thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-19 16:20:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into time_buckets_impl

Browse Source
This commit is contained in:
Yarik Briukhovetskyi 2024-05-23 13:39:35 +02:00 committed by GitHub
commit 872818b363
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2874 changed files with 149134 additions and 269730 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.clang-format
View File

@ -89,7 +89,7 @@ PenaltyBreakFirstLessLess: 120
PenaltyBreakString: 1000
PenaltyExcessCharacter: 1000000
PenaltyReturnTypeOnItsOwnLine: 60
RemoveBracesLLVM: true
RemoveBracesLLVM: false
SpaceAfterCStyleCast: false
SpaceBeforeAssignmentOperators: true
SpaceBeforeParens: ControlStatements

16
.clang-tidy
View File

@ -22,6 +22,7 @@ Checks: [
'-bugprone-exception-escape',
'-bugprone-forward-declaration-namespace',
'-bugprone-implicit-widening-of-multiplication-result',
'-bugprone-multi-level-implicit-pointer-conversion',
'-bugprone-narrowing-conversions',
'-bugprone-not-null-terminated-result',
'-bugprone-reserved-identifier', # useful but too slow, TODO retry when https://reviews.llvm.org/rG1c282052624f9d0bd273bde0b47b30c96699c6c7 is merged
@ -98,6 +99,7 @@ Checks: [
'-modernize-use-nodiscard',
'-modernize-use-trailing-return-type',
'-performance-enum-size',
'-performance-inefficient-string-concatenation',
'-performance-no-int-to-ptr',
'-performance-avoid-endl',
@ -105,6 +107,7 @@ Checks: [
'-portability-simd-intrinsics',
'-readability-avoid-nested-conditional-operator',
'-readability-avoid-unconditional-preprocessor-if',
'-readability-braces-around-statements',
'-readability-convert-member-functions-to-static',
@ -118,12 +121,23 @@ Checks: [
'-readability-magic-numbers',
'-readability-named-parameter',
'-readability-redundant-declaration',
'-readability-redundant-inline-specifier',
'-readability-redundant-member-init', # Useful but triggers another problem. Imagine a struct S with multiple String members. Structs are often instantiated via designated
# initializer S s{.s1 = [...], .s2 = [...], [...]}. In this case, compiler warning `missing-field-initializers` requires to specify all members which are not in-struct
# initialized (example: s1 in struct S { String s1; String s2{};}; is not in-struct initialized, therefore it must be specified at instantiation time). As explicitly
# specifying all members is tedious for large structs, `missing-field-initializers` makes programmers initialize as many members as possible in-struct. Clang-tidy
# warning `readability-redundant-member-init` does the opposite thing, both are not compatible with each other.
'-readability-simplify-boolean-expr',
'-readability-suspicious-call-argument',
'-readability-uppercase-literal-suffix',
'-readability-use-anyofallof',
'-zircon-*'
'-zircon-*',
# This is a good check, but clang-tidy crashes, see https://github.com/llvm/llvm-project/issues/91872
'-modernize-use-constraints',
# https://github.com/abseil/abseil-cpp/issues/1667
'-clang-analyzer-optin.core.EnumCastOutOfRange'
]
WarningsAsErrors: '*'

15
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -41,24 +41,26 @@ At a minimum, the following information should be added (but add more as needed)
> Information about CI checks: https://clickhouse.com/docs/en/development/continuous-integration/
---
### Modify your CI run:
<details>
<summary>CI Settings</summary>
**NOTE:** If your merge the PR with modified CI you **MUST KNOW** what you are doing
**NOTE:** Checked options will be applied if set before CI RunConfig/PrepareRunConfig step
#### Include tests (required builds will be added automatically):
- [ ] <!---ci_include_fast--> Fast test
#### Run these jobs only (required builds will be added automatically):
- [ ] <!---ci_include_integration--> Integration Tests
- [ ] <!---ci_include_stateless--> Stateless tests
- [ ] <!---ci_include_stateful--> Stateful tests
- [ ] <!---ci_include_unit--> Unit tests
- [ ] <!---ci_include_performance--> Performance tests
- [ ] <!---ci_include_aarch64--> All with aarch64
- [ ] <!---ci_include_asan--> All with ASAN
- [ ] <!---ci_include_tsan--> All with TSAN
- [ ] <!---ci_include_analyzer--> All with Analyzer
- [ ] <!---ci_include_azure --> All with Azure
- [ ] <!---ci_include_KEYWORD--> Add your option here
#### Exclude tests:
#### Deny these jobs:
- [ ] <!---ci_exclude_fast--> Fast test
- [ ] <!---ci_exclude_integration--> Integration Tests
- [ ] <!---ci_exclude_stateless--> Stateless tests
@ -70,7 +72,6 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] <!---ci_exclude_ubsan--> All with UBSAN
- [ ] <!---ci_exclude_coverage--> All with Coverage
- [ ] <!---ci_exclude_aarch64--> All with Aarch64
- [ ] <!---ci_exclude_KEYWORD--> Add your option here
#### Extra options:
- [ ] <!---do_not_test--> do not test (only style check)
@ -82,3 +83,5 @@ At a minimum, the following information should be added (but add more as needed)
- [ ] <!---batch_1--> 2
- [ ] <!---batch_2--> 3
- [ ] <!---batch_3--> 4
</details>

7
.github/actions/common_setup/action.yml vendored
View File

@ -28,3 +28,10 @@ runs:
run: |
# to remove every leftovers
sudo rm -fr "$TEMP_PATH" && mkdir -p "$TEMP_PATH"
- name: Tune vm.mmap_rnd_bits for sanitizers
shell: bash
run: |
sudo sysctl vm.mmap_rnd_bits
# https://github.com/google/sanitizers/issues/856
echo "Tune vm.mmap_rnd_bits for sanitizers"
sudo sysctl vm.mmap_rnd_bits=28

6
.github/workflows/backport_branches.yml vendored
View File

@ -9,6 +9,12 @@ on: # yamllint disable-line rule:truthy
push:
branches:
- 'backport/**'
# Cancel the previous wf run in PRs.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]

19
.github/workflows/cancel.yml vendored
View File

@ -1,19 +0,0 @@
name: Cancel
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
workflow_run:
workflows: ["PullRequestCI", "ReleaseBranchCI", "DocsCheck", "BackportPR"]
types:
- requested
jobs:
cancel:
runs-on: [self-hosted, style-checker]
steps:
- uses: styfle/cancel-workflow-action@0.9.1
with:
all_but_latest: true
workflow_id: ${{ github.event.workflow.id }}

11
.github/workflows/debug.yml vendored
View File

@ -1,11 +0,0 @@
# The CI for each commit, prints envs and content of GITHUB_EVENT_PATH
name: Debug
'on':
[push, pull_request, pull_request_review, release, workflow_dispatch, workflow_call]
jobs:
DebugInfo:
runs-on: ubuntu-latest
steps:
- uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a

52
.github/workflows/master.yml vendored
View File

@ -16,13 +16,17 @@ jobs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Merge sync PR
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 sync_pr.py --merge || :
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
@ -55,16 +59,17 @@ jobs:
uses: ./.github/workflows/reusable_docker.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Style check
runner_type: style-checker
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 style_check.py --no-push
# Tested in MQ
# StyleCheck:
# needs: [RunConfig, BuildDockers]
# if: ${{ !failure() && !cancelled() }}
# uses: ./.github/workflows/reusable_test.yml
# with:
# test_name: Style check
# runner_type: style-checker
# data: ${{ needs.RunConfig.outputs.data }}
# run_command: |
# python3 style_check.py --no-push
CompatibilityCheckX86:
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
@ -242,6 +247,14 @@ jobs:
build_name: binary_s390x
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
BuilderBinLoongarch64:
needs: [RunConfig, BuilderDebRelease]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_build.yml
with:
build_name: binary_loongarch64
data: ${{ needs.RunConfig.outputs.data }}
checkout_depth: 0
############################################################################################
##################################### Docker images #######################################
############################################################################################
@ -293,6 +306,7 @@ jobs:
- BuilderBinPPC64
- BuilderBinRISCV64
- BuilderBinS390X
- BuilderBinLoongarch64
- BuilderBinAmd64Compat
- BuilderBinAarch64V80Compat
- BuilderBinClangTidy
@ -442,6 +456,14 @@ jobs:
test_name: Stateless tests (debug)
runner_type: func-tester
data: ${{ needs.RunConfig.outputs.data }}
FunctionalStatelessTestAsanAzure:
needs: [RunConfig, BuilderDebAsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stateless tests (azure, asan)
runner_type: func-tester
data: ${{ needs.RunConfig.outputs.data }}
##############################################################################################
############################ FUNCTIONAl STATEFUL TESTS #######################################
##############################################################################################
@ -592,6 +614,14 @@ jobs:
test_name: Stress test (tsan)
runner_type: stress-tester
data: ${{ needs.RunConfig.outputs.data }}
StressTestTsanAzure:
needs: [RunConfig, BuilderDebTsan]
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Stress test (azure, tsan)
runner_type: stress-tester
data: ${{ needs.RunConfig.outputs.data }}
StressTestMsan:
needs: [RunConfig, BuilderDebMsan]
if: ${{ !failure() && !cancelled() }}

99
.github/workflows/merge_queue.yml vendored Normal file
View File

@ -0,0 +1,99 @@
# yamllint disable rule:comments-indentation
name: MergeQueueCI
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
merge_group:
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true # to ensure correct digests
fetch-depth: 0 # to get version
filter: tree:0
- name: Cancel PR workflow
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --cancel-previous-run
- name: Python unit tests
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
echo "Testing the main ci directory"
python3 -m unittest discover -s . -p 'test_*.py'
for dir in *_lambda/; do
echo "Testing $dir"
python3 -m unittest discover -s "$dir" -p 'test_*.py'
done
- name: PrepareRunConfig
id: runconfig
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --configure --outfile ${{ runner.temp }}/ci_run_data.json
echo "::group::CI configuration"
python3 -m json.tool ${{ runner.temp }}/ci_run_data.json
echo "::endgroup::"
{
echo 'CI_DATA<<EOF'
cat ${{ runner.temp }}/ci_run_data.json
echo 'EOF'
} >> "$GITHUB_OUTPUT"
BuildDockers:
needs: [RunConfig]
if: ${{ !failure() && !cancelled() && toJson(fromJson(needs.RunConfig.outputs.data).docker_data.missing_multi) != '[]' }}
uses: ./.github/workflows/reusable_docker.yml
with:
data: ${{ needs.RunConfig.outputs.data }}
StyleCheck:
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Style check')}}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Style check
runner_type: style-checker
run_command: |
python3 style_check.py
data: ${{ needs.RunConfig.outputs.data }}
secrets:
secret_envs: |
ROBOT_CLICKHOUSE_SSH_KEY<<RCSK
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
FastTest:
needs: [RunConfig, BuildDockers]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
uses: ./.github/workflows/reusable_test.yml
with:
test_name: Fast test
runner_type: builder
data: ${{ needs.RunConfig.outputs.data }}
run_command: |
python3 fast_test_check.py
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
- name: Check sync status
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 sync_pr.py --status
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py ${{ (contains(needs.*.result, 'failure') && github.event_name == 'merge_group') && '--pipeline-failure' || '' }}

5
.github/workflows/nightly.yml vendored
View File

@ -10,14 +10,13 @@ env:
workflow_dispatch:
jobs:
Debug:
# The task for having a preserved ENV and event.json for later investigation
uses: ./.github/workflows/debug.yml
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
outputs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:

63
.github/workflows/pull_request.yml vendored
View File

@ -6,7 +6,6 @@ env:
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
merge_group:
pull_request:
types:
- synchronize
@ -15,6 +14,11 @@ on: # yamllint disable-line rule:truthy
branches:
- master
# Cancel the previous wf run in PRs.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
RunConfig:
runs-on: [self-hosted, style-checker-aarch64]
@ -22,7 +26,7 @@ jobs:
data: ${{ steps.runconfig.outputs.CI_DATA }}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
@ -30,7 +34,6 @@ jobs:
fetch-depth: 0 # to get version
filter: tree:0
- name: Labels check
if: ${{ github.event_name != 'merge_group' }}
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 run_check.py
@ -58,7 +61,6 @@ jobs:
echo 'EOF'
} >> "$GITHUB_OUTPUT"
- name: Re-create GH statuses for skipped jobs if any
if: ${{ github.event_name != 'merge_group' }}
run: |
python3 "$GITHUB_WORKSPACE/tests/ci/ci.py" --infile ${{ runner.temp }}/ci_run_data.json --update-gh-statuses
BuildDockers:
@ -83,7 +85,7 @@ jobs:
${{secrets.ROBOT_CLICKHOUSE_SSH_KEY}}
RCSK
FastTest:
needs: [RunConfig, StyleCheck]
needs: [RunConfig, BuildDockers, StyleCheck]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'Fast test') }}
uses: ./.github/workflows/reusable_test.yml
with:
@ -97,7 +99,7 @@ jobs:
# for main CI chain
#
Builds_1:
needs: [RunConfig, FastTest]
needs: [RunConfig, StyleCheck, FastTest]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Builds_1') }}
# using callable wf (reusable_stage.yml) allows to group all nested jobs under a tab
uses: ./.github/workflows/reusable_build_stage.yml
@ -128,15 +130,21 @@ jobs:
with:
stage: Tests_2
data: ${{ needs.RunConfig.outputs.data }}
# stage for jobs that do not prohibit merge
Tests_3:
needs: [RunConfig, Tests_1, Tests_2]
if: ${{ !failure() && !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).stages_data.stages_to_do, 'Tests_3') }}
uses: ./.github/workflows/reusable_test_stage.yml
with:
stage: Tests_3
data: ${{ needs.RunConfig.outputs.data }}
################################# Reports #################################
# Reports should by run even if Builds_1/2 fail, so put them separatly in wf (not in Tests_1/2)
# Reports should by run even if Builds_1/2 fail, so put them separately in wf (not in Tests_1/2)
Builds_1_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
needs:
- RunConfig
- Builds_1
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse build check') }}
needs: [RunConfig, StyleCheck, Builds_1]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse build check
@ -144,30 +152,49 @@ jobs:
data: ${{ needs.RunConfig.outputs.data }}
Builds_2_Report:
# run report check for failed builds to indicate the CI error
if: ${{ !cancelled() && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
needs:
- RunConfig
- Builds_2
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' && contains(fromJson(needs.RunConfig.outputs.data).jobs_data.jobs_to_do, 'ClickHouse special build check') }}
needs: [RunConfig, StyleCheck, Builds_2]
uses: ./.github/workflows/reusable_test.yml
with:
test_name: ClickHouse special build check
runner_type: style-checker-aarch64
data: ${{ needs.RunConfig.outputs.data }}
CheckReadyForMerge:
if: ${{ !cancelled() && needs.StyleCheck.result == 'success' }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2]
runs-on: [self-hosted, style-checker-aarch64]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
filter: tree:0
- name: Check and set merge status
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 merge_pr.py --set-ci-status --wf-status ${{ contains(needs.*.result, 'failure') && 'failure' || 'success' }}
################################# Stage Final #################################
#
FinishCheck:
if: ${{ !failure() && !cancelled() && github.event_name != 'merge_group' }}
needs: [Tests_1, Tests_2]
if: ${{ !failure() && !cancelled() }}
needs: [RunConfig, BuildDockers, StyleCheck, FastTest, Builds_1, Builds_2, Builds_1_Report, Builds_2_Report, Tests_1, Tests_2, Tests_3]
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
filter: tree:0
- name: Finish label
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 finish_check.py
python3 merge_pr.py --check-approved
# FIXME: merge on approval does not work with MQ. Could be fixed by using defaul GH's automerge after some corrections in Mergeable Check status
# - name: Auto merge if approved
# if: ${{ github.event_name != 'merge_group' }}
# run: |
# cd "$GITHUB_WORKSPACE/tests/ci"
# python3 merge_pr.py --check-approved
#############################################################################################

23
.github/workflows/pull_request_approved.yml vendored
View File

@ -1,23 +0,0 @@
name: PullRequestApprovedCI
env:
# Force the stdout and stderr streams to be unbuffered
PYTHONUNBUFFERED: 1
on: # yamllint disable-line rule:truthy
pull_request_review:
types:
- submitted
jobs:
MergeOnApproval:
runs-on: [self-hosted, style-checker]
steps:
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:
clear-repository: true
- name: Merge approved PR
run: |
cd "$GITHUB_WORKSPACE/tests/ci"
python3 merge_pr.py --check-approved

2
.github/workflows/reusable_simple_job.yml vendored
View File

@ -63,7 +63,7 @@ jobs:
GITHUB_JOB_OVERRIDDEN: ${{inputs.test_name}}
steps:
- name: DebugInfo
uses: hmarr/debug-action@a701ed95a46e6f2fb0df25e1a558c16356fae35a
uses: hmarr/debug-action@f7318c783045ac39ed9bb497e22ce835fdafbfe6
- name: Check out repository code
uses: ClickHouse/checkout@v1
with:

2
.gitmessage
View File

@ -16,7 +16,7 @@
#ci_set_reduced
#ci_set_arm
#ci_set_integration
#ci_set_analyzer
#ci_set_old_analyzer
## To run specified job in CI:
#job_<JOB NAME>

23
.gitmodules vendored
View File

@ -6,7 +6,7 @@
url = https://github.com/facebook/zstd
[submodule "contrib/lz4"]
path = contrib/lz4
url = https://github.com/ClickHouse/lz4
url = https://github.com/lz4/lz4
[submodule "contrib/librdkafka"]
path = contrib/librdkafka
url = https://github.com/ClickHouse/librdkafka
@ -22,9 +22,6 @@
[submodule "contrib/capnproto"]
path = contrib/capnproto
url = https://github.com/ClickHouse/capnproto
[submodule "contrib/double-conversion"]
path = contrib/double-conversion
url = https://github.com/google/double-conversion
[submodule "contrib/re2"]
path = contrib/re2
url = https://github.com/google/re2
@ -176,9 +173,6 @@
[submodule "contrib/libpq"]
path = contrib/libpq
url = https://github.com/ClickHouse/libpq
[submodule "contrib/boringssl"]
path = contrib/boringssl
url = https://github.com/ClickHouse/boringssl
[submodule "contrib/NuRaft"]
path = contrib/NuRaft
url = https://github.com/ClickHouse/NuRaft
@ -278,9 +272,6 @@
[submodule "contrib/crc32-s390x"]
path = contrib/crc32-s390x
url = https://github.com/linux-on-ibm-z/crc32-s390x
[submodule "contrib/openssl"]
path = contrib/openssl
url = https://github.com/openssl/openssl
[submodule "contrib/google-benchmark"]
path = contrib/google-benchmark
url = https://github.com/google/benchmark
@ -326,6 +317,9 @@
[submodule "contrib/crc32-vpmsum"]
path = contrib/crc32-vpmsum
url = https://github.com/antonblanchard/crc32-vpmsum.git
[submodule "contrib/expected"]
path = contrib/expected
url = https://github.com/TartanLlama/expected
[submodule "contrib/liburing"]
path = contrib/liburing
url = https://github.com/axboe/liburing
@ -369,3 +363,12 @@
[submodule "contrib/idna"]
path = contrib/idna
url = https://github.com/ada-url/idna.git
[submodule "contrib/rust_vendor"]
path = contrib/rust_vendor
url = https://github.com/ClickHouse/rust_vendor.git
[submodule "contrib/openssl"]
path = contrib/openssl
url = https://github.com/ClickHouse/openssl.git
[submodule "contrib/double-conversion"]
path = contrib/double-conversion
url = https://github.com/ClickHouse/double-conversion.git

