All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
To: bpf@vger.kernel.org
Cc: "Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
	"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>,
	"Jesper Dangaard Brouer" <brouer@redhat.com>,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	netdev@vger.kernel.org
Subject: [PATCH bpf-next RFC v1 7/8] bpf: enable TCP congestion control kfunc from modules
Date: Mon, 30 Aug 2021 23:04:23 +0530	[thread overview]
Message-ID: <20210830173424.1385796-8-memxor@gmail.com> (raw)
In-Reply-To: <20210830173424.1385796-1-memxor@gmail.com>

This commit moves BTF ID lookup into the newly added registration
helper, in a way that the bbr, cubic, and dctcp implementation set up
their sets in the bpf_tcp_ca kfunc_btf_set list, while the ones not
dependent on modules are looked up from the wrapper function.

This lifts the restriction for them to be compiled as built in objects,
and can be loaded as modules if required. Also modify link-vmlinux.sh to
resolve_btfids in TCP congestion control modules if the config option is
set, using the base BTF support added in the previous commit.

See following commits for background on use of:

 CONFIG_X86 ifdef:
 569c484f9995 (bpf: Limit static tcp-cc functions in the .BTF_ids list to x86)

 CONFIG_DYNAMIC_FTRACE ifdef:
 7aae231ac93b (bpf: tcp: Limit calling some tcp cc functions to CONFIG_DYNAMIC_FTRACE)

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 include/linux/btf.h       |  2 ++
 kernel/bpf/btf.c          |  2 ++
 net/ipv4/bpf_tcp_ca.c     | 34 +++-------------------------------
 net/ipv4/tcp_bbr.c        | 28 +++++++++++++++++++++++++++-
 net/ipv4/tcp_cubic.c      | 26 +++++++++++++++++++++++++-
 net/ipv4/tcp_dctcp.c      | 26 +++++++++++++++++++++++++-
 scripts/Makefile.modfinal |  1 +
 7 files changed, 85 insertions(+), 34 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index d024b0eb43f9..8c0f29ed2af9 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -253,4 +253,6 @@ struct kfunc_btf_set {
 #define DEFINE_KFUNC_BTF_SET(set, name)                                        \
 	struct kfunc_btf_set name = { LIST_HEAD_INIT(name.list), (set) }
 
+DECLARE_KFUNC_BTF_SET_REG(bpf_tcp_ca);
+
 #endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 35873495761d..cc12470a55f9 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6249,3 +6249,5 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
 		mutex_unlock(&type##_kfunc_btf_set_mutex);                     \
 	}                                                                      \
 	EXPORT_SYMBOL_GPL(unregister_##type##_kfunc_btf_set)
+
+DEFINE_KFUNC_BTF_SET_REG(bpf_tcp_ca);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 0dcee9df1326..804f2f912fe9 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -223,41 +223,13 @@ BTF_ID(func, tcp_reno_cong_avoid)
 BTF_ID(func, tcp_reno_undo_cwnd)
 BTF_ID(func, tcp_slow_start)
 BTF_ID(func, tcp_cong_avoid_ai)
-#ifdef CONFIG_X86
-#ifdef CONFIG_DYNAMIC_FTRACE
-#if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC)
-BTF_ID(func, cubictcp_init)
-BTF_ID(func, cubictcp_recalc_ssthresh)
-BTF_ID(func, cubictcp_cong_avoid)
-BTF_ID(func, cubictcp_state)
-BTF_ID(func, cubictcp_cwnd_event)
-BTF_ID(func, cubictcp_acked)
-#endif
-#if IS_BUILTIN(CONFIG_TCP_CONG_DCTCP)
-BTF_ID(func, dctcp_init)
-BTF_ID(func, dctcp_update_alpha)
-BTF_ID(func, dctcp_cwnd_event)
-BTF_ID(func, dctcp_ssthresh)
-BTF_ID(func, dctcp_cwnd_undo)
-BTF_ID(func, dctcp_state)
-#endif
-#if IS_BUILTIN(CONFIG_TCP_CONG_BBR)
-BTF_ID(func, bbr_init)
-BTF_ID(func, bbr_main)
-BTF_ID(func, bbr_sndbuf_expand)
-BTF_ID(func, bbr_undo_cwnd)
-BTF_ID(func, bbr_cwnd_event)
-BTF_ID(func, bbr_ssthresh)
-BTF_ID(func, bbr_min_tso_segs)
-BTF_ID(func, bbr_set_state)
-#endif
-#endif  /* CONFIG_DYNAMIC_FTRACE */
-#endif	/* CONFIG_X86 */
 BTF_SET_END(bpf_tcp_ca_kfunc_ids)
 
