[lldb] [gdb-remote] Extend x86 pseudo-regs to i386

[mgorny]

Add sp test.

[mgorny]

Rebase.

[mgorny]

In the new version of the patch, both 32-bit and 64-bit x86 systems are handled immediately.

lldb/source/Plugins/Process/gdb-remote/CMakeLists.txt

add_lldb_library(lldbPluginProcessGDBRemote PLUGIN
   GDBRemoteCommunicationClient.cpp
   GDBRemoteCommunicationHistory.cpp
   GDBRemoteCommunicationReplayServer.cpp
   GDBRemoteCommunicationServer.cpp
   GDBRemoteCommunicationServerCommon.cpp
   GDBRemoteCommunicationServerLLGS.cpp
   GDBRemoteCommunicationServerPlatform.cpp
   GDBRemoteRegisterContext.cpp
-  GDBRemoteRegisterContext_x86_64.cpp
+  GDBRemoteRegisterContext_x86.cpp
   ProcessGDBRemote.cpp
   ProcessGDBRemoteLog.cpp
   ThreadGDBRemote.cpp
 
   LINK_LIBS
     lldbBreakpoint
     lldbCore
     lldbDataFormatters

lldb/source/Plugins/Process/gdb-remote/GDBRemoteRegisterContext.h

public:
   GDBRemoteDynamicRegisterInfo() : DynamicRegisterInfo() {}
 
   ~GDBRemoteDynamicRegisterInfo() override = default;
 
   void HardcodeARMRegisters(bool from_scratch);
   bool UpdateARM64SVERegistersInfos(uint64_t vg);
   void Finalize(const lldb_private::ArchSpec &arch);
 
-  void PreFinalize_x86_64();
-  void PostFinalize_x86_64();
+  void PreFinalize_x86(const lldb_private::ArchSpec &arch);
+  void PostFinalize_x86();
 };
 
 class GDBRemoteRegisterContext : public RegisterContext {
 public:
   GDBRemoteRegisterContext(ThreadGDBRemote &thread, uint32_t concrete_frame_idx,
                            GDBRemoteDynamicRegisterInfoSP reg_info_sp,
                            bool read_all_at_once, bool write_all_at_once);
 

lldb/source/Plugins/Process/gdb-remote/GDBRemoteRegisterContext.cpp

//   ======   ======  ===  ===  =============     ==========      ===================  ===================  ======================  =============   ====    ==========    =============== ========= ========
   }
 }
 
 void GDBRemoteDynamicRegisterInfo::Finalize(const ArchSpec &arch) {
   if (m_finalized)
     return;
 
   switch (arch.GetMachine()) {
+  case llvm::Triple::x86:
   case llvm::Triple::x86_64:
-    PreFinalize_x86_64();
+    PreFinalize_x86(arch);
     break;
 
   default:
     break;
   }
 
   DynamicRegisterInfo::Finalize(arch);
 
   switch (arch.GetMachine()) {
+  case llvm::Triple::x86:
   case llvm::Triple::x86_64:
-    PostFinalize_x86_64();
+    PostFinalize_x86();
     break;
 
   default:
     break;
   }
 }

lldb/source/Plugins/Process/gdb-remote/GDBRemoteRegisterContext_x86.cpp

-//===-- GDBRemoteRegisterContext_x86_64.cpp -------------------------------===//
+//===-- GDBRemoteRegisterContext_x86.cpp ----------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "GDBRemoteRegisterContext.h"
static std::array<YMMReg, 16> ymm_regs = {{
     {"ymm10", "xmm10", "ymm10h"},
     {"ymm11", "xmm11", "ymm11h"},
     {"ymm12", "xmm12", "ymm12h"},
     {"ymm13", "xmm13", "ymm13h"},
     {"ymm14", "xmm14", "ymm14h"},
     {"ymm15", "xmm15", "ymm15h"},
 }};
 
-void GDBRemoteDynamicRegisterInfo::PreFinalize_x86_64() {
+void GDBRemoteDynamicRegisterInfo::PreFinalize_x86(const ArchSpec& arch) {
   uint32_t max_regnum = 0;
   uint32_t next_regindex = m_regs.size();
   for (const RegisterInfo &reg : m_regs)
     max_regnum = std::max(max_regnum, reg.kinds[eRegisterKindProcessPlugin]);
 
   ConstString group;
   group.SetCString("partial registers");
 
   for (PartialGPRRegSet &partial_regset : partial_gpr_regs) {
-    const RegisterInfo *reg64 = GetRegisterInfo(partial_regset.reg64);
-    if (!reg64)
+    const RegisterInfo *base_reg;
+    uint32_t base_size;
+    int first_subreg;
+
+    switch (arch.GetMachine()) {
+    case llvm::Triple::x86:
+      base_reg = GetRegisterInfo(partial_regset.r[0].name);
+      base_size = 4;
+      first_subreg = eRegKind16;
+      break;
+
+    case llvm::Triple::x86_64:
+      base_reg = GetRegisterInfo(partial_regset.reg64);
+      base_size = 8;
+      first_subreg = eRegKind32;
+      break;
+
+    default:
+      llvm_unreachable("unexpected arch");
+    }
+
+    if (!base_reg)
       continue;
-    assert(reg64->byte_size == 8);
+    assert(base_reg->byte_size == base_size);
 
     const RegisterInfo *reginfo[eRegKindCount];
     uint32_t regno[eRegKindCount];
 
-    for (int i = 0; i < eRegKindCount; i++) {
+    for (int i = first_subreg; i < eRegKindCount; i++) {
       if (!partial_regset.r[i].name)
         continue;
 
       reginfo[i] = GetRegisterInfo(partial_regset.r[i].name);
       if (reginfo[i])
         regno[i] = reginfo[i]->kinds[eRegisterKindProcessPlugin];
       else
         regno[i] = ++max_regnum;
     }
 
-    for (int i = 0; i < eRegKindCount; i++) {
+    for (int i = first_subreg; i < eRegKindCount; i++) {
       if (!partial_regset.r[i].name)
         continue;
 
       partial_regset.r[i].value_regs[0] =
-          reg64->kinds[eRegisterKindProcessPlugin];
+          base_reg->kinds[eRegisterKindProcessPlugin];
       partial_regset.r[i].value_regs[1] = LLDB_INVALID_REGNUM;
 
       int k = 0;
-      for (int j = 0; j < eRegKindCount; j++) {
+      for (int j = first_subreg; j < eRegKindCount; j++) {
         if (i != j && partial_regset.r[j].name)
           partial_regset.r[i].invalidate_regs[k++] = regno[j];
       }
       partial_regset.r[i].invalidate_regs[k] = LLDB_INVALID_REGNUM;
 
       struct RegisterInfo new_reg {
         partial_regset.r[i].name, nullptr, partial_gpr_sizes[i],
-            LLDB_INVALID_INDEX32, reg64->encoding, reg64->format,
+            LLDB_INVALID_INDEX32, base_reg->encoding, base_reg->format,
             {
                 LLDB_INVALID_REGNUM, LLDB_INVALID_REGNUM,
                 LLDB_INVALID_REGNUM, regno[i],
                 next_regindex++,
             },
             partial_regset.r[i].value_regs, partial_regset.r[i].invalidate_regs,
             nullptr, 0
       };
for (YMMReg &ymmreg : ymm_regs) {
 
     ConstString name;
     ConstString alt_name;
     name.SetCString(new_reg.name);
     AddRegister(new_reg, name, alt_name, group);
   }
 }
 
