summaryrefslogtreecommitdiffstats
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/group.c2
-rw-r--r--drivers/vfio/iommufd.c37
-rw-r--r--drivers/vfio/pci/vfio_pci_config.c7
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c96
-rw-r--r--drivers/vfio/vfio_iommu_type1.c2
-rw-r--r--drivers/vfio/vfio_main.c7
6 files changed, 44 insertions, 107 deletions
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index 27d5ba7cf9dc..fc75c1000d74 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -878,7 +878,7 @@ int __init vfio_group_init(void)
return ret;
/* /dev/vfio/$GROUP */
- vfio.class = class_create(THIS_MODULE, "vfio");
+ vfio.class = class_create("vfio");
if (IS_ERR(vfio.class)) {
ret = PTR_ERR(vfio.class);
goto err_group_class;
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
index db4efbd56042..88b00c501015 100644
--- a/drivers/vfio/iommufd.c
+++ b/drivers/vfio/iommufd.c
@@ -32,13 +32,6 @@ int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx)
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.
- */
- if (!vdev->ops->bind_iommufd)
- return 0;
-
ret = vdev->ops->bind_iommufd(vdev, ictx, &device_id);
if (ret)
return ret;
@@ -119,7 +112,8 @@ EXPORT_SYMBOL_GPL(vfio_iommufd_physical_attach_ioas);
/*
* The emulated standard ops mean that vfio_device is going to use the
* "mdev path" and will call vfio_pin_pages()/vfio_dma_rw(). Drivers using this
- * ops set should call vfio_register_emulated_iommu_dev().
+ * ops set should call vfio_register_emulated_iommu_dev(). Drivers that do
+ * not call vfio_pin_pages()/vfio_dma_rw() have no need to provide dma_unmap.
*/
static void vfio_emulated_unmap(void *data, unsigned long iova,
@@ -127,7 +121,8 @@ static void vfio_emulated_unmap(void *data, unsigned long iova,
{
struct vfio_device *vdev = data;
- vdev->ops->dma_unmap(vdev, iova, length);
+ if (vdev->ops->dma_unmap)
+ vdev->ops->dma_unmap(vdev, iova, length);
}
static const struct iommufd_access_ops vfio_user_ops = {
@@ -138,10 +133,14 @@ static const struct iommufd_access_ops vfio_user_ops = {
int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
struct iommufd_ctx *ictx, u32 *out_device_id)
{
+ struct iommufd_access *user;
+
lockdep_assert_held(&vdev->dev_set->lock);
- vdev->iommufd_ictx = ictx;
- iommufd_ctx_get(ictx);
+ user = iommufd_access_create(ictx, &vfio_user_ops, vdev, out_device_id);
+ if (IS_ERR(user))
+ return PTR_ERR(user);
+ vdev->iommufd_access = user;
return 0;
}
EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_bind);
@@ -152,24 +151,24 @@ void vfio_iommufd_emulated_unbind(struct vfio_device *vdev)
if (vdev->iommufd_access) {
iommufd_access_destroy(vdev->iommufd_access);
+ vdev->iommufd_attached = false;
vdev->iommufd_access = NULL;
}
- iommufd_ctx_put(vdev->iommufd_ictx);
- vdev->iommufd_ictx = NULL;
}
EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_unbind);
int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id)
{
- struct iommufd_access *user;
+ int rc;
lockdep_assert_held(&vdev->dev_set->lock);
- user = iommufd_access_create(vdev->iommufd_ictx, *pt_id, &vfio_user_ops,
- vdev);
- if (IS_ERR(user))
- return PTR_ERR(user);
- vdev->iommufd_access = user;
+ if (vdev->iommufd_attached)
+ return -EBUSY;
+ rc = iommufd_access_attach(vdev->iommufd_access, *pt_id);
+ if (rc)
+ return rc;
+ vdev->iommufd_attached = true;
return 0;
}
EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_attach_ioas);
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 523e0144c86f..948cdd464f4e 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -96,6 +96,7 @@ static const u16 pci_ext_cap_length[PCI_EXT_CAP_ID_MAX + 1] = {
[PCI_EXT_CAP_ID_SECPCI] = 0, /* not yet */
[PCI_EXT_CAP_ID_PMUX] = 0, /* not yet */
[PCI_EXT_CAP_ID_PASID] = 0, /* not yet */
+ [PCI_EXT_CAP_ID_DVSEC] = 0xFF,
};
/*
@@ -1101,6 +1102,7 @@ int __init vfio_pci_init_perm_bits(void)
ret |= init_pci_ext_cap_err_perm(&ecap_perms[PCI_EXT_CAP_ID_ERR]);
ret |= init_pci_ext_cap_pwr_perm(&ecap_perms[PCI_EXT_CAP_ID_PWR]);
ecap_perms[PCI_EXT_CAP_ID_VNDR].writefn = vfio_raw_config_write;
+ ecap_perms[PCI_EXT_CAP_ID_DVSEC].writefn = vfio_raw_config_write;
if (ret)
vfio_pci_uninit_perm_bits();
@@ -1440,6 +1442,11 @@ static int vfio_ext_cap_len(struct vfio_pci_core_device *vdev, u16 ecap, u16 epo
return PCI_TPH_BASE_SIZEOF + (sts * 2) + 2;
}
return PCI_TPH_BASE_SIZEOF;
+ case PCI_EXT_CAP_ID_DVSEC:
+ ret = pci_read_config_dword(pdev, epos + PCI_DVSEC_HEADER1, &dword);
+ if (ret)
+ return pcibios_err_to_errno(ret);
+ return PCI_DVSEC_HEADER1_LEN(dword);
default:
pci_warn(pdev, "%s: unknown length for PCI ecap %#x@%#x\n",
__func__, ecap, epos);
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 60a50ce8701e..a94ec6225d31 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1190,52 +1190,6 @@ static long tce_iommu_ioctl(void *iommu_data,
static void tce_iommu_release_ownership(struct tce_container *container,
struct iommu_table_group *table_group)
