#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/dmar.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
#include <linux/mempool.h>
#include <linux/memory.h>
#include <linux/cpu.h>
#include <linux/io.h>
#include <linux/iova.h>
#include <linux/iommu.h>
+#include <linux/dma-iommu.h>
#include <linux/intel-iommu.h>
#include <linux/syscore_ops.h>
#include <linux/tboot.h>
#include <linux/dmi.h>
#include <linux/pci-ats.h>
#include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
#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>
#define MAX_AGAW_WIDTH 64
#define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
-#define __DOMAIN_MAX_PFN(gaw) ((((uint64_t)1) << (gaw-VTD_PAGE_SHIFT)) - 1)
-#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << gaw) - 1)
+#define __DOMAIN_MAX_PFN(gaw) ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1)
+#define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1)
/* We limit DOMAIN_MAX_PFN to fit in an unsigned long, and DOMAIN_MAX_ADDR
to match. That way, we can use 'unsigned long' for PFNs with impunity. */
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.
return fls(mask);
}
+static int domain_update_device_node(struct dmar_domain *domain)
+{
+ struct device_domain_info *info;
+ int nid = NUMA_NO_NODE;
+
+ assert_spin_locked(&device_domain_lock);
+
+ if (list_empty(&domain->devices))
+ return NUMA_NO_NODE;
+
+ list_for_each_entry(info, &domain->devices, link) {
+ if (!info->dev)
+ continue;
+
+ /*
+ * There could possibly be multiple device numa nodes as devices
+ * within the same domain may sit behind different IOMMUs. There
+ * isn't perfect answer in such situation, so we select first
+ * come first served policy.
+ */
+ nid = dev_to_node(info->dev);
+ if (nid != NUMA_NO_NODE)
+ break;
+ }
+
+ return nid;
+}
+
/* Some capabilities may be different across iommus */
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(domain, NULL);
+
+ /*
+ * If RHSA is missing, we should default to the device numa domain
+ * as fall back.
+ */
+ if (domain->nid == NUMA_NO_NODE)
+ domain->nid = domain_update_device_node(domain);
+
+ /*
+ * 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))
+ domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
+ else
+ domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
}
struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
pages can only be freed after the IOTLB flush has been done. */
static struct page *domain_unmap(struct dmar_domain *domain,
unsigned long start_pfn,
- unsigned long last_pfn)
+ unsigned long last_pfn,
+ struct page *freelist)
{
- struct page *freelist;
-
BUG_ON(!domain_pfn_supported(domain, start_pfn));
BUG_ON(!domain_pfn_supported(domain, last_pfn));
BUG_ON(start_pfn > last_pfn);
/* we don't need lock here; nobody else touches the iova range */
freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw),
- domain->pgd, 0, start_pfn, last_pfn, NULL);
+ domain->pgd, 0, start_pfn, last_pfn,
+ freelist);
/* free pgd */
if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
}
}
-static void iova_entry_free(unsigned long data)
-{
- struct page *freelist = (struct page *)data;
-
- dma_free_pagelist(freelist);
-}
-
/* iommu handling */
static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
iommu_flush_write_buffer(iommu);
}
-static void iommu_flush_iova(struct iova_domain *iovad)
+static void intel_flush_iotlb_all(struct iommu_domain *domain)
{
- struct dmar_domain *domain;
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
int idx;
- domain = container_of(iovad, struct dmar_domain, iovad);
-
- for_each_domain_iommu(idx, domain) {
+ for_each_domain_iommu(idx, dmar_domain) {
struct intel_iommu *iommu = g_iommus[idx];
