perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline

The {rd,wr}lbr_{to,from} wrappers are invoked in hot paths, e.g. context
switch and NMI handler. They should be always inline to achieve better
performance. However, the CONFIG_OPTIMIZE_INLINING allows the compiler
to uninline functions marked 'inline'.

Mark the {rd,wr}lbr_{to,from} wrappers as __always_inline to force
inline the wrappers.
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-12-git-send-email-kan.liang@linux.intel.com

arch/x86/events/intel/lbr.c

@@ -332,18 +332,18 @@ static u64 lbr_from_signext_quirk_rd(u64 val)
 	return val;
 }
 
-static inline void wrlbr_from(unsigned int idx, u64 val)
+static __always_inline void wrlbr_from(unsigned int idx, u64 val)
 {
 	val = lbr_from_signext_quirk_wr(val);
 	wrmsrl(x86_pmu.lbr_from + idx, val);
 }
 
-static inline void wrlbr_to(unsigned int idx, u64 val)
+static __always_inline void wrlbr_to(unsigned int idx, u64 val)
 {
 	wrmsrl(x86_pmu.lbr_to + idx, val);
 }
 
-static inline u64 rdlbr_from(unsigned int idx)
+static __always_inline u64 rdlbr_from(unsigned int idx)
 {
 	u64 val;
 
@@ -352,7 +352,7 @@ static inline u64 rdlbr_from(unsigned int idx)
 	return lbr_from_signext_quirk_rd(val);
 }
 
-static inline u64 rdlbr_to(unsigned int idx)
+static __always_inline u64 rdlbr_to(unsigned int idx)
 {
 	u64 val;