Re: [RFC PATCH v4 2/9] mm/damon/core: replace the access report buffer with per-context rings

[sashiko-bot@kernel.org]

> damon_report_access() queues reports into the global damon_access_reports[]
> buffer under a mutex, and kdamond applies them from there.  A perf-event
> overflow handler runs in NMI context and cannot take that mutex, and the
> buffer has no other producer.
> 
> Replace the buffer with a per-context, per-CPU SPSC report ring
> (ctx->perf_rings) that an NMI-context producer can publish into, and a
> kdamond drain that credits regions from each ring's pending reports.
> 
> NMI safety: the producer uses a busy counter to drop re-entrant reports on
> the same CPU, publishes with smp_wmb() before advancing the head, and sets
> a pending-CPU bitmask with smp_mb__before_atomic() so the consumer catches
> any report published between the bit-clear and the READ_ONCE(head).  The
> consumer publishes the tail with smp_store_release() after reading the
> entries, and the producer reads it with smp_load_acquire(), so a slot is
> [ ... ]
> the access_reported flag and kdamond_apply_zero_access_report(), which
> served only the page fault primitive's reports, with no user; remove
> them.
> 
> Signed-off-by: Ravi Jonnalagadda <ravis.opensrc@gmail.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261005-damon-perf-rfc-v3-send-2026-10-03-v4-0-b03452e137f3@gmail.com?part=2