net/sched: act_pedit: really ensure the skb is writable

Currently pedit tries to ensure that the accessed skb offset
is writable via skb_unclone(). The action potentially allows
touching any skb bytes, so it may end-up modifying shared data.

The above causes some sporadic MPTCP self-test failures, due to
this code:

	tc -n $ns2 filter add dev ns2eth$i egress \
		protocol ip prio 1000 \
		handle 42 fw \
		action pedit munge offset 148 u8 invert \
		pipe csum tcp \
		index 100

The above modifies a data byte outside the skb head and the skb is
a cloned one, carrying a TCP output packet.

This change addresses the issue by keeping track of a rough
over-estimate highest skb offset accessed by the action and ensuring
such offset is really writable.

Note that this may cause performance regressions in some scenarios,
but hopefully pedit is not in the critical path.

Fixes: db2c2417 ("act_pedit: access skb->data safely")
Acked-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Tested-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/1fcf78e6679d0a287dd61bb0f04730ce33b3255d.1652194627.git.pabeni@redhat.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/tc_act/tc_pedit.h

@@ -14,6 +14,7 @@ struct tcf_pedit {
 	struct tc_action	common;
 	unsigned char		tcfp_nkeys;
 	unsigned char		tcfp_flags;
+	u32			tcfp_off_max_hint;
 	struct tc_pedit_key	*tcfp_keys;
 	struct tcf_pedit_key_ex	*tcfp_keys_ex;
 };

net/sched/act_pedit.c

@@ -149,7 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	struct nlattr *pattr;
 	struct tcf_pedit *p;
 	int ret = 0, err;
-	int ksize;
+	int i, ksize;
 	u32 index;
 
 	if (!nla) {
@@ -228,6 +228,18 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		p->tcfp_nkeys = parm->nkeys;
 	}
 	memcpy(p->tcfp_keys, parm->keys, ksize);
+	p->tcfp_off_max_hint = 0;
+	for (i = 0; i < p->tcfp_nkeys; ++i) {
+		u32 cur = p->tcfp_keys[i].off;
+
+		/* The AT option can read a single byte, we can bound the actual
+		 * value with uchar max.
+		 */
+		cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift;
+
+		/* Each key touches 4 bytes starting from the computed offset */
+		p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4);
+	}
 
 	p->tcfp_flags = parm->flags;
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
@@ -308,13 +320,18 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
 			 struct tcf_result *res)
 {
 	struct tcf_pedit *p = to_pedit(a);
+	u32 max_offset;
 	int i;
 
-	if (skb_unclone(skb, GFP_ATOMIC))
-		return p->tcf_action;
-
 	spin_lock(&p->tcf_lock);
 
+	max_offset = (skb_transport_header_was_set(skb) ?
+		      skb_transport_offset(skb) :
+		      skb_network_offset(skb)) +
+		     p->tcfp_off_max_hint;
+	if (skb_ensure_writable(skb, min(skb->len, max_offset)))
+		goto unlock;
+
 	tcf_lastuse_update(&p->tcf_tm);
 
 	if (p->tcfp_nkeys > 0) {
@@ -403,6 +420,7 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
 	p->tcf_qstats.overlimits++;
 done:
 	bstats_update(&p->tcf_bstats, skb);
+unlock:
 	spin_unlock(&p->tcf_lock);
 	return p->tcf_action;
 }