From 06dad31134ce2a747433c09f4842574ceba54835 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Sat, 16 May 2026 07:28:53 +0900 Subject: [PATCH] net: skbuff: propagate shared-frag marker through frag-transfer helpers Two frag-transfer helpers (__pskb_copy_fclone() and skb_shift()) fail to propagate the SKBFL_SHARED_FRAG bit in skb_shinfo()->flags when moving frags from source to destination. __pskb_copy_fclone() defers the rest of the shinfo metadata to skb_copy_header() after copying frag descriptors, but that helper only carries over gso_{size,segs, type} and never touches skb_shinfo()->flags; skb_shift() moves frag descriptors directly and leaves flags untouched. As a result, the destination skb keeps a reference to the same externally-owned or page-cache-backed pages while reporting skb_has_shared_frag() as false. The mismatch is harmful in any in-place writer that uses skb_has_shared_frag() to decide whether shared pages must be detoured through skb_cow_data(). ESP input is one such writer (esp4.c, esp6.c), and a single nft 'dup to ' rule -- or any other nf_dup_ipv4() / xt_TEE caller -- is enough to land a pskb_copy()'d skb in esp_input() with the marker stripped, letting an unprivileged user write into the page cache of a root-owned read-only file via authencesn-ESN stray writes. Set SKBFL_SHARED_FRAG on the destination whenever frag descriptors were actually moved from the source. skb_copy() and skb_copy_expand() share skb_copy_header() too but linearize all paged data into freshly allocated head storage and emerge with nr_frags == 0, so skb_has_shared_frag() returns false on its own; they need no change. The same omission exists in skb_gro_receive() and skb_gro_receive_list(). The former moves the incoming skb's frag descriptors into the accumulator's last sub-skb via two paths (a direct frag-move loop and the head_frag + memcpy path); the latter chains the incoming skb whole onto p's frag_list. Downstream skb_segment() reads only skb_shinfo(p)->flags, and skb_segment_list() reuses each sub-skb's shinfo as the nskb -- both p and lp must carry the marker. The same omission also exists in tcp_clone_payload(), which builds an MTU probe skb by moving frag descriptors from skbs on sk_write_queue into a freshly allocated nskb. The helper falls into the same family and warrants the same fix for consistency; no TCP TX-side in-place writer is currently known to reach a user page through this gap, but a future consumer depending on the marker would regress silently. The same omission exists in skb_segment(): the per-iteration flag merge takes only head_skb's flag, and the inner switch that rebinds frag_skb to list_skb on head_skb-frags exhaustion does not fold the new frag_skb's flag into nskb. Fold frag_skb's flag at both sites so segments drawing frags from frag_list members carry the marker. Fixes: cef401de7be8 ("net: fix possible wrong checksum generation") Fixes: f4c50a4034e6 ("xfrm: esp: avoid in-place decrypt on shared skb frags") Suggested-by: Sabrina Dubroca Suggested-by: Sultan Alsawaf Suggested-by: Ben Hutchings Suggested-by: Lin Ma Suggested-by: Jingguo Tan Suggested-by: Aaron Esau Cc: stable@vger.kernel.org Signed-off-by: Hyunwoo Kim Tested-by: Rajat Gupta Link: https://patch.msgid.link/ageeJfJHwgzmKXbh@v4bel Signed-off-by: Paolo Abeni (cherry picked from commit 48f6a5356a33dd78e7144ae1faef95ffc990aae0) Orabug: 39368828 CVE: CVE-2026-46300 Conflicts: - net/core/gro.c - Not present in UEK6U3 - net/core/skbuff.c UEK6U3 doesn't have commit: 06b4feb3 ("net: group skb_shinfo zerocopy related bits together.") so used skb_shinfo(nskb)->tx_flags - net/ipv4/tcp_output.c - net/ipv4/tcp_output.c - UEK6U3 doesn't have commit: 73601329 ("tcp: let tcp_mtu_probe() build headless packets") so we need not take the hunk corresponding to tcp_clone_payload() Change-Id: I19fe41c96158d2614b04d4593083826135418615 Signed-off-by: Harshit Mogalapalli Reviewed-by: Joseph Salisbury Signed-off-by: Alok Tiwari Signed-off-by: Tashfin Shakeer Rhythm --- net/core/skbuff.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b240d85ea1f1..a54b7a4ad046 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1605,6 +1605,7 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; + skb_shinfo(n)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; } if (skb_has_frag_list(skb)) { @@ -3489,6 +3490,8 @@ onlymerged: tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; + skb_shinfo(tgt)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + /* Yak, is it really working this way? Some helper please? */ skb->len -= shiftlen; skb->data_len -= shiftlen; @@ -3832,6 +3835,8 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) p->truesize += skb->truesize; p->len += skb->len; + skb_shinfo(p)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + NAPI_GRO_CB(skb)->same_flow = 1; return 0; @@ -4061,7 +4066,8 @@ normal: skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & + skb_shinfo(nskb)->tx_flags |= (skb_shinfo(head_skb)->tx_flags | + skb_shinfo(frag_skb)->tx_flags) & SKBTX_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) @@ -4078,6 +4084,9 @@ normal: nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; + + skb_shinfo(nskb)->tx_flags |= skb_shinfo(frag_skb)->tx_flags & SKBTX_SHARED_FRAG; + if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { @@ -4294,10 +4303,12 @@ done: p->data_len += len; p->truesize += delta_truesize; p->len += len; + skb_shinfo(p)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; + skb_shinfo(lp)->tx_flags |= skbinfo->tx_flags & SKBTX_SHARED_FRAG; } NAPI_GRO_CB(skb)->same_flow = 1; return 0;