Re: [RFC PATCH 00/12] RCU pseudo-transactions

[David Woodhouse]

On Mon, 2026-11-09 at 17:34 -0800, Paul E. McKenney wrote:
> > Could the atomic flavor count its readers as srcu_read_lock_nmisafe()
> > does? Then a reader could also enter from NMI. The code I have for the
> > next version keeps one counter per NMI nesting level for this. With
> > SRCU, the sums of locks and unlocks handle the nesting already.
> 
> The other user that I know of is David Woodhouse, now CCed.
> 
> David, would you be OK with srcu_read_lock_atomic() using NMI-safe
> counters, similar to __srcu_read_lock_fast()?

I can't see any reason why I should object to that, as long as the
synchronize_srcu_atomic() stays in the 4-16µs bracket which was our
major criterion for this approach.

I'm still iterating on the KVM GPC use case¹, as sashiko-bot keeps
finding things that my own local sashiko runs don't. 

¹ https://git.infradead.org/users/dwmw2/linux.git/shortlog/refs/heads/gpc-srcu-v3

Attachment: smime.p7s
Description: S/MIME cryptographic signature