Commit Graph

4378 Commits

Author SHA1 Message Date
Enrico Granata daa0ac48e6 <rdar://problem/12582328>
If you want to define a formatter for "array of Foo of any size", ordinarily you would say

-x "Foo \[[0-9]+\]"

this checkin allows you to instead say "Foo[]" (or "Foo []") and LLDB will automatically create the regular expression and add the -x flag on your behalf

llvm-svn: 183272
2013-06-04 22:25:36 +00:00
Enrico Granata 983920d1a9 <rdar://problem/14003462>
Formatters for unsigned char* and const variant

llvm-svn: 183254
2013-06-04 21:53:55 +00:00
Greg Clayton 76ea03ea7b Add a more clear explanation of what is missing for core files with no LC_THREAD load commands.
llvm-svn: 183253
2013-06-04 21:48:36 +00:00
Greg Clayton 9645e82ce2 Make sure a core file has thread contexts before we try and load it.
llvm-svn: 183252
2013-06-04 21:34:37 +00:00
Greg Clayton e86cef633b Fixed printf build warning.
llvm-svn: 183250
2013-06-04 21:30:42 +00:00
Greg Clayton a3f14d8bf1 <rdar://problem/13941992>
Accept mach-o files with bad segments. Many core files are not created correctly and we should still be able to glean any information we can from them.

llvm-svn: 183247
2013-06-04 20:27:06 +00:00
Daniel Malea 6f0a5edb3f More minor FreeBSD fixes.
- link libexecinfo (as libc is missing backtrace())
- enable FreeBSD-specific plugins

Patch by Ed Maste!

llvm-svn: 183233
2013-06-04 15:59:01 +00:00
Jim Ingham 60c4118c88 If ThreadPlanCallFunction hasn't set its notion of the "real stop info" yet, just return the current PrivateStopInfo.
Also renamed a few more places where we were using StopReason in functions that were returning StopInfo's.

<rdar://problem/14042692>

llvm-svn: 183177
2013-06-04 01:40:51 +00:00
Daniel Malea f051dbce73 Fix crash (in optimized builds) due to invalid metadata operand
- ConstantDataArray is not a valid MDNode operand
- encode function-name strings in metadata by wrapping in an MDString instead

- should resolve reported by http://llvm-jenkins.debian.net/job/llvm-toolchain-quantal-binaries/architecture=amd64,distribution=quantal/173/

llvm-svn: 183153
2013-06-03 20:45:54 +00:00
Matt Kopec edee182bef Fix FreeBSD build due to previous changes to ProcessMonitor::Detach.
llvm-svn: 183150
2013-06-03 19:48:53 +00:00
Jim Ingham 35579dde40 Fix a couple of error message typos.
llvm-svn: 183145
2013-06-03 19:34:01 +00:00
Matt Kopec ef14371d3f Fix various build warnings.
llvm-svn: 183140
2013-06-03 18:00:07 +00:00
Matt Kopec 6f961239ae Fix setting of watchpoints on inferior thread creation for Linux.
llvm-svn: 183139
2013-06-03 17:40:20 +00:00
Ashok Thirumurthi 880728f3eb Matched a vector new with vector delete.
Thanks to Daniel and valgrind.

llvm-svn: 183110
2013-06-03 15:53:40 +00:00
Matt Kopec 085d6cec1a Add ability to attach/detach to multi-threaded inferiors on Linux.
All running threads will be detected and stopped on attach and all threads get resumed on detach.

llvm-svn: 183049
2013-05-31 22:00:07 +00:00
Daniel Malea c91e4ab26e Use C-style include to match style in file (instead of C++ style)
- as per review comment from Dimitry Andric!

llvm-svn: 183039
2013-05-31 20:21:38 +00:00
Daniel Malea 132c4a266c CMake FreeBSD fix: add missing Process plugin directory
Patch by Ed Maste!

llvm-svn: 183038
2013-05-31 20:16:40 +00:00
Han Ming Ong 79371ceedf <rdar://problem/13752848>
Add 'JoinExistingSession' to XPC for root debugging.

llvm-svn: 183037
2013-05-31 20:15:19 +00:00
Daniel Malea e376a65182 FreeBSD cmake build fixes.
- missing #include <cstdlib> in Mangled.cpp
- missing include dirs in FreeBSD CMakeLists.txt

Patch by Ed Maste!

