VFIO updates for v5.2-rc1

- Improve dev_printk() usage (Bjorn Helgaas)
 
  - Fix issue with blocking in !TASK_RUNNING state while waiting for
    userspace to release devices (Farhan Ali)
 
  - Fix error path cleanup in nvlink setup (Greg Kurz)
 
  - mdev-core cleanups and fixes in preparation for more use cases
    (Parav Pandit)
 
  - Cornelia has volunteered as an official vfio reviewer (Cornelia Huck)
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.14 (GNU/Linux)
 
 iQIcBAABAgAGBQJc1e9mAAoJECObm247sIsiB+sP/Rs94smfIyO/N3a73gd3KrAV
 wmnNGLbUGEEoumUmzWYjSq/l3zfehYpe2kiKJklH8sUPP+kGL0eQj2H5++/LWC3E
 EMMPGVoD0wHHoWwdVKY79xjDIUUeNZe2IFVUjLgwJ9UD79DBBGJUMpWQhbuUDkl1
 nGCb0ltzu6H+OzELLZxXSC7QdhnB97mRaamSI2sunTM7tr6QaL13YsrFES4mpj23
 vIGElbdpyPBeMMbh2rhhb581RDXEv5GCy6SKfBpHOMay4rpr37YX8CJ/7uh4rNcn
 DF3aikkK2NpVv5Rk1+AJvvri+MDmOF9TMC5EG24swEAqJrr4jYyWXvPb/WKNDm2w
 Z0qxBHkZLPJ9kARMQxuAAqJ5vKDwy/FgRjoZi0aEsOjJO+HYeCdIKkueFXdWXw2O
 pL5IdZr5VSejYdVxjV2Ft6y90dQjxIAdDd6QJDnuEAu2JEb2T1q9iea/QOMnEJyD
 QM3h1mx/rNZnkmEVgpE4t9TGnoPMmg/grzcfu+8wQZk8ys1uqSfBSdgWoBgheQ9z
 XJDHCvkRG7bc/VTVcet+HPBvK38Kdv0Er+8eHNmG4c11ifgODzShbXl5oKgDE3iC
 WJi/ilYVn2dleo/4ZqiCP+U/PEVgED4k4pvj0vWhaE7CfGJDC60Te2/q+aB4sTMI
 4EChWOml/T545Hzv6swn
 =JSGI
 -----END PGP SIGNATURE-----

Merge tag 'vfio-v5.2-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Improve dev_printk() usage (Bjorn Helgaas)

 - Fix issue with blocking in !TASK_RUNNING state while waiting for
   userspace to release devices (Farhan Ali)

 - Fix error path cleanup in nvlink setup (Greg Kurz)

 - mdev-core cleanups and fixes in preparation for more use cases (Parav
   Pandit)

 - Cornelia has volunteered as an official vfio reviewer (Cornelia Huck)

* tag 'vfio-v5.2-rc1' of git://github.com/awilliam/linux-vfio:
  vfio: Add Cornelia Huck as reviewer
  vfio/mdev: Avoid inline get and put parent helpers
  vfio/mdev: Fix aborting mdev child device removal if one fails
  vfio/mdev: Follow correct remove sequence
  vfio/mdev: Avoid masking error code to EBUSY
  vfio/mdev: Drop redundant extern for exported symbols
  vfio/mdev: Removed unused kref
  vfio/mdev: Avoid release parent reference during error path
  vfio-pci/nvlink2: Fix potential VMA leak
  vfio: Fix WARNING "do not call blocking ops when !TASK_RUNNING"
  vfio: Use dev_printk() when possible
This commit is contained in:
Linus Torvalds 2019-05-11 10:47:46 -04:00
commit 6fe567df04
12 changed files with 81 additions and 95 deletions

View File

@ -16557,6 +16557,7 @@ F: fs/fat/
VFIO DRIVER
M: Alex Williamson <alex.williamson@redhat.com>
R: Cornelia Huck <cohuck@redhat.com>
L: kvm@vger.kernel.org
T: git git://github.com/awilliam/linux-vfio.git
S: Maintained

