virtio_net: add optional flow dissection in virtio_net_hdr_to_skb
Subsystems (9)
v2 cover virtio_net: add optional flow dissection in virtio_net_hdr_to_skb
From: Tanner Love <[email protected]>
First patch extends the flow dissector BPF program type to accept virtio-net header members.
Second patch uses this feature to add optional flow dissection in virtio_net_hdr_to_skb(). This allows admins to define permitted packets more strictly, for example dropping deprecated UDP_UFO packets.
Third patch extends kselftest to cover this feature.
Tanner Love (3):
net: flow_dissector: extend bpf flow dissector support with vnet hdr
virtio_net: add optional flow dissection in virtio_net_hdr_to_skb selftests/net: amend bpf flow dissector prog to do vnet hdr validation
drivers/net/bonding/bond_main.c | 2 +- include/linux/skbuff.h | 26 ++- include/linux/virtio_net.h | 27 ++- include/net/flow_dissector.h | 6 + include/uapi/linux/bpf.h | 6 + net/core/filter.c | 55 +++++ net/core/flow_dissector.c | 24 ++- net/core/sysctl_net_core.c | 10 + tools/include/uapi/linux/bpf.h | 6 + tools/testing/selftests/bpf/progs/bpf_flow.c | 188 +++++++++++++----- .../selftests/bpf/test_flow_dissector.c | 181 +++++++++++++++-- .../selftests/bpf/test_flow_dissector.sh | 19 ++ 12 files changed, 470 insertions(+), 80 deletions(-)
Signature · 1 line
2.32.0.rc0.204.g9fa02ecfa5-goog
PATCH v2 1/3 net: flow_dissector: extend bpf flow dissector support with vnet hdr
From: Tanner Love <[email protected]>
Amend the bpf flow dissector program type to accept virtio_net_hdr members. Do this to enable bpf flow dissector programs to perform virtio-net header validation. The next patch in this series will add a flow dissection hook in virtio_net_hdr_to_skb and make use of this extended functionality. That commit message has more background on the use case.
--- drivers/net/bonding/bond_main.c | 2 +- include/linux/skbuff.h | 26 ++++++++++++---- include/net/flow_dissector.h | 6 ++++ include/uapi/linux/bpf.h | 6 ++++ net/core/filter.c | 55 +++++++++++++++++++++++++++++++++ net/core/flow_dissector.c | 24 ++++++++++++-- tools/include/uapi/linux/bpf.h | 6 ++++ 7 files changed, 116 insertions(+), 9 deletions(-)
drivers/net/bonding/bond_main.c +1 -1
@@ -3554,7 +3554,7 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,case BOND_XMIT_POLICY_ENCAP34 :memset (fk,0 ,sizeof (*fk));return __skb_flow_dissect (NULL , skb, &flow_keys_bonding, - fk,NULL ,0 ,0 ,0 ,0 ); + fk,NULL ,0 ,0 ,0 ,0 ,NULL );default :break ; }
include/linux/skbuff.h +20 -6
@@ -1312,18 +1312,20 @@ struct bpf_flow_dissector;bool bpf_flow_dissect (struct bpf_prog *prog,struct bpf_flow_dissector *ctx,__be16 proto,int nhoff,int hlen,unsigned int flags); +struct virtio_net_hdr ;bool __skb_flow_dissect (const struct net *net,const struct sk_buff *skb,struct flow_dissector *flow_dissector,void *target_container,const void *data, -__be16 proto,int nhoff,int hlen,unsigned int flags); +__be16 proto,int nhoff,int hlen,unsigned int flags, +const struct virtio_net_hdr *vhdr);static inline bool skb_flow_dissect (const struct sk_buff *skb,struct flow_dissector *flow_dissector,void *target_container,unsigned int flags) {return __skb_flow_dissect (NULL , skb, flow_dissector, - target_container,NULL ,0 ,0 ,0 , flags); + target_container,NULL ,0 ,0 ,0 , flags,NULL ); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
@@ -1332,7 +1334,20 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, {memset (flow,0 ,sizeof (*flow));return __skb_flow_dissect (NULL , skb, &flow_keys_dissector, - flow,NULL ,0 ,0 ,0 , flags); + flow,NULL ,0 ,0 ,0 , flags,NULL ); +} + +static inline bool +__skb_flow_dissect_flow_keys_basic (const struct net *net, +const struct sk_buff *skb, +struct flow_keys_basic *flow, +const void *data,__be16 proto, +int nhoff,int hlen,unsigned int flags, +const struct virtio_net_hdr *vhdr) +{ +memset (flow,0 ,sizeof (*flow)); +return __skb_flow_dissect (net, skb, &flow_keys_basic_dissector, flow, + data, proto, nhoff, hlen, flags, vhdr); } static inline bool
