~pali/llvm/lldb-trunk : changes

~pali/llvm/lldb-trunk » Changes from revision 20870

From Revision 17611 to 17592

Rev	Summary	Authors	Date
17611	[windows] Use a well-known path for ComSpec if we fail to re... [windows] Use a well-known path for ComSpec if we fail to retrieve it Summary: Right now we always try to retrieve ComSpec and if we fail, we give up. This rarely fails, but we can update the logic so that we fail even less frequently. Since there is a well-known path (albeit not always correct), try the path when we failed to retrieve it. Note that on other platforms, we generally just return a well-known path without any checking. Reviewers: asmith, zturner, labath Reviewed By: zturner, labath Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D49451	stella.stamenova	5 years ago
17610	[lit, lldbsuite] Remove tests that are duplicated between li... [lit, lldbsuite] Remove tests that are duplicated between lit and lldb-suite Summary: Several tests exist in both lit and lldbsuite. This removes the lit version of the duplicated tests. Reviewers: asmith, zturner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D49450	stella.stamenova	5 years ago
17609	Link the lldb driver ("lldb") against the llvm static Link the lldb driver ("lldb") against the llvm static libraries because of the new prettystackprinter dependency.	jmolenda	5 years ago
17608	Invert dependency between lldb-framework and lldb-suite Invert dependency between lldb-framework and lldb-suite Summary: Currently, if you build lldb-framework the entire framework doesn't actually build. In order to build the entire framework, you need to actually build lldb-suite. This abstraction doesn't feel quite right because lldb-framework truly does depend on lldb-suite (liblldb + related tools). In this change I want to invert their dependency. This will mean that lldb and finish_swig will depend on lldb-framework in a framework build, and lldb-suite otherwise. Instead of adding conditional logic everywhere to handle this, I introduce LLDB_SUITE_TARGET to handle it. Differential Revision: https://reviews.llvm.org/D49406	xiaobai	5 years ago
17607	[CMake] Have check-lldb-unit use CMAKE_CURRENT_BINARY_DIR [CMake] Have check-lldb-unit use CMAKE_CURRENT_BINARY_DIR llvm-lit uses `map_config` directives (generated at configuration-time) to make it possible to pass a test path relative to the source instead of the build folder (CMAKE_CURRENT_BINARY_DIR). However, this doesn't work in the case of swift where the build directory layout prevents llvm-lit from knowing about lldb and its test paths. This caused check-lldb-unit to fail in this configuration, while everything was working as expected upstream. This patch fixes the issue by passing a path relative to the build directory. This was already the case for check-lldb-lit.	jdevlieghere	5 years ago
17606	Move pretty stack trace printer into driver. Move pretty stack trace printer into driver. We used to have a pretty stack trace printer in SystemInitializerCommon. This was disabled on Apple because we didn't want the library to be setting signal handlers, as this was causing issues when loaded into Xcode. However, I think it's useful to have this for the LLDB driver, so I moved it up to use the PrettyStackTraceProgram in the driver's main. Differential revision: https://reviews.llvm.org/D49377	jdevlieghere	5 years ago
17605	[CMake] Give lldb tools functional install targets when buil... [CMake] Give lldb tools functional install targets when building LLDB.framework Summary: This change makes the install targets for lldb tools functional when building for the framework. I am currently working on the install rules for lldb-framework and this will let me make `install-lldb-framework` rely on `install-lldb-argdumper` for instance. This is especially important for `install-lldb-framework-stripped`. It is much better for `install-lldb-framework-stripped` to rely on `install-lldb-argdumper-stripped` than to copy and strip lldb-argdumper manually. Differential Revision: https://reviews.llvm.org/D49038	xiaobai	5 years ago
17604	Fix some crashes and deadlocks in FormatAnsiTerminalCodes Fix some crashes and deadlocks in FormatAnsiTerminalCodes Summary: This patch fixes a few problems with the FormatAnsiTerminalCodes function: * It does an infinite loop on an unknown color value. * It crashes when the color value is at the end of the string. * It deletes the first character behind the color token. Also added a few tests that reproduce those problems (and test some other corner cases). Reviewers: davide, labath Reviewed By: labath Subscribers: labath, lldb-commits, mgorny Differential Revision: https://reviews.llvm.org/D49307	teemperor	5 years ago
