On 3/3/23 09:19, Paolo Bonzini wrote:
This nasty difference between Linux and C11 read-modify-write operations has already caused issues in util/async.c and more are being found. Provide something similar to Linux smp_mb__before/after_atomic(); this has the double function of documenting clearly why there is a memory barrier, and avoiding a double barrier on x86 and s390x systems.
It does make me question our choice to use neither the Linux nor the C11 model.
+ +--------------------------------+ + | QEMU (incorrect) | + +================================+ + | :: | + | | + | a = qatomic_fetch_add(&x, 2);| + | smp_mb__after_rmw(); | + | b = qatomic_read(&y); | + +--------------------------------+
Correct, surely.
+/* + * SEQ_CST is weaker than the older __sync_* builtins and Linux + * kernel read-modify-write atomics. Provide a macro to obtain + * the same semantics. + */ +#if !defined(QEMU_SANITIZE_THREAD) && \ + (defined(__i386__) || defined(__x86_64__) || defined(__s390x__)) +# define smp_mb__before_rmw() signal_barrier() +# define smp_mb__after_rmw() signal_barrier() +#else +# define smp_mb__before_rmw() smp_mb() +# define smp_mb__after_rmw() smp_mb() +#endif
I notice you never actually use smp_mb__before_rmw(), but I suppose since we're trying to mirror smp_mb__before(), we should keep the interface whole.
Other than the "incorrect" above, Reviewed-by: Richard Henderson <richard.hender...@linaro.org> r~
