Merge tag 'xfs-for-linus-v3.13-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs update from Ben Myers:
 "For 3.13-rc1 we have an eclectic assortment of bugfixes, cleanups, and
  refactoring.  Bugfixes that stand out are the fix for the AGF/AGI
  deadlock, incore extent list fixes, verifier fixes for v4 superblocks
  and growfs, and memory leaks.  There are some asserts, warnings, and
  strings that were cleaned up.  There was further rearrangement of code
  to make libxfs and the kernel sync up more easily, differences between
  v2 and v3 directory code were abstracted using an ops vector,
  xfs_inactive was reworked, and the preallocation/hole punching code
  was refactored.

   - simplify kmem_zone_zalloc
   - add traces for AGF/AGI read ops
   - add additional AIL traces
   - fix xfs_remove AGF vs AGI deadlock
   - fix the extent count of new incore extent page in the indirection
     array
   - don't fail bad secondary superblocks verification on v4 filesystems
     due to unzeroed bits after v4 fields
   - fix possible NULL dereference in xlog_verify_iclog
   - remove redundant assert in xfs_dir2_leafn_split
   - prevent stack overflows from page cache allocation
   - fix some sparse warnings
   - fix directory block format verifier to check the leaf entry count
   - abstract the differences in dir2/dir3 via an ops vector
   - continue process of reorganization to make libxfs/kernel code
     merges easier
   - refactor the preallocation and hole punching code
   - fix for growfs and verifiers
   - remove unnecessary scary corruption error when probing non-xfs
     filesystems
   - remove extra newlines from strings passed to printk
   - prevent deadlock trying to cover an active log
   - rework xfs_inactive()
   - add the inode directory type support to XFS_IOC_FSGEOM
   - cleanup (remove) usage of is_bad_inode
   - fix miscalculation in xfs_iext_realloc_direct which results in
     oversized direct extent list
   - remove unnecessary count arg to xfs_iomap_write_allocate
   - fix memory leak in xlog_recover_add_to_trans
   - check superblock instead of block magic to determine if dtype field
     is present
   - fix lockdep annotation due to project quotas
   - fix regression in xfs_node_toosmall which can lead to incorrect
     directory btree node collapse
   - make log recovery verify filesystem uuid of recovering blocks
   - fix XFS_IOC_FREE_EOFBLOCKS definition
   - remove invalid assert in xfs_inode_free
   - fix for AIL lock regression"

* tag 'xfs-for-linus-v3.13-rc1' of git://oss.sgi.com/xfs/xfs: (49 commits)
  xfs: simplify kmem_{zone_}zalloc
  xfs: add tracepoints to AGF/AGI read operations
  xfs: trace AIL manipulations
  xfs: xfs_remove deadlocks due to inverted AGF vs AGI lock ordering
  xfs: fix the extent count when allocating an new indirection array entry
  xfs: be more forgiving of a v4 secondary sb w/ junk in v5 fields
  xfs: fix possible NULL dereference in xlog_verify_iclog
  xfs:xfs_dir2_node.c: pointer use before check for null
  xfs: prevent stack overflows from page cache allocation
  xfs: fix static and extern sparse warnings
  xfs: validity check the directory block leaf entry count
  xfs: make dir2 ftype offset pointers explicit
  xfs: convert directory vector functions to constants
  xfs: convert directory vector functions to constants
  xfs: vectorise encoding/decoding directory headers
  xfs: vectorise DA btree operations
  xfs: vectorise directory leaf operations
  xfs: vectorise directory data operations part 2
  xfs: vectorise directory data operations
  xfs: vectorise remaining shortform dir2 ops
  ...

1 files changed, 31 insertions, 262 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 97f952caea7..5887e41c032 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -18,31 +18,31 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
+#include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
 #include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_dinode.h"
+#include "xfs_da_format.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_trans.h"
 #include "xfs_extfree_item.h"
 #include "xfs_alloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_rtalloc.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 #include "xfs_trans_space.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_log.h"
+#include "xfs_dinode.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -965,32 +965,12 @@ xfs_free_eofblocks(
 	return error;
 }
 
-/*
- * xfs_alloc_file_space()
- *      This routine allocates disk space for the given file.
- *
- *	If alloc_type == 0, this request is for an ALLOCSP type
- *	request which will change the file size.  In this case, no
- *	DMAPI event will be generated by the call.  A TRUNCATE event
- *	will be generated later by xfs_setattr.
- *
- *	If alloc_type != 0, this request is for a RESVSP type
- *	request, and a DMAPI DM_EVENT_WRITE will be generated if the
- *	lower block boundary byte address is less than the file's
- *	length.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-STATIC int
+int
 xfs_alloc_file_space(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	xfs_off_t		offset,
 	xfs_off_t		len,
-	int			alloc_type,
-	int			attr_flags)
+	int			alloc_type)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_off_t		count;
@@ -1232,24 +1212,11 @@ xfs_zero_remaining_bytes(
 	return error;
 }
 