171
CHANGELOG.md
View File

@ -1,4 +1,5 @@
### Table of Contents
**[ClickHouse release v24.4, 2024-04-30](#244)**<br/>
**[ClickHouse release v24.3 LTS, 2024-03-26](#243)**<br/>
**[ClickHouse release v24.2, 2024-02-29](#242)**<br/>
**[ClickHouse release v24.1, 2024-01-30](#241)**<br/>
@ -6,6 +7,167 @@
# 2024 Changelog
### <a id="244"></a> ClickHouse release 24.4, 2024-04-30
#### Upgrade Notes
* `clickhouse-odbc-bridge` and `clickhouse-library-bridge` are now separate packages. This closes [#61677](https://github.com/ClickHouse/ClickHouse/issues/61677). [#62114](https://github.com/ClickHouse/ClickHouse/pull/62114) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Don't allow to set max_parallel_replicas (for the experimental parallel reading from replicas) to `0` as it doesn't make sense. Closes [#60140](https://github.com/ClickHouse/ClickHouse/issues/60140). [#61201](https://github.com/ClickHouse/ClickHouse/pull/61201) ([Kruglov Pavel](https://github.com/Avogar)).
* Remove support for `INSERT WATCH` query (part of the deprecated `LIVE VIEW` feature). [#62382](https://github.com/ClickHouse/ClickHouse/pull/62382) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Removed the `optimize_monotonous_functions_in_order_by` setting. [#63004](https://github.com/ClickHouse/ClickHouse/pull/63004) ([Raúl Marín](https://github.com/Algunenano)).
* Remove experimental tag from the `Replicated` database engine. Now it is in Beta stage. [#62937](https://github.com/ClickHouse/ClickHouse/pull/62937) ([Justin de Guzman](https://github.com/justindeguzman)).
#### New Feature
* Support recursive CTEs. [#62074](https://github.com/ClickHouse/ClickHouse/pull/62074) ([Maksim Kita](https://github.com/kitaisreal)).
* Support `QUALIFY` clause. Closes [#47819](https://github.com/ClickHouse/ClickHouse/issues/47819). [#62619](https://github.com/ClickHouse/ClickHouse/pull/62619) ([Maksim Kita](https://github.com/kitaisreal)).
* Table engines are grantable now, and it won't affect existing users behavior. [#60117](https://github.com/ClickHouse/ClickHouse/pull/60117) ([jsc0218](https://github.com/jsc0218)).
* Added a rewritable S3 disk which supports INSERT operations and does not require locally stored metadata. [#61116](https://github.com/ClickHouse/ClickHouse/pull/61116) ([Julia Kartseva](https://github.com/jkartseva)). The main use case is for system tables.
* The syntax highlighting while typing in the client will work on the syntax level (previously, it worked on the lexer level). [#62123](https://github.com/ClickHouse/ClickHouse/pull/62123) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Supports dropping multiple tables at the same time like `DROP TABLE a, b, c`;. [#58705](https://github.com/ClickHouse/ClickHouse/pull/58705) ([zhongyuankai](https://github.com/zhongyuankai)).
* Modifying memory table settings through `ALTER MODIFY SETTING` is now supported. Example: `ALTER TABLE memory MODIFY SETTING min_rows_to_keep = 100, max_rows_to_keep = 1000;`. [#62039](https://github.com/ClickHouse/ClickHouse/pull/62039) ([zhongyuankai](https://github.com/zhongyuankai)).
* Added `role` query parameter to the HTTP interface. It works similarly to `SET ROLE x`, applying the role before the statement is executed. This allows for overcoming the limitation of the HTTP interface, as multiple statements are not allowed, and it is not possible to send both `SET ROLE x` and the statement itself at the same time. It is possible to set multiple roles that way, e.g., `?role=x&role=y`, which will be an equivalent of `SET ROLE x, y`. [#62669](https://github.com/ClickHouse/ClickHouse/pull/62669) ([Serge Klochkov](https://github.com/slvrtrn)).
* Add `SYSTEM UNLOAD PRIMARY KEY` to free up memory usage for a table's primary key. [#62738](https://github.com/ClickHouse/ClickHouse/pull/62738) ([Pablo Marcos](https://github.com/pamarcos)).
* Added `value1`, `value2`, ..., `value10` columns to `system.text_log`. These columns contain values that were used to format the message. [#59619](https://github.com/ClickHouse/ClickHouse/pull/59619) ([Alexey Katsman](https://github.com/alexkats)).
* Added persistent virtual column `_block_offset` which stores original number of row in block that was assigned at insert. Persistence of column `_block_offset` can be enabled by the MergeTree setting `enable_block_offset_column`. Added virtual column`_part_data_version` which contains either min block number or mutation version of part. Persistent virtual column `_block_number` is not considered experimental anymore. [#60676](https://github.com/ClickHouse/ClickHouse/pull/60676) ([Anton Popov](https://github.com/CurtizJ)).
* Add a setting `input_format_json_throw_on_bad_escape_sequence`, disabling it allows saving bad escape sequences in JSON input formats. [#61889](https://github.com/ClickHouse/ClickHouse/pull/61889) ([Kruglov Pavel](https://github.com/Avogar)).
#### Performance Improvement
* JOIN filter push down improvements using equivalent sets. [#61216](https://github.com/ClickHouse/ClickHouse/pull/61216) ([Maksim Kita](https://github.com/kitaisreal)).
* Convert OUTER JOIN to INNER JOIN optimization if the filter after JOIN always filters default values. Optimization can be controlled with setting `query_plan_convert_outer_join_to_inner_join`, enabled by default. [#62907](https://github.com/ClickHouse/ClickHouse/pull/62907) ([Maksim Kita](https://github.com/kitaisreal)).
* Improvement for AWS S3. Client has to send header 'Keep-Alive: timeout=X' to the server. If a client receives a response from the server with that header, client has to use the value from the server. Also for a client it is better not to use a connection which is nearly expired in order to avoid connection close race. [#62249](https://github.com/ClickHouse/ClickHouse/pull/62249) ([Sema Checherinda](https://github.com/CheSema)).
* Reduce overhead of the mutations for SELECTs (v2). [#60856](https://github.com/ClickHouse/ClickHouse/pull/60856) ([Azat Khuzhin](https://github.com/azat)).
* More frequently invoked functions in PODArray are now force-inlined. [#61144](https://github.com/ClickHouse/ClickHouse/pull/61144) ([李扬](https://github.com/taiyang-li)).
* Speed up parsing of JSON by skipping the rest of the object when all required columns are read. [#62210](https://github.com/ClickHouse/ClickHouse/pull/62210) ([lgbo](https://github.com/lgbo-ustc)).
* Improve trivial insert select from files in file/s3/hdfs/url/... table functions. Add separate max_parsing_threads setting to control the number of threads used in parallel parsing. [#62404](https://github.com/ClickHouse/ClickHouse/pull/62404) ([Kruglov Pavel](https://github.com/Avogar)).
* Functions `to_utc_timestamp` and `from_utc_timestamp` are now about 2x faster. [#62583](https://github.com/ClickHouse/ClickHouse/pull/62583) ([KevinyhZou](https://github.com/KevinyhZou)).
* Functions `parseDateTimeOrNull`, `parseDateTimeOrZero`, `parseDateTimeInJodaSyntaxOrNull` and `parseDateTimeInJodaSyntaxOrZero` now run significantly faster (10x - 1000x) when the input contains mostly non-parseable values. [#62634](https://github.com/ClickHouse/ClickHouse/pull/62634) ([LiuNeng](https://github.com/liuneng1994)).
* SELECTs against `system.query_cache` are now noticeably faster when the query cache contains lots of entries (e.g. more than 100.000). [#62671](https://github.com/ClickHouse/ClickHouse/pull/62671) ([Robert Schulze](https://github.com/rschu1ze)).
* Less contention in filesystem cache (part 3): execute removal from filesystem without lock on space reservation attempt. [#61163](https://github.com/ClickHouse/ClickHouse/pull/61163) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Speed up dynamic resize of filesystem cache. [#61723](https://github.com/ClickHouse/ClickHouse/pull/61723) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Dictionary source with `INVALIDATE_QUERY` is not reloaded twice on startup. [#62050](https://github.com/ClickHouse/ClickHouse/pull/62050) ([vdimir](https://github.com/vdimir)).
* Fix an issue where when a redundant `= 1` or `= 0` is added after a boolean expression involving the primary key, the primary index is not used. For example, both `SELECT * FROM <table> WHERE <primary-key> IN (<value>) = 1` and `SELECT * FROM <table> WHERE <primary-key> NOT IN (<value>) = 0` will both perform a full table scan, when the primary index can be used. [#62142](https://github.com/ClickHouse/ClickHouse/pull/62142) ([josh-hildred](https://github.com/josh-hildred)).
* Return stream of chunks from `system.remote_data_paths` instead of accumulating the whole result in one big chunk. This allows to consume less memory, show intermediate progress and cancel the query. [#62613](https://github.com/ClickHouse/ClickHouse/pull/62613) ([Alexander Gololobov](https://github.com/davenger)).
#### Experimental Feature
* Support parallel write buffer for Azure Blob Storage managed by setting `azure_allow_parallel_part_upload`. [#62534](https://github.com/ClickHouse/ClickHouse/pull/62534) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Userspace page cache works with static web storage (`disk(type = web)`) now. Use client setting `use_page_cache_for_disks_without_file_cache=1` to enable. [#61911](https://github.com/ClickHouse/ClickHouse/pull/61911) ([Michael Kolupaev](https://github.com/al13n321)).
* Don't treat Bool and number variants as suspicious in the `Variant` type. [#61999](https://github.com/ClickHouse/ClickHouse/pull/61999) ([Kruglov Pavel](https://github.com/Avogar)).
* Implement better conversion from String to `Variant` using parsing. [#62005](https://github.com/ClickHouse/ClickHouse/pull/62005) ([Kruglov Pavel](https://github.com/Avogar)).
* Support `Variant` in JSONExtract functions. [#62014](https://github.com/ClickHouse/ClickHouse/pull/62014) ([Kruglov Pavel](https://github.com/Avogar)).
* Mark type `Variant` as comparable so it can be used in primary key. [#62693](https://github.com/ClickHouse/ClickHouse/pull/62693) ([Kruglov Pavel](https://github.com/Avogar)).
#### Improvement
* For convenience purpose, `SELECT * FROM numbers() `will work in the same way as `SELECT * FROM system.numbers` - without a limit. [#61969](https://github.com/ClickHouse/ClickHouse/pull/61969) ([YenchangChan](https://github.com/YenchangChan)).
* Introduce separate consumer/producer tags for the Kafka configuration. This avoids warnings from librdkafka (a bad C library with a lot of bugs) that consumer properties were specified for producer instances and vice versa (e.g. `Configuration property session.timeout.ms is a consumer property and will be ignored by this producer instance`). Closes: [#58983](https://github.com/ClickHouse/ClickHouse/issues/58983). [#58956](https://github.com/ClickHouse/ClickHouse/pull/58956) ([Aleksandr Musorin](https://github.com/AVMusorin)).
* Functions `date_diff` and `age` now calculate their result at nanosecond instead of microsecond precision. They now also offer `nanosecond` (or `nanoseconds` or `ns`) as a possible value for the `unit` parameter. [#61409](https://github.com/ClickHouse/ClickHouse/pull/61409) ([Austin Kothig](https://github.com/kothiga)).
* Added nano-, micro-, milliseconds unit for `date_trunc`. [#62335](https://github.com/ClickHouse/ClickHouse/pull/62335) ([Misz606](https://github.com/Misz606)).
* Reload certificate chain during certificate reload. [#61671](https://github.com/ClickHouse/ClickHouse/pull/61671) ([Pervakov Grigorii](https://github.com/GrigoryPervakov)).
* Try to prevent an error [#60432](https://github.com/ClickHouse/ClickHouse/issues/60432) by not allowing a table to be attached if there is an active replica for that replica path. [#61876](https://github.com/ClickHouse/ClickHouse/pull/61876) ([Arthur Passos](https://github.com/arthurpassos)).
* Implement support for `input` for `clickhouse-local`. [#61923](https://github.com/ClickHouse/ClickHouse/pull/61923) ([Azat Khuzhin](https://github.com/azat)).
* `Join` table engine with strictness `ANY` is consistent after reload. When several rows with the same key are inserted, the first one will have higher priority (before, it was chosen randomly upon table loading). close [#51027](https://github.com/ClickHouse/ClickHouse/issues/51027). [#61972](https://github.com/ClickHouse/ClickHouse/pull/61972) ([vdimir](https://github.com/vdimir)).
* Automatically infer Nullable column types from Apache Arrow schema. [#61984](https://github.com/ClickHouse/ClickHouse/pull/61984) ([Maksim Kita](https://github.com/kitaisreal)).
* Allow to cancel parallel merge of aggregate states during aggregation. Example: `uniqExact`. [#61992](https://github.com/ClickHouse/ClickHouse/pull/61992) ([Maksim Kita](https://github.com/kitaisreal)).
* Use `system.keywords` to fill in the suggestions and also use them in the all places internally. [#62000](https://github.com/ClickHouse/ClickHouse/pull/62000) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* `OPTIMIZE FINAL` for `ReplicatedMergeTree` now will wait for currently active merges to finish and then reattempt to schedule a final merge. This will put it more in line with ordinary `MergeTree` behaviour. [#62067](https://github.com/ClickHouse/ClickHouse/pull/62067) ([Nikita Taranov](https://github.com/nickitat)).
* While read data from a hive text file, it would use the first line of hive text file to resize of number of input fields, and sometimes the fields number of first line is not matched with the hive table defined , such as the hive table is defined to have 3 columns, like `test_tbl(a Int32, b Int32, c Int32)`, but the first line of text file only has 2 fields, and in this suitation, the input fields will be resized to 2, and if the next line of the text file has 3 fields, then the third field can not be read but set a default value 0, which is not right. [#62086](https://github.com/ClickHouse/ClickHouse/pull/62086) ([KevinyhZou](https://github.com/KevinyhZou)).
* `CREATE AS` copies the table's comment. [#62117](https://github.com/ClickHouse/ClickHouse/pull/62117) ([Pablo Marcos](https://github.com/pamarcos)).
* Add query progress to table zookeeper. [#62152](https://github.com/ClickHouse/ClickHouse/pull/62152) ([JackyWoo](https://github.com/JackyWoo)).
* Add ability to turn on trace collector (Real and CPU) server-wide. [#62189](https://github.com/ClickHouse/ClickHouse/pull/62189) ([alesapin](https://github.com/alesapin)).
* Added setting `lightweight_deletes_sync` (default value: 2 - wait all replicas synchronously). It is similar to setting `mutations_sync` but affects only behaviour of lightweight deletes. [#62195](https://github.com/ClickHouse/ClickHouse/pull/62195) ([Anton Popov](https://github.com/CurtizJ)).
* Distinguish booleans and integers while parsing values for custom settings: `SET custom_a = true; SET custom_b = 1;`. [#62206](https://github.com/ClickHouse/ClickHouse/pull/62206) ([Vitaly Baranov](https://github.com/vitlibar)).
* Support S3 access through AWS Private Link Interface endpoints. Closes [#60021](https://github.com/ClickHouse/ClickHouse/issues/60021), [#31074](https://github.com/ClickHouse/ClickHouse/issues/31074) and [#53761](https://github.com/ClickHouse/ClickHouse/issues/53761). [#62208](https://github.com/ClickHouse/ClickHouse/pull/62208) ([Arthur Passos](https://github.com/arthurpassos)).
* Do not create a directory for UDF in clickhouse-client if it does not exist. This closes [#59597](https://github.com/ClickHouse/ClickHouse/issues/59597). [#62366](https://github.com/ClickHouse/ClickHouse/pull/62366) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* The query cache now no longer caches results of queries against system tables (`system.*`, `information_schema.*`, `INFORMATION_SCHEMA.*`). [#62376](https://github.com/ClickHouse/ClickHouse/pull/62376) ([Robert Schulze](https://github.com/rschu1ze)).
* `MOVE PARTITION TO TABLE` query can be delayed or can throw `TOO_MANY_PARTS` exception to avoid exceeding limits on the part count. The same settings and limits are applied as for the`INSERT` query (see `max_parts_in_total`, `parts_to_delay_insert`, `parts_to_throw_insert`, `inactive_parts_to_throw_insert`, `inactive_parts_to_delay_insert`, `max_avg_part_size_for_too_many_parts`, `min_delay_to_insert_ms` and `max_delay_to_insert` settings). [#62420](https://github.com/ClickHouse/ClickHouse/pull/62420) ([Sergei Trifonov](https://github.com/serxa)).
* Changed the default installation directory on macOS from `/usr/bin` to `/usr/local/bin`. This is necessary because Apple's System Integrity Protection introduced with macOS El Capitan (2015) prevents writing into `/usr/bin`, even with `sudo`. [#62489](https://github.com/ClickHouse/ClickHouse/pull/62489) ([haohang](https://github.com/yokofly)).
* Make transform always return the first match. [#62518](https://github.com/ClickHouse/ClickHouse/pull/62518) ([Raúl Marín](https://github.com/Algunenano)).
* Added the missing `hostname` column to system table `blob_storage_log`. [#62456](https://github.com/ClickHouse/ClickHouse/pull/62456) ([Jayme Bird](https://github.com/jaymebrd)).
* For consistency with other system tables, `system.backup_log` now has a column `event_time`. [#62541](https://github.com/ClickHouse/ClickHouse/pull/62541) ([Jayme Bird](https://github.com/jaymebrd)).
* Table `system.backup_log` now has the "default" sorting key which is `event_date, event_time`, the same as for other `_log` table engines. [#62667](https://github.com/ClickHouse/ClickHouse/pull/62667) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Avoid evaluating table DEFAULT expressions while executing `RESTORE`. [#62601](https://github.com/ClickHouse/ClickHouse/pull/62601) ([Vitaly Baranov](https://github.com/vitlibar)).
* S3 storage and backups also need the same default keep alive settings as s3 disk. [#62648](https://github.com/ClickHouse/ClickHouse/pull/62648) ([Sema Checherinda](https://github.com/CheSema)).
* Add librdkafka's (that infamous C library, which has a lot of bugs) client identifier to log messages to be able to differentiate log messages from different consumers of a single table. [#62813](https://github.com/ClickHouse/ClickHouse/pull/62813) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Allow special macros `{uuid}` and `{database}` in a Replicated database ZooKeeper path. [#62818](https://github.com/ClickHouse/ClickHouse/pull/62818) ([Vitaly Baranov](https://github.com/vitlibar)).
* Allow quota key with different auth scheme in HTTP requests. [#62842](https://github.com/ClickHouse/ClickHouse/pull/62842) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Reduce the verbosity of command line argument `--help` in `clickhouse client` and `clickhouse local`. The previous output is now generated by `--help --verbose`. [#62973](https://github.com/ClickHouse/ClickHouse/pull/62973) ([Yarik Briukhovetskyi](https://github.com/yariks5s)).
* `log_bin_use_v1_row_events` was removed in MySQL 8.3, and we adjust the experimental `MaterializedMySQL` engine for it [#60479](https://github.com/ClickHouse/ClickHouse/issues/60479). [#63101](https://github.com/ClickHouse/ClickHouse/pull/63101) ([Eugene Klimov](https://github.com/Slach)). Author: Nikolay Yankin.
#### Build/Testing/Packaging Improvement
* Vendor in Rust dependencies, so the Rust code (that we use for minor features for hype and lulz) can be built in a sane way, similarly to C++. [#62297](https://github.com/ClickHouse/ClickHouse/pull/62297) ([Raúl Marín](https://github.com/Algunenano)).
* ClickHouse now uses OpenSSL 3.2 instead of BoringSSL. [#59870](https://github.com/ClickHouse/ClickHouse/pull/59870) ([Robert Schulze](https://github.com/rschu1ze)). Note that OpenSSL has generally worse engineering culture (such as non-zero number of sanitizer reports, that we had to patch, a complex build system with generated files, etc.) but has better compatibility.
* Ignore DROP queries in stress test with 1/2 probability, use TRUNCATE instead of ignoring DROP in upgrade check for Memory/JOIN tables. [#61476](https://github.com/ClickHouse/ClickHouse/pull/61476) ([Kruglov Pavel](https://github.com/Avogar)).
* Remove from the Keeper Docker image the volumes at /etc/clickhouse-keeper and /var/log/clickhouse-keeper. [#61683](https://github.com/ClickHouse/ClickHouse/pull/61683) ([Tristan](https://github.com/Tristan971)).
* Add tests for all issues which are no longer relevant with Analyzer being enabled by default. Closes: [#55794](https://github.com/ClickHouse/ClickHouse/issues/55794) Closes: [#49472](https://github.com/ClickHouse/ClickHouse/issues/49472) Closes: [#44414](https://github.com/ClickHouse/ClickHouse/issues/44414) Closes: [#13843](https://github.com/ClickHouse/ClickHouse/issues/13843) Closes: [#55803](https://github.com/ClickHouse/ClickHouse/issues/55803) Closes: [#48308](https://github.com/ClickHouse/ClickHouse/issues/48308) Closes: [#45535](https://github.com/ClickHouse/ClickHouse/issues/45535) Closes: [#44365](https://github.com/ClickHouse/ClickHouse/issues/44365) Closes: [#44153](https://github.com/ClickHouse/ClickHouse/issues/44153) Closes: [#42399](https://github.com/ClickHouse/ClickHouse/issues/42399) Closes: [#27115](https://github.com/ClickHouse/ClickHouse/issues/27115) Closes: [#23162](https://github.com/ClickHouse/ClickHouse/issues/23162) Closes: [#15395](https://github.com/ClickHouse/ClickHouse/issues/15395) Closes: [#15411](https://github.com/ClickHouse/ClickHouse/issues/15411) Closes: [#14978](https://github.com/ClickHouse/ClickHouse/issues/14978) Closes: [#17319](https://github.com/ClickHouse/ClickHouse/issues/17319) Closes: [#11813](https://github.com/ClickHouse/ClickHouse/issues/11813) Closes: [#13210](https://github.com/ClickHouse/ClickHouse/issues/13210) Closes: [#23053](https://github.com/ClickHouse/ClickHouse/issues/23053) Closes: [#37729](https://github.com/ClickHouse/ClickHouse/issues/37729) Closes: [#32639](https://github.com/ClickHouse/ClickHouse/issues/32639) Closes: [#9954](https://github.com/ClickHouse/ClickHouse/issues/9954) Closes: [#41964](https://github.com/ClickHouse/ClickHouse/issues/41964) Closes: [#54317](https://github.com/ClickHouse/ClickHouse/issues/54317) Closes: [#7520](https://github.com/ClickHouse/ClickHouse/issues/7520) Closes: [#36973](https://github.com/ClickHouse/ClickHouse/issues/36973) Closes: [#40955](https://github.com/ClickHouse/ClickHouse/issues/40955) Closes: [#19687](https://github.com/ClickHouse/ClickHouse/issues/19687) Closes: [#23104](https://github.com/ClickHouse/ClickHouse/issues/23104) Closes: [#21584](https://github.com/ClickHouse/ClickHouse/issues/21584) Closes: [#23344](https://github.com/ClickHouse/ClickHouse/issues/23344) Closes: [#22627](https://github.com/ClickHouse/ClickHouse/issues/22627) Closes: [#10276](https://github.com/ClickHouse/ClickHouse/issues/10276) Closes: [#19687](https://github.com/ClickHouse/ClickHouse/issues/19687) Closes: [#4567](https://github.com/ClickHouse/ClickHouse/issues/4567) Closes: [#17710](https://github.com/ClickHouse/ClickHouse/issues/17710) Closes: [#11068](https://github.com/ClickHouse/ClickHouse/issues/11068) Closes: [#24395](https://github.com/ClickHouse/ClickHouse/issues/24395) Closes: [#23416](https://github.com/ClickHouse/ClickHouse/issues/23416) Closes: [#23162](https://github.com/ClickHouse/ClickHouse/issues/23162) Closes: [#25655](https://github.com/ClickHouse/ClickHouse/issues/25655) Closes: [#11757](https://github.com/ClickHouse/ClickHouse/issues/11757) Closes: [#6571](https://github.com/ClickHouse/ClickHouse/issues/6571) Closes: [#4432](https://github.com/ClickHouse/ClickHouse/issues/4432) Closes: [#8259](https://github.com/ClickHouse/ClickHouse/issues/8259) Closes: [#9233](https://github.com/ClickHouse/ClickHouse/issues/9233) Closes: [#14699](https://github.com/ClickHouse/ClickHouse/issues/14699) Closes: [#27068](https://github.com/ClickHouse/ClickHouse/issues/27068) Closes: [#28687](https://github.com/ClickHouse/ClickHouse/issues/28687) Closes: [#28777](https://github.com/ClickHouse/ClickHouse/issues/28777) Closes: [#29734](https://github.com/ClickHouse/ClickHouse/issues/29734) Closes: [#61238](https://github.com/ClickHouse/ClickHouse/issues/61238) Closes: [#33825](https://github.com/ClickHouse/ClickHouse/issues/33825) Closes: [#35608](https://github.com/ClickHouse/ClickHouse/issues/35608) Closes: [#29838](https://github.com/ClickHouse/ClickHouse/issues/29838) Closes: [#35652](https://github.com/ClickHouse/ClickHouse/issues/35652) Closes: [#36189](https://github.com/ClickHouse/ClickHouse/issues/36189) Closes: [#39634](https://github.com/ClickHouse/ClickHouse/issues/39634) Closes: [#47432](https://github.com/ClickHouse/ClickHouse/issues/47432) Closes: [#54910](https://github.com/ClickHouse/ClickHouse/issues/54910) Closes: [#57321](https://github.com/ClickHouse/ClickHouse/issues/57321) Closes: [#59154](https://github.com/ClickHouse/ClickHouse/issues/59154) Closes: [#61014](https://github.com/ClickHouse/ClickHouse/issues/61014) Closes: [#61950](https://github.com/ClickHouse/ClickHouse/issues/61950) Closes: [#55647](https://github.com/ClickHouse/ClickHouse/issues/55647) Closes: [#61947](https://github.com/ClickHouse/ClickHouse/issues/61947). [#62185](https://github.com/ClickHouse/ClickHouse/pull/62185) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Add more tests from issues which are no longer relevant or fixed by analyzer. Closes: [#58985](https://github.com/ClickHouse/ClickHouse/issues/58985) Closes: [#59549](https://github.com/ClickHouse/ClickHouse/issues/59549) Closes: [#36963](https://github.com/ClickHouse/ClickHouse/issues/36963) Closes: [#39453](https://github.com/ClickHouse/ClickHouse/issues/39453) Closes: [#56521](https://github.com/ClickHouse/ClickHouse/issues/56521) Closes: [#47552](https://github.com/ClickHouse/ClickHouse/issues/47552) Closes: [#56503](https://github.com/ClickHouse/ClickHouse/issues/56503) Closes: [#59101](https://github.com/ClickHouse/ClickHouse/issues/59101) Closes: [#50271](https://github.com/ClickHouse/ClickHouse/issues/50271) Closes: [#54954](https://github.com/ClickHouse/ClickHouse/issues/54954) Closes: [#56466](https://github.com/ClickHouse/ClickHouse/issues/56466) Closes: [#11000](https://github.com/ClickHouse/ClickHouse/issues/11000) Closes: [#10894](https://github.com/ClickHouse/ClickHouse/issues/10894) Closes: https://github.com/ClickHouse/ClickHouse/issues/448 Closes: [#8030](https://github.com/ClickHouse/ClickHouse/issues/8030) Closes: [#32139](https://github.com/ClickHouse/ClickHouse/issues/32139) Closes: [#47288](https://github.com/ClickHouse/ClickHouse/issues/47288) Closes: [#50705](https://github.com/ClickHouse/ClickHouse/issues/50705) Closes: [#54511](https://github.com/ClickHouse/ClickHouse/issues/54511) Closes: [#55466](https://github.com/ClickHouse/ClickHouse/issues/55466) Closes: [#58500](https://github.com/ClickHouse/ClickHouse/issues/58500) Closes: [#39923](https://github.com/ClickHouse/ClickHouse/issues/39923) Closes: [#39855](https://github.com/ClickHouse/ClickHouse/issues/39855) Closes: [#4596](https://github.com/ClickHouse/ClickHouse/issues/4596) Closes: [#47422](https://github.com/ClickHouse/ClickHouse/issues/47422) Closes: [#33000](https://github.com/ClickHouse/ClickHouse/issues/33000) Closes: [#14739](https://github.com/ClickHouse/ClickHouse/issues/14739) Closes: [#44039](https://github.com/ClickHouse/ClickHouse/issues/44039) Closes: [#8547](https://github.com/ClickHouse/ClickHouse/issues/8547) Closes: [#22923](https://github.com/ClickHouse/ClickHouse/issues/22923) Closes: [#23865](https://github.com/ClickHouse/ClickHouse/issues/23865) Closes: [#29748](https://github.com/ClickHouse/ClickHouse/issues/29748) Closes: [#4222](https://github.com/ClickHouse/ClickHouse/issues/4222). [#62457](https://github.com/ClickHouse/ClickHouse/pull/62457) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fixed build errors when OpenSSL is linked dynamically (note: this is generally unsupported and only required for IBM's s390x platforms). [#62888](https://github.com/ClickHouse/ClickHouse/pull/62888) ([Harry Lee](https://github.com/HarryLeeIBM)).
#### Bug Fix (user-visible misbehavior in an official stable release)
* Fix logical-error when undoing quorum insert transaction. [#61953](https://github.com/ClickHouse/ClickHouse/pull/61953) ([Han Fei](https://github.com/hanfei1991)).
* Fix parser error when using COUNT(*) with FILTER clause [#61357](https://github.com/ClickHouse/ClickHouse/pull/61357) ([Duc Canh Le](https://github.com/canhld94)).
* Fix logical error in `group_by_use_nulls` + grouping sets + analyzer + materialize/constant [#61567](https://github.com/ClickHouse/ClickHouse/pull/61567) ([Kruglov Pavel](https://github.com/Avogar)).
* Cancel merges before removing moved parts [#61610](https://github.com/ClickHouse/ClickHouse/pull/61610) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Fix abort in Apache Arrow [#61720](https://github.com/ClickHouse/ClickHouse/pull/61720) ([Kruglov Pavel](https://github.com/Avogar)).
* Search for `convert_to_replicated` flag at the correct path corresponding to the specific disk [#61769](https://github.com/ClickHouse/ClickHouse/pull/61769) ([Kirill](https://github.com/kirillgarbar)).
* Fix possible connections data-race for distributed_foreground_insert/distributed_background_insert_batch [#61867](https://github.com/ClickHouse/ClickHouse/pull/61867) ([Azat Khuzhin](https://github.com/azat)).
* Mark CANNOT_PARSE_ESCAPE_SEQUENCE error as parse error to be able to skip it in row input formats [#61883](https://github.com/ClickHouse/ClickHouse/pull/61883) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix writing exception message in output format in HTTP when http_wait_end_of_query is used [#61951](https://github.com/ClickHouse/ClickHouse/pull/61951) ([Kruglov Pavel](https://github.com/Avogar)).
* Proper fix for LowCardinality together with JSONExtact functions [#61957](https://github.com/ClickHouse/ClickHouse/pull/61957) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Crash in Engine Merge if Row Policy does not have expression [#61971](https://github.com/ClickHouse/ClickHouse/pull/61971) ([Ilya Golshtein](https://github.com/ilejn)).
* Fix WriteBufferAzureBlobStorage destructor uncaught exception [#61988](https://github.com/ClickHouse/ClickHouse/pull/61988) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix CREATE TABLE without columns definition for ReplicatedMergeTree [#62040](https://github.com/ClickHouse/ClickHouse/pull/62040) ([Azat Khuzhin](https://github.com/azat)).
* Fix optimize_skip_unused_shards_rewrite_in for composite sharding key [#62047](https://github.com/ClickHouse/ClickHouse/pull/62047) ([Azat Khuzhin](https://github.com/azat)).
* ReadWriteBufferFromHTTP set right header host when redirected [#62068](https://github.com/ClickHouse/ClickHouse/pull/62068) ([Sema Checherinda](https://github.com/CheSema)).
* Fix external table cannot parse data type Bool [#62115](https://github.com/ClickHouse/ClickHouse/pull/62115) ([Duc Canh Le](https://github.com/canhld94)).
* Analyzer: Fix query parameter resolution [#62186](https://github.com/ClickHouse/ClickHouse/pull/62186) ([Dmitry Novik](https://github.com/novikd)).
* Fix restoring parts while readonly [#62207](https://github.com/ClickHouse/ClickHouse/pull/62207) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fix crash in index definition containing SQL UDF [#62225](https://github.com/ClickHouse/ClickHouse/pull/62225) ([vdimir](https://github.com/vdimir)).
* Fixing NULL random seed for generateRandom with analyzer. [#62248](https://github.com/ClickHouse/ClickHouse/pull/62248) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Correctly handle const columns in Distinct Transfom [#62250](https://github.com/ClickHouse/ClickHouse/pull/62250) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix Parts Splitter for queries with the FINAL modifier [#62268](https://github.com/ClickHouse/ClickHouse/pull/62268) ([Nikita Taranov](https://github.com/nickitat)).
* Analyzer: Fix alias to parametrized view resolution [#62274](https://github.com/ClickHouse/ClickHouse/pull/62274) ([Dmitry Novik](https://github.com/novikd)).
* Analyzer: Fix name resolution from parent scopes [#62281](https://github.com/ClickHouse/ClickHouse/pull/62281) ([Dmitry Novik](https://github.com/novikd)).
* Fix argMax with nullable non native numeric column [#62285](https://github.com/ClickHouse/ClickHouse/pull/62285) ([Raúl Marín](https://github.com/Algunenano)).
* Fix BACKUP and RESTORE of a materialized view in Ordinary database [#62295](https://github.com/ClickHouse/ClickHouse/pull/62295) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fix data race on scalars in Context [#62305](https://github.com/ClickHouse/ClickHouse/pull/62305) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix primary key in materialized view [#62319](https://github.com/ClickHouse/ClickHouse/pull/62319) ([Murat Khairulin](https://github.com/mxwell)).
* Do not build multithread insert pipeline for tables without support [#62333](https://github.com/ClickHouse/ClickHouse/pull/62333) ([vdimir](https://github.com/vdimir)).
* Fix analyzer with positional arguments in distributed query [#62362](https://github.com/ClickHouse/ClickHouse/pull/62362) ([flynn](https://github.com/ucasfl)).
* Fix filter pushdown from additional_table_filters in Merge engine in analyzer [#62398](https://github.com/ClickHouse/ClickHouse/pull/62398) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix GLOBAL IN table queries with analyzer. [#62409](https://github.com/ClickHouse/ClickHouse/pull/62409) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Respect settings truncate_on_insert/create_new_file_on_insert in s3/hdfs/azure engines during partitioned write [#62425](https://github.com/ClickHouse/ClickHouse/pull/62425) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix backup restore path for AzureBlobStorage [#62447](https://github.com/ClickHouse/ClickHouse/pull/62447) ([SmitaRKulkarni](https://github.com/SmitaRKulkarni)).
* Fix SimpleSquashingChunksTransform [#62451](https://github.com/ClickHouse/ClickHouse/pull/62451) ([Nikita Taranov](https://github.com/nickitat)).
* Fix capture of nested lambda. [#62462](https://github.com/ClickHouse/ClickHouse/pull/62462) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Avoid crash when reading protobuf with recursive types [#62506](https://github.com/ClickHouse/ClickHouse/pull/62506) ([Raúl Marín](https://github.com/Algunenano)).
* Fix a bug moving one partition from one to itself [#62524](https://github.com/ClickHouse/ClickHouse/pull/62524) ([helifu](https://github.com/helifu)).
* Fix scalar subquery in LIMIT [#62567](https://github.com/ClickHouse/ClickHouse/pull/62567) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix segfault in the experimental and unsupported Hive engine, which we don't like anyway [#62578](https://github.com/ClickHouse/ClickHouse/pull/62578) ([Nikolay Degterinsky](https://github.com/evillique)).
* Fix memory leak in groupArraySorted [#62597](https://github.com/ClickHouse/ClickHouse/pull/62597) ([Antonio Andelic](https://github.com/antonio2368)).
* Fix crash in largestTriangleThreeBuckets [#62646](https://github.com/ClickHouse/ClickHouse/pull/62646) ([Raúl Marín](https://github.com/Algunenano)).
* Fix tumble\[Start,End\] and hop\[Start,End\] for bigger resolutions [#62705](https://github.com/ClickHouse/ClickHouse/pull/62705) ([Jordi Villar](https://github.com/jrdi)).
* Fix argMin/argMax combinator state [#62708](https://github.com/ClickHouse/ClickHouse/pull/62708) ([Raúl Marín](https://github.com/Algunenano)).
* Fix temporary data in cache failing because of cache lock contention optimization [#62715](https://github.com/ClickHouse/ClickHouse/pull/62715) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix crash in function `mergeTreeIndex` [#62762](https://github.com/ClickHouse/ClickHouse/pull/62762) ([Anton Popov](https://github.com/CurtizJ)).
* fix: update: nested materialized columns: size check fixes [#62773](https://github.com/ClickHouse/ClickHouse/pull/62773) ([Eliot Hautefeuille](https://github.com/hileef)).
* Fix FINAL modifier is not respected in CTE with analyzer [#62811](https://github.com/ClickHouse/ClickHouse/pull/62811) ([Duc Canh Le](https://github.com/canhld94)).
* Fix crash in function `formatRow` with `JSON` format and HTTP interface [#62840](https://github.com/ClickHouse/ClickHouse/pull/62840) ([Anton Popov](https://github.com/CurtizJ)).
* Azure: fix building final url from endpoint object [#62850](https://github.com/ClickHouse/ClickHouse/pull/62850) ([Daniel Pozo Escalona](https://github.com/danipozo)).
* Fix GCD codec [#62853](https://github.com/ClickHouse/ClickHouse/pull/62853) ([Nikita Taranov](https://github.com/nickitat)).
* Fix LowCardinality(Nullable) key in hyperrectangle [#62866](https://github.com/ClickHouse/ClickHouse/pull/62866) ([Amos Bird](https://github.com/amosbird)).
* Fix fromUnixtimestamp in joda syntax while the input value beyond UInt32 [#62901](https://github.com/ClickHouse/ClickHouse/pull/62901) ([KevinyhZou](https://github.com/KevinyhZou)).
* Disable optimize_rewrite_aggregate_function_with_if for sum(nullable) [#62912](https://github.com/ClickHouse/ClickHouse/pull/62912) ([Raúl Marín](https://github.com/Algunenano)).
* Fix PREWHERE for StorageBuffer with different source table column types. [#62916](https://github.com/ClickHouse/ClickHouse/pull/62916) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix temporary data in cache incorrectly processing failure of cache key directory creation [#62925](https://github.com/ClickHouse/ClickHouse/pull/62925) ([Kseniia Sumarokova](https://github.com/kssenii)).
* gRPC: fix crash on IPv6 peer connection [#62978](https://github.com/ClickHouse/ClickHouse/pull/62978) ([Konstantin Bogdanov](https://github.com/thevar1able)).
* Fix possible CHECKSUM_DOESNT_MATCH (and others) during replicated fetches [#62987](https://github.com/ClickHouse/ClickHouse/pull/62987) ([Azat Khuzhin](https://github.com/azat)).
* Fix terminate with uncaught exception in temporary data in cache [#62998](https://github.com/ClickHouse/ClickHouse/pull/62998) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix optimize_rewrite_aggregate_function_with_if implicit cast [#62999](https://github.com/ClickHouse/ClickHouse/pull/62999) ([Raúl Marín](https://github.com/Algunenano)).
* Fix unhandled exception in ~RestorerFromBackup [#63040](https://github.com/ClickHouse/ClickHouse/pull/63040) ([Vitaly Baranov](https://github.com/vitlibar)).
* Do not remove server constants from GROUP BY key for secondary query. [#63047](https://github.com/ClickHouse/ClickHouse/pull/63047) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix incorrect judgement of of monotonicity of function abs [#63097](https://github.com/ClickHouse/ClickHouse/pull/63097) ([Duc Canh Le](https://github.com/canhld94)).
* Set server name for SSL handshake in MongoDB engine [#63122](https://github.com/ClickHouse/ClickHouse/pull/63122) ([Alexander Gololobov](https://github.com/davenger)).
* Use user specified db instead of "config" for MongoDB wire protocol version check [#63126](https://github.com/ClickHouse/ClickHouse/pull/63126) ([Alexander Gololobov](https://github.com/davenger)).
### <a id="243"></a> ClickHouse release 24.3 LTS, 2024-03-27
#### Upgrade Notes
@ -38,9 +200,9 @@
* Optimized function `dotProduct` to omit unnecessary and expensive memory copies. [#60928](https://github.com/ClickHouse/ClickHouse/pull/60928) ([Robert Schulze](https://github.com/rschu1ze)).
* 30x faster printing for 256-bit integers. [#61100](https://github.com/ClickHouse/ClickHouse/pull/61100) ([Raúl Marín](https://github.com/Algunenano)).
* If the table's primary key contains mostly useless columns, don't keep them in memory. This is controlled by a new setting `primary_key_ratio_of_unique_prefix_values_to_skip_suffix_columns` with the value `0.9` by default, which means: for a composite primary key, if a column changes its value for at least 0.9 of all the times, the next columns after it will be not loaded. [#60255](https://github.com/ClickHouse/ClickHouse/pull/60255) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Improve the performance of serialized aggregation method when involving multiple `Nullable` columns. [#55809](https://github.com/ClickHouse/ClickHouse/pull/55809) ([Amos Bird](https://github.com/amosbird)).
* Lazy build JSON's output to improve performance of ALL JOIN. [#58278](https://github.com/ClickHouse/ClickHouse/pull/58278) ([LiuNeng](https://github.com/liuneng1994)).
* Make HTTP/HTTPs connections with external services, such as AWS S3 reusable for all uses cases. Even when response is 3xx or 4xx. [#58845](https://github.com/ClickHouse/ClickHouse/pull/58845) ([Sema Checherinda](https://github.com/CheSema)).
* Improve the performance of serialized aggregation methods when involving multiple `Nullable` columns. [#55809](https://github.com/ClickHouse/ClickHouse/pull/55809) ([Amos Bird](https://github.com/amosbird)).
* Lazy builds JSON's output to improve performance of ALL JOIN. [#58278](https://github.com/ClickHouse/ClickHouse/pull/58278) ([LiuNeng](https://github.com/liuneng1994)).
* Make HTTP/HTTPs connections with external services, such as AWS S3 reusable for all use cases. Even when the response is 3xx or 4xx. [#58845](https://github.com/ClickHouse/ClickHouse/pull/58845) ([Sema Checherinda](https://github.com/CheSema)).
* Improvements to aggregate functions `argMin` / `argMax` / `any` / `anyLast` / `anyHeavy`, as well as `ORDER BY {u8/u16/u32/u64/i8/i16/u32/i64) LIMIT 1` queries. [#58640](https://github.com/ClickHouse/ClickHouse/pull/58640) ([Raúl Marín](https://github.com/Algunenano)).
* Trivial optimization for column's filter. Peak memory can be reduced to 44% of the original in some cases. [#59698](https://github.com/ClickHouse/ClickHouse/pull/59698) ([李扬](https://github.com/taiyang-li)).
* Execute `multiIf` function in a columnar fashion when the result type's underlying type is a number. [#60384](https://github.com/ClickHouse/ClickHouse/pull/60384) ([李扬](https://github.com/taiyang-li)).
@ -49,7 +211,7 @@
* Optimize data movement between columns of a Nullable number or a Nullable string, which improves some micro-benchmarks. [#60846](https://github.com/ClickHouse/ClickHouse/pull/60846) ([李扬](https://github.com/taiyang-li)).
* Operations with the filesystem cache will suffer less from the lock contention. [#61066](https://github.com/ClickHouse/ClickHouse/pull/61066) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Optimize array join and other JOINs by preventing a wrong compiler's optimization. Close [#61074](https://github.com/ClickHouse/ClickHouse/issues/61074). [#61075](https://github.com/ClickHouse/ClickHouse/pull/61075) ([李扬](https://github.com/taiyang-li)).
* If a query with a syntax error contained `COLUMNS` matcher with a regular expression, the regular expression was compiled each time during the parser's backtracking, instead of being compiled once. This was a fundamental error. The compiled regexp was put to AST. But the letter A in AST means "abstract" which means it should not contain heavyweight objects. Parts of AST can be created and discarded during parsing, including a large number of backtracking. This leads to slowness on the parsing side and consequently allows DoS by a readonly user. But the main problem is that it prevents progress in fuzzers. [#61543](https://github.com/ClickHouse/ClickHouse/pull/61543) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* If a query with a syntax error contained the `COLUMNS` matcher with a regular expression, the regular expression was compiled each time during the parser's backtracking, instead of being compiled once. This was a fundamental error. The compiled regexp was put to AST. But the letter A in AST means "abstract" which means it should not contain heavyweight objects. Parts of AST can be created and discarded during parsing, including a large number of backtracking. This leads to slowness on the parsing side and consequently allows DoS by a readonly user. But the main problem is that it prevents progress in fuzzers. [#61543](https://github.com/ClickHouse/ClickHouse/pull/61543) ([Alexey Milovidov](https://github.com/alexey-milovidov)).
* Add a new analyzer pass to optimize the IN operator for a single value. [#61564](https://github.com/ClickHouse/ClickHouse/pull/61564) ([LiuNeng](https://github.com/liuneng1994)).
* DNSResolver shuffles set of resolved IPs which is needed to uniformly utilize multiple endpoints of AWS S3. [#60965](https://github.com/ClickHouse/ClickHouse/pull/60965) ([Sema Checherinda](https://github.com/CheSema)).
@ -185,6 +347,7 @@
* Add sanity check for number of threads and block sizes. [#60138](https://github.com/ClickHouse/ClickHouse/pull/60138) ([Raúl Marín](https://github.com/Algunenano)).
* Don't infer floats in exponential notation by default. Add a setting `input_format_try_infer_exponent_floats` that will restore previous behaviour (disabled by default). Closes [#59476](https://github.com/ClickHouse/ClickHouse/issues/59476). [#59500](https://github.com/ClickHouse/ClickHouse/pull/59500) ([Kruglov Pavel](https://github.com/Avogar)).
* Allow alter operations to be surrounded by parenthesis. The emission of parentheses can be controlled by the `format_alter_operations_with_parentheses` config. By default, in formatted queries the parentheses are emitted as we store the formatted alter operations in some places as metadata (e.g.: mutations). The new syntax clarifies some of the queries where alter operations end in a list. E.g.: `ALTER TABLE x MODIFY TTL date GROUP BY a, b, DROP COLUMN c` cannot be parsed properly with the old syntax. In the new syntax the query `ALTER TABLE x (MODIFY TTL date GROUP BY a, b), (DROP COLUMN c)` is obvious. Older versions are not able to read the new syntax, therefore using the new syntax might cause issues if newer and older version of ClickHouse are mixed in a single cluster. [#59532](https://github.com/ClickHouse/ClickHouse/pull/59532) ([János Benjamin Antal](https://github.com/antaljanosbenjamin)).
* Fix for the materialized view security issue, which allowed a user to insert into a table without required grants for that. Fix validates that the user has permission to insert not only into a materialized view but also into all underlying tables. This means that some queries, which worked before, now can fail with `Not enough privileges`. To address this problem, the release introduces a new feature of SQL security for views https://clickhouse.com/docs/en/sql-reference/statements/create/view#sql_security. [#54901](https://github.com/ClickHouse/ClickHouse/pull/54901) [#60439](https://github.com/ClickHouse/ClickHouse/pull/60439) ([pufit](https://github.com/pufit)).
#### New Feature
* Added new syntax which allows to specify definer user in View/Materialized View. This allows to execute selects/inserts from views without explicit grants for underlying tables. So, a View will encapsulate the grants. [#54901](https://github.com/ClickHouse/ClickHouse/pull/54901) [#60439](https://github.com/ClickHouse/ClickHouse/pull/60439) ([pufit](https://github.com/pufit)).

