Re: [PATCH v7 06/11] perf bpf-filter: Extend lock_held() to other kernel lock types

[sashiko-bot@kernel.org]

> Extend the lock_held() BPF sample filter beyond global mutexes to
> support:
> - Other global/static kernel lock symbols (rwsem, spinlock, rwlock,
>   rt-mutex, percpu-rwsem, semaphore) and hexadecimal kernel lock
>   addresses.
> - Lock types and flags: mutex, spinlock, rwsem, rwsem:R, rwsem:W,
>   rwlock, rwlock:R, rwlock:W, rt-mutex, percpu-rwsem, pcpu-sem:W,
>   semaphore.
> 
> For rt-mutexes and write-locked rwsems, perf_sample_filter inspects the
> lock's owner field directly in kernel memory. For locks and modes without
> an authoritative per-task owner pointer (spinlocks, rwlocks, semaphores,
> reader-locked rwsems, percpu-rwsems, and lock type filters), attach BPF
> fentry/fexit hooks on kernel lock acquire and release functions to track
> held locks in the held_locks BPF LRU hash map.
> 
> Use classify_lock_sym() both when selecting which hooks to load and when
> resolving the filter, so the two agree. A '*_sem' suffix may be either a
> semaphore (console_sem) or an rw_semaphore (namespace_sem), so hook both
> and allow read mode.
> 
> Note that counting semaphores (down*() / up()) do not enforce same-task
> ownership in the kernel: when a semaphore is used as a cross-task
> completion/signaling mechanism, fexit/down and fentry/up will not pair
> on the same task ID. Semaphore hooks are therefore only enabled when
> 'semaphore' or a '*_sem' symbol (such as console_sem) is explicitly
> specified, and held_locks uses BPF_MAP_TYPE_LRU_HASH so any unpaired
> cross-task entries are automatically evicted.
> 
> Signed-off-by: Ian Rogers <irogers@google.com>

Sashiko has reviewed this patch and found no issues.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261023190558.3050796-1-irogers@google.com?part=6