void osq_unlock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node, *next;
int curr = encode_cpu(smp_processor_id());
/*
* Fast path for the uncontended case.
*/
if (likely(atomic_cmpxchg_release(&lock->tail, curr,
OSQ_UNLOCKED_VAL) == curr))
return;
/*
* Second most likely case.
*/
node = this_cpu_ptr(&osq_node);
next = xchg(&node->next, NULL);
if (next) {
WRITE_ONCE(next->locked, 1);
return;
}
next = osq_wait_next(lock, node, NULL);
if (next)
WRITE_ONCE(next->locked, 1);
}
void gtcm_protocol(protocol_msg *pro)
{
if (!proto_built)
{
memcpy(proto.msg + CM_CPU_OFFSET, encode_cpu(), 3);
memcpy(proto.msg + CM_OS_OFFSET, encode_os(), 3);
memcpy(proto.msg + CM_IMPLEMENTATION_OFFSET, "GTM", 3);
/* gtm_version is of the form Vi.j where i and j are digits */
assert('V' == gtm_version[0] && ISDIGIT_ASCII(gtm_version[1]) && '.' == gtm_version[2]
&& ISDIGIT_ASCII(gtm_version[3]));
proto.msg[CM_VERSION_OFFSET] = '0';
proto.msg[CM_VERSION_OFFSET + 1] = gtm_version[1];
proto.msg[CM_VERSION_OFFSET + 2] = gtm_version[3];
memcpy(proto.msg + CM_TYPE_OFFSET, CMM_PROTOCOL_TYPE, 3);
/* cm_ver_name is of the form Vijk where i, j, and k are digits */
assert('V' == cm_ver_name[0] && ISDIGIT_ASCII(cm_ver_name[1]) && ISDIGIT_ASCII(cm_ver_name[2])
&& ISDIGIT_ASCII(cm_ver_name[3]));
memcpy(proto.msg + CM_LEVEL_OFFSET, &cm_ver_name[1], 3);
#ifdef BIGENDIAN
proto.msg[CM_ENDIAN_OFFSET] = GTCM_BIG_ENDIAN_INDICATOR;
#else
proto.msg[CM_ENDIAN_OFFSET] = ' ';
#endif
memset(proto.msg + CM_ENDIAN_OFFSET + 1, ' ' , CM_FILLER_SIZE);
proto_built = TRUE;
}
memcpy(pro->msg, proto.msg, S_PROTSIZE);
/* memcpy(pro->msg, S_PROTOCOL, S_PROTSIZE); */
}
/*
* Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
* Can return NULL in case we were the last queued and we updated @lock instead.
*/
static inline struct optimistic_spin_node *
osq_wait_next(struct optimistic_spin_queue *lock,
struct optimistic_spin_node *node,
struct optimistic_spin_node *prev)
{
struct optimistic_spin_node *next = NULL;
int curr = encode_cpu(smp_processor_id());
int old;
/*
* If there is a prev node in queue, then the 'old' value will be
* the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
* we're currently last in queue, then the queue will then become empty.
*/
old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
for (;;) {
if (atomic_read(&lock->tail) == curr &&
atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
/*
* We were the last queued, we moved @lock back. @prev
* will now observe @lock and will complete its
* unlock()/unqueue().
*/
break;
}
/*
* We must xchg() the @node->next value, because if we were to
* leave it in, a concurrent unlock()/unqueue() from
* @node->next might complete Step-A and think its @prev is
* still valid.
*
* If the concurrent unlock()/unqueue() wins the race, we'll
* wait for either @lock to point to us, through its Step-B, or
* wait for a new @node->next from its Step-C.
*/
if (node->next) {
next = xchg(&node->next, NULL);
if (next)
break;
}
cpu_relax_lowlatency();
}
return next;
}
bool osq_lock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
struct optimistic_spin_node *prev, *next;
int curr = encode_cpu(smp_processor_id());
int old;
node->locked = 0;
node->next = NULL;
node->cpu = curr;
/*
* We need both ACQUIRE (pairs with corresponding RELEASE in
* unlock() uncontended, or fastpath) and RELEASE (to publish
* the node fields we just initialised) semantics when updating
* the lock tail.
*/
old = atomic_xchg(&lock->tail, curr);
if (old == OSQ_UNLOCKED_VAL)
return true;
prev = decode_cpu(old);
node->prev = prev;
WRITE_ONCE(prev->next, node);
/*
* Normally @prev is untouchable after the above store; because at that
* moment unlock can proceed and wipe the node element from stack.
*
* However, since our nodes are static per-cpu storage, we're
* guaranteed their existence -- this allows us to apply
* cmpxchg in an attempt to undo our queueing.
*/
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
*/
if (need_resched())
goto unqueue;
cpu_relax_lowlatency();
}
return true;
unqueue:
/*
* Step - A -- stabilize @prev
*
* Undo our @prev->next assignment; this will make @prev's
* unlock()/unqueue() wait for a next pointer since @lock points to us
* (or later).
*/
for (;;) {
if (prev->next == node &&
cmpxchg(&prev->next, node, NULL) == node)
break;
/*
* We can only fail the cmpxchg() racing against an unlock(),
* in which case we should observe @node->locked becomming
* true.
*/
if (smp_load_acquire(&node->locked))
return true;
cpu_relax_lowlatency();
/*
* Or we race against a concurrent unqueue()'s step-B, in which
* case its step-C will write us a new @node->prev pointer.
*/
prev = READ_ONCE(node->prev);
}
/*
* Step - B -- stabilize @next
*
* Similar to unlock(), wait for @node->next or move @lock from @node
* back to @prev.
*/
next = osq_wait_next(lock, node, prev);
if (!next)
return false;
/*
* Step - C -- unlink
*
* @prev is stable because its still waiting for a new @prev->next
* pointer, @next is stable because our @node->next pointer is NULL and
* it will wait in Step-A.
*/
WRITE_ONCE(next->prev, prev);
WRITE_ONCE(prev->next, next);
return false;
}
