------------------------------------------------------------------------
r328039 | mstorsjo | 2018-03-20 13:37:51 -0700 (Tue, 20 Mar 2018) | 8 lines
[X86] Don't use the MSVC stack protector names on mingw
Mingw uses the same stack protector functions as GCC provides
on other platforms as well.
Patch by Valentin Churavy!
Differential Revision: https://reviews.llvm.org/D27296
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@332001 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r327540 | ctopper | 2018-03-14 10:57:19 -0700 (Wed, 14 Mar 2018) | 7 lines
[X86] Add back fast-isel code for handling i8 shifts.
I removed this in r316797 because the coverage report showed no coverage and I thought it should have been handled by the auto generated table. I now see that there is code that bypasses the table if the shift amount is out of bounds.
This adds back the code. We'll codegen out of bounds i8 shifts to effectively (amount & 0x1f). The 0x1f is a strange quirk of x86 that shift amounts are always masked to 5-bits(except 64-bits). So if the masked value is still out bounds the result will be 0.
Fixes PR36731.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@331815 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r330186 | nemanjai | 2018-04-17 06:07:01 -0700 (Tue, 17 Apr 2018) | 11 lines
[PowerPC] Mark the BDNZ intrinsic as NoDuplicate
Duplicating this intrinsic is not generally valid because it has the side-effect
of decrementing the CTR. Any passes that duplicate it would need to be taught to
keep the regions formed completely disjoint.
This patch should be NFC for typical uses as CTRLoops runs after the remaining
loop passes. It only affects situations where the loop passes are scheduled on
the IR after the codegen passes (as is the case with some JIT pipelines).
Fixes https://bugs.llvm.org/show_bug.cgi?id=37050
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@331716 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r329761 | gberry | 2018-04-10 14:43:03 -0700 (Tue, 10 Apr 2018) | 13 lines
[AArch64][Falkor] Fix bug in Falkor HWPF collision avoidance pass.
Summary:
When inserting MOVs to avoid Falkor HWPF collisions, the non-base
register operand of load instructions (e.g. a register offset) was not
being considered live, so it could potentially have been used as a
scratch register, clobbering the actual offset value.
Reviewers: mcrosier
Subscribers: rengolin, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D45502
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@330209 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r322373 | d0k | 2018-01-12 07:03:24 -0800 (Fri, 12 Jan 2018) | 4 lines
[PowerPC] Don't miscompile rotate+mask into an ANDIo if it can't recreate the immediate
I'm not even sure if this transform is ever worth it, but this at least
stops the bleeding.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@330082 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r329852 | nemanjai | 2018-04-11 14:25:44 -0700 (Wed, 11 Apr 2018) | 8 lines
[PowerPC] Fix condition for 64-bit rotate when replacing r+r instr with r+i
This patch fixes https://bugs.llvm.org/show_bug.cgi?id=37039
The condition only covers one of the two 64-bit rotate instructions. This just
adds the second (RLDICLo).
Patch by Josh Stone.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@330076 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r325653 | sdardis | 2018-02-21 00:06:53 +0000 (Wed, 21 Feb 2018) | 31 lines
[mips] Spectre variant two mitigation for MIPSR2
This patch provides mitigation for CVE-2017-5715, Spectre variant two,
which affects the P5600 and P6600. It implements the LLVM part of
-mindirect-jump=hazard. It is _not_ enabled by default for the P5600.
The migitation strategy suggested by MIPS for these processors is to use
hazard barrier instructions. 'jalr.hb' and 'jr.hb' are hazard
barrier variants of the 'jalr' and 'jr' instructions respectively.
These instructions impede the execution of instruction stream until
architecturally defined hazards (changes to the instruction stream,
privileged registers which may affect execution) are cleared. These
instructions in MIPS' designs are not speculated past.
These instructions are used with the attribute +use-indirect-jump-hazard
when branching indirectly and for indirect function calls.
These instructions are defined by the MIPS32R2 ISA, so this mitigation
method is not compatible with processors which implement an earlier
revision of the MIPS ISA.
Performance benchmarking of this option with -fpic and lld using
-z hazardplt shows a difference of overall 10%~ time increase
for the LLVM testsuite. Certain benchmarks such as methcall show a
substantially larger increase in time due to their nature.
