This adds direct support for computing offsets from the thread pointer
for both variants. Of the architectures we support, variant 1 is used
only by aarch64 (but that doesn't seem to be documented anywhere.)
llvm-svn: 270243
Lazy binding is quite important for use case like a shared build of
llvm. Also, if someone wants to disable it, it is better done in the
compiler (disable plt generation).
The only reason to keep it is to make it easier to add a new
architecture. But it doesn't really help much as it is possible to start
with non lazy relocation and plt code but still let the generic part
create a dedicated .got.plt and .rela.plt.
llvm-svn: 269982
MIPS is the only target requires GOT header. We already have MIPS
specific code in the `GotSection` class, so move MIPS GOT header
generation there and delete redundant stuff like `GotHeaderEntriesNum`
field and `writeGotHeader` method.
Differential Revision: http://reviews.llvm.org/D19465
llvm-svn: 267460
It is now redundant. Writer.cpp can reason that 2 dynamic relocations
are needed: one to find the final got entry address and one to fill the
got entry.
llvm-svn: 266876
With this patch we use the first scan over the relocations to remember
the information we found about them: will them be relaxed, will a plt be
used, etc.
With that the actual relocation application becomes much simpler. That
is particularly true for the interfaces in Target.h.
This unfortunately means that we now do two passes over relocations for
non SHF_ALLOC sections. I think this can be solved by factoring out the
code that scans a single relocation. It can then be used both as a scan
that record info and for a dedicated direct relocation of non SHF_ALLOC
sections.
I also think it is possible to reduce the number of enum values by
representing a target with just an OutputSection and an offset (which
can be from the start or end).
This should unblock adding features like relocation optimizations.
llvm-svn: 266158
Some targets might require creation of thunks. For example, MIPS targets
require stubs to call PIC code from non-PIC one. The patch implements
infrastructure for thunk code creation and provides support for MIPS
LA25 stubs. Any MIPS PIC code function is invoked with its address
in register $t9. So if we have a branch instruction from non-PIC code
to the PIC one we cannot make the jump directly and need to create a small
stub to save the target function address.
See page 3-38 ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
- In relocation scanning phase we ask target about thunk creation necessity
by calling `TagetInfo::needsThunk` method. The `InputSection` class
maintains list of Symbols requires thunk creation.
- Reassigning offsets performed for each input sections after relocation
scanning complete because position of each section might change due
thunk creation.
- The patch introduces new dedicated value for DefinedSynthetic symbols
DefinedSynthetic::SectionEnd. Synthetic symbol with that value always
points to the end of the corresponding output section. That allows to
escape updating synthetic symbols if output sections sizes changes after
relocation scanning due thunk creation.
- In the `InputSection::writeTo` method we write thunks after corresponding
input section. Each thunk is written by calling `TargetInfo::writeThunk` method.
- The patch supports the only type of thunk code for each target. For now,
it is enough.
Differential Revision: http://reviews.llvm.org/D17934
llvm-svn: 265059
This simplifies a few things
* Read the value as early as possible, instead of passing a pointer to
the location.
* Print the warning for missing pair close to where we find out it is
missing.
* Don't pass the value to relocateOne.
llvm-svn: 264802
It was a badly specified hack for when a tls relocation should be
propagated to the dynamic relocation table.
This replaces it with a not as bad hack of saying that a local dynamic
tls relocation is never preempted.
I will try to remove even that second hack in the next patch.
llvm-svn: 262955
Patch changes the return type of Target::relaxTls
to size_t from unsigned. That is consistent with
its use from other code.
Change was reviewed http://reviews.llvm.org/D17882
and asked to commit separately from that patch above.
llvm-svn: 262794
Patch changes all relocations types to be uint32_t and also
fixes some dependent inconsistency in callers code.
Differential revision: http://reviews.llvm.org/D17882
llvm-svn: 262793
The rules for when we can relax tls relocations are target independent.
The only things that are target dependent are the relocation values.
llvm-svn: 262748
For shared libraries we allow any weak undefined symbol to eventually be
resolved, even if we never see a definition in another .so. This matches
the behavior when handling other undefined symbols in a shared library.
For executables, we require seeing a definition in a .so or resolve it
to zero. This is also similar to how non weak symbols are handled.
llvm-svn: 262017
This patch adds some TLS relocations and relaxations for AArch64.
