Since commit bd56a29c7a4e ("net: gro: change skb_gro_network_header()"), skb_gro_header_slow() no longer invalidates NAPI_GRO_CB(skb)->frag0 after pskb_may_pull(). skb_gro_may_pull() keeps comparing against the frag0_len value set in skb_gro_reset_offset(), assuming that after a slow pull, all later accesses are beyond frag0_len. This is not true: - udp4_gro_receive() and udp6_gro_receive() read the network header with skb_gro_network_header() after udp_gro_udphdr() pulled the UDP header. - vxlan_gro_receive() calls skb_gro_remcsum_cleanup() at a lower offset after the inner handlers pulled their headers. - skb_gro_remcsum_process() can pull beyond the inner Ethernet header before eth_gro_receive() reads it. - napi_frags_skb() calls __skb_pull(skb, ETH_HLEN) after a slow pull, so frag0 still points to the Ethernet header. If the pull consumed the first page fragment, __skb_pull_tail() released it. If the head had to grow, pskb_expand_head() freed the old one. These reads, and the 2-byte write in skb_gro_remcsum_cleanup(), then access memory the skb no longer holds a reference on. esp4_gro_receive(), esp6_gro_receive(), skb_gro_receive_list() and udp_gro_receive_segment() also pull directly and never invalidated frag0. Add skb_gro_frag0_invalidate(), which only clears frag0_len, and call it before each of these pulls. This is a single store in the slow path, and frag0 stays non NULL, so skb_gro_network_header() does not need a NULL test. frag0 must be invalidated even if the pull fails: __pskb_pull_tail() can return NULL after pskb_expand_head() freed the old head, for instance if a frag_list member has to be cloned or pulled. As frag0 is now invalidated before a pull that can fail, gro_try_pull_from_frag0() can see an skb whose linear part does not cover skb_gro_offset() while frag0 still points to the start of the packet, for instance after skb_gro_remcsum_cleanup() pulled a shorter length. Copying from frag0 would then corrupt the headers: only use frag0 while frag0_len is not zero, and use pskb_may_pull() otherwise. This was found by Taesoo Kim and Cen Zhang, using LLM assisted code analysis, and confirmed with reproducers. Fixes: bd56a29c7a4e ("net: gro: change skb_gro_network_header()") Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Cc: stable@vger.kernel.org Reported-by: Taesoo Kim Reported-by: Cen Zhang Signed-off-by: Eric Dumazet --- include/net/gro.h | 10 ++++++++++ net/core/gro.c | 9 ++++++++- net/ipv4/esp4_offload.c | 1 + net/ipv4/udp_offload.c | 1 + net/ipv6/esp6_offload.c | 1 + 5 files changed, 21 insertions(+), 1 deletion(-) diff --git a/include/net/gro.h b/include/net/gro.h index 13a8ef217a1d..2e6e4d6da725 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -160,9 +160,19 @@ static inline bool skb_gro_may_pull(const struct sk_buff *skb, return likely(hlen <= NAPI_GRO_CB(skb)->frag0_len); } +/* A pull can release the page fragment frag0 points to, or reallocate + * skb->head, even if it fails. Call this before the pull, to make sure later + * skb_gro_header() and skb_gro_network_header() calls no longer use frag0. + */ +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0_len = 0; +} + static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { + skb_gro_frag0_invalidate(skb); if (!pskb_may_pull(skb, hlen)) return NULL; diff --git a/net/core/gro.c b/net/core/gro.c index 1b033855a20d..49e7f64f2775 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -238,6 +238,7 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) NAPI_GRO_CB(skb)->flush)) return -E2BIG; + skb_gro_frag0_invalidate(skb); if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return -ENOMEM; @@ -454,8 +455,14 @@ static void gro_try_pull_from_frag0(struct sk_buff *skb) { int grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) + if (grow <= 0) + return; + + /* frag0 can only be used if no pull happened. */ + if (likely(NAPI_GRO_CB(skb)->frag0_len)) gro_pull_from_frag0(skb, grow); + else + pskb_may_pull(skb, skb_gro_offset(skb)); } static void gro_flush_oldest(struct gro_node *gro, struct list_head *head) diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index abd77162f5e7..2309468cfc3d 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -37,6 +37,7 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, __be32 seq; __be32 spi; + skb_gro_frag0_invalidate(skb); if (!pskb_pull(skb, offset)) return NULL; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index cf07c3c6611a..cd9d7426b227 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -743,6 +743,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { + skb_gro_frag0_invalidate(skb); if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 22895521a57d..ca947cb94fb7 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -64,6 +64,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, if (NAPI_GRO_CB(skb)->proto == IPPROTO_UDP) encap_type = UDP_ENCAP_ESPINUDP; + skb_gro_frag0_invalidate(skb); if (!pskb_pull(skb, offset)) return NULL; -- 2.53.0