aboutsummaryrefslogtreecommitdiff
path: root/contrib/llvm/lib/Target/Sparc
Commit message (Collapse)AuthorAgeFilesLines
* Move all sources from the llvm project into contrib/llvm-project.Dimitry Andric2019-12-2051-15713/+0
| | | | | | | | | | | | | This uses the new layout of the upstream repository, which was recently migrated to GitHub, and converted into a "monorepo". That is, most of the earlier separate sub-projects with their own branches and tags were consolidated into one top-level directory, and are now branched and tagged together. Updating the vendor area to match this layout is next. Notes: svn path=/head/; revision=355940
* Merge llvm, clang, compiler-rt, libc++, libunwind, lld, lldb, and openmpDimitry Andric2019-09-021-1/+1
| | | | | | | release_90 branch r369369, and update version numbers. Notes: svn path=/projects/clang900-import/; revision=351708
* Merge llvm trunk r366426, resolve conflicts, and update FREEBSD-Xlist.Dimitry Andric2019-08-2151-237/+206
| | | | Notes: svn path=/projects/clang900-import/; revision=351344
* Upgrade our copies of clang, llvm, lld, lldb, compiler-rt, libc++,Dimitry Andric2019-06-121-2/+2
| | | | | | | | | | | libunwind and openmp to the upstream release_80 branch r363030 (effectively, 8.0.1 rc2). The 8.0.1 release should follow this within a week or so. MFC after: 2 weeks Notes: svn path=/head/; revision=349004
* Merge llvm trunk r351319, resolve conflicts, and update FREEBSD-Xlist.Dimitry Andric2019-01-2021-375/+271
| | | | Notes: svn path=/projects/clang800-import/; revision=343210
* Merge llvm trunk r338150 (just before the 7.0.0 branch point), andDimitry Andric2018-08-027-17/+17
| | | | | | | resolve conflicts. Notes: svn path=/projects/clang700-import/; revision=337149
* Merge llvm trunk r338150, and resolve conflicts.Dimitry Andric2018-07-3019-101/+150
| | | | Notes: svn path=/projects/clang700-import/; revision=336916
* Upgrade our copies of clang, llvm, lld, lldb, compiler-rt and libc++ toDimitry Andric2018-02-021-5/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 6.0.0 (branches/release_60 r324090). This introduces retpoline support, with the -mretpoline flag. The upstream initial commit message (r323155 by Chandler Carruth) contains quite a bit of explanation. Quoting: Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre. Summary: First, we need to explain the core of the vulnerability. Note that this is a very incomplete description, please see the Project Zero blog post for details: https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html The basis for branch target injection is to direct speculative execution of the processor to some "gadget" of executable code by poisoning the prediction of indirect branches with the address of that gadget. The gadget in turn contains an operation that provides a side channel for reading data. Most commonly, this will look like a load of secret data followed by a branch on the loaded value and then a load of some predictable cache line. The attacker then uses timing of the processors cache to determine which direction the branch took *in the speculative execution*, and in turn what one bit of the loaded value was. Due to the nature of these timing side channels and the branch predictor on Intel processors, this allows an attacker to leak data only accessible to a privileged domain (like the kernel) back into an unprivileged domain. The goal is simple: avoid generating code which contains an indirect branch that could have its prediction poisoned by an attacker. In many cases, the compiler can simply use directed conditional branches and a small search tree. LLVM already has support for lowering switches in this way and the first step of this patch is to disable jump-table lowering of switches and introduce a pass to rewrite explicit indirectbr sequences into a switch over integers. However, there is no fully general alternative to indirect calls. We introduce a new construct we call a "retpoline" to implement indirect calls in a non-speculatable way. It can be thought of loosely as a trampoline for indirect calls which uses the RET instruction on x86. Further, we arrange for a specific call->ret sequence which ensures the processor predicts the return to go to a controlled, known location. The retpoline then "smashes" the return address pushed onto the stack by the call with the desired target of the original indirect call. The result is a predicted return to the next instruction after a call (which can be used to trap speculative execution within an infinite loop) and an actual indirect branch to an arbitrary address. On 64-bit x86 ABIs, this is especially easily done in the compiler by using a guaranteed scratch register to pass the target into this device. For 32-bit ABIs there isn't a guaranteed scratch register and so several different retpoline variants are introduced to use a scratch register if one is available in the calling convention and to otherwise use direct stack push/pop sequences to pass the target