Make breakpoint setting by file and line much more efficient by only looking for inlined breakpoint locations if we are setting a breakpoint in anything but a source implementation file. Implementing this complex for a many reasons. Turns out that parsing compile units lazily had some issues with respect to how we need to do things with DWARF in .o files. So the fixes in the checkin for this makes these changes:
- Add a new setting called "target.inline-breakpoint-strategy" which can be set to "never", "always", or "headers". "never" will never try and set any inlined breakpoints (fastest). "always" always looks for inlined breakpoint locations (slowest, but most accurate). "headers", which is the default setting, will only look for inlined breakpoint locations if the breakpoint is set in what are consudered to be header files, which is realy defined as "not in an implementation source file".
- modify the breakpoint setting by file and line to check the current "target.inline-breakpoint-strategy" setting and act accordingly
- Modify compile units to be able to get their language and other info lazily. This allows us to create compile units from the debug map and not have to fill all of the details in, and then lazily discover this information as we go on debuggging. This is needed to avoid parsing all .o files when setting breakpoints in implementation only files (no inlines). Otherwise we would need to parse the .o file, the object file (mach-o in our case) and the symbol file (DWARF in the object file) just to see what the compile unit was.
- modify the "SymbolFileDWARFDebugMap" to subclass lldb_private::Module so that the virtual "GetObjectFile()" and "GetSymbolVendor()" functions can be intercepted when the .o file contenst are later lazilly needed. Prior to this fix, when we first instantiated the "SymbolFileDWARFDebugMap" class, we would also make modules, object files and symbol files for every .o file in the debug map because we needed to fix up the sections in the .o files with information that is in the executable debug map. Now we lazily do this in the DebugMapModule::GetObjectFile()
Cleaned up header includes a bit as well.
llvm-svn: 162860
keep a shared pointer to their disassembler. This
is important for the LLVM-C disassembler because
it needs to lock its parent in order to disassemble
itself.
This means that every interface that returned a
Disassembler* needs to return a DisassemblerSP, so
that the instructions and any external owners share
the same reference count on the object. I changed
all clients to use this shared pointer, which also
plugged a few leaks.
<rdar://problem/12002822>
llvm-svn: 161123
Fixed the DisassemblerLLVMC disassembler to parse more efficiently instead of parsing opcodes over and over. The InstructionLLVMC class now only reads the opcode in the InstructionLLVMC::Decode function. This can be done very efficiently for ARM and architectures that have fixed opcode sizes. For x64 it still calls the disassembler to get the byte size.
Moved the lldb_private::Instruction::Dump(...) function up into the lldb_private::Instruction class and it now uses the function that gets the mnemonic, operandes and comments so that all disassembly is using the same code.
Added StreamString::FillLastLineToColumn() to allow filling a line up to a column with a character (which is used by the lldb_private::Instruction::Dump(...) function).
Modified the Opcode::GetData() fucntion to "do the right thing" for thumb instructions.
llvm-svn: 156532
I started work on being able to add symbol files after a debug session
had started with a new "target symfile add" command and quickly ran into
problems with stale Address objects in breakpoint locations that had
lldb_private::Section pointers into modules that had been removed or
replaced. This also let to grabbing stale modules from those sections.
So I needed to thread harded the Address, Section and related objects.
To do this I modified the ModuleChild class to now require a ModuleSP
on initialization so that a weak reference can created. I also changed
all places that were handing out "Section *" to have them hand out SectionSP.
All ObjectFile, SymbolFile and SymbolVendors were inheriting from ModuleChild
so all of the find plug-in, static creation function and constructors now
require ModuleSP references instead of Module *.
Address objects now have weak references to their sections which can
safely go stale when a module gets destructed.
This checkin doesn't complete the "target symfile add" command, but it
does get us a lot clioser to being able to do such things without a high
risk of crashing or memory corruption.
llvm-svn: 151336
objects for the backlink to the lldb_private::Process. The issues we were
running into before was someone was holding onto a shared pointer to a
lldb_private::Thread for too long, and the lldb_private::Process parent object
would get destroyed and the lldb_private::Thread had a "Process &m_process"
member which would just treat whatever memory that used to be a Process as a
valid Process. This was mostly happening for lldb_private::StackFrame objects
that had a member like "Thread &m_thread". So this completes the internal
strong/weak changes.
Documented the ExecutionContext and ExecutionContextRef classes so that our
LLDB developers can understand when and where to use ExecutionContext and
ExecutionContextRef objects.
llvm-svn: 151009
cause extra shared pointer references to one or more modules to be leaked.
This would cause many object files to stay around the life of LLDB, so after
a recompile and rexecution, we would keep adding more and more memory. After
fixing the leak, we found many cases where leaked stack frames were still
being used and causing crashes in the test suite. These are now all resolved.
llvm-svn: 137516
This is helping us track down some extra references to ModuleSP objects that
are causing things to get kept around for too long.
Added a module pointer accessor to target and change a lot of code to use
it where it would be more efficient.
"taret delete" can now specify "--clean=1" which will cleanup the global module
list for any orphaned module in the shared module cache which can save memory
and also help track down module reference leaks like we have now.
llvm-svn: 137294
bool
Address::SetLoadAddress (lldb::addr_t load_addr, Target *target);
Added an == and != operator to RegisterValue.
Modified the ThreadPlanTracer to use RegisterValue objects to store the
register values when single stepping. Also modified the output to be a bit
less wide.
