From patchwork Thu Jun 2 04:10:27 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Cong Wang X-Patchwork-Id: 12867490 X-Patchwork-Delegate: bpf@iogearbox.net Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 30FA6C433EF for ; Thu, 2 Jun 2022 04:11:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229713AbiFBELT (ORCPT ); Thu, 2 Jun 2022 00:11:19 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:32884 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229682AbiFBELC (ORCPT ); Thu, 2 Jun 2022 00:11:02 -0400 Received: from mail-qk1-x72e.google.com (mail-qk1-x72e.google.com [IPv6:2607:f8b0:4864:20::72e]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7204520C6CE; Wed, 1 Jun 2022 21:11:00 -0700 (PDT) Received: by mail-qk1-x72e.google.com with SMTP id d12so1252258qke.5; Wed, 01 Jun 2022 21:11:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=6SaQB2KY5hg6A/cClHc+Er5tacEkWzmSGpRc1pU4Ce8=; b=Bau+uP9R0LpNWLVrbbdidmqjTkIRm98LSk/M0y+BRiZJvJ8X4LD6T0Z+ijCm6PIiv9 wwISoTsJzmUYOm3lMJKd0RM+mViMamE+iVF1VAYp7Z4e67mWY5G3tvEgqhSO0e+Co/JJ 3mSl/7gL0+2BcvAnj8RFxwqqbzlVAgB4WQ632d4bOBLKzojg7IHWL2XBBZzjZ7CW4psE Sfs259Hxiz+ikE2v321RHGtFcTB1sPWQSJ6dNiR5+yc4t0hrBfD7ZoIe9h8Z5ZFli+Uq 7I6BwFIT1dy5/S+hmJKiLGy2MvCWtQWX2phZJiGJSjd0DCbZTzUlec0HuLodP0pUU3Y7 pwdQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=6SaQB2KY5hg6A/cClHc+Er5tacEkWzmSGpRc1pU4Ce8=; b=E2uv2qdMO80zlBEC3ZvWq1IP1+EFoP6lz1TW6llRRZANLlL9lv2O3whvlP1al44fy1 juNoZAaLUPaEdoIG+qTb18Jj7GBTtqn47mvVrKKUScAo0EKrOCNWv+hT02uvHvtscKyI p+fjuOoz3Jk9J5VZRKRfy4h7xpgJ4MtXsuo+YPxOf6zLopixfWaTneH2zSnX1zWSVhx4 1jwk6HHfczKd4xllwm03bDYGapV+StfrSaJHeBhrOTE5PO7vJDEUmJh93n7tc+FMLAZK saIbkTJHTA4dkqCMKFuGoMLQuDNqKESU60GdXhG/PpVwminU2gBW1G40z2Gyre/TPztf H24w== X-Gm-Message-State: AOAM533Qa42Dd3c7bSC/7xtebhkNRWlg7/nHA3jOoN848xczK4wkBz+g EpC/lz+vafqYjMFLIiAW87nJLDhQjz8= X-Google-Smtp-Source: ABdhPJzettd+5UO4ErfCUv0+Ddu74wWupigNSMNRw5VfjVY10q3wutHt+GVRoAueJM4756jlBE5UxA== X-Received: by 2002:a05:620a:244b:b0:6a5:b92e:9b with SMTP id h11-20020a05620a244b00b006a5b92e009bmr1944553qkn.610.1654143059261; Wed, 01 Jun 2022 21:10:59 -0700 (PDT) Received: from pop-os.attlocal.net ([2600:1700:65a0:ab60:d7c6:fc22:5340:d891]) by smtp.gmail.com with ESMTPSA id i187-20020a3786c4000000b0069fc13ce1fesm2396654qkd.47.2022.06.01.21.10.58 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 01 Jun 2022 21:10:58 -0700 (PDT) From: Cong Wang To: netdev@vger.kernel.org Cc: bpf@vger.kernel.org, Cong Wang , Cong Wang Subject: [RFC Patch v5 4/5] net_sched: introduce eBPF based Qdisc Date: Wed, 1 Jun 2022 21:10:27 -0700 Message-Id: <20220602041028.95124-5-xiyou.wangcong@gmail.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220602041028.95124-1-xiyou.wangcong@gmail.com> References: <20220602041028.95124-1-xiyou.wangcong@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: bpf@iogearbox.net X-Patchwork-State: RFC Introduce a new Qdisc which is completely managed by eBPF program of type BPF_PROG_TYPE_SCHED_QDISC. It accepts two eBPF programs of the same type, but one for enqueue and the other for dequeue. And it interacts with Qdisc layer in two ways: 1) It relies on Qdisc watchdog to handle throttling; 2) It could pass the skb enqueue/dequeue down to child classes The context of this eBPF program is different, as shown below: ┌─────────────────┬───────────────┬────────────────────────────────────┐ │ │ │ │ │ prog │ input │ output │ │ │ │ │ ├─────────────────┼───────────────┼────────────────────────────────────┤ │ │ │ │ │ │ ctx->skb │ SCH_BPF_THROTTLE: ctx->delay │ │ │ │ │ │ enqueue │ ctx->classid │ SCH_BPF_QUEUED: None │ │ │ │ │ │ │ │ SCH_BPF_DROP: None │ │ │ │ │ │ │ │ SCH_BPF_CN: None │ │ │ │ │ │ │ │ SCH_BPF_PASS: ctx->classid │ ├─────────────────┼───────────────┼────────────────────────────────────┤ │ │ │ │ │ │ │ SCH_BPF_THROTTLE: ctx->delay │ │ │ │ │ │ dequeue │ ctx->classid │ SCH_BPF_DEQUEUED: ctx->skb │ │ │ │ │ │ │ │ SCH_BPF_DROP: None │ │ │ │ │ │ │ │ SCH_BPF_PASS: ctx->classid │ │ │ │ │ └─────────────────┴───────────────┴────────────────────────────────────┘ Because eBPF maps are not directly visible to this Qdisc, so we have to rely on user-space dumping to retrieve the stats, which is not implemented yet as I don't find a right API to do this. Signed-off-by: Cong Wang --- include/linux/bpf.h | 4 - include/linux/bpf_types.h | 2 + include/uapi/linux/bpf.h | 16 ++ include/uapi/linux/pkt_sched.h | 17 ++ net/core/filter.c | 34 +++ net/sched/Kconfig | 15 + net/sched/Makefile | 1 + net/sched/sch_bpf.c | 485 +++++++++++++++++++++++++++++++++ 8 files changed, 570 insertions(+), 4 deletions(-) create mode 100644 net/sched/sch_bpf.c diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 43fbb45b6fc2..cf04ddce2c2d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2274,10 +2274,6 @@ extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_kptr_xchg_proto; -extern const struct bpf_func_proto bpf_skb_map_push_proto; -extern const struct bpf_func_proto bpf_skb_map_pop_proto; -extern const struct bpf_func_proto bpf_flow_map_push_proto; -extern const struct bpf_func_proto bpf_flow_map_pop_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b1276f9f9d26..1baeea8771d2 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -8,6 +8,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act, struct __sk_buff, struct sk_buff) BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act, struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_QDISC, tc_qdisc, + struct __sk_buff, struct sk_buff) BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, struct xdp_md, struct xdp_buff) #ifdef CONFIG_CGROUP_BPF diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cd9cff0df639..148ec0c4e643 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -954,6 +954,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ + BPF_PROG_TYPE_SCHED_QDISC, }; enum bpf_attach_type { @@ -6765,4 +6766,19 @@ struct bpf_core_relo { enum bpf_core_relo_kind kind; }; +struct sch_bpf_ctx { + struct __sk_buff *skb; + __u32 classid; + __u64 delay; +}; + +enum { + SCH_BPF_QUEUED, + SCH_BPF_DEQUEUED = SCH_BPF_QUEUED, + SCH_BPF_DROP, + SCH_BPF_CN, + SCH_BPF_THROTTLE, + SCH_BPF_PASS, +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index f292b467b27f..b51eb712517a 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1267,4 +1267,21 @@ enum { #define TCA_ETS_MAX (__TCA_ETS_MAX - 1) +#define TCA_SCH_BPF_FLAG_DIRECT _BITUL(0) +enum { + TCA_SCH_BPF_UNSPEC, + TCA_SCH_BPF_FLAGS, /* u32 */ + TCA_SCH_BPF_ENQUEUE_PROG_NAME, /* string */ + TCA_SCH_BPF_ENQUEUE_PROG_FD, /* u32 */ + TCA_SCH_BPF_ENQUEUE_PROG_ID, /* u32 */ + TCA_SCH_BPF_ENQUEUE_PROG_TAG, /* data */ + TCA_SCH_BPF_DEQUEUE_PROG_NAME, /* string */ + TCA_SCH_BPF_DEQUEUE_PROG_FD, /* u32 */ + TCA_SCH_BPF_DEQUEUE_PROG_ID, /* u32 */ + TCA_SCH_BPF_DEQUEUE_PROG_TAG, /* data */ + __TCA_SCH_BPF_MAX, +}; + +#define TCA_SCH_BPF_MAX (__TCA_SCH_BPF_MAX - 1) + #endif diff --git a/net/core/filter.c b/net/core/filter.c index 5af58eb48587..1205298a17ca 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7813,6 +7813,28 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_skb_map_push_proto __weak; +const struct bpf_func_proto bpf_skb_map_pop_proto __weak; +const struct bpf_func_proto bpf_flow_map_push_proto __weak; +const struct bpf_func_proto bpf_flow_map_pop_proto __weak; + +static const struct bpf_func_proto * +tc_qdisc_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_skb_map_push: + return &bpf_skb_map_push_proto; + case BPF_FUNC_skb_map_pop: + return &bpf_skb_map_pop_proto; + case BPF_FUNC_flow_map_push: + return &bpf_flow_map_push_proto; + case BPF_FUNC_flow_map_pop: + return &bpf_flow_map_pop_proto; + default: + return tc_cls_act_func_proto(func_id, prog); + } +} + static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -10476,6 +10498,18 @@ const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; +const struct bpf_verifier_ops tc_qdisc_verifier_ops = { + .get_func_proto = tc_qdisc_func_proto, + .is_valid_access = tc_cls_act_is_valid_access, + .convert_ctx_access = tc_cls_act_convert_ctx_access, + .gen_prologue = tc_cls_act_prologue, + .gen_ld_abs = bpf_gen_ld_abs, +}; + +const struct bpf_prog_ops tc_qdisc_prog_ops = { + .test_run = bpf_prog_test_run_skb, +}; + const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1e8ab4749c6c..19f68aac79b1 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -439,6 +439,21 @@ config NET_SCH_ETS If unsure, say N. +config NET_SCH_BPF + tristate "eBPF based programmable queue discipline" + help + This eBPF based queue discipline offers a way to program your + own packet scheduling algorithm. This is a classful qdisc which + also allows you to decide the hierarchy. + + Say Y here if you want to use the eBPF based programmable queue + discipline. + + To compile this driver as a module, choose M here: the module + will be called sch_bpf. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" help diff --git a/net/sched/Makefile b/net/sched/Makefile index dd14ef413fda..9ef0d579f5ff 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_NET_SCH_FQ_PIE) += sch_fq_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o +obj-$(CONFIG_NET_SCH_BPF) += sch_bpf.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/sch_bpf.c b/net/sched/sch_bpf.c new file mode 100644 index 000000000000..e9eba23ef4d1 --- /dev/null +++ b/net/sched/sch_bpf.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Programmable Qdisc with eBPF + * + * Copyright (C) 2022, ByteDance, Cong Wang + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ACT_BPF_NAME_LEN 256 + +struct sch_bpf_prog { + struct bpf_prog *prog; + const char *name; +}; + +struct sch_bpf_class { + struct Qdisc_class_common common; + struct Qdisc *qdisc; + + unsigned int drops; + unsigned int overlimits; + struct gnet_stats_basic_sync bstats; +}; + +struct sch_bpf_qdisc { + struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; + struct Qdisc_class_hash clhash; + struct sch_bpf_prog enqueue_prog; + struct