dep-protobuf/objectivec/GPBCodedInputStream_PackagePrivate.h
Tony Liao dd9d2ad02d [ObjC] Carry recursion depth across MessageSet item parsing (#27571)
## Summary

`GPBMessage::parseMessageSet:` reads each MessageSet item's payload bytes into
a separate buffer (because the type-id and payload tags can appear in any
order), then allocates a fresh `GPBCodedInputStream` to decode that buffer. The
fresh stream's `state_.recursionDepth` starts at `0` even when the parent
stream is already several MessageSet items deep, so a chain of nested
MessageSet items grows the native call stack without ever tripping the
documented `kDefaultRecursionLimit` (100). Other parser entry points that
recurse on the same stream (`readGroup:`, `readMessage:`, `readMapEntry:`,
`SkipToEndGroupInternal`) already increment and check `recursionDepth`; the
MessageSet path was the only spot where depth tracking did not cross the stream
boundary.

This change adds a package-private `-initWithData:parentRecursionDepth:`
initializer to `GPBCodedInputStream` that seeds the child stream's depth from
the parent's and runs `CheckRecursionLimit` before parsing begins. To prevent
memory leaks if `CheckRecursionLimit` raises an exception during
initialization, the check is wrapped in a `@try/@catch` block that releases
`self`. `parseMessageSet:` uses that initializer, so depth tracking carries
across the fresh stream. This mirrors the depth-inheritance done by the C++
`ParseContext` spawn helper.

Regression coverage: `testParseMessageSetRecursionDepthCarriedFromParent` in
`GPBWireFormatTests` builds MessageSet-of-MessageSet payloads (each layer is
`MSetMessage -> MSetMessageExtension1.recursive -> MSetMessage -> ...`, adding
2 to the recursion depth per layer). It verifies that 50 layers (depth 100,
`kDefaultRecursionLimit`) parses successfully, while 51 layers (depth 101,
`kDefaultRecursionLimit + 1`) fails with
`GPBCodedInputStreamErrorRecursionDepthExceeded`. Existing
`testErrorRecursionDepthReached` and the rest of `GPBWireFormatTests` continue
to pass unchanged.

## Test plan

- Existing ObjC test suite passes (`GPBWireFormatTests`,
  `GPBMessageTests+Serialization`, `GPBCodedInputStreamTests`,
  `GPBUnknownFieldsTest`).
- New `testParseMessageSetRecursionDepthCarriedFromParent` passes for both 50
  layers (passing at kDefaultRecursionLimit) and 51 layers (failing at
  kDefaultRecursionLimit + 1).

Closes #27571

PiperOrigin-RevId: 959041690
2026-08-04 08:41:24 -07:00

94 lines
4.3 KiB
Objective-C

// Protocol Buffers - Google's data interchange format
// Copyright 2008 Google Inc. All rights reserved.
//
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file or at
// https://developers.google.com/open-source/licenses/bsd
// This header is private to the ProtobolBuffers library and must NOT be
// included by any sources outside this library. The contents of this file are
// subject to change at any time without notice.
#import "GPBCodedInputStream.h"
#import "GPBDescriptor.h"
typedef struct GPBCodedInputStreamState {
const uint8_t *bytes;
size_t bufferSize;
size_t bufferPos;
// For parsing subsections of an input stream you can put a hard limit on
// how much should be read. Normally the limit is the end of the stream,
// but you can adjust it to anywhere, and if you hit it you will be at the
// end of the stream, until you adjust the limit.
size_t currentLimit;
int32_t lastTag;
NSUInteger recursionDepth;
} GPBCodedInputStreamState;
@interface GPBCodedInputStream () {
@package
struct GPBCodedInputStreamState state_;
NSData *buffer_;
}
// Initializes a new stream over `data` whose initial recursion depth is one
// deeper than `parentDepth`. Used when a parser needs to spawn a fresh
// CodedInputStream to decode a payload that has already been read into a
// separate buffer (e.g. MessageSet items), so that the native call stack
// growth is still bounded by kDefaultRecursionLimit. The initializer raises
// GPBCodedInputStreamErrorRecursionDepthExceeded if `parentDepth` is already
// at the limit. Mirrors the depth-inheritance done by the C++ ParseContext
// spawn helper.
- (instancetype)initWithData:(NSData *)data parentRecursionDepth:(NSUInteger)parentDepth;
// Group support is deprecated, so we hide this interface from users, but
// support for older data.
- (void)readGroup:(int32_t)fieldNumber
message:(GPBMessage *)message
extensionRegistry:(id<GPBExtensionRegistry>)extensionRegistry;
// Reads a map entry.
- (void)readMapEntry:(id)mapDictionary
extensionRegistry:(id<GPBExtensionRegistry>)extensionRegistry
field:(GPBFieldDescriptor *)field
parentMessage:(GPBMessage *)parentMessage;
@end
CF_EXTERN_C_BEGIN
void GPBRaiseStreamError(NSInteger code, NSString *reason);
int32_t GPBCodedInputStreamReadTag(GPBCodedInputStreamState *state);
double GPBCodedInputStreamReadDouble(GPBCodedInputStreamState *state);
float GPBCodedInputStreamReadFloat(GPBCodedInputStreamState *state);
uint64_t GPBCodedInputStreamReadUInt64(GPBCodedInputStreamState *state);
uint32_t GPBCodedInputStreamReadUInt32(GPBCodedInputStreamState *state);
int64_t GPBCodedInputStreamReadInt64(GPBCodedInputStreamState *state);
int32_t GPBCodedInputStreamReadInt32(GPBCodedInputStreamState *state);
uint64_t GPBCodedInputStreamReadFixed64(GPBCodedInputStreamState *state);
uint32_t GPBCodedInputStreamReadFixed32(GPBCodedInputStreamState *state);
int32_t GPBCodedInputStreamReadEnum(GPBCodedInputStreamState *state);
int32_t GPBCodedInputStreamReadSFixed32(GPBCodedInputStreamState *state);
int64_t GPBCodedInputStreamReadSFixed64(GPBCodedInputStreamState *state);
int32_t GPBCodedInputStreamReadSInt32(GPBCodedInputStreamState *state);
int64_t GPBCodedInputStreamReadSInt64(GPBCodedInputStreamState *state);
BOOL GPBCodedInputStreamReadBool(GPBCodedInputStreamState *state);
NSString *GPBCodedInputStreamReadRetainedString(GPBCodedInputStreamState *state)
__attribute((ns_returns_retained));
NSData *GPBCodedInputStreamReadRetainedBytes(GPBCodedInputStreamState *state)
__attribute((ns_returns_retained));
NSData *GPBCodedInputStreamReadRetainedBytesNoCopy(GPBCodedInputStreamState *state)
__attribute((ns_returns_retained));
NSData *GPBCodedInputStreamReadRetainedBytesToEndGroupNoCopy(GPBCodedInputStreamState *state,
int32_t fieldNumber)
__attribute((ns_returns_retained));
size_t GPBCodedInputStreamPushLimit(GPBCodedInputStreamState *state, size_t byteLimit);
void GPBCodedInputStreamPopLimit(GPBCodedInputStreamState *state, size_t oldLimit);
size_t GPBCodedInputStreamBytesUntilLimit(GPBCodedInputStreamState *state);
BOOL GPBCodedInputStreamIsAtEnd(GPBCodedInputStreamState *state);
void GPBCodedInputStreamCheckLastTagWas(GPBCodedInputStreamState *state, int32_t value);
CF_EXTERN_C_END