From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- net/sched/act_gate.c | 680 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 680 insertions(+) create mode 100644 net/sched/act_gate.c (limited to 'net/sched/act_gate.c') diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c new file mode 100644 index 000000000..c9a811f4c --- /dev/null +++ b/net/sched/act_gate.c @@ -0,0 +1,680 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright 2020 NXP */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct tc_action_ops act_gate_ops; + +static ktime_t gate_get_time(struct tcf_gate *gact) +{ + ktime_t mono = ktime_get(); + + switch (gact->tk_offset) { + case TK_OFFS_MAX: + return mono; + default: + return ktime_mono_to_any(mono, gact->tk_offset); + } + + return KTIME_MAX; +} + +static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +{ + struct tcf_gate_params *param = &gact->param; + ktime_t now, base, cycle; + u64 n; + + base = ns_to_ktime(param->tcfg_basetime); + now = gate_get_time(gact); + + if (ktime_after(base, now)) { + *start = base; + return; + } + + cycle = param->tcfg_cycletime; + + n = div64_u64(ktime_sub_ns(now, base), cycle); + *start = ktime_add_ns(base, (n + 1) * cycle); +} + +static void gate_start_timer(struct tcf_gate *gact, ktime_t start) +{ + ktime_t expires; + + expires = hrtimer_get_expires(&gact->hitimer); + if (expires == 0) + expires = KTIME_MAX; + + start = min_t(ktime_t, start, expires); + + hrtimer_start(&gact->hitimer, start, HRTIMER_MODE_ABS_SOFT); +} + +static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) +{ + struct tcf_gate *gact = container_of(timer, struct tcf_gate, + hitimer); + struct tcf_gate_params *p = &gact->param; + struct tcfg_gate_entry *next; + ktime_t close_time, now; + + spin_lock(&gact->tcf_lock); + + next = gact->next_entry; + + /* cycle start, clear pending bit, clear total octets */ + gact->current_gate_status = next->gate_state ? GATE_ACT_GATE_OPEN : 0; + gact->current_entry_octets = 0; + gact->current_max_octets = next->maxoctets; + + gact->current_close_time = ktime_add_ns(gact->current_close_time, + next->interval); + + close_time = gact->current_close_time; + + if (list_is_last(&next->list, &p->entries)) + next = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + else + next = list_next_entry(next, list); + + now = gate_get_time(gact); + + if (ktime_after(now, close_time)) { + ktime_t cycle, base; + u64 n; + + cycle = p->tcfg_cycletime; + base = ns_to_ktime(p->tcfg_basetime); + n = div64_u64(ktime_sub_ns(now, base), cycle); + close_time = ktime_add_ns(base, (n + 1) * cycle); + } + + gact->next_entry = next; + + hrtimer_set_expires(&gact->hitimer, close_time); + + spin_unlock(&gact->tcf_lock); + + return HRTIMER_RESTART; +} + +TC_INDIRECT_SCOPE int tcf_gate_act(struct sk_buff *skb, + const struct tc_action *a, + struct tcf_result *res) +{ + struct tcf_gate *gact = to_gate(a); + int action = READ_ONCE(gact->tcf_action); + + tcf_lastuse_update(&gact->tcf_tm); + tcf_action_update_bstats(&gact->common, skb); + + spin_lock(&gact->tcf_lock); + if (unlikely(gact->current_gate_status & GATE_ACT_PENDING)) { + spin_unlock(&gact->tcf_lock); + return action; + } + + if (!(gact->current_gate_status & GATE_ACT_GATE_OPEN)) { + spin_unlock(&gact->tcf_lock); + goto drop; + } + + if (gact->current_max_octets >= 0) { + gact->current_entry_octets += qdisc_pkt_len(skb); + if (gact->current_entry_octets > gact->current_max_octets) { + spin_unlock(&gact->tcf_lock); + goto overlimit; + } + } + spin_unlock(&gact->tcf_lock); + + return action; + +overlimit: + tcf_action_inc_overlimit_qstats(&gact->common); +drop: + tcf_action_inc_drop_qstats(&gact->common); + return TC_ACT_SHOT; +} + +static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = { + [TCA_GATE_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_GATE] = { .type = NLA_FLAG }, + [TCA_GATE_ENTRY_INTERVAL] = { .type = NLA_U32 }, + [TCA_GATE_ENTRY_IPV] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_MAX_OCTETS] = { .type = NLA_S32 }, +}; + +static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = { + [TCA_GATE_PARMS] = + NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)), + [TCA_GATE_PRIORITY] = { .type = NLA_S32 }, + [TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_GATE_BASE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME] = { .type = NLA_U64 }, + [TCA_GATE_CYCLE_TIME_EXT] = { .type = NLA_U64 }, + [TCA_GATE_FLAGS] = { .type = NLA_U32 }, + [TCA_GATE_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_gate_entry(struct nlattr **tb, struct tcfg_gate_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + entry->gate_state = nla_get_flag(tb[TCA_GATE_ENTRY_GATE]); + + if (tb[TCA_GATE_ENTRY_INTERVAL]) + interval = nla_get_u32(tb[TCA_GATE_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + if (tb[TCA_GATE_ENTRY_IPV]) + entry->ipv = nla_get_s32(tb[TCA_GATE_ENTRY_IPV]); + else + entry->ipv = -1; + + if (tb[TCA_GATE_ENTRY_MAX_OCTETS]) + entry->maxoctets = nla_get_s32(tb[TCA_GATE_ENTRY_MAX_OCTETS]); + else + entry->maxoctets = -1; + + return 0; +} + +static int parse_gate_entry(struct nlattr *n, struct tcfg_gate_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_GATE_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_GATE_ENTRY_MAX, n, entry_policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_gate_entry(tb, entry, extack); +} + +static void release_entry_list(struct list_head *entries) +{ + struct tcfg_gate_entry *entry, *e; + + list_for_each_entry_safe(entry, e, entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int parse_gate_list(struct nlattr *list_attr, + struct tcf_gate_params *sched, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list_attr) + return -EINVAL; + + nla_for_each_nested(n, list_attr, rem) { + if (nla_type(n) != TCA_GATE_ONE_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute isn't type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + err = -ENOMEM; + goto release_list; + } + + err = parse_gate_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + goto release_list; + } + + list_add_tail(&entry->list, &sched->entries); + i++; + } + + sched->num_entries = i; + + return i; + +release_list: + release_entry_list(&sched->entries); + + return err; +} + +static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, + enum tk_offsets tko, s32 clockid, + bool do_init) +{ + if (!do_init) { + if (basetime == gact->param.tcfg_basetime && + tko == gact->tk_offset && + clockid == gact->param.tcfg_clockid) + return; + + spin_unlock_bh(&gact->tcf_lock); + hrtimer_cancel(&gact->hitimer); + spin_lock_bh(&gact->tcf_lock); + } + gact->param.tcfg_basetime = basetime; + gact->param.tcfg_clockid = clockid; + gact->tk_offset = tko; + hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT); + gact->hitimer.function = gate_timer_func; +} + +static int tcf_gate_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action **a, + struct tcf_proto *tp, u32 flags, + struct netlink_ext_ack *extack) +{ + struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); + enum tk_offsets tk_offset = TK_OFFS_TAI; + bool bind = flags & TCA_ACT_FLAGS_BIND; + struct nlattr *tb[TCA_GATE_MAX + 1]; + struct tcf_chain *goto_ch = NULL; + u64 cycletime = 0, basetime = 0; + struct tcf_gate_params *p; + s32 clockid = CLOCK_TAI; + struct tcf_gate *gact; + struct tc_gate *parm; + int ret = 0, err; + u32 gflags = 0; + s32 prio = -1; + ktime_t start; + u32 index; + + if (!nla) + return -EINVAL; + + err = nla_parse_nested(tb, TCA_GATE_MAX, nla, gate_policy, extack); + if (err < 0) + return err; + + if (!tb[TCA_GATE_PARMS]) + return -EINVAL; + + if (tb[TCA_GATE_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); + switch (clockid) { + case CLOCK_REALTIME: + tk_offset = TK_OFFS_REAL; + break; + case CLOCK_MONOTONIC: + tk_offset = TK_OFFS_MAX; + break; + case CLOCK_BOOTTIME: + tk_offset = TK_OFFS_BOOT; + break; + case CLOCK_TAI: + tk_offset = TK_OFFS_TAI; + break; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; + } + } + + parm = nla_data(tb[TCA_GATE_PARMS]); + index = parm->index; + + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + + if (err && bind) + return 0; + + if (!err) { + ret = tcf_idr_create_from_flags(tn, index, est, a, + &act_gate_ops, bind, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + + ret = ACT_P_CREATED; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + + if (tb[TCA_GATE_PRIORITY]) + prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); + + if (tb[TCA_GATE_BASE_TIME]) + basetime = nla_get_u64(tb[TCA_GATE_BASE_TIME]); + + if (tb[TCA_GATE_FLAGS]) + gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); + + gact = to_gate(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&gact->param.entries); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + spin_lock_bh(&gact->tcf_lock); + p = &gact->param; + + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + + if (tb[TCA_GATE_ENTRY_LIST]) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto chain_put; + } + + if (!cycletime) { + struct tcfg_gate_entry *entry; + ktime_t cycle = 0; + + list_for_each_entry(entry, &p->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + cycletime = cycle; + if (!cycletime) { + err = -EINVAL; + goto chain_put; + } + } + p->tcfg_cycletime = cycletime; + + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + p->tcfg_cycletime_ext = + nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); + + gate_setup_timer(gact, basetime, tk_offset, clockid, + ret == ACT_P_CREATED); + p->tcfg_priority = prio; + p->tcfg_flags = gflags; + gate_get_start_time(gact, &start); + + gact->current_close_time = start; + gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; + + gact->next_entry = list_first_entry(&p->entries, + struct tcfg_gate_entry, list); + + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + + gate_start_timer(gact, start); + + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + + return ret; + +chain_put: + spin_unlock_bh(&gact->tcf_lock); + + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + /* action is not inserted in any list: it's safe to init hitimer + * without taking tcf_lock. + */ + if (ret == ACT_P_CREATED) + gate_setup_timer(gact, gact->param.tcfg_basetime, + gact->tk_offset, gact->param.tcfg_clockid, + true); + tcf_idr_release(*a, bind); + return err; +} + +static void tcf_gate_cleanup(struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_gate_params *p; + + p = &gact->param; + hrtimer_cancel(&gact->hitimer); + release_entry_list(&p->entries); +} + +static int dumping_entry(struct sk_buff *skb, + struct tcfg_gate_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start_noflag(skb, TCA_GATE_ONE_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (entry->gate_state && nla_put_flag(skb, TCA_GATE_ENTRY_GATE)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_ENTRY_INTERVAL, entry->interval)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_MAX_OCTETS, entry->maxoctets)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_ENTRY_IPV, entry->ipv)) + goto nla_put_failure; + + return nla_nest_end(skb, item); + +nla_put_failure: + nla_nest_cancel(skb, item); + return -1; +} + +static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tcf_gate *gact = to_gate(a); + struct tc_gate opt = { + .index = gact->tcf_index, + .refcnt = refcount_read(&gact->tcf_refcnt) - ref, + .