6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <edumazet@xxxxxxxxxx>
[ Upstream commit 3584718cf2ec7e79b6814f2596dcf398c5fb2eca ]
Jonathan Heathcote reported a regression caused by blamed commit
on aarch64 architecture.
x86 happens to have irq-safe __this_cpu_add_return()
and __this_cpu_sub(), but this is not generic.
I think my confusion came from "struct sock" argument,
because these helpers are called with a locked socket.
But the memory accounting is per-proto (and per-cpu after
the blamed commit). We might cleanup these helpers later
to directly accept a "struct proto *proto" argument.
Switch to this_cpu_add_return() and this_cpu_xchg()
operations, and get rid of preempt_disable()/preempt_enable() pairs.
Fast path becomes a bit faster as a result :)
Many thanks to Jonathan Heathcote for his awesome report and
investigations.
Fixes: 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated")
Reported-by: Jonathan Heathcote <jonathan.heathcote@xxxxxxxxx>
Closes: https://lore.kernel.org/netdev/VI1PR01MB42407D7947B2EA448F1E04EFD10D2@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Acked-by: Soheil Hassas Yeganeh <soheil@xxxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Link: https://lore.kernel.org/r/20240421175248.1692552-1-edumazet@xxxxxxxxxx
Signed-off-by: Jakub Kicinski <kuba@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
include/net/sock.h | 38 ++++++++++++++++++++------------------
1 file changed, 20 insertions(+), 18 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 6ef6ce43a2edc..77298c74822a6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1485,32 +1485,34 @@ sk_memory_allocated(const struct sock *sk)
#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT))
extern int sysctl_mem_pcpu_rsv;
+static inline void proto_memory_pcpu_drain(struct proto *proto)
+{
+ int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0);
+
+ if (val)
+ atomic_long_add(val, proto->memory_allocated);
+}
+
static inline void
-sk_memory_allocated_add(struct sock *sk, int amt)
+sk_memory_allocated_add(const struct sock *sk, int val)
{
- int local_reserve;
+ struct proto *proto = sk->sk_prot;
- preempt_disable();
- local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
- if (local_reserve >= READ_ONCE(sysctl_mem_pcpu_rsv)) {
- __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
- atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
- }
- preempt_enable();
+ val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val);
+
+ if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv)))
+ proto_memory_pcpu_drain(proto);
}
static inline void
-sk_memory_allocated_sub(struct sock *sk, int amt)
+sk_memory_allocated_sub(const struct sock *sk, int val)
{
- int local_reserve;
+ struct proto *proto = sk->sk_prot;
- preempt_disable();
- local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
- if (local_reserve <= -READ_ONCE(sysctl_mem_pcpu_rsv)) {
- __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
- atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
- }
- preempt_enable();
+ val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val);
+
+ if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv)))
+ proto_memory_pcpu_drain(proto);
}
#define SK_ALLOC_PERCPU_COUNTER_BATCH 16
--
2.43.0
