summaryrefslogtreecommitdiffstats
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/Kconfig2
-rw-r--r--drivers/vfio/container.c7
-rw-r--r--drivers/vfio/group.c7
-rw-r--r--drivers/vfio/iommufd.c19
-rw-r--r--drivers/vfio/pci/vfio_pci_core.c2
-rw-r--r--drivers/vfio/vfio.h8
-rw-r--r--drivers/vfio/vfio_iommu_type1.c54
-rw-r--r--drivers/vfio/vfio_main.c7
8 files changed, 66 insertions, 40 deletions
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index a8f544629467..89e06c981e43 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -32,6 +32,7 @@ config VFIO_IOMMU_SPAPR_TCE
tristate
depends on SPAPR_TCE_IOMMU
default VFIO
+endif
config VFIO_NOIOMMU
bool "VFIO No-IOMMU support"
@@ -46,7 +47,6 @@ config VFIO_NOIOMMU
this mode since there is no IOMMU to provide DMA translation.
If you don't know what to do here, say N.
-endif
config VFIO_VIRQFD
bool
diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c
index 95fd51817f2b..d53d08f16973 100644
--- a/drivers/vfio/container.c
+++ b/drivers/vfio/container.c
@@ -29,13 +29,6 @@ static struct vfio {
struct mutex iommu_drivers_lock;
} vfio;
-#ifdef CONFIG_VFIO_NOIOMMU
-bool vfio_noiommu __read_mostly;
-module_param_named(enable_unsafe_noiommu_mode,
- vfio_noiommu, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)");
-#endif
-
static void *vfio_noiommu_open(unsigned long arg)
{
if (arg != VFIO_NOIOMMU_IOMMU)
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index 160deff6649b..27d5ba7cf9dc 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -133,9 +133,12 @@ static int vfio_group_ioctl_set_container(struct vfio_group *group,
iommufd = iommufd_ctx_from_file(f.file);
if (!IS_ERR(iommufd)) {
- u32 ioas_id;
+ if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) &&
+ group->type == VFIO_NO_IOMMU)
+ ret = iommufd_vfio_compat_set_no_iommu(iommufd);
+ else
+ ret = iommufd_vfio_compat_ioas_create(iommufd);
- ret = iommufd_vfio_compat_ioas_id(iommufd, &ioas_id);
if (ret) {
iommufd_ctx_put(iommufd);
goto out_unlock;
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
index 4f82a6fa7c6c..db4efbd56042 100644
--- a/drivers/vfio/iommufd.c
+++ b/drivers/vfio/iommufd.c
@@ -18,6 +18,20 @@ int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx)
lockdep_assert_held(&vdev->dev_set->lock);
+ if (vfio_device_is_noiommu(vdev)) {
+ if (!capable(CAP_SYS_RAWIO))
+ return -EPERM;
+
+ /*
+ * Require no compat ioas to be assigned to proceed. The basic
+ * statement is that the user cannot have done something that
+ * implies they expected translation to exist
+ */
+ if (!iommufd_vfio_compat_ioas_get_id(ictx, &ioas_id))
+ return -EPERM;
+ return 0;
+ }
+
/*
* If the driver doesn't provide this op then it means the device does
* not do DMA at all. So nothing to do.
@@ -29,7 +43,7 @@ int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx)
if (ret)
return ret;
- ret = iommufd_vfio_compat_ioas_id(ictx, &ioas_id);
+ ret = iommufd_vfio_compat_ioas_get_id(ictx, &ioas_id);
if (ret)
goto err_unbind;
ret = vdev->ops->attach_ioas(vdev, &ioas_id);
@@ -52,6 +66,9 @@ void vfio_iommufd_unbind(struct vfio_device *vdev)
{
lockdep_assert_held(&vdev->dev_set->lock);
+ if (vfio_device_is_noiommu(vdev))
+ return;
+
if (vdev->ops->unbind_iommufd)
vdev->ops->unbind_iommufd(vdev);
}
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index a6492a25ff6a..a5ab416cf476 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1800,7 +1800,7 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma
* See remap_pfn_range(), called from vfio_pci_fault() but we can't
* change vm_flags within the fault handler. Set them now.
