[v1] net/sched: act_pedit: really ensure the skb is writable

[PATCH net] net/sched: act_pedit: really ensure the skb is writable

Posted by Paolo Abeni 1 year, 11 months ago

Currently pedit tries to ensure that the accessed skb offset
is writeble 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.

Address the issue keeping track of a rough over-estimate highest skb
offset accessed by the action and ensure such offset is really
writable.

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

v1 -> v2:
 - cleanup hint update (Jakub)
 - avoid raices while accessing the hint (Jakub)
 - re-organize the comments for clarity

Fixes: db2c24175d14 ("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>
---
 include/net/tc_act/tc_pedit.h |  1 +
 net/sched/act_pedit.c         | 25 +++++++++++++++++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index 748cf87a4d7e..3e02709a1df6 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/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;
 };
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index e01ef7f109f4..0fc07532e6f6 100644
--- a/net/sched/act_pedit.c
+++ b/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)))
+		return p->tcf_action;
+
 	tcf_lastuse_update(&p->tcf_tm);
 
 	if (p->tcfp_nkeys > 0) {
-- 
2.35.1

Re: [PATCH net] net/sched: act_pedit: really ensure the skb is writable

Posted by Mat Martineau 1 year, 11 months ago

On Thu, 5 May 2022, Paolo Abeni wrote:

> Currently pedit tries to ensure that the accessed skb offset
> is writeble 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.
>
> Address the issue keeping track of a rough over-estimate highest skb
> offset accessed by the action and ensure such offset is really
> writable.
>
> Note that this may cause performance regressions in some scenario,
> but hopefully pedit is not critical path.
>
> v1 -> v2:
> - cleanup hint update (Jakub)
> - avoid raices while accessing the hint (Jakub)
> - re-organize the comments for clarity
>
> Fixes: db2c24175d14 ("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>
> ---
> include/net/tc_act/tc_pedit.h |  1 +
> net/sched/act_pedit.c         | 25 +++++++++++++++++++++----
> 2 files changed, 22 insertions(+), 4 deletions(-)
>
> diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
> index 748cf87a4d7e..3e02709a1df6 100644
> --- a/include/net/tc_act/tc_pedit.h
> +++ b/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;
> };
> diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
> index e01ef7f109f4..0fc07532e6f6 100644
> --- a/net/sched/act_pedit.c
> +++ b/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)))
> +		return p->tcf_action;

Now that this hunk of code happens after the spinlock is acquired, that 
lock needs to be released before returning.

> +
> 	tcf_lastuse_update(&p->tcf_tm);
>
> 	if (p->tcfp_nkeys > 0) {
> -- 
> 2.35.1
>
>
>

--
Mat Martineau
Intel

Re: [PATCH net] net/sched: act_pedit: really ensure the skb is writable

Posted by Paolo Abeni 1 year, 11 months ago

On Thu, 2022-05-05 at 13:30 -0700, Mat Martineau wrote:
> On Thu, 5 May 2022, Paolo Abeni wrote:
> 
> > Currently pedit tries to ensure that the accessed skb offset
> > is writeble 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.
> > 
> > Address the issue keeping track of a rough over-estimate highest skb
> > offset accessed by the action and ensure such offset is really
> > writable.
> > 
> > Note that this may cause performance regressions in some scenario,
> > but hopefully pedit is not critical path.
> > 
> > v1 -> v2:
> > - cleanup hint update (Jakub)
> > - avoid raices while accessing the hint (Jakub)
> > - re-organize the comments for clarity
> > 
> > Fixes: db2c24175d14 ("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>
> > ---
> > include/net/tc_act/tc_pedit.h |  1 +
> > net/sched/act_pedit.c         | 25 +++++++++++++++++++++----
> > 2 files changed, 22 insertions(+), 4 deletions(-)
> > 
> > diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
> > index 748cf87a4d7e..3e02709a1df6 100644
> > --- a/include/net/tc_act/tc_pedit.h
> > +++ b/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;
> > };
> > diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
> > index e01ef7f109f4..0fc07532e6f6 100644
> > --- a/net/sched/act_pedit.c
> > +++ b/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)))
> > +		return p->tcf_action;
> 
> Now that this hunk of code happens after the spinlock is acquired, that 
> lock needs to be released before returning.

Oh my! I really should take more care. Thank you for catching it!

I'll send a v3.

/P