futex2: Implement vectorized wait

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 *timo)

struct futex_waitv {
	void *uaddr;
	unsigned int val;
	unsigned int flags;
};

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. *timo is an optional
timeout value for the operation. The flags argument of the syscall
should be used solely for specifying the timeout as realtime, if needed.
Flags for shared futexes, sizes, etc. should be used on the individual
flags of each waiter.

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

Signed-off-by: André Almeida <andrealmeid@collabora.com>

Rebased-by: Joshua Ashton <joshua@froggi.es>

arch/arm/tools/syscall.tbl

@@ -462,3 +462,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 447	common	futex_wait			sys_futex_wait
 448	common	futex_wake			sys_futex_wake
+449	common  futex_waitv                     sys_futex_waitv

arch/arm64/include/asm/unistd.h

@@ -38,7 +38,7 @@
 #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		449
+#define __NR_compat_syscalls		450
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/x86/entry/syscalls/syscall_32.tbl

@@ -453,3 +453,4 @@
 446	i386	landlock_restrict_self	sys_landlock_restrict_self
 447	i386	futex_wait		sys_futex_wait
 448	i386	futex_wake		sys_futex_wake
+449	i386	futex_waitv		sys_futex_waitv			compat_sys_futex_waitv

arch/x86/entry/syscalls/syscall_64.tbl

@@ -370,6 +370,7 @@
 446	common	landlock_restrict_self	sys_landlock_restrict_self
 447	common	futex_wait		sys_futex_wait
 448	common	futex_wake		sys_futex_wake
+449	common	futex_waitv		sys_futex_waitv
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

include/linux/compat.h

@@ -368,6 +368,12 @@ struct compat_robust_list_head {
 	compat_uptr_t			list_op_pending;
 };
 
+struct compat_futex_waitv {
+	compat_uptr_t uaddr;
+	compat_uint_t val;
+	compat_uint_t flags;
+};
+
 #ifdef CONFIG_COMPAT_OLD_SIGACTION
 struct compat_old_sigaction {
 	compat_uptr_t			sa_handler;
@@ -692,6 +698,11 @@ asmlinkage long
 compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			   compat_size_t __user *len_ptr);
 
+/* kernel/futex2.c */
+asmlinkage long compat_sys_futex_waitv(struct compat_futex_waitv *waiters,
+				       compat_uint_t nr_futexes, compat_uint_t flags,
+				       struct __kernel_timespec __user *timo);
+
 /* kernel/itimer.c */
 asmlinkage long compat_sys_getitimer(int which,
 				     struct old_itimerval32 __user *it);

include/linux/syscalls.h

@@ -71,6 +71,7 @@ struct open_how;
 struct mount_attr;
 struct landlock_ruleset_attr;
 enum landlock_rule_type;
+struct futex_waitv;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -629,6 +630,9 @@ asmlinkage long sys_futex_wait(void __user *uaddr, unsigned int val,
 			       struct __kernel_timespec __user *timo);
 asmlinkage long sys_futex_wake(void __user *uaddr, unsigned int nr_wake,
 			       unsigned int flags);
+asmlinkage long sys_futex_waitv(struct futex_waitv __user *waiters,
+				unsigned int nr_futexes, unsigned int flags,
+				struct __kernel_timespec __user *timo);
 
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,

include/uapi/asm-generic/unistd.h

@@ -878,8 +878,11 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_wake 444
 __SYSCALL(__NR_futex_wake, sys_futex_wake)
 
+#define __NR_futex_waitv 445
+__SC_COMP(__NR_futex_waitv, sys_futex_waitv, compat_sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/futex.h

@@ -48,6 +48,20 @@
 
 #define FUTEX_SHARED_FLAG 8
 
+#define FUTEX_WAITV_MAX 128
+
+/**
+ * struct futex_waitv - A waiter for vectorized wait
+ * @uaddr: User address to wait on
+ * @val:   Expected value at uaddr
+ * @flags: Flags for this waiter
+ */
+struct futex_waitv {
+	void __user *uaddr;
+	unsigned int val;
+	unsigned int flags;
+};
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.

