bpf: add two kfunc for TRACE_SESSION

If TRACE_SESSION exists, we will use extra 8-bytes in the stack of the
trampoline to store the flags that we needed, and the 8-bytes lie after
the return value, which means ctx[nr_args + 1]. And we will store the
flag "is_exit" to the first bit of it.

Introduce the kfunc bpf_tracing_is_exit(), which is used to tell if it
is fexit currently. Meanwhile, inline it in the verifier.

Add the kfunc bpf_fsession_cookie(), which is similar to
bpf_session_cookie() and return the address of the session cookie. The
address of the session cookie is stored after session flags, which means
ctx[nr_args + 2]. Inline this kfunc in the verifier too.

Signed-off-by: Menglong Dong <[email protected]>
Co-developed-by: Leon Hwang <[email protected]>
Signed-off-by: Leon Hwang <[email protected]>

Author: image-dragon

include/linux/bpf.h

@@ -1744,6 +1744,7 @@ 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_fsession_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 */

kernel/bpf/verifier.c

@@ -12290,6 +12290,8 @@ enum special_kfunc_type {
 	KF___bpf_trap,
 	KF_bpf_task_work_schedule_signal,
 	KF_bpf_task_work_schedule_resume,
+	KF_bpf_tracing_is_exit,
+	KF_bpf_fsession_cookie,
 };
 
 BTF_ID_LIST(special_kfunc_list)
@@ -12364,6 +12366,8 @@ BTF_ID(func, bpf_dynptr_file_discard)
 BTF_ID(func, __bpf_trap)
 BTF_ID(func, bpf_task_work_schedule_signal)
 BTF_ID(func, bpf_task_work_schedule_resume)
+BTF_ID(func, bpf_tracing_is_exit)
+BTF_ID(func, bpf_fsession_cookie)
 
 static bool is_task_work_add_kfunc(u32 func_id)
 {
@@ -12418,7 +12422,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	struct bpf_reg_state *reg = &regs[regno];
 	bool arg_mem_size = false;
 
-	if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx])
+	if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
+	    meta->func_id == special_kfunc_list[KF_bpf_tracing_is_exit] ||
+	    meta->func_id == special_kfunc_list[KF_bpf_fsession_cookie])
 		return KF_ARG_PTR_TO_CTX;
 
 	/* In this function, we verify the kfunc's BTF as per the argument type,
@@ -13916,7 +13922,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		}
 	}
 
-	if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie]) {
+	if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie] ||
+	    meta.func_id == special_kfunc_list[KF_bpf_fsession_cookie]) {
 		meta.r0_size = sizeof(u64);
 		meta.r0_rdonly = false;
 	}
@@ -14203,6 +14210,9 @@ 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_fsession_cookie])
+		env->prog->call_session_cookie = true;
+
 	return 0;
 }
 
@@ -22041,6 +22051,25 @@ 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_tracing_is_exit]) {
+		/* Load nr_args from ctx - 8 */
+		insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+		/* add rax, 1 */
+		insn_buf[1] = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1);
+		insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+		insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+		insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
+		insn_buf[5] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1);
+		*cnt = 6;
+	} else if (desc->func_id == special_kfunc_list[KF_bpf_fsession_cookie]) {
+		/* Load nr_args from ctx - 8 */
+		insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+		/* add rax, 2 */
+		insn_buf[1] = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2);
+		insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
+		insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1);
+		insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
+		*cnt = 5;
 	}
 
 	if (env->insn_aux_data[insn_idx].arg_prog) {

kernel/trace/bpf_trace.c

@@ -3356,12 +3356,65 @@ static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = {
 	.filter = bpf_kprobe_multi_filter,
 };
 
-static int __init bpf_kprobe_multi_kfuncs_init(void)
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc bool bpf_tracing_is_exit(void *ctx)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set);
+	/* This helper call is inlined by verifier. */
+	u64 nr_args = ((u64 *)ctx)[-1];
+
+	/*
+	 * ctx[nr_args + 1] is the session flags, and the last bit is
+	 * is_exit.
+	 */
+	return ((u64 *)ctx)[nr_args + 1] & 1;
+}
+
+__bpf_kfunc u64 *bpf_fsession_cookie(void *ctx)
+{
+	/* This helper call is inlined by verifier. */
+	u64 nr_args = ((u64 *)ctx)[-1];
+
+	/* ctx[nr_args + 2] is the session cookie address */
+	return (u64 *)((u64 *)ctx)[nr_args + 2];
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(tracing_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_tracing_is_exit, KF_FASTCALL)
+BTF_ID_FLAGS(func, bpf_fsession_cookie, KF_FASTCALL)
+BTF_KFUNCS_END(tracing_kfunc_set_ids)
+
+static int bpf_tracing_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&tracing_kfunc_set_ids, kfunc_id))
+		return 0;
+
+	if (prog->type != BPF_PROG_TYPE_TRACING ||
+	    prog->expected_attach_type != BPF_TRACE_SESSION)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct btf_kfunc_id_set bpf_tracing_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &tracing_kfunc_set_ids,
+	.filter = bpf_tracing_filter,
+};
+
+static int __init bpf_trace_kfuncs_init(void)
+{
+	int err = 0;
+
+	err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set);
+	err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_tracing_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);