Merge tag 'xfs-6.11-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Chandan Babu:
 "Major changes in this release are limited to enabling FITRIM on
  realtime devices and Byte-based grant head log reservation tracking.

  The remaining changes are limited to fixes and cleanups included in
  this pull request.

  Core:

   - Enable FITRIM on the realtime device

   - Introduce byte-based grant head log reservation tracking instead of
     physical log location tracking.

     This allows grant head to track a full 64 bit bytes space and hence
     overcome the limit of 4GB indexing that has been present until now

  Fixes:

   - xfs_flush_unmap_range() and xfs_prepare_shift() should consider RT
     extents in the flush unmap range

   - Implement bounds check when traversing log operations during log
     replay

   - Prevent out of bounds access when traversing a directory data block

   - Prevent incorrect ENOSPC when concurrently performing file creation
     and file writes

   - Fix rtalloc rotoring when delalloc is in use

  Cleanups:

   - Clean up I/O path inode locking helpers and the page fault handler

   - xfs: hoist inode operations to libxfs in anticipation of the
     metadata inode directory feature, which maintains a directory tree
     of metadata inodes. This will be necessary for further enhancements
     to the realtime feature, subvolume support

   - Clean up some warts in the extent freeing log intent code

   - Clean up the refcount and rmap intent code before adding support
     for realtime devices

   - Provide the correct email address for sysfs ABI documentation"

* tag 'xfs-6.11-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (80 commits)
  xfs: fix rtalloc rotoring when delalloc is in use
  xfs: get rid of xfs_ag_resv_rmapbt_alloc
  xfs: skip flushing log items during push
  xfs: grant heads track byte counts, not LSNs
  xfs: pass the full grant head to accounting functions
  xfs: track log space pinned by the AIL
  xfs: collapse xlog_state_set_callback in caller
  xfs: l_last_sync_lsn is really AIL state
  xfs: ensure log tail is always up to date
  xfs: background AIL push should target physical space
  xfs: AIL doesn't need manual pushing
  xfs: move and rename xfs_trans_committed_bulk
  xfs: fix the contact address for the sysfs ABI documentation
  xfs: Avoid races with cnt_btree lastrec updates
  xfs: move xfs_refcount_update_defer_add to xfs_refcount_item.c
  xfs: simplify usage of the rcur local variable in xfs_refcount_finish_one
  xfs: don't bother calling xfs_refcount_finish_one_cleanup in xfs_refcount_finish_one
  xfs: reuse xfs_refcount_update_cancel_item
  xfs: add a ci_entry helper
  xfs: remove xfs_trans_set_refcount_flags
  ...

1 files changed, 161 insertions, 1327 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a4e3cd8971fc..7dc6f326936c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -42,55 +42,11 @@
 #include "xfs_pnfs.h"
 #include "xfs_parent.h"
 #include "xfs_xattr.h"
-#include "xfs_sb.h"
+#include "xfs_inode_util.h"
 
 struct kmem_cache *xfs_inode_cache;
 
 /*
- * helper function to extract extent size hint from inode
- */
-xfs_extlen_t
-xfs_get_extsz_hint(
-	struct xfs_inode	*ip)
-{
-	/*
-	 * No point in aligning allocations if we need to COW to actually
-	 * write to them.
-	 */
-	if (xfs_is_always_cow_inode(ip))
-		return 0;
-	if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize)
-		return ip->i_extsize;
-	if (XFS_IS_REALTIME_INODE(ip) &&
-	    ip->i_mount->m_sb.sb_rextsize > 1)
-		return ip->i_mount->m_sb.sb_rextsize;
-	return 0;
-}
-
-/*
- * Helper function to extract CoW extent size hint from inode.
- * Between the extent size hint and the CoW extent size hint, we
- * return the greater of the two.  If the value is zero (automatic),
- * use the default size.
- */
-xfs_extlen_t
-xfs_get_cowextsz_hint(
-	struct xfs_inode	*ip)
-{
-	xfs_extlen_t		a, b;
-
-	a = 0;
-	if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
-		a = ip->i_cowextsize;
-	b = xfs_get_extsz_hint(ip);
-
-	a = max(a, b);
-	if (a == 0)
-		return XFS_DEFAULT_COWEXTSZ_HINT;
-	return a;
-}
-
-/*
  * 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
@@ -567,55 +523,6 @@ xfs_lock_two_inodes(
 	}
 }
 
-uint
-xfs_ip2xflags(
-	struct xfs_inode	*ip)
-{
-	uint			flags = 0;
-
-	if (ip->i_diflags & XFS_DIFLAG_ANY) {
-		if (ip->i_diflags & XFS_DIFLAG_REALTIME)
-			flags |= FS_XFLAG_REALTIME;
-		if (ip->i_diflags & XFS_DIFLAG_PREALLOC)
-			flags |= FS_XFLAG_PREALLOC;
-		if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
-			flags |= FS_XFLAG_IMMUTABLE;
-		if (ip->i_diflags & XFS_DIFLAG_APPEND)
-			flags |= FS_XFLAG_APPEND;
-		if (ip->i_diflags & XFS_DIFLAG_SYNC)
-			flags |= FS_XFLAG_SYNC;
-		if (ip->i_diflags & XFS_DIFLAG_NOATIME)
-			flags |= FS_XFLAG_NOATIME;
-		if (ip->i_diflags & XFS_DIFLAG_NODUMP)
-			flags |= FS_XFLAG_NODUMP;
-		if (ip->i_diflags & XFS_DIFLAG_RTINHERIT)
-			flags |= FS_XFLAG_RTINHERIT;
-		if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT)
-			flags |= FS_XFLAG_PROJINHERIT;
-		if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS)
-			flags |= FS_XFLAG_NOSYMLINKS;
-		if (ip->i_diflags & XFS_DIFLAG_EXTSIZE)
-			flags |= FS_XFLAG_EXTSIZE;
-		if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)
-			flags |= FS_XFLAG_EXTSZINHERIT;
-		if (ip->i_diflags & XFS_DIFLAG_NODEFRAG)
-			flags |= FS_XFLAG_NODEFRAG;
-		if (ip->i_diflags & XFS_DIFLAG_FILESTREAM)
-			flags |= FS_XFLAG_FILESTREAM;
-	}
-
-	if (ip->i_diflags2 & XFS_DIFLAG2_ANY) {
-		if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
-			flags |= FS_XFLAG_DAX;
-		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
-			flags |= FS_XFLAG_COWEXTSIZE;
-	}
-
-	if (xfs_inode_has_attr_fork(ip))
-		flags |= FS_XFLAG_HASATTR;
-	return flags;
-}
-
 /*
  * 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,
@@ -657,97 +564,6 @@ out_unlock:
 	return error;
 }
 
-/* Propagate di_flags from a parent inode to a child inode. */
-static void
-xfs_inode_inherit_flags(
-	struct xfs_inode	*ip,
-	const struct xfs_inode	*pip)
-{
-	unsigned int		di_flags = 0;
-	xfs_failaddr_t		failaddr;
-	umode_t			mode = VFS_I(ip)->i_mode;
-
-	if (S_ISDIR(mode)) {
-		if (pip->i_diflags & XFS_DIFLAG_RTINHERIT)
-			di_flags |= XFS_DIFLAG_RTINHERIT;
-		if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
-			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-			ip->i_extsize = pip->i_extsize;
-		}
-		if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT)
-			di_flags |= XFS_DIFLAG_PROJINHERIT;
-	} else if (S_ISREG(mode)) {
-		if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
-		    xfs_has_realtime(ip->i_mount))
-			di_flags |= XFS_DIFLAG_REALTIME;
-		if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
-			di_flags |= XFS_DIFLAG_EXTSIZE;
-			ip->i_extsize = pip->i_extsize;
-		}
-	}
-	if ((pip->i_diflags & XFS_DIFLAG_NOATIME) &&
-	    xfs_inherit_noatime)
-		di_flags |= XFS_DIFLAG_NOATIME;
-	if ((pip->i_diflags & XFS_DIFLAG_NODUMP) &&
-	    xfs_inherit_nodump)
-		di_flags |= XFS_DIFLAG_NODUMP;
-	if ((pip->i_diflags & XFS_DIFLAG_SYNC) &&
-	    xfs_inherit_sync)
-		di_flags |= XFS_DIFLAG_SYNC;
-	if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) &&
-	    xfs_inherit_nosymlinks)
-		di_flags |= XFS_DIFLAG_NOSYMLINKS;
-	if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) &&
-	    xfs_inherit_nodefrag)
-		di_flags |= XFS_DIFLAG_NODEFRAG;
-	if (pip->i_diflags & XFS_DIFLAG_FILESTREAM)
-		di_flags |= XFS_DIFLAG_FILESTREAM;
-
-	ip->i_diflags |= di_flags;
-
-	/*
-	 * Inode verifiers on older kernels only check that the extent size
-	 * hint is an integer multiple of the rt extent size on realtime files.
-	 * They did not check the hint alignment on a directory with both
-	 * rtinherit and extszinherit flags set.  If the misaligned hint is
-	 * propagated from a directory into a new realtime file, new file
-	 * allocations will fail due to math errors in the rt allocator and/or
-	 * trip the verifiers.  Validate the hint settings in the new file so
-	 * that we don't let broken hints propagate.
-	 */
-	failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize,
-			VFS_I(ip)->i_mode, ip->i_diflags);
-	if (failaddr) {
-		ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
-				   XFS_DIFLAG_EXTSZINHERIT);
-		ip->i_extsize = 0;
-	}
-}
-
-/* Propagate di_flags2 from a parent inode to a child inode. */
-static void
-xfs_inode_inherit_flags2(
-	struct xfs_inode	*ip,
-	const struct xfs_inode	*pip)
-{
-	xfs_failaddr_t		failaddr;
-
-	if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
-		ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
-		ip->i_cowextsize = pip->i_cowextsize;
-	}
-	if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
-		ip->i_diflags2 |= XFS_DIFLAG2_DAX;
-
-	/* Don't let invalid cowextsize hints propagate. */
-	failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
-			VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2);
-	if (failaddr) {
-		ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
-		ip->i_cowextsize = 0;
-	}
-}
-
 /*
  * Initialise a newly allocated inode and return the in-core inode to the
  * caller locked exclusively.
@@ -755,39 +571,15 @@ xfs_inode_inherit_flags2(
  * Caller is responsible for unlocking the inode manually upon return
  */
 int
-xfs_init_new_inode(
-	struct mnt_idmap	*idmap,
+xfs_icreate(
 	struct xfs_trans	*tp,
-	struct xfs_inode	*pip,
 	xfs_ino_t		ino,
-	umode_t			mode,
-	xfs_nlink_t		nlink,
-	dev_t			rdev,
-	prid_t			prid,
-	bool			init_xattrs,
+	const struct xfs_icreate_args *args,
 	struct xfs_inode	**ipp)
 {
-	struct inode		*dir = pip ? VFS_I(pip) : NULL;
 	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_inode	*ip;
-	unsigned int		flags;
+	struct xfs_inode	*ip = NULL;
 	int			error;
-	struct timespec64	tv;
-	struct inode		*inode;
-
-	/*
-	 * Protect against obviously corrupt allocation btree records. Later
-	 * xfs_iget checks will catch re-allocation of other active in-memory
-	 * and on-disk inodes. If we don't catch reallocating the parent inode
-	 * here we will deadlock in xfs_iget() so we have to do these checks
-	 * first.
-	 */
-	if ((pip && ino == pip->i_ino) || !xfs_verify_dir_ino(mp, ino)) {
-		xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
-		xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
-				XFS_SICK_AG_INOBT);
-		return -EFSCORRUPTED;
-	}
 
 	/*
 	 * Get the in-core inode with the lock held exclusively to prevent
@@ -798,96 +590,8 @@ xfs_init_new_inode(
 		return error;
 
 	ASSERT(ip != NULL);
-	inode = VFS_I(ip);
-	set_nlink(inode, nlink);
-	inode->i_rdev = rdev;
-	ip->i_projid = prid;
-
-	if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) {
-		inode_fsuid_set(inode, idmap);
-		inode->i_gid = dir->i_gid;
-		inode->i_mode = mode;
-	} else {
-		inode_init_owner(idmap, inode, dir, mode);
-	}
-
-	/*
-	 * If the group ID of the new file does not match the effective group
-	 * ID or one of the supplementary group IDs, the S_ISGID bit is cleared
-	 * (and only if the irix_sgid_inherit compatibility variable is set).
-	 */
-	if (irix_sgid_inherit && (inode->i_mode & S_ISGID) &&
-	    !vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)))
-		inode->i_mode &= ~S_ISGID;
-
-	ip->i_disk_size = 0;
-	ip->i_df.if_nextents = 0;
-	ASSERT(ip->i_nblocks == 0);
-
-	tv = inode_set_ctime_current(inode);
-	inode_set_mtime_to_ts(inode, tv);
-	inode_set_atime_to_ts(inode, tv);
-
-	ip->i_extsize = 0;
-	ip->i_diflags = 0;
-
-	if (xfs_has_v3inodes(mp)) {
-		inode_set_iversion(inode, 1);
-		ip->i_cowextsize = 0;
-		ip->i_crtime = tv;
-	}
-
-	flags = XFS_ILOG_CORE;
-	switch (mode & S_IFMT) {
-	case S_IFIFO:
-	case S_IFCHR:
-	case S_IFBLK:
-	case S_IFSOCK:
-		ip->i_df.if_format = XFS_DINODE_FMT_DEV;
-		flags |= XFS_ILOG_DEV;
-		break;
-	case S_IFREG:
-	case S_IFDIR:
-		if (pip && (pip->i_diflags & XFS_DIFLAG_ANY))
-			xfs_inode_inherit_flags(ip, pip);
-		if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY))
-			xfs_inode_inherit_flags2(ip, pip);
-		fallthrough;
-	case S_IFLNK:
-		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
-		ip->i_df.if_bytes = 0;
-		ip->i_df.if_data = NULL;
-		break;
-	default:
-		ASSERT(0);
-	}
-
-	/*
-	 * If we need to create attributes immediately after allocating the
-	 * inode, initialise an empty attribute fork right now. We use the
-	 * default fork offset for attributes here as we don't know exactly what
-	 * size or how many attributes we might be adding. We can do this
-	 * safely here because we know the data fork is completely empty and
-	 * this saves us from needing to run a separate transaction to set the
-	 * fork offset in the immediate future.
-	 */
-	if (init_xattrs) {
-		ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
-		xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
-
-		if (!xfs_has_attr(mp)) {
-			spin_lock(&mp->m_sb_lock);
-			xfs_add_attr(mp);
-			spin_unlock(&mp->m_sb_lock);
-			xfs_log_sb(tp);
-		}
-	}
-
-	/*
-	 * Log the new values stuffed into the inode.
-	 */
 	xfs_trans_ijoin(tp, ip, 0);
-	xfs_trans_log_inode(tp, ip, flags);
+	xfs_inode_init(tp, args, ip);
 