kernel/futex2.c

@@ -83,6 +83,12 @@ struct futex_bucket {
 /* Mask for futex2 flag operations */
 #define FUTEX2_MASK (FUTEX_SIZE_MASK | FUTEX_CLOCK_REALTIME | FUTEX_SHARED_FLAG)
 
+/* Mask for sys_futex_waitv flag */
+#define FUTEXV_MASK (FUTEX_CLOCK_REALTIME)
+
+/* Mask for each futex in futex_waitv list */
+#define FUTEXV_WAITER_MASK (FUTEX_SIZE_MASK | FUTEX_SHARED_FLAG)
+
 #define is_object_shared ((futexv->objects[i].flags & FUTEX_SHARED_FLAG) ? true : false)
 
 #define FUT_OFF_INODE    1 /* We set bit 0 if key has a reference on inode */
@@ -704,6 +710,177 @@ SYSCALL_DEFINE4(futex_wait, void __user *, uaddr, unsigned int, val,
 	return futex_set_timer_and_wait(futexv, 1, timo, flags);
 }
 
+#ifdef CONFIG_COMPAT
+/**
+ * compat_futex_parse_waitv - Parse a waitv array from userspace
+ * @futexv:	Kernel side list of waiters to be filled
+ * @uwaitv:     Userspace list to be parsed
+ * @nr_futexes: Length of futexv
+ *
+ * Return: Error code on failure, pointer to a prepared futexv otherwise
+ */
+static int compat_futex_parse_waitv(struct futex_waiter_head *futexv,
+				    struct compat_futex_waitv __user *uwaitv,
+				    unsigned int nr_futexes)
+{
+	struct futex_bucket *bucket;
+	struct compat_futex_waitv waitv;
+	unsigned int i;
+
+	for (i = 0; i < nr_futexes; i++) {
+		if (copy_from_user(&waitv, &uwaitv[i], sizeof(waitv)))
+			return -EFAULT;
+
+		if ((waitv.flags & ~FUTEXV_WAITER_MASK) ||
+		    (waitv.flags & FUTEX_SIZE_MASK) != FUTEX_32)
+			return -EINVAL;
+
+		futexv->objects[i].key.pointer = 0;
+		futexv->objects[i].flags  = waitv.flags;
+		futexv->objects[i].uaddr  = compat_ptr(waitv.uaddr);
+		futexv->objects[i].val    = waitv.val;
+		futexv->objects[i].index  = i;
+
+		bucket = futex_get_bucket(compat_ptr(waitv.uaddr),
+					  &futexv->objects[i].key,
+					  is_object_shared);
+
+		if (IS_ERR(bucket))
+			return PTR_ERR(bucket);
+
+		futexv->objects[i].bucket = bucket;
+
+		INIT_LIST_HEAD(&futexv->objects[i].list);
+	}
+
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE4(futex_waitv, struct compat_futex_waitv __user *, waiters,
+		       unsigned int, nr_futexes, unsigned int, flags,
+		       struct __kernel_timespec __user *, timo)
+{
+	struct futex_waiter_head *futexv;
+	int ret;
+
+	if (flags & ~FUTEXV_MASK)
+		return -EINVAL;
+
+	if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
+		return -EINVAL;
+
+	futexv = kmalloc((sizeof(struct futex_waiter) * nr_futexes) +
+			 sizeof(*futexv), GFP_KERNEL);
+	if (!futexv)
+		return -ENOMEM;
+
+	futexv->hint = false;
+	futexv->task = current;
+
+	ret = compat_futex_parse_waitv(futexv, waiters, nr_futexes);
+
+	if (!ret)
+		ret = futex_set_timer_and_wait(futexv, nr_futexes, timo, flags);
+
+	kfree(futexv);
+
+	return ret;
+}
+#endif
+
+/**
+ * futex_parse_waitv - Parse a waitv array from userspace
+ * @futexv:	Kernel side list of waiters to be filled
+ * @uwaitv:     Userspace list to be parsed
+ * @nr_futexes: Length of futexv
+ *
+ * Return: Error code on failure, pointer to a prepared futexv otherwise
+ */
+static int futex_parse_waitv(struct futex_waiter_head *futexv,
+			     struct futex_waitv __user *uwaitv,
+			     unsigned int nr_futexes)
+{
+	struct futex_bucket *bucket;