Some Global-Dynamic relocation are handled by optimizing them to
Local-Exec (Initial-Exec is not yet supported). They are:
- R_AARCH64_TLSDESC_ADR_PAGE21
- R_AARCH64_TLSDESC_LD64_LO12_NC
- R_AARCH64_TLSDESC_ADD_LO12_NC
- R_AARCH64_TLSDESC_CALL
Also some Init-Exec is optimized to Local-Exec if possible. They are:
- R_AARCH64_TLSIE_ADR_GOTTPREL_PAGE21
- R_AARCH64_TLSIE_LD64_GOTTPREL_LO12_NC
Finally some Local-Exec relocation are handled in relocateOne:
- R_AARCH64_TLSLE_ADD_TPREL_HI12
- R_AARCH64_TLSLE_ADD_TPREL_LO12_NC
This work is mainly for compiler bootstrap, where static binaries is
showing good progress (although shared object still lacking support
from both TLS aarch64 backend and some other issues).
llvm-svn: 260677
Previously, Target held a value until a new value is assigned to the
variable. That was a benign leak -- that was not an unbounded leak
and didn't grab any resources except a small amount of memory. But
it is better to fix than leaving as is.
llvm-svn: 260592
R_X86_64_TPOFF64 is a dynamic relocation,
it should not appear in static relocation processing.
Patch fixes it.
Differential revision: http://reviews.llvm.org/D16880
llvm-svn: 260508
This is the function equivalent of a copy relocation.
Since functions are expected to change sizes, we cannot use copy
relocations. In situations where one would be needed, what is done
instead is:
* Create a plt entry
* Output an undefined symbol whose addr is the plt entry.
The dynamic linker makes sure any shared library uses the plt entry as
the function address.
llvm-svn: 260224
Symbol does not need an entry i the 'global' part of GOT if it cannot be
preempted. So canBePreempted fully satisfies us at least for now.
llvm-svn: 259779
This function is a predicate that a given relocation can be relaxed.
The previous name implied that it returns true if a given relocation
has already been optimized away.
llvm-svn: 259128
In InputSection.cpp it was possible to dereference null.
Had to change signature of relocateTlsOptimize to accept pointer instead of reference.
Differential revision: http://reviews.llvm.org/D16466
llvm-svn: 258508
Some MIPS relocation (for now R_MIPS_GOT16) requires creation of GOT
entries for symbol not included in the dynamic symbol table. They are
local symbols and non-local symbols with 'local' visibility. Local GOT
entries occupy continuous block between GOT header and regular GOT
entries.
The patch adds initial support for handling local GOT entries. The main
problem is allocating local GOT entries for local symbols. Such entries
should be initialized by high 16-bit of the symbol value. In ideal world
there should be no duplicated entries with the same values. But at the
moment of the `Writer::scanRelocs` call we do not know a value of the
symbol. In this patch we create new local GOT entry for each relocation
against local symbol, though we can exhaust GOT quickly. That needs to
be optimized later. When we calculate relocation we know a final symbol
value and request local GOT entry index. To do that we maintain map
between addresses and local GOT entry indexes. If we start to calculate
relocations in parallel we will have to serialize access to this map.
Differential Revision: http://reviews.llvm.org/D16324
llvm-svn: 258388
MIPS ABI has relocations like R_MIPS_JALR which is just a hint for
linker to make some code optimization. Such relocations should not be
handled as a regular ones and lead to say dynamic relocation creation.
The patch introduces new virtual `Target::isHintReloc` method, overrides
it in the `MipsTargetInfo` class and calls it in the `Writer<ELFT>::scanRelocs`
method.
Differential Revision: http://reviews.llvm.org/D16193
llvm-svn: 257798
R_X86_64_PLT32 is handled in the same way as R_X86_64_PC32 by
relocateOne(), so this function does not seems to be needed.
Without this code, all tests still pass.
http://reviews.llvm.org/D15971
llvm-svn: 257203
All non-trivial relocation decisions need explanations like this
to help readers understand not only how relocations are handled but
why they are handled these ways. This is a start.
llvm-svn: 257119
This relocation is similar to R_*_RELATIVE except that the value used in this relocation is the program address returned by the function, which takes no arguments, at the address of
the result of the corresponding R_*_RELATIVE relocation as specified in the processor-specific ABI. The purpose of this relocation to avoid name lookup for locally defined STT_GNU_IFUNC symbols at load-time.