-/*
- * xfs_free_file_space()
- *      This routine frees disk space for the given file.
- *
- *	This routine is only called by xfs_change_file_space
- *	for an UNRESVSP type call.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-STATIC int
+int
 xfs_free_file_space(
-	xfs_inode_t		*ip,
+	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len,
-	int			attr_flags)
+	xfs_off_t		len)
 {
 	int			committed;
 	int			done;
@@ -1267,7 +1234,6 @@ xfs_free_file_space(
 	int			rt;
 	xfs_fileoff_t		startoffset_fsb;
 	xfs_trans_t		*tp;
-	int			need_iolock = 1;
 
 	mp = ip->i_mount;
 
@@ -1284,20 +1250,15 @@ xfs_free_file_space(
 	startoffset_fsb	= XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
-	if (attr_flags & XFS_ATTR_NOLOCK)
-		need_iolock = 0;
-	if (need_iolock) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		/* wait for the completion of any pending DIOs */
-		inode_dio_wait(VFS_I(ip));
-	}
+	/* wait for the completion of any pending DIOs */
+	inode_dio_wait(VFS_I(ip));
 
 	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
 	ioffset = offset & ~(rounding - 1);
 	error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
 					      ioffset, -1);
 	if (error)
-		goto out_unlock_iolock;
+		goto out;
 	truncate_pagecache_range(VFS_I(ip), ioffset, -1);
 
 	/*
@@ -1311,7 +1272,7 @@ xfs_free_file_space(
 		error = xfs_bmapi_read(ip, startoffset_fsb, 1,
 					&imap, &nimap, 0);
 		if (error)
-			goto out_unlock_iolock;
+			goto out;
 		ASSERT(nimap == 0 || nimap == 1);
 		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
 			xfs_daddr_t	block;
@@ -1326,7 +1287,7 @@ xfs_free_file_space(
 		error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
 					&imap, &nimap, 0);
 		if (error)
-			goto out_unlock_iolock;
+			goto out;
 		ASSERT(nimap == 0 || nimap == 1);
 		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
 			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
@@ -1412,27 +1373,23 @@ xfs_free_file_space(
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	}
 
- out_unlock_iolock:
-	if (need_iolock)
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+ out:
 	return error;
 
  error0:
 	xfs_bmap_cancel(&free_list);
  error1:
 	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
-	xfs_iunlock(ip, need_iolock ? (XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL) :
-		    XFS_ILOCK_EXCL);
-	return error;
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	goto out;
 }
 
 
-STATIC int
+int
 xfs_zero_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len,
-	int			attr_flags)
+	xfs_off_t		len)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	uint			granularity;
@@ -1453,9 +1410,6 @@ xfs_zero_file_space(
 	ASSERT(start_boundary >= offset);
 	ASSERT(end_boundary <= offset + len);
 
-	if (!(attr_flags & XFS_ATTR_NOLOCK))
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
 	if (start_boundary < end_boundary - 1) {
 		/* punch out the page cache over the conversion range */
 		truncate_pagecache_range(VFS_I(ip), start_boundary,
@@ -1463,16 +1417,16 @@ xfs_zero_file_space(
 		/* convert the blocks */
 		error = xfs_alloc_file_space(ip, start_boundary,
 					end_boundary - start_boundary - 1,
-					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT,
-					attr_flags);
+					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT);
 		if (error)
-			goto out_unlock;
+			goto out;
 
 		/* We've handled the interior of the range, now for the edges */
-		if (start_boundary != offset)
+		if (start_boundary != offset) {
 			error = xfs_iozero(ip, offset, start_boundary - offset);
-		if (error)
-			goto out_unlock;
+			if (error)
+				goto out;
+		}
 
 		if (end_boundary != offset + len)
 			error = xfs_iozero(ip, end_boundary,
@@ -1486,197 +1440,12 @@ xfs_zero_file_space(
 		error = xfs_iozero(ip, offset, len);
 	}
 
-out_unlock:
-	if (!(attr_flags & XFS_ATTR_NOLOCK))
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+out:
 	return error;
 
