From: Jeff Moyer <jmoyer@redhat.com>
Date: Tue, 1 Dec 2009 21:06:29 -0500
Subject: [fs] add eventfd core
Message-id: <1259701600-23508-2-git-send-email-jmoyer@redhat.com>
Patchwork-id: 21610
O-Subject: [RHEL5 PATCH 01/12 v2] signal/timer/event: eventfd core
Bugzilla: 493101
RH-Acked-by: Josef Bacik <josef@redhat.com>

Resolves: bug 493101.

commit e1ad7468c77ddb94b0615d5f50fa255525fde0f0
Author: Davide Libenzi <davidel@xmailserver.org>
Date:   Thu May 10 22:23:19 2007 -0700

    signal/timer/event: eventfd core

    This is a very simple and light file descriptor, that can be used as event
    wait/dispatch by userspace (both wait and dispatch) and by the kernel
    (dispatch only).  It can be used instead of pipe(2) in all cases where those
    would simply be used to signal events.  Their kernel overhead is much lower
    than pipes, and they do not consume two fds.  When used in the kernel, it can
    offer an fd-bridge to enable, for example, functionalities like KAIO or
    syslets/threadlets to signal to an fd the completion of certain operations.
    But more in general, an eventfd can be used by the kernel to signal readiness,
    in a POSIX poll/select way, of interfaces that would otherwise be incompatible
    with it.  The API is:

    int eventfd(unsigned int count);

    The eventfd API accepts an initial "count" parameter, and returns an eventfd
    fd.  It supports poll(2) (POLLIN, POLLOUT, POLLERR), read(2) and write(2).

    The POLLIN flag is raised when the internal counter is greater than zero.

    The POLLOUT flag is raised when at least a value of "1" can be written to the
    internal counter.

    The POLLERR flag is raised when an overflow in the counter value is detected.

    The write(2) operation can never overflow the counter, since it blocks (unless
    O_NONBLOCK is set, in which case -EAGAIN is returned).

    But the eventfd_signal() function can do it, since it's supposed to not sleep
    during its operation.

    The read(2) function reads the __u64 counter value, and reset the internal
    value to zero.  If the value read is equal to (__u64) -1, an overflow happened
    on the internal counter (due to 2^64 eventfd_signal() posts that has never
    been retired - unlickely, but possible).

    The write(2) call writes an __u64 count value, and adds it to the current
    counter.  The eventfd fd supports O_NONBLOCK also.

    On the kernel side, we have:

    struct file *eventfd_fget(int fd);
    int eventfd_signal(struct file *file, unsigned int n);

    The eventfd_fget() should be called to get a struct file* from an eventfd fd
    (this is an fget() + check of f_op being an eventfd fops pointer).

    The kernel can then call eventfd_signal() every time it wants to post an event
    to userspace.  The eventfd_signal() function can be called from any context.
    An eventfd() simple test and bench is available here:

    http://www.xmailserver.org/eventfd-bench.c

    This is the eventfd-based version of pipetest-4 (pipe(2) based):

    http://www.xmailserver.org/pipetest-4.c

    Not that performance matters much in the eventfd case, but eventfd-bench
    shows almost as double as performance than pipetest-4.

