| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAErSpo7ZYsES6kZXjcwr-gwKaXm7DzHBvUGz+cpZBBH7stAAAQ@mail.gmail.com>
Date: Tue, 7 Jan 2014 16:15:54 -0700
From: Bjorn Helgaas <bhelgaas@...gle.com>
To: Alex Williamson <alex.williamson@...hat.com>
Cc: "linux-pci@...r.kernel.org" <linux-pci@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] pci: Add "try" reset interfaces
Hi Alex,
Sorry for the delay in looking at this.
On Mon, Dec 16, 2013 at 3:14 PM, Alex Williamson
<alex.williamson@...hat.com> wrote:
> When doing a function/slot/bus reset PCI grabs the device_lock for
> each device to block things like suspend and driver probes, which is
> all well and good, but call paths exist where this lock may already be
> held. This creates an opportunity for deadlock. For instance, vfio
> allows userspace to issue resets so long as it owns the device(s).
> If a driver unbind .remove callback races with userspace issuing a
> reset, we have a deadlock as userspace gets stuck waiting on
> device_lock while another thread has device_lock and waits for .remove
> to complete.
Are you talking about vfio_pci_remove() (the vfio_pci_driver .remove()
method) racing with vfio_pci_ioctl()?
Or maybe it's vfio_pci_release (the vfio_pci_ops .release() method),
since it looks like you want to use pci_try_reset_function() there and
in vfio_pci_ioctl()?
Either way, aren't there at least potentially more locking issues than
just the reset problem? Seems like any ioctl that might take the
device_lock could have the same problem. How do you make sure there's
no userspace owner of the device before you release the device or
remove the driver?
Bjorn
> To resolve this, we can make a version of the reset
> interfaces which use trylock. With this, we can safely attempt a
> reset and return error to userspace if there is contention.
>
> Signed-off-by: Alex Williamson <alex.williamson@...hat.com>
> ---
> drivers/pci/pci.c | 155 +++++++++++++++++++++++++++++++++++++++++++++++++++
> include/linux/pci.h | 3 +
> 2 files changed, 158 insertions(+)
>
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 33120d1..de6416f 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -3445,6 +3445,18 @@ static void pci_dev_lock(struct pci_dev *dev)
> device_lock(&dev->dev);
> }
>
> +/* Return 1 on successful lock, 0 on contention */
> +static int pci_dev_trylock(struct pci_dev *dev)
> +{
> + if (pci_cfg_access_trylock(dev)) {
> + if (device_trylock(&dev->dev))
> + return 1;
> + pci_cfg_access_unlock(dev);
> + }
> +
> + return 0;
> +}
> +
> static void pci_dev_unlock(struct pci_dev *dev)
> {
> device_unlock(&dev->dev);
> @@ -3588,6 +3600,34 @@ int pci_reset_function(struct pci_dev *dev)
> }
> EXPORT_SYMBOL_GPL(pci_reset_function);
>
> +/**
> + * pci_try_reset_function - quiesce and reset a PCI device function
> + * @dev: PCI device to reset
> + *
> + * Same as above, except return -EAGAIN if unable to lock device.
> + */
> +int pci_try_reset_function(struct pci_dev *dev)
> +{
> + int rc;
> +
> + rc = pci_dev_reset(dev, 1);
> + if (rc)
> + return rc;
> +
> + pci_dev_save_and_disable(dev);
> +
> + if (pci_dev_trylock(dev)) {
> + rc = __pci_dev_reset(dev, 0);
> + pci_dev_unlock(dev);
> + } else
> + rc = -EAGAIN;
> +
> + pci_dev_restore(dev);
> +
> + return rc;
> +}
> +EXPORT_SYMBOL_GPL(pci_try_reset_function);
> +
> /* Lock devices from the top of the tree down */
> static void pci_bus_lock(struct pci_bus *bus)
> {
> @@ -3612,6 +3652,32 @@ static void pci_bus_unlock(struct pci_bus *bus)
> }
> }
>
> +/* Return 1 on successful lock, 0 on contention */
> +static int pci_bus_trylock(struct pci_bus *bus)
> +{
> + struct pci_dev *dev;
> +
> + list_for_each_entry(dev, &bus->devices, bus_list) {
> + if (!pci_dev_trylock(dev))
> + goto unlock;
> + if (dev->subordinate) {
> + if (!pci_bus_trylock(dev->subordinate)) {
> + pci_dev_unlock(dev);