@@ -1342,9 +1357,8 @@ skb_flow_dissect_flow_keys_basic(const struct net *net, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { - memset(flow, 0, sizeof(*flow)); -return __skb_flow_dissect (net, skb, &flow_keys_basic_dissector, flow, - data, proto, nhoff, hlen, flags); + return __skb_flow_dissect_flow_keys_basic(net, skb, flow, data, proto, +nhoff ,hlen ,flags ,NULL ); } void skb_flow_dissect_meta(const struct sk_buff *skb,
include/net/flow_dissector.h +6 -0
@@ -370,6 +370,12 @@ struct bpf_flow_dissector {const struct sk_buff *skb;const void *data;const void *data_end; +__u8 vhdr_flags; +__u8 vhdr_gso_type; +__u16 vhdr_hdr_len; +__u16 vhdr_gso_size; +__u16 vhdr_csum_start; +__u16 vhdr_csum_offset; }; static inline void
include/uapi/linux/bpf.h +6 -0
@@ -5155,6 +5155,12 @@ struct __sk_buff {__u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk);__u32 gso_size; +__u8 vhdr_flags; +__u8 vhdr_gso_type; +__u16 vhdr_hdr_len; +__u16 vhdr_gso_size; +__u16 vhdr_csum_start; +__u16 vhdr_csum_offset; };struct bpf_tunnel_key {
net/core/filter.c +55 -0
67 lines not on this page · raw message
net/core/flow_dissector.c +22 -2
@@ -28,6 +28,7 @@#include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> +#include <linux/virtio_net.h> #if IS_ENABLED (CONFIG_NF_CONNTRACK )#include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h>
@@ -904,6 +905,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,* @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. +* @vhdr: virtio_net_header to include in kernel context for BPF flow dissector * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the
@@ -915,7 +917,8 @@ bool __skb_flow_dissect(const struct net *net,const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, - __be16 proto, int nhoff, int hlen, unsigned int flags) + __be16 proto, int nhoff, int hlen, unsigned int flags, + const struct virtio_net_hdr *vhdr) { struct flow_dissector_key_control *key_control;struct flow_dissector_key_basic *key_basic;
@@ -1001,6 +1004,23 @@ bool __skb_flow_dissect(const struct net *net,__be16 n_proto = proto;struct bpf_prog *prog; +if (vhdr) { + ctx.vhdr_flags = vhdr->flags; + ctx.vhdr_gso_type = vhdr->gso_type; + ctx.vhdr_hdr_len = +__virtio16_to_cpu (virtio_legacy_is_little_endian (), + vhdr->hdr_len); + ctx.vhdr_gso_size = +__virtio16_to_cpu (virtio_legacy_is_little_endian (), + vhdr->gso_size); + ctx.vhdr_csum_start = +__virtio16_to_cpu (virtio_legacy_is_little_endian (), + vhdr->csum_start); + ctx.vhdr_csum_offset = +__virtio16_to_cpu (virtio_legacy_is_little_endian (), + vhdr->csum_offset); + } +if (skb) { ctx.skb = skb;/* we can't use 'proto' in the skb case
@@ -1610,7 +1630,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)memset (&keys,0 ,sizeof (keys));__skb_flow_dissect (NULL , skb, &flow_keys_dissector_symmetric, &keys,NULL ,0 ,0 ,0 , -FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL ); +FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL ,NULL );return __flow_hash_from_keys (&keys, &hashrnd); }
tools/include/uapi/linux/bpf.h +6 -0
@@ -5155,6 +5155,12 @@ struct __sk_buff {__u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk);__u32 gso_size; +__u8 vhdr_flags; +__u8 vhdr_gso_type; +__u16 vhdr_hdr_len; +__u16 vhdr_gso_size; +__u16 vhdr_csum_start; +__u16 vhdr_csum_offset; };struct bpf_tunnel_key {
Signature · 1 line
2.32.0.rc0.204.g9fa02ecfa5-goog
PATCH v2 2/3 virtio_net: add optional flow dissection in virtio_net_hdr_to_skb
In reply to Tanner LoveFrom: Tanner Love <[email protected]>
Syzkaller bugs have resulted from loose specification of virtio_net_hdr[1]. Enable execution of a BPF flow dissector program in virtio_net_hdr_to_skb to validate the vnet header and drop bad input.
