x86, hweight: Use a 32-bit popcnt for __arch_hweight32()

Use a 32-bit popcnt instruction for __arch_hweight32(), even on
x86-64.  Even though the input register will *usually* be
zero-extended due to the standard operation of the hardware, it isn't
necessarily so if the input value was the result of truncating a
64-bit operation.

Note: the POPCNT32 variant used on x86-64 has a technically
unnecessary REX prefix to make it five bytes long, the same as a CALL
instruction, therefore avoiding an unnecessary NOP.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Borislav Petkov <borislav.petkov@amd.com>
LKML-Reference: <alpine.LFD.2.00.1005171443060.4195@i5.linux-foundation.org>

arch/x86/include/asm/arch_hweight.h

@@ -2,13 +2,15 @@
 #define _ASM_X86_HWEIGHT_H
 
 #ifdef CONFIG_64BIT
+/* popcnt %edi, %eax -- redundant REX prefix for alignment */
+#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
 /* popcnt %rdi, %rax */
-#define POPCNT ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
+#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
 #define REG_IN "D"
 #define REG_OUT "a"
 #else
 /* popcnt %eax, %eax */
-#define POPCNT ".byte 0xf3,0x0f,0xb8,0xc0"
+#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0"
 #define REG_IN "a"
 #define REG_OUT "a"
 #endif
@@ -23,7 +25,7 @@ static inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res = 0;
 
-	asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT)
+	asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
 		     : "="REG_OUT (res)
 		     : REG_IN (w));
 
@@ -48,7 +50,7 @@ static inline unsigned long __arch_hweight64(__u64 w)
 	return  __arch_hweight32((u32)w) +
 		__arch_hweight32((u32)(w >> 32));
 #else
-	asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT)
+	asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
 		     : "="REG_OUT (res)
 		     : REG_IN (w));
 #endif /* CONFIG_X86_32 */