diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-01 01:51:09 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-01 01:51:09 +0300 |
commit | dbe69e43372212527abf48609aba7fc39a6daa27 (patch) | |
tree | 96cfafdf70f5325ceeac1054daf7deca339c9730 /net/core/filter.c | |
parent | a6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff) | |
parent | b6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff) | |
download | linux-dbe69e43372212527abf48609aba7fc39a6daa27.tar.xz |
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- BPF:
- add syscall program type and libbpf support for generating
instructions and bindings for in-kernel BPF loaders (BPF loaders
for BPF), this is a stepping stone for signed BPF programs
- infrastructure to migrate TCP child sockets from one listener to
another in the same reuseport group/map to improve flexibility
of service hand-off/restart
- add broadcast support to XDP redirect
- allow bypass of the lockless qdisc to improving performance (for
pktgen: +23% with one thread, +44% with 2 threads)
- add a simpler version of "DO_ONCE()" which does not require jump
labels, intended for slow-path usage
- virtio/vsock: introduce SOCK_SEQPACKET support
- add getsocketopt to retrieve netns cookie
- ip: treat lowest address of a IPv4 subnet as ordinary unicast
address allowing reclaiming of precious IPv4 addresses
- ipv6: use prandom_u32() for ID generation
- ip: add support for more flexible field selection for hashing
across multi-path routes (w/ offload to mlxsw)
- icmp: add support for extended RFC 8335 PROBE (ping)
- seg6: add support for SRv6 End.DT46 behavior
- mptcp:
- DSS checksum support (RFC 8684) to detect middlebox meddling
- support Connection-time 'C' flag
- time stamping support
- sctp: packetization Layer Path MTU Discovery (RFC 8899)
- xfrm: speed up state addition with seq set
- WiFi:
- hidden AP discovery on 6 GHz and other HE 6 GHz improvements
- aggregation handling improvements for some drivers
- minstrel improvements for no-ack frames
- deferred rate control for TXQs to improve reaction times
- switch from round robin to virtual time-based airtime scheduler
- add trace points:
- tcp checksum errors
- openvswitch - action execution, upcalls
- socket errors via sk_error_report
Device APIs:
- devlink: add rate API for hierarchical control of max egress rate
of virtual devices (VFs, SFs etc.)
- don't require RCU read lock to be held around BPF hooks in NAPI
context
- page_pool: generic buffer recycling
New hardware/drivers:
- mobile:
- iosm: PCIe Driver for Intel M.2 Modem
- support for Qualcomm MSM8998 (ipa)
- WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
- sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
- Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
- NXP SJA1110 Automotive Ethernet 10-port switch
- Qualcomm QCA8327 switch support (qca8k)
- Mikrotik 10/25G NIC (atl1c)
Driver changes:
- ACPI support for some MDIO, MAC and PHY devices from Marvell and
NXP (our first foray into MAC/PHY description via ACPI)
- HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
- Mellanox/Nvidia NIC (mlx5)
- NIC VF offload of L2 bridging
- support IRQ distribution to Sub-functions
- Marvell (prestera):
- add flower and match all
- devlink trap
- link aggregation
- Netronome (nfp): connection tracking offload
- Intel 1GE (igc): add AF_XDP support
- Marvell DPU (octeontx2): ingress ratelimit offload
- Google vNIC (gve): new ring/descriptor format support
- Qualcomm mobile (rmnet & ipa): inline checksum offload support
- MediaTek WiFi (mt76)
- mt7915 MSI support
- mt7915 Tx status reporting
- mt7915 thermal sensors support
- mt7921 decapsulation offload
- mt7921 enable runtime pm and deep sleep
- Realtek WiFi (rtw88)
- beacon filter support
- Tx antenna path diversity support
- firmware crash information via devcoredump
- Qualcomm WiFi (wcn36xx)
- Wake-on-WLAN support with magic packets and GTK rekeying
- Micrel PHY (ksz886x/ksz8081): add cable test support"
* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
tcp: change ICSK_CA_PRIV_SIZE definition
tcp_yeah: check struct yeah size at compile time
gve: DQO: Fix off by one in gve_rx_dqo()
stmmac: intel: set PCI_D3hot in suspend
stmmac: intel: Enable PHY WOL option in EHL
net: stmmac: option to enable PHY WOL with PMT enabled
net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
net: use netdev_info in ndo_dflt_fdb_{add,del}
ptp: Set lookup cookie when creating a PTP PPS source.
