[RFC v4 04/18] bpf,landlock: Add eBPF program subtype and is_valid_subtype() verifier

["Mickaël Salaün" <mic@digikod.net>]

The program subtype's goal is to be able to have different static
fine-grained verifications for a unique program type.

The struct bpf_verifier_ops gets a new optional function:
is_valid_subtype(). This new verifier is called at the begening of the
eBPF program verification to check if the (optional) program subtype is
valid.

For now, only Landlock eBPF programs are using a program subtype but
this could be used by other program types in the future.

Cf. the next commit to see how the subtype is used by Landlock LSM.

Changes since v3:
* remove the "origin" field
* add an "option" field
* cleanup comments

Signed-off-by: Mickaël Salaün <mic@digikod.net>
Link: https://lkml.kernel.org/r/20160827205559.GA43880@ast-mbp.thefacebook.com
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David S. Miller <davem@davemloft.net>
---
 include/linux/bpf.h      |  7 +++++--
 include/linux/filter.h   |  1 +
 include/uapi/linux/bpf.h | 18 ++++++++++++++++++
 kernel/bpf/syscall.c     |  5 +++--
 kernel/bpf/verifier.c    |  9 +++++++--
 kernel/trace/bpf_trace.c | 12 ++++++++----
 net/core/filter.c        | 26 ++++++++++++++++----------
 7 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 34b9e9cd1af7..2cca9fc8b72b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -163,18 +163,21 @@ struct bpf_prog;
 
 struct bpf_verifier_ops {
 	/* return eBPF function prototype for verification */
-	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+	const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id,
+			union bpf_prog_subtype *prog_subtype);
 
 	/* return true if 'size' wide access at offset 'off' within bpf_context
 	 * with 'type' (read or write) is allowed
 	 */
 	bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
-				enum bpf_reg_type *reg_type);
+				enum bpf_reg_type *reg_type,
+				union bpf_prog_subtype *prog_subtype);
 	int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
 			    const struct bpf_prog *prog);
 	u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg,
 				  int src_reg, int ctx_off,
 				  struct bpf_insn *insn, struct bpf_prog *prog);
+	bool (*is_valid_subtype)(union bpf_prog_subtype *prog_subtype);
 };
 
 struct bpf_prog_type_list {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1f09c521adfe..88470cdd3ee1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -406,6 +406,7 @@ struct bpf_prog {
 	kmemcheck_bitfield_end(meta);
 	u32			len;		/* Number of filter blocks */
 	enum bpf_prog_type	type;		/* Type of BPF program */
+	union bpf_prog_subtype	subtype;	/* For fine-grained verifications */
 	struct bpf_prog_aux	*aux;		/* Auxiliary fields */
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 339a9307ba6e..06621c401bc0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -130,6 +130,14 @@ enum bpf_attach_type {
 
 #define BPF_F_NO_PREALLOC	(1U << 0)
 
+union bpf_prog_subtype {
+	struct {
+		__u32		hook; /* enum landlock_hook */
+		__aligned_u64	access; /* LANDLOCK_SUBTYPE_ACCESS_* */
+		__aligned_u64	option; /* LANDLOCK_SUBTYPE_OPTION_* */
+	} landlock_rule;
+} __attribute__((aligned(8)));
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -158,6 +166,7 @@ union bpf_attr {
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
+		union bpf_prog_subtype prog_subtype;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -550,6 +559,15 @@ struct xdp_md {
 	__u32 data_end;
 };
 
+/* eBPF context and functions allowed for a rule */
+#define _LANDLOCK_SUBTYPE_ACCESS_MASK		((1ULL << 0) - 1)
+
+/*
+ * (future) options for a Landlock rule (e.g. run even if a previous rule
+ * returned an errno code)
+ */
+#define _LANDLOCK_SUBTYPE_OPTION_MASK	((1ULL << 0) - 1)
+
 /* Map handle entry */
 struct landlock_handle {
 	__u32 type; /* enum bpf_map_handle_type */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 13149c9cb3a4..6eef1da1e8a3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -572,7 +572,7 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 				continue;
 			}
 
-			fn = prog->aux->ops->get_func_proto(insn->imm);
+			fn = prog->aux->ops->get_func_proto(insn->imm, &prog->subtype);
 			/* all functions that have prototype and verifier allowed
 			 * programs to call them, must be real in-kernel functions
 			 */
@@ -710,7 +710,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
 EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD kern_version
+#define	BPF_PROG_LOAD_LAST_FIELD prog_subtype
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -768,6 +768,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	err = find_prog_type(type, prog);
 	if (err < 0)
 		goto free_prog;
+	prog->subtype = attr->prog_subtype;
 
 	/* run eBPF verifier */
 	err = bpf_check(&prog, attr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1bc7701466b0..9b921a9afa3c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -655,7 +655,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int off, int size,
 		return 0;
 
 	if (env->prog->aux->ops->is_valid_access &&
-	    env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) {
+	    env->prog->aux->ops->is_valid_access(off, size, t, reg_type,
+		    &env->prog->subtype)) {
 		/* remember the offset of last byte accessed in ctx */
 		if (env->prog->aux->max_ctx_offset < off + size)
 			env->prog->aux->max_ctx_offset = off + size;
@@ -1181,7 +1182,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 	}
 
 	if (env->prog->aux->ops->get_func_proto)
-		fn = env->prog->aux->ops->get_func_proto(func_id);
+		fn = env->prog->aux->ops->get_func_proto(func_id, &env->prog->subtype);
 
 	if (!fn) {
 		verbose("unknown func %d\n", func_id);
@@ -3065,6 +3066,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS)
 		return -E2BIG;
 
+	if ((*prog)->aux->ops->is_valid_subtype &&
+	    !(*prog)->aux->ops->is_valid_subtype(&(*prog)->subtype))
+		return -EINVAL;
+
 	/* 'struct bpf_verifier_env' can be global, but since it's not small,
 	 * allocate/free it every time bpf_check() is called
 	 */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5dcb99281259..51cf0f254bf2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -435,7 +435,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 	}
 }
 
-static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id,
+		union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
@@ -449,7 +450,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 
 /* bpf+kprobe programs can access fields of 'struct pt_regs' */
 static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
-					enum bpf_reg_type *reg_type)
+					enum bpf_reg_type *reg_type,
+					union bpf_prog_subtype *prog_subtype)
 {
 	if (off < 0 || off >= sizeof(struct pt_regs))
 		return false;
@@ -517,7 +519,8 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id,
+		union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
@@ -530,7 +533,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
 }
 
 static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type,
-				    enum bpf_reg_type *reg_type)
+				    enum bpf_reg_type *reg_type,
+				    union bpf_prog_subtype *prog_subtype)
 {
 	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
 		return false;
diff --git a/net/core/filter.c b/net/core/filter.c
index bd6eebeed5c6..a39f5956f31a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2483,7 +2483,8 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 };
 
 static const struct bpf_func_proto *
-sk_filter_func_proto(enum bpf_func_id func_id)
+sk_filter_func_proto(enum bpf_func_id func_id,
+		union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -2509,7 +2510,8 @@ sk_filter_func_proto(enum bpf_func_id func_id)
 }
 
 static const struct bpf_func_proto *
-tc_cls_act_func_proto(enum bpf_func_id func_id)
+tc_cls_act_func_proto(enum bpf_func_id func_id,
+		union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_skb_store_bytes:
@@ -2563,12 +2565,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return sk_filter_func_proto(func_id);
+		return sk_filter_func_proto(func_id, prog_subtype);
 	}
 }
 
 static const struct bpf_func_proto *
-xdp_func_proto(enum bpf_func_id func_id)
+xdp_func_proto(enum bpf_func_id func_id, union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
@@ -2576,18 +2578,19 @@ xdp_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
 	default:
-		return sk_filter_func_proto(func_id);
+		return sk_filter_func_proto(func_id, prog_subtype);
 	}
 }
 
 static const struct bpf_func_proto *
-cg_skb_func_proto(enum bpf_func_id func_id)
+cg_skb_func_proto(enum bpf_func_id func_id,
+		union bpf_prog_subtype *prog_subtype)
 {
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
 	default:
-		return sk_filter_func_proto(func_id);
+		return sk_filter_func_proto(func_id, prog_subtype);
 	}
 }
 
@@ -2606,7 +2609,8 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type)
 
 static bool sk_filter_is_valid_access(int off, int size,
 				      enum bpf_access_type type,
-				      enum bpf_reg_type *reg_type)
+				      enum bpf_reg_type *reg_type,
+				      union bpf_prog_subtype *prog_subtype)
 {
 	switch (off) {
 	case offsetof(struct __sk_buff, tc_classid):
@@ -2669,7 +2673,8 @@ static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write,
 
 static bool tc_cls_act_is_valid_access(int off, int size,
 				       enum bpf_access_type type,
-				       enum bpf_reg_type *reg_type)
+				       enum bpf_reg_type *reg_type,
+				       union bpf_prog_subtype *prog_subtype)
 {
 	if (type == BPF_WRITE) {
 		switch (off) {
@@ -2712,7 +2717,8 @@ static bool __is_valid_xdp_access(int off, int size,
 
 static bool xdp_is_valid_access(int off, int size,
 				enum bpf_access_type type,
-				enum bpf_reg_type *reg_type)
+				enum bpf_reg_type *reg_type,
+				union bpf_prog_subtype *prog_subtype)
 {
 	if (type == BPF_WRITE)
 		return false;
-- 
2.9.3