84
CMakeLists.txt
View File

@ -61,13 +61,16 @@ if (ENABLE_CHECK_HEAVY_BUILDS)
# set CPU time limit to 1000 seconds
set (RLIMIT_CPU 1000)
# Sanitizers are too heavy
if (SANITIZE OR SANITIZE_COVERAGE OR WITH_COVERAGE)
set (RLIMIT_DATA 10000000000) # 10G
# Sanitizers are too heavy. Some architectures too.
if (SANITIZE OR SANITIZE_COVERAGE OR WITH_COVERAGE OR ARCH_RISCV64 OR ARCH_LOONGARCH64)
# Twice as large
set (RLIMIT_DATA 10000000000)
set (RLIMIT_AS 20000000000)
endif()
# For some files currently building RISCV64 might be too slow. TODO: Improve compilation times per file
if (ARCH_RISCV64)
# For some files currently building RISCV64/LOONGARCH64 might be too slow.
# TODO: Improve compilation times per file
if (ARCH_RISCV64 OR ARCH_LOONGARCH64)
set (RLIMIT_CPU 1800)
endif()
@ -135,22 +138,20 @@ endif ()
include (cmake/check_flags.cmake)
include (cmake/add_warning.cmake)
if (COMPILER_CLANG)
# generate ranges for fast "addr2line" search
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# generate ranges for fast "addr2line" search
if (NOT CMAKE_BUILD_TYPE_UC STREQUAL "RELEASE")
# NOTE: that clang has a bug because of it does not emit .debug_aranges
# with ThinLTO, so custom ld.lld wrapper is shipped in docker images.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -gdwarf-aranges")
endif ()
endif ()
# See https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
# See https://blog.llvm.org/posts/2021-04-05-constructor-homing-for-debug-info/
if (CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG" OR CMAKE_BUILD_TYPE_UC STREQUAL "RELWITHDEBINFO")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -fuse-ctor-homing")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Xclang -fuse-ctor-homing")
endif()
endif()
no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
endif ()
no_warning(enum-constexpr-conversion) # breaks Protobuf in clang-16
option(ENABLE_TESTS "Provide unit_test_dbms target with Google.Test unit tests" ON)
option(ENABLE_EXAMPLES "Build all example programs in 'examples' subdirectories" OFF)
@ -284,16 +285,12 @@ endif ()
option (ENABLE_BUILD_PROFILING "Enable profiling of build time" OFF)
if (ENABLE_BUILD_PROFILING)
if (COMPILER_CLANG)
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ftime-trace")
if (LINKER_NAME MATCHES "lld")
set (CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,--time-trace")
set (CMAKE_MODULE_LINKER_FLAGS "${CMAKE_MODULE_LINKER_FLAGS} -Wl,--time-trace")
endif ()
else ()
message (${RECONFIGURE_MESSAGE_LEVEL} "Build profiling is only available with CLang")
endif ()
endif ()
set (CMAKE_CXX_STANDARD 23)
@ -304,22 +301,20 @@ set (CMAKE_C_STANDARD 11)
set (CMAKE_C_EXTENSIONS ON) # required by most contribs written in C
set (CMAKE_C_STANDARD_REQUIRED ON)
if (COMPILER_CLANG)
# Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
# See https://reviews.llvm.org/D112921
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
# Enable C++14 sized global deallocation functions. It should be enabled by setting -std=c++14 but I'm not sure.
# See https://reviews.llvm.org/D112921
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsized-deallocation")
# falign-functions=32 prevents from random performance regressions with the code change. Thus, providing more stable
# benchmarks.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -falign-functions=32")
# falign-functions=32 prevents from random performance regressions with the code change. Thus, providing more stable
# benchmarks.
set(COMPILER_FLAGS "${COMPILER_FLAGS} -falign-functions=32")
if (ARCH_AMD64)
if (ARCH_AMD64)
# align branches within a 32-Byte boundary to avoid the potential performance loss when code layout change,
# which makes benchmark results more stable.
set(BRANCHES_WITHIN_32B_BOUNDARIES "-mbranches-within-32B-boundaries")
set(COMPILER_FLAGS "${COMPILER_FLAGS} ${BRANCHES_WITHIN_32B_BOUNDARIES}")
endif()
endif ()
endif()
# Disable floating-point expression contraction in order to get consistent floating point calculation results across platforms
set (COMPILER_FLAGS "${COMPILER_FLAGS} -ffp-contract=off")
@ -348,39 +343,34 @@ set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} ${COMPILER_FLAGS} $
set (CMAKE_ASM_FLAGS_RELWITHDEBINFO "${CMAKE_ASM_FLAGS_RELWITHDEBINFO} -O3 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
set (CMAKE_ASM_FLAGS_DEBUG "${CMAKE_ASM_FLAGS_DEBUG} -O0 ${DEBUG_INFO_FLAGS} ${CMAKE_ASM_FLAGS_ADD}")
if (COMPILER_CLANG)
if (OS_DARWIN)
if (OS_DARWIN)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -Wl,-U,_inside_main")
endif()
endif()
# Display absolute paths in error messages. Otherwise KDevelop fails to navigate to correct file and opens a new file instead.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-absolute-paths")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-absolute-paths")
# Display absolute paths in error messages. Otherwise KDevelop fails to navigate to correct file and opens a new file instead.
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fdiagnostics-absolute-paths")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fdiagnostics-absolute-paths")
if (NOT ENABLE_TESTS AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND OS_LINUX)
if (NOT ENABLE_TESTS AND NOT SANITIZE AND NOT SANITIZE_COVERAGE AND OS_LINUX)
# https://clang.llvm.org/docs/ThinLTO.html
# Applies to clang and linux only.
# Disabled when building with tests or sanitizers.
option(ENABLE_THINLTO "Clang-specific link time optimization" ON)
endif()
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fstrict-vtable-pointers")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fstrict-vtable-pointers")
# We cannot afford to use LTO when compiling unit tests, and it's not enough
# to only supply -fno-lto at the final linking stage. So we disable it
# completely.
if (ENABLE_THINLTO AND NOT ENABLE_TESTS AND NOT SANITIZE)
# We cannot afford to use LTO when compiling unit tests, and it's not enough
# to only supply -fno-lto at the final linking stage. So we disable it
# completely.
if (ENABLE_THINLTO AND NOT ENABLE_TESTS AND NOT SANITIZE)
# Link time optimization
set (CMAKE_C_FLAGS_RELWITHDEBINFO "${CMAKE_C_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
set (CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO "${CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO} -flto=thin -fwhole-program-vtables")
elseif (ENABLE_THINLTO)
message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot enable ThinLTO")
endif ()
elseif (ENABLE_THINLTO)
message (${RECONFIGURE_MESSAGE_LEVEL} "ThinLTO is only available with Clang")
message (${RECONFIGURE_MESSAGE_LEVEL} "Cannot enable ThinLTO")
endif ()
# Turns on all external libs like s3, kafka, ODBC, ...
@ -455,8 +445,6 @@ endif ()
enable_testing() # Enable for tests without binary
option(ENABLE_OPENSSL "This option performs a build with OpenSSL. NOTE! This option is insecure and should never be used. By default, ClickHouse uses and only supports BoringSSL" OFF)
if (ARCH_S390X)
set(ENABLE_OPENSSL_DYNAMIC_DEFAULT ON)
else ()

2
PreLoad.cmake
View File

@ -93,6 +93,8 @@ if (OS MATCHES "Linux"
set (CMAKE_TOOLCHAIN_FILE "cmake/linux/toolchain-ppc64le.cmake" CACHE INTERNAL "")
elseif (ARCH MATCHES "^(s390x.*|S390X.*)")
set (CMAKE_TOOLCHAIN_FILE "cmake/linux/toolchain-s390x.cmake" CACHE INTERNAL "")
elseif (ARCH MATCHES "^(loongarch64.*|LOONGARCH64.*)")
set (CMAKE_TOOLCHAIN_FILE "cmake/linux/toolchain-loongarch64.cmake" CACHE INTERNAL "")
else ()
message (FATAL_ERROR "Unsupported architecture: ${ARCH}")
endif ()

25
README.md
View File

@ -34,26 +34,25 @@ curl https://clickhouse.com/ | sh
Every month we get together with the community (users, contributors, customers, those interested in learning more about ClickHouse) to discuss what is coming in the latest release. If you are interested in sharing what you've built on ClickHouse, let us know.
* [v24.3 Community Call](https://clickhouse.com/company/events/v24-3-community-release-call) - Mar 26
* [v24.4 Community Call](https://clickhouse.com/company/events/v24-4-community-release-call) - Apr 30
* [v24.5 Community Call](https://clickhouse.com/company/events/v24-5-community-release-call) - May 30
## Upcoming Events
Keep an eye out for upcoming meetups and eventsaround the world. Somewhere else you want us to be? Please feel free to reach out to tyler `<at>` clickhouse `<dot>` com. You can also peruse [ClickHouse Events](https://clickhouse.com/company/news-events) for a list of all upcoming trainings, meetups, speaking engagements, etc.
* [ClickHouse Meetup in Bellevue](https://www.meetup.com/clickhouse-seattle-user-group/events/298650371/) - Mar 11
* [ClickHouse Meetup at Ramp's Offices in NYC](https://www.meetup.com/clickhouse-new-york-user-group/events/298640542/) - Mar 19
* [ClickHouse Melbourne Meetup](https://www.meetup.com/clickhouse-australia-user-group/events/299479750/) - Mar 20
* [ClickHouse Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/298997115/) - Mar 21
* [ClickHouse Meetup in Bengaluru](https://www.meetup.com/clickhouse-bangalore-user-group/events/299479850/) - Mar 23
* [ClickHouse Meetup in Zurich](https://www.meetup.com/clickhouse-switzerland-meetup-group/events/299628922/) - Apr 16
* [ClickHouse Meetup in Copenhagen](https://www.meetup.com/clickhouse-denmark-meetup-group/events/299629133/) - Apr 23
* [ClickHouse Meetup in Dubai](https://www.meetup.com/clickhouse-dubai-meetup-group/events/299629189/) - May 28
Keep an eye out for upcoming meetups and events around the world. Somewhere else you want us to be? Please feel free to reach out to tyler `<at>` clickhouse `<dot>` com. You can also peruse [ClickHouse Events](https://clickhouse.com/company/news-events) for a list of all upcoming trainings, meetups, speaking engagements, etc.
* [ClickHouse Happy Hour @ Tom's Watch Bar - Los Angeles](https://www.meetup.com/clickhouse-los-angeles-user-group/events/300740584/) - May 22
* [ClickHouse & Confluent Meetup in Dubai](https://www.meetup.com/clickhouse-dubai-meetup-group/events/299629189/) - May 28
* [ClickHouse Meetup in Stockholm](https://www.meetup.com/clickhouse-stockholm-user-group/events/299752651/) - Jun 3
* [ClickHouse Meetup @ Cloudflare - San Francisco](https://www.meetup.com/clickhouse-silicon-valley-meetup-group/events/300523061/) - Jun 4
* [ClickHouse (クリックハウス) Meetup Tokyo](https://www.meetup.com/clickhouse-tokyo-user-group/events/300798053/) - Jun 5
* [ClickHouse Meetup in Amsterdam](https://www.meetup.com/clickhouse-netherlands-user-group/events/300781068/) - Jun 27
* [ClickHouse Meetup in Paris](https://www.meetup.com/clickhouse-france-user-group/events/300783448/) - Jul 9
* [ClickHouse Meetup @ Ramp - New York City](https://www.meetup.com/clickhouse-new-york-user-group/events/300595845/) - Jul 9
* [ClickHouse Meetup @ Klaviyo - Boston](https://www.meetup.com/clickhouse-boston-user-group/events/300907870) - Jul 11
## Recent Recordings
* **Recent Meetup Videos**: [Meetup Playlist](https://www.youtube.com/playlist?list=PL0Z2YDlm0b3iNDUzpY1S3L_iV4nARda_U) Whenever possible recordings of the ClickHouse Community Meetups are edited and presented as individual talks. Current featuring "Modern SQL in 2023", "Fast, Concurrent, and Consistent Asynchronous INSERTS in ClickHouse", and "Full-Text Indices: Design and Experiments"
* **Recording available**: [**v24.2 Release Call**](https://www.youtube.com/watch?v=iN2y-TK8f3A) All the features of 24.2, one convenient video! Watch it now!
* **Recording available**: [**v24.4 Release Call**](https://www.youtube.com/watch?v=dtUqgcfOGmE) All the features of 24.4, one convenient video! Watch it now!
## Interested in joining ClickHouse and making it your full-time job?

3
SECURITY.md
View File

@ -13,9 +13,10 @@ The following versions of ClickHouse server are currently being supported with s
| Version | Supported |
|:-|:-|
| 24.4 | ✔️ |
| 24.3 | ✔️ |
| 24.2 | ✔️ |
| 24.1 | ✔️ |
| 24.1 | ❌ |
| 23.* | ❌ |
| 23.8 | ✔️ |
| 23.7 | ❌ |

8
base/base/DecomposedFloat.h
View File

@ -51,11 +51,9 @@ struct DecomposedFloat
/// Returns 0 for both +0. and -0.
int sign() const
{
return (exponent() == 0 && mantissa() == 0)
? 0
: (isNegative()
? -1
: 1);
if (exponent() == 0 && mantissa() == 0)
return 0;
return isNegative() ? -1 : 1;
}
uint16_t exponent() const

2
base/base/EnumReflection.h
View File

@ -11,7 +11,7 @@ namespace detail
template <is_enum E, class F, size_t ...I>
constexpr void static_for(F && f, std::index_sequence<I...>)
{
(std::forward<F>(f)(std::integral_constant<E, magic_enum::enum_value<E>(I)>()) , ...);
(f(std::integral_constant<E, magic_enum::enum_value<E>(I)>()) , ...);
}
}

4
base/base/JSON.cpp
View File

@ -651,7 +651,9 @@ std::string_view JSON::getRawString() const
Pos s = ptr_begin;
if (*s != '"')
throw JSONException(std::string("JSON: expected \", got ") + *s);
while (++s != ptr_end && *s != '"');
++s;
while (s != ptr_end && *s != '"')
++s;
if (s != ptr_end)
return std::string_view(ptr_begin + 1, s - ptr_begin - 1);
throw JSONException("JSON: incorrect syntax (expected end of string, found end of JSON).");

2
base/base/JSON.h
View File

@ -74,7 +74,7 @@ public:
const char * data() const { return ptr_begin; }
const char * dataEnd() const { return ptr_end; }
enum ElementType
enum ElementType : uint8_t
{
TYPE_OBJECT,
TYPE_ARRAY,

2
base/base/TypeList.h
View File

@ -27,7 +27,7 @@ namespace TypeListUtils /// In some contexts it's more handy to use functions in
constexpr Root<Args...> changeRoot(TypeList<Args...>) { return {}; }
template <typename F, typename ...Args>
constexpr void forEach(TypeList<Args...>, F && f) { (std::forward<F>(f)(TypeList<Args>{}), ...); }
constexpr void forEach(TypeList<Args...>, F && f) { (f(TypeList<Args>{}), ...); }
}
template <typename TypeListLeft, typename TypeListRight>

26
base/base/cgroupsv2.cpp
View File

@ -9,11 +9,18 @@
bool cgroupsV2Enabled()
{
#if defined(OS_LINUX)
try
{
/// This file exists iff the host has cgroups v2 enabled.
auto controllers_file = default_cgroups_mount / "cgroup.controllers";
if (!std::filesystem::exists(controllers_file))
return false;
return true;
}
catch (const std::filesystem::filesystem_error &) /// all "underlying OS API errors", typically: permission denied
{
return false; /// not logging the exception as most callers fall back to cgroups v1
}
#else
return false;
#endif
@ -23,18 +30,17 @@ bool cgroupsV2MemoryControllerEnabled()
{
#if defined(OS_LINUX)
chassert(cgroupsV2Enabled());
/// According to https://docs.kernel.org/admin-guide/cgroup-v2.html:
/// - file 'cgroup.controllers' defines which controllers *can* be enabled
/// - file 'cgroup.subtree_control' defines which controllers *are* enabled
/// Caveat: nested groups may disable controllers. For simplicity, check only the top-level group.
std::ifstream subtree_control_file(default_cgroups_mount / "cgroup.subtree_control");
if (!subtree_control_file.is_open())
/// According to https://docs.kernel.org/admin-guide/cgroup-v2.html, file "cgroup.controllers" defines which controllers are available
/// for the current + child cgroups. The set of available controllers can be restricted from level to level using file
/// "cgroups.subtree_control". It is therefore sufficient to check the bottom-most nested "cgroup.controllers" file.
std::string cgroup = cgroupV2OfProcess();
auto cgroup_dir = cgroup.empty() ? default_cgroups_mount : (default_cgroups_mount / cgroup);
std::ifstream controllers_file(cgroup_dir / "cgroup.controllers");
if (!controllers_file.is_open())
return false;
std::string controllers;
std::getline(subtree_control_file, controllers);
if (controllers.find("memory") == std::string::npos)
return false;
return true;
std::getline(controllers_file, controllers);
return controllers.find("memory") != std::string::npos;
#else
return false;
#endif

2
base/base/constexpr_helpers.h
View File

@ -21,7 +21,7 @@ bool func_wrapper(Func && func, Arg && arg)
template <typename T, T Begin, typename Func, T... Is>
constexpr bool static_for_impl(Func && f, std::integer_sequence<T, Is...>)
{
return (func_wrapper(std::forward<Func>(f), std::integral_constant<T, Begin + Is>{}) || ...);
return (func_wrapper(f, std::integral_constant<T, Begin + Is>{}) || ...);
}
template <auto Begin, decltype(Begin) End, typename Func>

4
base/base/defines.h
View File

@ -28,8 +28,8 @@
#define NO_INLINE __attribute__((__noinline__))
#define MAY_ALIAS __attribute__((__may_alias__))
#if !defined(__x86_64__) && !defined(__aarch64__) && !defined(__PPC__) && !defined(__s390x__) && !(defined(__riscv) && (__riscv_xlen == 64))
# error "The only supported platforms are x86_64 and AArch64, PowerPC (work in progress), s390x (work in progress) and RISC-V 64 (experimental)"
#if !defined(__x86_64__) && !defined(__aarch64__) && !defined(__PPC__) && !defined(__s390x__) && !(defined(__loongarch64)) && !(defined(__riscv) && (__riscv_xlen == 64))
# error "The only supported platforms are x86_64 and AArch64, PowerPC (work in progress), s390x (work in progress), loongarch64 (experimental) and RISC-V 64 (experimental)"
#endif
/// Check for presence of address sanitizer

2
base/base/find_symbols.h
View File

@ -147,7 +147,7 @@ constexpr uint16_t maybe_negate(uint16_t x)
return ~x;
}
enum class ReturnMode
enum class ReturnMode : uint8_t
{
End,
Nullptr,

3
base/base/getMemoryAmount.cpp
View File

@ -77,8 +77,7 @@ uint64_t getMemoryAmountOrZero()
{
uint64_t limit_v1;
if (limit_file_v1 >> limit_v1)
if (limit_v1 < memory_amount)
memory_amount = limit_v1;
memory_amount = std::min(memory_amount, limit_v1);
}
}

10
base/base/hex.h
View File

@ -146,7 +146,7 @@ namespace impl
TUInt res;
if constexpr (sizeof(TUInt) == 1)
{
res = static_cast<UInt8>(unhexDigit(data[0])) * 0x10 + static_cast<UInt8>(unhexDigit(data[1]));
res = unhexDigit(data[0]) * 0x10 + unhexDigit(data[1]);
}
else if constexpr (sizeof(TUInt) == 2)
{
@ -176,17 +176,19 @@ namespace impl
};
/// Helper template class to convert a value of any supported type to hexadecimal representation and back.
template <typename T, typename SFINAE = void>
template <typename T>
struct HexConversion;
template <typename TUInt>
struct HexConversion<TUInt, std::enable_if_t<std::is_integral_v<TUInt>>> : public HexConversionUInt<TUInt> {};
requires(std::is_integral_v<TUInt>)
struct HexConversion<TUInt> : public HexConversionUInt<TUInt> {};
template <size_t Bits, typename Signed>
struct HexConversion<wide::integer<Bits, Signed>> : public HexConversionUInt<wide::integer<Bits, Signed>> {};
template <typename CityHashUInt128> /// Partial specialization here allows not to include <city.h> in this header.
struct HexConversion<CityHashUInt128, std::enable_if_t<std::is_same_v<CityHashUInt128, typename CityHash_v1_0_2::uint128>>>
requires(std::is_same_v<CityHashUInt128, typename CityHash_v1_0_2::uint128>)
struct HexConversion<CityHashUInt128>
{
static const constexpr size_t num_hex_digits = 32;

30
base/base/iostream_debug_helpers.h
View File

@ -20,24 +20,26 @@ Out & dumpValue(Out &, T &&);
/// Catch-all case.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == -1, Out> & dumpImpl(Out & out, T &&) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == -1)
Out & dumpImpl(Out & out, T &&) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << "{...}";
}
/// An object, that could be output with operator <<.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 0, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::declval<Out &>() << std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 0)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::declval<Out &>() << std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << x;
}
/// A pointer-like object.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 1
requires(priority == 1
/// Protect from the case when operator * do effectively nothing (function pointer).
&& !std::is_same_v<std::decay_t<T>, std::decay_t<decltype(*std::declval<T>())>>
, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(*std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
&& !std::is_same_v<std::decay_t<T>, std::decay_t<decltype(*std::declval<T>())>>)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(*std::declval<T>())> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
if (!x)
return out << "nullptr";
@ -46,7 +48,8 @@ std::enable_if_t<priority == 1
/// Container.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 2, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::begin(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 2)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::begin(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
bool first = true;
out << "{";
@ -63,8 +66,8 @@ std::enable_if_t<priority == 2, Out> & dumpImpl(Out & out, T && x, std::decay_t<
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && std::is_enum_v<std::decay_t<T>>, Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && std::is_enum_v<std::decay_t<T>>)
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << magic_enum::enum_name(x);
}
@ -72,8 +75,8 @@ dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
/// string and const char * - output not as container or pointer.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && (std::is_same_v<std::decay_t<T>, std::string> || std::is_same_v<std::decay_t<T>, const char *>), Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && (std::is_same_v<std::decay_t<T>, std::string> || std::is_same_v<std::decay_t<T>, const char *>))
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << std::quoted(x);
}
@ -81,8 +84,8 @@ dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
/// UInt8 - output as number, not char.
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 3 && std::is_same_v<std::decay_t<T>, unsigned char>, Out> &
dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 3 && std::is_same_v<std::decay_t<T>, unsigned char>)
Out & dumpImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return out << int(x);
}
@ -108,7 +111,8 @@ Out & dumpTupleImpl(Out & out, T && x) // NOLINT(cppcoreguidelines-missing-std-f
}
template <int priority, typename Out, typename T>
std::enable_if_t<priority == 4, Out> & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::get<0>(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
requires(priority == 4)
Out & dumpImpl(Out & out, T && x, std::decay_t<decltype(std::get<0>(std::declval<T>()))> * = nullptr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
return dumpTupleImpl<0>(out, x);
}

6
base/base/itoa.cpp
View File

@ -250,14 +250,16 @@ ALWAYS_INLINE inline char * uitoa<UnsignedOfSize<1>, 1>(char * p, UnsignedOfSize
//===----------------------------------------------------------===//
// itoa: handle unsigned integral operands (selected by SFINAE)
template <typename U, std::enable_if_t<!std::is_signed_v<U> && std::is_integral_v<U>> * = nullptr>
template <typename U>
requires(!std::is_signed_v<U> && std::is_integral_v<U>)
ALWAYS_INLINE inline char * itoa(U u, char * p)
{
return convert::uitoa(p, u);
}
// itoa: handle signed integral operands (selected by SFINAE)
template <typename I, size_t N = sizeof(I), std::enable_if_t<std::is_signed_v<I> && std::is_integral_v<I>> * = nullptr>
template <typename I, size_t N = sizeof(I)>
requires(std::is_signed_v<I> && std::is_integral_v<I>)
ALWAYS_INLINE inline char * itoa(I i, char * p)
{
// Need "mask" to be filled with a copy of the sign bit.

12
base/base/map.h
View File

@ -19,8 +19,8 @@ auto map(const Collection<Params...> & collection, Mapper && mapper)
using value_type = unqualified_t<decltype(mapper(*std::begin(collection)))>;
return Collection<value_type>(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
/** \brief Returns collection of specified container-type,
@ -33,8 +33,8 @@ auto map(const Collection & collection, Mapper && mapper)
using value_type = unqualified_t<decltype(mapper(*std::begin(collection)))>;
return ResultCollection<value_type>(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
/** \brief Returns collection of specified type,
@ -45,8 +45,8 @@ template <typename ResultCollection, typename Collection, typename Mapper>
auto map(const Collection & collection, Mapper && mapper)
{
return ResultCollection(
boost::make_transform_iterator(std::begin(collection), std::forward<Mapper>(mapper)),
boost::make_transform_iterator(std::end(collection), std::forward<Mapper>(mapper)));
boost::make_transform_iterator(std::begin(collection), mapper),
boost::make_transform_iterator(std::end(collection), mapper));
}
}

12
base/base/range.h
View File

@ -23,12 +23,10 @@ namespace internal
/// For loop adaptor which is used to iterate through a half-closed interval [begin, end).
/// The parameters `begin` and `end` can have any integral or enum types.
template <typename BeginType,
typename EndType,
typename = std::enable_if_t<
(std::is_integral_v<BeginType> || std::is_enum_v<BeginType>) &&
template <typename BeginType, typename EndType>
requires((std::is_integral_v<BeginType> || std::is_enum_v<BeginType>) &&
(std::is_integral_v<EndType> || std::is_enum_v<EndType>) &&
(!std::is_enum_v<BeginType> || !std::is_enum_v<EndType> || std::is_same_v<BeginType, EndType>), void>>
(!std::is_enum_v<BeginType> || !std::is_enum_v<EndType> || std::is_same_v<BeginType, EndType>))
inline auto range(BeginType begin, EndType end)
{
if constexpr (std::is_integral_v<BeginType> && std::is_integral_v<EndType>)
@ -50,8 +48,8 @@ inline auto range(BeginType begin, EndType end)
/// For loop adaptor which is used to iterate through a half-closed interval [0, end).
/// The parameter `end` can have any integral or enum type.
/// The same as range(0, end).
template <typename Type,
typename = std::enable_if_t<std::is_integral_v<Type> || std::is_enum_v<Type>, void>>
template <typename Type>
requires(std::is_integral_v<Type> || std::is_enum_v<Type>)
inline auto range(Type end)
{
if constexpr (std::is_integral_v<Type>)

6
base/base/scope_guard.h
View File

@ -29,11 +29,13 @@ public:
requires std::is_convertible_v<G, F>
constexpr BasicScopeGuard & operator=(BasicScopeGuard<G> && src) // NOLINT(cppcoreguidelines-rvalue-reference-param-not-moved, cppcoreguidelines-noexcept-move-operations)
{
if (this != &src)
if constexpr (std::is_same_v<G, F>)
{
if (this == &src)
return *this;
}
invoke();
function = src.release();
}
return *this;
}

4
base/base/sleep.cpp
View File

@ -2,6 +2,7 @@
#include <ctime>
#include <cerrno>
#include <system_error>
#if defined(OS_DARWIN)
#include <mach/mach.h>
@ -34,7 +35,8 @@ void sleepForNanoseconds(uint64_t nanoseconds)
constexpr auto clock_type = CLOCK_MONOTONIC;
struct timespec current_time;
clock_gettime(clock_type, &current_time);
if (0 != clock_gettime(clock_type, &current_time))
throw std::system_error(std::error_code(errno, std::system_category()));
constexpr uint64_t resolution = 1'000'000'000;
struct timespec finish_time = current_time;

10
base/base/wide_integer.h
View File

@ -111,7 +111,8 @@ public:
constexpr explicit operator bool() const noexcept;
template <typename T, typename = std::enable_if_t<std::is_arithmetic_v<T>, T>>
template <typename T>
requires(std::is_arithmetic_v<T>)
constexpr operator T() const noexcept;
constexpr operator long double() const noexcept;
@ -208,12 +209,14 @@ constexpr integer<Bits, Signed> operator<<(const integer<Bits, Signed> & lhs, in
template <size_t Bits, typename Signed>
constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, int n) noexcept;
template <size_t Bits, typename Signed, typename Int, typename = std::enable_if_t<!std::is_same_v<Int, int>>>
template <size_t Bits, typename Signed, typename Int>
requires(!std::is_same_v<Int, int>)
constexpr integer<Bits, Signed> operator<<(const integer<Bits, Signed> & lhs, Int n) noexcept
{
return lhs << int(n);
}
template <size_t Bits, typename Signed, typename Int, typename = std::enable_if_t<!std::is_same_v<Int, int>>>
template <size_t Bits, typename Signed, typename Int>
requires(!std::is_same_v<Int, int>)
constexpr integer<Bits, Signed> operator>>(const integer<Bits, Signed> & lhs, Int n) noexcept
{
return lhs >> int(n);
@ -262,4 +265,3 @@ struct hash<wide::integer<Bits, Signed>>;
// NOLINTEND(*)
#include "wide_integer_impl.h"

3
base/base/wide_integer_impl.h
View File

@ -1246,7 +1246,8 @@ constexpr integer<Bits, Signed>::operator bool() const noexcept
}
template <size_t Bits, typename Signed>
template <class T, class>
template <class T>
requires(std::is_arithmetic_v<T>)
constexpr integer<Bits, Signed>::operator T() const noexcept
{
static_assert(std::numeric_limits<T>::is_integer);

9
base/poco/Crypto/src/OpenSSLInitializer.cpp
View File

@ -23,6 +23,9 @@
#include <openssl/conf.h>
#endif
#if __has_feature(address_sanitizer)
#include <sanitizer/lsan_interface.h>
#endif
using Poco::RandomInputStream;
using Poco::Thread;
@ -71,7 +74,13 @@ void OpenSSLInitializer::initialize()
char seed[SEEDSIZE];
RandomInputStream rnd;
rnd.read(seed, sizeof(seed));
{
# if __has_feature(address_sanitizer)
/// Leak sanitizer (part of address sanitizer) thinks that a few bytes of memory in OpenSSL are allocated during but never released.
__lsan::ScopedDisabler lsan_disabler;
#endif
RAND_seed(seed, SEEDSIZE);
}
int nMutexes = CRYPTO_num_locks();
_mutexes = new Poco::FastMutex[nMutexes];

10
base/poco/Foundation/include/Poco/Message.h
View File

@ -66,9 +66,11 @@ public:
/// The thread and process ids are set.
Message(
const std::string & source, const std::string & text, Priority prio, const char * file, int line, std::string_view fmt_str = {});
const std::string & source, const std::string & text, Priority prio, const char * file, int line,
std::string_view fmt_str = {}, const std::vector<std::string> & fmt_str_args = {});
Message(
std::string && source, std::string && text, Priority prio, const char * file, int line, std::string_view fmt_str);
std::string && source, std::string && text, Priority prio, const char * file, int line,
std::string_view fmt_str, std::vector<std::string> && fmt_str_args);
/// Creates a Message with the given source, text, priority,
/// source file path and line.
///
@ -161,6 +163,9 @@ public:
std::string_view getFormatString() const;
void setFormatString(std::string_view fmt_str);
const std::vector<std::string> & getFormatStringArgs() const;
void setFormatStringArgs(const std::vector<std::string> & fmt_str_args);
int getSourceLine() const;
/// Returns the source file line of the statement
/// generating the log message. May be 0
@ -210,6 +215,7 @@ private:
int _line;
StringMap * _pMap;
std::string_view _fmt_str;
std::vector<std::string> _fmt_str_args;
};

4
base/poco/Foundation/include/Poco/Platform.h
View File

@ -120,6 +120,7 @@
#define POCO_ARCH_AARCH64 0x0f
#define POCO_ARCH_ARM64 0x0f // same as POCO_ARCH_AARCH64
#define POCO_ARCH_RISCV64 0x10
#define POCO_ARCH_LOONGARCH64 0x12
#if defined(__ALPHA) || defined(__alpha) || defined(__alpha__) || defined(_M_ALPHA)
@ -209,6 +210,9 @@
#elif defined(__riscv) && (__riscv_xlen == 64)
# define POCO_ARCH POCO_ARCH_RISCV64
# define POCO_ARCH_LITTLE_ENDIAN 1
#elif defined(__loongarch64)
# define POCO_ARCH POCO_ARCH_LOONGARCH64
# define POCO_ARCH_LITTLE_ENDIAN 1
#endif

32
base/poco/Foundation/src/Message.cpp
View File

@ -46,7 +46,9 @@ Message::Message(const std::string& source, const std::string& text, Priority pr
}
Message::Message(const std::string& source, const std::string& text, Priority prio, const char* file, int line, std::string_view fmt_str):
Message::Message(
const std::string& source, const std::string& text, Priority prio, const char* file, int line,
std::string_view fmt_str, const std::vector<std::string>& fmt_str_args):
_source(source),
_text(text),
_prio(prio),
@ -54,13 +56,16 @@ Message::Message(const std::string& source, const std::string& text, Priority pr
_file(file),
_line(line),
_pMap(0),
_fmt_str(fmt_str)
_fmt_str(fmt_str),
_fmt_str_args(fmt_str_args)
{
init();
}
Message::Message(std::string && source, std::string && text, Priority prio, const char * file, int line, std::string_view fmt_str):
Message::Message(
std::string && source, std::string && text, Priority prio, const char * file, int line,
std::string_view fmt_str, std::vector<std::string> && fmt_str_args):
_source(std::move(source)),
_text(std::move(text)),
_prio(prio),
@ -68,7 +73,8 @@ Message::Message(std::string && source, std::string && text, Priority prio, cons
_file(file),
_line(line),
_pMap(0),
_fmt_str(fmt_str)
_fmt_str(fmt_str),
_fmt_str_args(std::move(fmt_str_args))
{
init();
}
@ -83,7 +89,8 @@ Message::Message(const Message& msg):
_pid(msg._pid),
_file(msg._file),
_line(msg._line),
_fmt_str(msg._fmt_str)
_fmt_str(msg._fmt_str),
_fmt_str_args(msg._fmt_str_args)
{
if (msg._pMap)
_pMap = new StringMap(*msg._pMap);
@ -102,7 +109,8 @@ Message::Message(const Message& msg, const std::string& text):
_pid(msg._pid),
_file(msg._file),
_line(msg._line),
_fmt_str(msg._fmt_str)
_fmt_str(msg._fmt_str),
_fmt_str_args(msg._fmt_str_args)
{
if (msg._pMap)
_pMap = new StringMap(*msg._pMap);
@ -154,6 +162,7 @@ void Message::swap(Message& msg)
swap(_line, msg._line);
swap(_pMap, msg._pMap);
swap(_fmt_str, msg._fmt_str);
swap(_fmt_str_args, msg._fmt_str_args);
}
@ -227,6 +236,17 @@ void Message::setFormatString(std::string_view fmt_str)
}
const std::vector<std::string>& Message::getFormatStringArgs() const
{
return _fmt_str_args;
}
void Message::setFormatStringArgs(const std::vector<std::string>& fmt_str_args)
{
_fmt_str_args = fmt_str_args;
}
bool Message::has(const std::string& param) const
{
return _pMap && (_pMap->find(param) != _pMap->end());

5
base/poco/Net/include/Poco/Net/NameValueCollection.h
View File

@ -79,6 +79,11 @@ namespace Net
/// Returns the value of the first name-value pair with the given name.
/// If no value with the given name has been found, the defaultValue is returned.
const std::vector<std::reference_wrapper<const std::string>> getAll(const std::string & name) const;
/// Returns all values of all name-value pairs with the given name.
///
/// Returns an empty vector if there are no name-value pairs with the given name.
bool has(const std::string & name) const;
/// Returns true if there is at least one name-value pair
/// with the given name.

