1 files changed, 184 insertions, 47 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 17270b8404f1..0f82d5d46e2c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3604,13 +3604,30 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 	return err;
 }
 
-static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
+static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
 {
+	int load_reg;
 	int err;
 
-	if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
-	    insn->imm != 0) {
-		verbose(env, "BPF_XADD uses reserved fields\n");
+	switch (insn->imm) {
+	case BPF_ADD:
+	case BPF_ADD | BPF_FETCH:
+	case BPF_AND:
+	case BPF_AND | BPF_FETCH:
+	case BPF_OR:
+	case BPF_OR | BPF_FETCH:
+	case BPF_XOR:
+	case BPF_XOR | BPF_FETCH:
+	case BPF_XCHG:
+	case BPF_CMPXCHG:
+		break;
+	default:
+		verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm);
+		return -EINVAL;
+	}
+
+	if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) {
+		verbose(env, "invalid atomic operand size\n");
 		return -EINVAL;
 	}
 
@@ -3624,6 +3641,13 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	if (err)
 		return err;
 
+	if (insn->imm == BPF_CMPXCHG) {
+		/* Check comparison of R0 with memory location */
+		err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+		if (err)
+			return err;
+	}
+
 	if (is_pointer_value(env, insn->src_reg)) {
 		verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
 		return -EACCES;
@@ -3633,21 +3657,38 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 	    is_pkt_reg(env, insn->dst_reg) ||
 	    is_flow_key_reg(env, insn->dst_reg) ||
 	    is_sk_reg(env, insn->dst_reg)) {
-		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
+		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
 			insn->dst_reg,
 			reg_type_str[reg_state(env, insn->dst_reg)->type]);
 		return -EACCES;
 	}
 
-	/* check whether atomic_add can read the memory */
+	/* check whether we can read the memory */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_READ, -1, true);
 	if (err)
 		return err;
 
-	/* check whether atomic_add can write into the same memory */
-	return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+	/* check whether we can write into the same memory */
+	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+	if (err)
+		return err;
+
+	if (!(insn->imm & BPF_FETCH))
+		return 0;
+
+	if (insn->imm == BPF_CMPXCHG)
+		load_reg = BPF_REG_0;
+	else
+		load_reg = insn->src_reg;
+
+	/* check and record load of old value */
+	err = check_reg_arg(env, load_reg, DST_OP);
+	if (err)
+		return err;
+
+	return 0;
 }
 
 static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
@@ -4319,7 +4360,7 @@ skip_type_check:
 			err = mark_chain_precision(env, regno);
 	} else if (arg_type_is_alloc_size(arg_type)) {
 		if (!tnum_is_const(reg->var_off)) {
-			verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n",
+			verbose(env, "R%d is not a known constant'\n",
 				regno);
 			return -EACCES;
 		}
@@ -9524,14 +9565,19 @@ static int do_check(struct bpf_verifier_env *env)
 		} else if (class == BPF_STX) {
 			enum bpf_reg_type *prev_dst_type, dst_reg_type;
 
-			if (BPF_MODE(insn->code) == BPF_XADD) {
-				err = check_xadd(env, env->insn_idx, insn);
+			if (BPF_MODE(insn->code) == BPF_ATOMIC) {
+				err = check_atomic(env, env->insn_idx, insn);
 				if (err)
 					return err;
 				env->insn_idx++;
 				continue;
 			}
 
+			if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
+				verbose(env, "BPF_STX uses reserved fields\n");
+				return -EINVAL;
+			}
+
 			/* check src1 operand */
 			err = check_reg_arg(env, insn->src_reg, SRC_OP);
 			if (err)
@@ -9703,6 +9749,36 @@ process_bpf_exit:
 	return 0;
 }
 