17603	Fix typo in find-basic-function test Fix typo in find-basic-function test Wrong FileCheck header meant that we were not matching what we should. This allows us to get rid of the -allow-deprecated-dag-overlap flag in the test.	labath	5 years ago
17602	Fix TestDataFormatterUnordered for older libc++ versions Fix TestDataFormatterUnordered for older libc++ versions clang recently started diagnosing "exception specification in declaration does not match previous declaration" errors. Unfortunately old libc++ versions had a bug, where they violated this rule, which means that tests using this library version now fail due to build errors. Since it was easy to work around the bug by compiling this test with -fno-exceptions, I do that here. If supporting old libc++ versions becomes a burden, we'll have to revisit this.	labath	5 years ago
17601	Rollback r337070. Rollback r337070. Someone simultaneously fixed the breakage it was designed to fix.	saugustine	5 years ago
17600	Update ClangASTContext for the new DependentVector type. Update ClangASTContext for the new DependentVector type. https://reviews.llvm.org/D49326	saugustine	5 years ago
17599	[lldb-mi] Make symbol-list-lines.test XFAIL on Windows [lldb-mi] Make symbol-list-lines.test XFAIL on Windows It's a temporary decision until we reach out what causes a failure.	apolyakov	5 years ago
17598	Fix -Wswitch after introduction of clang;:Type::DependentVec... Fix -Wswitch after introduction of clang;:Type::DependentVector in r337036	maskray	5 years ago
17597	Make these tests c++ tests so they can be skipped on systems... Make these tests c++ tests so they can be skipped on systems that don't support those tests.	jingham	5 years ago
17596	Fix the libcxx set, multiset, vector and bitset formatters t... Fix the libcxx set, multiset, vector and bitset formatters to work on references. The synthetic child providers for these classes had a type expression that matched pointers & references to the type, but the Front End only worked on the actual object. I fixed this by adding a way for the Synthetic Child FrontEnd provider to request dereference, and then had these formatters use that mode. <rdar://problem/40849836> Differential Revision: https://reviews.llvm.org/D49279	jingham	5 years ago
17595	Add the new PDBLocationToDWARFExpression.{cpp,h} to the Xcod... Add the new PDBLocationToDWARFExpression.{cpp,h} to the Xcode project.	jingham	5 years ago
17594	Add includes for CompletionRequest to every file that uses i... Add includes for CompletionRequest to every file that uses it Summary: Should fix the builds (and prevent future builds from failing when people try to reduce includes). Reviewers: jingham Reviewed By: jingham Subscribers: jingham, lldb-commits Differential Revision: https://reviews.llvm.org/D49311	teemperor	5 years ago
17593	Replaced more boilerplate code with CompletionRequest (NFC) Replaced more boilerplate code with CompletionRequest (NFC) Summary: As suggested in D48796, this patch replaces even more internal calls that were using the old completion API style with a single CompletionRequest. In some cases we also pass an option vector/index, but as we don't always have this information, it currently is not part of the CompletionRequest class. The constructor of the CompletionRequest is now also more sensible. You only pass the user input, cursor position and your list of matches to the request and the rest will be inferred (using the same code we used before to calculate this). You also have to pass these match window parameters to it, even though they are unused right now. The patch shouldn't change any behavior. Reviewers: jingham Reviewed By: jingham Subscribers: lldb-commits Differential Revision: https://reviews.llvm.org/D48976	teemperor	5 years ago
17592	No longer pass a StringRef to the Python API No longer pass a StringRef to the Python API Summary: The refactoring patch for DoExecute missed this case of a variadic function that just silently accepts a StringRef which it then tries to reinterpret as a C-string. This should fix the Windows builds. Reviewers: stella.stamenova Reviewed By: stella.stamenova Subscribers: lldb-commits Differential Revision: https://reviews.llvm.org/D49309	teemperor	5 years ago