diff options
Diffstat (limited to 'fs/xfs/xfs_inode.c')
| -rw-r--r-- | fs/xfs/xfs_inode.c | 3764 |
1 files changed, 1621 insertions, 2143 deletions
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ae667ba74a1c..f1f88e48fe22 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3,7 +3,6 @@ * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ -#include <linux/log2.h> #include <linux/iversion.h> #include "xfs.h" @@ -12,19 +11,17 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" -#include "xfs_attr_sf.h" #include "xfs_attr.h" +#include "xfs_bit.h" #include "xfs_trans_space.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_inode_item.h" +#include "xfs_iunlink_item.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" @@ -32,7 +29,6 @@ #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_filestream.h" -#include "xfs_cksum.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_symlink.h" @@ -40,56 +36,16 @@ #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_reflink.h" -#include "xfs_dir2_priv.h" +#include "xfs_ag.h" +#include "xfs_log_priv.h" +#include "xfs_health.h" +#include "xfs_pnfs.h" +#include "xfs_parent.h" +#include "xfs_xattr.h" +#include "xfs_inode_util.h" +#include "xfs_metafile.h" -kmem_zone_t *xfs_inode_zone; - -/* - * Used in xfs_itruncate_extents(). This is the maximum number of extents - * freed from a file in a single transaction. - */ -#define XFS_ITRUNC_MAX_EXTENTS 2 - -STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *); -STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *); -STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *); - -/* - * helper function to extract extent size hint from inode - */ -xfs_extlen_t -xfs_get_extsz_hint( - struct xfs_inode *ip) -{ - if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize) - return ip->i_d.di_extsize; - if (XFS_IS_REALTIME_INODE(ip)) - 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_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) - a = ip->i_d.di_cowextsize; - b = xfs_get_extsz_hint(ip); - - a = max(a, b); - if (a == 0) - return XFS_DEFAULT_COWEXTSZ_HINT; - return a; -} +struct kmem_cache *xfs_inode_cache; /* * These two are wrapper routines around the xfs_ilock() routine used to @@ -112,8 +68,7 @@ xfs_ilock_data_map_shared( { uint lock_mode = XFS_ILOCK_SHARED; - if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE && - (ip->i_df.if_flags & XFS_IFEXTENTS) == 0) + if (xfs_need_iread_extents(&ip->i_df)) lock_mode = XFS_ILOCK_EXCL; xfs_ilock(ip, lock_mode); return lock_mode; @@ -125,16 +80,35 @@ xfs_ilock_attr_map_shared( { uint lock_mode = XFS_ILOCK_SHARED; - if (ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE && - (ip->i_afp->if_flags & XFS_IFEXTENTS) == 0) + if (xfs_inode_has_attr_fork(ip) && xfs_need_iread_extents(&ip->i_af)) lock_mode = XFS_ILOCK_EXCL; xfs_ilock(ip, lock_mode); return lock_mode; } /* + * You can't set both SHARED and EXCL for the same lock, + * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_MMAPLOCK_SHARED, + * XFS_MMAPLOCK_EXCL, XFS_ILOCK_SHARED, XFS_ILOCK_EXCL are valid values + * to set in lock_flags. + */ +static inline void +xfs_lock_flags_assert( + uint lock_flags) +{ + ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != + (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); + ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != + (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); + ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != + (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + ASSERT(lock_flags != 0); +} + +/* * In addition to i_rwsem in the VFS inode, the xfs inode contains 2 - * multi-reader locks: i_mmap_lock and the i_lock. This routine allows + * multi-reader locks: invalidate_lock and the i_lock. This routine allows * various combinations of the locks to be obtained. * * The 3 locks should always be ordered so that the IO lock is obtained first, @@ -142,23 +116,23 @@ xfs_ilock_attr_map_shared( * * Basic locking order: * - * i_rwsem -> i_mmap_lock -> page_lock -> i_ilock + * i_rwsem -> invalidate_lock -> page_lock -> i_ilock * - * mmap_sem locking order: + * mmap_lock locking order: * - * i_rwsem -> page lock -> mmap_sem - * mmap_sem -> i_mmap_lock -> page_lock + * i_rwsem -> page lock -> mmap_lock + * mmap_lock -> invalidate_lock -> page_lock * - * The difference in mmap_sem locking order mean that we cannot hold the - * i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can - * fault in pages during copy in/out (for buffered IO) or require the mmap_sem - * in get_user_pages() to map the user pages into the kernel address space for - * direct IO. Similarly the i_rwsem cannot be taken inside a page fault because - * page faults already hold the mmap_sem. + * The difference in mmap_lock locking order mean that we cannot hold the + * invalidate_lock over syscall based read(2)/write(2) based IO. These IO paths + * can fault in pages during copy in/out (for buffered IO) or require the + * mmap_lock in get_user_pages() to map the user pages into the kernel address + * space for direct IO. Similarly the i_rwsem cannot be taken inside a page + * fault because page faults already hold the mmap_lock. * * Hence to serialise fully against both syscall and mmap based IO, we need to - * take both the i_rwsem and the i_mmap_lock. These locks should *only* be both - * taken in places where we need to invalidate the page cache in a race + * take both the i_rwsem and the invalidate_lock. These locks should *only* be + * both taken in places where we need to invalidate the page cache in a race * free manner (e.g. truncate, hole punch and other extent manipulation * functions). */ @@ -169,18 +143,7 @@ xfs_ilock( { trace_xfs_ilock(ip, lock_flags, _RET_IP_); - /* - * You can't set both SHARED and EXCL for the same lock, - * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED, - * and XFS_ILOCK_EXCL are valid values to set in lock_flags. - */ - ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != - (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); - ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != - (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); - ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != - (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); - ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) { down_write_nested(&VFS_I(ip)->i_rwsem, @@ -190,15 +153,18 @@ xfs_ilock( XFS_IOLOCK_DEP(lock_flags)); } - if (lock_flags & XFS_MMAPLOCK_EXCL) - mrupdate_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags)); - else if (lock_flags & XFS_MMAPLOCK_SHARED) - mraccess_nested(&ip->i_mmaplock, XFS_MMAPLOCK_DEP(lock_flags)); + if (lock_flags & XFS_MMAPLOCK_EXCL) { + down_write_nested(&VFS_I(ip)->i_mapping->invalidate_lock, + XFS_MMAPLOCK_DEP(lock_flags)); + } else if (lock_flags & XFS_MMAPLOCK_SHARED) { + down_read_nested(&VFS_I(ip)->i_mapping->invalidate_lock, + XFS_MMAPLOCK_DEP(lock_flags)); + } if (lock_flags & XFS_ILOCK_EXCL) - mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); + down_write_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); else if (lock_flags & XFS_ILOCK_SHARED) - mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); + down_read_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags)); } /* @@ -220,18 +186,7 @@ xfs_ilock_nowait( { trace_xfs_ilock_nowait(ip, lock_flags, _RET_IP_); - /* - * You can't set both SHARED and EXCL for the same lock, - * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED, - * and XFS_ILOCK_EXCL are valid values to set in lock_flags. - */ - ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != - (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); - ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != - (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); - ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != - (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); - ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); + xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) { if (!down_write_trylock(&VFS_I(ip)->i_rwsem)) @@ -242,27 +197,27 @@ xfs_ilock_nowait( } if (lock_flags & XFS_MMAPLOCK_EXCL) { - if (!mrtryupdate(&ip->i_mmaplock)) + if (!down_write_trylock(&VFS_I(ip)->i_mapping->invalidate_lock)) goto out_undo_iolock; } else if (lock_flags & XFS_MMAPLOCK_SHARED) { - if (!mrtryaccess(&ip->i_mmaplock)) + if (!down_read_trylock(&VFS_I(ip)->i_mapping->invalidate_lock)) goto out_undo_iolock; } if (lock_flags & XFS_ILOCK_EXCL) { - if (!mrtryupdate(&ip->i_lock)) + if (!down_write_trylock(&ip->i_lock)) goto out_undo_mmaplock; } else if (lock_flags & XFS_ILOCK_SHARED) { - if (!mrtryaccess(&ip->i_lock)) + if (!down_read_trylock(&ip->i_lock)) goto out_undo_mmaplock; } return 1; out_undo_mmaplock: if (lock_flags & XFS_MMAPLOCK_EXCL) - mrunlock_excl(&ip->i_mmaplock); + up_write(&VFS_I(ip)->i_mapping->invalidate_lock); else if (lock_flags & XFS_MMAPLOCK_SHARED) - mrunlock_shared(&ip->i_mmaplock); + up_read(&VFS_I(ip)->i_mapping->invalidate_lock); out_undo_iolock: if (lock_flags & XFS_IOLOCK_EXCL) up_write(&VFS_I(ip)->i_rwsem); @@ -289,19 +244,7 @@ xfs_iunlock( xfs_inode_t *ip, uint lock_flags) { - /* - * You can't set both SHARED and EXCL for the same lock, - * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED, - * and XFS_ILOCK_EXCL are valid values to set in lock_flags. - */ - ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) != - (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)); - ASSERT((lock_flags & (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)) != - (XFS_MMAPLOCK_SHARED | XFS_MMAPLOCK_EXCL)); - ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) != - (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); - ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_SUBCLASS_MASK)) == 0); - ASSERT(lock_flags != 0); + xfs_lock_flags_assert(lock_flags); if (lock_flags & XFS_IOLOCK_EXCL) up_write(&VFS_I(ip)->i_rwsem); @@ -309,14 +252,14 @@ xfs_iunlock( up_read(&VFS_I(ip)->i_rwsem); if (lock_flags & XFS_MMAPLOCK_EXCL) - mrunlock_excl(&ip->i_mmaplock); + up_write(&VFS_I(ip)->i_mapping->invalidate_lock); else if (lock_flags & XFS_MMAPLOCK_SHARED) - mrunlock_shared(&ip->i_mmaplock); + up_read(&VFS_I(ip)->i_mapping->invalidate_lock); if (lock_flags & XFS_ILOCK_EXCL) - mrunlock_excl(&ip->i_lock); + up_write(&ip->i_lock); else if (lock_flags & XFS_ILOCK_SHARED) - mrunlock_shared(&ip->i_lock); + up_read(&ip->i_lock); trace_xfs_iunlock(ip, lock_flags, _RET_IP_); } @@ -335,44 +278,39 @@ xfs_ilock_demote( ~(XFS_IOLOCK_EXCL|XFS_MMAPLOCK_EXCL|XFS_ILOCK_EXCL)) == 0); if (lock_flags & XFS_ILOCK_EXCL) - mrdemote(&ip->i_lock); + downgrade_write(&ip->i_lock); if (lock_flags & XFS_MMAPLOCK_EXCL) - mrdemote(&ip->i_mmaplock); + downgrade_write(&VFS_I(ip)->i_mapping->invalidate_lock); if (lock_flags & XFS_IOLOCK_EXCL) downgrade_write(&VFS_I(ip)->i_rwsem); trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_); } -#if defined(DEBUG) || defined(XFS_WARN) -int -xfs_isilocked( - xfs_inode_t *ip, +void +xfs_assert_ilocked( + struct xfs_inode *ip, uint lock_flags) { - if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) { - if (!(lock_flags & XFS_ILOCK_SHARED)) - return !!ip->i_lock.mr_writer; - return rwsem_is_locked(&ip->i_lock.mr_lock); - } - - if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) { - if (!(lock_flags & XFS_MMAPLOCK_SHARED)) - return !!ip->i_mmaplock.mr_writer; - return rwsem_is_locked(&ip->i_mmaplock.mr_lock); - } + /* + * Sometimes we assert the ILOCK is held exclusively, but we're in + * a workqueue, so lockdep doesn't know we're the owner. + */ + if (lock_flags & XFS_ILOCK_SHARED) + rwsem_assert_held(&ip->i_lock); + else if (lock_flags & XFS_ILOCK_EXCL) + rwsem_assert_held_write_nolockdep(&ip->i_lock); - if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) { - if (!(lock_flags & XFS_IOLOCK_SHARED)) - return !debug_locks || - lockdep_is_held_type(&VFS_I(ip)->i_rwsem, 0); - return rwsem_is_locked(&VFS_I(ip)->i_rwsem); - } + if (lock_flags & XFS_MMAPLOCK_SHARED) + rwsem_assert_held(&VFS_I(ip)->i_mapping->invalidate_lock); + else if (lock_flags & XFS_MMAPLOCK_EXCL) + rwsem_assert_held_write(&VFS_I(ip)->i_mapping->invalidate_lock); - ASSERT(0); - return 0; + if (lock_flags & XFS_IOLOCK_SHARED) + rwsem_assert_held(&VFS_I(ip)->i_rwsem); + else if (lock_flags & XFS_IOLOCK_EXCL) + rwsem_assert_held_write(&VFS_I(ip)->i_rwsem); } -#endif /* * xfs_lockdep_subclass_ok() is only used in an ASSERT, so is only called when @@ -397,13 +335,14 @@ xfs_lockdep_subclass_ok( * parent locking. Care must be taken to ensure we don't overrun the subclass * storage fields in the class mask we build. */ -static inline int -xfs_lock_inumorder(int lock_mode, int subclass) +static inline uint +xfs_lock_inumorder( + uint lock_mode, + uint subclass) { - int class = 0; + 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)) { @@ -439,19 +378,22 @@ xfs_lock_inumorder(int lock_mode, int subclass) * lock more than one at a time, lockdep will report false positives saying we * have violated locking orders. */ -static void +void xfs_lock_inodes( - xfs_inode_t **ips, - int inodes, - uint lock_mode) + struct xfs_inode **ips, + int inodes, + uint lock_mode) { - int attempts = 0, i, j, try_lock; - xfs_log_item_t *lp; + int attempts = 0; + uint i; + int j; + bool try_lock; + struct xfs_log_item *lp; /* * Currently supports between 2 and 5 inodes with exclusive locking. We * support an arbitrary depth of locking here, but absolute limits on - * inodes depend on the the type of locking and the limits placed by + * inodes depend on the type of locking and the limits placed by * lockdep annotations in xfs_lock_inumorder. These are all checked by * the asserts. */ @@ -470,9 +412,9 @@ xfs_lock_inodes( } else if (lock_mode & XFS_MMAPLOCK_EXCL) ASSERT(!(lock_mode & XFS_ILOCK_EXCL)); - try_lock = 0; - i = 0; again: + try_lock = false; + i = 0; for (; i < inodes; i++) { ASSERT(ips[i]); @@ -485,9 +427,9 @@ again: */ if (!try_lock) { for (j = (i - 1); j >= 0 && !try_lock; j--) { - lp = (xfs_log_item_t *)ips[j]->i_itemp; + lp = &ips[j]->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) - try_lock++; + try_lock = true; } } @@ -527,19 +469,15 @@ again: if ((attempts % 5) == 0) { delay(1); /* Don't just spin the CPU */ } - i = 0; - try_lock = 0; goto again; } } /* - * xfs_lock_two_inodes() can only be used to lock one type of lock at a time - - * the mmaplock or the ilock, but not more than one type at a time. If we lock - * more than one at a time, lockdep will report false positives saying we have - * violated locking orders. The iolock must be double-locked separately since - * we use i_rwsem for that. We now support taking one lock EXCL and the other - * SHARED. + * xfs_lock_two_inodes() can only be used to lock ilock. The iolock and + * mmaplock must be double-locked separately since we use i_rwsem and + * invalidate_lock for that. We now support taking one lock EXCL and the + * other SHARED. */ void xfs_lock_two_inodes( @@ -548,33 +486,20 @@ xfs_lock_two_inodes( struct xfs_inode *ip1, uint ip1_mode) { - struct xfs_inode *temp; - uint mode_temp; int attempts = 0; - xfs_log_item_t *lp; + struct xfs_log_item *lp; ASSERT(hweight32(ip0_mode) == 1); ASSERT(hweight32(ip1_mode) == 1); ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))); ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))); - ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) || - !