[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220515023504.1823463-6-yosryahmed@google.com>
Date: Sun, 15 May 2022 02:35:02 +0000
From: Yosry Ahmed <yosryahmed@...gle.com>
To: Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>, Hao Luo <haoluo@...gle.com>,
Tejun Heo <tj@...nel.org>, Zefan Li <lizefan.x@...edance.com>,
Johannes Weiner <hannes@...xchg.org>,
Shuah Khan <shuah@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Michal Hocko <mhocko@...nel.org>
Cc: Stanislav Fomichev <sdf@...gle.com>,
David Rientjes <rientjes@...gle.com>,
Greg Thelen <gthelen@...gle.com>,
Shakeel Butt <shakeelb@...gle.com>,
linux-kernel@...r.kernel.org, netdev@...r.kernel.org,
bpf@...r.kernel.org, cgroups@...r.kernel.org,
Yosry Ahmed <yosryahmed@...gle.com>
Subject: [RFC PATCH bpf-next v2 5/7] bpf: Introduce cgroup iter
From: Hao Luo <haoluo@...gle.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@...gle.com>
Signed-off-by: Yosry Ahmed <yosryahmed@...gle.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 ca908a731cb4..45076c581f24 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -44,6 +44,7 @@ struct kobject;
struct mem_cgroup;
struct module;
struct bpf_func_state;
+struct cgroup;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
@@ -1579,6 +1580,7 @@ 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 022522174286..9a93b72bf39c 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. */
@@ -5986,6 +5989,9 @@ 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 0487133b799f..f2a6fd0633d6 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -37,7 +37,7 @@ obj-${CONFIG_BPF_LSM} += bpf_lsm.o
endif
obj-$(CONFIG_BPF_PRELOAD) += preload/
ifeq ($(CONFIG_CGROUPS),y)
-obj-$(CONFIG_BPF_SYSCALL) += rstat.o
+obj-$(CONFIG_BPF_SYSCALL) += rstat.o cgroup_iter.o
endif
obj-$(CONFIG_BPF_SYSCALL) += relo_core.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 022522174286..9a93b72bf39c 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. */
@@ -5986,6 +5989,9 @@ struct bpf_link_info {
struct {
__u32 map_id;
} map;
+ struct {
+ __u64 cgroup_id;
+ } cgroup;
};
} iter;
struct {
--
2.36.0.550.gb090851708-goog
Powered by blists - more mailing lists