Merge tag 'xfs-for-linus-3.16-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs updates from Dave Chinner:
 "This update contains:
   - cleanup removing unused function args
   - rework of the filestreams allocator to use dentry cache parent
     lookups
   - new on-disk free inode btree and optimised inode allocator
   - various bug fixes
   - rework of internal attribute API
   - cleanup of superblock feature bit support to remove historic cruft
   - more fixes and minor cleanups
   - added a new directory/attribute geometry abstraction
   - yet more fixes and minor cleanups"

* tag 'xfs-for-linus-3.16-rc1' of git://oss.sgi.com/xfs/xfs: (86 commits)
  xfs: fix xfs_da_args sparse warning in xfs_readdir
  xfs: Fix rounding in xfs_alloc_fix_len()
  xfs: tone down writepage/releasepage WARN_ONs
  xfs: small cleanup in xfs_lowbit64()
  xfs: kill xfs_buf_geterror()
  xfs: xfs_readsb needs to check for magic numbers
  xfs: block allocation work needs to be kswapd aware
  xfs: remove redundant geometry information from xfs_da_state
  xfs: replace attr LBSIZE with xfs_da_geometry
  xfs: pass xfs_da_args to xfs_attr_leaf_newentsize
  xfs: use xfs_da_geometry for block size in attr code
  xfs: remove mp->m_dir_geo from directory logging
  xfs: reduce direct usage of mp->m_dir_geo
  xfs: move node entry counts to xfs_da_geometry
  xfs: convert dir/attr btree threshold to xfs_da_geometry
  xfs: convert m_dirblksize to xfs_da_geometry
  xfs: convert m_dirblkfsbs to xfs_da_geometry
  xfs: convert directory segment limits to xfs_da_geometry
  xfs: convert directory db conversion to xfs_da_geometry
  xfs: convert directory dablk conversion to xfs_da_geometry
  ...

92 files changed, 2648 insertions, 2785 deletions

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2b363e23f36e..ff3f0b3cfdb3 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -278,6 +278,17 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	return ret;
 }
 
+static int quota_rmxquota(struct super_block *sb, void __user *addr)
+{
+	__u32 flags;
+
+	if (copy_from_user(&flags, addr, sizeof(flags)))
+		return -EFAULT;
+	if (!sb->s_qcop->rm_xquota)
+		return -ENOSYS;
+	return sb->s_qcop->rm_xquota(sb, flags);
+}
+
 /* Copy parameters and call proper function */
 static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		       void __user *addr, struct path *path)
@@ -316,8 +327,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return sb->s_qcop->quota_sync(sb, type);
 	case Q_XQUOTAON:
 	case Q_XQUOTAOFF:
-	case Q_XQUOTARM:
 		return quota_setxstate(sb, cmd, addr);
+	case Q_XQUOTARM:
+		return quota_rmxquota(sb, addr);
 	case Q_XGETQSTAT:
 		return quota_getxstate(sb, addr);
 	case Q_XGETQSTATV:
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 0fdd4109c624..6e247a99f5db 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -160,30 +160,38 @@ typedef struct xfs_agi {
 	 * still being referenced.
 	 */
 	__be32		agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
-
+	/*
+	 * This marks the end of logging region 1 and start of logging region 2.
+	 */
 	uuid_t		agi_uuid;	/* uuid of filesystem */
 	__be32		agi_crc;	/* crc of agi sector */
 	__be32		agi_pad32;
 	__be64		agi_lsn;	/* last write sequence */
 
+	__be32		agi_free_root; /* root of the free inode btree */
+	__be32		agi_free_level;/* levels in free inode btree */
+
 	/* structure must be padded to 64 bit alignment */
 } xfs_agi_t;
 
 #define XFS_AGI_CRC_OFF		offsetof(struct xfs_agi, agi_crc)
 
