time/posix-timers: Move the compat copyouts to the nanosleep implementations

Turn restart_block.nanosleep.{rmtp,compat_rmtp} into a tagged union (kind =
1 -> native, kind = 2 -> compat, kind = 0 -> nothing) and make the places
doing actual copyout handle compat as well as native (that will become a
helper in the next commit).  Result: compat wrappers, messing with
reassignments, etc. are gone.

[ tglx: Folded in a variant of Peter Zijlstras enum patch ]
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170607084241.28657-6-viro@ZenIV.linux.org.uk

include/linux/posix-timers.h

@@ -110,8 +110,6 @@ void posix_cpu_timers_exit_group(struct task_struct *task);
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 			   u64 *newval, u64 *oldval);
 
-long clock_nanosleep_restart(struct restart_block *restart_block);
-
 void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new);
 
 void posixtimer_rearm(struct siginfo *info);

include/linux/restart_block.h

@@ -11,6 +11,14 @@ struct timespec;
 struct compat_timespec;
 struct pollfd;
 
+enum timespec_type {
+	TT_NONE		= 0,
+	TT_NATIVE	= 1,
+#ifdef CONFIG_COMPAT
+	TT_COMPAT	= 2,
+#endif
+};
+
 /*
  * System call restart block.
  */
@@ -29,10 +37,13 @@ struct restart_block {
 		/* For nanosleep */
 		struct {
 			clockid_t clockid;
+			enum timespec_type type;
+			union {
 				struct timespec __user *rmtp;
 #ifdef CONFIG_COMPAT
 				struct compat_timespec __user *compat_rmtp;
 #endif
+			};
 			u64 expires;
 		} nanosleep;
 		/* For poll */

kernel/compat.c

@@ -213,82 +213,6 @@ int compat_convert_timespec(struct timespec __user **kts,
 	return 0;
 }
 
-static long compat_nanosleep_restart(struct restart_block *restart)
-{
-	struct compat_timespec __user *rmtp;
-	struct timespec rmt;
-	mm_segment_t oldfs;
-	long ret;
-
-	restart->nanosleep.rmtp = (struct timespec __user *) &rmt;
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = hrtimer_nanosleep_restart(restart);
-	set_fs(oldfs);
-
-	if (ret == -ERESTART_RESTARTBLOCK) {
-		rmtp = restart->nanosleep.compat_rmtp;
-
-		if (rmtp && compat_put_timespec(&rmt, rmtp))
-			return -EFAULT;
-	}
-
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
-		       struct compat_timespec __user *, rmtp)
-{
-	struct timespec tu, rmt;
-	struct timespec64 tu64;
-	mm_segment_t oldfs;
-	long ret;
-
-	if (compat_get_timespec(&tu, rqtp))
-		return -EFAULT;
-
-	tu64 = timespec_to_timespec64(tu);
-	if (!timespec64_valid(&tu64))
-		return -EINVAL;
-
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	current->restart_block.nanosleep.rmtp =
-				rmtp ? (struct timespec __user *)&rmt : NULL;
-	ret = hrtimer_nanosleep(&tu64, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
-	set_fs(oldfs);
-
-	/*
-	 * hrtimer_nanosleep() can only return 0 or
-	 * -ERESTART_RESTARTBLOCK here because:
-	 *
-	 * - we call it with HRTIMER_MODE_REL and therefor exclude the
-	 *   -ERESTARTNOHAND return path.
-	 *
-	 * - we supply the rmtp argument from the task stack (due to
-	 *   the necessary compat conversion. So the update cannot
-	 *   fail, which excludes the -EFAULT return path as well. If
-	 *   it fails nevertheless we have a bigger problem and wont
-	 *   reach this place anymore.
-	 *
-	 * - if the return value is 0, we do not have to update rmtp
-	 *    because there is no remaining time.
-	 *
-	 * We check for -ERESTART_RESTARTBLOCK nevertheless if the
-	 * core implementation decides to return random nonsense.
-	 */
-	if (ret == -ERESTART_RESTARTBLOCK) {
-		struct restart_block *restart = &current->restart_block;
-
-		restart->fn = compat_nanosleep_restart;
-		restart->nanosleep.compat_rmtp = rmtp;
-
-		if (rmtp && compat_put_timespec(&rmt, rmtp))
-			return -EFAULT;
-	}
-	return ret;
-}
-
 static inline long get_compat_itimerval(struct itimerval *o,
 		struct compat_itimerval __user *i)
 {
@@ -821,61 +745,6 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock,
 	return err;
 }
 
