linux/fs/xfs/xfs_icache.h

126 lines
3.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef XFS_SYNC_H
#define XFS_SYNC_H 1
struct xfs_mount;
struct xfs_perag;
struct xfs_eofblocks {
__u32 eof_flags;
kuid_t eof_uid;
kgid_t eof_gid;
prid_t eof_prid;
__u64 eof_min_file_size;
};
#define SYNC_WAIT 0x0001 /* wait for i/o to complete */
#define SYNC_TRYLOCK 0x0002 /* only try to lock inodes */
/*
* tags for inode radix tree
*/
#define XFS_ICI_NO_TAG (-1) /* special flag for an untagged lookup
in xfs_inode_ag_iterator */
#define XFS_ICI_RECLAIM_TAG 0 /* inode is to be reclaimed */
#define XFS_ICI_EOFBLOCKS_TAG 1 /* inode has blocks beyond EOF */
#define XFS_ICI_COWBLOCKS_TAG 2 /* inode can have cow blocks to gc */
/*
* Flags for xfs_iget()
*/
#define XFS_IGET_CREATE 0x1
#define XFS_IGET_UNTRUSTED 0x2
#define XFS_IGET_DONTCACHE 0x4
#define XFS_IGET_INCORE 0x8 /* don't read from disk or reinit */
/*
* flags for AG inode iterator
*/
#define XFS_AGITER_INEW_WAIT 0x1 /* wait on new inodes */
int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
uint flags, uint lock_flags, xfs_inode_t **ipp);
xfs: recovery of swap extents operations for CRC filesystems This is the recovery side of the btree block owner change operation performed by swapext on CRC enabled filesystems. We detect that an owner change is needed by the flag that has been placed on the inode log format flag field. Because the inode recovery is being replayed after the buffers that make up the BMBT in the given checkpoint, we can walk all the buffers and directly modify them when we see the flag set on an inode. Because the inode can be relogged and hence present in multiple chekpoints with the "change owner" flag set, we could do multiple passes across the inode to do this change. While this isn't optimal, we can't directly ignore the flag as there may be multiple independent swap extent operations being replayed on the same inode in different checkpoints so we can't ignore them. Further, because the owner change operation uses ordered buffers, we might have buffers that are newer on disk than the current checkpoint and so already have the owner changed in them. Hence we cannot just peek at a buffer in the tree and check that it has the correct owner and assume that the change was completed. So, for the moment just brute force the owner change every time we see an inode with the flag set. Note that we have to be careful here because the owner of the buffers may point to either the old owner or the new owner. Currently the verifier can't verify the owner directly, so there is no failure case here right now. If we verify the owner exactly in future, then we'll have to take this into account. This was tested in terms of normal operation via xfstests - all of the fsr tests now pass without failure. however, we really need to modify xfs/227 to stress v3 inodes correctly to ensure we fully cover this case for v5 filesystems. In terms of recovery testing, I used a hacked version of xfs_fsr that held the temp inode open for a few seconds before exiting so that the filesystem could be shut down with an open owner change recovery flags set on at least the temp inode. fsr leaves the temp inode unlinked and in btree format, so this was necessary for the owner change to be reliably replayed. logprint confirmed the tmp inode in the log had the correct flag set: INO: cnt:3 total:3 a:0x69e9e0 len:56 a:0x69ea20 len:176 a:0x69eae0 len:88 INODE: #regs:3 ino:0x44 flags:0x209 dsize:88 ^^^^^ 0x200 is set, indicating a data fork owner change needed to be replayed on inode 0x44. A printk in the revoery code confirmed that the inode change was recovered: XFS (vdc): Mounting Filesystem XFS (vdc): Starting recovery (logdev: internal) recovering owner change ino 0x44 XFS (vdc): Version 5 superblock detected. This kernel L support enabled! Use of these features in this kernel is at your own risk! XFS (vdc): Ending recovery (logdev: internal) The script used to test this was: $ cat ./recovery-fsr.sh #!/bin/bash dev=/dev/vdc mntpt=/mnt/scratch testfile=$mntpt/testfile umount $mntpt mkfs.xfs -f -m crc=1 $dev mount $dev $mntpt chmod 777 $mntpt for i in `seq 10000 -1 0`; do xfs_io -f -d -c "pwrite $(($i * 4096)) 4096" $testfile > /dev/null 2>&1 done xfs_bmap -vp $testfile |head -20 xfs_fsr -d -v $testfile & sleep 10 /home/dave/src/xfstests-dev/src/godown -f $mntpt wait umount $mntpt xfs_logprint -t $dev |tail -20 time mount $dev $mntpt xfs_bmap -vp $testfile umount $mntpt $ Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-30 00:23:45 +00:00
/* recovery needs direct inode allocation capability */
struct xfs_inode * xfs_inode_alloc(struct xfs_mount *mp, xfs_ino_t ino);
void xfs_inode_free(struct xfs_inode *ip);
void xfs_reclaim_worker(struct work_struct *work);
int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
int xfs_reclaim_inodes_count(struct xfs_mount *mp);
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 00:17:57 +00:00
long xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip);
