From 8ac6c7a54ed1b98d142dce24b11c6de6a1e239a5 Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 22 Oct 2024 10:36:11 +0000 Subject: [PATCH] 修改4g拨号为QMI,需要在系统里后台执行quectel-CM --- kernel/net/sched/sch_api.c | 400 +++++++++++++++++++++++++++++++++++++++----------------- 1 files changed, 275 insertions(+), 125 deletions(-) diff --git a/kernel/net/sched/sch_api.c b/kernel/net/sched/sch_api.c index 6b4ee7c..5c2d230 100644 --- a/kernel/net/sched/sch_api.c +++ b/kernel/net/sched/sch_api.c @@ -1,10 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_api.c Packet scheduler API. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * @@ -27,7 +23,6 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> @@ -36,6 +31,8 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> + +#include <trace/events/qdisc.h> /* @@ -270,7 +267,8 @@ root->handle == handle) return root; - hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle) { + hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle, + lockdep_rtnl_is_held()) { if (q->handle == handle) return q; } @@ -303,7 +301,7 @@ if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; @@ -322,7 +320,7 @@ if (!handle) return NULL; - q = qdisc_match_from_root(dev->qdisc, handle); + q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out; @@ -336,7 +334,6 @@ static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; - struct Qdisc *leaf; const struct Qdisc_class_ops *cops = p->ops->cl_ops; if (cops == NULL) @@ -345,8 +342,7 @@ if (cl == 0) return NULL; - leaf = cops->leaf(p, cl); - return leaf; + return cops->leaf(p, cl); } /* Find queueing discipline by name */ @@ -483,7 +479,8 @@ u16 *tab = NULL; int err; - err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, extack); + err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy, + extack); if (err < 0) return ERR_PTR(err); if (!tb[TCA_STAB_BASE]) { @@ -536,11 +533,6 @@ return stab; } -static void stab_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct qdisc_size_table, rcu)); -} - void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) @@ -548,7 +540,7 @@ if (--tab->refcnt == 0) { list_del(&tab->list); - call_rcu_bh(&tab->rcu, stab_kfree_rcu); + kfree_rcu(tab, rcu); } } EXPORT_SYMBOL(qdisc_put_stab); @@ -557,7 +549,7 @@ { struct nlattr *nest; - nest = nla_nest_start(skb, TCA_STAB); + nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) @@ -636,21 +628,28 @@ } EXPORT_SYMBOL(qdisc_watchdog_init); -void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) +void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, + u64 delta_ns) { if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state)) return; - if (wd->last_expires == expires) - return; + if (hrtimer_is_queued(&wd->timer)) { + /* If timer is already set in [expires, expires + delta_ns], + * do not reprogram it. + */ + if (wd->last_expires - expires <= delta_ns) + return; + } wd->last_expires = expires; - hrtimer_start(&wd->timer, - ns_to_ktime(expires), - HRTIMER_MODE_ABS_PINNED); + hrtimer_start_range_ns(&wd->timer, + ns_to_ktime(expires), + delta_ns, + HRTIMER_MODE_ABS_PINNED); } -EXPORT_SYMBOL(qdisc_watchdog_schedule_ns); +EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { @@ -768,8 +767,7 @@ return 0; } -void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, - unsigned int len) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; @@ -817,6 +815,71 @@ rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); + +int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, + void *type_data) +{ + struct net_device *dev = qdisc_dev(sch); + int err; + + sch->flags &= ~TCQ_F_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + sch->flags |= TCQ_F_OFFLOADED; + + return err; +} +EXPORT_SYMBOL(qdisc_offload_dump_helper); + +void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack) +{ + bool any_qdisc_is_offloaded; + int err; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); + + /* Don't report error if the graft is part of destroy operation. */ + if (!err || !new || new == &noop_qdisc) + return; + + /* Don't report error if the parent, the old child and the new + * one are not offloaded. + */ + any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; + any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; + + if (any_qdisc_is_offloaded) + NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); +} +EXPORT_SYMBOL(qdisc_offload_graft_helper); + +static void qdisc_offload_graft_root(struct net_device *dev, + struct Qdisc *new, struct Qdisc *old, + struct netlink_ext_ack *extack) +{ + struct tc_root_qopt_offload graft_offload = { + .command = TC_ROOT_GRAFT, + .handle = new ? new->handle : 0, + .ingress = (new && new->flags & TCQ_F_INGRESS) || + (old && old->flags & TCQ_F_INGRESS), + }; + + qdisc_offload_graft_helper(dev, NULL, new, old, + TC_SETUP_ROOT_QDISC, &graft_offload, extack); +} static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event) @@ -949,6 +1012,19 @@ qdisc_put(old); } +static void qdisc_clear_nolock(struct Qdisc *sch) +{ + sch->flags &= ~TCQ_F_NOLOCK; + if (!(sch->flags & TCQ_F_CPUSTATS)) + return; + + free_percpu(sch->cpu_bstats); + free_percpu(sch->cpu_qstats); + sch->cpu_bstats = NULL; + sch->cpu_qstats = NULL; + sch->flags &= ~TCQ_F_CPUSTATS; +} + /* Graft qdisc "new" to class "classid" of qdisc "parent" or * to device "dev". * @@ -965,16 +1041,15 @@ { struct Qdisc *q = old; struct net *net = dev_net(dev); - int err = 0; if (parent == NULL) { unsigned int i, num_q, ingress; + struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { - num_q = 1; ingress = 1; if (!dev_ingress_queue(dev)) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); @@ -985,30 +1060,33 @@ if (dev->flags & IFF_UP) dev_deactivate(dev); + qdisc_offload_graft_root(dev, new, old, extack); + if (new && new->ops->attach) goto skip; - for (i = 0; i < num_q; i++) { - struct netdev_queue *dev_queue = dev_ingress_queue(dev); - - if (!ingress) + if (!ingress) { + for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); + old = dev_graft_qdisc(dev_queue, new); - old = dev_graft_qdisc(dev_queue, new); - if (new && i > 0) - qdisc_refcount_inc(new); - - if (!ingress) + if (new && i > 0) + qdisc_refcount_inc(new); qdisc_put(old); + } + } else { + dev_queue = dev_ingress_queue(dev); + old = dev_graft_qdisc(dev_queue, new); } skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); - dev->qdisc = new ? : &noop_qdisc; + rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + + notify_and_destroy(net, skb, n, classid, old, new); if (new && new->ops->attach) new->ops->attach(new); @@ -1020,28 +1098,33 @@ dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; + unsigned long cl; + int err; /* Only support running class lockless if parent is lockless */ - if (new && (new->flags & TCQ_F_NOLOCK) && - parent && !