Implement session cookie for fsession. In order to limit the stack usage,
we make 4 as the maximum of the cookie count.

The offset of the current cookie is stored in the
"(ctx[-1] >> BPF_TRAMP_M_COOKIE) & 0xFF". Therefore, we can get the
session cookie with ctx[-offset].

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

Inline the bpf_fsession_cookie() in the verifer too.

Signed-off-by: Menglong Dong <redacted>
---
v4:
- limit the maximum of the cookie count to 4
- store the session cookies before nr_regs in stack
---
 include/linux/bpf.h      | 16 ++++++++++++++++
 kernel/bpf/trampoline.c  | 14 +++++++++++++-
 kernel/bpf/verifier.c    | 20 ++++++++++++++++++--
 kernel/trace/bpf_trace.c |  9 +++++++++
 4 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d165ace5cc9b..0f35c6ab538c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h

@@ -1215,6 +1215,7 @@ enum {

 #define BPF_TRAMP_M_NR_ARGS    0
 #define BPF_TRAMP_M_IS_RETURN  8
+#define BPF_TRAMP_M_COOKIE     9

 struct bpf_tramp_links {
        struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];

@@ -1318,6 +1319,7 @@ struct bpf_trampoline {
        struct mutex mutex;
        refcount_t refcnt;
        u32 flags;
+       int cookie_cnt;

        u64 key;
        struct {
                struct btf_func_model model;

@@ -1762,6 +1764,7 @@ 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 */