From 2d419c44658f75e7655794341a95c0687830f3df Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 24 Jan 2026 14:19:56 +0800 Subject: bpf: add fsession support The fsession is something that similar to kprobe session. It allow to attach a single BPF program to both the entry and the exit of the target functions. Introduce the struct bpf_fsession_link, which allows to add the link to both the fentry and fexit progs_hlist of the trampoline. Signed-off-by: Menglong Dong Co-developed-by: Leon Hwang Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260124062008.8657-2-dongml2@chinatelecom.cn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5936f8e2996f..41228b0add52 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1309,6 +1309,7 @@ enum bpf_tramp_prog_type { BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ + BPF_TRAMP_FSESSION, }; struct bpf_tramp_image { @@ -1875,6 +1876,11 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_fsession_link { + struct bpf_tracing_link link; + struct bpf_tramp_link fexit; +}; + struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; @@ -2169,6 +2175,19 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op #endif +static inline int bpf_fsession_cnt(struct bpf_tramp_links *links) +{ + struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY]; + int cnt = 0; + + for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) { + if (fentries.links[i]->link.prog->expected_attach_type == BPF_TRACE_FSESSION) + cnt++; + } + + return cnt; +} + int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, const struct bpf_ctx_arg_aux *info, u32 cnt); -- cgit v1.2.3 From 27d89baa6da8e5e546585c53a959176d1302d46e Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 24 Jan 2026 14:19:59 +0800 Subject: bpf: support fsession for bpf_session_is_return If fsession exists, we will use the bit (1 << BPF_TRAMP_IS_RETURN_SHIFT) in ((u64 *)ctx)[-1] to store the "is_return" flag. The logic of bpf_session_is_return() for fsession is implemented in the verifier by inline following code: bool bpf_session_is_return(void *ctx) { return (((u64 *)ctx)[-1] >> BPF_TRAMP_IS_RETURN_SHIFT) & 1; } Signed-off-by: Menglong Dong Co-developed-by: Leon Hwang Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20260124062008.8657-5-dongml2@chinatelecom.cn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ kernel/bpf/verifier.c | 13 +++++++++++++ kernel/trace/bpf_trace.c | 39 ++++++++++++++++++++++++++------------- 3 files changed, 41 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 41228b0add52..29eecd79352e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1229,6 +1229,8 @@ enum { #endif }; +#define BPF_TRAMP_IS_RETURN_SHIFT 63 + struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; int nr_links; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0fa73d56cb8b..d04aea235a12 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23011,6 +23011,19 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) { insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); *cnt = 1; + } else if (desc->func_id == special_kfunc_list[KF_bpf_session_is_return] && + env->prog->expected_attach_type == BPF_TRACE_FSESSION) { + /* + * inline the bpf_session_is_return() for fsession: + * bool bpf_session_is_return(void *ctx) + * { + * return (((u64 *)ctx)[-1] >> BPF_TRAMP_IS_RETURN_SHIFT) & 1; + * } + */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_IS_RETURN_SHIFT); + insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1); + *cnt = 3; } if (env->insn_aux_data[insn_idx].arg_prog) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 13f0a2de33b7..f7baeb8278ca 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1286,7 +1286,8 @@ static bool is_kprobe_multi(const struct bpf_prog *prog) static inline bool is_kprobe_session(const struct bpf_prog *prog) { - return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; + return prog->type == BPF_PROG_TYPE_KPROBE && + prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION; } static inline bool is_uprobe_multi(const struct bpf_prog *prog) @@ -1297,7 +1298,14 @@ static inline bool is_uprobe_multi(const struct bpf_prog *prog) static inline bool is_uprobe_session(const struct bpf_prog *prog) { - return prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; + return prog->type == BPF_PROG_TYPE_KPROBE && + prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION; +} + +static inline bool is_trace_fsession(const struct bpf_prog *prog) +{ + return prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_FSESSION; } static const struct bpf_func_proto * @@ -3341,34 +3349,39 @@ __bpf_kfunc __u64 *bpf_session_cookie(void *ctx) __bpf_kfunc_end_defs(); -BTF_KFUNCS_START(kprobe_multi_kfunc_set_ids) +BTF_KFUNCS_START(session_kfunc_set_ids) BTF_ID_FLAGS(func, bpf_session_is_return) BTF_ID_FLAGS(func, bpf_session_cookie) -BTF_KFUNCS_END(kprobe_multi_kfunc_set_ids) +BTF_KFUNCS_END(session_kfunc_set_ids) -static int bpf_kprobe_multi_filter(const struct bpf_prog *prog, u32 kfunc_id) +static int bpf_session_filter(const struct bpf_prog *prog, u32 kfunc_id) { - if (!btf_id_set8_contains(&kprobe_multi_kfunc_set_ids, kfunc_id)) + if (!btf_id_set8_contains(&session_kfunc_set_ids, kfunc_id)) return 0; - if (!is_kprobe_session(prog) && !is_uprobe_session(prog)) + if (!is_kprobe_session(prog) && !is_uprobe_session(prog) && !is_trace_fsession(prog)) return -EACCES; return 0; } -static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { +static const struct btf_kfunc_id_set bpf_session_kfunc_set = { .owner = THIS_MODULE, - .set = &kprobe_multi_kfunc_set_ids, - .filter = bpf_kprobe_multi_filter, + .set = &session_kfunc_set_ids, + .filter = bpf_session_filter, }; -static int __init bpf_kprobe_multi_kfuncs_init(void) +static int __init bpf_trace_kfuncs_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); + int err = 0; + + err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_session_kfunc_set); + err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_session_kfunc_set); + + return err; } -late_initcall(bpf_kprobe_multi_kfuncs_init); +late_initcall(bpf_trace_kfuncs_init); typedef int (*copy_fn_t)(void *dst, const void *src, u32 size, struct task_struct *tsk); -- cgit v1.2.3 From eeee4239dbb155a98f8ba737324ac081acde8417 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 24 Jan 2026 14:20:00 +0800 Subject: bpf: support fsession for bpf_session_cookie Implement session cookie for fsession. The session cookies will be stored in the stack, and the layout of the stack will look like this: return value -> 8 bytes argN -> 8 bytes ... arg1 -> 8 bytes nr_args -> 8 bytes ip (optional) -> 8 bytes cookie2 -> 8 bytes cookie1 -> 8 bytes The offset of the cookie for the current bpf program, which is in 8-byte units, is stored in the "(((u64 *)ctx)[-1] >> BPF_TRAMP_COOKIE_INDEX_SHIFT) & 0xFF". Therefore, we can get the session cookie with ((u64 *)ctx)[-offset]. Implement and inline the bpf_session_cookie() for the fsession in the verifier. Signed-off-by: Menglong Dong Link: https://lore.kernel.org/r/20260124062008.8657-6-dongml2@chinatelecom.cn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 15 +++++++++++++++ kernel/bpf/verifier.c | 20 ++++++++++++++++++++ 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 29eecd79352e..4427c6e98331 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1229,6 +1229,7 @@ enum { #endif }; +#define BPF_TRAMP_COOKIE_INDEX_SHIFT 8 #define BPF_TRAMP_IS_RETURN_SHIFT 63 struct bpf_tramp_links { @@ -1782,6 +1783,7 @@ struct bpf_prog { enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ + call_session_cookie:1, /* Do we call bpf_session_cookie() */ tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */ sleepable:1; /* BPF program is sleepable */ enum bpf_prog_type type; /* Type of BPF program */ @@ -2190,6 +2192,19 @@ static inline int bpf_fsession_cnt(struct bpf_tramp_links *links) return cnt; } +static inline int bpf_fsession_cookie_cnt(struct bpf_tramp_links *links) +{ + struct bpf_tramp_links fentries = links[BPF_TRAMP_FENTRY]; + int cnt = 0; + + for (int i = 0; i < links[BPF_TRAMP_FENTRY].nr_links; i++) { + if (fentries.links[i]->link.prog->call_session_cookie) + cnt++; + } + + return cnt; +} + int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog, const struct bpf_ctx_arg_aux *info, u32 cnt); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d04aea235a12..c2f2650db9fd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14406,6 +14406,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return err; } + if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) + env->prog->call_session_cookie = true; + return 0; } @@ -23024,6 +23027,23 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_IS_RETURN_SHIFT); insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1); *cnt = 3; + } else if (desc->func_id == special_kfunc_list[KF_bpf_session_cookie] && + env->prog->expected_attach_type == BPF_TRACE_FSESSION) { + /* + * inline bpf_session_cookie() for fsession: + * __u64 *bpf_session_cookie(void *ctx) + * { + * u64 off = (((u64 *)ctx)[-1] >> BPF_TRAMP_COOKIE_INDEX_SHIFT) & 0xFF; + * return &((u64 *)ctx)[-off]; + * } + */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_COOKIE_INDEX_SHIFT); + insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF); + insn_buf[3] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + insn_buf[4] = BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1); + insn_buf[5] = BPF_ALU64_IMM(BPF_NEG, BPF_REG_0, 0); + *cnt = 6; } if (env->insn_aux_data[insn_idx].arg_prog) { -- cgit v1.2.3