Summary:
Support jump tables belonging to split fragments with entries
pointing back to parent functions.
While skipping such families of functions, make sure to use the
topmost fragment to ignore its fragments.
(cherry picked from FBD24907438)
Summary:
In a jump table identification, register an invalid offset for jump table
entries pointing to function fragments.
These invalid offsets have no effect other than padding the jump
table size, calculated as `max(OffsetEntries, Entries)`.
Correct jump table size is required in strict mode (enabled by default
in aggregation mode by `perf2bolt`) in accounting of all PC-relative
relocations in data.
Functions containing these jump tables with invalid offsets are
marked to be ignored immediately afterwards in
`populateJumpTables`.
(cherry picked from FBD24897464)
Summary:
Introduce new BinaryFunction flag `IsCanonicalCFG`, which gets
unset by SCTC pass. Make DynoStats collection conditional on this
new flag.
SCTC leaves CFG in a state where branch counters of BBs with tail
calls/conditional tail calls are not available (except via annotations,
which get stripped by `lower-annotations`). Without branch
counters, DynoStats are invalid.
(cherry picked from FBD24558050)
Summary:
Fix cold fragment name matching regex by replacing existing
regexes `.*\.cold\..*` and `.*\.cold`
and combining them into `.*\.cold(\.\d)?`,
applied to restored name (with BOLT-added suffixes stripped)
This allows matching names like "execute_stack_op.cold/1", which
previously weren't recognized.
(cherry picked from FBD24804880)
Summary:
- Allow jump table entries to point to locations inside the function and its fragments.
Reasoning behind this is that jump table identification has the logic of stopping at entry which belongs to a function different from the one originally referencing jump table. This assumption is invalid for jump tables with entries pointing to both parent function and cold fragments, leading to "unclaimed PC-relative relocations" assertion.
- Add fragment identification heuristic based on function name regex and contiguous jump table entries.
Currently, parent-to-fragment relationship is set up based on interprocedural references – direct references from the parent function. These references don't include references through jump table.
Additionally, some fragments are only reachable through jump table. In that case, in order to fully consume jump table, add parent-to-fragment relationship during `analyzeJumpTable` using the following heuristics:
1. Fragment is identified as such based on name (contains `.cold.` part), but
2. Parent function is not set – no direct interprocedural references to that fragment, and
3. Fragment has the name of the form <parent>.cold(.\d+)
* For split functions with jump table entries spanning parent and fragments, mark parent and all fragments as ignored.
(cherry picked from FBD24456904)
Summary:
For interprocedural references to fragments, record them as
fragment entry points. Not registering these entry points leads to
UCE removing the blocks and "Undefined temporary symbol"
assertion.
(cherry picked from FBD24511281)
Summary:
Some of the TLS relocatios like R_AARCH64_TLSDESC_ADR_PAGE21 must be
handled by bolt and should not be skipped by the removed condition. Some
of the TLS relocations like R_AARCH64_TLS_TPREL64 could really be skipped
here, but AFAIU this condition was added as part of BOLT its self optimization, so
to prevent future problems here my suggestion is not to add another condition
like "isTLS(RType) && isTLSRelocatable(RType)", but just remove it since
absense of this condition should not broke any other TLS relocation.
Vladislav Khmelevsky,
Advanced Software Technology Lab, Huawei
Pull Request resolved: https://github.com/facebookincubator/BOLT/pull/103
GitHub Author: Vladislav Khmelevsky <Vladislav.Khmelevskyi@huawei.com>
(cherry picked from FBD24745928)
Summary:
Fix several issues to make C++ exceptions work in shared objects:
* Set MCObjectFileInfo PIC type based on the input binary type.
* Support indirect (DW_EH_PE_indirect) encoding while writing
exception Type Table.
* Use different LPStart value and landing pad encoding for .so's.
* Disable splitting of exception-handling code for .so's because of
the new encoding.
(cherry picked from FBD24698765)
Summary:
EliminateUnreachableBlocks has a data race because it depends
on BinaryContext::computeCodeSize. computeCodeSize supports independent
Emitters, enabling a lock-free execution. Unfortunately, that is almost
as expensive as the lock. Removing the boilerplate code for
parallellization of this pass turned out to be the best alternative: no
races and slightly better execution time for HHVM.
(cherry picked from FBD24716250)
Summary:
In BinaryContext, we had StringRef holding a reference to
an r-value std::string. This triggers clang's address sanitizer
warnings. In MCPlusBuilder we had a left shift overflowing a type,
which is undefined behavior. Similarly, in CallGraph, we had a hash
function shifting a negative value, which is also UB. The last two
triggers the UB sanitizer.
(cherry picked from FBD24661045)
Summary:
Some symbols in .dynsym will be erroneously marked as belonging to a
non-allocatable section that BOLT can remove. In that case, keep the
original invalid index for such symbols instead of setting the UNDEF
index.
(cherry picked from FBD24488677)
Summary:
Change .dot dumps filename format from
<function>-<passname>.dot
to
<function>-<passidx>_<passname>.dot
This change helps navigate dumps by making the pass order explicit.
Example:
execute_stack_op.cold.6-1(*2)-00_build-cfg.dot
execute_stack_op.cold.6-1(*2)-01_validate-internal-calls.dot
execute_stack_op.cold.6-1(*2)-02_strip-rep-ret.dot
...
