[llvm-objcopy]Preserve data in segments not covered by sections

llvm-objcopy previously knew nothing about data in segments that wasn't
covered by section headers, meaning that it wrote zeroes instead of what
was there. As it is possible for this data to be useful to the loader,
this patch causes llvm-objcopy to start preserving this data. Data in
sections that are explicitly removed continues to be written as zeroes.

This fixes https://bugs.llvm.org/show_bug.cgi?id=41005.

Reviewed by: jakehehrlich, rupprecht

Differential Revision: https://reviews.llvm.org/D59483

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@356919 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/tools/llvm-objcopy/ELF/preserve-segment-contents-ehdr-phdrs.test b/test/tools/llvm-objcopy/ELF/preserve-segment-contents-ehdr-phdrs.test
new file mode 100644 (file)
index 0000000..9dc63d7
--- /dev/null
+++ b/test/tools/llvm-objcopy/ELF/preserve-segment-contents-ehdr-phdrs.test
@@ -0,0 +1,41 @@
+## Show that llvm-objcopy correctly updates the elf header and program header
+## table when they are within a segment.
+
+# RUN: yaml2obj %s -o %t.in
+## Validate that the properties are different before the removal.
+# RUN: llvm-readobj --file-headers --program-headers %t.in | FileCheck %s --check-prefix=BEFORE
+# RUN: llvm-objcopy %t.in %t.out -R .remove_me
+# RUN: llvm-readobj --file-headers --program-headers %t.out | FileCheck %s --check-prefix=AFTER
+
+# BEFORE: SectionHeaderCount: 6
+# BEFORE:      Type: PT_LOAD
+# BEFORE-NEXT: Offset: 0x0
+# BEFORE:      Type: PT_LOAD
+# BEFORE-NEXT: Offset: 0x240
+
+# AFTER:      SectionHeaderCount: 5
+# AFTER:      Type: PT_LOAD
+# AFTER-NEXT: Offset: 0x0
+# AFTER:      Type: PT_LOAD
+# AFTER-NEXT: Offset: 0xB0
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+Sections:
+  - Name: .remove_me
+    Type: SHT_PROGBITS
+    Size: 0x10
+  - Name: .keep_me
+    Type: SHT_PROGBITS
+    Size: 0x10
+ProgramHeaders:
+  - Type:     PT_LOAD
+    Offset:   0
+    FileSize: 176 # sizeof(Elf64_Ehdr) + 2 * sizeof(Elf64_Phdr)
+  - Type:     PT_LOAD
+    Sections:
+      - Section: .keep_me

