When GNU tools create a weak alias, they produce a strong symbol
named .weak.<weaksymbol>.<relatedstrongsymbol>.
GNU ld allows many such weak alternatives for the same weak symbol, and
the linker picks the first one encountered.
This can't be reproduced by assembling from .s files, since llvm-mc
produces symbols named .weak.<weaksymbol>.default in these cases.
Differential Revision: https://reviews.llvm.org/D52601
llvm-svn: 343704
When GCC produces a jump table as part of a comdat function, the
jump table itself is produced as plain non-comdat rdata section. When
linked with ld.bfd, all of those rdata sections are kept, with
relocations unchanged in the sections that refer to discarded comdat
sections.
This has been observed with at least GCC 5.x and 7.x.
Differential Revision: https://reviews.llvm.org/D52600
llvm-svn: 343422
Don't assume that the IAT chunk will be a DefinedImportData, it can
just as well be a DefinedRegular for gnu import libraries.
Differential Revision: https://reviews.llvm.org/D52381
llvm-svn: 343069
This is a feature that MS link.exe lacks; it currently errors out on
such relocations, just like lld did before.
This allows linking clang.exe for ARM - practically, any image over
16 MB will likely run into the issue.
Differential Revision: https://reviews.llvm.org/D52156
llvm-svn: 342962
GNU binutils import libraries aren't the same kind of short import
libraries as link.exe and LLD produce, but are a plain static library
containing .idata section chunks. MSVC link.exe can successfully link
to them.
In order for imports from GNU import libraries to mix properly with the
normal import chunks, the chunks from the existing mechanism needs to
be added into named sections like .idata$2.
These GNU import libraries consist of one header object, a number of
object files, one for each imported function/variable, and one trailer.
Within the import libraries, the object files are ordered alphabetically
in this order. The chunks stemming from these libraries have to be
grouped by what library they originate from and sorted, to make sure
the section chunks for headers and trailers for the lists are ordered
as intended. This is done on all sections named .idata$*, before adding
the synthesized chunks to them.
Differential Revision: https://reviews.llvm.org/D38513
llvm-svn: 342777
- Log the reason for a PDB or precompiled-OBJ load failure
- Properly handle out-of-date PDB or precompiled-OBJ signature by displaying a corresponding error
- Slightly change behavior on PDB failure: any subsequent load attempt from another OBJ would result in the same error message being logged
- Slightly change behavior on PDB failure: retry with filename only if previous error was ENOENT ("no such file or directory")
- Tests: a. for native PDB errors; b. cover all the cases above
Differential Revision: https://reviews.llvm.org/D51559
llvm-svn: 341825
MinGW configurations don't use associative comdats, as GNU ld doesn't
support that. Instead they produce normal comdats named .text$sym,
.xdata$sym and .pdata$sym.
GNU ld doesn't discard any comdats starting with .xdata or .pdata,
even if --gc-sections is used (while it does discard other unreferenced
comdats), regardless of what symbol name is used after the $ separator.
For LLD, treat any such comdat as implicitly associative to the base
symbol. This requires maintaining a map from symbol name to section
number, but that is only maintained when the MinGW flag has been
enabled.
Differential Revision: https://reviews.llvm.org/D49700
llvm-svn: 339058
It's not an error if a common symbol (uninitialized data, with alignment
specified via the aligncomm directive) is replaced with a regular
one with initialized data (with alignment specified via the section
chunk).
Differential Revision: https://reviews.llvm.org/D50268
llvm-svn: 339049
This patch changes relative path for source files in obj files to
absolute path in PDB when linking with added flag.
I will make obj file generated by clang-cl independent from build
directory for chromium build. But I don't want to confuse visual studio
debugger or require additional configuration. To attain this goal, I
added flag to convert relative source file path in obj to absolute path
when emitting PDB.
By removing absolute path from obj files, we can share build cache
between chromium developers even when they are doing debug build.
That will make build time faster.
More context:
https://bugs.chromium.org/p/chromium/issues/detail?id=712796https://groups.google.com/a/chromium.org/forum/#!topic/chromium-dev/5HXSVX-7fPc
llvm-svn: 337439
Future symbol insertions can potentially change the type of these
symbols - keep pointers to the base class to reflect this, and
use dynamic casts to inspect them before using as the subclass
type.
