packet: copy user buffers before orphan or clone (5cd8d46e) · Commits · 戴 / test

tpacket_snd sends packets with user pages linked into skb frags. It notifies that pages can be reused when the skb is released by setting skb->destructor to tpacket_destruct_skb. This can cause data corruption if the skb is orphaned (e.g., on transmit through veth) or cloned (e.g., on mirror to another psock). Create a kernel-private copy of data in these cases, same as tun/tap zerocopy transmission. Reuse that infrastructure: mark the skb as SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx). Unlike other zerocopy packets, do not set shinfo destructor_arg to struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify when the original skb is released and a timestamp is recorded. Do not change this timestamp behavior. The ubuf_info->callback is not needed anyway, as no zerocopy notification is expected. Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The resulting value is not a valid ubuf_info pointer, nor a valid tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this. The fix relies on features introduced in commit ("sock: add MSG_ZEROCOPY"), so can be backported as is only to 4.14. Tested with from `./in_netns.sh ./txring_overwrite` from http://github.com/wdebruij/kerneltools/tests Fixes: ("net: TX_RING and packet mmap") Reported-by:

Anand H. Krishnan <anandhkrishnan@gmail.com> Signed-off-by:

Willem de Bruijn <willemb@google.com> Signed-off-by:

David S. Miller <davem@davemloft.net>

include/linux/skbuff.h

+17 −1

Original line number	Diff line number	Diff line
		@@ -1326,6 +1326,22 @@ static inline void skb_zcopy_set(struct sk_buff skb, struct ubuf_info uarg)
		}
		}

		static inline void skb_zcopy_set_nouarg(struct sk_buff skb, void val)
		{
		skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val \| 0x1UL);
		skb_shinfo(skb)->tx_flags \|= SKBTX_ZEROCOPY_FRAG;
		}

		static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
		{
		return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
		}

		static inline void skb_zcopy_get_nouarg(struct sk_buff skb)
		{
		return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
		}

		/* Release a reference on a zerocopy structure */
		static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
		{
		@@ -1335,7 +1351,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy)
		if (uarg->callback == sock_zerocopy_callback) {
		uarg->zerocopy = uarg->zerocopy && zerocopy;
		sock_zerocopy_put(uarg);
		} else {
		} else if (!skb_zcopy_is_nouarg(skb)) {
		uarg->callback(uarg, zerocopy);
		}

net/packet/af_packet.c

+2 −2

Original line number	Diff line number	Diff line
		@@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
		void *ph;
		__u32 ts;

		ph = skb_shinfo(skb)->destructor_arg;
		ph = skb_zcopy_get_nouarg(skb);
		packet_dec_pending(&po->tx_ring);

		ts = __packet_set_timestamp(po, ph, skb);
		@@ -2461,7 +2461,7 @@ static int tpacket_fill_skb(struct packet_sock po, struct sk_buff skb,
		skb->mark = po->sk.sk_mark;
		skb->tstamp = sockc->transmit_time;
		sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
		skb_shinfo(skb)->destructor_arg = ph.raw;
		skb_zcopy_set_nouarg(skb, ph.raw);

		skb_reserve(skb, hlen);
		skb_reset_network_header(skb);

Admin message