summaryrefslogtreecommitdiffstats
path: root/drivers/iommu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu')
-rw-r--r--drivers/iommu/amd/iommu.c5
-rw-r--r--drivers/iommu/dma-iommu.c18
-rw-r--r--drivers/iommu/intel/iommu.c38
-rw-r--r--drivers/iommu/intel/iommu.h2
-rw-r--r--drivers/iommu/intel/irq_remapping.c3
-rw-r--r--drivers/iommu/intel/pasid.c2
-rw-r--r--drivers/iommu/iommu.c77
-rw-r--r--drivers/iommu/iommufd/Kconfig2
-rw-r--r--drivers/iommu/iommufd/device.c8
-rw-r--r--drivers/iommu/iommufd/iommufd_private.h2
-rw-r--r--drivers/iommu/iommufd/main.c3
-rw-r--r--drivers/iommu/iommufd/pages.c6
-rw-r--r--drivers/iommu/iommufd/vfio_compat.c107
-rw-r--r--drivers/iommu/s390-iommu.c17
14 files changed, 191 insertions, 99 deletions
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index cbeaab55c0db..321d50e9df5b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2271,8 +2271,6 @@ static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap)
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return true;
- case IOMMU_CAP_INTR_REMAP:
- return (irq_remapping_enabled == 1);
case IOMMU_CAP_NOEXEC:
return false;
case IOMMU_CAP_PRE_BOOT_PROTECTION:
@@ -3671,7 +3669,8 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
}
irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_AMDVI);
- iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
+ iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
+ IRQ_DOMAIN_FLAG_ISOLATED_MSI;
if (amd_iommu_np_cache)
iommu->ir_domain->msi_parent_ops = &virt_amdvi_msi_parent_ops;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f798c44e0903..c99e4bc55d8c 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -713,7 +713,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
if (!iova)
return DMA_MAPPING_ERROR;
- if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
+ if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) {
iommu_dma_free_iova(cookie, iova, size, NULL);
return DMA_MAPPING_ERROR;
}
@@ -822,7 +822,14 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
if (!iova)
goto out_free_pages;
- if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, GFP_KERNEL))
+ /*
+ * Remove the zone/policy flags from the GFP - these are applied to the
+ * __iommu_dma_alloc_pages() but are not used for the supporting
+ * internal allocations that follow.
+ */
+ gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM | __GFP_COMP);
+
+ if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, gfp))
goto out_free_iova;
if (!(ioprot & IOMMU_CACHE)) {
@@ -833,7 +840,8 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
arch_dma_prep_coherent(sg_page(sg), sg->length);
}
- ret = iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot);
+ ret = iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, ioprot,
+ gfp);
if (ret < 0 || ret < size)
goto out_free_sg;
@@ -1281,7 +1289,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
* We'll leave any physical concatenation to the IOMMU driver's
* implementation - it knows better than we do.
*/
- ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot);
+ ret = iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
if (ret < 0 || ret < iova_len)
goto out_free_iova;
@@ -1615,7 +1623,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
if (!iova)
goto out_free_page;
- if (iommu_map(domain, iova, msi_addr, size, prot))
+ if (iommu_map(domain, iova, msi_addr, size, prot, GFP_KERNEL))
goto out_free_iova;
INIT_LIST_HEAD(&msi_page->list);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 59df7e42fd53..6fd223cf639f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -362,12 +362,12 @@ static int __init intel_iommu_setup(char *str)
}
__setup("intel_iommu=", intel_iommu_setup);
-void *alloc_pgtable_page(int node)
+void *alloc_pgtable_page(int node, gfp_t gfp)
{
struct page *page;
void *vaddr = NULL;
- page = alloc_pages_node(node, GFP_ATOMIC | __GFP_ZERO, 0);
+ page = alloc_pages_node(node, gfp | __GFP_ZERO, 0);
if (page)
vaddr = page_address(page);
return vaddr;
@@ -612,7 +612,7 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
if (!alloc)
return NULL;
- context = alloc_pgtable_page(iommu->node);
+ context = alloc_pgtable_page(iommu->node, GFP_ATOMIC);
if (!context)
return NULL;
@@ -908,7 +908,8 @@ pgtable_walk:
#endif
static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
- unsigned long pfn, int *target_level)
