memcg: net: track network throttling due to memcg memory pressure

The kernel can throttle network sockets if the memory cgroup associated
with the corresponding socket is under memory pressure.  The throttling
actions include clamping the transmit window, failing to expand receive or
send buffers, aggressively prune out-of-order receive queue, FIN deferred
to a retransmitted packet and more.  Let's add memcg metric to track such
throttling actions.

At the moment memcg memory pressure is defined through vmpressure and in
future it may be defined using PSI or we may add more flexible way for the
users to define memory pressure, maybe through ebpf.  However the
potential throttling actions will remain the same, so this newly
introduced metric will continue to track throttling actions irrespective
of how memcg memory pressure is defined.

Link: https://lkml.kernel.org/r/20251016161035.86161-1-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Daniel Sedlak <daniel.sedlak@cdn77.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kacinski <kuba@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 14 insertions, 1 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 0e6c67ac585a..3345961c30ac 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1515,6 +1515,10 @@ The following nested keys are defined.
           oom_group_kill
                 The number of times a group OOM has occurred.
 
+          sock_throttled
+                The number of times network sockets associated with
+                this cgroup are throttled.
+
   memory.events.local
 	Similar to memory.events but the fields in the file are local
 	to the cgroup i.e. not hierarchical. The file modified event
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 873e510d6f8d..5fe254813123 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,6 +52,7 @@ enum memcg_memory_event {
 	MEMCG_SWAP_HIGH,
 	MEMCG_SWAP_MAX,
 	MEMCG_SWAP_FAIL,
+	MEMCG_SOCK_THROTTLED,
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 60bcb13f045c..ff7d49af1619 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2635,8 +2635,12 @@ static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk)
 #endif /* CONFIG_MEMCG_V1 */
 
 	do {
-		if (time_before64(get_jiffies_64(), mem_cgroup_get_socket_pressure(memcg)))
+		if (time_before64(get_jiffies_64(),
+				  mem_cgroup_get_socket_pressure(memcg))) {
+			memcg_memory_event(mem_cgroup_from_sk(sk),
+					   MEMCG_SOCK_THROTTLED);
 			return true;
+		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
 	return false;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index fdee387f0d6b..8df671c59987 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4704,6 +4704,7 @@ void cgroup_file_notify(struct cgroup_file *cfile)
 	}
 	spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
 }
+EXPORT_SYMBOL_GPL(cgroup_file_notify);
 
 /**
  * cgroup_file_show - show or hide a hidden cgroup file
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3ae5cbcaed75..976412c8196e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -81,6 +81,7 @@ struct cgroup_subsys memory_cgrp_subsys __read_mostly;
 EXPORT_SYMBOL(memory_cgrp_subsys);
 
 struct mem_cgroup *root_mem_cgroup __read_mostly;
+EXPORT_SYMBOL(root_mem_cgroup);
 
 /* Active memory cgroup to use from an interrupt context */
 DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
@@ -4463,6 +4464,8 @@ static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
 		   atomic_long_read(&events[MEMCG_OOM_KILL]));
 	seq_printf(m, "oom_group_kill %lu\n",
 		   atomic_long_read(&events[MEMCG_OOM_GROUP_KILL]));
+	seq_printf(m, "sock_throttled %lu\n",
+		   atomic_long_read(&events[MEMCG_SOCK_THROTTLED]));
 }
 
 static int memory_events_show(struct seq_file *m, void *v)