2020-04-29 16:59:10

by Stefan Hajnoczi

[permalink] [raw]
Subject: [PATCH v3] virtio-blk: handle block_device_operations callbacks after hot unplug

A userspace process holding a file descriptor to a virtio_blk device can
still invoke block_device_operations after hot unplug. This leads to a
use-after-free accessing vblk->vdev in virtblk_getgeo() when
ioctl(HDIO_GETGEO) is invoked:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
PGD 800000003a92f067 PUD 3a930067 PMD 0
Oops: 0000 [#1] SMP
CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000
RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246
RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40
RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301
R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680
R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000
FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
[<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk]
[<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0
[<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20
[<ffffffff8d488771>] block_ioctl+0x41/0x50
[<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0
[<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0

A related problem is that virtblk_remove() leaks the vd_index_ida index
when something still holds a reference to vblk->disk during hot unplug.
This causes virtio-blk device names to be lost (vda, vdb, etc).

Fix these issues by protecting vblk->vdev with a mutex and reference
counting vblk so the vd_index_ida index can be removed in all cases.

Fixes: 48e4043d4529523cbc7fa8dd745bd8e2c45ce1d3
("virtio: add virtio disk geometry feature")
Reported-by: Lance Digby <[email protected]>
Signed-off-by: Stefan Hajnoczi <[email protected]>
---
drivers/block/virtio_blk.c | 87 ++++++++++++++++++++++++++++++++++----
1 file changed, 79 insertions(+), 8 deletions(-)

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 93468b7c6701..6f7f277495f4 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -33,6 +33,16 @@ struct virtio_blk_vq {
} ____cacheline_aligned_in_smp;

struct virtio_blk {
+ /*
+ * vdev may be accessed without taking this mutex in blk-mq and
+ * virtqueue code paths because virtblk_remove() stops them before vdev
+ * is freed.
+ *
+ * Everything else must hold this mutex when accessing vdev and must
+ * handle the case where vdev is NULL after virtblk_remove() has been
+ * called.
+ */
+ struct mutex vdev_mutex;
struct virtio_device *vdev;

/* The disk structure for the kernel. */
@@ -44,6 +54,13 @@ struct virtio_blk {
/* Process context for config space updates */
struct work_struct config_work;

+ /*
+ * Tracks references from block_device_operations open/release and
+ * virtio_driver probe/remove so this object can be freed once no
+ * longer in use.
+ */
+ refcount_t refs;
+
/* What host tells us, plus 2 for header & tailer. */
unsigned int sg_elems;

@@ -295,10 +312,55 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
return err;
}

+static void virtblk_get(struct virtio_blk *vblk)
+{
+ refcount_inc(&vblk->refs);
+}
+
+static void virtblk_put(struct virtio_blk *vblk)
+{
+ if (refcount_dec_and_test(&vblk->refs)) {
+ ida_simple_remove(&vd_index_ida, vblk->index);
+ mutex_destroy(&vblk->vdev_mutex);
+ kfree(vblk);
+ }
+}
+
+static int virtblk_open(struct block_device *bd, fmode_t mode)
+{
+ struct virtio_blk *vblk = bd->bd_disk->private_data;
+ int ret = 0;
+
+ mutex_lock(&vblk->vdev_mutex);
+
+ if (vblk->vdev)
+ virtblk_get(vblk);
+ else
+ ret = -ENXIO;
+
+ mutex_unlock(&vblk->vdev_mutex);
+ return ret;
+}
+
+static void virtblk_release(struct gendisk *disk, fmode_t mode)
+{
+ struct virtio_blk *vblk = disk->private_data;
+
+ virtblk_put(vblk);
+}
+
/* We provide getgeo only to please some old bootloader/partitioning tools */
static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
{
struct virtio_blk *vblk = bd->bd_disk->private_data;
+ int ret = 0;
+
+ mutex_lock(&vblk->vdev_mutex);
+
+ if (!vblk->vdev) {
+ ret = -ENXIO;
+ goto out;
+ }

/* see if the host passed in geometry config */
if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
@@ -314,11 +376,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
geo->sectors = 1 << 5;
geo->cylinders = get_capacity(bd->bd_disk) >> 11;
}
- return 0;
+out:
+ mutex_unlock(&vblk->vdev_mutex);
+ return ret;
}

static const struct block_device_operations virtblk_fops = {
.owner = THIS_MODULE,
+ .open = virtblk_open,
+ .release = virtblk_release,
.getgeo = virtblk_getgeo,
};

