From: Frederic Weisbecker <frederic@xxxxxxxxxx> Add some missing critical pieces of explanation to understand the need for full memory barriers throughout the whole grace period state machine, thanks to Paul's explanations. Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx> Cc: Neeraj Upadhyay <neeraju@xxxxxxxxxxxxxx> Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx> Cc: Uladzislau Rezki <urezki@xxxxxxxxx> Cc: Boqun Feng <boqun.feng@xxxxxxxxx> [ paulmck: Adjust code block per Akira Yokosawa. ] Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx> --- .../Tree-RCU-Memory-Ordering.rst | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst index 11cdab037bff6..eeb351296df11 100644 --- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst +++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst @@ -112,6 +112,35 @@ on PowerPC. The ``smp_mb__after_unlock_lock()`` invocations prevent this ``WARN_ON()`` from triggering. ++-----------------------------------------------------------------------+ +| **Quick Quiz**: | ++-----------------------------------------------------------------------+ +| But the chain of rcu_node-structure lock acquisitions guarantees | +| that new readers will see all of the updater's pre-grace-period | +| accesses and also guarantees that the updater's post-grace-period | +| accesses will see all of the old reader's accesses. So why do we | +| need all of those calls to smp_mb__after_unlock_lock()? | ++-----------------------------------------------------------------------+ +| **Answer**: | ++-----------------------------------------------------------------------+ +| Because we must provide ordering for RCU's polling grace-period | +| primitives, for example, get_state_synchronize_rcu() and | +| poll_state_synchronize_rcu(). Consider this code:: | +| | +| CPU 0 CPU 1 | +| ---- ---- | +| WRITE_ONCE(X, 1) WRITE_ONCE(Y, 1) | +| g = get_state_synchronize_rcu() smp_mb() | +| while (!poll_state_synchronize_rcu(g)) r1 = READ_ONCE(X) | +| continue; | +| r0 = READ_ONCE(Y) | +| | +| RCU guarantees that the outcome r0 == 0 && r1 == 0 will not | +| happen, even if CPU 1 is in an RCU extended quiescent state | +| (idle or offline) and thus won't interact directly with the RCU | +| core processing at all. | ++-----------------------------------------------------------------------+ + This approach must be extended to include idle CPUs, which need RCU's grace-period memory ordering guarantee to extend to any RCU read-side critical sections preceding and following the current -- 2.31.1.189.g2e36527f23
