Commit Graph

82 Commits

Author SHA1 Message Date
Peter Collingbourne 052e855e2b COFF: Implement ThinLTO cache and cache pruning support.
Differential Revision: https://reviews.llvm.org/D37607

llvm-svn: 312770
2017-09-08 00:50:50 +00:00
Saleem Abdulrasool 3170ad7431 COFF: handle multiply defined symbols with different storage
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
2017-09-01 22:12:10 +00:00
Rui Ueyama c1e101f356 Revert r312171: Support nested static libraries.
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
2017-08-30 21:22:59 +00:00
Rui Ueyama a68748659a Support nested static libraries.
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
2017-08-30 20:55:41 +00:00
Zachary Turner ee9906d884 [LLD/PDB] Write actual records to the globals stream.
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
2017-08-11 19:00:03 +00:00
Martin Storsjo b3c97b9623 [COFF] Align import address chunks to the pointer size
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
2017-07-20 05:49:54 +00:00
Saleem Abdulrasool ace2fa7da4 COFF: improve link conformance for import names
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
2017-07-19 02:01:27 +00:00
Saleem Abdulrasool 08c83ea0f3 test: add COFF test for library extension handling
Ensure that an extension other than .dll, .exe is preserved as per the
behaviour of link.

llvm-svn: 308386
2017-07-18 22:25:07 +00:00
Reid Kleckner 651db91c2d [PDB] Merge in types and items from type servers (/Zi)
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
2017-07-18 00:21:25 +00:00
Martin Storsjo 2779165d8c [COFF] Add initial support for some ARM64 relocations and import thunks
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
2017-07-11 07:22:44 +00:00
Zachary Turner c1e93e5fa4 Fix some differences between lld and MSVC generated PDBs.
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
2017-07-07 18:45:56 +00:00
Reid Kleckner 3f85192930 [PDB] Fill in "Parent" and "End" fields of scope-like symbol records
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
2017-07-06 16:39:32 +00:00
Reid Kleckner a1001b8f38 [COFF] Allow debug info to relocate against discarded symbols
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
2017-06-28 17:06:35 +00:00
Eric Beckmann 01822fa1c1 Add more stringent tests for the resource section of executables.
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
2017-06-27 21:28:55 +00:00
Reid Kleckner 91ef9de643 [codeview] YAMLize all section offsets and indices in symbol records
We forgot to serialize these because llvm-readobj didn't dump them. They
are typically all zeros in an object file. The linker fills them in with
relocations before adding them to the PDB. Now we can properly round
trip these symbols through pdb2yaml -> yaml2pdb.

I made these fields optional with a zero default so that we can elide
them from our test cases.

llvm-svn: 305857
2017-06-20 21:19:22 +00:00
Reid Kleckner f5bb738f75 [PDB] Don't emit debug info associated with dead chunks
Summary:
Previously we didn't add debug info chunks to the SparseChunks array, so
they didn't participate in section GC. Now we do.

Reviewers: ruiu

Subscribers: aprantl, llvm-commits

Differential Revision: https://reviews.llvm.org/D34356

llvm-svn: 305811
2017-06-20 17:14:09 +00:00
Reid Kleckner 44cdb10964 [PDB] Start emitting source file and line information
Summary:
This is a first step towards getting line info to show up in VS and
windbg. So far, only llvm-pdbutil can parse the PDBs that we produce.
cvdump doesn't like something about our file checksum tables. I'll have
to dig into that next.

This patch adds a new DebugSubsectionRecordBuilder which takes bytes
directly from some other producer, such as a linker, and sticks it into
the PDB. Line tables only need to be relocated. No data needs to be
rewritten.

File checksums and string tables, on the other hand, need to be re-done.

Reviewers: zturner, ruiu

Subscribers: llvm-commits, hiraditya

Differential Revision: https://reviews.llvm.org/D34257

llvm-svn: 305713
2017-06-19 17:21:45 +00:00
Reid Kleckner 79ac99b3e8 [COFF] Drop unused comdat sections when GC is turned off
Summary:
Adds a "Discarded" bool to SectionChunk to indicate if the section was
discarded by COMDAT deduplication. The Writer still just checks
`isLive()`.

Fixes PR33446

Reviewers: ruiu

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D34288

llvm-svn: 305582
2017-06-16 20:47:19 +00:00
Saleem Abdulrasool bc7ff7027e COFF: add support for lib mode usage
When link is invoked with `/def:` and no input files, it behaves as if
`lib.exe` was invoked.  Emulate this behaviour, generating the import
library from the def file that was passed.  Because there is no input to
actually generate the dll, we simply process the def file early and exit
once we have created the import library.

llvm-svn: 305502
2017-06-15 20:39:58 +00:00
Zachary Turner a8cfc29c9a Resubmit "[codeview] Make obj2yaml/yaml2obj support .debug$S..."
This was originally reverted because of some non-deterministic
failures on certain buildbots.  Luckily ASAN eventually caught
this as a stack-use-after-scope, so the fix is included in
this patch.

llvm-svn: 305393
2017-06-14 15:59:27 +00:00
Zachary Turner 0085dce221 Revert "[codeview] Make obj2yaml/yaml2obj support .debug$S..."
This is causing failures on linux bots with an invalid stream
read.  It doesn't repro in any configuration on Windows, so
reverting until I have a chance to investigate on Linux.

llvm-svn: 305371
2017-06-14 06:24:24 +00:00
Zachary Turner a3da4467fa [codeview] Make obj2yaml/yaml2obj support .debug$S/T sections.
This allows us to use yaml2obj and obj2yaml to round-trip CodeView
symbol and type information without having to manually specify the bytes
of the section. This makes for much easier to maintain tests. See the
tests under lld/COFF in this patch for example. Before they just said
SectionData: <blob> whereas now we can use meaningful record
descriptions. Note that it still supports the SectionData yaml field,
which could be useful for initializing a section to invalid bytes for
testing, for example.

Differential Revision: https://reviews.llvm.org/D34127

llvm-svn: 305366
2017-06-14 05:31:00 +00:00
Peter Collingbourne 89061b2224 IR: Replace the "Linker Options" module flag with "llvm.linker.options" named metadata.
The new metadata is easier to manipulate than module flags.

Differential Revision: https://reviews.llvm.org/D31349

llvm-svn: 305227
2017-06-12 20:10:48 +00:00
Rui Ueyama 69ae29b1d1 Do not allow delay-importing data symbols.
If you pass /delayload:<dllname> to the COFF linker, it creates thunks
so that DLLs are loaded when they are used for the first time instead of
load-time.

This mechanism do not work for data symbols as there's no way to trap
acccesses to data imported from DLLs. (Technically, I think if we do not
initially map dllimport tables in memory, we could actually trap accesses
and delay-load data symbols, but that's not what Windows do.)

This patch is to report an error when you try to delay-load data symbols.

Fixes https://bugs.llvm.org/show_bug.cgi?id=33106

Differential Revision: https://reviews.llvm.org/D33557

llvm-svn: 303890
2017-05-25 18:03:34 +00:00
Rui Ueyama 9aa82f76ac Garbage collect dllimported symbols.
This is a different implementation than r303225 (which was reverted
in r303270, re-submitted in r303304 and then re-reverted in r303527).

In the previous patch, I tried to add Live bit to each dllimported
symbol. It turned out that it didn't work with "oldnames.lib" which
contains a lot of weak aliases to dllimported symbols.

The way we handle weak aliases is to check if undefined symbols
can be resolved using weak aliases, and if so, memcpy the Defined
symbols to weak Undefined symbols, so that any references to weak
aliases automatically see defined symbols instead of undefined ones.

This memcpy happens before MarkLive kicks in.

That means we may have multiple copies of dllimported symbols. So
turning on one instance's Live bit is not enough.

This patch moves the Live bit to dllimport file. Since multiple
copies of dllsymbols still point to the same file, we can use it as the
central repository to keep track of liveness.

Differential Revision: https://reviews.llvm.org/D33520

llvm-svn: 303814
2017-05-24 22:30:06 +00:00
Rui Ueyama b6632d9cd1 Revert r303304: Re-submit r303225: Garbage collect dllimported symbols.
This reverts commit r303304 because it looks like the change
introduced a crash bug. At least after that change, LLD with thinlto
crashes when linking Chromium.

llvm-svn: 303527
2017-05-22 06:01:37 +00:00
Rui Ueyama cd41bc8dec Re-submit r303225: Garbage collect dllimported symbols.
This reverts re-submits r303225 which was reverted in r303270 because it
broke the sanitizer-windows bot.

The reason of the failure is that we were writing dead symbols to the
symbol table. I fixed the issue.

llvm-svn: 303304
2017-05-17 21:36:08 +00:00
Hans Wennborg e67c5f6b52 Revert r303225 "Garbage collect dllimported symbols."
and follow-up r303226 "Fix Windows buildbots."