> + goto unlock;
> + }
> + }
> + }
> + return 1;
> +
> +unlock:
> + list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) {
> + if (dev->subordinate)
> + pci_bus_unlock(dev->subordinate);
> + pci_dev_unlock(dev);
> + }
> + return 0;
> +}
> +
> /* Lock devices from the top of the tree down */
> static void pci_slot_lock(struct pci_slot *slot)
> {
> @@ -3640,6 +3706,37 @@ static void pci_slot_unlock(struct pci_slot *slot)
> }
> }
>
> +/* Return 1 on successful lock, 0 on contention */
> +static int pci_slot_trylock(struct pci_slot *slot)
> +{
> + struct pci_dev *dev;
> +
> + list_for_each_entry(dev, &slot->bus->devices, bus_list) {
> + if (!dev->slot || dev->slot != slot)
> + continue;
> + if (!pci_dev_trylock(dev))
> + goto unlock;
> + if (dev->subordinate) {
> + if (!pci_bus_trylock(dev->subordinate)) {
> + pci_dev_unlock(dev);
> + goto unlock;
> + }
> + }
> + }
> + return 1;
> +
> +unlock:
> + list_for_each_entry_continue_reverse(dev,
> + &slot->bus->devices, bus_list) {
> + if (!dev->slot || dev->slot != slot)
> + continue;
> + if (dev->subordinate)
> + pci_bus_unlock(dev->subordinate);
> + pci_dev_unlock(dev);
> + }
> + return 0;
> +}
> +
> /* Save and disable devices from the top of the tree down */
> static void pci_bus_save_and_disable(struct pci_bus *bus)
> {
> @@ -3763,6 +3860,35 @@ int pci_reset_slot(struct pci_slot *slot)
> }
> EXPORT_SYMBOL_GPL(pci_reset_slot);
>
> +/**
> + * pci_try_reset_slot - Try to reset a PCI slot
> + * @slot: PCI slot to reset
> + *
> + * Same as above except return -EAGAIN if the slot cannot be locked
> + */
> +int pci_try_reset_slot(struct pci_slot *slot)
> +{
> + int rc;
> +
> + rc = pci_slot_reset(slot, 1);
> + if (rc)
> + return rc;
> +
> + pci_slot_save_and_disable(slot);
> +
> + if (pci_slot_trylock(slot)) {
> + might_sleep();
> + rc = pci_reset_hotplug_slot(slot->hotplug, 0);
> + pci_slot_unlock(slot);
> + } else
> + rc = -EAGAIN;
> +
> + pci_slot_restore(slot);
> +
> + return rc;
> +}
> +EXPORT_SYMBOL_GPL(pci_try_reset_slot);
> +
> static int pci_bus_reset(struct pci_bus *bus, int probe)
> {
> if (!bus->self)
> @@ -3822,6 +3948,35 @@ int pci_reset_bus(struct pci_bus *bus)
> EXPORT_SYMBOL_GPL(pci_reset_bus);
>
> /**
> + * pci_try_reset_bus - Try to reset a PCI bus
> + * @bus: top level PCI bus to reset
> + *
> + * Same as above except return -EAGAIN if the bus cannot be locked
> + */
> +int pci_try_reset_bus(struct pci_bus *bus)
> +{
> + int rc;
> +
> + rc = pci_bus_reset(bus, 1);
> + if (rc)
> + return rc;
> +
> + pci_bus_save_and_disable(bus);
> +
> + if (pci_bus_trylock(bus)) {
> + might_sleep();
> + pci_reset_bridge_secondary_bus(bus->self);
> + pci_bus_unlock(bus);
> + } else
> + rc = -EAGAIN;
> +
> + pci_bus_restore(bus);
> +
> + return rc;
> +}
> +EXPORT_SYMBOL_GPL(pci_try_reset_bus);
> +
> +/**
> * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
> * @dev: PCI device to query
> *
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 1084a15..34629df 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -951,10 +951,13 @@ int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed,
> int __pci_reset_function(struct pci_dev *dev);
> int __pci_reset_function_locked(struct pci_dev *dev);
> int pci_reset_function(struct pci_dev *dev);
> +int pci_try_reset_function(struct pci_dev *dev);
> int pci_probe_reset_slot(struct pci_slot *slot);
> int pci_reset_slot(struct pci_slot *slot);
> +int pci_try_reset_slot(struct pci_slot *slot);
> int pci_probe_reset_bus(struct pci_bus *bus);
> int pci_reset_bus(struct pci_bus *bus);
> +int pci_try_reset_bus(struct pci_bus *bus);
> void pci_reset_bridge_secondary_bus(struct pci_dev *dev);
> void pci_update_resource(struct pci_dev *dev, int resno);
> int __must_check pci_assign_resource(struct pci_dev *dev, int i);
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists