To complement sys_futex_waitv() add sys_futex_wake(). This syscall
implements what was previously known as FUTEX_WAKE_BITSET except it
uses 'unsigned long' for the bitmask and takes FUTEX2 flags.

The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      |    1 
 arch/arm/tools/syscall.tbl                  |    1 
 arch/arm64/include/asm/unistd.h             |    2 -
 arch/arm64/include/asm/unistd32.h           |    2 +
 arch/ia64/kernel/syscalls/syscall.tbl       |    1 
 arch/m68k/kernel/syscalls/syscall.tbl       |    1 
 arch/microblaze/kernel/syscalls/syscall.tbl |    1 
 arch/mips/kernel/syscalls/syscall_n32.tbl   |    1 
 arch/mips/kernel/syscalls/syscall_n64.tbl   |    1 
 arch/mips/kernel/syscalls/syscall_o32.tbl   |    1 
 arch/parisc/kernel/syscalls/syscall.tbl     |    1 
 arch/powerpc/kernel/syscalls/syscall.tbl    |    1 
 arch/s390/kernel/syscalls/syscall.tbl       |    1 
 arch/sh/kernel/syscalls/syscall.tbl         |    1 
 arch/sparc/kernel/syscalls/syscall.tbl      |    1 
 arch/x86/entry/syscalls/syscall_32.tbl      |    1 
 arch/x86/entry/syscalls/syscall_64.tbl      |    1 
 arch/xtensa/kernel/syscalls/syscall.tbl     |    1 
 include/linux/syscalls.h                    |    3 ++
 include/uapi/asm-generic/unistd.h           |    5 ++--
 kernel/futex/syscalls.c                     |   30 ++++++++++++++++++++++++++++
 kernel/sys_ni.c                             |    1 
 22 files changed, 56 insertions(+), 3 deletions(-)

--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -491,3 +491,4 @@
 559	common  futex_waitv                     sys_futex_waitv
 560	common	set_mempolicy_home_node		sys_ni_syscall
 561	common	cachestat			sys_cachestat
+562	common	futex_wake			sys_futex_wake
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -465,3 +465,4 @@
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/arm64/include/asm/unistd.h
+++ b/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		452
+#define __NR_compat_syscalls		453
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -909,6 +909,8 @@ __SYSCALL(__NR_futex_waitv, sys_futex_wa
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
+#define __NR_futex_wake 452
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
 
 /*
  * Please add new compat syscalls above this comment and update
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -372,3 +372,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -457,3 +457,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -390,3 +390,4 @@
 449	n32	futex_waitv			sys_futex_waitv
 450	n32	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n32	cachestat			sys_cachestat
+452	n32	futex_wake			sys_futex_wake
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -366,3 +366,4 @@
 449	n64	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n64	cachestat			sys_cachestat
+452	n64	futex_wake			sys_futex_wake
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -439,3 +439,4 @@
 449	o32	futex_waitv			sys_futex_waitv
 450	o32	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	o32	cachestat			sys_cachestat
+452	o32	futex_wake			sys_futex_wake
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -450,3 +450,4 @@
 449	common	futex_waitv			sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -538,3 +538,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
 449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
 451  common	cachestat		sys_cachestat			sys_cachestat
+452  common	futex_wake		sys_futex_wake			sys_futex_wake
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -497,3 +497,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -456,3 +456,4 @@
 449	i386	futex_waitv		sys_futex_waitv
 450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	i386	cachestat		sys_cachestat
+452	i386	futex_wake		sys_futex_wake
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -373,6 +373,7 @@
 449	common	futex_waitv		sys_futex_waitv
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	cachestat		sys_cachestat
+452	common	futex_wake		sys_futex_wake
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -422,3 +422,4 @@
 449	common  futex_waitv                     sys_futex_waitv
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
+452	common	futex_wake			sys_futex_wake
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -563,6 +563,9 @@ asmlinkage long sys_set_robust_list(stru
 asmlinkage long sys_futex_waitv(struct futex_waitv *waiters,
 				unsigned int nr_futexes, unsigned int flags,
 				struct __kernel_timespec __user *timeout, clockid_t clockid);
+
+asmlinkage long sys_futex_wake(void __user *uaddr, unsigned long mask, int nr, unsigned int flags);
+
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);
 asmlinkage long sys_nanosleep_time32(struct old_timespec32 __user *rqtp,
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -816,12 +816,13 @@ __SYSCALL(__NR_process_mrelease, sys_pro
 __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
-
 #define __NR_cachestat 451
 __SYSCALL(__NR_cachestat, sys_cachestat)
+#define __NR_futex_wake 452
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
 
