[MC] Recalculate fragment offsets after relaxation

Summary:
The current relaxation implementation is not correctly adjusting the
size and offsets of fragements in one section based on changes in size
of another if the layout order of the two happened to be such that the
former was visited before the later. Therefore, we need to invalidate
the fragments in all sections after each iteration of relaxation, and
possibly further relax some of them in the next ieration. This fixes
PR#45190.

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76114

llvm/lib/MC/MCAssembler.cpp

@@ -785,9 +785,15 @@ void MCAssembler::layout(MCAsmLayout &Layout) {
   }
 
   // Layout until everything fits.
-  while (layoutOnce(Layout))
+  while (layoutOnce(Layout)) {
     if (getContext().hadError())
       return;
+    // Size of fragments in one section can depend on the size of fragments in
+    // another. If any fragment has changed size, we have to re-layout (and
+    // as a result possibly further relax) all.
+    for (MCSection &Sec : *this)
+      Layout.invalidateFragmentsFrom(&*Sec.begin());
+  }
 
   DEBUG_WITH_TYPE("mc-dump", {
       errs() << "assembler backend - post-relaxation\n--\n";

llvm/test/MC/X86/relax-offset.s

@@ -0,0 +1,13 @@
+# RUN: llvm-mc -filetype=obj -triple=i386 %s | llvm-objdump - --headers | FileCheck %s
+
+  # CHECK: .text1        00000005 00000000
+  # CHECK: .text2        00000005 00000000
+
+  .section .text1
+ .skip after-before,0x0
+.Lint80_keep_stack:
+
+  .section .text2
+before:
+ jmp .Lint80_keep_stack
+after: