xfs_inode.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include <linux/iversion.h>

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_attr.h"
#include "xfs_bit.h"
#include "xfs_trans_space.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_iunlink_item.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
#include "xfs_ag.h"
#include "xfs_log_priv.h"
#include "xfs_health.h"
#include "xfs_pnfs.h"
#include "xfs_parent.h"
#include "xfs_xattr.h"
#include "xfs_inode_util.h"

struct kmem_cache *xfs_inode_cache;

/*
 * These two are wrapper routines around the xfs_ilock() routine used to
 * centralize some grungy code.  They are used in places that wish to lock the
 * inode solely for reading the extents.  The reason these places can't just
 * call xfs_ilock(ip, XFS_ILOCK_SHARED) is that the inode lock also guards to
 * bringing in of the extents from disk for a file in b-tree format.  If the
 * inode is in b-tree format, then we need to lock the inode exclusively until
 * the extents are read in.  Locking it exclusively all the time would limit
 * our parallelism unnecessarily, though.  What we do instead is check to see
 * if the extents have been read in yet, and only lock the inode exclusively
 * if they have not.
 *
 * The functions return a value which should be given to the corresponding
 * xfs_iunlock() call.
 */
uint
xfs_ilock_data_map_shared(
	struct xfs_inode	*ip)
{ … }

uint
xfs_ilock_attr_map_shared(
	struct xfs_inode	*ip)
{ … }

/*
 * You can't set both SHARED and EXCL for the same lock,
 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_MMAPLOCK_SHARED,
 * XFS_MMAPLOCK_EXCL, XFS_ILOCK_SHARED, XFS_ILOCK_EXCL are valid values
 * to set in lock_flags.
 */
static inline void
xfs_lock_flags_assert(
	uint		lock_flags)
{ … }

/*
 * In addition to i_rwsem in the VFS inode, the xfs inode contains 2
 * multi-reader locks: invalidate_lock and the i_lock.  This routine allows
 * various combinations of the locks to be obtained.
 *
 * The 3 locks should always be ordered so that the IO lock is obtained first,
 * the mmap lock second and the ilock last in order to prevent deadlock.
 *
 * Basic locking order:
 *
 * i_rwsem -> invalidate_lock -> page_lock -> i_ilock
 *
 * mmap_lock locking order:
 *
 * i_rwsem -> page lock -> mmap_lock
 * mmap_lock -> invalidate_lock -> page_lock
 *
 * The difference in mmap_lock locking order mean that we cannot hold the
 * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths
 * can fault in pages during copy in/out (for buffered IO) or require the
 * mmap_lock in get_user_pages() to map the user pages into the kernel address
 * space for direct IO. Similarly the i_rwsem cannot be taken inside a page
 * fault because page faults already hold the mmap_lock.
 *
 * Hence to serialise fully against both syscall and mmap based IO, we need to
 * take both the i_rwsem and the invalidate_lock. These locks should *only* be
 * both taken in places where we need to invalidate the page cache in a race
 * free manner (e.g. truncate, hole punch and other extent manipulation
 * functions).
 */
void
xfs_ilock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{ … }

/*
 * This is just like xfs_ilock(), except that the caller
 * is guaranteed not to sleep.  It returns 1 if it gets
 * the requested locks and 0 otherwise.  If the IO lock is
 * obtained but the inode lock cannot be, then the IO lock
 * is dropped before returning.
 *
 * ip -- the inode being locked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be locked.  See the comment for xfs_ilock() for a list
 *	 of valid values.
 */
int
xfs_ilock_nowait(
	xfs_inode_t		*ip,
	uint			lock_flags)
{ … }

/*
 * xfs_iunlock() is used to drop the inode locks acquired with
 * xfs_ilock() and xfs_ilock_nowait().  The caller must pass
 * in the flags given to xfs_ilock() or xfs_ilock_nowait() so
 * that we know which locks to drop.
 *
 * ip -- the inode being unlocked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be unlocked.  See the comment for xfs_ilock() for a list
 *	 of valid values for this parameter.
 *
 */
void
xfs_iunlock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{ … }

/*
 * give up write locks.  the i/o lock cannot be held nested
 * if it is being demoted.
 */
void
xfs_ilock_demote(
	xfs_inode_t		*ip,
	uint			lock_flags)
{ … }

void
xfs_assert_ilocked(
	struct xfs_inode	*ip,
	uint			lock_flags)
{ … }

/*
 * xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when
 * DEBUG or XFS_WARN is set. And MAX_LOCKDEP_SUBCLASSES is then only defined
 * when CONFIG_LOCKDEP is set. Hence the complex define below to avoid build
 * errors and warnings.
 */
#if (defined(DEBUG) || defined(XFS_WARN)) && defined(CONFIG_LOCKDEP)
static bool
xfs_lockdep_subclass_ok(
	int subclass)
{ … }
#else
#define xfs_lockdep_subclass_ok …
#endif

/*
 * Bump the subclass so xfs_lock_inodes() acquires each lock with a different
 * value. This can be called for any type of inode lock combination, including
 * parent locking. Care must be taken to ensure we don't overrun the subclass
 * storage fields in the class mask we build.
 */
static inline uint
xfs_lock_inumorder(
	uint	lock_mode,
	uint	subclass)
{ … }

/*
 * The following routine will lock n inodes in exclusive mode.  We assume the
 * caller calls us with the inodes in i_ino order.
 *
 * We need to detect deadlock where an inode that we lock is in the AIL and we
 * start waiting for another inode that is locked by a thread in a long running
 * transaction (such as truncate). This can result in deadlock since the long
 * running trans might need to wait for the inode we just locked in order to
 * push the tail and free space in the log.
 *
 * xfs_lock_inodes() can only be used to lock one type of lock at a time -
 * the iolock, the mmaplock or the ilock, but not more than one at a time. If we
 * lock more than one at a time, lockdep will report false positives saying we
 * have violated locking orders.
 */
void
xfs_lock_inodes(
	struct xfs_inode	**ips,
	int			inodes,
	uint			lock_mode)
{ … }

/*
 * xfs_lock_two_inodes() can only be used to lock ilock. The iolock and
 * mmaplock must be double-locked separately since we use i_rwsem and
 * invalidate_lock for that. We now support taking one lock EXCL and the
 * other SHARED.
 */
void
xfs_lock_two_inodes(
	struct xfs_inode	*ip0,
	uint			ip0_mode,
	struct xfs_inode	*ip1,
	uint			ip1_mode)
{ … }

/*
 * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
 * is allowed, otherwise it has to be an exact match. If a CI match is found,
 * ci_name->name will point to a the actual name (caller must free) or
 * will be set to NULL if an exact match is found.
 */
int
xfs_lookup(
	struct xfs_inode	*dp,
	const struct xfs_name	*name,
	struct xfs_inode	**ipp,
	struct xfs_name		*ci_name)
{ … }

/*
 * Initialise a newly allocated inode and return the in-core inode to the
 * caller locked exclusively.
 *
 * Caller is responsible for unlocking the inode manually upon return
 */
int
xfs_icreate(
	struct xfs_trans	*tp,
	xfs_ino_t		ino,
	const struct xfs_icreate_args *args,
	struct xfs_inode	**ipp)
{ … }

/* Return dquots for the ids that will be assigned to a new file. */
int
xfs_icreate_dqalloc(
	const struct xfs_icreate_args	*args,
	struct xfs_dquot		**udqpp,
	struct xfs_dquot		**gdqpp,
	struct xfs_dquot		**pdqpp)
{ … }

int
xfs_create(
	const struct xfs_icreate_args *args,
	struct xfs_name		*name,
	struct xfs_inode	**ipp)
{ … }

int
xfs_create_tmpfile(
	const struct xfs_icreate_args *args,
	struct xfs_inode	**ipp)
{ … }

int
xfs_link(
	struct xfs_inode	*tdp,
	struct xfs_inode	*sip,
	struct xfs_name		*target_name)
{ … }

/* Clear the reflink flag and the cowblocks tag if possible. */
static void
xfs_itruncate_clear_reflink_flags(
	struct xfs_inode	*ip)
{ … }

