diff options
| author | Zihan Xi <zihanx@nebusec.ai> | 2026-09-08 11:58:39 +0000 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-09-10 08:48:44 -0700 |
| commit | b7ee18725f2292ab554aa96a101ae42d45f008bd (patch) | |
| tree | e9f27a905de4f01c5c44bf17c355c2bcc72477ce | |
| parent | 6ca81bbc31cdc964e4b74d17b86215d4a810a56f (diff) | |
ipmr: account multicast table and route memory
A netadmin in a user+net namespace can create many IPv4 and IPv6
multicast routing tables with MRT_TABLE and MRT6_TABLE. Each unseen
id allocates an mr_table via the shared mr_table_alloc(), links it
into the per-net list, and leaves it until netns teardown. Those
objects were not charged to memcg, so the host unreclaimable slab
grows with the table count.
Account mr_table allocations with GFP_KERNEL_ACCOUNT and mark the
IPv4/IPv6 MFC caches SLAB_ACCOUNT. This matches the established
handling of IP addresses, routes and alternate interface names.
Unresolved MFC entries are still allocated from softIRQ with
GFP_ATOMIC and are not charged. They expire after 10 seconds and are
bounded by the socket receive queue; see commit 0079ad8e8dc3
("ipmr: remove hard code cache_resolve_queue_len limit").
Fixes: f0ad0860d01e ("ipv4: ipmr: support multiple tables")
Fixes: d1db275dd3f6 ("ipv6: ip6mr: support multiple tables")
Cc: stable@vger.kernel.org
Reported-by: Vega <vega@nebusec.ai>
Signed-off-by: Zihan Xi <zihanx@nebusec.ai>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/050b58f7fc6b45da0fb12768ebb62d18fa46133d.1788784801.git.zihanx@nebusec.ai
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
| -rw-r--r-- | net/ipv4/ipmr.c | 3 | ||||
| -rw-r--r-- | net/ipv4/ipmr_base.c | 2 | ||||
| -rw-r--r-- | net/ipv6/ip6mr.c | 2 |
3 files changed, 4 insertions, 3 deletions
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e5f2b1c6150d..b9c544d48c45 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -3376,7 +3376,8 @@ int __init ip_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); + mrt_cachep = KMEM_CACHE(mfc_cache, + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); err = register_pernet_subsys(&ipmr_net_ops); if (err) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 867b24beded1..a0ec6d19a237 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -52,7 +52,7 @@ mr_table_alloc(struct net *net, u32 id, struct mr_table *mrt; int err; - mrt = kzalloc_obj(*mrt); + mrt = kzalloc_obj(*mrt, GFP_KERNEL_ACCOUNT); if (!mrt) return ERR_PTR(-ENOMEM); mrt->id = id; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 3f2ed9b77deb..9d8116b5edb1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1427,7 +1427,7 @@ int __init ip6_mr_init(void) { int err; - mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); + mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!mrt_cachep) return -ENOMEM; |