[lldb] Unwind through ARM Cortex-M exceptions automatically (#153922)

lldb/include/lldb/Core/Architecture.h

@@ -12,6 +12,7 @@
 #include "lldb/Core/PluginInterface.h"
 #include "lldb/Target/DynamicRegisterInfo.h"
 #include "lldb/Target/MemoryTagManager.h"
+#include "lldb/Target/RegisterContextUnwind.h"
 
 namespace lldb_private {
 
@@ -129,6 +130,14 @@ class Architecture : public PluginInterface {
                                        RegisterContext &reg_context) const {
     return false;
   }
+
+  /// Return an UnwindPlan that allows architecture-defined rules for finding
+  /// saved registers, given a particular set of register values.
+  virtual lldb::UnwindPlanSP GetArchitectureUnwindPlan(
+      lldb_private::Thread &thread, lldb_private::RegisterContextUnwind *regctx,
+      std::shared_ptr<const UnwindPlan> current_unwindplan) {
+    return lldb::UnwindPlanSP();
+  }
 };
 
 } // namespace lldb_private

lldb/include/lldb/Target/RegisterContextUnwind.h

@@ -21,6 +21,7 @@
 namespace lldb_private {
 
 class UnwindLLDB;
+class ArchitectureArm;
 
 class RegisterContextUnwind : public lldb_private::RegisterContext {
 public:
@@ -72,6 +73,25 @@ class RegisterContextUnwind : public lldb_private::RegisterContext {
   // above asynchronous trap handlers (sigtramp) for instance.
   bool BehavesLikeZerothFrame() const override;
 
+protected:
+  // Provide a location for where THIS function saved the CALLER's register
+  // value, or a frame "below" this one saved it. That is, this function doesn't
+  // modify the register, it may call a function that does & saved it to stack.
+  //
+  // The ConcreteRegisterLocation type may be set to eRegisterNotAvailable --
+  // this will happen for a volatile register being queried mid-stack.  Instead
+  // of floating frame 0's contents of that register up the stack (which may or
+  // may not be the value of that reg when the function was executing), we won't
+  // return any value.
+  //
+  // If a non-volatile register (a "preserved" register, a callee-preserved
+  // register) is requested mid-stack, and no frames "below" the requested stack
+  // have saved the register anywhere, it is safe to assume that frame 0's
+  // register value is the same.
+  lldb_private::UnwindLLDB::RegisterSearchResult SavedLocationForRegister(
+      uint32_t lldb_regnum,
+      lldb_private::UnwindLLDB::ConcreteRegisterLocation &regloc);
+
 private:
   enum FrameType {
     eNormalFrame,
@@ -86,6 +106,8 @@ class RegisterContextUnwind : public lldb_private::RegisterContext {
 
   // UnwindLLDB needs to pass around references to ConcreteRegisterLocations
   friend class UnwindLLDB;
+  // Architecture may need to retrieve caller register values from this frame
+  friend class ArchitectureArm;
 
   // Returns true if we have an unwind loop -- the same stack frame unwinding
   // multiple times.
@@ -130,27 +152,6 @@ class RegisterContextUnwind : public lldb_private::RegisterContext {
   void PropagateTrapHandlerFlagFromUnwindPlan(
       std::shared_ptr<const UnwindPlan> unwind_plan);
 
-  // Provide a location for where THIS function saved the CALLER's register
-  // value
-  // Or a frame "below" this one saved it, i.e. a function called by this one,
-  // preserved a register that this
-  // function didn't modify/use.
-  //
-  // The ConcreteRegisterLocation type may be set to eRegisterNotAvailable --
-  // this will happen for a volatile register being queried mid-stack.  Instead
-  // of floating frame 0's contents of that register up the stack (which may or
-  // may not be the value of that reg when the function was executing), we won't
-  // return any value.
-  //
-  // If a non-volatile register (a "preserved" register) is requested mid-stack
-  // and no frames "below" the requested
-  // stack have saved the register anywhere, it is safe to assume that frame 0's
-  // register values are still the same
-  // as the requesting frame's.
-  lldb_private::UnwindLLDB::RegisterSearchResult SavedLocationForRegister(
-      uint32_t lldb_regnum,
-      lldb_private::UnwindLLDB::ConcreteRegisterLocation &regloc);
-
   std::optional<UnwindPlan::Row::AbstractRegisterLocation>
   GetAbstractRegisterLocation(uint32_t lldb_regnum, lldb::RegisterKind &kind);
 