 static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id)
 {
-	return btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id);
+	if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id))
+		return true;
+	return __bpf_check_bpf_tcp_ca_kfunc_call(kfunc_btf_id);
 }
 
 static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6274462b86b4..1fea15dd0e05 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -56,6 +56,8 @@
  * otherwise TCP stack falls back to an internal pacing using one high
  * resolution timer per TCP socket and may use more resources.
  */
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/module.h>
 #include <net/tcp.h>
 #include <linux/inet_diag.h>
@@ -1152,14 +1154,38 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
 	.set_state	= bbr_set_state,
 };
 
+BTF_SET_START(tcp_bbr_kfunc_ids)
+#ifdef CONFIG_X86
+#ifdef CONFIG_DYNAMIC_FTRACE
+BTF_ID(func, bbr_init)
+BTF_ID(func, bbr_main)
+BTF_ID(func, bbr_sndbuf_expand)
+BTF_ID(func, bbr_undo_cwnd)
+BTF_ID(func, bbr_cwnd_event)
+BTF_ID(func, bbr_ssthresh)
+BTF_ID(func, bbr_min_tso_segs)
+BTF_ID(func, bbr_set_state)
+#endif
+#endif
+BTF_SET_END(tcp_bbr_kfunc_ids)
+
+static DEFINE_KFUNC_BTF_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set);
+
 static int __init bbr_register(void)
 {
+	int ret;
+
 	BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE);
-	return tcp_register_congestion_control(&tcp_bbr_cong_ops);
+	ret = tcp_register_congestion_control(&tcp_bbr_cong_ops);
+	if (ret)
+		return ret;
+	register_bpf_tcp_ca_kfunc_btf_set(&tcp_bbr_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit bbr_unregister(void)
 {
+	unregister_bpf_tcp_ca_kfunc_btf_set(&tcp_bbr_kfunc_btf_set);
 	tcp_unregister_congestion_control(&tcp_bbr_cong_ops);
 }
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 4a30deaa9a37..5b36b9442797 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -25,6 +25,8 @@
  */
 
 #include <linux/mm.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/module.h>
 #include <linux/math64.h>
 #include <net/tcp.h>
@@ -482,8 +484,25 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
 	.name		= "cubic",
 };
 
+BTF_SET_START(tcp_cubic_kfunc_ids)
+#ifdef CONFIG_X86
+#ifdef CONFIG_DYNAMIC_FTRACE
+BTF_ID(func, cubictcp_init)
+BTF_ID(func, cubictcp_recalc_ssthresh)
+BTF_ID(func, cubictcp_cong_avoid)
+BTF_ID(func, cubictcp_state)
+BTF_ID(func, cubictcp_cwnd_event)
+BTF_ID(func, cubictcp_acked)
+#endif
+#endif
+BTF_SET_END(tcp_cubic_kfunc_ids)
+
+static DEFINE_KFUNC_BTF_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set);
+
 static int __init cubictcp_register(void)
 {
+	int ret;
+
 	BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE);
 
 	/* Precompute a bunch of the scaling factors that are used per-packet
@@ -514,11 +533,16 @@ static int __init cubictcp_register(void)
 	/* divide by bic_scale and by constant Srtt (100ms) */
 	do_div(cube_factor, bic_scale * 10);
 
-	return tcp_register_congestion_control(&cubictcp);
+	ret = tcp_register_congestion_control(&cubictcp);
+	if (ret)
+		return ret;
+	register_bpf_tcp_ca_kfunc_btf_set(&tcp_cubic_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit cubictcp_unregister(void)
 {
+	unregister_bpf_tcp_ca_kfunc_btf_set(&tcp_cubic_kfunc_btf_set);
 	tcp_unregister_congestion_control(&cubictcp);
 }
 
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 79f705450c16..efc47b4c7a11 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -36,6 +36,8 @@
  *	Glenn Judd <glenn.judd@morganstanley.com>
  */
 
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <net/tcp.h>
@@ -236,14 +238,36 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = {
 	.name		= "dctcp-reno",
 };
 
+BTF_SET_START(tcp_dctcp_kfunc_ids)
+#ifdef CONFIG_X86
+#ifdef CONFIG_DYNAMIC_FTRACE
+BTF_ID(func, dctcp_init)
+BTF_ID(func, dctcp_update_alpha)
+BTF_ID(func, dctcp_cwnd_event)
+BTF_ID(func, dctcp_ssthresh)
+BTF_ID(func, dctcp_cwnd_undo)
+BTF_ID(func, dctcp_state)
+#endif
+#endif
+BTF_SET_END(tcp_dctcp_kfunc_ids)
+
+static DEFINE_KFUNC_BTF_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set);
+
 static int __init dctcp_register(void)
 {
+	int ret;
+
 	BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
-	return tcp_register_congestion_control(&dctcp);
+	ret = tcp_register_congestion_control(&dctcp);
+	if (ret)
+		return ret;
+	register_bpf_tcp_ca_kfunc_btf_set(&tcp_dctcp_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit dctcp_unregister(void)
 {
+	unregister_bpf_tcp_ca_kfunc_btf_set(&tcp_dctcp_kfunc_btf_set);
 	tcp_unregister_congestion_control(&dctcp);
 }
 
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 5e9b8057fb24..0755d4b8b74a 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -58,6 +58,7 @@ quiet_cmd_btf_ko = BTF [M] $@
       cmd_btf_ko = 							\
 	if [ -f vmlinux ]; then						\
 		LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \
+		$(RESOLVE_BTFIDS) --no-fail -s vmlinux $@; 		\
 	else								\
 		printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
 	fi;
-- 
2.33.0


  parent reply	other threads:[~2021-08-30 17:35 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-30 17:34 [PATCH bpf-next RFC v1 0/8] Support kernel module function calls from eBPF Kumar Kartikeya Dwivedi
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 1/8] bpf: Introduce BPF support for kernel module function calls Kumar Kartikeya Dwivedi
2021-08-30 20:01   ` Alexei Starovoitov
2021-08-30 20:03   ` kernel test robot
2021-08-30 22:19   ` kernel test robot
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 2/8] bpf: Be conservative during verification for invalid kfunc calls Kumar Kartikeya Dwivedi
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 3/8] libbpf: Support kernel module function calls Kumar Kartikeya Dwivedi
2021-09-01  0:55   ` Andrii Nakryiko
2021-09-01  2:27     ` Kumar Kartikeya Dwivedi
2021-09-01  2:59       ` Alexei Starovoitov
2021-09-01  3:38         ` Andrii Nakryiko
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 4/8] libbpf: Resolve invalid kfunc calls with imm = 0, off = 0 Kumar Kartikeya Dwivedi
2021-09-01  0:35   ` Andrii Nakryiko
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 5/8] tools: Allow specifying base BTF file in resolve_btfids Kumar Kartikeya Dwivedi
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 6/8] bpf: btf: Introduce helpers for dynamic BTF set registration Kumar Kartikeya Dwivedi
2021-08-30 17:34 ` Kumar Kartikeya Dwivedi [this message]
2021-08-31  0:16   ` [PATCH bpf-next RFC v1 7/8] bpf: enable TCP congestion control kfunc from modules kernel test robot
2021-09-01  0:48   ` Andrii Nakryiko
2021-08-30 17:34 ` [PATCH bpf-next RFC v1 8/8] bpf, selftests: Add basic test for module kfunc call Kumar Kartikeya Dwivedi
2021-08-30 20:07   ` Alexei Starovoitov

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=20210830173424.1385796-8-memxor@gmail.com \
    --to=memxor@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=kafai@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=songliubraving@fb.com \
    --cc=toke@redhat.com \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.