diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /net/dccp/dccp.h | |
download | linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip |
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski:
"Core:
- Add dedicated kmem_cache for typical/small skb->head, avoid having
to access struct page at kfree time, and improve memory use.
- Introduce sysctl to set default RPS configuration for new netdevs.
- Define Netlink protocol specification format which can be used to
describe messages used by each family and auto-generate parsers.
Add tools for generating kernel data structures and uAPI headers.
- Expose all net/core sysctls inside netns.
- Remove 4s sleep in netpoll if carrier is instantly detected on
boot.
- Add configurable limit of MDB entries per port, and port-vlan.
- Continue populating drop reasons throughout the stack.
- Retire a handful of legacy Qdiscs and classifiers.
Protocols:
- Support IPv4 big TCP (TSO frames larger than 64kB).
- Add IP_LOCAL_PORT_RANGE socket option, to control local port range
on socket by socket basis.
- Track and report in procfs number of MPTCP sockets used.
- Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
manager.
- IPv6: don't check net.ipv6.route.max_size and rely on garbage
collection to free memory (similarly to IPv4).
- Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).
- ICMP: add per-rate limit counters.
- Add support for user scanning requests in ieee802154.
- Remove static WEP support.
- Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
reporting.
- WiFi 7 EHT channel puncturing support (client & AP).
BPF:
- Add a rbtree data structure following the "next-gen data structure"
precedent set by recently added linked list, that is, by using
kfunc + kptr instead of adding a new BPF map type.
- Expose XDP hints via kfuncs with initial support for RX hash and
timestamp metadata.
- Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
better support decap on GRE tunnel devices not operating in collect
metadata.
- Improve x86 JIT's codegen for PROBE_MEM runtime error checks.
- Remove the need for trace_printk_lock for bpf_trace_printk and
bpf_trace_vprintk helpers.
- Extend libbpf's bpf_tracing.h support for tracing arguments of
kprobes/uprobes and syscall as a special case.
- Significantly reduce the search time for module symbols by
livepatch and BPF.
- Enable cpumasks to be used as kptrs, which is useful for tracing
programs tracking which tasks end up running on which CPUs in
different time intervals.
- Add support for BPF trampoline on s390x and riscv64.
- Add capability to export the XDP features supported by the NIC.
- Add __bpf_kfunc tag for marking kernel functions as kfuncs.
- Add cgroup.memory=nobpf kernel parameter option to disable BPF
memory accounting for container environments.
Netfilter:
- Remove the CLUSTERIP target. It has been marked as obsolete for
years, and we still have WARN splats wrt races of the out-of-band
/proc interface installed by this target.
- Add 'destroy' commands to nf_tables. They are identical to the
existing 'delete' commands, but do not return an error if the
referenced object (set, chain, rule...) did not exist.
Driver API:
- Improve cpumask_local_spread() locality to help NICs set the right
IRQ affinity on AMD platforms.
- Separate C22 and C45 MDIO bus transactions more clearly.
- Introduce new DCB table to control DSCP rewrite on egress.
- Support configuration of Physical Layer Collision Avoidance (PLCA)
Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
shared medium Ethernet.
- Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
preemption of low priority frames by high priority frames.
- Add support for controlling MACSec offload using netlink SET.
- Rework devlink instance refcounts to allow registration and
de-registration under the instance lock. Split the code into
multiple files, drop some of the unnecessarily granular locks and
factor out common parts of netlink operation handling.
- Add TX frame aggregation parameters (for USB drivers).
- Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
messages with notifications for debug.
- Allow offloading of UDP NEW connections via act_ct.
- Add support for per action HW stats in TC.
- Support hardware miss to TC action (continue processing in SW from
a specific point in the action chain).
- Warn if old Wireless Extension user space interface is used with
modern cfg80211/mac80211 drivers. Do not support Wireless
Extensions for Wi-Fi 7 devices at all. Everyone should switch to
using nl80211 interface instead.
- Improve the CAN bit timing configuration. Use extack to return
error messages directly to user space, update the SJW handling,
including the definition of a new default value that will benefit
CAN-FD controllers, by increasing their oscillator tolerance.
