From: Yosry Ahmed <yosryahmed@google.com>
To: Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Andrii Nakryiko <andrii@kernel.org>,
Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>,
John Fastabend <john.fastabend@gmail.com>,
KP Singh <kpsingh@kernel.org>, Hao Luo <haoluo@google.com>,
Tejun Heo <tj@kernel.org>, Zefan Li <lizefan.x@bytedance.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Shuah Khan <shuah@kernel.org>,
Roman Gushchin <roman.gushchin@linux.dev>,
Michal Hocko <mhocko@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>,
David Rientjes <rientjes@google.com>,
Greg Thelen <gthelen@google.com>,
Shakeel Butt <shakeelb@google.com>,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
bpf@vger.kernel.org, cgroups@vger.kernel.org,
Yosry Ahmed <yosryahmed@google.com>
Subject: [RFC PATCH bpf-next 8/9] bpf: Introduce cgroup iter
Date: Tue, 10 May 2022 00:18:06 +0000 [thread overview]
Message-ID: <20220510001807.4132027-9-yosryahmed@google.com> (raw)
In-Reply-To: <20220510001807.4132027-1-yosryahmed@google.com>
From: Hao Luo <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.
Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
---
include/linux/bpf.h | 2 +
include/uapi/linux/bpf.h | 6 ++
kernel/bpf/Makefile | 2 +-
kernel/bpf/cgroup_iter.c | 148 +++++++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 6 ++
5 files changed, 163 insertions(+), 1 deletion(-)
create mode 100644 kernel/bpf/cgroup_iter.c
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f6fa35ffe311..f472f43521d2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -43,6 +43,7 @@ struct kobject;
struct mem_cgroup;
struct module;
struct bpf_func_state;
+struct cgroup;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@@ -1601,6 +1602,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags);
struct bpf_iter_aux_info {
struct bpf_map *map;
+ struct cgroup *cgroup;
};
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 015ed402c642..096c521e34de 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. */
@@ -5963,6 +5966,9 @@ 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 6caf4a61e543..07a715b54190 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..86bdfe135d24
--- /dev/null
+++ b/kernel/bpf/cgroup_iter.c
@@ -0,0 +1,148 @@
+// 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)
+{
+ /* Only one session is supported. */
+ if (*pos > 0)
+ return NULL;
+
+ if (*pos == 0)
+ ++*pos;
+
+ return *(struct cgroup **)seq->private;
+}
+
+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)
+{
+}
+
+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)
+{
+ *(struct cgroup **)priv_data = aux->cgroup;
+ return 0;
+}
+
+static const struct bpf_iter_seq_info cgroup_iter_seq_info = {
+ .seq_ops = &cgroup_iter_seq_ops,
+ .init_seq_private = cgroup_iter_seq_init,
+ .seq_priv_size = sizeof(struct cgroup *),
+};
+
+static int bpf_iter_attach_cgroup(struct bpf_prog *prog,
+ union bpf_iter_link_info *linfo,
+ struct bpf_iter_aux_info *aux)
+{
+ struct cgroup *cgroup;
+
+ cgroup = cgroup_get_from_id(linfo->cgroup.cgroup_id);
+ if (!cgroup)
+ return -EBUSY;
+
+ aux->cgroup = cgroup;
+ return 0;
+}
+
+static void bpf_iter_detach_cgroup(struct bpf_iter_aux_info *aux)
+{
+ if (aux->cgroup)
+ cgroup_put(aux->cgroup);
+}
+
+static void bpf_iter_cgroup_show_fdinfo(const struct bpf_iter_aux_info *aux,
+ struct seq_file *seq)
+{
+ char *buf;
+
+ seq_printf(seq, "cgroup_id:\t%llu\n", cgroup_id(aux->cgroup));
+
+ buf = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!buf) {
+ seq_puts(seq, "cgroup_path:\n");
+ return;
+ }
+
+ /* If cgroup_path_ns() fails, buf will be an empty string, cgroup_path
+ * will print nothing.
