netdev.vger.kernel.org archive mirror
 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 v4 03/21] bpf: support bpf tracing/iter programs for BPF_LINK_CREATE
Date: Sat, 9 May 2020 10:59:01 -0700	[thread overview]
Message-ID: <20200509175901.2475084-1-yhs@fb.com> (raw)
In-Reply-To: <20200509175859.2474608-1-yhs@fb.com>

Given a bpf program, the step to create an anonymous bpf iterator is:
  - create a bpf_iter_link, which combines bpf program and the target.
    In the future, there could be more information recorded in the link.
    A link_fd will be returned to the user space.
  - create an anonymous bpf iterator with the given link_fd.

The bpf_iter_link can be pinned to bpffs mount file system to
create a file based bpf iterator as well.

The benefit to use of bpf_iter_link:
  - using bpf link simplifies design and implementation as bpf link
    is used for other tracing bpf programs.
  - for file based bpf iterator, bpf_iter_link provides a standard
    way to replace underlying bpf programs.
  - for both anonymous and free based iterators, bpf link query
    capability can be leveraged.

The patch added support of tracing/iter programs for BPF_LINK_CREATE.
A new link type BPF_LINK_TYPE_ITER is added to facilitate link
querying. Currently, only prog_id is needed, so there is no
additional in-kernel show_fdinfo() and fill_link_info() hook
is needed for BPF_LINK_TYPE_ITER link.

Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
---
 include/linux/bpf.h            |  1 +
 include/linux/bpf_types.h      |  1 +
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/bpf_iter.c          | 62 ++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           | 14 ++++++++
 tools/include/uapi/linux/bpf.h |  1 +
 6 files changed, 80 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f28bdd714754..e93d2d33c82c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1143,6 +1143,7 @@ struct bpf_iter_reg {
 int bpf_iter_reg_target(struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const char *target);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 8345cdf553b8..29d22752fc87 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -124,3 +124,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
 #ifdef CONFIG_CGROUP_BPF
 BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
 #endif
+BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c8a5325cc8d0..1e8dfff5d5d4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -229,6 +229,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
+	BPF_LINK_TYPE_ITER = 4,
 
 	MAX_BPF_LINK_TYPE,
 };
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index dec182d8395a..03f5832909db 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -15,6 +15,11 @@ struct bpf_iter_target_info {
 	u32 btf_id;	/* cached value */
 };
 
+struct bpf_iter_link {
+	struct bpf_link link;
+	struct bpf_iter_target_info *tinfo;
+};
+
 static struct list_head targets = LIST_HEAD_INIT(targets);
 static DEFINE_MUTEX(targets_mutex);
 
@@ -93,3 +98,60 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
 
 	return supported;
 }
+
+static void bpf_iter_link_release(struct bpf_link *link)
+{
+}
+
+static void bpf_iter_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+
+	kfree(iter_link);
+}
+
+static const struct bpf_link_ops bpf_iter_link_lops = {
+	.release = bpf_iter_link_release,
+	.dealloc = bpf_iter_link_dealloc,
+};
+
+int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct bpf_iter_target_info *tinfo;
+	struct bpf_iter_link *link;
+	bool existed = false;
+	u32 prog_btf_id;
+	int err;
+
+	if (attr->link_create.target_fd || attr->link_create.flags)
+		return -EINVAL;
+
+	prog_btf_id = prog->aux->attach_btf_id;
+	mutex_lock(&targets_mutex);
+	list_for_each_entry(tinfo, &targets, list) {
+		if (tinfo->btf_id == prog_btf_id) {
+			existed = true;
+			break;
+		}
+	}
+	mutex_unlock(&targets_mutex);
+	if (!existed)
+		return -ENOENT;
+
+	link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
+	if (!link)
+		return -ENOMEM;
+
+	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);
+	link->tinfo = tinfo;
+
+	err  = bpf_link_prime(&link->link, &link_primer);
+	if (err) {
+		kfree(link);
+		return err;
+	}
+
+	return bpf_link_settle(&link_primer);
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index bb1ab7da6103..6ffe2d8fb6c7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2729,6 +2729,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 	case BPF_CGROUP_GETSOCKOPT:
 	case BPF_CGROUP_SETSOCKOPT:
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
+	case BPF_TRACE_ITER:
+		return BPF_PROG_TYPE_TRACING;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -3729,6 +3731,15 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	return err;
 }
 
