2018-06-30 04:20:17 +08:00
|
|
|
; Test alloca instrumentation.
|
2018-01-12 06:53:30 +08:00
|
|
|
;
|
2018-09-25 07:03:34 +08:00
|
|
|
; RUN: opt < %s -hwasan -hwasan-with-ifunc=1 -S | FileCheck %s --check-prefixes=CHECK,DYNAMIC-SHADOW,NO-UAR-TAGS
|
2018-06-30 04:20:17 +08:00
|
|
|
; RUN: opt < %s -hwasan -hwasan-mapping-offset=0 -S | FileCheck %s --check-prefixes=CHECK,ZERO-BASED-SHADOW,NO-UAR-TAGS
|
2018-09-25 07:03:34 +08:00
|
|
|
; RUN: opt < %s -hwasan -hwasan-with-ifunc=1 -hwasan-uar-retag-to-zero=0 -S | FileCheck %s --check-prefixes=CHECK,DYNAMIC-SHADOW,UAR-TAGS
|
2018-01-12 06:53:30 +08:00
|
|
|
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
target triple = "aarch64--linux-android"
|
|
|
|
|
|
|
|
declare void @use32(i32*)
|
|
|
|
|
|
|
|
define void @test_alloca() sanitize_hwaddress {
|
|
|
|
; CHECK-LABEL: @test_alloca(
|
|
|
|
; CHECK: %[[FP:[^ ]*]] = call i8* @llvm.frameaddress(i32 0)
|
|
|
|
; CHECK: %[[A:[^ ]*]] = ptrtoint i8* %[[FP]] to i64
|
|
|
|
; CHECK: %[[B:[^ ]*]] = lshr i64 %[[A]], 20
|
|
|
|
; CHECK: %[[BASE_TAG:[^ ]*]] = xor i64 %[[A]], %[[B]]
|
|
|
|
|
|
|
|
; CHECK: %[[X:[^ ]*]] = alloca i32, align 16
|
|
|
|
; CHECK: %[[X_TAG:[^ ]*]] = xor i64 %[[BASE_TAG]], 0
|
|
|
|
; CHECK: %[[X1:[^ ]*]] = ptrtoint i32* %[[X]] to i64
|
|
|
|
; CHECK: %[[C:[^ ]*]] = shl i64 %[[X_TAG]], 56
|
|
|
|
; CHECK: %[[D:[^ ]*]] = or i64 %[[X1]], %[[C]]
|
|
|
|
; CHECK: %[[X_HWASAN:[^ ]*]] = inttoptr i64 %[[D]] to i32*
|
|
|
|
|
|
|
|
; CHECK: %[[X_TAG2:[^ ]*]] = trunc i64 %[[X_TAG]] to i8
|
|
|
|
; CHECK: %[[E:[^ ]*]] = ptrtoint i32* %[[X]] to i64
|
|
|
|
; CHECK: %[[F:[^ ]*]] = lshr i64 %[[E]], 4
|
hwasan: Move memory access checks into small outlined functions on aarch64.
Each hwasan check requires emitting a small piece of code like this:
https://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html#memory-accesses
The problem with this is that these code blocks typically bloat code
size significantly.
An obvious solution is to outline these blocks of code. In fact, this
has already been implemented under the -hwasan-instrument-with-calls
flag. However, as currently implemented this has a number of problems:
- The functions use the same calling convention as regular C functions.
This means that the backend must spill all temporary registers as
required by the platform's C calling convention, even though the
check only needs two registers on the hot path.
- The functions take the address to be checked in a fixed register,
which increases register pressure.
Both of these factors can diminish the code size effect and increase
the performance hit of -hwasan-instrument-with-calls.
The solution that this patch implements is to involve the aarch64
backend in outlining the checks. An intrinsic and pseudo-instruction
are created to represent a hwasan check. The pseudo-instruction
is register allocated like any other instruction, and we allow the
register allocator to select almost any register for the address to
check. A particular combination of (register selection, type of check)
triggers the creation in the backend of a function to handle the check
for specifically that pair. The resulting functions are deduplicated by
the linker. The pseudo-instruction (really the function) is specified
to preserve all registers except for the registers that the AAPCS
specifies may be clobbered by a call.
To measure the code size and performance effect of this change, I
took a number of measurements using Chromium for Android on aarch64,
comparing a browser with inlined checks (the baseline) against a
browser with outlined checks.
Code size: Size of .text decreases from 243897420 to 171619972 bytes,
or a 30% decrease.
Performance: Using Chromium's blink_perf.layout microbenchmarks I
measured a median performance regression of 6.24%.
The fact that a perf/size tradeoff is evident here suggests that
we might want to make the new behaviour conditional on -Os/-Oz.
But for now I've enabled it unconditionally, my reasoning being that
hwasan users typically expect a relatively large perf hit, and ~6%
isn't really adding much. We may want to revisit this decision in
the future, though.
I also tried experimenting with varying the number of registers
selectable by the hwasan check pseudo-instruction (which would result
in fewer variants being created), on the hypothesis that creating
fewer variants of the function would expose another perf/size tradeoff
by reducing icache pressure from the check functions at the cost of
register pressure. Although I did observe a code size increase with
fewer registers, I did not observe a strong correlation between the
number of registers and the performance of the resulting browser on the
microbenchmarks, so I conclude that we might as well use ~all registers
to get the maximum code size improvement. My results are below:
Regs | .text size | Perf hit
-----+------------+---------
~all | 171619972 | 6.24%
16 | 171765192 | 7.03%
8 | 172917788 | 5.82%
4 | 177054016 | 6.89%
Differential Revision: https://reviews.llvm.org/D56954
llvm-svn: 351920
2019-01-23 10:20:10 +08:00
|
|
|
; DYNAMIC-SHADOW: %[[X_SHADOW:[^ ]*]] = getelementptr i8, i8* %.hwasan.shadow, i64 %[[F]]
|
2018-04-21 04:04:04 +08:00
|
|
|
; ZERO-BASED-SHADOW: %[[X_SHADOW:[^ ]*]] = inttoptr i64 %[[F]] to i8*
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %[[X_SHADOW]], i8 %[[X_TAG2]], i64 1, i1 false)
|
2018-01-12 06:53:30 +08:00
|
|
|
; CHECK: call void @use32(i32* nonnull %[[X_HWASAN]])
|
|
|
|
|
2018-06-30 04:20:17 +08:00
|
|
|
; UAR-TAGS: %[[BASE_TAG_COMPL:[^ ]*]] = xor i64 %[[BASE_TAG]], 255
|
|
|
|
; UAR-TAGS: %[[X_TAG_UAR:[^ ]*]] = trunc i64 %[[BASE_TAG_COMPL]] to i8
|
2018-01-12 06:53:30 +08:00
|
|
|
; CHECK: %[[E2:[^ ]*]] = ptrtoint i32* %[[X]] to i64
|
|
|
|
; CHECK: %[[F2:[^ ]*]] = lshr i64 %[[E2]], 4
|
hwasan: Move memory access checks into small outlined functions on aarch64.
Each hwasan check requires emitting a small piece of code like this:
https://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html#memory-accesses
The problem with this is that these code blocks typically bloat code
size significantly.
An obvious solution is to outline these blocks of code. In fact, this
has already been implemented under the -hwasan-instrument-with-calls
flag. However, as currently implemented this has a number of problems:
- The functions use the same calling convention as regular C functions.
This means that the backend must spill all temporary registers as
required by the platform's C calling convention, even though the
check only needs two registers on the hot path.
- The functions take the address to be checked in a fixed register,
which increases register pressure.
Both of these factors can diminish the code size effect and increase
the performance hit of -hwasan-instrument-with-calls.
The solution that this patch implements is to involve the aarch64
backend in outlining the checks. An intrinsic and pseudo-instruction
are created to represent a hwasan check. The pseudo-instruction
is register allocated like any other instruction, and we allow the
register allocator to select almost any register for the address to
check. A particular combination of (register selection, type of check)
triggers the creation in the backend of a function to handle the check
for specifically that pair. The resulting functions are deduplicated by
the linker. The pseudo-instruction (really the function) is specified
to preserve all registers except for the registers that the AAPCS
specifies may be clobbered by a call.
To measure the code size and performance effect of this change, I
took a number of measurements using Chromium for Android on aarch64,
comparing a browser with inlined checks (the baseline) against a
browser with outlined checks.
Code size: Size of .text decreases from 243897420 to 171619972 bytes,
or a 30% decrease.
Performance: Using Chromium's blink_perf.layout microbenchmarks I
measured a median performance regression of 6.24%.
The fact that a perf/size tradeoff is evident here suggests that
we might want to make the new behaviour conditional on -Os/-Oz.
But for now I've enabled it unconditionally, my reasoning being that
hwasan users typically expect a relatively large perf hit, and ~6%
isn't really adding much. We may want to revisit this decision in
the future, though.
I also tried experimenting with varying the number of registers
selectable by the hwasan check pseudo-instruction (which would result
in fewer variants being created), on the hypothesis that creating
fewer variants of the function would expose another perf/size tradeoff
by reducing icache pressure from the check functions at the cost of
register pressure. Although I did observe a code size increase with
fewer registers, I did not observe a strong correlation between the
number of registers and the performance of the resulting browser on the
microbenchmarks, so I conclude that we might as well use ~all registers
to get the maximum code size improvement. My results are below:
Regs | .text size | Perf hit
-----+------------+---------
~all | 171619972 | 6.24%
16 | 171765192 | 7.03%
8 | 172917788 | 5.82%
4 | 177054016 | 6.89%
Differential Revision: https://reviews.llvm.org/D56954
llvm-svn: 351920
2019-01-23 10:20:10 +08:00
|
|
|
; DYNAMIC-SHADOW: %[[X_SHADOW2:[^ ]*]] = getelementptr i8, i8* %.hwasan.shadow, i64 %[[F2]]
|
2018-04-21 04:04:04 +08:00
|
|
|
; ZERO-BASED-SHADOW: %[[X_SHADOW2:[^ ]*]] = inttoptr i64 %[[F2]] to i8*
|
2018-06-30 04:20:17 +08:00
|
|
|
; NO-UAR-TAGS: call void @llvm.memset.p0i8.i64(i8* align 1 %[[X_SHADOW2]], i8 0, i64 1, i1 false)
|
|
|
|
; UAR-TAGS: call void @llvm.memset.p0i8.i64(i8* align 1 %[[X_SHADOW2]], i8 %[[X_TAG_UAR]], i64 1, i1 false)
|
2018-01-12 06:53:30 +08:00
|
|
|
; CHECK: ret void
|
|
|
|
|
|
|
|
|
|
|
|
entry:
|
|
|
|
%x = alloca i32, align 4
|
|
|
|
call void @use32(i32* nonnull %x)
|
|
|
|
ret void
|
|
|
|
}
|