Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

Pull XFS updates from Ben Myers:
 "Scalability improvements for dquots, log grant code cleanups, plus
  bugfixes and cleanups large and small"

Fix up various trivial conflicts that were due to some of the earlier
patches already having been integrated into v3.3 as bugfixes, and then
there were development patches on top of those.  Easily merged by just
taking the newer version from the pulled branch.

* 'for-linus' of git://oss.sgi.com/xfs/xfs: (45 commits)
  xfs: fallback to vmalloc for large buffers in xfs_getbmap
  xfs: fallback to vmalloc for large buffers in xfs_attrmulti_attr_get
  xfs: remove remaining scraps of struct xfs_iomap
  xfs: fix inode lookup race
  xfs: clean up minor sparse warnings
  xfs: remove the global xfs_Gqm structure
  xfs: remove the per-filesystem list of dquots
  xfs: use per-filesystem radix trees for dquot lookup
  xfs: per-filesystem dquot LRU lists
  xfs: use common code for quota statistics
  xfs: reimplement fdatasync support
  xfs: split in-core and on-disk inode log item fields
  xfs: make xfs_inode_item_size idempotent
  xfs: log timestamp updates
  xfs: log file size updates at I/O completion time
  xfs: log file size updates as part of unwritten extent conversion
  xfs: do not require an ioend for new EOF calculation
  xfs: use per-filesystem I/O completion workqueues
  quota: make Q_XQUOTASYNC a noop
  xfs: include reservations in quota reporting
  ...

1 files changed, 85 insertions, 79 deletions

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index baf40e378d35..912442cf0f82 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -324,10 +324,9 @@ xfs_parseargs(
                 } else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
                         mp->m_flags |= XFS_MOUNT_FILESTREAMS;
                 } else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
-                        mp->m_qflags &= ~(XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
-                                          XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
-                                          XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
-                                          XFS_UQUOTA_ENFD | XFS_OQUOTA_ENFD);
+                        mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
+                        mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+                        mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
                 } else if (!strcmp(this_char, MNTOPT_QUOTA) ||
                            !strcmp(this_char, MNTOPT_UQUOTA) ||
                            !strcmp(this_char, MNTOPT_USRQUOTA)) {
@@ -760,6 +759,36 @@ xfs_setup_devices(
         return 0;
 }
 
+STATIC int
+xfs_init_mount_workqueues(
+        struct xfs_mount        *mp)
+{
+        mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
+                        WQ_MEM_RECLAIM, 0, mp->m_fsname);
+        if (!mp->m_data_workqueue)
+                goto out;
+
+        mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
+                        WQ_MEM_RECLAIM, 0, mp->m_fsname);
+        if (!mp->m_unwritten_workqueue)
+                goto out_destroy_data_iodone_queue;
+
+        return 0;
+
+out_destroy_data_iodone_queue:
+        destroy_workqueue(mp->m_data_workqueue);
+out:
+        return -ENOMEM;
+}
+
+STATIC void
+xfs_destroy_mount_workqueues(
+        struct xfs_mount        *mp)
+{
+        destroy_workqueue(mp->m_data_workqueue);
+        destroy_workqueue(mp->m_unwritten_workqueue);
+}
+
 /* Catch misguided souls that try to use this interface on XFS */
 STATIC struct inode *
 xfs_fs_alloc_inode(
@@ -834,91 +863,58 @@ xfs_fs_inode_init_once(
 }
 
 /*
- * Dirty the XFS inode when mark_inode_dirty_sync() is called so that
- * we catch unlogged VFS level updates to the inode.
+ * This is called by the VFS when dirtying inode metadata.  This can happen
+ * for a few reasons, but we only care about timestamp updates, given that
+ * we handled the rest ourselves.  In theory no other calls should happen,
+ * but for example generic_write_end() keeps dirtying the inode after
+ * updating i_size.  Thus we check that the flags are exactly I_DIRTY_SYNC,
+ * and skip this call otherwise.
  *
- * We need the barrier() to maintain correct ordering between unlogged
- * updates and the transaction commit code that clears the i_update_core
- * field. This requires all updates to be completed before marking the
- * inode dirty.
+ * We'll hopefull get a different method just for updating timestamps soon,
+ * at which point this hack can go away, and maybe we'll also get real
+ * error handling here.
  */
 STATIC void
 xfs_fs_dirty_inode(
-        struct inode    *inode,
-        int             flags)
-{
-        barrier();
-        XFS_I(inode)->i_update_core = 1;
-}
-
-STATIC int
-xfs_fs_write_inode(
         struct inode            *inode,
-        struct writeback_control *wbc)
+        int                     flags)
 {
         struct xfs_inode        *ip = XFS_I(inode);
         struct xfs_mount        *mp = ip->i_mount;
-        int                     error = EAGAIN;
-
-        trace_xfs_write_inode(ip);
-
-        if (XFS_FORCED_SHUTDOWN(mp))
-                return -XFS_ERROR(EIO);
-
-        if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) {
-                /*
-                 * Make sure the inode has made it it into the log.  Instead
-                 * of forcing it all the way to stable storage using a
-                 * synchronous transaction we let the log force inside the
-                 * ->sync_fs call do that for thus, which reduces the number
-                 * of synchronous log forces dramatically.
-                 */
-                error = xfs_log_dirty_inode(ip, NULL, 0);
-                if (error)
-                        goto out;
-                return 0;
-        } else {
-                if (!ip->i_update_core)
-                        return 0;
+        struct xfs_trans        *tp;
+        int                     error;
 
-                /*
-                 * We make this non-blocking if the inode is contended, return
-                 * EAGAIN to indicate to the caller that they did not succeed.
-                 * This prevents the flush path from blocking on inodes inside
-                 * another operation right now, they get caught later by
-                 * xfs_sync.
-                 */
-                if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
-                        goto out;
+        if (flags != I_DIRTY_SYNC)
+                return;
 
-                if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
-                        goto out_unlock;
+        trace_xfs_dirty_inode(ip);
 
-                /*
-                 * Now we have the flush lock and the inode is not pinned, we
-                 * can check if the inode is really clean as we know that
-                 * there are no pending transaction completions, it is not
-                 * waiting on the delayed write queue and there is no IO in
-                 * progress.
-                 */
-                if (xfs_inode_clean(ip)) {
-                        xfs_ifunlock(ip);
-                        error = 0;
-                        goto out_unlock;
-                }
-                error = xfs_iflush(ip, SYNC_TRYLOCK);
+        tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+        error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+        if (error) {
+                xfs_trans_cancel(tp, 0);
+                goto trouble;
         }
-
- out_unlock:
-        xfs_iunlock(ip, XFS_ILOCK_SHARED);
- out:
+        xfs_ilock(ip, XFS_ILOCK_EXCL);
         /*
-         * if we failed to write out the inode then mark
-         * it dirty again so we'll try again later.
+         * Grab all the latest timestamps from the Linux inode.
          */
+        ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
+        ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
+        ip->i_d.di_ctime.t_sec = (__int32_t)inode->i_ctime.tv_sec;
+        ip->i_d.di_ctime.t_nsec = (__int32_t)inode->i_ctime.tv_nsec;
+        ip->i_d.di_mtime.t_sec = (__int32_t)inode->i_mtime.tv_sec;
+        ip->i_d.di_mtime.t_nsec = (__int32_t)inode->i_mtime.tv_nsec;
+
+        xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+        xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
+        error = xfs_trans_commit(tp, 0);
         if (error)
-                xfs_mark_inode_dirty_sync(ip);
-        return -error;
+                goto trouble;
+        return;
+
+trouble:
+        xfs_warn(mp, "failed to update timestamps for inode 0x%llx", ip->i_ino);
 }
 
 STATIC void
@@ -983,6 +979,7 @@ xfs_fs_put_super(
         xfs_unmountfs(mp);
         xfs_freesb(mp);
         xfs_icsb_destroy_counters(mp);
+        xfs_destroy_mount_workqueues(mp);
         xfs_close_devices(mp);
         xfs_free_fsname(mp);
         kfree(mp);
@@ -1309,10 +1306,14 @@ xfs_fs_fill_super(
         if (error)
                 goto out_free_fsname;
 
-        error = xfs_icsb_init_counters(mp);
+        error = xfs_init_mount_workqueues(mp);
         if (error)
                 goto out_close_devices;
 
+        error = xfs_icsb_init_counters(mp);
+        if (error)
+                goto out_destroy_workqueues;
+
         error = xfs_readsb(mp, flags);
         if (error)
                 goto out_destroy_counters;
@@ -1376,6 +1377,8 @@ xfs_fs_fill_super(
         xfs_freesb(mp);
  out_destroy_counters:
         xfs_icsb_destroy_counters(mp);
+out_destroy_workqueues:
+        xfs_destroy_mount_workqueues(mp);
  out_close_devices:
         xfs_close_devices(mp);
  out_free_fsname:
@@ -1429,7 +1432,6 @@ static const struct super_operations xfs_super_operations = {
         .alloc_inode            = xfs_fs_alloc_inode,
         .destroy_inode          = xfs_fs_destroy_inode,
         .dirty_inode            = xfs_fs_dirty_inode,
-        .write_inode            = xfs_fs_write_inode,
         .evict_inode            = xfs_fs_evict_inode,
         .put_super              = xfs_fs_put_super,
         .sync_fs                = xfs_fs_sync_fs,
@@ -1651,13 +1653,17 @@ init_xfs_fs(void)
         if (error)
                 goto out_cleanup_procfs;
 
-        vfs_initquota();
+        error = xfs_qm_init();
+        if (error)
+                goto out_sysctl_unregister;
 
         error = register_filesystem(&xfs_fs_type);
         if (error)
-                goto out_sysctl_unregister;
+                goto out_qm_exit;
         return 0;
 
+ out_qm_exit:
+        xfs_qm_exit();
  out_sysctl_unregister:
         xfs_sysctl_unregister();
  out_cleanup_procfs:
@@ -1679,7 +1685,7 @@ init_xfs_fs(void)
 STATIC void __exit
 exit_xfs_fs(void)
 {
-        vfs_exitquota();
+        xfs_qm_exit();
         unregister_filesystem(&xfs_fs_type);
         xfs_sysctl_unregister();
         xfs_cleanup_procfs();