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind, + }; + struct tcfg_gate_entry *entry; + struct tcf_gate_params *p; + struct nlattr *entry_list; + struct tcf_t t; + + spin_lock_bh(&gact->tcf_lock); + opt.action = gact->tcf_action; + + p = &gact->param; + + if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_BASE_TIME, + p->tcfg_basetime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME, + p->tcfg_cycletime, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME_EXT, + p->tcfg_cycletime_ext, TCA_GATE_PAD)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_CLOCKID, p->tcfg_clockid)) + goto nla_put_failure; + + if (nla_put_u32(skb, TCA_GATE_FLAGS, p->tcfg_flags)) + goto nla_put_failure; + + if (nla_put_s32(skb, TCA_GATE_PRIORITY, p->tcfg_priority)) + goto nla_put_failure; + + entry_list = nla_nest_start_noflag(skb, TCA_GATE_ENTRY_LIST); + if (!entry_list) + goto nla_put_failure; + + list_for_each_entry(entry, &p->entries, list) { + if (dumping_entry(skb, entry) < 0) + goto nla_put_failure; + } + + nla_nest_end(skb, entry_list); + + tcf_tm_dump(&t, &gact->tcf_tm); + if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) + goto nla_put_failure; + spin_unlock_bh(&gact->tcf_lock); + + return skb->len; + +nla_put_failure: + spin_unlock_bh(&gact->tcf_lock); + nlmsg_trim(skb, b); + return -1; +} + +static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets, + u64 drops, u64 lastuse, bool hw) +{ + struct tcf_gate *gact = to_gate(a); + struct tcf_t *tm = &gact->tcf_tm; + + tcf_action_update_stats(a, bytes, packets, drops, hw); + tm->lastuse = max_t(u64, tm->lastuse, lastuse); +} + +static size_t tcf_gate_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_gate)); +} + +static void tcf_gate_entry_destructor(void *priv) +{ + struct action_gate_entry *oe = priv; + + kfree(oe); +} + +static int tcf_gate_get_entries(struct flow_action_entry *entry, + const struct tc_action *act) +{ + entry->gate.entries = tcf_gate_get_list(act); + + if (!entry->gate.entries) + return -EINVAL; + + entry->destructor = tcf_gate_entry_destructor; + entry->destructor_priv = entry->gate.entries; + + return 0; +} + +static int tcf_gate_offload_act_setup(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack) +{ + int err; + + if (bind) { + struct flow_action_entry *entry = entry_data; + + entry->id = FLOW_ACTION_GATE; + entry->gate.prio = tcf_gate_prio(act); + entry->gate.basetime = tcf_gate_basetime(act); + entry->gate.cycletime = tcf_gate_cycletime(act); + entry->gate.cycletimeext = tcf_gate_cycletimeext(act); + entry->gate.num_entries = tcf_gate_num_entries(act); + err = tcf_gate_get_entries(entry, act); + if (err) + return err; + *index_inc = 1; + } else { + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_GATE; + } + + return 0; +} + +static struct tc_action_ops act_gate_ops = { + .kind = "gate", + .id = TCA_ID_GATE, + .owner = THIS_MODULE, + .act = tcf_gate_act, + .dump = tcf_gate_dump, + .init = tcf_gate_init, + .cleanup = tcf_gate_cleanup, + .stats_update = tcf_gate_stats_update, + .get_fill_size = tcf_gate_get_fill_size, + .offload_act_setup = tcf_gate_offload_act_setup, + .size = sizeof(struct tcf_gate), +}; + +static __net_init int gate_init_net(struct net *net) +{ + struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); + + return tc_action_net_init(net, tn, &act_gate_ops); +} + +static void __net_exit gate_exit_net(struct list_head *net_list) +{ + tc_action_net_exit(net_list, act_gate_ops.net_id); +} + +static struct pernet_operations gate_net_ops = { + .init = gate_init_net, + .exit_batch = gate_exit_net, + .id = &act_gate_ops.net_id, + .size = sizeof(struct tc_action_net), +}; + +static int __init gate_init_module(void) +{ + return tcf_register_action(&act_gate_ops, &gate_net_ops); +} + +static void __exit gate_cleanup_module(void) +{ + tcf_unregister_action(&act_gate_ops, &gate_net_ops); +} + +module_init(gate_init_module); +module_exit(gate_cleanup_module); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3