Why is (or isn't?) SFENCE + LFENCE equivalent to MFENCE?

Question

As we know from a previous answer to Does it make any sense instruction LFENCE in processors x86/x86_64? that we can not use SFENCE instead of MFENCE

Answer 1

In general MFENCE != SFENCE + LFENCE. For example the code below, when compiled with -DBROKEN, fails on some Westmere and Sandy Bridge systems but appears to work on Ryzen. In fact on AMD systems just an SFENCE seems to be sufficient.

#include 
#include 
#include 
#include 
using namespace std;

#define ITERATIONS (10000000)
class minircu {
        public:
                minircu() : rv_(0), wv_(0) {}
                class lock_guard {
                        minircu& _r;
                        const std::size_t _id;
                        public:
                        lock_guard(minircu& r, std::size_t id) : _r(r), _id(id) { _r.rlock(_id); }
                        ~lock_guard() { _r.runlock(_id); }
                };
                void synchronize() {
                        wv_.store(-1, std::memory_order_seq_cst);
                        while(rv_.load(std::memory_order_relaxed) & wv_.load(std::memory_order_acquire));
                }
        private:
                void rlock(std::size_t id) {
                        rab_[id].store(1, std::memory_order_relaxed);
#ifndef BROKEN
                        __asm__ __volatile__ ("mfence;" : : : "memory");
#else
                        __asm__ __volatile__ ("sfence; lfence;" : : : "memory");
#endif
                }
                void runlock(std::size_t id) {
                        rab_[id].store(0, std::memory_order_release);
                        wab_[id].store(0, std::memory_order_release);
                }
                union alignas(64) {
                        std::atomic           rv_;
                        std::atomic      rab_[8];
                };
                union alignas(8) {
                        std::atomic           wv_;
                        std::atomic      wab_[8];
                };
};

minircu r;

std::atomic shared_values[2];
std::atomic*> pvalue(shared_values);
std::atomic total(0);

void r_thread(std::size_t id) {
    uint64_t subtotal = 0;
    for(size_t i = 0; i < ITERATIONS; ++i) {
                minircu::lock_guard l(r, id);
                subtotal += (*pvalue).load(memory_order_acquire);
    }
    total += subtotal;
}

void wr_thread() {
    for (size_t i = 1; i < (ITERATIONS/10); ++i) {
                std::atomic* o = pvalue.load(memory_order_relaxed);
                std::atomic* p = shared_values + i % 2;
                p->store(1, memory_order_release);
                pvalue.store(p, memory_order_release);

                r.synchronize();
                o->store(0, memory_order_relaxed); // should not be visible to readers
    }
}

int main(int argc, char* argv[]) {
    std::vector vec_thread;
    shared_values[0] = shared_values[1] = 1;
    std::size_t readers = (argc > 1) ? ::atoi(argv[1]) : 8;
    if (readers > 8) {
        std::cout << "maximum number of readers is " << 8 << std::endl; return 0;
    } else
        std::cout << readers << " readers" << std::endl;

    vec_thread.emplace_back( [=]() { wr_thread(); } );
    for(size_t i = 0; i < readers; ++i)
        vec_thread.emplace_back( [=]() { r_thread(i); } );
    for(auto &i: vec_thread) i.join();

    std::cout << "total = " << total << ", expecting " << readers * ITERATIONS << std::endl;
    return 0;
}