[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion #123730

ylzsx · 2025-01-21T11:00:17Z

Complement #123715. When relaxation enable, remove redundant NOPs.

llvmbot · 2025-01-21T11:00:49Z

@llvm/pr-subscribers-backend-loongarch
@llvm/pr-subscribers-lld-elf

@llvm/pr-subscribers-lld

Author: Zhaoxin Yang (ylzsx)

Changes

Complement #123715. When relaxation enable, remove redundant NOPs.

Full diff: https://github.com/llvm/llvm-project/pull/123730.diff

2 Files Affected:

(modified) lld/ELF/Arch/LoongArch.cpp (+29-3)
(modified) lld/test/ELF/loongarch-relax-tlsdesc.s (+16-29)

diff --git a/lld/ELF/Arch/LoongArch.cpp b/lld/ELF/Arch/LoongArch.cpp
index 37614c3e9615d6..5f49b23e8ffb1a 100644
--- a/lld/ELF/Arch/LoongArch.cpp
+++ b/lld/ELF/Arch/LoongArch.cpp
@@ -965,10 +965,16 @@ static bool relax(Ctx &ctx, InputSection &sec) {
     case R_LARCH_GOT_PC_HI20:
     case R_LARCH_TLS_GD_PC_HI20:
     case R_LARCH_TLS_LD_PC_HI20:
-    case R_LARCH_TLS_DESC_PC_HI20:
       // The overflow check for i+2 will be carried out in isPairRelaxable.
-      if (r.expr != RE_LOONGARCH_RELAX_TLS_GD_TO_IE_PAGE_PC &&
-          r.expr != R_RELAX_TLS_GD_TO_LE && isPairRelaxable(relocs, i))
+      if (isPairRelaxable(relocs, i))
+        relaxPCHi20Lo12(ctx, sec, i, loc, r, relocs[i + 2], remove);
+      break;
+    case R_LARCH_TLS_DESC_PC_HI20:
+      if (r.expr == RE_LOONGARCH_RELAX_TLS_GD_TO_IE_PAGE_PC ||
+          r.expr == R_RELAX_TLS_GD_TO_LE) {
+        if (relaxable(relocs, i))
+          remove = 4;
+      } else if (isPairRelaxable(relocs, i))
         relaxPCHi20Lo12(ctx, sec, i, loc, r, relocs[i + 2], remove);
       break;
     case R_LARCH_CALL36:
@@ -986,6 +992,17 @@ static bool relax(Ctx &ctx, InputSection &sec) {
           isUInt<12>(r.sym->getVA(ctx, r.addend)))
         remove = 4;
       break;
+    case R_LARCH_TLS_DESC_PC_LO12:
+      if (relaxable(relocs, i) &&
+          (r.expr == RE_LOONGARCH_RELAX_TLS_GD_TO_IE_PAGE_PC ||
+           r.expr == R_RELAX_TLS_GD_TO_LE))
+        remove = 4;
+      break;
+    case R_LARCH_TLS_DESC_LD:
+      if (relaxable(relocs, i) && r.expr == R_RELAX_TLS_GD_TO_LE &&
+          isUInt<12>(r.sym->getVA(ctx, r.addend)))
+        remove = 4;
+      break;
     }
 
     // For all anchors whose offsets are <= r.offset, they are preceded by
@@ -1214,6 +1231,10 @@ void LoongArch::relocateAlloc(InputSectionBase &sec, uint8_t *buf) const {
                            bits);
         relocateNoSym(loc, rel.type, val);
       } else {
+        isRelax = relaxable(relocs, i);
+        if (isRelax && (rel.type == R_LARCH_TLS_DESC_PC_HI20 ||
+                        rel.type == R_LARCH_TLS_DESC_PC_LO12))
+          continue;
         tlsdescToIe(loc, rel, val);
       }
       continue;
@@ -1230,6 +1251,11 @@ void LoongArch::relocateAlloc(InputSectionBase &sec, uint8_t *buf) const {
                            bits);
         relocateNoSym(loc, rel.type, val);
       } else {
+        isRelax = relaxable(relocs, i);
+        if (isRelax && (rel.type == R_LARCH_TLS_DESC_PC_HI20 ||
+                        rel.type == R_LARCH_TLS_DESC_PC_LO12 ||
+                        (rel.type == R_LARCH_TLS_DESC_LD && isUInt<12>(val))))
+          continue;
         tlsdescToLe(loc, rel, val);
       }
       continue;
diff --git a/lld/test/ELF/loongarch-relax-tlsdesc.s b/lld/test/ELF/loongarch-relax-tlsdesc.s
index 5e538985d1402c..666ca6bd1e7243 100644
--- a/lld/test/ELF/loongarch-relax-tlsdesc.s
+++ b/lld/test/ELF/loongarch-relax-tlsdesc.s
@@ -9,7 +9,6 @@
 # RUN: llvm-readobj -r -x .got a.64.so | FileCheck --check-prefix=GD64-RELA %s
 # RUN: llvm-objdump --no-show-raw-insn -dr -h a.64.so | FileCheck %s --check-prefix=GD64
 
