public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Yonghong Song <yhs@fb•com>
To: Andrii Nakryiko <andriin@fb•com>, <bpf@vger•kernel.org>,
	Martin KaFai Lau <kafai@fb•com>, <netdev@vger•kernel.org>
Cc: Alexei Starovoitov <ast@fb•com>,
	Daniel Borkmann <daniel@iogearbox•net>, <kernel-team@fb•com>
Subject: [PATCH bpf-next v1 11/19] bpf: add task and task/file targets
Date: Mon, 27 Apr 2020 13:12:47 -0700	[thread overview]
Message-ID: <20200427201247.2995622-1-yhs@fb.com> (raw)
In-Reply-To: <20200427201235.2994549-1-yhs@fb.com>

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 <yhs@fb•com>
---
 kernel/bpf/Makefile    |   2 +-
 kernel/bpf/task_iter.c | 319 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 320 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..ee29574e427d
--- /dev/null
+++ b/kernel/bpf/task_iter.c
@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/pid_namespace.h>
+#include <linux/fs.h>
+#include <linux/fdtable.h>
+#include <linux/filter.h>
+
+struct bpf_iter_seq_task_info {
+	struct pid_namespace *ns;
+	struct task_struct *task;
+	u32 id;
+};
+
+static struct task_struct *task_seq_get_next(struct pid_namespace *ns, u32 *id)
+{
+	struct task_struct *task = NULL;
+	struct pid *pid;
+
+	rcu_read_lock();
+	pid = idr_get_next(&ns->idr, id);
+	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;
+	u32 id = info->id;
+
+	if (*pos == 0)
+		info->ns = task_active_pid_ns(current);
+
+	task = task_seq_get_next(info->ns, &id);
+	if (!task)
+		return NULL;
+
+	++*pos;
+	info->task = task;
+	info->id = id;
+
+	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->id;
+	task = task_seq_get_next(info->ns, &info->id);
+	if (!task)
+		return NULL;
+
+	put_task_struct(info->task);
+	info->task = task;
+	return task;
+}
+
+struct bpf_iter__task {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+};
+
+int __init __bpf_iter__task(struct bpf_iter_meta *meta, struct task_struct *task)
+{
+	return 0;
+}
+
+static int task_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_iter__task ctx;
+	struct bpf_prog *prog;
+	int ret = 0;
+
+	prog = bpf_iter_get_prog(seq, sizeof(struct bpf_iter_seq_task_info),
+				 &meta.session_id, &meta.seq_num,
+				 v == (void *)0);
+	if (prog) {
+		meta.seq = seq;
+		ctx.meta = &meta;
+		ctx.task = v;
+		ret = bpf_iter_run_prog(prog, &ctx);
+	}
+
+	return ret == 0 ? 0 : -EINVAL;
+}
+
+static void task_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_info *info = seq->private;
+
+	if (!v)
+		task_seq_show(seq, v);
+
+	if (info->task) {
+		put_task_struct(info->task);
+		info->task = NULL;
+	}
+}
+
+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 {
+	struct pid_namespace *ns;
+	struct task_struct *task;
+	struct files_struct *files;
+	u32 id;
+	u32 fd;
+};
+
+static struct file *task_file_seq_get_next(struct pid_namespace *ns, u32 *id,
+					   int *fd, struct task_struct **task,
+					   struct files_struct **fstruct)
+{
+	struct files_struct *files;
+	struct task_struct *tk;
+	u32 sid = *id;
+	int sfd;
+
+	/* If this function returns a non-NULL file object,
+	 * it held a reference to the files_struct and file.
+	 * Otherwise, it does not hold any reference.