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); - ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) || - !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); - ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) || - !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); - ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) || - !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))); - + ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); + ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))); ASSERT(ip0->i_ino != ip1->i_ino); if (ip0->i_ino > ip1->i_ino) { - temp = ip0; - ip0 = ip1; - ip1 = temp; - mode_temp = ip0_mode; - ip0_mode = ip1_mode; - ip1_mode = mode_temp; + swap(ip0, ip1); + swap(ip0_mode, ip1_mode); } again: @@ -585,7 +510,7 @@ xfs_lock_two_inodes( * the second lock. If we can't get it, we must release the first one * and try again. */ - lp = (xfs_log_item_t *)ip0->i_itemp; + lp = &ip0->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) { if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) { xfs_iunlock(ip0, ip0_mode); @@ -598,83 +523,6 @@ xfs_lock_two_inodes( } } -void -__xfs_iflock( - struct xfs_inode *ip) -{ - wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT); - DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT); - - do { - prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - if (xfs_isiflocked(ip)) - io_schedule(); - } while (!xfs_iflock_nowait(ip)); - - finish_wait(wq, &wait.wq_entry); -} - -STATIC uint -_xfs_dic2xflags( - uint16_t di_flags, - uint64_t di_flags2, - bool has_attr) -{ - uint flags = 0; - - if (di_flags & XFS_DIFLAG_ANY) { - if (di_flags & XFS_DIFLAG_REALTIME) - flags |= FS_XFLAG_REALTIME; - if (di_flags & XFS_DIFLAG_PREALLOC) - flags |= FS_XFLAG_PREALLOC; - if (di_flags & XFS_DIFLAG_IMMUTABLE) - flags |= FS_XFLAG_IMMUTABLE; - if (di_flags & XFS_DIFLAG_APPEND) - flags |= FS_XFLAG_APPEND; - if (di_flags & XFS_DIFLAG_SYNC) - flags |= FS_XFLAG_SYNC; - if (di_flags & XFS_DIFLAG_NOATIME) - flags |= FS_XFLAG_NOATIME; - if (di_flags & XFS_DIFLAG_NODUMP) - flags |= FS_XFLAG_NODUMP; - if (di_flags & XFS_DIFLAG_RTINHERIT) - flags |= FS_XFLAG_RTINHERIT; - if (di_flags & XFS_DIFLAG_PROJINHERIT) - flags |= FS_XFLAG_PROJINHERIT; - if (di_flags & XFS_DIFLAG_NOSYMLINKS) - flags |= FS_XFLAG_NOSYMLINKS; - if (di_flags & XFS_DIFLAG_EXTSIZE) - flags |= FS_XFLAG_EXTSIZE; - if (di_flags & XFS_DIFLAG_EXTSZINHERIT) - flags |= FS_XFLAG_EXTSZINHERIT; - if (di_flags & XFS_DIFLAG_NODEFRAG) - flags |= FS_XFLAG_NODEFRAG; - if (di_flags & XFS_DIFLAG_FILESTREAM) - flags |= FS_XFLAG_FILESTREAM; - } - - if (di_flags2 & XFS_DIFLAG2_ANY) { - if (di_flags2 & XFS_DIFLAG2_DAX) - flags |= FS_XFLAG_DAX; - if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE) - flags |= FS_XFLAG_COWEXTSIZE; - } - - if (has_attr) - flags |= FS_XFLAG_HASATTR; - - return flags; -} - -uint -xfs_ip2xflags( - struct xfs_inode *ip) -{ - struct xfs_icdinode *dic = &ip->i_d; - - return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip)); -} - /* * 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, @@ -683,9 +531,9 @@ xfs_ip2xflags( */ int xfs_lookup( - xfs_inode_t *dp, - struct xfs_name *name, - xfs_inode_t **ipp, + struct xfs_inode *dp, + const struct xfs_name *name, + struct xfs_inode **ipp, struct xfs_name *ci_name) { xfs_ino_t inum; @@ -693,7 +541,9 @@ xfs_lookup( trace_xfs_lookup(dp, name); - if (XFS_FORCED_SHUTDOWN(dp->i_mount)) + if (xfs_is_shutdown(dp->i_mount)) + return -EIO; + if (xfs_ifork_zapped(dp, XFS_DATA_FORK)) return -EIO; error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name); @@ -704,246 +554,56 @@ 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) - kmem_free(ci_name->name); + kfree(ci_name->name); out_unlock: *ipp = NULL; return error; } /* - * Allocate an inode on disk and return a copy of its in-core version. - * The in-core inode is locked exclusively. Set mode, nlink, and rdev - * appropriately within the inode. The uid and gid for the inode are - * set according to the contents of the given cred structure. + * Initialise a newly allocated inode and return the in-core inode to the + * caller locked exclusively. * - * Use xfs_dialloc() to allocate the on-disk inode. If xfs_dialloc() - * has a free inode available, call xfs_iget() to obtain the in-core - * version of the allocated inode. Finally, fill in the inode and - * log its initial contents. In this case, ialloc_context would be - * set to NULL. - * - * If xfs_dialloc() does not have an available inode, it will replenish - * its supply by doing an allocation. Since we can only do one - * allocation within a transaction without deadlocks, we must commit - * the current transaction before returning the inode itself. - * In this case, therefore, we will set ialloc_context and return. - * The caller should then commit the current transaction, start a new - * transaction, and call xfs_ialloc() again to actually get the inode. - * - * To ensure that some other process does not grab the inode that - * was allocated during the first call to xfs_ialloc(), this routine - * also returns the [locked] bp pointing to the head of the freelist - * as ialloc_context. The caller should hold this buffer across - * the commit and pass it back into this routine on the second call. - * - * If we are allocating quota inodes, we do not have a parent inode - * to attach to or associate with (i.e. pip == NULL) because they - * are not linked into the directory structure - they are attached - * directly to the superblock - and so have no parent. + * Caller is responsible for unlocking the inode manually upon return */ -static int -xfs_ialloc( - xfs_trans_t *tp, - xfs_inode_t *pip, - umode_t mode, - xfs_nlink_t nlink, - dev_t rdev, - prid_t prid, - xfs_buf_t **ialloc_context, - xfs_inode_t **ipp) +int +xfs_icreate( + struct xfs_trans *tp, + xfs_ino_t ino, + const struct xfs_icreate_args *args, + struct xfs_inode **ipp) { - struct xfs_mount *mp = tp->t_mountp; - xfs_ino_t ino; - xfs_inode_t *ip; - uint flags; - int error; - struct timespec64 tv; - struct inode *inode; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_inode *ip = NULL; + int error; /* - * Call the space management code to pick - * the on-disk inode to be allocated. + * Get the in-core inode with the lock held exclusively to prevent + * others from looking at until we're done. */ - error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, - ialloc_context, &ino); + error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip); if (error) return error; - if (*ialloc_context || ino == NULLFSINO) { - *ipp = NULL; - return 0; - } - ASSERT(*ialloc_context == NULL); - /* - * 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); - return -EFSCORRUPTED; - } - - /* - * Get the in-core inode with the lock held exclusively. - * This is because we're setting fields here we need - * to prevent others from looking at until we're done. - */ - error = xfs_iget(mp, tp, ino, XFS_IGET_CREATE, - XFS_ILOCK_EXCL, &ip); - if (error) - return error; ASSERT(ip != NULL); - inode = VFS_I(ip); - - /* - * We always convert v1 inodes to v2 now - we only support filesystems - * with >= v2 inode capability, so there is no reason for ever leaving - * an inode in v1 format. - */ - if (ip->i_d.di_version == 1) - ip->i_d.di_version = 2; - - inode->i_mode = mode; - set_nlink(inode, nlink); - ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid()); - ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid()); - inode->i_rdev = rdev; - xfs_set_projid(ip, prid); - - if (pip && XFS_INHERIT_GID(pip)) { - ip->i_d.di_gid = pip->i_d.di_gid; - if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode)) - inode->i_mode |= S_ISGID; - } - - /* - * 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) && - (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid)))) - inode->i_mode &= ~S_ISGID; - - ip->i_d.di_size = 0; - ip->i_d.di_nextents = 0; - ASSERT(ip->i_d.di_nblocks == 0); - - tv = current_time(inode); - inode->i_mtime = tv; - inode->i_atime = tv; - inode->i_ctime = tv; - - ip->i_d.di_extsize = 0; - ip->i_d.di_dmevmask = 0; - ip->i_d.di_dmstate = 0; - ip->i_d.di_flags = 0; - - if (ip->i_d.di_version == 3) { - inode_set_iversion(inode, 1); - ip->i_d.di_flags2 = 0; - ip->i_d.di_cowextsize = 0; - ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec; - ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec; - } - - - flags = XFS_ILOG_CORE; - switch (mode & S_IFMT) { - case S_IFIFO: - case S_IFCHR: - case S_IFBLK: - case S_IFSOCK: - ip->i_d.di_format = XFS_DINODE_FMT_DEV; - ip->i_df.if_flags = 0; - flags |= XFS_ILOG_DEV; - break; - case S_IFREG: - case S_IFDIR: - if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint di_flags = 0; - - if (S_ISDIR(mode)) { - if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) - di_flags |= XFS_DIFLAG_RTINHERIT; - if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) { - di_flags |= XFS_DIFLAG_EXTSZINHERIT; - ip->i_d.di_extsize = pip->i_d.di_extsize; - } - if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) - di_flags |= XFS_DIFLAG_PROJINHERIT; - } else if (S_ISREG(mode)) { - if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) - di_flags |= XFS_DIFLAG_REALTIME; - if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) { - di_flags |= XFS_DIFLAG_EXTSIZE; - ip->i_d.di_extsize = pip->i_d.di_extsize; - } - } - if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) && - xfs_inherit_noatime) - di_flags |= XFS_DIFLAG_NOATIME; - if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) && - xfs_inherit_nodump) - di_flags |= XFS_DIFLAG_NODUMP; - if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) && - xfs_inherit_sync) - di_flags |= XFS_DIFLAG_SYNC; - if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) && - xfs_inherit_nosymlinks) - di_flags |= XFS_DIFLAG_NOSYMLINKS; - if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) && - xfs_inherit_nodefrag) - di_flags |= XFS_DIFLAG_NODEFRAG; - if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) - di_flags |= XFS_DIFLAG_FILESTREAM; - - ip->i_d.di_flags |= di_flags; - } - if (pip && - (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && - pip->i_d.di_version == 3 && - ip->i_d.di_version == 3) { - uint64_t di_flags2 = 0; - - if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; - ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; - } - if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; - - ip->i_d.di_flags2 |= di_flags2; - } - /* FALLTHROUGH */ - case S_IFLNK: - ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS; - ip->i_df.if_flags = XFS_IFEXTENTS; - ip->i_df.if_bytes = 0; - ip->i_df.if_u1.if_root = NULL; - break; - default: - ASSERT(0); - } - /* - * Attribute fork settings for new inode. - */ - ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS; - ip->i_d.di_anextents = 0; - - /* - * Log the new values stuffed into the inode. - */ - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - xfs_trans_log_inode(tp, ip, flags); + xfs_trans_ijoin(tp, ip, 0); + xfs_inode_init(tp, args, ip); /* now that we have an i_mode we can setup the inode structure */ xfs_setup_inode(ip); @@ -952,300 +612,135 @@ xfs_ialloc( return 0; } -/* - * Allocates a new inode from disk and return a pointer to the - * incore copy. This routine will internally commit the current - * transaction and allocate a new one if the Space Manager needed - * to do an allocation to replenish the inode free-list. - * - * This routine is designed to be called from xfs_create and - * xfs_create_dir. - * - */ +/* Return dquots for the ids that will be assigned to a new file. */ int -xfs_dir_ialloc( - xfs_trans_t **tpp, /* input: current transaction; - output: may be a new transaction. */ - xfs_inode_t *dp, /* directory within whose allocate - the inode. */ - umode_t mode, - xfs_nlink_t nlink, - dev_t rdev, - prid_t prid, /* project id */ - xfs_inode_t **ipp) /* pointer to inode; it will be - locked. */ +xfs_icreate_dqalloc( + const struct xfs_icreate_args *args, + struct xfs_dquot **udqpp, + struct xfs_dquot **gdqpp, + struct xfs_dquot **pdqpp) { - xfs_trans_t *tp; - xfs_inode_t *ip; - xfs_buf_t *ialloc_context = NULL; - int code; - void *dqinfo; - uint tflags; - - tp = *tpp; - ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); - - /* - * xfs_ialloc will return a pointer to an incore inode if - * the Space Manager has an available inode on the free - * list. Otherwise, it will do an allocation and replenish - * the freelist. Since we can only do one allocation per - * transaction without deadlocks, we will need to commit the - * current transaction and start a new one. We will then - * need to call xfs_ialloc again to get the inode. - * - * If xfs_ialloc did an allocation to replenish the freelist, - * it returns the bp containing the head of the freelist as - * ialloc_context. We will hold a lock on it across the - * transaction commit so that no other process can steal - * the inode(s) that we've just allocated. - */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context, - &ip); - - /* - * Return an error if we were unable to allocate a new inode. - * This should only happen if we run out of space on disk or - * encounter a disk error. - */ - if (code) { - *ipp = NULL; - return code; - } - if (!ialloc_context && !ip) { - *ipp = NULL; - return -ENOSPC; - } - - /* - * If the AGI buffer is non-NULL, then we were unable to get an - * inode in one operation. We need to commit the current - * transaction and call xfs_ialloc() again. It is guaranteed - * to succeed the second time. - */ - if (ialloc_context) { - /* - * Normally, xfs_trans_commit releases all the locks. - * We call bhold to hang on to the ialloc_context across - * the commit. Holding this buffer prevents any other - * processes from doing any allocations in this - * allocation group. - */ - xfs_trans_bhold(tp, ialloc_context); - - /* - * We want the quota changes to be associated with the next - * transaction, NOT this one. So, detach the dqinfo from this - * and attach it to the next transaction. - */ - dqinfo = NULL; - tflags = 0; - if (tp->t_dqinfo) { - dqinfo = (void *)tp->t_dqinfo; - tp->t_dqinfo = NULL; - tflags = tp->t_flags & XFS_TRANS_DQ_DIRTY; - tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY); - } - - code = xfs_trans_roll(&tp); - - /* - * Re-attach the quota info that we detached from prev trx. - */ - if (dqinfo) { - tp->t_dqinfo = dqinfo; - tp->t_flags |= tflags; - } - - if (code) { - xfs_buf_relse(ialloc_context); - *tpp = tp; - *ipp = NULL; - return code; - } - xfs_trans_bjoin(tp, ialloc_context); + 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) { /* - * Call ialloc again. Since we've locked out all - * other allocations in this allocation group, - * this call should always succeed. + * 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. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, - &ialloc_context, &ip); - - /* - * If we get an error at this point, return to the caller - * so that the current transaction can be aborted. - */ - if (code) { - *tpp = tp; - *ipp = NULL; - return code; - } - ASSERT(!ialloc_context && ip); - + 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; } - *ipp = ip; - *tpp = tp; - - 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(). - */ -static int /* error */ -xfs_droplink( - xfs_trans_t *tp, - xfs_inode_t *ip) -{ - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); - - drop_nlink(VFS_I(ip)); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - if (VFS_I(ip)->i_nlink) - return 0; - - return xfs_iunlink(tp, ip); -} + *udqpp = *gdqpp = *pdqpp = NULL; -/* - * Increment the link count on an inode & log the change. - */ -static int -xfs_bumplink( - xfs_trans_t *tp, - xfs_inode_t *ip) -{ - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); - - ASSERT(ip->i_d.di_version > 1); - inc_nlink(VFS_I(ip)); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - return 0; + return xfs_qm_vop_dqalloc(args->pip, uid, gid, prid, flags, udqpp, + gdqpp, pdqpp); } int xfs_create( - xfs_inode_t *dp, + const struct xfs_icreate_args *args, struct xfs_name *name, - umode_t mode, - dev_t rdev, - 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; + xfs_ino_t ino; + bool unlock_dp_on_error = false; + bool is_dir = S_ISDIR(args->mode); uint resblks; + int error; trace_xfs_create(dp, name); - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) + return -EIO; + 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, xfs_kuid_to_uid(current_fsuid()), - xfs_kgid_to_gid(current_fsgid()), 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; if (is_dir) { - resblks = XFS_MKDIR_SPACE_RES(mp, name->len); + resblks = xfs_mkdir_space_res(mp, name->len); tres = &M_RES(mp)->tr_mkdir; } else { - resblks = XFS_CREATE_SPACE_RES(mp, name->len); + resblks = xfs_create_space_res(mp, name->len); tres = &M_RES(mp)->tr_create; } + error = xfs_parent_start(mp, &du.ppargs); + if (error) + goto out_release_dquots; + /* * Initially assume that the file does not exist and * reserve the resources for that case. If that is not * the case we'll drop the one we have and get a more * appropriate transaction later. */ - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error == -ENOSPC) { /* flush outstanding delalloc blocks and retry */ xfs_flush_inodes(mp); - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, + resblks, &tp); } if (error) - goto out_release_inode; + goto out_parent; xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = true; /* - * Reserve disk quota and the inode. - */ - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); - if (error) - goto out_trans_cancel; - - /* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip); + error = xfs_dialloc(&tp, args, &ino); + if (!error) + error = xfs_icreate(tp, ino, args, &du.ip); if (error) goto out_trans_cancel; /* * Now we join the directory inode to the transaction. We do not do it - * earlier because xfs_dir_ialloc might commit the previous transaction + * earlier because xfs_dialloc might commit the previous transaction * (and release all the locks). An error from here on will result in * the transaction cancel unlocking dp so don't do it explicitly in the * error path. */ - xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); - unlock_dp_on_error = false; + xfs_trans_ijoin(tp, dp, 0); - error = xfs_dir_createname(tp, dp, name, ip->i_ino, - resblks ? - resblks - XFS_IALLOC_SPACE_RES(mp) : 0); - 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; - - error = xfs_bumplink(tp, dp); - if (error) - goto out_trans_cancel; - } /* * If this is a synchronous mount, make sure that the * create transaction goes to disk before returning to * the user. */ - if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) + if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); /* @@ -1253,7 +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) @@ -1263,7 +758,10 @@ xfs_create( xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); - *ipp = ip; + *ipp = du.ip; + xfs_iunlock(du.ip, XFS_ILOCK_EXCL); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + xfs_parent_finish(mp, du.ppargs); return 0; out_trans_cancel: @@ -1274,11 +772,14 @@ xfs_create( * setup of the inode and release the inode. This prevents recursive * transactions and deadlocks from xfs_inactive. */ - if (ip) { - 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, du.ppargs); + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1290,53 +791,46 @@ xfs_create( int xfs_create_tmpfile( - struct xfs_inode *dp, - umode_t mode, + 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; + xfs_ino_t ino; uint resblks; + int error; - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; + ASSERT(args->flags & XFS_ICREATE_TMPFILE); - prid = xfs_get_initial_prid(dp); + if (xfs_is_shutdown(mp)) + return -EIO; - /* - * Make sure that we have allocated dquot(s) on disk. - */ - error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()), - xfs_kgid_to_gid(current_fsgid()), 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; resblks = XFS_IALLOC_SPACE_RES(mp); tres = &M_RES(mp)->tr_create_tmpfile; - error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error) - goto out_release_inode; - - error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp, - pdqp, resblks, 1, 0); + error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks, + &tp); if (error) - goto out_trans_cancel; + goto out_release_dquots; - error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, prid, &ip); + error = xfs_dialloc(&tp, args, &ino); + if (!error) + error = xfs_icreate(tp, ino, args, &ip); if (error) goto out_trans_cancel; - if (mp->m_flags & XFS_MOUNT_WSYNC) + if (xfs_has_wsync(mp)) xfs_trans_set_sync(tp); /* @@ -1359,6 +853,7 @@ xfs_create_tmpfile( xfs_qm_dqrele(pdqp); *ipp = ip; + xfs_iunlock(ip, XFS_ILOCK_EXCL); return 0; out_trans_cancel: @@ -1370,10 +865,11 @@ xfs_create_tmpfile( * transactions and deadlocks from xfs_inactive. */ if (ip) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_finish_inode_setup(ip); xfs_irele(ip); } - + out_release_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); xfs_qm_dqrele(pdqp); @@ -1381,22 +877,58 @@ 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( - xfs_inode_t *tdp, - xfs_inode_t *sip, + struct xfs_inode *tdp, + struct xfs_inode *sip, struct xfs_name *target_name) { - xfs_mount_t *mp = tdp->i_mount; - xfs_trans_t *tp; - int error; + 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; trace_xfs_link(tdp, target_name); ASSERT(!S_ISDIR(VFS_I(sip)->i_mode)); - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) + return -EIO; + if (xfs_ifork_zapped(tdp, XFS_DATA_FORK)) return -EIO; error = xfs_qm_dqattach(sip); @@ -1407,54 +939,31 @@ xfs_link( if (error) goto std_return; - resblks = XFS_LINK_SPACE_RES(mp, target_name->len); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, resblks, 0, 0, &tp); - if (error == -ENOSPC) { - resblks = 0; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_link, 0, 0, 0, &tp); - } + error = xfs_parent_start(mp, &du.ppargs); if (error) goto std_return; - xfs_lock_two_inodes(sip, XFS_ILOCK_EXCL, tdp, XFS_ILOCK_EXCL); - - xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL); + resblks = xfs_link_space_res(mp, target_name->len); + error = xfs_trans_alloc_dir(tdp, &M_RES(mp)->tr_link, sip, &resblks, + &tp, &nospace_error); + if (error) + goto out_parent; /* - * 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. + * We don't allow reservationless or quotaless hardlinking when parent + * pointers are enabled because we can't back out if the xattrs must + * grow. */ - if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(tdp) != xfs_get_projid(sip)))) { - error = -EXDEV; + if (du.ppargs && nospace_error) { + error = nospace_error; 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) { - error = xfs_iunlink_remove(tp, sip); - 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); - error = xfs_bumplink(tp, sip); + error = xfs_dir_add_child(tp, resblks, &du); if (error) goto error_return; @@ -1463,14 +972,24 @@ xfs_link( * link transaction goes to disk before returning to * the user. */ - if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) + if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); - return xfs_trans_commit(tp); + error = xfs_trans_commit(tp); + xfs_iunlock(tdp, XFS_ILOCK_EXCL); + xfs_iunlock(sip, XFS_ILOCK_EXCL); + xfs_parent_finish(mp, du.ppargs); + return error; error_return: xfs_trans_cancel(tp); + xfs_iunlock(tdp, XFS_ILOCK_EXCL); + xfs_iunlock(sip, XFS_ILOCK_EXCL); + out_parent: + xfs_parent_finish(mp, du.ppargs); std_return: + if (error == -ENOSPC && nospace_error) + error = nospace_error; return error; } @@ -1484,10 +1003,10 @@ xfs_itruncate_clear_reflink_flags( if (!xfs_is_reflink_inode(ip)) return; - dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK); - cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK); + dfork = xfs_ifork_ptr(ip, XFS_DATA_FORK); + cfork = xfs_ifork_ptr(ip, XFS_COW_FORK); if (dfork->if_bytes == 0 && cfork->if_bytes == 0) - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; if (cfork->if_bytes == 0) xfs_inode_clear_cowblocks_tag(ip); } @@ -1524,14 +1043,11 @@ xfs_itruncate_extents_flags( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp = *tpp; xfs_fileoff_t first_unmap_block; - xfs_fileoff_t last_block; - xfs_filblks_t unmap_len; int error = 0; - int done = 0; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(!atomic_read(&VFS_I(ip)->i_count) || - xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); + 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); ASSERT(ip->i_itemp != NULL); @@ -1547,41 +1063,26 @@ xfs_itruncate_extents_flags( * the end of the file (in a crash where the space is allocated * but the inode size is not yet updated), simply remove any * blocks which show up between the new EOF and the maximum - * possible file size. If the first block to be removed is - * beyond the maximum file size (ie it is the same as last_block), - * then there is nothing to do. + * possible file size. + * + * We have to free all the blocks to the bmbt maximum offset, even if + * the page cache can't scale that far. */ first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); - last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes); - if (first_unmap_block == last_block) + if (!xfs_verify_fileoff(mp, first_unmap_block)) { + WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF); return 0; - - ASSERT(first_unmap_block < last_block); - unmap_len = last_block - first_unmap_block + 1; - while (!done) { - ASSERT(tp->t_firstblock == NULLFSBLOCK); - error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags, - XFS_ITRUNC_MAX_EXTENTS, &done); - if (error) - goto out; - - /* - * Duplicate the transaction that has the permanent - * reservation and commit the old transaction. - */ - error = xfs_defer_finish(&tp); - if (error) - goto out; - - error = xfs_trans_roll_inode(&tp, ip); - if (error) - goto out; } + error = xfs_bunmapi_range(&tp, ip, flags, first_unmap_block, + XFS_MAX_FILEOFF); + if (error) + goto out; + if (whichfork == XFS_DATA_FORK) { /* Remove all pending CoW reservations. */ error = xfs_reflink_cancel_cow_blocks(ip, &tp, - first_unmap_block, last_block, true); + first_unmap_block, XFS_MAX_FILEOFF, true); if (error) goto out; @@ -1601,84 +1102,49 @@ out: return error; } -int -xfs_release( - xfs_inode_t *ip) +/* + * Mark all the buffers attached to this directory stale. In theory we should + * never be freeing a directory with any blocks at all, but this covers the + * case where we've recovered a directory swap with a "temporary" directory + * created by online repair and now need to dump it. + */ +STATIC void +xfs_inactive_dir( + struct xfs_inode *dp) { - xfs_mount_t *mp = ip->i_mount; - int error; - - 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 (mp->m_flags & XFS_MOUNT_RDONLY) - return 0; - - if (!XFS_FORCED_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 (xfs_can_free_eofblocks(ip, false)) { - - /* - * 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)) - return 0; - /* - * If we can't get the iolock just skip truncating the blocks - * past EOF because we could deadlock with the mmap_sem - * 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)) { - error = xfs_free_eofblocks(ip); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec got; + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_geometry *geo = mp->m_dir_geo; + struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); + xfs_fileoff_t off; + + /* + * Invalidate each directory block. All directory blocks are of + * fsbcount length and alignment, so we only need to walk those same + * offsets. We hold the only reference to this inode, so we must wait + * for the buffer locks. + */ + for_each_xfs_iext(ifp, &icur, &got) { + for (off = round_up(got.br_startoff, geo->fsbcount); + off < got.br_startoff + got.br_blockcount; + off += geo->fsbcount) { + struct xfs_buf *bp = NULL; + xfs_fsblock_t fsbno; + int error; + + fsbno = (off - got.br_startoff) + got.br_startblock; + error = xfs_buf_incore(mp->m_ddev_targp, + XFS_FSB_TO_DADDR(mp, fsbno), + XFS_FSB_TO_BB(mp, geo->fsbcount), + XBF_LIVESCAN, &bp); if (error) - return error; - } + continue; - /* delalloc blocks after truncation means it really is dirty */ - if (ip->i_delayed_blks) - xfs_iflags_set(ip, XFS_IDIRTY_RELEASE); + xfs_buf_stale(bp); + xfs_buf_relse(bp); + } } - return 0; } /* @@ -1696,7 +1162,7 @@ xfs_inactive_truncate( error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { - ASSERT(XFS_FORCED_SHUTDOWN(mp)); + ASSERT(xfs_is_shutdown(mp)); return error; } xfs_ilock(ip, XFS_ILOCK_EXCL); @@ -1707,14 +1173,14 @@ xfs_inactive_truncate( * of a system crash before the truncate completes. See the related * comment in xfs_vn_setattr_size() for details. */ - ip->i_d.di_size = 0; + ip->i_disk_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0); if (error) goto error_trans_cancel; - ASSERT(ip->i_d.di_nextents == 0); + ASSERT(ip->i_df.if_nextents == 0); error = xfs_trans_commit(tp); if (error) @@ -1754,7 +1220,7 @@ xfs_inactive_ifree( * now remains allocated and sits on the unlinked list until the fs is * repaired. */ - if (unlikely(mp->m_inotbt_nores)) { + if (unlikely(mp->m_finobt_nores)) { error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp); @@ -1767,28 +1233,48 @@ xfs_inactive_ifree( "Failed to remove inode(s) from unlinked list. " "Please free space, unmount and run xfs_repair."); } else { - ASSERT(XFS_FORCED_SHUTDOWN(mp)); + ASSERT(xfs_is_shutdown(mp)); } return error; } + /* + * We do not hold the inode locked across the entire rolling transaction + * here. We only need to hold it for the first transaction that + * xfs_ifree() builds, which may mark the inode