[3/3] eventfd: add internal reference counting to fix notifier race conditions

Commit Message

Davide Libenzi June 20, 2009, 10:11 p.m. UTC

On Sat, 20 Jun 2009, Davide Libenzi wrote:

> How about the one below?

Maybe with an interface that can be undone w/out a file* :)


- Davide


---
 fs/eventfd.c            |   34 +++++++++++++++++++++++++++++++++-
 include/linux/eventfd.h |    8 ++++++++
 2 files changed, 41 insertions(+), 1 deletion(-)

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

Index: linux-2.6.mod/fs/eventfd.c
===================================================================
--- linux-2.6.mod.orig/fs/eventfd.c	2009-06-20 13:08:22.000000000 -0700
+++ linux-2.6.mod/fs/eventfd.c	2009-06-20 15:07:18.000000000 -0700
@@ -17,8 +17,10 @@ 
 #include <linux/eventfd.h>
 #include <linux/syscalls.h>
 #include <linux/module.h>
+#include <linux/kref.h>
 
 struct eventfd_ctx {
+	struct kref kref;
 	wait_queue_head_t wqh;
 	/*
 	 * Every time that a write(2) is performed on an eventfd, the
@@ -59,9 +61,19 @@  int eventfd_signal(struct file *file, in
 }
 EXPORT_SYMBOL_GPL(eventfd_signal);
 
+static void eventfd_free(struct kref *kref)
+{
+	struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref);
+
+	kfree(ctx);
+}
+
 static int eventfd_release(struct inode *inode, struct file *file)
 {
-	kfree(file->private_data);
+	struct eventfd_ctx *ctx = file->private_data;
+
+	wake_up_poll(&ctx->wqh, POLLHUP);
+	kref_put(&ctx->kref, eventfd_free);
 	return 0;
 }
 
@@ -201,6 +213,25 @@  struct file *eventfd_fget(int fd)
 }
 EXPORT_SYMBOL_GPL(eventfd_fget);
 
+struct eventfd_kref *eventfd_refget(struct file *file)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+
+	if (file->f_op != &eventfd_fops)
+		return ERR_PTR(-EINVAL);
+	kref_get(&ctx->kref);
+	return (struct eventfd_kref *) ctx;
+}
+EXPORT_SYMBOL_GPL(eventfd_refget);
+
+void eventfd_refput(struct eventfd_kref *ref)
+{
+	struct eventfd_ctx *ctx = (struct eventfd_ctx *) ref;
+
+	kref_put(&ctx->kref, eventfd_free);
+}
+EXPORT_SYMBOL_GPL(eventfd_refput);
+
 SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 {
 	int fd;
@@ -217,6 +248,7 @@  SYSCALL_DEFINE2(eventfd2, unsigned int, 
 	if (!ctx)
 		return -ENOMEM;
 
+	kref_init(&ctx->kref);
 	init_waitqueue_head(&ctx->wqh);
 	ctx->count = count;
 	ctx->flags = flags;
Index: linux-2.6.mod/include/linux/eventfd.h
===================================================================
--- linux-2.6.mod.orig/include/linux/eventfd.h	2009-06-20 13:08:22.000000000 -0700
+++ linux-2.6.mod/include/linux/eventfd.h	2009-06-20 15:06:03.000000000 -0700
@@ -8,6 +8,8 @@ 
 #ifndef _LINUX_EVENTFD_H
 #define _LINUX_EVENTFD_H
 
+struct eventfd_kref;
+
 #ifdef CONFIG_EVENTFD
 
 /* For O_CLOEXEC and O_NONBLOCK */
@@ -29,12 +31,18 @@ 
 
 struct file *eventfd_fget(int fd);
 int eventfd_signal(struct file *file, int n);
+struct eventfd_kref *eventfd_refget(struct file *file);
+void eventfd_refput(struct eventfd_kref *ref);
 
 #else /* CONFIG_EVENTFD */
 
 #define eventfd_fget(fd) ERR_PTR(-ENOSYS)
 static inline int eventfd_signal(struct file *file, int n)
 { return 0; }
+static inline struct eventfd_kref *eventfd_refget(struct file *file)
+{ return ERR_PTR(-ENOSYS); }
+static inline void eventfd_refput(struct eventfd_kref *ref)
+{ }
 
 #endif /* CONFIG_EVENTFD */