BasicBlockSections.cpp | Explore in Territory

//===-- BasicBlockSections.cpp ---=========--------------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// BasicBlockSections implementation.
//
// The purpose of this pass is to assign sections to basic blocks when
// -fbasic-block-sections= option is used. Further, with profile information
// only the subset of basic blocks with profiles are placed in separate sections
// and the rest are grouped in a cold section. The exception handling blocks are
// treated specially to ensure they are all in one seciton.
//
// Basic Block Sections
// ====================
//
// With option, -fbasic-block-sections=list, every function may be split into
// clusters of basic blocks. Every cluster will be emitted into a separate
// section with its basic blocks sequenced in the given order. To get the
// optimized performance, the clusters must form an optimal BB layout for the
// function. We insert a symbol at the beginning of every cluster's section to
// allow the linker to reorder the sections in any arbitrary sequence. A global
// order of these sections would encapsulate the function layout.
// For example, consider the following clusters for a function foo (consisting
// of 6 basic blocks 0, 1, ..., 5).
//
// 0 2
// 1 3 5
//
// * Basic blocks 0 and 2 are placed in one section with symbol `foo`
//   referencing the beginning of this section.
// * Basic blocks 1, 3, 5 are placed in a separate section. A new symbol
//   `foo.__part.1` will reference the beginning of this section.
// * Basic block 4 (note that it is not referenced in the list) is placed in
//   one section, and a new symbol `foo.cold` will point to it.
//
// There are a couple of challenges to be addressed:
//
// 1. The last basic block of every cluster should not have any implicit
//    fallthrough to its next basic block, as it can be reordered by the linker.
//    The compiler should make these fallthroughs explicit by adding
//    unconditional jumps..
//
// 2. All inter-cluster branch targets would now need to be resolved by the
//    linker as they cannot be calculated during compile time. This is done
//    using static relocations. Further, the compiler tries to use short branch
//    instructions on some ISAs for small branch offsets. This is not possible
//    for inter-cluster branches as the offset is not determined at compile
//    time, and therefore, long branch instructions have to be used for those.
//
// 3. Debug Information (DebugInfo) and Call Frame Information (CFI) emission
//    needs special handling with basic block sections. DebugInfo needs to be
//    emitted with more relocations as basic block sections can break a
//    function into potentially several disjoint pieces, and CFI needs to be
//    emitted per cluster. This also bloats the object file and binary sizes.
//
// Basic Block Address Map
// ==================
//
// With -fbasic-block-address-map, we emit the offsets of BB addresses of
// every function into the .llvm_bb_addr_map section. Along with the function
// symbols, this allows for mapping of virtual addresses in PMU profiles back to
// the corresponding basic blocks. This logic is implemented in AsmPrinter. This
// pass only assigns the BBSectionType of every function to ``labels``.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/CodeGen/BasicBlockSectionUtils.h"
#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachinePostDominators.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/InitializePasses.h"
#include "llvm/Target/TargetMachine.h"
#include <optional>

usingnamespacellvm;

// Placing the cold clusters in a separate section mitigates against poor
// profiles and allows optimizations such as hugepage mapping to be applied at a
// section granularity. Defaults to ".text.split." which is recognized by lld
// via the `-z keep-text-section-prefix` flag.
cl::opt<std::string> llvm::BBSectionsColdTextPrefix(
    "bbsections-cold-text-prefix",
    cl::desc("The text prefix to use for cold basic block clusters"),
    cl::init(".text.split."), cl::Hidden);

static cl::opt<bool> BBSectionsDetectSourceDrift(
    "bbsections-detect-source-drift",
    cl::desc("This checks if there is a fdo instr. profile hash "
             "mismatch for this function"),
    cl::init(true), cl::Hidden);

namespace {

class BasicBlockSections : public MachineFunctionPass { … };

} // end anonymous namespace

char BasicBlockSections::ID = …;
INITIALIZE_PASS_BEGIN(
    BasicBlockSections, "bbsections-prepare",
    "Prepares for basic block sections, by splitting functions "
    "into clusters of basic blocks.",
    false, false)
INITIALIZE_PASS_DEPENDENCY(BasicBlockSectionsProfileReaderWrapperPass)
INITIALIZE_PASS_END(BasicBlockSections, "bbsections-prepare",
                    "Prepares for basic block sections, by splitting functions "
                    "into clusters of basic blocks.",
                    false, false)

// This function updates and optimizes the branching instructions of every basic
// block in a given function to account for changes in the layout.
static void
updateBranches(MachineFunction &MF,
               const SmallVector<MachineBasicBlock *> &PreLayoutFallThroughs) { … }

// This function sorts basic blocks according to the cluster's information.
// All explicitly specified clusters of basic blocks will be ordered
// accordingly. All non-specified BBs go into a separate "Cold" section.
// Additionally, if exception handling landing pads end up in more than one
// clusters, they are moved into a single "Exception" section. Eventually,
// clusters are ordered in increasing order of their IDs, with the "Exception"
// and "Cold" succeeding all other clusters.
// FuncClusterInfo represents the cluster information for basic blocks. It
// maps from BBID of basic blocks to their cluster information. If this is
// empty, it means unique sections for all basic blocks in the function.
static void
assignSections(MachineFunction &MF,
               const DenseMap<UniqueBBID, BBClusterInfo> &FuncClusterInfo) { … }

void llvm::sortBasicBlocksAndUpdateBranches(
    MachineFunction &MF, MachineBasicBlockComparator MBBCmp) { … }

// If the exception section begins with a landing pad, that landing pad will
// assume a zero offset (relative to @LPStart) in the LSDA. However, a value of
// zero implies "no landing pad." This function inserts a NOP just before the EH
// pad label to ensure a nonzero offset.
void llvm::avoidZeroOffsetLandingPad(MachineFunction &MF) { … }

bool llvm::hasInstrProfHashMismatch(MachineFunction &MF) { … }

// Identify, arrange, and modify basic blocks which need separate sections
// according to the specification provided by the -fbasic-block-sections flag.
bool BasicBlockSections::handleBBSections(MachineFunction &MF) { … }

// When the BB address map needs to be generated, this renumbers basic blocks to
// make them appear in increasing order of their IDs in the function. This
// avoids the need to store basic block IDs in the BB address map section, since
// they can be determined implicitly.
bool BasicBlockSections::handleBBAddrMap(MachineFunction &MF) { … }

bool BasicBlockSections::runOnMachineFunction(MachineFunction &MF) { … }

void BasicBlockSections::getAnalysisUsage(AnalysisUsage &AU) const { … }

MachineFunctionPass *llvm::createBasicBlockSectionsPass() { … }
llvm/llvm/lib/CodeGen/BasicBlockSections.cpp
