From patchwork Thu May 7 05:39:27 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yonghong Song X-Patchwork-Id: 219725 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.0 required=3.0 tests=DKIMWL_WL_HIGH, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH, MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS, UNWANTED_LANGUAGE_BODY,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id EF1B2C47247 for ; Thu, 7 May 2020 05:39:45 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id CB36D207DD for ; Thu, 7 May 2020 05:39:45 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=fb.com header.i=@fb.com header.b="Pe2aotZU" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726942AbgEGFjp (ORCPT ); Thu, 7 May 2020 01:39:45 -0400 Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:23084 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726891AbgEGFjl (ORCPT ); Thu, 7 May 2020 01:39:41 -0400 Received: from pps.filterd (m0044012.ppops.net [127.0.0.1]) by mx0a-00082601.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id 0475aYkw004112 for ; Wed, 6 May 2020 22:39:40 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fb.com; h=from : to : cc : subject : date : message-id : in-reply-to : references : mime-version : content-transfer-encoding : content-type; s=facebook; bh=V3CtjC2PiB+MBdplFiHNEa954VIjiO9FVy3lu+rilMI=; b=Pe2aotZUJk+41ks5BUdH01fgoj39UC3L22vC1yGWlFHvh2VRajlpT5UHHuZ62a9Z+RN6 2HtTaSPUpZpfZ/792r/DgwGVF26NDYfNpyAdY5kpP7XhDrftRzj6bVms+GGrBIyZlWzN WHyX1dulX9RrZxk7fMTbxds3xFejFi/WBeg= Received: from maileast.thefacebook.com ([163.114.130.16]) by mx0a-00082601.pphosted.com with ESMTP id 30up69eddc-12 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128 verify=NOT) for ; Wed, 06 May 2020 22:39:40 -0700 Received: from intmgw003.08.frc2.facebook.com (2620:10d:c0a8:1b::d) by mail.thefacebook.com (2620:10d:c0a8:82::d) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.1847.3; Wed, 6 May 2020 22:39:32 -0700 Received: by devbig003.ftw2.facebook.com (Postfix, from userid 128203) id 067403701B99; Wed, 6 May 2020 22:39:27 -0700 (PDT) Smtp-Origin-Hostprefix: devbig From: Yonghong Song Smtp-Origin-Hostname: devbig003.ftw2.facebook.com To: Andrii Nakryiko , , Martin KaFai Lau , CC: Alexei Starovoitov , Daniel Borkmann , Smtp-Origin-Cluster: ftw2c04 Subject: [PATCH bpf-next v3 11/21] bpf: add task and task/file iterator targets Date: Wed, 6 May 2020 22:39:27 -0700 Message-ID: <20200507053927.1543615-1-yhs@fb.com> X-Mailer: git-send-email 2.24.1 In-Reply-To: <20200507053915.1542140-1-yhs@fb.com> References: <20200507053915.1542140-1-yhs@fb.com> MIME-Version: 1.0 X-FB-Internal: Safe X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.216, 18.0.676 definitions=2020-05-07_02:2020-05-05,2020-05-07 signatures=0 X-Proofpoint-Spam-Details: rule=fb_default_notspam policy=fb_default score=0 priorityscore=1501 clxscore=1015 bulkscore=0 impostorscore=0 adultscore=0 spamscore=0 lowpriorityscore=0 phishscore=0 mlxscore=0 malwarescore=0 mlxlogscore=999 suspectscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2003020000 definitions=main-2005070043 X-FB-Internal: deliver Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song --- kernel/bpf/Makefile | 2 +- kernel/bpf/task_iter.c | 332 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 333 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/task_iter.c diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index b2b5eefc5254..37b2d8620153 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,7 +2,7 @@ obj-y := core.o CFLAGS_core.o += $(call cc-disable-warning, override-init) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c new file mode 100644 index 000000000000..21dd794bf5d9 --- /dev/null +++ b/kernel/bpf/task_iter.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ + +#include +#include +#include +#include +#include +#include + +struct bpf_iter_seq_task_common { + struct pid_namespace *ns; +}; + +struct bpf_iter_seq_task_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + u32 tid; +}; + +static struct task_struct *task_seq_get_next(struct pid_namespace *ns, + u32 *tid) +{ + struct task_struct *task = NULL; + struct pid *pid; + + rcu_read_lock(); + pid = idr_get_next(&ns->idr, tid); + if (pid) + task = get_pid_task(pid, PIDTYPE_PID); + rcu_read_unlock(); + + return task; +} + +static void *task_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_info *info = seq->private; + struct task_struct *task; + + task = task_seq_get_next(info->common.ns, &info->tid); + if (!task) + return NULL; + + ++*pos; + return task; +} + +static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_info *info = seq->private; + struct task_struct *task; + + ++*pos; + ++info->tid; + put_task_struct((struct task_struct *)v); + task = task_seq_get_next(info->common.ns, &info->tid); + if (!task) + return NULL; + + return task; +} + +struct bpf_iter__task { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); +}; + +DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task) + +static int __task_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter_meta meta; + struct bpf_iter__task ctx; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + meta.seq = seq; + ctx.meta = &meta; + ctx.task = v; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_seq_show(struct seq_file *seq, void *v) +{ + return __task_seq_show(seq, v, false); +} + +static void task_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__task_seq_show(seq, v, true); + else + put_task_struct((struct task_struct *)v); +} + +static const struct seq_operations task_seq_ops = { + .start = task_seq_start, + .next = task_seq_next, + .stop = task_seq_stop, + .show = task_seq_show, +}; + +struct bpf_iter_seq_task_file_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + struct task_struct *task; + struct files_struct *files; + u32 tid; + u32 fd; +}; + +static struct file *task_file_seq_get_next(struct pid_namespace *ns, u32 *tid, + int *fd, struct task_struct **task, + struct files_struct **fstruct) +{ + struct files_struct *curr_files; + struct task_struct *curr_task; + u32 curr_tid = *tid, max_fds; + int curr_fd = *fd; + + /* If this function returns a non-NULL file object, + * it held a reference to the task/files_struct/file. + * Otherwise, it does not hold any reference. + */ +again: + if (*task) { + curr_task = *task; + curr_files = *fstruct; + curr_fd = *fd; + } else { + curr_task = task_seq_get_next(ns, &curr_tid); + if (!curr_task) + return NULL; + + curr_files = get_files_struct(curr_task); + if (!curr_files) { + put_task_struct(curr_task); + curr_tid = ++(*tid); + *fd = 0; + goto again; + } + + /* set *fstruct, *task and *tid */ + *fstruct = curr_files; + *task = curr_task; + if (curr_tid == *tid) { + curr_fd = *fd; + } else { + *tid = curr_tid; + curr_fd = 0; + } + } + + rcu_read_lock(); + max_fds = files_fdtable(curr_files)->max_fds; + for (; curr_fd < max_fds; curr_fd++) { + struct file *f; + + f = fcheck_files(curr_files, curr_fd); + if (!f) + continue; + + /* set *fd */ + *fd = curr_fd; + get_file(f); + rcu_read_unlock(); + return f; + } + + /* the current task is done, go to the next task */ + rcu_read_unlock(); + put_files_struct(curr_files); + put_task_struct(curr_task); + *task = NULL; + *fstruct = NULL; + *fd = 0; + curr_tid = ++(*tid); + goto again; +} + +static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + struct files_struct *files = NULL; + struct task_struct *task = NULL; + struct file *file; + + file = task_file_seq_get_next(info->common.ns, &info->tid, &info->fd, + &task, &files); + if (!file) { + info->files = NULL; + info->task = NULL; + return NULL; + } + + ++*pos; + info->task = task; + info->files = files; + + return file; +} + +static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + struct files_struct *files = info->files; + struct task_struct *task = info->task; + struct file *file; + + ++*pos; + ++info->fd; + fput((struct file *)v); + file = task_file_seq_get_next(info->common.ns, &info->tid, &info->fd, + &task, &files); + if (!file) { + info->files = NULL; + info->task = NULL; + return NULL; + } + + info->task = task; + info->files = files; + + return file; +} + +struct bpf_iter__task_file { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); + u32 fd __aligned(8); + __bpf_md_ptr(struct file *, file); +}; + +DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta, + struct task_struct *task, u32 fd, + struct file *file) + +static int __task_file_seq_show(struct seq_file *seq, void *v, bool in_stop) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + struct bpf_iter__task_file ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.task = info->task; + ctx.fd = info->fd; + ctx.file = v; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_file_seq_show(struct seq_file *seq, void *v) +{ + return __task_file_seq_show(seq, v, false); +} + +static void task_file_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + + if (!v) { + (void)__task_file_seq_show(seq, v, true); + } else { + fput((struct file *)v); + put_files_struct(info->files); + put_task_struct(info->task); + info->files = NULL; + info->task = NULL; + } +} + +static int init_seq_pidns(void *priv_data) +{ + struct bpf_iter_seq_task_common *common = priv_data; + + common->ns = get_pid_ns(task_active_pid_ns(current)); + return 0; +} + +static void fini_seq_pidns(void *priv_data) +{ + struct bpf_iter_seq_task_common *common = priv_data; + + put_pid_ns(common->ns); +} + +static const struct seq_operations task_file_seq_ops = { + .start = task_file_seq_start, + .next = task_file_seq_next, + .stop = task_file_seq_stop, + .show = task_file_seq_show, +}; + +static int __init task_iter_init(void) +{ + struct bpf_iter_reg task_file_reg_info = { + .target = "task_file", + .seq_ops = &task_file_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_file_info), + }; + struct bpf_iter_reg task_reg_info = { + .target = "task", + .seq_ops = &task_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_info), + }; + int ret; + + ret = bpf_iter_reg_target(&task_reg_info); + if (ret) + return ret; + + return bpf_iter_reg_target(&task_file_reg_info); +} +late_initcall(task_iter_init);