-#define	XFS_AGI_MAGICNUM	0x00000001
-#define	XFS_AGI_VERSIONNUM	0x00000002
-#define	XFS_AGI_SEQNO		0x00000004
-#define	XFS_AGI_LENGTH		0x00000008
-#define	XFS_AGI_COUNT		0x00000010
-#define	XFS_AGI_ROOT		0x00000020
-#define	XFS_AGI_LEVEL		0x00000040
-#define	XFS_AGI_FREECOUNT	0x00000080
-#define	XFS_AGI_NEWINO		0x00000100
-#define	XFS_AGI_DIRINO		0x00000200
-#define	XFS_AGI_UNLINKED	0x00000400
-#define	XFS_AGI_NUM_BITS	11
-#define	XFS_AGI_ALL_BITS	((1 << XFS_AGI_NUM_BITS) - 1)
+#define	XFS_AGI_MAGICNUM	(1 << 0)
+#define	XFS_AGI_VERSIONNUM	(1 << 1)
+#define	XFS_AGI_SEQNO		(1 << 2)
+#define	XFS_AGI_LENGTH		(1 << 3)
+#define	XFS_AGI_COUNT		(1 << 4)
+#define	XFS_AGI_ROOT		(1 << 5)
+#define	XFS_AGI_LEVEL		(1 << 6)
+#define	XFS_AGI_FREECOUNT	(1 << 7)
+#define	XFS_AGI_NEWINO		(1 << 8)
+#define	XFS_AGI_DIRINO		(1 << 9)
+#define	XFS_AGI_UNLINKED	(1 << 10)
+#define	XFS_AGI_NUM_BITS_R1	11	/* end of the 1st agi logging region */
+#define	XFS_AGI_ALL_BITS_R1	((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define	XFS_AGI_FREE_ROOT	(1 << 11)
+#define	XFS_AGI_FREE_LEVEL	(1 << 12)
+#define	XFS_AGI_NUM_BITS_R2	13
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index c1cf6a336a72..d43813267a80 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -257,16 +257,14 @@ xfs_alloc_fix_len(
 	k = rlen % args->prod;
 	if (k == args->mod)
 		return;
-	if (k > args->mod) {
-		if ((int)(rlen = rlen - k - args->mod) < (int)args->minlen)
-			return;
-	} else {
-		if ((int)(rlen = rlen - args->prod - (args->mod - k)) <
-		    (int)args->minlen)
-			return;
-	}
-	ASSERT(rlen >= args->minlen);
-	ASSERT(rlen <= args->maxlen);
+	if (k > args->mod)
+		rlen = rlen - (k - args->mod);
+	else
+		rlen = rlen - args->prod + (args->mod - k);
+	if ((int)rlen < (int)args->minlen)
+		return;
+	ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
+	ASSERT(rlen % args->prod == args->mod);
 	args->len = rlen;
 }
 
@@ -541,7 +539,6 @@ xfs_alloc_read_agfl(
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
 	if (error)
 		return error;
-	ASSERT(!xfs_buf_geterror(bp));
 	xfs_buf_set_ref(bp, XFS_AGFL_REF);
 	*bpp = bp;
 	return 0;
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index cc1eadcbb049..8358f1ded94d 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -70,7 +70,6 @@ xfs_allocbt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			length,
 	int			*stat)
 {
 	int			error;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0479c32c5eb1..e32640eedea6 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -975,14 +975,39 @@ xfs_vm_writepage(
 	 * Given that we do not allow direct reclaim to call us, we should
 	 * never be called while in a filesystem transaction.
 	 */
-	if (WARN_ON(current->flags & PF_FSTRANS))
+	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
 		goto redirty;
 
 	/* Is this page beyond the end of the file? */
 	offset = i_size_read(inode);
 	end_index = offset >> PAGE_CACHE_SHIFT;
 	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
-	if (page->index >= end_index) {
+
+	/*
+	 * The page index is less than the end_index, adjust the end_offset
+	 * to the highest offset that this page should represent.
+	 * -----------------------------------------------------
+	 * |			file mapping	       | <EOF> |
+	 * -----------------------------------------------------
+	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
+	 * ^--------------------------------^----------|--------
+	 * |     desired writeback range    |      see else    |
+	 * ---------------------------------^------------------|
+	 */
+	if (page->index < end_index)
+		end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+	else {
+		/*
+		 * Check whether the page to write out is beyond or straddles
+		 * i_size or not.
+		 * -------------------------------------------------------
+		 * |		file mapping		        | <EOF>  |
+		 * -------------------------------------------------------
+		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
+		 * ^--------------------------------^-----------|---------
+		 * |				    |      Straddles     |
+		 * ---------------------------------^-----------|--------|
+		 */
 		unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
 
 		/*
@@ -990,24 +1015,36 @@ xfs_vm_writepage(
 		 * truncate operation that is in progress. We must redirty the
 		 * page so that reclaim stops reclaiming it. Otherwise
 		 * xfs_vm_releasepage() is called on it and gets confused.
+		 *
+		 * Note that the end_index is unsigned long, it would overflow
+		 * if the given offset is greater than 16TB on 32-bit system
+		 * and if we do check the page is fully outside i_size or not
+		 * via "if (page->index >= end_index + 1)" as "end_index + 1"
+		 * will be evaluated to 0.  Hence this page will be redirtied
+		 * and be written out repeatedly which would result in an
+		 * infinite loop, the user program that perform this operation
+		 * will hang.  Instead, we can verify this situation by checking
+		 * if the page to write is totally beyond the i_size or if it's
+		 * offset is just equal to the EOF.
 		 */
-		if (page->index >= end_index + 1 || offset_into_page == 0)
+		if (page->index > end_index ||
+		    (page->index == end_index && offset_into_page == 0))
 			goto redirty;
 
 		/*
 		 * The page straddles i_size.  It must be zeroed out on each
 		 * and every writepage invocation because it may be mmapped.
 		 * "A file is mapped in multiples of the page size.  For a file
-		 * that is not a multiple of the  page size, the remaining
+		 * that is not a multiple of the page size, the remaining
 		 * memory is zeroed when mapped, and writes to that region are
 		 * not written out to the file."
 		 */
 		zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+		/* Adjust the end_offset to the end of file */
+		end_offset = offset;
 	}
 
-	end_offset = min_t(unsigned long long,
-			(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
-			offset);
 	len = 1 << inode->i_blkbits;
 
 	bh = head = page_buffers(page);
@@ -1188,9 +1225,9 @@ xfs_vm_releasepage(
 
 	xfs_count_page_state(page, &delalloc, &unwritten);
 
-	if (WARN_ON(delalloc))
+	if (WARN_ON_ONCE(delalloc))
 		return 0;
-	if (WARN_ON(unwritten))
+	if (WARN_ON_ONCE(unwritten))
 		return 0;
 
 	return try_to_free_buffers(page);
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index abda1124a70f..bfe36fc2cdc2 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -77,17 +77,27 @@ STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
 
 
 STATIC int
-xfs_attr_name_to_xname(
-	struct xfs_name	*xname,
-	const unsigned char *aname)
+xfs_attr_args_init(
+	struct xfs_da_args	*args,
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	int			flags)
 {
-	if (!aname)
+
+	if (!name)
 		return EINVAL;
-	xname->name = aname;
-	xname->len = strlen((char *)aname);
-	if (xname->len >= MAXNAMELEN)
+
+	memset(args, 0, sizeof(*args));
+	args->geo = dp->i_mount->m_attr_geo;
+	args->whichfork = XFS_ATTR_FORK;
+	args->dp = dp;
+	args->flags = flags;
+	args->name = name;
+	args->namelen = strlen((const char *)name);
+	if (args->namelen >= MAXNAMELEN)
 		return EFAULT;		/* match IRIX behaviour */
 
+	args->hashval = xfs_da_hashname(args->name, args->namelen);
 	return 0;
 }
 
@@ -106,79 +116,46 @@ xfs_inode_hasattr(
  * Overall external interface routines.
  *========================================================================*/
 
-STATIC int
-xfs_attr_get_int(
+int
+xfs_attr_get(
 	struct xfs_inode	*ip,
-	struct xfs_name		*name,
+	const unsigned char	*name,
 	unsigned char		*value,
 	int			*valuelenp,
 	int			flags)
 {
-	xfs_da_args_t   args;
-	int             error;
+	struct xfs_da_args	args;
+	uint			lock_mode;
+	int			error;
+
+	XFS_STATS_INC(xs_attr_get);
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return EIO;
 
 	if (!xfs_inode_hasattr(ip))
 		return ENOATTR;
 
-	/*
-	 * Fill in the arg structure for this request.
-	 */
-	memset((char *)&args, 0, sizeof(args));
-	args.name = name->name;
-	args.namelen = name->len;
+	error = xfs_attr_args_init(&args, ip, name, flags);
+	if (error)
+		return error;
+
 	args.value = value;
 	args.valuelen = *valuelenp;
-	args.flags = flags;
-	args.hashval = xfs_da_hashname(args.name, args.namelen);
-	args.dp = ip;
-	args.whichfork = XFS_ATTR_FORK;
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
-	if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+	lock_mode = xfs_ilock_attr_map_shared(ip);
+	if (!xfs_inode_hasattr(ip))
+		error = ENOATTR;
+	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
 		error = xfs_attr_shortform_getvalue(&args);
-	} else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) {
+	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
 		error = xfs_attr_leaf_get(&args);
-	} else {
+	else
 		error = xfs_attr_node_get(&args);
-	}
+	xfs_iunlock(ip, lock_mode);
 
-	/*
-	 * Return the number of bytes in the value to the caller.
-	 */
 	*valuelenp = args.valuelen;
-
-	if (error == EEXIST)
-		error = 0;
-	return(error);
-}
-
-int
-xfs_attr_get(
-	xfs_inode_t	*ip,
-	const unsigned char *name,
-	unsigned char	*value,
-	int		*valuelenp,
-	int		flags)
-{
-	int		error;
-	struct xfs_name	xname;
-	uint		lock_mode;
-
-	XFS_STATS_INC(xs_attr_get);
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return(EIO);
-
-	error = xfs_attr_name_to_xname(&xname, name);
-	if (error)
-		return error;
-
-	lock_mode = xfs_ilock_attr_map_shared(ip);
-	error = xfs_attr_get_int(ip, &xname, value, valuelenp, flags);
-	xfs_iunlock(ip, lock_mode);
-	return(error);
+	return error == EEXIST ? 0 : error;
 }
 
 /*
@@ -186,12 +163,10 @@ xfs_attr_get(
  */
 STATIC int
 xfs_attr_calc_size(
-	struct xfs_inode 	*ip,
-	int			namelen,
-	int			valuelen,
+	struct xfs_da_args	*args,
 	int			*local)
 {