Reviewers: atanasyan, zoran.jovanovic
Differential Revision: https://reviews.llvm.org/D43486
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@329798 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r327651 | carrot | 2018-03-15 10:49:12 -0700 (Thu, 15 Mar 2018) | 9 lines
[PPC] Avoid non-simple MVT in STBRX optimization
PR35402 triggered this case. It bswap and stores a 48bit value, current STBRX optimization transforms it into STBRX. Unfortunately 48bit is not a simple MVT, there is no PPC instruction to support it, and it can't be automatically expanded by llvm, so caused a crash.
This patch detects the non-simple MVT and returns early.
Differential Revision: https://reviews.llvm.org/D44500
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@329641 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r322319 | matze | 2018-01-11 14:30:43 -0800 (Thu, 11 Jan 2018) | 7 lines
PeepholeOptimizer: Fix for vregs without defs
The PeepholeOptimizer would fail for vregs without a definition. If this
was caused by an undef operand abort to keep the code simple (so we
don't need to add logic everywhere to replicate the undef flag).
Differential Revision: https://reviews.llvm.org/D40763
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@329619 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r328341 | apazos | 2018-03-23 10:53:27 -0700 (Fri, 23 Mar 2018) | 16 lines
[ARM] Fix "Constant pool entry out of range!" in Thumb1 mode
This patch fixes PR36658, "Constant pool entry out of range!" in Thumb1 mode.
In ARMConstantIslands::optimizeThumb2JumpTables() in Thumb1 mode,
adjustBBOffsetsAfter() is not calculating postOffset correctly by
properly accounting for the padding that is required for the constant pool
that immediately follows the jump table branch instruction.
Reviewers: t.p.northover, eli.friedman
Reviewed By: t.p.northover
Subscribers: chrib, tstellar, javed.absar, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D44709
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@329487 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r326393 | ctopper | 2018-03-01 01:08:38 +0100 (Thu, 01 Mar 2018) | 5 lines
[X86] Make sure we don't combine (fneg (fma X, Y, Z)) to a target specific node when there are no FMA instructions.
This would cause a 'cannot select' error at isel when we should have emitted a lib call and an xor.
Fixes PR36553.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@326423 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r325739 | nemanjai | 2018-02-22 04:02:41 +0100 (Thu, 22 Feb 2018) | 9 lines
[PowerPC] Do not produce invalid CTR loop with an FRem
An FRem instruction inside a loop should prevent the loop from being converted
into a CTR loop since this is not an operation that is legal on any PPC
subtarget. This will always be a call to a library function which means the
loop will be invalid if this instruction is in the body.
Fixes PR36292.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325767 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r325654 | ctopper | 2018-02-21 01:15:48 +0100 (Wed, 21 Feb 2018) | 10 lines
[X86] Disable CLWB for Cannon Lake
Cannon Lake does not support CLWB, therefore it
does not include all features listed under SKX anymore.
Instead, enumerate all SKX features with the exception of CLWB.
Patch by Gabor Buella
Differential Revision: https://reviews.llvm.org/D43380
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325671 91177308-0d34-0410-b5e6-96231b3b80d8
These are needed for operations on fp16 types in a later patch.
This also re-instates the test/CodeGen/AArch64/GlobalISel/fp16-copy-gpr.mir
test that was deleted which depended on this patch.
(See PR36345.)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325669 91177308-0d34-0410-b5e6-96231b3b80d8
I couldn't get fp16-copy-gpr.mir to pass after merging so I removed it until
aemerson; the other test I re-generated and it seems to work.
------------------------------------------------------------------------
r325550 | aemerson | 2018-02-20 06:11:57 +0100 (Tue, 20 Feb 2018) | 7 lines
[AArch64][GlobalISel] When copying from a gpr32 to an fpr16 reg, convert to fpr32 first.
This is a follow on commit to r[x] where we fix the other direction of copy.
For this case, after converting the source from gpr32 -> fpr32, we use a
subregister copy, which is essentially what EXTRACT_SUBREG does in SDAG land.
https://reviews.llvm.org/D43444
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325591 91177308-0d34-0410-b5e6-96231b3b80d8
(I had to re-generate the test and manually update to handle the r323922 MIR physical register sigil.