@@ -655,6 +721,10 @@ static int virtblk_probe(struct virtio_device *vdev)
goto out_free_index;
}

+ /* This reference is dropped in virtblk_remove(). */
+ refcount_set(&vblk->refs, 1);
+ mutex_init(&vblk->vdev_mutex);
+
vblk->vdev = vdev;
vblk->sg_elems = sg_elems;

@@ -820,8 +890,6 @@ static int virtblk_probe(struct virtio_device *vdev)
static void virtblk_remove(struct virtio_device *vdev)
{
struct virtio_blk *vblk = vdev->priv;
- int index = vblk->index;
- int refc;

/* Make sure no work handler is accessing the device. */
flush_work(&vblk->config_work);
@@ -831,18 +899,21 @@ static void virtblk_remove(struct virtio_device *vdev)

blk_mq_free_tag_set(&vblk->tag_set);

+ mutex_lock(&vblk->vdev_mutex);
+
/* Stop all the virtqueues. */
vdev->config->reset(vdev);

- refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
+ /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
+ vblk->vdev = NULL;
+
put_disk(vblk->disk);
vdev->config->del_vqs(vdev);
kfree(vblk->vqs);
- kfree(vblk);

- /* Only free device id if we don't have any users */
- if (refc == 1)
- ida_simple_remove(&vd_index_ida, index);
+ mutex_unlock(&vblk->vdev_mutex);
+
+ virtblk_put(vblk);
}

#ifdef CONFIG_PM_SLEEP
--
2.25.3


2020-04-30 08:48:40

by Stefano Garzarella

[permalink] [raw]
Subject: Re: [PATCH v3] virtio-blk: handle block_device_operations callbacks after hot unplug

On Wed, Apr 29, 2020 at 05:53:45PM +0100, Stefan Hajnoczi wrote:
> A userspace process holding a file descriptor to a virtio_blk device can
> still invoke block_device_operations after hot unplug. This leads to a
> use-after-free accessing vblk->vdev in virtblk_getgeo() when
> ioctl(HDIO_GETGEO) is invoked:
>
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
> IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> PGD 800000003a92f067 PUD 3a930067 PMD 0
> Oops: 0000 [#1] SMP
> CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
> task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000
> RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246
> RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000
> RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40
> RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301
> R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680
> R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000
> FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
> [<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk]
> [<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0
> [<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20
> [<ffffffff8d488771>] block_ioctl+0x41/0x50
> [<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0
> [<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0
>
> A related problem is that virtblk_remove() leaks the vd_index_ida index
> when something still holds a reference to vblk->disk during hot unplug.
> This causes virtio-blk device names to be lost (vda, vdb, etc).
>
> Fix these issues by protecting vblk->vdev with a mutex and reference
> counting vblk so the vd_index_ida index can be removed in all cases.
>
> Fixes: 48e4043d4529523cbc7fa8dd745bd8e2c45ce1d3
> ("virtio: add virtio disk geometry feature")
> Reported-by: Lance Digby <[email protected]>
> Signed-off-by: Stefan Hajnoczi <[email protected]>
> ---
> drivers/block/virtio_blk.c | 87 ++++++++++++++++++++++++++++++++++----
> 1 file changed, 79 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> index 93468b7c6701..6f7f277495f4 100644
> --- a/drivers/block/virtio_blk.c
> +++ b/drivers/block/virtio_blk.c
> @@ -33,6 +33,16 @@ struct virtio_blk_vq {
> } ____cacheline_aligned_in_smp;
>
> struct virtio_blk {
> + /*
> + * vdev may be accessed without taking this mutex in blk-mq and
> + * virtqueue code paths because virtblk_remove() stops them before vdev
> + * is freed.
> + *
> + * Everything else must hold this mutex when accessing vdev and must
> + * handle the case where vdev is NULL after virtblk_remove() has been
> + * called.
> + */
> + struct mutex vdev_mutex;

The patch LGTM, I'm just worried about cache_type_store() and
cache_type_show() because IIUC they aren't in blk-mq and virtqueue code
paths, but they use vdev.

Do we have to take the mutex there too?

