This series contains fixes for locking bugs in the recently introduced
pds-vfio-pci driver. There was an initial bug reported by Dan Carpenter
at:
https://lore.kernel.org/kvm/[email protected]/
However, more locking bugs were found when looking into the previously
mentioned issue. So, all fixes are included in this series.
v3:
- Change reset lock from spinlock to mutex
v2:
https://lore.kernel.org/kvm/[email protected]/
- Trim the OOPs in the patch commit messages
- Rework patch 3/3 to only unlock the spinlock once
- Destroy the state_mutex in the driver specific vfio_device_ops.release
callback
v1:
https://lore.kernel.org/kvm/[email protected]/
Brett Creeley (3):
pds/vfio: Fix spinlock bad magic BUG
pds/vfio: Fix mutex lock->magic != lock warning
pds/vfio: Fix possible sleep while in atomic context
drivers/vfio/pci/pds/pci_drv.c | 4 ++--
drivers/vfio/pci/pds/vfio_dev.c | 30 +++++++++++++++++++++---------
drivers/vfio/pci/pds/vfio_dev.h | 2 +-
3 files changed, 24 insertions(+), 12 deletions(-)
--
2.17.1
The driver could possibly sleep while in atomic context resulting
in the following call trace while CONFIG_DEBUG_ATOMIC_SLEEP=y is
set:
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2817, name: bash
preempt_count: 1, expected: 0
RCU nest depth: 0, expected: 0
Call Trace:
<TASK>
dump_stack_lvl+0x36/0x50
__might_resched+0x123/0x170
mutex_lock+0x1e/0x50
pds_vfio_put_lm_file+0x1e/0xa0 [pds_vfio_pci]
pds_vfio_put_save_file+0x19/0x30 [pds_vfio_pci]
pds_vfio_state_mutex_unlock+0x2e/0x80 [pds_vfio_pci]
pci_reset_function+0x4b/0x70
reset_store+0x5b/0xa0
kernfs_fop_write_iter+0x137/0x1d0
vfs_write+0x2de/0x410
ksys_write+0x5d/0xd0
do_syscall_64+0x3b/0x90
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
This can happen if pds_vfio_put_restore_file() and/or
pds_vfio_put_save_file() grab the mutex_lock(&lm_file->lock)
while the spin_lock(&pds_vfio->reset_lock) is held, which can
happen during while calling pds_vfio_state_mutex_unlock().
Fix this by changing the reset_lock to reset_mutex so there are no such
conerns. Also, make sure to destroy the reset_mutex in the driver specific
VFIO device release function.
Reported-by: Dan Carpenter <[email protected]>
Closes: https://lore.kernel.org/kvm/[email protected]/
Signed-off-by: Brett Creeley <[email protected]>
Reviewed-by: Shannon Nelson <[email protected]>
---
drivers/vfio/pci/pds/pci_drv.c | 4 ++--
drivers/vfio/pci/pds/vfio_dev.c | 15 ++++++++-------
drivers/vfio/pci/pds/vfio_dev.h | 2 +-
3 files changed, 11 insertions(+), 10 deletions(-)
diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c
index ab4b5958e413..caffa1a2cf59 100644
--- a/drivers/vfio/pci/pds/pci_drv.c
+++ b/drivers/vfio/pci/pds/pci_drv.c
@@ -55,10 +55,10 @@ static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio)
* VFIO_DEVICE_STATE_RUNNING.