The existing behavior of accepting these vnet headers is part of the ABI. But individual admins may want to enforce restrictions. For example, verifying that a GSO_TCPV4 gso_type matches packet contents:
unencapsulated TCP/IPV4 packet with payload exceeding gso_size and hdr_len at payload offset.
Introduce a new sysctl net.core.flow_dissect_vnet_hdr controlling a static key to decide whether to perform flow dissection. When the key is false, virtio_net_hdr_to_skb computes as before.
[1] https://syzkaller.appspot.com/bug?id=b419a5ca95062664fe1a60b764621eb4526e2cd0
--- include/linux/virtio_net.h | 27 +++++++++++++++++++++++---- net/core/sysctl_net_core.c | 10 ++++++++++ 2 files changed, 33 insertions(+), 4 deletions(-)
include/linux/virtio_net.h +23 -4
@@ -3,6 +3,8 @@#define _LINUX_VIRTIO_NET_H#include <linux/if_vlan.h> +#include <linux/jump_label.h> +#include <net/sock.h> #include <uapi/linux/tcp.h> #include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h>
@@ -25,10 +27,13 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,return 0 ; } +DECLARE_STATIC_KEY_FALSE (sysctl_flow_dissect_vnet_hdr_key); +static inline int virtio_net_hdr_to_skb (struct sk_buff *skb,const struct virtio_net_hdr *hdr,bool little_endian) { +struct flow_keys_basic keys;unsigned int gso_type =0 ;unsigned int thlen =0 ;unsigned int p_off =0 ;
@@ -78,13 +83,24 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, p_off =skb_transport_offset (skb) + thlen;if (!pskb_may_pull (skb, p_off))return -EINVAL ; - }else { + } + +/* BPF flow dissection for optional strict validation. +* +* Admins can define permitted packets more strictly, such as dropping +* deprecated UDP_UFO packets and requiring skb->protocol to be non-zero +* and matching packet headers. +*/ +if (static_branch_unlikely (&sysctl_flow_dissect_vnet_hdr_key) && + !__skb_flow_dissect_flow_keys_basic (NULL , skb, &keys,NULL ,0 ,0 ,0 , +0 , hdr)) +return -EINVAL ; + +if (!(hdr->flags &VIRTIO_NET_HDR_F_NEEDS_CSUM )) {/* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { -struct flow_keys_basic keys; -if (!skb->protocol) {__be16 protocol =dev_parse_header_protocol (skb);
@@ -92,8 +108,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,if (protocol && protocol != skb->protocol)return -EINVAL ; } + retry: -if (!skb_flow_dissect_flow_keys_basic (NULL , skb, &keys, +/* only if flow dissection not already done */ +if (!static_branch_unlikely (&sysctl_flow_dissect_vnet_hdr_key) && + !skb_flow_dissect_flow_keys_basic (NULL , skb, &keys,NULL ,0 ,0 ,0 ,0 )) {/* UFO does not specify ipv4 or 6: try both */
net/core/sysctl_net_core.c +10 -0
@@ -36,6 +36,9 @@ static int net_msg_warn; /* Unused, but still a sysctl */int sysctl_fb_tunnels_only_for_init_net__read_mostly =0 ;EXPORT_SYMBOL (sysctl_fb_tunnels_only_for_init_net); +DEFINE_STATIC_KEY_FALSE (sysctl_flow_dissect_vnet_hdr_key); +EXPORT_SYMBOL (sysctl_flow_dissect_vnet_hdr_key); +/* 0 - Keep current behavior: * IPv4: inherit all current settings from init_net * IPv6: reset all settings to default
@@ -580,6 +583,13 @@ static struct ctl_table net_core_table[] = { .extra1 = SYSCTL_ONE, .extra2 = &int_3600, }, + { + .procname = "flow_dissect_vnet_hdr", + .data = &sysctl_flow_dissect_vnet_hdr_key.key, + .maxlen = sizeof(sysctl_flow_dissect_vnet_hdr_key), + .mode = 0644, + .proc_handler = proc_do_static_key, + }, { } };
