Re: rcu_read_lock lost its compiler barrier

From: Herbert Xu
Date: Mon Jun 03 2019 - 00:05:13 EST

On Sun, Jun 02, 2019 at 08:47:07PM -0700, Paul E. McKenney wrote:
> CPU2: if (b != 1)
> CPU2: b = 1;

Stop right there. The kernel is full of code that assumes that
assignment to an int/long is atomic. If your compiler breaks this
assumption that we can kiss the kernel good-bye.

Email: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Home Page:
PGP Key: