summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* AMDGPU/GlobalISel: Fix using wrong addrspace for apertureMatt Arsenault2019-10-042-9/+11
| | | | | | | This was always passing the destination flat address space, when it should be picking between the two valid source options. llvm-svn: 373716
* AMDGPU/GlobalISel: Select G_PTRTOINTMatt Arsenault2019-10-042-0/+102
| | | | llvm-svn: 373715
* AMDGPU/GlobalISel: Support wave32 waterfall loopsMatt Arsenault2019-10-0413-411/+734
| | | | llvm-svn: 373714
* Revert r371732: "lld-link: Fix tests that do not run on macOS after r371729."Martin Storsjo2019-10-041-1/+1
| | | | | | This commit should be reverted along with r371729. llvm-svn: 373713
* [Driver] NFC: Remove duplicate call to getLibGccTypeCullen Rhodes2019-10-041-1/+0
| | | | | | | | Reviewed By: saugustine Differential Revision: https://reviews.llvm.org/D68380 llvm-svn: 373712
* [lldb][modern-type-lookup] No longer import temporary declarations into the ↵Raphael Isemann2019-10-045-107/+135
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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
* [CodeComplete] Ensure object is the same in compareOverloads()Ilya Biryukov2019-10-043-0/+35
| | | | | | | | | | | | | | | | | | Summary: This fixes a regression that led to size() not being available in clangd when completing 'deque().^' and using libc++. Reviewers: sammccall Reviewed By: sammccall Subscribers: jkorous, arphaman, kadircet, usaxena95, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D68335 llvm-svn: 373710
* [clang-format] [PR43338] C# clang format has space issues betweern C# only ↵Paul Hoad2019-10-044-7/+82
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | keywords Summary: When formatting C# there can be issues with a lack of spaces between `using (` , `foreach (` and generic types The C# code ``` public class Foo { Dictionary<string,string> foo; } ``` will be formatted as ``` public class Foo { Dictionary<string, string>foo; ^^^^^ missing a space } ``` This revision also reverts some of {D66662} in order to make this cleaner and resolve an issues seen by @owenpan that the formatting didn't add a space when not in a code block This also transforms C# foreach commands to be seen as tok::kw_for commands (to ensure foreach gets the same Brace Wrapping behavior as for without littering the code with `if(Style.isCSharp())` Reviewers: owenpan, klimek, russellmcc, mitchell-stellar Reviewed By: mitchell-stellar Subscribers: cfe-commits Tags: #clang, #clang-format Differential Revision: https://reviews.llvm.org/D67660 llvm-svn: 373709
* [ELF] Use union-find set and doubly linked list in Call-Chain Clustering ↵Fangrui Song2019-10-041-52/+62
| | | | | | | | | | | | | | | | | (C³) heuristic Before, SecToClusters[*] was used to track the belonged cluster. During a merge (From -> Into), every element of From has to be updated. Use a union-find set to speed up this use case. Also, replace `std::vector<int> Sections;` with a doubly-linked pointers: int Next, Prev; Reviewed By: Bigcheese Differential Revision: https://reviews.llvm.org/D46228 llvm-svn: 373708
* [clang-format] [PR43333] Fix C# breaking before function name when using ↵Paul Hoad2019-10-045-69/+189
| | | | | | | | | | | | | | | | | | | | | | | | | Attributes Summary: This is a fix for https://bugs.llvm.org/show_bug.cgi?id=43333 This comes with 3 main parts - C# attributes cause function names on a new line even when AlwaysBreakAfterReturnType is set to None - Add AlwaysBreakAfterReturnType to None by default in the Microsoft style, - C# unit tests are not using Microsoft style (which we created to define the default C# style to match a vanilla C# project). Reviewers: owenpan, klimek, russellmcc, mitchell-stellar Reviewed By: mitchell-stellar Subscribers: cfe-commits Tags: #clang-tools-extra, #clang, #clang-format Differential Revision: https://reviews.llvm.org/D67629 llvm-svn: 373707
* [X86] Enable inline memcmp() to use AVX512David Zarzycki2019-10-042-2/+21
| | | | llvm-svn: 373706
* [MinGW] Add --reproduce optionRui Ueyama2019-10-043-0/+6
| | | | | | Differential Revision: https://reviews.llvm.org/D68382 llvm-svn: 373705
* Add /reproduce option to lld/COFFRui Ueyama2019-10-043-6/+35
| | | | | | | | | | | This patch adds /reproduce:<path> option to lld/COFF. This is an lld-specific option, so we can name it freely. I chose /reproduce over other names (e.g. /lldlinkrepro) for consistency with other lld ports. Differential Revision: https://reviews.llvm.org/D68381 llvm-svn: 373704
* Revert r371729: lld-link: Make /linkrepro: take a filename, not a directory.Rui Ueyama2019-10-045-16/+13
| | | | | | | | | | This reverts commit r371729 because /linkrepro option also exists in Microsoft link.exe and their linker takes not a filename but a directory name as an argument for /linkrepro. Differential Revision: https://reviews.llvm.org/D68378 llvm-svn: 373703
* [compiler-rt] Remove O1 tests from signal_line.cppVitaly Buka2019-10-041-4/+0
| | | | | | It does not work on arm llvm-svn: 373702
* Revert "[Symbolize] Use the local MSVC C++ demangler instead of relying on ↵Martin Storsjo2019-10-043-4/+45
| | | | | | | | | dbghelp. NFC." This reverts SVN r373698, as it broke sanitizer tests, e.g. in http://lab.llvm.org:8011/builders/sanitizer-windows/builds/52441. llvm-svn: 373701
* [test] Remove locale dependency for mri-utf8.testThomas Preud'homme2019-10-041-5/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: llvm-ar's mri-utf8.test test relies on the en_US.UTF-8 locale to be installed for its last RUN line to work. If not installed, the unicode string gets encoded (interpreted) as ascii which fails since the most significant byte is non zero. This commit changes the call to open to use a binary literal of the UTF-8 encoding for the pound sign instead, thus bypassing the encoding step. Note that the echo to create the <pound sign>.txt file will work regardless of the locale because both the shell and the echo (in case it's not a builtin of the shell concerned) only care about ascii character to operate. Indeed, the mri-utf8.test file (and in particular the pound sign) is encoded in UTF-8 and UTF-8 guarantees only ascii characters can create bytes that can be interpreted as ascii characters (i.e. bytes with the most significant bit null). So the process to break down the filename in the line goes something along: - find an ascii chevron '>' - find beginning of the filename by removing ascii space-like characters - find ascii newline character indicating the end of the redirection (no semicolon ';', closing curly bracket '}' or parenthesis ')' or the like - create a file whose name is made of all the bytes in between beginning and end of filename *without interpretting them* Reviewers: gbreynoo, MaskRay, rupprecht, JamesNagurne, jfb Subscribers: llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68418 llvm-svn: 373700
* [AMDGPU][SILoadStoreOptimizer] NFC: Refactor codePiotr Sobczak2019-10-041-120/+80
| | | | | | | | | | | | | | | | | | | | | | | Summary: This patch fixes a potential aliasing problem in InstClassEnum, where local values were mixed with machine opcodes. Introducing InstSubclass will keep them separate and help extending InstClassEnum with other instruction types (e.g. MIMG) in the future. This patch also makes getSubRegIdxs() more concise. Reviewers: nhaehnle, arsenm, tstellar Reviewed By: arsenm Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68384 llvm-svn: 373699
* [Symbolize] Use the local MSVC C++ demangler instead of relying on dbghelp. NFC.Martin Storsjo2019-10-043-45/+4
| | | | | | | | | This allows making a couple llvm-symbolizer tests run in all environments. Differential Revision: https://reviews.llvm.org/D68133 llvm-svn: 373698
* [test] Remove a needless declaration of REQUIRES: target-windowsMartin Storsjo2019-10-041-1/+1
| | | | | | | | | This test only relies on running on a case insensitive file system, the exact target triple of the toolchain shouldn't matter. Differential Revision: https://reviews.llvm.org/D68136 llvm-svn: 373697
* [JITLink] Remove a redundant semicolon, silencing -Wpedantic warnings with ↵Martin Storsjo2019-10-041-1/+1
| | | | | | GCC. NFC. llvm-svn: 373696
* [clang] [cmake] Add distribution install targets for remaining componentsMichal Gorny2019-10-044-9/+46
| | | | | | | | | Add install targets as necessary to install bash-autocomplete, scan-build and scan-view via LLVM_DISTRIBUTION_TARGETS. Differential Revision: https://reviews.llvm.org/D68413 llvm-svn: 373695
* [clang-tools-extra] [cmake] Use add_clang_tool() to install toolsMichal Gorny2019-10-047-19/+5
| | | | | | | | | | | | Replace add_clang_executable() calls with add_clang_tool() that takes care of creating correct, distribution-friendly install target. While at it, remove redundant install calls. This change also causes clang-move and pp-trace to be installed. Differential Revision: https://reviews.llvm.org/D68423 llvm-svn: 373694
* [JITLink] Explicitly destroy bumpptr-allocated blocks to avoid a memory leak.Lang Hames2019-10-042-8/+14
| | | | llvm-svn: 373693
* [JITLink] Fix an unused variable warning.Lang Hames2019-10-041-3/+2
| | | | llvm-svn: 373692
* Make libc++ gdb pretty printer Python 3 compatibleFangrui Song2019-10-042-10/+27
| | | | llvm-svn: 373691
* gn build: Merge r373689GN Sync Bot2019-10-041-1/+1
| | | | llvm-svn: 373690
* [JITLink] Switch from an atom-based model to a "blocks and symbols" model.Lang Hames2019-10-0425-2132/+2417
| | | | | | | | | | | | | | | | | | | | | | | | In the Atom model the symbols, content and relocations of a relocatable object file are represented as a graph of atoms, where each Atom represents a contiguous block of content with a single name (or no name at all if the content is anonymous), and where edges between Atoms represent relocations. If more than one symbol is associated with a contiguous block of content then the content is broken into multiple atoms and layout constraints (represented by edges) are introduced to ensure that the content remains effectively contiguous. These layout constraints must be kept in mind when examining the content associated with a symbol (it may be spread over multiple atoms) or when applying certain relocation types (e.g. MachO subtractors). This patch replaces the Atom model in JITLink with a blocks-and-symbols model. The blocks-and-symbols model represents relocatable object files as bipartite graphs, with one set of nodes representing contiguous content (Blocks) and another representing named or anonymous locations (Symbols) within a Block. Relocations are represented as edges from Blocks to Symbols. This scheme removes layout constraints (simplifying handling of MachO alt-entry symbols, and hopefully ELF sections at some point in the future) and simplifies some relocation logic. llvm-svn: 373689
* [RISCV] Split SP adjustment to reduce the offset of callee saved register ↵Shiva Chen2019-10-046-223/+267
| | | | | | | | | | | | | | | | | | | | spill and restore We would like to split the SP adjustment to reduce the instructions in prologue and epilogue as the following case. In this way, the offset of the callee saved register could fit in a single store. add sp,sp,-2032 sw ra,2028(sp) sw s0,2024(sp) sw s1,2020(sp) sw s3,2012(sp) sw s4,2008(sp) add sp,sp,-64 Differential Revision: https://reviews.llvm.org/D68011 llvm-svn: 373688
* 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 Smith2019-10-0431-156/+237
| | | | | | | | | 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
* [compiler-rt] Fix signal_line.cpp testVitaly Buka2019-10-041-2/+2
| | | | | | r373682 committed wrong experimental version llvm-svn: 373684
* [dsymutil] Fix stack-use-after-scopeJonas Devlieghere2019-10-041-2/+2
| | | | | | | | | | The lambda is taking the stack-allocated Verify boolean by reference and it would go out of scope on the next iteration. Moving it out of the loop should fix the issue. Fixes https://bugs.llvm.org/show_bug.cgi?id=43549 llvm-svn: 373683
* [compiler-rt] Remove O2, O3 from signal_line test for fix android testsVitaly Buka2019-10-041-11/+2
| | | | llvm-svn: 373682
* compiler-rt: use __GLIBC_PREREQ for SANITIZER_INTERCEPT_GETRANDOMVitaly Buka2019-10-041-2/+2
| | | | | | | | | | | | | | Summary: Fixes https://github.com/google/oss-fuzz/issues/2836 Reviewers: eugenis Subscribers: dberris, #sanitizers, llvm-commits Tags: #sanitizers, #llvm Differential Revision: https://reviews.llvm.org/D68178 llvm-svn: 373681
* 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
* LowerTypeTests: Rename local functions to avoid collisions with identically ↵Peter Collingbourne2019-10-032-0/+26
| | | | | | | | | | | named functions in ThinLTO modules. Without this we can encounter link errors or incorrect behaviour at runtime as a result of the wrong function being referenced. Differential Revision: https://reviews.llvm.org/D67945 llvm-svn: 373678
* 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
* [llvm-objdump][test] Move test to X86 dir to avoid errors disassembling on ↵Jordan Rupprecht2019-10-031-0/+0
| | | | | | non-x86 llvm-svn: 373676
* 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
* [MemorySSA] Don't hoist stores if interfering uses (as calls) exist.Alina Sbirlea2019-10-033-2/+46
| | | | llvm-svn: 373674
* 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
* [OPENMP]Fix the test on Windows, NFC.Alexey Bataev2019-10-031-1/+1
| | | | llvm-svn: 373672
* [llvm-objdump] Further rearrange llvm-objdump sections for compatabilityJordan Rupprecht2019-10-0348-296/+397
| | | | | | | | | | | | | | | | | | | | | | | | | | | Summary: rL371826 rearranged some output from llvm-objdump for GNU objdump compatability, but there still seem to be some more. I think this rearrangement is a little closer. Overview of the ordering which matches GNU objdump: * Archive headers * File headers * Section headers * Symbol table * Dwarf debugging * Relocations (if `--disassemble` is not used) * Section contents * Disassembly Reviewers: jhenderson, justice_adams, grimar, ychen, espindola Reviewed By: jhenderson Subscribers: aprantl, emaste, arichardson, jrtc27, atanasyan, seiya, llvm-commits, MaskRay Tags: #llvm Differential Revision: https://reviews.llvm.org/D68066 llvm-svn: 373671
* [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
* ASTContext - silence static analyzer getAs<> null dereference warnings. NFCI.Simon Pilgrim2019-10-031-32/+19
| | | | | | | | The static analyzer is warning about potential null dereferences, but we should be able to use castAs<> directly and if not assert will fire for us. We can also remove a number of explicit asserts and reply on the internal asserts in castAs<> llvm-svn: 373667
OpenPOWER on IntegriCloud