[lldb] Support disassembling discontinuous functions (#126505)

The command already supported disassembling multiple ranges, among other
reasons because inline functions can be discontinuous. The main thing
that was missing was being able to retrieve the function ranges from the
top level function object.

The output of the command for the case where the function entry point is
not its lowest address is somewhat confusing (we're showing negative
offsets), but it is correct.

Author: labath

lldb/source/Commands/CommandObjectDisassemble.cpp

@@ -21,6 +21,7 @@
 #include "lldb/Target/SectionLoadList.h"
 #include "lldb/Target/StackFrame.h"
 #include "lldb/Target/Target.h"
+#include <iterator>
 
 static constexpr unsigned default_disasm_byte_size = 32;
 static constexpr unsigned default_disasm_num_ins = 4;
@@ -236,35 +237,43 @@ CommandObjectDisassemble::CommandObjectDisassemble(
 
 CommandObjectDisassemble::~CommandObjectDisassemble() = default;
 
-llvm::Error CommandObjectDisassemble::CheckRangeSize(const AddressRange &range,
-                                                     llvm::StringRef what) {
+llvm::Expected<std::vector<AddressRange>>
+CommandObjectDisassemble::CheckRangeSize(std::vector<AddressRange> ranges,
+                                         llvm::StringRef what) {
+  addr_t total_range_size = 0;
+  for (const AddressRange &r : ranges)
+    total_range_size += r.GetByteSize();
+
   if (m_options.num_instructions > 0 || m_options.force ||
-      range.GetByteSize() < GetDebugger().GetStopDisassemblyMaxSize())
-    return llvm::Error::success();
+      total_range_size < GetDebugger().GetStopDisassemblyMaxSize())
+    return ranges;
+
   StreamString msg;
   msg << "Not disassembling " << what << " because it is very large ";
-  range.Dump(&msg, &GetTarget(), Address::DumpStyleLoadAddress,
-             Address::DumpStyleFileAddress);
+  for (const AddressRange &r : ranges)
+    r.Dump(&msg, &GetTarget(), Address::DumpStyleLoadAddress,
+           Address::DumpStyleFileAddress);
   msg << ". To disassemble specify an instruction count limit, start/stop "
          "addresses or use the --force option.";
-  return llvm::createStringError(llvm::inconvertibleErrorCode(),
-                                 msg.GetString());
+  return llvm::createStringError(msg.GetString());
 }
 
 llvm::Expected<std::vector<AddressRange>>
 CommandObjectDisassemble::GetContainingAddressRanges() {
   std::vector<AddressRange> ranges;
-  const auto &get_range = [&](Address addr) {
+  const auto &get_ranges = [&](Address addr) {
     ModuleSP module_sp(addr.GetModule());
     SymbolContext sc;
     bool resolve_tail_call_address = true;
     addr.GetModule()->ResolveSymbolContextForAddress(
         addr, eSymbolContextEverything, sc, resolve_tail_call_address);
     if (sc.function || sc.symbol) {
       AddressRange range;
-      sc.GetAddressRange(eSymbolContextFunction | eSymbolContextSymbol, 0,
-                         false, range);
-      ranges.push_back(range);
+      for (uint32_t idx = 0;
+           sc.GetAddressRange(eSymbolContextFunction | eSymbolContextSymbol,
+                              idx, false, range);
+           ++idx)
+        ranges.push_back(range);
     }
   };
 
@@ -273,14 +282,14 @@ CommandObjectDisassemble::GetContainingAddressRanges() {
     Address symbol_containing_address;
     if (target.ResolveLoadAddress(m_options.symbol_containing_addr,
                                   symbol_containing_address)) {
-      get_range(symbol_containing_address);
+      get_ranges(symbol_containing_address);
     }
   } else {
     for (lldb::ModuleSP module_sp : target.GetImages().Modules()) {
       Address file_address;
       if (module_sp->ResolveFileAddress(m_options.symbol_containing_addr,
                                         file_address)) {
-        get_range(file_address);
+        get_ranges(file_address);
       }
     }
   }
@@ -292,9 +301,7 @@ CommandObjectDisassemble::GetContainingAddressRanges() {
         m_options.symbol_containing_addr);
   }
 
