summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* [ValueTracking] Fix uninitialized variable warnings in matchSelectPattern ↵Simon Pilgrim2019-09-231-5/+6
| | | | | | | | | | const wrapper. NFCI. Static analyzer complains about const_cast uninitialized variables, we should explicitly set these to null. Ideally that const wrapper would go away though....... llvm-svn: 372603
* llvm-undname: Add support for demangling typeinfo namesNico Weber2019-09-234-0/+27
| | | | | | | | | | | | | | typeinfo names aren't symbols but string constant contents stored in compiler-generated typeinfo objects, but llvm-cxxfilt can demangle these for Itanium names. In the MSVC ABI, these are just a '.' followed by a mangled type -- this means they don't start with '?' like all MS-mangled symbols do. Differential Revision: https://reviews.llvm.org/D67851 llvm-svn: 372602
* Revert "[clang-tidy] Fix relative path in header-filter."Dmitri Gribenko2019-09-235-87/+3
| | | | | | | This reverts commit r372388. It made '-header-filter' inconsistent with paths printed in diagnostics. llvm-svn: 372601
* [Diagnostics] Avoid -Wsizeof-array-div when dividing the size of a nested ↵David Bolvansky2019-09-232-14/+12
| | | | | | array by the size of the deepest base type llvm-svn: 372600
* Cosmetic; don't use the magic constant 35 when HASH is more readable. This ↵Mark Murray2019-09-233-16/+17
| | | | | | | | | | | | | | | | matches other MCK__<THING>_* usage better. Summary: No functional change. This fixes a magic constant in MCK__*_... macros only. Reviewers: ostannard Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D67840 llvm-svn: 372599
* Function::BuildLazyArguments() - fix "variable used but never read" analyzer ↵Simon Pilgrim2019-09-231-1/+2
| | | | | | | | warning. NFCI. Simplify the code by separating the masking of the SDC variable from using it. llvm-svn: 372598
* gn build: Merge r372595GN Sync Bot2019-09-232-0/+2
| | | | llvm-svn: 372597
* [Alignment][NFC] DataLayout migration to llvm::AlignGuillaume Chatelet2019-09-237-20/+19
| | | | | | | | | | | | | | | | | Summary: This is patch is part of a series to introduce an Alignment type. See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html See this patch for the introduction of the type: https://reviews.llvm.org/D64790 Reviewers: courbet Subscribers: jholewinski, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D67914 llvm-svn: 372596
* [libTooling] Introduce new library of source-code builders.Yitzhak Mandelbaum2019-09-235-0/+478
| | | | | | | | | | | | | | | | | Summary: Introduces facilities for easily building source-code strings, including idiomatic use of parentheses and the address-of, dereference and member-access operators (dot and arrow) and queries about need for parentheses. Reviewers: gribozavr Subscribers: mgorny, cfe-commits, ilya-biryukov Tags: #clang Differential Revision: https://reviews.llvm.org/D67632 llvm-svn: 372595
* Removed dead code from Stencil.hDmitri Gribenko2019-09-231-10/+0
| | | | llvm-svn: 372594
* Removed an incorred namespace-end commentDmitri Gribenko2019-09-231-1/+1
| | | | llvm-svn: 372593
* [LLDB] Check for _WIN32 instead of _MSC_VER for code specific to windows in ↵Martin Storsjo2019-09-235-9/+9
| | | | | | | | | | | general These ifdefs contain code that isn't specific to MSVC but useful for any windows target, like MinGW. Differential Revision: https://reviews.llvm.org/D67893 llvm-svn: 372592
* [LLDB] Remove a now redundant windows specific workaroundMartin Storsjo2019-09-231-5/+0
| | | | | | | | | | | | | | | | vsnprintf(NULL, 0, ...) works for measuring the needed string size on all supported Windows variants; it's supported since at least MSVC 2015 (and LLVM requires a newer version than that), and works on both msvcrt.dll (since at least XP) and UCRT with MinGW. The previous use of ifdefs was wrong as well, as __MINGW64__ only is defined for 64 bit targets, and the define without trailing underscores is never defined automatically (neither by clang nor by gcc). Differential Revision: https://reviews.llvm.org/D67861 llvm-svn: 372591
* [LLDB] Add a void* cast when passing object pointers to printf %pMartin Storsjo2019-09-231-14/+10
| | | | | | | | | | This fixes build warnings in MinGW mode. Also remove leftover if (log) {} around the log macro. Differential Revision: https://reviews.llvm.org/D67896 llvm-svn: 372590
* [LLDB] Avoid a warning about an unused static variableMartin Storsjo2019-09-231-1/+1
| | | | | | | | The variable is unused on windows. Differential Revision: https://reviews.llvm.org/D67895 llvm-svn: 372589
* [LLDB] Remove a stray semicolon. NFC.Martin Storsjo2019-09-231-1/+1
| | | | | | This fixes build warnings with at least GCC. llvm-svn: 372588
* [LLDB] Add a missing specification of linking against dbghelpMartin Storsjo2019-09-231-0/+8
| | | | | | | | | | | | | | | | | | | The PECOFF object file plugin uses the dbghelp API, but doesn't specify that it has to be linked in anywhere. Current MSVC based builds have probably succeeded, as other parts in LLDB have had a "#pragma comment(lib, "dbghelp.lib")", but there's currently no such pragma in the PECOFF plugin. The "#pragma comment(lib, ...)" approach doesn't work in MinGW mode (unless the compiler is given the -fms-extensions option, and even then, it's only supported by clang/lld, not by GCC/binutils), thus add it to be linked via CMake. (The other parts of LLDB that use dbghelp are within _MSC_VER ifdefs.) Differential Revision: https://reviews.llvm.org/D67885 llvm-svn: 372587
* [LLDB] Use the Windows SOCKET type on all windows targets, not only MSVCMartin Storsjo2019-09-231-1/+1
| | | | | | Differential Revision: https://reviews.llvm.org/D67859 llvm-svn: 372586
* [Alignment] Get DataLayout::StackAlignment as AlignGuillaume Chatelet2019-09-234-6/+13
| | | | | | | | | | | | | | | | | | | | Summary: Internally it is needed to know if StackAlignment is set but we can expose it as llvm::Align. This is patch is part of a series to introduce an Alignment type. See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html See this patch for the introduction of the type: https://reviews.llvm.org/D64790 Reviewers: courbet Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D67852 llvm-svn: 372585
* Localizer - fix "variable used but never read" analyzer warning. NFCI.Simon Pilgrim2019-09-231-1/+2
| | | | | | Simplify the code by separating the modification of the Changed variable from returning it. llvm-svn: 372583
* TargetInstrInfo::getStackSlotRange - fix "variable used but never read" ↵Simon Pilgrim2019-09-231-1/+1
| | | | | | | | analyzer warning. NFCI. We don't need to divide the BitSize local variable at all. llvm-svn: 372582
* gn build: Merge r372564GN Sync Bot2019-09-231-0/+1
| | | | llvm-svn: 372581
* Revert "Reland "[utils] Implement the llvm-locstats tool""Djordje Todorovic2019-09-237-319/+0
| | | | | | This reverts commit rL372554. llvm-svn: 372580
* [llvm-readobj] - Stop treating ".stack_sizes.*" sections as stack sizes ↵George Rimar2019-09-232-6/+6
| | | | | | | | | | | | | | | | sections. llvm-readobj currently handles .stack_sizes.* (e.g. .stack_sizes.foo) as a normal stack sizes section. Though MC does not produce sections with such names. Also, linkers do not combine .stack_sizes.* into .stack_sizes. A mini discussion about this correctness issue is here: https://reviews.llvm.org/D67757#inline-609274 This patch changes implementation so that only now only '.stack_sizes' name is accepted as a real stack sizes section. Differential revision: https://reviews.llvm.org/D67824 llvm-svn: 372578
* CriticalAntiDepBreaker - Assert that we've found the bottom of the critical ↵Simon Pilgrim2019-09-231-0/+1
| | | | | | | | path. NFCI. Silences static analyzer null dereference warnings. llvm-svn: 372577
* [llvm-readobj] - Implement LLVM-style dumping for .stack_sizes sections.George Rimar2019-09-235-74/+204
| | | | | | | | | D65313 implemented GNU-style dumping (llvm-readelf). This one implements LLVM-style dumping (llvm-readobj). Differential revision: https://reviews.llvm.org/D67834 llvm-svn: 372576
* [NFC] Fixed clang wasm test after rL372573David Bolvansky2019-09-231-2/+2
| | | | | | These tests should not depend on -O1.. llvm-svn: 372575
* [lldb][NFC] Remove unused variable in Options::HandleOptionArgumentCompletionRaphael Isemann2019-09-231-1/+0
| | | | llvm-svn: 372574
* [FunctionAttrs] Enable nonnull arg propagationDavid Bolvansky2019-09-231-4/+1
| | | | | | Enable flag introduced in rL294998. Security concerns are no longer valid, since function signatures for mentioned libc functions has no nonnull attribute (Clang does not generate them? I see no nonnull attr in LLVM IR for these functions) and since rL372091 we carefully annotate the callsites where we know that size is static, non zero. So let's enable this flag again.. llvm-svn: 372573
* [lldb][NFC] Remove dead code in Options::HandleOptionArgumentCompletionRaphael Isemann2019-09-231-9/+2
| | | | llvm-svn: 372572
* [LLD][ELF] - Simplify getFlagsFromEmulation(). NFCI.George Rimar2019-09-231-12/+2
| | | | | | A straightforward simplification. llvm-svn: 372570
* [lldb][NFC] Fix documentation of CompletionRequest::AddCompletionRaphael Isemann2019-09-231-1/+2
| | | | llvm-svn: 372569
* [lldb][NFC] Make cursor char position unsigned in CompletionRequestRaphael Isemann2019-09-232-6/+6
| | | | | | | This was only an 'int' because to fit into the old API which is gone by now. llvm-svn: 372568
* [ARM][MVE] Remove old tail predicatesSam Parker2019-09-236-12/+672
| | | | | | | | | | | Remove any predicate that we replace with a vctp intrinsic, and try to remove their operands too. Also look into the exit block to see if there's any duplicates of the predicates that we've replaced and clone the vctp to be used there instead. Differential Revision: https://reviews.llvm.org/D67709 llvm-svn: 372567
* [lldb] Make cursor index in CompletionRequest unsignedRaphael Isemann2019-09-236-35/+46
| | | | | | | | | | | | The fact that index==-1 means "no arguments" is not obvious and only used in one place from what I can tell. Also fixes several warnings about using the cursor index as if it was a size_t when comparing. Not fully NFC as we now also correctly update the partial argument list when injecting the fake empty argument in the CompletionRequest constructor. llvm-svn: 372566
* [AArch64] support neon_sshl and neon_ushl in performIntrinsicCombine.Florian Hahn2019-09-232-6/+209
| | | | | | | | | | | | | | | | Try to generate ushll/sshll for aarch64_neon_ushl/aarch64_neon_sshl, if their first operand is extended and the second operand is a constant Also adds a few tests marked with FIXME, where we can further increase codegen. Reviewers: t.p.northover, samparker, dmgreen, anemet Reviewed By: anemet Differential Revision: https://reviews.llvm.org/D62308 llvm-svn: 372565
* [ASTImporter][NFC] Add comprehensive tests for ODR violation handling strategiesGabor Marton2019-09-233-184/+671
| | | | | | | | | | | | | | | | | Summary: In this patch we provide additional and comprehensive tests for the ODR handling strategies. This is the continuation of https://reviews.llvm.org/D59692. Reviewers: shafik, a_sidorin, balazske, a.sidorin Subscribers: mgorny, rnkovacs, dkrupp, Szelethus, gamesh411, cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D66951 llvm-svn: 372564
* [Alignment] fix buildGuillaume Chatelet2019-09-231-5/+6
| | | | llvm-svn: 372562
* [lldb][NFC] Remove argument prefix checking boilerplate when adding completionsRaphael Isemann2019-09-238-30/+64
| | | | llvm-svn: 372561
* [ARM][LowOverheadLoops] Use subs during revert.Sam Parker2019-09-235-27/+47
| | | | | | | | | | Check whether there are any uses or defs between the LoopDec and LoopEnd. If there's not, then we can use a subs to set the cpsr and skip generating a cmp. Differential Revision: https://reviews.llvm.org/D67801 llvm-svn: 372560
* [Alignment][NFC] Switch DataLayout private members to llvm::AlignGuillaume Chatelet2019-09-232-23/+22
| | | | | | | | | | | | | | | | | Summary: This is patch is part of a series to introduce an Alignment type. See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html See this patch for the introduction of the type: https://reviews.llvm.org/D64790 Reviewers: courbet Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D67836 llvm-svn: 372558
* [ARM][LowOverheadLoops] Use tBcc when revertingSam Parker2019-09-235-13/+16
| | | | | | | | | Check the branch target ranges and use a tBcc instead of t2Bcc when we can. Differential Revision: https://reviews.llvm.org/D67796 llvm-svn: 372557
* [lldb] Reduce some dangerous boilerplate with CompletionRequest::ShiftArgumentsRaphael Isemann2019-09-235-6/+45
| | | | | | | | | | | | | We should in general not allow external code to fiddle with the internals of CompletionRequest, but until this is gone let's at least provide a utility function that makes this less dangerous. This also now correct updates the partially parsed argument list, but it doesn't seem to be used by anything that is behind one of the current shift/SetCursorIndex calls, so this doesn't seeem to fix any currently used completion. llvm-svn: 372556
* [MIPS GlobalISel] VarArg argument lowering, select G_VASTART and vacopyPetar Avramovic2019-09-2310-6/+588
| | | | | | | | | | | | | | | | CC_Mips doesn't accept vararg functions for O32, so we have to explicitly use CC_Mips_FixedArg. For lowerCall we now properly figure out whether callee function is vararg or not, this has no effect for O32 since we always use CC_Mips_FixedArg. For lower formal arguments we need to copy arguments in register to stack and save pointer to start for argument list into MipsMachineFunction object so that G_VASTART could use it during instruction select. For vacopy we need to copy content from one vreg to another, load and store are used for that purpose. Differential Revision: https://reviews.llvm.org/D67756 llvm-svn: 372555
* Reland "[utils] Implement the llvm-locstats tool"Djordje Todorovic2019-09-237-0/+319
| | | | | | | | | | | | | | | | The tool reports verbose output for the DWARF debug location coverage. The llvm-locstats for each variable or formal parameter DIE computes what percentage from the code section bytes, where it is in scope, it has location description. The line 0 shows the number (and the percentage) of DIEs with no location information, but the line 100 shows the number (and the percentage) of DIEs where there is location information in all code section bytes (where the variable or parameter is in the scope). The line 50..59 shows the number (and the percentage) of DIEs where the location information is in between 50 and 59 percentage of its scope covered. Differential Revision: https://reviews.llvm.org/D66526 llvm-svn: 372554
* [lldb] Fix that importing decls in a TagDecl end up in wrong declaration ↵Raphael Isemann2019-09-232-3/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | context (partly reverts D61333) Summary: In D61333 we dropped some code from ClangASTSource that checks if imported declarations ended up in the right DeclContext. While this code wasn't tested by the test suite (or better, it was hit by the test suite but we didn't have any checks that were affected) and the code seems pointless (as usually Decls should end up in the right DeclContext), it actually broke the data formatters in LLDB and causes a bunch of obscure bugs where structs suddenly miss all their members. The first report we got about this was that printing a std::map doesn't work anymore when simply doing "expr m" (m is the std::map). This patch reverts D61333 partly and reintroduces the check in a more stricter way (we actually check now that we *move* the Decl and it is in a single DeclContext). This should fix all the problems we currently have until we figure out how to properly fix the underlying issues. I changed the order of some std::map formatter tests which is currently the most reliable way to test this problem (it's a tricky setup, see description below). Fixes rdar://55502701 and rdar://55129537 -------------------------------------- Some more explanation what is actually going on and what is going wrong: The situation we have is that if we have a `std::map m` and do a `expr m`, we end up seeing an empty map (even if `m` has elements). The reason for this is that our data formatter sees that std::pair<int, int> has no members. However, `frame var m` works just fine (and fixes all following `expr m` calls). The reason for why `expr` breaks std::map is that we actually copy the std::map nodes in two steps in the three ASTContexts that are involved: The debug information ASTContext (D-AST), the expression ASTContext we created for the current expression (E-AST) and the persistent ASTContext we use for our $variables (P-AST). When doing `expr m` we do a minimal import of `std::map` from D-AST to E-AST just do the type checking/codegen. This copies std::map itself and does a minimal.import of `std::pair<int, int>` (that is, we don't actually import the `first` and `second` members as we don't need them for anything). After the expression is done, we take the expression result and copy it from E-AST to P-AST. This imports the E-AST's `std::pair` into P-AST which still has no `first` and `second` as they are still undeserialized. Once we are in P-AST, the data formatter tries to inspect `std::map` (and also `std::pair` as that's what the elements are) and it asks for the `std::pair` members. We see that `std::pair` has undeserialized members and go to the ExternalASTSource to ask for them. However, P-ASTs ExternalASTSource points to D-AST (and not E-AST, which `std::pair` came from). It can't point to E-AST as that is only temporary and already gone (and also doesn't actually contain all decls we have in P-AST). So we go to D-AST to get the `std::pair` members. The ASTImporter is asked to copy over `std::pair` members and first checks if `std::pair` is already in P-AST. However, it only finds the std::pair we got from E-AST, so it can't use it's map of already imported declarations and does a comparison between the `std::pair` decls we have Because the ASTImporter thinks they are different declarations, it creates a second `std::pair` and fills in the members `first` and `second` into the second `std::pair`. However, the data formatter is looking at the first `std::pair` which still has no members as they are in the other decl. Now we pretend we have no declarations and just print an empty map as a fallback. The hack we had before fixed this issue by moving `first` and `second` to the first declaration which makes the formatters happy as they can now see the members in the DeclContext they are querying. Obviously this is a temporary patch until we get a real fix but I'm not sure what's the best way to fix this. Implementing that the ClassTemplateSpecializationDecl actually understands that the two std::pair's are the same decl fixes the issue, but this doesn't fix the bug for all declarations. My preferred solution would be to complete all declarations in E-AST before they get moved to P-AST (as we anyway have to do this from what I can tell), but that might have unintended side-effects and not sure what's the best way to implement this. Reviewers: friss, martong Reviewed By: martong Subscribers: aprantl, rnkovacs, christof, abidh, JDevlieghere, lldb-commits, shafik Tags: #lldb Differential Revision: https://reviews.llvm.org/D67803 llvm-svn: 372549
* [lldb] Fix LLDB build after r372538Raphael Isemann2019-09-231-1/+2
| | | | llvm-svn: 372548
* Revert "Extension: Mark the default constructor of chrono::duration as ↵Marshall Clow2019-09-232-48/+1
| | | | | | | | conditionally noexcept"; this breaks the gcc5 bot for C++11 This reverts commit c8ca15c95c4c0d6d1356500d5fe49a319ea4ca01. llvm-svn: 372546
* [X86] Canonicalize all zeroes vector to RHS in X86DAGToDAGISel::tryVPTESTM.Craig Topper2019-09-232-24/+19
| | | | llvm-svn: 372544
* [X86] Remove SETEQ/SETNE canonicalization code from LowerIntVSETCC_AVX512 to ↵Craig Topper2019-09-233-9/+29
| | | | | | | | | | | | prevent an infinite loop. The attached test case would previous infinite loop after r365711. I'm going to move this to X86ISelDAGToDAG.cpp to get the setcc to match VPTEST in 32-bit mode in a follow up commit. llvm-svn: 372543
OpenPOWER on IntegriCloud