 #undef __NR_syscalls
-#define __NR_syscalls 452
+#define __NR_syscalls 453
 
 /*
  * 32 bit systems traditionally used different
--- a/kernel/futex/syscalls.c
+++ b/kernel/futex/syscalls.c
@@ -306,6 +306,36 @@ SYSCALL_DEFINE5(futex_waitv, struct fute
 	return ret;
 }
 
+/*
+ * sys_futex_wake - Wake a number of futexes
+ * @uaddr:	Address of the futex(es) to wake
+ * @mask:	bitmask
+ * @nr:		Number of the futexes to wake
+ * @flags:	FUTEX2 flags
+ *
+ * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_wake,
+		void __user *, uaddr,
+		unsigned long, mask,
+		int, nr,
+		unsigned int, flags)
+{
+	if (flags & ~FUTEX2_VALID_MASK)
+		return -EINVAL;
+
+	flags = futex2_to_flags(flags);
+	if (!futex_flags_valid(flags))
+		return -EINVAL;
+
+	if (!futex_validate_input(flags, mask))
+		return -EINVAL;
+
+	return futex_wake(uaddr, flags, nr, mask);
+}
+
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE2(set_robust_list,
 		struct compat_robust_list_head __user *, head,
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -87,6 +87,7 @@ COND_SYSCALL_COMPAT(set_robust_list);
 COND_SYSCALL(get_robust_list);
 COND_SYSCALL_COMPAT(get_robust_list);
 COND_SYSCALL(futex_waitv);
+COND_SYSCALL(futex_wake);
 COND_SYSCALL(kexec_load);
 COND_SYSCALL_COMPAT(kexec_load);
 COND_SYSCALL(init_module);

Hi Peter,

Em 07/08/2023 09:18, Peter Zijlstra escreveu:
> To complement sys_futex_waitv() add sys_futex_wake(). This syscall
> implements what was previously known as FUTEX_WAKE_BITSET except it
> uses 'unsigned long' for the bitmask and takes FUTEX2 flags.
> 
> The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
> ---

[...]

> +/*
> + * sys_futex_wake - Wake a number of futexes
> + * @uaddr:	Address of the futex(es) to wake
> + * @mask:	bitmask
> + * @nr:		Number of the futexes to wake
> + * @flags:	FUTEX2 flags
> + *
> + * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
> + * futex2 family of calls.
> + */
> +
> +SYSCALL_DEFINE4(futex_wake,
> +		void __user *, uaddr,
> +		unsigned long, mask,
> +		int, nr,
> +		unsigned int, flags)
> +{

Do you think we could have a

	if (!nr)
		return 0;

here? Otherwise, calling futex_wake(&f, 0, flags) will wake 1 futex (if 
available), which is a strange undocumented behavior in my opinion.

> +	if (flags & ~FUTEX2_VALID_MASK)
> +		return -EINVAL;
> +
> +	flags = futex2_to_flags(flags);
> +	if (!futex_flags_valid(flags))
> +		return -EINVAL;
> +
> +	if (!futex_validate_input(flags, mask))
> +		return -EINVAL;
> +
> +	return futex_wake(uaddr, flags, nr, mask);
> +}
> +
>   #ifdef CONFIG_COMPAT
>   COMPAT_SYSCALL_DEFINE2(set_robust_list,
>   		struct compat_robust_list_head __user *, head,
> --- a/kernel/sys_ni.c
> +++ b/kernel/sys_ni.c
> @@ -87,6 +87,7 @@ COND_SYSCALL_COMPAT(set_robust_list);
>   COND_SYSCALL(get_robust_list);
>   COND_SYSCALL_COMPAT(get_robust_list);
>   COND_SYSCALL(futex_waitv);
> +COND_SYSCALL(futex_wake);
>   COND_SYSCALL(kexec_load);
>   COND_SYSCALL_COMPAT(kexec_load);
>   COND_SYSCALL(init_module);
> 
>

On Wed, Aug 09, 2023 at 07:25:19PM -0300, André Almeida wrote:
> Hi Peter,
> 
> Em 07/08/2023 09:18, Peter Zijlstra escreveu:
> > To complement sys_futex_waitv() add sys_futex_wake(). This syscall
> > implements what was previously known as FUTEX_WAKE_BITSET except it
> > uses 'unsigned long' for the bitmask and takes FUTEX2 flags.
> > 
> > The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms.
> > 
> > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> > Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
> > ---
> 
> [...]
> 
> > +/*
> > + * sys_futex_wake - Wake a number of futexes
> > + * @uaddr:	Address of the futex(es) to wake
> > + * @mask:	bitmask
> > + * @nr:		Number of the futexes to wake
> > + * @flags:	FUTEX2 flags
> > + *
> > + * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
> > + * futex2 family of calls.
> > + */
> > +
> > +SYSCALL_DEFINE4(futex_wake,
> > +		void __user *, uaddr,
> > +		unsigned long, mask,
> > +		int, nr,
> > +		unsigned int, flags)
> > +{
> 
> Do you think we could have a
> 
> 	if (!nr)
> 		return 0;
> 
> here? Otherwise, calling futex_wake(&f, 0, flags) will wake 1 futex (if
> available), which is a strange undocumented behavior in my opinion.

Oh 'cute' that.. yeah, but how about I put it ...

> > +	if (flags & ~FUTEX2_VALID_MASK)
> > +		return -EINVAL;
> > +
> > +	flags = futex2_to_flags(flags);
> > +	if (!futex_flags_valid(flags))
> > +		return -EINVAL;
> > +
> > +	if (!futex_validate_input(flags, mask))
> > +		return -EINVAL;

here, because otherwise we get:

	sys_futex_wake(&f, 0xFFFF, 0, FUTEX2_SIZE_U8)

to return 0, even though that is 'obviously' nonsensical and should
return -EINVAL. Or even garbage flags would be 'accepted'.

(because 0xFFFF is larger than U8 can accomodate)

> > +
> > +	return futex_wake(uaddr, flags, nr, mask);
> > +}

Em 10/08/2023 09:13, Peter Zijlstra escreveu:
> On Wed, Aug 09, 2023 at 07:25:19PM -0300, André Almeida wrote:
>> Hi Peter,
>>
>> Em 07/08/2023 09:18, Peter Zijlstra escreveu:
>>> To complement sys_futex_waitv() add sys_futex_wake(). This syscall
>>> implements what was previously known as FUTEX_WAKE_BITSET except it
>>> uses 'unsigned long' for the bitmask and takes FUTEX2 flags.
>>>
>>> The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms.
>>>
>>> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
>>> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
>>> ---
>>
>> [...]
>>
>>> +/*
>>> + * sys_futex_wake - Wake a number of futexes
>>> + * @uaddr:	Address of the futex(es) to wake
>>> + * @mask:	bitmask
>>> + * @nr:		Number of the futexes to wake
>>> + * @flags:	FUTEX2 flags
>>> + *
>>> + * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
>>> + * futex2 family of calls.
>>> + */
>>> +
>>> +SYSCALL_DEFINE4(futex_wake,
>>> +		void __user *, uaddr,
>>> +		unsigned long, mask,
>>> +		int, nr,
>>> +		unsigned int, flags)
>>> +{
>>
>> Do you think we could have a
>>
>> 	if (!nr)
>> 		return 0;
>>
>> here? Otherwise, calling futex_wake(&f, 0, flags) will wake 1 futex (if
>> available), which is a strange undocumented behavior in my opinion.
> 
> Oh 'cute' that.. yeah, but how about I put it ...
> 
>>> +	if (flags & ~FUTEX2_VALID_MASK)
>>> +		return -EINVAL;
>>> +
>>> +	flags = futex2_to_flags(flags);
>>> +	if (!futex_flags_valid(flags))
>>> +		return -EINVAL;
>>> +
>>> +	if (!futex_validate_input(flags, mask))
>>> +		return -EINVAL;
> 
> here, because otherwise we get:
> 
> 	sys_futex_wake(&f, 0xFFFF, 0, FUTEX2_SIZE_U8)
> 
> to return 0, even though that is 'obviously' nonsensical and should
> return -EINVAL. Or even garbage flags would be 'accepted'.
> 
> (because 0xFFFF is larger than U8 can accomodate)
> 

That make sense to me, but we would also want to validate the value of 
f, if it's NULL or something strange to return -EINVAL... but this 
happens only inside get_futex_key()...

To make this right, I think we would need to move this verification to 
the syscall validation part:

	if (unlikely((address % sizeof(u32)) != 0))
		return -EINVAL;

	if (unlikely(!access_ok(uaddr, sizeof(u32))))
		return -EFAULT;

And have u32 replaced with the proper size being used.

>>> +
>>> +	return futex_wake(uaddr, flags, nr, mask);
>>> +}

On Mon, Aug 07 2023 at 14:18, Peter Zijlstra wrote:

> To complement sys_futex_waitv() add sys_futex_wake(). This syscall
> implements what was previously known as FUTEX_WAKE_BITSET except it
> uses 'unsigned long' for the bitmask and takes FUTEX2 flags.
>
> The 'unsigned long' allows FUTEX2_SIZE_U64 on 64bit platforms.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>