[RFCv2][PATCH 7/7] fsnotify: track when ignored mask clearing is needed

[Dave Hansen]

From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

According to Jan Kara:

	You can have ignored mask set without any of the
	notification masks set and you are expected to clear the
	ignored mask on the first IN_MODIFY event.

But, the only way we currently have to go and find if we need to
do this ignored-mask-clearing is to go through the mark lists
and look for them.  That mark list iteration requires an
srcu_read_lock() which has a memory barrier and can be expensive.

The calculation of 'has_ignore' is pretty cheap because we store
it next to another value which we are updating and we do it
inside of a loop we were already running.

This patch will really only matter when we have a workload where
a file is being modified often _and_ there is an active fsnotify
mark on it.  Otherwise the checks against *_fsnotify.marks.first
will keep us out of the expensive srcu_read_lock() call.

Cc: Jan Kara <jack@xxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: linux-fsdevel@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
---

 b/fs/notify/fsnotify.c          |   44 ++++++++++++++++++++++++++++++++++------
 b/fs/notify/mark.c              |    8 +++++--
 b/include/linux/fsnotify_head.h |    1 
 3 files changed, 45 insertions(+), 8 deletions(-)

diff -puN fs/notify/fsnotify.c~fsnotify-ignore-present fs/notify/fsnotify.c
--- a/fs/notify/fsnotify.c~fsnotify-ignore-present	2015-06-24 17:14:37.187226743 -0700
+++ b/fs/notify/fsnotify.c	2015-06-24 17:14:37.194227057 -0700
@@ -183,6 +183,34 @@ static int send_to_group(struct inode *t
 }
 
 /*
+ * The "logical or" of all of the marks' ->mask is kept in the
+ * i/mnt_fsnotify.mask.  We can check it instead of going
+ * through all of the marks.  fsnotify_recalc_mask() does the
+ * updates.
+ */
+static int some_mark_is_interested(__u32 mask, struct inode *inode, struct mount *mnt)
+{
+	if (mask & inode->i_fsnotify.mask)
+		return 1;
+	if (mnt && (mask & mnt->mnt_fsnotify.mask))
+		return 1;
+	return 0;
+}
+
+/*
+ * fsnotify_recalc_mask() recalculates "has_ignore" whenever any
+ * mark's flags change.
+ */
+static int some_mark_needs_ignore_clear(struct inode *inode, struct mount *mnt)
+{
+	if (inode->i_fsnotify.has_ignore)
+		return 1;
+	if (mnt && mnt->mnt_fsnotify.has_ignore)
+		return 1;
+	return 0;
+}
+
+/*
  * This is the main call to fsnotify.  The VFS calls into hook specific functions
  * in linux/fsnotify.h.  Those functions then in turn call here.  Here will call
  * out to all of the registered fsnotify_group.  Those groups can then use the
@@ -205,14 +233,18 @@ int fsnotify(struct inode *to_tell, __u3
 		mnt = NULL;
 
 	/*
-	 * if this is a modify event we may need to clear the ignored masks
-	 * otherwise return if neither the inode nor the vfsmount care about
-	 * this type of event.
+	 * We must clear the (user-visible) ignored mask on the first IN_MODIFY
+	 * event despite the 'mask' which is passed in here.  But we can safely
+	 * skip that step if we know there are no marks which need this action.
+	 *
+	 * We can also skip looking at the list of marks if we know that none
+	 * of the marks are interested in the events in our 'mask'.
 	 */
-	if (!(mask & FS_MODIFY) &&
-	    !(test_mask & to_tell->i_fsnotify.mask) &&
-	    !(mnt && test_mask & mnt->mnt_fsnotify.mask))
+	if ((mask & FS_MODIFY) && !some_mark_needs_ignore_clear(to_tell, mnt))
+		return 0;
+	else if (!some_mark_is_interested(test_mask, to_tell, mnt))
 		return 0;
+
 	/*
 	 * Optimization: srcu_read_lock() has a memory barrier which can
 	 * be expensive.  It protects walking the *_fsnotify_marks lists.
diff -puN fs/notify/mark.c~fsnotify-ignore-present fs/notify/mark.c
--- a/fs/notify/mark.c~fsnotify-ignore-present	2015-06-24 17:14:37.189226832 -0700
+++ b/fs/notify/mark.c	2015-06-24 17:14:37.194227057 -0700
@@ -116,10 +116,14 @@ void fsnotify_recalc_mask(struct fsnotif
 {
 	u32 new_mask = 0;
 	struct fsnotify_mark *mark;
+	u32 has_ignore = 0;
 
-	hlist_for_each_entry(mark, &fsn->marks, obj_list)
+	hlist_for_each_entry(mark, &fsn->marks, obj_list) {
+		if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+			has_ignore = 1;
 		new_mask |= mark->mask;
-
+	}
+	fsn->has_ignore = has_ignore;
 	fsn->mask = new_mask;
 }
 
diff -puN include/linux/fsnotify_head.h~fsnotify-ignore-present include/linux/fsnotify_head.h
--- a/include/linux/fsnotify_head.h~fsnotify-ignore-present	2015-06-24 17:14:37.190226877 -0700
+++ b/include/linux/fsnotify_head.h	2015-06-24 17:14:37.193227012 -0700
@@ -11,6 +11,7 @@ struct fsnotify_head {
 #ifdef CONFIG_FSNOTIFY
 	__u32                   mask; /* all events this object cares about */
 	struct hlist_head       marks;
+	__u32                   has_ignore; /* any marks has ignore set */
 #endif
 };
 
_
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/