[llvm] Fix merging of debug_str_offsets with multiple contributions (PR #90461)

Morten larsen via llvm-commits llvm-commits at lists.llvm.org
Mon Apr 29 05:14:31 PDT 2024


https://github.com/molar created https://github.com/llvm/llvm-project/pull/90461

This pull request will change the merging of ``debug_str_offset`` to merge per contribution and correctly copy over each contribution header to the merged section. I have added some test data which is in dwarf5 format as this is where the section contribution header was introduced, as far as i can tell. 



>From 894af4a7dbcc0c769393d07b95b31f03b726d55b Mon Sep 17 00:00:00 2001
From: Morten Larsen <mortenlarsens at gmail.com>
Date: Thu, 18 Apr 2024 21:33:27 +0200
Subject: [PATCH] Fix merging of debug_str_offsets with multiple contributions
 in the section added test of merging contributions in debug_str_offsets

---
 llvm/lib/DWP/DWP.cpp                          |  42 +++++++++++----
 .../llvm-dwp/Inputs/merge_v5/notypes/ab.dwp   | Bin 0 -> 1240 bytes
 .../llvm-dwp/Inputs/merge_v5/notypes/c.dwo    | Bin 0 -> 800 bytes
 llvm/test/tools/llvm-dwp/X86/merge.test       |   5 ++
 llvm/test/tools/llvm-dwp/X86/merge_v5.test    |  48 ++++++++++++++++++
 5 files changed, 86 insertions(+), 9 deletions(-)
 create mode 100644 llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/ab.dwp
 create mode 100644 llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/c.dwo
 create mode 100644 llvm/test/tools/llvm-dwp/X86/merge_v5.test

diff --git a/llvm/lib/DWP/DWP.cpp b/llvm/lib/DWP/DWP.cpp
index 77bd22d1f071c6..fecd184ca68a86 100644
--- a/llvm/lib/DWP/DWP.cpp
+++ b/llvm/lib/DWP/DWP.cpp
@@ -415,6 +415,17 @@ Expected<InfoSectionUnitHeader> parseInfoSectionUnitHeader(StringRef Info) {
   return Header;
 }
 
+static void writeNewOffsetsTo(MCStreamer &Out, DataExtractor &Data,
+                              DenseMap<uint64_t, uint32_t> &OffsetRemapping,
+                              uint64_t &Offset, uint64_t &Size) {
+
+  while (Offset < Size) {
+    auto OldOffset = Data.getU32(&Offset);
+    auto NewOffset = OffsetRemapping[OldOffset];
+    Out.emitIntValue(NewOffset, 4);
+  }
+}
+
 void writeStringsAndOffsets(MCStreamer &Out, DWPStringPool &Strings,
                             MCSection *StrOffsetSection,
                             StringRef CurStrSection,
@@ -439,17 +450,30 @@ void writeStringsAndOffsets(MCStreamer &Out, DWPStringPool &Strings,
 
   Out.switchSection(StrOffsetSection);
 
-  uint64_t HeaderSize = debugStrOffsetsHeaderSize(Data, Version);
   uint64_t Offset = 0;
   uint64_t Size = CurStrOffsetSection.size();
-  // FIXME: This can be caused by bad input and should be handled as such.
-  assert(HeaderSize <= Size && "StrOffsetSection size is less than its header");
-  // Copy the header to the output.
-  Out.emitBytes(Data.getBytes(&Offset, HeaderSize));
-  while (Offset < Size) {
-    auto OldOffset = Data.getU32(&Offset);
-    auto NewOffset = OffsetRemapping[OldOffset];
-    Out.emitIntValue(NewOffset, 4);
+  if (Version > 4) {
+    while (Offset < Size) {
+      uint64_t HeaderSize = debugStrOffsetsHeaderSize(Data, Version);
+      assert(HeaderSize <= Size - Offset &&
+             "StrOffsetSection size is less than its header");
+
+      uint64_t ContributionEnd = 0;
+      uint64_t ContributionSize = 0;
+      uint64_t HeaderLengthOffset = Offset;
+      if (HeaderSize == 8) {
+        ContributionSize = Data.getU32(&HeaderLengthOffset);
+      } else if (HeaderSize == 16) {
+        HeaderLengthOffset += 4; // skip the dwarf64 marker
+        ContributionSize = Data.getU64(&HeaderLengthOffset);
+      }
+      ContributionEnd = ContributionSize + HeaderLengthOffset;
+      Out.emitBytes(Data.getBytes(&Offset, HeaderSize));
+      writeNewOffsetsTo(Out, Data, OffsetRemapping, Offset, ContributionEnd);
+    }
+
+  } else {
+    writeNewOffsetsTo(Out, Data, OffsetRemapping, Offset, Size);
   }
 }
 