+ unsigned long pfn, int *target_level,
+ gfp_t gfp)
{
struct dma_pte *parent, *pte;
int level = agaw_to_level(domain->agaw);
@@ -935,7 +936,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
if (!dma_pte_present(pte)) {
uint64_t pteval;
- tmp_page = alloc_pgtable_page(domain->nid);
+ tmp_page = alloc_pgtable_page(domain->nid, gfp);
if (!tmp_page)
return NULL;
@@ -1186,7 +1187,7 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
struct root_entry *root;
- root = (struct root_entry *)alloc_pgtable_page(iommu->node);
+ root = (struct root_entry *)alloc_pgtable_page(iommu->node, GFP_ATOMIC);
if (!root) {
pr_err("Allocating root entry for %s failed\n",
iommu->name);
@@ -2150,7 +2151,8 @@ static void switch_to_super_page(struct dmar_domain *domain,
while (start_pfn <= end_pfn) {
if (!pte)
- pte = pfn_to_dma_pte(domain, start_pfn, &level);
+ pte = pfn_to_dma_pte(domain, start_pfn, &level,
+ GFP_ATOMIC);
if (dma_pte_present(pte)) {
dma_pte_free_pagetable(domain, start_pfn,
@@ -2172,7 +2174,8 @@ static void switch_to_super_page(struct dmar_domain *domain,
static int
__domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
- unsigned long phys_pfn, unsigned long nr_pages, int prot)
+ unsigned long phys_pfn, unsigned long nr_pages, int prot,
+ gfp_t gfp)
{
struct dma_pte *first_pte = NULL, *pte = NULL;
unsigned int largepage_lvl = 0;
@@ -2202,7 +2205,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
largepage_lvl = hardware_largepage_caps(domain, iov_pfn,
phys_pfn, nr_pages);
- pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl);
+ pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl,
+ gfp);
if (!pte)
return -ENOMEM;
first_pte = pte;
@@ -2368,7 +2372,7 @@ static int iommu_domain_identity_map(struct dmar_domain *domain,
return __domain_mapping(domain, first_vpfn,
first_vpfn, last_vpfn - first_vpfn + 1,
- DMA_PTE_READ|DMA_PTE_WRITE);
+ DMA_PTE_READ|DMA_PTE_WRITE, GFP_KERNEL);
}
static int md_domain_init(struct dmar_domain *domain, int guest_width);
@@ -2676,7 +2680,7 @@ static int copy_context_table(struct intel_iommu *iommu,
if (!old_ce)
goto out;
- new_ce = alloc_pgtable_page(iommu->node);
+ new_ce = alloc_pgtable_page(iommu->node, GFP_KERNEL);
if (!new_ce)
goto out_unmap;
@@ -4136,7 +4140,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
domain->max_addr = 0;
/* always allocate the top pgd */
- domain->pgd = alloc_pgtable_page(domain->nid);
+ domain->pgd = alloc_pgtable_page(domain->nid, GFP_ATOMIC);
if (!domain->pgd)
return -ENOMEM;
domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
@@ -4298,7 +4302,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
the low bits of hpa would take us onto the next page */
size = aligned_nrpages(hpa, size);
return __domain_mapping(dmar_domain, iova >> VTD_PAGE_SHIFT,
- hpa >> VTD_PAGE_SHIFT, size, prot);
+ hpa >> VTD_PAGE_SHIFT, size, prot, gfp);
}
static int intel_iommu_map_pages(struct iommu_domain *domain,
@@ -4333,7 +4337,8 @@ 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));
+ BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level,
+ GFP_ATOMIC));
if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
size = VTD_PAGE_SIZE << level_to_offset_bits(level);
@@ -4392,7 +4397,8 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
int level = 0;
u64 phys = 0;
- pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
+ pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level,
+ GFP_ATOMIC);
if (pte && dma_pte_present(pte))
phys = dma_pte_addr(pte) +
(iova & (BIT_MASK(level_to_offset_bits(level) +
@@ -4464,8 +4470,6 @@ static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap)
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return true;
- case IOMMU_CAP_INTR_REMAP:
- return irq_remapping_enabled == 1;
case IOMMU_CAP_PRE_BOOT_PROTECTION:
return dmar_platform_optin();
case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 06e61e474856..ca9a035e0110 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -737,7 +737,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
extern int dmar_ir_support(void);
-void *alloc_pgtable_page(int node);
+void *alloc_pgtable_page(int node, gfp_t gfp);
void free_pgtable_page(void *vaddr);
void iommu_flush_write_buffer(struct intel_iommu *iommu);
struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index f58f5f57af78..6d01fa078c36 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -573,7 +573,8 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
}
irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_DMAR);
- iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
+ iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
+ IRQ_DOMAIN_FLAG_ISOLATED_MSI;
if (cap_caching_mode(iommu->cap))
iommu->ir_domain->msi_parent_ops = &virt_dmar_msi_parent_ops;
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index fb3c7020028d..c5bf74e9372d 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -200,7 +200,7 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
retry:
entries = get_pasid_table_from_pde(&dir[dir_index]);
if (!entries) {
- entries = alloc_pgtable_page(info->iommu->node);
+ entries = alloc_pgtable_page(info->iommu->node, GFP_ATOMIC);
if (!entries)
return NULL;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 5f6a85aea501..501e8bcf1aaa 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -30,6 +30,7 @@
#include <linux/cc_platform.h>
#include <trace/events/iommu.h>
#include <linux/sched/mm.h>
+#include <linux/msi.h>
#include "dma-iommu.h"
@@ -930,7 +931,7 @@ map_end:
if (map_size) {
ret = iommu_map(domain, addr - map_size,
addr - map_size, map_size,
- entry->prot);
+ entry->prot, GFP_KERNEL);
if (ret)
goto out;
map_size = 0;
@@ -1898,6 +1899,29 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
EXPORT_SYMBOL_GPL(device_iommu_capable);
/**
+ * iommu_group_has_isolated_msi() - Compute msi_device_has_isolated_msi()
+ * for a group
+ * @group: Group to query
+ *
+ * IOMMU groups should not have differing values of
+ * msi_device_has_isolated_msi() for devices in a group. However nothing
+ * directly prevents this, so ensure mistakes don't result in isolation failures
+ * by checking that all the devices are the same.
+ */
+bool iommu_group_has_isolated_msi(struct iommu_group *group)
+{
+ struct group_device *group_dev;
+ bool ret = true;
+
+ mutex_lock(&group->mutex);
+ list_for_each_entry(group_dev, &group->devices, list)
+ ret &= msi_device_has_isolated_msi(group_dev->dev);
+ mutex_unlock(&group->mutex);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_has_isolated_msi);
+
+/**
* iommu_set_fault_handler() - set a fault handler for an iommu domain
* @domain: iommu domain
* @handler: fault handler
@@ -2360,34 +2384,27 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
return ret;
}
-static int _iommu_map(struct iommu_domain *domain, unsigned long iova,
- phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+ phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
const struct iommu_domain_ops *ops = domain->ops;
int ret;
+ might_sleep_if(gfpflags_allow_blocking(gfp));
+
+ /* Discourage passing strange GFP flags */
+ if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
+ __GFP_HIGHMEM)))
+ return -EINVAL;
+
ret = __iommu_map(domain, iova, paddr, size, prot, gfp);
if (ret == 0 && ops->iotlb_sync_map)
ops->iotlb_sync_map(domain, iova, size);
return ret;
}
-
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
- phys_addr_t paddr, size_t size, int prot)
-{
- might_sleep();
- return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
-}
EXPORT_SYMBOL_GPL(iommu_map);
-int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
- phys_addr_t paddr, size_t size, int prot)
-{
- return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
-}
-EXPORT_SYMBOL_GPL(iommu_map_atomic);
-
static size_t __iommu_unmap_pages(struct iommu_domain *domain,
unsigned long iova, size_t size,
struct iommu_iotlb_gather *iotlb_gather)
@@ -2477,9 +2494,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
}
EXPORT_SYMBOL_GPL(iommu_unmap_fast);
-static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
- struct scatterlist *sg, unsigned int nents, int prot,
- gfp_t gfp)
+ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+ struct scatterlist *sg, unsigned int nents, int prot,
+ gfp_t gfp)
{
const struct iommu_domain_ops *ops = domain->ops;
size_t len = 0, mapped = 0;
@@ -2487,6 +2504,13 @@ static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
unsigned int i = 0;
int ret;
+ might_sleep_if(gfpflags_allow_blocking(gfp));
+
+ /* Discourage passing strange GFP flags */
+ if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 |
+ __GFP_HIGHMEM)))
+ return -EINVAL;
+
while (i <= nents) {
phys_addr_t s_phys = sg_phys(sg);