Thanks,
Stefano

> struct virtio_device *vdev;
>
> /* The disk structure for the kernel. */
> @@ -44,6 +54,13 @@ struct virtio_blk {
> /* Process context for config space updates */
> struct work_struct config_work;
>
> + /*
> + * Tracks references from block_device_operations open/release and
> + * virtio_driver probe/remove so this object can be freed once no
> + * longer in use.
> + */
> + refcount_t refs;
> +
> /* What host tells us, plus 2 for header & tailer. */
> unsigned int sg_elems;
>
> @@ -295,10 +312,55 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
> return err;
> }
>
> +static void virtblk_get(struct virtio_blk *vblk)
> +{
> + refcount_inc(&vblk->refs);
> +}
> +
> +static void virtblk_put(struct virtio_blk *vblk)
> +{
> + if (refcount_dec_and_test(&vblk->refs)) {
> + ida_simple_remove(&vd_index_ida, vblk->index);
> + mutex_destroy(&vblk->vdev_mutex);
> + kfree(vblk);
> + }
> +}
> +
> +static int virtblk_open(struct block_device *bd, fmode_t mode)
> +{
> + struct virtio_blk *vblk = bd->bd_disk->private_data;
> + int ret = 0;
> +
> + mutex_lock(&vblk->vdev_mutex);
> +
> + if (vblk->vdev)
> + virtblk_get(vblk);
> + else
> + ret = -ENXIO;
> +
> + mutex_unlock(&vblk->vdev_mutex);
> + return ret;
> +}
> +
> +static void virtblk_release(struct gendisk *disk, fmode_t mode)
> +{
> + struct virtio_blk *vblk = disk->private_data;
> +
> + virtblk_put(vblk);
> +}
> +
> /* We provide getgeo only to please some old bootloader/partitioning tools */
> static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
> {
> struct virtio_blk *vblk = bd->bd_disk->private_data;
> + int ret = 0;
> +
> + mutex_lock(&vblk->vdev_mutex);
> +
> + if (!vblk->vdev) {
> + ret = -ENXIO;
> + goto out;
> + }
>
> /* see if the host passed in geometry config */
> if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) {
> @@ -314,11 +376,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
> geo->sectors = 1 << 5;
> geo->cylinders = get_capacity(bd->bd_disk) >> 11;
> }
> - return 0;
> +out:
> + mutex_unlock(&vblk->vdev_mutex);
> + return ret;
> }
>
> static const struct block_device_operations virtblk_fops = {
> .owner = THIS_MODULE,
> + .open = virtblk_open,
> + .release = virtblk_release,
> .getgeo = virtblk_getgeo,
> };
>
> @@ -655,6 +721,10 @@ static int virtblk_probe(struct virtio_device *vdev)
> goto out_free_index;
> }
>
> + /* This reference is dropped in virtblk_remove(). */
> + refcount_set(&vblk->refs, 1);
> + mutex_init(&vblk->vdev_mutex);
> +
> vblk->vdev = vdev;
> vblk->sg_elems = sg_elems;
>
> @@ -820,8 +890,6 @@ static int virtblk_probe(struct virtio_device *vdev)
> static void virtblk_remove(struct virtio_device *vdev)
> {
> struct virtio_blk *vblk = vdev->priv;
> - int index = vblk->index;
> - int refc;
>
> /* Make sure no work handler is accessing the device. */
> flush_work(&vblk->config_work);
> @@ -831,18 +899,21 @@ static void virtblk_remove(struct virtio_device *vdev)
>
> blk_mq_free_tag_set(&vblk->tag_set);
>
> + mutex_lock(&vblk->vdev_mutex);
> +
> /* Stop all the virtqueues. */
> vdev->config->reset(vdev);
>
> - refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
> + /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */
> + vblk->vdev = NULL;
> +
> put_disk(vblk->disk);
> vdev->config->del_vqs(vdev);
> kfree(vblk->vqs);
> - kfree(vblk);
>
> - /* Only free device id if we don't have any users */
> - if (refc == 1)
> - ida_simple_remove(&vd_index_ida, index);
> + mutex_unlock(&vblk->vdev_mutex);
> +
> + virtblk_put(vblk);
> }
>
> #ifdef CONFIG_PM_SLEEP
> --
> 2.25.3
>

2020-04-30 10:16:44

by Stefan Hajnoczi

[permalink] [raw]
Subject: Re: [PATCH v3] virtio-blk: handle block_device_operations callbacks after hot unplug

