futex2: Implement requeue operation

Implement requeue interface similarly to FUTEX_CMP_REQUEUE operation.
This is the syscall implemented by this patch:

futex_requeue(struct futex_requeue *uaddr1, struct futex_requeue *uaddr2,
	      unsigned int nr_wake, unsigned int nr_requeue,
	      u64 cmpval, unsigned int flags)

struct futex_requeue {
	void *uaddr;
	unsigned int flags;
};

If (uaddr1->uaddr == cmpval), wake at uaddr1->uaddr a nr_wake number of
waiters and then, remove a number of nr_requeue waiters at uaddr1->uaddr
and add them to uaddr2->uaddr list. Each uaddr has its own set of flags,
that must be defined at struct futex_requeue (such as size, shared, NUMA).
The flags argument of the syscall is there just for the sake of
extensibility, and right now it needs to be zero.

Return the number of the woken futexes + the number of requeued ones on
success, error code otherwise.

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

arch/arm/tools/syscall.tbl

@@ -463,3 +463,4 @@
 447	common	futex_wait			sys_futex_wait
 448	common	futex_wake			sys_futex_wake
 449	common  futex_waitv                     sys_futex_waitv
+450	common	futex_requeue			sys_futex_requeue

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		450
+#define __NR_compat_syscalls		451
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

arch/arm64/include/asm/unistd32.h

@@ -906,6 +906,8 @@ __SYSCALL(__NR_futex_wait, compat_sys_futex_wait)
 __SYSCALL(__NR_futex_wake, sys_futex_wake)
 #define __NR_futex_waitv 449
 __SYSCALL(__NR_futex_waitv, compat_sys_futex_waitv)
+#define __NR_futex_requeue 450
+__SYSCALL(__NR_futex_requeue, compat_sys_futex_requeue)
 
 /*
  * Please add new compat syscalls above this comment and update

arch/x86/entry/syscalls/syscall_32.tbl

@@ -454,3 +454,4 @@
 447	i386	futex_wait		sys_futex_wait			compat_sys_futex_wait
 448	i386	futex_wake		sys_futex_wake
 449	i386	futex_waitv		sys_futex_waitv			compat_sys_futex_waitv
+450	i386	futex_requeue		sys_futex_requeue		compat_sys_futex_requeue

arch/x86/entry/syscalls/syscall_64.tbl

@@ -371,6 +371,7 @@
 447	common	futex_wait		sys_futex_wait
 448	common	futex_wake		sys_futex_wake
 449	common	futex_waitv		sys_futex_waitv
+450	common	futex_requeue		sys_futex_requeue
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

include/linux/compat.h

@@ -374,6 +374,11 @@ struct compat_futex_waitv {
 	compat_uint_t flags;
 };
 
+struct compat_futex_requeue {
+	compat_uptr_t uaddr;
+	compat_uint_t flags;
+};
+
 #ifdef CONFIG_COMPAT_OLD_SIGACTION
 struct compat_old_sigaction {
 	compat_uptr_t			sa_handler;
@@ -706,6 +711,13 @@ 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);
 
+asmlinkage long compat_sys_futex_requeue(struct compat_futex_requeue *uaddr1,
+					 struct compat_futex_requeue *uaddr2,
+					 compat_uint_t nr_wake,
+					 compat_uint_t nr_requeue,
+					 compat_u64 cmpval,
+					 compat_uint_t flags);
+
 /* kernel/itimer.c */
 asmlinkage long compat_sys_getitimer(int which,
 				     struct old_itimerval32 __user *it);

include/linux/syscalls.h

@@ -72,6 +72,7 @@ struct mount_attr;
 struct landlock_ruleset_attr;
 enum landlock_rule_type;
 struct futex_waitv;
+struct futex_requeue;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -632,6 +633,10 @@ asmlinkage long sys_futex_wake(void __user *uaddr, unsigned int nr_wake,
 asmlinkage long sys_futex_waitv(struct futex_waitv __user *waiters,
 				unsigned int nr_futexes, unsigned int flags,
 				struct __kernel_timespec __user *timo);
+asmlinkage long sys_futex_requeue(struct futex_requeue __user *uaddr1,
+				  struct futex_requeue __user *uaddr2,
+				  unsigned int nr_wake, unsigned int nr_requeue,
+				  u64 cmpval, unsigned int flags);
 
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,

include/uapi/asm-generic/unistd.h

@@ -881,8 +881,11 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 #define __NR_futex_waitv 449
 __SC_COMP(__NR_futex_waitv, sys_futex_waitv, compat_sys_futex_waitv)
 