void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip);
int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *);
xfs: run an eofblocks scan on ENOSPC/EDQUOT From: Brian Foster <bfoster@redhat.com> Speculative preallocation and and the associated throttling metrics assume we're working with large files on large filesystems. Users have reported inefficiencies in these mechanisms when we happen to be dealing with large files on smaller filesystems. This can occur because while prealloc throttling is aggressive under low free space conditions, it is not active until we reach 5% free space or less. For example, a 40GB filesystem has enough space for several files large enough to have multi-GB preallocations at any given time. If those files are slow growing, they might reserve preallocation for long periods of time as well as avoid the background scanner due to frequent modification. If a new file is written under these conditions, said file has no access to this already reserved space and premature ENOSPC is imminent. To handle this scenario, modify the buffered write ENOSPC handling and retry sequence to invoke an eofblocks scan. In the smaller filesystem scenario, the eofblocks scan resets the usage of preallocation such that when the 5% free space threshold is met, throttling effectively takes over to provide fair and efficient preallocation until legitimate ENOSPC. The eofblocks scan is selective based on the nature of the failure. For example, an EDQUOT failure in a particular quota will use a filtered scan for that quota. Because we don't know which quota might have caused an allocation failure at any given time, we include each applicable quota determined to be under low free space conditions in the scan. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-07-24 09:49:28 +00:00
int xfs_inode_free_quota_eofblocks(struct xfs_inode *ip);
void xfs_eofblocks_worker(struct work_struct *);
xfs: cancel eofblocks background trimming on remount read-only The filesystem quiesce sequence performs the operations necessary to drain all background work, push pending transactions through the log infrastructure and wait on I/O resulting from the final AIL push. We have had reports of remount,ro hangs in xfs_log_quiesce() -> xfs_wait_buftarg(), however, and some instrumentation code to detect transaction commits at this point in the quiesce sequence has inculpated the eofblocks background scanner as a cause. While higher level remount code generally prevents user modifications by the time the filesystem has made it to xfs_log_quiesce(), the background scanner may still be alive and can perform pending work at any time. If this occurs between the xfs_log_force() and xfs_wait_buftarg() calls within xfs_log_quiesce(), this can lead to an indefinite lockup in xfs_wait_buftarg(). To prevent this problem, cancel the background eofblocks scan worker during the remount read-only quiesce sequence. This suspends background trimming when a filesystem is remounted read-only. This is only done in the remount path because the freeze codepath has already locked out new transactions by the time the filesystem attempts to quiesce (and thus waiting on an active work item could deadlock). Kick the eofblocks worker to pick up where it left off once an fs is remounted back to read-write. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-06-21 01:53:28 +00:00
void xfs_queue_eofblocks(struct xfs_mount *);
void xfs_inode_set_cowblocks_tag(struct xfs_inode *ip);
void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip);
int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *);
int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip);
void xfs_cowblocks_worker(struct work_struct *);
void xfs_queue_cowblocks(struct xfs_mount *);
int xfs_inode_ag_iterator(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args);
int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args, int iter_flags);
int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args, int tag);
static inline int
xfs_fs_eofblocks_from_user(
struct xfs_fs_eofblocks *src,
struct xfs_eofblocks *dst)
{
if (src->eof_version != XFS_EOFBLOCKS_VERSION)
return -EINVAL;
if (src->eof_flags & ~XFS_EOF_FLAGS_VALID)
return -EINVAL;
if (memchr_inv(&src->pad32, 0, sizeof(src->pad32)) ||
memchr_inv(src->pad64, 0, sizeof(src->pad64)))
return -EINVAL;
dst->eof_flags = src->eof_flags;
dst->eof_prid = src->eof_prid;
dst->eof_min_file_size = src->eof_min_file_size;
dst->eof_uid = INVALID_UID;
if (src->eof_flags & XFS_EOF_FLAGS_UID) {
dst->eof_uid = make_kuid(current_user_ns(), src->eof_uid);
if (!uid_valid(dst->eof_uid))
return -EINVAL;
}
dst->eof_gid = INVALID_GID;
if (src->eof_flags & XFS_EOF_FLAGS_GID) {
dst->eof_gid = make_kgid(current_user_ns(), src->eof_gid);
if (!gid_valid(dst->eof_gid))
return -EINVAL;
}
return 0;
}
int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_ino_t ino, bool *inuse);
void xfs_stop_block_reaping(struct xfs_mount *mp);
void xfs_start_block_reaping(struct xfs_mount *mp);
#endif