diff options
Diffstat (limited to 'fs/xfs/xfs_inode.c')
| -rw-r--r-- | fs/xfs/xfs_inode.c | 1796 |
1 files changed, 286 insertions, 1510 deletions
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a4e3cd8971fc..f1f88e48fe22 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -42,55 +42,12 @@ #include "xfs_pnfs.h" #include "xfs_parent.h" #include "xfs_xattr.h" -#include "xfs_sb.h" +#include "xfs_inode_util.h" +#include "xfs_metafile.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 @@ -385,8 +342,7 @@ xfs_lock_inumorder( { uint class = 0; - ASSERT(!(lock_mode & (XFS_ILOCK_PARENT | XFS_ILOCK_RTBITMAP | - XFS_ILOCK_RTSUM))); + ASSERT(!(lock_mode & XFS_ILOCK_PARENT)); ASSERT(xfs_lockdep_subclass_ok(subclass)); if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)) { @@ -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, @@ -647,8 +554,20 @@ xfs_lookup( if (error) goto out_free_name; + /* + * Fail if a directory entry in the regular directory tree points to + * a metadata file. + */ + if (XFS_IS_CORRUPT(dp->i_mount, xfs_is_metadir_inode(*ipp))) { + xfs_fs_mark_sick(dp->i_mount, XFS_SICK_FS_METADIR); + error = -EFSCORRUPTED; + goto out_irele; + } + return 0; +out_irele: + xfs_irele(*ipp); out_free_name: if (ci_name) kfree(ci_name->name); @@ -657,97 +576,6 @@ 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 +583,15 @@ 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 +602,8 @@ 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 +612,60 @@ 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); +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; } - 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); -} + *udqpp = *gdqpp = *pdqpp = NULL; -/* - * 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); + return xfs_qm_vop_dqalloc(args->pip, uid, gid, prid, flags, udqpp, + gdqpp, pdqpp); } -#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); - } -} - -/* 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); -} - -/* 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); -} - -/* 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 +674,8 @@ 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 +687,7 @@ 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 +716,9 @@ 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, args, &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 +731,9 @@ 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 +748,7 @@ 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 +758,10 @@ 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 +772,13 @@ 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 +791,28 @@ 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 +824,9 @@ xfs_create_tmpfile( if (error) goto out_release_dquots; - error = xfs_dialloc(&tp, dp->i_ino, mode, &ino); + error = xfs_dialloc(&tp, args, &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; @@ -1305,17 +877,50 @@ xfs_create_tmpfile( return error; } +static inline int +xfs_projid_differ( + struct xfs_inode *tdp, + struct xfs_inode *sip) +{ + /* + * If we are using project inheritance, we only allow hard link/renames + * creation in our tree when the project IDs are the same; else + * the tree quota mechanism could be circumvented. + */ + if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && + tdp->i_projid != sip->i_projid)) { + /* + * Project quota setup skips special files which can + * leave inodes in a PROJINHERIT directory without a + * project ID set. We need to allow links to be made + * to these "project-less" inodes because userspace + * expects them to succeed after project ID setup, + * but everything else should be rejected. + */ + if (!special_file(VFS_I(sip)->i_mode) || + sip->i_projid != 0) { + return -EXDEV; + } + } + + return 0; +} + int xfs_link( struct xfs_inode *tdp, 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 +939,7 @@ 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; @@ -1349,74 +954,18 @@ 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; } - /* - * If we are using project inheritance, we only allow hard link - * creation in our tree when the project IDs are the same; else - * the tree quota mechanism could be circumvented. - */ - if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) && - tdp->i_projid != sip->i_projid)) { - /* - * Project quota setup skips special files which can - * leave inodes in a PROJINHERIT directory without a - * project ID set. We need to allow links to be made - * to these "project-less" inodes because userspace - * expects them to succeed after project ID setup, - * but everything else should be rejected. - */ - if (!special_file(VFS_I(sip)->i_mode) || - sip->i_projid != 0) { - error = -EXDEV; - goto error_return; - } - } - - 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_projid_differ(tdp, sip); 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); + error = xfs_dir_add_child(tp, resblks, &du); + if (error) + goto error_return; /* * If this is a synchronous mount, make sure that the @@ -1429,7 +978,7 @@ 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 +986,7 @@ 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; @@ -1497,7 +1046,7 @@ xfs_itruncate_extents_flags( int error = 0; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); - if (atomic_read(&VFS_I(ip)->i_count)) + if (icount_read(VFS_I(ip))) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); ASSERT(new_size <= XFS_ISIZE(ip)); ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); @@ -1553,88 +1102,6 @@ out: return error; } -int -xfs_release( - xfs_inode_t *ip) -{ - xfs_mount_t *mp = ip->i_mount; - int error = 0; - - if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0)) - return 0; - - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) - return 0; - - if (!xfs_is_shutdown(mp)) { - int truncated; - - /* - * If we previously truncated this file and removed old data - * in the process, we want to initiate "early" writeout on - * the last close. This is an attempt to combat the notorious - * NULL files problem which is particularly noticeable from a - * truncate down, buffered (re-)write (delalloc), followed by - * a crash. What we are effectively doing here is - * significantly reducing the time window where we'd otherwise - * be exposed to that problem. - */ - truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED); - if (truncated) { - xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE); - if (ip->i_delayed_blks > 0) { - error = filemap_flush(VFS_I(ip)->i_mapping); - if (error) - return error; - } - } - } - - if (VFS_I(ip)->i_nlink == 0) - return 0; - - /* - * If we can't get the iolock just skip truncating the blocks past EOF - * because we could deadlock with the mmap_lock otherwise. We'll get - * another chance to drop them once the last reference to the inode is - * dropped, so we'll never leak blocks permanently. - */ - if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) - return 0; - - if (xfs_can_free_eofblocks(ip)) { - /* - * Check if the inode is being opened, written and closed - * frequently and we have delayed allocation blocks outstanding - * (e.g. streaming writes from the NFS server), truncating the - * blocks past EOF will cause fragmentation to occur. - * - * In this case don't do the truncation, but we have to be - * careful how we detect this case. Blocks beyond EOF show up as - * i_delayed_blks even when the inode is clean, so we need to - * truncate them away first before checking for a dirty release. - * Hence on the first dirty close we will still remove the - * speculative allocation, but after that we will leave it in - * place. - */ - if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE)) - goto out_unlock; - - error = xfs_free_eofblocks(ip); - if (error) - goto out_unlock; - - /* delalloc blocks after truncation means it really is dirty */ - if (ip->i_delayed_blks) - xfs_iflags_set(ip, XFS_IDIRTY_RELEASE); - } - -out_unlock: - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return error; -} - /* * 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 @@ -1851,7 +1318,7 @@ xfs_inode_needs_inactive( return false; /* Metadata inodes require explicit resource cleanup. */ - if (xfs_is_metadata_inode(ip)) + if (xfs_is_internal_inode(ip)) return false; /* Want to clean out the cow blocks if there are any. */ @@ -1944,12 +1411,15 @@ xfs_inactive( goto out; /* Metadata inodes require explicit resource cleanup. */ - if (xfs_is_metadata_inode(ip)) + if (xfs_is_internal_inode(ip)) goto out; /* Try to clean out the cow blocks if there are any. */ - if (xfs_inode_has_cow_data(ip)) - xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); + if (xfs_inode_has_cow_data(ip)) { + error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); + if (error) + goto out; + } if (VFS_I(ip)->i_nlink != 0) { /* @@ -1965,7 +1435,7 @@ xfs_inactive( if (S_ISREG(VFS_I(ip)->i_mode) && (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 || - ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0)) + xfs_inode_has_filedata(ip))) truncate = 1; if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { @@ -2024,39 +1494,6 @@ 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 +1528,11 @@ 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, @@ -2167,9 +1540,8 @@ xfs_iunlink_reload_next( xfs_agino_t next_agino) { struct xfs_perag *pag = agibp->b_pag; - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); struct xfs_inode *next_ip = NULL; - xfs_ino_t ino; int error; ASSERT(next_agino != NULLAGINO); @@ -2183,7 +1555,7 @@ xfs_iunlink_reload_next( xfs_info_ratelimited(mp, "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.", - next_agino, pag->pag_agno); + next_agino, pag_agno(pag)); /* * Use an untrusted lookup just to be cautious in case the AGI has been @@ -2191,8 +1563,8 @@ xfs_iunlink_reload_next( * but we'd rather shut down now since we're already running in a weird * situation. */ - ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino); - error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip); + error = xfs_iget(mp, tp, xfs_agino_to_ino(pag, next_agino), + XFS_IGET_UNTRUSTED, 0, &next_ip); if (error) { xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); return error; @@ -2208,194 +1580,13 @@ xfs_iunlink_reload_next( next_ip->i_prev_unlinked = prev_agino; trace_xfs_iunlink_reload_next(next_ip); rele: - ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE)); + ASSERT(!(inode_state_read_once(VFS_I(next_ip)) & I_DONTCACHE)); if (xfs_is_quotacheck_running(mp) && next_ip) xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED); xfs_irele(next_ip); 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; - - trace_xfs_iunlink_remove(ip); - - /* - * Get the index into the agi hash table for the list this inode will - * go on. Make sure the head pointer isn't garbage. - */ - head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); - if (!xfs_verify_agino(pag, head_agino)) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - agi, sizeof(*agi)); - xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); - return -EFSCORRUPTED; - } - - /* - * Set our inode's next_unlinked pointer to NULL and then return - * the old pointer value so that we can update whatever was previous - * to us in the list to point to whatever was next in the list. - */ - error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO); - if (error) - return error; - - /* - * Update the prev pointer in the next inode to point back to previous - * inode in the chain. - */ - error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, - ip->i_next_unlinked); - if (error == -ENOLINK) - error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked, - ip->i_next_unlinked); - if (error) - return error; - - if (head_agino != agino) { - struct xfs_inode *prev_ip; - - prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked); - if (!prev_ip) { - xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); - return -EFSCORRUPTED; - } - - error = xfs_iunlink_log_inode(tp, prev_ip, pag, - ip->i_next_unlinked); - prev_ip->i_next_unlinked = ip->i_next_unlinked; - } else { - /* Point the head of the list to the next unlinked inode. */ - error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, - ip->i_next_unlinked); - } - - ip->i_next_unlinked = NULLAGINO; - ip->i_prev_unlinked = 0; - return error; -} - -/* - * Pull the on-disk inode from the AGI unlinked list. - */ -int -xfs_iunlink_remove( - struct xfs_trans *tp, - struct xfs_perag *pag, - struct xfs_inode *ip) -{ - struct xfs_buf *agibp; - int error; - - trace_xfs_iunlink_remove(ip); - - /* Get the agi buffer first. It ensures lock ordering on the list. */ - error = xfs_read_agi(pag, tp, 0, &agibp); - if (error) - return error; - - return xfs_iunlink_remove_inode(tp, pag, agibp, ip); -} - /* * 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 @@ -2407,7 +1598,7 @@ xfs_ifree_mark_inode_stale( struct xfs_inode *free_ip, xfs_ino_t inum) { - struct xfs_mount *mp = pag->pag_mount; + struct xfs_mount *mp = pag_mount(pag); struct xfs_inode_log_item *iip; struct xfs_inode *ip; @@ -2455,7 +1646,7 @@ retry: iip = ip->i_itemp; if (__xfs_iflags_test(ip, XFS_IFLUSHING)) { ASSERT(!list_empty(&iip->ili_item.li_bio_list)); - ASSERT(iip->ili_last_fields); + ASSERT(iip->ili_last_fields || xlog_is_shutdown(mp->m_log)); goto out_iunlock; } @@ -2476,7 +1667,6 @@ retry: spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; - iip->ili_fsync_fields = 0; spin_unlock(&iip->ili_lock); ASSERT(iip->ili_last_fields); @@ -2541,8 +1731,7 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * igeo->blocks_per_cluster, - XBF_UNMAPPED, &bp); + mp->m_bsize * igeo->blocks_per_cluster, 0, &bp); if (error) return error; @@ -2614,36 +1803,10 @@ xfs_ifree( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); - /* - * Free the inode first so that we guarantee that the AGI lock is going - * to be taken before we remove the inode from the unlinked list. This - * makes the AGI lock -> unlinked list modification order the same as - * used in O_TMPFILE creation. - */ - error = xfs_difree(tp, pag, ip->i_ino, &xic); - if (error) - goto out; - - error = xfs_iunlink_remove(tp, pag, ip); + error = xfs_inode_uninit(tp, pag, ip, &xic); if (error) goto out; - /* - * Free any local-format data sitting around before we reset the - * data fork to extents format. Note that the attr fork data has - * already been freed by xfs_attr_inactive. - */ - if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) { - kfree(ip->i_df.if_data); - ip->i_df.if_data = NULL; - ip->i_df.if_bytes = 0; - } - - VFS_I(ip)->i_mode = 0; /* mark incore inode as free */ - ip->i_diflags = 0; - ip->i_diflags2 = mp->m_ino_geo.new_diflags2; - ip->i_forkoff = 0; /* mark the attr fork not in use */ - ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS; if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) xfs_iflags_clear(ip, XFS_IPRESERVE_DM_FIELDS); @@ -2652,13 +1815,6 @@ xfs_ifree( iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER); spin_unlock(&iip->ili_lock); - /* - * Bump the generation count so no one will be confused - * by reincarnations of this inode. - */ - VFS_I(ip)->i_generation++; - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (xic.deleted) error = xfs_ifree_cluster(tp, pag, ip, &xic); out: @@ -2675,12 +1831,20 @@ static void xfs_iunpin( struct xfs_inode *ip) { - xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); + struct xfs_inode_log_item *iip = ip->i_itemp; + xfs_csn_t seq = 0; trace_xfs_inode_unpin_nowait(ip, _RET_IP_); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); + + spin_lock(&iip->ili_lock); + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); + if (!seq) + return; /* Give the log a push to start the unpinning I/O */ - xfs_log_force_seq(ip->i_mount, ip->i_itemp->ili_commit_seq, 0, NULL); + xfs_log_force_seq(ip->i_mount, seq, 0, NULL); } @@ -2742,13 +1906,17 @@ xfs_remove( struct xfs_name *name, struct xfs_inode *ip) { + struct xfs_dir_update du = { + .dp = dp, + .name = name, + .ip = ip, + }; struct xfs_mount *mp = dp->i_mount; struct xfs_trans *tp = NULL; int is_dir = S_ISDIR(VFS_I(ip)->i_mode); int dontcare; int error = 0; uint resblks; - struct xfs_parent_args *ppargs; trace_xfs_remove(dp, name); @@ -2765,7 +1933,7 @@ xfs_remove( if (error) goto std_return; - error = xfs_parent_start(mp, &ppargs); + error = xfs_parent_start(mp, &du.ppargs); if (error) goto std_return; @@ -2788,76 +1956,10 @@ xfs_remove( goto out_parent; } - /* - * If we're removing a directory perform some additional validation. - */ - if (is_dir) { - ASSERT(VFS_I(ip)->i_nlink >= 2); - if (VFS_I(ip)->i_nlink != 2) { - error = -ENOTEMPTY; - goto out_trans_cancel; - } - if (!xfs_dir_isempty(ip)) { - error = -ENOTEMPTY; - goto out_trans_cancel; - } - - /* Drop the link from ip's "..". */ - error = xfs_droplink(tp, dp); - if (error) - goto out_trans_cancel; - - /* Drop the "." link from ip to self. */ - error = xfs_droplink(tp, ip); - if (error) - goto out_trans_cancel; - - /* - * Point the unlinked child directory's ".." entry to the root - * directory to eliminate back-references to inodes that may - * get freed before the child directory is closed. If the fs - * gets shrunk, this can lead to dirent inode validation errors. - */ - if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) { - error = xfs_dir_replace(tp, ip, &xfs_name_dotdot, - tp->t_mountp->m_sb.sb_rootino, 0); - if (error) - goto out_trans_cancel; - } - } else { - /* - * When removing a non-directory we need to log the parent - * inode here. For a directory this is done implicitly - * by the xfs_droplink call for the ".." entry. - */ - xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); - } - xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - - /* Drop the link from dp to ip. */ - error = xfs_droplink(tp, ip); + error = xfs_dir_remove_child(tp, resblks, &du); if (error) goto out_trans_cancel; - error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks); - if (error) { - ASSERT(error != -ENOENT); - goto out_trans_cancel; - } - - /* Remove parent pointer. */ - if (ppargs) { - error = xfs_parent_removename(tp, ppargs, dp, name, ip); - if (error) - goto out_trans_cancel; - } - - /* - * Drop the link from dp to ip, and if ip was a directory, remove the - * '.' and '..' references since we freed the directory. - */ - xfs_dir_update_hook(dp, ip, -1, name); - /* * If this is a synchronous mount, make sure that the * remove transaction goes to disk before returning to @@ -2875,7 +1977,7 @@ xfs_remove( xfs_iunlock(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: @@ -2884,7 +1986,7 @@ xfs_remove( xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_iunlock(dp, XFS_ILOCK_EXCL); out_parent: - xfs_parent_finish(mp, ppargs); + xfs_parent_finish(mp, du.ppargs); std_return: return error; } @@ -2964,160 +2066,6 @@ xfs_sort_inodes( } } -static int -xfs_finish_rename( - struct xfs_trans *tp) -{ - /* - * If this is a synchronous mount, make sure that the rename transaction - * goes to disk before returning to the user. - */ - if (xfs_has_wsync(tp->t_mountp) || xfs_has_dirsync(tp->t_mountp)) - xfs_trans_set_sync(tp); - - return xfs_trans_commit(tp); -} - -/* - * xfs_cross_rename() - * - * responsible for handling RENAME_EXCHANGE flag in renameat2() syscall - */ -STATIC int -xfs_cross_rename( - struct xfs_trans *tp, - struct xfs_inode *dp1, - struct xfs_name *name1, - struct xfs_inode *ip1, - struct xfs_parent_args *ip1_ppargs, - struct xfs_inode *dp2, - struct xfs_name *name2, - struct xfs_inode *ip2, - struct xfs_parent_args *ip2_ppargs, - int spaceres) -{ - int error = 0; - int ip1_flags = 0; - int ip2_flags = 0; - int dp2_flags = 0; - - /* Swap inode number for dirent in first parent */ - error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres); - if (error) - goto out_trans_abort; - - /* Swap inode number for dirent in second parent */ - error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres); - if (error) - goto out_trans_abort; - - /* - * If we're renaming one or more directories across different parents, - * update the respective ".." entries (and link counts) to match the new - * parents. - */ - if (dp1 != dp2) { - dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; - - if (S_ISDIR(VFS_I(ip2)->i_mode)) { - error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot, - dp1->i_ino, spaceres); - if (error) - goto out_trans_abort; - - /* transfer ip2 ".." reference to dp1 */ - if (!S_ISDIR(VFS_I(ip1)->i_mode)) { - error = xfs_droplink(tp, dp2); - if (error) - goto out_trans_abort; - xfs_bumplink(tp, dp1); - } - - /* - * Although ip1 isn't changed here, userspace needs - * to be warned about the change, so that applications - * relying on it (like backup ones), will properly - * notify the change - */ - ip1_flags |= XFS_ICHGTIME_CHG; - ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; - } - - if (S_ISDIR(VFS_I(ip1)->i_mode)) { - error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot, - dp2->i_ino, spaceres); - if (error) - goto out_trans_abort; - - /* transfer ip1 ".." reference to dp2 */ - if (!S_ISDIR(VFS_I(ip2)->i_mode)) { - error = xfs_droplink(tp, dp1); - if (error) - goto out_trans_abort; - xfs_bumplink(tp, dp2); - } - - /* - * Although ip2 isn't changed here, userspace needs - * to be warned about the change, so that applications - * relying on it (like backup ones), will properly - * notify the change - */ - ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; - ip2_flags |= XFS_ICHGTIME_CHG; - } - } - - /* Schedule parent pointer replacements */ - if (ip1_ppargs) { - error = xfs_parent_replacename(tp, ip1_ppargs, dp1, name1, dp2, - name2, ip1); - if (error) - goto out_trans_abort; - } - - if (ip2_ppargs) { - error = xfs_parent_replacename(tp, ip2_ppargs, dp2, name2, dp1, - name1, ip2); - if (error) - goto out_trans_abort; - } - - if (ip1_flags) { - xfs_trans_ichgtime(tp, ip1, ip1_flags); - xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE); - } - if (ip2_flags) { - xfs_trans_ichgtime(tp, ip2, ip2_flags); - xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE); - } - if (dp2_flags) { - xfs_trans_ichgtime(tp, dp2, dp2_flags); - xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE); - } - xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE); - - /* - * Inform our hook clients that we've finished an exchange operation as - * follows: removed the source and target files from their directories; - * added the target to the source directory; and added the source to - * the target directory. All inodes are locked, so it's ok to model a - * rename this way so long as we say we deleted entries before we add - * new ones. - */ - xfs_dir_update_hook(dp1, ip1, -1, name1); - xfs_dir_update_hook(dp2, ip2, -1, name2); - xfs_dir_update_hook(dp1, ip2, 1, name1); - xfs_dir_update_hook(dp2, ip1, 1, name2); - - return xfs_finish_rename(tp); - -out_trans_abort: - xfs_trans_cancel(tp); - return error; -} - /* * xfs_rename_alloc_whiteout() * @@ -3133,12 +2081,17 @@ xfs_rename_alloc_whiteout( struct xfs_inode *dp, struct xfs_inode **wip) { + struct xfs_icreate_args args = { + .idmap = idmap, + .pip = dp, + .mode = S_IFCHR | WHITEOUT_MODE, + .flags = XFS_ICREATE_TMPFILE, + }; struct xfs_inode *tmpfile; struct qstr name; int error; - error = xfs_create_tmpfile(idmap, dp, S_IFCHR | WHITEOUT_MODE, - xfs_has_parent(dp->i_mount), &tmpfile); + error = xfs_create_tmpfile(&args, &tmpfile); if (error) return error; @@ -3158,7 +2111,7 @@ xfs_rename_alloc_whiteout( */ xfs_setup_iops(tmpfile); xfs_finish_inode_setup(tmpfile); - VFS_I(tmpfile)->i_state |= I_LINKABLE; + inode_state_set_raw(VFS_I(tmpfile), I_LINKABLE); *wip = tmpfile; return 0; @@ -3178,13 +2131,20 @@ xfs_rename( struct xfs_inode *target_ip, unsigned int flags) { + struct xfs_dir_update du_src = { + .dp = src_dp, + .name = src_name, + .ip = src_ip, + }; + struct xfs_dir_update du_tgt = { + .dp = target_dp, + .name = target_name, + .ip = target_ip, + }; + struct xfs_dir_update du_wip = { }; struct xfs_mount *mp = src_dp->i_mount; struct xfs_trans *tp; - struct xfs_inode *wip = NULL; /* whiteout inode */ struct xfs_inode *inodes[__XFS_SORT_INODES]; - struct xfs_parent_args *src_ppargs = NULL; - struct xfs_parent_args *tgt_ppargs = NULL; - struct xfs_parent_args *wip_ppargs = NULL; int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); @@ -3204,8 +2164,8 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - error = xfs_rename_alloc_whiteout(idmap, src_name, - target_dp, &wip); + error = xfs_rename_alloc_whiteout(idmap, src_name, target_dp, + &du_wip.ip); if (error) return error; @@ -3213,21 +2173,21 @@ xfs_rename( src_name->type = XFS_DIR3_FT_CHRDEV; } - xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, wip, - inodes, &num_inodes); + xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, du_wip.ip, + inodes, &num_inodes); - error = xfs_parent_start(mp, &src_ppargs); + error = xfs_parent_start(mp, &du_src.ppargs); if (error) goto out_release_wip; - if (wip) { - error = xfs_parent_start(mp, &wip_ppargs); + if (du_wip.ip) { + error = xfs_parent_start(mp, &du_wip.ppargs); if (error) goto out_src_ppargs; } if (target_ip) { - error = xfs_parent_start(mp, &tgt_ppargs); + error = xfs_parent_start(mp, &du_tgt.ppargs); if (error) goto out_wip_ppargs; } @@ -3235,7 +2195,7 @@ xfs_rename( retry: nospace_error = 0; spaceres = xfs_rename_space_res(mp, src_name->len, target_ip != NULL, - target_name->len, wip != NULL); + target_name->len, du_wip.ip != NULL); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, spaceres, 0, 0, &tp); if (error == -ENOSPC) { nospace_error = error; @@ -3250,7 +2210,7 @@ retry: * We don't allow reservationless renaming when parent pointers are * enabled because we can't back out if the xattrs must grow. */ - if (src_ppargs && nospace_error) { + if (du_src.ppargs && nospace_error) { error = nospace_error; xfs_trans_cancel(tp); goto out_tgt_ppargs; @@ -3282,27 +2242,20 @@ retry: xfs_trans_ijoin(tp, src_ip, 0); if (target_ip) xfs_trans_ijoin(tp, target_ip, 0); - if (wip) - xfs_trans_ijoin(tp, wip, 0); + if (du_wip.ip) + xfs_trans_ijoin(tp, du_wip.ip, 0); - /* - * If we are using project inheritance, we only allow renames - * into our tree when the project IDs are the same; else the - * tree quota mechanism would be circumvented. - */ - if (unlikely((target_dp->i_diflags & XFS_DIFLAG_PROJINHERIT) && - target_dp->i_projid != src_ip->i_projid)) { - error = -EXDEV; + error = xfs_projid_differ(target_dp, src_ip); + if (error) goto out_trans_cancel; - } /* RENAME_EXCHANGE is unique from here on. */ if (flags & RENAME_EXCHANGE) { - error = xfs_cross_rename(tp, src_dp, src_name, src_ip, - src_ppargs, target_dp, target_name, target_ip, - tgt_ppargs, spaceres); - nospace_error = 0; - goto out_unlock; + error = xfs_dir_exchange_children(tp, &du_src, &du_tgt, + spaceres); + if (error) + goto out_trans_cancel; + goto out_commit; } /* @@ -3335,39 +2288,12 @@ retry: * We don't allow quotaless renaming when parent pointers are enabled * because we can't back out if the xattrs must grow. */ - if (src_ppargs && nospace_error) { + if (du_src.ppargs && nospace_error) { error = nospace_error; goto out_trans_cancel; } /* - * Check for expected errors before we dirty the transaction - * so we can return an error without a transaction abort. - */ - if (target_ip == NULL) { - /* - * If there's no space reservation, check the entry will - * fit before actually inserting it. - */ - if (!spaceres) { - error = xfs_dir_canenter(tp, target_dp, target_name); - if (error) - goto out_trans_cancel; - } - } else { - /* - * If target exists and it's a directory, check that whether - * it can be destroyed. - */ - if (S_ISDIR(VFS_I(target_ip)->i_mode) && - (!xfs_dir_isempty(target_ip) || - (VFS_I(target_ip)->i_nlink > 2))) { - error = -EEXIST; - goto out_trans_cancel; - } - } - - /* * Lock the AGI buffers we need to handle bumping the nlink of the * whiteout inode off the unlinked list and to handle dropping the * nlink of the target inode. Per locking order rules, do this in @@ -3378,7 +2304,7 @@ retry: * target_ip is either null or an empty directory. */ for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { - if (inodes[i] == wip || + if (inodes[i] == du_wip.ip || (inodes[i] == target_ip && (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { struct xfs_perag *pag; @@ -3393,188 +2319,29 @@ retry: } } - /* - * Directory entry creation below may acquire the AGF. Remove - * the whiteout from the unlinked list first to preserve correct - * AGI/AGF locking order. This dirties the transaction so failures - * after this point will abort and log recovery will clean up the - * mess. - * - * For whiteouts, we need to bump the link count on the whiteout - * inode. After this point, we have a real link, clear the tmpfile - * state flag from the inode so it doesn't accidentally get misused - * in future. - */ - if (wip) { - struct xfs_perag *pag; - - ASSERT(VFS_I(wip)->i_nlink == 0); - - pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, wip->i_ino)); - error = xfs_iunlink_remove(tp, pag, wip); - xfs_perag_put(pag); - if (error) - goto out_trans_cancel; - - xfs_bumplink(tp, wip); - VFS_I(wip)->i_state &= ~I_LINKABLE; - } - - /* - * Set up the target. - */ - if (target_ip == NULL) { - /* - * If target does not exist and the rename crosses - * directories, adjust the target directory link count - * to account for the ".." reference from the new entry. - */ - error = xfs_dir_createname(tp, target_dp, target_name, - src_ip->i_ino, spaceres); - if (error) - goto out_trans_cancel; - - xfs_trans_ichgtime(tp, target_dp, - XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - - if (new_parent && src_is_directory) { - xfs_bumplink(tp, target_dp); - } - } else { /* target_ip != NULL */ - /* - * Link the source inode under the target name. - * If the source inode is a directory and we are moving - * it across directories, its ".." entry will be - * inconsistent until we replace that down below. - * - * In case there is already an entry with the same - * name at the destination directory, remove it first. - */ - error = xfs_dir_replace(tp, target_dp, target_name, - src_ip->i_ino, spaceres); - if (error) - goto out_trans_cancel; - - xfs_trans_ichgtime(tp, target_dp, - XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - - /* - * Decrement the link count on the target since the target - * dir no longer points to it. - */ - error = xfs_droplink(tp, target_ip); - if (error) - goto