This broke the sanitizer-windows buildbot.

> Previously, the garbage collector (enabled by default or by explicitly
> passing /opt:ref) did not kill dllimported symbols. As a result,
> dllimported symbols could be added to resulting executables' dllimport
> list even if no one was actually using them.
>
> This patch implements dllexported symbol garbage collection. Just like
> COMDAT sections, dllimported symbols now have Live bits to manage their
> liveness, and MarkLive marks reachable dllimported symbols.
>
> Fixes https://bugs.llvm.org/show_bug.cgi?id=32950
>
> Reviewers: pcc
>
> Subscribers: llvm-commits
>
> Differential Revision: https://reviews.llvm.org/D33264

llvm-svn: 303270
2017-05-17 16:22:03 +00:00
Rui Ueyama de83fec029 Fix Windows buildbots.
llvm-svn: 303226
2017-05-17 01:05:56 +00:00
Rui Ueyama 02df7a6cf1 Garbage collect dllimported symbols.
Summary:
Previously, the garbage collector (enabled by default or by explicitly
passing /opt:ref) did not kill dllimported symbols. As a result,
dllimported symbols could be added to resulting executables' dllimport
list even if no one was actually using them.

This patch implements dllexported symbol garbage collection. Just like
COMDAT sections, dllimported symbols now have Live bits to manage their
liveness, and MarkLive marks reachable dllimported symbols.

Fixes https://bugs.llvm.org/show_bug.cgi?id=32950

Reviewers: pcc

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D33264

llvm-svn: 303225
2017-05-17 00:35:50 +00:00
Saleem Abdulrasool 5c98b74536 COFF: actually synthesize CONST imports properly
CONSTANT imports expect both the `_imp_` prefixed and non-prefixed
symbols should be added to the symbol table.  This allows for linking
symbols like _NSConcreteGlobalBlock in WinObjC.  The previous change
would generate the import library properly by handling the option but
would not consume the generated entry properly.

llvm-svn: 301657
2017-04-28 17:06:40 +00:00
Bob Haarman 4110816253 [coff] for /msvclto, pass archive members with prevailing symbols first
Summary: When using /msvclto, lld and MSVC's linker both do their own symbol resolution. This can cause them to select different archive members, which can result in undefined references. This change avoids that situation by extracting archive members that are selected by lld and passing those to link.exe before any archives, so that MSVC's uses those objects for symbol resolution instead of different archive members.

Reviewers: pcc, rnk, ruiu

Reviewed By: pcc

Subscribers: llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D32317

llvm-svn: 301045
2017-04-21 21:38:01 +00:00
Saleem Abdulrasool 72fbd346c6 COFF: add support for CONSTANT exports
The CONSTANT export type is marked as obsolete, but link still supports
this.  Furthermore, WinObjC uses this for certain exports.  Add support
for this export type.

llvm-svn: 301013
2017-04-21 18:05:46 +00:00
Bob Haarman bf24cb7189 COFF: tests for thinlto with mangled names
Summary: This change adds tests for r299268.

Reviewers: pcc, rnk

Reviewed By: pcc

Subscribers: mehdi_amini, llvm-commits, Prazek

Differential Revision: https://reviews.llvm.org/D31549

llvm-svn: 299272
2017-03-31 22:17:02 +00:00
Bob Haarman 2d2b5b09e0 COFF: include archive name in LTO object name
Summary: In the ELF linker, we create the buffer identifier for bitcode files by appending the object name to the archive name. This change makes the COFF linker do the same. Without the change, ThinLTO builds can fail with an error message about multiple ThinLTO modules per object file, caused by object files contained in different archives having the same name.

Reviewers: pcc, ruiu

Reviewed By: pcc

Subscribers: mehdi_amini

Differential Revision: https://reviews.llvm.org/D31402

llvm-svn: 298942
2017-03-28 21:20:06 +00:00
Rui Ueyama 1e0b158dbd Add an option to use the MSVC linker to link LTO-generated object files.
This patch defines a new command line option, /MSVCLTO, to LLD.
If that option is given, LLD invokes link.exe to link LTO-generated
object files. This is hacky but useful because link.exe can create
PDB files.

Differential Revision: https://reviews.llvm.org/D29526

llvm-svn: 294234
2017-02-06 20:47:55 +00:00
Rui Ueyama 5289662e4a PDB: Merge type info.
This patch is to merge type info in multiple .debug$T sections.

One mystery that needs to be solved is that it is not clear how
the MSVC linker uses TPI and IPI streams. Both streams contain
type info, and it is not obvious what kind of record should go
which.

dumppdb command in microsoft-pdb repository prints out IPI stream
contents as "IDs" and TPI stream as "TYPES", but looks like the tool
don't really care about which stream type recrods were read from.

For now, in this patch, I emit all type records to TPI stream.
It might just work with other tools. If not, we need to investigate
it more.

llvm-svn: 291739
2017-01-12 03:09:25 +00:00
Rui Ueyama 569851f1d6 Partially revert r287009: Remove trailing whitespace.
This reverts part of r287009 because I accidentally changed binary files.

llvm-svn: 287010
2016-11-15 19:09:13 +00:00
Rui Ueyama d7cfb1b6dd Remove trailing whitespace.
llvm-svn: 287009
2016-11-15 19:07:17 +00:00
Rui Ueyama f83806a8ad Identify object files compiled with cl.exe /GL.
Object files compiled with cl.exe /GL contain intermediate code for LTO.
We can't (and don't want to) interpret such code, but we should print
out a user-friendly error message.

Differential Revision: https://reviews.llvm.org/D26647

llvm-svn: 286921
2016-11-15 01:01:51 +00:00
Hans Wennborg cb8f2ef644 LTO: Don't follow lazy references when seeing new definitions in the combined LTO object
Following the lazy reference might bring in an object file that depends
on bitcode files that weren't part of the LTO step.

Differential Revision: https://reviews.llvm.org/D25461

llvm-svn: 283989
2016-10-12 09:00:06 +00:00
Saleem Abdulrasool eea45bc478 COFF ARM: Error out if 24 bit thumb branches are out of range
In the ELF linker, the same situation already errors out with "relocation
R_ARM_THM_CALL out of range".

Patch by Martin Storsjö!

llvm-svn: 277838
2016-08-05 17:33:24 +00:00
Chris Bieneman ca5170e3e4 [yaml2obj] Updating LLD tests to account for LLVM r273915
This removed the -format flag from yaml2obj in favor of YAML tags.

llvm-svn: 273920
2016-06-27 20:17:08 +00:00
Rui Ueyama afb1901e42 COFF: Support /manifestinput command line option.
Manifest file is a separate or embedded XML file having metadata
of an executable. As it is XML, it can contain various types of
information. Probably the most popular one is to request escalated
priviledges.

Usually the linker creates an XML file and embed that file into
an executable. However, there's a way to supply an XML file from
command line. /manifestniput is it.

Apparently it is over-designed here, but if you supply two or more
manifest files, then the linker needs to merge the files into a
single XML file. A good news is that we don't need to do that ourselves.
MT.exe command can do that, so we call the command from the linker
in this patch.

llvm-svn: 266704
2016-04-19 01:21:58 +00:00
David Majnemer 18558b6d9e [COFF] Correct tests with bogus alignment
llvm-svn: 263838
2016-03-18 21:47:12 +00:00
David Majnemer 07f7fe5a4c [COFF] Fix invalid alignment in tests
Some COFF tests used INT_MIN for the alignment of the directive section.
This is invalid; replace the alignment with something more sensible: 1.

llvm-svn: 263723
2016-03-17 16:56:31 +00:00
David Blaikie 947bf5e0bb [opaque pointer type] update test cases for explicit pointee types on global aliases
llvm-svn: 247379
2015-09-11 03:22:12 +00:00
Rui Ueyama 28103266c6 COFF: Update a test for ICF.
The old test files were just compiler outputs, so it was hard to
debug if something goes wrong. The new test file is carefully
hand-crafted to trigger ICF to avoid that.

llvm-svn: 245826
2015-08-24 07:52:08 +00:00
Rui Ueyama 308915ade2 COFF: Fix seh.test.
seh.test was testing -flavor link. This should have been testing
-flavor link2.

llvm-svn: 243557
2015-07-29 19:17:15 +00:00
Rui Ueyama 9420dee328 COFF: Fix export symbol names for x86.
I don't fully understand the rationale behind the name mangling
scheme used for the DLL export table and the import library.
Why only leading "_" is dropped for the import library while
both "_" and "@" are dropped from DLL symbol table? But this seems
to be what MSVC linker does.

llvm-svn: 243490
2015-07-28 22:34:24 +00:00