10
base/poco/Net/src/NameValueCollection.cpp
View File

@ -15,6 +15,7 @@
#include "Poco/Net/NameValueCollection.h"
#include "Poco/Exception.h"
#include <algorithm>
#include <functional>
using Poco::NotFoundException;
@ -101,6 +102,15 @@ const std::string& NameValueCollection::get(const std::string& name, const std::
return defaultValue;
}
const std::vector<std::reference_wrapper<const std::string>> NameValueCollection::getAll(const std::string& name) const
{
std::vector<std::reference_wrapper<const std::string>> values;
for (ConstIterator it = _map.find(name); it != _map.end(); it++)
if (it->first == name)
values.push_back(it->second);
return values;
}
bool NameValueCollection::has(const std::string& name) const
{

1
base/poco/NetSSL_OpenSSL/src/Context.cpp
View File

@ -592,6 +592,7 @@ void Context::createSSLContext()
SSL_CTX_set_default_passwd_cb(_pSSLContext, &SSLManager::privateKeyPassphraseCallback);
Utility::clearErrorStack();
SSL_CTX_set_options(_pSSLContext, SSL_OP_ALL);
SSL_CTX_set_options(_pSSLContext, SSL_OP_IGNORE_UNEXPECTED_EOF);
}

41
base/poco/NetSSL_OpenSSL/src/SSLManager.cpp
View File

@ -330,26 +330,27 @@ void SSLManager::initDefaultContext(bool server)
else
_ptrDefaultClientContext->disableProtocols(disabledProtocols);
bool cacheSessions = config.getBool(prefix + CFG_CACHE_SESSIONS, false);
if (server)
{
std::string sessionIdContext = config.getString(prefix + CFG_SESSION_ID_CONTEXT, config.getString("application.name", ""));
_ptrDefaultServerContext->enableSessionCache(cacheSessions, sessionIdContext);
if (config.hasProperty(prefix + CFG_SESSION_CACHE_SIZE))
{
int cacheSize = config.getInt(prefix + CFG_SESSION_CACHE_SIZE);
_ptrDefaultServerContext->setSessionCacheSize(cacheSize);
}
if (config.hasProperty(prefix + CFG_SESSION_TIMEOUT))
{
int timeout = config.getInt(prefix + CFG_SESSION_TIMEOUT);
_ptrDefaultServerContext->setSessionTimeout(timeout);
}
}
else
{
_ptrDefaultClientContext->enableSessionCache(cacheSessions);
}
/// Temporarily disabled during the transition from boringssl to OpenSSL due to tsan issues.
/// bool cacheSessions = config.getBool(prefix + CFG_CACHE_SESSIONS, false);
/// if (server)
/// {
/// std::string sessionIdContext = config.getString(prefix + CFG_SESSION_ID_CONTEXT, config.getString("application.name", ""));
/// _ptrDefaultServerContext->enableSessionCache(cacheSessions, sessionIdContext);
/// if (config.hasProperty(prefix + CFG_SESSION_CACHE_SIZE))
/// {
/// int cacheSize = config.getInt(prefix + CFG_SESSION_CACHE_SIZE);
/// _ptrDefaultServerContext->setSessionCacheSize(cacheSize);
/// }
/// if (config.hasProperty(prefix + CFG_SESSION_TIMEOUT))
/// {
/// int timeout = config.getInt(prefix + CFG_SESSION_TIMEOUT);
/// _ptrDefaultServerContext->setSessionTimeout(timeout);
/// }
/// }
/// else
/// {
/// _ptrDefaultClientContext->enableSessionCache(cacheSessions);
/// }
bool extendedVerification = config.getBool(prefix + CFG_EXTENDED_VERIFICATION, false);
if (server)
_ptrDefaultServerContext->enableExtendedCertificateVerification(extendedVerification);

2
cmake/arch.cmake
View File

@ -11,6 +11,8 @@ elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(s390x.*|S390X.*)")
set (ARCH_S390X 1)
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "riscv64")
set (ARCH_RISCV64 1)
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "loongarch64")
set (ARCH_LOONGARCH64 1)
else ()
message (FATAL_ERROR "Platform ${CMAKE_SYSTEM_PROCESSOR} is not supported")
endif ()

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54485)
SET(VERSION_REVISION 54487)
SET(VERSION_MAJOR 24)
SET(VERSION_MINOR 4)
SET(VERSION_MINOR 6)
SET(VERSION_PATCH 1)
SET(VERSION_GITHASH 2c5c589a882ceec35439650337b92db3e76f0081)
SET(VERSION_DESCRIBE v24.4.1.1-testing)
SET(VERSION_STRING 24.4.1.1)
SET(VERSION_GITHASH 70a1d3a63d47f0be077d67b8deb907230fc7cfb0)
SET(VERSION_DESCRIBE v24.6.1.1-testing)
SET(VERSION_STRING 24.6.1.1)
# end of autochange

4
cmake/clang_tidy.cmake
View File

@ -5,14 +5,14 @@ if (ENABLE_CLANG_TIDY)
find_program (CLANG_TIDY_CACHE_PATH NAMES "clang-tidy-cache")
if (CLANG_TIDY_CACHE_PATH)
find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-17" "clang-tidy-16" "clang-tidy")
find_program (_CLANG_TIDY_PATH NAMES "clang-tidy-18" "clang-tidy-17" "clang-tidy-16" "clang-tidy")
# Why do we use ';' here?
# It's a cmake black magic: https://cmake.org/cmake/help/latest/prop_tgt/LANG_CLANG_TIDY.html#prop_tgt:%3CLANG%3E_CLANG_TIDY
# The CLANG_TIDY_PATH is passed to CMAKE_CXX_CLANG_TIDY, which follows CXX_CLANG_TIDY syntax.
set (CLANG_TIDY_PATH "${CLANG_TIDY_CACHE_PATH};${_CLANG_TIDY_PATH}" CACHE STRING "A combined command to run clang-tidy with caching wrapper")
else ()
find_program (CLANG_TIDY_PATH NAMES "clang-tidy-17" "clang-tidy-16" "clang-tidy")
find_program (CLANG_TIDY_PATH NAMES "clang-tidy-18" "clang-tidy-17" "clang-tidy-16" "clang-tidy")
endif ()
if (CLANG_TIDY_PATH)

16
cmake/freebsd/default_libs.cmake
View File

@ -1,11 +1,23 @@
set (DEFAULT_LIBS "-nodefaultlibs")
if (${CMAKE_SYSTEM_PROCESSOR} STREQUAL "amd64")
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --print-file-name=libclang_rt.builtins-x86_64.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
set(system_processor "x86_64")
else ()
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --print-file-name=libclang_rt.builtins-${CMAKE_SYSTEM_PROCESSOR}.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
set(system_processor "${CMAKE_SYSTEM_PROCESSOR}")
endif ()
file(GLOB bprefix "/usr/local/llvm${COMPILER_VERSION_MAJOR}/lib/clang/${COMPILER_VERSION_MAJOR}/lib/${system_processor}-portbld-freebsd*/")
message(STATUS "-Bprefix: ${bprefix}")
execute_process(COMMAND ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins-${system_processor}.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
# --print-file-name simply prints what you passed in case of nothing was resolved, so let's try one other possible option
if (BUILTINS_LIBRARY STREQUAL "libclang_rt.builtins-${system_processor}.a")
execute_process(COMMAND ${CMAKE_CXX_COMPILER} -Bprefix=${bprefix} --print-file-name=libclang_rt.builtins.a OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
endif()
if (BUILTINS_LIBRARY STREQUAL "libclang_rt.builtins.a")
message(FATAL_ERROR "libclang_rt.builtins had not been found")
endif()
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${COVERAGE_OPTION} -lc -lm -lrt -lpthread")
message(STATUS "Default libraries: ${DEFAULT_LIBS}")

17
cmake/linux/default_libs.cmake
View File

@ -5,21 +5,24 @@ set (DEFAULT_LIBS "-nodefaultlibs")
# We need builtins from Clang's RT even without libcxx - for ubsan+int128.
# See https://bugs.llvm.org/show_bug.cgi?id=16404
if (COMPILER_CLANG)
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
execute_process (COMMAND ${CMAKE_CXX_COMPILER} --target=${CMAKE_CXX_COMPILER_TARGET} --print-libgcc-file-name --rtlib=compiler-rt OUTPUT_VARIABLE BUILTINS_LIBRARY OUTPUT_STRIP_TRAILING_WHITESPACE)
if (NOT EXISTS "${BUILTINS_LIBRARY}")
# Apparently, in clang-19, the UBSan support library for C++ was moved out into ubsan_standalone_cxx.a, so we have to include both.
if (SANITIZE STREQUAL undefined)
string(REPLACE "builtins.a" "ubsan_standalone_cxx.a" EXTRA_BUILTINS_LIBRARY "${BUILTINS_LIBRARY}")
endif ()
if (NOT EXISTS "${BUILTINS_LIBRARY}")
set (BUILTINS_LIBRARY "-lgcc")
endif ()
endif ()
if (OS_ANDROID)
# pthread and rt are included in libc
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${COVERAGE_OPTION} -lc -lm -ldl")
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${EXTRA_BUILTINS_LIBRARY} ${COVERAGE_OPTION} -lc -lm -ldl")
elseif (USE_MUSL)
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${COVERAGE_OPTION} -static -lc")
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${EXTRA_BUILTINS_LIBRARY} ${COVERAGE_OPTION} -static -lc")
else ()
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${COVERAGE_OPTION} -lc -lm -lrt -lpthread -ldl")
set (DEFAULT_LIBS "${DEFAULT_LIBS} ${BUILTINS_LIBRARY} ${EXTRA_BUILTINS_LIBRARY} ${COVERAGE_OPTION} -lc -lm -lrt -lpthread -ldl")
endif ()
message(STATUS "Default libraries: ${DEFAULT_LIBS}")

23
cmake/linux/toolchain-loongarch64.cmake Normal file
View File

@ -0,0 +1,23 @@
# See linux/toolchain-x86_64.cmake for details about multiple load of toolchain file.
include_guard(GLOBAL)
set (CMAKE_TRY_COMPILE_TARGET_TYPE STATIC_LIBRARY)
set (CMAKE_SYSTEM_NAME "Linux")
set (CMAKE_SYSTEM_PROCESSOR "loongarch64")
set (CMAKE_C_COMPILER_TARGET "loongarch64-linux-gnu")
set (CMAKE_CXX_COMPILER_TARGET "loongarch64-linux-gnu")
set (CMAKE_ASM_COMPILER_TARGET "loongarch64-linux-gnu")
# Adding `-mcmodel=extreme` is to handle the link error:
# relocation R_LARCH_B26 out of range: 194148892 is not in [-134217728, 134217727]
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcmodel=extreme")
set(CMAKE_CXX_FLAGS "${CMAKE_C_FLAGS} -mcmodel=extreme")
set (CMAKE_SYSROOT "${CMAKE_CURRENT_LIST_DIR}/../../contrib/sysroot/linux-loongarch64")
set (TOOLCHAIN_PATH "${CMAKE_CURRENT_LIST_DIR}/../../contrib/sysroot/linux-loongarch64/usr")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} --gcc-toolchain=${TOOLCHAIN_PATH}")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} --gcc-toolchain=${TOOLCHAIN_PATH}")
set (CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} --gcc-toolchain=${TOOLCHAIN_PATH}")

7
cmake/sanitize.cmake
View File

@ -8,9 +8,6 @@ option (SANITIZE "Enable one of the code sanitizers" "")
set (SAN_FLAGS "${SAN_FLAGS} -g -fno-omit-frame-pointer -DSANITIZER")
# It's possible to pass an ignore list to sanitizers (-fsanitize-ignorelist). Intentionally not doing this because
# 1. out-of-source suppressions are awkward 2. it seems ignore lists don't work after the Clang v16 upgrade (#49829)
if (SANITIZE)
if (SANITIZE STREQUAL "address")
set (ASAN_FLAGS "-fsanitize=address -fsanitize-address-use-after-scope")
@ -29,9 +26,7 @@ if (SANITIZE)
elseif (SANITIZE STREQUAL "thread")
set (TSAN_FLAGS "-fsanitize=thread")
if (COMPILER_CLANG)
set (TSAN_FLAGS "${TSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/tsan_ignorelist.txt")
endif()
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_FLAGS} ${TSAN_FLAGS}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_FLAGS} ${TSAN_FLAGS}")
@ -47,9 +42,7 @@ if (SANITIZE)
# that's why we often receive reports about UIO. The simplest way to avoid this is just set this flag here.
set(UBSAN_FLAGS "${UBSAN_FLAGS} -fno-sanitize=unsigned-integer-overflow")
endif()
if (COMPILER_CLANG)
set (UBSAN_FLAGS "${UBSAN_FLAGS} -fsanitize-ignorelist=${PROJECT_SOURCE_DIR}/tests/ubsan_ignorelist.txt")
endif()
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SAN_FLAGS} ${UBSAN_FLAGS}")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SAN_FLAGS} ${UBSAN_FLAGS}")

19
cmake/target.cmake
View File

@ -41,10 +41,7 @@ if (CMAKE_CROSSCOMPILING)
set (ENABLE_ICU OFF CACHE INTERNAL "")
set (ENABLE_FASTOPS OFF CACHE INTERNAL "")
elseif (OS_LINUX OR OS_ANDROID)
if (ARCH_AARCH64)
# FIXME: broken dependencies
set (ENABLE_GRPC OFF CACHE INTERNAL "")
elseif (ARCH_PPC64LE)
if (ARCH_PPC64LE)
set (ENABLE_GRPC OFF CACHE INTERNAL "")
elseif (ARCH_RISCV64)
# RISC-V support is preliminary
@ -61,6 +58,20 @@ if (CMAKE_CROSSCOMPILING)
elseif (ARCH_S390X)
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_RUST OFF CACHE INTERNAL "")
elseif (ARCH_LOONGARCH64)
set (GLIBC_COMPATIBILITY OFF CACHE INTERNAL "")
set (ENABLE_LDAP OFF CACHE INTERNAL "")
set (OPENSSL_NO_ASM ON CACHE INTERNAL "")
set (ENABLE_JEMALLOC OFF CACHE INTERNAL "")
set (ENABLE_PARQUET OFF CACHE INTERNAL "")
set (ENABLE_GRPC OFF CACHE INTERNAL "")
set (ENABLE_HDFS OFF CACHE INTERNAL "")
set (ENABLE_MYSQL OFF CACHE INTERNAL "")
set (ENABLE_RUST OFF CACHE INTERNAL "")
set (ENABLE_LIBPQXX OFF CACHE INTERNAL "")
set (ENABLE_EMBEDDED_COMPILER OFF CACHE INTERNAL "")
set (ENABLE_DWARF_PARSER OFF CACHE INTERNAL "")
set (ENABLE_BLAKE3 OFF CACHE INTERNAL "")
endif ()
elseif (OS_FREEBSD)
# FIXME: broken dependencies

55
cmake/tools.cmake
View File

@ -1,10 +1,6 @@
# Compiler
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
set (COMPILER_CLANG 1) # Safe to treat AppleClang as a regular Clang, in general.
elseif (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
set (COMPILER_CLANG 1)
else ()
if (NOT CMAKE_CXX_COMPILER_ID MATCHES "Clang")
message (FATAL_ERROR "Compiler ${CMAKE_CXX_COMPILER_ID} is not supported")
endif ()
@ -13,12 +9,11 @@ execute_process(COMMAND ${CMAKE_CXX_COMPILER} --version OUTPUT_VARIABLE COMPILER
message (STATUS "Using compiler:\n${COMPILER_SELF_IDENTIFICATION}")
# Require minimum compiler versions
set (CLANG_MINIMUM_VERSION 16)
set (CLANG_MINIMUM_VERSION 17)
set (XCODE_MINIMUM_VERSION 12.0)
set (APPLE_CLANG_MINIMUM_VERSION 12.0.0)
if (COMPILER_CLANG)
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
if (CMAKE_CXX_COMPILER_ID MATCHES "AppleClang")
# (Experimental!) Specify "-DALLOW_APPLECLANG=ON" when running CMake configuration step, if you want to experiment with using it.
if (NOT ALLOW_APPLECLANG AND NOT DEFINED ENV{ALLOW_APPLECLANG})
message (FATAL_ERROR "Compilation with AppleClang is unsupported. Please use vanilla Clang, e.g. from Homebrew.")
@ -28,19 +23,16 @@ if (COMPILER_CLANG)
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${APPLE_CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with AppleClang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${APPLE_CLANG_MINIMUM_VERSION} (Xcode ${XCODE_MINIMUM_VERSION}).")
endif ()
else ()
else ()
if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS ${CLANG_MINIMUM_VERSION})
message (FATAL_ERROR "Compilation with Clang version ${CMAKE_CXX_COMPILER_VERSION} is unsupported, the minimum required version is ${CLANG_MINIMUM_VERSION}.")
endif ()
endif ()
endif ()
# Linker
string (REGEX MATCHALL "[0-9]+" COMPILER_VERSION_LIST ${CMAKE_CXX_COMPILER_VERSION})
list (GET COMPILER_VERSION_LIST 0 COMPILER_VERSION_MAJOR)
# Example values: `lld-10`
# Linker
option (LINKER_NAME "Linker name or full path")
if (LINKER_NAME MATCHES "gold")
@ -48,20 +40,16 @@ if (LINKER_NAME MATCHES "gold")
endif ()
if (NOT LINKER_NAME)
if (COMPILER_CLANG)
if (OS_LINUX AND NOT ARCH_S390X)
find_program (LLD_PATH NAMES "ld.lld-${COMPILER_VERSION_MAJOR}" "ld.lld")
elseif (OS_DARWIN)
find_program (LLD_PATH NAMES "ld")
endif ()
endif ()
if (LLD_PATH)
if (OS_LINUX OR OS_DARWIN)
if (COMPILER_CLANG)
# Clang driver simply allows full linker path.
set (LINKER_NAME ${LLD_PATH})
endif ()
endif ()
endif()
endif()
@ -82,47 +70,28 @@ else ()
endif ()
# Archiver
if (COMPILER_CLANG)
find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
endif ()
find_program (LLVM_AR_PATH NAMES "llvm-ar-${COMPILER_VERSION_MAJOR}" "llvm-ar")
if (LLVM_AR_PATH)
set (CMAKE_AR "${LLVM_AR_PATH}")
endif ()
message(STATUS "Using archiver: ${CMAKE_AR}")
# Ranlib
if (COMPILER_CLANG)
find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
endif ()
find_program (LLVM_RANLIB_PATH NAMES "llvm-ranlib-${COMPILER_VERSION_MAJOR}" "llvm-ranlib")
if (LLVM_RANLIB_PATH)
set (CMAKE_RANLIB "${LLVM_RANLIB_PATH}")
endif ()
message(STATUS "Using ranlib: ${CMAKE_RANLIB}")
# Install Name Tool
if (COMPILER_CLANG)
find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
endif ()
find_program (LLVM_INSTALL_NAME_TOOL_PATH NAMES "llvm-install-name-tool-${COMPILER_VERSION_MAJOR}" "llvm-install-name-tool")
if (LLVM_INSTALL_NAME_TOOL_PATH)
set (CMAKE_INSTALL_NAME_TOOL "${LLVM_INSTALL_NAME_TOOL_PATH}")
endif ()
message(STATUS "Using install-name-tool: ${CMAKE_INSTALL_NAME_TOOL}")
# Objcopy
if (COMPILER_CLANG)
find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
endif ()
find_program (OBJCOPY_PATH NAMES "llvm-objcopy-${COMPILER_VERSION_MAJOR}" "llvm-objcopy" "objcopy")
if (OBJCOPY_PATH)
message (STATUS "Using objcopy: ${OBJCOPY_PATH}")
else ()
@ -130,11 +99,7 @@ else ()
endif ()
# Strip
if (COMPILER_CLANG)
find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
endif ()
find_program (STRIP_PATH NAMES "llvm-strip-${COMPILER_VERSION_MAJOR}" "llvm-strip" "strip")
if (STRIP_PATH)
message (STATUS "Using strip: ${STRIP_PATH}")
else ()

66
cmake/warnings.cmake
View File

@ -15,37 +15,35 @@ if ((NOT CMAKE_BUILD_TYPE_UC STREQUAL "DEBUG") AND (NOT SANITIZE) AND (NOT CMAKE
add_warning(frame-larger-than=65536)
endif ()
if (COMPILER_CLANG)
# Add some warnings that are not available even with -Wall -Wextra -Wpedantic.
# We want to get everything out of the compiler for code quality.
add_warning(everything)
add_warning(pedantic)
no_warning(zero-length-array)
no_warning(c++98-compat-pedantic)
no_warning(c++98-compat)
no_warning(c++20-compat) # Use constinit in C++20 without warnings
no_warning(sign-conversion)
no_warning(implicit-int-conversion)
no_warning(implicit-int-float-conversion)
no_warning(ctad-maybe-unsupported) # clang 9+, linux-only
no_warning(disabled-macro-expansion)
no_warning(documentation-unknown-command)
no_warning(double-promotion)
no_warning(exit-time-destructors)
no_warning(float-equal)
no_warning(global-constructors)
no_warning(missing-prototypes)
no_warning(missing-variable-declarations)
no_warning(padded)
no_warning(switch-enum)
no_warning(undefined-func-template)
no_warning(unused-template)
no_warning(vla)
no_warning(weak-template-vtables)
no_warning(weak-vtables)
no_warning(thread-safety-negative) # experimental flag, too many false positives
no_warning(enum-constexpr-conversion) # breaks magic-enum library in clang-16
no_warning(unsafe-buffer-usage) # too aggressive
no_warning(switch-default) # conflicts with "defaults in a switch covering all enum values"
# TODO Enable conversion, sign-conversion, double-promotion warnings.
endif ()
# Add some warnings that are not available even with -Wall -Wextra -Wpedantic.
# We want to get everything out of the compiler for code quality.
add_warning(everything)
add_warning(pedantic)
no_warning(zero-length-array)
no_warning(c++98-compat-pedantic)
no_warning(c++98-compat)
no_warning(c++20-compat) # Use constinit in C++20 without warnings
no_warning(sign-conversion)
no_warning(implicit-int-conversion)
no_warning(implicit-int-float-conversion)
no_warning(ctad-maybe-unsupported) # clang 9+, linux-only
no_warning(disabled-macro-expansion)
no_warning(documentation-unknown-command)
no_warning(double-promotion)
no_warning(exit-time-destructors)
no_warning(float-equal)
no_warning(global-constructors)
no_warning(missing-prototypes)
no_warning(missing-variable-declarations)
no_warning(padded)
no_warning(switch-enum)
no_warning(undefined-func-template)
no_warning(unused-template)
no_warning(vla)
no_warning(weak-template-vtables)
no_warning(weak-vtables)
no_warning(thread-safety-negative) # experimental flag, too many false positives
no_warning(enum-constexpr-conversion) # breaks magic-enum library in clang-16
no_warning(unsafe-buffer-usage) # too aggressive
no_warning(switch-default) # conflicts with "defaults in a switch covering all enum values"
# TODO Enable conversion, sign-conversion, double-promotion warnings.

8
contrib/CMakeLists.txt vendored
View File

@ -37,11 +37,7 @@ function(add_contrib cmake_folder)
message(STATUS "Adding contrib module ${base_folders} (configuring with ${cmake_folder})")
add_subdirectory (${cmake_folder})
endfunction()
if (ENABLE_OPENSSL OR ENABLE_OPENSSL_DYNAMIC)
add_contrib (openssl-cmake openssl)
else ()
add_contrib (boringssl-cmake boringssl)
endif ()
add_contrib (openssl-cmake openssl)
add_contrib (miniselect-cmake miniselect)
add_contrib (pdqsort-cmake pdqsort)
add_contrib (pocketfft-cmake pocketfft)
@ -223,6 +219,8 @@ endif ()
add_contrib (xxHash-cmake xxHash)
add_contrib (expected-cmake expected)
add_contrib (libbcrypt-cmake libbcrypt)
add_contrib (google-benchmark-cmake google-benchmark)

4
contrib/abseil-cpp-cmake/CMakeLists.txt
View File

@ -52,7 +52,7 @@ function(absl_cc_library)
)
target_include_directories(${_NAME}
PUBLIC "${ABSL_COMMON_INCLUDE_DIRS}")
SYSTEM PUBLIC "${ABSL_COMMON_INCLUDE_DIRS}")
target_compile_options(${_NAME}
PRIVATE ${ABSL_CC_LIB_COPTS})
target_compile_definitions(${_NAME} PUBLIC ${ABSL_CC_LIB_DEFINES})
@ -61,7 +61,7 @@ function(absl_cc_library)
# Generating header-only library
add_library(${_NAME} INTERFACE)
target_include_directories(${_NAME}
INTERFACE "${ABSL_COMMON_INCLUDE_DIRS}")
SYSTEM INTERFACE "${ABSL_COMMON_INCLUDE_DIRS}")
target_link_libraries(${_NAME}
INTERFACE

2
contrib/arrow vendored

@ -1 +1 @@
Subproject commit ba5c67934e8274d649befcffab56731632dc5253
Subproject commit 8f36d71d18587f1f315ec832f424183cb6519cbb

2
contrib/aws vendored

@ -1 +1 @@
Subproject commit 32870e234cac03e0ac46370c26858b0ffdf14200
Subproject commit 2e12d7c6dafa81311ee3d73ac6a178550ffa75be

2
contrib/aws-c-cal vendored

@ -1 +1 @@
Subproject commit 9453687ff5493ba94eaccf8851200565c4364c77
Subproject commit 1586846816e6d7d5ff744a2db943107a3a74a082

2
contrib/azure vendored

@ -1 +1 @@
Subproject commit e71395e44f309f97b5a486f5c2c59b82f85dd2d2
Subproject commit 6262a76ef4c4c330c84e58dd4f6f13f4e6230fcd

1
contrib/azure-cmake/CMakeLists.txt
View File

@ -10,6 +10,7 @@ set(AZURE_SDK_LIBRARY_DIR "${AZURE_DIR}/sdk")
file(GLOB AZURE_SDK_SRC
"${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/*.cpp"
"${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/credentials/*.cpp"
"${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/cryptography/*.cpp"
"${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/http/*.cpp"
"${AZURE_SDK_LIBRARY_DIR}/core/azure-core/src/http/curl/*.cpp"

6
contrib/boost-cmake/CMakeLists.txt
View File

@ -140,6 +140,12 @@ elseif (ARCH_RISCV64)
"${LIBRARY_DIR}/libs/context/src/asm/make_riscv64_sysv_elf_gas.S"
"${LIBRARY_DIR}/libs/context/src/asm/ontop_riscv64_sysv_elf_gas.S"
)
elseif (ARCH_LOONGARCH64)
set (SRCS_CONTEXT ${SRCS_CONTEXT}
"${LIBRARY_DIR}/libs/context/src/asm/jump_loongarch64_sysv_elf_gas.S"
"${LIBRARY_DIR}/libs/context/src/asm/make_loongarch64_sysv_elf_gas.S"
"${LIBRARY_DIR}/libs/context/src/asm/ontop_loongarch64_sysv_elf_gas.S"
)
elseif(OS_DARWIN)
set (SRCS_CONTEXT ${SRCS_CONTEXT}
"${LIBRARY_DIR}/libs/context/src/asm/jump_x86_64_sysv_macho_gas.S"