XFS_ISTALE if the + * underlying cluster buffer is freed. Relogging an XFS_ISTALE inode + * here breaks the relationship between cluster buffer invalidation and + * stale inode invalidation on cluster buffer item journal commit + * completion, and can result in leaving dirty stale inodes hanging + * around in memory. + * + * We have no need for serialising this inode operation against other + * operations - we freed the inode and hence reallocation is required + * and that will serialise on reallocating the space the deferops need + * to free. Hence we can unlock the inode on the first commit of + * the transaction rather than roll it right through the deferops. This + * avoids relogging the XFS_ISTALE inode. + * + * We check that xfs_ifree() hasn't grown an internal transaction roll + * by asserting that the inode is still locked when it returns. + */ xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); error = xfs_ifree(tp, ip); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (error) { /* * If we fail to free the inode, shut down. The cancel * might do that, we need to make sure. Otherwise the * inode might be lost for a long time or forever. */ - if (!XFS_FORCED_SHUTDOWN(mp)) { + if (!xfs_is_shutdown(mp)) { xfs_notice(mp, "%s: xfs_ifree returned error %d", __func__, error); xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR); } xfs_trans_cancel(tp); - xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } @@ -1797,17 +1283,94 @@ xfs_inactive_ifree( */ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1); + return xfs_trans_commit(tp); +} + +/* + * Returns true if we need to update the on-disk metadata before we can free + * the memory used by this inode. Updates include freeing post-eof + * preallocations; freeing COW staging extents; and marking the inode free in + * the inobt if it is on the unlinked list. + */ +bool +xfs_inode_needs_inactive( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *cow_ifp = xfs_ifork_ptr(ip, XFS_COW_FORK); + /* - * Just ignore errors at this point. There is nothing we can do except - * to try to keep going. Make sure it's not a silent error. + * If the inode is already free, then there can be nothing + * to clean up here. */ - error = xfs_trans_commit(tp); - if (error) - xfs_notice(mp, "%s: xfs_trans_commit returned error %d", - __func__, error); + if (VFS_I(ip)->i_mode == 0) + return false; - xfs_iunlock(ip, XFS_ILOCK_EXCL); - return 0; + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) + return false; + + /* If the log isn't running, push inodes straight to reclaim. */ + if (xfs_is_shutdown(mp) || xfs_has_norecovery(mp)) + return false; + + /* Metadata inodes require explicit resource cleanup. */ + if (xfs_is_internal_inode(ip)) + return false; + + /* Want to clean out the cow blocks if there are any. */ + if (cow_ifp && cow_ifp->if_bytes > 0) + return true; + + /* Unlinked files must be freed. */ + if (VFS_I(ip)->i_nlink == 0) + return true; + + /* + * This file isn't being freed, so check if there are post-eof blocks + * to free. + * + * Note: don't bother with iolock here since lockdep complains about + * acquiring it in reclaim context. We have the only reference to the + * inode at this point anyways. + */ + return xfs_can_free_eofblocks(ip); +} + +/* + * Save health status somewhere, if we're dumping an inode with uncorrected + * errors and online repair isn't running. + */ +static inline void +xfs_inactive_health( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; + unsigned int sick; + unsigned int checked; + + xfs_inode_measure_sickness(ip, &sick, &checked); + if (!sick) + return; + + trace_xfs_inode_unfixed_corruption(ip, sick); + + if (sick & XFS_SICK_INO_FORGET) + return; + + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); + if (!pag) { + /* There had better still be a perag structure! */ + ASSERT(0); + return; + } + + xfs_ag_mark_sick(pag, XFS_SICK_AG_INODES); + xfs_perag_put(pag); } /* @@ -1818,12 +1381,12 @@ xfs_inactive_ifree( * now be truncated. Also, we clear all of the read-ahead state * kept for the inode here since the file is now closed. */ -void +int xfs_inactive( xfs_inode_t *ip) { struct xfs_mount *mp; - int error; + int error = 0; int truncate = 0; /* @@ -1832,344 +1395,291 @@ xfs_inactive( */ if (VFS_I(ip)->i_mode == 0) { ASSERT(ip->i_df.if_broot_bytes == 0); - return; + goto out; } mp = ip->i_mount; ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY)); - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (mp->m_flags & XFS_MOUNT_RDONLY) - return; + xfs_inactive_health(ip); + + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) + goto out; + + /* Metadata inodes require explicit resource cleanup. */ + 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) { /* - * force is true because we are evicting an inode from the - * cache. Post-eof blocks must be freed, lest we end up with - * broken free space accounting. - * * Note: don't bother with iolock here since lockdep complains * about acquiring it in reclaim context. We have the only * reference to the inode at this point anyways. */ - if (xfs_can_free_eofblocks(ip, true)) - xfs_free_eofblocks(ip); + if (xfs_can_free_eofblocks(ip)) + error = xfs_free_eofblocks(ip); - return; + goto out; } if (S_ISREG(VFS_I(ip)->i_mode) && - (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 || - ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0)) + (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 || + xfs_inode_has_filedata(ip))) truncate = 1; - error = xfs_qm_dqattach(ip); - if (error) - return; + if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { + /* + * If this inode is being inactivated during a quotacheck and + * has not yet been scanned by quotacheck, we /must/ remove + * the dquots from the inode before inactivation changes the + * block and inode counts. Most probably this is a result of + * reloading the incore iunlinked list to purge unrecovered + * unlinked inodes. + */ + xfs_qm_dqdetach(ip); + } else { + error = xfs_qm_dqattach(ip); + if (error) + goto out; + } + + if (S_ISDIR(VFS_I(ip)->i_mode) && ip->i_df.if_nextents > 0) { + xfs_inactive_dir(ip); + truncate = 1; + } if (S_ISLNK(VFS_I(ip)->i_mode)) error = xfs_inactive_symlink(ip); else if (truncate) error = xfs_inactive_truncate(ip); if (error) - return; + goto out; /* * If there are attributes associated with the file then blow them away * now. The code calls a routine that recursively deconstructs the * attribute fork. If also blows away the in-core attribute fork. */ - if (XFS_IFORK_Q(ip)) { + if (xfs_inode_has_attr_fork(ip)) { error = xfs_attr_inactive(ip); if (error) - return; + goto out; } - ASSERT(!ip->i_afp); - ASSERT(ip->i_d.di_anextents == 0); - ASSERT(ip->i_d.di_forkoff == 0); + ASSERT(ip->i_forkoff == 0); /* * Free the inode. */ error = xfs_inactive_ifree(ip); - if (error) - return; +out: /* - * Release the dquots held by inode, if any. + * We're done making metadata updates for this inode, so we can release + * the attached dquots. */ xfs_qm_dqdetach(ip); + return error; } /* - * This is called when the inode's link count goes to 0 or we are creating a - * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be - * set to true as the link count is dropped to zero by the VFS after we've - * created the file successfully, so we have to add it to the unlinked list - * while the link count is non-zero. - * - * We place the on-disk inode on a list in the AGI. It will be pulled from this - * list when the inode is freed. + * Find an inode on the unlinked list. This does not take references to the + * inode as we have existence guarantees by holding the AGI buffer lock and that + * only unlinked, referenced inodes can be on the unlinked inode list. If we + * don't find the inode in cache, then let the caller handle the situation. */ -STATIC int -xfs_iunlink( - struct xfs_trans *tp, - struct xfs_inode *ip) +struct xfs_inode * +xfs_iunlink_lookup( + struct xfs_perag *pag, + xfs_agino_t agino) { - xfs_mount_t *mp = tp->t_mountp; - xfs_agi_t *agi; - xfs_dinode_t *dip; - xfs_buf_t *agibp; - xfs_buf_t *ibp; - xfs_agino_t agino; - short bucket_index; - int offset; - int error; - - ASSERT(VFS_I(ip)->i_mode != 0); + struct xfs_inode *ip; - /* - * Get the agi buffer first. It ensures lock ordering - * on the list. - */ - error = xfs_read_agi(mp, tp, XFS_INO_TO_AGNO(mp, ip->i_ino), &agibp); - if (error) - return error; - agi = XFS_BUF_TO_AGI(agibp); + rcu_read_lock(); + ip = radix_tree_lookup(&pag->pag_ici_root, agino); + if (!ip) { + /* Caller can handle inode not being in memory. */ + rcu_read_unlock(); + return NULL; + } /* - * Get the index into the agi hash table for the - * list this inode will go on. + * Inode in RCU freeing limbo should not happen. Warn about this and + * let the caller handle the failure. */ - agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - ASSERT(agino != 0); - bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; - ASSERT(agi->agi_unlinked[bucket_index]); - ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino); + if (WARN_ON_ONCE(!ip->i_ino)) { + rcu_read_unlock(); + return NULL; + } + ASSERT(!xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM)); + rcu_read_unlock(); + return ip; +} - if (agi->agi_unlinked[bucket_index] != cpu_to_be32(NULLAGINO)) { - /* - * There is already another inode in the bucket we need - * to add ourselves to. Add us at the front of the list. - * Here we put the head pointer into our next pointer, - * and then we fall through to point the head at us. - */ - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, - 0, 0); - if (error) - return error; +/* + * Load the inode @next_agino into the cache and set its prev_unlinked pointer + * to @prev_agino. Caller must hold the AGI to synchronize with other changes + * to the unlinked list. + */ +int +xfs_iunlink_reload_next( + struct xfs_trans *tp, + struct xfs_buf *agibp, + xfs_agino_t prev_agino, + xfs_agino_t next_agino) +{ + struct xfs_perag *pag = agibp->b_pag; + struct xfs_mount *mp = pag_mount(pag); + struct xfs_inode *next_ip = NULL; + int error; - ASSERT(dip->di_next_unlinked == cpu_to_be32(NULLAGINO)); - dip->di_next_unlinked = agi->agi_unlinked[bucket_index]; - offset = ip->i_imap.im_boffset + - offsetof(xfs_dinode_t, di_next_unlinked); + ASSERT(next_agino != NULLAGINO); - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, dip); +#ifdef DEBUG + rcu_read_lock(); + next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino); + ASSERT(next_ip == NULL); + rcu_read_unlock(); +#endif - xfs_trans_inode_buf(tp, ibp); - xfs_trans_log_buf(tp, ibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - xfs_inobp_check(mp, ibp); - } + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.", + next_agino, pag_agno(pag)); /* - * Point the bucket head pointer at the inode being inserted. + * Use an untrusted lookup just to be cautious in case the AGI has been + * corrupted and now points at a free inode. That shouldn't happen, + * but we'd rather shut down now since we're already running in a weird + * situation. */ - ASSERT(agino != 0); - agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); - offset = offsetof(xfs_agi_t, agi_unlinked) + - (sizeof(xfs_agino_t) * bucket_index); - xfs_trans_log_buf(tp, agibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - return 0; + 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; + } + + /* If this is not an unlinked inode, something is very wrong. */ + if (VFS_I(next_ip)->i_nlink != 0) { + xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI); + error = -EFSCORRUPTED; + goto rele; + } + + next_ip->i_prev_unlinked = prev_agino; + trace_xfs_iunlink_reload_next(next_ip); +rele: + 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; } /* - * Pull the on-disk inode from the AGI unlinked list. + * Look up the inode number specified and if it is not already marked XFS_ISTALE + * mark it stale. We should only find clean inodes in this lookup that aren't + * already stale. */ -STATIC int -xfs_iunlink_remove( - xfs_trans_t *tp, - xfs_inode_t *ip) +static void +xfs_ifree_mark_inode_stale( + struct xfs_perag *pag, + struct xfs_inode *free_ip, + xfs_ino_t inum) { - xfs_ino_t next_ino; - xfs_mount_t *mp; - xfs_agi_t *agi; - xfs_dinode_t *dip; - xfs_buf_t *agibp; - xfs_buf_t *ibp; - xfs_agnumber_t agno; - xfs_agino_t agino; - xfs_agino_t next_agino; - xfs_buf_t *last_ibp; - xfs_dinode_t *last_dip = NULL; - short bucket_index; - int offset, last_offset = 0; - int error; - - mp = tp->t_mountp; - agno = XFS_INO_TO_AGNO(mp, ip->i_ino); + struct xfs_mount *mp = pag_mount(pag); + struct xfs_inode_log_item *iip; + struct xfs_inode *ip; + +retry: + rcu_read_lock(); + ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum)); + + /* Inode not in memory, nothing to do */ + if (!ip) { + rcu_read_unlock(); + return; + } /* - * Get the agi buffer first. It ensures lock ordering - * on the list. + * because this is an RCU protected lookup, we could find a recently + * freed or even reallocated inode during the lookup. We need to check + * under the i_flags_lock for a valid inode here. Skip it if it is not + * valid, the wrong inode or stale. */ - error = xfs_read_agi(mp, tp, agno, &agibp); - if (error) - return error; - - agi = XFS_BUF_TO_AGI(agibp); + spin_lock(&ip->i_flags_lock); + if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) + goto out_iflags_unlock; /* - * Get the index into the agi hash table for the - * list this inode will go on. + * Don't try to lock/unlock the current inode, but we _cannot_ skip the + * other inodes that we did not find in the list attached to the buffer + * and are not already marked stale. If we can't lock it, back off and + * retry. */ - agino = XFS_INO_TO_AGINO(mp, ip->i_ino); - if (!xfs_verify_agino(mp, agno, agino)) - return -EFSCORRUPTED; - bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; - if (!xfs_verify_agino(mp, agno, - be32_to_cpu(agi->agi_unlinked[bucket_index]))) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - agi, sizeof(*agi)); - return -EFSCORRUPTED; - } - - if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) { - /* - * We're at the head of the list. Get the inode's on-disk - * buffer to see if there is anyone after us on the list. - * Only modify our next pointer if it is not already NULLAGINO. - * This saves us the overhead of dealing with the buffer when - * there is no need to change it. - */ - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, - 0, 0); - if (error) { - xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.", - __func__, error); - return error; - } - next_agino = be32_to_cpu(dip->di_next_unlinked); - ASSERT(next_agino != 0); - if (next_agino != NULLAGINO) { - dip->di_next_unlinked = cpu_to_be32(NULLAGINO); - offset = ip->i_imap.im_boffset + - offsetof(xfs_dinode_t, di_next_unlinked); - - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, dip); - - xfs_trans_inode_buf(tp, ibp); - xfs_trans_log_buf(tp, ibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - xfs_inobp_check(mp, ibp); - } else { - xfs_trans_brelse(tp, ibp); + if (ip != free_ip) { + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { + spin_unlock(&ip->i_flags_lock); + rcu_read_unlock(); + delay(1); + goto retry; } - /* - * Point the bucket head pointer at the next inode. - */ - ASSERT(next_agino != 0); - ASSERT(next_agino != agino); - agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); - offset = offsetof(xfs_agi_t, agi_unlinked) + - (sizeof(xfs_agino_t) * bucket_index); - xfs_trans_log_buf(tp, agibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - } else { - /* - * We need to search the list for the inode being freed. - */ - next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]); - last_ibp = NULL; - while (next_agino != agino) { - struct xfs_imap imap; - - if (last_ibp) - xfs_trans_brelse(tp, last_ibp); - - imap.im_blkno = 0; - next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino); - - error = xfs_imap(mp, tp, next_ino, &imap, 0); - if (error) { - xfs_warn(mp, - "%s: xfs_imap returned error %d.", - __func__, error); - return error; - } + } + ip->i_flags |= XFS_ISTALE; - error = xfs_imap_to_bp(mp, tp, &imap, &last_dip, - &last_ibp, 0, 0); - if (error) { - xfs_warn(mp, - "%s: xfs_imap_to_bp returned error %d.", - __func__, error); - return error; - } + /* + * If the inode is flushing, it is already attached to the buffer. All + * we needed to do here is mark the inode stale so buffer IO completion + * will remove it from the AIL. + */ + 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 || xlog_is_shutdown(mp->m_log)); + goto out_iunlock; + } - last_offset = imap.im_boffset; - next_agino = be32_to_cpu(last_dip->di_next_unlinked); - if (!xfs_verify_agino(mp, agno, next_agino)) { - XFS_CORRUPTION_ERROR(__func__, - XFS_ERRLEVEL_LOW, mp, - last_dip, sizeof(*last_dip)); - return -EFSCORRUPTED; - } - } + /* + * Inodes not attached to the buffer can be released immediately. + * Everything else has to go through xfs_iflush_abort() on journal + * commit as the flock synchronises removal of the inode from the + * cluster buffer against inode reclaim. + */ + if (!iip || list_empty(&iip->ili_item.li_bio_list)) + goto out_iunlock; - /* - * Now last_ibp points to the buffer previous to us on the - * unlinked list. Pull us from the list. - */ - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, - 0, 0); - if (error) { - xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.", - __func__, error); - return error; - } - next_agino = be32_to_cpu(dip->di_next_unlinked); - ASSERT(next_agino != 0); - ASSERT(next_agino != agino); - if (next_agino != NULLAGINO) { - dip->di_next_unlinked = cpu_to_be32(NULLAGINO); - offset = ip->i_imap.im_boffset + - offsetof(xfs_dinode_t, di_next_unlinked); - - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, dip); - - xfs_trans_inode_buf(tp, ibp); - xfs_trans_log_buf(tp, ibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - xfs_inobp_check(mp, ibp); - } else { - xfs_trans_brelse(tp, ibp); - } - /* - * Point the previous inode on the list to the next inode. - */ - last_dip->di_next_unlinked = cpu_to_be32(next_agino); - ASSERT(next_agino != 0); - offset = last_offset + offsetof(xfs_dinode_t, di_next_unlinked); + __xfs_iflags_set(ip, XFS_IFLUSHING); + spin_unlock(&ip->i_flags_lock); + rcu_read_unlock(); - /* need to recalc the inode CRC if appropriate */ - xfs_dinode_calc_crc(mp, last_dip); + /* we have a dirty inode in memory that has not yet been flushed. */ + spin_lock(&iip->ili_lock); + iip->ili_last_fields = iip->ili_fields; + iip->ili_fields = 0; + spin_unlock(&iip->ili_lock); + ASSERT(iip->ili_last_fields); - xfs_trans_inode_buf(tp, last_ibp); - xfs_trans_log_buf(tp, last_ibp, offset, - (offset + sizeof(xfs_agino_t) - 1)); - xfs_inobp_check(mp, last_ibp); - } - return 0; + if (ip != free_ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return; + +out_iunlock: + if (ip != free_ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); +out_iflags_unlock: + spin_unlock(&ip->i_flags_lock); + rcu_read_unlock(); } /* @@ -2177,29 +1687,26 @@ xfs_iunlink_remove( * inodes that are in memory - they all must be marked stale and attached to * the cluster buffer. */ -STATIC int +static int xfs_ifree_cluster( - xfs_inode_t *free_ip, - xfs_trans_t *tp, + struct xfs_trans *tp, + struct xfs_perag *pag, + struct xfs_inode *free_ip, struct xfs_icluster *xic) { - xfs_mount_t *mp = free_ip->i_mount; + struct xfs_mount *mp = free_ip->i_mount; + struct xfs_ino_geometry *igeo = M_IGEO(mp); + struct xfs_buf *bp; + xfs_daddr_t blkno; + xfs_ino_t inum = xic->first_ino; int nbufs; int i, j; int ioffset; - xfs_daddr_t blkno; - xfs_buf_t *bp; - xfs_inode_t *ip; - xfs_inode_log_item_t *iip; - struct xfs_log_item *lip; - struct xfs_perag *pag; - xfs_ino_t inum; + int error; - inum = xic->first_ino; - pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum)); - nbufs = mp->m_ialloc_blks / mp->m_blocks_per_cluster; + nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster; - for (j = 0; j < nbufs; j++, inum += mp->m_inodes_per_cluster) { + for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) { /* * The allocation bitmap tells us which inodes of the chunk were * physically allocated. Skip the cluster if an inode falls into @@ -2207,7 +1714,7 @@ xfs_ifree_cluster( */ ioffset = inum - xic->first_ino; if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) { - ASSERT(ioffset % mp->m_inodes_per_cluster == 0); + ASSERT(ioffset % igeo->inodes_per_cluster == 0); continue; } @@ -2216,232 +1723,102 @@ xfs_ifree_cluster( /* * We obtain and lock the backing buffer first in the process - * here, as we have to ensure that any dirty inode that we - * can't get the flush lock on is attached to the buffer. + * here to ensure dirty inodes attached to the buffer remain in + * the flushing state while we mark them stale. + * * If we scan the in-memory inodes first, then buffer IO can * complete before we get a lock on it, and hence we may fail * to mark all the active inodes on the buffer stale. */ - bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * mp->m_blocks_per_cluster, - XBF_UNMAPPED); - - if (!bp) - return -ENOMEM; + error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, + mp->m_bsize * igeo->blocks_per_cluster, 0, &bp); + if (error) + return error; /* * This buffer may not have been correctly initialised as we * didn't read it from disk. That's not important because we are * only using to mark the buffer as stale in the log, and to - * attach stale cached inodes on it. That means it will never be - * dispatched for IO. If it is, we want to know about it, and we - * want it to fail. We can acheive this by adding a write - * verifier to the buffer. + * attach stale cached inodes on it. + * + * For the inode that triggered the cluster freeing, this + * attachment may occur in xfs_inode_item_precommit() after we + * have marked this buffer stale. If this buffer was not in + * memory before xfs_ifree_cluster() started, it will not be + * marked XBF_DONE and this will cause problems later in + * xfs_inode_item_precommit() when we trip over a (stale, !done) + * buffer to attached to the transaction. + * + * Hence we have to mark the buffer as XFS_DONE here. This is + * safe because we are also marking the buffer as XBF_STALE and + * XFS_BLI_STALE. That means it will never be dispatched for + * IO and it won't be unlocked until the cluster freeing has + * been committed to the journal and the buffer unpinned. If it + * is written, we want to know about it, and we want it to + * fail. We can acheive this by adding a write verifier to the + * buffer. */ + bp->b_flags |= XBF_DONE; bp->b_ops = &xfs_inode_buf_ops; /* - * Walk the inodes already attached to the buffer and mark them - * stale. These will all have the flush locks held, so an - * in-memory inode walk can't lock them. By marking them all - * stale first, we will not attempt to lock them in the loop - * below as the XFS_ISTALE flag will be set. - */ - list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (lip->li_type == XFS_LI_INODE) { - iip = (xfs_inode_log_item_t *)lip; - ASSERT(iip->ili_logged == 1); - lip->li_cb = xfs_istale_done; - xfs_trans_ail_copy_lsn(mp->m_ail, - &iip->ili_flush_lsn, - &iip->ili_item.li_lsn); - xfs_iflags_set(iip->ili_inode, XFS_ISTALE); - } - } - - - /* - * For each inode in memory attempt to add it to the inode - * buffer and set it up for being staled on buffer IO - * completion. This is safe as we've locked out tail pushing - * and flushing by locking the buffer. - * - * We have already marked every inode that was part of a - * transaction stale above, which means there is no point in - * even trying to lock them. + * Now we need to set all the cached clean inodes as XFS_ISTALE, + * too. This requires lookups, and will skip inodes that we've + * already marked XFS_ISTALE. */ - for (i = 0; i < mp->m_inodes_per_cluster; i++) { -retry: - rcu_read_lock(); - ip = radix_tree_lookup(&pag->pag_ici_root, - XFS_INO_TO_AGINO(mp, (inum + i))); - - /* Inode not in memory, nothing to do */ - if (!ip) { - rcu_read_unlock(); - continue; - } - - /* - * because this is an RCU protected lookup, we could - * find a recently freed or even reallocated inode - * during the lookup. We need to check under the - * i_flags_lock for a valid inode here. Skip it if it - * is not valid, the wrong inode or stale. - */ - spin_lock(&ip->i_flags_lock); - if (ip->i_ino != inum + i || - __xfs_iflags_test(ip, XFS_ISTALE)) { - spin_unlock(&ip->i_flags_lock); - rcu_read_unlock(); - continue; - } - spin_unlock(&ip->i_flags_lock); - - /* - * Don't try to lock/unlock the current inode, but we - * _cannot_ skip the other inodes that we did not find - * in the list attached to the buffer and are not - * already marked stale. If we can't lock it, back off - * and retry. - */ - if (ip != free_ip) { - if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { - rcu_read_unlock(); - delay(1); - goto retry; - } - - /* - * Check the inode number again in case we're - * racing with freeing in xfs_reclaim_inode(). - * See the comments in that function for more - * information as to why the initial check is - * not sufficient. - */ - if (ip->i_ino != inum + i) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - rcu_read_unlock(); - continue; - } - } - rcu_read_unlock(); - - xfs_iflock(ip); - xfs_iflags_set(ip, XFS_ISTALE); - - /* - * we don't need to attach clean inodes or those only - * with unlogged changes (which we throw away, anyway). - */ - iip = ip->i_itemp; - if (!iip || xfs_inode_clean(ip)) { - ASSERT(ip != free_ip); - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - continue; - } - - iip->ili_last_fields = iip->ili_fields; - iip->ili_fields = 0; - iip->ili_fsync_fields = 0; - iip->ili_logged = 1; - xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, - &iip->ili_item.li_lsn); - - xfs_buf_attach_iodone(bp, xfs_istale_done, - &iip->ili_item); - - if (ip != free_ip) - xfs_iunlock(ip, XFS_ILOCK_EXCL); - } + for (i = 0; i < igeo->inodes_per_cluster; i++) + xfs_ifree_mark_inode_stale(pag, free_ip, inum + i); xfs_trans_stale_inode_buf(tp, bp); xfs_trans_binval(tp, bp); } - - xfs_perag_put(pag); return 0; } /* - * Free any local-format buffers sitting around before we reset to - * extents format. - */ -static inline void -xfs_ifree_local_data( - struct xfs_inode *ip, - int whichfork) -{ - struct xfs_ifork *ifp; - - if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL) - return; - - ifp = XFS_IFORK_PTR(ip, whichfork); - xfs_idata_realloc(ip, -ifp->if_bytes, whichfork); -} - -/* - * This is called to return an inode to the inode free list. - * The inode should already be truncated to 0 length and have - * no pages associated with it. This routine also assumes that - * the inode is already a part of the transaction. + * This is called to return an inode to the inode free list. The inode should + * already be truncated to 0 length and have no pages associated with it. This + * routine also assumes that the inode is already a part of the transaction. * - * The on-disk copy of the inode will have been added to the list - * of unlinked inodes in the AGI. We need to remove the inode from - * that list atomically with respect to freeing it here. + * The on-disk copy of the inode will have been added to the list of unlinked + * inodes in the AGI. We need to remove the inode from that list atomically with + * respect to freeing it here. */ int xfs_ifree( struct xfs_trans *tp, struct xfs_inode *ip) { - int error; + struct xfs_mount *mp = ip->i_mount; + struct xfs_perag *pag; struct xfs_icluster xic = { 0 }; + struct xfs_inode_log_item *iip = ip->i_itemp; + int error; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(VFS_I(ip)->i_nlink == 0); - ASSERT(ip->i_d.di_nextents == 0); - ASSERT(ip->i_d.di_anextents == 0); - ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode)); - ASSERT(ip->i_d.di_nblocks == 0); + ASSERT(ip->i_df.if_nextents == 0); + ASSERT(ip->i_disk_size == 0 || !S_ISREG(VFS_I(ip)->i_mode)); + ASSERT(ip->i_nblocks == 0); - /* - * Pull the on-disk inode from the AGI unlinked list. - */ - error = xfs_iunlink_remove(tp, ip); - if (error) - return error; + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); - error = xfs_difree(tp, ip->i_ino, &xic); + error = xfs_inode_uninit(tp, pag, ip, &xic); if (error) - return error; + goto out; - xfs_ifree_local_data(ip, XFS_DATA_FORK); - xfs_ifree_local_data(ip, XFS_ATTR_FORK); - - VFS_I(ip)->i_mode = 0; /* mark incore inode as free */ - ip->i_d.di_flags = 0; - ip->i_d.di_flags2 = 0; - ip->i_d.di_dmevmask = 0; - ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */ - ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS; - ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS; + if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) + xfs_iflags_clear(ip, XFS_IPRESERVE_DM_FIELDS); /* Don't attempt to replay owner changes for a deleted inode */ - ip->i_itemp->ili_fields &= ~(XFS_ILOG_AOWNER|XFS_ILOG_DOWNER); - - /* - * 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); + spin_lock(&iip->ili_lock); + iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER); + spin_unlock(&iip->ili_lock); if (xic.deleted) - error = xfs_ifree_cluster(ip, tp, &xic); - + error = xfs_ifree_cluster(tp, pag, ip, &xic); +out: + xfs_perag_put(pag); return error; } @@ -2454,12 +1831,20 @@ static void xfs_iunpin( struct xfs_inode *ip) { - ASSERT(xfs_isilocked(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_lsn(ip->i_mount, ip->i_itemp->ili_last_lsn, 0, NULL); + xfs_log_force_seq(ip->i_mount, seq, 0, NULL); } @@ -2517,19 +1902,27 @@ xfs_iunpin_wait( */ int xfs_remove( - xfs_inode_t *dp, + struct xfs_inode *dp, struct xfs_name *name, - xfs_inode_t *ip) + struct xfs_inode *ip) { - xfs_mount_t *mp = dp->i_mount; - xfs_trans_t *tp = NULL; + 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; trace_xfs_remove(dp, name); - if (XFS_FORCED_SHUTDOWN(mp)) + if (xfs_is_shutdown(mp)) + return -EIO; + if (xfs_ifork_zapped(dp, XFS_DATA_FORK)) return -EIO; error = xfs_qm_dqattach(dp); @@ -2540,99 +1933,79 @@ xfs_remove( if (error) goto