New hardware / drivers:
- Ethernet:
- nVidia BlueField-3 support (control traffic driver)
- Ethernet support for imx93 SoCs
- Motorcomm yt8531 gigabit Ethernet PHY
- onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
- Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
- Amlogic gxl MDIO mux
- WiFi:
- RealTek RTL8188EU (rtl8xxxu)
- Qualcomm Wi-Fi 7 devices (ath12k)
- CAN:
- Renesas R-Car V4H
Drivers:
- Bluetooth:
- Set Per Platform Antenna Gain (PPAG) for Intel controllers.
- Ethernet NICs:
- Intel (1G, igc):
- support TSN / Qbv / packet scheduling features of i226 model
- Intel (100G, ice):
- use GNSS subsystem instead of TTY
- multi-buffer XDP support
- extend support for GPIO pins to E823 devices
- nVidia/Mellanox:
- update the shared buffer configuration on PFC commands
- implement PTP adjphase function for HW offset control
- TC support for Geneve and GRE with VF tunnel offload
- more efficient crypto key management method
- multi-port eswitch support
- Netronome/Corigine:
- add DCB IEEE support
- support IPsec offloading for NFP3800
- Freescale/NXP (enetc):
- support XDP_REDIRECT for XDP non-linear buffers
- improve reconfig, avoid link flap and waiting for idle
- support MAC Merge layer
- Other NICs:
- sfc/ef100: add basic devlink support for ef100
- ionic: rx_push mode operation (writing descriptors via MMIO)
- bnxt: use the auxiliary bus abstraction for RDMA
- r8169: disable ASPM and reset bus in case of tx timeout
- cpsw: support QSGMII mode for J721e CPSW9G
- cpts: support pulse-per-second output
- ngbe: add an mdio bus driver
- usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
- r8152: handle devices with FW with NCM support
- amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
- virtio-net: support multi buffer XDP
- virtio/vsock: replace virtio_vsock_pkt with sk_buff
- tsnep: XDP support
- Ethernet high-speed switches:
- nVidia/Mellanox (mlxsw):
- add support for latency TLV (in FW control messages)
- Microchip (sparx5):
- separate explicit and implicit traffic forwarding rules, make
the implicit rules always active
- add support for egress DSCP rewrite
- IS0 VCAP support (Ingress Classification)
- IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
etc.)
- ES2 VCAP support (Egress Access Control)
- support for Per-Stream Filtering and Policing (802.1Q,
8.6.5.1)
- Ethernet embedded switches:
- Marvell (mv88e6xxx):
- add MAB (port auth) offload support
- enable PTP receive for mv88e6390
- NXP (ocelot):
- support MAC Merge layer
- support for the the vsc7512 internal copper phys
- Microchip:
- lan9303: convert to PHYLINK
- lan966x: support TC flower filter statistics
- lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
- lan937x: support Credit Based Shaper configuration
- ksz9477: support Energy Efficient Ethernet
- other:
- qca8k: convert to regmap read/write API, use bulk operations
- rswitch: Improve TX timestamp accuracy
- Intel WiFi (iwlwifi):
- EHT (Wi-Fi 7) rate reporting
- STEP equalizer support: transfer some STEP (connection to radio
on platforms with integrated wifi) related parameters from the
BIOS to the firmware.
- Qualcomm 802.11ax WiFi (ath11k):
- IPQ5018 support
- Fine Timing Measurement (FTM) responder role support
- channel 177 support
- MediaTek WiFi (mt76):
- per-PHY LED support
- mt7996: EHT (Wi-Fi 7) support
- Wireless Ethernet Dispatch (WED) reset support
- switch to using page pool allocator
- RealTek WiFi (rtw89):
- support new version of Bluetooth co-existance
- Mobile:
- rmnet: support TX aggregation"
* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
page_pool: add a comment explaining the fragment counter usage
net: ethtool: fix __ethtool_dev_mm_supported() implementation
ethtool: pse-pd: Fix double word in comments
xsk: add linux/vmalloc.h to xsk.c
sefltests: netdevsim: wait for devlink instance after netns removal
selftest: fib_tests: Always cleanup before exit
net/mlx5e: Align IPsec ASO result memory to be as required by hardware
net/mlx5e: TC, Set CT miss to the specific ct action instance
net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
net/mlx5: Refactor tc miss handling to a single function
net/mlx5: Kconfig: Make tc offload depend on tc skb extension
net/sched: flower: Support hardware miss to tc action
net/sched: flower: Move filter handle initialization earlier
net/sched: cls_api: Support hardware miss to tc action
net/sched: Rename user cookie and act cookie
sfc: fix builds without CONFIG_RTC_LIB
sfc: clean up some inconsistent indentings
net/mlx4_en: Introduce flexible array to silence overflow warning
net: lan966x: Fix possible deadlock inside PTP
net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
...
Diffstat (limited to 'net/dccp/dccp.h')
-rw-r--r-- | net/dccp/dccp.h | 483 |
1 files changed, 483 insertions, 0 deletions
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h new file mode 100644 index 000000000..9ddc3a9e8 --- /dev/null +++ b/net/dccp/dccp.h @@ -0,0 +1,483 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _DCCP_H +#define _DCCP_H +/* + * net/dccp/dccp.h + * + * An implementation of the DCCP protocol + * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> + * Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz> + */ + +#include <linux/dccp.h> +#include <linux/ktime.h> +#include <net/snmp.h> +#include <net/sock.h> +#include <net/tcp.h> +#include "ackvec.h" + +/* + * DCCP - specific warning and debugging macros. + */ +#define DCCP_WARN(fmt, ...) \ + net_warn_ratelimited("%s: " fmt, __func__, ##__VA_ARGS__) +#define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \ + __FILE__, __LINE__, __func__) +#define DCCP_BUG(a...) do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0) +#define DCCP_BUG_ON(cond) do { if (unlikely((cond) != 0)) \ + DCCP_BUG("\"%s\" holds (exception!)", \ + __stringify(cond)); \ + } while (0) + +#define DCCP_PRINTK(enable, fmt, args...) do { if (enable) \ + printk(fmt, ##args); \ + } while(0) +#define DCCP_PR_DEBUG(enable, fmt, a...) DCCP_PRINTK(enable, KERN_DEBUG \ + "%s: " fmt, __func__, ##a) + +#ifdef CONFIG_IP_DCCP_DEBUG +extern bool dccp_debug; +#define dccp_pr_debug(format, a...) DCCP_PR_DEBUG(dccp_debug, format, ##a) +#define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) +#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) +#else +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) +#endif + +extern struct inet_hashinfo dccp_hashinfo; + +DECLARE_PER_CPU(unsigned int, dccp_orphan_count); + +void dccp_time_wait(struct sock *sk, int state, int timeo); + +/* + * Set safe upper bounds for header and option length. Since Data Offset is 8 + * bits (RFC 4340, sec. 5.1), the total header length can never be more than + * 4 * 255 = 1020 bytes. The largest possible header length is 28 bytes (X=1): + * - DCCP-Response with ACK Subheader and 4 bytes of Service code OR + * - DCCP-Reset with ACK Subheader and 4 bytes of Reset Code fields + * Hence a safe upper bound for the maximum option length is 1020-28 = 992 + */ +#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t)) +#define DCCP_MAX_PACKET_HDR 28 +#define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR) +#define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER) + +/* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */ +#define DCCP_FEATNEG_OVERHEAD (32 * sizeof(uint32_t)) + +#define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT + * state, about 60 seconds */ + +/* RFC 1122, 4.2.3.1 initial RTO value */ +#define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ)) + +/* + * The maximum back-off value for retransmissions. This is needed for + * - retransmitting client-Requests (sec. 8.1.1), + * - retransmitting Close/CloseReq when closing (sec. 8.3), + * - feature-negotiation retransmission (sec. 6.6.3), + * - Acks in client-PARTOPEN state (sec. 8.1.5). + */ +#define DCCP_RTO_MAX ((unsigned int)(64 * HZ)) + +/* + * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4 + */ +#define DCCP_SANE_RTT_MIN 100 +#define DCCP_FALLBACK_RTT (USEC_PER_SEC / 5) +#define DCCP_SANE_RTT_MAX (3 * USEC_PER_SEC) + +/* sysctl variables for DCCP */ +extern int sysctl_dccp_request_retries; +extern int sysctl_dccp_retries1; +extern int sysctl_dccp_retries2; +extern int sysctl_dccp_tx_qlen; +extern int sysctl_dccp_sync_ratelimit; + +/* + * 48-bit sequence number arithmetic (signed and unsigned) + */ +#define INT48_MIN 0x800000000000LL /* 2^47 */ +#define UINT48_MAX 0xFFFFFFFFFFFFLL /* 2^48 - 1 */ +#define COMPLEMENT48(x) (0x1000000000000LL - (x)) /* 2^48 - x */ +#define