[PATCH] zoned vm counters: conversion of nr_unstable to per zone counter

[safe/jmp/linux-2.6] / fs / fs-writeback.c

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e94ab39..892643d 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -230,7 +230,6 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
                         * The inode is clean, unused
                         */
                        list_move(&inode->i_list, &inode_unused);
-                       inodes_stat.nr_unused++;
                }
        }
        wake_up_inode(inode);
@@ -238,14 +237,20 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
 }
 
 /*
- * Write out an inode's dirty pages.  Called under inode_lock.
+ * Write out an inode's dirty pages.  Called under inode_lock.  Either the
+ * caller has ref on the inode (either via __iget or via syscall against an fd)
+ * or the inode has I_WILL_FREE set (via generic_forget_inode)
  */
 static int
-__writeback_single_inode(struct inode *inode,
-                       struct writeback_control *wbc)
+__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 {
        wait_queue_head_t *wqh;
 
+       if (!atomic_read(&inode->i_count))
+               WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
+       else
+               WARN_ON(inode->i_state & I_WILL_FREE);
+
        if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_LOCK)) {
                list_move(&inode->i_list, &inode->i_sb->s_dirty);
                return 0;
@@ -259,11 +264,9 @@ __writeback_single_inode(struct inode *inode,
 
                wqh = bit_waitqueue(&inode->i_state, __I_LOCK);
                do {
-                       __iget(inode);
                        spin_unlock(&inode_lock);
                        __wait_on_bit(wqh, &wq, inode_wait,
                                                        TASK_UNINTERRUPTIBLE);
-                       iput(inode);
                        spin_lock(&inode_lock);
                } while (inode->i_state & I_LOCK);
        }
@@ -378,8 +381,8 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
                        list_move(&inode->i_list, &sb->s_dirty);
                }
                spin_unlock(&inode_lock);
-               cond_resched();
                iput(inode);
+               cond_resched();
                spin_lock(&inode_lock);
                if (wbc->nr_to_write <= 0)
                        break;
@@ -458,9 +461,11 @@ void sync_inodes_sb(struct super_block *sb, int wait)
 {
        struct writeback_control wbc = {
                .sync_mode      = wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
+               .range_start    = 0,
+               .range_end      = LLONG_MAX,
        };
-       unsigned long nr_dirty = read_page_state(nr_dirty);
-       unsigned long nr_unstable = read_page_state(nr_unstable);
+       unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+       unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
        wbc.nr_to_write = nr_dirty + nr_unstable +
                        (inodes_stat.nr_inodes - inodes_stat.nr_unused) +
@@ -541,24 +546,27 @@ void sync_inodes(int wait)
 }
 
 /**
- *     write_inode_now -       write an inode to disk
- *     @inode: inode to write to disk
- *     @sync: whether the write should be synchronous or not
+ * write_inode_now     -       write an inode to disk
+ * @inode: inode to write to disk
+ * @sync: whether the write should be synchronous or not
  *
- *     This function commits an inode to disk immediately if it is
- *     dirty. This is primarily needed by knfsd.
+ * This function commits an inode to disk immediately if it is dirty. This is
+ * primarily needed by knfsd.
+ *
+ * The caller must either have a ref on the inode or must have set I_WILL_FREE.
  */
- 
 int write_inode_now(struct inode *inode, int sync)
 {
        int ret;
        struct writeback_control wbc = {
                .nr_to_write = LONG_MAX,
                .sync_mode = WB_SYNC_ALL,
+               .range_start = 0,
+               .range_end = LLONG_MAX,
        };
 
        if (!mapping_cap_writeback_dirty(inode->i_mapping))
-               return 0;
+               wbc.nr_to_write = 0;
 
        might_sleep();
        spin_lock(&inode_lock);
@@ -602,7 +610,7 @@ EXPORT_SYMBOL(sync_inode);
  * O_SYNC flag set, to flush dirty writes to disk.
  *
  * @what is a bitmask, specifying which part of the inode's data should be
- * written and waited upon:
+ * written and waited upon.
  *
  *    OSYNC_DATA:     i_mapping's dirty data
  *    OSYNC_METADATA: the buffers at i_mapping->private_list
@@ -615,7 +623,6 @@ int generic_osync_inode(struct inode *inode, struct address_space *mapping, int
        int need_write_inode_now = 0;
        int err2;
 
-       current->flags |= PF_SYNCWRITE;
        if (what & OSYNC_DATA)
                err = filemap_fdatawrite(mapping);
        if (what & (OSYNC_METADATA|OSYNC_DATA)) {
@@ -628,7 +635,6 @@ int generic_osync_inode(struct inode *inode, struct address_space *mapping, int
                if (!err)
                        err = err2;
        }
-       current->flags &= ~PF_SYNCWRITE;
 
        spin_lock(&inode_lock);
        if ((inode->i_state & I_DIRTY) &&
@@ -668,8 +674,9 @@ int writeback_acquire(struct backing_dev_info *bdi)
 
 /**
  * writeback_in_progress: determine whether there is writeback in progress
- *                        against a backing device.
  * @bdi: the device's backing_dev_info structure.
+ *
+ * Determine whether there is writeback in progress against a backing device.
  */
 int writeback_in_progress(struct backing_dev_info *bdi)
 {