- u16 did = domain->iommu_did[iommu->seq_id];
+ u16 did = dmar_domain->iommu_did[iommu->seq_id];
- if (domain_use_first_level(domain))
- domain_flush_piotlb(iommu, domain, 0, -1, 0);
+ if (domain_use_first_level(dmar_domain))
+ domain_flush_piotlb(iommu, dmar_domain, 0, -1, 0);
else
iommu->flush.flush_iotlb(iommu, did, 0, 0,
DMA_TLB_DSI_FLUSH);
return count;
}
-static struct iova_domain reserved_iova_list;
-static struct lock_class_key reserved_rbtree_key;
-
-static int dmar_init_reserved_ranges(void)
-{
- struct pci_dev *pdev = NULL;
- struct iova *iova;
- int i;
-
- init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN);
-
- lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
- &reserved_rbtree_key);
-
- /* IOAPIC ranges shouldn't be accessed by DMA */
- iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
- IOVA_PFN(IOAPIC_RANGE_END));
- if (!iova) {
- pr_err("Reserve IOAPIC range failed\n");
- return -ENODEV;
- }
-
- /* Reserve all PCI MMIO to avoid peer-to-peer access */
- for_each_pci_dev(pdev) {
- struct resource *r;
-
- for (i = 0; i < PCI_NUM_RESOURCES; i++) {
- r = &pdev->resource[i];
- if (!r->flags || !(r->flags & IORESOURCE_MEM))
- continue;
- iova = reserve_iova(&reserved_iova_list,
- IOVA_PFN(r->start),
- IOVA_PFN(r->end));
- if (!iova) {
- pci_err(pdev, "Reserve iova for %pR failed\n", r);
- return -ENODEV;
- }
- }
- }
- return 0;
-}
-
static inline int guestwidth_to_adjustwidth(int gaw)
{
int agaw;
/* destroy iovas */
if (domain->domain.type == IOMMU_DOMAIN_DMA)
- put_iova_domain(&domain->iovad);
+ iommu_put_dma_cookie(&domain->domain);
if (domain->pgd) {
struct page *freelist;
- freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+ freelist = domain_unmap(domain, 0,
+ DOMAIN_MAX_PFN(domain->gaw), NULL);
dma_free_pagelist(freelist);
}
{
struct device_domain_info *info;
+ if (unlikely(!dev || !dev->iommu))
+ return NULL;
+
if (unlikely(attach_deferred(dev)))
return NULL;
return NULL;
}
-static void do_deferred_attach(struct device *dev)
-{
- struct iommu_domain *domain;
-
- dev_iommu_priv_set(dev, NULL);
- domain = iommu_get_domain_for_dev(dev);
- if (domain)
- intel_iommu_attach_device(domain, dev);
-}
-
static inline struct device_domain_info *
dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
{
static int domain_setup_first_level(struct intel_iommu *iommu,
struct dmar_domain *domain,
struct device *dev,
- int pasid)
+ u32 pasid)
{
int flags = PASID_FLAG_SUPERVISOR_MODE;
struct dma_pte *pgd = domain->pgd;
}
/* Setup the PASID entry for requests without PASID: */
- spin_lock(&iommu->lock);
+ spin_lock_irqsave(&iommu->lock, flags);
if (hw_pass_through && domain_type_is_si(domain))
ret = intel_pasid_setup_pass_through(iommu, domain,
dev, PASID_RID2PASID);
else
ret = intel_pasid_setup_second_level(iommu, domain,
dev, PASID_RID2PASID);
- spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&iommu->lock, flags);
if (ret) {
dev_err(dev, "Setup RID2PASID failed\n");
dmar_remove_one_dev_info(dev);
return ret;
}
-/* This takes a number of _MM_ pages, not VTD pages */
-static unsigned long intel_alloc_iova(struct device *dev,
- struct dmar_domain *domain,
- unsigned long nrpages, uint64_t dma_mask)
-{
- unsigned long iova_pfn;
-
- /*
- * 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);
-
- if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
- /*
- * First try to allocate an io virtual address in
- * DMA_BIT_MASK(32) and if that fails then try allocating
- * from higher range
- */
- iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
- IOVA_PFN(DMA_BIT_MASK(32)), false);
- if (iova_pfn)
- return iova_pfn;
- }
- iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
