diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-26 16:07:23 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-26 16:07:23 -0700 |
commit | 6e98b09da931a00bf4e0477d0fa52748bf28fcce (patch) | |
tree | 9c658ed95add5693f42f29f63df80a2ede3f6ec2 /tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c | |
parent | b68ee1c6131c540a62ecd443be89c406401df091 (diff) | |
parent | 9b78d919632b7149d311aaad5a977e4b48b10321 (diff) |
Merge tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Paolo Abeni:
"Core:
- Introduce a config option to tweak MAX_SKB_FRAGS. Increasing the
default value allows for better BIG TCP performances
- Reduce compound page head access for zero-copy data transfers
- RPS/RFS improvements, avoiding unneeded NET_RX_SOFTIRQ when
possible
- Threaded NAPI improvements, adding defer skb free support and
unneeded softirq avoidance
- Address dst_entry reference count scalability issues, via false
sharing avoidance and optimize refcount tracking
- Add lockless accesses annotation to sk_err[_soft]
- Optimize again the skb struct layout
- Extends the skb drop reasons to make it usable by multiple
subsystems
- Better const qualifier awareness for socket casts
BPF:
- Add skb and XDP typed dynptrs which allow BPF programs for more
ergonomic and less brittle iteration through data and
variable-sized accesses
- Add a new BPF netfilter program type and minimal support to hook
BPF programs to netfilter hooks such as prerouting or forward
- Add more precise memory usage reporting for all BPF map types
- Adds support for using {FOU,GUE} encap with an ipip device
operating in collect_md mode and add a set of BPF kfuncs for
controlling encap params
- Allow BPF programs to detect at load time whether a particular
kfunc exists or not, and also add support for this in light
skeleton
- Bigger batch of BPF verifier improvements to prepare for upcoming
BPF open-coded iterators allowing for less restrictive looping
capabilities
- Rework RCU enforcement in the verifier, add kptr_rcu and enforce
BPF programs to NULL-check before passing such pointers into kfunc
- Add support for kptrs in percpu hashmaps, percpu LRU hashmaps and
in local storage maps
- Enable RCU semantics for task BPF kptrs and allow referenced kptr
tasks to be stored in BPF maps
- Add support for refcounted local kptrs to the verifier for allowing
shared ownership, useful for adding a node to both the BPF list and
rbtree
- Add BPF verifier support for ST instructions in
convert_ctx_access() which will help new -mcpu=v4 clang flag to
start emitting them
- Add ARM32 USDT support to libbpf
- Improve bpftool's visual program dump which produces the control
flow graph in a DOT format by adding C source inline annotations
Protocols:
- IPv4: Allow adding to IPv4 address a 'protocol' tag. Such value
indicates the provenance of the IP address
- IPv6: optimize route lookup, dropping unneeded R/W lock acquisition
- Add the handshake upcall mechanism, allowing the user-space to
implement generic TLS handshake on kernel's behalf
- Bridge: support per-{Port, VLAN} neighbor suppression, increasing
resilience to nodes failures
- SCTP: add support for Fair Capacity and Weighted Fair Queueing
schedulers
- MPTCP: delay first subflow allocation up to its first usage. This
will allow for later better LSM interaction
- xfrm: Remove inner/outer modes from input/output path. These are
not needed anymore
- WiFi:
- reduced neighbor report (RNR) handling for AP mode
- HW timestamping support
- support for randomized auth/deauth TA for PASN privacy
- per-link debugfs for multi-link
- TC offload support for mac80211 drivers
- mac80211 mesh fast-xmit and fast-rx support
- enable Wi-Fi 7 (EHT) mesh support
Netfilter:
- Add nf_tables 'brouting' support, to force a packet to be routed
instead of being bridged
- Update bridge netfilter and ovs conntrack helpers to handle IPv6
Jumbo packets properly, i.e. fetch the packet length from
hop-by-hop extension header. This is needed for BIT TCP support
- The iptables 32bit compat interface isn't compiled in by default
anymore
- Move ip(6)tables builtin icmp matches to the udptcp one. This has
the advantage that icmp/icmpv6 match doesn't load the
iptables/ip6tables modules anymore when iptables-nft is used
- Extended netlink error report for netdevice in flowtables and
netdev/chains. Allow for incrementally add/delete devices to netdev
basechain. Allow to create netdev chain without device
Driver API:
- Remove redundant Device Control Error Reporting Enable, as PCI core
has already error reporting enabled at enumeration time
- Move Multicast DB netlink handlers to core, allowing devices other