llvm-svn: 183032
2013-05-31 19:24:53 +00:00
Enrico Granata b294fd2037 <rdar://problem/14035604>
Fixing an issue where formats would not propagate from parents to children in all cases
Details follow:
an SBValue has children and those are fetched along with their values
Now, one calls SBValue::SetFormat() on the parent
Technically, the format choices should propagate onto the children (see ValueObject::GetFormat())
But if the children values are already fetched, they won't notice the format change and won't update themselves
This commit fixes that by making ValueObject::GetValueAsCString() check if any format change intervened from the previous call to the current one
A test case is also added

llvm-svn: 183030
2013-05-31 19:18:19 +00:00
Enrico Granata 39d5141085 Small code cleanups
llvm-svn: 183024
2013-05-31 17:43:40 +00:00
Sean Callanan 7d01ddd6f8 Fixed value evaluation to handle null constants.
<rdar://problem/14005311>

llvm-svn: 183022
2013-05-31 17:29:03 +00:00
Enrico Granata 1c333d071f An NSData with 0 bytes in it would report a summary of “0 byte”
Making sure that I get my English right by saying “0 bytes” instead

llvm-svn: 182978
2013-05-31 01:14:22 +00:00
Enrico Granata e0c70f1b2c <rdar://problem/11109316>
command script import now does reloads - for real
If you invoke command script import foo and it detects that foo has already been imported, it will
 - invoke reload(foo) to reload the module in Python
 - re-invoke foo.__lldb_init_module
 This second step is necessary to ensure that LLDB does not keep cached copies of any formatter, command, ... that the module is providing

Usual caveats with Python imports persist. Among these:
 - if you have objects lurking around, reloading the module won't magically update them to reflect changes
 - if module A imports module B, reloading A won't reload B
These are Python-specific issues independent of LLDB that would require more extensive design work

The --allow-reload (-r) option is maintained for compatibility with existing scripts, but is clearly documented as redundant - reloading is always enabled whether you use it or not

llvm-svn: 182977
2013-05-31 01:03:09 +00:00
Greg Clayton 83793fc188 <rdar://problem/13956179>
Cleaned up the thread updating code in the OperatingSystemPython class. It doesn't need to clear the "new_thread_list" anymore as it is always empty. 

It also now assigns the "core_thread_list" to "new_thread_list" if no threads are detected through python.

llvm-svn: 182893
2013-05-29 23:31:14 +00:00
Greg Clayton 086e085efa Remove unused variable.
llvm-svn: 182892
2013-05-29 23:22:22 +00:00
Sean Callanan 467441d511 Error out if the expression for a breakpoint
condition doesn't return a result, instead
of blindly trying to use that result.

<rdar://problem/14009519>

llvm-svn: 182875
2013-05-29 20:22:18 +00:00
Jim Ingham cbf7e26b3b For "expr", say what the timeout units are in the help string.
llvm-svn: 182873
2013-05-29 19:40:14 +00:00
Andrew Kaylor 93132f504f Adding support for stopping all threads of multithreaded inferiors on Linux. Also adding multithreaded test cases.
llvm-svn: 182809
2013-05-28 23:04:25 +00:00
Enrico Granata 2db281e910 <rdar://problem/13863031>
Giving a timeout for the call to NSPrintForDebugger() that happens when you “po” objects

This is a temporary workaround until a more detailed solution to the general problem of canceling actions is found

llvm-svn: 182782
2013-05-28 18:02:49 +00:00
Daniel Malea d77e9d4565 Mac OS X CMake fix: generate LLDB version from xcodeproj
- This resolves the remaining issues related to building lldb utility/dylib
- TODO: fix up debugserver build

Patch by Ahmed Bougacha!

llvm-svn: 182751
2013-05-28 03:44:37 +00:00
Filipe Cabecinhas 251f496578 lldbPluginOSDarwinKernel doesn't exist.
llvm-svn: 182687
2013-05-24 22:46:06 +00:00
Filipe Cabecinhas f104a830d4 Update countTrailingZeros function usage to match llvm's r182667.
llvm-svn: 182683
2013-05-24 22:24:17 +00:00
Sean Callanan 0b342b6ddf Fixed signed operations in the IR interpreter.
Scalar now can make itself signed if needed.

<rdar://problem/13977632>

llvm-svn: 182668
2013-05-24 20:36:56 +00:00
Ashok Thirumurthi 780593580f Added a parameter for relocation info to keep lldb in step with llvm due to r182625,
which takes a first step towards symbolization of disassembled instructions.

llvm-svn: 182650
2013-05-24 15:55:54 +00:00
Greg Clayton 7bcb93d5a5 <rdar://problem/13643315>
Fixed performance issues that arose after changing SBTarget, SBProcess, SBThread and SBFrame over to using a std::shared_ptr to a ExecutionContextRef. The ExecutionContextRef doesn't store a std::weak_ptr to a stack frame because stack frames often get replaced with new version, so it held onto a StackID object that would allow us to ask the thread each time for the frame for the StackID. The linear function was too slow for large recursive stacks. We also fixed an issue where anytime the std::shared_ptr<ExecutionContextRef> in any SBTarget, SBProcess, SBThread objects was turned into an ExecutionContext object, it would try to resolve all items in the ExecutionContext which are shared pointers. Even if the StackID in the ExecutionContextRef was invalid, it was looking through all frames in every thread. This causes a lot of unnecessary frame accesses.

llvm-svn: 182627
2013-05-24 00:58:29 +00:00
Filipe Cabecinhas 477d86d84d Adds PT_TLS and PT_GNU_EH_FRAME names to DumpELFProgramHeaders
llvm-svn: 182619
2013-05-23 23:01:14 +00:00
Michael Sartain c836ae7d36 ObjectFileELF::GetModuleSpecifications on Linux should work now.
Which means "platform process list" should work and list the architecture.
We are now parsing the elf build-id if it exists, which should allow us to load stripped symbols (looking at that next).

llvm-svn: 182610
2013-05-23 20:57:03 +00:00
Michael Sartain c3ce7f2740 Add ${ansi.XX} parsing to lldb prompt, use-color setting, and -no-use-colors command line options.
settings set use-color [false|true]
settings set prompt "${ansi.bold}${ansi.fg.green}(lldb)${ansi.normal} "
also "--no-use-colors" on the command prompt

llvm-svn: 182609
2013-05-23 20:47:45 +00:00
Greg Clayton cc24775b42 <rdar://problem/13966084>
Make sure to not call "regexec" from <regex.h> with a NULL C string, otherwise we can crash.

llvm-svn: 182607
2013-05-23 20:27:15 +00:00
Greg Clayton d389cc3a2e Don't compare 4 characters on a 2 character string.
llvm-svn: 182540
2013-05-22 23:36:10 +00:00
Greg Clayton 43d8279ffd Cleaned up the File API a bit.
llvm-svn: 182538
2013-05-22 23:30:09 +00:00
Greg Clayton fdbdc9c0ff Fixed a file leak introduced with my last checkin. Also be sure to include <stdio.h> just in case.
llvm-svn: 182537
2013-05-22 23:29:16 +00:00
Greg Clayton 62f80036be Added a new "lldb" log channel named "os" for the OperatingSystem plug-ins to use.
Added logging for the OS plug-in python objects in OperatingSystemPython so we can see the python dictionary returned from the plug-in when logging is enabled.

llvm-svn: 182530
2013-05-22 23:04:27 +00:00
Sean Callanan fbf5c682cb Fixed a bug where persistent variables did not
live as long as they needed to.  This led to
equality tests involving persistent variables
often failing or succeeding when they had no
business doing so.

To do this, I introduced the ability for a
memory allocation to "leak" - that is, to
persist in the process beyond the lifetime of
the expression.  Hand-declared persistent
variables do this now.

<rdar://problem/13956311>

llvm-svn: 182528
2013-05-22 22:49:06 +00:00
Greg Clayton a1b5dd9a20 <rdar://problem/13956179>
Fixed ProcessMachCore to be able to locate the main executeable in the core file even if it doesn't start at a core file address range boundary. Prior to this we only checked the first bytes of each range in the core file for mach_kernel or dyld. Now we still do this, but if we don't find the mach_kernel or dyld anywhere, we go through all core file ranges and check every 0x1000 to see if we can find dyld or the mach_kernel.

Now that we can properly detect the mach_kernel at any address, we don't need to call "DynamicLoaderDarwinKernel::SearchForDarwinKernel(Process*)" anymore.

llvm-svn: 182513
2013-05-22 21:00:49 +00:00
Greg Clayton 217b28baee <rdar://problem/13880690>
Lock the lldb_private::Module mutex while tearing down the module to make sure we don't get clients accessing the contents on a module as it is going away.

llvm-svn: 182511
2013-05-22 20:13:22 +00:00
Greg Clayton 8caea6db71 <rdar://problem/13455021>
Another fix to make sure that if we aren't able to extract an object file for any reason, we don't crash when trying to parse the debug map info.

llvm-svn: 182441
2013-05-22 00:10:28 +00:00
Greg Clayton 80e6c043e9 <rdar://problem/13455021>
lldb crashes with universal file containing skinny BSD archives when doing DWARF with .o file debugging.

llvm-svn: 182437
2013-05-21 23:36:34 +00:00
Enrico Granata 4e284caa9b Adding a newline for better overall readability
llvm-svn: 182434
2013-05-21 22:34:17 +00:00