@@ -202,6 +203,8 @@ class RegisterContextUnwind : public lldb_private::RegisterContext {
 
   std::shared_ptr<const UnwindPlan> GetFullUnwindPlanForFrame();
 
+  lldb::UnwindPlanSP TryAdoptArchitectureUnwindPlan();
+
   void UnwindLogMsg(const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 
   void UnwindLogMsgVerbose(const char *fmt, ...)

lldb/include/lldb/Target/UnwindLLDB.h

@@ -22,6 +22,7 @@
 namespace lldb_private {
 
 class RegisterContextUnwind;
+class ArchitectureArm;
 
 class UnwindLLDB : public lldb_private::Unwind {
 public:
@@ -37,6 +38,7 @@ class UnwindLLDB : public lldb_private::Unwind {
 
 protected:
   friend class lldb_private::RegisterContextUnwind;
+  friend class lldb_private::ArchitectureArm;
 
   /// An UnwindPlan::Row::AbstractRegisterLocation, combined with the register
   /// context and memory for a specific stop point, is used to create a

lldb/source/Plugins/ABI/ARM/ABISysV_arm.cpp

@@ -1921,6 +1921,13 @@ UnwindPlanSP ABISysV_arm::CreateFunctionEntryUnwindPlan() {
 
 UnwindPlanSP ABISysV_arm::CreateDefaultUnwindPlan() {
   // TODO: Handle thumb
+  // If we had a Target argument, could at least check
+  // target.GetArchitecture().GetTriple().isArmMClass()
+  // which is always thumb.
+  // To handle thumb properly, we'd need to fetch the current
+  // CPSR state at unwind time to tell if the processor is
+  // in thumb mode in this stack frame.  There's no way to
+  // express something like that in an UnwindPlan today.
   uint32_t fp_reg_num = dwarf_r11;
   uint32_t pc_reg_num = dwarf_pc;
 

lldb/source/Plugins/Architecture/Arm/ArchitectureArm.cpp

@@ -9,10 +9,18 @@
 #include "Plugins/Architecture/Arm/ArchitectureArm.h"
 #include "Plugins/Process/Utility/ARMDefines.h"
 #include "Plugins/Process/Utility/InstructionUtils.h"
+#include "Utility/ARM_DWARF_Registers.h"
 #include "lldb/Core/PluginManager.h"
+#include "lldb/Symbol/UnwindPlan.h"
+#include "lldb/Target/Process.h"
 #include "lldb/Target/RegisterContext.h"
+#include "lldb/Target/RegisterNumber.h"
 #include "lldb/Target/Thread.h"
+#include "lldb/Target/UnwindLLDB.h"
 #include "lldb/Utility/ArchSpec.h"
+#include "lldb/Utility/LLDBLog.h"
+#include "lldb/Utility/Log.h"
+#include "lldb/Utility/RegisterValue.h"
 
