13 files changed, 93 insertions, 93 deletions

diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 2dfdc62f795e..70a5b55e0870 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -25,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-        void            *ptr;
-        size_t          kmsize = maxsize;
-
-        while (!(ptr = vzalloc(kmsize))) {
-                if ((kmsize >>= 1) <= minsize)
-                        kmsize = minsize;
-        }
-        if (ptr)
-                *size = kmsize;
-        return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746224e7..f0fc84fcaac2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -69,8 +69,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a9c66d47757a..9bd104f32908 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
                 args.type = XFS_ALLOCTYPE_START_BNO;
                 args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
         } else if (dfops->dop_low) {
-try_another_ag:
                 args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
                 args.fsbno = *firstblock;
         } else {
                 args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ try_another_ag:
         if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
             args.fsbno == NULLFSBLOCK &&
             args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-                dfops->dop_low = true;
+                args.type = XFS_ALLOCTYPE_FIRST_AG;
                 goto try_another_ag;
         }
+        if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+                xfs_iroot_realloc(ip, -1, whichfork);
+                xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+                return -ENOSPC;
+        }
         /*
          * Allocation can't fail, the space was reserved.
          */
-        ASSERT(args.fsbno != NULLFSBLOCK);
         ASSERT(*firstblock == NULLFSBLOCK ||
                args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
         *firstblock = cur->bc_private.b.firstblock = args.fsbno;
@@ -4150,6 +4154,19 @@ xfs_bmapi_read(
         return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
         struct xfs_inode        *ip,
@@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc(
         got->br_startblock = nullstartblock(indlen);
         got->br_blockcount = alen;
         got->br_state = XFS_EXT_NORM;
-        xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-        /*
-         * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-         * might have merged it into one of the neighbouring ones.
-         */
-        xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+        xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
         /*
          * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc(
         if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
                 xfs_inode_set_cowblocks_tag(ip);
 
-        ASSERT(got->br_startoff <= aoff);
-        ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
-        ASSERT(isnullstartblock(got->br_startblock));
-        ASSERT(got->br_state == XFS_EXT_NORM);
         return 0;
 
 out_unreserve_blocks:
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index f93072b58a58..fd55db479385 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -447,8 +447,8 @@ xfs_bmbt_alloc_block(
 
         if (args.fsbno == NULLFSBLOCK) {
                 args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
                 args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
                 /*
                  * Make sure there is sufficient room left in the AG to
                  * complete a full tree split for an extent insert.  If
@@ -488,8 +488,8 @@ try_another_ag:
         if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
             args.fsbno == NULLFSBLOCK &&
             args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-                cur->bc_private.b.dfops->dop_low = true;
                 args.fsbno = cur->bc_private.b.firstblock;
+                args.type = XFS_ALLOCTYPE_FIRST_AG;
                 goto try_another_ag;
         }
 
@@ -506,7 +506,7 @@ try_another_ag:
                         goto error0;
                 cur->bc_private.b.dfops->dop_low = true;
         }
-        if (args.fsbno == NULLFSBLOCK) {
+        if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
                 XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
                 *stat = 0;
                 return 0;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index bf65a9ea8642..61494295d92f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -274,54 +274,49 @@ xfs_end_io(
         struct xfs_ioend        *ioend =
                 container_of(work, struct xfs_ioend, io_work);
         struct xfs_inode        *ip = XFS_I(ioend->io_inode);
+        xfs_off_t               offset = ioend->io_offset;
+        size_t                  size = ioend->io_size;
         int                     error = ioend->io_bio->bi_error;
 
         /*
-         * Set an error if the mount has shut down and proceed with end I/O
-         * processing so it can perform whatever cleanups are necessary.
+         * Just clean up the in-memory strutures if the fs has been shut down.
          */
-        if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+        if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
                 error = -EIO;
+                goto done;
+        }
 
         /*
-         * For a CoW extent, we need to move the mapping from the CoW fork
-         * to the data fork.  If instead an error happened, just dump the
-         * new blocks.
+         * Clean up any COW blocks on an I/O error.
          */
-        if (ioend->io_type == XFS_IO_COW) {
-                if (error)
-                        goto done;
-                if (ioend->io_bio->bi_error) {
-                        error = xfs_reflink_cancel_cow_range(ip,
-                                        ioend->io_offset, ioend->io_size);
-                        goto done;
+        if (unlikely(error)) {
+                switch (ioend->io_type) {
+                case XFS_IO_COW:
+                        xfs_reflink_cancel_cow_range(ip, offset, size, true);
+                        break;
                 }
-                error = xfs_reflink_end_cow(ip, ioend->io_offset,
-                                ioend->io_size);
-                if (error)
-                        goto done;
+
+                goto done;
         }
 
         /*
-         * For unwritten extents we need to issue transactions to convert a
-         * range to normal written extens after the data I/O has finished.
-         * Detecting and handling completion IO errors is done individually
-         * for each case as different cleanup operations need to be performed
-         * on error.
+         * Success:  commit the COW or unwritten blocks if needed.
          */
-        if (ioend->io_type == XFS_IO_UNWRITTEN) {
-                if (error)
-                        goto done;
-                error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
-                                                  ioend->io_size);
-        } else if (ioend->io_append_trans) {
-                error = xfs_setfilesize_ioend(ioend, error);
-        } else {
-                ASSERT(!xfs_ioend_is_append(ioend) ||
-                       ioend->io_type == XFS_IO_COW);
+        switch (ioend->io_type) {
+        case XFS_IO_COW:
+                error = xfs_reflink_end_cow(ip, offset, size);
+                break;
+        case XFS_IO_UNWRITTEN:
+                error = xfs_iomap_write_unwritten(ip, offset, size);
+                break;
+        default:
+                ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+                break;
         }
 
 done:
+        if (ioend->io_append_trans)
+                error = xfs_setfilesize_ioend(ioend, error);
         xfs_destroy_ioend(ioend, error);
 }
 
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7234b9748c36..3531f8f72fa5 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks(
         xfs_ilock(ip, XFS_IOLOCK_EXCL);
         xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 
-        ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+        ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
         xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
         xfs_iunlock(ip, XFS_IOLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index edfa6a55b064..7eaf1ef74e3c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1615,7 +1615,7 @@ xfs_itruncate_extents(
 
         /* Remove all pending CoW reservations. */
         error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
-                        last_block);
+                        last_block, true);
         if (error)
                 goto out;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 41662fb14e87..288ee5b840d7 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -630,6 +630,11 @@ retry:
                 goto out_unlock;
         }
 
+        /*
+         * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+         * them out if the write happens to fail.
+         */
+        iomap->flags = IOMAP_F_NEW;
         trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
         if (isnullstartblock(got.br_startblock))
@@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc(
         struct xfs_inode        *ip,
         loff_t                  offset,
         loff_t                  length,
-        ssize_t                 written)
+        ssize_t                 written,
+        struct iomap            *iomap)
 {
         struct xfs_mount        *mp = ip->i_mount;
         xfs_fileoff_t           start_fsb;
         xfs_fileoff_t           end_fsb;
         int                     error = 0;
 
-        /* behave as if the write failed if drop writes is enabled */
-        if (xfs_mp_drop_writes(mp))
+        /*
+         * Behave as if the write failed if drop writes is enabled. Set the NEW
+         * flag to force delalloc cleanup.
+         */
+        if (xfs_mp_drop_writes(mp)) {
+                iomap->flags |= IOMAP_F_NEW;
                 written = 0;
+        }
 
