From 2357672c54c3f748f675446f8eba8b0432b1e7e2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:49 +0530 Subject: bpf: Introduce BPF support for kernel module function calls This change adds support on the kernel side to allow for BPF programs to call kernel module functions. Userspace will prepare an array of module BTF fds that is passed in during BPF_PROG_LOAD using fd_array parameter. In the kernel, the module BTFs are placed in the auxilliary struct for bpf_prog, and loaded as needed. The verifier then uses insn->off to index into the fd_array. insn->off 0 is reserved for vmlinux BTF (for backwards compat), so userspace must use an fd_array index > 0 for module kfunc support. kfunc_btf_tab is sorted based on offset in an array, and each offset corresponds to one descriptor, with a max limit up to 256 such module BTFs. We also change existing kfunc_tab to distinguish each element based on imm, off pair as each such call will now be distinct. Another change is to check_kfunc_call callback, which now include a struct module * pointer, this is to be used in later patch such that the kfunc_id and module pointer are matched for dynamically registered BTF sets from loadable modules, so that same kfunc_id in two modules doesn't lead to check_kfunc_call succeeding. For the duration of the check_kfunc_call, the reference to struct module exists, as it returns the pointer stored in kfunc_btf_tab. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-2-memxor@gmail.com --- net/ipv4/bpf_tcp_ca.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 0dcee9df1326..b3afd3361f34 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -255,7 +255,7 @@ BTF_ID(func, bbr_set_state) #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); } -- cgit v1.2.3-70-g09d2 From 0e32dfc80bae53b05e9eda7eaf259f30ab9ba43a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:53 +0530 Subject: bpf: Enable TCP congestion control kfunc from modules 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 call resolve_btfids for each module. Note that since kernel kfunc_ids never overlap with module kfunc_ids, we only match the owner for module btf id sets. 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 Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-6-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(-) (limited to 'net/ipv4') diff --git a/include/linux/btf.h b/include/linux/btf.h index 6c4c61d821d7..1d56cd2bb362 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -274,4 +274,6 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, 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; + #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 62cbeb4951eb..1460dff3c154 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6395,3 +6395,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ EXPORT_SYMBOL_GPL(name) + +DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index b3afd3361f34..57709ac09fb2 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_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 +#include #include #include #include @@ -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 +#include +#include #include #include #include @@ -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 */ +#include +#include #include #include #include @@ -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..1fb45b011e4b 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) -b vmlinux $@; \ else \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ fi; -- cgit v1.2.3-70-g09d2 From 35346ab64132d0f5919b06932d708c0d10360553 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:23 +0800 Subject: bpf: Factor out helpers for ctx access checking Factor out two helpers to check the read access of ctx for raw tp and BTF function. bpf_tracing_ctx_access() is used to check the read access to argument is valid, and bpf_tracing_btf_ctx_access() checks whether the btf type of argument is valid besides the checking of argument read. bpf_tracing_btf_ctx_access() will be used by the following patch. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-3-houtao1@huawei.com --- include/linux/bpf.h | 23 +++++++++++++++++++++++ kernel/trace/bpf_trace.c | 16 ++-------------- net/ipv4/bpf_tcp_ca.c | 9 +-------- 3 files changed, 26 insertions(+), 22 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aabd3540aaaf..67f71e7def56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1650,6 +1650,29 @@ bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); + +static inline bool bpf_tracing_ctx_access(int off, int size, + enum bpf_access_type type) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + return true; +} + +static inline bool bpf_tracing_btf_ctx_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (!bpf_tracing_ctx_access(off, size, type)) + return false; + return btf_ctx_access(off, size, type, prog, info); +} + int 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, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cbcd0d6fca7c..7396488793ff 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1646,13 +1646,7 @@ static bool raw_tp_prog_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; - return true; + return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, @@ -1660,13 +1654,7 @@ static bool tracing_prog_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; - return btf_ctx_access(off, size, type, prog, info); + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 57709ac09fb2..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) -- cgit v1.2.3-70-g09d2