*/
if (deferred_reset_needed) {
- spin_lock(&pds_vfio->reset_lock);
+ mutex_lock(&pds_vfio->reset_mutex);
pds_vfio->deferred_reset = true;
pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR;
- spin_unlock(&pds_vfio->reset_lock);
+ mutex_unlock(&pds_vfio->reset_mutex);
}
}
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 306b1c25f016..4c351c59d05a 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -29,7 +29,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
{
again:
- spin_lock(&pds_vfio->reset_lock);
+ mutex_lock(&pds_vfio->reset_mutex);
if (pds_vfio->deferred_reset) {
pds_vfio->deferred_reset = false;
if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) {
@@ -39,23 +39,23 @@ void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
}
pds_vfio->state = pds_vfio->deferred_reset_state;
pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
- spin_unlock(&pds_vfio->reset_lock);
+ mutex_unlock(&pds_vfio->reset_mutex);
goto again;
}
mutex_unlock(&pds_vfio->state_mutex);
- spin_unlock(&pds_vfio->reset_lock);
+ mutex_unlock(&pds_vfio->reset_mutex);
}
void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio)
{
- spin_lock(&pds_vfio->reset_lock);
+ mutex_lock(&pds_vfio->reset_mutex);
pds_vfio->deferred_reset = true;
pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
if (!mutex_trylock(&pds_vfio->state_mutex)) {
- spin_unlock(&pds_vfio->reset_lock);
+ mutex_unlock(&pds_vfio->reset_mutex);
return;
}
- spin_unlock(&pds_vfio->reset_lock);
+ mutex_unlock(&pds_vfio->reset_mutex);
pds_vfio_state_mutex_unlock(pds_vfio);
}
@@ -156,7 +156,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
pds_vfio->vf_id = vf_id;
mutex_init(&pds_vfio->state_mutex);
- spin_lock_init(&pds_vfio->reset_lock);
+ mutex_init(&pds_vfio->reset_mutex);
vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
vdev->mig_ops = &pds_vfio_lm_ops;
@@ -178,6 +178,7 @@ static void pds_vfio_release_device(struct vfio_device *vdev)
vfio_coredev.vdev);
mutex_destroy(&pds_vfio->state_mutex);
+ mutex_destroy(&pds_vfio->reset_mutex);
vfio_pci_core_release_dev(vdev);
}
diff --git a/drivers/vfio/pci/pds/vfio_dev.h b/drivers/vfio/pci/pds/vfio_dev.h
index b8f2d667608f..e7b01080a1ec 100644
--- a/drivers/vfio/pci/pds/vfio_dev.h
+++ b/drivers/vfio/pci/pds/vfio_dev.h
@@ -18,7 +18,7 @@ struct pds_vfio_pci_device {
struct pds_vfio_dirty dirty;
struct mutex state_mutex; /* protect migration state */
enum vfio_device_mig_state state;
- spinlock_t reset_lock; /* protect reset_done flow */
+ struct mutex reset_mutex; /* protect reset_done flow */
u8 deferred_reset;
enum vfio_device_mig_state deferred_reset_state;
struct notifier_block nb;
--
2.17.1
The following BUG was found when running on a kernel with
CONFIG_DEBUG_MUTEXES=y set:
DEBUG_LOCKS_WARN_ON(lock->magic != lock)
RIP: 0010:mutex_trylock+0x10d/0x120
Call Trace:
<TASK>
? __warn+0x85/0x140
? mutex_trylock+0x10d/0x120
? report_bug+0xfc/0x1e0
? handle_bug+0x3f/0x70
? exc_invalid_op+0x17/0x70
? asm_exc_invalid_op+0x1a/0x20
? mutex_trylock+0x10d/0x120
? mutex_trylock+0x10d/0x120
pds_vfio_reset+0x3a/0x60 [pds_vfio_pci]
pci_reset_function+0x4b/0x70
reset_store+0x5b/0xa0
kernfs_fop_write_iter+0x137/0x1d0
vfs_write+0x2de/0x410
ksys_write+0x5d/0xd0
do_syscall_64+0x3b/0x90
entry_SYSCALL_64_after_hwframe+0x6e/0xd8
As shown, lock->magic != lock. This is because
mutex_init(&pds_vfio->state_mutex) is called in the VFIO open path. So,
if a reset is initiated before the VFIO device is opened the mutex will
have never been initialized. Fix this by calling
mutex_init(&pds_vfio->state_mutex) in the VFIO init path.
Also, don't destroy the mutex on close because the device may
be re-opened, which would cause mutex to be uninitialized. Fix this by
implementing a driver specific vfio_device_ops.release callback that
destroys the mutex before calling vfio_pci_core_release_dev().
