Message-ID: <Pine.LNX.4.64.0703091535360.3761@alien.or.mcafeemobile.com>
Date:	Fri, 9 Mar 2007 15:41:12 -0800 (PST)
From:	Davide Libenzi <davidel@...ilserver.org>
To:	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
cc:	Andrew Morton <akpm@...ux-foundation.org>,
	Linus Torvalds <torvalds@...ux-foundation.org>
Subject: [patch 6/9] signalfd/timerfd v1 - timerfd core ...

This patch introduces a new system call for timers events delivered
though file descriptors. This allows timer event to be used with
standard POSIX poll(2), select(2) and read(2). As a consequence of
supporting the Linux f_op->poll subsystem, they can be used with
epoll(2) too.
The system call is defined as:

int timerfd(int ufd, int tmrtype, const struct timespec *utmr);

The "ufd" parameter allows for re-use (re-programming) of an existing
timerfd w/out going through the close/open cycle (same as signalfd).
If "ufd" is -1, s new file descriptor will be created, otherwise the
existing "ufd" will be re-programmed.
The "tmrtype" parameter allows to specify the timer type. The following
values are supported:

    TFD_TIMER_REL
        The time specified in the "utmr" parameter is a relative time
	from NOW.

    TFD_TIMER_ABS
        The timer specified in the "utmr" parameter is an absolute time.

    TFD_TIMER_SEQ
        The time specified in the "utmr" parameter is an interval at
	which a continuous clock rate will be generated.

The function returns the new (or same, in case "ufd" is a valid timerfd
descriptor) file, or -1 in case of error.
As stated before, the timerfd file descriptor supports poll(2), select(2)
and epoll(2). When a timer event happened on the timerfd, a POLLIN mask
will be returned.
The read(2) call can be used, and it will return a u32 variable holding
the number of "ticks" that happened on the interface since the last call
to read(2). The read(2) call supportes the O_NONBLOCK flag too, and EAGAIN
will be returned if no ticks happened.
A quick test program, shows timerfd working correctly on my amd64 box:

