Merge branch 'writeable-bpf-tracepoints'

Matt Mullins says:

====================
This adds an opt-in interface for tracepoints to expose a writable context to
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE programs that are attached, while
supporting read-only access from existing BPF_PROG_TYPE_RAW_TRACEPOINT
programs, as well as from non-BPF-based tracepoints.

The initial motivation is to support tracing that can be observed from the
remote end of an NBD socket, e.g. by adding flags to the struct nbd_request
header.  Earlier attempts included adding an NBD-specific tracepoint fd, but in
code review, I was recommended to implement it more generically -- as a result,
this patchset is far simpler than my initial try.

v4->v5:
  * rebased onto bpf-next/master and fixed merge conflicts
  * "tools: sync bpf.h" also syncs comments that have previously changed
    in bpf-next

v3->v4:
  * fixed a silly copy/paste typo in include/trace/events/bpf_test_run.h
    (_TRACE_NBD_H -> _TRACE_BPF_TEST_RUN_H)
  * fixed incorrect/misleading wording in patch 1's commit message,
    since the pointer cannot be directly dereferenced in a
    BPF_PROG_TYPE_RAW_TRACEPOINT
  * cleaned up the error message wording if the prog_tests fail
  * Addressed feedback from Yonghong
    * reject non-pointer-sized accesses to the buffer pointer
    * use sizeof(struct nbd_request) as one-byte-past-the-end in
      raw_tp_writable_reject_nbd_invalid.c
    * use BPF_MOV64_IMM instead of BPF_LD_IMM64

v2->v3:
  * Andrew addressed Josef's comments:
    * C-style commenting in nbd.c
    * Collapsed identical events into a single DECLARE_EVENT_CLASS.
      This saves about 2kB of kernel text

v1->v2:
  * add selftests
    * sync tools/include/uapi/linux/bpf.h
  * reject variable offset into the buffer
  * add string representation of PTR_TO_TP_BUFFER to reg_type_str
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 37 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]);