bpf_scratchpad is a per-CPU variable and relies on disabled BH for its
locking. Without per-CPU locking in local_bh_disable() on PREEMPT_RT
this data structure requires explicit locking.

Add a local_lock_t to the data structure and use local_lock_nested_bh()
for locking. This change adds only lockdep coverage and does not alter
the functional behaviour for !PREEMPT_RT.

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Hao Luo <redacted>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <redacted>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: bpf@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 net/core/filter.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index c8013f762524b..896aa3fa699f9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c

@@ -1652,9 +1652,12 @@ struct bpf_scratchpad {
 		__be32 diff[MAX_BPF_STACK / sizeof(__be32)];
 		u8     buff[MAX_BPF_STACK];
 	};
+	local_lock_t	lock;
 };
 
-static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);
+static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = {
+	.lock	= INIT_LOCAL_LOCK(lock),
+};
 
 static inline int __bpf_try_make_writable(struct sk_buff *skb,
 					  unsigned int write_len)

@@ -2023,6 +2026,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
 		     diff_size > sizeof(sp->diff)))
 		return -EINVAL;
 
+	guard(local_lock_nested_bh)(&bpf_sp.lock);
 	for (i = 0; i < from_size / sizeof(__be32); i++, j++)
 		sp->diff[j] = ~from[i];
 	for (i = 0; i <   to_size / sizeof(__be32); i++, j++)

-- 
2.43.0