1 files changed, 218 insertions, 97 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index bc446418e227..e0905ad171f0 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1079,21 +1079,13 @@ xfs_bmap_add_attrfork(
 
 	blks = XFS_ADDAFORK_SPACE_RES(mp);
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_addafork, blks, 0,
-			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
+	error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_addafork, blks, 0,
+			rsvd, &tp);
 	if (error)
 		return error;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
-			XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
-			XFS_QMOPT_RES_REGBLKS);
-	if (error)
-		goto trans_cancel;
 	if (XFS_IFORK_Q(ip))
 		goto trans_cancel;
 
-	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_bmap_set_attrforkoff(ip, size, &version);
 	if (error)
@@ -3463,34 +3455,16 @@ xfs_bmap_btalloc_accounting(
 		args->len);
 }
 
-STATIC int
-xfs_bmap_btalloc(
-	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
+static int
+xfs_bmap_compute_alignments(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args)
 {
-	xfs_mount_t	*mp;		/* mount point structure */
-	xfs_alloctype_t	atype = 0;	/* type for allocation routines */
-	xfs_extlen_t	align = 0;	/* minimum allocation alignment */
-	xfs_agnumber_t	fb_agno;	/* ag number of ap->firstblock */
-	xfs_agnumber_t	ag;
-	xfs_alloc_arg_t	args;
-	xfs_fileoff_t	orig_offset;
-	xfs_extlen_t	orig_length;
-	xfs_extlen_t	blen;
-	xfs_extlen_t	nextminlen = 0;
-	int		nullfb;		/* true if ap->firstblock isn't set */
-	int		isaligned;
-	int		tryagain;
-	int		error;
-	int		stripe_align;
-
-	ASSERT(ap->length);
-	orig_offset = ap->offset;
-	orig_length = ap->length;
-
-	mp = ap->ip->i_mount;
+	struct xfs_mount	*mp = args->mp;
+	xfs_extlen_t		align = 0; /* minimum allocation alignment */
+	int			stripe_align = 0;
 
 	/* stripe alignment for allocation is determined by mount parameters */
-	stripe_align = 0;
 	if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
 		stripe_align = mp->m_swidth;
 	else if (mp->m_dalign)
@@ -3501,13 +3475,171 @@ xfs_bmap_btalloc(
 	else if (ap->datatype & XFS_ALLOC_USERDATA)
 		align = xfs_get_extsz_hint(ap->ip);
 	if (align) {
-		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
-						align, 0, ap->eof, 0, ap->conv,
-						&ap->offset, &ap->length);
-		ASSERT(!error);
+		if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0,
+					ap->eof, 0, ap->conv, &ap->offset,
+					&ap->length))
+			ASSERT(0);
 		ASSERT(ap->length);
 	}
 
