Merge branch 'v2.6.36-rc8' into for-2.6.37/barrier

Conflicts:
	block/blk-core.c
	drivers/block/loop.c
	mm/swapfile.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

7 files changed, 48 insertions, 58 deletions

diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 15412fe15c3a..b552f816de15 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -852,8 +852,8 @@ xfs_convert_page(
                 SetPageUptodate(page);
 
         if (count) {
-                wbc->nr_to_write--;
-                if (wbc->nr_to_write <= 0)
+                if (--wbc->nr_to_write <= 0 &&
+                    wbc->sync_mode == WB_SYNC_NONE)
                         done = 1;
         }
         xfs_start_page_writeback(page, !page_dirty, count);
@@ -1068,7 +1068,7 @@ xfs_vm_writepage(
          * by themselves.
          */
         if ((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC)
-                goto out_fail;
+                goto redirty;
 
         /*
          * We need a transaction if there are delalloc or unwritten buffers
@@ -1080,7 +1080,7 @@ xfs_vm_writepage(
          */
         xfs_count_page_state(page, &delalloc, &unwritten);
         if ((current->flags & PF_FSTRANS) && (delalloc || unwritten))
-                goto out_fail;
+                goto redirty;
 
         /* Is this page beyond the end of the file? */
         offset = i_size_read(inode);
@@ -1245,12 +1245,15 @@ error:
         if (iohead)
                 xfs_cancel_ioend(iohead);
 
+        if (err == -EAGAIN)
+                goto redirty;
+
         xfs_aops_discard_page(page);
         ClearPageUptodate(page);
         unlock_page(page);
         return err;
 
-out_fail:
+redirty:
         redirty_page_for_writepage(wbc, page);
         unlock_page(page);
         return 0;
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index b93ea3342281..1846a0dd7035 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -440,12 +440,7 @@ _xfs_buf_find(
                 ASSERT(btp == bp->b_target);
                 if (bp->b_file_offset == range_base &&
                     bp->b_buffer_length == range_length) {
-                        /*
-                         * If we look at something, bring it to the
-                         * front of the list for next time.
-                         */
                         atomic_inc(&bp->b_hold);
-                        list_move(&bp->b_hash_list, &hash->bh_list);
                         goto found;
                 }
         }
@@ -1431,8 +1426,7 @@ xfs_alloc_bufhash(
 {
         unsigned int            i;
 
-        btp->bt_hashshift = external ? 3 : 8;   /* 8 or 256 buckets */
-        btp->bt_hashmask = (1 << btp->bt_hashshift) - 1;
+        btp->bt_hashshift = external ? 3 : 12;  /* 8 or 4096 buckets */
         btp->bt_hash = kmem_zalloc_large((1 << btp->bt_hashshift) *
                                          sizeof(xfs_bufhash_t));
         for (i = 0; i < (1 << btp->bt_hashshift); i++) {
@@ -1926,7 +1920,8 @@ xfs_buf_init(void)
         if (!xfs_buf_zone)
                 goto out;
 
-        xfslogd_workqueue = create_workqueue("xfslogd");
+        xfslogd_workqueue = alloc_workqueue("xfslogd",
+                                        WQ_RESCUER | WQ_HIGHPRI, 1);
         if (!xfslogd_workqueue)
                 goto out_free_buf_zone;
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index d533d64e2c3e..9d021c73ea52 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -128,7 +128,6 @@ typedef struct xfs_buftarg {
         size_t                  bt_smask;
 
         /* per device buffer hash table */
-        uint                    bt_hashmask;
         uint                    bt_hashshift;
         xfs_bufhash_t           *bt_hash;
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 237f5ffb2ee8..3b9e626f7cd1 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -785,6 +785,8 @@ xfs_ioc_fsgetxattr(
 {
         struct fsxattr          fa;
 
+        memset(&fa, 0, sizeof(struct fsxattr));
+
         xfs_ilock(ip, XFS_ILOCK_SHARED);
         fa.fsx_xflags = xfs_ip2xflags(ip);
         fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
@@ -907,6 +909,13 @@ xfs_ioctl_setattr(
                 return XFS_ERROR(EIO);
 
         /*
+         * Disallow 32bit project ids because on-disk structure
+         * is 16bit only.
+         */
+        if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1))
+                return XFS_ERROR(EINVAL);
+
+        /*
          * If disk quotas is on, we make sure that the dquots do exist on disk,
          * before we start any other transactions. Trying to do this later
          * is messy. We don't care to take a readlock to look at the ids
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 68be25dcd301..b1fc2a6bfe83 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -664,7 +664,7 @@ xfs_vn_fiemap(
                                         fieinfo->fi_extents_max + 1;
         bm.bmv_count = min_t(__s32, bm.bmv_count,
                              (PAGE_SIZE * 16 / sizeof(struct getbmapx)));
-        bm.bmv_iflags = BMV_IF_PREALLOC;
+        bm.bmv_iflags = BMV_IF_PREALLOC | BMV_IF_NO_HOLES;
         if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
                 bm.bmv_iflags |= BMV_IF_ATTRFORK;
         if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 5fa7a30cc3f0..08fd3102128c 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -1225,6 +1225,7 @@ xfs_fs_statfs(
         struct xfs_inode        *ip = XFS_I(dentry->d_inode);
         __uint64_t              fakeinos, id;
         xfs_extlen_t            lsize;
+        __int64_t               ffree;
 
         statp->f_type = XFS_SB_MAGIC;
         statp->f_namelen = MAXNAMELEN - 1;
@@ -1248,7 +1249,11 @@ xfs_fs_statfs(
                 statp->f_files = min_t(typeof(statp->f_files),
                                         statp->f_files,
                                         mp->m_maxicount);
-        statp->f_ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
+
+        /* make sure statp->f_ffree does not underflow */
+        ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
+        statp->f_ffree = max_t(__int64_t, ffree, 0);
+
         spin_unlock(&mp->m_sb_lock);
 
         if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) ||
@@ -1401,7 +1406,7 @@ xfs_fs_freeze(
 
         xfs_save_resvblks(mp);
         xfs_quiesce_attr(mp);
-        return -xfs_fs_log_dummy(mp);
+        return -xfs_fs_log_dummy(mp, SYNC_WAIT);
 }
 
 STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index dfcbd98d1599..81976ffed7d6 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -34,6 +34,7 @@
 #include "xfs_inode_item.h"
 #include "xfs_quota.h"
 #include "xfs_trace.h"
+#include "xfs_fsops.h"
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
@@ -341,38 +342,6 @@ xfs_sync_attr(
 }
 
 STATIC int
-xfs_commit_dummy_trans(
-        struct xfs_mount        *mp,
-        uint                    flags)
-{
-        struct xfs_inode        *ip = mp->m_rootip;
-        struct xfs_trans        *tp;
-        int                     error;
-
-        /*
-         * Put a dummy transaction in the log to tell recovery
-         * that all others are OK.
-         */
-        tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
-        error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
-        if (error) {
-                xfs_trans_cancel(tp, 0);
-                return error;
-        }
-
-        xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-        xfs_trans_ijoin(tp, ip);
-        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-        error = xfs_trans_commit(tp, 0);
-        xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-        /* the log force ensures this transaction is pushed to disk */
-        xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
-        return error;
-}
-
-STATIC int
 xfs_sync_fsdata(
         struct xfs_mount        *mp)
 {
@@ -432,7 +401,7 @@ xfs_quiesce_data(
 
         /* mark the log as covered if needed */
         if (xfs_log_need_covered(mp))
-                error2 = xfs_commit_dummy_trans(mp, SYNC_WAIT);
+                error2 = xfs_fs_log_dummy(mp, SYNC_WAIT);
 
         /* flush data-only devices */
         if (mp->m_rtdev_targp)
@@ -563,7 +532,7 @@ xfs_flush_inodes(
 /*
  * Every sync period we need to unpin all items, reclaim inodes and sync
  * disk quotas.  We might need to cover the log to indicate that the
- * filesystem is idle.
+ * filesystem is idle and not frozen.
  */
 STATIC void
 xfs_sync_worker(
@@ -577,8 +546,9 @@ xfs_sync_worker(
                 xfs_reclaim_inodes(mp, 0);
                 /* dgc: errors ignored here */
                 error = xfs_qm_sync(mp, SYNC_TRYLOCK);
-                if (xfs_log_need_covered(mp))
-                        error = xfs_commit_dummy_trans(mp, 0);
+                if (mp->m_super->s_frozen == SB_UNFROZEN &&
+                    xfs_log_need_covered(mp))
+                        error = xfs_fs_log_dummy(mp, 0);
         }
         mp->m_sync_seq++;
         wake_up(&mp->m_wait_single_sync_task);
@@ -698,14 +668,11 @@ xfs_inode_set_reclaim_tag(
         xfs_perag_put(pag);
 }
 
-void
-__xfs_inode_clear_reclaim_tag(
-        xfs_mount_t     *mp,
+STATIC void
+__xfs_inode_clear_reclaim(
         xfs_perag_t     *pag,
         xfs_inode_t     *ip)
 {
-        radix_tree_tag_clear(&pag->pag_ici_root,
-                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
         pag->pag_ici_reclaimable--;
         if (!pag->pag_ici_reclaimable) {
                 /* clear the reclaim tag from the perag radix tree */
@@ -719,6 +686,17 @@ __xfs_inode_clear_reclaim_tag(
         }
 }
 
+void
+__xfs_inode_clear_reclaim_tag(
+        xfs_mount_t     *mp,
+        xfs_perag_t     *pag,
+        xfs_inode_t     *ip)
+{
+        radix_tree_tag_clear(&pag->pag_ici_root,
+                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+        __xfs_inode_clear_reclaim(pag, ip);
+}
+
 /*
  * Inodes in different states need to be treated differently, and the return
  * value of xfs_iflush is not sufficient to get this right. The following table
@@ -868,6 +846,7 @@ reclaim:
         if (!radix_tree_delete(&pag->pag_ici_root,
                                 XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
                 ASSERT(0);
+        __xfs_inode_clear_reclaim(pag, ip);
         write_unlock(&pag->pag_ici_lock);
 
         /*