x86/percpu: Fix this_cpu_read()

Eric reported that a sequence count loop using this_cpu_read() got
optimized out. This is wrong, this_cpu_read() must imply READ_ONCE()
because the interface is IRQ-safe, therefore an interrupt can have
changed the per-cpu value.

Fixes: 7c3576d2 ("[PATCH] i386: Convert PDA into the percpu section")
Reported-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NEric Dumazet <edumazet@google.com>
Cc: hpa@zytor.com
Cc: eric.dumazet@gmail.com
Cc: bp@alien8.de
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20181011104019.748208519@infradead.org

arch/x86/include/asm/percpu.h

@@ -185,22 +185,22 @@ do {									\
 	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_arg(1)",%0"		\
+		asm volatile(op "b "__percpu_arg(1)",%0"\
 		    : "=q" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_arg(1)",%0"		\
+		asm volatile(op "w "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_arg(1)",%0"		\
+		asm volatile(op "l "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 8:						\
-		asm(op "q "__percpu_arg(1)",%0"		\
+		asm volatile(op "q "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\