More info can be found in ifunc.txt from https://sites.google.com/site/x32abi/documents.
Differential revision: http://reviews.llvm.org/D15235
llvm-svn: 256144
R_386_GOTOFF is calculated as S + A - GOT, where:
S - Represents the value of the symbol whose index resides in the relocation entry.
A - Represents the addend used to compute the value of the relocatable field.
GOT - Represents the address of the global offset table.
Differential revision: http://reviews.llvm.org/D15383
llvm-svn: 256143
@indntpoff is similar to @gotntpoff, but for use in position dependent code. While @gotntpoff resolves to GOT slot address relative to the
start of the GOT in the movl or addl instructions, @indntpoff resolves to the
absolute GOT slot address. ("ELF Handling For Thread-Local Storage", Ulrich Drepper).
Differential revision: http://reviews.llvm.org/D15494
llvm-svn: 255884
R_X86_64_SIZE64/R_X86_64_SIZE32 relocations were introduced in 0.98v of "System V Application Binary Interface x86-64" (http://www.x86-64.org/documentation/abi.pdf).
Calculation for them is Z + A, where:
Z - Represents the size of the symbol whose index resides in the relocation entry.
A - Represents the addend used to compute the value of the relocatable field.
Differential revision: http://reviews.llvm.org/D15335
llvm-svn: 255332
"Ulrich Drepper, ELF Handling For Thread-Local Storage" (5.5 x86-x64 linker optimizations, http://www.akkadia.org/drepper/tls.pdf) shows how GD can be optimized to IE.
This patch implements the optimization.
Differential revision: http://reviews.llvm.org/D15000
llvm-svn: 254713
Some MIPS relocations including `R_MIPS_HI16/R_MIPS_LO16` use combined
addends. Such addend is calculated using addends of both paired relocations.
Each `R_MIPS_HI16` relocation is paired with the next `R_MIPS_LO16`
relocation. ABI requires to compute such combined addend in case of REL
relocation record format only.
For details see p. 4-17 at
ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
This patch implements lookup of the next paired relocation suing new
`InputSectionBase::findPairedRelocLocation` method. The primary
disadvantage of this approach is that we put MIPS specific logic into
the common code. The next disadvantage is that we lookup `R_MIPS_LO16`
for each `R_MIPS_HI16` relocation, while in fact multiple `R_MIPS_HI16`
might be paired with the single `R_MIPS_LO16`. From the other side
this way allows us to keep `MipsTargetInfo` class stateless and implement
later relocation handling in parallel.
This patch does not support `R_MIPS_HI16/R_MIPS_LO16` relocations against
`_gp_disp` symbol. In that case the relocations use a special formula for
the calculation. That will be implemented later.
Differential Revision: http://reviews.llvm.org/D15112
llvm-svn: 254461
Implements @tlsld (LD to LE) and @tlsgd (GD to LE) optimizations.
Patch does not implement the GD->IE case for @tlsgd.
Differential revision: http://reviews.llvm.org/D14870
llvm-svn: 254101
Patch implements lazy relocations for x86.
One of features of x86 is that executable files and shared object files have separate procedure linkage tables. So patch implements both cases.
Detailed information about instructions used can be found in http://docs.oracle.com/cd/E19620-01/805-3050/chapter6-1235/index.html (search: x86: Procedure Linkage Table).
Differential revision: http://reviews.llvm.org/D14955
llvm-svn: 254098
This patch implements next relocations:
R_386_TLS_LE - Negative offset relative to static TLS (GNU version).
R_386_TLS_LE_32 - Offset relative to static TLS block.
These ones are created when using next code sequences:
* @tpoff - The operator must be used to compute an immediate value. The linker will report
an error if the referenced variable is not defined or it is not code for the executable
itself. No GOT entry is created in this case.
* @ntpoff Calculate the negative offset of the variable it is added to relative to the static TLS block.
The operator must be used to compute an immediate value. The linker will report
an error if the referenced variable is not defined or it is not code for the executable
itself. No GOT entry is created in this case.
