Commit Graph

5356 Commits

Author SHA1 Message Date
Jim Ingham 48cdc58f0a SBValue::GetTypeName and SBValue::GetByteSize might have to update the dynamic value - which might involve running code. So they need to take the stop lock & target locks.
<rdar://problem/12001204>

llvm-svn: 162250
2012-08-21 01:46:35 +00:00
Johnny Chen d773139bbc Fix the wrong comment in TestUUIDMismatchWarnings.py.
llvm-svn: 162239
2012-08-20 22:36:58 +00:00
Johnny Chen 9b832fe40d Fix a crash (_wrap_SBDebugger_SetInputFileHandle -> PyString_AsString) running the test suite.
Also modify the boundary condition test case SBDebugger.DispatchInput(None) to be wrapped inside a try-except clause for now.

llvm-svn: 162228
2012-08-20 21:16:02 +00:00
Greg Clayton 486290078c Added qVAttachOrWaitSupported packet support.
llvm-svn: 162207
2012-08-20 16:50:43 +00:00
Filipe Cabecinhas c30199917a A baton isn't needed to dispatch input.
I also added a typemap to make DispatchInput usable in Python.

llvm-svn: 162204
2012-08-20 16:21:04 +00:00
Filipe Cabecinhas 4c1f3a1cc5 Add FILE* typemaps for SBDebugger.GetInputFileHandle() and friends.
llvm-svn: 162203
2012-08-20 16:10:44 +00:00
Jason Molenda 8eba46c68a Some eh_frame unwind instructions will define a return address register;
when you want to find the caller's saved pc, you look up the return address
register and use that.  On arm, for instance, this would be the contents of
the link register (lr).

If the eh_frame CIE defines an RA, record that fact in the UnwindPlan.

When we're finding a saved register, if it's the pc, lok for the location
of the return address register instead.

<rdar://problem/12062310> 

llvm-svn: 162167
2012-08-18 06:53:34 +00:00
Johnny Chen 8115c6d45d Fix missing braces from the python-GIL merge.
llvm-svn: 162162
2012-08-18 04:24:00 +00:00
Johnny Chen 2c90e999aa Merge python-GIL bracnh (by filcab) back into trunk!
llvm-svn: 162161
2012-08-18 04:14:54 +00:00
Johnny Chen 319e927ae1 Fix a race condition where multiple PythonInputReaderManager instances could, during destruction,
tread on the m_embedded_thread_input_reader_sp singleton maintained by the script interpreter.
Furthermore, use two additional slots under the script interpreter to store the PseudoTerminal and
the InputReaderSP pertaining to the embedded python interpreter -- resulted from the
ScriptInterpreterPython::ExecuteInterpreterLoop() call -- to facilitate separation from what is being
used by the PythonInputReaderManager instances.

llvm-svn: 162147
2012-08-17 23:44:35 +00:00
Sean Callanan 433c8a1f44 Committed a simple dtrace script that tracks
process termination, which can be useful to track
debugserver's delivery of signals.

llvm-svn: 162104
2012-08-17 16:30:13 +00:00
Sean Callanan adc43c998c Fixed some small formatting issues in the help for
"command regex."  It's now more readable and
grammatically correct.

<rdar://problem/12115962>

llvm-svn: 162047
2012-08-16 21:46:58 +00:00
Sean Callanan aa01b83078 Fixed a crash when incomplete expression variables
are materialized.

<rdar://problem/12105013>

llvm-svn: 162046
2012-08-16 21:34:44 +00:00
Johnny Chen a60c5ad819 Catch timestamps for the beginning and end of the test suite run.
llvm-svn: 162040
2012-08-16 19:15:21 +00:00
Johnny Chen a7e1d39309 Update build instructions. Patch from "Kopec, Matt" <matt.kopec@intel.com>!
llvm-svn: 162001
2012-08-16 00:08:21 +00:00
Johnny Chen eb46f78b08 rdar://problem/12096295
Add an lldb command line option to specify a core file: --core/-c.
For consistency, change the "target create" command to also use --core.