Signature · 1 line
2.32.0.rc0.204.g9fa02ecfa5-goog
kernel test robot
build botThank you for the patch! Yet something to improve:
Hi Tanner,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Tanner-Love/virtio_net-add-optional-flow-dissection-in-virtio_net_hdr_to_skb/20210528-102939 base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git af9207adb6d9986be6ed64e76705cf513087e724 config: csky-randconfig-r004-20210526 (attached as .config) compiler: csky-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/a7db8fd377c0ea96e7e810c9b0164013043ad83c
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Tanner-Love/virtio_net-add-optional-flow-dissection-in-virtio_net_hdr_to_skb/20210528-102939 git checkout a7db8fd377c0ea96e7e810c9b0164013043ad83c
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=csky
If you fix the issue, kindly add following tag as appropriate
All errors (new ones prefixed by >>):
csky-linux-ld: drivers/net/tun.o: in function `$d':
>> tun.c:(.text+0x5eec): undefined reference to `sysctl_flow_dissect_vnet_hdr_key' >> csky-linux-ld: tun.c:(.text+0x601c): undefined reference to `sysctl_flow_dissect_vnet_hdr_key'
Kconfig warnings: (for reference only)
WARNING: unmet direct dependencies detected for LOCKDEP
Depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT && (FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86) Selected by
- PROVE_LOCKING && DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
- DEBUG_LOCK_ALLOC && DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
kernel test robot
build botThank you for the patch! Yet something to improve:
Hi Tanner,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Tanner-Love/virtio_net-add-optional-flow-dissection-in-virtio_net_hdr_to_skb/20210528-102939 base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git af9207adb6d9986be6ed64e76705cf513087e724 config: um-randconfig-c024-20210528 (attached as .config) compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce (this is a W=1 build):
# https://github.com/0day-ci/linux/commit/a7db8fd377c0ea96e7e810c9b0164013043ad83c
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Tanner-Love/virtio_net-add-optional-flow-dissection-in-virtio_net_hdr_to_skb/20210528-102939 git checkout a7db8fd377c0ea96e7e810c9b0164013043ad83c
# save the attached .config to linux build tree
make W=1 ARCH=um
If you fix the issue, kindly add following tag as appropriate
All errors (new ones prefixed by >>):
/usr/bin/ld: arch/um/drivers/vector_transports.o: in function `raw_verify_header':
>> vector_transports.c:(.text+0x7b1): undefined reference to `sysctl_flow_dissect_vnet_hdr_key'
collect2: error: ld returned 1 exit status
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
PATCH v2 3/3 selftests/net: amend bpf flow dissector prog to do vnet hdr validation
In reply to Tanner LoveFrom: Tanner Love <[email protected]>
Change the BPF flow dissector program to perform various checks on the virtio_net_hdr fields after doing flow dissection.
Amend test_flow_dissector.(c|sh) to add test cases that inject packets with reasonable or unreasonable virtio-net headers and assert that bad packets are dropped and good packets are not. Do this via packet socket; the kernel executes tpacket_snd, which enters virtio_net_hdr_to_skb, where flow dissection / vnet header validation occurs.
