From: Hao Luo <haoluo@google.com>
To: Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>
Cc: Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>, KP Singh <kpsingh@kernel.org>,
Shakeel Butt <shakeelb@google.com>,
Joe Burton <jevburton.kernel@gmail.com>,
Tejun Heo <tj@kernel.org>,
joshdon@google.com, sdf@google.com, bpf@vger.kernel.org,
linux-kernel@vger.kernel.org, Hao Luo <haoluo@google.com>
Subject: [PATCH bpf-next v1 8/9] bpf: Introduce cgroup iter
Date: Fri, 25 Feb 2022 15:43:38 -0800 [thread overview]
Message-ID: <20220225234339.2386398-9-haoluo@google.com> (raw)
In-Reply-To: <20220225234339.2386398-1-haoluo@google.com>
Introduce a new type of iter prog: cgroup. Unlike other bpf_iter, this
iter doesn't iterate a set of kernel objects. Instead, it is supposed to
be parameterized by a cgroup id and prints only that cgroup. So one
needs to specify a target cgroup id when attaching this iter.
The target cgroup's state can be read out via a link of this iter.
Typically, we can monitor cgroup creation and deletion using sleepable
tracing and use it to create corresponding directories in bpffs and pin
a cgroup id parameterized link in the directory. Then we can read the
auto-pinned iter link to get cgroup's state. The output of the iter link
is determined by the program. See the selftest test_cgroup_stats.c for
an example.
Signed-off-by: Hao Luo <haoluo@google.com>
---
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 6 ++
kernel/bpf/Makefile | 2 +-
kernel/bpf/cgroup_iter.c | 141 +++++++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 6 ++
5 files changed, 155 insertions(+), 1 deletion(-)
create mode 100644 kernel/bpf/cgroup_iter.c
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 759ade7b24b3..3ce9b0b7ed89 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1595,6 +1595,7 @@ int bpf_obj_get_path(bpfptr_t pathname, int flags);
struct bpf_iter_aux_info {
struct bpf_map *map;
+ u64 cgroup_id;
};
typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a5dbc794403d..855ad80d9983 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -91,6 +91,9 @@ union bpf_iter_link_info {
struct {
__u32 map_fd;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
/* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -5887,6 +5890,9 @@ struct bpf_link_info {
struct {
__u32 map_id;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
} iter;
struct {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index c1a9be6a4b9f..52a0e4c6e96e 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -8,7 +8,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
-obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o cgroup_iter.o
obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o
obj-$(CONFIG_BPF_SYSCALL) += disasm.o
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
new file mode 100644
index 000000000000..011d9dcd1d51
--- /dev/null
+++ b/kernel/bpf/cgroup_iter.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2022 Google */
+#include <linux/bpf.h>
+#include <linux/btf_ids.h>
+#include <linux/cgroup.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+
+struct bpf_iter__cgroup {
+ __bpf_md_ptr(struct bpf_iter_meta *, meta);
+ __bpf_md_ptr(struct cgroup *, cgroup);
+};
+
+static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ struct cgroup *cgroup;
+ u64 cgroup_id;
+
+ /* Only one session is supported. */
+ if (*pos > 0)
+ return NULL;
+
+ cgroup_id = *(u64 *)seq->private;
+ cgroup = cgroup_get_from_id(cgroup_id);
+ if (!cgroup)
+ return NULL;
+
+ if (*pos == 0)
+ ++*pos;
+
+ return cgroup;
+}
+
+static void *cgroup_iter_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ ++*pos;
+ return NULL;
+}
+
+static int cgroup_iter_seq_show(struct seq_file *seq, void *v)
+{
+ struct bpf_iter__cgroup ctx;
+ struct bpf_iter_meta meta;
+ struct bpf_prog *prog;
+ int ret = 0;
+
+ ctx.meta = &meta;
+ ctx.cgroup = v;
+ meta.seq = seq;
+ prog = bpf_iter_get_info(&meta, false);
+ if (prog)
+ ret = bpf_iter_run_prog(prog, &ctx);
+
+ return ret;
+}
+
+static void cgroup_iter_seq_stop(struct seq_file *seq, void *v)
+{
+ if (v)
+ cgroup_put(v);
+}
+
+static const struct seq_operations cgroup_iter_seq_ops = {
+ .start = cgroup_iter_seq_start,
+ .next = cgroup_iter_seq_next,
+ .stop = cgroup_iter_seq_stop,
+ .show = cgroup_iter_seq_show,
+};
+
+BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup)
+
+static int cgroup_iter_seq_init(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+ *(u64 *)priv_data = aux->cgroup_id;
+ return 0;
+}
+
+static void cgroup_iter_seq_fini(void *priv_data)
+{
+}
+
+static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
+ .seq_ops = &cgroup_iter_seq_ops,
+ .init_seq_private = cgroup_iter_seq_init,
+ .fini_seq_private = cgroup_iter_seq_fini,
+ .seq_priv_size = sizeof(u64),
+};
+
+static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
+ union bpf_iter_link_info *linfo,
