net/sched/cls_bpf.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
Quan Sun reported [1] a stack overflow in cls_bpf_offload_cmd().
Reproducer on netdevsim: add a skip_sw cls_bpf filter, set the
bpf_tc_accept debugfs knob to 0, then `tc filter replace`. The replace
calls tc_setup_cb_replace() which fails. cls_bpf_offload_cmd() then
swaps prog/oldprog and recursively calls itself to roll back. But
bpf_tc_accept=0 makes the rollback fail too, which triggers yet another
rollback frame with the same arguments, and so on until the stack is
exhausted.
bpf_tc_accept is just a convenient knob for the reproducer. Any driver
whose tc_setup_cb_replace() fails twice in a row can hit the same loop,
so this is not a netdevsim-only issue.
Two ways to fix it:
1) Have the rollback call tc_setup_cb_add() on oldprog instead of
re-entering cls_bpf_offload_cmd().
2) Mark the rollback frame with a flag and skip a second-level
rollback from inside it.
Go with (2). It is the smaller change and keeps the original behaviour:
the rollback still goes through tc_setup_cb_replace(), so the driver
gets one real chance to restore its state. If that attempt also fails,
we just return the original error instead of recursing.
[1]: https://lore.kernel.org/bpf/ce5a6005-3c5e-4696-9e05-eba9461dc860@std.uestc.edu.cn/T/#u
Fixes: 102740bd9436 ("cls_bpf: fix offload assumptions after callback conversion")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
---
net/sched/cls_bpf.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 9a346b6221b35..d71fbf7cb407e 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -142,7 +142,8 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
struct cls_bpf_prog *oldprog,
- struct netlink_ext_ack *extack)
+ struct netlink_ext_ack *extack,
+ bool is_rollback)
{
struct tcf_block *block = tp->chain->block;
struct tc_cls_bpf_offload cls_bpf = {};
@@ -176,8 +177,8 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
skip_sw, &oldprog->gen_flags,
&oldprog->in_hw_count, true);
- if (prog && err) {
- cls_bpf_offload_cmd(tp, oldprog, prog, extack);
+ if (prog && err && !is_rollback) {
+ cls_bpf_offload_cmd(tp, oldprog, prog, extack, true);
return err;
}
@@ -208,7 +209,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
if (!prog && !oldprog)
return 0;
- return cls_bpf_offload_cmd(tp, prog, oldprog, extack);
+ return cls_bpf_offload_cmd(tp, prog, oldprog, extack, false);
}
static void cls_bpf_stop_offload(struct tcf_proto *tp,
@@ -217,7 +218,7 @@ static void cls_bpf_stop_offload(struct tcf_proto *tp,
{
int err;
- err = cls_bpf_offload_cmd(tp, NULL, prog, extack);
+ err = cls_bpf_offload_cmd(tp, NULL, prog, extack, false);
if (err)
pr_err("Stopping hardware offload failed: %d\n", err);
}
--
2.43.0
© 2016 - 2026 Red Hat, Inc.