timerfd: new timerfd API

This is the new timerfd API as it is implemented by the following patch:

int timerfd_create(int clockid, int flags);
int timerfd_settime(int ufd, int flags,
		    const struct itimerspec *utmr,
		    struct itimerspec *otmr);
int timerfd_gettime(int ufd, struct itimerspec *otmr);

The timerfd_create() API creates an un-programmed timerfd fd.  The "clockid"
parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME.

The timerfd_settime() API give new settings by the timerfd fd, by optionally
retrieving the previous expiration time (in case the "otmr" parameter is not
NULL).

The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit
is set in the "flags" parameter.  Otherwise it's a relative time.

The timerfd_gettime() API returns the next expiration time of the timer, or
{0, 0} if the timerfd has not been set yet.

Like the previous timerfd API implementation, read(2) and poll(2) are
supported (with the same interface).  Here's a simple test program I used to
exercise the new timerfd APIs:

http://www.xmailserver.org/timerfd-test2.c

[akpm@linux-foundation.org: coding-style cleanups]
[akpm@linux-foundation.org: fix ia64 build]
[akpm@linux-foundation.org: fix m68k build]
[akpm@linux-foundation.org: fix mips build]
[akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds]
[heiko.carstens@de.ibm.com: fix s390]
[akpm@linux-foundation.org: fix powerpc build]
[akpm@linux-foundation.org: fix sparc64 more]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 138 insertions, 69 deletions

diff --git a/fs/timerfd.c b/fs/timerfd.c
index 61983f3b107c..10c80b59ec4b 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -25,13 +25,15 @@ struct timerfd_ctx {
 	struct hrtimer tmr;
 	ktime_t tintv;
 	wait_queue_head_t wqh;
+	u64 ticks;
 	int expired;
+	int clockid;
 };
 
 /*
  * This gets called when the timer event triggers. We set the "expired"
  * flag, but we do not re-arm the timer (in case it's necessary,
- * tintv.tv64 != 0) until the timer is read.
+ * tintv.tv64 != 0) until the timer is accessed.
  */
 static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 {
@@ -40,13 +42,24 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	ctx->expired = 1;
+	ctx->ticks++;
 	wake_up_locked(&ctx->wqh);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
 	return HRTIMER_NORESTART;
 }
 
-static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags,
+static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
+{
+	ktime_t now, remaining;
+
+	now = ctx->tmr.base->get_time();
+	remaining = ktime_sub(ctx->tmr.expires, now);
+
+	return remaining.tv64 < 0 ? ktime_set(0, 0): remaining;
+}
+
+static void timerfd_setup(struct timerfd_ctx *ctx, int flags,
 			  const struct itimerspec *ktmr)
 {
 	enum hrtimer_mode htmode;
@@ -57,8 +70,9 @@ static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags,
 
 	texp = timespec_to_ktime(ktmr->it_value);
 	ctx->expired = 0;
+	ctx->ticks = 0;
 	ctx->tintv = timespec_to_ktime(ktmr->it_interval);
-	hrtimer_init(&ctx->tmr, clockid, htmode);
+	hrtimer_init(&ctx->tmr, ctx->clockid, htmode);
 	ctx->tmr.expires = texp;
 	ctx->tmr.function = timerfd_tmrproc;
 	if (texp.tv64 != 0)
@@ -83,7 +97,7 @@ static unsigned int timerfd_poll(struct file *file, poll_table *wait)
 	poll_wait(file, &ctx->wqh, wait);
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	if (ctx->expired)
+	if (ctx->ticks)
 		events |= POLLIN;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
@@ -102,11 +116,11 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
 		return -EINVAL;
 	spin_lock_irq(&ctx->wqh.lock);
 	res = -EAGAIN;
-	if (!ctx->expired && !(file->f_flags & O_NONBLOCK)) {
+	if (!ctx->ticks && !(file->f_flags & O_NONBLOCK)) {
 		__add_wait_queue(&ctx->wqh, &wait);
 		for (res = 0;;) {
 			set_current_state(TASK_INTERRUPTIBLE);
-			if (ctx->expired) {
+			if (ctx->ticks) {
 				res = 0;
 				break;
 			}
@@ -121,22 +135,21 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
 		__remove_wait_queue(&ctx->wqh, &wait);
 		__set_current_state(TASK_RUNNING);
 	}
-	if (ctx->expired) {
-		ctx->expired = 0;
-		if (ctx->tintv.tv64 != 0) {
+	if (ctx->ticks) {
+		ticks = ctx->ticks;
+		if (ctx->expired && ctx->tintv.tv64) {
 			/*
 			 * If tintv.tv64 != 0, this is a periodic timer that
 			 * needs to be re-armed. We avoid doing it in the timer
 			 * callback to avoid DoS attacks specifying a very
 			 * short timer period.
 			 */
-			ticks = (u64)
-				hrtimer_forward(&ctx->tmr,
-						hrtimer_cb_get_time(&ctx->tmr),
-						ctx->tintv);
+			ticks += hrtimer_forward_now(&ctx->tmr,
+						     ctx->tintv) - 1;
 			hrtimer_restart(&ctx->tmr);
-		} else
-			ticks = 1;
+		}
+		ctx->expired = 0;
+		ctx->ticks = 0;
 	}
 	spin_unlock_irq(&ctx->wqh.lock);
 	if (ticks)
@@ -150,76 +163,132 @@ static const struct file_operations timerfd_fops = {
 	.read		= timerfd_read,
 };
 
-asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
-			    const struct itimerspec __user *utmr)
+static struct file *timerfd_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+	if (file->f_op != &timerfd_fops) {
+		fput(file);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return file;
+}
+
+asmlinkage long sys_timerfd_create(int clockid, int flags)
 {
-	int error;
+	int error, ufd;
 	struct timerfd_ctx *ctx;
 	struct file *file;
 	struct inode *inode;
-	struct itimerspec ktmr;
-
-	if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
-		return -EFAULT;
 
+	if (flags)
+		return -EINVAL;
 	if (clockid != CLOCK_MONOTONIC &&
 	    clockid != CLOCK_REALTIME)
 		return -EINVAL;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	init_waitqueue_head(&ctx->wqh);
+	ctx->clockid = clockid;
+	hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
+
+	error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]",
+				 &timerfd_fops, ctx);
+	if (error) {
+		kfree(ctx);
+		return error;
+	}
+
+	return ufd;
+}
+
+asmlinkage long sys_timerfd_settime(int ufd, int flags,
+				    const struct itimerspec __user *utmr,
+				    struct itimerspec __user *otmr)
+{
+	struct file *file;
+	struct timerfd_ctx *ctx;
+	struct itimerspec ktmr, kotmr;
+
+	if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
+		return -EFAULT;
+
 	if (!timespec_valid(&ktmr.it_value) ||
 	    !timespec_valid(&ktmr.it_interval))
 		return -EINVAL;
 
-	if (ufd == -1) {
-		ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
-		if (!ctx)
-			return -ENOMEM;
-
-		init_waitqueue_head(&ctx->wqh);
-
-		timerfd_setup(ctx, clockid, flags, &ktmr);
-
-		/*
-		 * When we call this, the initialization must be complete, since
-		 * anon_inode_getfd() will install the fd.
-		 */
-		error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]",
-					 &timerfd_fops, ctx);
-		if (error)
-			goto err_tmrcancel;
-	} else {
-		file = fget(ufd);
-		if (!file)
-			return -EBADF;
-		ctx = file->private_data;
-		if (file->f_op != &timerfd_fops) {
-			fput(file);
-			return -EINVAL;
-		}
-		/*
-		 * We need to stop the existing timer before reprogramming
-		 * it to the new values.
-		 */
-		for (;;) {
-			spin_lock_irq(&ctx->wqh.lock);
-			if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
-				break;
-			spin_unlock_irq(&ctx->wqh.lock);
-			cpu_relax();
-		}
-		/*
-		 * Re-program the timer to the new value ...
-		 */
-		timerfd_setup(ctx, clockid, flags, &ktmr);
+	file = timerfd_fget(ufd);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+	ctx = file->private_data;
 
+	/*
+	 * We need to stop the existing timer before reprogramming
+	 * it to the new values.
+	 */
+	for (;;) {
+		spin_lock_irq(&ctx->wqh.lock);
+		if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
+			break;
 		spin_unlock_irq(&ctx->wqh.lock);
-		fput(file);
+		cpu_relax();
 	}
 
-	return ufd;
+	/*
+	 * If the timer is expired and it's periodic, we need to advance it
+	 * because the caller may want to know the previous expiration time.
+	 * We do not update "ticks" and "expired" since the timer will be
+	 * re-programmed again in the following timerfd_setup() call.
+	 */
+	if (ctx->expired && ctx->tintv.tv64)
+		hrtimer_forward_now(&ctx->tmr, ctx->tintv);
 
-err_tmrcancel:
-	hrtimer_cancel(&ctx->tmr);
-	kfree(ctx);
-	return error;
+	kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
+	kotmr.it_interval = ktime_to_timespec(ctx->tintv);
+
+	/*
+	 * Re-program the timer to the new value ...
+	 */
+	timerfd_setup(ctx, flags, &ktmr);
+
+	spin_unlock_irq(&ctx->wqh.lock);
+	fput(file);
+	if (otmr && copy_to_user(otmr, &kotmr, sizeof(kotmr)))
+		return -EFAULT;
+
+	return 0;
+}
+
+asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr)
+{
+	struct file *file;
+	struct timerfd_ctx *ctx;
+	struct itimerspec kotmr;
+
+	file = timerfd_fget(ufd);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+	ctx = file->private_data;
+
+	spin_lock_irq(&ctx->wqh.lock);
+	if (ctx->expired && ctx->tintv.tv64) {
+		ctx->expired = 0;
+		ctx->ticks +=
+			hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1;
+		hrtimer_restart(&ctx->tmr);
+	}
+	kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
+	kotmr.it_interval = ktime_to_timespec(ctx->tintv);
+	spin_unlock_irq(&ctx->wqh.lock);
+	fput(file);
+
+	return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0;
 }