-void GDBRemoteDynamicRegisterInfo::PostFinalize_x86_64() {
+void GDBRemoteDynamicRegisterInfo::PostFinalize_x86() {
   for (PartialGPRRegSet &partial_regset : partial_gpr_regs) {
     if (!partial_regset.r[eRegKind8h].name)
       continue;
 
     llvm::StringRef reg8h_name = partial_regset.r[eRegKind8h].name;
     const RegisterInfo *reg8h = GetRegisterInfo(reg8h_name);
     const RegisterInfo *reg8l =
         GetRegisterInfo(partial_regset.r[eRegKind8l].name);

lldb/test/API/functionalities/gdb_remote_client/TestGDBServerTargetXML.py

def test_i386_regs(self):
         self.match("register read esp",
                    ["esp = 0x44434241"])
         self.match("register read eip",
                    ["eip = 0x84838281"])
 
         # test generic aliases
         self.match("register read fp",
                    ["ebp = 0x54535251"])
+        self.match("register read sp",
+                   ["esp = 0x44434241"])
         self.match("register read pc",
                    ["eip = 0x84838281"])
         self.match("register read flags",
                    ["eflags = 0x94939291"])
 
+        # test pseudo-registers
+        self.match("register read cx",
+                   ["cx = 0x1211"])
+        self.match("register read ch",
+                   ["ch = 0x12"])
+        self.match("register read cl",
+                   ["cl = 0x11"])
+        self.match("register read mm0",
+                   ["mm0 = 0x0807060504030201"])
+        self.match("register read mm1",
+                   ["mm1 = 0x1817161514131211"])
+
+        # both stX and xmmX should be displayed as vectors
+        self.match("register read st0",
+                   ["st0 = {0x01 0x02 0x03 0x04 0x05 0x06 0x07 0x08 0x09 0x0a}"])
+        self.match("register read st1",
+                   ["st1 = {0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a}"])
+        self.match("register read xmm0",
+                   ["xmm0 = {0x81 0x82 0x83 0x84 0x85 0x86 0x87 0x88 "
+                    "0x89 0x8a 0x8b 0x8c 0x8d 0x8e 0x8f 0x90}"])
+        self.match("register read xmm1",
+                   ["xmm1 = {0x91 0x92 0x93 0x94 0x95 0x96 0x97 0x98 "
+                    "0x99 0x9a 0x9b 0x9c 0x9d 0x9e 0x9f 0xa0}"])
+
+        # test recombining ymmX
+        self.match("register read ymm0h",
+                   ["ymm0h = {0xb1 0xb2 0xb3 0xb4 0xb5 0xb6 0xb7 0xb8 "
+                    "0xb9 0xba 0xbb 0xbc 0xbd 0xbe 0xbf 0xc0}"])
+        self.match("register read ymm0",
+                   ["ymm0 = {0x81 0x82 0x83 0x84 0x85 0x86 0x87 0x88 0x89 0x8a "
+                    "0x8b 0x8c 0x8d 0x8e 0x8f 0x90 0xb1 0xb2 0xb3 0xb4 0xb5 "
+                    "0xb6 0xb7 0xb8 0xb9 0xba 0xbb 0xbc 0xbd 0xbe 0xbf 0xc0}"])
+        self.match("register read ymm1h",
+                   ["ymm1h = {0xc1 0xc2 0xc3 0xc4 0xc5 0xc6 0xc7 0xc8 "
+                    "0xc9 0xca 0xcb 0xcc 0xcd 0xce 0xcf 0xd0}"])
+        self.match("register read ymm1",
+                   ["ymm1 = {0x91 0x92 0x93 0x94 0x95 0x96 0x97 0x98 0x99 0x9a "
+                    "0x9b 0x9c 0x9d 0x9e 0x9f 0xa0 0xc1 0xc2 0xc3 0xc4 0xc5 "
