[llvm-branch-commits] [BOLT] Encode landing pads in BAT (PR #114602)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Nov 1 13:31:22 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-bolt
Author: Amir Ayupov (aaupov)
<details>
<summary>Changes</summary>
Reuse secondary entry points vector and include landing pad offsets.
Use LSB to encode LPENTRY bit, similar to BRANCHENTRY bit used to
distinguish branch and block entries in the address map.
Test Plan: updated bolt-address-translation.test
---
Full diff: https://github.com/llvm/llvm-project/pull/114602.diff
4 Files Affected:
- (modified) bolt/docs/BAT.md (+8-4)
- (modified) bolt/include/bolt/Profile/BoltAddressTranslation.h (+3)
- (modified) bolt/lib/Profile/BoltAddressTranslation.cpp (+41-29)
- (modified) bolt/test/X86/callcont-fallthru.s (+7-1)
``````````diff
diff --git a/bolt/docs/BAT.md b/bolt/docs/BAT.md
index 817ad288aa34ba..3b42c36541acd3 100644
--- a/bolt/docs/BAT.md
+++ b/bolt/docs/BAT.md
@@ -54,7 +54,7 @@ Functions table:
| table |
| |
| Secondary entry |
-| points |
+| points and LPs |
|------------------|
```
@@ -80,7 +80,7 @@ Hot indices are delta encoded, implicitly starting at zero.
| `HotIndex` | Delta, ULEB128 | Index of corresponding hot function in hot functions table | Cold |
| `FuncHash` | 8b | Function hash for input function | Hot |
| `NumBlocks` | ULEB128 | Number of basic blocks in the original function | Hot |
-| `NumSecEntryPoints` | ULEB128 | Number of secondary entry points in the original function | Hot |
+| `NumSecEntryPoints` | ULEB128 | Number of secondary entry points and landing pads in the original function | Hot |
| `ColdInputSkew` | ULEB128 | Skew to apply to all input offsets | Cold |
| `NumEntries` | ULEB128 | Number of address translation entries for a function | Both |
| `EqualElems` | ULEB128 | Number of equal offsets in the beginning of a function | Both |
@@ -116,7 +116,11 @@ 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.
+offsets denoting secondary entry points and landing pads, delta encoded,
+implicitly starting at zero.
| Entry | Encoding | Description |
| ----- | -------- | ----------- |
-| `SecEntryPoint` | Delta, ULEB128 | Secondary entry point offset |
+| `SecEntryPoint` | Delta, ULEB128 | Secondary entry point offset with `LPENTRY` LSB bit |
+
+`LPENTRY` bit denotes whether a given offset is a landing pad block. If not set,
+the offset is a secondary entry point.
diff --git a/bolt/include/bolt/Profile/BoltAddressTranslation.h b/bolt/include/bolt/Profile/BoltAddressTranslation.h
index 65b9ba874368f3..62367ca3aebdce 100644
--- a/bolt/include/bolt/Profile/BoltAddressTranslation.h
+++ b/bolt/include/bolt/Profile/BoltAddressTranslation.h
@@ -181,6 +181,9 @@ class BoltAddressTranslation {
/// translation map entry
const static uint32_t BRANCHENTRY = 0x1;
+ /// Identifies a landing pad in secondary entry point map entry.
+ const static uint32_t LPENTRY = 0x1;
+
public:
/// Map basic block input offset to a basic block index and hash pair.
class BBHashMapTy {
diff --git a/bolt/lib/Profile/BoltAddressTranslation.cpp b/bolt/lib/Profile/BoltAddressTranslation.cpp
index ec7e303c0f52e8..9ce62052653e36 100644
--- a/bolt/lib/Profile/BoltAddressTranslation.cpp
+++ b/bolt/lib/Profile/BoltAddressTranslation.cpp
@@ -86,21 +86,16 @@ void BoltAddressTranslation::write(const BinaryContext &BC, raw_ostream &OS) {
if (Function.isIgnored() || (!BC.HasRelocations && !Function.isSimple()))
continue;
- uint32_t NumSecondaryEntryPoints = 0;
- Function.forEachEntryPoint([&](uint64_t Offset, const MCSymbol *) {
- if (!Offset)
- return true;
- ++NumSecondaryEntryPoints;
- SecondaryEntryPointsMap[OutputAddress].push_back(Offset);
- return true;
- });
-
LLVM_DEBUG(dbgs() << "Function name: " << Function.getPrintName() << "\n");
LLVM_DEBUG(dbgs() << " Address reference: 0x"
<< Twine::utohexstr(Function.getOutputAddress()) << "\n");
LLVM_DEBUG(dbgs() << formatv(" Hash: {0:x}\n", getBFHash(InputAddress)));
- LLVM_DEBUG(dbgs() << " Secondary Entry Points: " << NumSecondaryEntryPoints
- << '\n');
+ LLVM_DEBUG({
+ uint32_t NumSecondaryEntryPoints = 0;
+ if (SecondaryEntryPointsMap.count(InputAddress))
+ NumSecondaryEntryPoints = SecondaryEntryPointsMap[InputAddress].size();
+ dbgs() << " Secondary Entry Points: " << NumSecondaryEntryPoints << '\n';
+ });
MapTy Map;
for (const BinaryBasicBlock *const BB :
@@ -207,10 +202,9 @@ void BoltAddressTranslation::writeMaps(std::map<uint64_t, MapTy> &Maps,
<< Twine::utohexstr(Address) << ".\n");