1
contrib/boringssl vendored

@ -1 +0,0 @@
Subproject commit aa6d2f865a2eab01cf94f197e11e36b6de47b5b4

799
contrib/boringssl-cmake/CMakeLists.txt
View File

@ -1,799 +0,0 @@
# Needed for:
# - securely connecting to an external server, e.g. clickhouse-client --host ... --secure
# - lots of thirdparty libraries
# Actually, so many 3rd party libraries + unit tests need SSL that we cannot disable it
# without breaking the build ...
option(ENABLE_SSL "Enable ssl" ON) # breaks if OFF
# TODO: Making SSL dependent on ENABLE_LIBRARIES is desirable but needs fixing dependent libs + tests.
# option(ENABLE_SSL "Enable ssl" ${ENABLE_LIBRARIES})
if(NOT ENABLE_SSL)
message(STATUS "Not using openssl")
return()
endif()
# Copyright (c) 2019 The Chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
# This file is created by generate_build_files.py and edited accordingly.
cmake_minimum_required(VERSION 3.5)
project(BoringSSL LANGUAGES C CXX)
set(BORINGSSL_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/boringssl")
if(CMAKE_CXX_COMPILER_ID MATCHES "Clang")
set(CLANG 1)
endif()
if(CMAKE_COMPILER_IS_GNUCXX OR CLANG)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11 -fno-common -fno-exceptions -fno-rtti")
if(APPLE AND CLANG)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")
endif()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fno-common -std=c11")
endif()
# pthread_rwlock_t requires a feature flag.
if(NOT WIN32)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -D_XOPEN_SOURCE=700")
endif()
if(WIN32)
add_definitions(-D_HAS_EXCEPTIONS=0)
add_definitions(-DWIN32_LEAN_AND_MEAN)
add_definitions(-DNOMINMAX)
# Allow use of fopen.
add_definitions(-D_CRT_SECURE_NO_WARNINGS)
# VS 2017 and higher supports STL-only warning suppressions.
# A bug in CMake < 3.13.0 may cause the space in this value to
# cause issues when building with NASM. In that case, update CMake.
add_definitions("-D_STL_EXTRA_DISABLED_WARNINGS=4774 4987")
endif()
add_definitions(-DBORINGSSL_IMPLEMENTATION)
# CMake's iOS support uses Apple's multiple-architecture toolchain. It takes an
# architecture list from CMAKE_OSX_ARCHITECTURES, leaves CMAKE_SYSTEM_PROCESSOR
# alone, and expects all architecture-specific logic to be conditioned within
# the source files rather than the build. This does not work for our assembly
# files, so we fix CMAKE_SYSTEM_PROCESSOR and only support single-architecture
# builds.
if(NOT OPENSSL_NO_ASM AND CMAKE_OSX_ARCHITECTURES)
list(LENGTH CMAKE_OSX_ARCHITECTURES NUM_ARCHES)
if(NOT NUM_ARCHES EQUAL 1)
message(FATAL_ERROR "Universal binaries not supported.")
endif()
list(GET CMAKE_OSX_ARCHITECTURES 0 CMAKE_SYSTEM_PROCESSOR)
endif()
if(OPENSSL_NO_ASM)
add_definitions(-DOPENSSL_NO_ASM)
set(ARCH "generic")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "x86_64")
set(ARCH "x86_64")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "amd64")
set(ARCH "x86_64")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "AMD64")
# cmake reports AMD64 on Windows, but we might be building for 32-bit.
if(CMAKE_SIZEOF_VOID_P EQUAL 8)
set(ARCH "x86_64")
else()
set(ARCH "x86")
endif()
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "x86")
set(ARCH "x86")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "i386")
# cmake uses `uname -p` to set the system processor, but Solaris
# systems support multiple architectures.
if((${CMAKE_SYSTEM_NAME} STREQUAL "SunOS") AND CMAKE_SIZEOF_VOID_P EQUAL 8)
set(ARCH "x86_64")
else()
set(ARCH "x86")
endif()
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "i686")
set(ARCH "x86")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "aarch64")
set(ARCH "aarch64")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "arm64")
set(ARCH "aarch64")
# Apple A12 Bionic chipset which is added in iPhone XS/XS Max/XR uses arm64e architecture.
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "arm64e")
set(ARCH "aarch64")
elseif(${CMAKE_SYSTEM_PROCESSOR} MATCHES "^arm*")
set(ARCH "arm")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "mips")
# Just to avoid the “unknown processor” error.
set(ARCH "generic")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "ppc64le")
set(ARCH "ppc64le")
elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "riscv64")
set(ARCH "riscv64")
else()
message(FATAL_ERROR "Unknown processor:" ${CMAKE_SYSTEM_PROCESSOR})
endif()
if(NOT OPENSSL_NO_ASM)
if(UNIX)
enable_language(ASM)
# Clang's integerated assembler does not support debug symbols.
if(NOT CMAKE_ASM_COMPILER_ID MATCHES "Clang")
set(CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} -Wa,-g")
endif()
# CMake does not add -isysroot and -arch flags to assembly.
if(APPLE)
if(CMAKE_OSX_SYSROOT)
set(CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} -isysroot \"${CMAKE_OSX_SYSROOT}\"")
endif()
foreach(arch ${CMAKE_OSX_ARCHITECTURES})
set(CMAKE_ASM_FLAGS "${CMAKE_ASM_FLAGS} -arch ${arch}")
endforeach()
endif()
else()
set(CMAKE_ASM_NASM_FLAGS "${CMAKE_ASM_NASM_FLAGS} -gcv8")
enable_language(ASM_NASM)
endif()
endif()
set(
CRYPTO_ios_aarch64_SOURCES
ios-aarch64/crypto/chacha/chacha-armv8.S
ios-aarch64/crypto/fipsmodule/aesv8-armx64.S
ios-aarch64/crypto/fipsmodule/armv8-mont.S
ios-aarch64/crypto/fipsmodule/ghash-neon-armv8.S
ios-aarch64/crypto/fipsmodule/ghashv8-armx64.S
ios-aarch64/crypto/fipsmodule/sha1-armv8.S
ios-aarch64/crypto/fipsmodule/sha256-armv8.S
ios-aarch64/crypto/fipsmodule/sha512-armv8.S
ios-aarch64/crypto/fipsmodule/vpaes-armv8.S
ios-aarch64/crypto/test/trampoline-armv8.S
)
set(
CRYPTO_ios_arm_SOURCES
ios-arm/crypto/chacha/chacha-armv4.S
ios-arm/crypto/fipsmodule/aesv8-armx32.S
ios-arm/crypto/fipsmodule/armv4-mont.S
ios-arm/crypto/fipsmodule/bsaes-armv7.S
ios-arm/crypto/fipsmodule/ghash-armv4.S
ios-arm/crypto/fipsmodule/ghashv8-armx32.S
ios-arm/crypto/fipsmodule/sha1-armv4-large.S
ios-arm/crypto/fipsmodule/sha256-armv4.S
ios-arm/crypto/fipsmodule/sha512-armv4.S
ios-arm/crypto/fipsmodule/vpaes-armv7.S
ios-arm/crypto/test/trampoline-armv4.S
)
set(
CRYPTO_linux_aarch64_SOURCES
linux-aarch64/crypto/chacha/chacha-armv8.S
linux-aarch64/crypto/fipsmodule/aesv8-armx64.S
linux-aarch64/crypto/fipsmodule/armv8-mont.S
linux-aarch64/crypto/fipsmodule/ghash-neon-armv8.S
linux-aarch64/crypto/fipsmodule/ghashv8-armx64.S
linux-aarch64/crypto/fipsmodule/sha1-armv8.S
linux-aarch64/crypto/fipsmodule/sha256-armv8.S
linux-aarch64/crypto/fipsmodule/sha512-armv8.S
linux-aarch64/crypto/fipsmodule/vpaes-armv8.S
linux-aarch64/crypto/test/trampoline-armv8.S
)
set(
CRYPTO_linux_arm_SOURCES
linux-arm/crypto/chacha/chacha-armv4.S
linux-arm/crypto/fipsmodule/aesv8-armx32.S
linux-arm/crypto/fipsmodule/armv4-mont.S
linux-arm/crypto/fipsmodule/bsaes-armv7.S
linux-arm/crypto/fipsmodule/ghash-armv4.S
linux-arm/crypto/fipsmodule/ghashv8-armx32.S
linux-arm/crypto/fipsmodule/sha1-armv4-large.S
linux-arm/crypto/fipsmodule/sha256-armv4.S
linux-arm/crypto/fipsmodule/sha512-armv4.S
linux-arm/crypto/fipsmodule/vpaes-armv7.S
linux-arm/crypto/test/trampoline-armv4.S
"${BORINGSSL_SOURCE_DIR}/crypto/curve25519/asm/x25519-asm-arm.S"
"${BORINGSSL_SOURCE_DIR}/crypto/poly1305/poly1305_arm_asm.S"
)
set(
CRYPTO_linux_ppc64le_SOURCES
linux-ppc64le/crypto/fipsmodule/aesp8-ppc.S
linux-ppc64le/crypto/fipsmodule/ghashp8-ppc.S
linux-ppc64le/crypto/test/trampoline-ppc.S
)
set(
CRYPTO_linux_x86_SOURCES
linux-x86/crypto/chacha/chacha-x86.S
linux-x86/crypto/fipsmodule/aesni-x86.S
linux-x86/crypto/fipsmodule/bn-586.S
linux-x86/crypto/fipsmodule/co-586.S
linux-x86/crypto/fipsmodule/ghash-ssse3-x86.S
linux-x86/crypto/fipsmodule/ghash-x86.S
linux-x86/crypto/fipsmodule/md5-586.S
linux-x86/crypto/fipsmodule/sha1-586.S
linux-x86/crypto/fipsmodule/sha256-586.S
linux-x86/crypto/fipsmodule/sha512-586.S
linux-x86/crypto/fipsmodule/vpaes-x86.S
linux-x86/crypto/fipsmodule/x86-mont.S
linux-x86/crypto/test/trampoline-x86.S
)
set(
CRYPTO_linux_x86_64_SOURCES
linux-x86_64/crypto/chacha/chacha-x86_64.S
linux-x86_64/crypto/cipher_extra/aes128gcmsiv-x86_64.S
linux-x86_64/crypto/cipher_extra/chacha20_poly1305_x86_64.S
linux-x86_64/crypto/fipsmodule/aesni-gcm-x86_64.S
linux-x86_64/crypto/fipsmodule/aesni-x86_64.S
linux-x86_64/crypto/fipsmodule/ghash-ssse3-x86_64.S
linux-x86_64/crypto/fipsmodule/ghash-x86_64.S
linux-x86_64/crypto/fipsmodule/md5-x86_64.S
linux-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
linux-x86_64/crypto/fipsmodule/p256_beeu-x86_64-asm.S
linux-x86_64/crypto/fipsmodule/rdrand-x86_64.S
linux-x86_64/crypto/fipsmodule/rsaz-avx2.S
linux-x86_64/crypto/fipsmodule/sha1-x86_64.S
linux-x86_64/crypto/fipsmodule/sha256-x86_64.S
linux-x86_64/crypto/fipsmodule/sha512-x86_64.S
linux-x86_64/crypto/fipsmodule/vpaes-x86_64.S
linux-x86_64/crypto/fipsmodule/x86_64-mont.S
linux-x86_64/crypto/fipsmodule/x86_64-mont5.S
linux-x86_64/crypto/test/trampoline-x86_64.S
"${BORINGSSL_SOURCE_DIR}/crypto/hrss/asm/poly_rq_mul.S"
)
set(
CRYPTO_mac_x86_SOURCES
mac-x86/crypto/chacha/chacha-x86.S
mac-x86/crypto/fipsmodule/aesni-x86.S
mac-x86/crypto/fipsmodule/bn-586.S
mac-x86/crypto/fipsmodule/co-586.S
mac-x86/crypto/fipsmodule/ghash-ssse3-x86.S
mac-x86/crypto/fipsmodule/ghash-x86.S
mac-x86/crypto/fipsmodule/md5-586.S
mac-x86/crypto/fipsmodule/sha1-586.S
mac-x86/crypto/fipsmodule/sha256-586.S
mac-x86/crypto/fipsmodule/sha512-586.S
mac-x86/crypto/fipsmodule/vpaes-x86.S
mac-x86/crypto/fipsmodule/x86-mont.S
mac-x86/crypto/test/trampoline-x86.S
)
set(
CRYPTO_mac_x86_64_SOURCES
mac-x86_64/crypto/chacha/chacha-x86_64.S
mac-x86_64/crypto/cipher_extra/aes128gcmsiv-x86_64.S
mac-x86_64/crypto/cipher_extra/chacha20_poly1305_x86_64.S
mac-x86_64/crypto/fipsmodule/aesni-gcm-x86_64.S
mac-x86_64/crypto/fipsmodule/aesni-x86_64.S
mac-x86_64/crypto/fipsmodule/ghash-ssse3-x86_64.S
mac-x86_64/crypto/fipsmodule/ghash-x86_64.S
mac-x86_64/crypto/fipsmodule/md5-x86_64.S
mac-x86_64/crypto/fipsmodule/p256-x86_64-asm.S
mac-x86_64/crypto/fipsmodule/p256_beeu-x86_64-asm.S
mac-x86_64/crypto/fipsmodule/rdrand-x86_64.S
mac-x86_64/crypto/fipsmodule/rsaz-avx2.S
mac-x86_64/crypto/fipsmodule/sha1-x86_64.S
mac-x86_64/crypto/fipsmodule/sha256-x86_64.S
mac-x86_64/crypto/fipsmodule/sha512-x86_64.S
mac-x86_64/crypto/fipsmodule/vpaes-x86_64.S
mac-x86_64/crypto/fipsmodule/x86_64-mont.S
mac-x86_64/crypto/fipsmodule/x86_64-mont5.S
mac-x86_64/crypto/test/trampoline-x86_64.S
)
set(
CRYPTO_win_aarch64_SOURCES
win-aarch64/crypto/chacha/chacha-armv8.S
win-aarch64/crypto/fipsmodule/aesv8-armx64.S
win-aarch64/crypto/fipsmodule/armv8-mont.S
win-aarch64/crypto/fipsmodule/ghash-neon-armv8.S
win-aarch64/crypto/fipsmodule/ghashv8-armx64.S
win-aarch64/crypto/fipsmodule/sha1-armv8.S
win-aarch64/crypto/fipsmodule/sha256-armv8.S
win-aarch64/crypto/fipsmodule/sha512-armv8.S
win-aarch64/crypto/fipsmodule/vpaes-armv8.S
win-aarch64/crypto/test/trampoline-armv8.S
)
set(
CRYPTO_win_x86_SOURCES
win-x86/crypto/chacha/chacha-x86.asm
win-x86/crypto/fipsmodule/aesni-x86.asm
win-x86/crypto/fipsmodule/bn-586.asm
win-x86/crypto/fipsmodule/co-586.asm
win-x86/crypto/fipsmodule/ghash-ssse3-x86.asm
win-x86/crypto/fipsmodule/ghash-x86.asm
win-x86/crypto/fipsmodule/md5-586.asm
win-x86/crypto/fipsmodule/sha1-586.asm
win-x86/crypto/fipsmodule/sha256-586.asm
win-x86/crypto/fipsmodule/sha512-586.asm
win-x86/crypto/fipsmodule/vpaes-x86.asm
win-x86/crypto/fipsmodule/x86-mont.asm
win-x86/crypto/test/trampoline-x86.asm
)
set(
CRYPTO_win_x86_64_SOURCES
win-x86_64/crypto/chacha/chacha-x86_64.asm
win-x86_64/crypto/cipher_extra/aes128gcmsiv-x86_64.asm
win-x86_64/crypto/cipher_extra/chacha20_poly1305_x86_64.asm
win-x86_64/crypto/fipsmodule/aesni-gcm-x86_64.asm
win-x86_64/crypto/fipsmodule/aesni-x86_64.asm
win-x86_64/crypto/fipsmodule/ghash-ssse3-x86_64.asm
win-x86_64/crypto/fipsmodule/ghash-x86_64.asm
win-x86_64/crypto/fipsmodule/md5-x86_64.asm
win-x86_64/crypto/fipsmodule/p256-x86_64-asm.asm
win-x86_64/crypto/fipsmodule/p256_beeu-x86_64-asm.asm
win-x86_64/crypto/fipsmodule/rdrand-x86_64.asm
win-x86_64/crypto/fipsmodule/rsaz-avx2.asm
win-x86_64/crypto/fipsmodule/sha1-x86_64.asm
win-x86_64/crypto/fipsmodule/sha256-x86_64.asm
win-x86_64/crypto/fipsmodule/sha512-x86_64.asm
win-x86_64/crypto/fipsmodule/vpaes-x86_64.asm
win-x86_64/crypto/fipsmodule/x86_64-mont.asm
win-x86_64/crypto/fipsmodule/x86_64-mont5.asm
win-x86_64/crypto/test/trampoline-x86_64.asm
)
if(APPLE AND ARCH STREQUAL "aarch64")
set(CRYPTO_ARCH_SOURCES ${CRYPTO_ios_aarch64_SOURCES})
elseif(APPLE AND ARCH STREQUAL "arm")
set(CRYPTO_ARCH_SOURCES ${CRYPTO_ios_arm_SOURCES})
elseif(APPLE)
set(CRYPTO_ARCH_SOURCES ${CRYPTO_mac_${ARCH}_SOURCES})
elseif(UNIX)
set(CRYPTO_ARCH_SOURCES ${CRYPTO_linux_${ARCH}_SOURCES})
elseif(WIN32)
set(CRYPTO_ARCH_SOURCES ${CRYPTO_win_${ARCH}_SOURCES})
endif()
add_library(
_crypto
${CRYPTO_ARCH_SOURCES}
err_data.c
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_bitstr.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_bool.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_d2i_fp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_dup.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_enum.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_gentm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_i2d_fp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_int.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_mbstr.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_object.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_octet.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_print.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_strex.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_strnid.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_time.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_type.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_utctm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/a_utf8.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/asn1_lib.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/asn1_par.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/asn_pack.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/f_enum.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/f_int.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/f_string.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_dec.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_enc.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_fre.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_new.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_typ.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/tasn_utl.c"
"${BORINGSSL_SOURCE_DIR}/crypto/asn1/time_support.c"
"${BORINGSSL_SOURCE_DIR}/crypto/base64/base64.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/bio.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/bio_mem.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/connect.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/fd.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/file.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/hexdump.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/pair.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/printf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/socket.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bio/socket_helper.c"
"${BORINGSSL_SOURCE_DIR}/crypto/blake2/blake2.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bn_extra/bn_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bn_extra/convert.c"
"${BORINGSSL_SOURCE_DIR}/crypto/buf/buf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bytestring/asn1_compat.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bytestring/ber.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bytestring/cbb.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bytestring/cbs.c"
"${BORINGSSL_SOURCE_DIR}/crypto/bytestring/unicode.c"
"${BORINGSSL_SOURCE_DIR}/crypto/chacha/chacha.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/cipher_extra.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/derive_key.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_aesccm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_aesctrhmac.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_aesgcmsiv.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_chacha20poly1305.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_null.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_rc2.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_rc4.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/e_tls.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cipher_extra/tls_cbc.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cmac/cmac.c"
"${BORINGSSL_SOURCE_DIR}/crypto/conf/conf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-aarch64-fuchsia.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-aarch64-linux.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-aarch64-win.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-arm-linux.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-arm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-intel.c"
"${BORINGSSL_SOURCE_DIR}/crypto/cpu-ppc64le.c"
"${BORINGSSL_SOURCE_DIR}/crypto/crypto.c"
"${BORINGSSL_SOURCE_DIR}/crypto/curve25519/curve25519.c"
"${BORINGSSL_SOURCE_DIR}/crypto/curve25519/spake25519.c"
"${BORINGSSL_SOURCE_DIR}/crypto/dh_extra/dh_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/dh_extra/params.c"
"${BORINGSSL_SOURCE_DIR}/crypto/digest_extra/digest_extra.c"
"${BORINGSSL_SOURCE_DIR}/crypto/dsa/dsa.c"
"${BORINGSSL_SOURCE_DIR}/crypto/dsa/dsa_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ec_extra/ec_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ec_extra/ec_derive.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ec_extra/hash_to_curve.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ecdh_extra/ecdh_extra.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ecdsa_extra/ecdsa_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/engine/engine.c"
"${BORINGSSL_SOURCE_DIR}/crypto/err/err.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/digestsign.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/evp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/evp_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/evp_ctx.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_dsa_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_ec.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_ec_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_ed25519.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_ed25519_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_rsa.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_rsa_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_x25519.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/p_x25519_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/pbkdf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/print.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/scrypt.c"
"${BORINGSSL_SOURCE_DIR}/crypto/evp/sign.c"
"${BORINGSSL_SOURCE_DIR}/crypto/ex_data.c"
"${BORINGSSL_SOURCE_DIR}/crypto/fipsmodule/bcm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/fipsmodule/fips_shared_support.c"
"${BORINGSSL_SOURCE_DIR}/crypto/hkdf/hkdf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/hpke/hpke.c"
"${BORINGSSL_SOURCE_DIR}/crypto/hrss/hrss.c"
"${BORINGSSL_SOURCE_DIR}/crypto/lhash/lhash.c"
"${BORINGSSL_SOURCE_DIR}/crypto/mem.c"
"${BORINGSSL_SOURCE_DIR}/crypto/obj/obj.c"
"${BORINGSSL_SOURCE_DIR}/crypto/obj/obj_xref.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_all.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_info.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_lib.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_oth.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_pk8.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_pkey.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pem/pem_xaux.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pkcs7/pkcs7.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pkcs7/pkcs7_x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pkcs8/p5_pbev2.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pkcs8/pkcs8.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pkcs8/pkcs8_x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/poly1305/poly1305.c"
"${BORINGSSL_SOURCE_DIR}/crypto/poly1305/poly1305_arm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/poly1305/poly1305_vec.c"
"${BORINGSSL_SOURCE_DIR}/crypto/pool/pool.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/deterministic.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/forkunsafe.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/fuchsia.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/passive.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/rand_extra.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rand_extra/windows.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rc4/rc4.c"
"${BORINGSSL_SOURCE_DIR}/crypto/refcount_c11.c"
"${BORINGSSL_SOURCE_DIR}/crypto/refcount_lock.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rsa_extra/rsa_asn1.c"
"${BORINGSSL_SOURCE_DIR}/crypto/rsa_extra/rsa_print.c"
"${BORINGSSL_SOURCE_DIR}/crypto/siphash/siphash.c"
"${BORINGSSL_SOURCE_DIR}/crypto/stack/stack.c"
"${BORINGSSL_SOURCE_DIR}/crypto/thread.c"
"${BORINGSSL_SOURCE_DIR}/crypto/thread_none.c"
"${BORINGSSL_SOURCE_DIR}/crypto/thread_pthread.c"
"${BORINGSSL_SOURCE_DIR}/crypto/thread_win.c"
"${BORINGSSL_SOURCE_DIR}/crypto/trust_token/pmbtoken.c"
"${BORINGSSL_SOURCE_DIR}/crypto/trust_token/trust_token.c"
"${BORINGSSL_SOURCE_DIR}/crypto/trust_token/voprf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/a_digest.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/a_sign.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/a_verify.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/algorithm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/asn1_gen.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/by_dir.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/by_file.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/i2d_pr.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/name_print.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/rsa_pss.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/t_crl.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/t_req.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/t_x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/t_x509a.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_att.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_cmp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_d2.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_def.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_ext.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_lu.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_obj.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_req.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_set.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_trs.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_txt.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_v3.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_vfy.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509_vpm.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509cset.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509name.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509rset.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x509spki.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_algor.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_all.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_attrib.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_crl.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_exten.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_info.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_name.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_pkey.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_pubkey.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_req.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_sig.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_spki.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_val.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_x509.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509/x_x509a.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_cache.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_data.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_lib.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_map.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_node.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/pcy_tree.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_akey.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_akeya.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_alt.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_bcons.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_bitst.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_conf.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_cpols.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_crld.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_enum.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_extku.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_genn.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_ia5.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_info.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_int.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_lib.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_ncons.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_ocsp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_pci.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_pcia.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_pcons.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_pmaps.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_prn.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_purp.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_skey.c"
"${BORINGSSL_SOURCE_DIR}/crypto/x509v3/v3_utl.c"
)
add_library(
_ssl
"${BORINGSSL_SOURCE_DIR}/ssl/bio_ssl.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/d1_both.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/d1_lib.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/d1_pkt.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/d1_srtp.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/dtls_method.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/dtls_record.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/encrypted_client_hello.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/extensions.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/handoff.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/handshake.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/handshake_client.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/handshake_server.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/s3_both.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/s3_lib.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/s3_pkt.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_aead_ctx.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_asn1.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_buffer.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_cert.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_cipher.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_file.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_key_share.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_lib.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_privkey.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_session.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_stat.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_transcript.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_versions.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/ssl_x509.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/t1_enc.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls13_both.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls13_client.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls13_enc.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls13_server.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls_method.cc"
"${BORINGSSL_SOURCE_DIR}/ssl/tls_record.cc"
"${BORINGSSL_SOURCE_DIR}/decrepit/ssl/ssl_decrepit.c"
"${BORINGSSL_SOURCE_DIR}/decrepit/cfb/cfb.c"
"${BORINGSSL_SOURCE_DIR}/decrepit/bio/base64_bio.c"
)
add_executable(
bssl
"${BORINGSSL_SOURCE_DIR}/tool/args.cc"
"${BORINGSSL_SOURCE_DIR}/tool/ciphers.cc"
"${BORINGSSL_SOURCE_DIR}/tool/client.cc"
"${BORINGSSL_SOURCE_DIR}/tool/const.cc"
"${BORINGSSL_SOURCE_DIR}/tool/digest.cc"
"${BORINGSSL_SOURCE_DIR}/tool/fd.cc"
"${BORINGSSL_SOURCE_DIR}/tool/file.cc"
"${BORINGSSL_SOURCE_DIR}/tool/generate_ech.cc"
"${BORINGSSL_SOURCE_DIR}/tool/generate_ed25519.cc"
"${BORINGSSL_SOURCE_DIR}/tool/genrsa.cc"
"${BORINGSSL_SOURCE_DIR}/tool/pkcs12.cc"
"${BORINGSSL_SOURCE_DIR}/tool/rand.cc"
"${BORINGSSL_SOURCE_DIR}/tool/server.cc"
"${BORINGSSL_SOURCE_DIR}/tool/sign.cc"
"${BORINGSSL_SOURCE_DIR}/tool/speed.cc"
"${BORINGSSL_SOURCE_DIR}/tool/tool.cc"
"${BORINGSSL_SOURCE_DIR}/tool/transport_common.cc"
)
target_link_libraries(_ssl _crypto)
target_link_libraries(bssl _ssl)
if(NOT WIN32 AND NOT ANDROID)
target_link_libraries(_crypto pthread)
endif()
# NOTE: that ClickHouse does not support WIN32 anyway.
if(WIN32)
target_link_libraries(bssl ws2_32)
endif()
target_include_directories(_crypto SYSTEM PUBLIC "${BORINGSSL_SOURCE_DIR}/include")
target_include_directories(_ssl SYSTEM PUBLIC "${BORINGSSL_SOURCE_DIR}/include")
target_compile_options(_crypto PRIVATE -Wno-gnu-anonymous-struct)
add_library(OpenSSL::Crypto ALIAS _crypto)
add_library(OpenSSL::SSL ALIAS _ssl)
# Helper function used in the populate_openssl_vars function below
function(from_hex HEX DEC)
string(TOUPPER "${HEX}" HEX)
set(_res 0)
string(LENGTH "${HEX}" _strlen)
while (_strlen GREATER 0)
math(EXPR _res "${_res} * 16")
string(SUBSTRING "${HEX}" 0 1 NIBBLE)
string(SUBSTRING "${HEX}" 1 -1 HEX)
if (NIBBLE STREQUAL "A")
math(EXPR _res "${_res} + 10")
elseif (NIBBLE STREQUAL "B")
math(EXPR _res "${_res} + 11")
elseif (NIBBLE STREQUAL "C")
math(EXPR _res "${_res} + 12")
elseif (NIBBLE STREQUAL "D")
math(EXPR _res "${_res} + 13")
elseif (NIBBLE STREQUAL "E")
math(EXPR _res "${_res} + 14")
elseif (NIBBLE STREQUAL "F")
math(EXPR _res "${_res} + 15")
else ()
math(EXPR _res "${_res} + ${NIBBLE}")
endif ()
string(LENGTH "${HEX}" _strlen)
endwhile ()
set(${DEC} ${_res} PARENT_SCOPE)
endfunction()
# ClickHouse uses BoringSSL which is a fork of OpenSSL.
# This populates CMAKE var OPENSSL_VERSION from the OPENSSL_VERSION_NUMBER defined
# in contrib/boringssl/include/openssl/base.h. It also sets the CMAKE var OPENSSL_IS_BORING_SSL
# if it's defined in the file. Both OPENSSL_VERSION and OPENSSL_IS_BORING_SSL variables will be
# used to populate flags in the `system.build_options` table for more context on ssl version used.
# This cmake script is adopted from FindOpenSSL cmake module and slightly modified for this use-case .
if (EXISTS "${BORINGSSL_SOURCE_DIR}/include/openssl/base.h")
file(STRINGS "${BORINGSSL_SOURCE_DIR}/include/openssl/base.h" openssl_version_str
REGEX "^#[\t ]*define[\t ]+OPENSSL_VERSION_NUMBER[\t ]+0x([0-9a-fA-F])+.*")
file(STRINGS "${BORINGSSL_SOURCE_DIR}/include/openssl/base.h" openssl_is_boringssl
REGEX "^#[\t ]*define[\t ]+OPENSSL_IS_BORINGSSL.*")
# Set to true if OPENSSL_IS_BORING_SSL is defined
if (openssl_is_boringssl)
set(OPENSSL_IS_BORING_SSL 1)
endif ()
# If openssl_version_str is defined extrapolate and set OPENSSL_VERSION
if (openssl_version_str)
# The version number is encoded as 0xMNNFFPPS: major minor fix patch status
# The status gives if this is a developer or prerelease and is ignored here.
# Major, minor, and fix directly translate into the version numbers shown in
# the string. The patch field translates to the single character suffix that
# indicates the bug fix state, which 00 -> nothing, 01 -> a, 02 -> b and so
# on.
string(REGEX REPLACE "^.*OPENSSL_VERSION_NUMBER[\t ]+0x([0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F][0-9a-fA-F])([0-9a-fA-F]).*$"
"\\1;\\2;\\3;\\4;\\5" OPENSSL_VERSION_LIST "${openssl_version_str}")
list(GET OPENSSL_VERSION_LIST 0 OPENSSL_VERSION_MAJOR)
list(GET OPENSSL_VERSION_LIST 1 OPENSSL_VERSION_MINOR)
from_hex("${OPENSSL_VERSION_MINOR}" OPENSSL_VERSION_MINOR)
list(GET OPENSSL_VERSION_LIST 2 OPENSSL_VERSION_FIX)
from_hex("${OPENSSL_VERSION_FIX}" OPENSSL_VERSION_FIX)
list(GET OPENSSL_VERSION_LIST 3 OPENSSL_VERSION_PATCH)
if (NOT OPENSSL_VERSION_PATCH STREQUAL "00")
from_hex("${OPENSSL_VERSION_PATCH}" _tmp)
# 96 is the ASCII code of 'a' minus 1
math(EXPR OPENSSL_VERSION_PATCH_ASCII "${_tmp} + 96")
unset(_tmp)
# Once anyone knows how OpenSSL would call the patch versions beyond 'z'
# this should be updated to handle that, too. This has not happened yet
# so it is simply ignored here for now.
string(ASCII "${OPENSSL_VERSION_PATCH_ASCII}" OPENSSL_VERSION_PATCH_STRING)
endif ()
set(OPENSSL_VERSION "${OPENSSL_VERSION_MAJOR}.${OPENSSL_VERSION_MINOR}.${OPENSSL_VERSION_FIX}${OPENSSL_VERSION_PATCH_STRING}")
else ()
# Since OpenSSL 3.0.0, the new version format is MAJOR.MINOR.PATCH and
# a new OPENSSL_VERSION_STR macro contains exactly that
file(STRINGS "${BORINGSSL_SOURCE_DIR}/include/openssl/base.h" OPENSSL_VERSION_STR
REGEX "^#[\t ]*define[\t ]+OPENSSL_VERSION_STR[\t ]+\"([0-9])+\\.([0-9])+\\.([0-9])+\".*")
string(REGEX REPLACE "^.*OPENSSL_VERSION_STR[\t ]+\"([0-9]+\\.[0-9]+\\.[0-9]+)\".*$"
"\\1" OPENSSL_VERSION_STR "${OPENSSL_VERSION_STR}")
set(OPENSSL_VERSION "${OPENSSL_VERSION_STR}")
# Setting OPENSSL_VERSION_MAJOR OPENSSL_VERSION_MINOR and OPENSSL_VERSION_FIX
string(REGEX MATCHALL "([0-9])+" OPENSSL_VERSION_NUMBER "${OPENSSL_VERSION}")
list(POP_FRONT OPENSSL_VERSION_NUMBER
OPENSSL_VERSION_MAJOR
OPENSSL_VERSION_MINOR
OPENSSL_VERSION_FIX)
unset(OPENSSL_VERSION_NUMBER)
unset(OPENSSL_VERSION_STR)
endif ()
endif ()
# Set CMAKE variables so that they can be referenced properly from everywhere
set(OPENSSL_VERSION "${OPENSSL_VERSION}" CACHE INTERNAL "")
set(OPENSSL_IS_BORING_SSL "${OPENSSL_IS_BORING_SSL}" CACHE INTERNAL 0)

5012
contrib/boringssl-cmake/crypto_test_data.cc
View File

File diff suppressed because one or more lines are too long

1457
contrib/boringssl-cmake/err_data.c
View File

File diff suppressed because it is too large Load Diff

1991
contrib/boringssl-cmake/ios-aarch64/crypto/chacha/chacha-armv8.S
View File

File diff suppressed because it is too large Load Diff

782
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/aesv8-armx64.S
View File