On Thu, Apr 30, 2020 at 10:43:23AM +0200, Stefano Garzarella wrote:
> On Wed, Apr 29, 2020 at 05:53:45PM +0100, Stefan Hajnoczi wrote:
> > A userspace process holding a file descriptor to a virtio_blk device can
> > still invoke block_device_operations after hot unplug. This leads to a
> > use-after-free accessing vblk->vdev in virtblk_getgeo() when
> > ioctl(HDIO_GETGEO) is invoked:
> >
> > BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
> > IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > PGD 800000003a92f067 PUD 3a930067 PMD 0
> > Oops: 0000 [#1] SMP
> > CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
> > task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000
> > RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246
> > RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000
> > RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40
> > RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301
> > R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680
> > R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000
> > FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000
> > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0
> > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> > Call Trace:
> > [<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk]
> > [<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0
> > [<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20
> > [<ffffffff8d488771>] block_ioctl+0x41/0x50
> > [<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0
> > [<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0
> >
> > A related problem is that virtblk_remove() leaks the vd_index_ida index
> > when something still holds a reference to vblk->disk during hot unplug.
> > This causes virtio-blk device names to be lost (vda, vdb, etc).
> >
> > Fix these issues by protecting vblk->vdev with a mutex and reference
> > counting vblk so the vd_index_ida index can be removed in all cases.
> >
> > Fixes: 48e4043d4529523cbc7fa8dd745bd8e2c45ce1d3
> > ("virtio: add virtio disk geometry feature")
> > Reported-by: Lance Digby <[email protected]>
> > Signed-off-by: Stefan Hajnoczi <[email protected]>
> > ---
> > drivers/block/virtio_blk.c | 87 ++++++++++++++++++++++++++++++++++----
> > 1 file changed, 79 insertions(+), 8 deletions(-)
> >
> > diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> > index 93468b7c6701..6f7f277495f4 100644
> > --- a/drivers/block/virtio_blk.c
> > +++ b/drivers/block/virtio_blk.c
> > @@ -33,6 +33,16 @@ struct virtio_blk_vq {
> > } ____cacheline_aligned_in_smp;
> >
> > struct virtio_blk {
> > + /*
> > + * vdev may be accessed without taking this mutex in blk-mq and
> > + * virtqueue code paths because virtblk_remove() stops them before vdev
> > + * is freed.
> > + *
> > + * Everything else must hold this mutex when accessing vdev and must
> > + * handle the case where vdev is NULL after virtblk_remove() has been
> > + * called.
> > + */
> > + struct mutex vdev_mutex;
>
> The patch LGTM, I'm just worried about cache_type_store() and
> cache_type_show() because IIUC they aren't in blk-mq and virtqueue code
> paths, but they use vdev.
>
> Do we have to take the mutex there too?

No, because del_gendisk() in virtblk_remove() deletes the sysfs
attributes before vblk->vdev is set to NULL. kernfs deactivates the
kernfs nodes so that further read()/write() operations fail with ENODEV
(see fs/kernfs/dir.c and fs/kernfs/file.c).

I have tested that a userspace process with a sysfs attr file open
cannot access the attribute after virtblk_remove().

Stefan


Attachments:
(No filename) (4.17 kB)
signature.asc (499.00 B)
Download all attachments

2020-04-30 10:30:38

by Michael S. Tsirkin

[permalink] [raw]
Subject: Re: [PATCH v3] virtio-blk: handle block_device_operations callbacks after hot unplug