diff --git a/llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/ab.dwp b/llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/ab.dwp
new file mode 100644
index 0000000000000000000000000000000000000000..a2388f0e37dff07fa401a80ca9b91b56bbdc145f
GIT binary patch
literal 1240
zcmb_b!EVz)5FM}Ms!~oNmsD_YRaq(uHFlh)X$vG00x1#)IDiB_M0Vn&5!8<CBoqm?
z5&S^8aqS0i=MOk?;lStc#@$Vf51bh3?aaJ+v+EseFP}VnDm0ChY4nKJnPQ24i*?-1
z!Y*w>sZ}(~sv5eru!uyHbgNhGY#o)4%c4f4SE*Ijt#X+Obp5TiwaV>V8{JxD=@tt*
zTj(%I)Hvx?iAsfbpGI*^FN1kBo124oel#{0VUkYb$aLGbYkTHyz20ydO~-3AoCD9@
z_v+!OHFU#)b1-Nf?ztD?`P98o68F&a9LH|A?vig0rc<oL_c8U~xPce=2?dm`St-a$
zxDy%K^>JJH4d4Xufja=##=sOv0In~9kH9Wqkg*9z_Q_Xw at 8R{8Cbmg03BvHOp}5BV
z at iR1PB30TK-+z7nakc+g)3>Q)h-^>o6+}W8UoJ_w+=~MD@%cKy-&O*YsXf%Wif7MS
z^~>3FKYw at L?jf-OzGFUaBkuqv at Nct+VK5)}2lM_U8iwa2b3X`@aFNYcGU+Vo$D>gi
z&e8&%PbbkRzR97V`2pGKhcov7$zEe09z at Yjd0Mc^ja#j1fQqOfkla#n?7K2KlU})E
z{}BqzIYdjPVgF4gpYkMP)vx@{np at _j_od)Lo?L5JY;VmiS0sYBvVWK-5vy|*&3TdI
g+D}RHgUDM^>!T<~otM#bN%BKv<32|As^As>2Mxt`WdHyG

literal 0
HcmV?d00001

diff --git a/llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/c.dwo b/llvm/test/tools/llvm-dwp/Inputs/merge_v5/notypes/c.dwo
new file mode 100644
index 0000000000000000000000000000000000000000..e58a4b0c34d0bbda67317948772c410217a6722e
GIT binary patch
literal 800
zcmb`E%SyvQ6oyZ3RY(`siYRU(G at uqkCedCLYc>i2K@@bMi;`=pN>ZCNii_Gu at sZrP
z at o79sCp83@4xE|ufAgQ2!_52H#W~9`kPilW at T+nP@KJz9h7G8oQ^H)xG at u4p#;9Vf
zV0ajh82vlqB;dd>h{3kr;KrT=@kDZ-tY9D|-Z&bDfkZkAQFLji+0<0+K-D!(ZR_Mv
zZ+d>qC7z?UomO|BOug3;ndTPK)pb=>I;~xB6lXNT*?kE?$4dne(q7>D;dAM7?f#qL
zw?U||S(D5ycFykME~ljvFgz>pz|<I7t_z%;$N;PYwXM~Pu at T6ed?X%=X8m*%z3X7s
z=Kz3j04MiEQA{sVT+f~i`j%~vy(DXck|-YcL*I|QI4a?y90q<k*XWNeJ3aCrhKXlz
zf1G2||GX;g6}~y!spCx9tY|f;XcQsl<@)rIQ>FsUa9IqOX3q;UPxAVF?INc6tZ4nB
XqFscT=XE(w^<VW>3Quw)UCZ at 9CP7eK

