[LLD][COFF] Align EC code ranges to page boundaries

We already ensure that code for different architectures is always placed in different pages
in assignAddresses. We represent those ranges using their first and last chunks.
However, the RVAs of those chunks may not be page-aligned, for example, due to extra padding
for entry-thunk offsets. Align the chunk RVAs to the page boundary so that the emitted ranges
correctly include the entire region.

This change affects an existing test that checks corner cases triggered by merging a data
section into a code section. We may now include such data in the code range. This differs from
MSVC’s behavior, but it should not cause practical issues, and the new behavior is arguably
more correct.

Fixes #168119.

Author: cjacek

lld/COFF/Chunks.cpp

@@ -946,7 +946,7 @@ void ECCodeMapChunk::writeTo(uint8_t *buf) const {
   auto table = reinterpret_cast<chpe_range_entry *>(buf);
   for (uint32_t i = 0; i < map.size(); i++) {
     const ECCodeMapEntry &entry = map[i];
-    uint32_t start = entry.first->getRVA();
+    uint32_t start = entry.first->getRVA() & ~0xfff;
     table[i].StartOffset = start | entry.type;
     table[i].Length = entry.last->getRVA() + entry.last->getSize() - start;
   }

lld/test/COFF/arm64ec-codemap.test

@@ -7,6 +7,7 @@ RUN: llvm-mc -filetype=obj -triple=arm64ec-windows arm64ec-func-sym2.s -o arm64e
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows data-sec.s -o data-sec.obj
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows data-sec2.s -o data-sec2.obj
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows empty-sec.s -o arm64ec-empty-sec.obj
+RUN: llvm-mc -filetype=obj -triple=arm64ec-windows entry-thunk.s -o entry-thunk.obj
 RUN: llvm-mc -filetype=obj -triple=x86_64-windows x86_64-func-sym.s -o x86_64-func-sym.obj
 RUN: llvm-mc -filetype=obj -triple=x86_64-windows empty-sec.s -o x86_64-empty-sec.obj
 RUN: llvm-mc -filetype=obj -triple=aarch64-windows %S/Inputs/loadconfig-arm64.s -o loadconfig-arm64.obj
@@ -162,15 +163,17 @@ RUN:          loadconfig-arm64ec.obj -dll -noentry -merge:test=.testdata -merge:
 
 RUN: llvm-readobj --coff-load-config testcm.dll | FileCheck -check-prefix=CODEMAPCM %s
 CODEMAPCM:      CodeMap [
-CODEMAPCM-NEXT:     0x4008 - 0x4016  X64
+CODEMAPCM-NEXT:     0x4000 - 0x4016  X64
 CODEMAPCM-NEXT: ]
 
 RUN: llvm-objdump -d testcm.dll | FileCheck -check-prefix=DISASMCM %s
 DISASMCM:      Disassembly of section .testdat:
 DISASMCM-EMPTY:
 DISASMCM-NEXT: 0000000180004000 <.testdat>:
-DISASMCM-NEXT: 180004000: 00000001     udf     #0x1
-DISASMCM-NEXT: 180004004: 00000000     udf     #0x0
+DISASMCM-NEXT: 180004000: 01 00                        addl %eax, (%rax)
+DISASMCM-NEXT: 180004002: 00 00                        addb %al, (%rax)
+DISASMCM-NEXT: 180004004: 00 00                        addb %al, (%rax)
+DISASMCM-NEXT: 180004006: 00 00                        addb %al, (%rax)
 DISASMCM-NEXT: 180004008: b8 03 00 00 00               movl    $0x3, %eax
 DISASMCM-NEXT: 18000400d: c3                           retq
 DISASMCM-NEXT: 18000400e: 00 00                        addb    %al, (%rax)
@@ -207,6 +210,14 @@ DISASMMS-NEXT: 0000000180006000 <test2>:
 DISASMMS-NEXT: 180006000: 528000a0     mov     w0, #0x5                // =5
 DISASMMS-NEXT: 180006004: d65f03c0     ret
 
+Test the code map that includes an ARM64EC function padded by its entry-thunk offset.
+
+RUN: lld-link -out:testpad.dll -machine:arm64ec entry-thunk.obj loadconfig-arm64ec.obj -dll -noentry -include:func
+RUN: llvm-readobj --coff-load-config testpad.dll | FileCheck -check-prefix=CODEMAPPAD %s
+CODEMAPPAD:      CodeMap [
+CODEMAPPAD:        0x1000 - 0x1010  ARM64EC
+CODEMAPPAD-NEXT: ]
+
 
 #--- arm64-func-sym.s
     .text
@@ -266,3 +277,22 @@ x86_64_func_sym2:
     .section .empty1, "xr"
     .section .empty2, "xr"
     .section .empty3, "xr"
+
+#--- entry-thunk.s
+    .section .text,"xr",discard,func
+    .globl func
+    .p2align 2, 0x0
+func:
+    mov w0, #1
+    ret
+
+    .section .wowthk$aa,"xr",discard,thunk
+    .globl thunk
+    .p2align 2
+thunk:
+    ret
+
+    .section .hybmp$x,"yi"
+    .symidx func
+    .symidx thunk
+    .word 1  // entry thunk