OrgACRN
/
acrn-kernel
mirror of https://github.com/projectacrn/acrn-kernel.git
1
0
Fork 0
Code Issues Releases Wiki Activity

net/sched: act_ct: Take per-cb reference to tcf_ct_flow_table 

[ Upstream commit 125f1c7f26ffcdbf96177abe75b70c1a6ceb17bc ]

The referenced change added custom cleanup code to act_ct to delete any
callbacks registered on the parent block when deleting the
tcf_ct_flow_table instance. However, the underlying issue is that the
drivers don't obtain the reference to the tcf_ct_flow_table instance when
registering callbacks which means that not only driver callbacks may still
be on the table when deleting it but also that the driver can still have
pointers to its internal nf_flowtable and can use it concurrently which
results either warning in netfilter[0] or use-after-free.

Fix the issue by taking a reference to the underlying struct
tcf_ct_flow_table instance when registering the callback and release the
reference when unregistering. Expose new API required for such reference
counting by adding two new callbacks to nf_flowtable_type and implementing
them for act_ct flowtable_ct type. This fixes the issue by extending the
lifetime of nf_flowtable until all users have unregistered.

[0]:
[106170.938634] ------------[ cut here ]------------
[106170.939111] WARNING: CPU: 21 PID: 3688 at include/net/netfilter/nf_flow_table.h:262 mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.940108] Modules linked in: act_ct nf_flow_table act_mirred act_skbedit act_tunnel_key vxlan cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa bonding openvswitch nsh rpcrdma rdma_ucm
ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat xt_addrtype xt_conntrack nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_regis
try overlay mlx5_core
[106170.943496] CPU: 21 PID: 3688 Comm: kworker/u48:0 Not tainted 6.6.0-rc7_for_upstream_min_debug_2023_11_01_13_02 #1
[106170.944361] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[106170.945292] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core]
[106170.945846] RIP: 0010:mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.946413] Code: 89 ef 48 83 05 71 a4 14 00 01 e8 f4 06 04 e1 48 83 05 6c a4 14 00 01 48 83 c4 28 5b 5d 41 5c 41 5d c3 48 83 05 d1 8b 14 00 01 <0f> 0b 48 83 05 d7 8b 14 00 01 e9 96 fe ff ff 48 83 05 a2 90 14 00
[106170.947924] RSP: 0018:ffff88813ff0fcb8 EFLAGS: 00010202
[106170.948397] RAX: 0000000000000000 RBX: ffff88811eabac40 RCX: ffff88811eabad48
[106170.949040] RDX: ffff88811eab8000 RSI: ffffffffa02cd560 RDI: 0000000000000000
[106170.949679] RBP: ffff88811eab8000 R08: 0000000000000001 R09: ffffffffa0229700
[106170.950317] R10: ffff888103538fc0 R11: 0000000000000001 R12: ffff88811eabad58
[106170.950969] R13: ffff888110c01c00 R14: ffff888106b40000 R15: 0000000000000000
[106170.951616] FS:  0000000000000000(0000) GS:ffff88885fd40000(0000) knlGS:0000000000000000
[106170.952329] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[106170.952834] CR2: 00007f1cefd28cb0 CR3: 000000012181b006 CR4: 0000000000370ea0
[106170.953482] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[106170.954121] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[106170.954766] Call Trace:
[106170.955057]  <TASK>
[106170.955315]  ? __warn+0x79/0x120
[106170.955648]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.956172]  ? report_bug+0x17c/0x190
[106170.956537]  ? handle_bug+0x3c/0x60
[106170.956891]  ? exc_invalid_op+0x14/0x70
[106170.957264]  ? asm_exc_invalid_op+0x16/0x20
[106170.957666]  ? mlx5_del_flow_rules+0x10/0x310 [mlx5_core]
[106170.958172]  ? mlx5_tc_ct_block_flow_offload_add+0x1240/0x1240 [mlx5_core]
[106170.958788]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.959339]  ? mlx5_tc_ct_del_ft_cb+0xc6/0x2b0 [mlx5_core]
[106170.959854]  ? mapping_remove+0x154/0x1d0 [mlx5_core]
[106170.960342]  ? mlx5e_tc_action_miss_mapping_put+0x4f/0x80 [mlx5_core]
[106170.960927]  mlx5_tc_ct_delete_flow+0x76/0xc0 [mlx5_core]
[106170.961441]  mlx5_free_flow_attr_actions+0x13b/0x220 [mlx5_core]
[106170.962001]  mlx5e_tc_del_fdb_flow+0x22c/0x3b0 [mlx5_core]
[106170.962524]  mlx5e_tc_del_flow+0x95/0x3c0 [mlx5_core]
[106170.963034]  mlx5e_flow_put+0x73/0xe0 [mlx5_core]
[106170.963506]  mlx5e_put_flow_list+0x38/0x70 [mlx5_core]
[106170.964002]  mlx5e_rep_update_flows+0xec/0x290 [mlx5_core]
[106170.964525]  mlx5e_rep_neigh_update+0x1da/0x310 [mlx5_core]
[106170.965056]  process_one_work+0x13a/0x2c0
[106170.965443]  worker_thread+0x2e5/0x3f0
[106170.965808]  ? rescuer_thread+0x410/0x410
[106170.966192]  kthread+0xc6/0xf0
[106170.966515]  ? kthread_complete_and_exit+0x20/0x20
[106170.966970]  ret_from_fork+0x2d/0x50
[106170.967332]  ? kthread_complete_and_exit+0x20/0x20
[106170.967774]  ret_from_fork_asm+0x11/0x20
[106170.970466]  </TASK>
[106170.970726] ---[ end trace 0000000000000000 ]---

