From 555cd03193c9c098d787bec93eadfe43b179db9c Mon Sep 17 00:00:00 2001
From: David Spickett <david.spickett@linaro.org>
Date: Fri, 25 Jun 2021 14:29:12 +0100
Subject: [lldb] Correct format of qMemTags type field

The type field is a signed integer.
(https://sourceware.org/gdb/current/onlinedocs/gdb/General-Query-Packets.html)

However it's not packed in the packet in the way
you might think. For example the type -1 should be:
qMemTags:<addr>,<len>:ffffffff
Instead of:
qMemTags:<addr>,<len>:-1

This change makes lldb-server's parsing more strict
and adds more tests to check that we handle negative types
correctly in lldb and lldb-server.

We only support one tag type value at this point,
for AArch64 MTE, which is positive. So this doesn't change
any of those interactions. It just brings us in line with GDB.

Also check that the test target has MTE. Previously
we just checked that we were AArch64 with a toolchain
that supports MTE.

Finally, update the tag type check for QMemTags to use
the same conversion steps that qMemTags now does.
Using static_cast can invoke UB and though we do do a limit
check to avoid this, I think it's clearer with the new method.

Reviewed By: omjavaid

Differential Revision: https://reviews.llvm.org/D104914
---
 .../GDBRemoteCommunicationServerLLGS.cpp           | 28 ++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

(limited to 'lldb/source/Plugins/Process/gdb-remote/GDBRemoteCommunicationServerLLGS.cpp')

diff --git a/lldb/source/Plugins/Process/gdb-remote/GDBRemoteCommunicationServerLLGS.cpp b/lldb/source/Plugins/Process/gdb-remote/GDBRemoteCommunicationServerLLGS.cpp
index 5e69b57..8e1f6bc 100644
--- a/lldb/source/Plugins/Process/gdb-remote/GDBRemoteCommunicationServerLLGS.cpp
+++ b/lldb/source/Plugins/Process/gdb-remote/GDBRemoteCommunicationServerLLGS.cpp
@@ -3474,15 +3474,31 @@ GDBRemoteCommunicationServerLLGS::Handle_qMemTags(
   if (packet.GetBytesLeft() < 1 || packet.GetChar() != ':')
     return SendIllFormedResponse(packet, invalid_type_err);
 
-  int32_t type =
-      packet.GetS32(std::numeric_limits<int32_t>::max(), /*base=*/16);
-  if (type == std::numeric_limits<int32_t>::max() ||
+  // Type is a signed integer but packed into the packet as its raw bytes.
+  // However, our GetU64 uses strtoull which allows +/-. We do not want this.
+  const char *first_type_char = packet.Peek();
+  if (first_type_char && (*first_type_char == '+' || *first_type_char == '-'))
+    return SendIllFormedResponse(packet, invalid_type_err);
+
+  // Extract type as unsigned then cast to signed.
+  // Using a uint64_t here so that we have some value outside of the 32 bit
+  // range to use as the invalid return value.
+  uint64_t raw_type =
+      packet.GetU64(std::numeric_limits<uint64_t>::max(), /*base=*/16);
+
+  if ( // Make sure the cast below would be valid
+      raw_type > std::numeric_limits<uint32_t>::max() ||
       // To catch inputs like "123aardvark" that will parse but clearly aren't
       // valid in this case.
       packet.GetBytesLeft()) {
     return SendIllFormedResponse(packet, invalid_type_err);
   }
 
+  // First narrow to 32 bits otherwise the copy into type would take
+  // the wrong 4 bytes on big endian.
+  uint32_t raw_type_32 = raw_type;
+  int32_t type = reinterpret_cast<int32_t &>(raw_type_32);
+
   StreamGDBRemote response;
   std::vector<uint8_t> tags;
   Status error = m_current_process->ReadMemoryTags(type, addr, length, tags);
@@ -3552,7 +3568,11 @@ GDBRemoteCommunicationServerLLGS::Handle_QMemTags(
       packet.GetU64(std::numeric_limits<uint64_t>::max(), /*base=*/16);
   if (raw_type > std::numeric_limits<uint32_t>::max())
     return SendIllFormedResponse(packet, invalid_type_err);
-  int32_t type = static_cast<int32_t>(raw_type);
+
+  // First narrow to 32 bits. Otherwise the copy below would get the wrong
+  // 4 bytes on big endian.
+  uint32_t raw_type_32 = raw_type;
+  int32_t type = reinterpret_cast<int32_t &>(raw_type_32);
 
   // Tag data
   if (packet.GetBytesLeft() < 1 || packet.GetChar() != ':')
-- 
cgit v1.1