[PATCH bpf-next v1 11/19] bpf: add task and task/file targets

[Yonghong Song <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