[PATCH net v2 1/1] net/sched: fix pedit partial COW leading to page cache corruption

[Jamal Hadi Salim]

From: Rajat Gupta <rajat.gupta@xxxxxxxxxxxxxxxx>

tcf_pedit_act() computes the COW range for skb_ensure_writable()
once before the key loop using tcfp_off_max_hint, but the hint does
not account for the runtime header offset added by typed keys. This
can leave part of the write region un-COW'd.

Fix by moving skb_ensure_writable() inside the per-key loop where
the actual write offset is known, and add overflow checking on the
offset arithmetic. For negative offsets (e.g. Ethernet header edits
at ingress), use skb_cow() to COW the headroom instead. Guard
offset_valid() against INT_MIN, where negation is undefined.

Additionally, linearize skbs with shared frags upfront to prevent
silent data corruption when pedit operates on zero-copy pages
(e.g. from sendfile).

Fixes: 8b796475fd78 ("net/sched: act_pedit: really ensure the skb is writable")
Reported-by: Yiming Qian <yimingqian591@xxxxxxxxx>
Reported-by: Keenan Dong <keenanat2000@xxxxxxxxx>
Reported-by: Han Guidong <2045gemini@xxxxxxxxx>
Reported-by: Zhang Cen <rollkingzzc@xxxxxxxxx>
Tested-by: Victor Nogueira <victor@xxxxxxxxxxxx>
Acked-by: Jamal Hadi Salim <jhs@xxxxxxxxxxxx>
Signed-off-by: Rajat Gupta <rajat.gupta@xxxxxxxxxxxxxxxx>
---
Changes v1->v2:
 1. Do better boundary analysis to cover cloned skbs with frags. Pointed
    out by sashiko-nipa:
    https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260519033950.2037-1-rajat.gupta%40oss.qualcomm.com
 2. As a result of fix #1 remove the skb_has_shared_frag() check, unnecessary.
    Also Jakub has plans where the shared frags is not going to be a "thing"
 3. Make small adjustments everywhere for integer checks, suggested by D. Laight
 4. Remove all reviewers and testers since this is a large enough change.
    Please retest and re-review.
 5. Remove Rajat as reporter since he is the author (which implies he is a reporter)
---
 net/sched/act_pedit.c | 49 ++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 17 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index bc20f08a2789..719bee335e1f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -16,6 +16,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/slab.h>
+#include <linux/overflow.h>
 #include <net/ipv6.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
@@ -323,7 +324,7 @@ static bool offset_valid(struct sk_buff *skb, int offset)
 	if (offset > 0 && offset > skb->len)
 		return false;
 
-	if  (offset < 0 && -offset > skb_headroom(skb))
+	if (offset < 0 && offset < -(int)skb_headroom(skb))
 		return false;
 
 	return true;
@@ -393,18 +394,10 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 	struct tcf_pedit_key_ex *tkey_ex;
 	struct tcf_pedit_parms *parms;
 	struct tc_pedit_key *tkey;
-	u32 max_offset;
 	int i;
 
 	parms = rcu_dereference_bh(p->parms);
 
-	max_offset = (skb_transport_header_was_set(skb) ?
-		      skb_transport_offset(skb) :
-		      skb_network_offset(skb)) +
-		     parms->tcfp_off_max_hint;
-	if (skb_ensure_writable(skb, min(skb->len, max_offset)))
-		goto done;
-
 	tcf_lastuse_update(&p->tcf_tm);
 	tcf_action_update_bstats(&p->common, skb);
 
@@ -412,9 +405,10 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 	tkey_ex = parms->tcfp_keys_ex;
 
 	for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) {
+		int write_offset, write_len;
 		int offset = tkey->off;
 		int hoffset = 0;
-		u32 *ptr, hdata;
+		u32 *ptr;
 		u32 val;
 		int rc;
 
@@ -451,15 +445,38 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 			}
 		}
 
-		if (!offset_valid(skb, hoffset + offset)) {
-			pr_info_ratelimited("tc action pedit offset %d out of bounds\n", hoffset + offset);
+		if (unlikely(check_add_overflow(hoffset, offset,
+						&write_offset))) {
+			pr_info_ratelimited("tc action pedit offset overflow\n");
 			goto bad;
 		}
 
-		ptr = skb_header_pointer(skb, hoffset + offset,
-					 sizeof(hdata), &hdata);
-		if (!ptr)
+		if (!offset_valid(skb, write_offset)) {
+			pr_info_ratelimited("tc action pedit offset %d out of bounds\n",
+					    write_offset);
 			goto bad;
+		}
+
+		if (write_offset < 0) {
+			if (skb_cow(skb, -write_offset))
+				goto bad;
+			if (write_offset + (int)sizeof(*ptr) > 0) {
+				if (skb_ensure_writable(skb,
+							min(skb->len,
+							    write_offset + sizeof(*ptr))))
+					goto bad;
+			}
+		} else {
+			if (unlikely(check_add_overflow(write_offset,
+							(int)sizeof(*ptr),
+							&write_len)))
+				goto bad;
+			if (skb_ensure_writable(skb, min_t(int, skb->len,
+							   write_len)))
+				goto bad;
+		}
+
+		ptr = (u32 *)(skb->data + write_offset);
 		/* just do it, baby */
 		switch (cmd) {
 		case TCA_PEDIT_KEY_EX_CMD_SET:
@@ -474,8 +491,6 @@ TC_INDIRECT_SCOPE int tcf_pedit_act(struct sk_buff *skb,
 		}
 
 		*ptr = ((*ptr & tkey->mask) ^ val);
-		if (ptr == &hdata)
-			skb_store_bits(skb, hoffset + offset, ptr, 4);
 	}
 
 	goto done;
-- 
2.34.1