@ -1,782 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
#if __ARM_MAX_ARCH__>=7
.text
.section __TEXT,__const
.align 5
Lrcon:
.long 0x01,0x01,0x01,0x01
.long 0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d // rotate-n-splat
.long 0x1b,0x1b,0x1b,0x1b
.text
.globl _aes_hw_set_encrypt_key
.private_extern _aes_hw_set_encrypt_key
.align 5
_aes_hw_set_encrypt_key:
Lenc_key:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
mov x3,#-1
cmp x0,#0
b.eq Lenc_key_abort
cmp x2,#0
b.eq Lenc_key_abort
mov x3,#-2
cmp w1,#128
b.lt Lenc_key_abort
cmp w1,#256
b.gt Lenc_key_abort
tst w1,#0x3f
b.ne Lenc_key_abort
adrp x3,Lrcon@PAGE
add x3,x3,Lrcon@PAGEOFF
cmp w1,#192
eor v0.16b,v0.16b,v0.16b
ld1 {v3.16b},[x0],#16
mov w1,#8 // reuse w1
ld1 {v1.4s,v2.4s},[x3],#32
b.lt Loop128
b.eq L192
b L256
.align 4
Loop128:
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
b.ne Loop128
ld1 {v1.4s},[x3]
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
eor v3.16b,v3.16b,v6.16b
st1 {v3.4s},[x2]
add x2,x2,#0x50
mov w12,#10
b Ldone
.align 4
L192:
ld1 {v4.8b},[x0],#8
movi v6.16b,#8 // borrow v6.16b
st1 {v3.4s},[x2],#16
sub v2.16b,v2.16b,v6.16b // adjust the mask
Loop192:
tbl v6.16b,{v4.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v4.8b},[x2],#8
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
dup v5.4s,v3.s[3]
eor v5.16b,v5.16b,v4.16b
eor v6.16b,v6.16b,v1.16b
ext v4.16b,v0.16b,v4.16b,#12
shl v1.16b,v1.16b,#1
eor v4.16b,v4.16b,v5.16b
eor v3.16b,v3.16b,v6.16b
eor v4.16b,v4.16b,v6.16b
st1 {v3.4s},[x2],#16
b.ne Loop192
mov w12,#12
add x2,x2,#0x20
b Ldone
.align 4
L256:
ld1 {v4.16b},[x0]
mov w1,#7
mov w12,#14
st1 {v3.4s},[x2],#16
Loop256:
tbl v6.16b,{v4.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v4.4s},[x2],#16
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
st1 {v3.4s},[x2],#16
b.eq Ldone
dup v6.4s,v3.s[3] // just splat
ext v5.16b,v0.16b,v4.16b,#12
aese v6.16b,v0.16b
eor v4.16b,v4.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v4.16b,v4.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v4.16b,v4.16b,v5.16b
eor v4.16b,v4.16b,v6.16b
b Loop256
Ldone:
str w12,[x2]
mov x3,#0
Lenc_key_abort:
mov x0,x3 // return value
ldr x29,[sp],#16
ret
.globl _aes_hw_set_decrypt_key
.private_extern _aes_hw_set_decrypt_key
.align 5
_aes_hw_set_decrypt_key:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
bl Lenc_key
cmp x0,#0
b.ne Ldec_key_abort
sub x2,x2,#240 // restore original x2
mov x4,#-16
add x0,x2,x12,lsl#4 // end of key schedule
ld1 {v0.4s},[x2]
ld1 {v1.4s},[x0]
st1 {v0.4s},[x0],x4
st1 {v1.4s},[x2],#16
Loop_imc:
ld1 {v0.4s},[x2]
ld1 {v1.4s},[x0]
aesimc v0.16b,v0.16b
aesimc v1.16b,v1.16b
st1 {v0.4s},[x0],x4
st1 {v1.4s},[x2],#16
cmp x0,x2
b.hi Loop_imc
ld1 {v0.4s},[x2]
aesimc v0.16b,v0.16b
st1 {v0.4s},[x0]
eor x0,x0,x0 // return value
Ldec_key_abort:
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
.globl _aes_hw_encrypt
.private_extern _aes_hw_encrypt
.align 5
_aes_hw_encrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
sub w3,w3,#2
ld1 {v1.4s},[x2],#16
Loop_enc:
aese v2.16b,v0.16b
aesmc v2.16b,v2.16b
ld1 {v0.4s},[x2],#16
subs w3,w3,#2
aese v2.16b,v1.16b
aesmc v2.16b,v2.16b
ld1 {v1.4s},[x2],#16
b.gt Loop_enc
aese v2.16b,v0.16b
aesmc v2.16b,v2.16b
ld1 {v0.4s},[x2]
aese v2.16b,v1.16b
eor v2.16b,v2.16b,v0.16b
st1 {v2.16b},[x1]
ret
.globl _aes_hw_decrypt
.private_extern _aes_hw_decrypt
.align 5
_aes_hw_decrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
sub w3,w3,#2
ld1 {v1.4s},[x2],#16
Loop_dec:
aesd v2.16b,v0.16b
aesimc v2.16b,v2.16b
ld1 {v0.4s},[x2],#16
subs w3,w3,#2
aesd v2.16b,v1.16b
aesimc v2.16b,v2.16b
ld1 {v1.4s},[x2],#16
b.gt Loop_dec
aesd v2.16b,v0.16b
aesimc v2.16b,v2.16b
ld1 {v0.4s},[x2]
aesd v2.16b,v1.16b
eor v2.16b,v2.16b,v0.16b
st1 {v2.16b},[x1]
ret
.globl _aes_hw_cbc_encrypt
.private_extern _aes_hw_cbc_encrypt
.align 5
_aes_hw_cbc_encrypt:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
subs x2,x2,#16
mov x8,#16
b.lo Lcbc_abort
csel x8,xzr,x8,eq
cmp w5,#0 // en- or decrypting?
ldr w5,[x3,#240]
and x2,x2,#-16
ld1 {v6.16b},[x4]
ld1 {v0.16b},[x0],x8
ld1 {v16.4s,v17.4s},[x3] // load key schedule...
sub w5,w5,#6
add x7,x3,x5,lsl#4 // pointer to last 7 round keys
sub w5,w5,#2
ld1 {v18.4s,v19.4s},[x7],#32
ld1 {v20.4s,v21.4s},[x7],#32
ld1 {v22.4s,v23.4s},[x7],#32
ld1 {v7.4s},[x7]
add x7,x3,#32
mov w6,w5
b.eq Lcbc_dec
cmp w5,#2
eor v0.16b,v0.16b,v6.16b
eor v5.16b,v16.16b,v7.16b
b.eq Lcbc_enc128
ld1 {v2.4s,v3.4s},[x7]
add x7,x3,#16
add x6,x3,#16*4
add x12,x3,#16*5
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
add x14,x3,#16*6
add x3,x3,#16*7
b Lenter_cbc_enc
.align 4
Loop_cbc_enc:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
st1 {v6.16b},[x1],#16
Lenter_cbc_enc:
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v0.16b,v2.16b
aesmc v0.16b,v0.16b
ld1 {v16.4s},[x6]
cmp w5,#4
aese v0.16b,v3.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x12]
b.eq Lcbc_enc192
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
ld1 {v16.4s},[x14]
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x3]
nop
Lcbc_enc192:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
subs x2,x2,#16
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
csel x8,xzr,x8,eq
aese v0.16b,v18.16b
aesmc v0.16b,v0.16b
aese v0.16b,v19.16b
aesmc v0.16b,v0.16b
ld1 {v16.16b},[x0],x8
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
eor v16.16b,v16.16b,v5.16b
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x7] // re-pre-load rndkey[1]
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
aese v0.16b,v23.16b
eor v6.16b,v0.16b,v7.16b
b.hs Loop_cbc_enc
st1 {v6.16b},[x1],#16
b Lcbc_done
.align 5
Lcbc_enc128:
ld1 {v2.4s,v3.4s},[x7]
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
b Lenter_cbc_enc128
Loop_cbc_enc128:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
st1 {v6.16b},[x1],#16
Lenter_cbc_enc128:
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
subs x2,x2,#16
aese v0.16b,v2.16b
aesmc v0.16b,v0.16b
csel x8,xzr,x8,eq
aese v0.16b,v3.16b
aesmc v0.16b,v0.16b
aese v0.16b,v18.16b
aesmc v0.16b,v0.16b
aese v0.16b,v19.16b
aesmc v0.16b,v0.16b
ld1 {v16.16b},[x0],x8
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
eor v16.16b,v16.16b,v5.16b
aese v0.16b,v23.16b
eor v6.16b,v0.16b,v7.16b
b.hs Loop_cbc_enc128
st1 {v6.16b},[x1],#16
b Lcbc_done
.align 5
Lcbc_dec:
ld1 {v18.16b},[x0],#16
subs x2,x2,#32 // bias
add w6,w5,#2
orr v3.16b,v0.16b,v0.16b
orr v1.16b,v0.16b,v0.16b
orr v19.16b,v18.16b,v18.16b
b.lo Lcbc_dec_tail
orr v1.16b,v18.16b,v18.16b
ld1 {v18.16b},[x0],#16
orr v2.16b,v0.16b,v0.16b
orr v3.16b,v1.16b,v1.16b
orr v19.16b,v18.16b,v18.16b
Loop3x_cbc_dec:
aesd v0.16b,v16.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aesd v0.16b,v17.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt Loop3x_cbc_dec
aesd v0.16b,v16.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
eor v4.16b,v6.16b,v7.16b
subs x2,x2,#0x30
eor v5.16b,v2.16b,v7.16b
csel x6,x2,x6,lo // x6, w6, is zero at this point
aesd v0.16b,v17.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
eor v17.16b,v3.16b,v7.16b
add x0,x0,x6 // x0 is adjusted in such way that
// at exit from the loop v1.16b-v18.16b
// are loaded with last "words"
orr v6.16b,v19.16b,v19.16b
mov x7,x3
aesd v0.16b,v20.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v20.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v20.16b
aesimc v18.16b,v18.16b
ld1 {v2.16b},[x0],#16
aesd v0.16b,v21.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v21.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v21.16b
aesimc v18.16b,v18.16b
ld1 {v3.16b},[x0],#16
aesd v0.16b,v22.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v22.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v22.16b
aesimc v18.16b,v18.16b
ld1 {v19.16b},[x0],#16
aesd v0.16b,v23.16b
aesd v1.16b,v23.16b
aesd v18.16b,v23.16b
ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0]
add w6,w5,#2
eor v4.16b,v4.16b,v0.16b
eor v5.16b,v5.16b,v1.16b
eor v18.16b,v18.16b,v17.16b
ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1]
st1 {v4.16b},[x1],#16
orr v0.16b,v2.16b,v2.16b
st1 {v5.16b},[x1],#16
orr v1.16b,v3.16b,v3.16b
st1 {v18.16b},[x1],#16
orr v18.16b,v19.16b,v19.16b
b.hs Loop3x_cbc_dec
cmn x2,#0x30
b.eq Lcbc_done
nop
Lcbc_dec_tail:
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt Lcbc_dec_tail
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
aesd v1.16b,v20.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v20.16b
aesimc v18.16b,v18.16b
cmn x2,#0x20
aesd v1.16b,v21.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v21.16b
aesimc v18.16b,v18.16b
eor v5.16b,v6.16b,v7.16b
aesd v1.16b,v22.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v22.16b
aesimc v18.16b,v18.16b
eor v17.16b,v3.16b,v7.16b
aesd v1.16b,v23.16b
aesd v18.16b,v23.16b
b.eq Lcbc_dec_one
eor v5.16b,v5.16b,v1.16b
eor v17.16b,v17.16b,v18.16b
orr v6.16b,v19.16b,v19.16b
st1 {v5.16b},[x1],#16
st1 {v17.16b},[x1],#16
b Lcbc_done
Lcbc_dec_one:
eor v5.16b,v5.16b,v18.16b
orr v6.16b,v19.16b,v19.16b
st1 {v5.16b},[x1],#16
Lcbc_done:
st1 {v6.16b},[x4]
Lcbc_abort:
ldr x29,[sp],#16
ret
.globl _aes_hw_ctr32_encrypt_blocks
.private_extern _aes_hw_ctr32_encrypt_blocks
.align 5
_aes_hw_ctr32_encrypt_blocks:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
ldr w5,[x3,#240]
ldr w8, [x4, #12]
ld1 {v0.4s},[x4]
ld1 {v16.4s,v17.4s},[x3] // load key schedule...
sub w5,w5,#4
mov x12,#16
cmp x2,#2
add x7,x3,x5,lsl#4 // pointer to last 5 round keys
sub w5,w5,#2
ld1 {v20.4s,v21.4s},[x7],#32
ld1 {v22.4s,v23.4s},[x7],#32
ld1 {v7.4s},[x7]
add x7,x3,#32
mov w6,w5
csel x12,xzr,x12,lo
#ifndef __ARMEB__
rev w8, w8
#endif
orr v1.16b,v0.16b,v0.16b
add w10, w8, #1
orr v18.16b,v0.16b,v0.16b
add w8, w8, #2
orr v6.16b,v0.16b,v0.16b
rev w10, w10
mov v1.s[3],w10
b.ls Lctr32_tail
rev w12, w8
sub x2,x2,#3 // bias
mov v18.s[3],w12
b Loop3x_ctr32
.align 4
Loop3x_ctr32:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
aese v18.16b,v16.16b
aesmc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
aese v18.16b,v17.16b
aesmc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt Loop3x_ctr32
aese v0.16b,v16.16b
aesmc v4.16b,v0.16b
aese v1.16b,v16.16b
aesmc v5.16b,v1.16b
ld1 {v2.16b},[x0],#16
orr v0.16b,v6.16b,v6.16b
aese v18.16b,v16.16b
aesmc v18.16b,v18.16b
ld1 {v3.16b},[x0],#16
orr v1.16b,v6.16b,v6.16b
aese v4.16b,v17.16b
aesmc v4.16b,v4.16b
aese v5.16b,v17.16b
aesmc v5.16b,v5.16b
ld1 {v19.16b},[x0],#16
mov x7,x3
aese v18.16b,v17.16b
aesmc v17.16b,v18.16b
orr v18.16b,v6.16b,v6.16b
add w9,w8,#1
aese v4.16b,v20.16b
aesmc v4.16b,v4.16b
aese v5.16b,v20.16b
aesmc v5.16b,v5.16b
eor v2.16b,v2.16b,v7.16b
add w10,w8,#2
aese v17.16b,v20.16b
aesmc v17.16b,v17.16b
eor v3.16b,v3.16b,v7.16b
add w8,w8,#3
aese v4.16b,v21.16b
aesmc v4.16b,v4.16b
aese v5.16b,v21.16b
aesmc v5.16b,v5.16b
eor v19.16b,v19.16b,v7.16b
rev w9,w9
aese v17.16b,v21.16b
aesmc v17.16b,v17.16b
mov v0.s[3], w9
rev w10,w10
aese v4.16b,v22.16b
aesmc v4.16b,v4.16b
aese v5.16b,v22.16b
aesmc v5.16b,v5.16b
mov v1.s[3], w10
rev w12,w8
aese v17.16b,v22.16b
aesmc v17.16b,v17.16b
mov v18.s[3], w12
subs x2,x2,#3
aese v4.16b,v23.16b
aese v5.16b,v23.16b
aese v17.16b,v23.16b
eor v2.16b,v2.16b,v4.16b
ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0]
st1 {v2.16b},[x1],#16
eor v3.16b,v3.16b,v5.16b
mov w6,w5
st1 {v3.16b},[x1],#16
eor v19.16b,v19.16b,v17.16b
ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1]
st1 {v19.16b},[x1],#16
b.hs Loop3x_ctr32
adds x2,x2,#3
b.eq Lctr32_done
cmp x2,#1
mov x12,#16
csel x12,xzr,x12,eq
Lctr32_tail:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
ld1 {v17.4s},[x7],#16
b.gt Lctr32_tail
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
ld1 {v2.16b},[x0],x12
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
aese v1.16b,v20.16b
aesmc v1.16b,v1.16b
ld1 {v3.16b},[x0]
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
aese v1.16b,v21.16b
aesmc v1.16b,v1.16b
eor v2.16b,v2.16b,v7.16b
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
aese v1.16b,v22.16b
aesmc v1.16b,v1.16b
eor v3.16b,v3.16b,v7.16b
aese v0.16b,v23.16b
aese v1.16b,v23.16b
cmp x2,#1
eor v2.16b,v2.16b,v0.16b
eor v3.16b,v3.16b,v1.16b
st1 {v2.16b},[x1],#16
b.eq Lctr32_done
st1 {v3.16b},[x1]
Lctr32_done:
ldr x29,[sp],#16
ret
#endif
#endif // !OPENSSL_NO_ASM

1433
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/armv8-mont.S
View File

File diff suppressed because it is too large Load Diff

343
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/ghash-neon-armv8.S
View File

@ -1,343 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.globl _gcm_init_neon
.private_extern _gcm_init_neon
.align 4
_gcm_init_neon:
AARCH64_VALID_CALL_TARGET
// This function is adapted from gcm_init_v8. xC2 is t3.
ld1 {v17.2d}, [x1] // load H
movi v19.16b, #0xe1
shl v19.2d, v19.2d, #57 // 0xc2.0
ext v3.16b, v17.16b, v17.16b, #8
ushr v18.2d, v19.2d, #63
dup v17.4s, v17.s[1]
ext v16.16b, v18.16b, v19.16b, #8 // t0=0xc2....01
ushr v18.2d, v3.2d, #63
sshr v17.4s, v17.4s, #31 // broadcast carry bit
and v18.16b, v18.16b, v16.16b
shl v3.2d, v3.2d, #1
ext v18.16b, v18.16b, v18.16b, #8
and v16.16b, v16.16b, v17.16b
orr v3.16b, v3.16b, v18.16b // H<<<=1
eor v5.16b, v3.16b, v16.16b // twisted H
st1 {v5.2d}, [x0] // store Htable[0]
ret
.globl _gcm_gmult_neon
.private_extern _gcm_gmult_neon
.align 4
_gcm_gmult_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v3.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]
adrp x9, Lmasks@PAGE // load constants
add x9, x9, Lmasks@PAGEOFF
ld1 {v24.2d, v25.2d}, [x9]
rev64 v3.16b, v3.16b // byteswap Xi
ext v3.16b, v3.16b, v3.16b, #8
eor v7.8b, v5.8b, v6.8b // Karatsuba pre-processing
mov x3, #16
b Lgmult_neon
.globl _gcm_ghash_neon
.private_extern _gcm_ghash_neon
.align 4
_gcm_ghash_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v0.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]
adrp x9, Lmasks@PAGE // load constants
add x9, x9, Lmasks@PAGEOFF
ld1 {v24.2d, v25.2d}, [x9]
rev64 v0.16b, v0.16b // byteswap Xi
ext v0.16b, v0.16b, v0.16b, #8
eor v7.8b, v5.8b, v6.8b // Karatsuba pre-processing
Loop_neon:
ld1 {v3.16b}, [x2], #16 // load inp
rev64 v3.16b, v3.16b // byteswap inp
ext v3.16b, v3.16b, v3.16b, #8
eor v3.16b, v3.16b, v0.16b // inp ^= Xi
Lgmult_neon:
// Split the input into v3 and v4. (The upper halves are unused,
// so it is okay to leave them alone.)
ins v4.d[0], v3.d[1]
ext v16.8b, v5.8b, v5.8b, #1 // A1
pmull v16.8h, v16.8b, v3.8b // F = A1*B
ext v0.8b, v3.8b, v3.8b, #1 // B1
pmull v0.8h, v5.8b, v0.8b // E = A*B1
ext v17.8b, v5.8b, v5.8b, #2 // A2
pmull v17.8h, v17.8b, v3.8b // H = A2*B
ext v19.8b, v3.8b, v3.8b, #2 // B2
pmull v19.8h, v5.8b, v19.8b // G = A*B2
ext v18.8b, v5.8b, v5.8b, #3 // A3
eor v16.16b, v16.16b, v0.16b // L = E + F
pmull v18.8h, v18.8b, v3.8b // J = A3*B
ext v0.8b, v3.8b, v3.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v0.8h, v5.8b, v0.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v3.8b, v3.8b, #4 // B4
eor v18.16b, v18.16b, v0.16b // N = I + J
pmull v19.8h, v5.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v0.8h, v5.8b, v3.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v0.16b, v0.16b, v16.16b
eor v0.16b, v0.16b, v18.16b
eor v3.8b, v3.8b, v4.8b // Karatsuba pre-processing
ext v16.8b, v7.8b, v7.8b, #1 // A1
pmull v16.8h, v16.8b, v3.8b // F = A1*B
ext v1.8b, v3.8b, v3.8b, #1 // B1
pmull v1.8h, v7.8b, v1.8b // E = A*B1
ext v17.8b, v7.8b, v7.8b, #2 // A2
pmull v17.8h, v17.8b, v3.8b // H = A2*B
ext v19.8b, v3.8b, v3.8b, #2 // B2
pmull v19.8h, v7.8b, v19.8b // G = A*B2
ext v18.8b, v7.8b, v7.8b, #3 // A3
eor v16.16b, v16.16b, v1.16b // L = E + F
pmull v18.8h, v18.8b, v3.8b // J = A3*B
ext v1.8b, v3.8b, v3.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v1.8h, v7.8b, v1.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v3.8b, v3.8b, #4 // B4
eor v18.16b, v18.16b, v1.16b // N = I + J
pmull v19.8h, v7.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v1.8h, v7.8b, v3.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v1.16b, v1.16b, v16.16b
eor v1.16b, v1.16b, v18.16b
ext v16.8b, v6.8b, v6.8b, #1 // A1
pmull v16.8h, v16.8b, v4.8b // F = A1*B
ext v2.8b, v4.8b, v4.8b, #1 // B1
pmull v2.8h, v6.8b, v2.8b // E = A*B1
ext v17.8b, v6.8b, v6.8b, #2 // A2
pmull v17.8h, v17.8b, v4.8b // H = A2*B
ext v19.8b, v4.8b, v4.8b, #2 // B2
pmull v19.8h, v6.8b, v19.8b // G = A*B2
ext v18.8b, v6.8b, v6.8b, #3 // A3
eor v16.16b, v16.16b, v2.16b // L = E + F
pmull v18.8h, v18.8b, v4.8b // J = A3*B
ext v2.8b, v4.8b, v4.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v2.8h, v6.8b, v2.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v4.8b, v4.8b, #4 // B4
eor v18.16b, v18.16b, v2.16b // N = I + J
pmull v19.8h, v6.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v2.8h, v6.8b, v4.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v2.16b, v2.16b, v16.16b
eor v2.16b, v2.16b, v18.16b
ext v16.16b, v0.16b, v2.16b, #8
eor v1.16b, v1.16b, v0.16b // Karatsuba post-processing
eor v1.16b, v1.16b, v2.16b
eor v1.16b, v1.16b, v16.16b // Xm overlaps Xh.lo and Xl.hi
ins v0.d[1], v1.d[0] // Xh|Xl - 256-bit result
// This is a no-op due to the ins instruction below.
// ins v2.d[0], v1.d[1]
// equivalent of reduction_avx from ghash-x86_64.pl
shl v17.2d, v0.2d, #57 // 1st phase
shl v18.2d, v0.2d, #62
eor v18.16b, v18.16b, v17.16b //
shl v17.2d, v0.2d, #63
eor v18.16b, v18.16b, v17.16b //
// Note Xm contains {Xl.d[1], Xh.d[0]}.
eor v18.16b, v18.16b, v1.16b
ins v0.d[1], v18.d[0] // Xl.d[1] ^= t2.d[0]
ins v2.d[0], v18.d[1] // Xh.d[0] ^= t2.d[1]
ushr v18.2d, v0.2d, #1 // 2nd phase
eor v2.16b, v2.16b,v0.16b
eor v0.16b, v0.16b,v18.16b //
ushr v18.2d, v18.2d, #6
ushr v0.2d, v0.2d, #1 //
eor v0.16b, v0.16b, v2.16b //
eor v0.16b, v0.16b, v18.16b //
subs x3, x3, #16
bne Loop_neon
rev64 v0.16b, v0.16b // byteswap Xi and write
ext v0.16b, v0.16b, v0.16b, #8
st1 {v0.16b}, [x0]
ret
.section __TEXT,__const
.align 4
Lmasks:
.quad 0x0000ffffffffffff // k48
.quad 0x00000000ffffffff // k32
.quad 0x000000000000ffff // k16
.quad 0x0000000000000000 // k0
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,100,101,114,105,118,101,100,32,102,114,111,109,32,65,82,77,118,52,32,118,101,114,115,105,111,110,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif // !OPENSSL_NO_ASM

249
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/ghashv8-armx64.S
View File

@ -1,249 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.globl _gcm_init_v8
.private_extern _gcm_init_v8
.align 4
_gcm_init_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x1] //load input H
movi v19.16b,#0xe1
shl v19.2d,v19.2d,#57 //0xc2.0
ext v3.16b,v17.16b,v17.16b,#8
ushr v18.2d,v19.2d,#63
dup v17.4s,v17.s[1]
ext v16.16b,v18.16b,v19.16b,#8 //t0=0xc2....01
ushr v18.2d,v3.2d,#63
sshr v17.4s,v17.4s,#31 //broadcast carry bit
and v18.16b,v18.16b,v16.16b
shl v3.2d,v3.2d,#1
ext v18.16b,v18.16b,v18.16b,#8
and v16.16b,v16.16b,v17.16b
orr v3.16b,v3.16b,v18.16b //H<<<=1
eor v20.16b,v3.16b,v16.16b //twisted H
st1 {v20.2d},[x0],#16 //store Htable[0]
//calculate H^2
ext v16.16b,v20.16b,v20.16b,#8 //Karatsuba pre-processing
pmull v0.1q,v20.1d,v20.1d
eor v16.16b,v16.16b,v20.16b
pmull2 v2.1q,v20.2d,v20.2d
pmull v1.1q,v16.1d,v16.1d
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v22.16b,v0.16b,v18.16b
ext v17.16b,v22.16b,v22.16b,#8 //Karatsuba pre-processing
eor v17.16b,v17.16b,v22.16b
ext v21.16b,v16.16b,v17.16b,#8 //pack Karatsuba pre-processed
st1 {v21.2d,v22.2d},[x0] //store Htable[1..2]
ret
.globl _gcm_gmult_v8
.private_extern _gcm_gmult_v8
.align 4
_gcm_gmult_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x0] //load Xi
movi v19.16b,#0xe1
ld1 {v20.2d,v21.2d},[x1] //load twisted H, ...
shl v19.2d,v19.2d,#57
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ext v3.16b,v17.16b,v17.16b,#8
pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo
eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi
pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi)
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
st1 {v0.2d},[x0] //write out Xi
ret
.globl _gcm_ghash_v8
.private_extern _gcm_ghash_v8
.align 4
_gcm_ghash_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v0.2d},[x0] //load [rotated] Xi
//"[rotated]" means that
//loaded value would have
//to be rotated in order to
//make it appear as in
//algorithm specification
subs x3,x3,#32 //see if x3 is 32 or larger
mov x12,#16 //x12 is used as post-
//increment for input pointer;
//as loop is modulo-scheduled
//x12 is zeroed just in time
//to preclude overstepping
//inp[len], which means that
//last block[s] are actually
//loaded twice, but last
//copy is not processed
ld1 {v20.2d,v21.2d},[x1],#32 //load twisted H, ..., H^2
movi v19.16b,#0xe1
ld1 {v22.2d},[x1]
csel x12,xzr,x12,eq //is it time to zero x12?
ext v0.16b,v0.16b,v0.16b,#8 //rotate Xi
ld1 {v16.2d},[x2],#16 //load [rotated] I[0]
shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant
#ifndef __ARMEB__
rev64 v16.16b,v16.16b
rev64 v0.16b,v0.16b
#endif
ext v3.16b,v16.16b,v16.16b,#8 //rotate I[0]
b.lo Lodd_tail_v8 //x3 was less than 32
ld1 {v17.2d},[x2],x12 //load [rotated] I[1]
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ext v7.16b,v17.16b,v17.16b,#8
eor v3.16b,v3.16b,v0.16b //I[i]^=Xi
pmull v4.1q,v20.1d,v7.1d //H·Ii+1
eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing
pmull2 v6.1q,v20.2d,v7.2d
b Loop_mod2x_v8
.align 4
Loop_mod2x_v8:
ext v18.16b,v3.16b,v3.16b,#8
subs x3,x3,#32 //is there more data?
pmull v0.1q,v22.1d,v3.1d //H^2.lo·Xi.lo
csel x12,xzr,x12,lo //is it time to zero x12?
pmull v5.1q,v21.1d,v17.1d
eor v18.16b,v18.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v22.2d,v3.2d //H^2.hi·Xi.hi
eor v0.16b,v0.16b,v4.16b //accumulate
pmull2 v1.1q,v21.2d,v18.2d //(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
ld1 {v16.2d},[x2],x12 //load [rotated] I[i+2]
eor v2.16b,v2.16b,v6.16b
csel x12,xzr,x12,eq //is it time to zero x12?
eor v1.16b,v1.16b,v5.16b
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v17.2d},[x2],x12 //load [rotated] I[i+3]
#ifndef __ARMEB__
rev64 v16.16b,v16.16b
#endif
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
ext v7.16b,v17.16b,v17.16b,#8
ext v3.16b,v16.16b,v16.16b,#8
eor v0.16b,v1.16b,v18.16b
pmull v4.1q,v20.1d,v7.1d //H·Ii+1
eor v3.16b,v3.16b,v2.16b //accumulate v3.16b early
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v3.16b,v3.16b,v18.16b
eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing
eor v3.16b,v3.16b,v0.16b
pmull2 v6.1q,v20.2d,v7.2d
b.hs Loop_mod2x_v8 //there was at least 32 more bytes
eor v2.16b,v2.16b,v18.16b
ext v3.16b,v16.16b,v16.16b,#8 //re-construct v3.16b
adds x3,x3,#32 //re-construct x3
eor v0.16b,v0.16b,v2.16b //re-construct v0.16b
b.eq Ldone_v8 //is x3 zero?
Lodd_tail_v8:
ext v18.16b,v0.16b,v0.16b,#8
eor v3.16b,v3.16b,v0.16b //inp^=Xi
eor v17.16b,v16.16b,v18.16b //v17.16b is rotated inp^Xi
pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo
eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi
pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi)
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
Ldone_v8:
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
st1 {v0.2d},[x0] //write out Xi
ret
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif // !OPENSSL_NO_ASM

1236
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/sha1-armv8.S
View File

File diff suppressed because it is too large Load Diff

1214
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/sha256-armv8.S
View File

File diff suppressed because it is too large Load Diff

1084
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/sha512-armv8.S
View File

File diff suppressed because it is too large Load Diff

1232
contrib/boringssl-cmake/ios-aarch64/crypto/fipsmodule/vpaes-armv8.S
View File

File diff suppressed because it is too large Load Diff

758
contrib/boringssl-cmake/ios-aarch64/crypto/test/trampoline-armv8.S
View File

@ -1,758 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
// abi_test_trampoline loads callee-saved registers from |state|, calls |func|
// with |argv|, then saves the callee-saved registers into |state|. It returns
// the result of |func|. The |unwind| argument is unused.
// uint64_t abi_test_trampoline(void (*func)(...), CallerState *state,
// const uint64_t *argv, size_t argc,
// uint64_t unwind);
.globl _abi_test_trampoline
.private_extern _abi_test_trampoline
.align 4
_abi_test_trampoline:
Labi_test_trampoline_begin:
AARCH64_SIGN_LINK_REGISTER
// Stack layout (low to high addresses)
// x29,x30 (16 bytes)
// d8-d15 (64 bytes)
// x19-x28 (80 bytes)
// x1 (8 bytes)
// padding (8 bytes)
stp x29, x30, [sp, #-176]!
mov x29, sp
// Saved callee-saved registers and |state|.
stp d8, d9, [sp, #16]
stp d10, d11, [sp, #32]
stp d12, d13, [sp, #48]
stp d14, d15, [sp, #64]
stp x19, x20, [sp, #80]
stp x21, x22, [sp, #96]
stp x23, x24, [sp, #112]
stp x25, x26, [sp, #128]
stp x27, x28, [sp, #144]
str x1, [sp, #160]
// Load registers from |state|, with the exception of x29. x29 is the
// frame pointer and also callee-saved, but AAPCS64 allows platforms to
// mandate that x29 always point to a frame. iOS64 does so, which means
// we cannot fill x29 with entropy without violating ABI rules
// ourselves. x29 is tested separately below.
ldp d8, d9, [x1], #16
ldp d10, d11, [x1], #16
ldp d12, d13, [x1], #16
ldp d14, d15, [x1], #16
ldp x19, x20, [x1], #16
ldp x21, x22, [x1], #16
ldp x23, x24, [x1], #16
ldp x25, x26, [x1], #16
ldp x27, x28, [x1], #16
// Move parameters into temporary registers.
mov x9, x0
mov x10, x2
mov x11, x3
// Load parameters into registers.
cbz x11, Largs_done
ldr x0, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x1, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x2, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x3, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x4, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x5, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x6, [x10], #8
subs x11, x11, #1
b.eq Largs_done
ldr x7, [x10], #8
Largs_done:
blr x9
// Reload |state| and store registers.
ldr x1, [sp, #160]
stp d8, d9, [x1], #16
stp d10, d11, [x1], #16
stp d12, d13, [x1], #16
stp d14, d15, [x1], #16
stp x19, x20, [x1], #16
stp x21, x22, [x1], #16
stp x23, x24, [x1], #16
stp x25, x26, [x1], #16
stp x27, x28, [x1], #16
// |func| is required to preserve x29, the frame pointer. We cannot load
// random values into x29 (see comment above), so compare it against the
// expected value and zero the field of |state| if corrupted.
mov x9, sp
cmp x29, x9
b.eq Lx29_ok
str xzr, [x1]
Lx29_ok:
// Restore callee-saved registers.
ldp d8, d9, [sp, #16]
ldp d10, d11, [sp, #32]
ldp d12, d13, [sp, #48]
ldp d14, d15, [sp, #64]
ldp x19, x20, [sp, #80]
ldp x21, x22, [sp, #96]
ldp x23, x24, [sp, #112]
ldp x25, x26, [sp, #128]
ldp x27, x28, [sp, #144]
ldp x29, x30, [sp], #176
AARCH64_VALIDATE_LINK_REGISTER
ret
.globl _abi_test_clobber_x0
.private_extern _abi_test_clobber_x0
.align 4
_abi_test_clobber_x0:
AARCH64_VALID_CALL_TARGET
mov x0, xzr
ret
.globl _abi_test_clobber_x1
.private_extern _abi_test_clobber_x1
.align 4
_abi_test_clobber_x1:
AARCH64_VALID_CALL_TARGET
mov x1, xzr
ret
.globl _abi_test_clobber_x2
.private_extern _abi_test_clobber_x2
.align 4
_abi_test_clobber_x2:
AARCH64_VALID_CALL_TARGET
mov x2, xzr
ret
.globl _abi_test_clobber_x3
.private_extern _abi_test_clobber_x3
.align 4
_abi_test_clobber_x3:
AARCH64_VALID_CALL_TARGET
mov x3, xzr
ret
.globl _abi_test_clobber_x4
.private_extern _abi_test_clobber_x4
.align 4
_abi_test_clobber_x4:
AARCH64_VALID_CALL_TARGET
mov x4, xzr
ret
.globl _abi_test_clobber_x5
.private_extern _abi_test_clobber_x5
.align 4
_abi_test_clobber_x5:
AARCH64_VALID_CALL_TARGET
mov x5, xzr
ret
.globl _abi_test_clobber_x6
.private_extern _abi_test_clobber_x6
.align 4
_abi_test_clobber_x6:
AARCH64_VALID_CALL_TARGET
mov x6, xzr
ret
.globl _abi_test_clobber_x7
.private_extern _abi_test_clobber_x7
.align 4
_abi_test_clobber_x7:
AARCH64_VALID_CALL_TARGET
mov x7, xzr
ret
.globl _abi_test_clobber_x8
.private_extern _abi_test_clobber_x8
.align 4
_abi_test_clobber_x8:
AARCH64_VALID_CALL_TARGET
mov x8, xzr
ret
.globl _abi_test_clobber_x9
.private_extern _abi_test_clobber_x9
.align 4
_abi_test_clobber_x9:
AARCH64_VALID_CALL_TARGET
mov x9, xzr
ret
.globl _abi_test_clobber_x10
.private_extern _abi_test_clobber_x10
.align 4
_abi_test_clobber_x10:
AARCH64_VALID_CALL_TARGET
mov x10, xzr
ret
.globl _abi_test_clobber_x11
.private_extern _abi_test_clobber_x11
.align 4
_abi_test_clobber_x11:
AARCH64_VALID_CALL_TARGET
mov x11, xzr
ret
.globl _abi_test_clobber_x12
.private_extern _abi_test_clobber_x12
.align 4
_abi_test_clobber_x12:
AARCH64_VALID_CALL_TARGET
mov x12, xzr
ret
.globl _abi_test_clobber_x13
.private_extern _abi_test_clobber_x13
.align 4
_abi_test_clobber_x13:
AARCH64_VALID_CALL_TARGET
mov x13, xzr
ret
.globl _abi_test_clobber_x14
.private_extern _abi_test_clobber_x14
.align 4
_abi_test_clobber_x14:
AARCH64_VALID_CALL_TARGET
mov x14, xzr
ret
.globl _abi_test_clobber_x15
.private_extern _abi_test_clobber_x15
.align 4
_abi_test_clobber_x15:
AARCH64_VALID_CALL_TARGET
mov x15, xzr
ret
.globl _abi_test_clobber_x16
.private_extern _abi_test_clobber_x16
.align 4
_abi_test_clobber_x16:
AARCH64_VALID_CALL_TARGET
mov x16, xzr
ret
.globl _abi_test_clobber_x17
.private_extern _abi_test_clobber_x17
.align 4
_abi_test_clobber_x17:
AARCH64_VALID_CALL_TARGET
mov x17, xzr
ret
.globl _abi_test_clobber_x19
.private_extern _abi_test_clobber_x19
.align 4
_abi_test_clobber_x19:
AARCH64_VALID_CALL_TARGET
mov x19, xzr
ret
.globl _abi_test_clobber_x20
.private_extern _abi_test_clobber_x20
.align 4
_abi_test_clobber_x20:
AARCH64_VALID_CALL_TARGET
mov x20, xzr
ret
.globl _abi_test_clobber_x21
.private_extern _abi_test_clobber_x21
.align 4
_abi_test_clobber_x21:
AARCH64_VALID_CALL_TARGET
mov x21, xzr
ret
.globl _abi_test_clobber_x22
.private_extern _abi_test_clobber_x22
.align 4
_abi_test_clobber_x22:
AARCH64_VALID_CALL_TARGET
mov x22, xzr
ret
.globl _abi_test_clobber_x23
.private_extern _abi_test_clobber_x23
.align 4
_abi_test_clobber_x23:
AARCH64_VALID_CALL_TARGET
mov x23, xzr
ret
.globl _abi_test_clobber_x24
.private_extern _abi_test_clobber_x24
.align 4
_abi_test_clobber_x24:
AARCH64_VALID_CALL_TARGET
mov x24, xzr
ret
.globl _abi_test_clobber_x25
.private_extern _abi_test_clobber_x25
.align 4
_abi_test_clobber_x25:
AARCH64_VALID_CALL_TARGET
mov x25, xzr
ret
.globl _abi_test_clobber_x26
.private_extern _abi_test_clobber_x26
.align 4
_abi_test_clobber_x26:
AARCH64_VALID_CALL_TARGET
mov x26, xzr
ret
.globl _abi_test_clobber_x27
.private_extern _abi_test_clobber_x27
.align 4
_abi_test_clobber_x27:
AARCH64_VALID_CALL_TARGET
mov x27, xzr
ret
.globl _abi_test_clobber_x28
.private_extern _abi_test_clobber_x28
.align 4
_abi_test_clobber_x28:
AARCH64_VALID_CALL_TARGET
mov x28, xzr
ret
.globl _abi_test_clobber_x29
.private_extern _abi_test_clobber_x29
.align 4
_abi_test_clobber_x29:
AARCH64_VALID_CALL_TARGET
mov x29, xzr
ret
.globl _abi_test_clobber_d0
.private_extern _abi_test_clobber_d0
.align 4
_abi_test_clobber_d0:
AARCH64_VALID_CALL_TARGET
fmov d0, xzr
ret
.globl _abi_test_clobber_d1
.private_extern _abi_test_clobber_d1
.align 4
_abi_test_clobber_d1:
AARCH64_VALID_CALL_TARGET
fmov d1, xzr
ret
.globl _abi_test_clobber_d2
.private_extern _abi_test_clobber_d2
.align 4
_abi_test_clobber_d2:
AARCH64_VALID_CALL_TARGET
fmov d2, xzr
ret
.globl _abi_test_clobber_d3
.private_extern _abi_test_clobber_d3
.align 4
_abi_test_clobber_d3:
AARCH64_VALID_CALL_TARGET
fmov d3, xzr
ret
.globl _abi_test_clobber_d4
.private_extern _abi_test_clobber_d4
.align 4
_abi_test_clobber_d4:
AARCH64_VALID_CALL_TARGET
fmov d4, xzr
ret
.globl _abi_test_clobber_d5
.private_extern _abi_test_clobber_d5
.align 4
_abi_test_clobber_d5:
AARCH64_VALID_CALL_TARGET
fmov d5, xzr
ret
.globl _abi_test_clobber_d6
.private_extern _abi_test_clobber_d6
.align 4
_abi_test_clobber_d6:
AARCH64_VALID_CALL_TARGET
fmov d6, xzr
ret
.globl _abi_test_clobber_d7
.private_extern _abi_test_clobber_d7
.align 4
_abi_test_clobber_d7:
AARCH64_VALID_CALL_TARGET
fmov d7, xzr
ret
.globl _abi_test_clobber_d8
.private_extern _abi_test_clobber_d8
.align 4
_abi_test_clobber_d8:
AARCH64_VALID_CALL_TARGET
fmov d8, xzr
ret
.globl _abi_test_clobber_d9
.private_extern _abi_test_clobber_d9
.align 4
_abi_test_clobber_d9:
AARCH64_VALID_CALL_TARGET
fmov d9, xzr
ret
.globl _abi_test_clobber_d10
.private_extern _abi_test_clobber_d10
.align 4
_abi_test_clobber_d10:
AARCH64_VALID_CALL_TARGET
fmov d10, xzr
ret
.globl _abi_test_clobber_d11
.private_extern _abi_test_clobber_d11
.align 4
_abi_test_clobber_d11:
AARCH64_VALID_CALL_TARGET
fmov d11, xzr
ret
.globl _abi_test_clobber_d12
.private_extern _abi_test_clobber_d12
.align 4
_abi_test_clobber_d12:
AARCH64_VALID_CALL_TARGET
fmov d12, xzr
ret
.globl _abi_test_clobber_d13
.private_extern _abi_test_clobber_d13
.align 4
_abi_test_clobber_d13:
AARCH64_VALID_CALL_TARGET
fmov d13, xzr
ret
.globl _abi_test_clobber_d14
.private_extern _abi_test_clobber_d14
.align 4
_abi_test_clobber_d14:
AARCH64_VALID_CALL_TARGET
fmov d14, xzr
ret
.globl _abi_test_clobber_d15
.private_extern _abi_test_clobber_d15
.align 4
_abi_test_clobber_d15:
AARCH64_VALID_CALL_TARGET
fmov d15, xzr
ret
.globl _abi_test_clobber_d16
.private_extern _abi_test_clobber_d16
.align 4
_abi_test_clobber_d16:
AARCH64_VALID_CALL_TARGET
fmov d16, xzr
ret
.globl _abi_test_clobber_d17
.private_extern _abi_test_clobber_d17
.align 4
_abi_test_clobber_d17:
AARCH64_VALID_CALL_TARGET
fmov d17, xzr
ret
.globl _abi_test_clobber_d18
.private_extern _abi_test_clobber_d18
.align 4
_abi_test_clobber_d18:
AARCH64_VALID_CALL_TARGET
fmov d18, xzr
ret
.globl _abi_test_clobber_d19
.private_extern _abi_test_clobber_d19
.align 4
_abi_test_clobber_d19:
AARCH64_VALID_CALL_TARGET
fmov d19, xzr
ret
.globl _abi_test_clobber_d20
.private_extern _abi_test_clobber_d20
.align 4
_abi_test_clobber_d20:
AARCH64_VALID_CALL_TARGET
fmov d20, xzr
ret
.globl _abi_test_clobber_d21
.private_extern _abi_test_clobber_d21
.align 4
_abi_test_clobber_d21:
AARCH64_VALID_CALL_TARGET
fmov d21, xzr
ret
.globl _abi_test_clobber_d22
.private_extern _abi_test_clobber_d22
.align 4
_abi_test_clobber_d22:
AARCH64_VALID_CALL_TARGET
fmov d22, xzr
ret
.globl _abi_test_clobber_d23
.private_extern _abi_test_clobber_d23
.align 4
_abi_test_clobber_d23:
AARCH64_VALID_CALL_TARGET
fmov d23, xzr
ret
.globl _abi_test_clobber_d24
.private_extern _abi_test_clobber_d24
.align 4
_abi_test_clobber_d24:
AARCH64_VALID_CALL_TARGET
fmov d24, xzr
ret
.globl _abi_test_clobber_d25
.private_extern _abi_test_clobber_d25
.align 4
_abi_test_clobber_d25:
AARCH64_VALID_CALL_TARGET
fmov d25, xzr
ret
.globl _abi_test_clobber_d26
.private_extern _abi_test_clobber_d26
.align 4
_abi_test_clobber_d26:
AARCH64_VALID_CALL_TARGET
fmov d26, xzr
ret
.globl _abi_test_clobber_d27
.private_extern _abi_test_clobber_d27
.align 4
_abi_test_clobber_d27:
AARCH64_VALID_CALL_TARGET
fmov d27, xzr
ret
.globl _abi_test_clobber_d28
.private_extern _abi_test_clobber_d28
.align 4
_abi_test_clobber_d28:
AARCH64_VALID_CALL_TARGET
fmov d28, xzr
ret
.globl _abi_test_clobber_d29
.private_extern _abi_test_clobber_d29
.align 4
_abi_test_clobber_d29:
AARCH64_VALID_CALL_TARGET
fmov d29, xzr
ret
.globl _abi_test_clobber_d30
.private_extern _abi_test_clobber_d30
.align 4
_abi_test_clobber_d30:
AARCH64_VALID_CALL_TARGET
fmov d30, xzr
ret
.globl _abi_test_clobber_d31
.private_extern _abi_test_clobber_d31
.align 4
_abi_test_clobber_d31:
AARCH64_VALID_CALL_TARGET
fmov d31, xzr
ret
.globl _abi_test_clobber_v8_upper
.private_extern _abi_test_clobber_v8_upper
.align 4
_abi_test_clobber_v8_upper:
AARCH64_VALID_CALL_TARGET
fmov v8.d[1], xzr
ret
.globl _abi_test_clobber_v9_upper
.private_extern _abi_test_clobber_v9_upper
.align 4
_abi_test_clobber_v9_upper:
AARCH64_VALID_CALL_TARGET
fmov v9.d[1], xzr
ret
.globl _abi_test_clobber_v10_upper
.private_extern _abi_test_clobber_v10_upper
.align 4
_abi_test_clobber_v10_upper:
AARCH64_VALID_CALL_TARGET
fmov v10.d[1], xzr
ret
.globl _abi_test_clobber_v11_upper
.private_extern _abi_test_clobber_v11_upper
.align 4
_abi_test_clobber_v11_upper:
AARCH64_VALID_CALL_TARGET
fmov v11.d[1], xzr
ret
.globl _abi_test_clobber_v12_upper
.private_extern _abi_test_clobber_v12_upper
.align 4
_abi_test_clobber_v12_upper:
AARCH64_VALID_CALL_TARGET
fmov v12.d[1], xzr
ret
.globl _abi_test_clobber_v13_upper
.private_extern _abi_test_clobber_v13_upper
.align 4
_abi_test_clobber_v13_upper:
AARCH64_VALID_CALL_TARGET
fmov v13.d[1], xzr
ret
.globl _abi_test_clobber_v14_upper
.private_extern _abi_test_clobber_v14_upper
.align 4
_abi_test_clobber_v14_upper:
AARCH64_VALID_CALL_TARGET
fmov v14.d[1], xzr
ret
.globl _abi_test_clobber_v15_upper
.private_extern _abi_test_clobber_v15_upper
.align 4
_abi_test_clobber_v15_upper:
AARCH64_VALID_CALL_TARGET
fmov v15.d[1], xzr
ret
#endif // !OPENSSL_NO_ASM

