bpf: Populate kfunc BTF ID sets in struct btf

This patch prepares the kernel to support putting all kinds of kfunc BTF
ID sets in the struct btf itself. The various kernel subsystems will
make register_btf_kfunc_id_set call in the initcalls (for built-in code
and modules).

The 'hook' is one of the many program types, e.g. XDP and TC/SCHED_CLS,
STRUCT_OPS, and 'types' are check (allowed or not), acquire, release,
and ret_null (with PTR_TO_BTF_ID_OR_NULL return type).

A maximum of BTF_KFUNC_SET_MAX_CNT (32) kfunc BTF IDs are permitted in a
set of certain hook and type for vmlinux sets, since they are allocated
on demand, and otherwise set as NULL. Module sets can only be registered
once per hook and type, hence they are directly assigned.

A new btf_kfunc_id_set_contains function is exposed for use in verifier,
this new method is faster than the existing list searching method, and
is also automatic. It also lets other code not care whether the set is
unallocated or not.

Note that module code can only do single register_btf_kfunc_id_set call
per hook. This is why sorting is only done for in-kernel vmlinux sets,
because there might be multiple sets for the same hook and type that
must be concatenated, hence sorting them is required to ensure bsearch
in btf_id_set_contains continues to work correctly.

Next commit will update the kernel users to make use of this
infrastructure.

Finally, add __maybe_unused annotation for BTF ID macros for the
!CONFIG_DEBUG_INFO_BTF case, so that they don't produce warnings during
build time.

The previous patch is also needed to provide synchronization against
initialization for module BTF's kfunc_set_tab introduced here, as
described below:

  The kfunc_set_tab pointer in struct btf is write-once (if we consider
  the registration phase (comprised of multiple register_btf_kfunc_id_set
  calls) as a single operation). In this sense, once it has been fully
  prepared, it isn't modified, only used for lookup (from the verifier
  context).

  For btf_vmlinux, it is initialized fully during the do_initcalls phase,
  which happens fairly early in the boot process, before any processes are
  present. This also eliminates the possibility of bpf_check being called
  at that point, thus relieving us of ensuring any synchronization between
  the registration and lookup function (btf_kfunc_id_set_contains).

  However, the case for module BTF is a bit tricky. The BTF is parsed,
  prepared, and published from the MODULE_STATE_COMING notifier callback.
  After this, the module initcalls are invoked, where our registration
  function will be called to populate the kfunc_set_tab for module BTF.

  At this point, BTF may be available to userspace while its corresponding
  module is still intializing. A BTF fd can then be passed to verifier
  using bpf syscall (e.g. for kfunc call insn).

  Hence, there is a race window where verifier may concurrently try to
  lookup the kfunc_set_tab. To prevent this race, we must ensure the
  operations are serialized, or waiting for the __init functions to
  complete.

  In the earlier registration API, this race was alleviated as verifier
  bpf_check_mod_kfunc_call didn't find the kfunc BTF ID until it was added
  by the registration function (called usually at the end of module __init
  function after all module resources have been initialized). If the
  verifier made the check_kfunc_call before kfunc BTF ID was added to the
  list, it would fail verification (saying call isn't allowed). The
  access to list was protected using a mutex.

  Now, it would still fail verification, but for a different reason
  (returning ENXIO due to the failed btf_try_get_module call in
  add_kfunc_call), because if the __init call is in progress the module
  will be in the middle of MODULE_STATE_COMING -> MODULE_STATE_LIVE
  transition, and the BTF_MODULE_LIVE flag for btf_module instance will
  not be set, so the btf_try_get_module call will fail.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20220114163953.1455836-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 46 insertions, 6 deletions

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 0c74348cbc9d..c451f8e2612a 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -12,11 +12,33 @@
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val)
 
+enum btf_kfunc_type {
+	BTF_KFUNC_TYPE_CHECK,
+	BTF_KFUNC_TYPE_ACQUIRE,
+	BTF_KFUNC_TYPE_RELEASE,
+	BTF_KFUNC_TYPE_RET_NULL,
+	BTF_KFUNC_TYPE_MAX,
+};
+
 struct btf;
 struct btf_member;
 struct btf_type;
 union bpf_attr;
 struct btf_show;
+struct btf_id_set;
+
+struct btf_kfunc_id_set {
+	struct module *owner;
+	union {
+		struct {
+			struct btf_id_set *check_set;
+			struct btf_id_set *acquire_set;
+			struct btf_id_set *release_set;
+			struct btf_id_set *ret_null_set;
+		};
+		struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
+	};
+};
 
 extern const struct file_operations btf_fops;
 
@@ -307,6 +329,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
+bool btf_kfunc_id_set_contains(const struct btf *btf,
+			       enum bpf_prog_type prog_type,
+			       enum btf_kfunc_type type, u32 kfunc_btf_id);
+int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+			      const struct btf_kfunc_id_set *s);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
@@ -318,6 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf,
 {
 	return NULL;
 }
+static inline bool btf_kfunc_id_set_contains(const struct btf *btf,
+					     enum bpf_prog_type prog_type,
+					     enum btf_kfunc_type type,
+					     u32 kfunc_btf_id)
+{
+	return false;
+}
+static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+					    const struct btf_kfunc_id_set *s)
+{
+	return 0;
+}
 #endif
 
 struct kfunc_btf_id_set {
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 919c0fde1c51..bc5d9cc34e4c 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -11,6 +11,7 @@ struct btf_id_set {
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */
+#include <linux/compiler_attributes.h> /* for __maybe_unused */
 
 /*
  * Following macros help to define lists of BTF IDs placed
@@ -146,14 +147,14 @@ extern struct btf_id_set name;
 
 #else
 
-#define BTF_ID_LIST(name) static u32 name[5];
+#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
-#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n];
-#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
-#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1];
-#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
-#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
+#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1];
+#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
 #define BTF_SET_END(name)
 
 #endif /* CONFIG_DEBUG_INFO_BTF */