This fixes crashes that were possible before, by touching these
symbols that now are populated as e.g. a DefinedRegular, via
the old pointers with DefinedImportThunk type.
Differential Revision: https://reviews.llvm.org/D48953
llvm-svn: 336652
The reference implementation uses a case-insensitive string
comparison for strings of equal length. This will cause the
string "tEo" to compare less than "VUo". However we were using
a case sensitive comparison, which would generate the opposite
outcome. Switch to a case insensitive comparison. Also, when
one of the strings contains non-ascii characters, fallback to
a straight memcmp.
The only way to really test this is with a DIA test. Before this
patch, the test will fail (but succeed if link.exe is used instead
of lld-link). After the patch, it succeeds even with lld-link.
llvm-svn: 336464
It seems like the debugger first computes a symbol's bucket,
and then does a binary search of entries in the bucket using the
symbol's name in order to find it. If the bucket entries are not
in sorted order, this obviously won't work. After this patch a
couple of simple test cases show that we generate an exactly
identical GSI hash stream, which is very nice.
llvm-svn: 336405
Summary:
Control flow guard works best when targets it checks are 16-byte aligned.
Microsoft's link.exe helps ensure this by aligning code from sections
that are referenced from the gfids table to 16 bytes when linking with
-guard:cf, even if the original section specifies a smaller alignment.
This change implements that behavior in lld-link.
See https://crbug.com/857012 for more details.
Reviewers: ruiu, hans, thakis, zturner
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D48690
llvm-svn: 335864
Previously we emitted 20-byte SHA1 hashes. This is overkill
for identifying debug info records, and has the negative side
effect of making object files bigger and links slower. By
using only the last 8 bytes of a SHA1, we get smaller object
files and ~10% faster links.
This modifies the format of the .debug$H section by adding a new
value for the hash algorithm field, so that the linker will still
work when its object files have an old format.
Differential Revision: https://reviews.llvm.org/D46855
llvm-svn: 332669
The prefix includes type kind, which is important to preserve. Two
different type leafs can easily have the same interior record contents
as another type.
We ran into this issue in PR37492 where a bitfield type record collided
with a const modifier record. Their contents were bitwise identical, but
their kinds were different.
llvm-svn: 332664
Now only IMAGE_REL_ARM64_ABSOLUTE and IMAGE_REL_ARM64_TOKEN
are unhandled.
Also add range checks for the existing BRANCH26 relocation.
Differential Revision: https://reviews.llvm.org/D46354
llvm-svn: 331505
This was reverted several times due to what ultimately turned out
to be incompatibilities in our serialized hash table format.
Several changes went in prior to this to fix those issues since
they were more fundamental and independent of supporting injected
sources, so now that those are fixed this change should hopefully
pass.
llvm-svn: 328363
This is still failing on a different bot this time due to some
issue related to hashing absolute paths. Reverting until I can
figure it out.
llvm-svn: 328014
The issue causing this to fail in certain configurations
should be fixed.
It was due to the fact that DIA apparently expects there to be
a null string at ID 1 in the string table. I'm not sure why this
is important but it seems to make a difference, so set it.
llvm-svn: 328002
Natvis is a debug language supported by Visual Studio for
specifying custom visualizers. The /NATVIS option is an
undocumented link.exe flag which will take a .natvis file
and "inject" it into the PDB. This way, you can ship the
debug visualizers for a program along with the PDB, which
is very useful for postmortem debugging.
This is implemented by adding a new "named stream" to the
PDB with a special name of /src/files/<natvis file name>
and simply copying the contents of the xml into this file.
Additionally, we need to emit a single stream named
/src/headerblock which contains a hash table of embedded
files to records describing them.
This patch adds this functionality, including the /NATVIS
option to lld-link.
Differential Revision: https://reviews.llvm.org/D44328
llvm-svn: 327895
This tests that LLVM emits the relocations that /guard:cf needs to
identify address taken.
This was PR36624, which was fixed in r327557.
llvm-svn: 327559
With the /order option, you can give an order file. An order file
contains symbol names, one per line, and the linker places comdat
sections in that given order. The option is used often to optimize
an output binary for (in particular, startup) speed by improving
locality.