sch_bpf_prog dequeue_prog; + + struct qdisc_watchdog watchdog; +}; + +static int sch_bpf_dump_prog(const struct sch_bpf_prog *prog, struct sk_buff *skb, + int name, int id, int tag) +{ + struct nlattr *nla; + + if (prog->name && + nla_put_string(skb, name, prog->name)) + return -EMSGSIZE; + + if (nla_put_u32(skb, id, prog->prog->aux->id)) + return -EMSGSIZE; + + nla = nla_reserve(skb, tag, sizeof(prog->prog->tag)); + if (!nla) + return -EMSGSIZE; + + memcpy(nla_data(nla), prog->prog->tag, nla_len(nla)); + return 0; +} + +static int sch_bpf_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + struct nlattr *opts; + u32 bpf_flags = 0; + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_put_failure; + + if (bpf_flags && nla_put_u32(skb, TCA_SCH_BPF_FLAGS, bpf_flags)) + goto nla_put_failure; + + if (sch_bpf_dump_prog(&q->enqueue_prog, skb, TCA_SCH_BPF_ENQUEUE_PROG_NAME, + TCA_SCH_BPF_ENQUEUE_PROG_ID, TCA_SCH_BPF_ENQUEUE_PROG_TAG)) + goto nla_put_failure; + if (sch_bpf_dump_prog(&q->dequeue_prog, skb, TCA_SCH_BPF_DEQUEUE_PROG_NAME, + TCA_SCH_BPF_DEQUEUE_PROG_ID, TCA_SCH_BPF_DEQUEUE_PROG_TAG)) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + return -1; +} + +static int sch_bpf_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + return 0; +} + +static struct sch_bpf_class *sch_bpf_find(struct Qdisc *sch, u32 classid) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + struct Qdisc_class_common *clc; + + clc = qdisc_class_find(&q->clhash, classid); + if (!clc) + return NULL; + return container_of(clc, struct sch_bpf_class, common); +} + +static int sch_bpf_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); + struct sch_bpf_ctx ctx = {}; + struct sch_bpf_class *cl; + int res = NET_XMIT_SUCCESS; + struct bpf_prog *enqueue; + s64 now; + + enqueue = rcu_dereference(q->enqueue_prog.prog); + bpf_compute_data_pointers(skb); + ctx.skb = (struct __sk_buff *)skb; + ctx.classid = sch->handle; + res = bpf_prog_run(enqueue, &ctx); + switch (res) { + case SCH_BPF_THROTTLE: + now = ktime_get_ns(); + qdisc_watchdog_schedule_ns(&q->watchdog, now + ctx.delay); + qdisc_qstats_overlimit(sch); + fallthrough; + case SCH_BPF_QUEUED: + return NET_XMIT_SUCCESS; + case SCH_BPF_CN: + return NET_XMIT_CN; + case SCH_BPF_PASS: + break; + default: + __qdisc_drop(skb, to_free); + return NET_XMIT_DROP; + } + + cl = sch_bpf_find(sch, ctx.classid); + if (!cl || !cl->qdisc) { + if (res & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return res; + } + + res = qdisc_enqueue(skb, cl->qdisc, to_free); + if (res != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(res)) { + qdisc_qstats_drop(sch); + cl->drops++; + } + return res; + } + + sch->qstats.backlog += len; + sch->q.qlen++; + return res; +} + +static struct sk_buff *sch_bpf_dequeue(struct Qdisc *sch) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + struct sk_buff *ret = NULL; + struct sch_bpf_ctx ctx = {}; + struct bpf_prog *dequeue; + struct sch_bpf_class *cl; + s64 now; + int res; + + dequeue = rcu_dereference(q->dequeue_prog.prog); + ctx.classid = sch->handle; + res = bpf_prog_run(dequeue, &ctx); + switch (res) { + case SCH_BPF_DEQUEUED: + ret = (struct sk_buff *)ctx.skb; + break; + case SCH_BPF_THROTTLE: + now = ktime_get_ns(); + qdisc_watchdog_schedule_ns(&q->watchdog, now + ctx.delay); + qdisc_qstats_overlimit(sch); + cl->overlimits++; + return NULL; + case SCH_BPF_PASS: + cl = sch_bpf_find(sch, ctx.classid); + if (!cl || !cl->qdisc) + return NULL; + ret = qdisc_dequeue_peeked(cl->qdisc); + if (ret) { + qdisc_bstats_update(sch, ret); + qdisc_qstats_backlog_dec(sch, ret); + sch->q.qlen--; + } + } + + return ret; +} + +static struct Qdisc *sch_bpf_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct sch_bpf_class *cl = (struct sch_bpf_class *)arg; + + return cl->qdisc; +} + +static int sch_bpf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old, struct netlink_ext_ack *extack) +{ + struct sch_bpf_class *cl = (struct sch_bpf_class *)arg; + + if (new) + *old = qdisc_replace(sch, new, &cl->qdisc); + return 0; +} + +static unsigned long sch_bpf_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static void sch_bpf_unbind(struct Qdisc *q, unsigned long cl) +{ +} + +static unsigned long sch_bpf_search(struct Qdisc *sch, u32 handle) +{ + return (unsigned long)sch_bpf_find(sch, handle); +} + +static struct tcf_block *sch_bpf_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + + if (cl) + return NULL; + return q->block; +} + +static const struct nla_policy sch_bpf_policy[TCA_SCH_BPF_MAX + 1] = { + [TCA_SCH_BPF_FLAGS] = { .type = NLA_U32 }, + [TCA_SCH_BPF_ENQUEUE_PROG_FD] = { .type = NLA_U32 }, + [TCA_SCH_BPF_ENQUEUE_PROG_NAME] = { .type = NLA_NUL_STRING, + .len = ACT_BPF_NAME_LEN }, + [TCA_SCH_BPF_DEQUEUE_PROG_FD] = { .type = NLA_U32 }, + [TCA_SCH_BPF_DEQUEUE_PROG_NAME] = { .type = NLA_NUL_STRING, + .len = ACT_BPF_NAME_LEN }, +}; + +static int bpf_init_prog(struct nlattr *fd, struct nlattr *name, struct sch_bpf_prog *prog) +{ + char *prog_name = NULL; + struct bpf_prog *fp; + u32 bpf_fd; + + if (!fd) + return -EINVAL; + bpf_fd = nla_get_u32(fd); + + fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_QDISC); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + if (name) { + prog_name = nla_memdup(name, GFP_KERNEL); + if (!prog_name) { + bpf_prog_put(fp); + return -ENOMEM; + } + } + + prog->name = prog_name; + prog->prog = fp; + return 0; +} + +static void bpf_cleanup_prog(struct sch_bpf_prog *prog) +{ + if (prog->prog) + bpf_prog_put(prog->prog); + kfree(prog->name); +} + +static int sch_bpf_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + struct nlattr *tb[TCA_SCH_BPF_MAX + 1]; + int err; + + if (!opt) + return -EINVAL; + + err = nla_parse_nested_deprecated(tb, TCA_SCH_BPF_MAX, opt, + sch_bpf_policy, NULL); + if (err < 0) + return err; + + if (tb[TCA_SCH_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_SCH_BPF_FLAGS]); + + if (bpf_flags & ~TCA_SCH_BPF_FLAG_DIRECT) + return -EINVAL; + } + + err = bpf_init_prog(tb[TCA_SCH_BPF_ENQUEUE_PROG_FD], + tb[TCA_SCH_BPF_ENQUEUE_PROG_NAME], &q->enqueue_prog); + if (err) + return err; + err = bpf_init_prog(tb[TCA_SCH_BPF_DEQUEUE_PROG_FD], + tb[TCA_SCH_BPF_DEQUEUE_PROG_NAME], &q->dequeue_prog); + return err; +} + +static int sch_bpf_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + int err; + + qdisc_watchdog_init(&q->watchdog, sch); + if (opt) { + err = sch_bpf_change(sch, opt, extack); + if (err) + return err; + } + + err = tcf_block_get(&q->block, &q->filter_list, sch, extack); + if (err) + return err; + + return qdisc_class_hash_init(&q->clhash); +} + +static void sch_bpf_reset(struct Qdisc *sch) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); +} + +static void sch_bpf_destroy(struct Qdisc *sch) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); + tcf_block_put(q->block); + qdisc_class_hash_destroy(&q->clhash); + bpf_cleanup_prog(&q->enqueue_prog); + bpf_cleanup_prog(&q->dequeue_prog); +} + +static int sch_bpf_change_class(struct Qdisc *sch, u32 classid, + u32 parentid, struct nlattr **tca, + unsigned long *arg, + struct netlink_ext_ack *extack) +{ + struct sch_bpf_class *cl = (struct sch_bpf_class *)*arg; + struct sch_bpf_qdisc *q = qdisc_priv(sch); + + if (!cl) { + cl = kzalloc(sizeof(*cl), GFP_KERNEL); + if (!cl) + return -ENOBUFS; + qdisc_class_hash_insert(&q->clhash, &cl->common); + } + + qdisc_class_hash_grow(sch, &q->clhash); + *arg = (unsigned long)cl; + return 0; +} + +static int sch_bpf_delete(struct Qdisc *sch, unsigned long arg, + struct netlink_ext_ack *extack) +{ + struct sch_bpf_class *cl = (struct sch_bpf_class *)arg; + struct sch_bpf_qdisc *q = qdisc_priv(sch); + + qdisc_class_hash_remove(&q->clhash, &cl->common); + if (cl->qdisc) + qdisc_put(cl->qdisc); + return 0; +} + +static int sch_bpf_dump_class(struct Qdisc *sch, unsigned long arg, + struct sk_buff *skb, struct tcmsg *tcm) +{ + return 0; +} + +static int +sch_bpf_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) +{ + struct sch_bpf_class *cl = (struct sch_bpf_class *)arg; + struct gnet_stats_queue qs = { + .drops = cl->drops, + .overlimits = cl->overlimits, + }; + __u32 qlen = 0; + + if (cl->qdisc) + qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &qs.backlog); + else + qlen = 0; + + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || + gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0) + return -1; + return 0; +} + +static void sch_bpf_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct sch_bpf_qdisc *q = qdisc_priv(sch); + struct sch_bpf_class *cl; + unsigned int i; + + if (arg->stop) + return; + + for (i = 0; i < q->clhash.hashsize; i++) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, (unsigned long)cl, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + } +} + +static const struct Qdisc_class_ops sch_bpf_class_ops = { + .graft = sch_bpf_graft, + .leaf = sch_bpf_leaf, + .find = sch_bpf_search, + .change = sch_bpf_change_class, + .delete = sch_bpf_delete, + .tcf_block = sch_bpf_tcf_block, + .bind_tcf = sch_bpf_bind, + .unbind_tcf = sch_bpf_unbind, + .dump = sch_bpf_dump_class, + .dump_stats = sch_bpf_dump_class_stats, + .walk = sch_bpf_walk, +}; + +static struct Qdisc_ops sch_bpf_qdisc_ops __read_mostly = { + .cl_ops = &sch_bpf_class_ops, + .id = "bpf", + .priv_size = sizeof(struct sch_bpf_qdisc), + .enqueue = sch_bpf_enqueue, + .dequeue = sch_bpf_dequeue, + .peek = qdisc_peek_dequeued, + .init = sch_bpf_init, + .reset = sch_bpf_reset, + .destroy = sch_bpf_destroy, + .change = sch_bpf_change, + .dump = sch_bpf_dump, + .dump_stats = sch_bpf_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init sch_bpf_mod_init(void) +{ + return register_qdisc(&sch_bpf_qdisc_ops); +} + +static void __exit sch_bpf_mod_exit(void) +{ + unregister_qdisc(&sch_bpf_qdisc_ops); +} + +module_init(sch_bpf_mod_init) +module_exit(sch_bpf_mod_exit) +MODULE_AUTHOR("Cong Wang"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("eBPF queue discipline");