1 files changed, 163 insertions, 63 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 99a7e5b388f2..cdc43b899f28 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19,6 +19,7 @@
 #include <net/netlink.h>
 #include <linux/file.h>
 #include <linux/vmalloc.h>
+#include <linux/stringify.h>
 
 /* bpf_check() is a static code analyzer that walks eBPF program
  * instruction by instruction and updates register/stack state.
@@ -190,6 +191,22 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_PACKET_END]	= "pkt_end",
 };
 
+#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x)
+static const char * const func_id_str[] = {
+	__BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN)
+};
+#undef __BPF_FUNC_STR_FN
+
+static const char *func_id_name(int id)
+{
+	BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
+
+	if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
+		return func_id_str[id];
+	else
+		return "unknown";
+}
+
 static void print_verifier_state(struct bpf_verifier_state *state)
 {
 	struct bpf_reg_state *reg;
@@ -212,12 +229,13 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE ||
 			 t == PTR_TO_MAP_VALUE_OR_NULL ||
 			 t == PTR_TO_MAP_VALUE_ADJ)
-			verbose("(ks=%d,vs=%d)",
+			verbose("(ks=%d,vs=%d,id=%u)",
 				reg->map_ptr->key_size,
-				reg->map_ptr->value_size);
+				reg->map_ptr->value_size,
+				reg->id);
 		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
-			verbose(",min_value=%llu",
-				(unsigned long long)reg->min_value);
+			verbose(",min_value=%lld",
+				(long long)reg->min_value);
 		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
 			verbose(",max_value=%llu",
 				(unsigned long long)reg->max_value);
@@ -353,7 +371,8 @@ static void print_bpf_insn(struct bpf_insn *insn)
 		u8 opcode = BPF_OP(insn->code);
 
 		if (opcode == BPF_CALL) {
-			verbose("(%02x) call %d\n", insn->code, insn->imm);
+			verbose("(%02x) call %s#%d\n", insn->code,
+				func_id_name(insn->imm), insn->imm);
 		} else if (insn->code == (BPF_JMP | BPF_JA)) {
 			verbose("(%02x) goto pc%+d\n",
 				insn->code, insn->off);
@@ -443,13 +462,19 @@ static void init_reg_state(struct bpf_reg_state *regs)
 	regs[BPF_REG_1].type = PTR_TO_CTX;
 }
 
-static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
 {
-	BUG_ON(regno >= MAX_BPF_REG);
 	regs[regno].type = UNKNOWN_VALUE;
+	regs[regno].id = 0;
 	regs[regno].imm = 0;
 }
 
+static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+{
+	BUG_ON(regno >= MAX_BPF_REG);
+	__mark_reg_unknown_value(regs, regno);
+}
+
 static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
@@ -613,12 +638,19 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 #define MAX_PACKET_OFF 0xffff
 
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
-				       const struct bpf_call_arg_meta *meta)
+				       const struct bpf_call_arg_meta *meta,
+				       enum bpf_access_type t)
 {
 	switch (env->prog->type) {
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+		/* dst_input() and dst_output() can't write for now */
+		if (t == BPF_WRITE)
+			return false;
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
 	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_LWT_XMIT:
 		if (meta)
 			return meta->pkt_access;
 
@@ -758,7 +790,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 			 * index'es we need to make sure that whatever we use
 			 * will have a set floor within our range.
 			 */
-			if ((s64)reg->min_value < 0) {
+			if (reg->min_value < 0) {
 				verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
 					regno);
 				return -EACCES;
@@ -817,7 +849,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 			err = check_stack_read(state, off, size, value_regno);
 		}
 	} else if (state->regs[regno].type == PTR_TO_PACKET) {
-		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL)) {
+		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
 			verbose("cannot write into packet\n");
 			return -EACCES;
 		}
@@ -950,7 +982,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		return 0;
 	}
 
-	if (type == PTR_TO_PACKET && !may_access_direct_pkt_data(env, meta)) {
+	if (type == PTR_TO_PACKET &&
+	    !may_access_direct_pkt_data(env, meta, BPF_READ)) {
 		verbose("helper access to the packet is not allowed\n");
 		return -EACCES;
 	}
@@ -1112,8 +1145,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 
 	return 0;
 error:
-	verbose("cannot pass map_type %d into func %d\n",
-		map->map_type, func_id);
+	verbose("cannot pass map_type %d into func %s#%d\n",
+		map->map_type, func_id_name(func_id), func_id);
 	return -EINVAL;
 }
 
@@ -1170,7 +1203,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 
 	/* find function prototype */
 	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
-		verbose("invalid func %d\n", func_id);
+		verbose("invalid func %s#%d\n", func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
@@ -1178,7 +1211,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 		fn = env->prog->aux->ops->get_func_proto(func_id);
 
 	if (!fn) {
-		verbose("unknown func %d\n", func_id);
+		verbose("unknown func %s#%d\n", func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
@@ -1188,7 +1221,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 		return -EINVAL;
 	}
 
-	changes_data = bpf_helper_changes_skb_data(fn->func);
+	changes_data = bpf_helper_changes_pkt_data(fn->func);
 
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
@@ -1198,7 +1231,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 	 */
 	err = check_raw_mode(fn);
 	if (err) {
-		verbose("kernel subsystem misconfigured func %d\n", func_id);
+		verbose("kernel subsystem misconfigured func %s#%d\n",
+			func_id_name(func_id), func_id);
 		return err;
 	}
 
@@ -1252,9 +1286,10 @@ static int check_call(struct bpf_verifier_env *env, int func_id)
 			return -EINVAL;
 		}
 		regs[BPF_REG_0].map_ptr = meta.map_ptr;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else {
-		verbose("unknown return type %d of func %d\n",
-			fn->ret_type, func_id);
+		verbose("unknown return type %d of func %s#%d\n",
+			fn->ret_type, func_id_name(func_id), func_id);
 		return -EINVAL;
 	}
 
@@ -1451,14 +1486,19 @@ static int evaluate_reg_imm_alu(struct bpf_verifier_env *env,
 	struct bpf_reg_state *src_reg = &regs[insn->src_reg];
 	u8 opcode = BPF_OP(insn->code);
 
-	/* dst_reg->type == CONST_IMM here, simulate execution of 'add' insn.
-	 * Don't care about overflow or negative values, just add them
+	/* dst_reg->type == CONST_IMM here, simulate execution of 'add'/'or'
+	 * insn. Don't care about overflow or negative values, just add them
 	 */
 	if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_K)
 		dst_reg->imm += insn->imm;
 	else if (opcode == BPF_ADD && BPF_SRC(insn->code) == BPF_X &&
 		 src_reg->type == CONST_IMM)
 		dst_reg->imm += src_reg->imm;
+	else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_K)
+		dst_reg->imm |= insn->imm;
+	else if (opcode == BPF_OR && BPF_SRC(insn->code) == BPF_X &&
+		 src_reg->type == CONST_IMM)
+		dst_reg->imm |= src_reg->imm;
 	else
 		mark_reg_unknown_value(regs, insn->dst_reg);
 	return 0;
@@ -1468,7 +1508,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
 {
 	if (reg->max_value > BPF_REGISTER_MAX_RANGE)
 		reg->max_value = BPF_REGISTER_MAX_RANGE;
-	if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE)
+	if (reg->min_value < BPF_REGISTER_MIN_RANGE ||
+	    reg->min_value > BPF_REGISTER_MAX_RANGE)
 		reg->min_value = BPF_REGISTER_MIN_RANGE;
 }
 
@@ -1476,8 +1517,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				    struct bpf_insn *insn)
 {
 	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
-	u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE;
-	bool min_set = false, max_set = false;
+	s64 min_val = BPF_REGISTER_MIN_RANGE;
+	u64 max_val = BPF_REGISTER_MAX_RANGE;
 	u8 opcode = BPF_OP(insn->code);
 
 	dst_reg = &regs[insn->dst_reg];
@@ -1500,7 +1541,6 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
 		   (s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
 		min_val = max_val = insn->imm;
-		min_set = max_set = true;
 	}
 
 	/* We don't know anything about what was done to this register, mark it
@@ -1512,22 +1552,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		return;
 	}
 
+	/* If one of our values was at the end of our ranges then we can't just
+	 * do our normal operations to the register, we need to set the values
+	 * to the min/max since they are undefined.
+	 */
+	if (min_val == BPF_REGISTER_MIN_RANGE)
+		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+	if (max_val == BPF_REGISTER_MAX_RANGE)
+		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+
 	switch (opcode) {
 	case BPF_ADD:
-		dst_reg->min_value += min_val;
-		dst_reg->max_value += max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value += min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value += max_val;
 		break;
 	case BPF_SUB:
-		dst_reg->min_value -= min_val;
-		dst_reg->max_value -= max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value -= min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value -= max_val;
 		break;
 	case BPF_MUL:
-		dst_reg->min_value *= min_val;
-		dst_reg->max_value *= max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value *= min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value *= max_val;
 		break;
 	case BPF_AND:
-		/* & is special since it could end up with 0 bits set. */
-		dst_reg->min_value &= min_val;
+		/* Disallow AND'ing of negative numbers, ain't nobody got time
+		 * for that.  Otherwise the minimum is 0 and the max is the max
+		 * value we could AND against.
+		 */
+		if (min_val < 0)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		else
+			dst_reg->min_value = 0;
 		dst_reg->max_value = max_val;
 		break;
 	case BPF_LSH:
@@ -1537,24 +1598,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		 */
 		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else
+		else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value <<= min_val;
 