*/
- vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+ vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
vma->vm_ops = &vfio_pci_mmap_ops;
return 0;
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index e9721d8424bc..7b19c621e0e6 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -10,10 +10,10 @@
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/module.h>
+#include <linux/vfio.h>
struct iommufd_ctx;
struct iommu_group;
-struct vfio_device;
struct vfio_container;
void vfio_device_put_registration(struct vfio_device *device);
@@ -88,6 +88,12 @@ bool vfio_device_has_container(struct vfio_device *device);
int __init vfio_group_init(void);
void vfio_group_cleanup(void);
+static inline bool vfio_device_is_noiommu(struct vfio_device *vdev)
+{
+ return IS_ENABLED(CONFIG_VFIO_NOIOMMU) &&
+ vdev->group->type == VFIO_NO_IOMMU;
+}
+
#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
/**
* struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 29616f20c778..493c31de0edb 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -37,7 +37,6 @@
#include <linux/vfio.h>
#include <linux/workqueue.h>
#include <linux/notifier.h>
-#include <linux/irqdomain.h>
#include "vfio.h"
#define DRIVER_VERSION "0.2"
@@ -1428,7 +1427,8 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
list_for_each_entry(d, &iommu->domain_list, next) {
ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
- npage << PAGE_SHIFT, prot | IOMMU_CACHE);
+ npage << PAGE_SHIFT, prot | IOMMU_CACHE,
+ GFP_KERNEL);
if (ret)
goto unwind;
@@ -1741,8 +1741,8 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
size = npage << PAGE_SHIFT;
}
- ret = iommu_map(domain->domain, iova, phys,
- size, dma->prot | IOMMU_CACHE);
+ ret = iommu_map(domain->domain, iova, phys, size,
+ dma->prot | IOMMU_CACHE, GFP_KERNEL);
if (ret) {
if (!dma->iommu_mapped) {
vfio_unpin_pages_remote(dma, iova,
@@ -1820,24 +1820,33 @@ unwind:
* significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when
* hugetlbfs is in use.
*/
-static void vfio_test_domain_fgsp(struct vfio_domain *domain)
+static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *regions)
{
- struct page *pages;
int ret, order = get_order(PAGE_SIZE * 2);
+ struct vfio_iova *region;
+ struct page *pages;
+ dma_addr_t start;
pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!pages)
return;
- ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
- IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
- if (!ret) {
- size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
+ list_for_each_entry(region, regions, list) {
+ start = ALIGN(region->start, PAGE_SIZE * 2);
+ if (start >= region->end || (region->end - start < PAGE_SIZE * 2))
+ continue;
- if (unmapped == PAGE_SIZE)
- iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE);
- else
- domain->fgsp = true;
+ ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
+ IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE, GFP_KERNEL);
+ if (!ret) {
+ size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
+
+ if (unmapped == PAGE_SIZE)
+ iommu_unmap(domain->domain, start + PAGE_SIZE, PAGE_SIZE);
+ else
+ domain->fgsp = true;
+ }
+ break;
}
__free_pages(pages, order);
@@ -2124,12 +2133,6 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
list_splice_tail(iova_copy, iova);
}
-/* Redundantly walks non-present capabilities to simplify caller */
-static int vfio_iommu_device_capable(struct device *dev, void *data)
-{
- return device_iommu_capable(dev, (enum iommu_cap)data);
-}
-
static int vfio_iommu_domain_alloc(struct device *dev, void *data)
{
struct iommu_domain **domain = data;
@@ -2144,7 +2147,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
struct vfio_iommu *iommu = iommu_data;
struct vfio_iommu_group *group;
struct vfio_domain *domain, *d;
- bool resv_msi, msi_remap;
+ bool resv_msi;
phys_addr_t resv_msi_base = 0;
struct iommu_domain_geometry *geo;
LIST_HEAD(iova_copy);
@@ -2247,11 +2250,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
INIT_LIST_HEAD(&domain->group_list);
list_add(&group->next, &domain->group_list);
- msi_remap = irq_domain_check_msi_remap() ||
- iommu_group_for_each_dev(iommu_group, (void *)IOMMU_CAP_INTR_REMAP,
- vfio_iommu_device_capable);
-
- if (!allow_unsafe_interrupts && !msi_remap) {
+ if (!allow_unsafe_interrupts &&
+ !iommu_group_has_isolated_msi(iommu_group)) {
pr_warn("%s: No interrupt remapping support. Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
__func__);
ret = -EPERM;
@@ -2295,7 +2295,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
}
}
- vfio_test_domain_fgsp(domain);
+ vfio_test_domain_fgsp(domain, &iova_copy);
/* replay mappings on new domains */
ret = vfio_iommu_replay(iommu, domain);
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 3a597e799918..43bd6b76e2b6 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -48,6 +48,13 @@ static struct vfio {
struct ida device_ida;
} vfio;
+#ifdef CONFIG_VFIO_NOIOMMU
+bool vfio_noiommu __read_mostly;
+module_param_named(enable_unsafe_noiommu_mode,
+ vfio_noiommu, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)");
+#endif
+
static DEFINE_XARRAY(vfio_device_set_xa);
int vfio_assign_device_set(struct vfio_device *device, void *set_id)
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-15 19:58:50 +0100