Signed-off-by: Jeff Moyer <jmoyer@redhat.com>

diff --git a/fs/Makefile b/fs/Makefile
index 80f0076..e93f24f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-$(CONFIG_ANON_INODES)	+= anon_inodes.o
+obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 
 nfsd-$(CONFIG_NFSD)		:= nfsctl.o
diff --git a/fs/eventfd.c b/fs/eventfd.c
new file mode 100644
index 0000000..480e2b3
--- /dev/null
+++ b/fs/eventfd.c
@@ -0,0 +1,228 @@
+/*
+ *  fs/eventfd.c
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/anon_inodes.h>
+#include <linux/eventfd.h>
+
+struct eventfd_ctx {
+	spinlock_t lock;
+	wait_queue_head_t wqh;
+	/*
+	 * Every time that a write(2) is performed on an eventfd, the
+	 * value of the __u64 being written is added to "count" and a
+	 * wakeup is performed on "wqh". A read(2) will return the "count"
+	 * value to userspace, and will reset "count" to zero. The kernel
+	 * size eventfd_signal() also, adds to the "count" counter and
+	 * issue a wakeup.
+	 */
+	__u64 count;
+};
+
+/*
+ * Adds "n" to the eventfd counter "count". Returns "n" in case of
+ * success, or a value lower then "n" in case of coutner overflow.
+ * This function is supposed to be called by the kernel in paths
+ * that do not allow sleeping. In this function we allow the counter
+ * to reach the ULLONG_MAX value, and we signal this as overflow
+ * condition by returining a POLLERR to poll(2).
+ */
+int eventfd_signal(struct file *file, int n)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	unsigned long flags;
+
+	if (n < 0)
+		return -EINVAL;
+	spin_lock_irqsave(&ctx->lock, flags);
+	if (ULLONG_MAX - ctx->count < n)
+		n = (int) (ULLONG_MAX - ctx->count);
+	ctx->count += n;
+	if (waitqueue_active(&ctx->wqh))
+		wake_up_locked(&ctx->wqh);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	return n;
+}
+
+static int eventfd_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static unsigned int eventfd_poll(struct file *file, poll_table *wait)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	unsigned int events = 0;
+	unsigned long flags;
+
+	poll_wait(file, &ctx->wqh, wait);
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	if (ctx->count > 0)
+		events |= POLLIN;
+	if (ctx->count == ULLONG_MAX)
+		events |= POLLERR;
+	if (ULLONG_MAX - 1 > ctx->count)
+		events |= POLLOUT;
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	return events;
+}
+
+static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	ssize_t res;
+	__u64 ucnt;
+	DECLARE_WAITQUEUE(wait, current);
+
+	if (count < sizeof(ucnt))
+		return -EINVAL;
+	spin_lock_irq(&ctx->lock);
+	res = -EAGAIN;
+	ucnt = ctx->count;
+	if (ucnt > 0)
+		res = sizeof(ucnt);
+	else if (!(file->f_flags & O_NONBLOCK)) {
+		__add_wait_queue(&ctx->wqh, &wait);
+		for (res = 0;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if (ctx->count > 0) {
+				ucnt = ctx->count;
+				res = sizeof(ucnt);
+				break;
+			}
+			if (signal_pending(current)) {
+				res = -ERESTARTSYS;
+				break;
+			}
+			spin_unlock_irq(&ctx->lock);
+			schedule();
+			spin_lock_irq(&ctx->lock);
+		}
+		__remove_wait_queue(&ctx->wqh, &wait);
+		__set_current_state(TASK_RUNNING);
+	}
+	if (res > 0) {
+		ctx->count = 0;
+		if (waitqueue_active(&ctx->wqh))
+			wake_up_locked(&ctx->wqh);
+	}
+	spin_unlock_irq(&ctx->lock);
+	if (res > 0 && put_user(ucnt, (__u64 __user *) buf))
+		return -EFAULT;
+
+	return res;
+}
+
+static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
+			     loff_t *ppos)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	ssize_t res;
+	__u64 ucnt;
+	DECLARE_WAITQUEUE(wait, current);
+
+	if (count < sizeof(ucnt))
+		return -EINVAL;
+	if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
+		return -EFAULT;
+	if (ucnt == ULLONG_MAX)
+		return -EINVAL;
+	spin_lock_irq(&ctx->lock);
+	res = -EAGAIN;
+	if (ULLONG_MAX - ctx->count > ucnt)
+		res = sizeof(ucnt);
+	else if (!(file->f_flags & O_NONBLOCK)) {
+		__add_wait_queue(&ctx->wqh, &wait);
+		for (res = 0;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if (ULLONG_MAX - ctx->count > ucnt) {
+				res = sizeof(ucnt);
+				break;
+			}
+			if (signal_pending(current)) {
+				res = -ERESTARTSYS;
+				break;
+			}
+			spin_unlock_irq(&ctx->lock);
+			schedule();
+			spin_lock_irq(&ctx->lock);
+		}
+		__remove_wait_queue(&ctx->wqh, &wait);
+		__set_current_state(TASK_RUNNING);
+	}
+	if (res > 0) {
+		ctx->count += ucnt;
+		if (waitqueue_active(&ctx->wqh))
+			wake_up_locked(&ctx->wqh);
+	}
+	spin_unlock_irq(&ctx->lock);
+
+	return res;
+}
+
+static const struct file_operations eventfd_fops = {
+	.release	= eventfd_release,
+	.poll		= eventfd_poll,
+	.read		= eventfd_read,
+	.write		= eventfd_write,
+};
+
+struct file *eventfd_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+	if (file->f_op != &eventfd_fops) {
+		fput(file);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return file;
+}
+
+asmlinkage long sys_eventfd(unsigned int count)
+{
+	int error, fd;
+	struct eventfd_ctx *ctx;
+	struct file *file;
+	struct inode *inode;
+
+	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	init_waitqueue_head(&ctx->wqh);
+	spin_lock_init(&ctx->lock);
+	ctx->count = count;
+
+	/*
+	 * When we call this, the initialization must be complete, since
+	 * anon_inode_getfd() will install the fd.
+	 */
+	error = anon_inode_getfd(&fd, &inode, &file, "[eventfd]",
+				 &eventfd_fops, ctx);
+	if (!error)
+		return fd;
+
+	kfree(ctx);
+	return error;
+}
+
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
new file mode 100644
index 0000000..0d6ecc6
--- /dev/null
+++ b/include/linux/eventfd.h
@@ -0,0 +1,29 @@
+/*
+ *  include/linux/eventfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#ifndef _LINUX_EVENTFD_H
+#define _LINUX_EVENTFD_H
+
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_EVENTFD
+
+struct file *eventfd_fget(int fd);
+int eventfd_signal(struct file *file, int n);
+
+#else /* CONFIG_EVENTFD */
+
+#define eventfd_fget(fd) ERR_PTR(-ENOSYS)
+#define eventfd_signal(f, n) 0
+
+#endif /* CONFIG_EVENTFD */
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_EVENTFD_H */
+
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5a10f9c..0db3ebd 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -601,4 +601,5 @@ asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 asmlinkage long sys_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *cache);
 asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
+asmlinkage long sys_eventfd(unsigned int count);
 #endif
diff --git a/init/Kconfig b/init/Kconfig
index 9f130cc..fbab124 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -392,6 +392,16 @@ config EPOLL
 	  Disabling this option will cause the kernel to be built without
 	  support for epoll family of system calls.
 
+config EVENTFD
+	bool "Enable eventfd() system call" if EMBEDDED
+	depends on ANON_INODES
+	default y
+	help
+	  Enable the eventfd() system call that allows to receive both
+	  kernel notification (ie. KAIO) or userspace notifications.
+
+	  If unsure, say Y.
+
 config SHMEM
 	bool "Use full shmem filesystem" if EMBEDDED
 	default y
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 5c23f69..abfe96b 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -139,3 +139,6 @@ cond_syscall(sys_madvise);
 cond_syscall(sys_mremap);
 cond_syscall(sys_remap_file_pages);
 cond_syscall(compat_sys_move_pages);
+
+/* New file descriptors */
+cond_syscall(sys_eventfd);