bpf: improve verifier ARG_CONST_SIZE_OR_ZERO semantics

For helpers, the argument type ARG_CONST_SIZE_OR_ZERO permits the
access size to be 0 when accessing the previous argument (arg).
Right now, it requires the arg needs to be NULL when size passed
is 0 or could be 0. It also requires a non-NULL arg when the size
is proved to be non-0.

This patch changes verifier ARG_CONST_SIZE_OR_ZERO behavior
such that for size-0 or possible size-0, it is not required
the arg equal to NULL.

There are a couple of reasons for this semantics change, and
all of them intends to simplify user bpf programs which
may improve user experience and/or increase chances of
verifier acceptance. Together with the next patch which
changes bpf_probe_read arg2 type from ARG_CONST_SIZE to
ARG_CONST_SIZE_OR_ZERO, the following two examples, which
fail the verifier currently, are able to get verifier acceptance.

Example 1:
   unsigned long len = pend - pstart;
   len = len > MAX_PAYLOAD_LEN ? MAX_PAYLOAD_LEN : len;
   len &= MAX_PAYLOAD_LEN;
   bpf_probe_read(data->payload, len, pstart);

It does not have test for "len > 0" and it failed the verifier.
Users may not be aware that they have to add this test.
Converting the bpf_probe_read helper to have
ARG_CONST_SIZE_OR_ZERO helps the above code get
verifier acceptance.

Example 2:
  Here is one example where llvm "messed up" the code and
  the verifier fails.

......
   unsigned long len = pend - pstart;
   if (len > 0 && len <= MAX_PAYLOAD_LEN)
     bpf_probe_read(data->payload, len, pstart);
......

The compiler generates the following code and verifier fails:
......
39: (79) r2 = *(u64 *)(r10 -16)
40: (1f) r2 -= r8
41: (bf) r1 = r2
42: (07) r1 += -1
43: (25) if r1 > 0xffe goto pc+3
  R0=inv(id=0) R1=inv(id=0,umax_value=4094,var_off=(0x0; 0xfff))
  R2=inv(id=0) R6=map_value(id=0,off=0,ks=4,vs=4095,imm=0) R7=inv(id=0)
  R8=inv(id=0) R9=inv0 R10=fp0
44: (bf) r1 = r6
45: (bf) r3 = r8
46: (85) call bpf_probe_read#45
R2 min value is negative, either use unsigned or 'var &= const'
......

The compiler optimization is correct. If r1 = 0,
r1 - 1 = 0xffffffffffffffff > 0xffe.  If r1 != 0, r1 - 1 will not wrap.
r1 > 0xffe at insn #43 can actually capture
both "r1 > 0" and "len <= MAX_PAYLOAD_LEN".
This however causes an issue in verifier as the value range of arg2
"r2" does not properly get refined and lead to verification failure.

Relaxing bpf_prog_read arg2 from ARG_CONST_SIZE to ARG_CONST_SIZE_OR_ZERO
allows the following simplied code:
   unsigned long len = pend - pstart;
   if (len <= MAX_PAYLOAD_LEN)
     bpf_probe_read(data->payload, len, pstart);

The llvm compiler will generate less complex code and the
verifier is able to verify that the program is okay.
Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/verifier.c

@@ -799,12 +799,13 @@ static int check_stack_read(struct bpf_verifier_env *env,
 
 /* check read/write into map element returned by bpf_map_lookup_elem() */
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
-			    int size)
+			      int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_map *map = regs[regno].map_ptr;
 
-	if (off < 0 || size <= 0 || off + size > map->value_size) {
+	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+	    off + size > map->value_size) {
 		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
 			map->value_size, off, size);
 		return -EACCES;
@@ -814,7 +815,7 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 
 /* check read/write into a map element with possible variable offset */
 static int check_map_access(struct bpf_verifier_env *env, u32 regno,
-			    int off, int size)
+			    int off, int size, bool zero_size_allowed)
 {
 	struct bpf_verifier_state *state = env->cur_state;
 	struct bpf_reg_state *reg = &state->regs[regno];
@@ -837,7 +838,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->smin_value + off, size);
+	err = __check_map_access(env, regno, reg->smin_value + off, size,
+				 zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d min value is outside of the array range\n",
 			regno);
@@ -853,7 +855,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 			regno);
 		return -EACCES;
 	}
-	err = __check_map_access(env, regno, reg->umax_value + off, size);
+	err = __check_map_access(env, regno, reg->umax_value + off, size,
+				 zero_size_allowed);
 	if (err)
 		verbose(env, "R%d max value is outside of the array range\n",
 			regno);
@@ -889,12 +892,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 }
 
 static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
-				 int off, int size)
+				 int off, int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
 
-	if (off < 0 || size <= 0 || (u64)off + size > reg->range) {
+	if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
+	    (u64)off + size > reg->range) {
 		verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
 			off, size, regno, reg->id, reg->off, reg->range);
 		return -EACCES;
@@ -903,7 +907,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
 }
 
 static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
-			       int size)
+			       int size, bool zero_size_allowed)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
@@ -922,7 +926,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
 			regno);
 		return -EACCES;
 	}
-	err = __check_packet_access(env, regno, off, size);
+	err = __check_packet_access(env, regno, off, size, zero_size_allowed);
 	if (err) {
 		verbose(env, "R%d offset is outside of the packet\n", regno);
 		return err;
@@ -1097,7 +1101,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			return -EACCES;
 		}
 
-		err = check_map_access(env, regno, off, size);
+		err = check_map_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 
@@ -1184,7 +1188,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				value_regno);
 			return -EACCES;
 		}
-		err = check_packet_access(env, regno, off, size);
+		err = check_packet_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
@@ -1281,7 +1285,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 	}
 	off = regs[regno].off + regs[regno].var_off.value;
 	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
-	    access_size <= 0) {
+	    access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
 		verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
 			regno, off, access_size);
 		return -EACCES;
@@ -1319,9 +1323,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	switch (reg->type) {
 	case PTR_TO_PACKET:
 	case PTR_TO_PACKET_META:
-		return check_packet_access(env, regno, reg->off, access_size);
+		return check_packet_access(env, regno, reg->off, access_size,
+					   zero_size_allowed);
 	case PTR_TO_MAP_VALUE:
-		return check_map_access(env, regno, reg->off, access_size);
+		return check_map_access(env, regno, reg->off, access_size,
+					zero_size_allowed);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
 		return check_stack_boundary(env, regno, access_size,
 					    zero_size_allowed, meta);
@@ -1415,7 +1421,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		}
 		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->key_size);
+						  meta->map_ptr->key_size,
+						  false);
 		else
 			err = check_stack_boundary(env, regno,
 						   meta->map_ptr->key_size,
@@ -1431,7 +1438,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		}
 		if (type_is_pkt_pointer(type))
 			err = check_packet_access(env, regno, reg->off,
-						  meta->map_ptr->value_size);
+						  meta->map_ptr->value_size,
+						  false);
 		else
 			err = check_stack_boundary(env, regno,
 						   meta->map_ptr->value_size,