 	/* now that we have an i_mode we can setup the inode structure */
 	xfs_setup_inode(ip);
@@ -896,158 +600,60 @@ xfs_init_new_inode(
 	return 0;
 }
 
-/*
- * Decrement the link count on an inode & log the change.  If this causes the
- * link count to go to zero, move the inode to AGI unlinked list so that it can
- * be freed when the last active reference goes away via xfs_inactive().
- */
+/* Return dquots for the ids that will be assigned to a new file. */
 int
-xfs_droplink(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip)
-{
-	struct inode		*inode = VFS_I(ip);
-
-	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
-
-	if (inode->i_nlink == 0) {
-		xfs_info_ratelimited(tp->t_mountp,
- "Inode 0x%llx link count dropped below zero.  Pinning link count.",
-				ip->i_ino);
-		set_nlink(inode, XFS_NLINK_PINNED);
-	}
-	if (inode->i_nlink != XFS_NLINK_PINNED)
-		drop_nlink(inode);
-
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-	if (inode->i_nlink)
-		return 0;
-
-	return xfs_iunlink(tp, ip);
-}
-
-/*
- * Increment the link count on an inode & log the change.
- */
-void
-xfs_bumplink(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip)
-{
-	struct inode		*inode = VFS_I(ip);
-
-	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
-
-	if (inode->i_nlink == XFS_NLINK_PINNED - 1)
-		xfs_info_ratelimited(tp->t_mountp,
- "Inode 0x%llx link count exceeded maximum.  Pinning link count.",
-				ip->i_ino);
-	if (inode->i_nlink != XFS_NLINK_PINNED)
-		inc_nlink(inode);
-
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-}
-
-#ifdef CONFIG_XFS_LIVE_HOOKS
-/*
- * Use a static key here to reduce the overhead of directory live update hooks.
- * If the compiler supports jump labels, the static branch will be replaced by
- * a nop sled when there are no hook users.  Online fsck is currently the only
- * caller, so this is a reasonable tradeoff.
- *
- * Note: Patching the kernel code requires taking the cpu hotplug lock.  Other
- * parts of the kernel allocate memory with that lock held, which means that
- * XFS callers cannot hold any locks that might be used by memory reclaim or
- * writeback when calling the static_branch_{inc,dec} functions.
- */
-DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch);
-
-void
-xfs_dir_hook_disable(void)
-{
-	xfs_hooks_switch_off(&xfs_dir_hooks_switch);
-}
-
-void
-xfs_dir_hook_enable(void)
-{
-	xfs_hooks_switch_on(&xfs_dir_hooks_switch);
-}
-
-/* Call hooks for a directory update relating to a child dirent update. */
-inline void
-xfs_dir_update_hook(
-	struct xfs_inode		*dp,
-	struct xfs_inode		*ip,
-	int				delta,
-	const struct xfs_name		*name)
-{
-	if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) {
-		struct xfs_dir_update_params	p = {
-			.dp		= dp,
-			.ip		= ip,
-			.delta		= delta,
-			.name		= name,
-		};
-		struct xfs_mount	*mp = ip->i_mount;
-
-		xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p);
+xfs_icreate_dqalloc(
+	const struct xfs_icreate_args	*args,
+	struct xfs_dquot		**udqpp,
+	struct xfs_dquot		**gdqpp,
+	struct xfs_dquot		**pdqpp)
+{
+	struct inode			*dir = VFS_I(args->pip);
+	kuid_t				uid = GLOBAL_ROOT_UID;
+	kgid_t				gid = GLOBAL_ROOT_GID;
+	prid_t				prid = 0;
+	unsigned int			flags = XFS_QMOPT_QUOTALL;
+
+	if (args->idmap) {
+		/*
+		 * The uid/gid computation code must match what the VFS uses to
+		 * assign i_[ug]id.  INHERIT adjusts the gid computation for
+		 * setgid/grpid systems.
+		 */
+		uid = mapped_fsuid(args->idmap, i_user_ns(dir));
+		gid = mapped_fsgid(args->idmap, i_user_ns(dir));
+		prid = xfs_get_initial_prid(args->pip);
+		flags |= XFS_QMOPT_INHERIT;
 	}
-}
 