- IOVA_PFN(dma_mask), true);
- if (unlikely(!iova_pfn)) {
- dev_err_once(dev, "Allocating %ld-page iova failed\n",
- nrpages);
- return 0;
- }
-
- return iova_pfn;
-}
-
-static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
- size_t size, int dir, u64 dma_mask)
-{
- struct dmar_domain *domain;
- phys_addr_t start_paddr;
- unsigned long iova_pfn;
- int prot = 0;
- int ret;
- struct intel_iommu *iommu;
- unsigned long paddr_pfn = paddr >> PAGE_SHIFT;
-
- BUG_ON(dir == DMA_NONE);
-
- if (unlikely(attach_deferred(dev)))
- do_deferred_attach(dev);
-
- domain = find_domain(dev);
- if (!domain)
- return DMA_MAPPING_ERROR;
-
- iommu = domain_get_iommu(domain);
- size = aligned_nrpages(paddr, size);
-
- iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size), dma_mask);
- if (!iova_pfn)
- goto 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;
- /*
- * paddr - (paddr + size) might be partial page, we should map the whole
- * page. Note: if two part of one page are separately mapped, we
- * might have two guest_addr mapping to the same host paddr, but this
- * is not a big problem
- */
- ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn),
- mm_to_dma_pfn(paddr_pfn), size, prot);
- if (ret)
- goto error;
-
- 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:
- if (iova_pfn)
- free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
- dev_err(dev, "Device request: %zx@%llx dir %d --- failed\n",
- size, (unsigned long long)paddr, dir);
- return DMA_MAPPING_ERROR;
-}
-
-static dma_addr_t intel_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- return __intel_map_single(dev, page_to_phys(page) + offset,
- size, dir, *dev->dma_mask);
-}
-
-static dma_addr_t intel_map_resource(struct device *dev, phys_addr_t phys_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- return __intel_map_single(dev, phys_addr, size, dir, *dev->dma_mask);
-}
-
-static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
-{
- struct dmar_domain *domain;
- unsigned long start_pfn, last_pfn;
- unsigned long nrpages;
- unsigned long iova_pfn;
- struct intel_iommu *iommu;
- struct page *freelist;
- struct pci_dev *pdev = NULL;
-
- domain = find_domain(dev);
- BUG_ON(!domain);
-
- iommu = domain_get_iommu(domain);
-
- iova_pfn = IOVA_PFN(dev_addr);
-
- nrpages = aligned_nrpages(dev_addr, size);
- start_pfn = mm_to_dma_pfn(iova_pfn);
- last_pfn = start_pfn + nrpages - 1;
-
- if (dev_is_pci(dev))
- pdev = to_pci_dev(dev);
-
- 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,
- nrpages, !freelist, 0);
- /* free iova */
- free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages));
- dma_free_pagelist(freelist);
- } else {
- queue_iova(&domain->iovad, iova_pfn, nrpages,
- (unsigned long)freelist);
- /*
- * queue up the release of the unmap to save the 1/6th of the
- * 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,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- intel_unmap(dev, dev_addr, size);
-}
-
-static void intel_unmap_resource(struct device *dev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
- intel_unmap(dev, dev_addr, size);
-}
-
-static void *intel_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags,
- unsigned long attrs)
-{
- struct page *page = NULL;
- int order;
-
- if (unlikely(attach_deferred(dev)))
- do_deferred_attach(dev);
-
- size = PAGE_ALIGN(size);
- order = get_order(size);
-
- if (gfpflags_allow_blocking(flags)) {
- unsigned int count = size >> PAGE_SHIFT;
-
- page = dma_alloc_from_contiguous(dev, count, order,
- flags & __GFP_NOWARN);
- }
-
- if (!page)
- page = alloc_pages(flags, order);
- if (!page)
- return NULL;
- memset(page_address(page), 0, size);
-
- *dma_handle = __intel_map_single(dev, page_to_phys(page), size,
