGE_MODE_NONE)
pte_root = iommu_virt_to_phys(domain->pt_root);
@@ -1922,8 +1940,20 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain,
flags &= ~DEV_DOMID_MASK;
flags |= domain->id;
+ old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK;
amd_iommu_dev_table[devid].data[1] = flags;
amd_iommu_dev_table[devid].data[0] = pte_root;
+
+ /*
+ * A kdump kernel might be replacing a domain ID that was copied from
+ * the previous kernel--if so, it needs to flush the translation cache
+ * entries for the old domain ID that is being overwritten
+ */
+ if (old_domid) {
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ amd_iommu_flush_tlb_domid(iommu, old_domid);
+ }
}
static void clear_dte_entry(u16 devid)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index a9a9fabd3968..c5c93e48b4db 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1186,8 +1186,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
ste_live = true;
break;
case STRTAB_STE_0_CFG_ABORT:
- if (disable_bypass)
- break;
+ BUG_ON(!disable_bypass);
+ break;
default:
BUG(); /* STE corruption */
}
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a7f9c3edbcb2..f68a62c3c32b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -459,13 +459,11 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
{
struct iommu_domain *domain = iommu_get_dma_domain(dev);
struct iommu_dma_cookie *cookie = domain->iova_cookie;
- size_t iova_off = 0;
+ struct iova_domain *iovad = &cookie->iovad;
+ size_t iova_off = iova_offset(iovad, phys);
dma_addr_t iova;
- if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
- iova_off = iova_offset(&cookie->iovad, phys);
- size = iova_align(&cookie->iovad, size + iova_off);
- }
+ size = iova_align(iovad, size + iova_off);
iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
if (!iova)
@@ -574,7 +572,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
struct iova_domain *iovad = &cookie->iovad;
bool coherent = dev_is_dma_coherent(dev);
int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
- pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+ pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
struct page **pages;
struct sg_table sgt;
@@ -764,7 +762,7 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
* - and wouldn't make the resulting output segment too long
*/
if (cur_len && !s_iova_off && (dma_addr & seg_mask) &&
- (cur_len + s_length <= max_len)) {
+ (max_len - cur_len >= s_length)) {
/* ...then concatenate it with the previous one */
cur_len += s_length;
} else {
@@ -967,15 +965,18 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
{
bool coherent = dev_is_dma_coherent(dev);
size_t alloc_size = PAGE_ALIGN(size);
+ int node = dev_to_node(dev);
struct page *page = NULL;
void *cpu_addr;
page = dma_alloc_contiguous(dev, alloc_size, gfp);
if (!page)
+ page = alloc_pages_node(node, gfp, get_order(alloc_size));
+ if (!page)
return NULL;
if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
- pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+ pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
cpu_addr = dma_common_contiguous_remap(page, alloc_size,
VM_USERMAP, prot, __builtin_return_address(0));
@@ -1035,7 +1036,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long pfn, off = vma->vm_pgoff;
int ret;
- vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
@@ -1147,16 +1148,21 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
if (!msi_page)
return NULL;
- iova = __iommu_dma_map(dev, msi_addr, size, prot);
- if (iova == DMA_MAPPING_ERROR)
+ iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+ if (!iova)
goto out_free_page;
+ if (iommu_map(domain, iova, msi_addr, size, prot))
+ goto out_free_iova;
+
INIT_LIST_HEAD(&msi_page->list);
msi_page->phys = msi_addr;
msi_page->iova = iova;
list_add(&msi_page->list, &cookie->msi_page_list);
return msi_page;
+out_free_iova:
+ iommu_dma_free_iova(cookie, iova, size);
out_free_page:
kfree(msi_page);
return NULL;
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 2b25d9c59336..471f05d452e0 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -235,7 +235,7 @@ static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus)
tbl_wlk.ctx_entry = context;
m->private = &tbl_wlk;
- if (pasid_supported(iommu) && is_pasid_enabled(context)) {
+ if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT) {
pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
pasid_dir_size = get_pasid_dir_size(context);
pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index bdaed2da8a55..c4e0e4a9ee9e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -339,6 +339,8 @@ 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);
@@ -2105,9 +2107,26 @@ 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 +2136,17 @@ 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,
@@ -3449,6 +3478,7 @@ static bool iommu_need_mapping(struct device *dev)