-## FIXME: IE/LE relaxation have not yet been implemented, --relax/--no-relax obtain the same results.
 ## Transition from TLSDESC to IE/LE. Also check --emit-relocs.
 # RUN: ld.lld --relax -e 0 -z now --emit-relocs a.64.o c.64.o -o a.64.le
 # RUN: llvm-readobj -r -x .got a.64.le 2>&1 | FileCheck --check-prefix=LE64-RELA %s
@@ -73,25 +72,21 @@
 # LE64-RELA: could not find section '.got'
 
 ## a@tprel = 0x8
-# LE64:        20158: nop
+# LE64:        20158: ori     $a0, $zero, 8
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 a
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 a
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_LD a
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          ori     $a0, $zero, 8
 # LE64-NEXT:            R_LARCH_TLS_DESC_CALL a
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
 # LE64-NEXT:          add.d   $a1, $a0, $tp
 
 ## b@tprel = 0x7ff
-# LE64:        2016c: nop
+# LE64:        20160: nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 b
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 b
 # LE64-NEXT:          nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_LD b
@@ -101,7 +96,7 @@
 
 ## c@tprel = 0x800
 ## Without R_LARCH_RELAX relocation. No relaxation.
-# LE64:        20180: nop
+# LE64:        20170: nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 c
 # LE64-NEXT:          addi.d  $t0, $zero, 0
 # LE64-NEXT:          nop
@@ -115,13 +110,11 @@
 # LE64-NEXT:          add.d   $a3, $a0, $tp
 
 ## d@tprel = 0x1000
-# LE64:        201a0: nop
+# LE64:        20190: lu12i.w $a0, 1
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 d
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          nop
 # LE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 d
 # LE64-NEXT:            R_LARCH_RELAX *ABS*
-# LE64-NEXT:          lu12i.w $a0, 1
 # LE64-NEXT:            R_LARCH_TLS_DESC_LD d
 # LE64-NEXT:          ori     $a0, $a0, 0
 # LE64-NEXT:            R_LARCH_TLS_DESC_CALL d
@@ -160,35 +153,31 @@
 # LE64-NORELAX-NEXT:          add.d   $a4, $a0, $tp
 
 # IE64-RELA:      .rela.dyn {
-# IE64-RELA-NEXT:   0x30408 R_LARCH_TLS_TPREL64 c 0x0
-# IE64-RELA-NEXT:   0x30410 R_LARCH_TLS_TPREL64 d 0x0
+# IE64-RELA-NEXT:   0x303F0 R_LARCH_TLS_TPREL64 c 0x0
+# IE64-RELA-NEXT:   0x303F8 R_LARCH_TLS_TPREL64 d 0x0
 # IE64-RELA-NEXT: }
 # IE64-RELA:      Hex dump of section '.got':
-# IE64-RELA-NEXT: 0x00030408 00000000 00000000 00000000 00000000 .
+# IE64-RELA-NEXT: 0x000303f0 00000000 00000000 00000000 00000000 .
 
-# IE64:   .got           00000010 0000000000030408
+# IE64:   .got           00000010 00000000000303f0
 
 ## a and b are optimized to use LE. c and d are optimized to IE.
 ## a@tprel = 0x8
-# IE64:        202c8: nop
+# IE64:        202c8: ori     $a0, $zero, 8
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 a
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 a
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_LD a
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          ori     $a0, $zero, 8
 # IE64-NEXT:            R_LARCH_TLS_DESC_CALL a
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
 # IE64-NEXT:          add.d   $a1, $a0, $tp
 
 ## b@tprel = 0x7ff
-# IE64:        202dc: nop
+# IE64:        202d0: nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 b
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 b
 # IE64-NEXT:          nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_LD b
@@ -196,9 +185,9 @@
 # IE64-NEXT:            R_LARCH_TLS_DESC_CALL b
 # IE64-NEXT:          add.d   $a2, $a0, $tp
 
-## &.got[c]-. = 0x30408 - 0x20300: 0x10 pages, page offset 0x408
+## &.got[c]-. = 0x303f0 - 0x202f0: 0x10 pages, page offset 0x3f0
 ## Without R_LARCH_RELAX relocation. No relaxation.
-# IE64:        202f0: nop
+# IE64:        202e0: nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 c
 # IE64-NEXT:          addi.d  $t0, $zero, 0
 # IE64-NEXT:          nop
@@ -207,20 +196,18 @@
 # IE64-NEXT:          pcalau12i $a0, 16
 # IE64-NEXT:            R_LARCH_TLS_DESC_LD c
 # IE64-NEXT:          addi.d  $t0, $t0, 1
-# IE64-NEXT:          ld.d    $a0, $a0, 1032
+# IE64-NEXT:          ld.d    $a0, $a0, 1008
 # IE64-NEXT:            R_LARCH_TLS_DESC_CALL c
 # IE64-NEXT:          add.d   $a3, $a0, $tp
 