Fixed the ABIMacOSX_arm to not overwrite stuff on the stack. Also made the
trivial function call be able to set the ARM/Thumbness of the target
correctly, and also sets the return value ARM/Thumbness.
Fixed the encoding on the arm s0-s31 and d16 - d31 registers when the default
register set from a standard GDB server register sets.
llvm-svn: 131517
respective ABI plugins as they were plug-ins that supplied ABI specfic info.
Also hookep up the UnwindAssemblyInstEmulation so that it can generate the
unwind plans for ARM.
Changed the way ABI plug-ins are handed out when you get an instance from
the plug-in manager. They used to return pointers that would be mananged
individually by each client that requested them, but now they are handed out
as shared pointers since there is no state in the ABI objects, they can be
shared.
llvm-svn: 131193
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
plugin by name on the command line for when there is more than one disassembler
plugin.
Taught the Opcode class to dump itself so that "disassembler -b" will dump
the bytes correctly for each opcode type. Modified all places that were passing
the opcode bytes buffer in so that the bytes could be displayed to just pass
in a bool that indicates if we should dump the opcode bytes since the opcode
now lives inside llvm_private::Instruction.
llvm-svn: 128290
the way LLDB lazily gets complete definitions for types within the debug info.
When we run across a class/struct/union definition in the DWARF, we will only
parse the full definition if we need to. This works fine for top level types
that are assigned directly to variables and arguments, but when we have a
variable with a class, lets say "A" for this example, that has a member:
"B *m_b". Initially we don't need to hunt down a definition for this class
unless we are ever asked to do something with it ("expr m_b->getDecl()" for
example). With my previous approach to lazy type completion, we would be able
to take a "A *a" and get a complete type for it, but we wouldn't be able to
then do an "a->m_b->getDecl()" unless we always expanded all types within a
class prior to handing out the type. Expanding everything is very costly and
it would be great if there were a better way.
A few months ago I worked with the llvm/clang folks to have the
ExternalASTSource class be able to complete classes if there weren't completed
yet:
class ExternalASTSource {
....
virtual void
CompleteType (clang::TagDecl *Tag);
virtual void
CompleteType (clang::ObjCInterfaceDecl *Class);
};
This was great, because we can now have the class that is producing the AST
(SymbolFileDWARF and SymbolFileDWARFDebugMap) sign up as external AST sources
and the object that creates the forward declaration types can now also
complete them anywhere within the clang type system.
This patch makes a few major changes:
- lldb_private::Module classes now own the AST context. Previously the TypeList
objects did.
- The DWARF parsers now sign up as an external AST sources so they can complete
types.
- All of the pure clang type system wrapper code we have in LLDB (ClangASTContext,
ClangASTType, and more) can now be iterating through children of any type,
and if a class/union/struct type (clang::RecordType or ObjC interface)
is found that is incomplete, we can ask the AST to get the definition.
- The SymbolFileDWARFDebugMap class now will create and use a single AST that
all child SymbolFileDWARF classes will share (much like what happens when
we have a complete linked DWARF for an executable).
We will need to modify some of the ClangUserExpression code to take more
advantage of this completion ability in the near future. Meanwhile we should
be better off now that we can be accessing any children of variables through
pointers and always be able to resolve the clang type if needed.
llvm-svn: 123613
an issue with the way the UnwindLLDB was handing out RegisterContexts: it
was making shared pointers to register contexts and then handing out just
the pointers (which would get put into shared pointers in the thread and
stack frame classes) and cause double free issues. MallocScribble helped to
find these issues after I did some other cleanup. To help avoid any
RegisterContext issue in the future, all code that deals with them now
returns shared pointers to the register contexts so we don't end up with
multiple deletions. Also now that the RegisterContext class doesn't require
a stack frame, we patched a memory leak where a StackFrame object was being
created and leaked.
Made the RegisterContext class not have a pointer to a StackFrame object as
one register context class can be used for N inlined stack frames so there is
not a 1 - 1 mapping. Updates the ExecutionContextScope part of the
RegisterContext class to never return a stack frame to indicate this when it
is asked to recreate the execution context. Now register contexts point to the
concrete frame using a concrete frame index. Concrete frames are all of the
frames that are actually formed on the stack of a thread. These concrete frames
can be turned into one or more user visible frames due to inlining. Each
inlined stack frame has the exact same register context (shared via shared
pointers) as any parent inlined stack frames all the way up to the concrete
frame itself.
So now the stack frames and the register contexts should behave much better.
llvm-svn: 122976
cases when getting the clang type:
- need only a forward declaration
- need a clang type that can be used for layout (members and args/return types)
- need a full clang type
This allows us to partially parse the clang types and be as lazy as possible.
The first case is when we just need to declare a type and we will complete it
later. The forward declaration happens only for class/union/structs and enums.
The layout type allows us to resolve the full clang type _except_ if we have
any modifiers on a pointer or reference (both R and L value). In this case
when we are adding members or function args or return types, we only need to
know how the type will be laid out and we can defer completing the pointee
type until we later need it. The last type means we need a full definition for
the clang type.
Did some renaming of some enumerations to get rid of the old "DC" prefix (which
stands for DebugCore which is no longer around).
Modified the clang namespace support to be almost ready to be fed to the
expression parser. I made a new ClangNamespaceDecl class that can carry around
the AST and the namespace decl so we can copy it into the expression AST. I
modified the symbol vendor and symbol file plug-ins to use this new class.
llvm-svn: 118976
Jim Ingham