+static int find_btf_percpu_datasec(struct btf *btf)
+{
+	const struct btf_type *t;
+	const char *tname;
+	int i, n;
+
+	/*
+	 * Both vmlinux and module each have their own ".data..percpu"
+	 * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF
+	 * types to look at only module's own BTF types.
+	 */
+	n = btf_nr_types(btf);
+	if (btf_is_module(btf))
+		i = btf_nr_types(btf_vmlinux);
+	else
+		i = 1;
+
+	for(; i < n; i++) {
+		t = btf_type_by_id(btf, i);
+		if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
+			continue;
+
+		tname = btf_name_by_offset(btf, t->name_off);
+		if (!strcmp(tname, ".data..percpu"))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
 /* replace pseudo btf_id with kernel symbol address */
 static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			       struct bpf_insn *insn,
@@ -9710,48 +9786,57 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 {
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *datasec;
+	struct btf_mod_pair *btf_mod;
 	const struct btf_type *t;
 	const char *sym_name;
 	bool percpu = false;
 	u32 type, id = insn->imm;
+	struct btf *btf;
 	s32 datasec_id;
 	u64 addr;
-	int i;
-
-	if (!btf_vmlinux) {
-		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
-		return -EINVAL;
-	}
+	int i, btf_fd, err;
 
-	if (insn[1].imm != 0) {
-		verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
-		return -EINVAL;
+	btf_fd = insn[1].imm;
+	if (btf_fd) {
+		btf = btf_get_by_fd(btf_fd);
+		if (IS_ERR(btf)) {
+			verbose(env, "invalid module BTF object FD specified.\n");
+			return -EINVAL;
+		}
+	} else {
+		if (!btf_vmlinux) {
+			verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+			return -EINVAL;
+		}
+		btf = btf_vmlinux;
+		btf_get(btf);
 	}
 
-	t = btf_type_by_id(btf_vmlinux, id);
+	t = btf_type_by_id(btf, id);
 	if (!t) {
 		verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
-		return -ENOENT;
+		err = -ENOENT;
+		goto err_put;
 	}
 
 	if (!btf_type_is_var(t)) {
-		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
-			id);
-		return -EINVAL;
+		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id);
+		err = -EINVAL;
+		goto err_put;
 	}
 
-	sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+	sym_name = btf_name_by_offset(btf, t->name_off);
 	addr = kallsyms_lookup_name(sym_name);
 	if (!addr) {
 		verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
 			sym_name);
-		return -ENOENT;
+		err = -ENOENT;
+		goto err_put;
 	}
 
-	datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
-					   BTF_KIND_DATASEC);
+	datasec_id = find_btf_percpu_datasec(btf);
 	if (datasec_id > 0) {
-		datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+		datasec = btf_type_by_id(btf, datasec_id);
 		for_each_vsi(i, datasec, vsi) {
 			if (vsi->type == id) {
 				percpu = true;
@@ -9764,10 +9849,10 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 	insn[1].imm = addr >> 32;
 
 	type = t->type;
-	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+	t = btf_type_skip_modifiers(btf, type, NULL);
 	if (percpu) {
 		aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
-		aux->btf_var.btf = btf_vmlinux;
+		aux->btf_var.btf = btf;
 		aux->btf_var.btf_id = type;
 	} else if (!btf_type_is_struct(t)) {
 		const struct btf_type *ret;
@@ -9775,21 +9860,54 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 		u32 tsize;
 
 		/* resolve the type size of ksym. */
-		ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+		ret = btf_resolve_size(btf, t, &tsize);
 		if (IS_ERR(ret)) {
-			tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+			tname = btf_name_by_offset(btf, t->name_off);
 			verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
 				tname, PTR_ERR(ret));
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_put;
 		}
 		aux->btf_var.reg_type = PTR_TO_MEM;
 		aux->btf_var.mem_size = tsize;
 	} else {
 		aux->btf_var.reg_type = PTR_TO_BTF_ID;
-		aux->btf_var.btf = btf_vmlinux;
+		aux->btf_var.btf = btf;
 		aux->btf_var.btf_id = type;
 	}
+
+	/* check whether we recorded this BTF (and maybe module) already */
+	for (i = 0; i < env->used_btf_cnt; i++) {
+		if (env->used_btfs[i].btf == btf) {
+			btf_put(btf);
+			return 0;
+		}
+	}
+
+	if (env->used_btf_cnt >= MAX_USED_BTFS) {
+		err = -E2BIG;
+		goto err_put;
+	}
+
+	btf_mod = &env->used_btfs[env->used_btf_cnt];
+	btf_mod->btf = btf;
+	btf_mod->module = NULL;
+
+	/* if we reference variables from kernel module, bump its refcount */
+	if (btf_is_module(btf)) {
+		btf_mod->module = btf_try_get_module(btf);
+		if (!btf_mod->module) {
+			err = -ENXIO;
+			goto err_put;
+		}
+	}
+
+	env->used_btf_cnt++;
+
 	return 0;
+err_put:
+	btf_put(btf);
+	return err;
 }
 
 static int check_map_prealloc(struct bpf_map *map)
@@ -9936,13 +10054,6 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 			return -EINVAL;
 		}
 
-		if (BPF_CLASS(insn->code) == BPF_STX &&
-		    ((BPF_MODE(insn->code) != BPF_MEM &&
-		      BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
-			verbose(env, "BPF_STX uses reserved fields\n");
-			return -EINVAL;
-		}
-
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
 			struct bpf_insn_aux_data *aux;
 			struct bpf_map *map;
@@ -10086,6 +10197,13 @@ static void release_maps(struct bpf_verifier_env *env)
 			     env->used_map_cnt);
 }
 
+/* drop refcnt of maps used by the rejected program */
+static void release_btfs(struct bpf_verifier_env *env)
+{
+	__bpf_free_used_btfs(env->prog->aux, env->used_btfs,
+			     env->used_btf_cnt);
+}
+
 /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
 static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
 {
@@ -12098,7 +12216,10 @@ skip_full_check:
 		goto err_release_maps;
 	}
 
-	if (ret == 0 && env->used_map_cnt) {
+	if (ret)
+		goto err_release_maps;
+
+	if (env->used_map_cnt) {
 		/* if program passed verifier, update used_maps in bpf_prog_info */
 		env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
 							  sizeof(env->used_maps[0]),
@@ -12112,15 +12233,29 @@ skip_full_check:
 		memcpy(env->prog->aux->used_maps, env->used_maps,
 		       sizeof(env->used_maps[0]) * env->used_map_cnt);
 		env->prog->aux->used_map_cnt = env->used_map_cnt;
+	}
+	if (env->used_btf_cnt) {
+		/* if program passed verifier, update used_btfs in bpf_prog_aux */
+		env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt,
+							  sizeof(env->used_btfs[0]),
+							  GFP_KERNEL);
+		if (!env->prog->aux->used_btfs) {
+			ret = -ENOMEM;
+			goto err_release_maps;
+		}
 
+		memcpy(env->prog->aux->used_btfs, env->used_btfs,
+		       sizeof(env->used_btfs[0]) * env->used_btf_cnt);
+		env->prog->aux->used_btf_cnt = env->used_btf_cnt;
+	}
+	if (env->used_map_cnt || env->used_btf_cnt) {
 		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
 		 * bpf_ld_imm64 instructions
 		 */
 		convert_pseudo_ld_imm64(env);
 	}
 
-	if (ret == 0)
-		adjust_btf_func(env);
+	adjust_btf_func(env);
 
 err_release_maps:
 	if (!env->prog->aux->used_maps)
@@ -12128,6 +12263,8 @@ err_release_maps:
 		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
+	if (!env->prog->aux->used_btfs)
+		release_btfs(env);
 
 	/* extension progs temporarily inherit the attach_type of their targets
 	   for verification purposes, so set it back to zero before returning