[PATCH bpf-next v13 04/13] bpf: support fsession for bpf_session_is_return

[Menglong Dong <menglong8.dong@gmail.com>]

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 <dongml2@chinatelecom.cn>
Co-developed-by: Leon Hwang <leon.hwang@linux.dev>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
v11:
- rename BPF_TRAMP_SHIFT_IS_RETURN to BPF_TRAMP_IS_RETURN_SHIFT

v10:
- fix the wrong description of bpf_session_is_return() in commit log and
  comment
- rename the prefix from BPF_TRAMP_M_ tp BPF_TRAMP_SHIFT_
- remove the definition of BPF_TRAMP_M_NR_ARGS
- use 63 for the shift of BPF_TRAMP_SHIFT_IS_RETURN
- check the program type in bpf_session_filter()

v9:
- remove the definition of bpf_fsession_is_return()

v7:
- reuse the kfunc bpf_session_is_return() instead of introduce new kfunc

v4:
- split out the bpf_fsession_cookie() to another patch

v3:
- merge the bpf_tracing_is_exit and bpf_fsession_cookie into a single
  patch

v2:
- store the session flags after return value, instead of before nr_args
- inline the bpf_tracing_is_exit, as Jiri suggested
---
 include/linux/bpf.h      |  2 ++
 kernel/bpf/verifier.c    | 13 +++++++++++++
 kernel/trace/bpf_trace.c | 39 ++++++++++++++++++++++++++-------------
 3 files changed, 41 insertions(+), 13 deletions(-)

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);
 
-- 
2.52.0