Commit Graph

4966 Commits

Author SHA1 Message Date
Greg Clayton 0021bd2fe3 Remove comments and an extra print statement.
llvm-svn: 156651
2012-05-11 21:57:50 +00:00
Filipe Cabecinhas 1a96ef800b Make every Python API __len__() method return a PyIntObject.
swig 2.0+ seems to default to using PyLongObjects, but the __len__()
method _must_ return a PyIntObject.

llvm-svn: 156639
2012-05-11 20:39:42 +00:00
Filipe Cabecinhas 0bfed4bc7a Fix SBProcess::ReadMemory's typemap to handle PyLongObjects.
llvm-svn: 156638
2012-05-11 20:38:28 +00:00
Filipe Cabecinhas 0c543ea186 Make issue_11588/Test11588 work with a recent swig that converts ints to PyLongObjects
llvm-svn: 156637
2012-05-11 20:37:34 +00:00
Jim Ingham 923886ce2c Don't try to use "OkayToDiscard" to mean BOTH this plan is a user plan or not AND unwind on error.
rdar://problem/11419156

llvm-svn: 156627
2012-05-11 18:43:38 +00:00
Greg Clayton 4ae4160974 Fixed an issue in the platform options where if no architecture was specified where the platform would fail to select itself with something like:
(lldb) platfrom select remote-ios

llvm-svn: 156626
2012-05-11 18:37:58 +00:00
Jim Ingham db81e83c2e Add "echo" -> "script print".
llvm-svn: 156624
2012-05-11 18:01:15 +00:00
Greg Clayton 341039faca More fixes to "malloc_history".
llvm-svn: 156605
2012-05-11 02:42:36 +00:00
Greg Clayton 60bb58f669 Modified the symbolication.Image object to store its uuid as a uuid.UUID object and made an accessor for getting a normalized UUID value out of the image object.
Modified the crashlog darwin module to always create a uuid.UUID object when making the symbolication.Image objects. Also modified it to handle some more types of crash log files and improved the register reading for thread registers of crashed threads.

llvm-svn: 156596
2012-05-11 00:30:14 +00:00
Greg Clayton c0debe8566 Don't intercept the quit command and override what is was doing. This was causing the "lldb" command line to deadlock when the quit command was executed sometimes.
llvm-svn: 156595
2012-05-11 00:27:51 +00:00
Greg Clayton 7200ed1b94 "--stack-history" now works if you have MallocStackLogggingNoCompact defined in your app's environment.
llvm-svn: 156588
2012-05-10 23:37:52 +00:00
Greg Clayton 370f5fd20a Fixed a build error.
llvm-svn: 156586
2012-05-10 23:20:50 +00:00
Greg Clayton d9fc53509e Added the ability to get the stack history for a malloc block. This is a work in progress. Checking this in so I can work on it some more.
llvm-svn: 156584
2012-05-10 23:17:28 +00:00
Johnny Chen afc98a6d7e Make crashlog.py more robust when dealing with the "Version: ..." header from the crash log file.
rdar://problem/11428134

llvm-svn: 156581
2012-05-10 22:45:54 +00:00
Sean Callanan 6f3b394bfa Updated LLVM/Clang to force the record layout engine
to complete C++ classes before traversing their base
classes.

llvm-svn: 156570
2012-05-10 20:29:51 +00:00
Johnny Chen bbc00939f2 Sanity check the return value from SBSCopyApplicationDisplayIdentifiers() before calling CFArrayGetCount() on it.
rdar://problem/11331867

llvm-svn: 156562
2012-05-10 19:24:41 +00:00
Greg Clayton 3d081399f0 <rdar://problem/11388521>
Fixed a case where the install header phase in the Xcode project would not set the LLDB_VERSION #define correctly. It has now been fixed to key off of the CURRENT_PROJECT_VERSION which will get auto updated with "agvtool bump -all". This was done by adding a build setting to the install-headers makefile based target.

llvm-svn: 156535
2012-05-10 03:27:35 +00:00
Greg Clayton 5cc6ef9e89 Remove stuff from the xcscheme file that need not be checked in.
llvm-svn: 156533
2012-05-10 02:52:56 +00:00
Greg Clayton ba812f4284 <rdar://problem/11330621>
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
2012-05-10 02:52:23 +00:00
Jim Ingham 18de2fdc55 If the ObjC Step Through Trampoline plan causes a target crash, properly propagate the error back to
the controlling plans so that they don't lose control.