(cherry picked from FBD24452903)
Summary:
While refactoring the pass, I removed the important transactional
property of the patching process. Restore it.
(cherry picked from FBD24440214)
Summary:
When -hot-text is on, do not read __hot_start and __hot_end
from input (inserted by a linker script with the intent of ordering
functions). This can confuse BOLT into creating a function with this
name depending on which address the symbol lands and we will assert
when trying to emit our own __hot_start/__hot_end with symbol
redefinition.
(cherry picked from FBD24366636)
Summary:
This diff is a preparation for loading the runtime on MachO.
The proposed schema is the following:
1/ Function "bolt_instr_setup" is placed into the predefined section "setup" (in the final setting this function will be coming from the instrumentation runtime but we still will be placing it into this section).
2/ In the instrumentation pass we create a symbol "bolt_instr_setup" and inject the corresponding call into the beginning of the function representing the entry point of the binary.
(cherry picked from FBD24329530)
Summary:
Do not store processed DWARF DIEs, but instead process them while
reading one at a time.
Reduces memory consumption when updating debug info by 10%-25%.
(cherry picked from FBD24327029)
Summary:
When placing restore instructions in the shrink wrapping pass,
we typically put them right before the last instruction of a block at
the dominance frontier. If this instruction happened to have a prefix,
because the MC lib separates prefix into separate MCInsts, we would
accidentally put a load between a prefix and another instruction. Fix
this.
(cherry picked from FBD24295324)
Summary:
Add first bits to support emitting instrumented code on MachO.
This diff enables us to instrument branches / emit counters.
(cherry picked from FBD24255164)
Summary:
On targets that support it, emit size of the emitted function symbol.
At the moment there's no use for the size except that it is visible in a
temporary .o file symbol table.
(cherry picked from FBD24246177)
Summary: _end is "defined" but its address doesn't belong to any section. This diff adds special handling for this symbol.
(cherry picked from FBD24249120)
Summary:
Append ".cold.0" suffix to the original part of the name, such that
"foo/1" becomes "foo.cold.0/1" instead of "foo/1.cold.0".
(cherry picked from FBD24246112)
Summary:
At the moment we are not using PatchEntries pass in non-relocation mode
on ELF. However, we will use it on MachO.
(cherry picked from FBD24235271)
Summary: Add ToolPath field to MachORewriteInstance. This will enable us to locate the runtime library relative to the tool's location.
(cherry picked from FBD24183448)
Summary:
Do not mix relocation codes from different archs. Even though
they do not intersect at the moment, this could easily introduce bugs
once new relocations are supported (for example, ILP32 for AArch64).
(cherry picked from FBD24169425)
Summary:
This diff adds a command line option to disable the check of overlapping elements in Mach-O parsing. This check in its current form is prohibitively expensive for large binaries.
A long-term fix would be to reimplement the check in a more efficient manner (and contribute it to the upstream).
(cherry picked from FBD24109468)
Summary:
In analyzeRelocations, we extract the result of the relocation
from binary code to recreate the target of it in a few special cases.
For R_X86_64_32S relocations, however, we were neglecting the
possibility of the encoded value in the instruction to be negative.
(cherry picked from FBD24096347)
Summary:
This patch fixes the assertion failure during instrumentation.
The assertion is raised by `getInstructionAtOffset` , which expects `CurrentState` to be either `Disassembled` or `CFG`.
The function is called from `postProcessEntryPoints`, which goes over Labels and performs a series of checks. The checks call BinaryFunction methods `setSimple(false)` or `setIgnored()`.
However, if `setIgnored` is invoked, it resets the state to `Empty`. Thus subsequent call to `getInstructionAtOffset` will fail.
(cherry picked from FBD24005197)
Summary:
Enable initial support for reading and patching special Linux kernel sections.
Author: Tanvir Ahmed Khan <takh@fb.com>
GitHub Author: takhandipu
(cherry picked from FBD22998869)
Summary:
Whenever we search for a function based on its address in the input
binary, we now always return a corresponding fragment for split
functions. If the user needs an access to the main fragment, they can
call getTopmostFragment().
(cherry picked from FBD23670311)
Summary:
Sections that do not originate from the input binary will have an
input address set to zero and thus do not have to be mapped.
Mapping such sections caused a build time regression in non-relocation
mode.
(cherry picked from FBD23670334)
Summary:
Fix issue with splitting critical edges originating at
the same BB in ShrinkWrapping::splitFrontierCritEdges.
Splitting of critical edges originating at the same FromBB
wasn't handled correctly as the Frontier at index corresponding
to FromBB was overwritten with basic blocks created for
multiple DestinationBBs.
(cherry picked from FBD23232398)
Summary:
Right now, if activity is recorded in cold parts, we write to
the .fdata file the ".cold" name instead of the correct name of the
function. Fix this.
(cherry picked from FBD23148705)
Summary:
When the input file is processed by BOLT, we cannot save profile in YAML
format as it requires CFG representation of functions.
(cherry picked from FBD22941794)
Summary:
Add first bits to support emitting more than 255 sections.
Update llvm.patch to include the changes in MachOObjectFile.cpp.
(cherry picked from FBD22655053)
Amir Ayupov