On Thu, Apr 30, 2020 at 11:14:10AM +0100, Stefan Hajnoczi wrote:
> On Thu, Apr 30, 2020 at 10:43:23AM +0200, Stefano Garzarella wrote:
> > On Wed, Apr 29, 2020 at 05:53:45PM +0100, Stefan Hajnoczi wrote:
> > > A userspace process holding a file descriptor to a virtio_blk device can
> > > still invoke block_device_operations after hot unplug. This leads to a
> > > use-after-free accessing vblk->vdev in virtblk_getgeo() when
> > > ioctl(HDIO_GETGEO) is invoked:
> > >
> > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
> > > IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > > PGD 800000003a92f067 PUD 3a930067 PMD 0
> > > Oops: 0000 [#1] SMP
> > > CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1
> > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
> > > task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000
> > > RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > > RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246
> > > RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000
> > > RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40
> > > RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301
> > > R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680
> > > R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000
> > > FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000
> > > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0
> > > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> > > Call Trace:
> > > [<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk]
> > > [<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0
> > > [<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20
> > > [<ffffffff8d488771>] block_ioctl+0x41/0x50
> > > [<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0
> > > [<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0
> > >
> > > A related problem is that virtblk_remove() leaks the vd_index_ida index
> > > when something still holds a reference to vblk->disk during hot unplug.
> > > This causes virtio-blk device names to be lost (vda, vdb, etc).
> > >
> > > Fix these issues by protecting vblk->vdev with a mutex and reference
> > > counting vblk so the vd_index_ida index can be removed in all cases.
> > >
> > > Fixes: 48e4043d4529523cbc7fa8dd745bd8e2c45ce1d3
> > > ("virtio: add virtio disk geometry feature")
> > > Reported-by: Lance Digby <[email protected]>
> > > Signed-off-by: Stefan Hajnoczi <[email protected]>
> > > ---
> > > drivers/block/virtio_blk.c | 87 ++++++++++++++++++++++++++++++++++----
> > > 1 file changed, 79 insertions(+), 8 deletions(-)
> > >
> > > diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> > > index 93468b7c6701..6f7f277495f4 100644
> > > --- a/drivers/block/virtio_blk.c
> > > +++ b/drivers/block/virtio_blk.c
> > > @@ -33,6 +33,16 @@ struct virtio_blk_vq {
> > > } ____cacheline_aligned_in_smp;
> > >
> > > struct virtio_blk {
> > > + /*
> > > + * vdev may be accessed without taking this mutex in blk-mq and
> > > + * virtqueue code paths because virtblk_remove() stops them before vdev
> > > + * is freed.
> > > + *
> > > + * Everything else must hold this mutex when accessing vdev and must
> > > + * handle the case where vdev is NULL after virtblk_remove() has been
> > > + * called.
> > > + */
> > > + struct mutex vdev_mutex;
> >
> > The patch LGTM, I'm just worried about cache_type_store() and
> > cache_type_show() because IIUC they aren't in blk-mq and virtqueue code
> > paths, but they use vdev.
> >
> > Do we have to take the mutex there too?
>
> No, because del_gendisk() in virtblk_remove() deletes the sysfs
> attributes before vblk->vdev is set to NULL. kernfs deactivates the
> kernfs nodes so that further read()/write() operations fail with ENODEV
> (see fs/kernfs/dir.c and fs/kernfs/file.c).
>
> I have tested that a userspace process with a sysfs attr file open
> cannot access the attribute after virtblk_remove().
>
> Stefan

Sounds good, but pls update the comment adding something like
" .. or anything coming from block layer since del_gendisk()
in virtblk_remove deletes the disk before vblk->vdev is set to NULL.
"

--
MST

2020-04-30 10:46:44

by Stefano Garzarella

[permalink] [raw]
Subject: Re: [PATCH v3] virtio-blk: handle block_device_operations callbacks after hot unplug