Differential Revision: https://reviews.llvm.org/D42598
llvm-svn: 323579
These tests started failing because we now properly convert
DefRange records to and from Yaml, but there were some old yaml
files that had incorrect record definitions generated by the
old buggy obj2yaml. Rather than try to re-generate the yaml files,
it's easier to just remove the records, and they weren't necessary
for the proper execution of the test anyway.
llvm-svn: 322040
The problem was that our Obj -> Yaml dumper had not been taught
to handle certain types of records. This meant that when I
generated the test input files, the records were still there but
none of its fields were filled out. So when it did the
Yaml -> Obj conversion as part of the test, it generated records
with garbage in them.
The patch here fixes the Obj <-> Yaml converter, and additionally
updates the test file with fresh Yaml generated by the fixed
converter.
llvm-svn: 322029
This is not a record type that clang currently generates,
but it is a record that is encountered in object files generated
by cl. This record is unusual in that it refers directly to
the string table instead of indirectly to the string table via
the FileChecksums table. Because of this, it was previously
overlooked and we weren't remapping the string indices at all.
This would lead to crashes in MSVC when trying to display a
variable whose debug info involved an S_FILESTATIC.
Original bug report by Alexander Ganea
Differential Revision: https://reviews.llvm.org/D41718
llvm-svn: 321883
Locally imported symbols are a very surprising linker feature. link.exe
warns for them, and we should warn too.
Differential Revision: https://reviews.llvm.org/D41269
llvm-svn: 320792
This adds the /DEBUG:GHASH option to LLD which will look for
the existence of .debug$H sections in linker inputs and use them
to accelerate type merging. The clang-cl side has already been
added, so this completes the work necessary to begin experimenting
with this feature.
Differential Revision: https://reviews.llvm.org/D40980
llvm-svn: 320719
This is similar to what was added in SVN r277838 for 24 bit
branch instructions.
Differential Revision: https://reviews.llvm.org/D41163
llvm-svn: 320677
Summary:
We previously assumed that all SafeSEH handlers are
DefinedRegular symbols. This is not the case for handlers defined in
DLLs. As a result, we were failing to emit entries in the SafeSEH
table for those handlers. This change fixes that.
Fixes PR35324.
Reviewers: rnk, ruiu
Reviewed By: rnk
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D40102
llvm-svn: 318364
If a symbol is locally defined and is DLL imported in another
translation unit, and the object with the locally defined version is
loaded prior to the imported version, then the linker will fail to
resolve the definition of the thunk and return the locally defined
symbol. This will then be attempted to be cast to an import thunk,
which will clearly fail.
Only return the thunk if the symbol is inserted or a thunk is created.
Otherwise, report a duplication error.
llvm-svn: 312386
This reverts commit r312171 because it is pointed out that that's not a
correct fix (see https://bugs.llvm.org/show_bug.cgi?id=32674#c14) and
also because it broke buildbots.
llvm-svn: 312174
MSVC link.exe supports nested static libraries. That is, an .a file can
contain other .a file as its member. It is reported that MySQL actually
depends on this feature.
Fixes https://bugs.llvm.org/show_bug.cgi?id=32674
llvm-svn: 312171
Previously we were writing an empty globals stream. Windows
tools interpret this as "private symbols are not present in
this PDB", even when they are, so we need to fix this. Regardless,
without it we don't have information about global variables, so
we need to fix it anyway. This patch does that.
With this patch, the "lm" command in WinDbg correctly reports
that we have private symbols available, but the "dv" command
still refuses to display local variables.
Differential Revision: https://reviews.llvm.org/D36535
llvm-svn: 310743
This fixes cases on ARM64 when importing from more than one DLL,
in case the imports from the first DLL ended up unaligned.
When fixing up a IMAGE_REL_ARM64_PAGEOFFSET_12L, which shifts the
offset by the load/store size, check that the shift doesn't discard
any bits. (This would also detect if the import address chunks were
unaligned.)
Differential revision: https://reviews.llvm.org/D35640
llvm-svn: 308585
Improve the link conformance for the import name embedded into the
import library. This requires the associated change to the LLVM portion
for the DEF file parser. The import file generation embeds a different
name based on whether the driver is invoked as "link" or "lib".
