X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnotify%2Finode_mark.c;h=0399bcbe09c83f02bdf1627b1dcfc6b12c316d5f;hb=b2e75eff5e859d0c294e7405958362b26a423c6e;hp=cdc154146974e0aede8e93cde6b78c9b381d2534;hpb=3be25f49b9d6a97eae9bcb96d3292072b7658bd8;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index cdc1541..0399bcb 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -87,8 +87,8 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/writeback.h> /* for inode_lock */
 
 #include <asm/atomic.h>
 
@@ -131,6 +131,8 @@ void fsnotify_recalc_inode_mask(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	fsnotify_recalc_inode_mask_locked(inode);
 	spin_unlock(&inode->i_lock);
+
+	__fsnotify_update_child_dentry_flags(inode);
 }
 
 /*
@@ -187,7 +189,23 @@ void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry)
 	 * callback to the group function to let it know that this entry
 	 * is being freed.
 	 */
-	group->ops->freeing_mark(entry, group);
+	if (group->ops->freeing_mark)
+		group->ops->freeing_mark(entry, group);
+
+	/*
+	 * __fsnotify_update_child_dentry_flags(inode);
+	 *
+	 * I really want to call that, but we can't, we have no idea if the inode
+	 * still exists the second we drop the entry->lock.
+	 *
+	 * The next time an event arrive to this inode from one of it's children
+	 * __fsnotify_parent will see that the inode doesn't care about it's
+	 * children and will update all of these flags then.  So really this
+	 * is just a lazy update (and could be a perf win...)
+	 */
+
+
+	iput(inode);
 
 	/*
 	 * it's possible that this group tried to destroy itself, but this
@@ -291,6 +309,10 @@ int fsnotify_add_mark(struct fsnotify_mark_entry *entry,
 	struct fsnotify_mark_entry *lentry;
 	int ret = 0;
 
+	inode = igrab(inode);
+	if (unlikely(!inode))
+		return -EINVAL;
+
 	/*
 	 * LOCKING ORDER!!!!
 	 * entry->lock
@@ -301,11 +323,11 @@ int fsnotify_add_mark(struct fsnotify_mark_entry *entry,
 	spin_lock(&group->mark_lock);
 	spin_lock(&inode->i_lock);
 
-	entry->group = group;
-	entry->inode = inode;
-
 	lentry = fsnotify_find_mark_entry(group, inode);
 	if (!lentry) {
+		entry->group = group;
+		entry->inode = inode;
+
 		hlist_add_head(&entry->i_list, &inode->i_fsnotify_mark_entries);
 		list_add(&entry->g_list, &group->mark_entries);
 
@@ -322,8 +344,82 @@ int fsnotify_add_mark(struct fsnotify_mark_entry *entry,
 
 	if (lentry) {
 		ret = -EEXIST;
+		iput(inode);
 		fsnotify_put_mark(lentry);
+	} else {
+		__fsnotify_update_child_dentry_flags(inode);
 	}
 
 	return ret;
 }
+
+/**
+ * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
+ * @list: list of inodes being unmounted (sb->s_inodes)
+ *
+ * Called with inode_lock held, protecting the unmounting super block's list
+ * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
+ * We temporarily drop inode_lock, however, and CAN block.
+ */
+void fsnotify_unmount_inodes(struct list_head *list)
+{
+	struct inode *inode, *next_i, *need_iput = NULL;
+
+	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+		struct inode *need_iput_tmp;
+
+		/*
+		 * We cannot __iget() an inode in state I_CLEAR, I_FREEING,
+		 * I_WILL_FREE, or I_NEW which is fine because by that point
+		 * the inode cannot have any associated watches.
+		 */
+		if (inode->i_state & (I_CLEAR|I_FREEING|I_WILL_FREE|I_NEW))
+			continue;
+
+		/*
+		 * If i_count is zero, the inode cannot have any watches and
+		 * doing an __iget/iput with MS_ACTIVE clear would actually
+		 * evict all inodes with zero i_count from icache which is
+		 * unnecessarily violent and may in fact be illegal to do.
+		 */
+		if (!atomic_read(&inode->i_count))
+			continue;
+
+		need_iput_tmp = need_iput;
+		need_iput = NULL;
+
+		/* In case fsnotify_inode_delete() drops a reference. */
+		if (inode != need_iput_tmp)
+			__iget(inode);
+		else
+			need_iput_tmp = NULL;
+
+		/* In case the dropping of a reference would nuke next_i. */
+		if ((&next_i->i_sb_list != list) &&
+		    atomic_read(&next_i->i_count) &&
+		    !(next_i->i_state & (I_CLEAR | I_FREEING | I_WILL_FREE))) {
+			__iget(next_i);
+			need_iput = next_i;
+		}
+
+		/*
+		 * We can safely drop inode_lock here because we hold
+		 * references on both inode and next_i.  Also no new inodes
+		 * will be added since the umount has begun.  Finally,
+		 * iprune_mutex keeps shrink_icache_memory() away.
+		 */
+		spin_unlock(&inode_lock);
+
+		if (need_iput_tmp)
+			iput(need_iput_tmp);
+
+		/* for each watch, send FS_UNMOUNT and then remove it */
+		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+
+		fsnotify_inode_delete(inode);
+
+		iput(inode);
+
+		spin_lock(&inode_lock);
+	}
+}