encodeULEB128(Address - PrevAddress, OS);
PrevAddress = Address;
- const uint32_t NumSecondaryEntryPoints =
- SecondaryEntryPointsMap.count(Address)
- ? SecondaryEntryPointsMap[Address].size()
- : 0;
+ uint32_t NumSecondaryEntryPoints = 0;
+ if (SecondaryEntryPointsMap.count(HotInputAddress))
+ NumSecondaryEntryPoints = SecondaryEntryPointsMap[HotInputAddress].size();
uint32_t Skew = 0;
if (Cold) {
auto HotEntryIt = Maps.find(ColdPartSource[Address]);
@@ -281,7 +275,7 @@ void BoltAddressTranslation::writeMaps(std::map<uint64_t, MapTy> &Maps,
if (!Cold && NumSecondaryEntryPoints) {
LLVM_DEBUG(dbgs() << "Secondary entry points: ");
// Secondary entry point offsets, delta-encoded
- for (uint32_t Offset : SecondaryEntryPointsMap[Address]) {
+ for (uint32_t Offset : SecondaryEntryPointsMap[HotInputAddress]) {
encodeULEB128(Offset - PrevOffset, OS);
LLVM_DEBUG(dbgs() << formatv("{0:x} ", Offset));
PrevOffset = Offset;
@@ -471,8 +465,12 @@ void BoltAddressTranslation::dump(raw_ostream &OS) const {
const std::vector<uint32_t> &SecondaryEntryPoints =
SecondaryEntryPointsIt->second;
OS << SecondaryEntryPoints.size() << " secondary entry points:\n";
- for (uint32_t EntryPointOffset : SecondaryEntryPoints)
- OS << formatv("{0:x}\n", EntryPointOffset);
+ for (uint32_t EntryPointOffset : SecondaryEntryPoints) {
+ OS << formatv("{0:x}", EntryPointOffset >> 1);
+ if (EntryPointOffset & LPENTRY)
+ OS << " (lp)";
+ OS << '\n';
+ }
}
OS << "\n";
}
@@ -584,14 +582,21 @@ void BoltAddressTranslation::saveMetadata(BinaryContext &BC) {
// changed
if (BF.isIgnored() || (!BC.HasRelocations && !BF.isSimple()))
continue;
+ const uint64_t FuncAddress = BF.getAddress();
// Prepare function and block hashes
- FuncHashes.addEntry(BF.getAddress(), BF.computeHash());
+ FuncHashes.addEntry(FuncAddress, BF.computeHash());
BF.computeBlockHashes();
- BBHashMapTy &BBHashMap = getBBHashMap(BF.getAddress());
+ BBHashMapTy &BBHashMap = getBBHashMap(FuncAddress);
+ std::vector<uint32_t> SecondaryEntryPoints;
// Set BF/BB metadata
- for (const BinaryBasicBlock &BB : BF)
+ for (const BinaryBasicBlock &BB : BF) {
BBHashMap.addEntry(BB.getInputOffset(), BB.getIndex(), BB.getHash());
- NumBasicBlocksMap.emplace(BF.getAddress(), BF.size());
+ bool IsLandingPad = BB.isLandingPad();
+ if (IsLandingPad || BF.getSecondaryEntryPointSymbol(BB))
+ SecondaryEntryPoints.emplace_back(BB.getOffset() << 1 | IsLandingPad);
+ }
+ SecondaryEntryPointsMap.emplace(FuncAddress, SecondaryEntryPoints);
+ NumBasicBlocksMap.emplace(FuncAddress, BF.size());
}
}
@@ -601,13 +606,20 @@ BoltAddressTranslation::getSecondaryEntryPointId(uint64_t Address,
auto FunctionIt = SecondaryEntryPointsMap.find(Address);
if (FunctionIt == SecondaryEntryPointsMap.end())
return 0;
- const std::vector<uint32_t> &Offsets = FunctionIt->second;
- auto OffsetIt = std::find(Offsets.begin(), Offsets.end(), Offset);
- if (OffsetIt == Offsets.end())
- return 0;
- // Adding one here because main entry point is not stored in BAT, and
- // enumeration for secondary entry points starts with 1.
- return OffsetIt - Offsets.begin() + 1;
+ unsigned EntryPoints = 0;
+ // Note we need to scan the vector to get the entry point id because it
+ // contains both entry points and landing pads.
+ for (uint32_t Off : FunctionIt->second) {
+ // Skip landing pads.
+ if (Off & LPENTRY)
+ continue;
+ // Adding one here because main entry point is not stored in BAT, and
+ // enumeration for secondary entry points starts with 1.
+ if (Off >> 1 == Offset)
+ return EntryPoints + 1;
+ ++EntryPoints;
+ }
+ return 0;
}
std::pair<const BinaryFunction *, unsigned>
diff --git a/bolt/test/X86/callcont-fallthru.s b/bolt/test/X86/callcont-fallthru.s
index 31a7910d7fa3f4..641beb79ecf2ac 100644
--- a/bolt/test/X86/callcont-fallthru.s
+++ b/bolt/test/X86/callcont-fallthru.s
@@ -22,9 +22,15 @@
# RUN: --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK3
## Check fallthrough to a landing pad case.
-# RUN: llvm-bolt %t.exe --pa -p %t.pa4 -o %t.out \
+# RUN: llvm-bolt %t.exe --pa -p %t.pa4 -o %t.out --enable-bat \
# RUN: --print-cfg --print-only=main | FileCheck %s --check-prefix=CHECK4
+## Check that a landing pad is emitted in BAT
+# RUN: llvm-bat-dump %t.out --dump-all | FileCheck %s --check-prefix=CHECK-BAT
+
+# CHECK-BAT: 1 secondary entry points:
+# CHECK-BAT-NEXT: 0x38 (lp)
+
.globl foo
.type foo, %function
foo:
``````````
</details>
https://github.com/llvm/llvm-project/pull/114602
More information about the llvm-branch-commits
mailing list