Added the ability to get the min and max instruction byte size for

an architecture into ArchSpec:

uint32_t
ArchSpec::GetMinimumOpcodeByteSize() const;

uint32_t
ArchSpec::GetMaximumOpcodeByteSize() const;

Added an AddressClass to the Instruction class in Disassembler.h.
This allows decoded instructions to know know if they are code,
code with alternate ISA (thumb), or even data which can be mixed
into code. The instruction does have an address, but it is a good
idea to cache this value so we don't have to look it up more than 
once.

Fixed an issue in Opcode::SetOpcodeBytes() where the length wasn't
getting set.

Changed:

	bool
	SymbolContextList::AppendIfUnique (const SymbolContext& sc);

To:
	bool
	SymbolContextList::AppendIfUnique (const SymbolContext& sc, 
									   bool merge_symbol_into_function);

This function was typically being used when looking up functions
and symbols. Now if you lookup a function, then find the symbol,
they can be merged into the same symbol context and not cause
multiple symbol contexts to appear in a symbol context list that
describes the same function.

Fixed the SymbolContext not equal operator which was causing mixed
mode disassembly to not work ("disassembler --mixed --name main").

Modified the disassembler classes to know about the fact we know,
for a given architecture, what the min and max opcode byte sizes
are. The InstructionList class was modified to return the max
opcode byte size for all of the instructions in its list.
These two fixes means when disassemble a list of instructions and dump 
them and show the opcode bytes, we can format the output more 
intelligently when showing opcode bytes. This affects any architectures
that have varying opcode byte sizes (x86_64 and i386). Knowing the max
opcode byte size also helps us to be able to disassemble N instructions
without having to re-read data if we didn't read enough bytes.

Added the ability to set the architecture for the disassemble command.
This means you can easily cross disassemble data for any supported 
architecture. I also added the ability to specify "thumb" as an 
architecture so that we can force disassembly into thumb mode when
needed. In GDB this was done using a hack of specifying an odd
address when disassembling. I don't want to repeat this hack in LLDB,
so the auto detection between ARM and thumb is failing, just specify
thumb when disassembling:

(lldb) disassemble --arch thumb --name main

You can also have data in say an x86_64 file executable and disassemble
data as any other supported architecture:
% lldb a.out
Current executable set to 'a.out' (x86_64).
(lldb) b main
(lldb) run
(lldb) disassemble --arch thumb --count 2 --start-address 0x0000000100001080 --bytes
0x100001080:  0xb580 push   {r7, lr}
0x100001082:  0xaf00 add    r7, sp, #0

Fixed Target::ReadMemory(...) to be able to deal with Address argument object
that isn't section offset. When an address object was supplied that was
out on the heap or stack, target read memory would fail. Disassembly uses
Target::ReadMemory(...), and the example above where we disassembler thumb
opcodes in an x86 binary was failing do to this bug.

llvm-svn: 128347

3 files changed, 52 insertions, 49 deletions

diff --git a/lldb/source/Commands/CommandObjectBreakpoint.cpp b/lldb/source/Commands/CommandObjectBreakpoint.cpp
index c7bbf85c0b0..6bf408b2460 100644
--- a/lldb/source/Commands/CommandObjectBreakpoint.cpp
+++ b/lldb/source/Commands/CommandObjectBreakpoint.cpp
@@ -155,7 +155,7 @@ CommandObjectBreakpointSet::CommandOptions::SetOptionValue (int option_idx, cons
             break;
 
         case 'f':
-            m_filename = option_arg;
+            m_filename.assign (option_arg);
             break;
 
         case 'l':
@@ -163,32 +163,32 @@ CommandObjectBreakpointSet::CommandOptions::SetOptionValue (int option_idx, cons
             break;
 
         case 'b':
-            m_func_name = option_arg;
+            m_func_name.assign (option_arg);
             m_func_name_type_mask |= eFunctionNameTypeBase;
             break;
 
         case 'n':
-            m_func_name = option_arg;
+            m_func_name.assign (option_arg);
             m_func_name_type_mask |= eFunctionNameTypeAuto;
             break;
 
         case 'F':
-            m_func_name = option_arg;
+            m_func_name.assign (option_arg);
             m_func_name_type_mask |= eFunctionNameTypeFull;
             break;
 