-  if (llvm::Error err = CheckRangeSize(ranges[0], "the function"))
-    return std::move(err);
-  return ranges;
+  return CheckRangeSize(std::move(ranges), "the function");
 }
 
 llvm::Expected<std::vector<AddressRange>>
@@ -304,29 +311,24 @@ CommandObjectDisassemble::GetCurrentFunctionRanges() {
   if (!frame) {
     if (process) {
       return llvm::createStringError(
-          llvm::inconvertibleErrorCode(),
-          "Cannot disassemble around the current "
-          "function without the process being stopped.\n");
-    } else {
-      return llvm::createStringError(llvm::inconvertibleErrorCode(),
-                                     "Cannot disassemble around the current "
-                                     "function without a selected frame: "
-                                     "no currently running process.\n");
+          "Cannot disassemble around the current function without the process "
+          "being stopped.\n");
     }
+    return llvm::createStringError(
+        "Cannot disassemble around the current function without a selected "
+        "frame: no currently running process.\n");
   }
-  SymbolContext sc(
-      frame->GetSymbolContext(eSymbolContextFunction | eSymbolContextSymbol));
-  AddressRange range;
+  SymbolContext sc =
+      frame->GetSymbolContext(eSymbolContextFunction | eSymbolContextSymbol);
+  std::vector<AddressRange> ranges;
   if (sc.function)
-    range = sc.function->GetAddressRange();
-  else if (sc.symbol && sc.symbol->ValueIsAddress()) {
-    range = {sc.symbol->GetAddress(), sc.symbol->GetByteSize()};
-  } else
-    range = {frame->GetFrameCodeAddress(), default_disasm_byte_size};
-
-  if (llvm::Error err = CheckRangeSize(range, "the current function"))
-    return std::move(err);
-  return std::vector<AddressRange>{range};
+    ranges = sc.function->GetAddressRanges();
+  else if (sc.symbol && sc.symbol->ValueIsAddress())
+    ranges.emplace_back(sc.symbol->GetAddress(), sc.symbol->GetByteSize());
+  else
+    ranges.emplace_back(frame->GetFrameCodeAddress(), default_disasm_byte_size);
+
+  return CheckRangeSize(std::move(ranges), "the current function");
 }
 
 llvm::Expected<std::vector<AddressRange>>
@@ -372,19 +374,23 @@ CommandObjectDisassemble::GetNameRanges(CommandReturnObject &result) {
 
   std::vector<AddressRange> ranges;
   llvm::Error range_errs = llvm::Error::success();
-  AddressRange range;
   const uint32_t scope =
       eSymbolContextBlock | eSymbolContextFunction | eSymbolContextSymbol;
   const bool use_inline_block_range = true;
   for (SymbolContext sc : sc_list.SymbolContexts()) {
+    std::vector<AddressRange> fn_ranges;
+    AddressRange range;
     for (uint32_t range_idx = 0;
          sc.GetAddressRange(scope, range_idx, use_inline_block_range, range);
-         ++range_idx) {
-      if (llvm::Error err = CheckRangeSize(range, "a range"))
-        range_errs = joinErrors(std::move(range_errs), std::move(err));
-      else
-        ranges.push_back(range);
-    }
+         ++range_idx)
+      fn_ranges.push_back(std::move(range));
+
+    if (llvm::Expected<std::vector<AddressRange>> checked_ranges =
+            CheckRangeSize(std::move(fn_ranges), "a function"))
+      llvm::move(*checked_ranges, std::back_inserter(ranges));
+    else
+      range_errs =
+          joinErrors(std::move(range_errs), checked_ranges.takeError());
   }
   if (ranges.empty()) {
     if (range_errs)

lldb/source/Commands/CommandObjectDisassemble.h

@@ -100,7 +100,8 @@ class CommandObjectDisassemble : public CommandObjectParsed {
   llvm::Expected<std::vector<AddressRange>> GetPCRanges();
   llvm::Expected<std::vector<AddressRange>> GetStartEndAddressRanges();
 
-  llvm::Error CheckRangeSize(const AddressRange &range, llvm::StringRef what);
+  llvm::Expected<std::vector<AddressRange>>
+  CheckRangeSize(std::vector<AddressRange> ranges, llvm::StringRef what);
 
   CommandOptions m_options;
 };

lldb/source/Symbol/SymbolContext.cpp

@@ -351,8 +351,8 @@ bool SymbolContext::GetAddressRange(uint32_t scope, uint32_t range_idx,
   }
 
   if ((scope & eSymbolContextFunction) && (function != nullptr)) {
-    if (range_idx == 0) {
-      range = function->GetAddressRange();
+    if (range_idx < function->GetAddressRanges().size()) {
+      range = function->GetAddressRanges()[range_idx];
       return true;
     }
   }

lldb/test/Shell/Commands/command-disassemble.s

@@ -82,20 +82,25 @@
 # CHECK-NEXT: (lldb) disassemble --name case2
 # CHECK-NEXT: command-disassemble.s.tmp`n1::case2:
 # CHECK-NEXT: command-disassemble.s.tmp[0x2044] <+0>: int    $0x32
-# CHECK-NEXT: warning: Not disassembling a range because it is very large [0x0000000000002046-0x0000000000004046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
+# CHECK-NEXT: warning: Not disassembling a function because it is very large [0x0000000000002046-0x0000000000004046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
 # CHECK-NEXT: (lldb) disassemble --name case3
-# CHECK-NEXT: error: Not disassembling a range because it is very large [0x0000000000004046-0x0000000000006046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
-# CHECK-NEXT: Not disassembling a range because it is very large [0x0000000000006046-0x0000000000008046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
+# CHECK-NEXT: error: Not disassembling a function because it is very large [0x0000000000006046-0x0000000000007046)[0x0000000000009046-0x000000000000a046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
+# CHECK-NEXT: Not disassembling a function because it is very large [0x0000000000004046-0x0000000000006046). To disassemble specify an instruction count limit, start/stop addresses or use the --force option.
 # CHECK-NEXT: (lldb) disassemble --name case3 --count 3
+# CHECK-NEXT: command-disassemble.s.tmp`n2::case3:
+# CHECK-NEXT: command-disassemble.s.tmp[0x6046] <-12288>: int    $0x2a
+# CHECK-NEXT: command-disassemble.s.tmp[0x6048] <-12286>: int    $0x2a
+# CHECK-NEXT: command-disassemble.s.tmp[0x604a] <-12284>: int    $0x2a
+# CHECK-EMPTY:
+# CHECK-NEXT: command-disassemble.s.tmp`n2::case3:
+# CHECK-NEXT: command-disassemble.s.tmp[0x9046] <+0>: int    $0x2a
+# CHECK-NEXT: command-disassemble.s.tmp[0x9048] <+2>: int    $0x2a
+# CHECK-NEXT: command-disassemble.s.tmp[0x904a] <+4>: int    $0x2a
+# CHECK-EMPTY:
 # CHECK-NEXT: command-disassemble.s.tmp`n1::case3:
 # CHECK-NEXT: command-disassemble.s.tmp[0x4046] <+0>: int    $0x2a
 # CHECK-NEXT: command-disassemble.s.tmp[0x4048] <+2>: int    $0x2a
 # CHECK-NEXT: command-disassemble.s.tmp[0x404a] <+4>: int    $0x2a
-# CHECK-EMPTY:
-# CHECK-NEXT: command-disassemble.s.tmp`n2::case3:
-# CHECK-NEXT: command-disassemble.s.tmp[0x6046] <+0>: int    $0x2a
-# CHECK-NEXT: command-disassemble.s.tmp[0x6048] <+2>: int    $0x2a
-# CHECK-NEXT: command-disassemble.s.tmp[0x604a] <+4>: int    $0x2a
 # CHECK-EMPTY:
 
 
@@ -158,8 +163,97 @@ _ZN2n15case3Ev:
         .rept 0x1000
         int $42
         .endr
+        .size _ZN2n15case3Ev, .-_ZN2n15case3Ev
 
