[patch 19/28] fs: dcache avoid starvation in dcache multi-step operations

[Nick Piggin]

Long lived dcache "multi-step" operations which retry on rename seq can
be starved with a lot of rename activity. If they fail after the 1st pass,
take the rename_lock for writing to avoid further starvation.

Signed-off-by: Nick Piggin <npiggin@xxxxxxxxx>

---
 fs/dcache.c |   56 ++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 42 insertions(+), 14 deletions(-)

Index: linux-2.6/fs/dcache.c
===================================================================
--- linux-2.6.orig/fs/dcache.c	2010-11-17 00:52:37.000000000 +1100
+++ linux-2.6/fs/dcache.c	2010-11-17 01:05:40.000000000 +1100
@@ -937,10 +937,11 @@ int have_submounts(struct dentry *parent
 	struct dentry *this_parent;
 	struct list_head *next;
 	unsigned seq;
+	int locked = 0;
 
-rename_retry:
-	this_parent = parent;
 	seq = read_seqbegin(&rename_lock);
+again:
+	this_parent = parent;
 
 	if (d_mountpoint(parent))
 		goto positive;
@@ -985,7 +986,7 @@ int have_submounts(struct dentry *parent
 		/* might go back up the wrong parent if we have had a rename
 		 * or deletion */
 		if (this_parent != child->d_parent ||
-				read_seqretry(&rename_lock, seq)) {
+			 (!locked && read_seqretry(&rename_lock, seq))) {
 			spin_unlock(&this_parent->d_lock);
 			rcu_read_unlock();
 			goto rename_retry;
@@ -995,13 +996,22 @@ int have_submounts(struct dentry *parent
 		goto resume;
 	}
 	spin_unlock(&this_parent->d_lock);
-	if (read_seqretry(&rename_lock, seq))
+	if (!locked && read_seqretry(&rename_lock, seq))
 		goto rename_retry;
+	if (locked)
+		write_sequnlock(&rename_lock);
 	return 0; /* No mount points found in tree */
 positive:
-	if (read_seqretry(&rename_lock, seq))
+	if (!locked && read_seqretry(&rename_lock, seq))
 		goto rename_retry;
+	if (locked)
+		write_sequnlock(&rename_lock);
 	return 1;
+
+rename_retry:
+	locked = 1;
+	write_seqlock(&rename_lock);
+	goto again;
 }
 EXPORT_SYMBOL(have_submounts);
 
@@ -1025,11 +1035,11 @@ static int select_parent(struct dentry *
 	struct list_head *next;
 	unsigned seq;
 	int found = 0;
+	int locked = 0;
 
-rename_retry:
-	this_parent = parent;
 	seq = read_seqbegin(&rename_lock);
-
+again:
+	this_parent = parent;
 	spin_lock(&this_parent->d_lock);
 repeat:
 	next = this_parent->d_subdirs.next;
@@ -1091,7 +1101,7 @@ static int select_parent(struct dentry *
 		/* might go back up the wrong parent if we have had a rename
 		 * or deletion */
 		if (this_parent != child->d_parent ||
-				read_seqretry(&rename_lock, seq)) {
+			(!locked && read_seqretry(&rename_lock, seq))) {
 			spin_unlock(&this_parent->d_lock);
 			rcu_read_unlock();
 			goto rename_retry;
@@ -1102,9 +1112,18 @@ static int select_parent(struct dentry *
 	}
 out:
 	spin_unlock(&this_parent->d_lock);
-	if (read_seqretry(&rename_lock, seq))
+	if (!locked && read_seqretry(&rename_lock, seq))
 		goto rename_retry;
+	if (locked)
+		write_sequnlock(&rename_lock);
 	return found;
+
+rename_retry:
+	if (found)
+		return found;
+	locked = 1;
+	write_seqlock(&rename_lock);
+	goto again;
 }
 
 /**
@@ -2602,10 +2621,11 @@ void d_genocide(struct dentry *root)
 	struct dentry *this_parent;
 	struct list_head *next;
 	unsigned seq;
+	int locked = 0;
 
-rename_retry:
-	this_parent = root;
 	seq = read_seqbegin(&rename_lock);
+again:
+	this_parent = root;
 	spin_lock(&this_parent->d_lock);
 repeat:
 	next = this_parent->d_subdirs.next;
@@ -2650,7 +2670,7 @@ void d_genocide(struct dentry *root)
 		/* might go back up the wrong parent if we have had a rename
 		 * or deletion */
 		if (this_parent != child->d_parent ||
-				read_seqretry(&rename_lock, seq)) {
+			 (!locked && read_seqretry(&rename_lock, seq))) {
 			spin_unlock(&this_parent->d_lock);
 			rcu_read_unlock();
 			goto rename_retry;
@@ -2660,8 +2680,16 @@ void d_genocide(struct dentry *root)
 		goto resume;
 	}
 	spin_unlock(&this_parent->d_lock);
-	if (read_seqretry(&rename_lock, seq))
+	if (!locked && read_seqretry(&rename_lock, seq))
 		goto rename_retry;
+	if (locked)
+		write_sequnlock(&rename_lock);
+	return;
+
+rename_retry:
+	locked = 1;
+	write_seqlock(&rename_lock);
+	goto again;
 }
 
 /**


--
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/