+	 */
+again:
+	if (*fstruct) {
+		files = *fstruct;
+		sfd = *fd;
+	} else {
+		tk = task_seq_get_next(ns, &sid);
+		if (!tk)
+			return NULL;
+
+		files = get_files_struct(tk);
+		put_task_struct(tk);
+		if (!files) {
+			sid = ++(*id);
+			*fd = 0;
+			goto again;
+		}
+		*fstruct = files;
+		*task = tk;
+		if (sid == *id) {
+			sfd = *fd;
+		} else {
+			*id = sid;
+			sfd = 0;
+		}
+	}
+
+	rcu_read_lock();
+	for (; sfd < files_fdtable(files)->max_fds; sfd++) {
+		struct file *f;
+
+		f = fcheck_files(files, sfd);
+		if (!f)
+			continue;
+		*fd = sfd;
+		get_file(f);
+		rcu_read_unlock();
+		return f;
+	}
+
+	/* the current task is done, go to the next task */
+	rcu_read_unlock();
+	put_files_struct(files);
+	*fstruct = NULL;
+	sid = ++(*id);
+	*fd = 0;
+	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;
+	u32 id = info->id;
+	int fd = info->fd;
+
+	if (*pos == 0)
+		info->ns = task_active_pid_ns(current);
+
+	file = task_file_seq_get_next(info->ns, &id, &fd, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		return NULL;
+	}
+
+	++*pos;
+	info->id = id;
+	info->fd = fd;
+	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;
+	u32 id = info->id;
+
+	++*pos;
+	++info->fd;
+	fput((struct file *)v);
+	file = task_file_seq_get_next(info->ns, &id, &info->fd, &task, &files);
+	if (!file) {
+		info->files = NULL;
+		return NULL;
+	}
+
+	info->id = id;
+	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;
+	__bpf_md_ptr(struct file *, file);
+};
+
+int __init __bpf_iter__task_file(struct bpf_iter_meta *meta,
+			      struct task_struct *task, u32 fd,
+			      struct file *file)
+{
+	return 0;
+}
+
+static int task_file_seq_show(struct seq_file *seq, void *v)
+{
+	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;
+	int ret = 0;
+
+	prog = bpf_iter_get_prog(seq, sizeof(struct bpf_iter_seq_task_file_info),
+				 &meta.session_id, &meta.seq_num, v == (void *)0);
+	if (prog) {
+		meta.seq = seq;
+		ctx.meta = &meta;
+		ctx.task = info->task;
+		ctx.fd = info->fd;
+		ctx.file = v;
+		ret = bpf_iter_run_prog(prog, &ctx);
+	}
+
+	return ret == 0 ? 0 : -EINVAL;
+}
+
+static void task_file_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_file_info *info = seq->private;
+
+	if (v)
+		fput((struct file *)v);
+	else
+		task_file_seq_show(seq, v);
+
+	if (info->files) {
+		put_files_struct(info->files);
+		info->files = NULL;
+	}
+}
+
+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",
+		.target_func_name	= "__bpf_iter__task_file",
+		.seq_ops		= &task_file_seq_ops,
+		.seq_priv_size		= sizeof(struct bpf_iter_seq_task_file_info),
+		.target_feature		= 0,
+	};
+	struct bpf_iter_reg task_reg_info = {
+		.target			= "task",
+		.target_func_name	= "__bpf_iter__task",
+		.seq_ops		= &task_seq_ops,
+		.seq_priv_size		= sizeof(struct bpf_iter_seq_task_info),
+		.target_feature		= 0,
+	};
+	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);
-- 
2.24.1


  parent reply	other threads:[~2020-04-27 20:13 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-27 20:12 [PATCH bpf-next v1 00/19] bpf: implement bpf iterator for kernel data Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 01/19] net: refactor net assignment for seq_net_private structure Yonghong Song
2020-04-29  5:38   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 02/19] bpf: implement an interface to register bpf_iter targets Yonghong Song
2020-04-28 16:20   ` Martin KaFai Lau
2020-04-28 16:50     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 03/19] bpf: add bpf_map iterator Yonghong Song
2020-04-29  0:37   ` Martin KaFai Lau
2020-04-29  0:48     ` Alexei Starovoitov
2020-04-29  1:15       ` Yonghong Song
2020-04-29  2:44         ` Alexei Starovoitov
2020-04-29  5:09           ` Yonghong Song
2020-04-29  6:08             ` Andrii Nakryiko
2020-04-29  6:20               ` Yonghong Song
2020-04-29  6:30                 ` Alexei Starovoitov
2020-04-29  6:40                   ` Andrii Nakryiko
2020-04-29  6:44                     ` Yonghong Song
2020-04-29 15:34                       ` Alexei Starovoitov
2020-04-29 18:14                         ` Yonghong Song