------------------------------------------------------------------------
r325463 | aemerson | 2018-02-18 18:10:49 +0100 (Sun, 18 Feb 2018) | 8 lines
[AArch64][GlobalISel] Fix an assert fail/miscompile when fp16 types are copied
to gpr register banks.
PR36345.
rdar://36478867
Differential Revision: https://reviews.llvm.org/D43310
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325586 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324576 | ctopper | 2018-02-08 08:45:55 +0100 (Thu, 08 Feb 2018) | 20 lines
[X86] Don't emit KTEST instructions unless only the Z flag is being used
Summary:
KTEST has weird flag behavior. The Z flag is set for all bits in the AND of the k-registers being 0, and the C flag is set for all bits being 1. All other flags are cleared.
We currently emit this instruction in EmitTEST and don't check the condition code. This can lead to strange things like using the S flag after a KTEST for a signed compare.
The domain reassignment pass can also transform TEST instructions into KTEST and is not protected against the flag usage either. For now I've disabled this part of the domain reassignment pass. I tried to comment out the checks in the mir test so that we could recover them later, but I couldn't figure out how to get that to work.
This patch moves the KTEST handling into LowerSETCC and now creates a ktest+x86setcc. I've chosen this approach because I'd like to add support for the C flag for all ones in a followup patch. To do that requires that I can rewrite the condition code going in the x86setcc to be different than the original SETCC condition code.
This fixes PR36182. I'll file a PR to fix domain reassignment once this goes in. Should this be merged to 6.0?
Reviewers: spatel, guyblank, RKSimon, zvi
Reviewed By: guyblank
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D42770
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325106 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r325049 | rnk | 2018-02-13 12:47:49 -0800 (Tue, 13 Feb 2018) | 17 lines
[X86] Use EDI for retpoline when no scratch regs are left
Summary:
Instead of solving the hard problem of how to pass the callee to the indirect
jump thunk without a register, just use a CSR. At a call boundary, there's
nothing stopping us from using a CSR to hold the callee as long as we save and
restore it in the prologue.
Also, add tests for this mregparm=3 case. I wrote execution tests for
__llvm_retpoline_push, but they never got committed as lit tests, either
because I never rewrote them or because they got lost in merge conflicts.
Reviewers: chandlerc, dwmw2
Subscribers: javed.absar, kristof.beyls, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D43214
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325084 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324645 | dwmw2 | 2018-02-08 12:06:05 -0800 (Thu, 08 Feb 2018) | 5 lines
[X86] Support 'V' register operand modifier
This allows the register name to be printed without the leading '%'.
This can be used for emitting calls to the retpoline thunks from inline
asm.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325083 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324449 | chandlerc | 2018-02-06 22:16:24 -0800 (Tue, 06 Feb 2018) | 15 lines
[x86/retpoline] Make the external thunk names exactly match the names
that happened to end up in GCC.
This is really unfortunate, as the names don't have much rhyme or reason
to them. Originally in the discussions it seemed fine to rely on aliases
to map different names to whatever external thunk code developers wished
to use but there are practical problems with that in the kernel it turns
out. And since we're discovering this practical problems late and since
GCC has already shipped a release with one set of names, we are forced,
yet again, to blindly match what is there.
Somewhat rushing this patch out for the Linux kernel folks to test and
so we can get it patched into our releases.
Differential Revision: https://reviews.llvm.org/D42998
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@325082 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324422 | efriedma | 2018-02-07 00:00:17 +0100 (Wed, 07 Feb 2018) | 16 lines
[LivePhysRegs] Fix handling of return instructions.
See D42509 for the original version of this.
Basically, there are two significant changes to behavior here:
- addLiveOuts always adds all pristine registers (even if a block has
no successors).
- addLiveOuts and addLiveOutsNoPristines always add all callee-saved
registers for return blocks (including conditional return blocks).
I cleaned up the functions a bit to make it clear these properties hold.
Differential Revision: https://reviews.llvm.org/D42655
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324466 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324039 | matze | 2018-02-02 01:08:19 +0100 (Fri, 02 Feb 2018) | 33 lines
SplitKit: Fix liveness recomputation in some remat cases.