+                    "0xc6 0xc7 0xc8 0xc9 0xca 0xcb 0xcc 0xcd 0xce 0xcf 0xd0}"])
+
+        # test writing into pseudo-registers
+        self.runCmd("register write cx 0xfbfa")
+        reg_data[1] = "fafb1314"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read ecx",
+                   ["ecx = 0x1413fbfa"])
+
+        self.runCmd("register write ch 0xf9")
+        reg_data[1] = "faf91314"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read cx",
+                   ["cx = 0xf9fa"])
+        self.match("register read ecx",
+                   ["ecx = 0x1413f9fa"])
+
+        self.runCmd("register write cl 0xf8")
+        reg_data[1] = "f8f91314"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read cx",
+                   ["cx = 0xf9f8"])
+        self.match("register read ecx",
+                   ["ecx = 0x1413f9f8"])
+
+        self.runCmd("register write mm0 0xfffefdfcfbfaf9f8")
+        reg_data[10] = "f8f9fafbfcfdfeff090a"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read st0",
+                   ["st0 = {0xf8 0xf9 0xfa 0xfb 0xfc 0xfd 0xfe 0xff 0x09 0x0a}"])
+
+        self.runCmd("register write xmm0 \"{0xff 0xfe 0xfd 0xfc 0xfb 0xfa 0xf9 "
+                    "0xf8 0xf7 0xf6 0xf5 0xf4 0xf3 0xf2 0xf1 0xf0}\"")
+        reg_data[18] = "fffefdfcfbfaf9f8f7f6f5f4f3f2f1f0"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read ymm0",
+                   ["ymm0 = {0xff 0xfe 0xfd 0xfc 0xfb 0xfa 0xf9 0xf8 0xf7 0xf6 "
+                    "0xf5 0xf4 0xf3 0xf2 0xf1 0xf0 0xb1 0xb2 0xb3 0xb4 0xb5 "
+                    "0xb6 0xb7 0xb8 0xb9 0xba 0xbb 0xbc 0xbd 0xbe 0xbf 0xc0}"])
+
+        self.runCmd("register write ymm0h \"{0xef 0xee 0xed 0xec 0xeb 0xea 0xe9 "
+                    "0xe8 0xe7 0xe6 0xe5 0xe4 0xe3 0xe2 0xe1 0xe0}\"")
+        reg_data[27] = "efeeedecebeae9e8e7e6e5e4e3e2e1e0"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read ymm0",
+                   ["ymm0 = {0xff 0xfe 0xfd 0xfc 0xfb 0xfa 0xf9 0xf8 0xf7 0xf6 "
+                    "0xf5 0xf4 0xf3 0xf2 0xf1 0xf0 0xef 0xee 0xed 0xec 0xeb "
+                    "0xea 0xe9 0xe8 0xe7 0xe6 0xe5 0xe4 0xe3 0xe2 0xe1 0xe0}"])
+
+        self.runCmd("register write ymm0 \"{0xd0 0xd1 0xd2 0xd3 0xd4 0xd5 0xd6 "
+                    "0xd7 0xd8 0xd9 0xda 0xdb 0xdc 0xdd 0xde 0xdf 0xe0 0xe1 "
+                    "0xe2 0xe3 0xe4 0xe5 0xe6 0xe7 0xe8 0xe9 0xea 0xeb 0xec "
+                    "0xed 0xee 0xef}\"")
+        reg_data[18] = "d0d1d2d3d4d5d6d7d8d9dadbdcdddedf"
+        reg_data[27] = "e0e1e2e3e4e5e6e7e8e9eaebecedeeef"
+        self.assertPacketLogContains(["G" + "".join(reg_data)])
+        self.match("register read ymm0",
+                   ["ymm0 = {0xd0 0xd1 0xd2 0xd3 0xd4 0xd5 0xd6 0xd7 0xd8 0xd9 "
+                    "0xda 0xdb 0xdc 0xdd 0xde 0xdf 0xe0 0xe1 0xe2 0xe3 0xe4 "
+                    "0xe5 0xe6 0xe7 0xe8 0xe9 0xea 0xeb 0xec 0xed 0xee 0xef}"])
+
     @skipIfXmlSupportMissing
     @skipIfRemote
     def test_aarch64_regs(self):
         """Test grabbing various aarch64 registers from gdbserver."""
         reg_data = [
             "0102030405060708",  # x0
             "1112131415161718",  # x1
         ] + 27 * [