futex: Provide FUTEX_LOCK_PI2 to support clock selection

The FUTEX_LOCK_PI futex operand uses a CLOCK_REALTIME based absolute
timeout since it was implemented, but it does not require that the
FUTEX_CLOCK_REALTIME flag is set, because that was introduced later.

In theory as none of the user space implementations can set the
FUTEX_CLOCK_REALTIME flag on this operand, it would be possible to
creatively abuse it and make the meaning invers, i.e. select CLOCK_REALTIME
when not set and CLOCK_MONOTONIC when set. But that's a nasty hackery.

Another option would be to have a new FUTEX_CLOCK_MONOTONIC flag only for
FUTEX_LOCK_PI, but that's also awkward because it does not allow libraries
to handle the timeout clock selection consistently.

So provide a new FUTEX_LOCK_PI2 operand which implements the timeout
semantics which the other operands use and leave FUTEX_LOCK_PI alone.
Reported-by: Kurt Kanzenbach <kurt@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210422194705.440773992@linutronix.de

include/uapi/linux/futex.h

@@ -21,6 +21,7 @@
 #define FUTEX_WAKE_BITSET	10
 #define FUTEX_WAIT_REQUEUE_PI	11
 #define FUTEX_CMP_REQUEUE_PI	12
+#define FUTEX_LOCK_PI2		13
 
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
@@ -32,6 +33,7 @@
 #define FUTEX_CMP_REQUEUE_PRIVATE (FUTEX_CMP_REQUEUE | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_OP_PRIVATE	(FUTEX_WAKE_OP | FUTEX_PRIVATE_FLAG)
 #define FUTEX_LOCK_PI_PRIVATE	(FUTEX_LOCK_PI | FUTEX_PRIVATE_FLAG)
+#define FUTEX_LOCK_PI2_PRIVATE	(FUTEX_LOCK_PI2 | FUTEX_PRIVATE_FLAG)
 #define FUTEX_UNLOCK_PI_PRIVATE	(FUTEX_UNLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE	(FUTEX_WAIT_BITSET | FUTEX_PRIVATE_FLAG)

kernel/futex.c

@@ -3707,12 +3707,14 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 	if (op & FUTEX_CLOCK_REALTIME) {
 		flags |= FLAGS_CLOCKRT;
-		if (cmd != FUTEX_WAIT_BITSET &&	cmd != FUTEX_WAIT_REQUEUE_PI)
+		if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI &&
+		    cmd != FUTEX_LOCK_PI2)
 			return -ENOSYS;
 	}
 
 	switch (cmd) {
 	case FUTEX_LOCK_PI:
+	case FUTEX_LOCK_PI2:
 	case FUTEX_UNLOCK_PI:
 	case FUTEX_TRYLOCK_PI:
 	case FUTEX_WAIT_REQUEUE_PI:
@@ -3740,6 +3742,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
 	case FUTEX_LOCK_PI:
 		flags |= FLAGS_CLOCKRT;
+		fallthrough;
+	case FUTEX_LOCK_PI2:
 		return futex_lock_pi(uaddr, flags, timeout, 0);
 	case FUTEX_UNLOCK_PI:
 		return futex_unlock_pi(uaddr, flags);
@@ -3760,6 +3764,7 @@ static __always_inline bool futex_cmd_has_timeout(u32 cmd)
 	switch (cmd) {
 	case FUTEX_WAIT:
 	case FUTEX_LOCK_PI:
+	case FUTEX_LOCK_PI2:
 	case FUTEX_WAIT_BITSET:
 	case FUTEX_WAIT_REQUEUE_PI:
 		return true;