-static long compat_clock_nanosleep_restart(struct restart_block *restart)
-{
-	long err;
-	mm_segment_t oldfs;
-	struct timespec tu;
-	struct compat_timespec __user *rmtp = restart->nanosleep.compat_rmtp;
-
-	restart->nanosleep.rmtp = (struct timespec __user *) &tu;
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	err = clock_nanosleep_restart(restart);
-	set_fs(oldfs);
-
-	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-	    compat_put_timespec(&tu, rmtp))
-		return -EFAULT;
-
-	if (err == -ERESTART_RESTARTBLOCK) {
-		restart->fn = compat_clock_nanosleep_restart;
-		restart->nanosleep.compat_rmtp = rmtp;
-	}
-	return err;
-}
-
-COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
-		       struct compat_timespec __user *, rqtp,
-		       struct compat_timespec __user *, rmtp)
-{
-	long err;
-	mm_segment_t oldfs;
-	struct timespec in, out;
-	struct restart_block *restart;
-
-	if (compat_get_timespec(&in, rqtp))
-		return -EFAULT;
-
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	err = sys_clock_nanosleep(which_clock, flags,
-				  (struct timespec __user *) &in,
-				  (struct timespec __user *) &out);
-	set_fs(oldfs);
-
-	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-	    compat_put_timespec(&out, rmtp))
-		return -EFAULT;
-
-	if (err == -ERESTART_RESTARTBLOCK) {
-		restart = &current->restart_block;
-		restart->fn = compat_clock_nanosleep_restart;
-		restart->nanosleep.compat_rmtp = rmtp;
-	}
-	return err;
-}
-
 /*
  * We currently only need the following fields from the sigevent
  * structure: sigev_value, sigev_signo, sig_notify and (sometimes

kernel/time/alarmtimer.c

@@ -27,6 +27,7 @@
 #include <linux/posix-timers.h>
 #include <linux/workqueue.h>
 #include <linux/freezer.h>
+#include <linux/compat.h>
 
 #include "posix-timers.h"
 
@@ -691,7 +692,7 @@ static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm,
 static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
 				enum alarmtimer_type type)
 {
-	struct timespec __user *rmtp;
+	struct restart_block *restart;
 	alarm->data = (void *)current;
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -709,8 +710,8 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
 
 	if (freezing(current))
 		alarmtimer_freezerset(absexp, type);
-	rmtp = current->restart_block.nanosleep.rmtp;
-	if (rmtp) {
+	restart = &current->restart_block;
+	if (restart->nanosleep.type != TT_NONE) {
 		struct timespec rmt;
 		ktime_t rem;
 
@@ -720,7 +721,14 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp,
 			return 0;
 		rmt = ktime_to_timespec(rem);
 
-		if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
+#ifdef CONFIG_COMPAT
+		if (restart->nanosleep.type == TT_COMPAT) {
+			if (compat_put_timespec(&rmt,
+						restart->nanosleep.compat_rmtp))
+				return -EFAULT;
+		} else
+#endif
+		if (copy_to_user(restart->nanosleep.rmtp, &rmt, sizeof(rmt)))
 			return -EFAULT;
 	}
 	return -ERESTART_RESTARTBLOCK;

kernel/time/hrtimer.c

@@ -51,6 +51,7 @@
 #include <linux/sched/debug.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 
@@ -1441,7 +1442,8 @@ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
 {
-	struct timespec __user *rmtp;
+	struct restart_block *restart;
+
 	hrtimer_init_sleeper(t, current);
 
 	do {
@@ -1461,15 +1463,23 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	if (!t->task)
 		return 0;
 
-	rmtp = current->restart_block.nanosleep.rmtp;
-	if (rmtp) {
-		struct timespec rmt;
+	restart = &current->restart_block;
+	if (restart->nanosleep.type != TT_NONE) {
 		ktime_t rem = hrtimer_expires_remaining(&t->timer);
+		struct timespec rmt;
+
 		if (rem <= 0)
 			return 0;
 		rmt = ktime_to_timespec(rem);
 
-		if (copy_to_user(rmtp, &rmt, sizeof(*rmtp)))
+#ifdef CONFIG_COMPAT
+		if (restart->nanosleep.type == TT_COMPAT) {
+			if (compat_put_timespec(&rmt,
+						restart->nanosleep.compat_rmtp))
+				return -EFAULT;
+		} else
+#endif
+		if (copy_to_user(restart->nanosleep.rmtp, &rmt, sizeof(rmt)))
 			return -EFAULT;
 	}
 	return -ERESTART_RESTARTBLOCK;
@@ -1535,10 +1545,32 @@ SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 	if (!timespec64_valid(&tu64))
 		return -EINVAL;
 
+	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 	return hrtimer_nanosleep(&tu64, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
+#ifdef CONFIG_COMPAT
+
+COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp,
+		       struct compat_timespec __user *, rmtp)
+{
+	struct timespec64 tu64;
+	struct timespec tu;
+
+	if (compat_get_timespec(&tu, rqtp))
+		return -EFAULT;
+
+	tu64 = timespec_to_timespec64(tu);
+	if (!timespec64_valid(&tu64))
+		return -EINVAL;
+
+	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
+	current->restart_block.nanosleep.compat_rmtp = rmtp;
+	return hrtimer_nanosleep(&tu64, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+}
+#endif
+
 /*
  * Functions related to boot-time initialization:
  */

kernel/time/posix-cpu-timers.c

@@ -12,6 +12,7 @@
 #include <trace/events/timer.h>
 #include <linux/tick.h>
 #include <linux/workqueue.h>
+#include <linux/compat.h>
 