Example situation:
```
BB0:
%0 = ...
use %0
; ...
condjump BB1
jmp BB2
BB1:
%0 = ... ; rematerialized def from above (from earlier split step)
jmp BB2
BB2:
; ...
use %0
```
%0 will have a live interval with 3 value numbers (for the BB0, BB1 and
BB2 parts). Now SplitKit tries and succeeds in rematerializing the value
number in BB2 (This only works because it is a secondary split so
SplitKit is can trace this back to a single original def).
We need to recompute all live ranges affected by a value number that we
rematerialize. The case that we missed before is that when the value
that is rematerialized is at a join (Phi VNI) then we also have to
recompute liveness for the predecessor VNIs.
rdar://35699130
Differential Revision: https://reviews.llvm.org/D42667
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324218 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r324002 | ctopper | 2018-02-01 21:48:50 +0100 (Thu, 01 Feb 2018) | 7 lines
[DAGCombiner] When folding (insert_subvector undef, (bitcast (extract_subvector N1, Idx)), Idx) -> (bitcast N1) make sure that N1 has the same total size as the original output
We were only checking the element count, but not the total width. This could cause illegal bitcasts to be created if for example the output was 512-bits, but N1 is 256 bits, and the extraction size was 128-bits.
Fixes PR36199
Differential Revision: https://reviews.llvm.org/D42809
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324216 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323643 | jdevlieghere | 2018-01-29 13:10:32 +0100 (Mon, 29 Jan 2018) | 16 lines
[Sparc] Account for bias in stack readjustment
Summary: This was broken long ago in D12208, which failed to account for
the fact that 64-bit SPARC uses a stack bias of 2047, and it is the
*unbiased* value which should be aligned, not the biased one. This was
seen to be an issue with Rust.
Patch by: jrtc27 (James Clarke)
Reviewers: jyknight, venkatra
Reviewed By: jyknight
Subscribers: jacob_hansen, JDevlieghere, fhahn, fedor.sergeev, llvm-commits
Differential Revision: https://reviews.llvm.org/D39425
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324090 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323781 | sdardis | 2018-01-30 17:24:10 +0100 (Tue, 30 Jan 2018) | 15 lines
[mips] Fix incorrect sign extension for fpowi libcall
PR36061 showed that during the expansion of ISD::FPOWI, that there
was an incorrect zero extension of the integer argument which for
MIPS64 would then give incorrect results. Address this with the
existing mechanism for correcting sign extensions.
This resolves PR36061.
Thanks to James Cowgill for reporting the issue!
Reviewers: atanasyan, hfinkel
Differential Revision: https://reviews.llvm.org/D42537
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324085 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323857 | rogfer01 | 2018-01-31 10:23:43 +0100 (Wed, 31 Jan 2018) | 19 lines
[ARM] Allow the scheduler to clone a node with glue to avoid a copy CPSR ↔ GPR.
In Thumb 1, with the new ADDCARRY / SUBCARRY the scheduler may need to do
copies CPSR ↔ GPR but not all Thumb1 targets implement them.
The schedule can attempt, before attempting a copy, to clone the instructions
but it does not currently do that for nodes with input glue. In this patch we
introduce a target-hook to let the hook decide if a glued machinenode is still
eligible for copying. In this case these are ARM::tADCS and ARM::tSBCS .
As a follow-up of this change we should actually implement the copies for the
Thumb1 targets that do implement them and restrict the hook to the targets that
can't really do such copy as these clones are not ideal.
This change fixes PR35836.
Differential Revision: https://reviews.llvm.org/D42051
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324082 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323915 | chandlerc | 2018-01-31 21:56:37 +0100 (Wed, 31 Jan 2018) | 17 lines
[x86] Make the retpoline thunk insertion a machine function pass.
Summary:
This removes the need for a machine module pass using some deeply
questionable hacks. This should address PR36123 which is a case where in
full LTO the memory usage of a machine module pass actually ended up
being significant.
We should revert this on trunk as soon as we understand and fix the
memory usage issue, but we should include this in any backports of
retpolines themselves.
Reviewers: echristo, MatzeB
Subscribers: sanjoy, mcrosier, mehdi_amini, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D42726
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324071 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323155 | chandlerc | 2018-01-22 23:05:25 +0100 (Mon, 22 Jan 2018) | 133 lines
Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre..
Summary:
First, we need to explain the core of the vulnerability. Note that this
is a very incomplete description, please see the Project Zero blog post
for details:
https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html
The basis for branch target injection is to direct speculative execution
of the processor to some "gadget" of executable code by poisoning the
prediction of indirect branches with the address of that gadget. The
gadget in turn contains an operation that provides a side channel for
reading data. Most commonly, this will look like a load of secret data
followed by a branch on the loaded value and then a load of some
predictable cache line. The attacker then uses timing of the processors
cache to determine which direction the branch took *in the speculative
execution*, and in turn what one bit of the loaded value was. Due to the
nature of these timing side channels and the branch predictor on Intel
processors, this allows an attacker to leak data only accessible to
a privileged domain (like the kernel) back into an unprivileged domain.
The goal is simple: avoid generating code which contains an indirect
branch that could have its prediction poisoned by an attacker. In many
cases, the compiler can simply use directed conditional branches and
a small search tree. LLVM already has support for lowering switches in
this way and the first step of this patch is to disable jump-table
lowering of switches and introduce a pass to rewrite explicit indirectbr
sequences into a switch over integers.
However, there is no fully general alternative to indirect calls. We
introduce a new construct we call a "retpoline" to implement indirect
calls in a non-speculatable way. It can be thought of loosely as
a trampoline for indirect calls which uses the RET instruction on x86.
Further, we arrange for a specific call->ret sequence which ensures the
processor predicts the return to go to a controlled, known location. The
retpoline then "smashes" the return address pushed onto the stack by the
call with the desired target of the original indirect call. The result
is a predicted return to the next instruction after a call (which can be
used to trap speculative execution within an infinite loop) and an
actual indirect branch to an arbitrary address.
On 64-bit x86 ABIs, this is especially easily done in the compiler by
using a guaranteed scratch register to pass the target into this device.
For 32-bit ABIs there isn't a guaranteed scratch register and so several
different retpoline variants are introduced to use a scratch register if
one is available in the calling convention and to otherwise use direct
stack push/pop sequences to pass the target address.
This "retpoline" mitigation is fully described in the following blog
post: https://support.google.com/faqs/answer/7625886
We also support a target feature that disables emission of the retpoline
thunk by the compiler to allow for custom thunks if users want them.
These are particularly useful in environments like kernels that
routinely do hot-patching on boot and want to hot-patch their thunk to
different code sequences. They can write this custom thunk and use
`-mretpoline-external-thunk` *in addition* to `-mretpoline`. In this
case, on x86-64 thu thunk names must be:
```
__llvm_external_retpoline_r11
```
or on 32-bit:
```
__llvm_external_retpoline_eax
__llvm_external_retpoline_ecx
__llvm_external_retpoline_edx
__llvm_external_retpoline_push
```
And the target of the retpoline is passed in the named register, or in
the case of the `push` suffix on the top of the stack via a `pushl`
instruction.
There is one other important source of indirect branches in x86 ELF
binaries: the PLT. These patches also include support for LLD to
generate PLT entries that perform a retpoline-style indirection.
The only other indirect branches remaining that we are aware of are from
precompiled runtimes (such as crt0.o and similar). The ones we have
found are not really attackable, and so we have not focused on them
here, but eventually these runtimes should also be replicated for
retpoline-ed configurations for completeness.
For kernels or other freestanding or fully static executables, the
compiler switch `-mretpoline` is sufficient to fully mitigate this
particular attack. For dynamic executables, you must compile *all*
libraries with `-mretpoline` and additionally link the dynamic
executable and all shared libraries with LLD and pass `-z retpolineplt`
(or use similar functionality from some other linker). We strongly
recommend also using `-z now` as non-lazy binding allows the
retpoline-mitigated PLT to be substantially smaller.