diff --git a/test/tools/llvm-objcopy/ELF/preserve-segment-contents.test b/test/tools/llvm-objcopy/ELF/preserve-segment-contents.test
new file mode 100644 (file)
index 0000000..4de3ac9
--- /dev/null
+++ b/test/tools/llvm-objcopy/ELF/preserve-segment-contents.test
@@ -0,0 +1,639 @@
+# We want to preserve areas in segments that are not covered by section headers.
+# This test shows that we do this for areas at the start of a segment, between
+# sections in a segment, and after all sections in a segment.
+# To create inputs with arbitrary data in segments, not covered by sections, we
+# use yaml2obj to create segments with sections covering all areas, then remove
+# some sections in those segments, and finally write over the areas of the
+# removed sections using python.
+
+# blob* sections are the sections that will be removed to create unlabelled
+# areas and then overwritten with data to show we preserve the data.
+
+# RUN: yaml2obj %s -o %t.base
+# RUN: llvm-objcopy %t.base %t.stripped --regex -R blob.*
+# Show that the removal leaves the bytes as zeroes, as desired, for all our
+# test cases.
+# RUN: od -t x1 -j 0x2000 -N 24 %t.stripped | FileCheck %s --check-prefix=CHECK1 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x2100 -N 12 %t.stripped | FileCheck %s --check-prefix=CHECK2 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x2200 -N 4  %t.stripped | FileCheck %s --check-prefix=CHECK3 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x2300 -N 12 %t.stripped | FileCheck %s --check-prefix=CHECK4 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x3000 -N 68 %t.stripped | FileCheck %s --check-prefix=CHECK5 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x4000 -N 60 %t.stripped | FileCheck %s --check-prefix=CHECK6 -DPATTERN="00 00 00 00"
+# RUN: od -t x1 -j 0x5000 -N 60 %t.stripped | FileCheck %s --check-prefix=CHECK7 -DPATTERN="00 00 00 00"
+
+# RUN: cp %t.stripped %t.in
+# RUN: echo "with open('%/t.in', 'r+') as input:"                                  > %t.py
+# RUN: echo "  for offset in ["                                                   >> %t.py
+# RUN: echo "   0x2000, 0x2008, 0x200C, 0x2014, 0x2104, 0x2300,"                  >> %t.py
+# RUN: echo "   0x3008, 0x3010, 0x3018, 0x3020, 0x3028, 0x302C, 0x3034, 0x303C,"  >> %t.py
+# RUN: echo "   0x4000, 0x4008, 0x4010, 0x4014, 0x401C, 0x4024, 0x4034,"          >> %t.py
+# RUN: echo "   0x5000, 0x5008, 0x5010, 0x501C, 0x5024, 0x502C, 0x5030, 0x5038]:" >> %t.py
+# RUN: echo "    input.seek(offset)"                                              >> %t.py
+# RUN: echo "    input.write('\xDE\xAD\xBE\xEF')"                                 >> %t.py
+# RUN: %python %t.py
+# RUN: llvm-objcopy %t.in %t.out
+# RUN: od -t x1 -j 0x2000 -N 24 %t.out | FileCheck %s --check-prefix=CHECK1 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x2100 -N 12 %t.out | FileCheck %s --check-prefix=CHECK2 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x2200 -N 4  %t.out | FileCheck %s --check-prefix=CHECK3 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x2300 -N 12 %t.out | FileCheck %s --check-prefix=CHECK4 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x3000 -N 68 %t.out | FileCheck %s --check-prefix=CHECK5 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x4000 -N 60 %t.out | FileCheck %s --check-prefix=CHECK6 -DPATTERN="de ad be ef"
+# RUN: od -t x1 -j 0x5000 -N 60 %t.out | FileCheck %s --check-prefix=CHECK7 -DPATTERN="de ad be ef"
+
+# CHECK1:      [[PATTERN]] 11 22 33 44 [[PATTERN]] [[PATTERN]]
+# CHECK1-NEXT: 55 66 77 88 [[PATTERN]]
+# CHECK2:      99 00 aa bb [[PATTERN]] cc dd ee ff
+# CHECK3:      fe fe fe fe
+# CHECK4:      [[PATTERN]] 00 00 00 00 00 00 00 00
+# CHECK5:      ff ff ee ee dd dd cc cc [[PATTERN]] bb bb aa aa
+# CHECK5-NEXT: [[PATTERN]] 00 00 99 99 [[PATTERN]] 88 88 77 77
+# CHECK5-NEXT: [[PATTERN]] 66 66 55 55 [[PATTERN]] [[PATTERN]]
+# CHECK5-NEXT: 44 44 33 33 [[PATTERN]] 22 22 11 11 [[PATTERN]]
+# CHECK5-NEXT: 00 11 22 33
+# CHECK6:      [[PATTERN]] 44 55 66 77 [[PATTERN]] 88 99 aa bb
+# CHECK6-NEXT: [[PATTERN]] [[PATTERN]] cc dd ee ff [[PATTERN]]
+# CHECK6-NEXT: ff ee dd cc [[PATTERN]] bb aa 99 88 77 66 55 44
+# CHECK6-NEXT: 33 22 11 00 [[PATTERN]] 11 11 11 11
+# CHECK7:      [[PATTERN]] 12 34 56 78 [[PATTERN]] 90 ab cd ef
+# CHECK7-NEXT: [[PATTERN]] fe dc ba 09 87 65 43 21 [[PATTERN]]
+# CHECK7-NEXT: 22 22 22 22 [[PATTERN]] 33 33 33 33 [[PATTERN]]
+# CHECK7-NEXT: [[PATTERN]] 44 44 44 44 [[PATTERN]]
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+Sections:
+  - Name: blob1
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2000
+    AddressAlign: 0x2000
+  - Name: section1
+    Type: SHT_PROGBITS
+    Address: 0x2004
+    Content: '11223344'
+  - Name: blob2
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2008
+  - Name: section2
+    Type: SHT_NOBITS
+    Size: 4
+    Address: 0x200C
+  - Name: blob3
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2010
+  - Name: section3
+    Type: SHT_PROGBITS
+    Content: '55667788'
+    Address: 0x2014
+  - Name: blob4
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2018
+  - Name: section4
+    Type: SHT_PROGBITS
+    Content: '9900aabb'
+    Address: 0x2100
+    AddressAlign: 0x100
+  - Name: blob5
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2104
+  - Name: section5
+    Type: SHT_PROGBITS
+    Address: 0x2108
+    Content: 'ccddeeff'
+  - Name: section6
+    Type: SHT_PROGBITS
+    Content: 'fefefefe'
+    Address: 0x2200
+    AddressAlign: 0x100
+  - Name: blob6
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x2300
+    AddressAlign: 0x100
+  - Name: sectionA
+    Type: SHT_PROGBITS
+    Content: 'ffffeeee'
+    Address: 0x3000
+    AddressAlign: 0x1000
+  - Name: sectionB
+    Type: SHT_PROGBITS
+    Content: 'ddddcccc'
+    Address: 0x3004
+  - Name: blobA
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3008
+  - Name: sectionC
+    Type: SHT_PROGBITS
+    Content: 'bbbbaaaa'
+    Address: 0x300C
