@@ -458,3 +458,4 @@
442 common mount_setattr sys_mount_setattr
443 common futex_wait sys_futex_wait
444 common futex_wake sys_futex_wake
+445 common futex_waitv sys_futex_waitv
@@ -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 445
+#define __NR_compat_syscalls 446
#endif
#define __ARCH_WANT_SYS_CLONE
@@ -897,6 +897,8 @@ __SYSCALL(__NR_mount_setattr, sys_mount_setattr)
__SYSCALL(__NR_futex_wait, sys_futex_wait)
#define __NR_futex_wake 444
__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_waitv 445
+__SYSCALL(__NR_futex_waitv, compat_sys_futex_waitv)
/*
* Please add new compat syscalls above this comment and update
@@ -449,3 +449,4 @@
442 i386 mount_setattr sys_mount_setattr
443 i386 futex_wait sys_futex_wait
444 i386 futex_wake sys_futex_wake
+445 i386 futex_waitv sys_futex_waitv compat_sys_futex_waitv
@@ -366,6 +366,7 @@
442 common mount_setattr sys_mount_setattr
443 common futex_wait sys_futex_wait
444 common futex_wake sys_futex_wake
+445 common futex_waitv sys_futex_waitv
#
# Due to a historical design error, certain syscalls are numbered differently
@@ -365,6 +365,12 @@ struct compat_robust_list_head {
compat_uptr_t list_op_pending;
};
+struct compat_futex_waitv {
+ compat_u64 val;
+ compat_uptr_t uaddr;
+ compat_uint_t flags;
+};
+
#ifdef CONFIG_COMPAT_OLD_SIGACTION
struct compat_old_sigaction {
compat_uptr_t sa_handler;
@@ -658,6 +664,9 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
asmlinkage long
compat_sys_futex_wait(void __user *uaddr, compat_u64 val, unsigned int flags,
struct __kernel_timespec __user *timo);
+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,
@@ -69,6 +69,7 @@ struct io_uring_params;
struct clone_args;
struct open_how;
struct mount_attr;
+struct futex_waitv;
#include <linux/types.h>
#include <linux/aio_abi.h>
@@ -624,6 +625,9 @@ asmlinkage long sys_futex_wait(void __user *uaddr, u64 val, unsigned int flags,
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,
@@ -870,8 +870,11 @@ __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 445
+#define __NR_syscalls 446
/*
* 32 bit systems traditionally used different
@@ -48,6 +48,20 @@
#define FUTEX_SHARED_FLAG 8
+#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
+ */
+struct futex_waitv {
+ __u64 val;
+ void __user *uaddr;
+ unsigned int flags;
+};
+
/*
* Support for robust futexes: the kernel cleans up held futexes at
* thread exit time.
@@ -82,6 +82,12 @@ 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 */
@@ -701,6 +707,177 @@ SYSCALL_DEFINE4(futex_wait, void __user *, uaddr, u64, val, unsigned int, flags,
return ksys_futex_wait(uaddr, val, flags, timo);
}
+#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 compat_futex_waitv waitv;
+ struct futex_bucket *bucket;
+ 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_waitv(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_waitv(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
@@ -154,6 +154,8 @@ COND_SYSCALL_COMPAT(get_robust_list);
COND_SYSCALL(futex_wait);
COND_SYSCALL_COMPAT(futex_wait);
COND_SYSCALL(futex_wake);
+COND_SYSCALL(futex_waitv);
+COND_SYSCALL_COMPAT(futex_waitv);
/* kernel/hrtimer.c */
@@ -870,8 +870,11 @@ __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 445
+#define __NR_syscalls 446
/*
* 32 bit systems traditionally used different
@@ -366,6 +366,7 @@
442 common mount_setattr sys_mount_setattr
443 common futex_wait sys_futex_wait
444 common futex_wake sys_futex_wake
+445 common futex_waitv sys_futex_waitv
#
# Due to a historical design error, certain syscalls are numbered differently
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 { __u64 val; void *uaddr; 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> --- arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/compat.h | 9 + include/linux/syscalls.h | 4 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/futex.h | 14 ++ kernel/futex2.c | 177 ++++++++++++++++++ kernel/sys_ni.c | 2 + tools/include/uapi/asm-generic/unistd.h | 5 +- .../arch/x86/entry/syscalls/syscall_64.tbl | 1 + 13 files changed, 221 insertions(+), 3 deletions(-)