 		if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
-		else
+		else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value <<= max_val;
 		break;
 	case BPF_RSH:
-		dst_reg->min_value >>= min_val;
-		dst_reg->max_value >>= max_val;
-		break;
-	case BPF_MOD:
-		/* % is special since it is an unsigned modulus, so the floor
-		 * will always be 0.
+		/* RSH by a negative number is undefined, and the BPF_RSH is an
+		 * unsigned shift, so make the appropriate casts.
 		 */
-		dst_reg->min_value = 0;
-		dst_reg->max_value = max_val - 1;
+		if (min_val < 0 || dst_reg->min_value < 0)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		else
+			dst_reg->min_value =
+				(u64)(dst_reg->min_value) >> min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value >>= max_val;
 		break;
 	default:
 		reset_reg_range_values(regs, insn->dst_reg);
@@ -1644,8 +1706,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 						insn->src_reg);
 					return -EACCES;
 				}
-				regs[insn->dst_reg].type = UNKNOWN_VALUE;
-				regs[insn->dst_reg].map_ptr = NULL;
+				mark_reg_unknown_value(regs, insn->dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -1907,6 +1968,43 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 	check_reg_overflow(true_reg);
 }
 
+static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
+			 enum bpf_reg_type type)
+{
+	struct bpf_reg_state *reg = &regs[regno];
+
+	if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
+		reg->type = type;
+		/* We don't need id from this point onwards anymore, thus we
+		 * should better reset it, so that state pruning has chances
+		 * to take effect.
+		 */
+		reg->id = 0;
+		if (type == UNKNOWN_VALUE)
+			__mark_reg_unknown_value(regs, regno);
+	}
+}
+
+/* The logic is similar to find_good_pkt_pointers(), both could eventually
+ * be folded together at some point.
+ */
+static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
+			  enum bpf_reg_type type)
+{
+	struct bpf_reg_state *regs = state->regs;
+	u32 id = regs[regno].id;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		mark_map_reg(regs, i, id, type);
+
+	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
+		if (state->stack_slot_type[i] != STACK_SPILL)
+			continue;
+		mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type);
+	}
+}
+
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			     struct bpf_insn *insn, int *insn_idx)
 {
@@ -1994,18 +2092,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	if (BPF_SRC(insn->code) == BPF_K &&
 	    insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
 	    dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
-		if (opcode == BPF_JEQ) {
-			/* next fallthrough insn can access memory via
-			 * this register
-			 */
-			regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			/* branch targer cannot access it, since reg == 0 */
-			mark_reg_unknown_value(other_branch->regs,
-					       insn->dst_reg);
-		} else {
-			other_branch->regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-			mark_reg_unknown_value(regs, insn->dst_reg);
-		}
+		/* Mark all identical map registers in each branch as either
+		 * safe or unknown depending R == 0 or R != 0 conditional.
+		 */
+		mark_map_regs(this_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? PTR_TO_MAP_VALUE : UNKNOWN_VALUE);
+		mark_map_regs(other_branch, insn->dst_reg,
+			      opcode == BPF_JEQ ? UNKNOWN_VALUE : PTR_TO_MAP_VALUE);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
@@ -2430,6 +2523,7 @@ static bool states_equal(struct bpf_verifier_env *env,
 			 struct bpf_verifier_state *old,
 			 struct bpf_verifier_state *cur)
 {
+	bool varlen_map_access = env->varlen_map_value_access;
 	struct bpf_reg_state *rold, *rcur;
 	int i;
 
@@ -2443,12 +2537,17 @@ static bool states_equal(struct bpf_verifier_env *env,
 		/* If the ranges were not the same, but everything else was and
 		 * we didn't do a variable access into a map then we are a-ok.
 		 */
-		if (!env->varlen_map_value_access &&
-		    rold->type == rcur->type && rold->imm == rcur->imm)
+		if (!varlen_map_access &&
+		    memcmp(rold, rcur, offsetofend(struct bpf_reg_state, id)) == 0)
 			continue;
 
+		/* If we didn't map access then again we don't care about the
+		 * mismatched range values and it's ok if our old type was
+		 * UNKNOWN and we didn't go to a NOT_INIT'ed reg.
+		 */
 		if (rold->type == NOT_INIT ||
-		    (rold->type == UNKNOWN_VALUE && rcur->type != NOT_INIT))
+		    (!varlen_map_access && rold->type == UNKNOWN_VALUE &&
+		     rcur->type != NOT_INIT))
 			continue;
 
 		if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET &&
@@ -2837,6 +2936,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 	int insn_cnt = env->prog->len;
 	int i, j, err;
 
+	err = bpf_prog_calc_tag(env->prog);
+	if (err)
+		return err;
+
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		if (BPF_CLASS(insn->code) == BPF_LDX &&
 		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
@@ -3044,9 +3147,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	struct bpf_verifier_env *env;
 	int ret = -EINVAL;
 
-	if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS)
-		return -E2BIG;
-
 	/* 'struct bpf_verifier_env' can be global, but since it's not small,
 	 * allocate/free it every time bpf_check() is called
 	 */