+ struct bpf_iter_aux_info *aux)
+{
+ aux->cgroup_id = linfo->cgroup.cgroup_id;
+ return 0;
+}
+
+static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
+{
+}
+
+void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
+ struct seq_file *seq)
+{
+ char buf[64] = {0};
+
+ cgroup_path_from_kernfs_id(aux->cgroup_id, buf, sizeof(buf));
+ seq_printf(seq, "cgroup_id:\t%lu\n", aux->cgroup_id);
+ seq_printf(seq, "cgroup_path:\t%s\n", buf);
+}
+
+int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
+ struct bpf_link_info *info)
+{
+ info->iter.cgroup.cgroup_id = aux->cgroup_id;
+ return 0;
+}
+
+DEFINE_BPF_ITER_FUNC(cgroup, struct bpf_iter_meta *meta,
+ struct cgroup *cgroup)
+
+static struct bpf_iter_reg bpf_cgroup_reg_info = {
+ .target = "cgroup",
+ .attach_target = bpf_iter_attach_cgroup,
+ .detach_target = bpf_iter_detach_cgroup,
+ .show_fdinfo = bpf_iter_cgroup_show_fdinfo,
+ .fill_link_info = bpf_iter_cgroup_fill_link_info,
+ .ctx_arg_info_size = 1,
+ .ctx_arg_info = {
+ { offsetof(struct bpf_iter__cgroup, cgroup),
+ PTR_TO_BTF_ID },
+ },
+ .seq_info = &cgroup_iter_seq_info,
+};
+
+static int __init bpf_cgroup_iter_init(void)
+{
+ bpf_cgroup_reg_info.ctx_arg_info[0].btf_id = bpf_cgroup_btf_id[0];
+ return bpf_iter_reg_target(&bpf_cgroup_reg_info);
+}
+
+late_initcall(bpf_cgroup_iter_init);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a5dbc794403d..855ad80d9983 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -91,6 +91,9 @@ union bpf_iter_link_info {
struct {
__u32 map_fd;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
/* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -5887,6 +5890,9 @@ struct bpf_link_info {
struct {
__u32 map_id;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
} iter;
struct {
--
2.35.1.574.g5d30c73bfb-goog
next prev parent reply other threads:[~2022-02-25 23:44 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-25 23:43 [PATCH bpf-next v1 0/9] Extend cgroup interface with bpf Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 1/9] bpf: Add mkdir, rmdir, unlink syscalls for prog_bpf_syscall Hao Luo
2022-02-27 5:18 ` Kumar Kartikeya Dwivedi
2022-02-28 22:10 ` Hao Luo
2022-03-02 19:34 ` Alexei Starovoitov
2022-03-03 18:50 ` Hao Luo
2022-03-04 18:37 ` Hao Luo
2022-03-05 23:47 ` Alexei Starovoitov
2022-03-08 21:08 ` Hao Luo
2022-03-02 20:55 ` Yonghong Song
2022-03-03 18:56 ` Hao Luo
2022-03-03 19:13 ` Yonghong Song
2022-03-03 19:15 ` Hao Luo
2022-03-12 3:46 ` Al Viro
2022-03-14 17:07 ` Hao Luo
2022-03-14 23:10 ` Al Viro
2022-03-15 17:27 ` Hao Luo
2022-03-15 18:59 ` Alexei Starovoitov
2022-03-15 19:03 ` Alexei Starovoitov
2022-03-15 19:00 ` Al Viro
2022-03-15 19:47 ` Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 2/9] bpf: Add BPF_OBJ_PIN and BPF_OBJ_GET in the bpf_sys_bpf helper Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 3/9] selftests/bpf: tests mkdir, rmdir, unlink and pin in syscall Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 4/9] bpf: Introduce sleepable tracepoints Hao Luo
2022-03-02 19:41 ` Alexei Starovoitov
2022-03-03 19:37 ` Hao Luo
2022-03-03 19:59 ` Alexei Starovoitov
2022-03-02 21:23 ` Yonghong Song
2022-03-02 21:30 ` Alexei Starovoitov
2022-03-03 1:08 ` Yonghong Song
2022-03-03 2:29 ` Alexei Starovoitov
2022-03-03 19:43 ` Hao Luo
2022-03-03 20:02 ` Alexei Starovoitov
2022-03-03 20:04 ` Alexei Starovoitov
2022-03-03 22:06 ` Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 5/9] cgroup: Sleepable cgroup tracepoints Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 6/9] libbpf: Add sleepable tp_btf Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 7/9] bpf: Lift permission check in __sys_bpf when called from kernel Hao Luo
2022-03-02 20:01 ` Alexei Starovoitov
2022-03-03 19:14 ` Hao Luo
2022-02-25 23:43 ` Hao Luo [this message]
2022-02-26 2:32 ` [PATCH bpf-next v1 8/9] bpf: Introduce cgroup iter kernel test robot
2022-02-26 2:32 ` kernel test robot
2022-02-26 2:53 ` kernel test robot
2022-03-02 21:59 ` Yonghong Song
2022-03-03 20:02 ` Hao Luo
2022-03-02 22:45 ` Kumar Kartikeya Dwivedi
2022-03-03 2:03 ` Yonghong Song
2022-03-03 3:03 ` Kumar Kartikeya Dwivedi
2022-03-03 4:00 ` Alexei Starovoitov
2022-03-03 7:33 ` Yonghong Song
2022-03-03 8:13 ` Kumar Kartikeya Dwivedi
2022-03-03 21:52 ` Hao Luo
2022-02-25 23:43 ` [PATCH bpf-next v1 9/9] selftests/bpf: Tests using sleepable tracepoints to monitor cgroup events Hao Luo
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=20220225234339.2386398-9-haoluo@google.com \
--to=haoluo@google.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=jevburton.kernel@gmail.com \
--cc=joshdon@google.com \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sdf@google.com \
--cc=shakeelb@google.com \
--cc=songliubraving@fb.com \
--cc=tj@kernel.org \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
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;
as well as URLs for NNTP newsgroup(s).