View File

@ -88,7 +88,7 @@ static void mdev_release_parent(struct kref *kref)
put_device(dev);
}
static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
static struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
{
if (parent)
kref_get(&parent->ref);
@ -96,7 +96,7 @@ static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
return parent;
}
static inline void mdev_put_parent(struct mdev_parent *parent)
static void mdev_put_parent(struct mdev_parent *parent)
{
if (parent)
kref_put(&parent->ref, mdev_release_parent);
@ -141,7 +141,7 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
*/
ret = parent->ops->remove(mdev);
if (ret && !force_remove)
return -EBUSY;
return ret;
sysfs_remove_groups(&mdev->dev.kobj, parent->ops->mdev_attr_groups);
return 0;
@ -149,10 +149,10 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
static int mdev_device_remove_cb(struct device *dev, void *data)
{
if (!dev_is_mdev(dev))
return 0;
if (dev_is_mdev(dev))
mdev_device_remove(dev, true);
return mdev_device_remove(dev, data ? *(bool *)data : true);
return 0;
}
/*
@ -181,6 +181,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
/* Check for duplicate */
parent = __find_parent_device(dev);
if (parent) {
parent = NULL;
ret = -EEXIST;
goto add_dev_err;
}
@ -239,7 +240,6 @@ EXPORT_SYMBOL(mdev_register_device);
void mdev_unregister_device(struct device *dev)
{
struct mdev_parent *parent;
bool force_remove = true;
mutex_lock(&parent_list_lock);
parent = __find_parent_device(dev);
@ -253,8 +253,7 @@ void mdev_unregister_device(struct device *dev)
list_del(&parent->next);
class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
device_for_each_child(dev, (void *)&force_remove,
mdev_device_remove_cb);
device_for_each_child(dev, NULL, mdev_device_remove_cb);
parent_remove_sysfs_files(parent);
@ -310,7 +309,6 @@ int mdev_device_create(struct kobject *kobj,
mutex_unlock(&mdev_list_lock);
mdev->parent = parent;
kref_init(&mdev->ref);
mdev->dev.parent = dev;
mdev->dev.bus = &mdev_bus_type;

View File

@ -30,7 +30,6 @@ struct mdev_device {
struct mdev_parent *parent;
guid_t uuid;
void *driver_data;
struct kref ref;
struct list_head next;
struct kobject *type_kobj;
bool active;

View File

@ -280,7 +280,7 @@ type_link_failed:
void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type)
{
sysfs_remove_files(&dev->kobj, mdev_device_attrs);
sysfs_remove_link(&dev->kobj, "mdev_type");
sysfs_remove_link(type->devices_kobj, dev_name(dev));
sysfs_remove_files(&dev->kobj, mdev_device_attrs);
}

View File

@ -12,6 +12,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#define dev_fmt pr_fmt
#include <linux/device.h>
#include <linux/eventfd.h>
@ -287,12 +288,11 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
pci_save_state(pdev);
vdev->pci_saved_state = pci_store_saved_state(pdev);
if (!vdev->pci_saved_state)
pr_debug("%s: Couldn't store %s saved state\n",
__func__, dev_name(&pdev->dev));
pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__);
if (likely(!nointxmask)) {
if (vfio_pci_nointx(pdev)) {
dev_info(&pdev->dev, "Masking broken INTx support\n");
pci_info(pdev, "Masking broken INTx support\n");
vdev->nointx = true;
pci_intx(pdev, 0);
} else
@ -336,8 +336,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
if (ret) {
dev_warn(&vdev->pdev->dev,
"Failed to setup Intel IGD regions\n");
pci_warn(pdev, "Failed to setup Intel IGD regions\n");
goto disable_exit;
}
}
@ -346,8 +345,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
ret = vfio_pci_nvdia_v100_nvlink2_init(vdev);
if (ret && ret != -ENODEV) {
dev_warn(&vdev->pdev->dev,
"Failed to setup NVIDIA NV2 RAM region\n");
pci_warn(pdev, "Failed to setup NVIDIA NV2 RAM region\n");
goto disable_exit;
}
}
@ -356,8 +354,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
ret = vfio_pci_ibm_npu2_init(vdev);
if (ret && ret != -ENODEV) {
dev_warn(&vdev->pdev->dev,
"Failed to setup NVIDIA NV2 ATSD region\n");
pci_warn(pdev, "Failed to setup NVIDIA NV2 ATSD region\n");
goto disable_exit;
}
}
@ -429,8 +426,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
* is just busy work.
*/
if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
pr_info("%s: Couldn't reload %s saved state\n",
__func__, dev_name(&pdev->dev));
pci_info(pdev, "%s: Couldn't reload saved state\n", __func__);
if (!vdev->reset_works)
goto out;
@ -1255,17 +1251,18 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
static void vfio_pci_request(void *device_data, unsigned int count)
{
struct vfio_pci_device *vdev = device_data;
struct pci_dev *pdev = vdev->pdev;
mutex_lock(&vdev->igate);
if (vdev->req_trigger) {
if (!(count % 10))
dev_notice_ratelimited(&vdev->pdev->dev,
pci_notice_ratelimited(pdev,
"Relaying device request to user (#%u)\n",
count);
eventfd_signal(vdev->req_trigger, 1);
} else if (count == 0) {
dev_warn(&vdev->pdev->dev,
pci_warn(pdev,
"No device request channel registered, blocked until released by user\n");
}