--- tools/testing/selftests/bpf/progs/bpf_flow.c | 188 +++++++++++++----- .../selftests/bpf/test_flow_dissector.c | 181 +++++++++++++++-- .../selftests/bpf/test_flow_dissector.sh | 19 ++ 3 files changed, 321 insertions(+), 67 deletions(-)
tools/testing/selftests/bpf/progs/bpf_flow.c +143 -45
@@ -13,6 +13,7 @@#include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_packet.h> +#include <linux/virtio_net.h> #include <sys/socket.h> #include <linux/if_tunnel.h> #include <linux/mpls.h>
@@ -71,15 +72,119 @@ struct { __type(value, struct bpf_flow_keys); } last_dissection SEC(".maps"); -static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, -int ret) +/* Drops invalid virtio-net headers */ +static __always_inline int validate_virtio_net_hdr(const struct __sk_buff *skb) { +const struct bpf_flow_keys *keys = skb->flow_keys; + +/* Check gso */ +if (skb->vhdr_gso_type !=VIRTIO_NET_HDR_GSO_NONE ) { +if (!(skb->vhdr_flags &VIRTIO_NET_HDR_F_NEEDS_CSUM )) +return BPF_DROP ; + +if (keys->is_encap) +return BPF_DROP ; + +switch (skb->vhdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN ) { +case VIRTIO_NET_HDR_GSO_TCPV4 : +if (keys->addr_proto !=ETH_P_IP || + keys->ip_proto !=IPPROTO_TCP ) +return BPF_DROP ; + +if (skb->vhdr_gso_size >= skb->len - keys->thoff - +sizeof (struct tcphdr )) +return BPF_DROP ; + +break ; +case VIRTIO_NET_HDR_GSO_TCPV6 : +if (keys->addr_proto !=ETH_P_IPV6 || + keys->ip_proto !=IPPROTO_TCP ) +return BPF_DROP ; + +if (skb->vhdr_gso_size >= skb->len - keys->thoff - +sizeof (struct tcphdr )) +return BPF_DROP ; + +break ; +case VIRTIO_NET_HDR_GSO_UDP : +if (keys->ip_proto !=IPPROTO_UDP ) +return BPF_DROP ; + +if (skb->vhdr_gso_size >= skb->len - keys->thoff - +sizeof (struct udphdr )) +return BPF_DROP ; + +break ; +default : +return BPF_DROP ; + } + } + +/* Check hdr_len */ +if (skb->vhdr_hdr_len) { +switch (keys->ip_proto) { +case IPPROTO_TCP : +if (skb->vhdr_hdr_len != skb->flow_keys->thoff + +sizeof (struct tcphdr )) +return BPF_DROP ; + +break ; +case IPPROTO_UDP : +if (skb->vhdr_hdr_len != keys->thoff + +sizeof (struct udphdr )) +return BPF_DROP ; + +break ; + } + } + +/* Check csum */ +if (skb->vhdr_flags &VIRTIO_NET_HDR_F_NEEDS_CSUM ) { +if (keys->addr_proto !=ETH_P_IP && + keys->addr_proto !=ETH_P_IPV6 ) +return BPF_DROP ; + +if (skb->vhdr_csum_start != keys->thoff) +return BPF_DROP ; + +switch (keys->ip_proto) { +case IPPROTO_TCP : +if (skb->vhdr_csum_offset != + offsetof(struct tcphdr , check)) +return BPF_DROP ; + +break ; +case IPPROTO_UDP : +if (skb->vhdr_csum_offset != + offsetof(struct udphdr , check)) +return BPF_DROP ; + +break ; +default : +return BPF_DROP ; + } + } + +return BPF_OK ; +} + +/* Common steps to perform regardless of where protocol parsing finishes: +* 1. store flow keys in map +* 2. if parse result is BPF_OK, parse the vnet hdr if present +* 3. return the parse result +*/ +static __always_inline int parse_epilogue(struct __sk_buff *skb, int ret) +{ +const struct bpf_flow_keys *keys = skb->flow_keys;__u32 key = (__u32)(keys->sport) <<16 | keys->dport;struct bpf_flow_keys val;memcpy (&val, keys,sizeof (val));bpf_map_update_elem (&last_dissection, &key, &val,BPF_ANY ); -return ret; + +if (ret !=BPF_OK ) +return ret; +return validate_virtio_net_hdr (skb); }#define IPV6_FLOWLABEL_MASK __bpf_constant_htonl(0x000FFFFF)
@@ -114,8 +219,6 @@ static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb,/* Dispatches on ETHERTYPE */ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) { -struct bpf_flow_keys *keys = skb->flow_keys; -switch (proto) {case bpf_htons (ETH_P_IP ):bpf_tail_call_static (skb, &jmp_table,IP );
@@ -131,12 +234,10 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)case bpf_htons (ETH_P_8021AD ):bpf_tail_call_static (skb, &jmp_table,VLAN );break ; -default : -/* Protocol not supported */ -return export_flow_keys (keys,BPF_DROP ); } -return export_flow_keys (keys,BPF_DROP ); +/* Protocol not supported */ +return parse_epilogue (skb,BPF_DROP ); }SEC ("flow_dissector" )
