diff options
| -rw-r--r-- | Documentation/filesystems/porting.rst | 96 | ||||
| -rw-r--r-- | fs/aio.c | 2 | ||||
| -rw-r--r-- | fs/fs-writeback.c | 11 | ||||
| -rw-r--r-- | fs/libfs.c | 1 | ||||
| -rw-r--r-- | fs/ntfs3/super.c | 1 | ||||
| -rw-r--r-- | fs/overlayfs/copy_up.c | 2 | ||||
| -rw-r--r-- | fs/overlayfs/file.c | 6 | ||||
| -rw-r--r-- | fs/pipe.c | 1 | ||||
| -rw-r--r-- | fs/reiserfs/reiserfs.h | 6 |
9 files changed, 117 insertions, 9 deletions
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index deac4e973ddc..4d05b9862451 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -949,3 +949,99 @@ mmap_lock held. All in-tree users have been audited and do not seem to depend on the mmap_lock being held, but out of tree users should verify for themselves. If they do need it, they can return VM_FAULT_RETRY to be called with the mmap_lock held. + +--- + +**mandatory** + +The order of opening block devices and matching or creating superblocks has +changed. + +The old logic opened block devices first and then tried to find a +suitable superblock to reuse based on the block device pointer. + +The new logic tries to find a suitable superblock first based on the device +number, and opening the block device afterwards. + +Since opening block devices cannot happen under s_umount because of lock +ordering requirements s_umount is now dropped while opening block devices and +reacquired before calling fill_super(). + +In the old logic concurrent mounters would find the superblock on the list of +superblocks for the filesystem type. Since the first opener of the block device +would hold s_umount they would wait until the superblock became either born or +was discarded due to initialization failure. + +Since the new logic drops s_umount concurrent mounters could grab s_umount and +would spin. Instead they are now made to wait using an explicit wait-wake +mechanism without having to hold s_umount. + +--- + +**mandatory** + +The holder of a block device is now the superblock. + +The holder of a block device used to be the file_system_type which wasn't +particularly useful. It wasn't possible to go from block device to owning +superblock without matching on the device pointer stored in the superblock. +This mechanism would only work for a single device so the block layer couldn't +find the owning superblock of any additional devices. + +In the old mechanism reusing or creating a superblock for a racing mount(2) and +umount(2) relied on the file_system_type as the holder. This was severly +underdocumented however: + +(1) Any concurrent mounter that managed to grab an active reference on an + existing superblock was made to wait until the superblock either became + ready or until the superblock was removed from the list of superblocks of + the filesystem type. If the superblock is ready the caller would simple + reuse it. + +(2) If the mounter came after deactivate_locked_super() but before + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would wait until the superblock was shutdown, + reuse the block device and allocate a new superblock. + +(3) If the mounter came after deactivate_locked_super() and after + the superblock had been removed from the list of superblocks of the + filesystem type the mounter would reuse the block device and allocate a new + superblock (the bd_holder point may still be set to the filesystem type). + +Because the holder of the block device was the file_system_type any concurrent +mounter could open the block devices of any superblock of the same +file_system_type without risking seeing EBUSY because the block device was +still in use by another superblock. + +Making the superblock the owner of the block device changes this as the holder +is now a unique superblock and thus block devices associated with it cannot be +reused by concurrent mounters. So a concurrent mounter in (2) could suddenly +see EBUSY when trying to open a block device whose holder was a different +superblock. + +The new logic thus waits until the superblock and the devices are shutdown in +->kill_sb(). Removal of the superblock from the list of superblocks of the +filesystem type is now moved to a later point when the devices are closed: + +(1) Any concurrent mounter managing to grab an active reference on an existing + superblock is made to wait until the superblock is either ready or until + the superblock and all devices are shutdown in ->kill_sb(). If the + superblock is ready the caller will simply