korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-14 07:44:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

bpf: Fix too early release of tcx_entry

Browse Source 
[ Upstream commit 1cb6f0bae5 ]

Pedro Pinto and later independently also Hyunwoo Kim and Wongi Lee reported
an issue that the tcx_entry can be released too early leading to a use
after free (UAF) when an active old-style ingress or clsact qdisc with a
shared tc block is later replaced by another ingress or clsact instance.

Essentially, the sequence to trigger the UAF (one example) can be as follows:

  1. A network namespace is created
  2. An ingress qdisc is created. This allocates a tcx_entry, and
     &tcx_entry->miniq is stored in the qdisc's miniqp->p_miniq. At the
     same time, a tcf block with index 1 is created.
  3. chain0 is attached to the tcf block. chain0 must be connected to
     the block linked to the ingress qdisc to later reach the function
     tcf_chain0_head_change_cb_del() which triggers the UAF.
  4. Create and graft a clsact qdisc. This causes the ingress qdisc
     created in step 1 to be removed, thus freeing the previously linked
     tcx_entry:

     rtnetlink_rcv_msg()
       => tc_modify_qdisc()
         => qdisc_create()
           => clsact_init() [a]
         => qdisc_graft()
           => qdisc_destroy()
             => __qdisc_destroy()
               => ingress_destroy() [b]
                 => tcx_entry_free()
                   => kfree_rcu() // tcx_entry freed

  5. Finally, the network namespace is closed. This registers the
     cleanup_net worker, and during the process of releasing the
     remaining clsact qdisc, it accesses the tcx_entry that was
     already freed in step 4, causing the UAF to occur:

     cleanup_net()
       => ops_exit_list()
         => default_device_exit_batch()
           => unregister_netdevice_many()
             => unregister_netdevice_many_notify()
               => dev_shutdown()
                 => qdisc_put()
                   => clsact_destroy() [c]
                     => tcf_block_put_ext()
                       => tcf_chain0_head_change_cb_del()
                         => tcf_chain_head_change_item()
                           => clsact_chain_head_change()
                             => mini_qdisc_pair_swap() // UAF

There are also other variants, the gist is to add an ingress (or clsact)
qdisc with a specific shared block, then to replace that qdisc, waiting
for the tcx_entry kfree_rcu() to be executed and subsequently accessing
the current active qdisc's miniq one way or another.

The correct fix is to turn the miniq_active boolean into a counter. What
can be observed, at step 2 above, the counter transitions from 0->1, at
step [a] from 1->2 (in order for the miniq object to remain active during
the replacement), then in [b] from 2->1 and finally [c] 1->0 with the
eventual release. The reference counter in general ranges from [0,2] and
it does not need to be atomic since all access to the counter is protected
by the rtnl mutex. With this in place, there is no longer a UAF happening
and the tcx_entry is freed at the correct time.

Fixes: e420bed025 ("bpf: Add fd-based tcx multi-prog infra with link support")
Reported-by: Pedro Pinto <xten@osec.io>
Co-developed-by: Pedro Pinto <xten@osec.io>
Signed-off-by: Pedro Pinto <xten@osec.io>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Hyunwoo Kim <v4bel@theori.io>
Cc: Wongi Lee <qwerty@theori.io>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240708133130.11609-1-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Daniel Borkmann 2024-07-08 15:31:29 +02:00 committed by Greg Kroah-Hartman
parent 124886cf20
commit 230bb13650
2 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
include/net/tcx.h
View File

@ -13,7 +13,7 @@ struct mini_Qdisc;
struct tcx_entry {
struct mini_Qdisc __rcu *miniq;
struct bpf_mprog_bundle bundle;
bool miniq_active;
u32 miniq_active;
struct rcu_head rcu;
};
@ -129,11 +129,16 @@ static inline void tcx_skeys_dec(bool ingress)
tcx_dec();
}
static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry,
const bool active)
static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry)
{
ASSERT_RTNL();
tcx_entry(entry)->miniq_active = active;
tcx_entry(entry)->miniq_active++;
}
static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry)
{
ASSERT_RTNL();
tcx_entry(entry)->miniq_active--;
}
static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry)

12
net/sched/sch_ingress.c
View File

@ -91,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
entry = tcx_entry_fetch_or_create(dev, true, &created);
if (!entry)
return -ENOMEM;
tcx_miniq_set_active(entry, true);
tcx_miniq_inc(entry);
mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq);
if (created)
tcx_entry_update(dev, entry, true);
@ -121,7 +121,7 @@ static void ingress_destroy(struct Qdisc *sch)
tcf_block_put_ext(q->block, sch, &q->block_info);
if (entry) {
tcx_miniq_set_active(entry, false);
tcx_miniq_dec(entry);
if (!tcx_entry_is_active(entry)) {
tcx_entry_update(dev, NULL, true);
tcx_entry_free(entry);
@ -256,7 +256,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
entry = tcx_entry_fetch_or_create(dev, true, &created);
if (!entry)
return -ENOMEM;
tcx_miniq_set_active(entry, true);
tcx_miniq_inc(entry);
mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq);
if (created)
tcx_entry_update(dev, entry, true);
@ -275,7 +275,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
entry = tcx_entry_fetch_or_create(dev, false, &created);
if (!entry)
return -ENOMEM;
tcx_miniq_set_active(entry, true);
tcx_miniq_inc(entry);
mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq);
if (created)
tcx_entry_update(dev, entry, false);
@ -301,7 +301,7 @@ static void clsact_destroy(struct Qdisc *sch)
tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info);
if (ingress_entry) {
tcx_miniq_set_active(ingress_entry, false);
tcx_miniq_dec(ingress_entry);
if (!tcx_entry_is_active(ingress_entry)) {
tcx_entry_update(dev, NULL, true);
tcx_entry_free(ingress_entry);
@ -309,7 +309,7 @@ static void clsact_destroy(struct Qdisc *sch)
}
if (egress_entry) {
tcx_miniq_set_active(egress_entry, false);
tcx_miniq_dec(egress_entry);
if (!tcx_entry_is_active(egress_entry)) {
tcx_entry_update(dev, NULL, false);
tcx_entry_free(egress_entry);