4 files changed, 105 insertions, 13 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 224963b1efc0..de2d26d32844 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4294,8 +4294,8 @@ xfs_bmapi_delay(
 }
 
 
-int
-__xfs_bmapi_allocate(
+static int
+xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
 {
 	struct xfs_mount	*mp = bma->ip->i_mount;
@@ -4574,9 +4574,6 @@ xfs_bmapi_write(
 	bma.flist = flist;
 	bma.firstblock = firstblock;
 
-	if (flags & XFS_BMAPI_STACK_SWITCH)
-		bma.stack_switch = 1;
-
 	while (bno < end && n < *nmap) {
 		inhole = eof || bma.got.br_startoff > bno;
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 38ba36e9b2f0..b879ca56a64c 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -77,7 +77,6 @@ typedef	struct xfs_bmap_free
  * from written to unwritten, otherwise convert from unwritten to written.
  */
 #define XFS_BMAPI_CONVERT	0x040
-#define XFS_BMAPI_STACK_SWITCH	0x080
 
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
@@ -86,8 +85,7 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
-	{ XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }
 
 
 static inline int xfs_bmapi_aflag(int w)
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2435928b0765..8fe6a93ff473 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/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.
@@ -2323,7 +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,
@@ -2503,6 +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.
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index f5ca0286a0af..6e93b5ef0a6b 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -483,10 +483,16 @@ xfs_sb_quota_to_disk(
 	}
 
 	/*
-	 * GQUOTINO and PQUOTINO cannot be used together in versions
-	 * of superblock that do not have pquotino. from->sb_flags
-	 * tells us which quota is active and should be copied to
-	 * disk.
+	 * GQUOTINO and PQUOTINO cannot be used together in versions of
+	 * superblock that do not have pquotino. from->sb_flags tells us which
+	 * quota is active and should be copied to disk. If neither are active,
+	 * make sure we write NULLFSINO to the sb_gquotino field as a quota
+	 * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature
+	 * bit is set.
+	 *
+	 * Note that we don't need to handle the sb_uquotino or sb_pquotino here
+	 * as they do not require any translation. Hence the main sb field loop
+	 * will write them appropriately from the in-core superblock.
 	 */
 	if ((*fields & XFS_SB_GQUOTINO) &&
 				(from->sb_qflags & XFS_GQUOTA_ACCT))
@@ -494,6 +500,17 @@ xfs_sb_quota_to_disk(
 	else if ((*fields & XFS_SB_PQUOTINO) &&
 				(from->sb_qflags & XFS_PQUOTA_ACCT))
 		to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
+	else {
+		/*
+		 * We can't rely on just the fields being logged to tell us
+		 * that it is safe to write NULLFSINO - we should only do that
+		 * if quotas are not actually enabled. Hence only write
+		 * NULLFSINO if both in-core quota inodes are NULL.
+		 */
+		if (from->sb_gquotino == NULLFSINO &&
+		    from->sb_pquotino == NULLFSINO)
+			to->sb_gquotino = cpu_to_be64(NULLFSINO);
+	}
 
 	*fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO);
 }