out_trans_cancel; - - if (src_is_directory) { - /* - * Drop the link from the old "." entry. - */ - error = xfs_droplink(tp, target_ip); - if (error) - goto out_trans_cancel; - } - } /* target_ip != NULL */ - - /* - * Remove the source. - */ - if (new_parent && src_is_directory) { - /* - * Rewrite the ".." entry to point to the new - * directory. - */ - error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot, - target_dp->i_ino, spaceres); - ASSERT(error != -EEXIST); - if (error) - goto out_trans_cancel; - } - - /* - * We always want to hit the ctime on the source inode. - * - * This isn't strictly required by the standards since the source - * inode isn't really being changed, but old unix file systems did - * it and some incremental backup programs won't work without it. - */ - xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE); - - /* - * Adjust the link count on src_dp. This is necessary when - * renaming a directory, either within one parent when - * the target existed, or across two parent directories. - */ - if (src_is_directory && (new_parent || target_ip != NULL)) { + error = xfs_dir_rename_children(tp, &du_src, &du_tgt, spaceres, + &du_wip); + if (error) + goto out_trans_cancel; + if (du_wip.ip) { /* - * Decrement link count on src_directory since the - * entry that's moved no longer points to it. + * Now we have a real link, clear the "I'm a tmpfile" state + * flag from the inode so it doesn't accidentally get misused in + * future. */ - error = xfs_droplink(tp, src_dp); - if (error) - goto out_trans_cancel; + inode_state_clear_raw(VFS_I(du_wip.ip), I_LINKABLE); } +out_commit: /* - * For whiteouts, we only need to update the source dirent with the - * inode number of the whiteout inode rather than removing it - * altogether. + * If this is a synchronous mount, make sure that the rename + * transaction goes to disk before returning to the user. */ - if (wip) - error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino, - spaceres); - else - error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino, - spaceres); - - if (error) - goto out_trans_cancel; - - /* Schedule parent pointer updates. */ - if (wip_ppargs) { - error = xfs_parent_addname(tp, wip_ppargs, src_dp, src_name, - wip); - if (error) - goto out_trans_cancel; - } - - if (src_ppargs) { - error = xfs_parent_replacename(tp, src_ppargs, src_dp, - src_name, target_dp, target_name, src_ip); - if (error) - goto out_trans_cancel; - } - - if (tgt_ppargs) { - error = xfs_parent_removename(tp, tgt_ppargs, target_dp, - target_name, target_ip); - if (error) - goto out_trans_cancel; - } - - xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE); - if (new_parent) - xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); - - /* - * Inform our hook clients that we've finished a rename operation as - * follows: removed the source and target files from their directories; - * that we've added the source to the target directory; and finally - * that we've added the whiteout, if there was one. All inodes are - * locked, so it's ok to model a rename this way so long as we say we - * deleted entries before we add new ones. - */ - if (target_ip) - xfs_dir_update_hook(target_dp, target_ip, -1, target_name); - xfs_dir_update_hook(src_dp, src_ip, -1, src_name); - xfs_dir_update_hook(target_dp, src_ip, 1, target_name); - if (wip) - xfs_dir_update_hook(src_dp, wip, 1, src_name); + if (xfs_has_wsync(tp->t_mountp) || xfs_has_dirsync(tp->t_mountp)) + xfs_trans_set_sync(tp); - error = xfs_finish_rename(tp); + error = xfs_trans_commit(tp); nospace_error = 0; goto out_unlock; @@ -3583,14 +2350,14 @@ out_trans_cancel: out_unlock: xfs_iunlock_rename(inodes, num_inodes); out_tgt_ppargs: - xfs_parent_finish(mp, tgt_ppargs); + xfs_parent_finish(mp, du_tgt.ppargs); out_wip_ppargs: - xfs_parent_finish(mp, wip_ppargs); + xfs_parent_finish(mp, du_wip.ppargs); out_src_ppargs: - xfs_parent_finish(mp, src_ppargs); + xfs_parent_finish(mp, du_src.ppargs); out_release_wip: - if (wip) - xfs_irele(wip); + if (du_wip.ip) + xfs_irele(du_wip.ip); if (error == -ENOSPC && nospace_error) error = nospace_error; return error; @@ -3621,37 +2388,44 @@ xfs_iflush( * error handling as the caller will shutdown and fail the buffer. */ error = -EFSCORRUPTED; - if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC), - mp, XFS_ERRTAG_IFLUSH_1)) { + if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_IFLUSH_1)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad inode %llu magic number 0x%x, ptr "PTR_FMT, __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); goto flush_out; } - if (S_ISREG(VFS_I(ip)->i_mode)) { - if (XFS_TEST_ERROR( - ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE, - mp, XFS_ERRTAG_IFLUSH_3)) { + if (ip->i_df.if_format == XFS_DINODE_FMT_META_BTREE) { + if (!S_ISREG(VFS_I(ip)->i_mode) || + !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: Bad %s meta btree inode %Lu, ptr "PTR_FMT, + __func__, xfs_metafile_type_str(ip->i_metatype), + ip->i_ino, ip); + goto flush_out; + } + } else if (S_ISREG(VFS_I(ip)->i_mode)) { + if ((ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && + ip->i_df.if_format != XFS_DINODE_FMT_BTREE) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_IFLUSH_3)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad regular inode %llu, ptr "PTR_FMT, __func__, ip->i_ino, ip); goto flush_out; } } else if (S_ISDIR(VFS_I(ip)->i_mode)) { - if (XFS_TEST_ERROR( - ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && - ip->i_df.if_format != XFS_DINODE_FMT_BTREE && - ip->i_df.if_format != XFS_DINODE_FMT_LOCAL, - mp, XFS_ERRTAG_IFLUSH_4)) { + if ((ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS && + ip->i_df.if_format != XFS_DINODE_FMT_BTREE && + ip->i_df.if_format != XFS_DINODE_FMT_LOCAL) || + XFS_TEST_ERROR(mp, XFS_ERRTAG_IFLUSH_4)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad directory inode %llu, ptr "PTR_FMT, __func__, ip->i_ino, ip); goto flush_out; } } - if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af) > - ip->i_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) { + if (ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af) > + ip->i_nblocks || XFS_TEST_ERROR(mp, XFS_ERRTAG_IFLUSH_5)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: detected corrupt incore inode %llu, " "total extents = %llu nblocks = %lld, ptr "PTR_FMT, @@ -3660,14 +2434,22 @@ xfs_iflush( ip->i_nblocks, ip); goto flush_out; } - if (XFS_TEST_ERROR(ip->i_forkoff > mp->m_sb.sb_inodesize, - mp, XFS_ERRTAG_IFLUSH_6)) { + if (ip->i_forkoff > mp->m_sb.sb_inodesize || + XFS_TEST_ERROR(mp, XFS_ERRTAG_IFLUSH_6)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: bad inode %llu, forkoff 0x%x, ptr "PTR_FMT, __func__, ip->i_ino, ip->i_forkoff, ip); goto flush_out; } + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_META_BTREE) { + xfs_alert_tag(mp, XFS_PTAG_IFLUSH, + "%s: meta btree in inode %Lu attr fork, ptr "PTR_FMT, + __func__, ip->i_ino, ip); + goto flush_out; + } + /* * Inode item log recovery for v2 inodes are dependent on the flushiter * count for correct sequencing. We bump the flush iteration count so @@ -3729,7 +2511,7 @@ flush_out: spin_lock(&iip->ili_lock); iip->ili_last_fields = iip->ili_fields; iip->ili_fields = 0; - iip->ili_fsync_fields = 0; + set_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags); spin_unlock(&iip->ili_lock); /* @@ -3887,12 +2669,15 @@ int xfs_log_force_inode( struct xfs_inode *ip) { + struct xfs_inode_log_item *iip = ip->i_itemp; xfs_csn_t seq = 0; - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_ipincount(ip)) - seq = ip->i_itemp->ili_commit_seq; - xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (!iip) + return 0; + + spin_lock(&iip->ili_lock); + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); if (!seq) return 0; @@ -3960,21 +2745,16 @@ xfs_mmaplock_two_inodes_and_break_dax_layout( struct xfs_inode *ip2) { int error; - bool retry; - struct page *page; if (ip1->i_ino > ip2->i_ino) swap(ip1, ip2); again: - retry = false; /* Lock the first inode */ xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); - error = xfs_break_dax_layouts(VFS_I(ip1), &retry); - if (error || retry) { + error = xfs_break_dax_layouts(VFS_I(ip1)); + if (error) { xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); - if (error == 0 && retry) - goto again; return error; } @@ -3988,8 +2768,8 @@ again: * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable * for this nested lock case. */ - page = dax_layout_busy_page(VFS_I(ip2)->i_mapping); - if (page && page_ref_count(page) != 1) { + error = dax_break_layout(VFS_I(ip2), 0, -1, NULL); + if (error) { xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); goto again; @@ -4163,12 +2943,9 @@ xfs_inode_reload_unlinked( struct xfs_inode *ip) { struct xfs_trans *tp; - int error; - - error = xfs_trans_alloc_empty(ip->i_mount, &tp); - if (error) - return error; + int error = 0; + tp = xfs_trans_alloc_empty(ip->i_mount); xfs_ilock(ip, XFS_ILOCK_SHARED); if (xfs_inode_unlinked_incomplete(ip)) error = xfs_inode_reload_unlinked_bucket(tp, ip); @@ -4233,21 +3010,11 @@ xfs_wait_dax_page( int xfs_break_dax_layouts( - struct inode *inode, - bool *retry) + struct inode *inode) { - struct page *page; - xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL); - page = dax_layout_busy_page(inode->i_mapping); - if (!page) - return 0; - - *retry = true; - return ___wait_var_event(&page->_refcount, - atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, - 0, 0, xfs_wait_dax_page(inode)); + return dax_break_layout_inode(inode, xfs_wait_dax_page); } int @@ -4265,8 +3032,8 @@ xfs_break_layouts( retry = false; switch (reason) { case BREAK_UNMAP: - error = xfs_break_dax_layouts(inode, &retry); - if (error || retry) + error = xfs_break_dax_layouts(inode); + if (error) break; fallthrough; case BREAK_WRITE: @@ -4293,3 +3060,12 @@ xfs_inode_alloc_unitsize( return XFS_FSB_TO_B(ip->i_mount, blocks); } + +/* Should we always be using copy on write for file writes? */ +bool +xfs_is_always_cow_inode( + const struct xfs_inode *ip) +{ + return xfs_is_zoned_inode(ip) || + (ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount)); +} |