Futex hash computation requires a mask operation with read-only after
init data that will be converted to a runtime constant in the subsequent
commit.

Introduce runtime_const_mask_32 to further optimize the mask operation
in the futex hash computation hot path.

GCC generates a:

  nilf %r1,<imm32>

to tackle arbitrary 32-bit masks and the same is implemented here.
Immediate patching pattern for __runtime_fixup_mask() has been adopted
from __runtime_fixup_ptr().

Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
---
 arch/s390/include/asm/runtime-const.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/arch/s390/include/asm/runtime-const.h b/arch/s390/include/asm/runtime-const.h
index 17878b1d048c..c0f0d59066e2 100644
--- a/arch/s390/include/asm/runtime-const.h
+++ b/arch/s390/include/asm/runtime-const.h
@@ -33,6 +33,19 @@
 	__ret;							\
 })
 
+#define runtime_const_mask_32(val, sym)				\
+({								\
+	unsigned int __ret = (val);				\
+								\
+	asm_inline(						\
+		"0:	nilf	%[__ret],12\n"			\
+		".pushsection runtime_mask_" #sym ",\"a\"\n"	\
+		".long 0b - .\n"				\
+		".popsection"					\
+		: [__ret] "+d" (__ret));			\
+	__ret;							\
+})
+
 #define runtime_const_init(type, sym) do {			\
 	extern s32 __start_runtime_##type##_##sym[];		\
 	extern s32 __stop_runtime_##type##_##sym[];		\
@@ -65,6 +78,12 @@ static inline void __runtime_fixup_shift(void *where, unsigned long val)
 	s390_kernel_write(where, &insn, sizeof(insn));
 }
 
+/* 32-bit immediate for nilf in bits in I2 field */
+static inline void __runtime_fixup_mask(void *where, unsigned long val)
+{
+	__runtime_fixup_32(where + 2, val);
+}
+
 static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 				       unsigned long val, s32 *start, s32 *end)
 {
-- 
2.43.0

On Mon, Mar 16, 2026 at 05:23:59AM +0000, K Prateek Nayak wrote:
> Futex hash computation requires a mask operation with read-only after
> init data that will be converted to a runtime constant in the subsequent
> commit.
> 
> Introduce runtime_const_mask_32 to further optimize the mask operation
> in the futex hash computation hot path.
> 
> GCC generates a:
> 
>   nilf %r1,<imm32>
> 
> to tackle arbitrary 32-bit masks and the same is implemented here.
> Immediate patching pattern for __runtime_fixup_mask() has been adopted
> from __runtime_fixup_ptr().
> 
> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
> ---
>  arch/s390/include/asm/runtime-const.h | 19 +++++++++++++++++++
>  1 file changed, 19 insertions(+)

...

> +#define runtime_const_mask_32(val, sym)				\
> +({								\
> +	unsigned int __ret = (val);				\
> +								\
> +	asm_inline(						\
> +		"0:	nilf	%[__ret],12\n"			\
> +		".pushsection runtime_mask_" #sym ",\"a\"\n"	\
> +		".long 0b - .\n"				\
> +		".popsection"					\
> +		: [__ret] "+d" (__ret));			\
> +	__ret;							\
> +})

The nilf instruction changes the condition code and this must be reflected in
the clobber list. Besides that I would also appreciate if you would move the
existing comment above __runtime_fixup_32().

Or in other words, if you merge the patch below into this one feel free to
add:

Acked-by: Heiko Carstens <hca@linux.ibm.com>

diff --git a/arch/s390/include/asm/runtime-const.h b/arch/s390/include/asm/runtime-const.h
index c0f0d59066e2..7b71156031ec 100644
--- a/arch/s390/include/asm/runtime-const.h
+++ b/arch/s390/include/asm/runtime-const.h
@@ -42,7 +42,8 @@
 		".pushsection runtime_mask_" #sym ",\"a\"\n"	\
 		".long 0b - .\n"				\
 		".popsection"					\
-		: [__ret] "+d" (__ret));			\
+		: [__ret] "+d" (__ret)				\
+		: : "cc");					\
 	__ret;							\
 })
 
@@ -56,12 +57,12 @@
 			    __stop_runtime_##type##_##sym);	\
 } while (0)
 
-/* 32-bit immediate for iihf and iilf in bits in I2 field */
 static inline void __runtime_fixup_32(u32 *p, unsigned int val)
 {
 	s390_kernel_write(p, &val, sizeof(val));
 }
 
+/* 32-bit immediate for iihf and iilf in bits in I2 field */
 static inline void __runtime_fixup_ptr(void *where, unsigned long val)
 {
 	__runtime_fixup_32(where + 2, val >> 32);

Hello Heiko,

On 3/17/2026 12:49 AM, Heiko Carstens wrote:
>> +#define runtime_const_mask_32(val, sym)				\
>> +({								\
>> +	unsigned int __ret = (val);				\
>> +								\
>> +	asm_inline(						\
>> +		"0:	nilf	%[__ret],12\n"			\
>> +		".pushsection runtime_mask_" #sym ",\"a\"\n"	\
>> +		".long 0b - .\n"				\
>> +		".popsection"					\
>> +		: [__ret] "+d" (__ret));			\
>> +	__ret;							\
>> +})
> 
> The nilf instruction changes the condition code and this must be reflected in
> the clobber list.

Thanks a ton for catching that!

> Besides that I would also appreciate if you would move the
> existing comment above __runtime_fixup_32().
> 
> Or in other words, if you merge the patch below into this one feel free to
> add:

I'll fold in the suggested diff when spinning up the next version.

> 
> Acked-by: Heiko Carstens <hca@linux.ibm.com>

Thanks a ton for taking a look at the series!

-- 
Thanks and Regards,
Prateek