@@ -2526,21 +2550,8 @@ out_err:
return ret;
}
-
-ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
- struct scatterlist *sg, unsigned int nents, int prot)
-{
- might_sleep();
- return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
-}
EXPORT_SYMBOL_GPL(iommu_map_sg);
-ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
- struct scatterlist *sg, unsigned int nents, int prot)
-{
- return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
-}
-
/**
* report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
* @domain: the iommu domain where the fault has happened
diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
index 8306616b6d81..ada693ea51a7 100644
--- a/drivers/iommu/iommufd/Kconfig
+++ b/drivers/iommu/iommufd/Kconfig
@@ -23,7 +23,7 @@ config IOMMUFD_VFIO_CONTAINER
removed.
IOMMUFD VFIO container emulation is known to lack certain features
- of the native VFIO container, such as no-IOMMU support, peer-to-peer
+ of the native VFIO container, such as peer-to-peer
DMA mapping, PPC IOMMU support, as well as other potentially
undiscovered gaps. This option is currently intended for the
purpose of testing IOMMUFD with unmodified userspace supporting VFIO
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index d81f93a321af..a0c66f47a65a 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -4,7 +4,6 @@
#include <linux/iommufd.h>
#include <linux/slab.h>
#include <linux/iommu.h>
-#include <linux/irqdomain.h>
#include "io_pagetable.h"
#include "iommufd_private.h"
@@ -169,8 +168,7 @@ static int iommufd_device_setup_msi(struct iommufd_device *idev,
* operation from the device (eg a simple DMA) cannot trigger an
* interrupt outside this iommufd context.
*/
- if (!device_iommu_capable(idev->dev, IOMMU_CAP_INTR_REMAP) &&
- !irq_domain_check_msi_remap()) {
+ if (!iommu_group_has_isolated_msi(idev->group)) {
if (!allow_unsafe_interrupts)
return -EPERM;
@@ -346,10 +344,6 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
rc = iommufd_device_do_attach(idev, hwpt);
if (rc)
goto out_put_pt_obj;
-
- mutex_lock(&hwpt->ioas->mutex);
- list_add_tail(&hwpt->hwpt_item, &hwpt->ioas->hwpt_list);
- mutex_unlock(&hwpt->ioas->mutex);
break;
}
case IOMMUFD_OBJ_IOAS: {
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 222e86591f8a..9d7f71510ca1 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -18,6 +18,8 @@ struct iommufd_ctx {
struct xarray objects;
u8 account_mode;
+ /* Compatibility with VFIO no iommu */
+ u8 no_iommu_mode;
struct iommufd_ioas *vfio_ioas;
};
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 083e6fcbe10a..3fbe636c3d8a 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -252,9 +252,12 @@ union ucmd_buffer {
struct iommu_destroy destroy;
struct iommu_ioas_alloc alloc;
struct iommu_ioas_allow_iovas allow_iovas;
+ struct iommu_ioas_copy ioas_copy;
struct iommu_ioas_iova_ranges iova_ranges;
struct iommu_ioas_map map;
struct iommu_ioas_unmap unmap;
+ struct iommu_option option;
+ struct iommu_vfio_ioas vfio_ioas;
#ifdef CONFIG_IOMMUFD_TEST
struct iommu_test_cmd test;
#endif
diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index 1e1d3509efae..f8d92c9bb65b 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -456,7 +456,8 @@ static int batch_iommu_map_small(struct iommu_domain *domain,
size % PAGE_SIZE);
while (size) {
- rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot);
+ rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot,
+ GFP_KERNEL_ACCOUNT);
if (rc)
goto err_unmap;
iova += PAGE_SIZE;
@@ -500,7 +501,8 @@ static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain,
else
rc = iommu_map(domain, iova,
PFN_PHYS(batch->pfns[cur]) + page_offset,
- next_iova - iova, area->iommu_prot);
+ next_iova - iova, area->iommu_prot,
+ GFP_KERNEL_ACCOUNT);
if (rc)
goto err_unmap;
iova = next_iova;
diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c
index 3ceca0e8311c..514494a0025b 100644
--- a/drivers/iommu/iommufd/vfio_compat.c
+++ b/drivers/iommu/iommufd/vfio_compat.c
@@ -26,39 +26,84 @@ out_unlock:
}
/**
- * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use
+ * iommufd_vfio_compat_ioas_get_id - Ensure a compat IOAS exists
+ * @ictx: Context to operate on
+ * @out_ioas_id: The IOAS ID of the compatibility IOAS
+ *
+ * Return the ID of the current compatibility IOAS. The ID can be passed into
+ * other functions that take an ioas_id.
