[llvm] [X86] Change how we treat functions with explicit sections as small/large (PR #88172)

[Arthur Eubanks via llvm-commits]

https://github.com/aeubanks updated https://github.com/llvm/llvm-project/pull/88172

>From 838f4b1abc42d2e50d4124876ebee6773d3adc4e Mon Sep 17 00:00:00 2001
From: Arthur Eubanks <aeubanks at google.com>
Date: Mon, 8 Apr 2024 16:40:19 -0600
Subject: [PATCH 1/2] [X86] Change how we treat functions with explicit
 sections as small/large

Following #78348, we should treat functions with an explicit section as
small, unless the section name is (or has the prefix) ".ltext".

Clang emits global initializers into a ".text.startup" section on Linux.
If we mix small/medium code model object files with large code model
object files, we'll end up mixing sections with and without the large
section flag.

Reland of #87838 with a check for non-ELF platforms in
TargetMachine::isLargeGlobalValue(), otherwise MCJIT on Windows tests
fail.
---
 llvm/lib/Target/TargetMachine.cpp             | 23 ++++++++++++++-----
 .../X86/code-model-elf-text-sections.ll       | 23 +++++++++++++++++++
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/llvm/lib/Target/TargetMachine.cpp b/llvm/lib/Target/TargetMachine.cpp
index a7fe329b064ee1..4ae6a468df21f3 100644
--- a/llvm/lib/Target/TargetMachine.cpp
+++ b/llvm/lib/Target/TargetMachine.cpp
@@ -43,6 +43,9 @@ bool TargetMachine::isLargeGlobalValue(const GlobalValue *GVal) const {
   if (getTargetTriple().getArch() != Triple::x86_64)
     return false;
 
+  if (!getTargetTriple().isOSBinFormatELF())
+    return getCodeModel() == CodeModel::Large;
+
   auto *GO = GVal->getAliaseeObject();
 
   // Be conservative if we can't find an underlying GlobalObject.
@@ -51,9 +54,20 @@ bool TargetMachine::isLargeGlobalValue(const GlobalValue *GVal) const {
 
   auto *GV = dyn_cast<GlobalVariable>(GO);
 
+  auto IsPrefix = [](StringRef Name, StringRef Prefix) {
+    return Name.consume_front(Prefix) && (Name.empty() || Name[0] == '.');
+  };
+
   // Functions/GlobalIFuncs are only large under the large code model.
-  if (!GV)
+  if (!GV) {
+    // Handle explicit sections as we do for GlobalVariables with an explicit
+    // section, see comments below.
+    if (GO->hasSection()) {
+      StringRef Name = GO->getSection();
+      return IsPrefix(Name, ".ltext");
+    }
     return getCodeModel() == CodeModel::Large;
+  }
 
   if (GV->isThreadLocal())
     return false;
@@ -73,11 +87,8 @@ bool TargetMachine::isLargeGlobalValue(const GlobalValue *GVal) const {
   // data sections. The code model attribute overrides this above.
   if (GV->hasSection()) {
     StringRef Name = GV->getSection();
-    auto IsPrefix = [&](StringRef Prefix) {
-      StringRef S = Name;
-      return S.consume_front(Prefix) && (S.empty() || S[0] == '.');
-    };
-    return IsPrefix(".lbss") || IsPrefix(".ldata") || IsPrefix(".lrodata");
+    return IsPrefix(Name, ".lbss") || IsPrefix(Name, ".ldata") ||
+           IsPrefix(Name, ".lrodata");
   }
 
   // Respect large data threshold for medium and large code models.
diff --git a/llvm/test/CodeGen/X86/code-model-elf-text-sections.ll b/llvm/test/CodeGen/X86/code-model-elf-text-sections.ll
index 016c9a4d7b8390..66a6fd37675427 100644
--- a/llvm/test/CodeGen/X86/code-model-elf-text-sections.ll
+++ b/llvm/test/CodeGen/X86/code-model-elf-text-sections.ll
@@ -13,9 +13,20 @@
 ; RUN: llvm-readelf -S %t | FileCheck %s --check-prefix=LARGE-DS
 
 ; SMALL: .text {{.*}} AX {{.*}}
+; SMALL: .ltext {{.*}} AXl {{.*}}
+; SMALL: .ltext.2 {{.*}} AXl {{.*}}
+; SMALL: .foo {{.*}} AX {{.*}}
 ; SMALL-DS: .text.func {{.*}} AX {{.*}}
+; SMALL-DS: .ltext {{.*}} AXl {{.*}}
+; SMALL-DS: .ltext.2 {{.*}} AXl {{.*}}
+; SMALL-DS: .foo {{.*}} AX {{.*}}
 ; LARGE: .ltext {{.*}} AXl {{.*}}
+; LARGE: .ltext.2 {{.*}} AXl {{.*}}
+; LARGE: .foo {{.*}} AX {{.*}}
 ; LARGE-DS: .ltext.func {{.*}} AXl {{.*}}
+; LARGE-DS: .ltext {{.*}} AXl {{.*}}
+; LARGE-DS: .ltext.2 {{.*}} AXl {{.*}}
+; LARGE-DS: .foo {{.*}} AX {{.*}}
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64--linux"
@@ -23,3 +34,15 @@ target triple = "x86_64--linux"
 define void @func() {
   ret void
 }
+
+define void @ltext() section ".ltext" {
+  ret void
+}
+
+define void @ltext2() section ".ltext.2" {
+  ret void
+}
+
+define void @foo() section ".foo" {
+  ret void
+}

>From fa0655b3f3ddbb8d82232bdffd846615abc74e75 Mon Sep 17 00:00:00 2001
From: Arthur Eubanks <aeubanks at google.com>
Date: Tue, 16 Apr 2024 18:20:04 +0000
Subject: [PATCH 2/2] add comment

---
 llvm/lib/Target/TargetMachine.cpp | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/llvm/lib/Target/TargetMachine.cpp b/llvm/lib/Target/TargetMachine.cpp
index 4ae6a468df21f3..8ddc742004292b 100644
--- a/llvm/lib/Target/TargetMachine.cpp
+++ b/llvm/lib/Target/TargetMachine.cpp
@@ -43,6 +43,9 @@ bool TargetMachine::isLargeGlobalValue(const GlobalValue *GVal) const {
   if (getTargetTriple().getArch() != Triple::x86_64)
     return false;
 
+  // Remaining logic below is ELF-specific. For other object file formats where
+  // the large code model is mostly used for JIT compilation, just look at the
+  // code model.
   if (!getTargetTriple().isOSBinFormatELF())
     return getCodeModel() == CodeModel::Large;