-/* Call the specified function during a directory update. */
-int
-xfs_dir_hook_add(
-	struct xfs_mount	*mp,
-	struct xfs_dir_hook	*hook)
-{
-	return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook);
-}
+	*udqpp = *gdqpp = *pdqpp = NULL;
 
-/* Stop calling the specified function during a directory update. */
-void
-xfs_dir_hook_del(
-	struct xfs_mount	*mp,
-	struct xfs_dir_hook	*hook)
-{
-	xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook);
+	return xfs_qm_vop_dqalloc(args->pip, uid, gid, prid, flags, udqpp,
+			gdqpp, pdqpp);
 }
 
-/* Configure directory update hook functions. */
-void
-xfs_dir_hook_setup(
-	struct xfs_dir_hook	*hook,
-	notifier_fn_t		mod_fn)
-{
-	xfs_hook_setup(&hook->dirent_hook, mod_fn);
-}
-#endif /* CONFIG_XFS_LIVE_HOOKS */
-
 int
 xfs_create(
-	struct mnt_idmap	*idmap,
-	struct xfs_inode	*dp,
+	const struct xfs_icreate_args *args,
 	struct xfs_name		*name,
-	umode_t			mode,
-	dev_t			rdev,
-	bool			init_xattrs,
-	xfs_inode_t		**ipp)
+	struct xfs_inode	**ipp)
 {
-	int			is_dir = S_ISDIR(mode);
+	struct xfs_inode	*dp = args->pip;
+	struct xfs_dir_update	du = {
+		.dp		= dp,
+		.name		= name,
+	};
 	struct xfs_mount	*mp = dp->i_mount;
-	struct xfs_inode	*ip = NULL;
 	struct xfs_trans	*tp = NULL;
-	int			error;
-	bool			unlock_dp_on_error = false;
-	prid_t			prid;
-	struct xfs_dquot	*udqp = NULL;
-	struct xfs_dquot	*gdqp = NULL;
-	struct xfs_dquot	*pdqp = NULL;
+	struct xfs_dquot	*udqp;
+	struct xfs_dquot	*gdqp;
+	struct xfs_dquot	*pdqp;
 	struct xfs_trans_res	*tres;
-	uint			resblks;
 	xfs_ino_t		ino;
-	struct xfs_parent_args	*ppargs;
+	bool			unlock_dp_on_error = false;
+	bool			is_dir = S_ISDIR(args->mode);
+	uint			resblks;
+	int			error;
 
 	trace_xfs_create(dp, name);
 
@@ -1056,15 +662,8 @@ xfs_create(
 	if (xfs_ifork_zapped(dp, XFS_DATA_FORK))
 		return -EIO;
 
-	prid = xfs_get_initial_prid(dp);
-
-	/*
-	 * Make sure that we have allocated dquot(s) on disk.
-	 */
-	error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns),
-			mapped_fsgid(idmap, &init_user_ns), prid,
-			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-			&udqp, &gdqp, &pdqp);
+	/* Make sure that we have allocated dquot(s) on disk. */
+	error = xfs_icreate_dqalloc(args, &udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
@@ -1076,7 +675,7 @@ xfs_create(
 		tres = &M_RES(mp)->tr_create;
 	}
 
-	error = xfs_parent_start(mp, &ppargs);
+	error = xfs_parent_start(mp, &du.ppargs);
 	if (error)
 		goto out_release_dquots;
 
@@ -1105,10 +704,9 @@ xfs_create(
 	 * entry pointing to them, but a directory also the "." entry
 	 * pointing to itself.
 	 */
-	error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
+	error = xfs_dialloc(&tp, dp->i_ino, args->mode, &ino);
 	if (!error)
-		error = xfs_init_new_inode(idmap, tp, dp, ino, mode,
-				is_dir ? 2 : 1, rdev, prid, init_xattrs, &ip);
+		error = xfs_icreate(tp, ino, args, &du.ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1121,38 +719,9 @@ xfs_create(
 	 */
 	xfs_trans_ijoin(tp, dp, 0);
 
-	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-					resblks - XFS_IALLOC_SPACE_RES(mp));
-	if (error) {
-		ASSERT(error != -ENOSPC);
+	error = xfs_dir_create_child(tp, resblks, &du);
+	if (error)
 		goto out_trans_cancel;
-	}
-	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
-
-	if (is_dir) {
-		error = xfs_dir_init(tp, ip, dp);
-		if (error)
-			goto out_trans_cancel;
-
-		xfs_bumplink(tp, dp);
-	}
-
-	/*
-	 * If we have parent pointers, we need to add the attribute containing
-	 * the parent information now.
-	 */
-	if (ppargs) {
-		error = xfs_parent_addname(tp, ppargs, dp, name, ip);
-		if (error)
-			goto out_trans_cancel;
-	}
-
-	/*
-	 * Create ip with a reference from dp, and add '.' and '..' references
-	 * if it's a directory.
-	 */
-	xfs_dir_update_hook(dp, ip, 1, name);
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -1167,7 +736,7 @@ xfs_create(
 	 * These ids of the inode couldn't have changed since the new
 	 * inode has been locked ever since it was created.
 	 */
-	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
+	xfs_qm_vop_create_dqattach(tp, du.ip, udqp, gdqp, pdqp);
 
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -1177,10 +746,10 @@ xfs_create(
 	xfs_qm_dqrele(gdqp);
 	xfs_qm_dqrele(pdqp);
 
-	*ipp = ip;
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	*ipp = du.ip;
+	xfs_iunlock(du.ip, XFS_ILOCK_EXCL);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-	xfs_parent_finish(mp, ppargs);
+	xfs_parent_finish(mp, du.ppargs);
 	return 0;
 
  out_trans_cancel:
@@ -1191,13 +760,13 @@ xfs_create(
 	 * setup of the inode and release the inode.  This prevents recursive
 	 * transactions and deadlocks from xfs_inactive.
 	 */
-	if (ip) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_finish_inode_setup(ip);
-		xfs_irele(ip);
+	if (du.ip) {
+		xfs_iunlock(du.ip, XFS_ILOCK_EXCL);
+		xfs_finish_inode_setup(du.ip);
+		xfs_irele(du.ip);
 	}
  out_parent:
-	xfs_parent_finish(mp, ppargs);
+	xfs_parent_finish(mp, du.ppargs);
  out_release_dquots:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
@@ -1210,36 +779,28 @@ xfs_create(
 
 int
 xfs_create_tmpfile(
-	struct mnt_idmap	*idmap,
-	struct xfs_inode	*dp,
-	umode_t			mode,
-	bool			init_xattrs,
+	const struct xfs_icreate_args *args,
 	struct xfs_inode	**ipp)
 {
+	struct xfs_inode	*dp = args->pip;
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_inode	*ip = NULL;
 	struct xfs_trans	*tp = NULL;
-	int			error;
-	prid_t                  prid;
-	struct xfs_dquot	*udqp = NULL;
-	struct xfs_dquot	*gdqp = NULL;
-	struct xfs_dquot	*pdqp = NULL;
+	struct xfs_dquot	*udqp;
+	struct xfs_dquot	*gdqp;
+	struct xfs_dquot	*pdqp;
 	struct xfs_trans_res	*tres;
-	uint			resblks;
 	xfs_ino_t		ino;
+	uint			resblks;
+	int			error;
+
+	ASSERT(args->flags & XFS_ICREATE_TMPFILE);
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
-	prid = xfs_get_initial_prid(dp);
-
-	/*
-	 * Make sure that we have allocated dquot(s) on disk.
-	 */
-	error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns),
-			mapped_fsgid(idmap, &init_user_ns), prid,
-			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
-			&udqp, &gdqp, &pdqp);
+	/* Make sure that we have allocated dquot(s) on disk. */
+	error = xfs_icreate_dqalloc(args, &udqp, &gdqp, &pdqp);
 	if (error)
 		return error;
 
@@ -1251,10 +812,9 @@ xfs_create_tmpfile(
 	if (error)
 		goto out_release_dquots;
 
-	error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
+	error = xfs_dialloc(&tp, dp->i_ino, args->mode, &ino);
 	if (!error)
-		error = xfs_init_new_inode(idmap, tp, dp, ino, mode,
-				0, 0, prid, init_xattrs, &ip);
+		error = xfs_icreate(tp, ino, args, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1311,11 +871,15 @@ xfs_link(
 	struct xfs_inode	*sip,
 	struct xfs_name		*target_name)
 {
+	struct xfs_dir_update	du = {
+		.dp		= tdp,
+		.name		= target_name,
+		.ip		= sip,
+	};
 	struct xfs_mount	*mp = tdp->i_mount;
 	struct xfs_trans	*tp;
 	int			error, nospace_error = 0;
 	int			resblks;
-	struct xfs_parent_args	*ppargs;
 
 	trace_xfs_link(tdp, target_name);
 
