bpf: add writable context for raw tracepoints

This is an opt-in interface that allows a tracepoint to provide a safe
buffer that can be written from a BPF_PROG_TYPE_RAW_TRACEPOINT program.
The size of the buffer must be a compile-time constant, and is checked
before allowing a BPF program to attach to a tracepoint that uses this
feature.

The pointer to this buffer will be the first argument of tracepoints
that opt in; the pointer is valid and can be bpf_probe_read() by both
BPF_PROG_TYPE_RAW_TRACEPOINT and BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE
programs that attach to such a tracepoint, but the buffer to which it
points may only be written by the latter.

Signed-off-by: Matt Mullins <mmullins@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 61 insertions, 2 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b0de49598341..ae141e745f92 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1789,12 +1789,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	}
 	raw_tp->btp = btp;
 
-	prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
-				 BPF_PROG_TYPE_RAW_TRACEPOINT);
+	prog = bpf_prog_get(attr->raw_tracepoint.prog_fd);
 	if (IS_ERR(prog)) {
 		err = PTR_ERR(prog);
 		goto out_free_tp;
 	}
+	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
 
 	err = bpf_probe_register(raw_tp->btp, prog);
 	if (err)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 423f242a5efb..2ef442c62c0e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -405,6 +405,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
 	[PTR_TO_TCP_SOCK]	= "tcp_sock",
 	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
+	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 };
 
 static char slot_type_char[] = {
@@ -1993,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg,
+				  int regno, int off, int size)
+{
+	if (off < 0) {
+		verbose(env,
+			"R%d invalid tracepoint buffer access: off=%d, size=%d",
+			regno, off, size);
+		return -EACCES;
+	}
+	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env,
+			"R%d invalid variable buffer offset: off=%d, var_off=%s",
+			regno, off, tn_buf);
+		return -EACCES;
+	}
+	if (off + size > env->prog->aux->max_tp_access)
+		env->prog->aux->max_tp_access = off + size;
+
+	return 0;
+}
+
+
 /* truncate register to smaller size (in bytes)
  * must be called with size < BPF_REG_SIZE
  */
@@ -2137,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_sock_access(env, insn_idx, regno, off, size, t);
 		if (!err && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_TP_BUFFER) {
+		err = check_tp_buffer_access(env, reg, regno, off, size);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 91800be0c8eb..8607aba1d882 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -915,6 +915,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 const struct bpf_prog_ops raw_tracepoint_prog_ops = {
 };
 
+static bool raw_tp_writable_prog_is_valid_access(int off, int size,
+						 enum bpf_access_type type,
+						 const struct bpf_prog *prog,
+						 struct bpf_insn_access_aux *info)
+{
+	if (off == 0) {
+		if (size != sizeof(u64) || type != BPF_READ)
+			return false;
+		info->reg_type = PTR_TO_TP_BUFFER;
+	}
+	return raw_tp_prog_is_valid_access(off, size, type, prog, info);
+}
+
+const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = {
+	.get_func_proto  = raw_tp_prog_func_proto,
+	.is_valid_access = raw_tp_writable_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    const struct bpf_prog *prog,
 				    struct bpf_insn_access_aux *info)
@@ -1204,6 +1225,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
 	if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64))
 		return -EINVAL;
 
+	if (prog->aux->max_tp_access > btp->writable_size)
+		return -EINVAL;
+
 	return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
 }