bpf: verifier: remove dead code

Instead of overwriting dead code with jmp -1 instructions
remove it completely for root.  Adjust verifier state and
line info appropriately.

v2:
 - adjust func_info (Alexei);
 - make sure first instruction retains line info (Alexei).
v4: (Yonghong)
 - remove unnecessary if (!insn to remove) checks;
 - always keep last line info if first live instruction lacks one.
v5: (Martin Lau)
 - improve and clarify comments.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/filter.h

@@ -778,6 +778,7 @@ static inline bool bpf_dump_raw_ok(void)
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
+int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt);
 
 void bpf_clear_redirect_map(struct bpf_map *map);
 

kernel/bpf/core.c

@@ -462,6 +462,18 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	return prog_adj;
 }
 
+int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
+{
+	/* Branch offsets can't overflow when program is shrinking, no need
+	 * to call bpf_adj_branches(..., true) here
+	 */
+	memmove(prog->insnsi + off, prog->insnsi + off + cnt,
+		sizeof(struct bpf_insn) * (prog->len - off - cnt));
+	prog->len -= cnt;
+
+	return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
+}
+
 void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
 {
 	int i;

kernel/bpf/verifier.c

@@ -6432,6 +6432,150 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
+static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
+					      u32 off, u32 cnt)
+{
+	int i, j;
+
+	/* find first prog starting at or after off (first to remove) */
+	for (i = 0; i < env->subprog_cnt; i++)
+		if (env->subprog_info[i].start >= off)
+			break;
+	/* find first prog starting at or after off + cnt (first to stay) */
+	for (j = i; j < env->subprog_cnt; j++)
+		if (env->subprog_info[j].start >= off + cnt)
+			break;
+	/* if j doesn't start exactly at off + cnt, we are just removing
+	 * the front of previous prog
+	 */
+	if (env->subprog_info[j].start != off + cnt)
+		j--;
+
+	if (j > i) {
+		struct bpf_prog_aux *aux = env->prog->aux;
+		int move;
+
+		/* move fake 'exit' subprog as well */
+		move = env->subprog_cnt + 1 - j;
+
+		memmove(env->subprog_info + i,
+			env->subprog_info + j,
+			sizeof(*env->subprog_info) * move);
+		env->subprog_cnt -= j - i;
+
+		/* remove func_info */
+		if (aux->func_info) {
+			move = aux->func_info_cnt - j;
+
+			memmove(aux->func_info + i,
+				aux->func_info + j,
+				sizeof(*aux->func_info) * move);
+			aux->func_info_cnt -= j - i;
+			/* func_info->insn_off is set after all code rewrites,
+			 * in adjust_btf_func() - no need to adjust
+			 */
+		}
+	} else {
+		/* convert i from "first prog to remove" to "first to adjust" */
+		if (env->subprog_info[i].start == off)
+			i++;
+	}
+
+	/* update fake 'exit' subprog as well */
+	for (; i <= env->subprog_cnt; i++)
+		env->subprog_info[i].start -= cnt;
+
+	return 0;
+}
+
+static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off,
+				      u32 cnt)
+{
+	struct bpf_prog *prog = env->prog;
+	u32 i, l_off, l_cnt, nr_linfo;
+	struct bpf_line_info *linfo;
+
+	nr_linfo = prog->aux->nr_linfo;
+	if (!nr_linfo)
+		return 0;
+
+	linfo = prog->aux->linfo;
+
+	/* find first line info to remove, count lines to be removed */
+	for (i = 0; i < nr_linfo; i++)
+		if (linfo[i].insn_off >= off)
+			break;
+
+	l_off = i;
+	l_cnt = 0;
+	for (; i < nr_linfo; i++)
+		if (linfo[i].insn_off < off + cnt)
+			l_cnt++;
+		else
+			break;
+
+	/* First live insn doesn't match first live linfo, it needs to "inherit"
+	 * last removed linfo.  prog is already modified, so prog->len == off
+	 * means no live instructions after (tail of the program was removed).
+	 */
+	if (prog->len != off && l_cnt &&
+	    (i == nr_linfo || linfo[i].insn_off != off + cnt)) {
+		l_cnt--;
+		linfo[--i].insn_off = off + cnt;
+	}
+
+	/* remove the line info which refer to the removed instructions */
+	if (l_cnt) {
+		memmove(linfo + l_off, linfo + i,
+			sizeof(*linfo) * (nr_linfo - i));
+
+		prog->aux->nr_linfo -= l_cnt;
+		nr_linfo = prog->aux->nr_linfo;
+	}
+
+	/* pull all linfo[i].insn_off >= off + cnt in by cnt */
+	for (i = l_off; i < nr_linfo; i++)
+		linfo[i].insn_off -= cnt;
+
+	/* fix up all subprogs (incl. 'exit') which start >= off */
+	for (i = 0; i <= env->subprog_cnt; i++)
+		if (env->subprog_info[i].linfo_idx > l_off) {
+			/* program may have started in the removed region but
+			 * may not be fully removed
+			 */
+			if (env->subprog_info[i].linfo_idx >= l_off + l_cnt)
+				env->subprog_info[i].linfo_idx -= l_cnt;
+			else
+				env->subprog_info[i].linfo_idx = l_off;
+		}
+
+	return 0;
+}
+
+static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	unsigned int orig_prog_len = env->prog->len;
+	int err;
+
+	err = bpf_remove_insns(env->prog, off, cnt);
+	if (err)
+		return err;
+
+	err = adjust_subprog_starts_after_remove(env, off, cnt);
+	if (err)
+		return err;
+
+	err = bpf_adj_linfo_after_remove(env, off, cnt);
+	if (err)
+		return err;
+
+	memmove(aux_data + off,	aux_data + off + cnt,
+		sizeof(*aux_data) * (orig_prog_len - off - cnt));
+
+	return 0;
+}
+
 /* The verifier does more data flow analysis than llvm and will not
  * explore branches that are dead at run time. Malicious programs can
  * have dead code too. Therefore replace all dead at-run-time code
@@ -6492,6 +6636,30 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
 	}
 }
 
+static int opt_remove_dead_code(struct bpf_verifier_env *env)
+{
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	int insn_cnt = env->prog->len;
+	int i, err;
+
+	for (i = 0; i < insn_cnt; i++) {
+		int j;
+
+		j = 0;
+		while (i + j < insn_cnt && !aux_data[i + j].seen)
+			j++;
+		if (!j)
+			continue;
+
+		err = verifier_remove_insns(env, i, j);
+		if (err)
+			return err;
+		insn_cnt = env->prog->len;
+	}
+
+	return 0;
+}
+
 /* convert load instructions that access fields of a context type into a
  * sequence of instructions that access fields of the underlying structure:
  *     struct __sk_buff    -> struct sk_buff
@@ -7282,10 +7450,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (is_priv) {
 		if (ret == 0)
 			opt_hard_wire_dead_code_branches(env);
-	}
+		if (ret == 0)
-
+			ret = opt_remove_dead_code(env);
+	} else {
 		if (ret == 0)
 			sanitize_dead_code(env);
+	}
 
 	if (ret == 0)
 		/* program is valid, convert *(u32*)(ctx + off) accesses */