Hello Jan,
tried on 3.7-rc4, works great! thanks!
will You submit as-is, or do You plan any further changes?
do You plan to backport for stable kernels? I can try it and send for review
if You want (although we'll have to wait till it's upstream anyways)
cheers
nik
On Wed, Nov 07, 2012 at 07:51:37PM +0100, Jan Kara wrote:
> On Thu 01-11-12 23:50:53, Jan Kara wrote:
> > On Thu 01-11-12 15:23:25, Nikola Ciprich wrote:
> > > Nov 1 14:23:25 vmnci22 [ 1075.178123] SysRq : Show Blocked State
> > > Nov 1 14:23:25 vmnci22 [ 1075.180555] task PC stack pid father
> > > Nov 1 14:23:25 vmnci22 [ 1075.180592] fsfreeze D 0000000000000000 0 4215 4195 0x00000000
> > > Nov 1 14:23:25 vmnci22 [ 1075.180599] ffff8800090b9b28 0000000000000046 0000000000000000 ffffffff00000000
> > > Nov 1 14:23:25 vmnci22 [ 1075.180606] 0000000000013780 ffff8800090b9fd8 ffff88000f716170 ffff88000f715e80
> > > Nov 1 14:23:25 vmnci22 [ 1075.180612] ffff88000f715dc0 ffffffff81566080 ffff88000f716170 000000010002f405
> > > Nov 1 14:23:25 vmnci22 [ 1075.180619] Call Trace:
> > > Nov 1 14:23:25 vmnci22 [ 1075.180693] [<ffffffff810e2dbb>] __generic_file_aio_write+0xbb/0x420
> > > Nov 1 14:23:25 vmnci22 [ 1075.180729] [<ffffffff81079290>] ? autoremove_wake_function+0x0/0x40
> > > Nov 1 14:23:25 vmnci22 [ 1075.180736] [<ffffffff810e317f>] generic_file_aio_write+0x5f/0xc0
> > Thanks. So the system isn't really deadlocked. It's just that fsfreeze
> > command hangs, isn't it? OK, I understand that it's kind of incovenient
> > situation because every command will hang like this when the filesystem is
> > frozen.
> >
> > Now I only have to come up with a way to improve this... It isn't quite
> > simple - to properly protect against freezing be have to communicate down
> > into generic_file_aio_write() that we want to bail out if filesystem is
> > frozen instead of waiting.
> OK, can you test attached patch?
>
> Honza
>
> --
> Jan Kara <jack@xxxxxxx>
> SUSE Labs, CR
> From 1cc937c5a850b2f9f0c2a83fdf757911602db198 Mon Sep 17 00:00:00 2001
> From: Jan Kara <jack@xxxxxxx>
> Date: Wed, 7 Nov 2012 19:26:45 +0100
> Subject: [PATCH] fs: Fix hang with BSD accounting on frozen filesystem
>
> When BSD process accounting is enabled and logs information to a filesystem
> which gets frozen, system easily becomes unusable because each attempt to
> account process information blocks. Thus e.g. every task gets blocked in exit.
>
> It seems better to drop accounting information (which can already happen when
> filesystem is running out of space) instead of locking system up. This is
> implemented using a special flag FMODE_NO_FREEZE_WAIT in file->f_mode of a
> file to which accounting information is written.
>
> Signed-off-by: Jan Kara <jack@xxxxxxx>
> ---
> fs/btrfs/file.c | 3 ++-
> fs/cifs/file.c | 3 ++-
> fs/fuse/file.c | 3 ++-
> fs/ntfs/file.c | 3 ++-
> fs/ocfs2/file.c | 3 ++-
> fs/open.c | 2 +-
> fs/xfs/xfs_file.c | 3 ++-
> include/linux/fs.h | 14 ++++++++++++++
> kernel/acct.c | 1 +
> mm/filemap.c | 3 ++-
> 10 files changed, 30 insertions(+), 8 deletions(-)
>
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index 9ab1bed..6eb2e30 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -1411,7 +1411,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
> ssize_t err = 0;
> size_t count, ocount;
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
>
> mutex_lock(&inode->i_mutex);
>
> diff --git a/fs/cifs/file.c b/fs/cifs/file.c
> index edb25b4..1629e47 100644
> --- a/fs/cifs/file.c
> +++ b/fs/cifs/file.c
> @@ -2448,7 +2448,8 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
>
> BUG_ON(iocb->ki_pos != pos);
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
>
> /*
> * We need to hold the sem to be sure nobody modifies lock list
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 78d2837..641df9e 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -947,7 +947,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
> return err;
>
> count = ocount;
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
> mutex_lock(&inode->i_mutex);
>
> /* We can write back this queue in page reclaim */
> diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
> index 1ecf464..028b349 100644
> --- a/fs/ntfs/file.c
> +++ b/fs/ntfs/file.c
> @@ -2118,7 +2118,8 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
>
> BUG_ON(iocb->ki_pos != pos);
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
> mutex_lock(&inode->i_mutex);
> ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
> mutex_unlock(&inode->i_mutex);
> diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
> index 5a4ee77..93ef34d 100644
> --- a/fs/ocfs2/file.c
> +++ b/fs/ocfs2/file.c
> @@ -2265,7 +2265,8 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
> if (iocb->ki_left == 0)
> return 0;
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
>
> appending = file->f_flags & O_APPEND ? 1 : 0;
> direct_io = file->f_flags & O_DIRECT ? 1 : 0;
> diff --git a/fs/open.c b/fs/open.c
> index 59071f5..42bd875 100644
> --- a/fs/open.c
> +++ b/fs/open.c
> @@ -808,7 +808,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
> op->mode = 0;
>
> /* Must never be set by userspace */
> - flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
> + flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC & ~FMODE_NO_FREEZE_WAIT;
>
> /*
> * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index aa473fa..7d8af61 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -771,7 +771,8 @@ xfs_file_aio_write(
> if (ocount == 0)
> return 0;
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
>
> if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
> ret = -EIO;
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index b33cfc9..c040a6c 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -123,6 +123,9 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
> /* File was opened by fanotify and shouldn't generate fanotify events */
> #define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
>
> +/* Write to file should fail on frozen fs rather than block */
> +#define FMODE_NO_FREEZE_WAIT ((__force fmode_t)0x2000000)
> +
> /*
> * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
> * that indicates that they should check the contents of the iovec are
> @@ -1401,6 +1404,17 @@ static inline int sb_start_write_trylock(struct super_block *sb)
> return __sb_start_write(sb, SB_FREEZE_WRITE, false);
> }
>
> +/*
> + * We use trylock semantics if write originates in kernel and normal lock
> + * semantics otherwise. This is a hack but solves problems with deadlocking
> + * of e.g. psacct when filesystem is frozen.
> + */
> +static inline int sb_start_file_write(struct file *file)
> +{
> + return __sb_start_write(file->f_mapping->host->i_sb, SB_FREEZE_WRITE,
> + !(file->f_mode & FMODE_NO_FREEZE_WAIT));
> +}
> +
> /**
> * sb_start_pagefault - get write access to a superblock from a page fault
> * @sb: the super we write to
> diff --git a/kernel/acct.c b/kernel/acct.c
> index 051e071..0b5f231 100644
> --- a/kernel/acct.c
> +++ b/kernel/acct.c
> @@ -183,6 +183,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
> acct->needcheck = jiffies + ACCT_TIMEOUT*HZ;
> acct->active = 1;
> list_add(&acct->list, &acct_list);
> + file->f_mode |= FMODE_NO_FREEZE_WAIT;
> }
> if (old_acct) {
> mnt_unpin(old_acct->f_path.mnt);
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 83efee7..3b2812b 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -2527,7 +2527,8 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
>
> BUG_ON(iocb->ki_pos != pos);
>
> - sb_start_write(inode->i_sb);
> + if (!sb_start_file_write(file))
> + return -EAGAIN;
> mutex_lock(&inode->i_mutex);
> ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
> mutex_unlock(&inode->i_mutex);
> --
> 1.7.1
>
--
-------------------------------------
Ing. Nikola CIPRICH
LinuxBox.cz, s.r.o.
28. rijna 168, 709 00 Ostrava
tel.: +420 591 166 214
fax: +420 596 621 273
mobil: +420 777 093 799
www.linuxbox.cz
mobil servis: +420 737 238 656
email servis: servis@xxxxxxxxxxx
-------------------------------------
Attachment:
pgpAFbwPsI7wC.pgp
Description: PGP signature