address. This "retpoline" mitigation is fully described in the following blog post: https://support.google.com/faqs/answer/7625886 We also support a target feature that disables emission of the retpoline thunk by the compiler to allow for custom thunks if users want them. These are particularly useful in environments like kernels that routinely do hot-patching on boot and want to hot-patch their thunk to different code sequences. They can write this custom thunk and use `-mretpoline-external-thunk` *in addition* to `-mretpoline`. In this case, on x86-64 thu thunk names must be: ``` __llvm_external_retpoline_r11 ``` or on 32-bit: ``` __llvm_external_retpoline_eax __llvm_external_retpoline_ecx __llvm_external_retpoline_edx __llvm_external_retpoline_push ``` And the target of the retpoline is passed in the named register, or in the case of the `push` suffix on the top of the stack via a `pushl` instruction. There is one other important source of indirect branches in x86 ELF binaries: the PLT. These patches also include support for LLD to generate PLT entries that perform a retpoline-style indirection. The only other indirect branches remaining that we are aware of are from precompiled runtimes (such as crt0.o and similar). The ones we have found are not really attackable, and so we have not focused on them here, but eventually these runtimes should also be replicated for retpoline-ed configurations for completeness. For kernels or other freestanding or fully static executables, the compiler switch `-mretpoline` is sufficient to fully mitigate this particular attack. For dynamic executables, you must compile *all* libraries with `-mretpoline` and additionally link the dynamic executable and all shared libraries with LLD and pass `-z retpolineplt` (or use similar functionality from some other linker). We strongly recommend also using `-z now` as non-lazy binding allows the retpoline-mitigated PLT to be substantially smaller. When manually apply similar transformations to `-mretpoline` to the Linux kernel we observed very small performance hits to applications running typic al workloads, and relatively minor hits (approximately 2%) even for extremely syscall-heavy applications. This is largely due to the small number of indirect branches that occur in performance sensitive paths of the kernel. When using these patches on statically linked applications, especially C++ applications, you should expect to see a much more dramatic performance hit. For microbenchmarks that are switch, indirect-, or virtual-call heavy we have seen overheads ranging from 10% to 50%. However, real-world workloads exhibit substantially lower performance impact. Notably, techniques such as PGO and ThinLTO dramatically reduce the impact of hot indirect calls (by speculatively promoting them to direct calls) and allow optimized search trees to be used to lower switches. If you need to deploy these techniques in C++ applications, we *strongly* recommend that you ensure all hot call targets are statically linked (avoiding PLT indirection) and use both PGO and ThinLTO. Well tuned servers using all of these techniques saw 5% - 10% overhead from the use of retpoline. We will add detailed documentation covering these components in subsequent patches, but wanted to make the core functionality available as soon as possible. Happy for more code review, but we'd really like to get these patches landed and backported ASAP for obvious reasons. We're planning to backport this to both 6.0 and 5.0 release streams and get a 5.0 release with just this cherry picked ASAP for distros and vendors. This patch is the work of a number of people over the past month: Eric, Reid, Rui, and myself. I'm mailing it out as a single commit due to the time sensitive nature of landing this and the need to backport it. Huge thanks to everyone who helped out here, and everyone at Intel who helped out in discussions about how to craft this. Also, credit goes to Paul Turner (at Google, but not an LLVM contributor) for much of the underlying retpoline design. Reviewers: echristo, rnk, ruiu, craig.topper, DavidKreitzer Subscribers: sanjoy, emaste, mcrosier, mgorny, mehdi_amini, hiraditya, llvm-commits Differential Revision: https://reviews.llvm.org/D41723 MFC after: 3 months X-MFC-With: r327952 PR: 224669 Notes: svn path=/head/; revision=328817
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ release_60 r321788,Dimitry Andric2018-01-062-4/+5
| | | | | | | update build glue and version numbers. Notes: svn path=/projects/clang600-import/; revision=327657
* Merge llvm trunk r321017 to contrib/llvm.Dimitry Andric2017-12-2024-429/+165
| | | | Notes: svn path=/projects/clang600-import/; revision=327023
* Upgrade our copies of clang, llvm, lld and lldb to r309439 from theDimitry Andric2017-07-301-8/+7
| | | | | | | | | | upstream release_50 branch. This is just after upstream's 5.0.0-rc1. MFC after: 2 months X-MFC-with: r321369 Notes: svn path=/head/; revision=321723
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r308421, and updateDimitry Andric2017-07-195-1/+24
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=321238
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r307894, and updateDimitry Andric2017-07-131-1/+2
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=320970
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r306956, and updateDimitry Andric2017-07-021-5/+7
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=320572
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r306325, and updateDimitry Andric2017-06-273-7/+13
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=320397
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r305145, and updateDimitry Andric2017-06-109-12/+11
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=319799
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r304460, and updateDimitry Andric2017-06-012-2/+6
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=319479
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r303571, and updateDimitry Andric2017-05-225-27/+19
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=318681
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r303197, and updateDimitry Andric2017-05-163-12/+34
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=318384
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r302418, and updateDimitry Andric2017-05-081-1/+1
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=317969
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r302069, and updateDimitry Andric2017-05-032-10/+9
| | | | | | | build glue (preliminary, not all option combinations work yet). Notes: svn path=/projects/clang500-import/; revision=317778
* Merge llvm, clang, lld, lldb, compiler-rt and libc++ r301441, and updateDimitry Andric2017-04-261-1/+3
| | | | | | | build glue. Notes: svn path=/projects/clang500-import/; revision=317472
* Merge llvm, clang, lld and lldb trunk r300890, and update build glue.Dimitry Andric2017-04-201-1/+1
| | | | Notes: svn path=/projects/clang500-import/; revision=317230
* Merge llvm trunk r300422 and resolve conflicts.Dimitry Andric2017-04-168-49/+77
| | | | Notes: svn path=/projects/clang500-import/; revision=317029
* Update llvm to trunk r290819 and resolve conflicts.Dimitry Andric2017-01-0225-1098/+474
| | | | Notes: svn path=/projects/clang400-import/; revision=311142
* Update llvm to release_39 branch r276489, and resolve conflicts.Dimitry Andric2016-08-1634-893/+3261
| | | | Notes: svn path=/projects/clang390-import/; revision=304240
* Update llvm and clang to release_38 branch r261369.Dimitry Andric2016-02-211-3/+3
| | | | Notes: svn path=/projects/clang380-import/; revision=295859
* Update llvm, clang and lldb to trunk r257626, and update build glue.Dimitry Andric2016-01-142-89/+96
| | | | Notes: svn path=/projects/clang380-import/; revision=294024
* Update llvm to trunk r256633.Dimitry Andric2015-12-3021-205/+1105
| | | | Notes: svn path=/projects/clang380-import/; revision=292941
* Upgrade our copies of clang and llvm to 3.7.1 release. This is aDimitry Andric2015-12-251-1/+1
| | | | | | | | | | bugfix-only release, with no new features. Please note that from 3.5.0 onwards, clang and llvm require C++11 support to build; see UPDATING for more information. Notes: svn path=/head/; revision=292735
* Update llvm, clang and lldb to 3.7.0 release.Dimitry Andric2015-09-061-8/+11
| | | | Notes: svn path=/projects/clang370-import/; revision=287521
* Update llvm/clang to r242221.Dimitry Andric2015-08-1214-158/+250
| | | | Notes: svn path=/projects/clang-trunk/; revision=286684
* Update llvm/clang to r241361.Dimitry Andric2015-07-0511-80/+92
| | | | Notes: svn path=/projects/clang-trunk/; revision=285181
* Update llvm/clang to r240225.Dimitry Andric2015-06-2318-48/+77
| | | | Notes: svn path=/projects/clang-trunk/; revision=284734
* Update Makefiles and other build glue for llvm/clang 3.7.0, as of trunkDimitry Andric2015-06-1012-60/+48
| | | | | | | r239412. Notes: svn path=/projects/clang-trunk/; revision=284236
* Merge llvm trunk r238337 from ^/vendor/llvm/dist, resolve conflicts, andDimitry Andric2015-05-2735-524/+851
| | | | | | | preserve our customizations, where necessary. Notes: svn path=/projects/clang-trunk/; revision=283631
* Merge llvm 3.6.0rc2 from ^/vendor/llvm/dist, merge clang 3.6.0rc2 fromDimitry Andric2015-01-311-1/+2
| | | | | | | ^/vendor/clang/dist, resolve conflicts, and cleanup patches. Notes: svn path=/projects/clang360-import/; revision=278002
* Merge llvm 3.6.0rc1 from ^/vendor/llvm/dist, merge clang 3.6.0rc1 fromDimitry Andric2015-01-2534-933/+176
| | | | | | | ^/vendor/clang/dist, resolve conflicts, and cleanup patches. Notes: svn path=/projects/clang360-import/; revision=277718
* Merge llvm 3.5.0 release from ^/vendor/llvm/dist, resolve conflicts, andDimitry Andric2014-11-2446-770/+2063
| | | | | | | preserve our customizations, where necessary. Notes: svn path=/projects/clang350-import/; revision=274968
* Repair a few minor mismerges from r262261 in the clang-sparc64 projectDimitry Andric2014-03-104-85/+1
| | | | | | | | | | branch. This is also to minimize differences with upstream. MFC after: 3 weeks X-MFC-With: r262613 Notes: svn path=/head/; revision=262985
* Pull in r202422 from upstream llvm trunk (by Roman Divacky):Dimitry Andric2014-02-271-17/+8
| | | | | | | | | Lower FNEG just like FABS to fneg[ds] and fmov[ds], thus avoiding expensive libcall. Also, Qp_neg is not implemented on at least FreeBSD. This is also what gcc is doing. Notes: svn path=/projects/clang-sparc64/; revision=262582
* Pull in r201994 from upstream llvm trunk (by Benjamin Kramer):Dimitry Andric2014-02-232-0/+5
| | | | | | | | | | SPARC: Implement TRAP lowering. Matches what GCC emits. This lets clang emit "ta 5" for trap instructions on sparc64, instead of emitting a call to abort(), making it possible to link the kernel. Notes: svn path=/projects/clang-sparc64/; revision=262415
* Pull in r201718 from upstream llvm trunk:Dimitry Andric2014-02-201-0/+4
| | | | | | | | | Expand 64bit {SHL,SHR,SRA}_PARTS on sparcv9. Submitted by: rdivacky Notes: svn path=/projects/clang-sparc64/; revision=262265
* Pull in r200453 from upstream llvm trunk:Dimitry Andric2014-02-202-3/+15
| | | | | | | | | | | | | Implement SPARCv9 atomic_swap_64 with a pseudo. The SWAP instruction only exists in a 32-bit variant, but the 64-bit atomic swap can be implemented in terms of CASX, like the other atomic rmw primitives. Submitted by: rdivacky Notes: svn path=/projects/clang-sparc64/; revision=262264
* Import a whole bunch of llvm trunk commits to enable self-hosting clangDimitry Andric2014-02-2037-757/+4437
| | | | | | | | | | | | | | | | | 3.4 on Sparc64 (commit descriptions left out for brevity): r196755 r198028 r198029 r198030 r198145 r198149 r198157 r198565 r199186 r199187 r198280 r198281 r198286 r198480 r198484 r198533 r198567 r198580 r198591 r198592 r198658 r198681 r198738 r198739 r198740 r198893 r198909 r198910 r199014 r199024 r199028 r199031 r199033 r199061 r199775 r199781 r199786 r199940 r199974 r199975 r199977 r200103 r200104 r200112 r200130 r200131 r200141 r200282 r200368 r200373 r200376 r200509 r200617 r200960 r200961 r200962 r200963 r200965 Submitted by: rdivacky Notes: svn path=/projects/clang-sparc64/; revision=262261
* Upgrade our copy of llvm/clang to 3.4 release. This version supportsDimitry Andric2014-02-1632-712/+3199
| | | | | | | | | | | | | | | | | | | | all of the features in the current working draft of the upcoming C++ standard, provisionally named C++1y. The code generator's performance is greatly increased, and the loop auto-vectorizer is now enabled at -Os and -O2 in addition to -O3. The PowerPC backend has made several major improvements to code generation quality and compile time, and the X86, SPARC, ARM32, Aarch64 and SystemZ backends have all seen major feature work. Release notes for llvm and clang can be found here: <http://llvm.org/releases/3.4/docs/ReleaseNotes.html> <http://llvm.org/releases/3.4/tools/clang/docs/ReleaseNotes.html> MFC after: 1 month Notes: svn path=/head/; revision=261991
* Pull in r191165 from upstream llvm trunk:Dimitry Andric2013-09-221-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | ISelDAG: spot chain cycles involving MachineNodes Previously, the DAGISel function WalkChainUsers was spotting that it had entered already-selected territory by whether a node was a MachineNode (amongst other things). Since it's fairly common practice to insert MachineNodes during ISelLowering, this was not the correct check. Looking around, it seems that other nodes get their NodeId set to -1 upon selection, so this makes sure the same thing happens to all MachineNodes and uses that characteristic to determine whether we should stop looking for a loop during selection. This should fix PR15840. Specifically, this fixes the long-standing assertion failure when compiling the multimedia/gstreamer port on i386. Thanks to Tijl Coosemans for his help in getting upstream to fix it. Approved by: re (marius) Notes: svn path=/head/; revision=255804
* Upgrade our copy of llvm/clang to 3.3 release.Dimitry Andric2013-06-1214-176/+941
| | | | | | | | | Release notes are still in the works, these will follow soon. MFC after: 1 month Notes: svn path=/head/; revision=251662
* Upgrade our copy of llvm/clang to trunk r178860, in preparation of theDimitry Andric2013-04-1220-211/+660
| | | | | | | | | | | | upcoming 3.3 release (branching and freezing expected in a few weeks). Preliminary release notes can be found at the usual location: <http://llvm.org/docs/ReleaseNotes.html> An MFC is planned once the actual 3.3 release is finished. Notes: svn path=/head/; revision=249423
* Upgrade our copy of llvm/clang to r168974, from upstream's release_32Dimitry Andric2012-12-035-8/+17
| | | | | | | | branch. This is effectively llvm/clang 3.2 RC2; the 3.2 release is coming soon. Notes: svn path=/head/; revision=243830
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-05 00:00:57 +0000