Signed-off-by: Brett Creeley <[email protected]>
Reviewed-by: Shannon Nelson <[email protected]>
---
drivers/vfio/pci/pds/vfio_dev.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index c351f588fa13..306b1c25f016 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -155,6 +155,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
pds_vfio->vf_id = vf_id;
+ mutex_init(&pds_vfio->state_mutex);
spin_lock_init(&pds_vfio->reset_lock);
vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
@@ -170,6 +171,16 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
return 0;
}
+static void pds_vfio_release_device(struct vfio_device *vdev)
+{
+ struct pds_vfio_pci_device *pds_vfio =
+ container_of(vdev, struct pds_vfio_pci_device,
+ vfio_coredev.vdev);
+
+ mutex_destroy(&pds_vfio->state_mutex);
+ vfio_pci_core_release_dev(vdev);
+}
+
static int pds_vfio_open_device(struct vfio_device *vdev)
{
struct pds_vfio_pci_device *pds_vfio =
@@ -181,7 +192,6 @@ static int pds_vfio_open_device(struct vfio_device *vdev)
if (err)
return err;
- mutex_init(&pds_vfio->state_mutex);
pds_vfio->state = VFIO_DEVICE_STATE_RUNNING;
pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
@@ -201,14 +211,13 @@ static void pds_vfio_close_device(struct vfio_device *vdev)
pds_vfio_put_save_file(pds_vfio);
pds_vfio_dirty_disable(pds_vfio, true);
mutex_unlock(&pds_vfio->state_mutex);
- mutex_destroy(&pds_vfio->state_mutex);
vfio_pci_core_close_device(vdev);
}
static const struct vfio_device_ops pds_vfio_ops = {
.name = "pds-vfio",
.init = pds_vfio_init_device,
- .release = vfio_pci_core_release_dev,
+ .release = pds_vfio_release_device,
.open_device = pds_vfio_open_device,
.close_device = pds_vfio_close_device,
.ioctl = vfio_pci_core_ioctl,
--
2.17.1
> From: Brett Creeley <[email protected]>
> Sent: Saturday, October 28, 2023 6:37 AM
>
> The driver could possibly sleep while in atomic context resulting
> in the following call trace while CONFIG_DEBUG_ATOMIC_SLEEP=y is
> set:
>
> BUG: sleeping function called from invalid context at
> kernel/locking/mutex.c:283
> in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2817, name: bash
> preempt_count: 1, expected: 0
> RCU nest depth: 0, expected: 0
> Call Trace:
> <TASK>
> dump_stack_lvl+0x36/0x50
> __might_resched+0x123/0x170
> mutex_lock+0x1e/0x50
> pds_vfio_put_lm_file+0x1e/0xa0 [pds_vfio_pci]
> pds_vfio_put_save_file+0x19/0x30 [pds_vfio_pci]
> pds_vfio_state_mutex_unlock+0x2e/0x80 [pds_vfio_pci]
> pci_reset_function+0x4b/0x70
> reset_store+0x5b/0xa0
> kernfs_fop_write_iter+0x137/0x1d0
> vfs_write+0x2de/0x410
> ksys_write+0x5d/0xd0
> do_syscall_64+0x3b/0x90
> entry_SYSCALL_64_after_hwframe+0x6e/0xd8
>
> This can happen if pds_vfio_put_restore_file() and/or
> pds_vfio_put_save_file() grab the mutex_lock(&lm_file->lock)
> while the spin_lock(&pds_vfio->reset_lock) is held, which can
> happen during while calling pds_vfio_state_mutex_unlock().
>
> Fix this by changing the reset_lock to reset_mutex so there are no such
> conerns. Also, make sure to destroy the reset_mutex in the driver specific
> VFIO device release function.
>
> Reported-by: Dan Carpenter <[email protected]>
> Closes: https://lore.kernel.org/kvm/1f9bc27b-3de9-4891-9687-
> [email protected]/
> Signed-off-by: Brett Creeley <[email protected]>
> Reviewed-by: Shannon Nelson <[email protected]>
better change all three drivers together...