6 files changed, 270 insertions, 0 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 39625da9e2d6..720c29d57a62 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-$(CONFIG_ANON_INODES)       += anon_inodes.o
 obj-$(CONFIG_SIGNALFD)          += signalfd.o
 obj-$(CONFIG_TIMERFD)           += timerfd.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 000000000000..480e2b3c4166
--- /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 000000000000..0d6ecc60b94d
--- /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 fc637be1d9cf..b02070eac422 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -607,6 +607,7 @@ asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct g
 asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask);
 asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
                             const struct itimerspec __user *utmr);
+asmlinkage long sys_eventfd(unsigned int count);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
diff --git a/init/Kconfig b/init/Kconfig
index 02c167de9646..4e009fde4b69 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -512,6 +512,16 @@ config TIMERFD
 
           If unsure, say Y.
 
+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 b18f62549515..b6d77a8a1ca9 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -145,3 +145,4 @@ cond_syscall(sys_ioprio_get);
 /* New file descriptors */
 cond_syscall(sys_signalfd);
 cond_syscall(sys_timerfd);
+cond_syscall(sys_eventfd);