{
- int i;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = container->tables[i];
-
- if (!tbl)
- continue;
-
- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
- if (tbl->it_map)
- iommu_release_ownership(tbl);
-
- container->tables[i] = NULL;
- }
-}
-
-static int tce_iommu_take_ownership(struct tce_container *container,
- struct iommu_table_group *table_group)
-{
- int i, j, rc = 0;
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
- struct iommu_table *tbl = table_group->tables[i];
-
- if (!tbl || !tbl->it_map)
- continue;
-
- rc = iommu_take_ownership(tbl);
- if (rc) {
- for (j = 0; j < i; ++j)
- iommu_release_ownership(
- table_group->tables[j]);
-
- return rc;
- }
- }
-
- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
- container->tables[i] = table_group->tables[i];
-
- return 0;
-}
-
-static void tce_iommu_release_ownership_ddw(struct tce_container *container,
- struct iommu_table_group *table_group)
-{
long i;
if (!table_group->ops->unset_window) {
@@ -1246,23 +1200,13 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
if (container->tables[i])
table_group->ops->unset_window(table_group, i);
-
- table_group->ops->release_ownership(table_group);
}
-static long tce_iommu_take_ownership_ddw(struct tce_container *container,
+static long tce_iommu_take_ownership(struct tce_container *container,
struct iommu_table_group *table_group)
{
long i, ret = 0;
- if (!table_group->ops->create_table || !table_group->ops->set_window ||
- !table_group->ops->release_ownership) {
- WARN_ON_ONCE(1);
- return -EFAULT;
- }
-
- table_group->ops->take_ownership(table_group);
-
/* Set all windows to the new group */
for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
struct iommu_table *tbl = container->tables[i];
@@ -1281,8 +1225,6 @@ release_exit:
for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
table_group->ops->unset_window(table_group, i);
- table_group->ops->release_ownership(table_group);
-
return ret;
}
@@ -1307,9 +1249,14 @@ static int tce_iommu_attach_group(void *iommu_data,
goto unlock_exit;
}
- if (tce_groups_attached(container) && (!table_group->ops ||
- !table_group->ops->take_ownership ||
- !table_group->ops->release_ownership)) {
+ /* v2 requires full support of dynamic DMA windows */
+ if (container->v2 && table_group->max_dynamic_windows_supported == 0) {
+ ret = -EINVAL;
+ goto unlock_exit;
+ }
+
+ /* v1 reuses TCE tables and does not share them among PEs */
+ if (!container->v2 && tce_groups_attached(container)) {
ret = -EBUSY;
goto unlock_exit;
}
@@ -1344,29 +1291,15 @@ static int tce_iommu_attach_group(void *iommu_data,
goto unlock_exit;
}
- if (!table_group->ops || !table_group->ops->take_ownership ||
- !table_group->ops->release_ownership) {
- if (container->v2) {
- ret = -EPERM;
- goto free_exit;
- }
- ret = tce_iommu_take_ownership(container, table_group);
- } else {
- if (!container->v2) {
- ret = -EPERM;
- goto free_exit;
- }
- ret = tce_iommu_take_ownership_ddw(container, table_group);
- if (!tce_groups_attached(container) && !container->tables[0])
- container->def_window_pending = true;
- }
+ ret = tce_iommu_take_ownership(container, table_group);
+ if (!tce_groups_attached(container) && !container->tables[0])
+ container->def_window_pending = true;
if (!ret) {
tcegrp->grp = iommu_group;
list_add(&tcegrp->next, &container->group_list);
}
-free_exit:
if (ret && tcegrp)
kfree(tcegrp);
@@ -1405,10 +1338,7 @@ static void tce_iommu_detach_group(void *iommu_data,
table_group = iommu_group_get_iommudata(iommu_group);
BUG_ON(!table_group);
- if (!table_group->ops || !table_group->ops->release_ownership)
- tce_iommu_release_ownership(container, table_group);
- else
- tce_iommu_release_ownership_ddw(container, table_group);
+ tce_iommu_release_ownership(container, table_group);
unlock_exit:
mutex_unlock(&container->lock);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 493c31de0edb..3d4dd9420c30 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -580,7 +580,7 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr,
goto done;
}
- vaddr = untagged_addr(vaddr);
+ vaddr = untagged_addr_remote(mm, vaddr);
retry:
vma = vma_lookup(mm, vaddr);
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 43bd6b76e2b6..f0ca33b2e1df 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -255,8 +255,9 @@ static int __vfio_register_dev(struct vfio_device *device,
{
int ret;
- if (WARN_ON(device->ops->bind_iommufd &&
- (!device->ops->unbind_iommufd ||
+ if (WARN_ON(IS_ENABLED(CONFIG_IOMMUFD) &&
+ (!device->ops->bind_iommufd ||
+ !device->ops->unbind_iommufd ||
!device->ops->attach_ioas)))
return -EINVAL;
@@ -1408,7 +1409,7 @@ static int __init vfio_init(void)
goto err_virqfd;
/* /sys/class/vfio-dev/vfioX */
- vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
+ vfio.device_class = class_create("vfio-dev");
if (IS_ERR(vfio.device_class)) {
ret = PTR_ERR(vfio.device_class);
goto err_dev_class;