+static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
+	    prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+
+	return -EINVAL;
+}
+
 #define BPF_LINK_CREATE_LAST_FIELD link_create.flags
 static int link_create(union bpf_attr *attr)
 {
@@ -3765,6 +3776,9 @@ static int link_create(union bpf_attr *attr)
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		ret = cgroup_bpf_link_attach(attr, prog);
 		break;
+	case BPF_PROG_TYPE_TRACING:
+		ret = tracing_bpf_link_attach(attr, prog);
+		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c8a5325cc8d0..1e8dfff5d5d4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -229,6 +229,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
 	BPF_LINK_TYPE_TRACING = 2,
 	BPF_LINK_TYPE_CGROUP = 3,
+	BPF_LINK_TYPE_ITER = 4,
 
 	MAX_BPF_LINK_TYPE,
 };
-- 
2.24.1


  parent reply	other threads:[~2020-05-09 17:59 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-09 17:58 [PATCH bpf-next v4 00/21] bpf: implement bpf iterator for kernel data Yonghong Song
2020-05-09 17:58 ` [PATCH bpf-next v4 01/21] bpf: implement an interface to register bpf_iter targets Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 02/21] bpf: allow loading of a bpf_iter program Yonghong Song
2020-05-10  0:41   ` Alexei Starovoitov
2020-05-10  5:07     ` Yonghong Song
2020-05-12 15:41     ` Yonghong Song
2020-05-12 16:25       ` Alexei Starovoitov
2020-05-12 16:29         ` Yonghong Song
2020-05-09 17:59 ` Yonghong Song [this message]
2020-05-09 17:59 ` [PATCH bpf-next v4 04/21] bpf: support bpf tracing/iter programs for BPF_LINK_UPDATE Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 05/21] bpf: implement bpf_seq_read() for bpf iterator Yonghong Song
2020-05-10  0:30   ` Alexei Starovoitov
2020-05-10  4:51     ` Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 06/21] bpf: create anonymous " Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 07/21] bpf: create file " Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 08/21] bpf: implement common macros/helpers for target iterators Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 09/21] bpf: add bpf_map iterator Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 10/21] net: bpf: add netlink and ipv6_route bpf_iter targets Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 11/21] bpf: add task and task/file iterator targets Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 12/21] bpf: add PTR_TO_BTF_ID_OR_NULL support Yonghong Song
2020-05-10  0:50   ` Alexei Starovoitov
2020-05-10  5:18     ` Yonghong Song
2020-05-10 16:11       ` Alexei Starovoitov
2020-05-10 17:05         ` Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 13/21] bpf: add bpf_seq_printf and bpf_seq_write helpers Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 14/21] bpf: handle spilled PTR_TO_BTF_ID properly when checking stack_boundary Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 15/21] bpf: support variable length array in tracing programs Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 16/21] tools/libbpf: add bpf_iter support Yonghong Song
2020-05-10  0:35   ` Alexei Starovoitov
2020-05-10  5:06     ` Yonghong Song
2020-05-10 16:09       ` Alexei Starovoitov
2020-05-10 17:04         ` Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 17/21] tools/libpf: add offsetof/container_of macro in bpf_helpers.h Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 18/21] tools/bpftool: add bpf_iter support for bptool Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 19/21] tools/bpf: selftests: add iterator programs for ipv6_route and netlink Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 20/21] tools/bpf: selftests: add iter progs for bpf_map/task/task_file Yonghong Song
2020-05-09 17:59 ` [PATCH bpf-next v4 21/21] tools/bpf: selftests: add bpf_iter selftests Yonghong Song
2020-05-10  0:34   ` Alexei Starovoitov
2020-05-10  5:01     ` Yonghong Song
2020-05-10 16:14       ` Alexei Starovoitov
2020-05-10  0:27 ` [PATCH bpf-next v4 00/21] bpf: implement bpf iterator for kernel data Alexei Starovoitov
2020-05-10  4:47   ` 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=20200509175901.2475084-1-yhs@fb.com \
    --to=yhs@fb.com \
    --cc=andriin@fb.com \
    --cc=ast@fb.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=kafai@fb.com \
    --cc=kernel-team@fb.com \
    --cc=netdev@vger.kernel.org \
    /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).