1 files changed, 54 insertions, 9 deletions

diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 848ffa77707b..83d0cf3df930 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2437,6 +2437,7 @@ 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;
@@ -3082,6 +3083,7 @@ xfs_bmap_extents_to_btree(
          * Convert to a btree with two levels, one record in root.
          */
         XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);
+        memset(&args, 0, sizeof(args));
         args.tp = tp;
         args.mp = mp;
         args.firstblock = *firstblock;
@@ -3237,6 +3239,7 @@ xfs_bmap_local_to_extents(
                 xfs_buf_t       *bp;    /* buffer for extent block */
                 xfs_bmbt_rec_host_t *ep;/* extent record pointer */
 
+                memset(&args, 0, sizeof(args));
                 args.tp = tp;
                 args.mp = ip->i_mount;
                 args.firstblock = *firstblock;
@@ -4616,12 +4619,11 @@ xfs_bmapi_delay(
 
 
 STATIC int
-xfs_bmapi_allocate(
-        struct xfs_bmalloca     *bma,
-        int                     flags)
+__xfs_bmapi_allocate(
+        struct xfs_bmalloca     *bma)
 {
         struct xfs_mount        *mp = bma->ip->i_mount;
-        int                     whichfork = (flags & XFS_BMAPI_ATTRFORK) ?
+        int                     whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ?
                                                 XFS_ATTR_FORK : XFS_DATA_FORK;
         struct xfs_ifork        *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
         int                     tmp_logflags = 0;
@@ -4654,24 +4656,27 @@ xfs_bmapi_allocate(
          * Indicate if this is the first user data in the file, or just any
          * user data.
          */
-        if (!(flags & XFS_BMAPI_METADATA)) {
+        if (!(bma->flags & XFS_BMAPI_METADATA)) {
                 bma->userdata = (bma->offset == 0) ?
                         XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
         }
 
-        bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
+        bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
 
         /*
          * Only want to do the alignment at the eof if it is userdata and
          * allocation length is larger than a stripe unit.
          */
         if (mp->m_dalign && bma->length >= mp->m_dalign &&
-            !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
+            !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {
                 error = xfs_bmap_isaeof(bma, whichfork);
                 if (error)
                         return error;
         }
 
+        if (bma->flags & XFS_BMAPI_STACK_SWITCH)
+                bma->stack_switch = 1;
+
         error = xfs_bmap_alloc(bma);
         if (error)
                 return error;
@@ -4706,7 +4711,7 @@ xfs_bmapi_allocate(
          * A wasdelay extent has been initialized, so shouldn't be flagged
          * as unwritten.
          */
-        if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) &&
+        if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) &&
             xfs_sb_version_hasextflgbit(&mp->m_sb))
                 bma->got.br_state = XFS_EXT_UNWRITTEN;
 
@@ -4734,6 +4739,45 @@ xfs_bmapi_allocate(
         return 0;
 }
 
+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);
+        return args->result;
+}
+
 STATIC int
 xfs_bmapi_convert_unwritten(
         struct xfs_bmalloca     *bma,
@@ -4919,6 +4963,7 @@ xfs_bmapi_write(
                         bma.conv = !!(flags & XFS_BMAPI_CONVERT);
                         bma.wasdel = wasdelay;
                         bma.offset = bno;
+                        bma.flags = flags;
 
                         /*
                          * There's a 32/64 bit type mismatch between the
@@ -4934,7 +4979,7 @@ xfs_bmapi_write(
 
                         ASSERT(len > 0);
                         ASSERT(bma.length > 0);
-                        error = xfs_bmapi_allocate(&bma, flags);
+                        error = xfs_bmapi_allocate(&bma);
                         if (error)
                                 goto error0;
                         if (bma.blkno == NULLFSBLOCK)