         case 'S':
-            m_func_name = option_arg;
+            m_func_name.assign (option_arg);
             m_func_name_type_mask |= eFunctionNameTypeSelector;
             break;
 
         case 'M':
-            m_func_name = option_arg;
+            m_func_name.assign (option_arg);
             m_func_name_type_mask |= eFunctionNameTypeMethod;
             break;
 
         case 'r':
-            m_func_regexp = option_arg;
+            m_func_regexp.assign (option_arg);
             break;
 
         case 's':
@@ -211,10 +211,10 @@ CommandObjectBreakpointSet::CommandOptions::SetOptionValue (int option_idx, cons
         }
         break;
         case 'T':
-            m_thread_name = option_arg;
+            m_thread_name.assign (option_arg);
             break;
         case 'q':
-            m_queue_name = option_arg;
+            m_queue_name.assign (option_arg);
             break;
         case 'x':
         {
@@ -1087,7 +1087,7 @@ CommandObjectBreakpointClear::CommandOptions::SetOptionValue (int option_idx, co
     switch (short_option)
     {
         case 'f':
-            m_filename = option_arg;
+            m_filename.assign (option_arg);
             break;
 
         case 'l':
@@ -1406,7 +1406,7 @@ CommandObjectBreakpointModify::CommandOptions::SetOptionValue (int option_idx, c
     {
         case 'c':
             if (option_arg != NULL)
-                m_condition = option_arg;
+                m_condition.assign (option_arg);
             else
                 m_condition.clear();
             m_condition_passed = true;
@@ -1445,14 +1445,14 @@ CommandObjectBreakpointModify::CommandOptions::SetOptionValue (int option_idx, c
         break;
         case 'T':
             if (option_arg != NULL)
-                m_thread_name = option_arg;
+                m_thread_name.assign (option_arg);
             else
                 m_thread_name.clear();
             m_name_passed = true;
             break;
         case 'q':
             if (option_arg != NULL)
-                m_queue_name = option_arg;
+                m_queue_name.assign (option_arg);
             else
                 m_queue_name.clear();
             m_queue_passed = true;
diff --git a/lldb/source/Commands/CommandObjectDisassemble.cpp b/lldb/source/Commands/CommandObjectDisassemble.cpp
index c3b52cfeab8..74c27e39090 100644
--- a/lldb/source/Commands/CommandObjectDisassemble.cpp
+++ b/lldb/source/Commands/CommandObjectDisassemble.cpp
@@ -40,7 +40,8 @@ CommandObjectDisassemble::CommandOptions::CommandOptions () :
     m_start_addr(),
     m_end_addr (),
     m_at_pc (false),
-    m_plugin_name ()
+    m_plugin_name (),
+    m_arch() 
 {
     ResetOptionValues();
 }
@@ -64,7 +65,7 @@ CommandObjectDisassemble::CommandOptions::SetOptionValue (int option_idx, const
         show_mixed = true;
         break;
 
-    case 'x':
+    case 'C':
         num_lines_context = Args::StringToUInt32(option_arg, 0, 0, &success);
         if (!success)
             error.SetErrorStringWithFormat ("Invalid num context lines string: \"%s\".\n", option_arg);
@@ -118,6 +119,10 @@ CommandObjectDisassemble::CommandOptions::SetOptionValue (int option_idx, const
         // There's no need to set any flag.
         break;
 
+    case 'a':
+        m_arch.SetTriple (option_arg);
+        break;
+
     default:
         error.SetErrorStringWithFormat("Unrecognized short option '%c'.\n", short_option);
         break;
@@ -140,6 +145,7 @@ CommandObjectDisassemble::CommandOptions::ResetOptionValues ()
     m_end_addr = LLDB_INVALID_ADDRESS;
     raw = false;
     m_plugin_name.clear();
+    m_arch.Clear();
 }
 
