Merge tag 'xfs-for-linus-4.10-rc6-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs uodates from Darrick Wong:
 "I have some more fixes this week: better input validation, corruption
  avoidance, build fixes, memory leak fixes, and a couple from Christoph
  to avoid an ENOSPC failure.

  Summary:
   - Fix race conditions in the CoW code
   - Fix some incorrect input validation checks
   - Avoid crashing fs by running out of space when freeing inodes
   - Fix toctou race wrt whether or not an inode has an attr
   - Fix build error on arm
   - Fix page refcount corruption when readahead fails
   - Don't corrupt userspace in the bmap ioctl"

* tag 'xfs-for-linus-4.10-rc6-5' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: prevent quotacheck from overloading inode lru
  xfs: fix bmv_count confusion w/ shared extents
  xfs: clear _XBF_PAGES from buffers when readahead page
  xfs: extsize hints are not unlikely in xfs_bmap_btalloc
  xfs: remove racy hasattr check from attr ops
  xfs: use per-AG reservations for the finobt
  xfs: only update mount/resv fields on success in __xfs_ag_resv_init
  xfs: verify dirblocklog correctly
  xfs: fix COW writeback race

fs/xfs/libxfs/xfs_ag_resv.c

@@ -39,6 +39,7 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_ialloc_btree.h"
 
 /*
  * Per-AG Block Reservations
@@ -200,22 +201,30 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
+	xfs_extlen_t			reserved;
 
-	resv = xfs_perag_resv(pag, type);
 	if (used > ask)
 		ask = used;
-	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = ask - used;
-	mp->m_ag_max_usable -= ask;
+	reserved = ask - used;
 
-	trace_xfs_ag_resv_init(pag, type, ask);
-
-	error = xfs_mod_fdblocks(mp, -(int64_t)resv->ar_reserved, true);
-	if (error)
+	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
+		xfs_warn(mp,
+"Per-AG reservation for AG %u failed.  Filesystem may run out of space.",
+				pag->pag_agno);
+		return error;
+	}
 
-	return error;
+	mp->m_ag_max_usable -= ask;
+
+	resv = xfs_perag_resv(pag, type);
+	resv->ar_asked = ask;
+	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+
+	trace_xfs_ag_resv_init(pag, type, ask);
+	return 0;
 }
 
 /* Create a per-AG block reservation. */
@@ -223,6 +232,8 @@ int
 xfs_ag_resv_init(
 	struct xfs_perag		*pag)
 {
+	struct xfs_mount		*mp = pag->pag_mount;
+	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_extlen_t			ask;
 	xfs_extlen_t			used;
 	int				error = 0;
@@ -231,23 +242,45 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(pag->pag_mount,
-				pag->pag_agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
-				ask, used);
+		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
+
+		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+				ask, used);
+		if (error) {
+			/*
+			 * Because we didn't have per-AG reservations when the
+			 * finobt feature was added we might not be able to
+			 * reserve all needed blocks.  Warn and fall back to the
+			 * old and potentially buggy code in that case, but
+			 * ensure we do have the reservation for the refcountbt.
+			 */
+			ask = used = 0;
+
+			mp->m_inotbt_nores = true;
+
+			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+					&used);
+			if (error)
+				goto out;
+
+			error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+					ask, used);
+			if (error)
+				goto out;
+		}
 	}
 
 	/* Create the AGFL metadata reservation */
 	if (pag->pag_agfl_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(pag->pag_mount, pag->pag_agno,
-				&ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -256,9 +289,16 @@ xfs_ag_resv_init(
 			goto out;
 	}
 
+#ifdef DEBUG
+	/* need to read in the AGF for the ASSERT below to work */
+	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	if (error)
+		return error;
+
 	ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
 	       xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
 	       pag->pagf_freeblks + pag->pagf_flcount);
+#endif
 out:
 	return error;
 }

fs/xfs/libxfs/xfs_attr.c

@@ -131,9 +131,6 @@ xfs_attr_get(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(ip))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, ip, name, flags);
 	if (error)
 		return error;
@@ -392,9 +389,6 @@ xfs_attr_remove(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(dp))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, dp, name, flags);
 	if (error)
 		return error;

fs/xfs/libxfs/xfs_bmap.c

@@ -3629,7 +3629,7 @@ xfs_bmap_btalloc(
 		align = xfs_get_cowextsz_hint(ap->ip);
 	else if (xfs_alloc_is_userdata(ap->datatype))
 		align = xfs_get_extsz_hint(ap->ip);
-	if (unlikely(align)) {
+	if (align) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
 						align, 0, ap->eof, 0, ap->conv,
 						&ap->offset, &ap->length);
@@ -3701,7 +3701,7 @@ xfs_bmap_btalloc(
 		args.minlen = ap->minlen;
 	}
 	/* apply extent size hints if obtained earlier */
-	if (unlikely(align)) {
+	if (align) {
 		args.prod = align;
 		if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod)))
 			args.mod = (xfs_extlen_t)(args.prod - args.mod);
@@ -4514,8 +4514,6 @@ xfs_bmapi_write(
 	int			n;		/* current extent index */
 	xfs_fileoff_t		obno;		/* old block number (offset) */
 	int			whichfork;	/* data or attr fork */
-	char			inhole;		/* current location is hole in file */
-	char			wasdelay;	/* old extent was delayed */
 
 #ifdef DEBUG
 	xfs_fileoff_t		orig_bno;	/* original block number value */
@@ -4603,22 +4601,44 @@ xfs_bmapi_write(
 	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
-		inhole = eof || bma.got.br_startoff > bno;
-		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
+		bool			need_alloc = false, wasdelay = false;
 
-		/*
-		 * Make sure we only reflink into a hole.
-		 */
-		if (flags & XFS_BMAPI_REMAP)
-			ASSERT(inhole);
-		if (flags & XFS_BMAPI_COWFORK)
-			ASSERT(!inhole);
+		/* in hole or beyoned EOF? */
+		if (eof || bma.got.br_startoff > bno) {
+			if (flags & XFS_BMAPI_DELALLOC) {
+				/*
+				 * For the COW fork we can reasonably get a
+				 * request for converting an extent that races
+				 * with other threads already having converted
+				 * part of it, as there converting COW to
+				 * regular blocks is not protected using the
+				 * IOLOCK.
+				 */
+				ASSERT(flags & XFS_BMAPI_COWFORK);
+				if (!(flags & XFS_BMAPI_COWFORK)) {
+					error = -EIO;
+					goto error0;
+				}
+
+				if (eof || bno >= end)
+					break;
+			} else {
+				need_alloc = true;
+			}
+		} else {
+			/*
+			 * Make sure we only reflink into a hole.
+			 */
+			ASSERT(!(flags & XFS_BMAPI_REMAP));
+			if (isnullstartblock(bma.got.br_startblock))
+				wasdelay = true;
+		}
 
 		/*
 		 * First, deal with the hole before the allocated space
 		 * that we found, if any.
 		 */
-		if (inhole || wasdelay) {
+		if (need_alloc || wasdelay) {
 			bma.eof = eof;
 			bma.conv = !!(flags & XFS_BMAPI_CONVERT);
 			bma.wasdel = wasdelay;

fs/xfs/libxfs/xfs_bmap.h

@@ -110,6 +110,9 @@ struct xfs_extent_free_item
 /* Map something in the CoW fork. */
 #define XFS_BMAPI_COWFORK	0x200
 
+/* Only convert delalloc space, don't allocate entirely new extents */
+#define XFS_BMAPI_DELALLOC	0x400
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -120,7 +123,8 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
 	{ XFS_BMAPI_REMAP,	"REMAP" }, \
-	{ XFS_BMAPI_COWFORK,	"COWFORK" }
+	{ XFS_BMAPI_COWFORK,	"COWFORK" }, \
+	{ XFS_BMAPI_DELALLOC,	"DELALLOC" }
 
 
 static inline int xfs_bmapi_aflag(int w)

fs/xfs/libxfs/xfs_ialloc_btree.c

@@ -82,11 +82,12 @@ xfs_finobt_set_root(
 }
 
 STATIC int
-xfs_inobt_alloc_block(
+__xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			*stat)
+	int			*stat,
+	enum xfs_ag_resv_type	resv)
 {
 	xfs_alloc_arg_t		args;		/* block allocation args */
 	int			error;		/* error return value */
@@ -103,6 +104,7 @@ xfs_inobt_alloc_block(
 	args.maxlen = 1;
 	args.prod = 1;
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
+	args.resv = resv;
 
 	error = xfs_alloc_vextent(&args);
 	if (error) {
@@ -122,6 +124,27 @@ xfs_inobt_alloc_block(
 	return 0;
 }
 
+STATIC int
+xfs_inobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE);
+}
+
+STATIC int
+xfs_finobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat,
+			XFS_AG_RESV_METADATA);
+}
+
 STATIC int
 xfs_inobt_free_block(
 	struct xfs_btree_cur	*cur,
@@ -328,7 +351,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_finobt_set_root,
-	.alloc_block		= xfs_inobt_alloc_block,
+	.alloc_block		= xfs_finobt_alloc_block,
 	.free_block		= xfs_inobt_free_block,
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
@@ -480,3 +503,64 @@ xfs_inobt_rec_check_count(
 	return 0;
 }
 #endif	/* DEBUG */
+
+static xfs_extlen_t
+xfs_inobt_max_size(
+	struct xfs_mount	*mp)
+{
+	/* Bail out if we're uninitialized, which can happen in mkfs. */
+	if (mp->m_inobt_mxr[0] == 0)
+		return 0;
+
+	return xfs_btree_calc_size(mp, mp->m_inobt_mnr,
+		(uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
+				XFS_INODES_PER_CHUNK);
+}
+
+static int
+xfs_inobt_count_blocks(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_btnum_t		btnum,
+	xfs_extlen_t		*tree_blocks)
+{
+	struct xfs_buf		*agbp;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	if (error)
+		return error;
+
+	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	error = xfs_btree_count_blocks(cur, tree_blocks);
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_buf_relse(agbp);
+
+	return error;
+}
+
+/*
+ * Figure out how many blocks to reserve and how many are used by this btree.
+ */
+int
+xfs_finobt_calc_reserves(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_extlen_t		*ask,
+	xfs_extlen_t		*used)
+{
+	xfs_extlen_t		tree_len = 0;
+	int			error;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return 0;
+
+	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	if (error)
+		return error;
+
+	*ask += xfs_inobt_max_size(mp);
+	*used += tree_len;
+	return 0;
+}

fs/xfs/libxfs/xfs_ialloc_btree.h

@@ -72,4 +72,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
+		xfs_extlen_t *ask, xfs_extlen_t *used);
+
 #endif	/* __XFS_IALLOC_BTREE_H__ */

fs/xfs/libxfs/xfs_sb.c

@@ -242,7 +242,7 @@ xfs_mount_validate_sb(
 	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
 	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
 	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
-	    sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG			||
+	    sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
 	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
 	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||

fs/xfs/xfs_bmap_util.c

@@ -528,7 +528,6 @@ xfs_getbmap(
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
 	xfs_mount_t		*mp;		/* file system mount point */
 	int			nex;		/* # of user extents can do */
-	int			nexleft;	/* # of user extents left */
 	int			subnex;		/* # of bmapi's can do */
 	int			nmap;		/* number of map entries */
 	struct getbmapx		*out;		/* output structure */
@@ -686,10 +685,8 @@ xfs_getbmap(
 		goto out_free_map;
 	}
 
-	nexleft = nex;
-
 	do {
-		nmap = (nexleft > subnex) ? subnex : nexleft;
+		nmap = (nex> subnex) ? subnex : nex;
 		error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
 				       XFS_BB_TO_FSB(mp, bmv->bmv_length),
 				       map, &nmap, bmapi_flags);
@@ -697,8 +694,8 @@ xfs_getbmap(
 			goto out_free_map;
 		ASSERT(nmap <= subnex);
 