 #include "posix-timers.h"
 
@@ -1243,10 +1244,9 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 	timer.it_process = current;
 	if (!error) {
 		static struct itimerspec64 zero_it;
-		struct restart_block *restart = &current->restart_block;
-		struct timespec __user *rmtp;
+		struct restart_block *restart;
 
-		memset(&it, 0, sizeof it);
+		memset(&it, 0, sizeof(it));
 		it.it_value = *rqtp;
 
 		spin_lock_irq(&timer.it_lock);
@@ -1311,12 +1311,20 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		/*
 		 * Report back to the user the time still remaining.
 		 */
-		rmtp = restart->nanosleep.rmtp;
-		if (rmtp) {
+		restart = &current->restart_block;
+		if (restart->nanosleep.type != TT_NONE) {
 			struct timespec ts;
 
 			ts = timespec64_to_timespec(it.it_value);
-			if (copy_to_user(rmtp, &ts, sizeof(*rmtp)))
+#ifdef CONFIG_COMPAT
+			if (restart->nanosleep.type == TT_COMPAT) {
+				if (compat_put_timespec(&ts,
+						restart->nanosleep.compat_rmtp))
+					return -EFAULT;
+			} else
+#endif
+			if (copy_to_user(restart->nanosleep.rmtp, &ts,
+					sizeof(ts)))
 				return -EFAULT;
 		}
 		restart->nanosleep.expires = timespec64_to_ns(rqtp);

kernel/time/posix-stubs.c

@@ -17,6 +17,7 @@
 #include <linux/ktime.h>
 #include <linux/timekeeping.h>
 #include <linux/posix-timers.h>
+#include <linux/compat.h>
 
 asmlinkage long sys_ni_posix_timers(void)
 {
@@ -110,6 +111,11 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	case CLOCK_REALTIME:
 	case CLOCK_MONOTONIC:
 	case CLOCK_BOOTTIME:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
 		return -EFAULT;
 	t64 = timespec_to_timespec64(t);
@@ -117,18 +123,41 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 	return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ?
 				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
 				 which_clock);
-	default:
-		return -EINVAL;
-	}
 }
 
 #ifdef CONFIG_COMPAT
-long clock_nanosleep_restart(struct restart_block *restart_block)
+COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
+		       struct compat_timespec __user *, rqtp,
+		       struct compat_timespec __user *, rmtp)
 {
-	return hrtimer_nanosleep_restart(restart_block);
+	struct timespec64 t64;
+	struct timespec t;
+
+	switch (which_clock) {
+	case CLOCK_REALTIME:
+	case CLOCK_MONOTONIC:
+	case CLOCK_BOOTTIME:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (compat_get_timespec(&t, rqtp))
+		return -EFAULT;
+	t64 = timespec_to_timespec64(t);
+	if (!timespec64_valid(&t64))
+		return -EINVAL;
+	if (flags & TIMER_ABSTIME)
+		rmtp = NULL;
+	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
+	current->restart_block.nanosleep.compat_rmtp = rmtp;
+	return hrtimer_nanosleep(&t64, flags & TIMER_ABSTIME ?
+				 HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
+				 which_clock);
 }
 #endif

kernel/time/posix-timers.c

@@ -49,6 +49,7 @@
 #include <linux/workqueue.h>
 #include <linux/export.h>
 #include <linux/hashtable.h>
+#include <linux/compat.h>
 
 #include "timekeeping.h"
 #include "posix-timers.h"
@@ -1069,25 +1070,40 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		return -EINVAL;
 	if (flags & TIMER_ABSTIME)
 		rmtp = NULL;
+	current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
 	current->restart_block.nanosleep.rmtp = rmtp;
 
 	return kc->nsleep(which_clock, flags, &t64);
 }
 
-/*
- * This will restart clock_nanosleep. This is required only by
- * compat_clock_nanosleep_restart for now.
- */
-long clock_nanosleep_restart(struct restart_block *restart_block)
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
+		       struct compat_timespec __user *, rqtp,
+		       struct compat_timespec __user *, rmtp)
 {
-	clockid_t which_clock = restart_block->nanosleep.clockid;
 	const struct k_clock *kc = clockid_to_kclock(which_clock);
+	struct timespec64 t64;
+	struct timespec t;
 
-	if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
+	if (!kc)
 		return -EINVAL;
+	if (!kc->nsleep)
+		return -ENANOSLEEP_NOTSUP;
+
+	if (compat_get_timespec(&t, rqtp))
+		return -EFAULT;
 
-	return kc->nsleep_restart(restart_block);
+	t64 = timespec_to_timespec64(t);
+	if (!timespec64_valid(&t64))
+		return -EINVAL;
+	if (flags & TIMER_ABSTIME)
+		rmtp = NULL;
+	current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE;
+	current->restart_block.nanosleep.compat_rmtp = rmtp;
+
+	return kc->nsleep(which_clock, flags, &t64);
 }
+#endif
 
 static const struct k_clock clock_realtime = {
 	.clock_getres		= posix_get_hrtimer_res,