(parent->flags & TCQ_F_NOLOCK)) - new->flags &= ~TCQ_F_NOLOCK; + if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) + qdisc_clear_nolock(new); - err = -EOPNOTSUPP; - if (cops && cops->graft) { - unsigned long cl = cops->find(parent, classid); + if (!cops || !cops->graft) + return -EOPNOTSUPP; - if (cl) { - err = cops->graft(parent, cl, new, &old, - extack); - } else { - NL_SET_ERR_MSG(extack, "Specified class not found"); - err = -ENOENT; - } + cl = cops->find(parent, classid); + if (!cl) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return -ENOENT; } - if (!err) - notify_and_destroy(net, skb, n, classid, old, new); + + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + + err = cops->graft(parent, cl, new, &old, extack); + if (err) + return err; + notify_and_destroy(net, skb, n, classid, old, new); } - return err; + return 0; } static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, @@ -1077,10 +1160,6 @@ } return 0; } - -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; /* Allocate and initialize new qdisc. @@ -1144,17 +1223,22 @@ sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); - err = -ENOMEM; - if (handle == 0) + if (handle == 0) { + NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); + err = -ENOSPC; goto err_out3; + } } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } @@ -1191,7 +1275,7 @@ rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - net_seqlock_t *running; + seqcount_t *running; err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { @@ -1219,6 +1303,7 @@ } qdisc_hash_add(sch, false); + trace_qdisc_create(ops, dev, parent); return sch; @@ -1333,8 +1418,7 @@ } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, @@ -1364,8 +1448,8 @@ !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, - extack); + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1387,7 +1471,7 @@ q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); @@ -1429,10 +1513,28 @@ return 0; } +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1449,8 +1551,8 @@ replay: /* Reinit, just in case something touches this. */ - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, - extack); + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1476,7 +1578,7 @@ q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { - q = dev->qdisc; + q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ @@ -1505,10 +1607,19 @@ NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; + } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; } qdisc_refcount_inc(q); goto graft; @@ -1520,27 +1631,35 @@ * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1574,6 +1693,7 @@ NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), p, @@ -1684,8 +1804,8 @@ idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, - rtm_tca_policy, NULL); + err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX, + rtm_tca_policy, cb->extack); if (err < 0) return err; @@ -1698,7 +1818,8 @@ s_q_idx = 0; q_idx = 0; - if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, + if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), + skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; @@ -1778,6 +1899,7 @@ { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) @@ -1788,8 +1910,11 @@ return -EINVAL; } - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (err > 0) + err = 0; + return err; } static int tclass_del_notify(struct net *net, @@ -1820,8 +1945,11 @@ return err; } - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); + if (err > 0) + err = 0; + return err; } #ifdef CONFIG_NET_CLS @@ -1847,36 +1975,57 @@ return 0; } +struct tc_bind_class_args { + struct qdisc_walker w; + unsigned long new_cl; + u32 portid; + u32 clid; +}; + +static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w) +{ + struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tcf_block *block; + struct tcf_chain *chain; + + block = cops->tcf_block(q, cl, NULL); + if (!block) + return 0; + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + struct tcf_proto *tp; + + for (tp = tcf_get_next_proto(chain, NULL, true); + tp; tp = tcf_get_next_proto(chain, tp, true)) { + struct tcf_bind_args arg = {}; + + arg.w.fn = tcf_node_bind; + arg.classid = a->clid; + arg.base = cl; + arg.cl = a->new_cl; + tp->ops->walk(tp, &arg.w, true); + } + } + + return 0; +} + static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { const struct Qdisc_class_ops *cops = q->ops->cl_ops; - struct tcf_block *block; - struct tcf_chain *chain; - unsigned long cl; + struct tc_bind_class_args args = {}; - cl = cops->find(q, portid); - if (!cl) - return; if (!cops->tcf_block) return; - block = cops->tcf_block(q, cl, NULL); - if (!block) - return; - list_for_each_entry(chain, &block->chain_list, list) { - struct tcf_proto *tp; - - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) { - struct tcf_bind_args arg = {}; - - arg.w.fn = tcf_node_bind; - arg.classid = clid; - arg.base = cl; - arg.cl = new_cl; - tp->ops->walk(tp, &arg.w); - } - } + args.portid = portid; + args.clid = clid; + args.new_cl = new_cl; + args.w.fn = tc_bind_class_walker; + q->ops->cl_ops->walk(q, &args.w); } #else @@ -1908,8 +2057,8 @@ !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, - extack); + err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, + rtm_tca_policy, extack); if (err < 0) return err; @@ -1946,7 +2095,7 @@ } else if (qid1) { qid = qid1; } else if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. @@ -1957,7 +2106,7 @@ portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) - qid = dev->qdisc->handle; + qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ @@ -2118,7 +2267,8 @@ s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) + if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), + skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); -- Gitblit v1.6.2