Removal of virtual block device by "nvm lnvm remove..." undergoing IO
and created by "nvme lnvm create... -t pblk" results in following and
is annoying.
446416.309757] bdi-block not registered
[446416.309773] ------------[ cut here ]------------
[446416.309780] WARNING: CPU: 3 PID: 4319 at fs/fs-writeback.c:2159 __mark_inode_dirty+0x268/0x340
.....
This patch solves this by checking bd_openers for each partition
before removal can continue. Note that this isn't full proof as
device can become busy as soon as it's bd_mutex is unlocked but it
needn't be full proof either. It does work for general case where
device is mounted and removal can be prevented.
Signed-off-by: Rakesh Pandit <[email protected]>
---
drivers/lightnvm/core.c | 42 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 42 insertions(+)
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index bbea2c8..cff91c7 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -369,6 +369,10 @@ static void __nvm_remove_target(struct nvm_target *t)
static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
{
struct nvm_target *t;
+ struct gendisk *tdisk;
+ struct disk_part_iter piter;
+ struct hd_struct *part;
+ int err;
mutex_lock(&dev->mlock);
t = nvm_find_target(dev, remove->tgtname);
@@ -376,10 +380,48 @@ static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
mutex_unlock(&dev->mlock);
return 1;
}
+
+ /*
+ * Lets make sure device is not in use. Note that this isn't full proof
+ * in anyway (as devices can become busy after unlock) but it is useful
+ * for preventing removal of devices which are open and undergoing IO.
+ */
+ tdisk = t->disk;
+ disk_part_iter_init(&piter, tdisk,
+ DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0 |
+ DISK_PITER_INCL_EMPTY_PART0);
+ while ((part = disk_part_iter_next(&piter))) {
+ struct block_device *bdev;
+
+ bdev = bdget(part_devt(part));
+ if (!bdev) {
+ err = -ENOMEM;
+ pr_err("nvm: removal failed, allocating bd failed\n");
+ goto err_out;
+ }
+ mutex_lock(&bdev->bd_mutex);
+ if (bdev->bd_openers) {
+ mutex_unlock(&bdev->bd_mutex);
+ bdput(bdev);
+ err = -EBUSY;
+ pr_err("nvm: removal failed, block device busy\n");
+ goto err_out;
+ }
+ mutex_unlock(&bdev->bd_mutex);
+ bdput(bdev);
+ }
+ disk_part_iter_exit(&piter);
+
__nvm_remove_target(t);
mutex_unlock(&dev->mlock);
return 0;
+err_out:
+ disk_part_iter_exit(&piter);
+ disk_put_part(part);
+ mutex_unlock(&dev->mlock);
+
+ return err;
}
static int nvm_register_map(struct nvm_dev *dev)
--
2.7.4
On 09/07/2017 03:58 PM, Rakesh Pandit wrote:
> Removal of virtual block device by "nvm lnvm remove..." undergoing IO
> and created by "nvme lnvm create... -t pblk" results in following and
> is annoying.
>
> 446416.309757] bdi-block not registered
> [446416.309773] ------------[ cut here ]------------
> [446416.309780] WARNING: CPU: 3 PID: 4319 at fs/fs-writeback.c:2159 __mark_inode_dirty+0x268/0x340
> .....
>
> This patch solves this by checking bd_openers for each partition
> before removal can continue. Note that this isn't full proof as
> device can become busy as soon as it's bd_mutex is unlocked but it
> needn't be full proof either. It does work for general case where
> device is mounted and removal can be prevented.
>
> Signed-off-by: Rakesh Pandit <[email protected]>
> ---
> drivers/lightnvm/core.c | 42 ++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 42 insertions(+)
>
> diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
> index bbea2c8..cff91c7 100644
> --- a/drivers/lightnvm/core.c
> +++ b/drivers/lightnvm/core.c
> @@ -369,6 +369,10 @@ static void __nvm_remove_target(struct nvm_target *t)
> static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
> {
> struct nvm_target *t;
> + struct gendisk *tdisk;
> + struct disk_part_iter piter;
> + struct hd_struct *part;
> + int err;
>
> mutex_lock(&dev->mlock);
> t = nvm_find_target(dev, remove->tgtname);
> @@ -376,10 +380,48 @@ static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
> mutex_unlock(&dev->mlock);
> return 1;
> }
> +
> + /*
> + * Lets make sure device is not in use. Note that this isn't full proof
> + * in anyway (as devices can become busy after unlock) but it is useful
> + * for preventing removal of devices which are open and undergoing IO.
> + */
> + tdisk = t->disk;
> + disk_part_iter_init(&piter, tdisk,
> + DISK_PITER_INCL_EMPTY | DISK_PITER_INCL_PART0 |
> + DISK_PITER_INCL_EMPTY_PART0);
> + while ((part = disk_part_iter_next(&piter))) {
A race condition can occur where disk_part_next tries to pblk (in
block/genhd.c), and it in the meantime has been set to NULL. Leading to
a kernel crash. Is there a better way to do it?
[root@localhost ~]# nvme lnvm remove -n pblk0
[ 5262.338647] BUG: unable to handle kernel NULL pointer dereference at
0000000000000010
[ 5262.340769] IP: disk_part_iter_next+0xd3/0xf0
[ 5262.342312] PGD 233f65067 P4D 233f65067 PUD 22ef94067 PMD 0
[ 5262.344285] Oops: 0000 [#1] SMP
[ 5262.345216] Modules linked in:
[ 5262.346110] CPU: 0 PID: 459 Comm: nvme Not tainted 4.13.0+ #74
[ 5262.347770] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[ 5262.351168] task: ffff9abbf1020f40 task.stack: ffffb3d841864000
[ 5262.352722] RIP: 0010:disk_part_iter_next+0xd3/0xf0
[ 5262.354024] RSP: 0018:ffffb3d841867dd8 EFLAGS: 00010246
[ 5262.355322] RAX: ffff9abbf42be000 RBX: ffff9abbf42be000 RCX:
000000000000000e
[ 5262.356983] RDX: 000000000000000e RSI: ffff9abbf42be000 RDI:
0000000000000000
[ 5262.359217] RBP: ffffb3d841867df0 R08: 0000000000000000 R09:
0000000001513fe0
[ 5262.360972] R10: 00007fffc4b764a0 R11: ffff9abbf1020f40 R12:
ffffb3d841867e08
[ 5262.362732] R13: ffff9abbf63b2800 R14: 0000000040244c23 R15:
ffff9abbf3e2efc0
[ 5262.364540] FS: 00007f185e4bb700(0000) GS:ffff9abbffc00000(0000)
knlGS:0000000000000000
[ 5262.366462] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 5262.367711] CR2: 0000000000000010 CR3: 000000022efcc002 CR4:
00000000003606f0
[ 5262.369742] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[ 5262.371784] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[ 5262.373618] Call Trace:
[ 5262.374163] nvm_ctl_ioctl+0x344/0x590
[ 5262.375828] ? kmem_cache_alloc+0x9b/0x1b0
[ 5262.376906] do_vfs_ioctl+0x9f/0x5d0
[ 5262.378272] ? putname+0x54/0x60
[ 5262.378817] SyS_ioctl+0x79/0x90
[ 5262.379378] entry_SYSCALL_64_fastpath+0x1e/0xa9
[ 5262.380309] RIP: 0033:0x7f185ddc7e47
[ 5262.381043] RSP: 002b:00007fffc4b766c8 EFLAGS: 00000202 ORIG_RAX:
0000000000000010
[ 5262.382735] RAX: ffffffffffffffda RBX: 00007fffc4b76730 RCX:
00007f185ddc7e47
[ 5262.383769] RDX: 00007fffc4b766d0 RSI: 0000000040244c23 RDI:
0000000000000003
[ 5262.384203] RBP: 0000000001513fe0 R08: 0000000000000000 R09:
0000000001513fe0
[ 5262.384640] R10: 00007fffc4b764a0 R11: 0000000000000202 R12:
0000000001514050
[ 5262.385068] R13: 0000000000000003 R14: 00007fffc4b76d98 R15:
0000000000000001
[ 5262.385491] Code: 54 24 10 75 c6 5b 31 c0 41 5c 41 5d 5d c3 48 8d 7b
28 e8 41 32 1c 00 49 89 5c 24 08 45 01 6c 24 10 48 89 d8 5b 41 5c 41 5d
5d c3 <8b> 77 10 41 bd 01 00 00 00 e9 72 ff ff ff 0f 1f 44 00 00 66 2e
[ 5262.386619] RIP: disk_part_iter_next+0xd3/0xf0 RSP: ffffb3d841867dd8
[ 5262.386997] CR2: 0000000000000010
[ 5262.387181] ---[ end trace 4815d3130f7418a9 ]---
Killed
> + struct block_device *bdev;
> +
> + bdev = bdget(part_devt(part));
> + if (!bdev) {
> + err = -ENOMEM;
> + pr_err("nvm: removal failed, allocating bd failed\n");
> + goto err_out;
> + }
> + mutex_lock(&bdev->bd_mutex);
> + if (bdev->bd_openers) {
> + mutex_unlock(&bdev->bd_mutex);
> + bdput(bdev);
> + err = -EBUSY;
> + pr_err("nvm: removal failed, block device busy\n");
> + goto err_out;
> + }
> + mutex_unlock(&bdev->bd_mutex);
> + bdput(bdev);
> + }
> + disk_part_iter_exit(&piter);
> +
> __nvm_remove_target(t);
> mutex_unlock(&dev->mlock);
>
> return 0;
> +err_out:
> + disk_part_iter_exit(&piter);
> + disk_put_part(part);
> + mutex_unlock(&dev->mlock);
> +
> + return err;
> }
>
> static int nvm_register_map(struct nvm_dev *dev)
>
On Fri, Sep 08, 2017 at 12:42:47PM +0200, Matias Bj?rling wrote:
> On 09/07/2017 03:58 PM, Rakesh Pandit wrote:
> > Removal of virtual block device by "nvm lnvm remove..." undergoing IO
> > and created by "nvme lnvm create... -t pblk" results in following and
> > is annoying.
> >
> > 446416.309757] bdi-block not registered
> > [446416.309773] ------------[ cut here ]------------
> > [446416.309780] WARNING: CPU: 3 PID: 4319 at fs/fs-writeback.c:2159 __mark_inode_dirty+0x268/0x340
> > .....
> >
> > This patch solves this by checking bd_openers for each partition
> > before removal can continue. Note that this isn't full proof as
> > device can become busy as soon as it's bd_mutex is unlocked but it
> > needn't be full proof either. It does work for general case where
> > device is mounted and removal can be prevented.
> >
> > Signed-off-by: Rakesh Pandit <[email protected]>
[..]
> > + while ((part = disk_part_iter_next(&piter))) {
>
> A race condition can occur where disk_part_next tries to pblk (in
> block/genhd.c), and it in the meantime has been set to NULL. Leading to a
> kernel crash. Is there a better way to do it?
>
> [root@localhost ~]# nvme lnvm remove -n pblk0
> [ 5262.338647] BUG: unable to handle kernel NULL pointer dereference at
> 0000000000000010
> [ 5262.340769] IP: disk_part_iter_next+0xd3/0xf0
Thanks, indeed partition can go away from our feet if we don't lock
the whole thing from changing and not just individual partition locks.
I have given it another go which should avoid taking mutex locks on
bdev. Posted V2.