http://www.xmailserver.org/timerfd-test.c




Signed-off-by: Davide Libenzi <davidel@...ilserver.org>



- Davide



Index: linux-2.6.20.ep2/fs/timerfd.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6.20.ep2/fs/timerfd.c	2007-03-09 15:09:52.000000000 -0800
@@ -0,0 +1,263 @@
+/*
+ *  fs/timerfd.c
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@...ilserver.org>
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/jiffies.h>
+#include <linux/anon_inodes.h>
+#include <linux/timerfd.h>
+
+#include <asm/uaccess.h>
+
+
+
+struct timerfd_ctx {
+	struct hrtimer tmr;
+	ktime_t tval;
+	int tmrtype;
+	spinlock_t lock;
+	wait_queue_head_t wqh;
+	unsigned long ticks;
+};
+
+
+static int timerfd_tmrproc(struct hrtimer *htmr);
+static void timerfd_cleanup(struct timerfd_ctx *ctx);
+static int timerfd_close(struct inode *inode, struct file *file);
+static unsigned int timerfd_poll(struct file *file, poll_table *wait);
+static ssize_t timerfd_read(struct file *file, char *buf, size_t count, loff_t *ppos);
+
+
+
+static const struct file_operations timerfd_fops = {
+	.release	= timerfd_close,
+	.poll		= timerfd_poll,
+	.read		= timerfd_read,
+};
+static struct kmem_cache *timerfd_ctx_cachep;
+
+
+
+static int timerfd_tmrproc(struct hrtimer *htmr)
+{
+	struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
+	int rval = HRTIMER_NORESTART;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	ctx->ticks++;
+	__wake_up_locked(&ctx->wqh, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE);
+	if (ctx->tmrtype == TFD_TIMER_SEQ) {
+		hrtimer_forward(htmr, htmr->base->softirq_time, ctx->tval);
+		rval = HRTIMER_RESTART;
+	}
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	return rval;
+}
+
+/*
+ * Create a file descriptor that is associated with our signal
+ * state. We can pass it around to others if we want to, but
+ * it will always be _our_ signal state.
+ */
+asmlinkage long sys_timerfd(int ufd, int tmrtype, const struct timespec __user *utmr)
+{
+	int error;
+	struct timerfd_ctx *ctx;
+	struct file *file;
+	struct inode *inode;
+	ktime_t tval, tnow;
+	struct timespec ktmr, tmrnow;
+
+	error = -EFAULT;
+	if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
+		goto err_exit;
+
+	tval = timespec_to_ktime(ktmr);
+	error = -EINVAL;
+	switch (tmrtype) {
+	case TFD_TIMER_REL:
+	case TFD_TIMER_SEQ:
+		break;
+	case TFD_TIMER_ABS:
+		getnstimeofday(&tmrnow);
+		tnow = timespec_to_ktime(tmrnow);
+		if (ktime_to_ns(tval) <= ktime_to_ns(tnow))
+			goto err_exit;
+		tval = ktime_sub(tval, tnow);
+		break;
+	default:
+		goto err_exit;
+	}
+
+	if (ufd == -1) {
+		error = -ENOMEM;
+		ctx = kmem_cache_alloc(timerfd_ctx_cachep, GFP_KERNEL);
+		if (!ctx)
+			goto err_exit;
+
+		init_waitqueue_head(&ctx->wqh);
+		spin_lock_init(&ctx->lock);
+		ctx->ticks = 0;
+		ctx->tmrtype = tmrtype;
+		ctx->tval = tval;
+		hrtimer_init(&ctx->tmr, CLOCK_MONOTONIC, HRTIMER_REL);
+		ctx->tmr.expires = ctx->tval;
+		ctx->tmr.function = timerfd_tmrproc;
+
+		hrtimer_start(&ctx->tmr, ctx->tval, HRTIMER_REL);
+
+		/*
+		 * When we call this, the initialization must be complete, since
+		 * aino_getfd() will install the fd.
+		 */
+		error = aino_getfd(&ufd, &inode, &file, "[timerfd]",
+				   &timerfd_fops, ctx);
+		if (error)
+			goto err_fdalloc;
+	} else {
+		error = -EBADF;
+		file = fget(ufd);
+		if (!file)
+			goto err_exit;
+		ctx = file->private_data;
+		error = -EINVAL;
+		if (file->f_op != &timerfd_fops) {
+			fput(file);
+			goto err_exit;
+		}
+
+		/*
+		 * We need to stop the exiting timer before. We call
+		 * hrtimer_cancel() w/out holding our lock.
+		 */
+		spin_lock_irq(&ctx->lock);
+		while (hrtimer_active(&ctx->tmr)) {
+			spin_unlock_irq(&ctx->lock);
+			hrtimer_cancel(&ctx->tmr);
+			spin_lock_irq(&ctx->lock);
+		}
+		/*
+		 * Re-program the timer to the new value ...
+		 */
+		ctx->ticks = 0;
+		ctx->tmrtype = tmrtype;
+		ctx->tval = tval;
+		hrtimer_init(&ctx->tmr, CLOCK_MONOTONIC, HRTIMER_REL);
+		ctx->tmr.expires = ctx->tval;
+		ctx->tmr.function = timerfd_tmrproc;
+
+		hrtimer_start(&ctx->tmr, ctx->tval, HRTIMER_REL);
+
+		spin_unlock_irq(&ctx->lock);
+
+		fput(file);
+	}
+
+	return ufd;
+
+err_fdalloc:
+	timerfd_cleanup(ctx);
+err_exit:
+	return error;
+}
+
+
+static void timerfd_cleanup(struct timerfd_ctx *ctx)
+{
+	hrtimer_cancel(&ctx->tmr);
+	kmem_cache_free(timerfd_ctx_cachep, ctx);
+}
+
+
+static int timerfd_close(struct inode *inode, struct file *file)
+{
+	timerfd_cleanup(file->private_data);
+	return 0;
+}
+
+
+static unsigned int timerfd_poll(struct file *file, poll_table *wait)
+{
+	struct timerfd_ctx *ctx = file->private_data;
+
+	poll_wait(file, &ctx->wqh, wait);
+
+	return ctx->ticks ? POLLIN: 0;
+}
+
+
+static ssize_t timerfd_read(struct file *file, char *buf, size_t count, loff_t *ppos)
+{
+	struct timerfd_ctx *ctx = file->private_data;
+	ssize_t res;
+	u32 ticks;
+	DECLARE_WAITQUEUE(wait, current);
+
+	if (count < sizeof(ticks))
+		return -EINVAL;
+	spin_lock_irq(&ctx->lock);
+	res = -EAGAIN;
+	if ((ticks = (u32) ctx->ticks) == 0 &&
+	    !(file->f_flags & O_NONBLOCK)) {
+		__add_wait_queue(&ctx->wqh, &wait);
+		for (res = 0;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			if ((ticks = (u32) ctx->ticks) != 0) {
+				res = 0;
+				break;
+			}
+			if (signal_pending(current)) {
+				res = -EINTR;
+				break;
+			}
+			spin_unlock_irq(&ctx->lock);
+			schedule();
+			spin_lock_irq(&ctx->lock);
+		}
+		__remove_wait_queue(&ctx->wqh, &wait);
+		set_current_state(TASK_RUNNING);
+	}
+	if (ticks)
+		ctx->ticks = 0;
+	spin_unlock_irq(&ctx->lock);
+	if (ticks)
+		res = put_user(ticks, buf) ? -EFAULT: sizeof(ticks);
+	return res;
+}
+
+
+static int __init timerfd_init(void)
+{
+	timerfd_ctx_cachep = kmem_cache_create("timerfd_ctx_cache",
+						sizeof(struct timerfd_ctx),
+						0, SLAB_PANIC, NULL, NULL);
+	return 0;
+}
+
+
+static void __exit timerfd_exit(void)
+{
+	kmem_cache_destroy(timerfd_ctx_cachep);
+}
+
+module_init(timerfd_init);
+module_exit(timerfd_exit);
+
+MODULE_LICENSE("GPL");
Index: linux-2.6.20.ep2/include/linux/timerfd.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6.20.ep2/include/linux/timerfd.h	2007-03-09 10:56:08.000000000 -0800
@@ -0,0 +1,20 @@
+/*
+ *  include/linux/timerfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@...ilserver.org>
+ *
+ */
+
+#ifndef _LINUX_TIMERFD_H
+#define _LINUX_TIMERFD_H
+
+
+#define TFD_TIMER_REL 1
+#define TFD_TIMER_ABS 2
+#define TFD_TIMER_SEQ 3
+
+
+
+
+#endif /* _LINUX_TIMERFD_H */
+
Index: linux-2.6.20.ep2/fs/Makefile
===================================================================
--- linux-2.6.20.ep2.orig/fs/Makefile	2007-03-09 10:43:17.000000000 -0800
+++ linux-2.6.20.ep2/fs/Makefile	2007-03-09 10:56:08.000000000 -0800
@@ -11,7 +11,7 @@
 		attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o drop_caches.o splice.o sync.o utimes.o \
-		stack.o anon_inodes.o signalfd.o
+		stack.o anon_inodes.o signalfd.o timerfd.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o
Index: linux-2.6.20.ep2/include/linux/syscalls.h
===================================================================
--- linux-2.6.20.ep2.orig/include/linux/syscalls.h	2007-03-09 11:52:08.000000000 -0800
+++ linux-2.6.20.ep2/include/linux/syscalls.h	2007-03-09 11:52:29.000000000 -0800
@@ -603,6 +603,7 @@
 				    size_t len);
 asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache);
 asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask);
+asmlinkage long sys_timerfd(int ufd, int tmrtype, const struct timespec __user *utmr);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists