From 0f50641222f5f4f5a5dfd90e0798fa72286e057d Mon Sep 17 00:00:00 2001 From: Abel Wu Date: Mon, 14 Aug 2023 15:09:11 +0800 Subject: [PATCH] net-memcg: Fix scope of sockmem pressure indicators [ Upstream commit ac8a52962164a50e693fa021d3564d7745b83a7f ] Now there are two indicators of socket memory pressure sit inside struct mem_cgroup, socket_pressure and tcpmem_pressure, indicating memory reclaim pressure in memcg->memory and ->tcpmem respectively. When in legacy mode (cgroupv1), the socket memory is charged into ->tcpmem which is independent of ->memory, so socket_pressure has nothing to do with socket's pressure at all. Things could be worse by taking socket_pressure into consideration in legacy mode, as a pressure in ->memory can lead to premature reclamation/throttling in socket. While for the default mode (cgroupv2), the socket memory is charged into ->memory, and ->tcpmem/->tcpmem_pressure are simply not used. So {socket,tcpmem}_pressure are only used in default/legacy mode respectively for indicating socket memory pressure. This patch fixes the pieces of code that make mixed use of both. Fixes: 8e8ae645249b ("mm: memcontrol: hook up vmpressure to socket pressure") Signed-off-by: Abel Wu Acked-by: Shakeel Butt Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/memcontrol.h | 9 +++++++-- mm/vmpressure.c | 8 ++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e03976302956..099521835cd1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -283,6 +283,11 @@ struct mem_cgroup { atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; + /* + * Hint of reclaim pressure for socket memroy management. Note + * that this indicator should NOT be used in legacy cgroup mode + * where socket memory is accounted/charged separately. + */ unsigned long socket_pressure; /* Legacy tcp memory accounting */ @@ -1704,8 +1709,8 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) - return true; + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return !!memcg->tcpmem_pressure; do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index b52644771cc4..22c6689d9302 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -244,6 +244,14 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (mem_cgroup_disabled()) return; + /* + * The in-kernel users only care about the reclaim efficiency + * for this @memcg rather than the whole subtree, and there + * isn't and won't be any in-kernel user in a legacy cgroup. + */ + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !tree) + return; + vmpr = memcg_to_vmpressure(memcg); /*