-## &.got[d]-. = 0x30408+8 - 0x20318: 0x10 pages, page offset 0x410
-# IE64:        20310: nop
+## &.got[d]-. = 0x303f0+8 - 0x20300: 0x10 pages, page offset 0x3f8
+# IE64:        20300: pcalau12i $a0, 16
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_HI20 d
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          nop
 # IE64-NEXT:            R_LARCH_TLS_DESC_PC_LO12 d
 # IE64-NEXT:            R_LARCH_RELAX *ABS*
-# IE64-NEXT:          pcalau12i $a0, 16
 # IE64-NEXT:            R_LARCH_TLS_DESC_LD d
-# IE64-NEXT:          ld.d    $a0, $a0, 1040
+# IE64-NEXT:          ld.d    $a0, $a0, 1016
 # IE64-NEXT:            R_LARCH_TLS_DESC_CALL d
 # IE64-NEXT:          add.d   $a4, $a0, $tp

SixWeining · 2025-02-19T10:20:44Z

cc @xen0n

MaskRay · 2025-05-14T03:18:22Z

cc @xen0n

Hope that @xen0n or @xry111 could take a look :)

SixWeining · 2025-06-17T03:14:16Z

cc @MQ-mengqing

Complement https://. When relaxation enable, remove redundant NOPs.

xen0n · 2025-07-04T06:54:26Z

I'm on a plane right now and will try to take a look in the evening...

ylzsx · 2025-07-09T03:49:42Z

ping

SixWeining

LGTM. But I think it's better to keep open for a couple of days in case @xen0n having any comments.

…version (llvm#123730) Complement llvm#123715. When relaxation enable, remove redundant NOPs.

…version (llvm#123730) Complement llvm#123715. When relaxation enable, remove redundant NOPs. (cherry picked from commit 2a5cd50)

llvmbot added lld lld:ELF labels Jan 21, 2025

ylzsx added the backend:loongarch label Jan 21, 2025

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-relax branch from ad372af to e024b7c Compare January 21, 2025 12:21

ylzsx mentioned this pull request Jan 21, 2025

[lld][LoongArch] GOT indirection to PC relative optimization #123743

Merged

ylzsx changed the title ~~[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion.~~ [lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion Jan 22, 2025

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-relax branch from e024b7c to 99a1e07 Compare January 22, 2025 06:15

ylzsx requested review from MaskRay, wangleiat and SixWeining January 23, 2025 02:06

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-norelax branch from 0c6ba1d to baee006 Compare April 11, 2025 09:50

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-relax branch from 99a1e07 to f74a55b Compare May 14, 2025 04:05

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-norelax branch from 85165b3 to 243ec8f Compare June 26, 2025 06:47

Base automatically changed from users/ylzsx/r-tlsdesc-to-iele-norelax to main July 2, 2025 08:09

ylzsx added 2 commits July 3, 2025 14:35

Support relaxation during TLSDESC GD/LD to IE/LE conversion.

527e5cd

Complement https://. When relaxation enable, remove redundant NOPs.

Modify loongarch-relax-tlsdesc.s.

fd76622

ylzsx force-pushed the users/ylzsx/r-tlsdesc-to-iele-relax branch from f74a55b to fd76622 Compare July 3, 2025 07:01

SixWeining approved these changes Jul 17, 2025

View reviewed changes

Merge branch 'main' into users/ylzsx/r-tlsdesc-to-iele-relax

6a5ae88

ylzsx merged commit 2a5cd50 into main Jul 23, 2025
9 checks passed

ylzsx deleted the users/ylzsx/r-tlsdesc-to-iele-relax branch July 23, 2025 09:12

mahesh-attarde pushed a commit to mahesh-attarde/llvm-project that referenced this pull request Jul 28, 2025

[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE con…

f02a073

…version (llvm#123730) Complement llvm#123715. When relaxation enable, remove redundant NOPs.

dwblaikie mentioned this pull request Sep 16, 2025

port 5b4819e to release #159209

Open

jhuber6 mentioned this pull request Sep 17, 2025

[LLVM] Update CUDA ELF flags for their new ABI #159451

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion #123730

[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion #123730

Uh oh!

ylzsx commented Jan 21, 2025

Uh oh!

llvmbot commented Jan 21, 2025 •

edited

Loading

Uh oh!

SixWeining commented Feb 19, 2025

Uh oh!

MaskRay commented May 14, 2025

Uh oh!

SixWeining commented Jun 17, 2025

Uh oh!

xen0n commented Jul 4, 2025

Uh oh!

ylzsx commented Jul 9, 2025

Uh oh!

SixWeining left a comment

Uh oh!

Uh oh!

Uh oh!

[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion #123730

[lld][LoongArch] Support relaxation during TLSDESC GD/LD to IE/LE conversion #123730

Uh oh!

Conversation

ylzsx commented Jan 21, 2025

Uh oh!

llvmbot commented Jan 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

SixWeining commented Feb 19, 2025

Uh oh!

MaskRay commented May 14, 2025

Uh oh!

SixWeining commented Jun 17, 2025

Uh oh!

xen0n commented Jul 4, 2025

Uh oh!

ylzsx commented Jul 9, 2025

Uh oh!

SixWeining left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

llvmbot commented Jan 21, 2025 •

edited

Loading