llvm-svn: 161993
2012-08-15 22:10:42 +00:00
Sean Callanan be3c5dab76 Fixed a typo.
<rdar://problem/12090979>

llvm-svn: 161910
2012-08-15 00:26:32 +00:00
Johnny Chen 6cf6f89005 A little bit of refactoring.
llvm-svn: 161903
2012-08-14 23:09:48 +00:00
Johnny Chen 25c0eb4a38 When trying to take snapshots of a watched variable, if the frame is unable to evaluate the variable expression,
do not take the sanpshot and forget about the stop info.  It is possible that the variable expression has gone
out of scope, we'll revise the hit count due to the false alarms.

llvm-svn: 161892
2012-08-14 20:56:37 +00:00
Enrico Granata 273d177bdf <rdar://problem/11589605> Making a
'type category enable *' command
to match 'type category disable *'

llvm-svn: 161882
2012-08-14 18:18:07 +00:00
Johnny Chen 88fc73b8f7 Simplify the "Watchpoint ... hit" printout, make it more terse.
Change the test case, too. 

llvm-svn: 161806
2012-08-13 23:27:50 +00:00
Jason Molenda 4d04d477d9 When emulating instructions that read from memory,
return 0x0 as the read value instead of uninitialized
stack data so we get consistent behavior from the
emulator.
<rdar://problem/12058770>

llvm-svn: 161795
2012-08-13 21:53:35 +00:00
Johnny Chen f97ecd70b2 Comment changes.
llvm-svn: 161787
2012-08-13 21:19:11 +00:00
Johnny Chen 209bd65ea4 rdar://problem/12007576
Record the snapshot of our watched value when the watchpoint is set or hit.
And report the old/new values when watchpoint is triggered.  Add some test scenarios.

llvm-svn: 161785
2012-08-13 21:09:54 +00:00
Greg Clayton 45b673dad5 <rdar://problem/12087275>
Make the crashlog parser able to deal with spaces in the process name.

llvm-svn: 161772
2012-08-13 18:48:03 +00:00
Greg Clayton 774ebdfcd1 Added a new "objc_refs" command that will track down all allocations on the heap that have the "isa" for the objective C class at offset zero. This will need to be improved to deal with KVO classes, but it is a start. It also disallows looking up a pointer value of zero since that would return way too many matches.
llvm-svn: 161724
2012-08-11 02:26:26 +00:00
Jim Ingham 0e41084ad1 Add an option to "process continue" to ignore the next <N> crossings of the breakpoint under
the currently selected thread.

<rdar://problem/10458225>

llvm-svn: 161723
2012-08-11 01:27:55 +00:00
Greg Clayton 7f4c7430f7 <rdar://problem/11791234>
Remember to copy the address byte size and the byte order when copying data into a DWARF location object, or things will go wrong.

llvm-svn: 161721
2012-08-11 00:49:14 +00:00
Greg Clayton 1fdbee5a6b Revert changes where we copied the expression locations back to using the reference into the debug info until test suite failures are resolved.
llvm-svn: 161720
2012-08-11 00:39:03 +00:00
Jim Ingham f94e179172 Add explicit casts to bool in "shared pointer is valid" constructs that return bool.
llvm-svn: 161719
2012-08-11 00:35:26 +00:00
Jim Ingham d6551dc0bf Change the minimum deployment target to 10.7 since clang requires 10.7 to use the new libc++.
llvm-svn: 161718
2012-08-11 00:33:08 +00:00
Greg Clayton 8179bcac55 <rdar://problem/11791234>
Fixed an issue that could cause references the shared data for an object file to stay around longer than intended and could cause memory bloat when debugging multiple times.

llvm-svn: 161716
2012-08-10 23:33:27 +00:00
Jim Ingham e9ce62b663 Use the file completer for "process launch" arguments.
<rdar://problem/11274012>

llvm-svn: 161704
2012-08-10 21:48:41 +00:00
Jason Molenda 4210713491 Remove a little unuseful output from the UnwindPlan::Row::Dump and UnwindPlan::Dump methods.
llvm-svn: 161696
2012-08-10 20:52:59 +00:00
Johnny Chen 01c0d4ec1f Add command completion test case for 'watchpoint command'.
llvm-svn: 161684
2012-08-10 19:05:48 +00:00
Sean Callanan d2a5a90148 Fixed a potential crash where we attempt to read
an invalid register.

<rdar://problem/12065366>

llvm-svn: 161679
2012-08-10 18:35:24 +00:00
Johnny Chen 1320641067 rdar://problem/11457143
Forgot to check in this file.  Oops!

llvm-svn: 161639
2012-08-09 23:10:57 +00:00
Johnny Chen e9a5627e7a rdar://problem/11457143 [ER] need "watchpoint command ..."
Add 'watchpoint command add/delete/list' to lldb, plus two .py test files.

llvm-svn: 161638
2012-08-09 23:09:42 +00:00
Johnny Chen 4ac1d9e160 Added back member initialization for m_batch_command_mode, which was most likely removed accidentally a while back.
The consequence occurred recently probably due to our swicth to build with c++11.
This fixed 3 test failures.

llvm-svn: 161625
2012-08-09 22:06:10 +00:00
Enrico Granata 17b1174911 <rdar://problem/11578397> Adding a new --summary-string option for the frame variable command which allows the user to provide a summary string with which he wants to display the variables without having to make a named summary first
llvm-svn: 161623
2012-08-09 22:02:51 +00:00
Jim Ingham 462227b08b Turn on function args by default in thread & frame formats.
<rdar://problem/11703715>

llvm-svn: 161611
2012-08-09 20:29:34 +00:00
Enrico Granata 7ec18e3d10 <rdar://problem/10449092> Adding a new uppercase hex format specifier. This commit also changes the short names for formats so that uppercase hex can be 'X', which was previously assigned to hex float. hex float now has no short name.
llvm-svn: 161606
2012-08-09 19:33:34 +00:00
Sean Callanan bcf897fa89 LLDB no longer prints <no result> by default if
the expression returns nothing.  There is now a
setting, "notify-void."  When the user enables
that setting, lldb prints (void) if an expression's
result is void.  Otherwise, lldb is silent.

<rdar://problem/11225150>

llvm-svn: 161600
2012-08-09 18:18:47 +00:00
Enrico Granata 2b2631c915 <rdar://problem/11505459> Stripping off the object's type from the output of the 'po' command
llvm-svn: 161592
2012-08-09 16:51:25 +00:00
Sean Callanan 1727742634 On Mac OS X, lldb will now build c++11 and use
libc++.  We also no longer use the GNU extensions
to C++ and C (we didn't use them anyway).

This also means that the LLVM we use must be
built with the new libc++.

I will commit llvm.zip next.

<rdar://problem/11930775>

llvm-svn: 161562
2012-08-09 01:32:13 +00:00
Sean Callanan ecb20887d8 Made lldb.swig include <string>, which it requires.
llvm-svn: 161560
2012-08-09 00:53:54 +00:00
Sean Callanan 9a028519e8 Removed explicit NULL checks for shared pointers
and instead made us use implicit casts to bool.
This generated a warning in C++11.

<rdar://problem/11930775>

llvm-svn: 161559
2012-08-09 00:50:26 +00:00
Sean Callanan 33baca29e5 When compiling with C++11, switch from
hash_multimap to unordered_multimap.

<rdar://problem/11930775>

llvm-svn: 161558
2012-08-09 00:46:55 +00:00
Sean Callanan 91e776d132 Now that the testcase is fixed, it is no longer
an expected failure.

llvm-svn: 161556
2012-08-09 00:40:16 +00:00
Enrico Granata 6656e6c2b6 <rdar://problem/12061386> Fixing data-formatter-cpp test case - previous version had an unfortunate dependency on the value of uninitialized memory
llvm-svn: 161555
2012-08-09 00:35:41 +00:00