View File

@ -412,8 +412,7 @@ static void vfio_bar_restore(struct vfio_pci_device *vdev)
if (pdev->is_virtfn)
return;
pr_info("%s: %s reset recovery - restoring bars\n",
__func__, dev_name(&pdev->dev));
pci_info(pdev, "%s: reset recovery - restoring BARs\n", __func__);
for (i = PCI_BASE_ADDRESS_0; i <= PCI_BASE_ADDRESS_5; i += 4, rbar++)
pci_user_write_config_dword(pdev, i, *rbar);
@ -1298,8 +1297,8 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
else
return PCI_SATA_SIZEOF_SHORT;
default:
pr_warn("%s: %s unknown length for pci cap 0x%x@0x%x\n",
dev_name(&pdev->dev), __func__, cap, pos);
pci_warn(pdev, "%s: unknown length for PCI cap %#x@%#x\n",
__func__, cap, pos);
}
return 0;
@ -1372,8 +1371,8 @@ static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
}
return PCI_TPH_BASE_SIZEOF;
default:
pr_warn("%s: %s unknown length for pci ecap 0x%x@0x%x\n",
dev_name(&pdev->dev), __func__, ecap, epos);
pci_warn(pdev, "%s: unknown length for PCI ecap %#x@%#x\n",
__func__, ecap, epos);
}
return 0;
@ -1474,8 +1473,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
}
if (!len) {
pr_info("%s: %s hiding cap 0x%x\n",
__func__, dev_name(&pdev->dev), cap);
pci_info(pdev, "%s: hiding cap %#x@%#x\n", __func__,
cap, pos);
*prev = next;
pos = next;
continue;
@ -1486,9 +1485,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
if (likely(map[pos + i] == PCI_CAP_ID_INVALID))
continue;
pr_warn("%s: %s pci config conflict @0x%x, was cap 0x%x now cap 0x%x\n",
__func__, dev_name(&pdev->dev),
pos + i, map[pos + i], cap);
pci_warn(pdev, "%s: PCI config conflict @%#x, was cap %#x now cap %#x\n",
__func__, pos + i, map[pos + i], cap);
}
BUILD_BUG_ON(PCI_CAP_ID_MAX >= PCI_CAP_ID_INVALID_VIRT);
@ -1549,8 +1547,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
}
if (!len) {
pr_info("%s: %s hiding ecap 0x%x@0x%x\n",
__func__, dev_name(&pdev->dev), ecap, epos);
pci_info(pdev, "%s: hiding ecap %#x@%#x\n",
__func__, ecap, epos);
/* If not the first in the chain, we can skip over it */
if (prev) {
@ -1572,9 +1570,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
if (likely(map[epos + i] == PCI_CAP_ID_INVALID))
continue;
pr_warn("%s: %s pci config conflict @0x%x, was ecap 0x%x now ecap 0x%x\n",
__func__, dev_name(&pdev->dev),
epos + i, map[epos + i], ecap);
pci_warn(pdev, "%s: PCI config conflict @%#x, was ecap %#x now ecap %#x\n",
__func__, epos + i, map[epos + i], ecap);
}
/*