 }
 
 /*
- * xfs_change_file_space()
- *      This routine allocates or frees disk space for the given file.
- *      The user specified parameters are checked for alignment and size
- *      limitations.
- *
- * RETURNS:
- *       0 on success
- *      errno on error
- *
- */
-int
-xfs_change_file_space(
-	xfs_inode_t	*ip,
-	int		cmd,
-	xfs_flock64_t	*bf,
-	xfs_off_t	offset,
-	int		attr_flags)
-{
-	xfs_mount_t	*mp = ip->i_mount;
-	int		clrprealloc;
-	int		error;
-	xfs_fsize_t	fsize;
-	int		setprealloc;
-	xfs_off_t	startoffset;
-	xfs_trans_t	*tp;
-	struct iattr	iattr;
-
-	if (!S_ISREG(ip->i_d.di_mode))
-		return XFS_ERROR(EINVAL);
-
-	switch (bf->l_whence) {
-	case 0: /*SEEK_SET*/
-		break;
-	case 1: /*SEEK_CUR*/
-		bf->l_start += offset;
-		break;
-	case 2: /*SEEK_END*/
-		bf->l_start += XFS_ISIZE(ip);
-		break;
-	default:
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * length of <= 0 for resv/unresv/zero is invalid.  length for
-	 * alloc/free is ignored completely and we have no idea what userspace
-	 * might have set it to, so set it to zero to allow range
-	 * checks to pass.
-	 */
-	switch (cmd) {
-	case XFS_IOC_ZERO_RANGE:
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_UNRESVSP64:
-		if (bf->l_len <= 0)
-			return XFS_ERROR(EINVAL);
-		break;
-	default:
-		bf->l_len = 0;
-		break;
-	}
-
-	if (bf->l_start < 0 ||
-	    bf->l_start > mp->m_super->s_maxbytes ||
-	    bf->l_start + bf->l_len < 0 ||
-	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
-		return XFS_ERROR(EINVAL);
-
-	bf->l_whence = 0;
-
-	startoffset = bf->l_start;
-	fsize = XFS_ISIZE(ip);
-
-	setprealloc = clrprealloc = 0;
-	switch (cmd) {
-	case XFS_IOC_ZERO_RANGE:
-		error = xfs_zero_file_space(ip, startoffset, bf->l_len,
-						attr_flags);
-		if (error)
-			return error;
-		setprealloc = 1;
-		break;
-
-	case XFS_IOC_RESVSP:
-	case XFS_IOC_RESVSP64:
-		error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
-						XFS_BMAPI_PREALLOC, attr_flags);
-		if (error)
-			return error;
-		setprealloc = 1;
-		break;
-
-	case XFS_IOC_UNRESVSP:
-	case XFS_IOC_UNRESVSP64:
-		if ((error = xfs_free_file_space(ip, startoffset, bf->l_len,
-								attr_flags)))
-			return error;
-		break;
-
-	case XFS_IOC_ALLOCSP:
-	case XFS_IOC_ALLOCSP64:
-	case XFS_IOC_FREESP:
-	case XFS_IOC_FREESP64:
-		/*
-		 * These operations actually do IO when extending the file, but
-		 * the allocation is done seperately to the zeroing that is
-		 * done. This set of operations need to be serialised against
-		 * other IO operations, such as truncate and buffered IO. We
-		 * need to take the IOLOCK here to serialise the allocation and
-		 * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
-		 * truncate, direct IO) from racing against the transient
-		 * allocated but not written state we can have here.
-		 */
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		if (startoffset > fsize) {
-			error = xfs_alloc_file_space(ip, fsize,
-					startoffset - fsize, 0,
-					attr_flags | XFS_ATTR_NOLOCK);
-			if (error) {
-				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-				break;
-			}
-		}
-
-		iattr.ia_valid = ATTR_SIZE;
-		iattr.ia_size = startoffset;
-
-		error = xfs_setattr_size(ip, &iattr,
-					 attr_flags | XFS_ATTR_NOLOCK);
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-
-		if (error)
-			return error;
-
-		clrprealloc = 1;
-		break;
-
-	default:
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-
-	/*
-	 * update the inode timestamp, mode, and prealloc flag bits
-	 */
-	tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
-	if ((attr_flags & XFS_ATTR_DMI) == 0) {
-		ip->i_d.di_mode &= ~S_ISUID;
-
-		/*
-		 * Note that we don't have to worry about mandatory
-		 * file locking being disabled here because we only
-		 * clear the S_ISGID bit if the Group execute bit is
-		 * on, but if it was on then mandatory locking wouldn't
-		 * have been enabled.
-		 */
-		if (ip->i_d.di_mode & S_IXGRP)
-			ip->i_d.di_mode &= ~S_ISGID;
-
-		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	}
-	if (setprealloc)
-		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
-	else if (clrprealloc)
-		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
-
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	if (attr_flags & XFS_ATTR_SYNC)
-		xfs_trans_set_sync(tp);
-	return xfs_trans_commit(tp, 0);
-}
-
-/*
  * We need to check that the format of the data fork in the temporary inode is
  * valid for the target inode before doing the swap. This is not a problem with
  * attr1 because of the fixed fork offset, but attr2 has a dynamically sized