4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Andrea Parri <parri.andrea@xxxxxxxxx> [ Upstream commit cb13b424e986aed68d74cbaec3449ea23c50e167 ] Continuing along with the fight against smp_read_barrier_depends() [1] (or rather, against its improper use), add an unconditional barrier to cmpxchg. This guarantees that dependency ordering is preserved when a dependency is headed by an unsuccessful cmpxchg. As it turns out, the change could enable further simplification of LKMM as proposed in [2]. [1] https://marc.info/?l=linux-kernel&m=150884953419377&w=2 https://marc.info/?l=linux-kernel&m=150884946319353&w=2 https://marc.info/?l=linux-kernel&m=151215810824468&w=2 https://marc.info/?l=linux-kernel&m=151215816324484&w=2 [2] https://marc.info/?l=linux-kernel&m=151881978314872&w=2 Signed-off-by: Andrea Parri <parri.andrea@xxxxxxxxx> Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx> Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Matt Turner <mattst88@xxxxxxxxx> Cc: Richard Henderson <rth@xxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Will Deacon <will.deacon@xxxxxxx> Cc: linux-alpha@xxxxxxxxxxxxxxx Link: http://lkml.kernel.org/r/1519152356-4804-1-git-send-email-parri.andrea@xxxxxxxxx Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/alpha/include/asm/xchg.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) --- a/arch/alpha/include/asm/xchg.h +++ b/arch/alpha/include/asm/xchg.h @@ -127,10 +127,9 @@ ____xchg(, volatile void *ptr, unsigned * store NEW in MEM. Return the initial value in MEM. Success is * indicated by comparing RETURN with OLD. * - * The memory barrier should be placed in SMP only when we actually - * make the change. If we don't change anything (so if the returned - * prev is equal to old) then we aren't acquiring anything new and - * we don't need any memory barrier as far I can tell. + * The memory barrier is placed in SMP unconditionally, in order to + * guarantee that dependency ordering is preserved when a dependency + * is headed by an unsuccessful operation. */ static inline unsigned long @@ -149,8 +148,8 @@ ____cmpxchg(_u8, volatile char *m, unsig " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -176,8 +175,8 @@ ____cmpxchg(_u16, volatile short *m, uns " or %1,%2,%2\n" " stq_c %2,0(%4)\n" " beq %2,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -199,8 +198,8 @@ ____cmpxchg(_u32, volatile int *m, int o " mov %4,%1\n" " stl_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous" @@ -222,8 +221,8 @@ ____cmpxchg(_u64, volatile long *m, unsi " mov %4,%1\n" " stq_c %1,%2\n" " beq %1,3f\n" - __ASM__MB "2:\n" + __ASM__MB ".subsection 2\n" "3: br 1b\n" ".previous"
