The following commit has been merged into the core/rcu branch of tip:
Commit-ID: 4e7ccfae52b39aeee93ed39d4184d50ea201fbef
Gitweb: https://git.kernel.org/tip/4e7ccfae52b39aeee93ed39d4184d50ea201fbef
Author: Paul E. McKenney <paulmck@xxxxxxxxxx>
AuthorDate: Sun, 15 Nov 2020 20:33:38 -08:00
Committer: Paul E. McKenney <paulmck@xxxxxxxxxx>
CommitterDate: Mon, 04 Jan 2021 13:53:39 -08:00
srcu: Add comment explaining cookie overflow/wrap
This commit adds to the poll_state_synchronize_srcu() header comment
describing the issues surrounding SRCU cookie overflow/wrap for the
different kernel configurations.
Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@xxxxxxxxxxxxxx/
Reported-by: Kent Overstreet <kent.overstreet@xxxxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
---
kernel/rcu/srcutree.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index c5d0c03..119938d 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1058,6 +1058,21 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
* get_state_synchronize_srcu() or start_poll_synchronize_srcu(), and
* returns @true if an SRCU grace period elapsed since the time that the
* cookie was created.
+ *
+ * Because cookies are finite in size, wrapping/overflow is possible.
+ * This is more pronounced on 32-bit systems where cookies are 32 bits,
+ * where in theory wrapping could happen in about 14 hours assuming
+ * 25-microsecond expedited SRCU grace periods. However, a more likely
+ * overflow lower bound is on the order of 24 days in the case of
+ * one-millisecond SRCU grace periods. Of course, wrapping in a 64-bit
+ * system requires geologic timespans, as in more than seven million years
+ * even for expedited SRCU grace periods.
+ *
+ * Wrapping/overflow is much more of an issue for CONFIG_SMP=n systems
+ * that also have CONFIG_PREEMPTION=n, which selects Tiny SRCU. This uses
+ * a 16-bit cookie, which rcutorture routinely wraps in a matter of a
+ * few minutes. If this proves to be a problem, this counter will be
+ * expanded to the same size as for Tree SRCU.
*/
bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
{
|