On Thu, Apr 30, 2020 at 06:28:21AM -0400, Michael S. Tsirkin wrote:
> On Thu, Apr 30, 2020 at 11:14:10AM +0100, Stefan Hajnoczi wrote:
> > On Thu, Apr 30, 2020 at 10:43:23AM +0200, Stefano Garzarella wrote:
> > > On Wed, Apr 29, 2020 at 05:53:45PM +0100, Stefan Hajnoczi wrote:
> > > > A userspace process holding a file descriptor to a virtio_blk device can
> > > > still invoke block_device_operations after hot unplug. This leads to a
> > > > use-after-free accessing vblk->vdev in virtblk_getgeo() when
> > > > ioctl(HDIO_GETGEO) is invoked:
> > > >
> > > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000090
> > > > IP: [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > > > PGD 800000003a92f067 PUD 3a930067 PMD 0
> > > > Oops: 0000 [#1] SMP
> > > > CPU: 0 PID: 1310 Comm: hdio-getgeo Tainted: G OE ------------ 3.10.0-1062.el7.x86_64 #1
> > > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
> > > > task: ffff9be5fbfb8000 ti: ffff9be5fa890000 task.ti: ffff9be5fa890000
> > > > RIP: 0010:[<ffffffffc00e5450>] [<ffffffffc00e5450>] virtio_check_driver_offered_feature+0x10/0x90 [virtio]
> > > > RSP: 0018:ffff9be5fa893dc8 EFLAGS: 00010246
> > > > RAX: ffff9be5fc3f3400 RBX: ffff9be5fa893e30 RCX: 0000000000000000
> > > > RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff9be5fbc10b40
> > > > RBP: ffff9be5fa893dc8 R08: 0000000000000301 R09: 0000000000000301
> > > > R10: 0000000000000000 R11: 0000000000000000 R12: ffff9be5fdc24680
> > > > R13: ffff9be5fbc10b40 R14: ffff9be5fbc10480 R15: 0000000000000000
> > > > FS: 00007f1bfb968740(0000) GS:ffff9be5ffc00000(0000) knlGS:0000000000000000
> > > > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > > CR2: 0000000000000090 CR3: 000000003a894000 CR4: 0000000000360ff0
> > > > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> > > > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> > > > Call Trace:
> > > > [<ffffffffc016ac37>] virtblk_getgeo+0x47/0x110 [virtio_blk]
> > > > [<ffffffff8d3f200d>] ? handle_mm_fault+0x39d/0x9b0
> > > > [<ffffffff8d561265>] blkdev_ioctl+0x1f5/0xa20
> > > > [<ffffffff8d488771>] block_ioctl+0x41/0x50
> > > > [<ffffffff8d45d9e0>] do_vfs_ioctl+0x3a0/0x5a0
> > > > [<ffffffff8d45dc81>] SyS_ioctl+0xa1/0xc0
> > > >
> > > > A related problem is that virtblk_remove() leaks the vd_index_ida index
> > > > when something still holds a reference to vblk->disk during hot unplug.
> > > > This causes virtio-blk device names to be lost (vda, vdb, etc).
> > > >
> > > > Fix these issues by protecting vblk->vdev with a mutex and reference
> > > > counting vblk so the vd_index_ida index can be removed in all cases.
> > > >
> > > > Fixes: 48e4043d4529523cbc7fa8dd745bd8e2c45ce1d3
> > > > ("virtio: add virtio disk geometry feature")
> > > > Reported-by: Lance Digby <[email protected]>
> > > > Signed-off-by: Stefan Hajnoczi <[email protected]>
> > > > ---
> > > > drivers/block/virtio_blk.c | 87 ++++++++++++++++++++++++++++++++++----
> > > > 1 file changed, 79 insertions(+), 8 deletions(-)
> > > >
> > > > diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> > > > index 93468b7c6701..6f7f277495f4 100644
> > > > --- a/drivers/block/virtio_blk.c
> > > > +++ b/drivers/block/virtio_blk.c
> > > > @@ -33,6 +33,16 @@ struct virtio_blk_vq {
> > > > } ____cacheline_aligned_in_smp;
> > > >
> > > > struct virtio_blk {
> > > > + /*
> > > > + * vdev may be accessed without taking this mutex in blk-mq and
> > > > + * virtqueue code paths because virtblk_remove() stops them before vdev
> > > > + * is freed.
> > > > + *
> > > > + * Everything else must hold this mutex when accessing vdev and must
> > > > + * handle the case where vdev is NULL after virtblk_remove() has been
> > > > + * called.
> > > > + */
> > > > + struct mutex vdev_mutex;
> > >
> > > The patch LGTM, I'm just worried about cache_type_store() and
> > > cache_type_show() because IIUC they aren't in blk-mq and virtqueue code
> > > paths, but they use vdev.
> > >
> > > Do we have to take the mutex there too?
> >
> > No, because del_gendisk() in virtblk_remove() deletes the sysfs
> > attributes before vblk->vdev is set to NULL. kernfs deactivates the
> > kernfs nodes so that further read()/write() operations fail with ENODEV
> > (see fs/kernfs/dir.c and fs/kernfs/file.c).

Thanks for the clarification!

> >
> > I have tested that a userspace process with a sysfs attr file open
> > cannot access the attribute after virtblk_remove().

Great!

> >
> > Stefan
>
> Sounds good, but pls update the comment adding something like
> " .. or anything coming from block layer since del_gendisk()
> in virtblk_remove deletes the disk before vblk->vdev is set to NULL.
> "

With the comment fixed:

Reviewed-by: Stefano Garzarella <[email protected]>

Thanks,
Stefano