 const OptionDefinition*
@@ -151,28 +157,23 @@ CommandObjectDisassemble::CommandOptions::GetDefinitions ()
 OptionDefinition
 CommandObjectDisassemble::CommandOptions::g_option_table[] =
 {
-{ LLDB_OPT_SET_ALL, false, "bytes",    'b', no_argument,       NULL, 0, eArgTypeNone,    "Show opcode bytes when disassembling."},
-{ LLDB_OPT_SET_ALL, false, "context",  'x', required_argument, NULL, 0, eArgTypeNumLines,"Number of context lines of source to show."},
-{ LLDB_OPT_SET_ALL, false, "mixed",    'm', no_argument,       NULL, 0, eArgTypeNone,    "Enable mixed source and assembly display."},
-{ LLDB_OPT_SET_ALL, false, "raw",      'r', no_argument,       NULL, 0, eArgTypeNone,    "Print raw disassembly with no symbol information."},
-{ LLDB_OPT_SET_ALL, false, "plugin",   'P', required_argument, NULL, 0, eArgTypePlugin,  "Name of the disassembler plugin you want to use."},
-
-{ LLDB_OPT_SET_1, true, "start-address",  's', required_argument, NULL, 0, eArgTypeStartAddress,      "Address at which to start disassembling."},
-{ LLDB_OPT_SET_1, false, "end-address",  'e', required_argument, NULL, 0, eArgTypeEndAddress,      "Address at which to end disassembling."},
-
-{ LLDB_OPT_SET_2, true, "start-address",  's', required_argument, NULL, 0, eArgTypeStartAddress,      "Address at which to start disassembling."},
-{ LLDB_OPT_SET_2, false, "instruction-count",  'c', required_argument, NULL, 0, eArgTypeNumLines,      "Number of instructions to display."},
-
-{ LLDB_OPT_SET_3, true, "name",     'n', required_argument, NULL, CommandCompletions::eSymbolCompletion, eArgTypeFunctionName,             "Disassemble entire contents of the given function name."},
-{ LLDB_OPT_SET_3, false, "instruction-count",  'c', required_argument, NULL, 0, eArgTypeNumLines,      "Number of instructions to display."},
-
-{ LLDB_OPT_SET_4, true, "current-frame", 'f',  no_argument, NULL, 0, eArgTypeNone,             "Disassemble from the start of the current frame's function."},
-{ LLDB_OPT_SET_4, false, "instruction-count",  'c', required_argument, NULL, 0, eArgTypeNumLines,      "Number of instructions to display."},
-
-{ LLDB_OPT_SET_5, true, "current-pc", 'p',  no_argument, NULL, 0, eArgTypeNone,             "Disassemble from the current pc."},
-{ LLDB_OPT_SET_5, false, "instruction-count",  'c', required_argument, NULL, 0, eArgTypeNumLines,      "Number of instructions to display."},
-
-{ 0, false, NULL, 0, 0, NULL, 0, eArgTypeNone, NULL }
+{ LLDB_OPT_SET_ALL  , false , "bytes",          'b', no_argument        , NULL, 0, eArgTypeNone,        "Show opcode bytes when disassembling."},
+{ LLDB_OPT_SET_ALL  , false , "context",        'C', required_argument  , NULL, 0, eArgTypeNumLines,    "Number of context lines of source to show."},
+{ LLDB_OPT_SET_ALL  , false , "mixed",          'm', no_argument        , NULL, 0, eArgTypeNone,        "Enable mixed source and assembly display."},
+{ LLDB_OPT_SET_ALL  , false , "raw",            'r', no_argument        , NULL, 0, eArgTypeNone,        "Print raw disassembly with no symbol information."},
+{ LLDB_OPT_SET_ALL  , false , "plugin",         'P', required_argument  , NULL, 0, eArgTypePlugin,      "Name of the disassembler plugin you want to use."},
+{ LLDB_OPT_SET_ALL  , false , "arch",           'a', required_argument  , NULL, 0, eArgTypeArchitecture,"Specify the architecture to use from cross disassembly."},
+{ LLDB_OPT_SET_1 |
+  LLDB_OPT_SET_2    , true  , "start-address" , 's', required_argument  , NULL, 0, eArgTypeStartAddress,"Address at which to start disassembling."},
+{ LLDB_OPT_SET_1    , false , "end-address"  ,  'e', required_argument  , NULL, 0, eArgTypeEndAddress,  "Address at which to end disassembling."},
+{ LLDB_OPT_SET_2 |
+  LLDB_OPT_SET_3 |
+  LLDB_OPT_SET_4 |
+  LLDB_OPT_SET_5    , false , "count",          'c', required_argument  , NULL, 0, eArgTypeNumLines,    "Number of instructions to display."},
+{ LLDB_OPT_SET_3    , true  , "name",           'n', required_argument  , NULL, CommandCompletions::eSymbolCompletion, eArgTypeFunctionName,             "Disassemble entire contents of the given function name."},
+{ LLDB_OPT_SET_4    , true  , "frame",          'f', no_argument        , NULL, 0, eArgTypeNone,        "Disassemble from the start of the current frame's function."},
+{ LLDB_OPT_SET_5    , true  , "pc",             'p', no_argument        , NULL, 0, eArgTypeNone,        "Disassemble from the current pc."},
+{ 0                 , false , NULL,             0,   0                  , NULL, 0, eArgTypeNone,        NULL }
 };
 
