Merge branch 'iomap-fixes-4.8-rc3' into for-next

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 776ae2f..3dd8f1d 100644 (file)
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1582,6 +1582,7 @@ xfs_alloc_ag_vextent_small(
        xfs_extlen_t    *flenp, /* result length */
        int             *stat)  /* status: 0-freelist, 1-normal/none */
 {
+       struct xfs_owner_info   oinfo;
        int             error;
        xfs_agblock_t   fbno;
        xfs_extlen_t    flen;
@@ -1624,6 +1625,18 @@ xfs_alloc_ag_vextent_small(
                                error0);
                        args->wasfromfl = 1;
                        trace_xfs_alloc_small_freelist(args);
+
+                       /*
+                        * If we're feeding an AGFL block to something that
+                        * doesn't live in the free space, we need to clear
+                        * out the OWN_AG rmap.
+                        */
+                       xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+                       error = xfs_rmap_free(args->tp, args->agbp, args->agno,
+                                       fbno, 1, &oinfo);
+                       if (error)
+                               goto error0;
+
                        *stat = 0;
                        return 0;
                }
@@ -2264,6 +2277,7 @@ xfs_alloc_log_agf(
                offsetof(xfs_agf_t, agf_longest),
                offsetof(xfs_agf_t, agf_btreeblks),
                offsetof(xfs_agf_t, agf_uuid),
+               offsetof(xfs_agf_t, agf_rmap_blocks),
                sizeof(xfs_agf_t)
        };
 

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index f814d42..e6a8bea 100644 (file)
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -640,12 +640,15 @@ typedef struct xfs_agf {
        __be32          agf_btreeblks;  /* # of blocks held in AGF btrees */
        uuid_t          agf_uuid;       /* uuid of filesystem */
 
+       __be32          agf_rmap_blocks;        /* rmapbt blocks used */
+       __be32          agf_padding;            /* padding */
+
        /*
         * reserve some contiguous space for future logged fields before we add
         * the unlogged fields. This makes the range logging via flags and
         * structure offsets much simpler.
         */
-       __be64          agf_spare64[16];
+       __be64          agf_spare64[15];
 
        /* unlogged fields, written during buffer writeback. */
        __be64          agf_lsn;        /* last write sequence */
@@ -670,7 +673,8 @@ typedef struct xfs_agf {
 #define        XFS_AGF_LONGEST         0x00000400
 #define        XFS_AGF_BTREEBLKS       0x00000800
 #define        XFS_AGF_UUID            0x00001000
-#define        XFS_AGF_NUM_BITS        13
+#define        XFS_AGF_RMAP_BLOCKS     0x00002000
+#define        XFS_AGF_NUM_BITS        14
 #define        XFS_AGF_ALL_BITS        ((1 << XFS_AGF_NUM_BITS) - 1)
 
 #define XFS_AGF_FLAGS \
@@ -686,7 +690,8 @@ typedef struct xfs_agf {
        { XFS_AGF_FREEBLKS,     "FREEBLKS" }, \
        { XFS_AGF_LONGEST,      "LONGEST" }, \
        { XFS_AGF_BTREEBLKS,    "BTREEBLKS" }, \
-       { XFS_AGF_UUID,         "UUID" }
+       { XFS_AGF_UUID,         "UUID" }, \
+       { XFS_AGF_RMAP_BLOCKS,  "RMAP_BLOCKS" }
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGF_DADDR(mp)      ((xfs_daddr_t)(1 << (mp)->m_sectbb_log))

diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index bc1faeb..17b8eeb 100644 (file)
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -98,6 +98,8 @@ xfs_rmapbt_alloc_block(
        union xfs_btree_ptr     *new,
        int                     *stat)
 {
+       struct xfs_buf          *agbp = cur->bc_private.a.agbp;
+       struct xfs_agf          *agf = XFS_BUF_TO_AGF(agbp);
        int                     error;
        xfs_agblock_t           bno;
 
@@ -124,6 +126,8 @@ xfs_rmapbt_alloc_block(
 
        xfs_trans_agbtree_delta(cur->bc_tp, 1);
        new->s = cpu_to_be32(bno);
+       be32_add_cpu(&agf->agf_rmap_blocks, 1);
+       xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
 
        XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
        *stat = 1;
@@ -143,6 +147,8 @@ xfs_rmapbt_free_block(
        bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp));
        trace_xfs_rmapbt_free_block(cur->bc_mp, cur->bc_private.a.agno,
                        bno, 1);
+       be32_add_cpu(&agf->agf_rmap_blocks, -1);
+       xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
        error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
        if (error)
                return error;

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 47a318c..607cc29 100644 (file)
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -115,7 +115,6 @@ xfs_buf_ioacct_dec(
        if (!(bp->b_flags & _XBF_IN_FLIGHT))
                return;
 
-       ASSERT(bp->b_flags & XBF_ASYNC);
        bp->b_flags &= ~_XBF_IN_FLIGHT;
        percpu_counter_dec(&bp->b_target->bt_io_count);
 }

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index ed95e5b..e612a02 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -741,9 +741,20 @@ xfs_file_dax_write(
         * page is inserted into the pagecache when we have to serve a write
         * fault on a hole.  It should never be dirtied and can simply be
         * dropped from the pagecache once we get real data for the page.
+        *
+        * XXX: This is racy against mmap, and there's nothing we can do about
+        * it. dax_do_io() should really do this invalidation internally as
+        * it will know if we've allocated over a holei for this specific IO and
+        * if so it needs to update the mapping tree and invalidate existing
+        * PTEs over the newly allocated range. Remove this invalidation when
+        * dax_do_io() is fixed up.
         */
        if (mapping->nrpages) {
-               ret = invalidate_inode_pages2(mapping);
+               loff_t end = iocb->ki_pos + iov_iter_count(from) - 1;
+
+               ret = invalidate_inode_pages2_range(mapping,
+                                                   iocb->ki_pos >> PAGE_SHIFT,
+                                                   end >> PAGE_SHIFT);
                WARN_ON_ONCE(ret);
        }
 

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 0f96847..0b7f986 100644 (file)
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -248,6 +248,7 @@ xfs_growfs_data_private(
                        agf->agf_roots[XFS_BTNUM_RMAPi] =
                                                cpu_to_be32(XFS_RMAP_BLOCK(mp));
                        agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+                       agf->agf_rmap_blocks = cpu_to_be32(1);
                }
 
                agf->agf_flfirst = cpu_to_be32(1);

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 697c8fd..2af0dda 100644 (file)
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -715,12 +715,16 @@ xfs_iomap_write_allocate(
                 * is in the delayed allocation extent on which we sit
                 * but before our buffer starts.
                 */
-
                nimaps = 0;
                while (nimaps == 0) {
                        nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
-
-                       error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres,
+                       /*
+                        * We have already reserved space for the extent and any
+                        * indirect blocks when creating the delalloc extent,
+                        * there is no need to reserve space in this transaction
+                        * again.
+                        */
+                       error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0,
                                        0, XFS_TRANS_RESERVE, &tp);
                        if (error)
                                return error;