When manually apply similar transformations to `-mretpoline` to the
Linux kernel we observed very small performance hits to applications
running typical workloads, and relatively minor hits (approximately 2%)
even for extremely syscall-heavy applications. This is largely due to
the small number of indirect branches that occur in performance
sensitive paths of the kernel.
When using these patches on statically linked applications, especially
C++ applications, you should expect to see a much more dramatic
performance hit. For microbenchmarks that are switch, indirect-, or
virtual-call heavy we have seen overheads ranging from 10% to 50%.
However, real-world workloads exhibit substantially lower performance
impact. Notably, techniques such as PGO and ThinLTO dramatically reduce
the impact of hot indirect calls (by speculatively promoting them to
direct calls) and allow optimized search trees to be used to lower
switches. If you need to deploy these techniques in C++ applications, we
*strongly* recommend that you ensure all hot call targets are statically
linked (avoiding PLT indirection) and use both PGO and ThinLTO. Well
tuned servers using all of these techniques saw 5% - 10% overhead from
the use of retpoline.
We will add detailed documentation covering these components in
subsequent patches, but wanted to make the core functionality available
as soon as possible. Happy for more code review, but we'd really like to
get these patches landed and backported ASAP for obvious reasons. We're
planning to backport this to both 6.0 and 5.0 release streams and get
a 5.0 release with just this cherry picked ASAP for distros and vendors.
This patch is the work of a number of people over the past month: Eric, Reid,
Rui, and myself. I'm mailing it out as a single commit due to the time
sensitive nature of landing this and the need to backport it. Huge thanks to
everyone who helped out here, and everyone at Intel who helped out in
discussions about how to craft this. Also, credit goes to Paul Turner (at
Google, but not an LLVM contributor) for much of the underlying retpoline
design.
Reviewers: echristo, rnk, ruiu, craig.topper, DavidKreitzer
Subscribers: sanjoy, emaste, mcrosier, mgorny, mehdi_amini, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D41723
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@324067 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323706 | mareko | 2018-01-30 00:19:10 +0100 (Tue, 30 Jan 2018) | 15 lines
AMDGPU: Allow a SGPR for the conditional KILL operand
Patch by: Bas Nieuwenhuizen
Just use the _e64 variant if needed. This should be possible as per
def : Pat <
(int_amdgcn_kill (i1 (setcc f32:$src, InlineFPImm<f32>:$imm, cond:$cond))),
(SI_KILL_F32_COND_IMM_PSEUDO $src, (bitcast_fpimm_to_i32 $imm), (cond_as_i32imm $cond))
> ;
I don't think we can get an immediate for the other operand for which we
need the second 32-bit word.
https://reviews.llvm.org/D42302
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323772 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323355 | nha | 2018-01-24 19:02:05 +0100 (Wed, 24 Jan 2018) | 9 lines
Revert r321751, "StructurizeCFG: Fix broken backedge detection"
It causes regressions in various OpenGL test suites.
Keep the test cases introduced by r321751 as XFAIL, and add a test case
for the regression.
Change-Id: I90b4cc354f68cebe5fcef1f2422dc8fe1c6d3514
Bugzilla: https://bugs.llvm.org/show_bug.cgi?id=36015
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323749 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323710 | qcolombet | 2018-01-30 00:42:37 +0100 (Tue, 30 Jan 2018) | 13 lines
[RAFast] Don't dereference MBB::end
When RAFast sees liveins in on a basic block, it uses that information
to initialize the availability of the registers. The called
method uses an instruction as one of its argument and in the liveins
case, RAFast was dereferencing MBB::begin which can be MBB::end for
empty basic block.
Change the API of definePhysReg to use MachineBasicBlock::iterator
instead of MachineInstr so that we don't dereference an
invalid iterator while making the call.
rdar://problem/36952401
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323746 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323672 | ctopper | 2018-01-29 18:56:57 +0100 (Mon, 29 Jan 2018) | 5 lines
[X86] Don't create SHRUNKBLEND when the condition is used by the true or false operand of the vselect.
Fixes PR34592.
Differential Revision: https://reviews.llvm.org/D42628
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323743 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323582 | aemerson | 2018-01-27 08:07:20 +0100 (Sat, 27 Jan 2018) | 6 lines
[GlobalISel][Legalizer] Convert the FP constants to the right APFloat type for G_FCONSTANT.