2020-04-29 19:19                         ` Andrii Nakryiko
2020-04-29 20:15                           ` Yonghong Song
2020-04-30  3:06                             ` Alexei Starovoitov
2020-04-30  4:01                               ` Yonghong Song
2020-04-29  6:34                 ` Martin KaFai Lau
2020-04-29  6:51                   ` Yonghong Song
2020-04-29 19:25                     ` Andrii Nakryiko
2020-04-29  1:02     ` Yonghong Song
2020-04-29  6:04   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 04/19] bpf: allow loading of a bpf_iter program Yonghong Song
2020-04-29  0:54   ` Martin KaFai Lau
2020-04-29  1:27     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 05/19] bpf: support bpf tracing/iter programs for BPF_LINK_CREATE Yonghong Song
2020-04-29  1:17   ` [Potential Spoof] " Martin KaFai Lau
2020-04-29  6:25   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 06/19] bpf: support bpf tracing/iter programs for BPF_LINK_UPDATE Yonghong Song
2020-04-29  1:32   ` Martin KaFai Lau
2020-04-29  5:04     ` Yonghong Song
2020-04-29  5:58       ` Martin KaFai Lau
2020-04-29  6:32         ` Andrii Nakryiko
2020-04-29  6:41           ` Martin KaFai Lau
2020-04-27 20:12 ` [PATCH bpf-next v1 07/19] bpf: create anonymous bpf iterator Yonghong Song
2020-04-29  5:39   ` Martin KaFai Lau
2020-04-29  6:56   ` Andrii Nakryiko
2020-04-29  7:06     ` Yonghong Song
2020-04-29 18:16       ` Andrii Nakryiko
2020-04-29 18:46         ` Martin KaFai Lau
2020-04-29 19:20           ` Yonghong Song
2020-04-29 20:50             ` Martin KaFai Lau
2020-04-29 20:54               ` Yonghong Song
2020-04-29 19:39   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 08/19] bpf: create file " Yonghong Song
2020-04-29 20:40   ` Andrii Nakryiko
2020-04-30 18:02     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 09/19] bpf: add PTR_TO_BTF_ID_OR_NULL support Yonghong Song
2020-04-29 20:46   ` Andrii Nakryiko
2020-04-29 20:51     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 10/19] bpf: add netlink and ipv6_route targets Yonghong Song
2020-04-28 19:49   ` kbuild test robot
2020-04-28 19:50   ` [RFC PATCH] bpf: __bpf_iter__netlink() can be static kbuild test robot
2020-04-27 20:12 ` Yonghong Song [this message]
2020-04-30  2:08   ` [PATCH bpf-next v1 11/19] bpf: add task and task/file targets Andrii Nakryiko
2020-05-01 17:23     ` Yonghong Song
2020-05-01 19:01       ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 12/19] bpf: add bpf_seq_printf and bpf_seq_write helpers Yonghong Song
2020-04-28  6:02   ` kbuild test robot
2020-04-28 16:35     ` Yonghong Song
2020-04-30 20:06       ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 13/19] bpf: handle spilled PTR_TO_BTF_ID properly when checking stack_boundary Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 14/19] bpf: support variable length array in tracing programs Yonghong Song
2020-04-30 20:04   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 15/19] tools/libbpf: add bpf_iter support Yonghong Song
2020-04-30  1:41   ` Andrii Nakryiko
2020-05-02  7:17     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 16/19] tools/bpftool: add bpf_iter support for bptool Yonghong Song
2020-04-28  9:27   ` Quentin Monnet
2020-04-28 17:35     ` Yonghong Song
2020-04-29  8:37       ` Quentin Monnet
2020-04-27 20:12 ` [PATCH bpf-next v1 17/19] tools/bpf: selftests: add iterator programs for ipv6_route and netlink Yonghong Song
2020-04-30  2:12   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 18/19] tools/bpf: selftests: add iter progs for bpf_map/task/task_file Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 19/19] tools/bpf: selftests: add bpf_iter selftests Yonghong Song

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200427201247.2995622-1-yhs@fb.com \
    --to=yhs@fb$(echo .)com \
    --cc=andriin@fb$(echo .)com \
    --cc=ast@fb$(echo .)com \
    --cc=bpf@vger$(echo .)kernel.org \
    --cc=daniel@iogearbox$(echo .)net \
    --cc=kafai@fb$(echo .)com \
    --cc=kernel-team@fb$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox