* Peter Zijlstra peterz@infradead.org wrote:
On Fri, 2013-02-22 at 13:50 +0100, Frederic Weisbecker wrote:
atomic64_read() and atomic64_set() are supposed to take care of that, without even the need for _inc() or _add() parts that use LOCK.
Are you sure? Generally atomic*_set() is not actually an atomic operation.
as per Documentation/atomic_ops.h:
#define atomic_read(v) ((v)->counter)
which simply reads the counter value currently visible to the calling thread. The read is atomic in that the return value is guaranteed to be one of the values initialized or modified with the interface operations if a proper implicit or explicit memory barrier is used after possible runtime initialization by any other thread and the value is modified only with the interface operations.
...
Properly aligned pointers, longs, ints, and chars (and unsigned equivalents) may be atomically loaded from and stored to in the same sense as described for atomic_read() and atomic_set().
The ACCESS_ONCE() macro should be used to prevent the compiler from using optimizations that might otherwise optimize accesses out of existence on the one hand, or that might create unsolicited accesses on the other.
This is usually a side effect of M[O]ESI cache coherency protocols - you can only get a 'split' word access if the word crosses cache line boundaries (multiples of 32 bytes, generally).
Thanks,
Ingo