net: sock: add trace for socket errors
net: sock: introduce sk_error_report
net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
net: dsa: include fdb entries pointing to bridge in the host fdb list
net: dsa: include bridge addresses which are local in the host fdb list
net: dsa: sync static FDB entries on foreign interfaces to hardware
net: dsa: install the host MDB and FDB entries in the master's RX filter
net: dsa: reference count the FDB addresses at the cross-chip notifier level
net: dsa: introduce a separate cross-chip notifier type for host FDBs
net: dsa: reference count the MDB entries at the cross-chip notifier level
...
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 114 |
1 files changed, 87 insertions, 27 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index d81352ca1b5c..d70187ce851b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3241,9 +3241,6 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -3255,19 +3252,11 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV4 needs to be changed into - * SKB_GSO_TCPV6. - */ + /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } - - /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -3282,9 +3271,6 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -3296,19 +3282,11 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV6 needs to be changed into - * SKB_GSO_TCPV4. - */ + /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } - - /* Due to IPv4 header, MSS can be upgraded. */ - skb_increase_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -3919,6 +3897,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; +/* XDP_REDIRECT works by a three-step process, implemented in the functions + * below: + * + * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target + * of the redirect and store it (along with some other metadata) in a per-CPU + * struct bpf_redirect_info. + * + * 2. When the program returns the XDP_REDIRECT return code, the driver will + * call xdp_do_redirect() which will use the information in struct + * bpf_redirect_info to actually enqueue the frame into a map type-specific + * bulk queue structure. + * + * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), + * which will flush all the different bulk queues, thus completing the + * redirect. + * + * Pointers to the map entries will be kept around for this whole sequence of + * steps, protected by RCU. However, there is no top-level rcu_read_lock() in + * the core code; instead, the RCU protection relies on everything happening + * inside a single NAPI poll sequence, which means it's between a pair of calls + * to local_bh_disable()/local_bh_enable(). + * + * The map entries are marked as __rcu and the map code makes sure to + * dereference those pointers with rcu_dereference_check() in a way that works + * for both sections that to hold an rcu_read_lock() and sections that are + * called from NAPI without a separate rcu_read_lock(). The code below does not + * use RCU annotations, but relies on those in the map code. + */ void xdp_do_flush(void) { __dev_flush(); @@ -3927,6 +3933,23 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +void bpf_clear_redirect_map(struct bpf_map *map) +{ + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -3934,6 +3957,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ @@ -3943,7 +3967,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_enqueue(fwd, xdp, dev); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_enqueue_multi(xdp, dev, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_enqueue(fwd, xdp, dev); + } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdp, dev); @@ -3985,13 +4016,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_generic_redirect(fwd, skb, xdp_prog); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_redirect_multi(dev, skb, xdp_prog, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_generic_redirect(fwd, skb, xdp_prog); + } if (unlikely(err)) goto err; break; @@ -10008,11 +10047,13 @@ out: static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; + reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; @@ -10021,12 +10062,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; - bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) @@ -10136,6 +10178,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_ptr_cookie_proto; default: return bpf_base_func_proto(func_id); } @@ -10165,6 +10209,14 @@ sk_reuseport_is_valid_access(int off, int size, case offsetof(struct sk_reuseport_md, hash): return size == size_default; + case offsetof(struct sk_reuseport_md, sk): + info->reg_type = PTR_TO_SOCKET; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, migrating_sk): + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + return size == sizeof(__u64); + /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) @@ -10237,6 +10289,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; + + case offsetof(struct sk_reuseport_md, sk): + SK_REUSEPORT_LOAD_FIELD(sk); + break; + + case offsetof(struct sk_reuseport_md, migrating_sk): + SK_REUSEPORT_LOAD_FIELD(migrating_sk); + break; } return insn - insn_buf; |