- DMA_BIDIRECTIONAL,
- dev->coherent_dma_mask);
- if (*dma_handle != DMA_MAPPING_ERROR)
- return page_address(page);
- if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
- __free_pages(page, order);
-
- return NULL;
-}
-
-static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- int order;
- struct page *page = virt_to_page(vaddr);
-
- size = PAGE_ALIGN(size);
- order = get_order(size);
-
- intel_unmap(dev, dma_handle, size);
- if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
- __free_pages(page, order);
-}
-
-static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
- int nelems, enum dma_data_direction dir,
- unsigned long attrs)
-{
- dma_addr_t startaddr = sg_dma_address(sglist) & PAGE_MASK;
- unsigned long nrpages = 0;
- struct scatterlist *sg;
- int i;
-
- for_each_sg(sglist, sg, nelems, i) {
- nrpages += aligned_nrpages(sg_dma_address(sg), sg_dma_len(sg));
- }
-
- 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,
- enum dma_data_direction dir, unsigned long attrs)
-{
- int i;
- struct dmar_domain *domain;
- size_t size = 0;
- int prot = 0;
- unsigned long iova_pfn;
- int ret;
- struct scatterlist *sg;
- unsigned long start_vpfn;
- struct intel_iommu *iommu;
-
- BUG_ON(dir == DMA_NONE);
-
- if (unlikely(attach_deferred(dev)))
- do_deferred_attach(dev);
-
- domain = find_domain(dev);
- if (!domain)
- return 0;
-
- iommu = domain_get_iommu(domain);
-
- for_each_sg(sglist, sg, nelems, i)
- size += aligned_nrpages(sg->offset, sg->length);
-
- iova_pfn = intel_alloc_iova(dev, domain, dma_to_mm_pfn(size),
- *dev->dma_mask);
- if (!iova_pfn) {
- sglist->dma_length = 0;
- return 0;
- }
-
- /*
- * 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;
-
- start_vpfn = mm_to_dma_pfn(iova_pfn);
-
- ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot);
- if (unlikely(ret)) {
- dma_pte_free_pagetable(domain, start_vpfn,
- start_vpfn + size - 1,
- agaw_to_level(domain->agaw) + 1);
- free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(size));
- 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)
-{
- return DMA_BIT_MASK(32);
-}
-
-static const struct dma_map_ops intel_dma_ops = {
- .alloc = intel_alloc_coherent,
- .free = intel_free_coherent,
- .map_sg = intel_map_sg,
- .unmap_sg = intel_unmap_sg,
- .map_page = intel_map_page,
- .unmap_page = intel_unmap_page,
- .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;
-
- if (unlikely(attach_deferred(dev)))
- do_deferred_attach(dev);
-
- domain = find_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)
{
int ret = 0;
struct page *freelist;
freelist = domain_unmap(si_domain,
- start_vpfn, last_vpfn);
+ start_vpfn, last_vpfn,
+ NULL);
rcu_read_lock();
for_each_active_iommu(iommu, drhd)
if (!domain || domain->domain.type != IOMMU_DOMAIN_DMA)
continue;
- free_cpu_cached_iovas(cpu, &domain->iovad);
+ iommu_dma_free_cpu_cached_iovas(cpu, &domain->domain);
}
}
}
if (list_empty(&dmar_atsr_units))
pr_info("No ATSR found\n");
- if (dmar_init_reserved_ranges()) {
- if (force_on)
- panic("tboot: Failed to reserve iommu ranges\n");
- goto out_free_reserved_range;
- }
-
if (dmar_map_gfx)
intel_iommu_gfx_mapped = 1;
if (force_on)
panic("tboot: Failed to initialize DMARs\n");
pr_err("Initialization failed\n");
- goto out_free_reserved_range;
+ goto out_free_dmar;
}
up_write(&dmar_global_lock);
return 0;
-out_free_reserved_range:
- put_iova_domain(&reserved_iova_list);
out_free_dmar:
intel_iommu_free_dmars();
up_write(&dmar_global_lock);
return 0;
}
-static void intel_init_iova_domain(struct dmar_domain *dmar_domain)
-{
- init_iova_domain(&dmar_domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
- copy_reserved_iova(&reserved_iova_list, &dmar_domain->iovad);