Also change "ThreadPlanStepThrough" to take the return StackID for its backstop breakpoint as an argument
to the constructor rather than having it try to figure it out itself, since it might get it wrong whereas
the caller always knows where it is coming from.

rdar://problem/11402287

llvm-svn: 156529
2012-05-10 01:35:39 +00:00
Sean Callanan 26e184d4e4 Added a #define of NULL to 0 to make NULL usable
in expressions.

llvm-svn: 156514
2012-05-09 21:27:03 +00:00
Johnny Chen fd02a89960 Make ctrl-c terminate the current input line and start an empty line, instead of the previous content.
rdar://problem/11412821

llvm-svn: 156510
2012-05-09 21:03:07 +00:00
Johnny Chen a21bd407e5 Option processing fix: should match '-F' exactly, instead.
llvm-svn: 156509
2012-05-09 21:00:03 +00:00
Filipe Cabecinhas 3a9b6e7140 Make redo.py more error-proof
Deal with being passed no parameters
Remove the infinite loop when it's passed something like --help

llvm-svn: 156504
2012-05-09 19:02:19 +00:00
Jim Ingham 5ce45fdfb1 Remove the string pool from the global destructor chain so it doesn't get yanked out from under us prematurely on exit.
rdar://problem/11358062

llvm-svn: 156496
2012-05-09 18:37:10 +00:00
Jim Ingham 8499e1a4cb Print out a notification when the process of a target other than the currently selected target stops.
llvm-svn: 156433
2012-05-08 23:06:07 +00:00
Enrico Granata a777dc2abe <rdar://problem/11338654> Fixing a bug where having a summary for a bitfield without a format specified would in certain cases crash LLDB - This has also led to refactoring the by-type accessors for the data formatter subsystem. These now belong in our internal layer, and are just invoked by the public API stratum
llvm-svn: 156429
2012-05-08 21:49:57 +00:00
Han Ming Ong b9c53daa55 <rdar://problem/11400476>
On Lion, because the rights initially doesn't exist in /etc/authorization, if an admin user logs in and uses lldb within the first 5 minutes, it is possible to do AuthorizationCopyRights on LaunchUsingXPCRightName and get the rights back. As another security measure, we make sure that the LaunchUsingXPCRightName rights actually exists.

Removed Xcode as the user of the XPC service to shrink the security surface area.

llvm-svn: 156424
2012-05-08 21:35:52 +00:00
Han Ming Ong 222bb03518 <rdar://problem/11408853>
We make sure that if the user cancels out of the authentication dialog to add 'com.apple.lldb.LaunchUsingXPC' rights to /etc/authorization, we don't try to do AuthorizationCopyRights.

As well, refactored a bit so that control flow is easier to read for other folks. Added more comments.

llvm-svn: 156423
2012-05-08 21:32:32 +00:00
Enrico Granata 07a4ac22ed <rdar://problem/11239650> Fixing a bug where the SetValueFromCString() method failed to operate on dynamic values. The fix consists in making the set operation fall through to the parent. We only actually allow this if the dynamic value is at a 0-offset from the parent, or the new value is 0. Other scenarios would need agreement on the actual meaning of the set operation (do we keep offsetting? do we just assume the user knows what they are doing?) so we prevent them, and let the expression parser deal with the complexity
llvm-svn: 156422
2012-05-08 21:25:06 +00:00
Jim Ingham 5bad4799a3 Fixing some indentation.
llvm-svn: 156412
2012-05-08 20:05:08 +00:00
Enrico Granata 9123950ab1 A simple implementation of a summary and synthetic children providers for LLDB-specific shared pointers - This could be generalized to work with C++11 shared pointers with relative ease
llvm-svn: 156410
2012-05-08 19:21:13 +00:00
Enrico Granata 601ccb583f Removing spurious friend declaration
llvm-svn: 156398
2012-05-08 18:49:36 +00:00
Enrico Granata 886147f0ac First part of a fix to make GetNonSyntheticValue() work correctly
llvm-svn: 156397
2012-05-08 18:47:08 +00:00
Greg Clayton af6f2755ab <rdar://problem/10605072>
Fixed the command callback override lookup function so we can now override the "process launch" command  (or any other multi-word commands).

llvm-svn: 156368
2012-05-08 04:29:20 +00:00
Jason Molenda b2c7b92ae8 bump TOT version number to lldb-146 to match the checkin on the branch.
llvm-svn: 156359
2012-05-08 02:54:06 +00:00
Greg Clayton 7051231709 <rdar://problem/11358639>
Switch over to the "*-apple-macosx" for desktop and "*-apple-ios" for iOS triples.