+#define __NR_futex_requeue 450
+__SC_COMP(__NR_futex_requeue, sys_futex_requeue, compat_sys_futex_requeue)
+
 #undef __NR_syscalls
-#define __NR_syscalls 450
+#define __NR_syscalls 451
 
 /*
  * 32 bit systems traditionally used different

include/uapi/linux/futex.h

@@ -62,6 +62,16 @@ struct futex_waitv {
 	unsigned int flags;
 };
 
+/**
+ * struct futex_requeue - Define an address and its flags for requeue operation
+ * @uaddr: User address of one of the requeue arguments
+ * @flags: Flags for this address
+ */
+struct futex_requeue {
+	void __user *uaddr;
+	unsigned int flags;
+};
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.

kernel/futex2.c

@@ -972,6 +972,214 @@ SYSCALL_DEFINE3(futex_wake, void __user *, uaddr, unsigned int, nr_wake,
 	return ret;
 }
 
+static void futex_double_unlock(struct futex_bucket *b1, struct futex_bucket *b2)
+{
+	spin_unlock(&b1->lock);
+	if (b1 != b2)
+		spin_unlock(&b2->lock);
+}
+
+static inline int __futex_requeue(struct futex_requeue rq1,
+				  struct futex_requeue rq2, unsigned int nr_wake,
+				  unsigned int nr_requeue, u64 cmpval)
+{
+	struct futex_waiter w1, w2, *aux, *tmp;
+	bool retry = false;
+	struct futex_bucket *b1, *b2;
+	DEFINE_WAKE_Q(wake_q);
+	u32 uval;
+	int ret;
+	bool shared1 = (rq1.flags  & FUTEX_SHARED_FLAG) ? true : false;
+	bool shared2 = (rq2.flags  & FUTEX_SHARED_FLAG) ? true : false;
+
+	b1 = futex_get_bucket(rq1.uaddr, &w1.key, shared1);
+	if (IS_ERR(b1))
+		return PTR_ERR(b1);
+
+	b2 = futex_get_bucket(rq2.uaddr, &w2.key, shared2);
+	if (IS_ERR(b2))
+		return PTR_ERR(b2);
+
+retry:
+	if (shared1 && retry) {
+		b1 = futex_get_bucket(rq1.uaddr, &w1.key, shared1);
+		if (IS_ERR(b1))
+			return PTR_ERR(b1);
+	}
+
+	if (shared2 && retry) {
+		b2 = futex_get_bucket(rq2.uaddr, &w2.key, shared2);
+		if (IS_ERR(b2))
+			return PTR_ERR(b2);
+	}
+
+	bucket_inc_waiters(b2);
+	/*
+	 * To ensure the locks are taken in the same order for all threads (and
+	 * thus avoiding deadlocks), take the "smaller" one first
+	 */
+	if (b1 <= b2) {
+		spin_lock(&b1->lock);
+		if (b1 < b2)
+			spin_lock_nested(&b2->lock, SINGLE_DEPTH_NESTING);
+	} else {
+		spin_lock(&b2->lock);
+		spin_lock_nested(&b1->lock, SINGLE_DEPTH_NESTING);
+	}
+
+	ret = futex_get_user(&uval, rq1.uaddr);
+
+	if (unlikely(ret)) {
+		futex_double_unlock(b1, b2);
+		if (__get_user(uval, (u32 __user *)rq1.uaddr))
+			return -EFAULT;
+
+		bucket_dec_waiters(b2);
+		retry = true;
+		goto retry;
+	}
+
+	if (uval != cmpval) {
+		futex_double_unlock(b1, b2);
+
+		bucket_dec_waiters(b2);
+		return -EAGAIN;
+	}
+
+	list_for_each_entry_safe(aux, tmp, &b1->list, list) {
+		if (futex_match(w1.key, aux->key)) {
+			if (ret < nr_wake) {
+				futex_mark_wake(aux, b1, &wake_q);
+				ret++;
+				continue;
+			}
+
+			if (ret >= nr_wake + nr_requeue)
+				break;
+
+			aux->key.pointer = w2.key.pointer;
+			aux->key.index = w2.key.index;
+			aux->key.offset = w2.key.offset;
+
+			if (b1 != b2) {
+				list_del_init(&aux->list);
+				bucket_dec_waiters(b1);
+
+				list_add_tail(&aux->list, &b2->list);
+				bucket_inc_waiters(b2);
+			}
+			ret++;
+		}
+	}
+
+	futex_double_unlock(b1, b2);
+	wake_up_q(&wake_q);
+	bucket_dec_waiters(b2);
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static int compat_futex_parse_requeue(struct futex_requeue *rq,
+				      struct compat_futex_requeue __user *uaddr)
+{
+	struct compat_futex_requeue tmp;
+
+	if (copy_from_user(&tmp, uaddr, sizeof(tmp)))
+		return -EFAULT;
+
+	if (tmp.flags & ~FUTEXV_WAITER_MASK ||
+	    (tmp.flags & FUTEX_SIZE_MASK) != FUTEX_32)
+		return -EINVAL;
+
+	rq->uaddr = compat_ptr(tmp.uaddr);
+	rq->flags = tmp.flags;
+
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE6(futex_requeue, struct compat_futex_requeue __user *, uaddr1,
+		       struct compat_futex_requeue __user *, uaddr2,
+		       unsigned int, nr_wake, unsigned int, nr_requeue,
+		       compat_u64, cmpval, unsigned int, flags)
+{
+	struct futex_requeue rq1, rq2;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	ret = compat_futex_parse_requeue(&rq1, uaddr1);
+	if (ret)
+		return ret;
+
+	ret = compat_futex_parse_requeue(&rq2, uaddr2);
+	if (ret)
+		return ret;
+
+	return __futex_requeue(rq1, rq2, nr_wake, nr_requeue, cmpval);
+}
+#endif
+
+/**
+ * futex_parse_requeue - Copy a user struct futex_requeue and check it's flags
+ * @rq:    Kernel struct
+ * @uaddr: Address of user struct
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int futex_parse_requeue(struct futex_requeue *rq,
+			       struct futex_requeue __user *uaddr)
+{
+	if (copy_from_user(rq, uaddr, sizeof(*rq)))
+		return -EFAULT;
+
+	if (rq->flags & ~FUTEXV_WAITER_MASK ||
+	    (rq->flags & FUTEX_SIZE_MASK) != FUTEX_32)
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * sys_futex_requeue - Wake futexes at uaddr1 and requeue from uaddr1 to uaddr2
+ * @uaddr1:	Address of futexes to be waken/dequeued
+ * @uaddr2:	Address for the futexes to be enqueued
+ * @nr_wake:	Number of futexes waiting in uaddr1 to be woken up
+ * @nr_requeue: Number of futexes to be requeued from uaddr1 to uaddr2
+ * @cmpval:	Expected value at uaddr1
+ * @flags:	Reserved flags arg for requeue operation expansion. Must be 0.
+ *
+ * If (uaddr1->uaddr == cmpval), wake at uaddr1->uaddr a nr_wake number of
+ * waiters and then, remove a number of nr_requeue waiters at uaddr1->uaddr
+ * and add then to uaddr2->uaddr list. Each uaddr has its own set of flags,
+ * that must be defined at struct futex_requeue (such as size, shared, NUMA).
+ *
+ * Return the number of the woken futexes + the number of requeued ones on
+ * success, error code otherwise.
+ */
+SYSCALL_DEFINE6(futex_requeue, struct futex_requeue __user *, uaddr1,
+		struct futex_requeue __user *, uaddr2,
+		unsigned int, nr_wake, unsigned int, nr_requeue,
+		u64, cmpval, unsigned int, flags)
+{
+	struct futex_requeue rq1, rq2;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	ret = futex_parse_requeue(&rq1, uaddr1);
+	if (ret)
+		return ret;
+
+	ret = futex_parse_requeue(&rq2, uaddr2);
+	if (ret)
+		return ret;
+
+	return __futex_requeue(rq1, rq2, nr_wake, nr_requeue, cmpval);
+}
+
 static int __init futex2_init(void)
 {
 	int i;

kernel/sys_ni.c

@@ -157,6 +157,8 @@ COND_SYSCALL_COMPAT(futex_wait);
 COND_SYSCALL(futex_wake);
 COND_SYSCALL(futex_waitv);
 COND_SYSCALL_COMPAT(futex_waitv);
+COND_SYSCALL(futex_requeue);
+COND_SYSCALL_COMPAT(futex_requeue);
 
 /* kernel/hrtimer.c */
 

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

@@ -371,6 +371,7 @@
 447	common  futex_wait              sys_futex_wait
 448	common  futex_wake              sys_futex_wake
 449	common  futex_waitv             sys_futex_waitv
+450	common  futex_requeue		sys_futex_requeue
 
 #
 # Due to a historical design error, certain syscalls are numbered differently