bpf: enforce types for __arg_ctx-tagged arguments in global subprogs

Add enforcement of expected types for context arguments tagged with
arg:ctx (__arg_ctx) tag.

First, any program type will accept generic `void *` context type when
combined with __arg_ctx tag.

Besides accepting "canonical" struct names and `void *`, for a bunch of
program types for which program context is actually a named struct, we
allows a bunch of pragmatic exceptions to match real-world and expected
usage:

  - for both kprobes and perf_event we allow `bpf_user_pt_regs_t *` as
    canonical context argument type, where `bpf_user_pt_regs_t` is a
    *typedef*, not a struct;
  - for kprobes, we also always accept `struct pt_regs *`, as that's what
    actually is passed as a context to any kprobe program;
  - for perf_event, we resolve typedefs (unless it's `bpf_user_pt_regs_t`)
    down to actual struct type and accept `struct pt_regs *`, or
    `struct user_pt_regs *`, or `struct user_regs_struct *`, depending
    on the actual struct type kernel architecture points `bpf_user_pt_regs_t`
    typedef to; otherwise, canonical `struct bpf_perf_event_data *` is
    expected;
  - for raw_tp/raw_tp.w programs, `u64/long *` are accepted, as that's
    what's expected with BPF_PROG() usage; otherwise, canonical
    `struct bpf_raw_tracepoint_args *` is expected;
  - tp_btf supports both `struct bpf_raw_tracepoint_args *` and `u64 *`
    formats, both are coded as expections as tp_btf is actually a TRACING
    program type, which has no canonical context type;
  - iterator programs accept `struct bpf_iter__xxx *` structs, currently
    with no further iterator-type specific enforcement;
  - fentry/fexit/fmod_ret/lsm/struct_ops all accept `u64 *`;
  - classic tracepoint programs, as well as syscall and freplace
    programs allow any user-provided type.

In all other cases kernel will enforce exact match of struct name to
expected canonical type. And if user-provided type doesn't match that
expectation, verifier will emit helpful message with expected type name.

Note a bit unnatural way the check is done after processing all the
arguments. This is done to avoid conflict between bpf and bpf-next
trees. Once trees converge, a small follow up patch will place a simple
btf_validate_prog_ctx_type() check into a proper ARG_PTR_TO_CTX branch
(which bpf-next tree patch refactored already), removing duplicated
arg:ctx detection logic.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 10ac9efc662d0493afddbb74cde18cd307ee20c3..59647118917676c7aa3c69a20cffd0946ff7a2fb 100644 (file)
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5709,6 +5709,149 @@ again:
        return ctx_type;
 }
 
+/* forward declarations for arch-specific underlying types of
+ * bpf_user_pt_regs_t; this avoids the need for arch-specific #ifdef
+ * compilation guards below for BPF_PROG_TYPE_PERF_EVENT checks, but still
+ * works correctly with __builtin_types_compatible_p() on respective
+ * architectures
+ */
+struct user_regs_struct;
+struct user_pt_regs;
+
+static int btf_validate_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+                                     const struct btf_type *t, int arg,
+                                     enum bpf_prog_type prog_type,
+                                     enum bpf_attach_type attach_type)
+{
+       const struct btf_type *ctx_type;
+       const char *tname, *ctx_tname;
+
+       if (!btf_is_ptr(t)) {
+               bpf_log(log, "arg#%d type isn't a pointer\n", arg);
+               return -EINVAL;
+       }
+       t = btf_type_by_id(btf, t->type);
+
+       /* KPROBE and PERF_EVENT programs allow bpf_user_pt_regs_t typedef */
+       if (prog_type == BPF_PROG_TYPE_KPROBE || prog_type == BPF_PROG_TYPE_PERF_EVENT) {
+               while (btf_type_is_modifier(t) && !btf_type_is_typedef(t))
+                       t = btf_type_by_id(btf, t->type);
+
+               if (btf_type_is_typedef(t)) {
+                       tname = btf_name_by_offset(btf, t->name_off);
+                       if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0)
+                               return 0;
+               }
+       }
+
+       /* all other program types don't use typedefs for context type */
+       while (btf_type_is_modifier(t))
+               t = btf_type_by_id(btf, t->type);
+
+       /* `void *ctx __arg_ctx` is always valid */
+       if (btf_type_is_void(t))
+               return 0;
+
+       tname = btf_name_by_offset(btf, t->name_off);
+       if (str_is_empty(tname)) {
+               bpf_log(log, "arg#%d type doesn't have a name\n", arg);
+               return -EINVAL;
+       }
+
+       /* special cases */
+       switch (prog_type) {
+       case BPF_PROG_TYPE_KPROBE:
+               if (__btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+                       return 0;
+               break;
+       case BPF_PROG_TYPE_PERF_EVENT:
+               if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) &&
+                   __btf_type_is_struct(t) && strcmp(tname, "pt_regs") == 0)
+                       return 0;
+               if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) &&
+                   __btf_type_is_struct(t) && strcmp(tname, "user_pt_regs") == 0)
+                       return 0;
+               if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) &&
+                   __btf_type_is_struct(t) && strcmp(tname, "user_regs_struct") == 0)
+                       return 0;
+               break;
+       case BPF_PROG_TYPE_RAW_TRACEPOINT:
+       case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+               /* allow u64* as ctx */
+               if (btf_is_int(t) && t->size == 8)
+                       return 0;
+               break;
+       case BPF_PROG_TYPE_TRACING:
+               switch (attach_type) {
+               case BPF_TRACE_RAW_TP:
+                       /* tp_btf program is TRACING, so need special case here */
+                       if (__btf_type_is_struct(t) &&
+                           strcmp(tname, "bpf_raw_tracepoint_args") == 0)
+                               return 0;
+                       /* allow u64* as ctx */
+                       if (btf_is_int(t) && t->size == 8)
+                               return 0;
+                       break;
+               case BPF_TRACE_ITER:
+                       /* allow struct bpf_iter__xxx types only */
+                       if (__btf_type_is_struct(t) &&
+                           strncmp(tname, "bpf_iter__", sizeof("bpf_iter__") - 1) == 0)
+                               return 0;
+                       break;
+               case BPF_TRACE_FENTRY:
+               case BPF_TRACE_FEXIT:
+               case BPF_MODIFY_RETURN:
+                       /* allow u64* as ctx */
+                       if (btf_is_int(t) && t->size == 8)
+                               return 0;
+                       break;
+               default:
+                       break;
+               }
+               break;
+       case BPF_PROG_TYPE_LSM:
+       case BPF_PROG_TYPE_STRUCT_OPS:
+               /* allow u64* as ctx */
+               if (btf_is_int(t) && t->size == 8)
+                       return 0;
+               break;
+       case BPF_PROG_TYPE_TRACEPOINT:
+       case BPF_PROG_TYPE_SYSCALL:
+       case BPF_PROG_TYPE_EXT:
+               return 0; /* anything goes */
+       default:
+               break;
+       }
+
+       ctx_type = find_canonical_prog_ctx_type(prog_type);
+       if (!ctx_type) {
+               /* should not happen */
+               bpf_log(log, "btf_vmlinux is malformed\n");
+               return -EINVAL;
+       }
+
+       /* resolve typedefs and check that underlying structs are matching as well */
+       while (btf_type_is_modifier(ctx_type))
+               ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
+
+       /* if program type doesn't have distinctly named struct type for
+        * context, then __arg_ctx argument can only be `void *`, which we
+        * already checked above
+        */
+       if (!__btf_type_is_struct(ctx_type)) {
+               bpf_log(log, "arg#%d should be void pointer\n", arg);
+               return -EINVAL;
+       }
+
+       ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
+       if (!__btf_type_is_struct(t) || strcmp(ctx_tname, tname) != 0) {
+               bpf_log(log, "arg#%d should be `struct %s *`\n", arg, ctx_tname);
+               return -EINVAL;
+       }
+
+       return 0;
+}
+
 static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
                                     struct btf *btf,
                                     const struct btf_type *t,
@@ -6953,6 +7096,23 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
                return -EINVAL;
        }
 
+       for (i = 0; i < nargs; i++) {
+               const char *tag;
+
+               if (sub->args[i].arg_type != ARG_PTR_TO_CTX)
+                       continue;
+
+               /* check if arg has "arg:ctx" tag */
+               t = btf_type_by_id(btf, args[i].type);
+               tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:");
+               if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0)
+                       continue;
+
+               if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type,
+                                              prog->expected_attach_type))
+                       return -EINVAL;
+       }
+
        sub->arg_cnt = nargs;
        sub->args_cached = true;