@@ -162,28 +263,28 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)case IPPROTO_ICMP : icmp =bpf_flow_dissect_get_header (skb,sizeof (*icmp), &_icmp);if (!icmp) -return export_flow_keys (keys,BPF_DROP ); -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_DROP ); +return parse_epilogue (skb,BPF_OK );case IPPROTO_IPIP : keys->is_encap = true;if (keys->flags &BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP ) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );return parse_eth_proto (skb,bpf_htons (ETH_P_IP ));case IPPROTO_IPV6 : keys->is_encap = true;if (keys->flags &BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP ) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );return parse_eth_proto (skb,bpf_htons (ETH_P_IPV6 ));case IPPROTO_GRE : gre =bpf_flow_dissect_get_header (skb,sizeof (*gre), &_gre);if (!gre) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );if (bpf_htons (gre->flags &GRE_VERSION ))/* Only inspect standard GRE packets with version 0 */ -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK ); keys->thoff +=sizeof (*gre);/* Step over GRE Flags and Proto */ if (GRE_IS_CSUM (gre->flags))
@@ -195,13 +296,13 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) keys->is_encap = true;if (keys->flags &BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP ) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );if (gre->proto ==bpf_htons (ETH_P_TEB )) { eth =bpf_flow_dissect_get_header (skb,sizeof (*eth), &_eth);if (!eth) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->thoff +=sizeof (*eth);
@@ -212,37 +313,35 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto)case IPPROTO_TCP : tcp =bpf_flow_dissect_get_header (skb,sizeof (*tcp), &_tcp);if (!tcp) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );if (tcp->doff <5 ) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );if ((__u8 *)tcp + (tcp->doff <<2 ) > data_end) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->sport = tcp->source; keys->dport = tcp->dest; -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );case IPPROTO_UDP :case IPPROTO_UDPLITE : udp =bpf_flow_dissect_get_header (skb,sizeof (*udp), &_udp);if (!udp) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->sport = udp->source; keys->dport = udp->dest; -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );default : -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); } -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); } static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) { -struct bpf_flow_keys *keys = skb->flow_keys; -switch (nexthdr) {case IPPROTO_HOPOPTS :case IPPROTO_DSTOPTS :
@@ -255,7 +354,7 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr)return parse_ip_proto (skb, nexthdr); } -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); }PROG (IP )(struct __sk_buff *skb)
@@ -268,11 +367,11 @@ PROG(IP)(struct __sk_buff *skb) iph =bpf_flow_dissect_get_header (skb,sizeof (*iph), &_iph);if (!iph) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );/* IP header cannot be smaller than 20 bytes */ if (iph->ihl <5 ) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->addr_proto =ETH_P_IP ; keys->ipv4_src = iph->saddr;
@@ -281,7 +380,7 @@ PROG(IP)(struct __sk_buff *skb) keys->thoff += iph->ihl <<2 ;if (data + keys->thoff > data_end) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );if (iph->frag_off &bpf_htons (IP_MF |IP_OFFSET )) { keys->is_frag = true;
@@ -302,7 +401,7 @@ PROG(IP)(struct __sk_buff *skb) }if (done) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );return parse_ip_proto (skb, iph->protocol); }
@@ -314,7 +413,7 @@ PROG(IPV6)(struct __sk_buff *skb) ip6h =bpf_flow_dissect_get_header (skb,sizeof (*ip6h), &_ip6h);if (!ip6h) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->addr_proto =ETH_P_IPV6 ;memcpy (&keys->ipv6_src, &ip6h->saddr,2 *sizeof (ip6h->saddr));
@@ -324,7 +423,7 @@ PROG(IPV6)(struct __sk_buff *skb) keys->flow_label =ip6_flowlabel (ip6h);if (keys->flags &BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL ) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK );return parse_ipv6_proto (skb, ip6h->nexthdr); }
