diff options
author | Jakub Kicinski <kuba@kernel.org> | 2021-11-01 19:59:45 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2021-11-01 19:59:46 -0700 |
commit | b7b98f868987cd3e86c9bd9a6db048614933d7a0 (patch) | |
tree | 8651e9d44726348ea56692d988b26c273e129c7a /net | |
parent | 52fa3ee0cce60a04739f4a5ca1c9d5c2a8ee1578 (diff) | |
parent | 0b170456e0dda92b8925d40e217461fcc4e1efc9 (diff) | |
download | linux-b7b98f868987cd3e86c9bd9a6db048614933d7a0.tar.bz2 |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2021-11-01
We've added 181 non-merge commits during the last 28 day(s) which contain
a total of 280 files changed, 11791 insertions(+), 5879 deletions(-).
The main changes are:
1) Fix bpf verifier propagation of 64-bit bounds, from Alexei.
2) Parallelize bpf test_progs, from Yucong and Andrii.
3) Deprecate various libbpf apis including af_xdp, from Andrii, Hengqi, Magnus.
4) Improve bpf selftests on s390, from Ilya.
5) bloomfilter bpf map type, from Joanne.
6) Big improvements to JIT tests especially on Mips, from Johan.
7) Support kernel module function calls from bpf, from Kumar.
8) Support typeless and weak ksym in light skeleton, from Kumar.
9) Disallow unprivileged bpf by default, from Pawan.
10) BTF_KIND_DECL_TAG support, from Yonghong.
11) Various bpftool cleanups, from Quentin.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (181 commits)
libbpf: Deprecate AF_XDP support
kbuild: Unify options for BTF generation for vmlinux and modules
selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
selftests/bpf: Fix also no-alu32 strobemeta selftest
bpf: Add missing map_delete_elem method to bloom filter map
selftests/bpf: Add bloom map success test for userspace calls
bpf: Add alignment padding for "map_extra" + consolidate holes
bpf: Bloom filter map naming fixups
selftests/bpf: Add test cases for struct_ops prog
bpf: Add dummy BPF STRUCT_OPS for test purpose
bpf: Factor out helpers for ctx access checking
bpf: Factor out a helper to prepare trampoline for struct_ops prog
selftests, bpf: Fix broken riscv build
riscv, libbpf: Add RISC-V (RV64) support to bpf_tracing.h
tools, build: Add RISC-V to HOSTARCH parsing
riscv, bpf: Increase the maximum number of iterations
selftests, bpf: Add one test for sockmap with strparser
selftests, bpf: Fix test_txmsg_ingress_parser error
...
====================
Link: https://lore.kernel.org/r/20211102013123.9005-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
-rw-r--r-- | net/bpf/Makefile | 3 | ||||
-rw-r--r-- | net/bpf/bpf_dummy_struct_ops.c | 200 | ||||
-rw-r--r-- | net/bpf/test_run.c | 28 | ||||
-rw-r--r-- | net/core/filter.c | 23 | ||||
-rw-r--r-- | net/core/skmsg.c | 43 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 45 | ||||
-rw-r--r-- | net/ipv4/tcp_bbr.c | 28 | ||||
-rw-r--r-- | net/ipv4/tcp_cubic.c | 26 | ||||
-rw-r--r-- | net/ipv4/tcp_dctcp.c | 26 |
9 files changed, 352 insertions, 70 deletions
diff --git a/net/bpf/Makefile b/net/bpf/Makefile index 1c0a98d8c28f..1ebe270bde23 100644 --- a/net/bpf/Makefile +++ b/net/bpf/Makefile @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BPF_SYSCALL) := test_run.o +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_dummy_struct_ops.o +endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c new file mode 100644 index 000000000000..fbc896323bec --- /dev/null +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021. Huawei Technologies Co., Ltd + */ +#include <linux/kernel.h> +#include <linux/bpf_verifier.h> +#include <linux/bpf.h> +#include <linux/btf.h> + +extern struct bpf_struct_ops bpf_bpf_dummy_ops; + +/* A common type for test_N with return value in bpf_dummy_ops */ +typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); + +struct bpf_dummy_ops_test_args { + u64 args[MAX_BPF_FUNC_ARGS]; + struct bpf_dummy_ops_state state; +}; + +static struct bpf_dummy_ops_test_args * +dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) +{ + __u32 size_in; + struct bpf_dummy_ops_test_args *args; + void __user *ctx_in; + void __user *u_state; + + size_in = kattr->test.ctx_size_in; + if (size_in != sizeof(u64) * nr) + return ERR_PTR(-EINVAL); + + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return ERR_PTR(-ENOMEM); + + ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + if (copy_from_user(args->args, ctx_in, size_in)) + goto out; + + /* args[0] is 0 means state argument of test_N will be NULL */ + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_from_user(&args->state, u_state, + sizeof(args->state))) + goto out; + + return args; +out: + kfree(args); + return ERR_PTR(-EFAULT); +} + +static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args) +{ + void __user *u_state; + + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_to_user(u_state, &args->state, sizeof(args->state))) + return -EFAULT; + + return 0; +} + +static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args) +{ + dummy_ops_test_ret_fn test = (void *)image; + struct bpf_dummy_ops_state *state = NULL; + + /* state needs to be NULL if args[0] is 0 */ + if (args->args[0]) + state = &args->state; + return test(state, args->args[1], args->args[2], + args->args[3], args->args[4]); +} + +int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops; + const struct btf_type *func_proto; + struct bpf_dummy_ops_test_args *args; + struct bpf_tramp_progs *tprogs; + void *image = NULL; + unsigned int op_idx; + int prog_ret; + int err; + + if (prog->aux->attach_btf_id != st_ops->type_id) + return -EOPNOTSUPP; + + func_proto = prog->aux->attach_func_proto; + args = dummy_ops_init_args(kattr, btf_type_vlen(func_proto)); + if (IS_ERR(args)) + return PTR_ERR(args); + + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) { + err = -ENOMEM; + goto out; + } + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) { + err = -ENOMEM; + goto out; + } + set_vm_flush_reset_perms(image); + + op_idx = prog->expected_attach_type; + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[op_idx], + image, image + PAGE_SIZE); + if (err < 0) + goto out; + + set_memory_ro((long)image, 1); + set_memory_x((long)image, 1); + prog_ret = dummy_ops_call_op(image, args); + + err = dummy_ops_copy_args(args); + if (err) + goto out; + if (put_user(prog_ret, &uattr->test.retval)) + err = -EFAULT; +out: + kfree(args); + bpf_jit_free_exec(image); + kfree(tprogs); + return err; +} + +static int bpf_dummy_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_dummy_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id) +{ + const struct btf_type *state; + s32 type_id; + int err; + + type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state", + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + + state = btf_type_by_id(btf, type_id); + if (t != state) { + bpf_log(log, "only access to bpf_dummy_ops_state is supported\n"); + return -EACCES; + } + + err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id); + if (err < 0) + return err; + + return atype == BPF_READ ? err : NOT_INIT; +} + +static const struct bpf_verifier_ops bpf_dummy_verifier_ops = { + .is_valid_access = bpf_dummy_ops_is_valid_access, + .btf_struct_access = bpf_dummy_ops_btf_struct_access, +}; + +static int bpf_dummy_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return -EOPNOTSUPP; +} + +static int bpf_dummy_reg(void *kdata) +{ + return -EOPNOTSUPP; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +struct bpf_struct_ops bpf_bpf_dummy_ops = { + .verifier_ops = &bpf_dummy_verifier_ops, + .init = bpf_dummy_init, + .init_member = bpf_dummy_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .name = "bpf_dummy_ops", +}; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 072f0c16c779..46dd95755967 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017 Facebook */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -241,9 +242,11 @@ BTF_ID(func, bpf_kfunc_call_test2) BTF_ID(func, bpf_kfunc_call_test3) BTF_SET_END(test_sk_kfunc_ids) -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) +bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) { - return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id); + if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id)) + return true; + return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner); } static void *bpf_test_init(const union bpf_attr *kattr, u32 size, @@ -355,13 +358,9 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, return -EINVAL; if (ctx_size_in) { - info.ctx = kzalloc(ctx_size_in, GFP_USER); - if (!info.ctx) - return -ENOMEM; - if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) { - err = -EFAULT; - goto out; - } + info.ctx = memdup_user(ctx_in, ctx_size_in); + if (IS_ERR(info.ctx)) + return PTR_ERR(info.ctx); } else { info.ctx = NULL; } @@ -389,7 +388,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32))) err = -EFAULT; -out: kfree(info.ctx); return err; } @@ -1049,13 +1047,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, return -EINVAL; if (ctx_size_in) { - ctx = kzalloc(ctx_size_in, GFP_USER); - if (!ctx) - return -ENOMEM; - if (copy_from_user(ctx, ctx_in, ctx_size_in)) { - err = -EFAULT; - goto out; - } + ctx = memdup_user(ctx_in, ctx_size_in); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); } rcu_read_lock_trace(); diff --git a/net/core/filter.c b/net/core/filter.c index 4bace37a6a44..8e8d3b49c297 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; +BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) +{ + /* unix_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct unix_sock); + if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { + .func = bpf_skc_to_unix_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; + case BPF_FUNC_skc_to_unix_sock: + func = &bpf_skc_to_unix_sock_proto; + break; default: return bpf_base_func_proto(func_id); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a86ef7e844f8..1ae52ac943f6 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -508,6 +508,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + u32 off, u32 len, struct sk_psock *psock, struct sock *sk, struct sk_msg *msg) @@ -521,11 +522,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, */ if (skb_linearize(skb)) return -EAGAIN; - num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (unlikely(num_sge < 0)) return num_sge; - copied = skb->len; + copied = len; msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; @@ -536,9 +537,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return copied; } -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sock *sk = psock->sk; struct sk_msg *msg; @@ -549,7 +552,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb); + return sk_psock_skb_ingress_self(psock, skb, off, len); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -561,7 +564,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -571,7 +574,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * skb. In this case we do not need to check memory limits or skb_set_owner_r * because the skb is already accounted for here. */ -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; @@ -581,7 +585,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -595,7 +599,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb); + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -638,6 +642,12 @@ static void sk_psock_backlog(struct work_struct *work) while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); @@ -877,6 +887,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { + skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } @@ -944,6 +955,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, { struct sock *sk_other; int err = 0; + u32 len, off; switch (verdict) { case __SK_PASS: @@ -951,6 +963,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + skb_bpf_redirect_clear(skb); goto out_free; } @@ -963,7 +976,15 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress_self(psock, skb); + len = skb->len; + off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } + err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); @@ -1029,6 +1050,8 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); + if (ret == SK_PASS) + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 0dcee9df1326..2cf02b4d77fb 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -81,14 +81,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - if (!btf_ctx_access(off, size, type, prog, info)) + if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) @@ -223,41 +216,13 @@ 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) +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_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, 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); } |