On Thu, Nov 04, 2021 at 12:58:02PM -0700, Peter Oskolkov wrote:

+/* Update the state variable, set new timestamp. */
+static bool umcg_update_state(uint64_t *state, uint64_t *prev, uint64_t next)
+{
+	uint64_t prev_ts = (*prev) >> (64 - UMCG_STATE_TIMESTAMP_BITS);
+	struct timespec now;
+	uint64_t next_ts;
+	int res;
+
+	/*
+	 * clock_gettime(CLOCK_MONOTONIC, ...) takes less than 20ns on a
+	 * typical Intel processor on average, even when run concurrently,
+	 * so the overhead is low enough for most applications.
+	 *
+	 * If this is still too high, `next_ts = prev_ts + 1` should work
+	 * as well. The only real requirement is that the "timestamps" are
+	 * uniqueue per thread within a reasonable time frame.
+	 */
+	res = clock_gettime(CLOCK_MONOTONIC, &now);
+	assert(!res);
+	next_ts = (now.tv_sec * NSEC_PER_SEC + now.tv_nsec) >>
+		UMCG_STATE_TIMESTAMP_GRANULARITY;
+
+	/* Cut higher order bits. */
+	next_ts &= ((1ULL << UMCG_STATE_TIMESTAMP_BITS) - 1);

This is the right cut.. The same to the kernel side.

+
+	if (next_ts == prev_ts)
+		++next_ts;
+
+#ifndef NDEBUG
+	if (prev_ts > next_ts) {
+		fprintf(stderr, "%s: time goes back: prev_ts: %lu "
+				"next_ts: %lu diff: %lu\n", __func__,
+				prev_ts, next_ts, prev_ts - next_ts);
+	}
+#endif
+
+	/* Remove old timestamp, if any. */
+	next &= ((1ULL << (64 - UMCG_STATE_TIMESTAMP_BITS)) - 1);
+
+	/* Set the new timestamp. */
+	next |= (next_ts << (64 - UMCG_STATE_TIMESTAMP_BITS));
+
+	/*
+	 * TODO: review whether memory order below can be weakened to
+	 * memory_order_acq_rel for success and memory_order_acquire for
+	 * failure.
+	 */
+	return atomic_compare_exchange_strong_explicit(state, prev, next,
+			memory_order_seq_cst, memory_order_seq_cst);
+}
+

+static void task_unlock(struct umcg_task_tls *task, uint64_t expected_state,
+		uint64_t new_state)
+{
+	bool ok;
+	uint64_t next;
+	uint64_t prev = atomic_load_explicit(&task->umcg_task.state_ts,
+					memory_order_acquire);
+
+	next = ((prev & ~UMCG_TASK_STATE_MASK_FULL) | new_state) & ~UMCG_TF_LOCKED;

Use UMCG_TASK_STATE_MASK instead and the other state flag can be checked.

All others places that use UMCG_TASK_STATE_MASK_FULL to mask to check
the task state may seems reasonable if the state flag not allowed to
be set when we check that task state, otherwise use UMCG_TASK_STATE_MASK
will be enough.

Not sure.


Thanks,
Tao

+	assert(next != prev);
+	assert((prev & UMCG_TASK_STATE_MASK_FULL & ~UMCG_TF_LOCKED) == expected_state);
+
+	ok = umcg_update_state(&task->umcg_task.state_ts, &prev, next);
+	assert(ok);
+}