+	/* apply extent size hints if obtained earlier */
+	if (align) {
+		args->prod = align;
+		div_u64_rem(ap->offset, args->prod, &args->mod);
+		if (args->mod)
+			args->mod = args->prod - args->mod;
+	} else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) {
+		args->prod = 1;
+		args->mod = 0;
+	} else {
+		args->prod = PAGE_SIZE >> mp->m_sb.sb_blocklog;
+		div_u64_rem(ap->offset, args->prod, &args->mod);
+		if (args->mod)
+			args->mod = args->prod - args->mod;
+	}
+
+	return stripe_align;
+}
+
+static void
+xfs_bmap_process_allocated_extent(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_fileoff_t		orig_offset,
+	xfs_extlen_t		orig_length)
+{
+	int			nullfb;
+
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
+
+	/*
+	 * check the allocation happened at the same or higher AG than
+	 * the first block that was allocated.
+	 */
+	ASSERT(nullfb ||
+		XFS_FSB_TO_AGNO(args->mp, ap->tp->t_firstblock) <=
+		XFS_FSB_TO_AGNO(args->mp, args->fsbno));
+
+	ap->blkno = args->fsbno;
+	if (nullfb)
+		ap->tp->t_firstblock = args->fsbno;
+	ap->length = args->len;
+	/*
+	 * If the extent size hint is active, we tried to round the
+	 * caller's allocation request offset down to extsz and the
+	 * length up to another extsz boundary.  If we found a free
+	 * extent we mapped it in starting at this new offset.  If the
+	 * newly mapped space isn't long enough to cover any of the
+	 * range of offsets that was originally requested, move the
+	 * mapping up so that we can fill as much of the caller's
+	 * original request as possible.  Free space is apparently
+	 * very fragmented so we're unlikely to be able to satisfy the
+	 * hints anyway.
+	 */
+	if (ap->length <= orig_length)
+		ap->offset = orig_offset;
+	else if (ap->offset + ap->length < orig_offset + orig_length)
+		ap->offset = orig_offset + orig_length - ap->length;
+	xfs_bmap_btalloc_accounting(ap, args);
+}
+
+#ifdef DEBUG
+static int
+xfs_bmap_exact_minlen_extent_alloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
+	xfs_fileoff_t		orig_offset;
+	xfs_extlen_t		orig_length;
+	int			error;
+
+	ASSERT(ap->length);
+
+	if (ap->minlen != 1) {
+		ap->blkno = NULLFSBLOCK;
+		ap->length = 0;
+		return 0;
+	}
+
+	orig_offset = ap->offset;
+	orig_length = ap->length;
+
+	args.alloc_minlen_only = 1;
+
+	xfs_bmap_compute_alignments(ap, &args);
+
+	if (ap->tp->t_firstblock == NULLFSBLOCK) {
+		/*
+		 * Unlike the longest extent available in an AG, we don't track
+		 * the length of an AG's shortest extent.
+		 * XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and
+		 * hence we can afford to start traversing from the 0th AG since
+		 * we need not be concerned about a drop in performance in
+		 * "debug only" code paths.
+		 */
+		ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0);
+	} else {
+		ap->blkno = ap->tp->t_firstblock;
+	}
+
+	args.fsbno = ap->blkno;
+	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
+	args.type = XFS_ALLOCTYPE_FIRST_AG;
+	args.total = args.minlen = args.maxlen = ap->minlen;
+
+	args.alignment = 1;
+	args.minalignslop = 0;
+
+	args.minleft = ap->minleft;
+	args.wasdel = ap->wasdel;
+	args.resv = XFS_AG_RESV_NONE;
+	args.datatype = ap->datatype;
+
+	error = xfs_alloc_vextent(&args);
+	if (error)
+		return error;
+
+	if (args.fsbno != NULLFSBLOCK) {
+		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
+			orig_length);
+	} else {
+		ap->blkno = NULLFSBLOCK;
+		ap->length = 0;
+	}
+
+	return 0;
+}
+#else
+
+#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED)
+
+#endif
+
+STATIC int
+xfs_bmap_btalloc(
+	struct xfs_bmalloca	*ap)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
+	xfs_alloctype_t		atype = 0;
+	xfs_agnumber_t		fb_agno;	/* ag number of ap->firstblock */
+	xfs_agnumber_t		ag;
+	xfs_fileoff_t		orig_offset;
+	xfs_extlen_t		orig_length;
+	xfs_extlen_t		blen;
+	xfs_extlen_t		nextminlen = 0;
+	int			nullfb; /* true if ap->firstblock isn't set */
+	int			isaligned;
+	int			tryagain;
+	int			error;
+	int			stripe_align;
+
+	ASSERT(ap->length);
+	orig_offset = ap->offset;
+	orig_length = ap->length;
+
+	stripe_align = xfs_bmap_compute_alignments(ap, &args);
 
 	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
@@ -3538,9 +3670,6 @@ xfs_bmap_btalloc(
 	 * Normal allocation, done through xfs_alloc_vextent.
 	 */
 	tryagain = isaligned = 0;
-	memset(&args, 0, sizeof(args));
-	args.tp = ap->tp;
-	args.mp = mp;
 	args.fsbno = ap->blkno;
 	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
 
@@ -3571,21 +3700,7 @@ xfs_bmap_btalloc(
 		args.total = ap->total;
 		args.minlen = ap->minlen;
 	}
-	/* apply extent size hints if obtained earlier */
-	if (align) {
-		args.prod = align;
-		div_u64_rem(ap->offset, args.prod, &args.mod);
-		if (args.mod)
-			args.mod = args.prod - args.mod;
-	} else if (mp->m_sb.sb_blocksize >= PAGE_SIZE) {
-		args.prod = 1;
-		args.mod = 0;
-	} else {
-		args.prod = PAGE_SIZE >> mp->m_sb.sb_blocklog;
-		div_u64_rem(ap->offset, args.prod, &args.mod);
-		if (args.mod)
-			args.mod = args.prod - args.mod;
-	}
+
 	/*
 	 * If we are not low on available data blocks, and the underlying
 	 * logical volume manager is a stripe, and the file offset is zero then
@@ -3687,37 +3802,10 @@ xfs_bmap_btalloc(
 			return error;
 		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
+
 	if (args.fsbno != NULLFSBLOCK) {
-		/*
-		 * check the allocation happened at the same or higher AG than
-		 * the first block that was allocated.
-		 */
-		ASSERT(ap->tp->t_firstblock == NULLFSBLOCK ||
-		       XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <=
-		       XFS_FSB_TO_AGNO(mp, args.fsbno));
-
-		ap->blkno = args.fsbno;
-		if (ap->tp->t_firstblock == NULLFSBLOCK)
-			ap->tp->t_firstblock = args.fsbno;
-		ASSERT(nullfb || fb_agno <= args.agno);
-		ap->length = args.len;
-		/*
-		 * If the extent size hint is active, we tried to round the
-		 * caller's allocation request offset down to extsz and the
-		 * length up to another extsz boundary.  If we found a free
-		 * extent we mapped it in starting at this new offset.  If the
-		 * newly mapped space isn't long enough to cover any of the
-		 * range of offsets that was originally requested, move the
-		 * mapping up so that we can fill as much of the caller's
-		 * original request as possible.  Free space is apparently
-		 * very fragmented so we're unlikely to be able to satisfy the
-		 * hints anyway.
-		 */
-		if (ap->length <= orig_length)
-			ap->offset = orig_offset;
-		else if (ap->offset + ap->length < orig_offset + orig_length)
-			ap->offset = orig_offset + orig_length - ap->length;
-		xfs_bmap_btalloc_accounting(ap, &args);
+		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
+			orig_length);
 	} else {
 		ap->blkno = NULLFSBLOCK;
 		ap->length = 0;
@@ -4001,8 +4089,7 @@ xfs_bmapi_reserve_delalloc(
 	 * blocks.  This number gets adjusted later.  We return if we haven't
 	 * allocated blocks already inside this loop.
 	 */
-	error = xfs_trans_reserve_quota_nblks(NULL, ip, (long)alen, 0,
-						XFS_QMOPT_RES_REGBLKS);
+	error = xfs_quota_reserve_blkres(ip, alen);
 	if (error)
 		return error;
 
@@ -4048,8 +4135,7 @@ out_unreserve_blocks:
 	xfs_mod_fdblocks(mp, alen, false);
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
-		xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0,
-						XFS_QMOPT_RES_REGBLKS);
+		xfs_quota_unreserve_blkres(ip, alen);
 	return error;
 }
 
@@ -4083,6 +4169,10 @@ xfs_bmap_alloc_userdata(
 			return xfs_bmap_rtalloc(bma);
 	}
 
+	if (unlikely(XFS_TEST_ERROR(false, mp,
+			XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
+		return xfs_bmap_exact_minlen_extent_alloc(bma);
+
 	return xfs_bmap_btalloc(bma);
 }
 
@@ -4119,10 +4209,15 @@ xfs_bmapi_allocate(
 	else
 		bma->minlen = 1;
 
-	if (bma->flags & XFS_BMAPI_METADATA)
-		error = xfs_bmap_btalloc(bma);
-	else
+	if (bma->flags & XFS_BMAPI_METADATA) {
+		if (unlikely(XFS_TEST_ERROR(false, mp,
+				XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
+			error = xfs_bmap_exact_minlen_extent_alloc(bma);
+		else
+			error = xfs_bmap_btalloc(bma);
+	} else {
 		error = xfs_bmap_alloc_userdata(bma);
+	}
 	if (error || bma->blkno == NULLFSBLOCK)
 		return error;
 
@@ -4527,6 +4622,12 @@ xfs_bmapi_convert_delalloc(
 		return error;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	error = xfs_iext_count_may_overflow(ip, whichfork,
+			XFS_IEXT_ADD_NOSPLIT_CNT);
+	if (error)
+		goto out_trans_cancel;
+
 	xfs_trans_ijoin(tp, ip, 0);
 
 	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) ||
@@ -4826,9 +4927,8 @@ xfs_bmap_del_extent_delay(
 	 * sb counters as we might have to borrow some blocks for the
 	 * indirect block accounting.
 	 */
-	error = xfs_trans_reserve_quota_nblks(NULL, ip,
-			-((long)del->br_blockcount), 0,
-			isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
+	ASSERT(!isrt);
+	error = xfs_quota_unreserve_blkres(ip, del->br_blockcount);
 	if (error)
 		return error;
 	ip->i_delayed_blks -= del->br_blockcount;
@@ -5145,6 +5245,27 @@ xfs_bmap_del_extent_real(
 		/*
 		 * Deleting the middle of the extent.
 		 */
+
+		/*
+		 * For directories, -ENOSPC is returned since a directory entry
+		 * remove operation must not fail due to low extent count
+		 * availability. -ENOSPC will be handled by higher layers of XFS
+		 * by letting the corresponding empty Data/Free blocks to linger
+		 * until a future remove operation. Dabtree blocks would be
+		 * swapped with the last block in the leaf space and then the
+		 * new last block will be unmapped.
+		 *
+		 * The above logic also applies to the source directory entry of
+		 * a rename operation.
+		 */
+		error = xfs_iext_count_may_overflow(ip, whichfork, 1);
+		if (error) {
+			ASSERT(S_ISDIR(VFS_I(ip)->i_mode) &&
+				whichfork == XFS_DATA_FORK);
+			error = -ENOSPC;
+			goto done;
+		}
+
 		old = got;
 
 		got.br_blockcount = del->br_startoff - got.br_startoff;