riscv: Optimize hweight API with Zbb extension

The Hamming Weight of a number is the total number of bits set in it, so
the cpop/cpopw instruction from Zbb extension can be used to accelerate
hweight() API.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20231112095244.4015351-1-xiao.w.wang@intel.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: XiaoWang1772

arch/riscv/include/asm/arch_hweight.h

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Based on arch/x86/include/asm/arch_hweight.h
+ */
+
+#ifndef _ASM_RISCV_HWEIGHT_H
+#define _ASM_RISCV_HWEIGHT_H
+
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if (BITS_PER_LONG == 64)
+#define CPOPW	"cpopw "
+#elif (BITS_PER_LONG == 32)
+#define CPOPW	"cpop "
+#else
+#error "Unexpected BITS_PER_LONG"
+#endif
+
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
+{
+#ifdef CONFIG_RISCV_ISA_ZBB
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     CPOPW "%0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+#endif
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __arch_hweight32(w & 0xff);
+}
+
+#if BITS_PER_LONG == 64
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+# ifdef CONFIG_RISCV_ISA_ZBB
+	asm_volatile_goto(ALTERNATIVE("j %l[legacy]", "nop", 0,
+				      RISCV_ISA_EXT_ZBB, 1)
+			  : : : : legacy);
+
+	asm (".option push\n"
+	     ".option arch,+zbb\n"
+	     "cpop %0, %0\n"
+	     ".option pop\n"
+	     : "+r" (w) : :);
+
+	return w;
+
+legacy:
+# endif
+	return __sw_hweight64(w);
+}
+#else /* BITS_PER_LONG == 64 */
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return  __arch_hweight32((u32)w) +
+		__arch_hweight32((u32)(w >> 32));
+}
+#endif /* !(BITS_PER_LONG == 64) */
+
+#endif /* _ASM_RISCV_HWEIGHT_H */

arch/riscv/include/asm/bitops.h

@@ -271,7 +271,9 @@ static __always_inline int variable_fls(unsigned int x)
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 
-#include <asm-generic/bitops/hweight.h>
+#include <asm/arch_hweight.h>
+
+#include <asm-generic/bitops/const_hweight.h>
 
 #if (BITS_PER_LONG == 64)
 #define __AMO(op)	"amo" #op ".d"