-
- if (!intel_iommu_strict &&
- init_iova_flush_queue(&dmar_domain->iovad,
- iommu_flush_iova, iova_entry_free))
- pr_info("iova flush queue initialization failed\n");
-}
-
static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
{
struct dmar_domain *dmar_domain;
return NULL;
}
- if (type == IOMMU_DOMAIN_DMA)
- intel_init_iova_domain(dmar_domain);
-
- domain_update_iommu_cap(dmar_domain);
+ if (type == IOMMU_DOMAIN_DMA &&
+ iommu_get_dma_cookie(&dmar_domain->domain))
+ return NULL;
domain = &dmar_domain->domain;
domain->geometry.aperture_start = 0;
return -ENODEV;
if (domain->default_pasid <= 0) {
- int pasid;
+ u32 pasid;
/* No private data needed for the default pasid */
pasid = ioasid_alloc(NULL, PASID_MIN,
aux_domain_remove_dev(to_dmar_domain(domain), dev);
}
+#ifdef CONFIG_INTEL_IOMMU_SVM
/*
* 2D array for converting and sanitizing IOMMU generic TLB granularity to
* VT-d granularity. Invalidation is typically included in the unmap operation
return order_base_2(nr_pages);
}
-#ifdef CONFIG_INTEL_IOMMU_SVM
static int
intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
struct iommu_cache_invalidate_info *inv_info)
int ret = 0;
u64 size = 0;
- if (!inv_info || !dmar_domain ||
- inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+ if (!inv_info || !dmar_domain)
return -EINVAL;
if (!dev || !dev_is_pci(dev))
/* Size is only valid in address selective invalidation */
if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
- size = to_vtd_size(inv_info->addr_info.granule_size,
- inv_info->addr_info.nb_granules);
+ size = to_vtd_size(inv_info->granu.addr_info.granule_size,
+ inv_info->granu.addr_info.nb_granules);
for_each_set_bit(cache_type,
(unsigned long *)&inv_info->cache,
* granularity.
*/
if (inv_info->granularity == IOMMU_INV_GRANU_PASID &&
- (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
- pasid = inv_info->pasid_info.pasid;
+ (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
+ pasid = inv_info->granu.pasid_info.pasid;
else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
- (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
- pasid = inv_info->addr_info.pasid;
+ (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
+ pasid = inv_info->granu.addr_info.pasid;
switch (BIT(cache_type)) {
case IOMMU_CACHE_INV_TYPE_IOTLB:
/* HW will ignore LSB bits based on address mask */
if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
size &&
- (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
+ (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n",
- inv_info->addr_info.addr, size);
+ inv_info->granu.addr_info.addr, size);
}
/*
* We use npages = -1 to indicate that.
*/
qi_flush_piotlb(iommu, did, pasid,
- mm_to_dma_pfn(inv_info->addr_info.addr),
+ mm_to_dma_pfn(inv_info->granu.addr_info.addr),
(granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size,
- inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
+ inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
if (!info->ats_enabled)
break;
size = 64 - VTD_PAGE_SHIFT;
addr = 0;
} else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) {
- addr = inv_info->addr_info.addr;
+ addr = inv_info->granu.addr_info.addr;
}
if (info->ats_enabled)
struct iommu_iotlb_gather *gather)
{
struct dmar_domain *dmar_domain = to_dmar_domain(domain);
- struct page *freelist = NULL;
unsigned long start_pfn, last_pfn;
- unsigned int npages;
- int iommu_id, level = 0;
+ int level = 0;
/* Cope with horrid API which requires us to unmap more than the
size argument if it happens to be a large-page mapping. */
start_pfn = iova >> VTD_PAGE_SHIFT;
last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT;
- freelist = domain_unmap(dmar_domain, start_pfn, last_pfn);
