summaryrefslogtreecommitdiffstats
path: root/lldb
Commit message (Collapse)AuthorAgeFilesLines
* [lldb] [cmake] Support linking against clang-cpp dylibMichal Gorny2019-10-0412-27/+50
| | | | | | | | | Link against clang-cpp dylib rather than split libs when CLANG_LINK_CLANG_DYLIB is enabled. Differential Revision: https://reviews.llvm.org/D68456 llvm-svn: 373734
* [lldb] Get the TargetAPI lock in SBProcess::IsInstrumentationRuntimePresentRaphael Isemann2019-10-041-0/+3
| | | | | | | | | | | | | | | | | | | Summary: We should get the TargetAPI lock here to prevent the process of being destroyed while we are in the function. Thanks Jim for explaining what's going on. Fixes rdar://54424754 Reviewers: jingham Reviewed By: jingham Subscribers: JDevlieghere, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D67831 llvm-svn: 373725
* [lldb] Fix that 'ninja clean' breaks the build by deleting debugserver_vers.cRaphael Isemann2019-10-041-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | Summary: We mark debugserver_vers.c as a generated file in CMake. This means that when we run `ninja clean` we end up deleting that file, but any following `ninja` invocation will fail due to the file missing. The file can't be generated as `ninja` doesn't know it has to rerun CMake to create the file. Turns out that marking the output of configure_file as generated is wrong as explained in this bug report: https://gitlab.kitware.com/cmake/cmake/issues/18032 This patch just removes that property. The only side effect of this seems to be that this file maybe shows up in your IDE when opening our CMake project, but that seems like a small sacrifice. This patch can be quickly tested by running `ninja clean ; ninja lldbDebugserverCommon`. Before this patch the build will fail due to debugserver_vers.c missing. Reviewers: JDevlieghere, labath Reviewed By: labath Subscribers: mgorny, abidh, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68376 llvm-svn: 373723
* [lldb] Fix -Wreorder-ctor in r373673Sam McCall2019-10-041-13/+12
| | | | llvm-svn: 373721
* [lldb] Fix typo in r373675Sam McCall2019-10-041-1/+1
| | | | llvm-svn: 373719
* [lldb][modern-type-lookup] No longer import temporary declarations into the ↵Raphael Isemann2019-10-043-98/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | persistent AST Summary: As we figured out in D67803, importing declarations from a temporary ASTContext that were originally from a persistent ASTContext causes a bunch of duplicated declarations where we end up having declarations in the target AST that have no associated ASTImporter that can complete them. I haven't figured out how/if we can solve this in the current way we do things in LLDB, but in the modern-type-lookup this is solvable as we have a saner architecture with the ExternalASTMerger. As we can (hopefully) make modern-type-lookup the default mode in the future, I would say we try fixing this issue here. As we don't use the hack that was reinstated in D67803 during modern-type-lookup, the test case for this is essentially just printing any kind of container in `std::` as we would otherwise run into the issue that required a hack like D67803. What this patch is doing in essence is that instead of importing a declaration from a temporary ASTContext, we instead check if the declaration originally came from a persistent ASTContext (e.g. the debug information) and we directly import from there. The ExternalASTMerger is already connected with ASTImporters to these different sources, so this patch is essentially just two parts: 1. Mark our temporary ASTContext/ImporterSource as temporary when we import from the expression AST. 2. If the ExternalASTMerger sees we import from the expression AST, instead of trying to import these temporary declarations, check if we can instead import from the persistent ASTContext that is already connected. This ensures that all records from the persistent source actually come from the persistent source and are minimally imported in a way that allows them to be completed later on in the target AST. The next step is to run the ASTImporter for these temporary expressions with the MinimalImport mode disabled, but that's a follow up patch. This patch fixes most test failures with modern-type-lookup enabled by default (down to 73 failing tests, which includes the 22 import-std-module tests which need special treatment). Reviewers: shafik, martong Reviewed By: martong Subscribers: aprantl, rnkovacs, christof, abidh, JDevlieghere, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68326 llvm-svn: 373711