std_return; - /* - * We try to get the real space reservation first, - * allowing for directory btree deletion(s) implying - * possible bmap insert(s). If we can't get the space - * reservation then we use 0 instead, and avoid the bmap - * btree insert(s) in the directory code by, if the bmap - * insert tries to happen, instead trimming the LAST - * block from the directory. - */ - resblks = XFS_REMOVE_SPACE_RES(mp); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, resblks, 0, 0, &tp); - if (error == -ENOSPC) { - resblks = 0; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_remove, 0, 0, 0, - &tp); - } - if (error) { - ASSERT(error != -ENOSPC); + error = xfs_parent_start(mp, &du.ppargs); + if (error) goto std_return; - } - - xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL); - - xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); /* - * If we're removing a directory perform some additional validation. + * We try to get the real space reservation first, allowing for + * directory btree deletion(s) implying possible bmap insert(s). If we + * can't get the space reservation then we use 0 instead, and avoid the + * bmap btree insert(s) in the directory code by, if the bmap insert + * tries to happen, instead trimming the LAST block from the directory. + * + * Ignore EDQUOT and ENOSPC being returned via nospace_error because + * the directory code can handle a reservationless update and we don't + * want to prevent a user from trying to free space by deleting things. */ - 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; - } 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); + resblks = xfs_remove_space_res(mp, name->len); + error = xfs_trans_alloc_dir(dp, &M_RES(mp)->tr_remove, ip, &resblks, + &tp, &dontcare); + if (error) { + ASSERT(error != -ENOSPC); + goto out_parent; } - 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; - } - /* * If this is a synchronous mount, make sure that the * remove transaction goes to disk before returning to * the user. */ - if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) + if (xfs_has_wsync(mp) || xfs_has_dirsync(mp)) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); if (error) - goto std_return; + goto out_unlock; if (is_dir && xfs_inode_is_filestream(ip)) xfs_filestream_deassociate(ip); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + xfs_parent_finish(mp, du.ppargs); return 0; out_trans_cancel: xfs_trans_cancel(tp); + out_unlock: + xfs_iunlock(ip, XFS_ILOCK_EXCL); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + out_parent: + xfs_parent_finish(mp, du.ppargs); std_return: return error; } +static inline void +xfs_iunlock_rename( + struct xfs_inode **i_tab, + int num_inodes) +{ + int i; + + for (i = num_inodes - 1; i >= 0; i--) { + /* Skip duplicate inodes if src and target dps are the same */ + if (!i_tab[i] || (i > 0 && i_tab[i] == i_tab[i - 1])) + continue; + xfs_iunlock(i_tab[i], XFS_ILOCK_EXCL); + } +} + /* * Enter all inodes for a rename transaction into a sorted array. */ @@ -2647,7 +2020,7 @@ xfs_sort_for_rename( struct xfs_inode **i_tab,/* out: sorted array of inodes */ int *num_inodes) /* in/out: inodes in array */ { - int i, j; + int i; ASSERT(*num_inodes == __XFS_SORT_INODES); memset(i_tab, 0, *num_inodes * sizeof(struct xfs_inode *)); @@ -2669,178 +2042,76 @@ xfs_sort_for_rename( i_tab[i++] = wip; *num_inodes = i; - /* - * Sort the elements via bubble sort. (Remember, there are at - * most 5 elements to sort, so this is adequate.) - */ - for (i = 0; i < *num_inodes; i++) { - for (j = 1; j < *num_inodes; j++) { - if (i_tab[j]->i_ino < i_tab[j-1]->i_ino) { - struct xfs_inode *temp = i_tab[j]; - i_tab[j] = i_tab[j-1]; - i_tab[j-1] = temp; - } - } - } + xfs_sort_inodes(i_tab, *num_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 (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) - xfs_trans_set_sync(tp); - - return xfs_trans_commit(tp); -} - -/* - * xfs_cross_rename() - * - * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall - */ -STATIC int -xfs_cross_rename( - struct xfs_trans *tp, - struct xfs_inode *dp1, - struct xfs_name *name1, - struct xfs_inode *ip1, - struct xfs_inode *dp2, - struct xfs_name *name2, - struct xfs_inode *ip2, - int spaceres) +void +xfs_sort_inodes( + struct xfs_inode **i_tab, + unsigned int num_inodes) { - 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; + int i, j; - /* 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; + ASSERT(num_inodes <= __XFS_SORT_INODES); /* - * If we're renaming one or more directories across different parents, - * update the respective ".." entries (and link counts) to match the new - * parents. + * Sort the elements via bubble sort. (Remember, there are at + * most 5 elements to sort, so this is adequate.) */ - 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; - error = xfs_bumplink(tp, dp1); - if (error) - goto out_trans_abort; - } - - /* - * 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; - error = xfs_bumplink(tp, dp2); - if (error) - goto out_trans_abort; - } - - /* - * 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; + for (i = 0; i < num_inodes; i++) { + for (j = 1; j < num_inodes; j++) { + if (i_tab[j]->i_ino < i_tab[j-1]->i_ino) + swap(i_tab[j], i_tab[j - 1]); } } - - 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); - return xfs_finish_rename(tp); - -out_trans_abort: - xfs_trans_cancel(tp); - return error; } /* * xfs_rename_alloc_whiteout() * - * Return a referenced, unlinked, unlocked inode that that can be used as a + * Return a referenced, unlinked, unlocked inode that can be used as a * whiteout in a rename transaction. We use a tmpfile inode here so that if we * crash between allocating the inode and linking it into the rename transaction * recovery will free the inode and we won't leak it. */ static int xfs_rename_alloc_whiteout( + struct mnt_idmap *idmap, + struct xfs_name *src_name, struct xfs_inode *dp, struct xfs_inode **wip) { + 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(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile); + error = xfs_create_tmpfile(&args, &tmpfile); if (error) return error; + name.name = src_name->name; + name.len = src_name->len; + error = xfs_inode_init_security(VFS_I(tmpfile), VFS_I(dp), &name); + if (error) { + xfs_finish_inode_setup(tmpfile); + xfs_irele(tmpfile); + return error; + } + /* * Prepare the tmpfile inode as if it were created through the VFS. - * Otherwise, the link increment paths will complain about nlink 0->1. - * Drop the link count as done by d_tmpfile(), complete the inode setup - * and flag it as linkable. + * Complete the inode setup and flag it as linkable. nlink is already + * zero, so we can skip the drop_nlink. */ - drop_nlink(VFS_I(tmpfile)); 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; @@ -2851,6 +2122,7 @@ xfs_rename_alloc_whiteout( */ int xfs_rename( + struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, @@ -2859,15 +2131,27 @@ 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]; + int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); int spaceres; - int error; + bool retried = false; + int error, nospace_error = 0; trace_xfs_rename(src_dp, target_dp, src_name, target_name); @@ -2880,8 +2164,8 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); - error = xfs_rename_alloc_whiteout(target_dp, &wip); + error = xfs_rename_alloc_whiteout(idmap, src_name, target_dp, + &du_wip.ip); if (error) return error; @@ -2889,705 +2173,899 @@ 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, &du_src.ppargs); + if (error) + goto out_release_wip; + + 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, &du_tgt.ppargs); + if (error) + goto out_wip_ppargs; + } - spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len); +retry: + nospace_error = 0; + spaceres = xfs_rename_space_res(mp, src_name->len, target_ip != 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; spaceres = 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_rename, 0, 0, 0, &tp); } if (error) - goto out_release_wip; + goto out_tgt_ppargs; + + /* + * We don't allow reservationless renaming when parent pointers are + * enabled because we can't back out if the xattrs must grow. + */ + if (du_src.ppargs && nospace_error) { + error = nospace_error; + xfs_trans_cancel(tp); + goto out_tgt_ppargs; + } /* * Attach the dquots to the inodes */ error = xfs_qm_vop_rename_dqattach(inodes); - if (error) - goto out_trans_cancel; + if (error) { + xfs_trans_cancel(tp); + goto out_tgt_ppargs; + } /* * Lock all the participating inodes. Depending upon whether * the target_name exists in the target directory, and * whether the target directory is the same as the source - * directory, we can lock from 2 to 4 inodes. + * directory, we can lock from 2 to 5 inodes. */ xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL); /* - * Join all the inodes to the transaction. From this point on, - * we can rely on either trans_commit or trans_cancel to unlock - * them. + * Join all the inodes to the transaction. */ - xfs_trans_ijoin(tp, src_dp, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, src_dp, 0); if (new_parent) - xfs_trans_ijoin(tp, target_dp, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, src_ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, target_dp, 0); + xfs_trans_ijoin(tp, src_ip, 0); if (target_ip) - xfs_trans_ijoin(tp, target_ip, XFS_ILOCK_EXCL); - if (wip) - xfs_trans_ijoin(tp, wip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, target_ip, 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_d.di_flags & XFS_DIFLAG_PROJINHERIT) && - (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) { - 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) - return xfs_cross_rename(tp, src_dp, src_name, src_ip, - target_dp, target_name, target_ip, - spaceres); + if (flags & RENAME_EXCHANGE) { + error = xfs_dir_exchange_children(tp, &du_src, &du_tgt, + spaceres); + if (error) + goto out_trans_cancel; + goto out_commit; + } /* - * Set up the target. + * Try to reserve quota to handle an expansion of the target directory. + * We'll allow the rename to continue in reservationless mode if we hit + * a space usage constraint. If we trigger reservationless mode, save + * the errno if there isn't any free space in the target directory. */ - 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; + if (spaceres != 0) { + error = xfs_trans_reserve_quota_nblks(tp, target_dp, spaceres, + 0, false); + if (error == -EDQUOT || error == -ENOSPC) { + if (!retried) { + xfs_trans_cancel(tp); + xfs_iunlock_rename(inodes, num_inodes); + xfs_blockgc_free_quota(target_dp, 0); + retried = true; + goto retry; + } + + nospace_error = error; + spaceres = 0; + error = 0; } - /* - * 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); + /* + * We don't allow quotaless renaming when parent pointers are enabled + * because we can't back out if the xattrs must grow. + */ + if (du_src.ppargs && nospace_error) { + error = nospace_error; + goto out_trans_cancel; + } - if (new_parent && src_is_directory) { - error = xfs_bumplink(tp, target_dp); + /* + * 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 + * increasing AG order and before directory block allocation tries to + * grab AGFs because we grab AGIs before AGFs. + * + * The (vfs) caller must ensure that if src is a directory then + * target_ip is either null or an empty directory. + */ + for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { + if (inodes[i] == du_wip.ip || + (inodes[i] == target_ip && + (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { + struct xfs_perag *pag; + struct xfs_buf *bp; + + pag = xfs_perag_get(mp, + XFS_INO_TO_AGNO(mp, inodes[i]->i_ino)); + error = xfs_read_agi(pag, tp, 0, &bp); + xfs_perag_put(pag); if (error) goto out_trans_cancel; } - } else { /* target_ip != NULL */ - /* - * If target exists and it's a directory, check that both - * target and source are directories and that target can be - * destroyed, or that neither is a directory. - */ - if (S_ISDIR(VFS_I(target_ip)->i_mode)) { - /* - * Make sure target dir is empty. - */ - if (!(xfs_dir_isempty(target_ip)) || - (VFS_I(target_ip)->i_nlink > 2)) { - error = -EEXIST; - goto out_trans_cancel; - } - } + } + + error = xfs_dir_rename_children(tp, &du_src, &du_tgt, spaceres, + &du_wip); + if (error) + goto out_trans_cancel; + if (du_wip.ip) { /* - * 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. + * 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_dir_replace(tp, target_dp, target_name, - src_ip->i_ino, spaceres); - if (error) - goto out_trans_cancel; + inode_state_clear_raw(VFS_I(du_wip.ip), I_LINKABLE); + } - xfs_trans_ichgtime(tp, target_dp, - XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); +out_commit: + /* + * 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); - /* - * 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; + error = xfs_trans_commit(tp); + nospace_error = 0; + goto out_unlock; - 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 */ +out_trans_cancel: + xfs_trans_cancel(tp); +out_unlock: + xfs_iunlock_rename(inodes, num_inodes); +out_tgt_ppargs: + xfs_parent_finish(mp, du_tgt.ppargs); +out_wip_ppargs: + xfs_parent_finish(mp, du_wip.ppargs); +out_src_ppargs: + xfs_parent_finish(mp, du_src.ppargs); +out_release_wip: + if (du_wip.ip) + xfs_irele(du_wip.ip); + if (error == -ENOSPC && nospace_error) + error = nospace_error; + return error; +} + +static int +xfs_iflush( + struct xfs_inode *ip, + struct xfs_buf *bp) +{ + struct xfs_inode_log_item *iip = ip->i_itemp; + struct xfs_dinode *dip; + struct xfs_mount *mp = ip->i_mount; + int error; + + xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED); + ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING)); + ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE || + ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); + ASSERT(iip->ili_item.li_buf == bp); + + dip = xfs_buf_offset(bp, ip->i_imap.im_boffset); /* - * Remove the source. + * We don't flush the inode if any of the following checks fail, but we + * do still update the log item and attach to the backing buffer as if + * the flush happened. This is a formality to facilitate predictable + * error handling as the caller will shutdown and fail the buffer. */ - 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; + error = -EFSCORRUPTED; + 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 (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 ((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 (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, + __func__, ip->i_ino, + ip->i_df.if_nextents + xfs_ifork_nextents(&ip->i_af), + ip->i_nblocks, ip); + goto flush_out; + } + 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; } - /* - * 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); + 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; + } /* - * 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. + * Inode item log recovery for v2 inodes are dependent on the flushiter + * count for correct sequencing. We bump the flush