Fixes: 77ac5e40c4 ("net/sched: act_ct: remove and free nf_table callbacks")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Vlad Buslov 2023-12-05 18:25:54 +01:00 committed by Greg Kroah-Hartman
parent 2bb4ecb334
commit a29b15cc68
2 changed files with 38 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
include/net/netfilter/nf_flow_table.h
View File

@ -62,6 +62,8 @@ struct nf_flowtable_type {
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule);
void (*free)(struct nf_flowtable *ft);
void (*get)(struct nf_flowtable *ft);
void (*put)(struct nf_flowtable *ft);
nf_hookfn *hook;
struct module *owner;
};
@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
}
list_add_tail(&block_cb->list, &block->cb_list);
up_write(&flow_table->flow_block_lock);
if (flow_table->type->get)
flow_table->type->get(flow_table);
return 0;
unlock:
up_write(&flow_table->flow_block_lock);
@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
WARN_ON(true);
}
up_write(&flow_table->flow_block_lock);
if (flow_table->type->put)
flow_table->type->put(flow_table);
}
int flow_offload_route_init(struct flow_offload *flow,

34
net/sched/act_ct.c
View File

@ -280,9 +280,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
!test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
}
static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
static void tcf_ct_nf_get(struct nf_flowtable *ft)
{
struct tcf_ct_flow_table *ct_ft =
container_of(ft, struct tcf_ct_flow_table, nf_ft);
tcf_ct_flow_table_get_ref(ct_ft);
}
static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
static void tcf_ct_nf_put(struct nf_flowtable *ft)
{
struct tcf_ct_flow_table *ct_ft =
container_of(ft, struct tcf_ct_flow_table, nf_ft);
tcf_ct_flow_table_put(ct_ft);
}
static struct nf_flowtable_type flowtable_ct = {
.gc = tcf_ct_flow_is_outdated,
.action = tcf_ct_flow_table_fill_actions,
.get = tcf_ct_nf_get,
.put = tcf_ct_nf_put,
.owner = THIS_MODULE,
};
@ -331,9 +353,13 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
return err;
}
static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
{
refcount_inc(&ct_ft->ref);
}
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
struct flow_block *block;
@ -341,13 +367,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
/* Remove any remaining callbacks before cleanup */
block = &ct_ft->nf_ft.flow_block;
down_write(&ct_ft->nf_ft.flow_block_lock);
list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
list_del(&block_cb->list);
flow_block_cb_free(block_cb);
}
WARN_ON(!list_empty(&block->cb_list));
up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);