TO_SIGNED48(x) (((x) < INT48_MIN)? (x) : -COMPLEMENT48( (x))) +#define TO_UNSIGNED48(x) (((x) >= 0)? (x) : COMPLEMENT48(-(x))) +#define ADD48(a, b) (((a) + (b)) & UINT48_MAX) +#define SUB48(a, b) ADD48((a), COMPLEMENT48(b)) + +static inline void dccp_inc_seqno(u64 *seqno) +{ + *seqno = ADD48(*seqno, 1); +} + +/* signed mod-2^48 distance: pos. if seqno1 < seqno2, neg. if seqno1 > seqno2 */ +static inline s64 dccp_delta_seqno(const u64 seqno1, const u64 seqno2) +{ + u64 delta = SUB48(seqno2, seqno1); + + return TO_SIGNED48(delta); +} + +/* is seq1 < seq2 ? */ +static inline int before48(const u64 seq1, const u64 seq2) +{ + return (s64)((seq2 << 16) - (seq1 << 16)) > 0; +} + +/* is seq1 > seq2 ? */ +#define after48(seq1, seq2) before48(seq2, seq1) + +/* is seq2 <= seq1 <= seq3 ? */ +static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3) +{ + return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16); +} + +/** + * dccp_loss_count - Approximate the number of lost data packets in a burst loss + * @s1: last known sequence number before the loss ('hole') + * @s2: first sequence number seen after the 'hole' + * @ndp: NDP count on packet with sequence number @s2 + */ +static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp) +{ + s64 delta = dccp_delta_seqno(s1, s2); + + WARN_ON(delta < 0); + delta -= ndp + 1; + + return delta > 0 ? delta : 0; +} + +/** + * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1 + */ +static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) +{ + return dccp_loss_count(s1, s2, ndp) == 0; +} + +enum { + DCCP_MIB_NUM = 0, + DCCP_MIB_ACTIVEOPENS, /* ActiveOpens */ + DCCP_MIB_ESTABRESETS, /* EstabResets */ + DCCP_MIB_CURRESTAB, /* CurrEstab */ + DCCP_MIB_OUTSEGS, /* OutSegs */ + DCCP_MIB_OUTRSTS, + DCCP_MIB_ABORTONTIMEOUT, + DCCP_MIB_TIMEOUTS, + DCCP_MIB_ABORTFAILED, + DCCP_MIB_PASSIVEOPENS, + DCCP_MIB_ATTEMPTFAILS, + DCCP_MIB_OUTDATAGRAMS, + DCCP_MIB_INERRS, + DCCP_MIB_OPTMANDATORYERROR, + DCCP_MIB_INVALIDOPT, + __DCCP_MIB_MAX +}; + +#define DCCP_MIB_MAX __DCCP_MIB_MAX +struct dccp_mib { + unsigned long mibs[DCCP_MIB_MAX]; +}; + +DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); +#define DCCP_INC_STATS(field) SNMP_INC_STATS(dccp_statistics, field) +#define __DCCP_INC_STATS(field) __SNMP_INC_STATS(dccp_statistics, field) +#define DCCP_DEC_STATS(field) SNMP_DEC_STATS(dccp_statistics, field) + +/* + * Checksumming routines + */ +static inline unsigned int dccp_csum_coverage(const struct sk_buff *skb) +{ + const struct dccp_hdr* dh = dccp_hdr(skb); + + if (dh->dccph_cscov == 0) + return skb->len; + return (dh->dccph_doff + dh->dccph_cscov - 1) * sizeof(u32); +} + +static inline void dccp_csum_outgoing(struct sk_buff *skb) +{ + unsigned int cov = dccp_csum_coverage(skb); + + if (cov >= skb->len) + dccp_hdr(skb)->dccph_cscov = 0; + + skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0); +} + +void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); + +int dccp_retransmit_skb(struct sock *sk); + +void dccp_send_ack(struct sock *sk); +void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, + struct request_sock *rsk); + +void dccp_send_sync(struct sock *sk, const u64 seq, + const enum dccp_pkt_type pkt_type); + +/* + * TX Packet Dequeueing Interface + */ +void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb); +bool dccp_qpolicy_full(struct sock *sk); +void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb); +struct sk_buff *dccp_qpolicy_top(struct sock *sk); +struct sk_buff *dccp_qpolicy_pop(struct sock *sk); +bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param); + +/* + * TX Packet Output and TX Timers + */ +void dccp_write_xmit(struct sock *sk); +void dccp_write_space(struct sock *sk); +void dccp_flush_write_queue(struct sock *sk, long *time_budget); + +void dccp_init_xmit_timers(struct sock *sk); +static inline void dccp_clear_xmit_timers(struct