futex: Implement sys_futex_waitv()

Add support to wait on multiple futexes. This is the interface
implemented by this syscall:

futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes,
	    unsigned int flags, struct timespec *timeout, clockid_t clockid)

struct futex_waitv {
	__u64 val;
	__u64 uaddr;
	__u32 flags;
	__u32 __reserved;
};

Given an array of struct futex_waitv, wait on each uaddr. The thread
wakes if a futex_wake() is performed at any uaddr. The syscall returns
immediately if any waiter has *uaddr != val. *timeout is an optional
absolute timeout value for the operation. This syscall supports only
64bit sized timeout structs. The flags argument of the syscall should be
empty, but it can be used for future extensions. Flags for shared
futexes, sizes, etc. should be used on the individual flags of each
waiter.

__reserved is used for explicit padding and should be 0, but it might be
used for future extensions. If the userspace uses 32-bit pointers, it
should make sure to explicitly cast it when assigning to waitv::uaddr.

Returns the array index of one of the woken futexes. There’s no given
information of how many were woken, or any particular attribute of it
(if it’s the first woken, if it is of the smaller index...).

Signed-off-by: André Almeida <andrealmeid@collabora.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210923171111.300673-17-andrealmeid@collabora.com

3 files changed, 34 insertions, 1 deletions

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 25979682ade5..528a478dbda8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -58,6 +58,7 @@ struct mq_attr;
 struct compat_stat;
 struct old_timeval32;
 struct robust_list_head;
+struct futex_waitv;
 struct getcpu_cache;
 struct old_linux_dirent;
 struct perf_event_attr;
@@ -623,6 +624,10 @@ asmlinkage long sys_get_robust_list(int pid,
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 
+asmlinkage long sys_futex_waitv(struct futex_waitv *waiters,
+				unsigned int nr_futexes, unsigned int flags,
+				struct __kernel_timespec __user *timeout, clockid_t clockid);
+
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1c5fb86d455a..4557a8b6086f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index 235e5b2facaa..71a5df8d2689 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -44,6 +44,31 @@
 					 FUTEX_PRIVATE_FLAG)
 
 /*
+ * Flags to specify the bit length of the futex word for futex2 syscalls.
+ * Currently, only 32 is supported.
+ */
+#define FUTEX_32		2
+
+/*
+ * Max numbers of elements in a futex_waitv array
+ */
+#define FUTEX_WAITV_MAX		128
+
+/**
+ * struct futex_waitv - A waiter for vectorized wait
+ * @val:	Expected value at uaddr
+ * @uaddr:	User address to wait on
+ * @flags:	Flags for this waiter
+ * @__reserved:	Reserved member to preserve data alignment. Should be 0.
+ */
+struct futex_waitv {
+	__u64 val;
+	__u64 uaddr;
+	__u32 flags;
+	__u32 __reserved;
+};
+
+/*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
  */