 using namespace lldb_private;
 using namespace lldb;
@@ -150,3 +158,181 @@ addr_t ArchitectureArm::GetOpcodeLoadAddress(addr_t opcode_addr,
   }
   return opcode_addr & ~(1ull);
 }
+
+// The ARM M-Profile Armv7-M Architecture Reference Manual,
+// subsection "B1.5 Armv7-M exception model", see the parts
+// describing "Exception entry behavior" and "Exception
+// return behavior".
+// When an exception happens on this processor, certain registers are
+// saved below the stack pointer, the stack pointer is decremented,
+// a special value is put in the link register to indicate the
+// exception has been taken, and an exception handler function
+// is invoked.
+//
+// Detect that special value in $lr, and if present, add
+// unwind rules for the registers that were saved above this
+// stack frame's CFA.  Overwrite any register locations that
+// the current_unwindplan has for these registers; they are
+// not correct when we're invoked this way.
+UnwindPlanSP ArchitectureArm::GetArchitectureUnwindPlan(
+    Thread &thread, RegisterContextUnwind *regctx,
+    std::shared_ptr<const UnwindPlan> current_unwindplan) {
+
+  ProcessSP process_sp = thread.GetProcess();
+  if (!process_sp)
+    return {};
+
+  const ArchSpec arch = process_sp->GetTarget().GetArchitecture();
+  if (!arch.GetTriple().isArmMClass() || arch.GetAddressByteSize() != 4)
+    return {};
+
+  // Get the caller's LR value from regctx (the LR value
+  // at function entry to this function).
+  RegisterNumber ra_regnum(thread, eRegisterKindGeneric,
+                           LLDB_REGNUM_GENERIC_RA);
+  uint32_t ra_regnum_lldb = ra_regnum.GetAsKind(eRegisterKindLLDB);
+
+  if (ra_regnum_lldb == LLDB_INVALID_REGNUM)
+    return {};
+
+  UnwindLLDB::ConcreteRegisterLocation regloc = {};
+  bool got_concrete_location = false;
+  if (regctx->SavedLocationForRegister(ra_regnum_lldb, regloc) ==
+      UnwindLLDB::RegisterSearchResult::eRegisterFound) {
+    got_concrete_location = true;
+  } else {
+    RegisterNumber pc_regnum(thread, eRegisterKindGeneric,
+                             LLDB_REGNUM_GENERIC_PC);
+    uint32_t pc_regnum_lldb = pc_regnum.GetAsKind(eRegisterKindLLDB);
+    if (regctx->SavedLocationForRegister(pc_regnum_lldb, regloc) ==
+        UnwindLLDB::RegisterSearchResult::eRegisterFound)
+      got_concrete_location = true;
+  }
+
+  if (!got_concrete_location)
+    return {};
+
+  addr_t callers_return_address = LLDB_INVALID_ADDRESS;
+  const RegisterInfo *reg_info = regctx->GetRegisterInfoAtIndex(ra_regnum_lldb);
+  if (reg_info) {
+    RegisterValue reg_value;
+    if (regctx->ReadRegisterValueFromRegisterLocation(regloc, reg_info,
+                                                      reg_value)) {
+      callers_return_address = reg_value.GetAsUInt32();
+    }
+  }
+
+  if (callers_return_address == LLDB_INVALID_ADDRESS)
+    return {};
+
+  // ARMv7-M ARM says that the LR will be set to
+  // one of these values when an exception has taken
+  // place:
+  //    if HaveFPExt() then
+  //      if CurrentMode==Mode_Handler then
+  //        LR = Ones(27):NOT(CONTROL.FPCA):'0001';
+  //      else
+  //        LR = Ones(27):NOT(CONTROL.FPCA):'1':CONTROL.SPSEL:'01';
+  //    else
+  //      if CurrentMode==Mode_Handler then
+  //        LR = Ones(28):'0001';
+  //      else
+  //        LR = Ones(29):CONTROL.SPSEL:'01';
+
+  // Top 27 bits are set for an exception return.
+  const uint32_t exception_return = -1U & ~0b11111U;
+  // Bit4 is 1 if only GPRs were saved.
+  const uint32_t gprs_only = 0b10000;
+  // Bit<1:0> are '01'.
+  const uint32_t lowbits = 0b01;
+
+  if ((callers_return_address & exception_return) != exception_return)
+    return {};
+  if ((callers_return_address & lowbits) != lowbits)
+    return {};
+
+  const bool fp_regs_saved = !(callers_return_address & gprs_only);
+
+  const RegisterKind plan_regkind = current_unwindplan->GetRegisterKind();
+  UnwindPlanSP new_plan = std::make_shared<UnwindPlan>(plan_regkind);
+  new_plan->SetSourceName("Arm Cortex-M exception return UnwindPlan");
+  new_plan->SetSourcedFromCompiler(eLazyBoolNo);
+  new_plan->SetUnwindPlanValidAtAllInstructions(eLazyBoolYes);
+  new_plan->SetUnwindPlanForSignalTrap(eLazyBoolYes);
+
+  int stored_regs_size = fp_regs_saved ? 0x68 : 0x20;
+
+  uint32_t gpr_regs[] = {dwarf_r0,  dwarf_r1, dwarf_r2, dwarf_r3,
+                         dwarf_r12, dwarf_lr, dwarf_pc, dwarf_cpsr};
+  const int gpr_reg_count = std::size(gpr_regs);
+  uint32_t fpr_regs[] = {dwarf_s0,  dwarf_s1,  dwarf_s2,  dwarf_s3,
+                         dwarf_s4,  dwarf_s5,  dwarf_s6,  dwarf_s7,
+                         dwarf_s8,  dwarf_s9,  dwarf_s10, dwarf_s11,
+                         dwarf_s12, dwarf_s13, dwarf_s14, dwarf_s15};
+  const int fpr_reg_count = std::size(fpr_regs);
+
+  RegisterContextSP reg_ctx_sp = thread.GetRegisterContext();
+  std::vector<uint32_t> saved_regs;
+  for (int i = 0; i < gpr_reg_count; i++) {
+    uint32_t regno = gpr_regs[i];
+    reg_ctx_sp->ConvertBetweenRegisterKinds(eRegisterKindDWARF, gpr_regs[i],
+                                            plan_regkind, regno);
+    saved_regs.push_back(regno);
+  }
+  if (fp_regs_saved) {
+    for (int i = 0; i < fpr_reg_count; i++) {
+      uint32_t regno = fpr_regs[i];
+      reg_ctx_sp->ConvertBetweenRegisterKinds(eRegisterKindDWARF, fpr_regs[i],
+                                              plan_regkind, regno);
+      saved_regs.push_back(regno);
+    }
+  }
+
+  addr_t cfa;
+  if (!regctx->GetCFA(cfa))
+    return {};
+
+  // The CPSR value saved to stack is actually (from Armv7-M ARM)
+  //   "XPSR<31:10>:frameptralign:XPSR<8:0>"
+  // Bit 9 indicates that the stack pointer was aligned (to
+  // an 8-byte alignment) when the exception happened, and we must
+  // account for that when restoring the original stack pointer value.
+  Status error;
+  uint32_t callers_xPSR =
+      process_sp->ReadUnsignedIntegerFromMemory(cfa + 0x1c, 4, 0, error);
+  const bool align_stack = callers_xPSR & (1U << 9);
+  uint32_t callers_sp = cfa + stored_regs_size;
+  if (align_stack)
+    callers_sp |= 4;
+
+  Log *log = GetLog(LLDBLog::Unwind);
+  LLDB_LOGF(log,
+            "ArchitectureArm::GetArchitectureUnwindPlan found caller return "
+            "addr of 0x%" PRIx64 ", for frame with CFA 0x%" PRIx64
+            ", fp_regs_saved %d, stored_regs_size 0x%x, align stack %d",
+            callers_return_address, cfa, fp_regs_saved, stored_regs_size,
+            align_stack);
+
+  uint32_t sp_regnum = dwarf_sp;
+  reg_ctx_sp->ConvertBetweenRegisterKinds(eRegisterKindDWARF, dwarf_sp,
+                                          plan_regkind, sp_regnum);
+
+  const int row_count = current_unwindplan->GetRowCount();
+  for (int i = 0; i < row_count; i++) {
+    UnwindPlan::Row row = *current_unwindplan->GetRowAtIndex(i);
+    uint32_t offset = 0;
+    const size_t saved_reg_count = saved_regs.size();
+    for (size_t j = 0; j < saved_reg_count; j++) {
+      // The locations could be set with
+      // SetRegisterLocationToIsConstant(regno, cfa+offset)
+      // expressing it in terms of CFA addr+offset - this UnwindPlan
+      // is only used once, with this specific CFA.  I'm not sure
+      // which will be clearer for someone reading the unwind log.
+      row.SetRegisterLocationToAtCFAPlusOffset(saved_regs[j], offset, true);
+      offset += 4;
+    }
+    row.SetRegisterLocationToIsCFAPlusOffset(sp_regnum, callers_sp - cfa, true);
+    new_plan->AppendRow(row);
+  }
+  return new_plan;
+}

lldb/source/Plugins/Architecture/Arm/ArchitectureArm.h

@@ -10,6 +10,7 @@
 #define LLDB_SOURCE_PLUGINS_ARCHITECTURE_ARM_ARCHITECTUREARM_H
 
 #include "lldb/Core/Architecture.h"
+#include "lldb/Target/Thread.h"
 
 namespace lldb_private {
 
@@ -29,6 +30,10 @@ class ArchitectureArm : public Architecture {
   lldb::addr_t GetOpcodeLoadAddress(lldb::addr_t load_addr,
                                     AddressClass addr_class) const override;
 
+  lldb::UnwindPlanSP GetArchitectureUnwindPlan(
+      lldb_private::Thread &thread, lldb_private::RegisterContextUnwind *regctx,
+      std::shared_ptr<const UnwindPlan> current_unwindplan) override;
+
 private:
   static std::unique_ptr<Architecture> Create(const ArchSpec &arch);
   ArchitectureArm() = default;