* Revert "Explicitly set entry point arch when it's thumb"Antonio Afonso2019-10-043-179/+0
| | | | | | | | Backing out because SymbolFile/Breakpad/symtab.test is failing and it seems to be a legit issue. Will investigate. This reverts commit 72153f95ee4c1b52d2f4f483f0ea4f650ec863be. llvm-svn: 373687
* [Python] Remove unused variableJonas Devlieghere2019-10-041-1/+0
| | | | | | warning: unused variable 'py_func_obj' [-Wunused-variable] PyObject *py_func_obj = m_py_obj; llvm-svn: 373686
* Properly handle instantiation-dependent array bounds.Richard Smith2019-10-041-2/+2
| | | | | | | | | We previously failed to treat an array with an instantiation-dependent but not value-dependent bound as being an instantiation-dependent type. We now track the array bound expression as part of a constant array type if it's an instantiation-dependent expression. llvm-svn: 373685
* Explicitly set entry point arch when it's thumbAntonio Afonso2019-10-043-0/+179
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: I found a case where the main android binary (app_process32) had thumb code at its entry point but no entry in the symbol table indicating this. This made lldb set a 4 byte breakpoint at that address (we default to arm code) instead of a 2 byte one (like we should for thumb). The big deal with this is that the expression evaluator uses the entry point as a way to know when a JITed expression has finished executing by putting a breakpoint there. Because of this, evaluating expressions on certain android devices (Google Pixel something) made the process crash. This was fixed by checking this specific situation when we parse the symbol table and add an artificial symbol for this 2 byte range and indicating that it's arm thumb. I created 2 unit tests for this, one to check that now we know that the entry point is arm thumb, and the other to make sure we didn't change the behaviour for arm code. I also run the following on the command line with the `app_process32` where I found the issue: **Before:** ``` (lldb) dis -s 0x1640 -e 0x1644 app_process32[0x1640]: .long 0xf0004668 ; unknown opcode ``` **After:** ``` (lldb) dis -s 0x1640 -e 0x1644 app_process32`: app_process32[0x1640] <+0>: mov r0, sp app_process32[0x1642]: andeq r0, r0, r0 ``` Reviewers: clayborg, labath, wallace, espindola Subscribers: srhines, emaste, arichardson, kristof.beyls, MaskRay, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68069 llvm-svn: 373680
* Python3 doesn't seem to allow you to tell whether an object is a classJim Ingham2019-10-033-5/+2
| | | | | | | | | PyClass_Check and everything it relied on seems gone from Python3.7. So I won't check whether it is a class first... Also cleaned up a couple of warnings. llvm-svn: 373679
* Forgot to change the header guards on OptionGroupPythonClassWithDict.Jim Ingham2019-10-032-4/+5
| | | | | | I think that's what is confusing the modules build on the bots. llvm-svn: 373677
* Pass an SBStructuredData to scripted ThreadPlans on use.Jim Ingham2019-10-0322-137/+336
| | | | | | | | | | This will allow us to write reusable scripted ThreadPlans, since you can use key/value pairs with known keys in the plan to parametrize its behavior. Differential Revision: https://reviews.llvm.org/D68366 llvm-svn: 373675
* Break out the Python class & key/value options into a separate OptionGroup.Jim Ingham2019-10-038-41/+224
| | | | | | | | | | Use this in the scripted breakpoint command. Added some tests for parsing the key/value options. This uncovered a bug in handling parsing errors mid-line. I also fixed that bug. Differential Revision: https://reviews.llvm.org/D68363 llvm-svn: 373673
* [process list] make the TRIPLE column widerWalter Erquinigo2019-10-032-14/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: Now that `process list` works better on the android platform, the arch aarch64-unknown-linux-android appears quite often. The existing printed width of the TRIPLE column is not long enough, which doesn't look okay. E.g. ``` 1561 1016 aarch64-unknown-linux-android ip6tables-restore 1999 1 aarch64-unknown-linux-android tlc_server 2332 982 com.android.systemui 2378 983 webview_zygote ``` Now, after adding 6 spaces, it looks better ``` PID PARENT USER TRIPLE NAME ====== ====== ========== ============================== ============================ ... 1561 1016 aarch64-unknown-linux-android ip6tables-restore 1999 1 aarch64-unknown-linux-android tlc_server 2332 982 com.android.systemui 2378 983 webview_zygote 2448 982 com.sec.location.nsflp2 ``` Reviewers: clayborg, labath, xiaobai, aadsm Reviewed By: labath Subscribers: srhines, kristof.beyls, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68291 llvm-svn: 373670
* [lldb] Remove unused variables.Haibo Huang2019-10-031-5/+0
| | | | | | Fixes the comment in https://reviews.llvm.org/D67993 llvm-svn: 373669
* [lldb] Calculate relative path for symbol linksHaibo Huang2019-10-031-17/+4
| | | | | | | | | | | | | | Summary: This replaces the hard coded path. Reviewers: labath, mgorny Subscribers: lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D67993 llvm-svn: 373668
* [test] Disable TestCustomShell on LinuxJonas Devlieghere2019-10-031-0/+4
| | | | | | | ShellExpandArguments is unimplemented on Linux. I need to come up with another way to test this on Linux. llvm-svn: 373662
* [JSON] Don't wrap json::Array in a value (NFC)Jonas Devlieghere2019-10-031-3/+3
| | | | | | | | There's no need to wrap the just-constructed json::Array in a json::Value, we can just return that and pass ownership to the raw_ostream. llvm-svn: 373656
* [Host] Return the user's shell from GetDefaultShellJonas Devlieghere2019-10-033-9/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | LLDB handles shell expansion by running lldb-argdumper under a shell. Currently, this is always /bin/sh on POSIX. This potentially leads to different behavior between lldb and the user's current shell. Here's an example of different expansions between shells: $ /bin/bash -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config={Options:[key:foo_key]} -config={Options:[value:foo_value]} $ /bin/zsh -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' zsh:1: no matches found: -config={Options:[key:foo_key]} $ /bin/sh -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config={Options:[key:foo_key]} -config={Options:[value:foo_value]} $ /bin/fish -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config=Options:[key:foo_key] -config=Options:[value:foo_value] To reduce surprises, this patch returns the user's current shell. It first looks at the SHELL environment variable. If that isn't set, it'll ask for the user's default shell. Only if that fails, we'll fallback to /bin/sh, which should always be available. Differential revision: https://reviews.llvm.org/D68316 llvm-svn: 373644
* "Fix" TestFileHandle.py on non-darwin platformsPavel Labath2019-10-031-0/+8
| | | | | | | | | | | | | | | | | | This test exposed a very long standing issue that the python file objects returned by the FILE* typemap were unusable on non-darwin platforms. The reason they work on darwin is that they rely on a non-standard extension to fetch the "mode" of a FILE* object. On other platforms, this code was #ifdefed out, and so we were returning an empty mode. As there's no portable way to get this information, I just change the non-darwin path to return "r+", which should permit both reading and writing operations on the object. If the underlying file descriptor turns out to be incompatible with this mode, the operating system should return EBADF (or equivalent), instead of the "file not open for XXX" error from python. llvm-svn: 373573
* Fix a use-after-free in GDBRemoteCommunicationServerLLGSPavel Labath2019-10-031-1/+2
| | | | | | | | | | | | Although it's called "GetString", StreamString::GetString actually returns a StringRef. Creating a json object with a StringRef does not make a copy, which means the StringRef will be dangling as soon as the underlying stream is destroyed. Add a .str() to force the json object to hold a copy of the string. This fixes nearly every test on linux. llvm-svn: 373572
* factor out an abstract base class for FileLawrence D'Anna2019-10-0317-262/+367
| | | | | | | | | | | | | | | | | | | | | | | | | Summary: This patch factors out File as an abstract base class and moves most of its actual functionality into a subclass called NativeFile. In the next patch, I'm going to be adding subclasses of File that don't necessarily have any connection to actual OS files, so they will not inherit from NativeFile. This patch was split out as a prerequisite for https://reviews.llvm.org/D68188 Reviewers: JDevlieghere, jasonmolenda, labath Reviewed By: labath Subscribers: lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68317 llvm-svn: 373564
* SBDebugger::SetInputFile, SetOutputFile, etc.Lawrence D'Anna2019-10-039-35/+275
| | | | | | | | | | | | | | | | | | | | | Summary: Add new methods to SBDebugger to set IO files as SBFiles instead of as FILE* streams. In future commits, the FILE* methods will be deprecated and these will become the primary way to set the debugger I/O streams. Reviewers: JDevlieghere, jasonmolenda, labath Reviewed By: labath Subscribers: lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D68181 llvm-svn: 373563
* new api class: SBFileLawrence D'Anna2019-10-0316-25/+428
| | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: SBFile is a scripting API wrapper for lldb_private::File This is the first step in a project to enable arbitrary python io.IOBase file objects -- including those that override the read() and write() methods -- to be used as the main debugger IOStreams. Currently this is impossible because python file objects must first be converted into FILE* streams by SWIG in order to be passed into the debugger. full prototype: https://github.com/smoofra/llvm-project/tree/files Reviewers: JDevlieghere, jasonmolenda, zturner, jingham, labath Reviewed By: labath Subscribers: labath, mgorny, lldb-commits Tags: #lldb Differential Revision: https://reviews.llvm.org/D67793 llvm-svn: 373562
* [ARM64] XPC services are unsupported on device.Davide Italiano2019-10-021-2/+2
| | | | | | | | While around, clean up support for a 8 years old OS. <rdar://problem/55916729> llvm-svn: 373510
* [RegisterContextDarwin_arm64] Include the headers for getsysctlbyname.Davide Italiano2019-10-021-0/+5
| | | | | | | | This code is only used under __arm64__, use the correct guard. <rdar://problem/55916729> llvm-svn: 373509
* [ObjectFileMachO] FileSpec::SetFile() now takes the style as arg.Davide Italiano2019-10-021-1/+1
| | | | | | | | | Another block that's only compiled on __arm64__ and wasn't updated. <rdar://problem/55916729> llvm-svn: 373508
* [ObjectFileMachO] Catch up with FileDesc changes.Davide Italiano2019-10-021-3/+3
| | | | | | | | This didn't show up because nobody built __arm64__ in a while. <rdar://problem/55916729> llvm-svn: 373507
* [JSON] Remove Utility/JSON.{h|cpp}Jonas Devlieghere2019-10-025-861/+0
| | | | | | | | | | | | | This patch is the final step in my quest to get rid of the JSON parser in LLDB. Vedant's coverage report [1] shows that it was mostly untested. Furthermore, the LLVM implementation has a much nicer API and using it means one less thing to maintain for LLDB. [1] http://lab.llvm.org:8080/coverage/coverage-reports/index.html Differential revision: https://reviews.llvm.org/D68305 llvm-svn: 373501
* [JSON] Use LLVM's library for encoding JSON in ↵Jonas Devlieghere2019-10-021-20/+17
| | | | | | | | | | | GDBRemoteCommunicationServerCommon This patch replaces the LLDB's JSON implementation with the one from LLVM in GDBRemoteCommunicationServerCommon. Differential revision: https://reviews.llvm.org/D68304 llvm-svn: 373500
* [JSON] Use LLVM's library for encoding JSON in ↵Jonas Devlieghere2019-10-021-11/+10
| | | | | | | | | | | GDBRemoteCommunicationServerPlatform This patch replaces the LLDB's JSON implementation with the one from LLVM in GDBRemoteCommunicationServerPlatform. Differential revision: https://reviews.llvm.org/D68302 llvm-svn: 373499
* [JSON] Use LLVM's library for encoding JSON in GDBRemoteCommunicationClientJonas Devlieghere2019-10-021-10/+10
| | | | | | | | | This patch replaces the LLDB's JSON implementation with the one from LLVM in GDBRemoteCommunicationClient. Differential revision: https://reviews.llvm.org/D68301 llvm-svn: 373498
* [JSON] Use LLVM's library for encoding JSON in GDBRemoteCommunicationServerLLGSJonas Devlieghere2019-10-021-48/+51
| | | | | | | | | This patch replaces the LLDB's JSON implementation with the one from LLVM in GDBRemoteCommunicationServerLLGS. Differential revision: https://reviews.llvm.org/D68299 llvm-svn: 373497
* [lldb] Fix evaluation of nested classes with parent from other CURaphael Isemann2019-10-026-0/+83
| | | | | | | | | | | | | | This makes sure that we associate DIEs that are imported from other CUs with the appropriate decl context. Without this fix, nested classes can be dumped directly into their CU context if their parent was imported from another CU. Reviewed By: teemperor, labath Differential Revision: https://reviews.llvm.org/D68278 Patch by Jaroslav Sevcik! llvm-svn: 373470
* [lldb][NFC] Remove ClangASTContext::ClearRaphael Isemann2019-10-022-15/+0
| | | | | | | | | | We now only use this function directly after initialization. As Clear() resets the ASTContext back to its initial state, this is just a no-op. There are no other users for this and we no longer can set the ASTContext after construction, so Clear has no useful purpose anymore. It's also mostly copy-pasted from Finalize(). llvm-svn: 373460
* [lldb][NFC] Create the ASTContext in ClangASTContext exactly once.Raphael Isemann2019-10-023-63/+78
| | | | | | | | | | | | | | | Reason for this patch is the Ssame reason as for the previous patches: Having a ClangASTContext and being able to switch the associated ASTContext isn't a use case we have (or should have), so let's simplify all this code. This way it becomes clearer in what order we initialize data structures. The DWARFASTParserClangTests changes are necessary as the test is using a ClangASTContext but relied on the fact that no called function ever calls getASTContext() on our ClangASTContext (as that would create the ASTContext). As we now always create the ASTContext the fact that we had an uninitialized FileSystem made the test crash. llvm-svn: 373457
* Make yet another attempt in restoring SymbolFilePDBTestsAdrian Prantl2019-10-021-13/+13
| | | | | | | | The original test was passing false to the append argument of FindTypes (the only use of this feature!). This patch now replicates that by passing a fresh TypeMap into the function where applicable. llvm-svn: 373409
* [lldb] Fix unused variable warningJordan Rupprecht2019-10-011-1/+0
| | | | llvm-svn: 373399
* Make another attempt at fixing SymbolFilePDBTests.Adrian Prantl2019-10-011-0/+1
| | | | llvm-svn: 373373
* [JSON] Use LLVM's library for argdumperJonas Devlieghere2019-10-012-19/+7
| | | | | | | | | This patch replaces the LLDB's JSON implementation with the one from LLVM in argdumper. Differential revision: https://reviews.llvm.org/D68279 llvm-svn: 373361
* [JSON] Use LLVM's library for decoding JSON in StructuredDataJonas Devlieghere2019-10-012-101/+48
| | | | | | | | | This patch replaces the hand-rolled JSON decoding in StructuredData with LLVM's JSON library. Differential revision: https://reviews.llvm.org/D68282 llvm-svn: 373360
* [JSON] Use LLVM's library for encoding JSON in StructuredDataJonas Devlieghere2019-10-017-102/+57
| | | | | | | | | This patch replaces the hand-rolled JSON emission in StructuredData with LLVM's JSON library. Differential revision: https://reviews.llvm.org/D68248 llvm-svn: 373359
* Fix a syntax error.Adrian Prantl2019-10-011-1/+1
| | | | llvm-svn: 373355
* Fix a condition-flip regression introduced in r373344.Adrian Prantl2019-10-011-1/+1
| | | | llvm-svn: 373354
* Typo (NFC)Adrian Prantl2019-10-011-3/+3
| | | | llvm-svn: 373353
* Simplify condition (NFC)Adrian Prantl2019-10-011-1/+1
| | | | llvm-svn: 373352
* Remove size_t return parameter from FindTypesAdrian Prantl2019-10-0124-344/+261
| | | | | | | | | | | | | | | In r368345 I accidentally introduced a regression that would over-report the number of matches found by FindTypes if the DeclContext Filter was hit. This patch simply removes the size_t return parameter altogether — it's not that useful. rdar://problem/55500457 Differential Revision: https://reviews.llvm.org/D68169 llvm-svn: 373344
* Update SymbolFilePDB for FindTypes API change.Adrian Prantl2019-10-012-22/+17
| | | | | | This is untested, I don't have access to a Windows machine. llvm-svn: 373342
* [lldb][NFC] Mark ClangASTContext constructor as explicitRaphael Isemann2019-10-011-1/+1
| | | | | | | Given that we can implicitly construct a ClangASTContext from any string, we should really mark this as explicit. llvm-svn: 373339
OpenPOWER on IntegriCloud