View File

@ -472,6 +472,8 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
return 0;
free_exit:
if (data->base)
memunmap(data->base);
kfree(data);
return ret;

View File

@ -89,7 +89,8 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
} while ((pcs_value & MDIO_CTRL1_RESET) && --count);
if (pcs_value & MDIO_CTRL1_RESET)
pr_warn("%s XGBE PHY reset timeout\n", __func__);
dev_warn(vdev->device, "%s: XGBE PHY reset timeout\n",
__func__);
/* disable auto-negotiation */
value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1);
@ -114,7 +115,7 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
usleep_range(500, 600);
if (!count)
pr_warn("%s MAC SW reset failed\n", __func__);
dev_warn(vdev->device, "%s: MAC SW reset failed\n", __func__);
return 0;
}

View File

@ -12,6 +12,8 @@
* GNU General Public License for more details.
*/
#define dev_fmt(fmt) "VFIO: " fmt
#include <linux/device.h>
#include <linux/acpi.h>
#include <linux/iommu.h>
@ -63,7 +65,7 @@ static int vfio_platform_acpi_probe(struct vfio_platform_device *vdev,
adev = ACPI_COMPANION(dev);
if (!adev) {
pr_err("VFIO: ACPI companion device not found for %s\n",
dev_err(dev, "ACPI companion device not found for %s\n",
vdev->name);
return -ENODEV;
}
@ -638,7 +640,7 @@ static int vfio_platform_of_probe(struct vfio_platform_device *vdev,
ret = device_property_read_string(dev, "compatible",
&vdev->compat);
if (ret)
pr_err("VFIO: Cannot retrieve compat for %s\n", vdev->name);
dev_err(dev, "Cannot retrieve compat for %s\n", vdev->name);
return ret;
}
@ -680,14 +682,14 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
ret = vfio_platform_get_reset(vdev);
if (ret && vdev->reset_required) {
pr_err("VFIO: No reset function found for device %s\n",
vdev->name);
dev_err(dev, "No reset function found for device %s\n",
vdev->name);
return ret;
}
group = vfio_iommu_group_get(dev);
if (!group) {
pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
dev_err(dev, "No IOMMU group for device %s\n", vdev->name);
ret = -EINVAL;
goto put_reset;
}

View File

@ -34,6 +34,7 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/wait.h>
#include <linux/sched/signal.h>
#define DRIVER_VERSION "0.3"
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
@ -704,8 +705,8 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
return 0;
/* TODO Prevent device auto probing */
WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
iommu_group_id(group->iommu_group));
dev_WARN(dev, "Device added to live group %d!\n",
iommu_group_id(group->iommu_group));
return 0;
}
@ -748,25 +749,22 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
*/
break;
case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
pr_debug("%s: Device %s, group %d binding to driver\n",
__func__, dev_name(dev),
iommu_group_id(group->iommu_group));
dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
iommu_group_id(group->iommu_group));
break;
case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
pr_debug("%s: Device %s, group %d bound to driver %s\n",
__func__, dev_name(dev),
iommu_group_id(group->iommu_group), dev->driver->name);
dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
iommu_group_id(group->iommu_group), dev->driver->name);
BUG_ON(vfio_group_nb_verify(group, dev));
break;
case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
__func__, dev_name(dev),
iommu_group_id(group->iommu_group), dev->driver->name);
dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
__func__, iommu_group_id(group->iommu_group),
dev->driver->name);
break;
case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
pr_debug("%s: Device %s, group %d unbound from driver\n",
__func__, dev_name(dev),
iommu_group_id(group->iommu_group));
dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
iommu_group_id(group->iommu_group));
/*
* XXX An unbound device in a live group is ok, but we'd
* really like to avoid the above BUG_ON by preventing other
@ -830,8 +828,8 @@ int vfio_add_group_dev(struct device *dev,
device = vfio_group_get_device(group, dev);
if (device) {
WARN(1, "Device %s already exists on group %d\n",
dev_name(dev), iommu_group_id(iommu_group));
dev_WARN(dev, "Device already exists on group %d\n",
iommu_group_id(iommu_group));
vfio_device_put(device);
vfio_group_put(group);
return -EBUSY;
@ -904,30 +902,17 @@ void *vfio_device_data(struct vfio_device *device)
}
EXPORT_SYMBOL_GPL(vfio_device_data);
/* Given a referenced group, check if it contains the device */
static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
{
struct vfio_device *device;
device = vfio_group_get_device(group, dev);
if (!device)
return false;
vfio_device_put(device);
return true;
}
/*
* Decrement the device reference count and wait for the device to be
* removed. Open file descriptors for the device... */
void *vfio_del_group_dev(struct device *dev)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct vfio_device *device = dev_get_drvdata(dev);
struct vfio_group *group = device->group;
void *device_data = device->device_data;
struct vfio_unbound_dev *unbound;
unsigned int i = 0;
long ret;
bool interrupted = false;
/*
@ -964,6 +949,8 @@ void *vfio_del_group_dev(struct device *dev)
* interval with counter to allow the driver to take escalating
* measures to release the device if it has the ability to do so.
*/
add_wait_queue(&vfio.release_q, &wait);
do {
device = vfio_group_get_device(group, dev);
if (!device)
@ -975,12 +962,10 @@ void *vfio_del_group_dev(struct device *dev)
vfio_device_put(device);
if (interrupted) {
ret = wait_event_timeout(vfio.release_q,
!vfio_dev_present(group, dev), HZ * 10);
wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
} else {
ret = wait_event_interruptible_timeout(vfio.release_q,
!vfio_dev_present(group, dev), HZ * 10);
if (ret == -ERESTARTSYS) {
wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
if (signal_pending(current)) {
interrupted = true;
dev_warn(dev,
"Device is currently in use, task"
@ -989,8 +974,10 @@ void *vfio_del_group_dev(struct device *dev)
current->comm, task_pid_nr(current));
}
}
} while (ret <= 0);
} while (1);
remove_wait_queue(&vfio.release_q, &wait);
/*
* In order to support multiple devices per group, devices can be
* plucked from the group while other devices in the group are still

View File

@ -118,21 +118,20 @@ struct mdev_driver {
#define to_mdev_driver(drv) container_of(drv, struct mdev_driver, driver)
extern void *mdev_get_drvdata(struct mdev_device *mdev);
extern void mdev_set_drvdata(struct mdev_device *mdev, void *data);
extern const guid_t *mdev_uuid(struct mdev_device *mdev);
void *mdev_get_drvdata(struct mdev_device *mdev);
void mdev_set_drvdata(struct mdev_device *mdev, void *data);
const guid_t *mdev_uuid(struct mdev_device *mdev);
extern struct bus_type mdev_bus_type;
extern int mdev_register_device(struct device *dev,
const struct mdev_parent_ops *ops);
extern void mdev_unregister_device(struct device *dev);
int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops);
void mdev_unregister_device(struct device *dev);
extern int mdev_register_driver(struct mdev_driver *drv, struct module *owner);
extern void mdev_unregister_driver(struct mdev_driver *drv);
int mdev_register_driver(struct mdev_driver *drv, struct module *owner);
void mdev_unregister_driver(struct mdev_driver *drv);
extern struct device *mdev_parent_dev(struct mdev_device *mdev);
extern struct device *mdev_dev(struct mdev_device *mdev);
extern struct mdev_device *mdev_from_dev(struct device *dev);
struct device *mdev_parent_dev(struct mdev_device *mdev);
struct device *mdev_dev(struct mdev_device *mdev);
struct mdev_device *mdev_from_dev(struct device *dev);
#endif /* MDEV_H */

View File

@ -2363,4 +2363,7 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type);
#define pci_info(pdev, fmt, arg...) dev_info(&(pdev)->dev, fmt, ##arg)
#define pci_dbg(pdev, fmt, arg...) dev_dbg(&(pdev)->dev, fmt, ##arg)
#define pci_notice_ratelimited(pdev, fmt, arg...) \
dev_notice_ratelimited(&(pdev)->dev, fmt, ##arg)
#endif /* LINUX_PCI_H */