reuse it. + +(2) If the mounter comes after deactivate_locked_super() but before + the superblock has been removed from the list of superblocks of the + filesystem type the mounter is made to wait until the superblock and the + devices are shut down in ->kill_sb() and the superblock is removed from the + list of superblocks of the filesystem type. The mounter will allocate a new + superblock and grab ownership of the block device (the bd_holder pointer of + the block device will be set to the newly allocated superblock). + +(3) This case is now collapsed into (2) as the superblock is left on the list + of superblocks of the filesystem type until all devices are shutdown in + ->kill_sb(). In other words, if the superblock isn't on the list of + superblock of the filesystem type anymore then it has given up ownership of + all associated block devices (the bd_holder pointer is NULL). + +As this is a VFS level change it has no practical consequences for filesystems +other than that all of them must use one of the provided kill_litter_super(), +kill_anon_super(), or kill_block_super() helpers. @@ -80,7 +80,7 @@ struct aio_ring { struct kioctx_table { struct rcu_head rcu; unsigned nr; - struct kioctx __rcu *table[]; + struct kioctx __rcu *table[] __counted_by(nr); }; struct kioctx_cpu { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 969ce991b0b0..c1af01b2c42d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1535,10 +1535,15 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, if (wbc->pages_skipped) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * Writeback is not making progress due to locked buffers. + * Skip this inode for now. Although having skipped pages + * is odd for clean inodes, it can happen for some + * filesystems so handle that gracefully. */ - redirty_tail_locked(inode, wb); + if (inode->i_state & I_DIRTY_ALL) + redirty_tail_locked(inode, wb); + else + inode_cgwb_move_to_attached(inode, wb); return; } diff --git a/fs/libfs.c b/fs/libfs.c index a4eb12757886..37f2d34ee090 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1903,6 +1903,7 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ + iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index cfec5e0c7f66..5661a363005e 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1562,6 +1562,7 @@ load_root: put_inode_out: iput(inode); out: + ntfs3_put_sbi(sbi); kfree(boot2); return err; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index d1761ec5866a..ada3fcc9c6d5 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -337,7 +337,7 @@ static int ovl_set_timestamps(struct ovl_fs *ofs, struct dentry *upperdentry, { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4193633c4c7a..693971d20280 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -391,6 +391,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); + /* + * Overlayfs doesn't support deferred completions, don't copy + * this property in case it is set by the issuer. + */ + ifl &= ~IOCB_DIO_CALLER_COMP; + old_cred = ovl_override_creds(file_inode(file)->i_sb); if (is_sync_kiocb(iocb)) { file_start_write(real.file); diff --git a/fs/pipe.c b/fs/pipe.c index 6c1a9b1db907..139190165a1c 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -537,7 +537,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) break; } ret += copied; - buf->offset = 0; buf->len = copied; if (!iov_iter_count(from)) diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index b81749492ef9..7d12b8c5b2fa 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -2699,7 +2699,7 @@ struct reiserfs_iget_args { #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12) #define journal_trans_half(blocksize) \ - ((blocksize - sizeof (struct reiserfs_journal_desc) + sizeof (__u32) - 12) / sizeof (__u32)) + ((blocksize - sizeof(struct reiserfs_journal_desc) - 12) / sizeof(__u32)) /* journal.c see journal.c for all the comments here */ @@ -2711,7 +2711,7 @@ struct reiserfs_journal_desc { __le32 j_len; __le32 j_mount_id; /* mount id of this trans */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_desc_trans_id(d) le32_to_cpu((d)->j_trans_id) @@ -2726,7 +2726,7 @@ struct reiserfs_journal_desc { struct reiserfs_journal_commit { __le32 j_trans_id; /* must match j_trans_id from the desc block */ __le32 j_len; /* ditto */ - __le32 j_realblock[1]; /* real locations for each block */ + __le32 j_realblock[]; /* real locations for each block */ }; #define get_commit_trans_id(c) le32_to_cpu((c)->j_trans_id) |