+ *
+ * Cgroup_path is the path in the calliing process's cgroup namespace.
+ */
+ cgroup_path_ns(aux->cgroup, buf, sizeof(buf),
+ current->nsproxy->cgroup_ns);
+ seq_printf(seq, "cgroup_path:\t%s\n", buf);
+ kfree(buf);
+}
+
+static int bpf_iter_cgroup_fill_link_info(const struct bpf_iter_aux_info *aux,
+ struct bpf_link_info *info)
+{
+ info->iter.cgroup.cgroup_id = cgroup_id(aux->cgroup);
+ 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 015ed402c642..096c521e34de 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. */
@@ -5963,6 +5966,9 @@ struct bpf_link_info {
struct {
__u32 map_id;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
} iter;
struct {
--
2.36.0.512.ge40c2bad7a-goog
next prev parent reply other threads:[~2022-05-10 0:19 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-05-10 0:17 [RFC PATCH bpf-next 0/9] bpf: cgroup hierarchical stats collection Yosry Ahmed
2022-05-10 0:17 ` [RFC PATCH bpf-next 1/9] bpf: introduce CGROUP_SUBSYS_RSTAT program type Yosry Ahmed
2022-05-10 18:07 ` Yosry Ahmed
2022-05-10 19:21 ` Yosry Ahmed
2022-05-10 18:44 ` Tejun Heo
2022-05-10 19:34 ` Yosry Ahmed
2022-05-10 19:59 ` Tejun Heo
2022-05-10 20:43 ` Yosry Ahmed
2022-05-10 21:01 ` Tejun Heo
2022-05-10 21:55 ` Yosry Ahmed
2022-05-10 22:09 ` Tejun Heo
2022-05-10 22:10 ` Yosry Ahmed
2022-05-10 0:18 ` [RFC PATCH bpf-next 2/9] cgroup: bpf: flush bpf stats on rstat flush Yosry Ahmed
2022-05-10 18:45 ` Tejun Heo
2022-05-10 0:18 ` [RFC PATCH bpf-next 3/9] libbpf: Add support for rstat progs and links Yosry Ahmed
2022-05-10 0:18 ` [RFC PATCH bpf-next 4/9] bpf: add bpf rstat helpers Yosry Ahmed
2022-05-10 0:18 ` [RFC PATCH bpf-next 5/9] bpf: add bpf_map_lookup_percpu_elem() helper Yosry Ahmed
2022-05-10 0:18 ` [RFC PATCH bpf-next 6/9] cgroup: add v1 support to cgroup_get_from_id() Yosry Ahmed
2022-05-10 18:33 ` Tejun Heo
2022-05-10 18:36 ` Yosry Ahmed
2022-05-10 0:18 ` [RFC PATCH bpf-next 7/9] cgroup: Add cgroup_put() in !CONFIG_CGROUPS case Yosry Ahmed
2022-05-10 18:25 ` Hao Luo
2022-05-10 0:18 ` Yosry Ahmed [this message]
2022-05-10 18:25 ` [RFC PATCH bpf-next 8/9] bpf: Introduce cgroup iter Hao Luo
2022-05-10 18:54 ` Tejun Heo
2022-05-10 21:12 ` Hao Luo
2022-05-10 22:07 ` Tejun Heo
2022-05-10 22:49 ` Hao Luo
2022-05-10 0:18 ` [RFC PATCH bpf-next 9/9] selftest/bpf: add a selftest for cgroup hierarchical stats Yosry Ahmed
2022-05-13 7:16 ` [RFC PATCH bpf-next 0/9] bpf: cgroup hierarchical stats collection Yosry Ahmed
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=20220510001807.4132027-9-yosryahmed@google.com \
--to=yosryahmed@google.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=cgroups@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=haoluo@google.com \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan.x@bytedance.com \
--cc=mhocko@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=sdf@google.com \
--cc=shakeelb@google.com \
--cc=shuah@kernel.org \
--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).