iteration count so + * we can detect flushes which postdate a log record during recovery. + * This is redundant as we now log every change and hence this can't + * happen but we need to still do it to ensure backwards compatibility + * with old kernels that predate logging all inode changes. */ - if (src_is_directory && (new_parent || target_ip != NULL)) { - - /* - * Decrement link count on src_directory since the - * entry that's moved no longer points to it. - */ - error = xfs_droplink(tp, src_dp); - if (error) - goto out_trans_cancel; - } + if (!xfs_has_v3inodes(mp)) + ip->i_flushiter++; /* - * For whiteouts, we only need to update the source dirent with the - * inode number of the whiteout inode rather than removing it - * altogether. + * If there are inline format data / attr forks attached to this inode, + * make sure they are not corrupt. */ - 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; + if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL && + xfs_ifork_verify_local_data(ip)) + goto flush_out; + if (xfs_inode_has_attr_fork(ip) && + ip->i_af.if_format == XFS_DINODE_FMT_LOCAL && + xfs_ifork_verify_local_attr(ip)) + goto flush_out; /* - * For whiteouts, we need to bump the link count on the whiteout inode. - * This means that failures all the way up to this point leave the inode - * on the unlinked list and so cleanup is a simple matter of dropping - * the remaining reference to it. If we fail here after bumping the link - * count, we're shutting down the filesystem so we'll never see the - * intermediate state on disk. + * Copy the dirty parts of the inode into the on-disk inode. We always + * copy out the core of the inode, because if the inode is dirty at all + * the core must be. */ - if (wip) { - ASSERT(VFS_I(wip)->i_nlink == 0); - error = xfs_bumplink(tp, wip); - if (error) - goto out_trans_cancel; - error = xfs_iunlink_remove(tp, wip); - if (error) - goto out_trans_cancel; - xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE); + xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn); - /* - * 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. - */ - VFS_I(wip)->i_state &= ~I_LINKABLE; + /* Wrap, we never let the log put out DI_MAX_FLUSH */ + if (!xfs_has_v3inodes(mp)) { + if (ip->i_flushiter == DI_MAX_FLUSH) + ip->i_flushiter = 0; } - 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); + xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); + if (xfs_inode_has_attr_fork(ip)) + xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); - error = xfs_finish_rename(tp); - if (wip) - xfs_irele(wip); - return error; + /* + * We've recorded everything logged in the inode, so we'd like to clear + * the ili_fields bits so we don't log and flush things unnecessarily. + * However, we can't stop logging all this information until the data + * we've copied into the disk buffer is written to disk. If we did we + * might overwrite the copy of the inode in the log with all the data + * after re-logging only part of it, and in the face of a crash we + * wouldn't have all the data we need to recover. + * + * What we do is move the bits to the ili_last_fields field. When + * logging the inode, these bits are moved back to the ili_fields field. + * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since + * we know that the information those bits represent is permanently on + * disk. As long as the flush completes before the inode is logged + * again, then both ili_fields and ili_last_fields will be cleared. + */ + error = 0; +flush_out: + spin_lock(&iip->ili_lock); + iip->ili_last_fields = iip->ili_fields; + iip->ili_fields = 0; + set_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags); + spin_unlock(&iip->ili_lock); -out_trans_cancel: - xfs_trans_cancel(tp); -out_release_wip: - if (wip) - xfs_irele(wip); + /* + * Store the current LSN of the inode so that we can tell whether the + * item has moved in the AIL from xfs_buf_inode_iodone(). + */ + xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, + &iip->ili_item.li_lsn); + + /* generate the checksum. */ + xfs_dinode_calc_crc(mp, dip); + if (error) + xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE); return error; } -STATIC int +/* + * Non-blocking flush of dirty inode metadata into the backing buffer. + * + * The caller must have a reference to the inode and hold the cluster buffer + * locked. The function will walk across all the inodes on the cluster buffer it + * can find and lock without blocking, and flush them to the cluster buffer. + * + * On successful flushing of at least one inode, the caller must write out the + * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and + * the caller needs to release the buffer. On failure, the filesystem will be + * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED + * will be returned. + */ +int xfs_iflush_cluster( - struct xfs_inode *ip, struct xfs_buf *bp) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_perag *pag; - unsigned long first_index, mask; - unsigned long inodes_per_cluster; - int cilist_size; - struct xfs_inode **cilist; - struct xfs_inode *cip; - int nr_found; + struct xfs_mount *mp = bp->b_mount; + struct xfs_log_item *lip, *n; + struct xfs_inode *ip; + struct xfs_inode_log_item *iip; int clcount = 0; - int i; - - pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); - - inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog; - cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *); - cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS); - if (!cilist) - goto out_put; + int error = 0; - mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1); - first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask; - rcu_read_lock(); - /* really need a gang lookup range call here */ - nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist, - first_index, inodes_per_cluster); - if (nr_found == 0) - goto out_free; - - for (i = 0; i < nr_found; i++) { - cip = cilist[i]; - if (cip == ip) - continue; + /* + * We must use the safe variant here as on shutdown xfs_iflush_abort() + * will remove itself from the list. + */ + list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) { + iip = (struct xfs_inode_log_item *)lip; + ip = iip->ili_inode; /* - * because this is an RCU protected lookup, we could find a - * recently freed or even reallocated inode during the lookup. - * We need to check under the i_flags_lock for a valid inode - * here. Skip it if it is not valid or the wrong inode. + * Quick and dirty check to avoid locks if possible. */ - spin_lock(&cip->i_flags_lock); - if (!cip->i_ino || - __xfs_iflags_test(cip, XFS_ISTALE)) { - spin_unlock(&cip->i_flags_lock); + if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) + continue; + if (xfs_ipincount(ip)) continue; - } /* - * Once we fall off the end of the cluster, no point checking - * any more inodes in the list because they will also all be - * outside the cluster. + * The inode is still attached to the buffer, which means it is + * dirty but reclaim might try to grab it. Check carefully for + * that, and grab the ilock while still holding the i_flags_lock + * to guarantee reclaim will not be able to reclaim this inode + * once we drop the i_flags_lock. */ - if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) { - spin_unlock(&cip->i_flags_lock); - break; + spin_lock(&ip->i_flags_lock); + ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE)); + if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) { + spin_unlock(&ip->i_flags_lock); + continue; } - spin_unlock(&cip->i_flags_lock); /* - * Do an un-protected check to see if the inode is dirty and - * is a candidate for flushing. These checks will be repeated - * later after the appropriate locks are acquired. + * ILOCK will pin the inode against reclaim and prevent + * concurrent transactions modifying the inode while we are + * flushing the inode. If we get the lock, set the flushing + * state before we drop the i_flags_lock. */ - if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0) + if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) { + spin_unlock(&ip->i_flags_lock); continue; + } + __xfs_iflags_set(ip, XFS_IFLUSHING); + spin_unlock(&ip->i_flags_lock); /* - * Try to get locks. If any are unavailable or it is pinned, - * then this inode cannot be flushed and is skipped. + * Abort flushing this inode if we are shut down because the + * inode may not currently be in the AIL. This can occur when + * log I/O failure unpins the inode without inserting into the + * AIL, leaving a dirty/unpinned inode attached to the buffer + * that otherwise looks like it should be flushed. */ - - if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED)) - continue; - if (!xfs_iflock_nowait(cip)) { - xfs_iunlock(cip, XFS_ILOCK_SHARED); - continue; - } - if (xfs_ipincount(cip)) { - xfs_ifunlock(cip); - xfs_iunlock(cip, XFS_ILOCK_SHARED); + if (xlog_is_shutdown(mp->m_log)) { + xfs_iunpin_wait(ip); + xfs_iflush_abort(ip); + xfs_iunlock(ip, XFS_ILOCK_SHARED); + error = -EIO; continue; } - - /* - * Check the inode number again, just to be certain we are not - * racing with freeing in xfs_reclaim_inode(). See the comments - * in that function for more information as to why the initial - * check is not sufficient. - */ - if (!cip->i_ino) { - xfs_ifunlock(cip); - xfs_iunlock(cip, XFS_ILOCK_SHARED); + /* don't block waiting on a log force to unpin dirty inodes */ + if (xfs_ipincount(ip)) { + xfs_iflags_clear(ip, XFS_IFLUSHING); + xfs_iunlock(ip, XFS_ILOCK_SHARED); continue; } + if (!xfs_inode_clean(ip)) + error = xfs_iflush(ip, bp); + else + xfs_iflags_clear(ip, XFS_IFLUSHING); + xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (error) + break; + clcount++; + } + + if (error) { /* - * arriving here means that this inode can be flushed. First - * re-check that it's dirty before flushing. + * Shutdown first so we kill the log before we release this + * buffer. If it is an INODE_ALLOC buffer and pins the tail + * of the log, failing it before the _log_ is shut down can + * result in the log tail being moved forward in the journal + * on disk because log writes can still be taking place. Hence + * unpinning the tail will allow the ICREATE intent to be + * removed from the log an recovery will fail with uninitialised + * inode cluster buffers. */ - if (!xfs_inode_clean(cip)) { - int error; - error = xfs_iflush_int(cip, bp); - if (error) { - xfs_iunlock(cip, XFS_ILOCK_SHARED); - goto cluster_corrupt_out; - } - clcount++; - } else { - xfs_ifunlock(cip); - } - xfs_iunlock(cip, XFS_ILOCK_SHARED); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + bp->b_flags |= XBF_ASYNC; + xfs_buf_ioend_fail(bp); + return error; } - if (clcount) { - XFS_STATS_INC(mp, xs_icluster_flushcnt); - XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount); - } + if (!clcount) + return -EAGAIN; -out_free: - rcu_read_unlock(); - kmem_free(cilist); -out_put: - xfs_perag_put(pag); + XFS_STATS_INC(mp, xs_icluster_flushcnt); + XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount); return 0; +} -cluster_corrupt_out: - /* - * Corruption detected in the clustering loop. Invalidate the - * inode buffer and shut down the filesystem. - */ - rcu_read_unlock(); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); - - /* - * We'll always have an inode attached to the buffer for completion - * process by the time we are called from xfs_iflush(). Hence we have - * always need to do IO completion processing to abort the inodes - * attached to the buffer. handle them just like the shutdown case in - * xfs_buf_submit(). - */ - ASSERT(bp->b_iodone); - bp->b_flags &= ~XBF_DONE; - xfs_buf_stale(bp); - xfs_buf_ioerror(bp, -EIO); - xfs_buf_ioend(bp); - - /* abort the corrupt inode, as it was not attached to the buffer */ - xfs_iflush_abort(cip, false); - kmem_free(cilist); - xfs_perag_put(pag); - return -EFSCORRUPTED; +/* Release an inode. */ +void +xfs_irele( + struct xfs_inode *ip) +{ + trace_xfs_irele(ip, _RET_IP_); + iput(VFS_I(ip)); } /* - * Flush dirty inode metadata into the backing buffer. - * - * The caller must have the inode lock and the inode flush lock held. The - * inode lock will still be held upon return to the caller, and the inode - * flush lock will be released after the inode has reached the disk. - * - * The caller must write out the buffer returned in *bpp and release it. + * Ensure all commited transactions touching the inode are written to the log. */ int -xfs_iflush( - struct xfs_inode *ip, - struct xfs_buf **bpp) +xfs_log_force_inode( + struct xfs_inode *ip) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_buf *bp = NULL; - struct xfs_dinode *dip; - int error; + struct xfs_inode_log_item *iip = ip->i_itemp; + xfs_csn_t seq = 0; - XFS_STATS_INC(mp, xs_iflush_count); + if (!iip) + return 0; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(xfs_isiflocked(ip)); - ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || - ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); + spin_lock(&iip->ili_lock); + seq = iip->ili_commit_seq; + spin_unlock(&iip->ili_lock); - *bpp = NULL; + if (!seq) + return 0; + return xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, NULL); +} + +/* + * Grab the exclusive iolock for a data copy from src to dest, making sure to + * abide vfs locking order (lowest pointer value goes first) and breaking the + * layout leases before proceeding. The loop is needed because we cannot call + * the blocking break_layout() with the iolocks held, and therefore have to + * back out both locks. + */ +static int +xfs_iolock_two_inodes_and_break_layout( + struct inode *src, + struct inode *dest) +{ + int error; - xfs_iunpin_wait(ip); + if (src > dest) + swap(src, dest); - /* - * For stale inodes we cannot rely on the backing buffer remaining - * stale in cache for the remaining life of the stale inode and so - * xfs_imap_to_bp() below may give us a buffer that no longer contains - * inodes below. We have to check this after ensuring the inode is - * unpinned so that it is safe to reclaim the stale inode after the - * flush call. - */ - if (xfs_iflags_test(ip, XFS_ISTALE)) { - xfs_ifunlock(ip); - return 0; +retry: + /* Wait to break both inodes' layouts before we start locking. */ + error = break_layout(src, true); + if (error) + return error; + if (src != dest) { + error = break_layout(dest, true); + if (error) + return error; } - /* - * This may have been unpinned because the filesystem is shutting - * down forcibly. If that's the case we must not write this inode - * to disk, because the log record didn't make it to disk. - * - * We also have to remove the log item from the AIL in this case, - * as we wait for an empty AIL as part of the unmount process. - */ - if (XFS_FORCED_SHUTDOWN(mp)) { - error = -EIO; - goto abort_out; + /* Lock one inode and make sure nobody got in and leased it. */ + inode_lock(src); + error = break_layout(src, false); + if (error) { + inode_unlock(src); + if (error == -EWOULDBLOCK) + goto retry; + return error; } - /* - * Get the buffer containing the on-disk inode. We are doing a try-lock - * operation here, so we may get an EAGAIN error. In that case, we - * simply want to return with the inode still dirty. - * - * If we get any other error, we effectively have a corruption situation - * and we cannot flush the inode, so we treat it the same as failing - * xfs_iflush_int(). - */ - error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK, - 0); - if (error == -EAGAIN) { - xfs_ifunlock(ip); + if (src == dest) + return 0; + + /* Lock the other inode and make sure nobody got in and leased it. */ + inode_lock_nested(dest, I_MUTEX_NONDIR2); + error = break_layout(dest, false); + if (error) { + inode_unlock(src); + inode_unlock(dest); + if (error == -EWOULDBLOCK) + goto retry; return error; } - if (error) - goto corrupt_out; - /* - * First flush out the inode that xfs_iflush was called with. - */ - error = xfs_iflush_int(ip, bp); - if (error) - goto corrupt_out; + return 0; +} - /* - * If the buffer is pinned then push on the log now so we won't - * get stuck waiting in the write for too long. - */ - if (xfs_buf_ispinned(bp)) - xfs_log_force(mp, 0); +static int +xfs_mmaplock_two_inodes_and_break_dax_layout( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int error; + + if (ip1->i_ino > ip2->i_ino) + swap(ip1, ip2); + +again: + /* Lock the first inode */ + xfs_ilock(ip1, XFS_MMAPLOCK_EXCL); + error = xfs_break_dax_layouts(VFS_I(ip1)); + if (error) { + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + return error; + } + if (ip1 == ip2) + return 0; + + /* Nested lock the second inode */ + xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1)); /* - * inode clustering: try to gather other inodes into this write - * - * Note: Any error during clustering will result in the filesystem - * being shut down and completion callbacks run on the cluster buffer. - * As we have already flushed and attached this inode to the buffer, - * it has already been aborted and released by xfs_iflush_cluster() and - * so we have no further error handling to do here. + * We cannot use xfs_break_dax_layouts() directly here because it may + * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable + * for this nested lock case. */ - error = xfs_iflush_cluster(ip, bp); - if (error) - return error; + 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; + } - *bpp = bp; return 0; +} -corrupt_out: - if (bp) - xfs_buf_relse(bp); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); -abort_out: - /* abort the corrupt inode, as it was not attached to the buffer */ - xfs_iflush_abort(ip, false); - return error; +/* + * Lock two inodes so that userspace cannot initiate I/O via file syscalls or + * mmap activity. + */ +int +xfs_ilock2_io_mmap( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + int ret; + + ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2)); + if (ret) + return ret; + + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2); + if (ret) { + inode_unlock(VFS_I(ip2)); + if (ip1 != ip2) + inode_unlock(VFS_I(ip1)); + return ret; + } + } else + filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + + return 0; +} + +/* Unlock both inodes to allow IO and mmap activity. */ +void +xfs_iunlock2_io_mmap( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) { + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + if (ip1 != ip2) + xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL); + } else + filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping, + VFS_I(ip2)->i_mapping); + + inode_unlock(VFS_I(ip2)); + if (ip1 != ip2) + inode_unlock(VFS_I(ip1)); +} + +/* Drop the MMAPLOCK and the IOLOCK after a remap completes. */ +void +xfs_iunlock2_remapping( + struct xfs_inode *ip1, + struct xfs_inode *ip2) +{ + xfs_iflags_clear(ip1, XFS_IREMAPPING); + + if (ip1 != ip2) + xfs_iunlock(ip1, XFS_MMAPLOCK_SHARED); + xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL); + + if (ip1 != ip2) + inode_unlock_shared(VFS_I(ip1)); + inode_unlock(VFS_I(ip2)); } /* - * If there are inline format data / attr forks attached to this inode, - * make sure they're not corrupt. + * Reload the incore inode list for this inode. Caller should ensure that + * the link count cannot change, either by taking ILOCK_SHARED or otherwise + * preventing other threads from executing. */ -bool -xfs_inode_verify_forks( +int +xfs_inode_reload_unlinked_bucket( + struct xfs_trans *tp, struct xfs_inode *ip) { - struct xfs_ifork *ifp; - xfs_failaddr_t fa; - - fa = xfs_ifork_verify_data(ip, &xfs_default_ifork_ops); - if (fa) { - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); - xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork", - ifp->if_u1.if_data, ifp->if_bytes, fa); - return false; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *agibp; + struct xfs_agi *agi; + struct xfs_perag *pag; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino); + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + xfs_agino_t prev_agino, next_agino; + unsigned int bucket; + bool foundit = false; + int error; + + /* Grab the first inode in the list */ + pag = xfs_perag_get(mp, agno); + error = xfs_ialloc_read_agi(pag, tp, 0, &agibp); + xfs_perag_put(pag); + if (error) + return error; + + /* + * We've taken ILOCK_SHARED and the AGI buffer lock to stabilize the + * incore unlinked list pointers for this inode. Check once more to + * see if we raced with anyone else to reload the unlinked list. + */ + if (!xfs_inode_unlinked_incomplete(ip)) { + foundit = true; + goto out_agibp; } - fa = xfs_ifork_verify_attr(ip, &xfs_default_ifork_ops); - if (fa) { - ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK); - xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork", - ifp ? ifp->if_u1.if_data : NULL, - ifp ? ifp->if_bytes : 0, fa); - return false; + bucket = agino % XFS_AGI_UNLINKED_BUCKETS; + agi = agibp->b_addr; + + trace_xfs_inode_reload_unlinked_bucket(ip); + + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating list recovery.", + agino, agno); + + prev_agino = NULLAGINO; + next_agino = be32_to_cpu(agi->agi_unlinked[bucket]); + while (next_agino != NULLAGINO) { + struct xfs_inode *next_ip = NULL; + + /* Found this caller's inode, set its backlink. */ + if (next_agino == agino) { + next_ip = ip; + next_ip->i_prev_unlinked = prev_agino; + foundit = true; + goto next_inode; + } + + /* Try in-memory lookup first. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + if (next_ip) + goto next_inode; + + /* Inode not in memory, try reloading it. */ + error = xfs_iunlink_reload_next(tp, agibp, prev_agino, + next_agino); + if (error) + break; + + /* Grab the reloaded inode. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + if (!next_ip) { + /* No incore inode at all? We reloaded it... */ + ASSERT(next_ip != NULL); + error = -EFSCORRUPTED; + break; + } + +next_inode: + prev_agino = next_agino; + next_agino = next_ip->i_next_unlinked; } - return true; + +out_agibp: + xfs_trans_brelse(tp, agibp); + /* Should have found this inode somewhere in the iunlinked bucket. */ + if (!error && !foundit) + error = -EFSCORRUPTED; + return error; } -STATIC int -xfs_iflush_int( - struct xfs_inode *ip, - struct xfs_buf *bp) +/* Decide if this inode is missing its unlinked list and reload it. */ +int +xfs_inode_reload_unlinked( + struct xfs_inode *ip) { - struct xfs_inode_log_item *iip = ip->i_itemp; - struct xfs_dinode *dip; - struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error = 0; - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - ASSERT(xfs_isiflocked(ip)); - ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || - ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); - ASSERT(iip != NULL && iip->ili_fields != 0); - ASSERT(ip->i_d.di_version > 1); + 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); + xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_trans_cancel(tp); - /* set *dip = inode's place in the buffer */ - dip = xfs_buf_offset(bp, ip->i_imap.im_boffset); + return error; +} - if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC), - mp, XFS_ERRTAG_IFLUSH_1)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: Bad inode %Lu magic number 0x%x, ptr "PTR_FMT, - __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); - goto corrupt_out; - } - if (S_ISREG(VFS_I(ip)->i_mode)) { - if (XFS_TEST_ERROR( - (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && - (ip->i_d.di_format != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_IFLUSH_3)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: Bad regular inode %Lu, ptr "PTR_FMT, - __func__, ip->i_ino, ip); - goto corrupt_out; - } - } else if (S_ISDIR(VFS_I(ip)->i_mode)) { - if (XFS_TEST_ERROR( - (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && - (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) && - (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL), - mp, XFS_ERRTAG_IFLUSH_4)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: Bad directory inode %Lu, ptr "PTR_FMT, - __func__, ip->i_ino, ip); - goto corrupt_out; +/* Has this inode fork been zapped by repair? */ +bool +xfs_ifork_zapped( + const struct xfs_inode *ip, + int whichfork) +{ + unsigned int datamask = 0; + + switch (whichfork) { + case XFS_DATA_FORK: + switch (ip->i_vnode.i_mode & S_IFMT) { + case S_IFDIR: + datamask = XFS_SICK_INO_DIR_ZAPPED; + break; + case S_IFLNK: + datamask = XFS_SICK_INO_SYMLINK_ZAPPED; + break; } + return ip->i_sick & (XFS_SICK_INO_BMBTD_ZAPPED | datamask); + case XFS_ATTR_FORK: + return ip->i_sick & XFS_SICK_INO_BMBTA_ZAPPED; + default: + return false; } - if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents > - ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: detected corrupt incore inode %Lu, " - "total extents = %d, nblocks = %Ld, ptr "PTR_FMT, - __func__, ip->i_ino, - ip->i_d.di_nextents + ip->i_d.di_anextents, - ip->i_d.di_nblocks, ip); - goto corrupt_out; - } - if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize, - mp, XFS_ERRTAG_IFLUSH_6)) { - xfs_alert_tag(mp, XFS_PTAG_IFLUSH, - "%s: bad inode %Lu, forkoff 0x%x, ptr "PTR_FMT, - __func__, ip->i_ino, ip->i_d.di_forkoff, ip); - goto corrupt_out; - } - - /* - * Inode item log recovery for v2 inodes are dependent on the - * di_flushiter count for correct sequencing. We bump the flush - * iteration count so we can detect flushes which postdate a log record - * during recovery. This is redundant as we now log every change and - * hence this can't happen but we need to still do it to ensure - * backwards compatibility with old kernels that predate logging all - * inode changes. - */ - if (ip->i_d.di_version < 3) - ip->i_d.di_flushiter++; +} - /* Check the inline fork data before we write out. */ - if (!xfs_inode_verify_forks(ip)) - goto corrupt_out; +/* Compute the number of data and realtime blocks used by a file. */ +void +xfs_inode_count_blocks( + struct xfs_trans *tp, + struct xfs_inode *ip, + xfs_filblks_t *dblocks, + xfs_filblks_t *rblocks) +{ + struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK); - /* - * Copy the dirty parts of the inode into the on-disk inode. We always - * copy out the core of the inode, because if the inode is dirty at all - * the core must be. - */ - xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn); + *rblocks = 0; + if (XFS_IS_REALTIME_INODE(ip)) + xfs_bmap_count_leaves(ifp, rblocks); + *dblocks = ip->i_nblocks - *rblocks; +} - /* Wrap, we never let the log put out DI_MAX_FLUSH */ - if (ip->i_d.di_flushiter == DI_MAX_FLUSH) - ip->i_d.di_flushiter = 0; +static void +xfs_wait_dax_page( + struct inode *inode) +{ + struct xfs_inode *ip = XFS_I(inode); - xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK); - if (XFS_IFORK_Q(ip)) - xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK); - xfs_inobp_check(mp, bp); + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + schedule(); + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); +} - /* - * We've recorded everything logged in the inode, so we'd like to clear - * the ili_fields bits so we don't log and flush things unnecessarily. - * However, we can't stop logging all this information until the data - * we've copied into the disk buffer is written to disk. If we did we - * might overwrite the copy of the inode in the log with all the data - * after re-logging only part of it, and in the face of a crash we - * wouldn't have all the data we need to recover. - * - * What we do is move the bits to the ili_last_fields field. When - * logging the inode, these bits are moved back to the ili_fields field. - * In the xfs_iflush_done() routine we clear ili_last_fields, since we - * know that the information those bits represent is permanently on - * disk. As long as the flush completes before the inode is logged - * again, then both ili_fields and ili_last_fields will be cleared. - * - * We can play with the ili_fields bits here, because the inode lock - * must be held exclusively in order to set bits there and the flush - * lock protects the ili_last_fields bits. Set ili_logged so the flush - * done routine can tell whether or not to look in the AIL. Also, store - * the current LSN of the inode so that we can tell whether the item has - * moved in the AIL from xfs_iflush_done(). In order to read the lsn we - * need the AIL lock, because it is a 64 bit value that cannot be read - * atomically. - */ - iip->ili_last_fields = iip->ili_fields; - iip->ili_fields = 0; - iip->ili_fsync_fields = 0; - iip->ili_logged = 1; +int +xfs_break_dax_layouts( + struct inode *inode) +{ + xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL); - xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn, - &iip->ili_item.li_lsn); + return dax_break_layout_inode(inode, xfs_wait_dax_page); +} - /* - * Attach the function xfs_iflush_done to the inode's - * buffer. This will remove the inode from the AIL - * and unlock the inode's flush lock when the inode is - * completely written to disk. - */ - xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item); +int +xfs_break_layouts( + struct inode *inode, + uint *iolock, + enum layout_break_reason reason) +{ + bool retry; + int error; - /* generate the checksum. */ - xfs_dinode_calc_crc(mp, dip); + xfs_assert_ilocked(XFS_I(inode), XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL); - ASSERT(!list_empty(&bp->b_li_list)); - ASSERT(bp->b_iodone != NULL); - return 0; + do { + retry = false; + switch (reason) { + case BREAK_UNMAP: + error = xfs_break_dax_layouts(inode); + if (error) + break; + fallthrough; + case BREAK_WRITE: + error = xfs_break_leased_layouts(inode, iolock, &retry); + break; + default: + WARN_ON_ONCE(1); + error = -EINVAL; + } + } while (error == 0 && retry); -corrupt_out: - return -EFSCORRUPTED; + return error; } -/* Release an inode. */ -void -xfs_irele( +/* Returns the size of fundamental allocation unit for a file, in bytes. */ +unsigned int +xfs_inode_alloc_unitsize( struct xfs_inode *ip) { - trace_xfs_irele(ip, _RET_IP_); - iput(VFS_I(ip)); + unsigned int blocks = 1; + + if (XFS_IS_REALTIME_INODE(ip)) + blocks = ip->i_mount->m_sb.sb_rextsize; + + 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)); } |