[RFC PATCH v2 4/7] riscv/runtime-const: Introduce runtime_const_mask_32()

[K Prateek Nayak]

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:

  lui   a0, 0x12346       # upper; +0x800 then >>12 for correct rounding
  addi  a0, a0, 0x678     # lower 12 bits
  and   a1, a1, a0        # a1 = a1 & a0

pattern to tackle arbitrary 32-bit masks and the same was also suggested
by Claude which is implemented here. __runtime_fixup_ptr() already
patches a "lui + addi" sequence which has been reused to patch the same
sequence for __runtime_fixup_mask().

Assisted-by: Claude:claude-sonnet-4-5
Signed-off-by: K Prateek Nayak <kprateek.nayak at amd.com>
---
 arch/riscv/include/asm/runtime-const.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
index d766e2b9e6df..f54289a7ddeb 100644
--- a/arch/riscv/include/asm/runtime-const.h
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -153,6 +153,24 @@
 	__ret;							\
 })
 
+#define runtime_const_mask_32(val, sym)				\
+({								\
+	u32 __ret;						\
+	asm_inline(".option push\n\t"				\
+		".option norvc\n\t"				\
+		"1:\t"						\
+		"lui	%[__ret],0x89abd\n\t"			\
+		"addi	%[__ret],%[__ret],-0x211\n\t"		\
+		"and	%[__ret],%[__ret],%[__val]\n\t"		\
+		".option pop\n\t"				\
+		".pushsection runtime_mask_" #sym ",\"a\"\n\t"	\
+		".long 1b - .\n\t"				\
+		".popsection"					\
+		: [__ret] "=&r" (__ret)				\
+		: [__val] "r" (val));				\
+	__ret;							\
+})
+
 #define runtime_const_init(type, sym) do {			\
 	extern s32 __start_runtime_##type##_##sym[];		\
 	extern s32 __stop_runtime_##type##_##sym[];		\
@@ -256,6 +274,12 @@ static inline void __runtime_fixup_shift(void *where, unsigned long val)
 	mutex_unlock(&text_mutex);
 }
 
+static inline void __runtime_fixup_mask(void *where, unsigned long val)
+{
+	__runtime_fixup_32(where, where + 4, val);
+	__runtime_fixup_caches(where, 2);
+}
+
 static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 				       unsigned long val, s32 *start, s32 *end)
 {
-- 
2.43.0