[RFC PATCH v2 2/7] arm64/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:

  movz  w1, #lo16, lsl #0     // w1 = bits [15:0]
  movk  w1, #hi16, lsl #16    // w1 = full 32-bit value
  and   w0, w0, w1	      // w0 = w0 & w1

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 "movz, + movk lsl #16" 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/arm64/include/asm/runtime-const.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/arm64/include/asm/runtime-const.h b/arch/arm64/include/asm/runtime-const.h
index c3dbd3ae68f6..4c3f0b9aad98 100644
--- a/arch/arm64/include/asm/runtime-const.h
+++ b/arch/arm64/include/asm/runtime-const.h
@@ -35,6 +35,19 @@
 		:"r" (0u+(val)));				\
 	__ret; })
 
+#define runtime_const_mask_32(val, sym) ({			\
+	unsigned long __ret;					\
+	asm_inline("1:\t"					\
+		"movz %w0, #0xcdef\n\t"				\
+		"movk %w0, #0x89ab, lsl #16\n\t"			\
+		"and %w0,%w0,%w1\n\t"				\
+		".pushsection runtime_mask_" #sym ",\"a\"\n\t"	\
+		".long 1b - .\n\t"				\
+		".popsection"					\
+		:"=r" (__ret)					\
+		:"r" (0u+(val)));				\
+	__ret; })
+
 #define runtime_const_init(type, sym) do {		\
 	extern s32 __start_runtime_##type##_##sym[];	\
 	extern s32 __stop_runtime_##type##_##sym[];	\
@@ -80,6 +93,15 @@ static inline void __runtime_fixup_shift(void *where, unsigned long val)
 	__runtime_fixup_caches(where, 1);
 }
 
+/* Immediate value is 6 bits starting at bit #16 */
+static inline void __runtime_fixup_mask(void *where, unsigned long val)
+{
+	__le32 *p = lm_alias(where);
+	__runtime_fixup_16(p, val);
+	__runtime_fixup_16(p+1, val >> 16);
+	__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