[obj2yaml] - Fix the issue with dumping empty sections when dumping program headers.

Imagine we have:

```
ProgramHeaders:
  - Type:  PT_LOAD
    Flags: [ PF_W, PF_R ]
    Sections:
      - Section: .bar
    VAddr: 0x2000
Sections:
  - Name:    .foo
    Type:    SHT_PROGBITS
    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
    Address: 0x1000
  - Name:    .bar
    Type:    SHT_PROGBITS
    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
    Address: 0x2000
```

Both `.foo` and `.bar` share the same starting file offset,
but `VA(.foo)` < `VA(PT_LOAD)`, we should not include it into segment.

This patch fixes the issue.

Differential revision: https://reviews.llvm.org/D77652

3 files changed, 127 insertions, 5 deletions

diff --git a/llvm/test/Object/obj2yaml.test b/llvm/test/Object/obj2yaml.test
index a4398fb..a1b0d1e 100644
--- a/llvm/test/Object/obj2yaml.test
+++ b/llvm/test/Object/obj2yaml.test
@@ -664,7 +664,6 @@ Symbols:
 # ELF-AVR-NEXT:    Flags: [ PF_X, PF_R ]
 # ELF-AVR-NEXT:    Sections:
 # ELF-AVR-NEXT:     - Section: .text
-# ELF-AVR-NEXT:     - Section: .data
 # ELF-AVR-NEXT:    Align: 0x0000000000000002
 # ELF-AVR-NEXT:  - Type:  PT_LOAD
 # ELF-AVR-NEXT:    Flags: [ PF_W, PF_R ]
diff --git a/llvm/test/tools/obj2yaml/program-headers.yaml b/llvm/test/tools/obj2yaml/program-headers.yaml
index 5d56487..740d349 100644
--- a/llvm/test/tools/obj2yaml/program-headers.yaml
+++ b/llvm/test/tools/obj2yaml/program-headers.yaml
@@ -574,3 +574,118 @@ Sections:
     Flags:    [ SHF_ALLOC ]
     Size:     0x1
     ShOffset: 0x0
+
+## Check how we dump segments which contain empty sections.
+# RUN: yaml2obj --docnum=7 %s -o %t7
+
+## Show the layout of the object before we dump it using obj2yaml.
+## Notes: 1) '.empty.foo', '.empty.bar1' and '.bar' have the same file offset, but '.empty.foo'
+##           has a VA that is outside of the segment, hence we should not include it in it.
+##        2) '.bar1' ends at 0x79, which is the starting file offset of both '.empty.bar2'
+##           and '.empty.zed'. We should only include '.empty.bar2', because the VA of the
+##           '.empty.zed' section is outside the segment's virtual space.
+# RUN: llvm-readelf -sections %t7 | FileCheck %s --check-prefix=ZERO-SIZE-MAPPING
+
+# ZERO-SIZE-MAPPING:      Section Headers:
+# ZERO-SIZE-MAPPING-NEXT:   [Nr] Name        Type     Address          Off    Size
+# ZERO-SIZE-MAPPING:        [ 1] .empty.foo  PROGBITS 0000000000001000 000078 000000
+# ZERO-SIZE-MAPPING-NEXT:   [ 2] .empty.bar1 PROGBITS 0000000000002000 000078 000000
+# ZERO-SIZE-MAPPING-NEXT:   [ 3] .bar        PROGBITS 0000000000002000 000078 000001
+# ZERO-SIZE-MAPPING-NEXT:   [ 4] .empty.bar2 PROGBITS 0000000000002001 000079 000000
+# ZERO-SIZE-MAPPING-NEXT:   [ 5] .empty.zed  PROGBITS 0000000000003000 000079 000000
+
+# RUN: obj2yaml %t7 | FileCheck %s --check-prefix=ZERO-SIZE
+
+# ZERO-SIZE:      ProgramHeaders:
+# ZERO-SIZE-NEXT:   - Type:  PT_LOAD
+# ZERO-SIZE-NEXT:     Flags: [ PF_W, PF_R ]
+# ZERO-SIZE-NEXT:     Sections:
+# ZERO-SIZE-NEXT:       - Section: .empty.bar1
+# ZERO-SIZE-NEXT:       - Section: .bar
+# ZERO-SIZE-NEXT:       - Section: .empty.bar2
+# ZERO-SIZE-NEXT:     VAddr: 0x0000000000002000
+# ZERO-SIZE-NEXT: Sections:
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+ProgramHeaders:
