6 files changed, 90 insertions, 62 deletions

diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 96175df211b1..75c3fe5f3d9d 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4298,8 +4298,8 @@ xfs_bmapi_delay(
 }
 
 
-int
-__xfs_bmapi_allocate(
+static int
+xfs_bmapi_allocate(
         struct xfs_bmalloca     *bma)
 {
         struct xfs_mount        *mp = bma->ip->i_mount;
@@ -4578,9 +4578,6 @@ 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/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 38ba36e9b2f0..b879ca56a64c 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/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/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 057f671811d6..64731ef3324d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -249,49 +249,6 @@ xfs_bmap_rtalloc(
 }
 
 /*
- * Stack switching interfaces for allocation
- */
-static void
-xfs_bmapi_allocate_worker(
-        struct work_struct      *work)
-{
-        struct xfs_bmalloca     *args = container_of(work,
-                                                struct xfs_bmalloca, work);
-        unsigned long           pflags;
-
-        /* we are in a transaction context here */
-        current_set_flags_nested(&pflags, PF_FSTRANS);
-
-        args->result = __xfs_bmapi_allocate(args);
-        complete(args->done);
-
-        current_restore_flags_nested(&pflags, PF_FSTRANS);
-}
-
-/*
- * Some allocation 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. Otherwise just
- * call directly to avoid the context switch overhead here.
- */
-int
-xfs_bmapi_allocate(
-        struct xfs_bmalloca     *args)
-{
-        DECLARE_COMPLETION_ONSTACK(done);
-
-        if (!args->stack_switch)
-                return __xfs_bmapi_allocate(args);
-
-
-        args->done = &done;
-        INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
-        queue_work(xfs_alloc_wq, &args->work);
-        wait_for_completion(&done);
-        destroy_work_on_stack(&args->work);
-        return args->result;
-}
-
-/*
  * Check if the endoff is outside the last extent. If so the caller will grow
  * the allocation to a stripe unit boundary.  All offsets are considered outside
  * the end of file for an empty fork, so 1 is returned in *eof in that case.
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 935ed2b24edf..2fdb72d2c908 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -50,12 +50,11 @@ struct xfs_bmalloca {
         xfs_extlen_t            total;  /* total blocks needed for xaction */
         xfs_extlen_t            minlen; /* minimum allocation size (blocks) */
         xfs_extlen_t            minleft; /* amount must be left after alloc */
-        char                    eof;    /* set if allocating past last extent */
-        char                    wasdel; /* replacing a delayed allocation */
-        char                    userdata;/* set if is user data */
-        char                    aeof;   /* allocated space at eof */
-        char                    conv;   /* overwriting unwritten extents */
-        char                    stack_switch;
+        bool                    eof;    /* set if allocating past last extent */
+        bool                    wasdel; /* replacing a delayed allocation */
+        bool                    userdata;/* set if is user data */
+        bool                    aeof;   /* allocated space at eof */
+        bool                    conv;   /* overwriting unwritten extents */
         int                     flags;
         struct completion       *done;
         struct work_struct      work;
@@ -65,8 +64,6 @@ struct xfs_bmalloca {
 int     xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
                         int *committed);
 int     xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
-int     xfs_bmapi_allocate(struct xfs_bmalloca *args);
-int     __xfs_bmapi_allocate(struct xfs_bmalloca *args);
 int     xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
                      int whichfork, int *eof);
 int     xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index bf810c6baf2b..cf893bc1e373 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.
@@ -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/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 6c5eb4c551e3..6d3ec2b6ee29 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -749,8 +749,7 @@ xfs_iomap_write_allocate(
                          * pointer that the caller gave to us.
                          */
                         error = xfs_bmapi_write(tp, ip, map_start_fsb,
-                                                count_fsb,
-                                                XFS_BMAPI_STACK_SWITCH,
+                                                count_fsb, 0,
                                                 &first_block, 1,
                                                 imap, &nimaps, &free_list);
                         if (error)