We weren't converting the immediate ConstantFP during legalization, which caused
the wrong bit patterns to be emitted for half type FP constants.
Fixes PR36106.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323742 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323369 | aemerson | 2018-01-24 20:59:29 +0100 (Wed, 24 Jan 2018) | 4 lines
[GlobalISel] Don't fall back to FastISel.
Apparently checking the pass structure isn't enough to ensure that we don't fall
back to FastISel, as it's set up as part of the SelectionDAGISel.
------------------------------------------------------------------------
------------------------------------------------------------------------
r323371 | aemerson | 2018-01-24 21:35:37 +0100 (Wed, 24 Jan 2018) | 12 lines
[AArch64][GlobalISel] Fall back during AArch64 isel if we have a volatile load.
The tablegen imported patterns for sext(load(a)) don't check for single uses
of the load or delete the original after matching. As a result two loads are
left in the generated code. This particular issue will be fixed by adding
support for a G_SEXTLOAD opcode in future.
There are however other potential issues around this that wouldn't be fixed by
a G_SEXTLOAD, so until we have a proper solution we don't try to handle volatile
loads at all in the AArch64 selector.
Fixes/works around PR36018.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323434 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r322900 | mstorsjo | 2018-01-18 22:21:48 +0100 (Thu, 18 Jan 2018) | 6 lines
[test] Actually check the common parts in CodeGen/ARM/global-merge-external.ll. NFC.
Previously, these parts weren't ever checked. The label patterns
need to be extended to match successfully on macho.
Differential Revision: https://reviews.llvm.org/D42126
------------------------------------------------------------------------
------------------------------------------------------------------------
r323307 | mstorsjo | 2018-01-24 07:40:04 +0100 (Wed, 24 Jan 2018) | 6 lines
[GlobalMerge] Don't merge dllexport globals
Merging such globals loses the dllexport attribute. Add a test
to check that normal globals still are merged.
Differential Revision: https://reviews.llvm.org/D42127
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323337 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r323190 | rksimon | 2018-01-23 12:39:06 +0100 (Tue, 23 Jan 2018) | 5 lines
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - fix PSHUFB source/index operand ordering
As detailed in rL317463, PSHUFB (like most variable shuffle instructions) uses Op[0] for the source vector and Op[1] for the shuffle index vector, VPERMV works in reverse which is probably where the confusion comes from.
Differential Revision: https://reviews.llvm.org/D42380
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323335 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r322372 | nemanjai | 2018-01-12 15:58:41 +0100 (Fri, 12 Jan 2018) | 10 lines
[PowerPC] Zero-extend the compare operand for ATOMIC_CMP_SWAP
Part of the fix for https://bugs.llvm.org/show_bug.cgi?id=35812.
This patch ensures that the compare operand for the atomic compare and swap
is properly zero-extended to 32 bits if applicable.
A follow-up commit will fix the extension for the SETCC node generated when
expanding an ATOMIC_CMP_SWAP_WITH_SUCCESS. That will complete the bug fix.
Differential Revision: https://reviews.llvm.org/D41856
------------------------------------------------------------------------
------------------------------------------------------------------------
r322767 | efriedma | 2018-01-17 23:04:36 +0100 (Wed, 17 Jan 2018) | 12 lines
[LegalizeDAG] Fix ATOMIC_CMP_SWAP_WITH_SUCCESS legalization.
The code wasn't zero-extending correctly, so the comparison could
spuriously fail.
Adds some AArch64 tests to cover this case.
Inspired by D41791.
Differential Revision: https://reviews.llvm.org/D41798
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@323334 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r322644 | d0k | 2018-01-17 05:01:06 -0800 (Wed, 17 Jan 2018) | 7 lines
[X86] Don't mutate shuffle arguments after early-out for AVX512
The match* functions have the annoying behavior of modifying its inputs.
Save and restore the inputs, just in case the early out for AVX512 is
hit. This is still not great and its only a matter of time this kind of
bug happens again, but I couldn't come up with a better pattern without
rewriting significant chunks of this code. Fixes PR35977.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@322840 91177308-0d34-0410-b5e6-96231b3b80d8