+  - Type:  PT_LOAD
+    Flags: [ PF_W, PF_R ]
+    Sections:
+      - Section: .bar
+    VAddr: 0x2000
+Sections:
+  - Name:    .empty.foo
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0x1000
+  - Name:    .empty.bar1
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0x2000
+  - Name:    .bar
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_WRITE, SHF_ALLOC ]
+    Address: 0x2000
+    Size:    0x1
+  - Name:    .empty.bar2
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0x2001
+  - Name:    .empty.zed
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0x3000
+
+## Check how we dump a segment when we have sections that are outside of the virtual
+## address space of a segment, but inside its file space. We do not include such sections
+## in a segment when they are at the edges of a segment, because this is a normal case and
+## it may mean they belong to a different segment.
+# RUN: yaml2obj --docnum=8 %s -o %t8
+# RUN: obj2yaml %t8 | FileCheck %s --check-prefix=BROKEN-VA
+
+# BROKEN-VA:      ProgramHeaders:
+# BROKEN-VA-NEXT:  - Type:  PT_LOAD
+# BROKEN-VA-NEXT:    Flags: [ PF_W, PF_R ]
+# BROKEN-VA-NEXT:    Sections:
+# BROKEN-VA-NEXT:      - Section: .empty_middle
+# BROKEN-VA-NEXT:    VAddr: 0x0000000000001000
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+ProgramHeaders:
+  - Type:  PT_LOAD
+    Flags: [ PF_W, PF_R ]
+    VAddr: 0x1000
+    Sections:
+      - Section: .empty_begin
+      - Section: .empty_middle
+      - Section: .empty_end
+Sections:
+  - Name:    .empty_begin
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0xFEFEFEFE
+  - Type:    Fill
+    Pattern: "00"
+    Size:    1
+    Name:    begin
+  - Name:    .empty_middle
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0xFEFEFEFE
+  - Type:    Fill
+    Pattern: "00"
+    Size:    1
+  - Name:    .empty_end
+    Type:    SHT_PROGBITS
+    Flags:   [ SHF_ALLOC, SHF_EXECINSTR ]
+    Address: 0xFEFEFEFE
diff --git a/llvm/tools/obj2yaml/elf2yaml.cpp b/llvm/tools/obj2yaml/elf2yaml.cpp
index c145142..fe3f36f 100644
--- a/llvm/tools/obj2yaml/elf2yaml.cpp
+++ b/llvm/tools/obj2yaml/elf2yaml.cpp
@@ -305,17 +305,25 @@ static bool isInSegment(const ELFYAML::Section &Sec,
       SHdr.sh_offset >= Phdr.p_offset &&
       (SHdr.sh_offset + SHdr.sh_size <= Phdr.p_offset + Phdr.p_filesz);
 
-  if (FileOffsetsMatch)
+  bool VirtualAddressesMatch = SHdr.sh_addr >= Phdr.p_vaddr &&
+                               SHdr.sh_addr <= Phdr.p_vaddr + Phdr.p_memsz;
+
+  if (FileOffsetsMatch) {
+    // An empty section on the edges of a program header can be outside of the
+    // virtual address space of the segment. This means it is not included in
+    // the segment and we should ignore it.
+    if (SHdr.sh_size == 0 && (SHdr.sh_offset == Phdr.p_offset ||
+                              SHdr.sh_offset == Phdr.p_offset + Phdr.p_filesz))
+      return VirtualAddressesMatch;
     return true;
+  }
 
   // SHT_NOBITS sections usually occupy no physical space in a file. Such
   // sections belong to a segment when they reside in the segment's virtual
   // address space.
   if (Sec.Type != ELF::SHT_NOBITS)
     return false;
-
-  return SHdr.sh_addr >= Phdr.p_vaddr &&
-         SHdr.sh_addr <= Phdr.p_vaddr + Phdr.p_memsz;
+  return VirtualAddressesMatch;
 }
 
 template <class ELFT>