-
- npages = last_pfn - start_pfn + 1;
-
- for_each_domain_iommu(iommu_id, dmar_domain)
- iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
- start_pfn, npages, !freelist, 0);
-
- dma_free_pagelist(freelist);
+ gather->freelist = domain_unmap(dmar_domain, start_pfn,
+ last_pfn, gather->freelist);
if (dmar_domain->max_addr == iova + size)
dmar_domain->max_addr = iova;
+ iommu_iotlb_gather_add_page(domain, gather, iova, size);
+
return size;
}
+static void intel_iommu_tlb_sync(struct iommu_domain *domain,
+ struct iommu_iotlb_gather *gather)
+{
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+ unsigned long iova_pfn = IOVA_PFN(gather->start);
+ size_t size = gather->end - gather->start;
+ unsigned long start_pfn, last_pfn;
+ unsigned long nrpages;
+ int iommu_id;
+
+ nrpages = aligned_nrpages(gather->start, size);
+ start_pfn = mm_to_dma_pfn(iova_pfn);
+ last_pfn = start_pfn + nrpages - 1;
+
+ for_each_domain_iommu(iommu_id, dmar_domain)
+ iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain,
+ start_pfn, nrpages, !gather->freelist, 0);
+
+ dma_free_pagelist(gather->freelist);
+}
+
static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
dma_addr_t iova)
{
static void intel_iommu_probe_finalize(struct device *dev)
{
- struct iommu_domain *domain;
+ dma_addr_t base = IOVA_START_PFN << VTD_PAGE_SHIFT;
+ struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
- domain = iommu_get_domain_for_dev(dev);
- if (device_needs_bounce(dev))
- set_dma_ops(dev, &bounce_dma_ops);
- else if (domain && domain->type == IOMMU_DOMAIN_DMA)
- set_dma_ops(dev, &intel_dma_ops);
+ if (domain && domain->type == IOMMU_DOMAIN_DMA)
+ iommu_setup_dma_ops(dev, base,
+ __DOMAIN_MAX_ADDR(dmar_domain->gaw) - base);
else
set_dma_ops(dev, NULL);
}
return ret;
}
-static void intel_iommu_apply_resv_region(struct device *dev,
- struct iommu_domain *domain,
- struct iommu_resv_region *region)
-{
- struct dmar_domain *dmar_domain = to_dmar_domain(domain);
- unsigned long start, end;
-
- start = IOVA_PFN(region->start);
- end = IOVA_PFN(region->start + region->length - 1);
-
- 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 ret;
}
+static int
+intel_iommu_domain_get_attr(struct iommu_domain *domain,
+ enum iommu_attr attr, void *data)
+{
+ switch (domain->type) {
+ case IOMMU_DOMAIN_UNMANAGED:
+ return -ENODEV;
+ case IOMMU_DOMAIN_DMA:
+ switch (attr) {
+ case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+ *(int *)data = !intel_iommu_strict;
+ return 0;
+ default:
+ return -ENODEV;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+}
+
/*
* Check that the device does not live on an external facing PCI port that is
* marked as untrusted. Such devices should not be able to apply quirks and
.capable = intel_iommu_capable,
.domain_alloc = intel_iommu_domain_alloc,
.domain_free = intel_iommu_domain_free,
+ .domain_get_attr = intel_iommu_domain_get_attr,
.domain_set_attr = intel_iommu_domain_set_attr,
.attach_dev = intel_iommu_attach_device,
.detach_dev = intel_iommu_detach_device,
.aux_get_pasid = intel_iommu_aux_get_pasid,
.map = intel_iommu_map,
.unmap = intel_iommu_unmap,
+ .flush_iotlb_all = intel_flush_iotlb_all,
+ .iotlb_sync = intel_iommu_tlb_sync,
.iova_to_phys = intel_iommu_iova_to_phys,
.probe_device = intel_iommu_probe_device,
.probe_finalize = intel_iommu_probe_finalize,
.release_device = intel_iommu_release_device,
.get_resv_regions = intel_iommu_get_resv_regions,
.put_resv_regions = generic_iommu_put_resv_regions,
- .apply_resv_region = intel_iommu_apply_resv_region,
.device_group = intel_iommu_device_group,
.dev_has_feat = intel_iommu_dev_has_feat,
.dev_feat_enabled = intel_iommu_dev_feat_enabled,