/*
 * Free up the underlying blocks past new_size.  The new size must be smaller
 * than the current size.  This routine can be used both for the attribute and
 * data fork, and does not modify the inode size, which is left to the caller.
 *
 * The transaction passed to this routine must have made a permanent log
 * reservation of at least XFS_ITRUNCATE_LOG_RES.  This routine may commit the
 * given transaction and start new ones, so make sure everything involved in
 * the transaction is tidy before calling here.  Some transaction will be
 * returned to the caller to be committed.  The incoming transaction must
 * already include the inode, and both inode locks must be held exclusively.
 * The inode must also be "held" within the transaction.  On return the inode
 * will be "held" within the returned transaction.  This routine does NOT
 * require any disk space to be reserved for it within the transaction.
 *
 * If we get an error, we must return with the inode locked and linked into the
 * current transaction. This keeps things simple for the higher level code,
 * because it always knows that the inode is locked and held in the transaction
 * that returns to it whether errors occur or not.  We don't mark the inode
 * dirty on error so that transactions can be easily aborted if possible.
 */
int
xfs_itruncate_extents_flags(
	struct xfs_trans	**tpp,
	struct xfs_inode	*ip,
	int			whichfork,
	xfs_fsize_t		new_size,
	int			flags)
{ … }

int
xfs_release(
	xfs_inode_t	*ip)
{ … }

/*
 * Mark all the buffers attached to this directory stale.  In theory we should
 * never be freeing a directory with any blocks at all, but this covers the
 * case where we've recovered a directory swap with a "temporary" directory
 * created by online repair and now need to dump it.
 */
STATIC void
xfs_inactive_dir(
	struct xfs_inode	*dp)
{ … }

/*
 * xfs_inactive_truncate
 *
 * Called to perform a truncate when an inode becomes unlinked.
 */
STATIC int
xfs_inactive_truncate(
	struct xfs_inode *ip)
{ … }

/*
 * xfs_inactive_ifree()
 *
 * Perform the inode free when an inode is unlinked.
 */
STATIC int
xfs_inactive_ifree(
	struct xfs_inode *ip)
{ … }

/*
 * Returns true if we need to update the on-disk metadata before we can free
 * the memory used by this inode.  Updates include freeing post-eof
 * preallocations; freeing COW staging extents; and marking the inode free in
 * the inobt if it is on the unlinked list.
 */
bool
xfs_inode_needs_inactive(
	struct xfs_inode	*ip)
{ … }

/*
 * Save health status somewhere, if we're dumping an inode with uncorrected
 * errors and online repair isn't running.
 */
static inline void
xfs_inactive_health(
	struct xfs_inode	*ip)
{ … }

/*
 * xfs_inactive
 *
 * This is called when the vnode reference count for the vnode
 * goes to zero.  If the file has been unlinked, then it must
 * now be truncated.  Also, we clear all of the read-ahead state
 * kept for the inode here since the file is now closed.
 */
int
xfs_inactive(
	xfs_inode_t	*ip)
{ … }

/*
 * Find an inode on the unlinked list. This does not take references to the
 * inode as we have existence guarantees by holding the AGI buffer lock and that
 * only unlinked, referenced inodes can be on the unlinked inode list.  If we
 * don't find the inode in cache, then let the caller handle the situation.
 */
struct xfs_inode *
xfs_iunlink_lookup(
	struct xfs_perag	*pag,
	xfs_agino_t		agino)
{ … }

/*
 * Load the inode @next_agino into the cache and set its prev_unlinked pointer
 * to @prev_agino.  Caller must hold the AGI to synchronize with other changes
 * to the unlinked list.
 */
int
xfs_iunlink_reload_next(
	struct xfs_trans	*tp,
	struct xfs_buf		*agibp,
	xfs_agino_t		prev_agino,
	xfs_agino_t		next_agino)
{ … }

