net: fix wrong network header length
Subsystems (5)
PATCH v6 1/2 net: fix wrong network header length
When clatd starts with ebpf offloaing, and NETIF_F_GRO_FRAGLIST is enable, several skbs are gathered in skb_shinfo(skb)->frag_list. The first skb's ipv6 header will be changed to ipv4 after bpf_skb_proto_6_to_4, network_header\transport_header\mac_header have been updated as ipv4 acts, but other skbs in frag_list didnot update anything, just ipv6 packets.
udp_queue_rcv_skb will call skb_segment_list to traverse other skbs in frag_list and make sure right udp payload is delivered to user space. Unfortunately, other skbs in frag_list who are still ipv6 packets are updated like the first skb and will have wrong transport header length.
e.g.before bpf_skb_proto_6_to_4,the first skb and other skbs in frag_list has the same network_header(24)& transport_header(64), after bpf_skb_proto_6_to_4, ipv6 protocol has been changed to ipv4, the first skb's network_header is 44,transport_header is 64, other skbs in frag_list didnot change.After skb_segment_list, the other skbs in frag_list has different network_header(24) and transport_header(44), so there will be 20 bytes different from original,that is difference between ipv6 header and ipv4 header. Just change transport_header to be the same with original.
Actually, there are two solutions to fix it, one is traversing all skbs and changing every skb header in bpf_skb_proto_6_to_4, the other is modifying frag_list skb's header in skb_segment_list. Considering efficiency, adopt the second one--- when the first skb and other skbs in frag_list has different network_header length, restore them to make sure right udp payload is delivered to user space.
--- net/core/skbuff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/core/skbuff.c +3 -1
@@ -3897,7 +3897,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,unsigned int delta_len =0 ;struct sk_buff *tail =NULL ;struct sk_buff *nskb, *tmp; -int err; +int len_diff, err;skb_push (skb, -skb_network_offset (skb) + offset);
@@ -3937,9 +3937,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,skb_push (nskb, -skb_network_offset (nskb) + offset);skb_release_head_state (nskb); + len_diff =skb_network_header_len (nskb) -skb_network_header_len (skb);__copy_skb_header (nskb, skb);skb_headers_offset_update (nskb,skb_headroom (nskb) -skb_headroom (skb)); + nskb->transport_header += len_diff;skb_copy_from_linear_data_offset (skb, -tnl_hlen, nskb->data - tnl_hlen, offset + tnl_hlen);
Signature · 1 line
2.18.0
PATCH v6 2/2 selftests net: add UDP GRO fraglist + bpf self-tests
When NET_F_F_GRO_FRAGLIST is enabled and bpf_skb_change_proto is used, check if udp packets and tcp packets are successfully delivered to user space. If wrong udp packets are delivered, udpgso_bench_rx will exit with "Initial byte out of range"
--- tools/testing/selftests/net/Makefile | 3 + tools/testing/selftests/net/bpf/Makefile | 17 ++ tools/testing/selftests/net/bpf/nat6to4.c | 286 ++++++++++++++++++ tools/testing/selftests/net/udpgro_frglist.sh | 101 +++++++ 4 files changed, 407 insertions(+) create mode 100644 tools/testing/selftests/net/bpf/Makefile create mode 100644 tools/testing/selftests/net/bpf/nat6to4.c create mode 100755 tools/testing/selftests/net/udpgro_frglist.sh
tools/testing/selftests/net/Makefile +3 -0
@@ -25,6 +25,7 @@ TEST_PROGS += bareudp.sh TEST_PROGS += amt.sh TEST_PROGS += unicast_extensions.sh TEST_PROGS += udpgro_fwd.sh +TEST_PROGS += udpgro_frglist.sh TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh
@@ -60,6 +61,8 @@ TEST_FILES := settings KSFT_KHDR_INSTALL := 1 include ../lib.mk +include bpf/Makefile + $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
tools/testing/selftests/net/bpf/Makefile new file +17 -0
@@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 + +CLANG ?= clang +CCINCLUDE += -I../../bpf +CCINCLUDE += -I../../../../../usr/include/ + +TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o +all: $(TEST_CUSTOM_PROGS) + +$(OUTPUT)/%.o: %.c + $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@ + +clean: + rm -f $(TEST_CUSTOM_PROGS) + + +
tools/testing/selftests/net/bpf/nat6to4.c new file +286 -0
286 lines not on this page · raw message
tools/testing/selftests/net/udpgro_frglist.sh new file +101 -0
101 lines not on this page · raw message
Signature · 1 line
2.18.0
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Hello:
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Quoted 6 lines · On Thu, 5 May 2022 13:48:49 +0800 you wrote:
When clatd starts with ebpf offloaing, and
NETIF_F_GRO_FRAGLISTis enable, several skbs are gathered in skb_shinfo(skb)->frag_list. The first skb's ipv6 header will be changed to ipv4 afterbpf_skb_proto_6_to_4, network_header\transport_header\mac_header have been updated as ipv4 acts, but other skbs infrag_listdidnot update anything, just ipv6 packets.
Quoted 6 lines
udp_queue_rcv_skbwill callskb_segment_listto traverse other skbs infrag_listand make sure right udp payload is delivered to user space. Unfortunately, other skbs infrag_listwho are still ipv6 packets are updated like the first skb and will have wrong transport header length.[...]
Here is the summary with links:
- [v6,1/2] net: fix wrong network header length
https://git.kernel.org/netdev/net/c/cf3ab8d4a797
- [v6,2/2] selftests net: add UDP GRO fraglist + bpf self-tests (no matching commit)
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html