[PATCH bpf-next v11 05/12] bpf: support fsession for bpf_session_cookie

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

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 <dongml2@chinatelecom.cn>
---
v11:
- rename BPF_TRAMP_SHIFT_COOKIE to BPF_TRAMP_COOKIE_INDEX_SHIFT

v10:
- describe the offset of the session cookie more explicit
- make 8 as the bit shift of session cookie
- remove the session cookie count limitation

v9:
- remove the definition of bpf_fsession_cookie()

v7:
- reuse bpf_session_cookie() instead of introduce new kfunc

v5:
- remove "cookie_cnt" in struct bpf_trampoline

v4:
- limit the maximum of the cookie count to 4
- store the session cookies before nr_regs in stack
---
 include/linux/bpf.h   | 15 +++++++++++++++
 kernel/bpf/verifier.c | 20 ++++++++++++++++++++
 2 files changed, 35 insertions(+)

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 2ae8f29b854f..1f171ac3462e 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) {
-- 
2.52.0