futex: Add sys_futex_requeue()

Finish off the 'simple' futex2 syscall group by adding
sys_futex_requeue(). Unlike sys_futex_{wait,wake}() its arguments are
too numerous to fit into a regular syscall. As such, use struct
futex_waitv to pass the 'source' and 'destination' futexes to the
syscall.

This syscall implements what was previously known as FUTEX_CMP_REQUEUE
and uses {val, uaddr, flags} for source and {uaddr, flags} for
destination.

This design explicitly allows requeueing between different types of
futex by having a different flags word per uaddr.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20230921105248.511860556@noisy.programming.kicks-ass.net

arch/alpha/kernel/syscalls/syscall.tbl

@@ -494,3 +494,4 @@
 562	common	fchmodat2			sys_fchmodat2
 563	common	futex_wake			sys_futex_wake
 564	common	futex_wait			sys_futex_wait
+565	common	futex_requeue			sys_futex_requeue

arch/arm/tools/syscall.tbl

@@ -468,3 +468,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/arm64/include/asm/unistd.h

@@ -39,7 +39,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		456
+#define __NR_compat_syscalls		457
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -915,6 +915,8 @@ __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
 __SYSCALL(__NR_futex_wake, sys_futex_wake)
 #define __NR_futex_wait 455
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/ia64/kernel/syscalls/syscall.tbl

@@ -375,3 +375,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/m68k/kernel/syscalls/syscall.tbl

@@ -454,3 +454,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -460,3 +460,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -393,3 +393,4 @@
 452	n32	fchmodat2			sys_fchmodat2
 454	n32	futex_wake			sys_futex_wake
 455	n32	futex_wait			sys_futex_wait
+456	n32	futex_requeue			sys_futex_requeue

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -369,3 +369,4 @@
 452	n64	fchmodat2			sys_fchmodat2
 454	n64	futex_wake			sys_futex_wake
 455	n64	futex_wait			sys_futex_wait
+456	n64	futex_requeue			sys_futex_requeue

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -442,3 +442,4 @@
 452	o32	fchmodat2			sys_fchmodat2
 454	o32	futex_wake			sys_futex_wake
 455	o32	futex_wait			sys_futex_wait
+456	o32	futex_requeue			sys_futex_requeue

arch/parisc/kernel/syscalls/syscall.tbl

@@ -453,3 +453,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -541,3 +541,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/s390/kernel/syscalls/syscall.tbl

@@ -457,3 +457,4 @@
 452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
 454  common	futex_wake		sys_futex_wake			sys_futex_wake
 455  common	futex_wait		sys_futex_wait			sys_futex_wait
+456  common	futex_requeue		sys_futex_requeue			sys_futex_requeue

arch/sh/kernel/syscalls/syscall.tbl

@@ -457,3 +457,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/sparc/kernel/syscalls/syscall.tbl

@@ -500,3 +500,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

arch/x86/entry/syscalls/syscall_32.tbl

@@ -459,3 +459,4 @@
 452	i386	fchmodat2		sys_fchmodat2
 454	i386	futex_wake		sys_futex_wake
 455	i386	futex_wait		sys_futex_wait
+456	i386	futex_requeue		sys_futex_requeue

arch/x86/entry/syscalls/syscall_64.tbl

@@ -377,6 +377,7 @@
 453	64	map_shadow_stack	sys_map_shadow_stack
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
+456	common	futex_requeue		sys_futex_requeue
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -425,3 +425,4 @@
 452	common	fchmodat2			sys_fchmodat2
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
+456	common	futex_requeue			sys_futex_requeue

include/linux/syscalls.h

@@ -556,6 +556,9 @@ asmlinkage long sys_futex_wait(void __user *uaddr, unsigned long val, unsigned l
 			       unsigned int flags, struct __kernel_timespec __user *timespec,
 			       clockid_t clockid);
 
+asmlinkage long sys_futex_requeue(struct futex_waitv __user *waiters,
+				  unsigned int flags, int nr_wake, int nr_requeue);
+
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
 asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp,

include/uapi/asm-generic/unistd.h

@@ -826,9 +826,11 @@ __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
 __SYSCALL(__NR_futex_wake, sys_futex_wake)
 #define __NR_futex_wait 455
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 #undef __NR_syscalls
-#define __NR_syscalls 456
+#define __NR_syscalls 457
 
 /*
  * 32 bit systems traditionally used different

kernel/futex/syscalls.c

@@ -396,6 +396,44 @@ SYSCALL_DEFINE6(futex_wait,
 	return ret;
 }
 
+/*
+ * sys_futex_requeue - Requeue a waiter from one futex to another
+ * @waiters:	array describing the source and destination futex
+ * @flags:	unused
+ * @nr_wake:	number of futexes to wake
+ * @nr_requeue:	number of futexes to requeue
+ *
+ * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_requeue,
+		struct futex_waitv __user *, waiters,
+		unsigned int, flags,
+		int, nr_wake,
+		int, nr_requeue)
+{
+	struct futex_vector futexes[2];
+	u32 cmpval;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (!waiters)
+		return -EINVAL;
+
+	ret = futex_parse_waitv(futexes, waiters, 2);
+	if (ret)
+		return ret;
+
+	cmpval = futexes[0].w.val;
+
+	return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
+			     u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags,
+			     nr_wake, nr_requeue, &cmpval, 0);
+}
+
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE2(set_robust_list,
 		struct compat_robust_list_head __user *, head,

kernel/sys_ni.c

@@ -89,6 +89,7 @@ COND_SYSCALL_COMPAT(get_robust_list);
 COND_SYSCALL(futex_waitv);
 COND_SYSCALL(futex_wake);
 COND_SYSCALL(futex_wait);
+COND_SYSCALL(futex_requeue);
 COND_SYSCALL(kexec_load);
 COND_SYSCALL_COMPAT(kexec_load);
 COND_SYSCALL(init_module);