/*
 * Look up the inode number specified and if it is not already marked XFS_ISTALE
 * mark it stale. We should only find clean inodes in this lookup that aren't
 * already stale.
 */
static void
xfs_ifree_mark_inode_stale(
	struct xfs_perag	*pag,
	struct xfs_inode	*free_ip,
	xfs_ino_t		inum)
{ … }

/*
 * A big issue when freeing the inode cluster is that we _cannot_ skip any
 * inodes that are in memory - they all must be marked stale and attached to
 * the cluster buffer.
 */
static int
xfs_ifree_cluster(
	struct xfs_trans	*tp,
	struct xfs_perag	*pag,
	struct xfs_inode	*free_ip,
	struct xfs_icluster	*xic)
{ … }

/*
 * This is called to return an inode to the inode free list.  The inode should
 * already be truncated to 0 length and have no pages associated with it.  This
 * routine also assumes that the inode is already a part of the transaction.
 *
 * The on-disk copy of the inode will have been added to the list of unlinked
 * inodes in the AGI. We need to remove the inode from that list atomically with
 * respect to freeing it here.
 */
int
xfs_ifree(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip)
{ … }

/*
 * This is called to unpin an inode.  The caller must have the inode locked
 * in at least shared mode so that the buffer cannot be subsequently pinned
 * once someone is waiting for it to be unpinned.
 */
static void
xfs_iunpin(
	struct xfs_inode	*ip)
{ … }

static void
__xfs_iunpin_wait(
	struct xfs_inode	*ip)
{ … }

void
xfs_iunpin_wait(
	struct xfs_inode	*ip)
{ … }

/*
 * Removing an inode from the namespace involves removing the directory entry
 * and dropping the link count on the inode. Removing the directory entry can
 * result in locking an AGF (directory blocks were freed) and removing a link
 * count can result in placing the inode on an unlinked list which results in
 * locking an AGI.
 *
 * The big problem here is that we have an ordering constraint on AGF and AGI
 * locking - inode allocation locks the AGI, then can allocate a new extent for
 * new inodes, locking the AGF after the AGI. Similarly, freeing the inode
 * removes the inode from the unlinked list, requiring that we lock the AGI
 * first, and then freeing the inode can result in an inode chunk being freed
 * and hence freeing disk space requiring that we lock an AGF.
 *
 * Hence the ordering that is imposed by other parts of the code is AGI before
 * AGF. This means we cannot remove the directory entry before we drop the inode
 * reference count and put it on the unlinked list as this results in a lock
 * order of AGF then AGI, and this can deadlock against inode allocation and
 * freeing. Therefore we must drop the link counts before we remove the
 * directory entry.
 *
 * This is still safe from a transactional point of view - it is not until we
 * get to xfs_defer_finish() that we have the possibility of multiple
 * transactions in this operation. Hence as long as we remove the directory
 * entry and drop the link count in the first transaction of the remove
 * operation, there are no transactional constraints on the ordering here.
 */
int
xfs_remove(
	struct xfs_inode	*dp,
	struct xfs_name		*name,
	struct xfs_inode	*ip)
{ … }

static inline void
xfs_iunlock_rename(
	struct xfs_inode	**i_tab,
	int			num_inodes)
{ … }

/*
 * Enter all inodes for a rename transaction into a sorted array.
 */
#define __XFS_SORT_INODES …
STATIC void
xfs_sort_for_rename(
	struct xfs_inode	*dp1,	/* in: old (source) directory inode */
	struct xfs_inode	*dp2,	/* in: new (target) directory inode */
	struct xfs_inode	*ip1,	/* in: inode of old entry */
	struct xfs_inode	*ip2,	/* in: inode of new entry */
	struct xfs_inode	*wip,	/* in: whiteout inode */
	struct xfs_inode	**i_tab,/* out: sorted array of inodes */
	int			*num_inodes)  /* in/out: inodes in array */
{ … }

void
xfs_sort_inodes(
	struct xfs_inode	**i_tab,
	unsigned int		num_inodes)
{ … }

/*
 * xfs_rename_alloc_whiteout()
 *
 * Return a referenced, unlinked, unlocked inode that can be used as a
 * whiteout in a rename transaction. We use a tmpfile inode here so that if we
 * crash between allocating the inode and linking it into the rename transaction
 * recovery will free the inode and we won't leak it.
 */
static int
xfs_rename_alloc_whiteout(
	struct mnt_idmap	*idmap,
	struct xfs_name		*src_name,
	struct xfs_inode	*dp,
	struct xfs_inode	**wip)
{ … }

/*
 * xfs_rename
 */
int
xfs_rename(
	struct mnt_idmap	*idmap,
	struct xfs_inode	*src_dp,
	struct xfs_name		*src_name,
	struct xfs_inode	*src_ip,
	struct xfs_inode	*target_dp,
	struct xfs_name		*target_name,
	struct xfs_inode	*target_ip,
	unsigned int		flags)
{ … }

static int
xfs_iflush(
	struct xfs_inode	*ip,
	struct xfs_buf		*bp)
{ … }

/*
 * Non-blocking flush of dirty inode metadata into the backing buffer.
 *
 * The caller must have a reference to the inode and hold the cluster buffer
 * locked. The function will walk across all the inodes on the cluster buffer it
 * can find and lock without blocking, and flush them to the cluster buffer.
 *
 * On successful flushing of at least one inode, the caller must write out the
 * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and
 * the caller needs to release the buffer. On failure, the filesystem will be
 * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED
 * will be returned.
 */
int
xfs_iflush_cluster(
	struct xfs_buf		*bp)
{ … }

/* Release an inode. */
void
xfs_irele(
	struct xfs_inode	*ip)
{ … }

/*
 * Ensure all commited transactions touching the inode are written to the log.
 */
int
xfs_log_force_inode(
	struct xfs_inode	*ip)
{ … }

/*
 * Grab the exclusive iolock for a data copy from src to dest, making sure to
 * abide vfs locking order (lowest pointer value goes first) and breaking the
 * layout leases before proceeding.  The loop is needed because we cannot call
 * the blocking break_layout() with the iolocks held, and therefore have to
 * back out both locks.
 */
static int
xfs_iolock_two_inodes_and_break_layout(
	struct inode		*src,
	struct inode		*dest)
{ … }

static int
xfs_mmaplock_two_inodes_and_break_dax_layout(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/*
 * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
 * mmap activity.
 */
int
xfs_ilock2_io_mmap(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/* Unlock both inodes to allow IO and mmap activity. */
void
xfs_iunlock2_io_mmap(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/* Drop the MMAPLOCK and the IOLOCK after a remap completes. */
void
xfs_iunlock2_remapping(
	struct xfs_inode	*ip1,
	struct xfs_inode	*ip2)
{ … }

/*
 * Reload the incore inode list for this inode.  Caller should ensure that
 * the link count cannot change, either by taking ILOCK_SHARED or otherwise
 * preventing other threads from executing.
 */
int
xfs_inode_reload_unlinked_bucket(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip)
{ … }

/* Decide if this inode is missing its unlinked list and reload it. */
int
xfs_inode_reload_unlinked(
	struct xfs_inode	*ip)
{ … }

/* Has this inode fork been zapped by repair? */
bool
xfs_ifork_zapped(
	const struct xfs_inode	*ip,
	int			whichfork)
{ … }

/* Compute the number of data and realtime blocks used by a file. */
void
xfs_inode_count_blocks(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	xfs_filblks_t		*dblocks,
	xfs_filblks_t		*rblocks)
{ … }

static void
xfs_wait_dax_page(
	struct inode		*inode)
{ … }

int
xfs_break_dax_layouts(
	struct inode		*inode,
	bool			*retry)
{ … }

int
xfs_break_layouts(
	struct inode		*inode,
	uint			*iolock,
	enum layout_break_reason reason)
{ … }

/* Returns the size of fundamental allocation unit for a file, in bytes. */
unsigned int
xfs_inode_alloc_unitsize(
	struct xfs_inode	*ip)
{ … }

/* Should we always be using copy on write for file writes? */
bool
xfs_is_always_cow_inode(
	struct xfs_inode	*ip)
{ … }
linux/fs/xfs/xfs_inode.c