 
@@ -207,27 +208,28 @@ CommandObjectDisassemble::Execute
         result.SetStatus (eReturnStatusFailed);
         return false;
     }
+    if (!m_options.m_arch.IsValid())
+        m_options.m_arch = target->GetArchitecture();
 
-    ArchSpec arch(target->GetArchitecture());
-    if (!arch.IsValid())
+    if (!m_options.m_arch.IsValid())
     {
-        result.AppendError ("target needs valid architecure in order to be able to disassemble");
+        result.AppendError ("use the --arch option or set the target architecure to disassemble");
         result.SetStatus (eReturnStatusFailed);
         return false;
     }
 
     const char *plugin_name = m_options.GetPluginName ();
-    Disassembler *disassembler = Disassembler::FindPlugin(arch, plugin_name);
+    Disassembler *disassembler = Disassembler::FindPlugin(m_options.m_arch, plugin_name);
 
     if (disassembler == NULL)
     {
         if (plugin_name)
-            result.AppendErrorWithFormat ("Unable to find Disassembler plug-in for %s architecture named '%s'.\n", 
-                                          arch.GetArchitectureName(),
-                                          plugin_name);
+            result.AppendErrorWithFormat ("Unable to find Disassembler plug-in named '%s' that supports the '%s' architecture.\n", 
+                                          plugin_name,
+                                          m_options.m_arch.GetArchitectureName());
         else
-            result.AppendErrorWithFormat ("Unable to find Disassembler plug-in for %s architecture.\n", 
-                                          arch.GetArchitectureName());
+            result.AppendErrorWithFormat ("Unable to find Disassembler plug-in for the '%s' architecture.\n", 
+                                          m_options.m_arch.GetArchitectureName());
         result.SetStatus (eReturnStatusFailed);
         return false;
     }
@@ -255,7 +257,7 @@ CommandObjectDisassemble::Execute
         ConstString name(m_options.m_func_name.c_str());
         
         if (Disassembler::Disassemble (m_interpreter.GetDebugger(), 
-                                       arch,
+                                       m_options.m_arch,
                                        plugin_name,
                                        exe_ctx,
                                        name,
@@ -337,7 +339,7 @@ CommandObjectDisassemble::Execute
             }
 
             if (Disassembler::Disassemble (m_interpreter.GetDebugger(), 
-                                           arch,
+                                           m_options.m_arch,
                                            plugin_name,
                                            exe_ctx,
                                            start_addr,
@@ -387,7 +389,7 @@ CommandObjectDisassemble::Execute
                 range.SetByteSize(DEFAULT_DISASM_BYTE_SIZE);
 
             if (Disassembler::Disassemble (m_interpreter.GetDebugger(), 
-                                           arch,
+                                           m_options.m_arch,
                                            plugin_name,
                                            exe_ctx,
                                            range,
diff --git a/lldb/source/Commands/CommandObjectDisassemble.h b/lldb/source/Commands/CommandObjectDisassemble.h
index 91812af3187..42ede79787d 100644
--- a/lldb/source/Commands/CommandObjectDisassemble.h
+++ b/lldb/source/Commands/CommandObjectDisassemble.h
@@ -63,6 +63,7 @@ public:
         lldb::addr_t m_end_addr;
         bool m_at_pc;
         std::string m_plugin_name;
+        ArchSpec m_arch;
         static OptionDefinition g_option_table[];
     };