+  - Name: blobB
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3010
+  - Name: sectionD
+    Type: SHT_PROGBITS
+    Content: '00009999'
+    Address: 0x3014
+  - Name: blobC
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3018
+  - Name: sectionE
+    Type: SHT_PROGBITS
+    Content: '88887777'
+    Address: 0x301C
+  - Name: blobD
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3020
+  - Name: sectionF
+    Type: SHT_PROGBITS
+    Content: '66665555'
+    Address: 0x3024
+  - Name: blobE
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3028
+  - Name: blobF
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x302C
+  - Name: sectionG
+    Type: SHT_PROGBITS
+    Content: '44443333'
+    Address: 0x3030
+  - Name: blobG
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x3034
+  - Name: sectionH
+    Type: SHT_PROGBITS
+    Content: '22221111'
+    Address: 0x3038
+  - Name: blobH
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x303C
+  - Name: sectionI
+    Type: SHT_PROGBITS
+    Content: '00112233'
+    Address: 0x3040
+  - Name: blobz
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4000
+    AddressAlign: 0x1000
+  - Name: sectionz
+    Type: SHT_PROGBITS
+    Content: '44556677'
+    Address: 0x4004
+  - Name: bloby
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4008
+  - Name: sectiony
+    Type: SHT_PROGBITS
+    Content: '8899aabb'
+    Address: 0x400C
+  - Name: blobx
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4010
+  - Name: blobw
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4014
+  - Name: sectionx
+    Type: SHT_PROGBITS
+    Content: 'ccddeeff'
+    Address: 0x4018
+  - Name: blobv
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x401C
+  - Name: sectionw
+    Type: SHT_PROGBITS
+    Content: 'ffeeddcc'
+    Address: 0x4020
+  - Name: blobu
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4024
+  - Name: sectionv
+    Type: SHT_PROGBITS
+    Content: 'bbaa9988'
+    Address: 0x4028
+  - Name: sectionu
+    Type: SHT_PROGBITS
+    Content: '77665544'
+    Address: 0x402C
+  - Name: sectiont
+    Type: SHT_PROGBITS
+    Content: '33221100'
+    Address: 0x4030
+  - Name: blobt
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x4034
+  - Name: sections
+    Type: SHT_PROGBITS
+    Content: '11111111'
+    Address: 0x4038
+  - Name: bloba
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5000
+    AddressAlign: 0x1000
+  - Name: sectiona
+    Type: SHT_PROGBITS
+    Content: '12345678'
+    Address: 0x5004
+  - Name: blobb
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5008
+  - Name: sectionb
+    Type: SHT_PROGBITS
+    Content: '90abcdef'
+    Address: 0x500C
+  - Name: blobc
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5010
+  - Name: sectionc
+    Type: SHT_PROGBITS
+    Content: 'fedcba09'
+    Address: 0x5014
+  - Name: sectiond
+    Type: SHT_PROGBITS
+    Content: '87654321'
+    Address: 0x5018
+  - Name: blobd
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x501C
+  - Name: sectione
+    Type: SHT_PROGBITS
+    Content: '22222222'
+    Address: 0x5020
+  - Name: blobe
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5024
+  - Name: sectionf
+    Type: SHT_PROGBITS
+    Content: '33333333'
+    Address: 0x5028
+  - Name: blobf
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x502C
+  - Name: blobg
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5030
+  - Name: sectiong
+    Type: SHT_PROGBITS
+    Content: '44444444'
+    Address: 0x5034
+  - Name: blobh
+    Type: SHT_PROGBITS
+    Content: 'abbababa'
+    Address: 0x5038
+ProgramHeaders:
+  # First segment has unlabelled space at start and end.
+  - Type:  0x6ABCDEF0 # Non-specific segment type.
+    VAddr: 0x2000
+    PAddr: 0x2000
+    Align: 0x2000
+    Sections:
+      - Section: blob1
+      - Section: section1
+      - Section: blob2
+      - Section: section2 # nobits
+      - Section: blob3
+      - Section: section3
+      - Section: blob4
+  # Second segment has sections at start and end.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x2100
+    PAddr: 0x2100
+    Align: 0x100
+    Sections:
+      - Section: section4
+      - Section: blob5
+      - Section: section5
+  # Third segment is all covered by a section.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x2200
+    PAddr: 0x2200
+    Align: 0x100
+    Sections:
+      - Section: section6
+  # Fourth segment has no sections (after removing blob headers).
+  - Type:  0x6ABCDEF0
+    VAddr: 0x2300
+    PAddr: 0x2300
+    Align: 0x100
+    Sections:
+      - Section: blob6
+  # Fifth segment is empty.
+  - Type:   0x6ABCDEF0
+    VAddr:  0x2308
+    PAddr:  0x2308
+    Offset: 0x2308
+
+  # The next few segments test behaviour of fully nested segments.
+  # Sixth segment is the "parent" segment.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x3000
+    PAddr: 0x3000
+    Align: 0x1000
+    Sections:
+      - Section: sectionA
+      - Section: sectionB
+      - Section: blobA
+      - Section: sectionC
+      - Section: blobB
+      - Section: sectionD
+      - Section: blobC
+      - Section: sectionE
+      - Section: blobD
+      - Section: sectionF
+      - Section: blobE
+      - Section: blobF
+      - Section: sectionG
+      - Section: blobG
+      - Section: sectionH
+      - Section: blobH
+      - Section: sectionI
+  # Seventh segment is empty and nested.
+  - Type:   0x6ABCDEF0
+    VAddr:  0x3002
+    PAddr:  0x3002
+    Offset: 0x3002
+  # Eighth segment contains only a section and is nested.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x3004
+    PAddr: 0x3004
+    Sections:
+      - Section: sectionB
+  # Ninth segment contains only unlabelled space and is nested.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x3008
+    PAddr: 0x3008
+    Sections:
+      - Section: blobA
+  # Tenth segment contains two sections with space between and is nested.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x300C
+    PAddr: 0x300C
+    Sections:
+      - Section: sectionC
+      - Section: blobB
+      - Section: sectionD
+  # Eleventh segment contains two sections with space between and at ends and is nested.
+  - Type:  0x6ABCDEF0
+    VAddr: 0x3018
+    PAddr: 0x3018
+    Sections:
+      - Section: blobC
+      - Section: sectionE
+      - Section: blobD
+      - Section: sectionF
+      - Section: blobE
+  # Twelfth segment contains one section with space at ends adjacent to space in parent segment.
+  - Type:     0x6ABCDEF0
+    VAddr:    0x302E
+    PAddr:    0x302E
+    Offset:   0x302E
+    FileSize: 8
+    Sections:
+      - Section: sectionG
+  # Thirteenth segment contains overlaps sections at either end in parent segment.
+  - Type:     0x6ABCDEF0
+    VAddr:    0x303A
+    PAddr:    0x303A
+    Offset:   0x303A
+    FileSize: 0x8
+    Sections:
+      - Section: blobH
+
+  # The next batch of segments are segments that only partially overlap other segments.
+
+  # Segment14: |-unlabelled-|-Sec-|
+  # Segment15:           |--|-Sec-|-unlabelled-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4000
+    PAddr: 0x4000
+    Sections:
+      - Section: blobz
+      - Section: sectionz
+  - Type:   0x6ABCDEF0
+    VAddr:  0x4002
+    PAddr:  0x4002
+    Offset: 0x4002
+    Sections:
+      - Section: sectionz
+      - Section: bloby
+
+  # Segment16: |-Sec-|--|
+  # Segment17:    |--|----unlabelled---|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x400C
+    PAddr: 0x400C
+    FileSize: 6
+    Sections:
+      - Section: sectiony
+  - Type:   0x6ABCDEF0
+    VAddr:  0x400E
+    PAddr:  0x400E
+    Offset: 0x400E
+    Sections:
+      - Section: blobx
+
+  # Segment18: |-unlabelled-|-Sec-|
+  # Segment19:              |-Sec-|-unlabelled-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4014
+    PAddr: 0x4014
+    Sections:
+      - Section: blobw
+      - Section: sectionx
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4018
+    PAddr: 0x4018
+    Sections:
+      - Section: sectionx
+      - Section: blobv
+
+  # Segment20: |-Sec-|
+  # Segment21:    |--|-unlabelled-|-Sec-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4020
+    PAddr: 0x4020
+    Sections:
+      - Section: sectionw
+  - Type:   0x6ABCDEF0
+    VAddr:  0x4022
+    PAddr:  0x4022
+    Offset: 0x4022
+    Sections:
+      - Section: blobu
+      - Section: sectionv
+
+  # Segment22: |-Sec-|
+  # Segment23:    |--|-Sec-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x402C
+    PAddr: 0x402C
+    Sections:
+      - Section: sectionu
+  - Type:   0x6ABCDEF0
+    VAddr:  0x402E
+    PAddr:  0x402E
+    Offset: 0x402E
+    Sections:
+      - Section: sectiont
+
+  # Segment24: |-unlabelled-|--|
+  # Segment25:              |--Sec--|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4034
+    PAddr: 0x4034
+    FileSize: 6
+    Sections:
+      - Section: blobt
+  - Type:  0x6ABCDEF0
+    VAddr: 0x4038
+    PAddr: 0x4038
+    Sections:
+      - Section: sections
+
+  # The next batch of segments represent groups of three nested/overlapping segments,
+  # with one parent segment containing two overlapping segments.
+
+  # Segment26: |-unlabelled-|-Sec-|-unlabelled-|
+  # Segment27: |------------|--|
+  # Segment28:              |-Sec-|------------|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5000
+    PAddr: 0x5000
+    Align: 0x1000
+    Sections:
+      - Section: bloba
+      - Section: sectiona
+      - Section: blobb
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5000
+    PAddr: 0x5000
+    FileSize: 6
+    Sections:
+      - Section: bloba
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5004
+    PAddr: 0x5004
+    Sections:
+      - Section: sectiona
+      - Section: blobb
+
+  # Segment29: |-Sec-|-unlabelled-|-Sec-|
+  # Segment30: |-Sec-|--------|
+  # Segment31:          |---------|-Sec-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x500C
+    PAddr: 0x500C
+    Sections:
+      - Section: sectionb
+      - Section: blobc
+      - Section: sectionc
+  - Type:  0x6ABCDEF0
+    VAddr: 0x500C
+    PAddr: 0x500C
+    FileSize: 7
+    Sections:
+      - Section: sectionb
+  - Type:   0x6ABCDEF0
+    VAddr:  0x5011
+    PAddr:  0x5011
+    Offset: 0x5011
+    Sections:
+      - Section: sectionc
+
+  # Segment32: |-Sec-|-unlabelled-|-Sec-|
+  # Segment33: |-Sec-|------------|
+  # Segment34:       |------------|-Sec-|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5018
+    PAddr: 0x5018
+    Sections:
+      - Section: sectiond
+      - Section: blobd
+      - Section: sectione
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5018
+    PAddr: 0x5018
+    Sections:
+      - Section: sectiond
+      - Section: blobd
+  - Type:  0x6ABCDEF0
+    VAddr: 0x501C
+    PAddr: 0x501C
+    Sections:
+      - Section: blobd
+      - Section: sectione
+
+  # Segment35: |-unlabelled-|-Sec-|-unlabelled-|
+  # Segment36: |------------|-Sec-|
+  # Segment37:              |-Sec-|------------|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5024
+    PAddr: 0x5024
+    Sections:
+      - Section: blobe
+      - Section: sectionf
+      - Section: blobf
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5024
+    PAddr: 0x5024
+    Sections:
+      - Section: blobe
+      - Section: sectionf
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5028
+    PAddr: 0x5028
+    Sections:
+      - Section: sectionf
+      - Section: blobf
+
+  # Segment38: |-unlabelled-|-Sec-|-unlabelled-|
+  # Segment39: |------------|---|
+  # Segment40:                |---|------------|
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5030
+    PAddr: 0x5030
+    Sections:
+      - Section: blobg
+      - Section: sectiong
+      - Section: blobh
+  - Type:  0x6ABCDEF0
+    VAddr: 0x5030
+    PAddr: 0x5030
+    FileSize: 7
+    Sections:
+      - Section: blobg
+  - Type:   0x6ABCDEF0
+    VAddr:  0x5035
+    PAddr:  0x5035
+    Offset: 0x5035
+    Sections:
+      - Section: blobh

diff --git a/tools/llvm-objcopy/ELF/Object.cpp b/tools/llvm-objcopy/ELF/Object.cpp
index 4639d9053943ee797ceaefebeedb891430d4ed28..7cceb70ca63bbc58588b417947c0af29936d779c 100644 (file)
--- a/tools/llvm-objcopy/ELF/Object.cpp
+++ b/tools/llvm-objcopy/ELF/Object.cpp
@@ -906,7 +906,9 @@ template <class ELFT> void ELFBuilder<ELFT>::setParentSegment(Segment &Child) {
 template <class ELFT> void ELFBuilder<ELFT>::readProgramHeaders() {
   uint32_t Index = 0;
   for (const auto &Phdr : unwrapOrError(ElfFile.program_headers())) {
-    Segment &Seg = Obj.addSegment();
+    ArrayRef<uint8_t> Data{ElfFile.base() + Phdr.p_offset,
+                           (size_t)Phdr.p_filesz};
+    Segment &Seg = Obj.addSegment(Data);
     Seg.Type = Phdr.p_type;
     Seg.Flags = Phdr.p_flags;
     Seg.OriginalOffset = Phdr.p_offset;
@@ -1350,7 +1352,31 @@ template <class ELFT> void ELFWriter<ELFT>::writeShdrs() {
 
 template <class ELFT> void ELFWriter<ELFT>::writeSectionData() {
   for (auto &Sec : Obj.sections())
-    Sec.accept(*SecWriter);
+    // Segments are responsible for writing their contents, so only write the
+    // section data if the section is not in a segment. Note that this renders
+    // sections in segments effectively immutable.
+    if (Sec.ParentSegment == nullptr)
+      Sec.accept(*SecWriter);
+}
+
+template <class ELFT> void ELFWriter<ELFT>::writeSegmentData() {
+  for (Segment &Seg : Obj.segments()) {
+    uint8_t *B = Buf.getBufferStart() + Seg.Offset;
+    assert(Seg.FileSize == Seg.getContents().size() &&
+           "Segment size must match contents size");
+    std::memcpy(B, Seg.getContents().data(), Seg.FileSize);
+  }
+
+  // Iterate over removed sections and overwrite their old data with zeroes.
+  for (auto &Sec : Obj.removedSections()) {
+    Segment *Parent = Sec.ParentSegment;
+    if (Parent == nullptr || Sec.Type == SHT_NOBITS || Sec.Size == 0)
+      continue;
+    uint64_t Offset =
+        Sec.OriginalOffset - Parent->OriginalOffset + Parent->Offset;
+    uint8_t *B = Buf.getBufferStart();
+    std::memset(B + Offset, 0, Sec.Size);
+  }
 }
 