-		for (i = 0; i < nmap && nexleft && bmv->bmv_length &&
-				cur_ext < bmv->bmv_count; i++) {
+		for (i = 0; i < nmap && bmv->bmv_length &&
+				cur_ext < bmv->bmv_count - 1; i++) {
 			out[cur_ext].bmv_oflags = 0;
 			if (map[i].br_state == XFS_EXT_UNWRITTEN)
 				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
@@ -760,16 +757,27 @@ xfs_getbmap(
 				continue;
 			}
 
+			/*
+			 * In order to report shared extents accurately,
+			 * we report each distinct shared/unshared part
+			 * of a single bmbt record using multiple bmap
+			 * extents.  To make that happen, we iterate the
+			 * same map array item multiple times, each
+			 * time trimming out the subextent that we just
+			 * reported.
+			 *
+			 * Because of this, we must check the out array
+			 * index (cur_ext) directly against bmv_count-1
+			 * to avoid overflows.
+			 */
 			if (inject_map.br_startblock != NULLFSBLOCK) {
 				map[i] = inject_map;
 				i--;
-			} else
-				nexleft--;
+			}
 			bmv->bmv_entries++;
 			cur_ext++;
 		}
-	} while (nmap && nexleft && bmv->bmv_length &&
-		 cur_ext < bmv->bmv_count);
+	} while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1);
 
  out_free_map:
 	kmem_free(map);

fs/xfs/xfs_buf.c

@@ -422,6 +422,7 @@ retry:
 out_free_pages:
 	for (i = 0; i < bp->b_page_count; i++)
 		__free_page(bp->b_pages[i]);
+	bp->b_flags &= ~_XBF_PAGES;
 	return error;
 }
 

fs/xfs/xfs_inode.c

@@ -1792,22 +1792,23 @@ xfs_inactive_ifree(
 	int			error;
 
 	/*
-	 * The ifree transaction might need to allocate blocks for record
-	 * insertion to the finobt. We don't want to fail here at ENOSPC, so
-	 * allow ifree to dip into the reserved block pool if necessary.
-	 *
-	 * Freeing large sets of inodes generally means freeing inode chunks,
-	 * directory and file data blocks, so this should be relatively safe.
-	 * Only under severe circumstances should it be possible to free enough
-	 * inodes to exhaust the reserve block pool via finobt expansion while
-	 * at the same time not creating free space in the filesystem.
+	 * We try to use a per-AG reservation for any block needed by the finobt
+	 * tree, but as the finobt feature predates the per-AG reservation
+	 * support a degraded file system might not have enough space for the
+	 * reservation at mount time.  In that case try to dip into the reserved
+	 * pool and pray.
 	 *
 	 * Send a warning if the reservation does happen to fail, as the inode
 	 * now remains allocated and sits on the unlinked list until the fs is
 	 * repaired.
 	 */
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
-			XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+	if (unlikely(mp->m_inotbt_nores)) {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
+				XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
+				&tp);
+	} else {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp);
+	}
 	if (error) {
 		if (error == -ENOSPC) {
 			xfs_warn_ratelimited(mp,

fs/xfs/xfs_iomap.c

@@ -681,7 +681,7 @@ xfs_iomap_write_allocate(
 	xfs_trans_t	*tp;
 	int		nimaps;
 	int		error = 0;
-	int		flags = 0;
+	int		flags = XFS_BMAPI_DELALLOC;
 	int		nres;
 
 	if (whichfork == XFS_COW_FORK)

fs/xfs/xfs_mount.h

@@ -140,6 +140,7 @@ typedef struct xfs_mount {
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
 	__uint64_t		m_flags;	/* global mount flags */
+	bool			m_inotbt_nores; /* no per-AG finobt resv. */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
 	int			m_ialloc_min_blks;/* min blocks in sparse inode

fs/xfs/xfs_qm.c

@@ -1177,7 +1177,8 @@ xfs_qm_dqusage_adjust(
 	 * the case in all other instances. It's OK that we do this because
 	 * quotacheck is done only at mount time.
 	 */
-	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
+	error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
+			 &ip);
 	if (error) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;