         /*
          * start_fsb refers to the first unused block after a short write. If
@@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc(
         end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
         /*
-         * Trim back delalloc blocks if we didn't manage to write the whole
-         * range reserved.
+         * Trim delalloc blocks if they were allocated by this write and we
+         * didn't manage to write the whole range.
          *
          * We don't need to care about racing delalloc as we hold i_mutex
          * across the reserve/allocate/unreserve calls. If there are delalloc
          * blocks in the range, they are ours.
          */
-        if (start_fsb < end_fsb) {
+        if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
                 truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
                                          XFS_FSB_TO_B(mp, end_fsb) - 1);
 
@@ -1131,7 +1142,7 @@ xfs_file_iomap_end(
 {
         if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
                 return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-                                length, written);
+                                length, written, iomap);
         return 0;
 }
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 66e881790c17..2a6d9b1558e0 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -361,7 +361,6 @@ xfs_bulkstat(
         xfs_agino_t             agino;  /* inode # in allocation group */
         xfs_agnumber_t          agno;   /* allocation group number */
         xfs_btree_cur_t         *cur;   /* btree cursor for ialloc btree */
-        size_t                  irbsize; /* size of irec buffer in bytes */
         xfs_inobt_rec_incore_t  *irbuf; /* start of irec buffer */
         int                     nirbuf; /* size of irbuf */
         int                     ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
         *ubcountp = 0;
         *done = 0;
 
-        irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+        irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
         if (!irbuf)
                 return -ENOMEM;
-
-        nirbuf = irbsize / sizeof(*irbuf);
+        nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
 
         /*
          * Loop over the allocation groups, starting from the last
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 450bde68bb75..688ebff1f663 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -513,8 +513,7 @@ STATIC void
 xfs_set_inoalignment(xfs_mount_t *mp)
 {
         if (xfs_sb_version_hasalign(&mp->m_sb) &&
-            mp->m_sb.sb_inoalignmt >=
-            XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+                mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
                 mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
         else
                 mp->m_inoalign_mask = 0;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index da6d08fb359c..4a84c5ea266d 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow(
 }
 
 /*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_blocks(
         struct xfs_inode                *ip,
         struct xfs_trans                **tpp,
         xfs_fileoff_t                   offset_fsb,
-        xfs_fileoff_t                   end_fsb)
+        xfs_fileoff_t                   end_fsb,
+        bool                            cancel_real)
 {
         struct xfs_ifork                *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
         struct xfs_bmbt_irec            got, del;
@@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks(
                                         &idx, &got, &del);
                         if (error)
                                 break;
-                } else {
+                } else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
                         xfs_trans_ijoin(*tpp, ip, 0);
                         xfs_defer_init(&dfops, &firstfsb);
 
@@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks(
 }
 
 /*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_range(
         struct xfs_inode        *ip,
         xfs_off_t               offset,
-        xfs_off_t               count)
+        xfs_off_t               count,
+        bool                    cancel_real)
 {
         struct xfs_trans        *tp;
         xfs_fileoff_t           offset_fsb;
@@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range(
         xfs_trans_ijoin(tp, ip, 0);
 
         /* Scrape out the old CoW reservations */
-        error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+        error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+                        cancel_real);
         if (error)
                 goto out_cancel;
 
@@ -1450,7 +1459,7 @@ next:
          * We didn't find any shared blocks so turn off the reflink flag.
          * First, get rid of any leftover CoW mappings.
          */
-        error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+        error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
         if (error)
                 return error;
 
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 33ac9b8db683..d29a7967f029 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
                 struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
-                xfs_fileoff_t end_fsb);
+                xfs_fileoff_t end_fsb, bool cancel_real);
 extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
-                xfs_off_t count);
+                xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
                 xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 890862f2447c..685c042a120f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -953,7 +953,7 @@ xfs_fs_destroy_inode(
         XFS_STATS_INC(ip->i_mount, vn_remove);
 
         if (xfs_is_reflink_inode(ip)) {
-                error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+                error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
                 if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
                         xfs_warn(ip->i_mount,
 "Error %d while evicting CoW blocks for inode %llu.",