 Error Object::removeSections(
@@ -1396,7 +1422,10 @@ Error Object::removeSections(
       return E;
   }
 
-  // Now finally get rid of them all togethor.
+  // Transfer removed sections into the Object RemovedSections container for use
+  // later.
+  std::move(Iter, Sections.end(), std::back_inserter(RemovedSections));
+  // Now finally get rid of them all together.
   Sections.erase(Iter, std::end(Sections));
   return Error::success();
 }
@@ -1542,6 +1571,9 @@ template <class ELFT> size_t ELFWriter<ELFT>::totalSize() const {
 }
 
 template <class ELFT> Error ELFWriter<ELFT>::write() {
+  // Segment data must be written first, so that the ELF header and program
+  // header tables can overwrite it, if covered by a segment.
+  writeSegmentData();
   writeEhdr();
   writePhdrs();
   writeSectionData();

diff --git a/tools/llvm-objcopy/ELF/Object.h b/tools/llvm-objcopy/ELF/Object.h
index e892d066a6cd19e7b44ea5ff63ba10432ea58b5c..26d6a122c4681caef29b094a246579612144a74f 100644 (file)
--- a/tools/llvm-objcopy/ELF/Object.h
+++ b/tools/llvm-objcopy/ELF/Object.h
@@ -215,6 +215,7 @@ private:
   void writePhdrs();
   void writeShdrs();
   void writeSectionData();
+  void writeSegmentData();
 
   void assignOffsets();
 
@@ -312,6 +313,10 @@ public:
   uint32_t Index;
   uint64_t OriginalOffset;
   Segment *ParentSegment = nullptr;
+  ArrayRef<uint8_t> Contents;
+
+  explicit Segment(ArrayRef<uint8_t> Data) : Contents(Data) {}
+  Segment() {}
 
   const SectionBase *firstSection() const {
     if (!Sections.empty())
@@ -321,6 +326,8 @@ public:
 
   void removeSection(const SectionBase *Sec) { Sections.erase(Sec); }
   void addSection(const SectionBase *Sec) { Sections.insert(Sec); }
+
+  ArrayRef<uint8_t> getContents() const { return Contents; }
 };
 
 class Section : public SectionBase {
@@ -773,6 +780,7 @@ private:
 
   std::vector<SecPtr> Sections;
   std::vector<SegPtr> Segments;
+  std::vector<SecPtr> RemovedSections;
 
 public:
   template <class T>
@@ -815,6 +823,8 @@ public:
         find_if(Sections, [&](const SecPtr &Sec) { return Sec->Name == Name; });
     return SecIt == Sections.end() ? nullptr : SecIt->get();
   }
+  SectionTableRef removedSections() { return SectionTableRef(RemovedSections); }
+
   Range<Segment> segments() { return make_pointee_range(Segments); }
   ConstRange<Segment> segments() const { return make_pointee_range(Segments); }
 
@@ -827,8 +837,8 @@ public:
     Ptr->Index = Sections.size();
     return *Ptr;
   }
-  Segment &addSegment() {
-    Segments.emplace_back(llvm::make_unique<Segment>());
+  Segment &addSegment(ArrayRef<uint8_t> Data) {
+    Segments.emplace_back(llvm::make_unique<Segment>(Data));
     return *Segments.back();
   }
 };