then bridge to use them
- Allow the page_pool to directly recycle the pages from safely
localized NAPI
- Implement lockless TX queue stop/wake combo macros, allowing for
further code de-duplication and sanitization
- Add YNL support for user headers and struct attrs
- Add partial YNL specification for devlink
- Add partial YNL specification for ethtool
- Add tc-mqprio and tc-taprio support for preemptible traffic classes
- Add tx push buf len param to ethtool, specifies the maximum number
of bytes of a transmitted packet a driver can push directly to the
underlying device
- Add basic LED support for switch/phy
- Add NAPI documentation, stop relaying on external links
- Convert dsa_master_ioctl() to netdev notifier. This is a
preparatory work to make the hardware timestamping layer selectable
by user space
- Add transceiver support and improve the error messages for CAN-FD
controllers
New hardware / drivers:
- Ethernet:
- AMD/Pensando core device support
- MediaTek MT7981 SoC
- MediaTek MT7988 SoC
- Broadcom BCM53134 embedded switch
- Texas Instruments CPSW9G ethernet switch
- Qualcomm EMAC3 DWMAC ethernet
- StarFive JH7110 SoC
- NXP CBTX ethernet PHY
- WiFi:
- Apple M1 Pro/Max devices
- RealTek rtl8710bu/rtl8188gu
- RealTek rtl8822bs, rtl8822cs and rtl8821cs SDIO chipset
- Bluetooth:
- Realtek RTL8821CS, RTL8851B, RTL8852BS
- Mediatek MT7663, MT7922
- NXP w8997
- Actions Semi ATS2851
- QTI WCN6855
- Marvell 88W8997
- Can:
- STMicroelectronics bxcan stm32f429
Drivers:
- Ethernet NICs:
- Intel (1G, icg):
- add tracking and reporting of QBV config errors
- add support for configuring max SDU for each Tx queue
- Intel (100G, ice):
- refactor mailbox overflow detection to support Scalable IOV
- GNSS interface optimization
- Intel (i40e):
- support XDP multi-buffer
- nVidia/Mellanox:
- add the support for linux bridge multicast offload
- enable TC offload for egress and engress MACVLAN over bond
- add support for VxLAN GBP encap/decap flows offload
- extend packet offload to fully support libreswan
- support tunnel mode in mlx5 IPsec packet offload
- extend XDP multi-buffer support
- support MACsec VLAN offload
- add support for dynamic msix vectors allocation
- drop RX page_cache and fully use page_pool
- implement thermal zone to report NIC temperature
- Netronome/Corigine:
- add support for multi-zone conntrack offload
- Solarflare/Xilinx:
- support offloading TC VLAN push/pop actions to the MAE
- support TC decap rules
- support unicast PTP
- Other NICs:
- Broadcom (bnxt): enforce software based freq adjustments only on
shared PHC NIC
- RealTek (r8169): refactor to addess ASPM issues during NAPI poll
- Micrel (lan8841): add support for PTP_PF_PEROUT
- Cadence (macb): enable PTP unicast
- Engleder (tsnep): add XDP socket zero-copy support
- virtio-net: implement exact header length guest feature
- veth: add page_pool support for page recycling
- vxlan: add MDB data path support
- gve: add XDP support for GQI-QPL format
- geneve: accept every ethertype
- macvlan: allow some packets to bypass broadcast queue
- mana: add support for jumbo frame
- Ethernet high-speed switches:
- Microchip (sparx5): Add support for TC flower templates
- Ethernet embedded switches:
- Broadcom (b54):
- configure 6318 and 63268 RGMII ports
- Marvell (mv88e6xxx):
- faster C45 bus scan
- Microchip:
- lan966x:
- add support for IS1 VCAP
- better TX/RX from/to CPU performances
- ksz9477: add ETS Qdisc support
- ksz8: enhance static MAC table operations and error handling
- sama7g5: add PTP capability
- NXP (ocelot):
- add support for external ports
- add support for preemptible traffic classes
- Texas Instruments:
- add CPSWxG SGMII support for J7200 and J721E
- Intel WiFi (iwlwifi):
- preparation for Wi-Fi 7 EHT and multi-link support
- EHT (Wi-Fi 7) sniffer support
- hardware timestamping support for some devices/firwmares
- TX beacon protection on newer hardware
- Qualcomm 802.11ax WiFi (ath11k):
- MU-MIMO parameters support
- ack signal support for management packets
- RealTek WiFi (rtw88):
- SDIO bus support
- better support for some SDIO devices (e.g. MAC address from
efuse)
- RealTek WiFi (rtw89):
- HW scan support for 8852b
- better support for 6 GHz scanning
- support for various newer firmware APIs
- framework firmware backwards compatibility
- MediaTek WiFi (mt76):
- P2P support
- mesh A-MSDU support
- EHT (Wi-Fi 7) support
- coredump support"
* tag 'net-next-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2078 commits)
net: phy: hide the PHYLIB_LEDS knob
net: phy: marvell-88x2222: remove unnecessary (void*) conversions
tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp.
net: amd: Fix link leak when verifying config failed
net: phy: marvell: Fix inconsistent indenting in led_blink_set
lan966x: Don't use xdp_frame when action is XDP_TX
tsnep: Add XDP socket zero-copy TX support
tsnep: Add XDP socket zero-copy RX support
tsnep: Move skb receive action to separate function
tsnep: Add functions for queue enable/disable
tsnep: Rework TX/RX queue initialization
tsnep: Replace modulo operation with mask
net: phy: dp83867: Add led_brightness_set support
net: phy: Fix reading LED reg property
drivers: nfc: nfcsim: remove return value check of `dev_dir`
net: phy: dp83867: Remove unnecessary (void*) conversions
net: ethtool: coalesce: try to make user settings stick twice
net: mana: Check if netdev/napi_alloc_frag returns single page
net: mana: Rename mana_refill_rxoob and remove some empty lines
net: veth: add page_pool stats
...
Diffstat (limited to 'tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c')
-rw-r--r-- | tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c | 487 |
1 files changed, 487 insertions, 0 deletions
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c new file mode 100644 index 000000000000..f997f5080748 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c @@ -0,0 +1,487 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Facebook +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <bpf/bpf_helpers.h> +#include "test_iptunnel_common.h" +#include <bpf/bpf_endian.h> + +#include "bpf_kfuncs.h" + +static __always_inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static __noinline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, MAX_VIPS); + __type(key, struct vip); + __type(value, struct vip_meta); +} vip_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CH_RINGS_SIZE); + __type(key, __u32); + __type(value, __u32); +} ch_rings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, MAX_REALS); + __type(key, __u32); + __type(value, struct real_definition); +} reals SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, MAX_VIPS); + __type(key, __u32); + __type(value, struct vip_stats); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, CTL_MAP_SIZE); + __type(key, __u32); + __type(value, struct ctl_value); +} ctl_array SEC(".maps"); + +static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __noinline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6); + __u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE; + __u32 *real_pos; + + if (hash != 0x358459b7 /* jhash of ipv4 packet */ && + hash != 0x2f4bc6bb /* jhash of ipv6 packet */) + return false; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __noinline int parse_icmpv6(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct ipv6hdr)] = {}; + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!icmp_hdr) + return TC_ACT_SHOT; + + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!ip6h) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __noinline int parse_icmp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer_icmp[sizeof(struct iphdr)] = {}; + __u8 buffer_ip[sizeof(struct iphdr)] = {}; + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer_icmp, sizeof(buffer_icmp)); + if (!icmp_hdr) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = bpf_dynptr_slice(skb_ptr, off, buffer_ip, sizeof(buffer_ip)); + if (!iph || iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __noinline bool parse_udp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct udphdr)] = {}; + struct udphdr *udp; + + udp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!udp) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __noinline bool parse_tcp(struct bpf_dynptr *skb_ptr, __u64 off, + struct packet_description *pckt) +{ + __u8 buffer[sizeof(struct tcphdr)] = {}; + struct tcphdr *tcp; + + tcp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!tcp) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __noinline int process_packet(struct bpf_dynptr *skb_ptr, + struct eth_hdr *eth, __u64 off, + bool is_ipv6, struct __sk_buff *skb) +{ + struct packet_description pckt = {}; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + __u8 buffer[sizeof(struct ipv6hdr)] = {}; + + ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!ip6h) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(skb_ptr, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + __u8 buffer[sizeof(struct iphdr)] = {}; + + iph = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer)); + if (!iph || iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(skb_ptr, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(skb_ptr, off, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(skb_ptr, off, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + __u8 buffer[sizeof(struct eth_hdr)] = {}; + struct bpf_dynptr ptr; + struct eth_hdr *eth; + __u32 eth_proto; + __u32 nh_off; + int err; + + nh_off = sizeof(struct eth_hdr); + + bpf_dynptr_from_skb(ctx, 0, &ptr); + eth = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer)); + if (!eth) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + err = process_packet(&ptr, eth, nh_off, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + err = process_packet(&ptr, eth, nh_off, true, ctx); + else + return TC_ACT_SHOT; + + if (eth == buffer) + bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0); + + return err; +} + +char _license[] SEC("license") = "GPL"; |