percpu: make this_cpu_generic_read() atomic w.r.t. interrupts

As raw_cpu_generic_read() is a plain read from a raw_cpu_ptr() address,
it's possible (albeit unlikely) that the compiler will split the access
across multiple instructions.

In this_cpu_generic_read() we disable preemption but not interrupts
before calling raw_cpu_generic_read(). Thus, an interrupt could be taken
in the middle of the split load instructions. If a this_cpu_write() or
RMW this_cpu_*() op is made to the same variable in the interrupt
handling path, this_cpu_read() will return a torn value.

For native word types, we can avoid tearing using READ_ONCE(), but this
won't work in all cases (e.g. 64-bit types on most 32-bit platforms).
This patch reworks this_cpu_generic_read() to use READ_ONCE() where
possible, otherwise falling back to disabling interrupts.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pranith Kumar <bobby.prani@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Tejun Heo <tj@kernel.org>

include/asm-generic/percpu.h

@@ -115,15 +115,35 @@ do {									\
 	(__ret);							\
 })
 
-#define this_cpu_generic_read(pcp)					\
+#define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
 	typeof(pcp) __ret;						\
 	preempt_disable_notrace();					\
-	__ret = raw_cpu_generic_read(pcp);				\
+	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable_notrace();					\
 	__ret;								\
 })
 
+#define __this_cpu_generic_read_noirq(pcp)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_read(pcp);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	if (__native_word(pcp))						\
+		__ret = __this_cpu_generic_read_nopreempt(pcp);		\
+	else								\
+		__ret = __this_cpu_generic_read_noirq(pcp);		\
+	__ret;								\
+})
+
 #define this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	unsigned long __flags;						\