+ */
+int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
+{
+ struct iommufd_ioas *ioas;
+
+ ioas = get_compat_ioas(ictx);
+ if (IS_ERR(ioas))
+ return PTR_ERR(ioas);
+ *out_ioas_id = ioas->obj.id;
+ iommufd_put_object(&ioas->obj);
+ return 0;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO);
+
+/**
+ * iommufd_vfio_compat_set_no_iommu - Called when a no-iommu device is attached
+ * @ictx: Context to operate on
+ *
+ * This allows selecting the VFIO_NOIOMMU_IOMMU and blocks normal types.
+ */
+int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
+{
+ int ret;
+
+ xa_lock(&ictx->objects);
+ if (!ictx->vfio_ioas) {
+ ictx->no_iommu_mode = 1;
+ ret = 0;
+ } else {
+ ret = -EINVAL;
+ }
+ xa_unlock(&ictx->objects);
+ return ret;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_set_no_iommu, IOMMUFD_VFIO);
+
+/**
+ * iommufd_vfio_compat_ioas_create - Ensure the compat IOAS is created
* @ictx: Context to operate on
- * @out_ioas_id: The ioas_id the caller should use
*
* The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate
* on since they do not have an IOAS ID input in their ABI. Only attaching a
- * group should cause a default creation of the internal ioas, this returns the
- * existing ioas if it has already been assigned somehow.
+ * group should cause a default creation of the internal ioas, this does nothing
+ * if an existing ioas has already been assigned somehow.
*/
-int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
+int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx)
{
struct iommufd_ioas *ioas = NULL;
- struct iommufd_ioas *out_ioas;
+ int ret;
ioas = iommufd_ioas_alloc(ictx);
if (IS_ERR(ioas))
return PTR_ERR(ioas);
xa_lock(&ictx->objects);
- if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj))
- out_ioas = ictx->vfio_ioas;
- else {
- out_ioas = ioas;
- ictx->vfio_ioas = ioas;
+ /*
+ * VFIO won't allow attaching a container to both iommu and no iommu
+ * operation
+ */
+ if (ictx->no_iommu_mode) {
+ ret = -EINVAL;
+ goto out_abort;
}
- xa_unlock(&ictx->objects);
- *out_ioas_id = out_ioas->obj.id;
- if (out_ioas != ioas) {
- iommufd_put_object(&out_ioas->obj);
- iommufd_object_abort(ictx, &ioas->obj);
- return 0;
+ if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) {
+ ret = 0;
+ iommufd_put_object(&ictx->vfio_ioas->obj);
+ goto out_abort;
}
+ ictx->vfio_ioas = ioas;
+ xa_unlock(&ictx->objects);
+
/*
* An automatically created compat IOAS is treated as a userspace
* created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET,
@@ -67,8 +112,13 @@ int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
*/
iommufd_object_finalize(ictx, &ioas->obj);
return 0;
+
+out_abort:
+ xa_unlock(&ictx->objects);
+ iommufd_object_abort(ictx, &ioas->obj);
+ return ret;
}
-EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO);
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_create, IOMMUFD_VFIO);
int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
{
@@ -235,6 +285,9 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx,
case VFIO_UNMAP_ALL:
return 1;
+ case VFIO_NOIOMMU_IOMMU:
+ return IS_ENABLED(CONFIG_VFIO_NOIOMMU);
+
case VFIO_DMA_CC_IOMMU:
return iommufd_vfio_cc_iommu(ictx);
@@ -261,10 +314,24 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx,
static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type)
{
+ bool no_iommu_mode = READ_ONCE(ictx->no_iommu_mode);
struct iommufd_ioas *ioas = NULL;
int rc = 0;
- if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU)
+ /*
+ * Emulation for NOIOMMU is imperfect in that VFIO blocks almost all
+ * other ioctls. We let them keep working but they mostly fail since no
+ * IOAS should exist.
+ */
+ if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && type == VFIO_NOIOMMU_IOMMU &&
+ no_iommu_mode) {
+ if (!capable(CAP_SYS_RAWIO))
+ return -EPERM;
+ return 0;
+ }
+
+ if ((type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) ||
+ no_iommu_mode)
return -EINVAL;
/* VFIO fails the set_iommu if there is no group */
@@ -381,7 +448,7 @@ static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx,
};
size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
struct vfio_info_cap_header __user *last_cap = NULL;
- struct vfio_iommu_type1_info info;
+ struct vfio_iommu_type1_info info = {};
struct iommufd_ioas *ioas;
size_t total_cap_size;
int rc;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index ed33c6cce083..c489714ddc4d 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -34,8 +34,6 @@ static bool s390_iommu_capable(struct device *dev, enum iommu_cap cap)
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
return true;
- case IOMMU_CAP_INTR_REMAP:
- return true;
default:
return false;
}
@@ -52,7 +50,7 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type)
if (!s390_domain)
return NULL;
- s390_domain->dma_table = dma_alloc_cpu_table();
+ s390_domain->dma_table = dma_alloc_cpu_table(GFP_KERNEL);
if (!s390_domain->dma_table) {
kfree(s390_domain);
return NULL;
@@ -260,7 +258,8 @@ static void s390_iommu_iotlb_sync_map(struct iommu_domain *domain,
static int s390_iommu_validate_trans(struct s390_domain *s390_domain,
phys_addr_t pa, dma_addr_t dma_addr,
- unsigned long nr_pages, int flags)
+ unsigned long nr_pages, int flags,
+ gfp_t gfp)
{
phys_addr_t page_addr = pa & PAGE_MASK;
unsigned long *entry;
@@ -268,7 +267,8 @@ static int s390_iommu_validate_trans(struct s390_domain *s390_domain,
int rc;
for (i = 0; i < nr_pages; i++) {
- entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr);
+ entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr,
+ gfp);
if (unlikely(!entry)) {
rc = -ENOMEM;
goto undo_cpu_trans;
@@ -284,7 +284,7 @@ undo_cpu_trans:
while (i-- > 0) {
dma_addr -= PAGE_SIZE;
entry = dma_walk_cpu_trans(s390_domain->dma_table,
- dma_addr);
+ dma_addr, gfp);
if (!entry)
break;
dma_update_cpu_trans(entry, 0, ZPCI_PTE_INVALID);
@@ -301,7 +301,8 @@ static int s390_iommu_invalidate_trans(struct s390_domain *s390_domain,
int rc = 0;
for (i = 0; i < nr_pages; i++) {
- entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr);
+ entry = dma_walk_cpu_trans(s390_domain->dma_table, dma_addr,
+ GFP_ATOMIC);
if (unlikely(!entry)) {
rc = -EINVAL;
break;
@@ -339,7 +340,7 @@ static int s390_iommu_map_pages(struct iommu_domain *domain,
flags |= ZPCI_TABLE_PROTECTED;
rc = s390_iommu_validate_trans(s390_domain, paddr, iova,
- pgcount, flags);
+ pgcount, flags, gfp);
if (!rc)
*mapped = size;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-04 22:56:53 +0100