Merge remote branch 'origin/master' into next-merge
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index affa347..ffd0632 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1012,6 +1012,7 @@
static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
{
struct pci_dev *pdev = vdev->pdev;
+ u32 dword;
u16 word;
u8 byte;
int ret;
@@ -1025,7 +1026,9 @@
return pcibios_err_to_errno(ret);
if (PCI_X_CMD_VERSION(word)) {
- vdev->extended_caps = true;
+ /* Test for extended capabilities */
+ pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+ vdev->extended_caps = (dword != 0);
return PCI_CAP_PCIX_SIZEOF_V2;
} else
return PCI_CAP_PCIX_SIZEOF_V0;
@@ -1037,9 +1040,11 @@
return byte;
case PCI_CAP_ID_EXP:
- /* length based on version */
- vdev->extended_caps = true;
+ /* Test for extended capabilities */
+ pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &dword);
+ vdev->extended_caps = (dword != 0);
+ /* length based on version */
if ((pcie_caps_reg(pdev) & PCI_EXP_FLAGS_VERS) == 1)
return PCI_CAP_EXP_ENDPOINT_SIZEOF_V1;
else
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 4bc704e..641bc87 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -130,8 +130,8 @@
void (*thread)(struct vfio_pci_device *, void *),
void *data, struct virqfd **pvirqfd, int fd)
{
- struct file *file = NULL;
- struct eventfd_ctx *ctx = NULL;
+ struct fd irqfd;
+ struct eventfd_ctx *ctx;
struct virqfd *virqfd;
int ret = 0;
unsigned int events;
@@ -149,16 +149,16 @@
INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
INIT_WORK(&virqfd->inject, virqfd_inject);
- file = eventfd_fget(fd);
- if (IS_ERR(file)) {
- ret = PTR_ERR(file);
- goto fail;
+ irqfd = fdget(fd);
+ if (!irqfd.file) {
+ ret = -EBADF;
+ goto err_fd;
}
- ctx = eventfd_ctx_fileget(file);
+ ctx = eventfd_ctx_fileget(irqfd.file);
if (IS_ERR(ctx)) {
ret = PTR_ERR(ctx);
- goto fail;
+ goto err_ctx;
}
virqfd->eventfd = ctx;
@@ -174,7 +174,7 @@
if (*pvirqfd) {
spin_unlock_irq(&vdev->irqlock);
ret = -EBUSY;
- goto fail;
+ goto err_busy;
}
*pvirqfd = virqfd;
@@ -187,7 +187,7 @@
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
- events = file->f_op->poll(file, &virqfd->pt);
+ events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
/*
* Check if there was an event already pending on the eventfd
@@ -202,17 +202,14 @@
* Do not drop the file until the irqfd is fully initialized,
* otherwise we might race against the POLLHUP.
*/
- fput(file);
+ fdput(irqfd);
return 0;
-
-fail:
- if (ctx && !IS_ERR(ctx))
- eventfd_ctx_put(ctx);
-
- if (file && !IS_ERR(file))
- fput(file);
-
+err_busy:
+ eventfd_ctx_put(ctx);
+err_ctx:
+ fdput(irqfd);
+err_fd:
kfree(virqfd);
return ret;
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 842f450..1eab4ac 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1109,7 +1109,7 @@
* We can't use anon_inode_getfd() because we need to modify
* the f_mode flags directly to allow more than just ioctls
*/
- ret = get_unused_fd();
+ ret = get_unused_fd_flags(O_CLOEXEC);
if (ret < 0) {
device->ops->release(device->device_data);
break;
@@ -1353,6 +1353,68 @@
};
/**
+ * External user API, exported by symbols to be linked dynamically.
+ *
+ * The protocol includes:
+ * 1. do normal VFIO init operation:
+ * - opening a new container;
+ * - attaching group(s) to it;
+ * - setting an IOMMU driver for a container.
+ * When IOMMU is set for a container, all groups in it are
+ * considered ready to use by an external user.
+ *
+ * 2. User space passes a group fd to an external user.
+ * The external user calls vfio_group_get_external_user()
+ * to verify that:
+ * - the group is initialized;
+ * - IOMMU is set for it.
+ * If both checks passed, vfio_group_get_external_user()
+ * increments the container user counter to prevent
+ * the VFIO group from disposal before KVM exits.
+ *
+ * 3. The external user calls vfio_external_user_iommu_id()
+ * to know an IOMMU ID.
+ *
+ * 4. When the external KVM finishes, it calls
+ * vfio_group_put_external_user() to release the VFIO group.
+ * This call decrements the container user counter.
+ */
+struct vfio_group *vfio_group_get_external_user(struct file *filep)
+{
+ struct vfio_group *group = filep->private_data;
+
+ if (filep->f_op != &vfio_group_fops)
+ return ERR_PTR(-EINVAL);
+
+ if (!atomic_inc_not_zero(&group->container_users))
+ return ERR_PTR(-EINVAL);
+
+ if (!group->container->iommu_driver ||
+ !vfio_group_viable(group)) {
+ atomic_dec(&group->container_users);
+ return ERR_PTR(-EINVAL);
+ }
+
+ vfio_group_get(group);
+
+ return group;
+}
+EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
+
+void vfio_group_put_external_user(struct vfio_group *group)
+{
+ vfio_group_put(group);
+ vfio_group_try_dissolve_container(group);
+}
+EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
+
+int vfio_external_user_iommu_id(struct vfio_group *group)
+{
+ return iommu_group_id(group->iommu_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
+
+/**
* Module/class support
*/
static char *vfio_devnode(struct device *dev, umode_t *mode)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index ac8d488..24579a0 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -90,4 +90,11 @@
TYPE tmp; \
offsetof(TYPE, MEMBER) + sizeof(tmp.MEMBER); }) \
+/*
+ * External user API
+ */
+extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
+extern void vfio_group_put_external_user(struct vfio_group *group);
+extern int vfio_external_user_iommu_id(struct vfio_group *group);
+
#endif /* VFIO_H */