sock *sk) +{ + inet_csk_clear_xmit_timers(sk); +} + +unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); + +const char *dccp_packet_name(const int type); + +void dccp_set_state(struct sock *sk, const int state); +void dccp_done(struct sock *sk); + +int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp, + struct sk_buff const *skb); + +int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb); + +struct sock *dccp_create_openreq_child(const struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb); + +int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); + +struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req); +struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, + struct request_sock *req); + +int dccp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb); +int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, + struct dccp_hdr *dh, unsigned int len); +int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, const unsigned int len); + +void dccp_destruct_common(struct sock *sk); +int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); +void dccp_destroy_sock(struct sock *sk); + +void dccp_close(struct sock *sk, long timeout); +struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst, + struct request_sock *req); + +int dccp_connect(struct sock *sk); +int dccp_disconnect(struct sock *sk, int flags); +int dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int dccp_setsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, unsigned int optlen); +int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, + int *addr_len); +void dccp_shutdown(struct sock *sk, int how); +int inet_dccp_listen(struct socket *sock, int backlog); +__poll_t dccp_poll(struct file *file, struct socket *sock, + poll_table *wait); +int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +void dccp_req_err(struct sock *sk, u64 seq); + +struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb); +int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); +void dccp_send_close(struct sock *sk, const int active); +int dccp_invalid_packet(struct sk_buff *skb); +u32 dccp_sample_rtt(struct sock *sk, long delta); + +static inline bool dccp_bad_service_code(const struct sock *sk, + const __be32 service) +{ + const struct dccp_sock *dp = dccp_sk(sk); + + if (dp->dccps_service == service) + return false; + return !dccp_list_has_service(dp->dccps_service_list, service); +} + +/** + * dccp_skb_cb - DCCP per-packet control information + * @dccpd_type: one of %dccp_pkt_type (or unknown) + * @dccpd_ccval: CCVal field (5.1), see e.g. RFC 4342, 8.1 + * @dccpd_reset_code: one of %dccp_reset_codes + * @dccpd_reset_data: Data1..3 fields (depend on @dccpd_reset_code) + * @dccpd_opt_len: total length of all options (5.8) in the packet + * @dccpd_seq: sequence number + * @dccpd_ack_seq: acknowledgment number subheader field value + * + * This is used for transmission as well as for reception. + */ +struct dccp_skb_cb { + union { + struct inet_skb_parm h4; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_skb_parm h6; +#endif + } header; + __u8 dccpd_type:4; + __u8 dccpd_ccval:4; + __u8 dccpd_reset_code, + dccpd_reset_data[3]; + __u16 dccpd_opt_len; + __u64 dccpd_seq; + __u64 dccpd_ack_seq; +}; + +#define DCCP_SKB_CB(__skb) ((struct dccp_skb_cb *)&((__skb)->cb[0])) + +/* RFC 4340, sec. 7.7 */ +static inline int dccp_non_data_packet(const struct sk_buff *skb) +{ + const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; + + return type == DCCP_PKT_ACK || + type == DCCP_PKT_CLOSE || + type == DCCP_PKT_CLOSEREQ || + type == DCCP_PKT_RESET || + type == DCCP_PKT_SYNC || + type == DCCP_PKT_SYNCACK; +} + +/* RFC 4340, sec. 7.7 */ +static inline int dccp_data_packet(const struct sk_buff *skb) +{ + const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; + + return type == DCCP_PKT_DATA || + type == DCCP_PKT_DATAACK || + type == DCCP_PKT_REQUEST || + type == DCCP_PKT_RESPONSE; +} + +static inline int dccp_packet_without_ack(const struct sk_buff *skb) +{ + const __u8 type = DCCP_SKB_CB(skb)->dccpd_type; + + return type == DCCP_PKT_DATA || type == DCCP_PKT_REQUEST; +} + +#define DCCP_PKT_WITHOUT_ACK_SEQ (UINT48_MAX << 2) + +static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss) +{ + struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh + + sizeof(*dh)); + dh->dccph_seq2 = 0; + dh->dccph_seq = htons((gss >> 32) & 0xfffff); + dhx->dccph_seq_low = htonl(gss & 0xffffffff); +} + +static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack, + const u64 gsr) +{ + dhack->dccph_reserved1 = 0; + dhack->dccph_ack_nr_high = htons(gsr >> 32); + dhack->dccph_ack_nr_low = htonl(gsr & 0xffffffff); +} + +static inline void dccp_update_gsr(struct sock *sk, u64 seq) +{ + struct dccp_sock *dp = dccp_sk(sk); + + if (after48(seq, dp->dccps_gsr)) + dp->dccps_gsr = seq; + /* Sequence validity window depends on remote Sequence Window (7.5.1) */ + dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); + /* + * Adjust SWL so that it is not below ISR. In contrast to RFC 4340, + * 7.5.1 we perform this check beyond the initial handshake: W/W' are + * always > 32, so for the first W/W' packets in the lifetime of a + * connection we always have to adjust SWL. + * A second reason why we are doing this is that the window depends on + * the feature-remote value of Sequence Window: nothing stops the peer + * from updating this value while we are busy adjusting SWL for the + * first W packets (we would have to count from scratch again then). + * Therefore it is safer to always make sure that the Sequence Window + * is not artificially extended by a peer who grows SWL downwards by + * continually updating the feature-remote Sequence-Window. + * If sequence numbers wrap it is bad luck. But that will take a while + * (48 bit), and this measure prevents Sequence-number attacks. + */ + if (before48(dp->dccps_swl, dp->dccps_isr)) + dp->dccps_swl = dp->dccps_isr; + dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4); +} + +static inline void dccp_update_gss(struct sock *sk, u64 seq) +{ + struct dccp_sock *dp = dccp_sk(sk); + + dp->dccps_gss = seq; + /* Ack validity window depends on local Sequence Window value (7.5.1) */ + dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win); + /* Adjust AWL so that it is not below ISS - see comment above for SWL */ + if (before48(dp->dccps_awl, dp->dccps_iss)) + dp->dccps_awl = dp->dccps_iss; + dp->dccps_awh = dp->dccps_gss; +} + +static inline int dccp_ackvec_pending(const struct sock *sk) +{ + return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL && + !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec); +} + +static inline int dccp_ack_pending(const struct sock *sk) +{ + return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); +} + +int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val); +int dccp_feat_finalise_settings(struct dccp_sock *dp); +int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq); +int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*, + struct sk_buff *skb); +int dccp_feat_activate_values(struct sock *sk, struct list_head *fn); +void dccp_feat_list_purge(struct list_head *fn_list); + +int dccp_insert_options(struct sock *sk, struct sk_buff *skb); +int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *); +u32 dccp_timestamp(void); +void dccp_timestamping_init(void); +int dccp_insert_option(struct sk_buff *skb, unsigned char option, + const void *value, unsigned char len); + +#ifdef CONFIG_SYSCTL +int dccp_sysctl_init(void); +void dccp_sysctl_exit(void); +#else +static inline int dccp_sysctl_init(void) +{ + return 0; +} + +static inline void dccp_sysctl_exit(void) +{ +} +#endif + +#endif /* _DCCP_H */ |