+	struct futex_waitv waitv;
+	unsigned int i;
+
+	for (i = 0; i < nr_futexes; i++) {
+		if (copy_from_user(&waitv, &uwaitv[i], sizeof(waitv)))
+			return -EFAULT;
+
+		if ((waitv.flags & ~FUTEXV_WAITER_MASK) ||
+		    (waitv.flags & FUTEX_SIZE_MASK) != FUTEX_32)
+			return -EINVAL;
+
+		futexv->objects[i].key.pointer = 0;
+		futexv->objects[i].flags  = waitv.flags;
+		futexv->objects[i].uaddr  = waitv.uaddr;
+		futexv->objects[i].val    = waitv.val;
+		futexv->objects[i].index  = i;
+
+		bucket = futex_get_bucket(waitv.uaddr, &futexv->objects[i].key,
+					  is_object_shared);
+
+		if (IS_ERR(bucket))
+			return PTR_ERR(bucket);
+
+		futexv->objects[i].bucket = bucket;
+
+		INIT_LIST_HEAD(&futexv->objects[i].list);
+	}
+
+	return 0;
+}
+
+/**
+ * sys_futex_waitv - Wait on a list of futexes
+ * @waiters:    List of futexes to wait on
+ * @nr_futexes: Length of futexv
+ * @flags:      Flag for timeout (monotonic/realtime)
+ * @timo:	Optional absolute timeout.
+ *
+ * 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. *timo is an optional timeout value for the
+ * operation. Each waiter has individual flags. The `flags` argument for the
+ * syscall should be used solely for specifying the timeout as realtime, if
+ * needed. Flags for shared futexes, sizes, etc. should be used on the
+ * individual flags of each waiter.
+ *
+ * Returns the array index of one of the awaken futexes. There's no given
+ * information of how many were awakened, or any particular attribute of it (if
+ * it's the first awakened, if it is of the smaller index...).
+ */
+SYSCALL_DEFINE4(futex_waitv, struct futex_waitv __user *, waiters,
+		unsigned int, nr_futexes, unsigned int, flags,
+		struct __kernel_timespec __user *, timo)
+{
+	struct futex_waiter_head *futexv;
+	int ret;
+
+	if (flags & ~FUTEXV_MASK)
+		return -EINVAL;
+
+	if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
+		return -EINVAL;
+
+	futexv = kmalloc((sizeof(struct futex_waiter) * nr_futexes) +
+			 sizeof(*futexv), GFP_KERNEL);
+	if (!futexv)
+		return -ENOMEM;
+
+	futexv->hint = false;
+	futexv->task = current;
+
+	ret = futex_parse_waitv(futexv, waiters, nr_futexes);
+	if (!ret)
+		ret = futex_set_timer_and_wait(futexv, nr_futexes, timo, flags);
+
+	kfree(futexv);
+
+	return ret;
+}
+
 /**
  * futex_get_parent - For a given futex in a futexv list, get a pointer to the futexv
  * @waiter: Address of futex in the list

kernel/sys_ni.c

@@ -154,6 +154,7 @@ COND_SYSCALL_COMPAT(get_robust_list);
 /* kernel/futex2.c */
 COND_SYSCALL(futex_wait);
 COND_SYSCALL(futex_wake);
+COND_SYSCALL(futex_waitv);
 
 /* kernel/hrtimer.c */
 

tools/include/uapi/asm-generic/unistd.h

@@ -878,8 +878,11 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_wake 444
 __SYSCALL(__NR_futex_wake, sys_futex_wake)
 
+#define __NR_futex_waitv 445
+__SC_COMP(__NR_futex_waitv, sys_futex_waitv, compat_sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -370,6 +370,7 @@
 446	common	landlock_restrict_self	sys_landlock_restrict_self
 447	common  futex_wait              sys_futex_wait
 448	common  futex_wake              sys_futex_wake
+449	common	futex_waitv		sys_futex_waitv
 
 #
 # Due to a historical design error, certain syscalls are numbered differently