llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-bolt Author: Amir Ayupov (aaupov) <details> <summary>Changes</summary> Deleted basic blocks are required for correct mapping of branches modified by SCTC. Test Plan: updated bb-with-two-tail-calls.s --- Full diff: https://github.com/llvm/llvm-project/pull/91906.diff 4 Files Affected: - (modified) bolt/docs/BAT.md (+5) - (modified) bolt/include/bolt/Profile/BoltAddressTranslation.h (+1) - (modified) bolt/lib/Profile/BoltAddressTranslation.cpp (+13) - (modified) bolt/test/X86/bb-with-two-tail-calls.s (+9) ``````````diff diff --git a/bolt/docs/BAT.md b/bolt/docs/BAT.md index 7ffb5d7c00816..817ad288aa34b 100644 --- a/bolt/docs/BAT.md +++ b/bolt/docs/BAT.md @@ -106,9 +106,14 @@ equals output offset. `BRANCHENTRY` bit denotes whether a given offset pair is a control flow source (branch or call instruction). If not set, it signifies a control flow target (basic block offset). + `InputAddr` is omitted for equal offsets in input and output function. In this case, `BRANCHENTRY` bits are encoded separately in a `BranchEntries` bitvector. +Deleted basic blocks are emitted as having `OutputOffset` equal to the size of +the function. They don't affect address translation and only participate in +input basic block mapping. + ### Secondary Entry Points table The table is emitted for hot fragments only. It contains `NumSecEntryPoints` offsets denoting secondary entry points, delta encoded, implicitly starting at zero. diff --git a/bolt/include/bolt/Profile/BoltAddressTranslation.h b/bolt/include/bolt/Profile/BoltAddressTranslation.h index 68b993ee363cc..16fe0442f10a5 100644 --- a/bolt/include/bolt/Profile/BoltAddressTranslation.h +++ b/bolt/include/bolt/Profile/BoltAddressTranslation.h @@ -217,6 +217,7 @@ class BoltAddressTranslation { auto begin() const { return Map.begin(); } auto end() const { return Map.end(); } auto upper_bound(uint32_t Offset) const { return Map.upper_bound(Offset); } + auto size() const { return Map.size(); } }; /// Map function output address to its hash and basic blocks hash map. diff --git a/bolt/lib/Profile/BoltAddressTranslation.cpp b/bolt/lib/Profile/BoltAddressTranslation.cpp index 7cfb9c132c2c6..724b348c7845e 100644 --- a/bolt/lib/Profile/BoltAddressTranslation.cpp +++ b/bolt/lib/Profile/BoltAddressTranslation.cpp @@ -108,6 +108,19 @@ void BoltAddressTranslation::write(const BinaryContext &BC, raw_ostream &OS) { for (const BinaryBasicBlock *const BB : Function.getLayout().getMainFragment()) writeEntriesForBB(Map, *BB, InputAddress, OutputAddress); + // Add entries for deleted blocks. They are still required for correct BB + // mapping of branches modified by SCTC. By convention, they would have the + // end of the function as output address. + const BBHashMapTy &BBHashMap = getBBHashMap(InputAddress); + if (BBHashMap.size() != Function.size()) { + const uint64_t EndOffset = Function.getOutputSize(); + std::unordered_set<uint32_t> MappedInputOffsets; + for (const BinaryBasicBlock &BB : Function) + MappedInputOffsets.emplace(BB.getInputOffset()); + for (const auto &[InputOffset, _] : BBHashMap) + if (!llvm::is_contained(MappedInputOffsets, InputOffset)) + Map[EndOffset] = InputOffset << 1; + } Maps.emplace(Function.getOutputAddress(), std::move(Map)); ReverseMap.emplace(OutputAddress, InputAddress); diff --git a/bolt/test/X86/bb-with-two-tail-calls.s b/bolt/test/X86/bb-with-two-tail-calls.s index bb2b0cd4cc23a..c0b01e1894a49 100644 --- a/bolt/test/X86/bb-with-two-tail-calls.s +++ b/bolt/test/X86/bb-with-two-tail-calls.s @@ -10,11 +10,20 @@ # RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib # RUN: llvm-bolt %t.exe -o %t.out --data %t.fdata --lite=0 --dyno-stats \ # RUN: --print-sctc --print-only=_start -enable-bat 2>&1 | FileCheck %s +# RUN: llvm-objdump --syms %t.out | FileCheck %s --check-prefix=CHECK-NM +# RUN: llvm-bat-dump %t.out --dump-all | FileCheck %s --check-prefix=CHECK-BAT + # CHECK-NOT: Assertion `BranchInfo.size() == 2 && "could only be called for blocks with 2 successors"' failed. # Two tail calls in the same basic block after SCTC: # CHECK: {{.*}}: ja {{.*}} # TAILCALL # Offset: 7 # CTCTakenCount: 4 # CHECK-NEXT: {{.*}}: jmp {{.*}} # TAILCALL # Offset: 12 +# Confirm that a deleted basic block is emitted at function end offset (0xe) +# CHECK-NM: 0000000000600000 g .text 000000000000000e _start +# CHECK-BAT: Function Address: 0x600000, hash: 0xf8bf620b266cdc1b +# CHECK-BAT: 0xe -> 0xc hash: 0x823623240f000c +# CHECK-BAT: NumBlocks: 5 + .globl _start _start: je x `````````` </details> https://github.com/llvm/llvm-project/pull/91906 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
