diff mbox series

[bpf-next,v2,05/10] bpf: Enable TCP congestion control kfunc from modules

Message ID 20210914123750.460750-6-memxor@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Support kernel module function calls from eBPF | expand

Checks

Context Check Description
bpf/vmtest-bpf-next fail VM_Test
bpf/vmtest-bpf-next-PR fail PR summary
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 13 maintainers not CCed: davem@davemloft.net kpsingh@kernel.org masahiroy@kernel.org john.fastabend@gmail.com haoluo@google.com michal.lkml@markovi.net ndesaulniers@google.com yoshfuji@linux-ipv6.org edumazet@google.com linux-kbuild@vger.kernel.org kuba@kernel.org dsahern@kernel.org alan.maguire@oracle.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 126 this patch: 126
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 126 this patch: 126
netdev/header_inline success Link

Commit Message

Kumar Kartikeya Dwivedi Sept. 14, 2021, 12:37 p.m. UTC
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 Makefile.modfinal
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)

[ resolve_btfids uses --no-fail because some crypto kernel modules
  under arch/x86/crypto generated from ASM do not have the .BTF sections ]

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 include/linux/btf.h       |  4 ++++
 kernel/bpf/btf.c          |  3 +++
 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, 88 insertions(+), 34 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/btf.h b/include/linux/btf.h
index e29a486d09d4..c7b6382123e1 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -270,4 +270,8 @@  static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 	struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set),     \
 					 THIS_MODULE }
 
+extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
+
+DECLARE_CHECK_KFUNC_CALLBACK(bpf_tcp_ca);
+
 #endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eecafed56300..8240478b7398 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6266,3 +6266,6 @@  EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set);
 		mutex_unlock(&list_name.mutex);                                \
 		return false;                                                  \
 	}
+
+DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
+DEFINE_CHECK_KFUNC_CALLBACK(bpf_tcp_ca, bpf_tcp_ca_kfunc_list);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index b3afd3361f34..c9f1d2dcf67b 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, struct module *owner)
 {
-	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, owner);
 }
 
 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..ec5550089b4d 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_ID_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_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit bbr_unregister(void)
 {
+	unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &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..5e9d9c51164c 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_ID_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_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit cubictcp_unregister(void)
 {
+	unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &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..0d7ab3cc7b61 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_ID_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_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set);
+	return 0;
 }
 
 static void __exit dctcp_unregister(void)
 {
+	unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set);
 	tcp_unregister_congestion_control(&dctcp);
 }
 
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index ff805777431c..b4f83533eda6 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -41,6 +41,7 @@  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;