bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS

This patch allows the kernel's struct ops (i.e. func ptr) to be
implemented in BPF.  The first use case in this series is the
"struct tcp_congestion_ops" which will be introduced in a
latter patch.

This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS.
The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular
func ptr of a kernel struct.  The attr->attach_btf_id is the btf id
of a kernel struct.  The attr->expected_attach_type is the member
"index" of that kernel struct.  The first member of a struct starts
with member index 0.  That will avoid ambiguity when a kernel struct
has multiple func ptrs with the same func signature.

For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written
to implement the "init" func ptr of the "struct tcp_congestion_ops".
The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops"
of the _running_ kernel.  The attr->expected_attach_type is 3.

The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved
by arch_prepare_bpf_trampoline that will be done in the next
patch when introducing BPF_MAP_TYPE_STRUCT_OPS.

"struct bpf_struct_ops" is introduced as a common interface for the kernel
struct that supports BPF_PROG_TYPE_STRUCT_OPS prog.  The supporting kernel
struct will need to implement an instance of the "struct bpf_struct_ops".

The supporting kernel struct also needs to implement a bpf_verifier_ops.
During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right
bpf_verifier_ops by searching the attr->attach_btf_id.

A new "btf_struct_access" is also added to the bpf_verifier_ops such
that the supporting kernel struct can optionally provide its own specific
check on accessing the func arg (e.g. provide limited write access).

After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called
to initialize some values (e.g. the btf id of the supporting kernel
struct) and it can only be done once the btf_vmlinux is available.

The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog
if the return type of the prog->aux->attach_func_proto is "void".

Signed-off-by: Martin KaFai Lau <[email protected]>
Signed-off-by: Alexei Starovoitov <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Acked-by: Yonghong Song <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

include/linux/bpf.h

@@ -349,6 +349,10 @@ struct bpf_verifier_ops {
 				  const struct bpf_insn *src,
 				  struct bpf_insn *dst,
 				  struct bpf_prog *prog, u32 *target_size);
+	int (*btf_struct_access)(struct bpf_verifier_log *log,
+				 const struct btf_type *t, int off, int size,
+				 enum bpf_access_type atype,
+				 u32 *next_btf_id);
 };
 
 struct bpf_prog_offload_ops {
@@ -668,6 +672,32 @@ struct bpf_array_aux {
 	struct work_struct work;
 };
 
+struct btf_type;
+struct btf_member;
+
+#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+struct bpf_struct_ops {
+	const struct bpf_verifier_ops *verifier_ops;
+	int (*init)(struct btf *btf);
+	int (*check_member)(const struct btf_type *t,
+			    const struct btf_member *member);
+	const struct btf_type *type;
+	const char *name;
+	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
+	u32 type_id;
+};
+
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
+void bpf_struct_ops_init(struct btf *btf);
+#else
+static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
+{
+	return NULL;
+}
+static inline void bpf_struct_ops_init(struct btf *btf) { }
+#endif
+
 struct bpf_array {
 	struct bpf_map map;
 	u32 elem_size;

include/linux/bpf_types.h

@@ -65,6 +65,10 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
 	      struct sk_reuseport_md, struct sk_reuseport_kern)
 #endif
+#if defined(CONFIG_BPF_JIT)
+BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
+	      void *, void *)
+#endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)

include/linux/btf.h

@@ -53,6 +53,18 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   u32 expected_offset, u32 expected_size);
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
 bool btf_type_is_void(const struct btf_type *t);
+s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
+const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
+					       u32 id, u32 *res_id);
+const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
+					    u32 id, u32 *res_id);
+const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
+						 u32 id, u32 *res_id);
+
+#define for_each_member(i, struct_type, member)			\
+	for (i = 0, member = btf_type_member(struct_type);	\
+	     i < btf_type_vlen(struct_type);			\
+	     i++, member++)
 
 static inline bool btf_type_is_ptr(const struct btf_type *t)
 {
@@ -84,6 +96,28 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
 }
 