dmar_domain = to_dmar_domain(domain);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
}
+ dmar_remove_one_dev_info(dev);
get_private_domain_for_dev(dev);
}
@@ -4758,6 +4788,28 @@ 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;
@@ -4778,7 +4830,7 @@ 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);
}
@@ -4790,7 +4842,8 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
/* free the private domain */
if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN &&
- !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY))
+ !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
+ list_empty(&domain->devices))
domain_exit(info->domain);
free_devinfo_mem(info);
@@ -4803,7 +4856,8 @@ static void dmar_remove_one_dev_info(struct device *dev)
spin_lock_irqsave(&device_domain_lock, flags);
info = dev->archdata.iommu;
- __dmar_remove_one_dev_info(info);
+ if (info)
+ __dmar_remove_one_dev_info(info);
spin_unlock_irqrestore(&device_domain_lock, flags);
}
@@ -5281,6 +5335,7 @@ static int intel_iommu_add_device(struct device *dev)
if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) {
ret = iommu_request_dm_for_dev(dev);
if (ret) {
+ dmar_remove_one_dev_info(dev);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
domain_add_dev_info(si_domain, dev);
dev_info(dev,
@@ -5291,6 +5346,7 @@ static int intel_iommu_add_device(struct device *dev)
if (device_def_domain_type(dev) == IOMMU_DOMAIN_DMA) {
ret = iommu_request_dma_domain_for_dev(dev);
if (ret) {
+ dmar_remove_one_dev_info(dev);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
if (!get_private_domain_for_dev(dev)) {
dev_warn(dev,
@@ -5316,6 +5372,8 @@ static void intel_iommu_remove_device(struct device *dev)
if (!iommu)
return;
+ dmar_remove_one_dev_info(dev);
+
iommu_group_remove_device(dev);
iommu_device_unlink(&iommu->iommu, dev);
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 780de0caafe8..9b159132405d 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -100,24 +100,19 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
}
static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
- unsigned long address, unsigned long pages, int ih, int gl)
+ unsigned long address, unsigned long pages, int ih)
{
struct qi_desc desc;
- if (pages == -1) {
- /* For global kernel pages we have to flush them in *all* PASIDs
- * because that's the only option the hardware gives us. Despite
- * the fact that they are actually only accessible through one. */
- if (gl)
- desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
- QI_EIOTLB_DID(sdev->did) |
- QI_EIOTLB_GRAN(QI_GRAN_ALL_ALL) |
- QI_EIOTLB_TYPE;
- else
- desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
- QI_EIOTLB_DID(sdev->did) |
- QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
- QI_EIOTLB_TYPE;
+ /*
+ * Do PASID granu IOTLB invalidation if page selective capability is
+ * not available.
+ */
+ if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) {
+ desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
+ QI_EIOTLB_DID(sdev->did) |
+ QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+ QI_EIOTLB_TYPE;
desc.qw1 = 0;
} else {
int mask = ilog2(__roundup_pow_of_two(pages));
@@ -127,7 +122,6 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
QI_EIOTLB_TYPE;
desc.qw1 = QI_EIOTLB_ADDR(address) |
- QI_EIOTLB_GL(gl) |
QI_EIOTLB_IH(ih) |
QI_EIOTLB_AM(mask);
}
@@ -162,13 +156,13 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
}
static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
- unsigned long pages, int ih, int gl)
+ unsigned long pages, int ih)
{
struct intel_svm_dev *sdev;
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list)
- intel_flush_svm_range_dev(svm, sdev, address, pages, ih, gl);
+ intel_flush_svm_range_dev(svm, sdev, address, pages, ih);
rcu_read_unlock();
}
@@ -180,7 +174,7 @@ static void intel_invalidate_range(struct mmu_notifier *mn,
struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
intel_flush_svm_range(svm, start,
- (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0, 0);
+ (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
}
static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -203,7 +197,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list) {
intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid);
- intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+ intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
}
rcu_read_unlock();
@@ -425,7 +419,7 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
* large and has to be physically contiguous. So it's
* hard to be as defensive as we might like. */
intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
- intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+ intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
kfree_rcu(sdev, rcu);
if (list_empty(&svm->devs)) {