Furthermore, the LIBRARY keyword in the DEF file influences the import
name. The behaviour can be summarised according to the following table:
| LIBRARY w/ ext | LIBRARY w/o ext | no LIBRARY
-----+----------------+---------------------+------------------
LINK | {value} | {value}.{.dll/.exe} | {output name}
LIB | {value} | {value}.dll | {output name}.dll
llvm-svn: 308407
Summary:
Object files compiled with /Zi emit type information into a type server
PDB. The .debug$S section will contain a single TypeServer2Record with
the absolute path and GUID of the type server. LLD needs to load the
type server PDB and merge all types and items it finds in it into the
destination PDB.
Depends on D35495
Reviewers: ruiu, inglorion
Subscribers: zturner, llvm-commits
Differential Revision: https://reviews.llvm.org/D35504
llvm-svn: 308235
This is enough to link a working hello world executable, with
a call to an imported function, a string constant passed to
the imported function, and loads from a global variable.
Differential Revision: https://reviews.llvm.org/D34964
llvm-svn: 307629
A couple of things were different about our generated PDBs.
1) We were outputting the wrong Version on the PDB Stream.
The version we were setting was newer than what MSVC is setting.
It's not clear what the implications are, but we change LLD
to use PdbImplVC70, as MSVC does.
2) For the optional debug stream indices in the DBI Stream, we
were outputting 0 to mean "the stream is not present". MSVC
outputs uint16_t(-1), which is the "correct" way to specify
that a stream is not present. So we fix that as well.
3) We were setting the PDB Stream signature to 0. This is supposed
to be the result of calling time(nullptr). Although this leads
to non-deterministic builds, a better way to solve that is by
having a command line option explicitly for generating a
reproducible build, and have the default behavior of lld-link
match the default behavior of link.
To test this, I'm making use of the new and improved `pdb diff`
sub command. To make it suitable for writing tests against, I had
to modify the diff subcommand slightly to print less verbose output.
Previously it would always print | <column> | <value1> | <value2> |
which is quite verbose, and the values are fragile. All we really
want to know is "did we produce the same value as link?" So I added
command line options to print a single character representing the
result status (different, identical, equivalent), and another to
hide the value display. Note that just inspecting the diff output
used to write the test, you can see some things that are obviously
wrong. That is just reflective of the fact that this is the state
of affairs today, not that we're asserting that this is "correct".
We can use this as a starting point to discover differences, fix
them, and update the test.
Differential Revision: https://reviews.llvm.org/D35086
llvm-svn: 307422
Summary:
There are a variety of records that open scopes: function scopes, block
scopes, and inlined call site scopes. These symbol records contain
Parent and End fields with the offsets of other symbol records. The End
field contains the offset of the matching S_END or S_INLINESITE_END
record. The Parent field contains the offset of the parent record, or 0
if this is a top-level scope (i.e. a function).
With this change, `llvm-pdbutil pretty -all` no longer crashes on PDBs
produced by LLD. I haven't tried a real debugger yet.
Reviewers: zturner, ruiu
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34898
llvm-svn: 307278
Summary:
In order to do this without switching on the symbol kind multiple times,
I created Defined::getChunkAndOffset and use that instead of
SymbolBody::getRVA in the inner relocation loop.
Now we get the symbol's chunk before switching over relocation types, so
we can test if it has been discarded outside the inner relocation type
switch. This also simplifies application of section relative
relocations. Previously we would switch on symbol kind to compute the
RVA, then the relocation type, and then the symbol kind again to get the
output section so we could subtract that from the symbol RVA. Now we
*always* have an OutputSection, so applying SECREL and SECTION
relocations isn't as much of a special case.
I'm still not quite happy with the cleanliness of this code. I'm not
sure what offsets and bases we should be using during the relocation
processing loop: VA, RVA, or OutputSectionOffset.
Reviewers: ruiu, pcc
Reviewed By: ruiu
Subscribers: majnemer, inglorion, llvm-commits, aprantl
Differential Revision: https://reviews.llvm.org/D34650
llvm-svn: 306566
Summary: The testing on the resource section of executables produced by lld has been very lax, and allowed a major bug to go unnoticed when we switched from shelling out to cvtres.exe to using llvm's own library. These additional tests should cover all the major failure points.
Reviewers: zturner, ruiu
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D34664
llvm-svn: 306465
Martin Storsjo