x86/percpu: Use %RIP-relative address in untagged_addr()

%RIP-relative addresses are nowadays correctly handled in alternative
instructions, so remove misleading comment and improve assembly to
use %RIP-relative address.

Also, explicitly using %gs: prefix will segfault for non-SMP builds.
Use macros from percpu.h which will DTRT with segment prefix register
as far as SMP/non-SMP builds are concerned.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradaed.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/all/20231213150357.5942-1-ubizjak%40gmail.com

Author: ubizjak

arch/x86/include/asm/uaccess_64.h

@@ -11,21 +11,18 @@
 #include <asm/alternative.h>
 #include <asm/cpufeatures.h>
 #include <asm/page.h>
+#include <asm/percpu.h>
 
 #ifdef CONFIG_ADDRESS_MASKING
 /*
  * Mask out tag bits from the address.
  */
 static inline unsigned long __untagged_addr(unsigned long addr)
 {
-	/*
-	 * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation
-	 * in alternative instructions. The relocation gets wrong when gets
-	 * copied to the target place.
-	 */
 	asm (ALTERNATIVE("",
-			 "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM)
-	     : [addr] "+r" (addr) : "m" (tlbstate_untag_mask));
+			 "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM)
+	     : [addr] "+r" (addr)
+	     : [mask] "m" (__my_cpu_var(tlbstate_untag_mask)));
 
 	return addr;
 }