Information was found in Ulrich Drepper, ELF Handling For Thread-Local Storage, http://www.akkadia.org/drepper/tls.pdf, (6.2, p76)
Differential revision: http://reviews.llvm.org/D14930
llvm-svn: 254090
https://docs.oracle.com/cd/E19683-01/817-3677/chapter6-26/index.html says:
R_386_GOTPC
Resembles R_386_PC32, except that it uses the address of the global offset table in its calculation. The symbol referenced in this relocation normally is _GLOBAL_OFFSET_TABLE_, which also instructs the link-editor to create the global offset table.
Currently _GLOBAL_OFFSET_TABLE_ has value == zero. And we use GOT address to calculate the relocation. This patch does not changes that. It just removes the method which is used only for x86. So it is close to non functional change.
Differential revision: http://reviews.llvm.org/D14993
llvm-svn: 254088
R_X86_64_GOTTPOFF is not always requires GOT entries. Some relocations can be converted to local ones.
Differential revision: http://reviews.llvm.org/D14713
llvm-svn: 253966
With these relocations, it is now possible to build a simple "hello world"
program for AArch64 Debian.
Differential revision: http://reviews.llvm.org/D14917
llvm-svn: 253957
The content of reserved entries of the .got.plt section is target specific.
In particular, on x86_64 the zero entry holds the address of the .dynamic section,
but on AArch64 the same info is stored in the zero entry of the .got section.
Differential revision: http://reviews.llvm.org/D14703
llvm-svn: 253239
leaq symbol@tlsld(%rip), %rdi
call __tls_get_addr@plt
symbol@tlsld (R_X86_64_TLSLD) instructs the linker to generate a tls_index entry (two GOT slots) in the GOT for the entire module (shared object or executable) with an offset of 0. The symbol for this GOT entry doesn't matter (as long as it's either local to the module or null), and gold doesn't put a symbol in the dynamic R_X86_64_DTPMOD64 relocation for the GOT entry.
All other platforms defined in http://www.akkadia.org/drepper/tls.pdf except for Itanium use a similar model where global and local dynamic GOT entries take up 2 contiguous GOT slots, so we can handle this in a unified manner if we don't care about Itanium.
While scanning relocations we need to identify local dynamic relocations and generate a single tls_index entry in the GOT for the module and store the address of it somewhere so we can later statically resolve the offset for R_X86_64_TLSLD relocations. We also need to generate a R_X86_64_DTPMOD64 relocation in the RelaDyn relocation section.
This implementation is a bit hacky. It side steps the issue of GotSection and RelocationSection only handling SymbolBody entries by relying on a specific relocation type. The alternative to this seemed to be completely rewriting how GotSection and RelocationSection work, or using a different hacky signaling method.
llvm-svn: 252682
This patch implements R_MIPS_GOT16 relocation for global symbols in order to
generate some entries in GOT. Only reserved and global entries are supported
for now. For the detailed description about GOT in MIPS, see "Global Offset
Table" in Chapter 5 in the followin document:
ftp://www.linux-mips.org/pub/linux/mips/doc/ABI/mipsabi.pdf
In addition, the platform specific symbol "_gp" is added, see "Global Data
Symbols" in Chapter 6 in the aforementioned document.
Differential revision: http://reviews.llvm.org/D14211
llvm-svn: 252275
relocateOne is a function to apply a relocation. Previously, that
function took a pointer to Elf_Rel or Elf_Rela in addition to other
information that can be derived from the relocation entry. This patch
simplifies the parameter list. The new parameters, P or SA, are used
in the ELF spec to describe each relocation. These names make
relocateOne look like a mechanical, direct translation of the ELF spec.
llvm-svn: 251090
Target has supportsLazyRelocations() method which can switch lazy relocations on/off (currently all targets are OFF except x64 which is ON). So no any other targets are affected now.
Differential Revision: http://reviews.llvm.org/D13856?id=37726
llvm-svn: 250808
R_PPC64_TOC does not have an associated symbol, but does have a non-zero VA
that target-specific code must compute using some non-trivial rule. We
handled this as a special case in PPC64TargetInfo::relocateOne, where
we knew to write this special address, but that did not work when creating shared
libraries. The special TOC address needs to be the subject of a
R_PPC64_RELATIVE relocation, and so we also need to know how to encode this
special address in the addend of that relocation.
Thus, some target-specific logic is necessary when creating R_PPC64_RELATIVE as
well. To solve this problem, we teach getLocalRelTarget to handle R_PPC64_TOC
as a special case. This allows us to remove the special case in
PPC64TargetInfo::relocateOne (simplifying code there), and naturally allows the
existing logic to do the right thing when creating associated R_PPC64_RELATIVE
relocations for shared libraries.
llvm-svn: 250555
After some additional post-commit (post-revert) discussion and research, this
reverts, in part, r250205, so the ABI-recommended starting address can be used
on PPC64 (as is done by other linkers).
Also, this addresses the FIXME in ELF/Writer.cpp by making VAStart a
target-dependent property.
llvm-svn: 250378
- Make the `MipsTargetInfo` template class with `ELFType` argument. Use
the argument to select an appropriate relocation type and read/write
routines.
- Add template function `add32` to add-and-write relocation value in
both big and little endian cases. Keep the `add32le` to reduce code
changes.
Differential Revision: http://reviews.llvm.org/D13723
llvm-svn: 250297
This has turned out to be unnecessary, and while some ability to set VAStart
will be needed at some point, this is not clearly the right direction.
llvm-svn: 250205
What was done:
1) .got.plt section is created for functions that requires PLT. .got.plt has 3 predefined empty entries now that are required for dynamic linker.
Also other new items created are configured to have correct jump to PLT[N].
2) PLT section now has PLT[0] entry, also others ones are configured to support PLT->GOT(.got.plt) calls.
3) Implemented .rel[a].plt sections (based on patch http://reviews.llvm.org/D13569).
4) Fixed plt relocations types (based on patch http://reviews.llvm.org/D13589).
NOTES:
The .plt.got zero entry is still empty now. According to ELF specification it should hold the address of the dynamic structure, referenced with the symbol
_DYNAMIC. The _DYNAMIC entry points to the .dynamic section which contains information used by the ELF interpreter to setup the binary.
Differential Revision: http://reviews.llvm.org/D13651
llvm-svn: 250169
Now all Target<Arch> classes are used only in Target.cpp.
We can put them in an anonymous namespace. In order to avoid
merge conflict with other people's patches, I'll do that later.
llvm-svn: 250168
Under the PPC64 ELF ABI, functions that might call into other modules (and,
thus, need to load a different TOC base value into %r2), need to restore the
old value after the call. The old value is saved by the .plt code, and the
caller only needs to include a nop instruction after the call, which the linker
will transform into a TOC restore if necessary.
In order to do this the relocation handler needs two things:
1. It needs to know whether the call instruction it is modifying is targeting
a .plt stub that will load a new TOC base value (necessitating a restore after
the call).
2. It needs to know where the buffer ends, so that it does not accidentally
run off the end of the buffer when looking for the 'nop' instruction after the
call.
Given these two pieces of information, we can insert the restore instruction in
place of the following nop when necessary.
llvm-svn: 250110
The required page alignment is different on different targets. On PowerPC, for
example, we need 64K pages (the loader won't set different permissions on a
finer granularity than that). I've set the existing targets to what I believe
to be the correct values, and have updated the regression tests accordingly.
llvm-svn: 249760
The size of a .plt entry is different on different targets (it is,
specifically, much larger than 8 on all PPC ABIs). There is no functional
change here (later patches to create .plt entries for PPC64 will depend on this
change).
llvm-svn: 249756
Reapply r249726 (and r249723), hopefully with the correct test fixups this time.
Original commit message:
Address a FIXME in ELF/Writer.cpp: Make VAStart a target-dependent property.
I've set the values for the existing targets to what I believe to be the
correct values, and updated the regression tests accordingly.
llvm-svn: 249752
Address a FIXME in ELF/Writer.cpp: Make VAStart a target-dependent property.
I've set the values for the existing targets to what I believe to be the
correct values, and updated the regression tests accordingly.
llvm-svn: 249723
Besides a trivial MIPS support the patch introduces new TargetInfo class
member getDefaultEntry() to override default name of the entry symbol.
MIPS uses __start for that.
Differential Revision: http://reviews.llvm.org/D13227
llvm-svn: 248779
Unfortunately the i386 and x86_64 relocation have the same numerical value
and it is a probably a bit much to add got support for another architecture
just to test this.
llvm-svn: 248326
This is just enough to get PLT working on 32 bit x86.
The idea behind using a virtual interface is that it should be easy to
convert any of the functions to template parameters if any turns out to be
performance critical.
llvm-svn: 248308
Rafael Espindola