Also make the selection process for auto selecting platforms based off of an arch much better.

llvm-svn: 156354
2012-05-08 01:45:38 +00:00
Johnny Chen 6943e7c569 Add clarification comments.
llvm-svn: 156350
2012-05-08 00:43:20 +00:00
Sean Callanan 0a2722d63d Updated LLVM to take a fix for disassembly of
Thumb branch operands.

llvm-svn: 156344
2012-05-08 00:01:21 +00:00
Johnny Chen 4ab2e6be38 Updated to a more meaningful macro name.
llvm-svn: 156340
2012-05-07 23:23:41 +00:00
Johnny Chen 5ec8fcbf0c Fix the problem that 'help breakpoint set' is printing a lot of redundant lines.
Correctly specify the LLDB_OPT_SET's that the 'shlib' command option belongs to by using a newly added macro like this:

    #define LLDB_OPT_NOT_10 ( LLDB_OPT_SET_FROM(1, 10) & ~LLDB_OPT_SET_10 )

rdar://problem/11393864

llvm-svn: 156337
2012-05-07 23:04:49 +00:00
Johnny Chen ddb149069e Add an -F option to the redo.py script to selectively re-run only those failed sessions whose filenames contain the component(s)
specified.  For example:

    ./redo.py -F x86_64 -n 2012-05-07-15_28_24

will redo the failed sessions under the 2012-05-07-15_28_24 directory, but only for session names which contain 'x86_64' in it.

llvm-svn: 156335
2012-05-07 22:59:00 +00:00
Johnny Chen 5a4b4b86d6 Move the el_source() call after the section of code which sets up the default "ctrl-r" and "ctrl-w" bindings
so that user-provided .editrc has a chance to override the lldb's default key bindings.

llvm-svn: 156314
2012-05-07 18:18:08 +00:00
Sean Callanan bcaa94db6c Updated LLVM to fix bad disassembly of operands
and occasionally failure to recognize instructions.
This problem affects ARM and Thumb BLX instructions.

llvm-svn: 156307
2012-05-07 16:50:20 +00:00
Filipe Cabecinhas f86cf78190 Remove repeated word.
llvm-svn: 156300
2012-05-07 09:30:51 +00:00
Filipe Cabecinhas 75bc95ec28 Fixed some strncat/strlcat uses.
llvm-svn: 156264
2012-05-06 17:56:42 +00:00
Johnny Chen 66b7c59593 Jason Molenda convinced me that we should make ctrl-w on the command line bind to ed-delete-prev-word.
If you have ctrl-w key binding specified with your .editrc file, it will be overridden with ed-delete-prev-word. :-)

llvm-svn: 156230
2012-05-05 04:44:12 +00:00
Jim Ingham 444717b318 Missed a few uses of Mutex::GetMutex in template functions that don't seem to get instantiated on the Mac OS X build,
but were causing build failures on Linux.

llvm-svn: 156224
2012-05-04 23:54:57 +00:00
Sean Callanan 247e62a706 Added an "attach" alias as promised on the web page.
llvm-svn: 156223
2012-05-04 23:15:02 +00:00
Jim Ingham 10ebffa48a Don't expose the pthread_mutex_t underlying the Mutex & Mutex::Locker classes.
No one was using it and Locker(pthread_mutex_t *) immediately asserts for 
pthread_mutex_t's that don't come from a Mutex anyway.  Rather than try to make
that work, we should maintain the Mutex abstraction and not pass around the
platform implementation...

Make Mutex::Locker::Lock take a Mutex & or a Mutex *, and remove the constructor
taking a pthread_mutex_t *.  You no longer need to call Mutex::GetMutex to pass
your mutex to a Locker (you can't in fact, since I made it private.)

llvm-svn: 156221
2012-05-04 23:02:50 +00:00