literal 0
HcmV?d00001

diff --git a/llvm/test/tools/llvm-dwp/X86/merge.test b/llvm/test/tools/llvm-dwp/X86/merge.test
index 0cf56bd858a04b..25a1315ee63f33 100644
--- a/llvm/test/tools/llvm-dwp/X86/merge.test
+++ b/llvm/test/tools/llvm-dwp/X86/merge.test
@@ -44,3 +44,8 @@ CHECK:    Index  Signature INFO                                        ABBREV
 CHECK-DAG:       [[DWOC]]  [0x00000000[[#COFF]], 0x00000000[[#AOFF]]) [0x0000[[CAOFF]], 0x0000[[AAOFF]]) [0x00000000, 0x00000011) [0x00000000, 0x00000018)
 CHECK-DAG:       [[DWOA]]  [0x00000000[[#AOFF]], 0x00000000[[#BOFF]]) [0x0000[[AAOFF]], 0x0000[[BAOFF]]) [0x00000011, 0x00000022) [0x00000018, 0x00000028)
 CHECK-DAG:       [[DWOB]]  [0x00000000[[#BOFF]], 0x00000000[[#XOFF]]) [0x0000[[BAOFF]], 0x000000c3)      [0x00000022, 0x00000033) [0x00000028, 0x0000003c)
+
+CHECK-LABEL: .debug_str_offsets.dwo contents:
+CHECK: Contribution size = 24, Format = DWARF32, Version = 4
+CHECK: Contribution size = 16, Format = DWARF32, Version = 4
+CHECK: Contribution size = 20, Format = DWARF32, Version = 4
diff --git a/llvm/test/tools/llvm-dwp/X86/merge_v5.test b/llvm/test/tools/llvm-dwp/X86/merge_v5.test
new file mode 100644
index 00000000000000..ea9ef030e5d05b
--- /dev/null
+++ b/llvm/test/tools/llvm-dwp/X86/merge_v5.test
@@ -0,0 +1,48 @@
+RUN: llvm-dwp %p/../Inputs/merge_v5/notypes/c.dwo %p/../Inputs/merge_v5/notypes/ab.dwp -o - | \
+RUN:   llvm-dwarfdump -v - | FileCheck --check-prefix=CHECK %s
+
+DWP from a DWO (c.dwo) and a DWP (ab.dwp, created from a.dwo and b.dwo)
+Make sure the entries for A and B are updated correctly when read/processed from ab.dwp
+a.cpp:
+  struct foo { };
+  foo a;
+
+b.cpp:
+  struct bar { };
+  void b(bar) {
+  }
+
+c.cpp:
+  typedef int baz;
+  baz c() {
+  }
+
+CHECK-LABEL: .debug_abbrev.dwo contents:
+CHECK-LABEL: Abbrev table for offset:
+CHECK: 0x0000[[CAOFF:.*]]
+CHECK-LABEL: Abbrev table for offset:
+CHECK: 0x0000[[AAOFF:.*]]
+CHECK-LABEL: Abbrev table for offset:
+CHECK: 0x0000[[BAOFF:.*]]
+
+CHECK: .debug_info.dwo contents:
+CHECK: 0x[[#%.8x,COFF:]]:
+CHECK-LABEL: Compile Unit: length = {{.*}}, format = DWARF32, version = 0x0005, unit_type = DW_UT_split_compile, abbr_offset =
+CHECK:         0x[[CAOFF]], addr_size = 0x08, DWO_id = 0x[[DWOC:.*]] (next unit at 0x[[#%.8x,BOFF:]])
+CHECK: [[#BOFF]]:
+CHECK-LABEL: Compile Unit: length = {{.*}}, format = DWARF32, version = 0x0005, unit_type = DW_UT_split_compile, abbr_offset =
+CHECK:         0x[[BAOFF]], addr_size = 0x08, DWO_id = 0x[[DWOB:.*]] (next unit at 0x[[#%.8x,AOFF:]])
+CHECK: [[#AOFF]]:
+CHECK-LABEL: Compile Unit: length = {{.*}}, format = DWARF32, version = 0x0005, unit_type = DW_UT_split_compile, abbr_offset =
+CHECK:         0x[[AAOFF]], addr_size = 0x08, DWO_id = 0x[[DWOA:.*]] (next unit at 0x[[#%.8x,XOFF:]])
+
+CHECK-LABEL: .debug_cu_index contents:
+CHECK:    Index Signature          INFO                                     ABBREV                                  STR_OFFSETS 
+CHECK-DAG:       [[DWOC]]  [0x00000000[[#COFF]], 0x00000000[[#BOFF]]) [0x0000[[CAOFF]], 0x0000[[AAOFF]]) [0x00000000, 0x00000024) 
+CHECK-DAG:       [[DWOB]]  [0x00000000[[#BOFF]], 0x00000000[[#AOFF]]) [0x0000[[BAOFF]],  
+CHECK-DAG:       [[DWOA]]  [0x00000000[[#AOFF]], 0x00000000[[#XOFF]]) [0x0000[[AAOFF]], 
+
+CHECK-LABEL: .debug_str_offsets.dwo contents:
+CHECK: Contribution size = 32, Format = DWARF32, Version = 5
+CHECK: Contribution size = 24, Format = DWARF32, Version = 5
+CHECK: Contribution size = 28, Format = DWARF32, Version = 5



More information about the llvm-commits mailing list