-_ZN2n25case3Ev:
+.L_ZN2n25case3Ev.__part.1:
+        .rept 0x800
+        int $42
+        .endr
+.L_ZN2n25case3Ev.__part.1_end:
+
+.Lpadding:
         .rept 0x1000
         int $42
         .endr
+
+_ZN2n25case3Ev:
+        .rept 0x800
+        int $42
+        .endr
+.L_ZN2n25case3Ev_end:
+
+        .section        .debug_abbrev,"",@progbits
+        .byte   1                               # Abbreviation Code
+        .byte   17                              # DW_TAG_compile_unit
+        .byte   1                               # DW_CHILDREN_yes
+        .byte   37                              # DW_AT_producer
+        .byte   8                               # DW_FORM_string
+        .byte   19                              # DW_AT_language
+        .byte   5                               # DW_FORM_data2
+        .byte   17                              # DW_AT_low_pc
+        .byte   1                               # DW_FORM_addr
+        .byte   85                              # DW_AT_ranges
+        .byte   23                              # DW_FORM_sec_offset
+        .byte   0                               # EOM(1)
+        .byte   0                               # EOM(2)
+        .byte   2                               # Abbreviation Code
+        .byte   57                              # DW_TAG_namespace
+        .byte   1                               # DW_CHILDREN_yes
+        .byte   3                               # DW_AT_name
+        .byte   8                               # DW_FORM_string
+        .byte   0                               # EOM(1)
+        .byte   0                               # EOM(2)
+        .byte   3                               # Abbreviation Code
+        .byte   46                              # DW_TAG_subprogram
+        .byte   0                               # DW_CHILDREN_no
+        .byte   85                              # DW_AT_ranges
+        .byte   23                              # DW_FORM_sec_offset
+        .byte   3                               # DW_AT_name
+        .byte   8                               # DW_FORM_string
+        .byte   110                             # DW_AT_linkage_name
+        .byte   8                               # DW_FORM_string
+        .byte   0                               # EOM(1)
+        .byte   0                               # EOM(2)
+        .byte   0                               # EOM(3)
+
+        .section        .debug_info,"",@progbits
+.Lcu_begin0:
+        .long   .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+        .short  5                               # DWARF version number
+        .byte   1                               # DWARF Unit Type
+        .byte   8                               # Address Size (in bytes)
+        .long   .debug_abbrev                   # Offset Into Abbrev. Section
+        .byte   1                               # Abbrev DW_TAG_compile_unit
+        .asciz  "Hand-written DWARF"            # DW_AT_producer
+        .short  29                              # DW_AT_language
+        .quad   0                               # DW_AT_low_pc
+        .long   .Ldebug_ranges0                 # DW_AT_ranges
+        .byte   2                               # Abbrev DW_TAG_namespace
+        .asciz  "n2"                            # DW_AT_name
+        .byte   3                               # Abbrev DW_TAG_subprogram
+        .long   .Ldebug_ranges0                 # DW_AT_ranges
+        .asciz  "case3"                         # DW_AT_name
+        .asciz  "_ZN2n25case3Ev"                # DW_AT_linkage_name
+        .byte   0                               # End Of Children Mark
+        .byte   0                               # End Of Children Mark
+.Ldebug_info_end0:
+
+        .section        .debug_rnglists,"",@progbits
+        .long   .Ldebug_list_header_end0-.Ldebug_list_header_start0 # Length
+.Ldebug_list_header_start0:
+        .short  5                               # Version
+        .byte   8                               # Address size
+        .byte   0                               # Segment selector size
+        .long   2                               # Offset entry count
+.Lrnglists_table_base0:
+        .long   .Ldebug_ranges0-.Lrnglists_table_base0
+.Ldebug_ranges0:
+        .byte   6                               # DW_RLE_start_end
+        .quad _ZN2n25case3Ev
+        .quad .L_ZN2n25case3Ev_end
+        .byte   6                               # DW_RLE_start_end
+        .quad .L_ZN2n25case3Ev.__part.1
+        .quad .L_ZN2n25case3Ev.__part.1_end
+        .byte   0                               # DW_RLE_end_of_list
+.Ldebug_list_header_end0: