1 files changed, 103 insertions, 35 deletions

diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e80d59fdf89..cf893bc1e37 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -33,6 +33,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_alloc.h"
 
 /*
  * Cursor allocation zone.
@@ -43,9 +44,10 @@ kmem_zone_t	*xfs_btree_cur_zone;
  * Btree magic numbers.
  */
 static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
-	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC },
+	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+	  XFS_FIBT_MAGIC },
 	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
-	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC }
+	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
 };
 #define xfs_btree_magic(cur) \
 	xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
@@ -552,14 +554,11 @@ xfs_btree_get_bufl(
 	xfs_fsblock_t	fsbno,		/* file system block number */
 	uint		lock)		/* lock flags for get_buf */
 {
-	xfs_buf_t	*bp;		/* buffer pointer (return value) */
 	xfs_daddr_t		d;		/* real disk block address */
 
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
-	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(!xfs_buf_geterror(bp));
-	return bp;
+	return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
 }
 
 /*
@@ -574,15 +573,12 @@ xfs_btree_get_bufs(
 	xfs_agblock_t	agbno,		/* allocation group block number */
 	uint		lock)		/* lock flags for get_buf */
 {
-	xfs_buf_t	*bp;		/* buffer pointer (return value) */
 	xfs_daddr_t		d;		/* real disk block address */
 
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agbno != NULLAGBLOCK);
 	d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(!xfs_buf_geterror(bp));
-	return bp;
+	return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
 }
 
 /*
@@ -722,7 +718,6 @@ xfs_btree_read_bufl(
 				   mp->m_bsize, lock, &bp, ops);
 	if (error)
 		return error;
-	ASSERT(!xfs_buf_geterror(bp));
 	if (bp)
 		xfs_buf_set_ref(bp, refval);
 	*bpp = bp;
@@ -1115,6 +1110,7 @@ xfs_btree_set_refs(
 		xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
 		break;
 	case XFS_BTNUM_INO:
+	case XFS_BTNUM_FINO:
 		xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
 		break;
 	case XFS_BTNUM_BMAP:
@@ -1159,7 +1155,6 @@ STATIC int
 xfs_btree_read_buf_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*ptr,
-	int			level,
 	int			flags,
 	struct xfs_btree_block	**block,
 	struct xfs_buf		**bpp)
@@ -1178,7 +1173,6 @@ xfs_btree_read_buf_block(
 	if (error)
 		return error;
 
-	ASSERT(!xfs_buf_geterror(*bpp));
 	xfs_btree_set_refs(cur, *bpp);
 	*block = XFS_BUF_TO_BLOCK(*bpp);
 	return 0;
@@ -1517,8 +1511,8 @@ xfs_btree_increment(
 		union xfs_btree_ptr	*ptrp;
 
 		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
-		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
-							0, &block, &bp);
+		--lev;
+		error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
 		if (error)
 			goto error0;
 
@@ -1616,8 +1610,8 @@ xfs_btree_decrement(
 		union xfs_btree_ptr	*ptrp;
 
 		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
-		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
-							0, &block, &bp);
+		--lev;
+		error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
 		if (error)
 			goto error0;
 		xfs_btree_setbuf(cur, lev, bp);
@@ -1667,7 +1661,7 @@ xfs_btree_lookup_get_block(
 		return 0;
 	}
 
-	error = xfs_btree_read_buf_block(cur, pp, level, 0, blkp, &bp);
+	error = xfs_btree_read_buf_block(cur, pp, 0, blkp, &bp);
 	if (error)
 		return error;
 
@@ -2018,7 +2012,7 @@ xfs_btree_lshift(
 		goto out0;
 
 	/* Set up the left neighbor as "left". */
-	error = xfs_btree_read_buf_block(cur, &lptr, level, 0, &left, &lbp);
+	error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 	if (error)
 		goto error0;
 
@@ -2202,7 +2196,7 @@ xfs_btree_rshift(
 		goto out0;
 
 	/* Set up the right neighbor as "right". */
-	error = xfs_btree_read_buf_block(cur, &rptr, level, 0, &right, &rbp);
+	error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 	if (error)
 		goto error0;
 
@@ -2330,7 +2324,7 @@ error1:
  * record (to be inserted into parent).
  */
 STATIC int					/* error */
-xfs_btree_split(
+__xfs_btree_split(
 	struct xfs_btree_cur	*cur,
 	int			level,
 	union xfs_btree_ptr	*ptrp,
@@ -2372,7 +2366,7 @@ xfs_btree_split(
 	xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -2470,7 +2464,7 @@ xfs_btree_split(
 	 * point back to right instead of to left.
 	 */
 	if (!xfs_btree_ptr_is_null(cur, &rrptr)) {
-		error = xfs_btree_read_buf_block(cur, &rrptr, level,
+		error = xfs_btree_read_buf_block(cur, &rrptr,
 							0, &rrblock, &rrbp);
 		if (error)
 			goto error0;
@@ -2510,6 +2504,85 @@ error0:
 	return error;
 }
 
+struct xfs_btree_split_args {
+	struct xfs_btree_cur	*cur;
+	int			level;
+	union xfs_btree_ptr	*ptrp;
+	union xfs_btree_key	*key;
+	struct xfs_btree_cur	**curp;
+	int			*stat;		/* success/failure */
+	int			result;
+	bool			kswapd;	/* allocation in kswapd context */
+	struct completion	*done;
+	struct work_struct	work;
+};
+
+/*
+ * Stack switching interfaces for allocation
+ */
+static void
+xfs_btree_split_worker(
+	struct work_struct	*work)
+{
+	struct xfs_btree_split_args	*args = container_of(work,
+						struct xfs_btree_split_args, work);
+	unsigned long		pflags;
+	unsigned long		new_pflags = PF_FSTRANS;
+
+	/*
+	 * we are in a transaction context here, but may also be doing work
+	 * in kswapd context, and hence we may need to inherit that state
+	 * temporarily to ensure that we don't block waiting for memory reclaim
+	 * in any way.
+	 */
+	if (args->kswapd)
+		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+	current_set_flags_nested(&pflags, new_pflags);
+
+	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
+					 args->key, args->curp, args->stat);
+	complete(args->done);
+
+	current_restore_flags_nested(&pflags, new_pflags);
+}
+
+/*
+ * BMBT split requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. For the other
+ * btree types, just call directly to avoid the context switch overhead here.
+ */
+STATIC int					/* error */
+xfs_btree_split(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	union xfs_btree_ptr	*ptrp,
+	union xfs_btree_key	*key,
+	struct xfs_btree_cur	**curp,
+	int			*stat)		/* success/failure */
+{
+	struct xfs_btree_split_args	args;
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	if (cur->bc_btnum != XFS_BTNUM_BMAP)
+		return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
+
+	args.cur = cur;
+	args.level = level;
+	args.ptrp = ptrp;
+	args.key = key;
+	args.curp = curp;
+	args.stat = stat;
+	args.done = &done;
+	args.kswapd = current_is_kswapd();
+	INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
+	queue_work(xfs_alloc_wq, &args.work);
+	wait_for_completion(&done);
+	destroy_work_on_stack(&args.work);
+	return args.result;
+}
+
+
 /*
  * Copy the old inode root contents into a real block and make the
  * broot point to it.
@@ -2545,7 +2618,7 @@ xfs_btree_new_iroot(
 	pp = xfs_btree_ptr_addr(cur, 1, block);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, pp, &nptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0) {
@@ -2649,7 +2722,7 @@ xfs_btree_new_root(
 	cur->bc_ops->init_ptr_from_cur(cur, &rptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -2684,8 +2757,7 @@ xfs_btree_new_root(
 		lbp = bp;
 		xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 		left = block;
-		error = xfs_btree_read_buf_block(cur, &rptr,
-					cur->bc_nlevels - 1, 0, &right, &rbp);
+		error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 		if (error)
 			goto error0;
 		bp = rbp;
@@ -2696,8 +2768,7 @@ xfs_btree_new_root(
 		xfs_btree_buf_to_ptr(cur, rbp, &rptr);
 		right = block;
 		xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
-		error = xfs_btree_read_buf_block(cur, &lptr,
-					cur->bc_nlevels - 1, 0, &left, &lbp);
+		error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 		if (error)
 			goto error0;
 		bp = lbp;
@@ -3649,8 +3720,7 @@ xfs_btree_delrec(
 		rptr = cptr;
 		right = block;
 		rbp = bp;
-		error = xfs_btree_read_buf_block(cur, &lptr, level,
-							0, &left, &lbp);
+		error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 		if (error)
 			goto error0;
 
@@ -3667,8 +3737,7 @@ xfs_btree_delrec(
 		lptr = cptr;
 		left = block;
 		lbp = bp;
-		error = xfs_btree_read_buf_block(cur, &rptr, level,
-							0, &right, &rbp);
+		error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 		if (error)
 			goto error0;
 
@@ -3740,8 +3809,7 @@ xfs_btree_delrec(
 	/* If there is a right sibling, point it to the remaining block. */
 	xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
 	if (!xfs_btree_ptr_is_null(cur, &cptr)) {
-		error = xfs_btree_read_buf_block(cur, &cptr, level,
-							0, &rrblock, &rrbp);
+		error = xfs_btree_read_buf_block(cur, &cptr, 0, &rrblock, &rrbp);
 		if (error)
 			goto error0;
 		xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB);