eventfd.c 5.08 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46
/*
 *  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 {
	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;
47
	spin_lock_irqsave(&ctx->wqh.lock, flags);
48 49 50 51 52
	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);
53
	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

	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);

72
	spin_lock_irqsave(&ctx->wqh.lock, flags);
73 74 75 76 77 78
	if (ctx->count > 0)
		events |= POLLIN;
	if (ctx->count == ULLONG_MAX)
		events |= POLLERR;
	if (ULLONG_MAX - 1 > ctx->count)
		events |= POLLOUT;
79
	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
80 81 82 83 84 85 86 87 88 89 90 91 92 93

	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;
94
	spin_lock_irq(&ctx->wqh.lock);
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
	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;
			}
112
			spin_unlock_irq(&ctx->wqh.lock);
113
			schedule();
114
			spin_lock_irq(&ctx->wqh.lock);
115 116 117 118 119 120 121 122 123
		}
		__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);
	}
124
	spin_unlock_irq(&ctx->wqh.lock);
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
	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;
145
	spin_lock_irq(&ctx->wqh.lock);
146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
	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;
			}
161
			spin_unlock_irq(&ctx->wqh.lock);
162
			schedule();
163
			spin_lock_irq(&ctx->wqh.lock);
164 165 166 167 168 169 170 171 172
		}
		__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);
	}
173
	spin_unlock_irq(&ctx->wqh.lock);
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226

	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);
	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;
}