@@ -1334,7 +898,7 @@ xfs_link(
 	if (error)
 		goto std_return;
 
-	error = xfs_parent_start(mp, &ppargs);
+	error = xfs_parent_start(mp, &du.ppargs);
 	if (error)
 		goto std_return;
 
@@ -1349,7 +913,7 @@ xfs_link(
 	 * pointers are enabled because we can't back out if the xattrs must
 	 * grow.
 	 */
-	if (ppargs && nospace_error) {
+	if (du.ppargs && nospace_error) {
 		error = nospace_error;
 		goto error_return;
 	}
@@ -1376,47 +940,9 @@ xfs_link(
 		}
 	}
 
-	if (!resblks) {
-		error = xfs_dir_canenter(tp, tdp, target_name);
-		if (error)
-			goto error_return;
-	}
-
-	/*
-	 * Handle initial link state of O_TMPFILE inode
-	 */
-	if (VFS_I(sip)->i_nlink == 0) {
-		struct xfs_perag	*pag;
-
-		pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sip->i_ino));
-		error = xfs_iunlink_remove(tp, pag, sip);
-		xfs_perag_put(pag);
-		if (error)
-			goto error_return;
-	}
-
-	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-				   resblks);
+	error = xfs_dir_add_child(tp, resblks, &du);
 	if (error)
 		goto error_return;
-	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
-
-	xfs_bumplink(tp, sip);
-
-	/*
-	 * If we have parent pointers, we now need to add the parent record to
-	 * the attribute fork of the inode. If this is the initial parent
-	 * attribute, we need to create it correctly, otherwise we can just add
-	 * the parent to the inode.
-	 */
-	if (ppargs) {
-		error = xfs_parent_addname(tp, ppargs, tdp, target_name, sip);
-		if (error)
-			goto error_return;
-	}
-
-	xfs_dir_update_hook(tdp, sip, 1, target_name);
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -1429,7 +955,7 @@ xfs_link(
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(tdp, XFS_ILOCK_EXCL);
 	xfs_iunlock(sip, XFS_ILOCK_EXCL);
-	xfs_parent_finish(mp, ppargs);
+	xfs_parent_finish(mp, du.ppargs);
 	return error;
 
  error_return:
@@ -1437,7 +963,7 @@ xfs_link(
 	xfs_iunlock(tdp, XFS_ILOCK_EXCL);
 	xfs_iunlock(sip, XFS_ILOCK_EXCL);
  out_parent:
-	xfs_parent_finish(mp, ppargs);
+	xfs_parent_finish(mp, du.ppargs);
  std_return:
 	if (error == -ENOSPC && nospace_error)
 		error = nospace_error;
@@ -2024,39 +1550,6 @@ out:
 }
 
 /*
- * In-Core Unlinked List Lookups
- * =============================
- *
- * Every inode is supposed to be reachable from some other piece of metadata
- * with the exception of the root directory.  Inodes with a connection to a
- * file descriptor but not linked from anywhere in the on-disk directory tree
- * are collectively known as unlinked inodes, though the filesystem itself
- * maintains links to these inodes so that on-disk metadata are consistent.
- *
- * XFS implements a per-AG on-disk hash table of unlinked inodes.  The AGI
- * header contains a number of buckets that point to an inode, and each inode
- * record has a pointer to the next inode in the hash chain.  This
- * singly-linked list causes scaling problems in the iunlink remove function
- * because we must walk that list to find the inode that points to the inode
- * being removed from the unlinked hash bucket list.
- *
- * Hence we keep an in-memory double linked list to link each inode on an
- * unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer
- * based lists would require having 64 list heads in the perag, one for each
- * list. This is expensive in terms of memory (think millions of AGs) and cache
- * misses on lookups. Instead, use the fact that inodes on the unlinked list
- * must be referenced at the VFS level to keep them on the list and hence we
- * have an existence guarantee for inodes on the unlinked list.
- *
- * Given we have an existence guarantee, we can use lockless inode cache lookups
- * to resolve aginos to xfs inodes. This means we only need 8 bytes per inode
- * for the double linked unlinked list, and we don't need any extra locking to
- * keep the list safe as all manipulations are done under the AGI buffer lock.
- * Keeping the list up to date does not require memory allocation, just finding
- * the XFS inode and updating the next/prev unlinked list aginos.
- */
-
-/*
  * 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
@@ -2091,75 +1584,11 @@ xfs_iunlink_lookup(
 }
 
 /*
- * Update the prev pointer of the next agino.  Returns -ENOLINK if the inode
- * is not in cache.
- */
-static int
-xfs_iunlink_update_backref(
-	struct xfs_perag	*pag,
-	xfs_agino_t		prev_agino,
-	xfs_agino_t		next_agino)
-{
-	struct xfs_inode	*ip;
-
-	/* No update necessary if we are at the end of the list. */
-	if (next_agino == NULLAGINO)
-		return 0;
-
-	ip = xfs_iunlink_lookup(pag, next_agino);
-	if (!ip)
-		return -ENOLINK;
-
-	ip->i_prev_unlinked = prev_agino;
-	return 0;
-}
-
-/*
- * Point the AGI unlinked bucket at an inode and log the results.  The caller
- * is responsible for validating the old value.
- */
-STATIC int
-xfs_iunlink_update_bucket(
-	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
-	struct xfs_buf		*agibp,
-	unsigned int		bucket_index,
-	xfs_agino_t		new_agino)
-{
-	struct xfs_agi		*agi = agibp->b_addr;
-	xfs_agino_t		old_value;
-	int			offset;
-
-	ASSERT(xfs_verify_agino_or_null(pag, new_agino));
-
-	old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
-	trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index,
-			old_value, new_agino);
-
-	/*
-	 * We should never find the head of the list already set to the value
-	 * passed in because either we're adding or removing ourselves from the
-	 * head of the list.
-	 */
-	if (old_value == new_agino) {
-		xfs_buf_mark_corrupt(agibp);
-		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
-		return -EFSCORRUPTED;
-	}
-
-	agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
-	offset = offsetof(struct xfs_agi, agi_unlinked) +
-			(sizeof(xfs_agino_t) * bucket_index);
-	xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1);
-	return 0;
-}
-
-/*
  * 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.
  */
-STATIC int
+int
 xfs_iunlink_reload_next(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agibp,
@@ -2215,187 +1644,6 @@ rele:
 	return error;
 }
 
-static int
-xfs_iunlink_insert_inode(
-	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
-	struct xfs_buf		*agibp,
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_agi		*agi = agibp->b_addr;
-	xfs_agino_t		next_agino;
-	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
-	short			bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
-	int			error;
-
-	/*
-	 * Get the index into the agi hash table for the list this inode will
-	 * go on.  Make sure the pointer isn't garbage and that this inode
-	 * isn't already on the list.
-	 */
-	next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
-	if (next_agino == agino ||
-	    !xfs_verify_agino_or_null(pag, next_agino)) {
-		xfs_buf_mark_corrupt(agibp);
-		xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
-		return -EFSCORRUPTED;
-	}
-
-	/*
-	 * Update the prev pointer in the next inode to point back to this
-	 * inode.
-	 */
-	error = xfs_iunlink_update_backref(pag, agino, next_agino);
-	if (error == -ENOLINK)
-		error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino);
-	if (error)
-		return error;
-
-	if (next_agino != NULLAGINO) {
-		/*
-		 * There is already another inode in the bucket, so point this
-		 * inode to the current head of the list.
-		 */
-		error = xfs_iunlink_log_inode(tp, ip, pag, next_agino);
-		if (error)
-			return error;
-		ip->i_next_unlinked = next_agino;
-	}
-
-	/* Point the head of the list to point to this inode. */
-	ip->i_prev_unlinked = NULLAGINO;
-	return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino);
-}
-
-/*
- * This is called when the inode's link count has gone to 0 or we are creating
- * a tmpfile via O_TMPFILE.  The inode @ip must have nlink == 0.
- *
- * We place the on-disk inode on a list in the AGI.  It will be pulled from this
- * list when the inode is freed.
- */
-int
-xfs_iunlink(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_perag	*pag;
-	struct xfs_buf		*agibp;
-	int			error;
-
-	ASSERT(VFS_I(ip)->i_nlink == 0);
-	ASSERT(VFS_I(ip)->i_mode != 0);
-	trace_xfs_iunlink(ip);
-
-	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-
-	/* Get the agi buffer first.  It ensures lock ordering on the list. */
-	error = xfs_read_agi(pag, tp, 0, &agibp);
-	if (error)
-		goto out;
-
-	error = xfs_iunlink_insert_inode(tp, pag, agibp, ip);
-out:
-	xfs_perag_put(pag);
-	return error;
-}
-
-static int
-xfs_iunlink_remove_inode(
-	struct xfs_trans	*tp,
-	struct xfs_perag	*pag,
-	struct xfs_buf		*agibp,
-	struct xfs_inode	*ip)
-{
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_agi		*agi = agibp->b_addr;
-	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
-	xfs_agino_t		head_agino;
-	short			bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
-	int			error;
-