+static inline u16 btf_type_vlen(const struct btf_type *t)
+{
+	return BTF_INFO_VLEN(t->info);
+}
+
+static inline bool btf_type_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type,
+					   const struct btf_member *member)
+{
+	return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
+					   : 0;
+}
+
+static inline const struct btf_member *btf_type_member(const struct btf_type *t)
+{
+	return (const struct btf_member *)(t + 1);
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 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);

include/uapi/linux/bpf.h

@@ -174,6 +174,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
 	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 	BPF_PROG_TYPE_TRACING,
+	BPF_PROG_TYPE_STRUCT_OPS,
 };
 
 enum bpf_attach_type {

kernel/bpf/Makefile

@@ -27,3 +27,6 @@ endif
 ifeq ($(CONFIG_SYSFS),y)
 obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
 endif
+ifeq ($(CONFIG_BPF_JIT),y)
+obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o
+endif

kernel/bpf/bpf_struct_ops.c

@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <linux/slab.h>
+#include <linux/numa.h>
+#include <linux/seq_file.h>
+#include <linux/refcount.h>
+
+#define BPF_STRUCT_OPS_TYPE(_name)				\
+extern struct bpf_struct_ops bpf_##_name;
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+
+enum {
+#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+	__NR_BPF_STRUCT_OPS_TYPE,
+};
+
+static struct bpf_struct_ops * const bpf_struct_ops[] = {
+#define BPF_STRUCT_OPS_TYPE(_name)				\
+	[BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name,
+#include "bpf_struct_ops_types.h"
+#undef BPF_STRUCT_OPS_TYPE
+};
+
+const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = {
+};
+
+const struct bpf_prog_ops bpf_struct_ops_prog_ops = {
+};
+
+void bpf_struct_ops_init(struct btf *btf)
+{
+	const struct btf_member *member;
+	struct bpf_struct_ops *st_ops;
+	struct bpf_verifier_log log = {};
+	const struct btf_type *t;
+	const char *mname;
+	s32 type_id;
+	u32 i, j;
+
+	for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+		st_ops = bpf_struct_ops[i];
+
+		type_id = btf_find_by_name_kind(btf, st_ops->name,
+						BTF_KIND_STRUCT);
+		if (type_id < 0) {
+			pr_warn("Cannot find struct %s in btf_vmlinux\n",
+				st_ops->name);
+			continue;
+		}
+		t = btf_type_by_id(btf, type_id);
+		if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) {
+			pr_warn("Cannot support #%u members in struct %s\n",
+				btf_type_vlen(t), st_ops->name);
+			continue;
+		}
+
+		for_each_member(j, t, member) {
+			const struct btf_type *func_proto;
+
+			mname = btf_name_by_offset(btf, member->name_off);
+			if (!*mname) {
+				pr_warn("anon member in struct %s is not supported\n",
+					st_ops->name);
+				break;
+			}
+
+			if (btf_member_bitfield_size(t, member)) {
+				pr_warn("bit field member %s in struct %s is not supported\n",
+					mname, st_ops->name);
+				break;
+			}
+
+			func_proto = btf_type_resolve_func_ptr(btf,
+							       member->type,
+							       NULL);
+			if (func_proto &&
+			    btf_distill_func_proto(&log, btf,
+						   func_proto, mname,
+						   &st_ops->func_models[j])) {
+				pr_warn("Error in parsing func ptr %s in struct %s\n",
+					mname, st_ops->name);
+				break;
+			}
+		}
+
+		if (j == btf_type_vlen(t)) {
+			if (st_ops->init(btf)) {
+				pr_warn("Error in init bpf_struct_ops %s\n",
+					st_ops->name);
+			} else {
+				st_ops->type_id = type_id;
+				st_ops->type = t;
+			}
+		}
+	}
+}
+
+extern struct btf *btf_vmlinux;
+
+const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
+{
+	unsigned int i;
+
+	if (!type_id || !btf_vmlinux)
+		return NULL;
+
+	for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) {
+		if (bpf_struct_ops[i]->type_id == type_id)
+			return bpf_struct_ops[i];
+	}
+
+	return NULL;
+}

kernel/bpf/bpf_struct_ops_types.h

@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* internal file - do not include directly */
+
+/* To be filled in a later patch */

kernel/bpf/btf.c

@@ -180,11 +180,6 @@
  */
 #define BTF_MAX_SIZE (16 * 1024 * 1024)
 