@@ -336,7 +435,7 @@ PROG(IPV6OP)(struct __sk_buff *skb) ip6h =bpf_flow_dissect_get_header (skb,sizeof (*ip6h), &_ip6h);if (!ip6h) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );/* hlen is in 8-octets and does not include the first 8 bytes * of the header
@@ -354,7 +453,7 @@ PROG(IPV6FR)(struct __sk_buff *skb) fragh =bpf_flow_dissect_get_header (skb,sizeof (*fragh), &_fragh);if (!fragh) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->thoff +=sizeof (*fragh); keys->is_frag = true;
@@ -367,9 +466,9 @@ PROG(IPV6FR)(struct __sk_buff *skb)* explicitly asked for. */ if (!(keys->flags &BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG )) -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK ); }else { -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK ); }return parse_ipv6_proto (skb, fragh->nexthdr);
@@ -377,14 +476,13 @@ PROG(IPV6FR)(struct __sk_buff *skb)PROG (MPLS )(struct __sk_buff *skb) { -struct bpf_flow_keys *keys = skb->flow_keys;struct mpls_label *mpls, _mpls; mpls =bpf_flow_dissect_get_header (skb,sizeof (*mpls), &_mpls);if (!mpls) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); -return export_flow_keys (keys,BPF_OK ); +return parse_epilogue (skb,BPF_OK ); }PROG (VLAN )(struct __sk_buff *skb)
@@ -396,10 +494,10 @@ PROG(VLAN)(struct __sk_buff *skb)if (keys->n_proto ==bpf_htons (ETH_P_8021AD )) { vlan =bpf_flow_dissect_get_header (skb,sizeof (*vlan), &_vlan);if (!vlan) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP );if (vlan->h_vlan_encapsulated_proto !=bpf_htons (ETH_P_8021Q )) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->nhoff +=sizeof (*vlan); keys->thoff +=sizeof (*vlan);
@@ -407,14 +505,14 @@ PROG(VLAN)(struct __sk_buff *skb) vlan =bpf_flow_dissect_get_header (skb,sizeof (*vlan), &_vlan);if (!vlan) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->nhoff +=sizeof (*vlan); keys->thoff +=sizeof (*vlan);/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto ==bpf_htons (ETH_P_8021AD ) || vlan->h_vlan_encapsulated_proto ==bpf_htons (ETH_P_8021Q )) -return export_flow_keys (keys,BPF_DROP ); +return parse_epilogue (skb,BPF_DROP ); keys->n_proto = vlan->h_vlan_encapsulated_proto;return parse_eth_proto (skb, vlan->h_vlan_encapsulated_proto);
tools/testing/selftests/bpf/test_flow_dissector.c +159 -22
343 lines not on this page · raw message
tools/testing/selftests/bpf/test_flow_dissector.sh +19 -0
@@ -51,6 +51,9 @@ if [[ -z $(ip netns identify $$) ]]; then echo "Skipping root flow dissector test, bpftool not found" >&2 fi + orig_flow_dissect_sysctl=$(</proc/sys/net/core/flow_dissect_vnet_hdr) + sysctl net.core.flow_dissect_vnet_hdr=1 + # Run the rest of the tests in a net namespace. ../net/in_netns.sh "$0" "$@" err=$(( $err + $? ))
@@ -61,6 +64,7 @@ if [[ -z $(ip netns identify $$) ]]; then echo "selftests: $TESTNAME [FAILED]"; fi + sysctl net.core.flow_dissect_vnet_hdr=$orig_flow_dissect_sysctl exit $err fi
@@ -165,4 +169,19 @@ tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \ # Send 10 IPv6/UDP packets from port 10. Filter should not drop any. ./test_flow_dissector -i 6 -f 10 + +echo "Testing virtio-net header validation..." +echo "Testing valid vnet headers. Should *not* be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v +echo "Testing partial transport header. Should be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v -U -E +echo "Testing valid vnet gso spec. Should *not* be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v -g -c -l 8000 +echo "Testing invalid vnet gso size. Should be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v -g -c -l 100 -E +echo "Testing invalid vnet header len. Should be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v -L -E +echo "Testing vnet gso without csum. Should be dropped." +./with_addr.sh ./test_flow_dissector -i 4 -D 192.168.0.1 -S 1.1.1.1 -p -v -g -l 8000 -E + exit 0
Signature · 1 line
2.32.0.rc0.204.g9fa02ecfa5-goog