-#define for_each_member(i, struct_type, member)			\
-	for (i = 0, member = btf_type_member(struct_type);	\
-	     i < btf_type_vlen(struct_type);			\
-	     i++, member++)
-
 #define for_each_member_from(i, from, struct_type, member)		\
 	for (i = from, member = btf_type_member(struct_type) + from;	\
 	     i < btf_type_vlen(struct_type);				\
@@ -382,6 +377,65 @@ static bool btf_type_is_datasec(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
 }
 
+s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind)
+{
+	const struct btf_type *t;
+	const char *tname;
+	u32 i;
+
+	for (i = 1; i <= btf->nr_types; i++) {
+		t = btf->types[i];
+		if (BTF_INFO_KIND(t->info) != kind)
+			continue;
+
+		tname = btf_name_by_offset(btf, t->name_off);
+		if (!strcmp(tname, name))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
+					       u32 id, u32 *res_id)
+{
+	const struct btf_type *t = btf_type_by_id(btf, id);
+
+	while (btf_type_is_modifier(t)) {
+		id = t->type;
+		t = btf_type_by_id(btf, t->type);
+	}
+
+	if (res_id)
+		*res_id = id;
+
+	return t;
+}
+
+const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
+					    u32 id, u32 *res_id)
+{
+	const struct btf_type *t;
+
+	t = btf_type_skip_modifiers(btf, id, NULL);
+	if (!btf_type_is_ptr(t))
+		return NULL;
+
+	return btf_type_skip_modifiers(btf, t->type, res_id);
+}
+
+const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf,
+						 u32 id, u32 *res_id)
+{
+	const struct btf_type *ptype;
+
+	ptype = btf_type_resolve_ptr(btf, id, res_id);
+	if (ptype && btf_type_is_func_proto(ptype))
+		return ptype;
+
+	return NULL;
+}
+
 /* Types that act only as a source, not sink or intermediate
  * type when resolving.
  */
@@ -446,30 +500,13 @@ static const char *btf_int_encoding_str(u8 encoding)
 		return "UNKN";
 }
 
-static u16 btf_type_vlen(const struct btf_type *t)
-{
-	return BTF_INFO_VLEN(t->info);
-}
-
-static bool btf_type_kflag(const struct btf_type *t)
-{
-	return BTF_INFO_KFLAG(t->info);
-}
-
 static u32 btf_member_bit_offset(const struct btf_type *struct_type,
 			     const struct btf_member *member)
 {
 	return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
 					   : member->offset;
 }
 
-static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
-				    const struct btf_member *member)
-{
-	return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
-					   : 0;
-}
-
 static u32 btf_type_int(const struct btf_type *t)
 {
 	return *(u32 *)(t + 1);
@@ -480,11 +517,6 @@ static const struct btf_array *btf_type_array(const struct btf_type *t)
 	return (const struct btf_array *)(t + 1);
 }
 
-static const struct btf_member *btf_type_member(const struct btf_type *t)
-{
-	return (const struct btf_member *)(t + 1);
-}
-
 static const struct btf_enum *btf_type_enum(const struct btf_type *t)
 {
 	return (const struct btf_enum *)(t + 1);
@@ -3605,6 +3637,8 @@ struct btf *btf_parse_vmlinux(void)
 		goto errout;
 	}
 
+	bpf_struct_ops_init(btf);
+
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
 	return btf;