1498
contrib/boringssl-cmake/ios-arm/crypto/chacha/chacha-armv4.S
View File

File diff suppressed because it is too large Load Diff

790
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/aesv8-armx32.S
View File

@ -1,790 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
#if __ARM_MAX_ARCH__>=7
.text
.code 32
#undef __thumb2__
.align 5
Lrcon:
.long 0x01,0x01,0x01,0x01
.long 0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d @ rotate-n-splat
.long 0x1b,0x1b,0x1b,0x1b
.text
.globl _aes_hw_set_encrypt_key
.private_extern _aes_hw_set_encrypt_key
#ifdef __thumb2__
.thumb_func _aes_hw_set_encrypt_key
#endif
.align 5
_aes_hw_set_encrypt_key:
Lenc_key:
mov r3,#-1
cmp r0,#0
beq Lenc_key_abort
cmp r2,#0
beq Lenc_key_abort
mov r3,#-2
cmp r1,#128
blt Lenc_key_abort
cmp r1,#256
bgt Lenc_key_abort
tst r1,#0x3f
bne Lenc_key_abort
adr r3,Lrcon
cmp r1,#192
veor q0,q0,q0
vld1.8 {q3},[r0]!
mov r1,#8 @ reuse r1
vld1.32 {q1,q2},[r3]!
blt Loop128
beq L192
b L256
.align 4
Loop128:
vtbl.8 d20,{q3},d4
vtbl.8 d21,{q3},d5
vext.8 q9,q0,q3,#12
vst1.32 {q3},[r2]!
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
subs r1,r1,#1
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q10,q10,q1
veor q3,q3,q9
vshl.u8 q1,q1,#1
veor q3,q3,q10
bne Loop128
vld1.32 {q1},[r3]
vtbl.8 d20,{q3},d4
vtbl.8 d21,{q3},d5
vext.8 q9,q0,q3,#12
vst1.32 {q3},[r2]!
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q10,q10,q1
veor q3,q3,q9
vshl.u8 q1,q1,#1
veor q3,q3,q10
vtbl.8 d20,{q3},d4
vtbl.8 d21,{q3},d5
vext.8 q9,q0,q3,#12
vst1.32 {q3},[r2]!
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q10,q10,q1
veor q3,q3,q9
veor q3,q3,q10
vst1.32 {q3},[r2]
add r2,r2,#0x50
mov r12,#10
b Ldone
.align 4
L192:
vld1.8 {d16},[r0]!
vmov.i8 q10,#8 @ borrow q10
vst1.32 {q3},[r2]!
vsub.i8 q2,q2,q10 @ adjust the mask
Loop192:
vtbl.8 d20,{q8},d4
vtbl.8 d21,{q8},d5
vext.8 q9,q0,q3,#12
vst1.32 {d16},[r2]!
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
subs r1,r1,#1
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vdup.32 q9,d7[1]
veor q9,q9,q8
veor q10,q10,q1
vext.8 q8,q0,q8,#12
vshl.u8 q1,q1,#1
veor q8,q8,q9
veor q3,q3,q10
veor q8,q8,q10
vst1.32 {q3},[r2]!
bne Loop192
mov r12,#12
add r2,r2,#0x20
b Ldone
.align 4
L256:
vld1.8 {q8},[r0]
mov r1,#7
mov r12,#14
vst1.32 {q3},[r2]!
Loop256:
vtbl.8 d20,{q8},d4
vtbl.8 d21,{q8},d5
vext.8 q9,q0,q3,#12
vst1.32 {q8},[r2]!
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
subs r1,r1,#1
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q3,q3,q9
vext.8 q9,q0,q9,#12
veor q10,q10,q1
veor q3,q3,q9
vshl.u8 q1,q1,#1
veor q3,q3,q10
vst1.32 {q3},[r2]!
beq Ldone
vdup.32 q10,d7[1]
vext.8 q9,q0,q8,#12
.byte 0x00,0x43,0xf0,0xf3 @ aese q10,q0
veor q8,q8,q9
vext.8 q9,q0,q9,#12
veor q8,q8,q9
vext.8 q9,q0,q9,#12
veor q8,q8,q9
veor q8,q8,q10
b Loop256
Ldone:
str r12,[r2]
mov r3,#0
Lenc_key_abort:
mov r0,r3 @ return value
bx lr
.globl _aes_hw_set_decrypt_key
.private_extern _aes_hw_set_decrypt_key
#ifdef __thumb2__
.thumb_func _aes_hw_set_decrypt_key
#endif
.align 5
_aes_hw_set_decrypt_key:
stmdb sp!,{r4,lr}
bl Lenc_key
cmp r0,#0
bne Ldec_key_abort
sub r2,r2,#240 @ restore original r2
mov r4,#-16
add r0,r2,r12,lsl#4 @ end of key schedule
vld1.32 {q0},[r2]
vld1.32 {q1},[r0]
vst1.32 {q0},[r0],r4
vst1.32 {q1},[r2]!
Loop_imc:
vld1.32 {q0},[r2]
vld1.32 {q1},[r0]
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
vst1.32 {q0},[r0],r4
vst1.32 {q1},[r2]!
cmp r0,r2
bhi Loop_imc
vld1.32 {q0},[r2]
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
vst1.32 {q0},[r0]
eor r0,r0,r0 @ return value
Ldec_key_abort:
ldmia sp!,{r4,pc}
.globl _aes_hw_encrypt
.private_extern _aes_hw_encrypt
#ifdef __thumb2__
.thumb_func _aes_hw_encrypt
#endif
.align 5
_aes_hw_encrypt:
ldr r3,[r2,#240]
vld1.32 {q0},[r2]!
vld1.8 {q2},[r0]
sub r3,r3,#2
vld1.32 {q1},[r2]!
Loop_enc:
.byte 0x00,0x43,0xb0,0xf3 @ aese q2,q0
.byte 0x84,0x43,0xb0,0xf3 @ aesmc q2,q2
vld1.32 {q0},[r2]!
subs r3,r3,#2
.byte 0x02,0x43,0xb0,0xf3 @ aese q2,q1
.byte 0x84,0x43,0xb0,0xf3 @ aesmc q2,q2
vld1.32 {q1},[r2]!
bgt Loop_enc
.byte 0x00,0x43,0xb0,0xf3 @ aese q2,q0
.byte 0x84,0x43,0xb0,0xf3 @ aesmc q2,q2
vld1.32 {q0},[r2]
.byte 0x02,0x43,0xb0,0xf3 @ aese q2,q1
veor q2,q2,q0
vst1.8 {q2},[r1]
bx lr
.globl _aes_hw_decrypt
.private_extern _aes_hw_decrypt
#ifdef __thumb2__
.thumb_func _aes_hw_decrypt
#endif
.align 5
_aes_hw_decrypt:
ldr r3,[r2,#240]
vld1.32 {q0},[r2]!
vld1.8 {q2},[r0]
sub r3,r3,#2
vld1.32 {q1},[r2]!
Loop_dec:
.byte 0x40,0x43,0xb0,0xf3 @ aesd q2,q0
.byte 0xc4,0x43,0xb0,0xf3 @ aesimc q2,q2
vld1.32 {q0},[r2]!
subs r3,r3,#2
.byte 0x42,0x43,0xb0,0xf3 @ aesd q2,q1
.byte 0xc4,0x43,0xb0,0xf3 @ aesimc q2,q2
vld1.32 {q1},[r2]!
bgt Loop_dec
.byte 0x40,0x43,0xb0,0xf3 @ aesd q2,q0
.byte 0xc4,0x43,0xb0,0xf3 @ aesimc q2,q2
vld1.32 {q0},[r2]
.byte 0x42,0x43,0xb0,0xf3 @ aesd q2,q1
veor q2,q2,q0
vst1.8 {q2},[r1]
bx lr
.globl _aes_hw_cbc_encrypt
.private_extern _aes_hw_cbc_encrypt
#ifdef __thumb2__
.thumb_func _aes_hw_cbc_encrypt
#endif
.align 5
_aes_hw_cbc_encrypt:
mov ip,sp
stmdb sp!,{r4,r5,r6,r7,r8,lr}
vstmdb sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ ABI specification says so
ldmia ip,{r4,r5} @ load remaining args
subs r2,r2,#16
mov r8,#16
blo Lcbc_abort
moveq r8,#0
cmp r5,#0 @ en- or decrypting?
ldr r5,[r3,#240]
and r2,r2,#-16
vld1.8 {q6},[r4]
vld1.8 {q0},[r0],r8
vld1.32 {q8,q9},[r3] @ load key schedule...
sub r5,r5,#6
add r7,r3,r5,lsl#4 @ pointer to last 7 round keys
sub r5,r5,#2
vld1.32 {q10,q11},[r7]!
vld1.32 {q12,q13},[r7]!
vld1.32 {q14,q15},[r7]!
vld1.32 {q7},[r7]
add r7,r3,#32
mov r6,r5
beq Lcbc_dec
cmp r5,#2
veor q0,q0,q6
veor q5,q8,q7
beq Lcbc_enc128
vld1.32 {q2,q3},[r7]
add r7,r3,#16
add r6,r3,#16*4
add r12,r3,#16*5
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
add r14,r3,#16*6
add r3,r3,#16*7
b Lenter_cbc_enc
.align 4
Loop_cbc_enc:
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vst1.8 {q6},[r1]!
Lenter_cbc_enc:
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x04,0x03,0xb0,0xf3 @ aese q0,q2
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.32 {q8},[r6]
cmp r5,#4
.byte 0x06,0x03,0xb0,0xf3 @ aese q0,q3
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.32 {q9},[r12]
beq Lcbc_enc192
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.32 {q8},[r14]
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.32 {q9},[r3]
nop
Lcbc_enc192:
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
subs r2,r2,#16
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
moveq r8,#0
.byte 0x24,0x03,0xb0,0xf3 @ aese q0,q10
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x26,0x03,0xb0,0xf3 @ aese q0,q11
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.8 {q8},[r0],r8
.byte 0x28,0x03,0xb0,0xf3 @ aese q0,q12
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
veor q8,q8,q5
.byte 0x2a,0x03,0xb0,0xf3 @ aese q0,q13
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.32 {q9},[r7] @ re-pre-load rndkey[1]
.byte 0x2c,0x03,0xb0,0xf3 @ aese q0,q14
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x2e,0x03,0xb0,0xf3 @ aese q0,q15
veor q6,q0,q7
bhs Loop_cbc_enc
vst1.8 {q6},[r1]!
b Lcbc_done
.align 5
Lcbc_enc128:
vld1.32 {q2,q3},[r7]
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
b Lenter_cbc_enc128
Loop_cbc_enc128:
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vst1.8 {q6},[r1]!
Lenter_cbc_enc128:
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
subs r2,r2,#16
.byte 0x04,0x03,0xb0,0xf3 @ aese q0,q2
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
moveq r8,#0
.byte 0x06,0x03,0xb0,0xf3 @ aese q0,q3
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x24,0x03,0xb0,0xf3 @ aese q0,q10
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x26,0x03,0xb0,0xf3 @ aese q0,q11
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
vld1.8 {q8},[r0],r8
.byte 0x28,0x03,0xb0,0xf3 @ aese q0,q12
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x2a,0x03,0xb0,0xf3 @ aese q0,q13
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x2c,0x03,0xb0,0xf3 @ aese q0,q14
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
veor q8,q8,q5
.byte 0x2e,0x03,0xb0,0xf3 @ aese q0,q15
veor q6,q0,q7
bhs Loop_cbc_enc128
vst1.8 {q6},[r1]!
b Lcbc_done
.align 5
Lcbc_dec:
vld1.8 {q10},[r0]!
subs r2,r2,#32 @ bias
add r6,r5,#2
vorr q3,q0,q0
vorr q1,q0,q0
vorr q11,q10,q10
blo Lcbc_dec_tail
vorr q1,q10,q10
vld1.8 {q10},[r0]!
vorr q2,q0,q0
vorr q3,q1,q1
vorr q11,q10,q10
Loop3x_cbc_dec:
.byte 0x60,0x03,0xb0,0xf3 @ aesd q0,q8
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x60,0x23,0xb0,0xf3 @ aesd q1,q8
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x60,0x43,0xf0,0xf3 @ aesd q10,q8
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.32 {q8},[r7]!
subs r6,r6,#2
.byte 0x62,0x03,0xb0,0xf3 @ aesd q0,q9
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x62,0x23,0xb0,0xf3 @ aesd q1,q9
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x62,0x43,0xf0,0xf3 @ aesd q10,q9
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.32 {q9},[r7]!
bgt Loop3x_cbc_dec
.byte 0x60,0x03,0xb0,0xf3 @ aesd q0,q8
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x60,0x23,0xb0,0xf3 @ aesd q1,q8
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x60,0x43,0xf0,0xf3 @ aesd q10,q8
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
veor q4,q6,q7
subs r2,r2,#0x30
veor q5,q2,q7
movlo r6,r2 @ r6, r6, is zero at this point
.byte 0x62,0x03,0xb0,0xf3 @ aesd q0,q9
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x62,0x23,0xb0,0xf3 @ aesd q1,q9
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x62,0x43,0xf0,0xf3 @ aesd q10,q9
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
veor q9,q3,q7
add r0,r0,r6 @ r0 is adjusted in such way that
@ at exit from the loop q1-q10
@ are loaded with last "words"
vorr q6,q11,q11
mov r7,r3
.byte 0x68,0x03,0xb0,0xf3 @ aesd q0,q12
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x68,0x23,0xb0,0xf3 @ aesd q1,q12
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x68,0x43,0xf0,0xf3 @ aesd q10,q12
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.8 {q2},[r0]!
.byte 0x6a,0x03,0xb0,0xf3 @ aesd q0,q13
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x6a,0x23,0xb0,0xf3 @ aesd q1,q13
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x6a,0x43,0xf0,0xf3 @ aesd q10,q13
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.8 {q3},[r0]!
.byte 0x6c,0x03,0xb0,0xf3 @ aesd q0,q14
.byte 0xc0,0x03,0xb0,0xf3 @ aesimc q0,q0
.byte 0x6c,0x23,0xb0,0xf3 @ aesd q1,q14
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x6c,0x43,0xf0,0xf3 @ aesd q10,q14
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.8 {q11},[r0]!
.byte 0x6e,0x03,0xb0,0xf3 @ aesd q0,q15
.byte 0x6e,0x23,0xb0,0xf3 @ aesd q1,q15
.byte 0x6e,0x43,0xf0,0xf3 @ aesd q10,q15
vld1.32 {q8},[r7]! @ re-pre-load rndkey[0]
add r6,r5,#2
veor q4,q4,q0
veor q5,q5,q1
veor q10,q10,q9
vld1.32 {q9},[r7]! @ re-pre-load rndkey[1]
vst1.8 {q4},[r1]!
vorr q0,q2,q2
vst1.8 {q5},[r1]!
vorr q1,q3,q3
vst1.8 {q10},[r1]!
vorr q10,q11,q11
bhs Loop3x_cbc_dec
cmn r2,#0x30
beq Lcbc_done
nop
Lcbc_dec_tail:
.byte 0x60,0x23,0xb0,0xf3 @ aesd q1,q8
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x60,0x43,0xf0,0xf3 @ aesd q10,q8
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.32 {q8},[r7]!
subs r6,r6,#2
.byte 0x62,0x23,0xb0,0xf3 @ aesd q1,q9
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x62,0x43,0xf0,0xf3 @ aesd q10,q9
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
vld1.32 {q9},[r7]!
bgt Lcbc_dec_tail
.byte 0x60,0x23,0xb0,0xf3 @ aesd q1,q8
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x60,0x43,0xf0,0xf3 @ aesd q10,q8
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
.byte 0x62,0x23,0xb0,0xf3 @ aesd q1,q9
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x62,0x43,0xf0,0xf3 @ aesd q10,q9
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
.byte 0x68,0x23,0xb0,0xf3 @ aesd q1,q12
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x68,0x43,0xf0,0xf3 @ aesd q10,q12
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
cmn r2,#0x20
.byte 0x6a,0x23,0xb0,0xf3 @ aesd q1,q13
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x6a,0x43,0xf0,0xf3 @ aesd q10,q13
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
veor q5,q6,q7
.byte 0x6c,0x23,0xb0,0xf3 @ aesd q1,q14
.byte 0xc2,0x23,0xb0,0xf3 @ aesimc q1,q1
.byte 0x6c,0x43,0xf0,0xf3 @ aesd q10,q14
.byte 0xe4,0x43,0xf0,0xf3 @ aesimc q10,q10
veor q9,q3,q7
.byte 0x6e,0x23,0xb0,0xf3 @ aesd q1,q15
.byte 0x6e,0x43,0xf0,0xf3 @ aesd q10,q15
beq Lcbc_dec_one
veor q5,q5,q1
veor q9,q9,q10
vorr q6,q11,q11
vst1.8 {q5},[r1]!
vst1.8 {q9},[r1]!
b Lcbc_done
Lcbc_dec_one:
veor q5,q5,q10
vorr q6,q11,q11
vst1.8 {q5},[r1]!
Lcbc_done:
vst1.8 {q6},[r4]
Lcbc_abort:
vldmia sp!,{d8,d9,d10,d11,d12,d13,d14,d15}
ldmia sp!,{r4,r5,r6,r7,r8,pc}
.globl _aes_hw_ctr32_encrypt_blocks
.private_extern _aes_hw_ctr32_encrypt_blocks
#ifdef __thumb2__
.thumb_func _aes_hw_ctr32_encrypt_blocks
#endif
.align 5
_aes_hw_ctr32_encrypt_blocks:
mov ip,sp
stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,lr}
vstmdb sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ ABI specification says so
ldr r4, [ip] @ load remaining arg
ldr r5,[r3,#240]
ldr r8, [r4, #12]
vld1.32 {q0},[r4]
vld1.32 {q8,q9},[r3] @ load key schedule...
sub r5,r5,#4
mov r12,#16
cmp r2,#2
add r7,r3,r5,lsl#4 @ pointer to last 5 round keys
sub r5,r5,#2
vld1.32 {q12,q13},[r7]!
vld1.32 {q14,q15},[r7]!
vld1.32 {q7},[r7]
add r7,r3,#32
mov r6,r5
movlo r12,#0
#ifndef __ARMEB__
rev r8, r8
#endif
vorr q1,q0,q0
add r10, r8, #1
vorr q10,q0,q0
add r8, r8, #2
vorr q6,q0,q0
rev r10, r10
vmov.32 d3[1],r10
bls Lctr32_tail
rev r12, r8
sub r2,r2,#3 @ bias
vmov.32 d21[1],r12
b Loop3x_ctr32
.align 4
Loop3x_ctr32:
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x20,0x23,0xb0,0xf3 @ aese q1,q8
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
.byte 0x20,0x43,0xf0,0xf3 @ aese q10,q8
.byte 0xa4,0x43,0xf0,0xf3 @ aesmc q10,q10
vld1.32 {q8},[r7]!
subs r6,r6,#2
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x22,0x23,0xb0,0xf3 @ aese q1,q9
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
.byte 0x22,0x43,0xf0,0xf3 @ aese q10,q9
.byte 0xa4,0x43,0xf0,0xf3 @ aesmc q10,q10
vld1.32 {q9},[r7]!
bgt Loop3x_ctr32
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x83,0xb0,0xf3 @ aesmc q4,q0
.byte 0x20,0x23,0xb0,0xf3 @ aese q1,q8
.byte 0x82,0xa3,0xb0,0xf3 @ aesmc q5,q1
vld1.8 {q2},[r0]!
vorr q0,q6,q6
.byte 0x20,0x43,0xf0,0xf3 @ aese q10,q8
.byte 0xa4,0x43,0xf0,0xf3 @ aesmc q10,q10
vld1.8 {q3},[r0]!
vorr q1,q6,q6
.byte 0x22,0x83,0xb0,0xf3 @ aese q4,q9
.byte 0x88,0x83,0xb0,0xf3 @ aesmc q4,q4
.byte 0x22,0xa3,0xb0,0xf3 @ aese q5,q9
.byte 0x8a,0xa3,0xb0,0xf3 @ aesmc q5,q5
vld1.8 {q11},[r0]!
mov r7,r3
.byte 0x22,0x43,0xf0,0xf3 @ aese q10,q9
.byte 0xa4,0x23,0xf0,0xf3 @ aesmc q9,q10
vorr q10,q6,q6
add r9,r8,#1
.byte 0x28,0x83,0xb0,0xf3 @ aese q4,q12
.byte 0x88,0x83,0xb0,0xf3 @ aesmc q4,q4
.byte 0x28,0xa3,0xb0,0xf3 @ aese q5,q12
.byte 0x8a,0xa3,0xb0,0xf3 @ aesmc q5,q5
veor q2,q2,q7
add r10,r8,#2
.byte 0x28,0x23,0xf0,0xf3 @ aese q9,q12
.byte 0xa2,0x23,0xf0,0xf3 @ aesmc q9,q9
veor q3,q3,q7
add r8,r8,#3
.byte 0x2a,0x83,0xb0,0xf3 @ aese q4,q13
.byte 0x88,0x83,0xb0,0xf3 @ aesmc q4,q4
.byte 0x2a,0xa3,0xb0,0xf3 @ aese q5,q13
.byte 0x8a,0xa3,0xb0,0xf3 @ aesmc q5,q5
veor q11,q11,q7
rev r9,r9
.byte 0x2a,0x23,0xf0,0xf3 @ aese q9,q13
.byte 0xa2,0x23,0xf0,0xf3 @ aesmc q9,q9
vmov.32 d1[1], r9
rev r10,r10
.byte 0x2c,0x83,0xb0,0xf3 @ aese q4,q14
.byte 0x88,0x83,0xb0,0xf3 @ aesmc q4,q4
.byte 0x2c,0xa3,0xb0,0xf3 @ aese q5,q14
.byte 0x8a,0xa3,0xb0,0xf3 @ aesmc q5,q5
vmov.32 d3[1], r10
rev r12,r8
.byte 0x2c,0x23,0xf0,0xf3 @ aese q9,q14
.byte 0xa2,0x23,0xf0,0xf3 @ aesmc q9,q9
vmov.32 d21[1], r12
subs r2,r2,#3
.byte 0x2e,0x83,0xb0,0xf3 @ aese q4,q15
.byte 0x2e,0xa3,0xb0,0xf3 @ aese q5,q15
.byte 0x2e,0x23,0xf0,0xf3 @ aese q9,q15
veor q2,q2,q4
vld1.32 {q8},[r7]! @ re-pre-load rndkey[0]
vst1.8 {q2},[r1]!
veor q3,q3,q5
mov r6,r5
vst1.8 {q3},[r1]!
veor q11,q11,q9
vld1.32 {q9},[r7]! @ re-pre-load rndkey[1]
vst1.8 {q11},[r1]!
bhs Loop3x_ctr32
adds r2,r2,#3
beq Lctr32_done
cmp r2,#1
mov r12,#16
moveq r12,#0
Lctr32_tail:
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x20,0x23,0xb0,0xf3 @ aese q1,q8
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
vld1.32 {q8},[r7]!
subs r6,r6,#2
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x22,0x23,0xb0,0xf3 @ aese q1,q9
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
vld1.32 {q9},[r7]!
bgt Lctr32_tail
.byte 0x20,0x03,0xb0,0xf3 @ aese q0,q8
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x20,0x23,0xb0,0xf3 @ aese q1,q8
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
.byte 0x22,0x03,0xb0,0xf3 @ aese q0,q9
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x22,0x23,0xb0,0xf3 @ aese q1,q9
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
vld1.8 {q2},[r0],r12
.byte 0x28,0x03,0xb0,0xf3 @ aese q0,q12
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x28,0x23,0xb0,0xf3 @ aese q1,q12
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
vld1.8 {q3},[r0]
.byte 0x2a,0x03,0xb0,0xf3 @ aese q0,q13
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x2a,0x23,0xb0,0xf3 @ aese q1,q13
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
veor q2,q2,q7
.byte 0x2c,0x03,0xb0,0xf3 @ aese q0,q14
.byte 0x80,0x03,0xb0,0xf3 @ aesmc q0,q0
.byte 0x2c,0x23,0xb0,0xf3 @ aese q1,q14
.byte 0x82,0x23,0xb0,0xf3 @ aesmc q1,q1
veor q3,q3,q7
.byte 0x2e,0x03,0xb0,0xf3 @ aese q0,q15
.byte 0x2e,0x23,0xb0,0xf3 @ aese q1,q15
cmp r2,#1
veor q2,q2,q0
veor q3,q3,q1
vst1.8 {q2},[r1]!
beq Lctr32_done
vst1.8 {q3},[r1]
Lctr32_done:
vldmia sp!,{d8,d9,d10,d11,d12,d13,d14,d15}
ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,pc}
#endif
#endif // !OPENSSL_NO_ASM

982
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/armv4-mont.S
View File

@ -1,982 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
@ Silence ARMv8 deprecated IT instruction warnings. This file is used by both
@ ARMv7 and ARMv8 processors and does not use ARMv8 instructions.
.text
#if defined(__thumb2__)
.syntax unified
.thumb
#else
.code 32
#endif
#if __ARM_MAX_ARCH__>=7
.align 5
LOPENSSL_armcap:
.word OPENSSL_armcap_P-Lbn_mul_mont
#endif
.globl _bn_mul_mont
.private_extern _bn_mul_mont
#ifdef __thumb2__
.thumb_func _bn_mul_mont
#endif
.align 5
_bn_mul_mont:
Lbn_mul_mont:
ldr ip,[sp,#4] @ load num
stmdb sp!,{r0,r2} @ sp points at argument block
#if __ARM_MAX_ARCH__>=7
tst ip,#7
bne Lialu
adr r0,Lbn_mul_mont
ldr r2,LOPENSSL_armcap
ldr r0,[r0,r2]
#ifdef __APPLE__
ldr r0,[r0]
#endif
tst r0,#ARMV7_NEON @ NEON available?
ldmia sp, {r0,r2}
beq Lialu
add sp,sp,#8
b bn_mul8x_mont_neon
.align 4
Lialu:
#endif
cmp ip,#2
mov r0,ip @ load num
#ifdef __thumb2__
ittt lt
#endif
movlt r0,#0
addlt sp,sp,#2*4
blt Labrt
stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr} @ save 10 registers
mov r0,r0,lsl#2 @ rescale r0 for byte count
sub sp,sp,r0 @ alloca(4*num)
sub sp,sp,#4 @ +extra dword
sub r0,r0,#4 @ "num=num-1"
add r4,r2,r0 @ &bp[num-1]
add r0,sp,r0 @ r0 to point at &tp[num-1]
ldr r8,[r0,#14*4] @ &n0
ldr r2,[r2] @ bp[0]
ldr r5,[r1],#4 @ ap[0],ap++
ldr r6,[r3],#4 @ np[0],np++
ldr r8,[r8] @ *n0
str r4,[r0,#15*4] @ save &bp[num]
umull r10,r11,r5,r2 @ ap[0]*bp[0]
str r8,[r0,#14*4] @ save n0 value
mul r8,r10,r8 @ "tp[0]"*n0
mov r12,#0
umlal r10,r12,r6,r8 @ np[0]*n0+"t[0]"
mov r4,sp
L1st:
ldr r5,[r1],#4 @ ap[j],ap++
mov r10,r11
ldr r6,[r3],#4 @ np[j],np++
mov r11,#0
umlal r10,r11,r5,r2 @ ap[j]*bp[0]
mov r14,#0
umlal r12,r14,r6,r8 @ np[j]*n0
adds r12,r12,r10
str r12,[r4],#4 @ tp[j-1]=,tp++
adc r12,r14,#0
cmp r4,r0
bne L1st
adds r12,r12,r11
ldr r4,[r0,#13*4] @ restore bp
mov r14,#0
ldr r8,[r0,#14*4] @ restore n0
adc r14,r14,#0
str r12,[r0] @ tp[num-1]=
mov r7,sp
str r14,[r0,#4] @ tp[num]=
Louter:
sub r7,r0,r7 @ "original" r0-1 value
sub r1,r1,r7 @ "rewind" ap to &ap[1]
ldr r2,[r4,#4]! @ *(++bp)
sub r3,r3,r7 @ "rewind" np to &np[1]
ldr r5,[r1,#-4] @ ap[0]
ldr r10,[sp] @ tp[0]
ldr r6,[r3,#-4] @ np[0]
ldr r7,[sp,#4] @ tp[1]
mov r11,#0
umlal r10,r11,r5,r2 @ ap[0]*bp[i]+tp[0]
str r4,[r0,#13*4] @ save bp
mul r8,r10,r8
mov r12,#0
umlal r10,r12,r6,r8 @ np[0]*n0+"tp[0]"
mov r4,sp
Linner:
ldr r5,[r1],#4 @ ap[j],ap++
adds r10,r11,r7 @ +=tp[j]
ldr r6,[r3],#4 @ np[j],np++
mov r11,#0
umlal r10,r11,r5,r2 @ ap[j]*bp[i]
mov r14,#0
umlal r12,r14,r6,r8 @ np[j]*n0
adc r11,r11,#0
ldr r7,[r4,#8] @ tp[j+1]
adds r12,r12,r10
str r12,[r4],#4 @ tp[j-1]=,tp++
adc r12,r14,#0
cmp r4,r0
bne Linner
adds r12,r12,r11
mov r14,#0
ldr r4,[r0,#13*4] @ restore bp
adc r14,r14,#0
ldr r8,[r0,#14*4] @ restore n0
adds r12,r12,r7
ldr r7,[r0,#15*4] @ restore &bp[num]
adc r14,r14,#0
str r12,[r0] @ tp[num-1]=
str r14,[r0,#4] @ tp[num]=
cmp r4,r7
#ifdef __thumb2__
itt ne
#endif
movne r7,sp
bne Louter
ldr r2,[r0,#12*4] @ pull rp
mov r5,sp
add r0,r0,#4 @ r0 to point at &tp[num]
sub r5,r0,r5 @ "original" num value
mov r4,sp @ "rewind" r4
mov r1,r4 @ "borrow" r1
sub r3,r3,r5 @ "rewind" r3 to &np[0]
subs r7,r7,r7 @ "clear" carry flag
Lsub: ldr r7,[r4],#4
ldr r6,[r3],#4
sbcs r7,r7,r6 @ tp[j]-np[j]
str r7,[r2],#4 @ rp[j]=
teq r4,r0 @ preserve carry
bne Lsub
sbcs r14,r14,#0 @ upmost carry
mov r4,sp @ "rewind" r4
sub r2,r2,r5 @ "rewind" r2
Lcopy: ldr r7,[r4] @ conditional copy
ldr r5,[r2]
str sp,[r4],#4 @ zap tp
#ifdef __thumb2__
it cc
#endif
movcc r5,r7
str r5,[r2],#4
teq r4,r0 @ preserve carry
bne Lcopy
mov sp,r0
add sp,sp,#4 @ skip over tp[num+1]
ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr} @ restore registers
add sp,sp,#2*4 @ skip over {r0,r2}
mov r0,#1
Labrt:
#if __ARM_ARCH__>=5
bx lr @ bx lr
#else
tst lr,#1
moveq pc,lr @ be binary compatible with V4, yet
.word 0xe12fff1e @ interoperable with Thumb ISA:-)
#endif
#if __ARM_MAX_ARCH__>=7
#ifdef __thumb2__
.thumb_func bn_mul8x_mont_neon
#endif
.align 5
bn_mul8x_mont_neon:
mov ip,sp
stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11}
vstmdb sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ ABI specification says so
ldmia ip,{r4,r5} @ load rest of parameter block
mov ip,sp
cmp r5,#8
bhi LNEON_8n
@ special case for r5==8, everything is in register bank...
vld1.32 {d28[0]}, [r2,:32]!
veor d8,d8,d8
sub r7,sp,r5,lsl#4
vld1.32 {d0,d1,d2,d3}, [r1]! @ can't specify :32 :-(
and r7,r7,#-64
vld1.32 {d30[0]}, [r4,:32]
mov sp,r7 @ alloca
vzip.16 d28,d8
vmull.u32 q6,d28,d0[0]
vmull.u32 q7,d28,d0[1]
vmull.u32 q8,d28,d1[0]
vshl.i64 d29,d13,#16
vmull.u32 q9,d28,d1[1]
vadd.u64 d29,d29,d12
veor d8,d8,d8
vmul.u32 d29,d29,d30
vmull.u32 q10,d28,d2[0]
vld1.32 {d4,d5,d6,d7}, [r3]!
vmull.u32 q11,d28,d2[1]
vmull.u32 q12,d28,d3[0]
vzip.16 d29,d8
vmull.u32 q13,d28,d3[1]
vmlal.u32 q6,d29,d4[0]
sub r9,r5,#1
vmlal.u32 q7,d29,d4[1]
vmlal.u32 q8,d29,d5[0]
vmlal.u32 q9,d29,d5[1]
vmlal.u32 q10,d29,d6[0]
vmov q5,q6
vmlal.u32 q11,d29,d6[1]
vmov q6,q7
vmlal.u32 q12,d29,d7[0]
vmov q7,q8
vmlal.u32 q13,d29,d7[1]
vmov q8,q9
vmov q9,q10
vshr.u64 d10,d10,#16
vmov q10,q11
vmov q11,q12
vadd.u64 d10,d10,d11
vmov q12,q13
veor q13,q13
vshr.u64 d10,d10,#16
b LNEON_outer8
.align 4
LNEON_outer8:
vld1.32 {d28[0]}, [r2,:32]!
veor d8,d8,d8
vzip.16 d28,d8
vadd.u64 d12,d12,d10
vmlal.u32 q6,d28,d0[0]
vmlal.u32 q7,d28,d0[1]
vmlal.u32 q8,d28,d1[0]
vshl.i64 d29,d13,#16
vmlal.u32 q9,d28,d1[1]
vadd.u64 d29,d29,d12
veor d8,d8,d8
subs r9,r9,#1
vmul.u32 d29,d29,d30
vmlal.u32 q10,d28,d2[0]
vmlal.u32 q11,d28,d2[1]
vmlal.u32 q12,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q13,d28,d3[1]
vmlal.u32 q6,d29,d4[0]
vmlal.u32 q7,d29,d4[1]
vmlal.u32 q8,d29,d5[0]
vmlal.u32 q9,d29,d5[1]
vmlal.u32 q10,d29,d6[0]
vmov q5,q6
vmlal.u32 q11,d29,d6[1]
vmov q6,q7
vmlal.u32 q12,d29,d7[0]
vmov q7,q8
vmlal.u32 q13,d29,d7[1]
vmov q8,q9
vmov q9,q10
vshr.u64 d10,d10,#16
vmov q10,q11
vmov q11,q12
vadd.u64 d10,d10,d11
vmov q12,q13
veor q13,q13
vshr.u64 d10,d10,#16
bne LNEON_outer8
vadd.u64 d12,d12,d10
mov r7,sp
vshr.u64 d10,d12,#16
mov r8,r5
vadd.u64 d13,d13,d10
add r6,sp,#96
vshr.u64 d10,d13,#16
vzip.16 d12,d13
b LNEON_tail_entry
.align 4
LNEON_8n:
veor q6,q6,q6
sub r7,sp,#128
veor q7,q7,q7
sub r7,r7,r5,lsl#4
veor q8,q8,q8
and r7,r7,#-64
veor q9,q9,q9
mov sp,r7 @ alloca
veor q10,q10,q10
add r7,r7,#256
veor q11,q11,q11
sub r8,r5,#8
veor q12,q12,q12
veor q13,q13,q13
LNEON_8n_init:
vst1.64 {q6,q7},[r7,:256]!
subs r8,r8,#8
vst1.64 {q8,q9},[r7,:256]!
vst1.64 {q10,q11},[r7,:256]!
vst1.64 {q12,q13},[r7,:256]!
bne LNEON_8n_init
add r6,sp,#256
vld1.32 {d0,d1,d2,d3},[r1]!
add r10,sp,#8
vld1.32 {d30[0]},[r4,:32]
mov r9,r5
b LNEON_8n_outer
.align 4
LNEON_8n_outer:
vld1.32 {d28[0]},[r2,:32]! @ *b++
veor d8,d8,d8
vzip.16 d28,d8
add r7,sp,#128
vld1.32 {d4,d5,d6,d7},[r3]!
vmlal.u32 q6,d28,d0[0]
vmlal.u32 q7,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q8,d28,d1[0]
vshl.i64 d29,d13,#16
vmlal.u32 q9,d28,d1[1]
vadd.u64 d29,d29,d12
vmlal.u32 q10,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q11,d28,d2[1]
vst1.32 {d28},[sp,:64] @ put aside smashed b[8*i+0]
vmlal.u32 q12,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q13,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q6,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q7,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q8,d29,d5[0]
vshr.u64 d12,d12,#16
vmlal.u32 q9,d29,d5[1]
vmlal.u32 q10,d29,d6[0]
vadd.u64 d12,d12,d13
vmlal.u32 q11,d29,d6[1]
vshr.u64 d12,d12,#16
vmlal.u32 q12,d29,d7[0]
vmlal.u32 q13,d29,d7[1]
vadd.u64 d14,d14,d12
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+0]
vmlal.u32 q7,d28,d0[0]
vld1.64 {q6},[r6,:128]!
vmlal.u32 q8,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q9,d28,d1[0]
vshl.i64 d29,d15,#16
vmlal.u32 q10,d28,d1[1]
vadd.u64 d29,d29,d14
vmlal.u32 q11,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q12,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+1]
vmlal.u32 q13,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q6,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q7,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q8,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q9,d29,d5[0]
vshr.u64 d14,d14,#16
vmlal.u32 q10,d29,d5[1]
vmlal.u32 q11,d29,d6[0]
vadd.u64 d14,d14,d15
vmlal.u32 q12,d29,d6[1]
vshr.u64 d14,d14,#16
vmlal.u32 q13,d29,d7[0]
vmlal.u32 q6,d29,d7[1]
vadd.u64 d16,d16,d14
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+1]
vmlal.u32 q8,d28,d0[0]
vld1.64 {q7},[r6,:128]!
vmlal.u32 q9,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q10,d28,d1[0]
vshl.i64 d29,d17,#16
vmlal.u32 q11,d28,d1[1]
vadd.u64 d29,d29,d16
vmlal.u32 q12,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q13,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+2]
vmlal.u32 q6,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q7,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q8,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q9,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q10,d29,d5[0]
vshr.u64 d16,d16,#16
vmlal.u32 q11,d29,d5[1]
vmlal.u32 q12,d29,d6[0]
vadd.u64 d16,d16,d17
vmlal.u32 q13,d29,d6[1]
vshr.u64 d16,d16,#16
vmlal.u32 q6,d29,d7[0]
vmlal.u32 q7,d29,d7[1]
vadd.u64 d18,d18,d16
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+2]
vmlal.u32 q9,d28,d0[0]
vld1.64 {q8},[r6,:128]!
vmlal.u32 q10,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q11,d28,d1[0]
vshl.i64 d29,d19,#16
vmlal.u32 q12,d28,d1[1]
vadd.u64 d29,d29,d18
vmlal.u32 q13,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q6,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+3]
vmlal.u32 q7,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q8,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q9,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q10,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q11,d29,d5[0]
vshr.u64 d18,d18,#16
vmlal.u32 q12,d29,d5[1]
vmlal.u32 q13,d29,d6[0]
vadd.u64 d18,d18,d19
vmlal.u32 q6,d29,d6[1]
vshr.u64 d18,d18,#16
vmlal.u32 q7,d29,d7[0]
vmlal.u32 q8,d29,d7[1]
vadd.u64 d20,d20,d18
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+3]
vmlal.u32 q10,d28,d0[0]
vld1.64 {q9},[r6,:128]!
vmlal.u32 q11,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q12,d28,d1[0]
vshl.i64 d29,d21,#16
vmlal.u32 q13,d28,d1[1]
vadd.u64 d29,d29,d20
vmlal.u32 q6,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q7,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+4]
vmlal.u32 q8,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q9,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q10,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q11,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q12,d29,d5[0]
vshr.u64 d20,d20,#16
vmlal.u32 q13,d29,d5[1]
vmlal.u32 q6,d29,d6[0]
vadd.u64 d20,d20,d21
vmlal.u32 q7,d29,d6[1]
vshr.u64 d20,d20,#16
vmlal.u32 q8,d29,d7[0]
vmlal.u32 q9,d29,d7[1]
vadd.u64 d22,d22,d20
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+4]
vmlal.u32 q11,d28,d0[0]
vld1.64 {q10},[r6,:128]!
vmlal.u32 q12,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q13,d28,d1[0]
vshl.i64 d29,d23,#16
vmlal.u32 q6,d28,d1[1]
vadd.u64 d29,d29,d22
vmlal.u32 q7,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q8,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+5]
vmlal.u32 q9,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q10,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q11,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q12,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q13,d29,d5[0]
vshr.u64 d22,d22,#16
vmlal.u32 q6,d29,d5[1]
vmlal.u32 q7,d29,d6[0]
vadd.u64 d22,d22,d23
vmlal.u32 q8,d29,d6[1]
vshr.u64 d22,d22,#16
vmlal.u32 q9,d29,d7[0]
vmlal.u32 q10,d29,d7[1]
vadd.u64 d24,d24,d22
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+5]
vmlal.u32 q12,d28,d0[0]
vld1.64 {q11},[r6,:128]!
vmlal.u32 q13,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q6,d28,d1[0]
vshl.i64 d29,d25,#16
vmlal.u32 q7,d28,d1[1]
vadd.u64 d29,d29,d24
vmlal.u32 q8,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q9,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+6]
vmlal.u32 q10,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q11,d28,d3[1]
vld1.32 {d28[0]},[r2,:32]! @ *b++
vmlal.u32 q12,d29,d4[0]
veor d10,d10,d10
vmlal.u32 q13,d29,d4[1]
vzip.16 d28,d10
vmlal.u32 q6,d29,d5[0]
vshr.u64 d24,d24,#16
vmlal.u32 q7,d29,d5[1]
vmlal.u32 q8,d29,d6[0]
vadd.u64 d24,d24,d25
vmlal.u32 q9,d29,d6[1]
vshr.u64 d24,d24,#16
vmlal.u32 q10,d29,d7[0]
vmlal.u32 q11,d29,d7[1]
vadd.u64 d26,d26,d24
vst1.32 {d29},[r10,:64]! @ put aside smashed m[8*i+6]
vmlal.u32 q13,d28,d0[0]
vld1.64 {q12},[r6,:128]!
vmlal.u32 q6,d28,d0[1]
veor d8,d8,d8
vmlal.u32 q7,d28,d1[0]
vshl.i64 d29,d27,#16
vmlal.u32 q8,d28,d1[1]
vadd.u64 d29,d29,d26
vmlal.u32 q9,d28,d2[0]
vmul.u32 d29,d29,d30
vmlal.u32 q10,d28,d2[1]
vst1.32 {d28},[r10,:64]! @ put aside smashed b[8*i+7]
vmlal.u32 q11,d28,d3[0]
vzip.16 d29,d8
vmlal.u32 q12,d28,d3[1]
vld1.32 {d28},[sp,:64] @ pull smashed b[8*i+0]
vmlal.u32 q13,d29,d4[0]
vld1.32 {d0,d1,d2,d3},[r1]!
vmlal.u32 q6,d29,d4[1]
vmlal.u32 q7,d29,d5[0]
vshr.u64 d26,d26,#16
vmlal.u32 q8,d29,d5[1]
vmlal.u32 q9,d29,d6[0]
vadd.u64 d26,d26,d27
vmlal.u32 q10,d29,d6[1]
vshr.u64 d26,d26,#16
vmlal.u32 q11,d29,d7[0]
vmlal.u32 q12,d29,d7[1]
vadd.u64 d12,d12,d26
vst1.32 {d29},[r10,:64] @ put aside smashed m[8*i+7]
add r10,sp,#8 @ rewind
sub r8,r5,#8
b LNEON_8n_inner
.align 4
LNEON_8n_inner:
subs r8,r8,#8
vmlal.u32 q6,d28,d0[0]
vld1.64 {q13},[r6,:128]
vmlal.u32 q7,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+0]
vmlal.u32 q8,d28,d1[0]
vld1.32 {d4,d5,d6,d7},[r3]!
vmlal.u32 q9,d28,d1[1]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q10,d28,d2[0]
vmlal.u32 q11,d28,d2[1]
vmlal.u32 q12,d28,d3[0]
vmlal.u32 q13,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+1]
vmlal.u32 q6,d29,d4[0]
vmlal.u32 q7,d29,d4[1]
vmlal.u32 q8,d29,d5[0]
vmlal.u32 q9,d29,d5[1]
vmlal.u32 q10,d29,d6[0]
vmlal.u32 q11,d29,d6[1]
vmlal.u32 q12,d29,d7[0]
vmlal.u32 q13,d29,d7[1]
vst1.64 {q6},[r7,:128]!
vmlal.u32 q7,d28,d0[0]
vld1.64 {q6},[r6,:128]
vmlal.u32 q8,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+1]
vmlal.u32 q9,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q10,d28,d1[1]
vmlal.u32 q11,d28,d2[0]
vmlal.u32 q12,d28,d2[1]
vmlal.u32 q13,d28,d3[0]
vmlal.u32 q6,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+2]
vmlal.u32 q7,d29,d4[0]
vmlal.u32 q8,d29,d4[1]
vmlal.u32 q9,d29,d5[0]
vmlal.u32 q10,d29,d5[1]
vmlal.u32 q11,d29,d6[0]
vmlal.u32 q12,d29,d6[1]
vmlal.u32 q13,d29,d7[0]
vmlal.u32 q6,d29,d7[1]
vst1.64 {q7},[r7,:128]!
vmlal.u32 q8,d28,d0[0]
vld1.64 {q7},[r6,:128]
vmlal.u32 q9,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+2]
vmlal.u32 q10,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q11,d28,d1[1]
vmlal.u32 q12,d28,d2[0]
vmlal.u32 q13,d28,d2[1]
vmlal.u32 q6,d28,d3[0]
vmlal.u32 q7,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+3]
vmlal.u32 q8,d29,d4[0]
vmlal.u32 q9,d29,d4[1]
vmlal.u32 q10,d29,d5[0]
vmlal.u32 q11,d29,d5[1]
vmlal.u32 q12,d29,d6[0]
vmlal.u32 q13,d29,d6[1]
vmlal.u32 q6,d29,d7[0]
vmlal.u32 q7,d29,d7[1]
vst1.64 {q8},[r7,:128]!
vmlal.u32 q9,d28,d0[0]
vld1.64 {q8},[r6,:128]
vmlal.u32 q10,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+3]
vmlal.u32 q11,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q12,d28,d1[1]
vmlal.u32 q13,d28,d2[0]
vmlal.u32 q6,d28,d2[1]
vmlal.u32 q7,d28,d3[0]
vmlal.u32 q8,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+4]
vmlal.u32 q9,d29,d4[0]
vmlal.u32 q10,d29,d4[1]
vmlal.u32 q11,d29,d5[0]
vmlal.u32 q12,d29,d5[1]
vmlal.u32 q13,d29,d6[0]
vmlal.u32 q6,d29,d6[1]
vmlal.u32 q7,d29,d7[0]
vmlal.u32 q8,d29,d7[1]
vst1.64 {q9},[r7,:128]!
vmlal.u32 q10,d28,d0[0]
vld1.64 {q9},[r6,:128]
vmlal.u32 q11,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+4]
vmlal.u32 q12,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q13,d28,d1[1]
vmlal.u32 q6,d28,d2[0]
vmlal.u32 q7,d28,d2[1]
vmlal.u32 q8,d28,d3[0]
vmlal.u32 q9,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+5]
vmlal.u32 q10,d29,d4[0]
vmlal.u32 q11,d29,d4[1]
vmlal.u32 q12,d29,d5[0]
vmlal.u32 q13,d29,d5[1]
vmlal.u32 q6,d29,d6[0]
vmlal.u32 q7,d29,d6[1]
vmlal.u32 q8,d29,d7[0]
vmlal.u32 q9,d29,d7[1]
vst1.64 {q10},[r7,:128]!
vmlal.u32 q11,d28,d0[0]
vld1.64 {q10},[r6,:128]
vmlal.u32 q12,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+5]
vmlal.u32 q13,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q6,d28,d1[1]
vmlal.u32 q7,d28,d2[0]
vmlal.u32 q8,d28,d2[1]
vmlal.u32 q9,d28,d3[0]
vmlal.u32 q10,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+6]
vmlal.u32 q11,d29,d4[0]
vmlal.u32 q12,d29,d4[1]
vmlal.u32 q13,d29,d5[0]
vmlal.u32 q6,d29,d5[1]
vmlal.u32 q7,d29,d6[0]
vmlal.u32 q8,d29,d6[1]
vmlal.u32 q9,d29,d7[0]
vmlal.u32 q10,d29,d7[1]
vst1.64 {q11},[r7,:128]!
vmlal.u32 q12,d28,d0[0]
vld1.64 {q11},[r6,:128]
vmlal.u32 q13,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+6]
vmlal.u32 q6,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q7,d28,d1[1]
vmlal.u32 q8,d28,d2[0]
vmlal.u32 q9,d28,d2[1]
vmlal.u32 q10,d28,d3[0]
vmlal.u32 q11,d28,d3[1]
vld1.32 {d28},[r10,:64]! @ pull smashed b[8*i+7]
vmlal.u32 q12,d29,d4[0]
vmlal.u32 q13,d29,d4[1]
vmlal.u32 q6,d29,d5[0]
vmlal.u32 q7,d29,d5[1]
vmlal.u32 q8,d29,d6[0]
vmlal.u32 q9,d29,d6[1]
vmlal.u32 q10,d29,d7[0]
vmlal.u32 q11,d29,d7[1]
vst1.64 {q12},[r7,:128]!
vmlal.u32 q13,d28,d0[0]
vld1.64 {q12},[r6,:128]
vmlal.u32 q6,d28,d0[1]
vld1.32 {d29},[r10,:64]! @ pull smashed m[8*i+7]
vmlal.u32 q7,d28,d1[0]
it ne
addne r6,r6,#16 @ don't advance in last iteration
vmlal.u32 q8,d28,d1[1]
vmlal.u32 q9,d28,d2[0]
vmlal.u32 q10,d28,d2[1]
vmlal.u32 q11,d28,d3[0]
vmlal.u32 q12,d28,d3[1]
it eq
subeq r1,r1,r5,lsl#2 @ rewind
vmlal.u32 q13,d29,d4[0]
vld1.32 {d28},[sp,:64] @ pull smashed b[8*i+0]
vmlal.u32 q6,d29,d4[1]
vld1.32 {d0,d1,d2,d3},[r1]!
vmlal.u32 q7,d29,d5[0]
add r10,sp,#8 @ rewind
vmlal.u32 q8,d29,d5[1]
vmlal.u32 q9,d29,d6[0]
vmlal.u32 q10,d29,d6[1]
vmlal.u32 q11,d29,d7[0]
vst1.64 {q13},[r7,:128]!
vmlal.u32 q12,d29,d7[1]
bne LNEON_8n_inner
add r6,sp,#128
vst1.64 {q6,q7},[r7,:256]!
veor q2,q2,q2 @ d4-d5
vst1.64 {q8,q9},[r7,:256]!
veor q3,q3,q3 @ d6-d7
vst1.64 {q10,q11},[r7,:256]!
vst1.64 {q12},[r7,:128]
subs r9,r9,#8
vld1.64 {q6,q7},[r6,:256]!
vld1.64 {q8,q9},[r6,:256]!
vld1.64 {q10,q11},[r6,:256]!
vld1.64 {q12,q13},[r6,:256]!
itt ne
subne r3,r3,r5,lsl#2 @ rewind
bne LNEON_8n_outer
add r7,sp,#128
vst1.64 {q2,q3}, [sp,:256]! @ start wiping stack frame
vshr.u64 d10,d12,#16
vst1.64 {q2,q3},[sp,:256]!
vadd.u64 d13,d13,d10
vst1.64 {q2,q3}, [sp,:256]!
vshr.u64 d10,d13,#16
vst1.64 {q2,q3}, [sp,:256]!
vzip.16 d12,d13
mov r8,r5
b LNEON_tail_entry
.align 4
LNEON_tail:
vadd.u64 d12,d12,d10
vshr.u64 d10,d12,#16
vld1.64 {q8,q9}, [r6, :256]!
vadd.u64 d13,d13,d10
vld1.64 {q10,q11}, [r6, :256]!
vshr.u64 d10,d13,#16
vld1.64 {q12,q13}, [r6, :256]!
vzip.16 d12,d13
LNEON_tail_entry:
vadd.u64 d14,d14,d10
vst1.32 {d12[0]}, [r7, :32]!
vshr.u64 d10,d14,#16
vadd.u64 d15,d15,d10
vshr.u64 d10,d15,#16
vzip.16 d14,d15
vadd.u64 d16,d16,d10
vst1.32 {d14[0]}, [r7, :32]!
vshr.u64 d10,d16,#16
vadd.u64 d17,d17,d10
vshr.u64 d10,d17,#16
vzip.16 d16,d17
vadd.u64 d18,d18,d10
vst1.32 {d16[0]}, [r7, :32]!
vshr.u64 d10,d18,#16
vadd.u64 d19,d19,d10
vshr.u64 d10,d19,#16
vzip.16 d18,d19
vadd.u64 d20,d20,d10
vst1.32 {d18[0]}, [r7, :32]!
vshr.u64 d10,d20,#16
vadd.u64 d21,d21,d10
vshr.u64 d10,d21,#16
vzip.16 d20,d21
vadd.u64 d22,d22,d10
vst1.32 {d20[0]}, [r7, :32]!
vshr.u64 d10,d22,#16
vadd.u64 d23,d23,d10
vshr.u64 d10,d23,#16
vzip.16 d22,d23
vadd.u64 d24,d24,d10
vst1.32 {d22[0]}, [r7, :32]!
vshr.u64 d10,d24,#16
vadd.u64 d25,d25,d10
vshr.u64 d10,d25,#16
vzip.16 d24,d25
vadd.u64 d26,d26,d10
vst1.32 {d24[0]}, [r7, :32]!
vshr.u64 d10,d26,#16
vadd.u64 d27,d27,d10
vshr.u64 d10,d27,#16
vzip.16 d26,d27
vld1.64 {q6,q7}, [r6, :256]!
subs r8,r8,#8
vst1.32 {d26[0]}, [r7, :32]!
bne LNEON_tail
vst1.32 {d10[0]}, [r7, :32] @ top-most bit
sub r3,r3,r5,lsl#2 @ rewind r3
subs r1,sp,#0 @ clear carry flag
add r2,sp,r5,lsl#2
LNEON_sub:
ldmia r1!, {r4,r5,r6,r7}
ldmia r3!, {r8,r9,r10,r11}
sbcs r8, r4,r8
sbcs r9, r5,r9
sbcs r10,r6,r10
sbcs r11,r7,r11
teq r1,r2 @ preserves carry
stmia r0!, {r8,r9,r10,r11}
bne LNEON_sub
ldr r10, [r1] @ load top-most bit
mov r11,sp
veor q0,q0,q0
sub r11,r2,r11 @ this is num*4
veor q1,q1,q1
mov r1,sp
sub r0,r0,r11 @ rewind r0
mov r3,r2 @ second 3/4th of frame
sbcs r10,r10,#0 @ result is carry flag
LNEON_copy_n_zap:
ldmia r1!, {r4,r5,r6,r7}
ldmia r0, {r8,r9,r10,r11}
it cc
movcc r8, r4
vst1.64 {q0,q1}, [r3,:256]! @ wipe
itt cc
movcc r9, r5
movcc r10,r6
vst1.64 {q0,q1}, [r3,:256]! @ wipe
it cc
movcc r11,r7
ldmia r1, {r4,r5,r6,r7}
stmia r0!, {r8,r9,r10,r11}
sub r1,r1,#16
ldmia r0, {r8,r9,r10,r11}
it cc
movcc r8, r4
vst1.64 {q0,q1}, [r1,:256]! @ wipe
itt cc
movcc r9, r5
movcc r10,r6
vst1.64 {q0,q1}, [r3,:256]! @ wipe
it cc
movcc r11,r7
teq r1,r2 @ preserves carry
stmia r0!, {r8,r9,r10,r11}
bne LNEON_copy_n_zap
mov sp,ip
vldmia sp!,{d8,d9,d10,d11,d12,d13,d14,d15}
ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11}
bx lr @ bx lr
#endif
.byte 77,111,110,116,103,111,109,101,114,121,32,109,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,65,82,77,118,52,47,78,69,79,78,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#if __ARM_MAX_ARCH__>=7
.comm _OPENSSL_armcap_P,4
.non_lazy_symbol_pointer
OPENSSL_armcap_P:
.indirect_symbol _OPENSSL_armcap_P
.long 0
.private_extern _OPENSSL_armcap_P
#endif
#endif // !OPENSSL_NO_ASM

1536
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/bsaes-armv7.S
View File

File diff suppressed because it is too large Load Diff

258
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/ghash-armv4.S
View File

@ -1,258 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
@ Silence ARMv8 deprecated IT instruction warnings. This file is used by both
@ ARMv7 and ARMv8 processors and does not use ARMv8 instructions. (ARMv8 PMULL
@ instructions are in aesv8-armx.pl.)
.text
#if defined(__thumb2__) || defined(__clang__)
.syntax unified
#define ldrplb ldrbpl
#define ldrneb ldrbne
#endif
#if defined(__thumb2__)
.thumb
#else
.code 32
#endif
#if __ARM_MAX_ARCH__>=7
.globl _gcm_init_neon
.private_extern _gcm_init_neon
#ifdef __thumb2__
.thumb_func _gcm_init_neon
#endif
.align 4
_gcm_init_neon:
vld1.64 d7,[r1]! @ load H
vmov.i8 q8,#0xe1
vld1.64 d6,[r1]
vshl.i64 d17,#57
vshr.u64 d16,#63 @ t0=0xc2....01
vdup.8 q9,d7[7]
vshr.u64 d26,d6,#63
vshr.s8 q9,#7 @ broadcast carry bit
vshl.i64 q3,q3,#1
vand q8,q8,q9
vorr d7,d26 @ H<<<=1
veor q3,q3,q8 @ twisted H
vstmia r0,{q3}
bx lr @ bx lr
.globl _gcm_gmult_neon
.private_extern _gcm_gmult_neon
#ifdef __thumb2__
.thumb_func _gcm_gmult_neon
#endif
.align 4
_gcm_gmult_neon:
vld1.64 d7,[r0]! @ load Xi
vld1.64 d6,[r0]!
vmov.i64 d29,#0x0000ffffffffffff
vldmia r1,{d26,d27} @ load twisted H
vmov.i64 d30,#0x00000000ffffffff
#ifdef __ARMEL__
vrev64.8 q3,q3
#endif
vmov.i64 d31,#0x000000000000ffff
veor d28,d26,d27 @ Karatsuba pre-processing
mov r3,#16
b Lgmult_neon
.globl _gcm_ghash_neon
.private_extern _gcm_ghash_neon
#ifdef __thumb2__
.thumb_func _gcm_ghash_neon
#endif
.align 4
_gcm_ghash_neon:
vld1.64 d1,[r0]! @ load Xi
vld1.64 d0,[r0]!
vmov.i64 d29,#0x0000ffffffffffff
vldmia r1,{d26,d27} @ load twisted H
vmov.i64 d30,#0x00000000ffffffff
#ifdef __ARMEL__
vrev64.8 q0,q0
#endif
vmov.i64 d31,#0x000000000000ffff
veor d28,d26,d27 @ Karatsuba pre-processing
Loop_neon:
vld1.64 d7,[r2]! @ load inp
vld1.64 d6,[r2]!
#ifdef __ARMEL__
vrev64.8 q3,q3
#endif
veor q3,q0 @ inp^=Xi
Lgmult_neon:
vext.8 d16, d26, d26, #1 @ A1
vmull.p8 q8, d16, d6 @ F = A1*B
vext.8 d0, d6, d6, #1 @ B1
vmull.p8 q0, d26, d0 @ E = A*B1
vext.8 d18, d26, d26, #2 @ A2
vmull.p8 q9, d18, d6 @ H = A2*B
vext.8 d22, d6, d6, #2 @ B2
vmull.p8 q11, d26, d22 @ G = A*B2
vext.8 d20, d26, d26, #3 @ A3
veor q8, q8, q0 @ L = E + F
vmull.p8 q10, d20, d6 @ J = A3*B
vext.8 d0, d6, d6, #3 @ B3
veor q9, q9, q11 @ M = G + H
vmull.p8 q0, d26, d0 @ I = A*B3
veor d16, d16, d17 @ t0 = (L) (P0 + P1) << 8
vand d17, d17, d29
vext.8 d22, d6, d6, #4 @ B4
veor d18, d18, d19 @ t1 = (M) (P2 + P3) << 16
vand d19, d19, d30
vmull.p8 q11, d26, d22 @ K = A*B4
veor q10, q10, q0 @ N = I + J
veor d16, d16, d17
veor d18, d18, d19
veor d20, d20, d21 @ t2 = (N) (P4 + P5) << 24
vand d21, d21, d31
vext.8 q8, q8, q8, #15
veor d22, d22, d23 @ t3 = (K) (P6 + P7) << 32
vmov.i64 d23, #0
vext.8 q9, q9, q9, #14
veor d20, d20, d21
vmull.p8 q0, d26, d6 @ D = A*B
vext.8 q11, q11, q11, #12
vext.8 q10, q10, q10, #13
veor q8, q8, q9
veor q10, q10, q11
veor q0, q0, q8
veor q0, q0, q10
veor d6,d6,d7 @ Karatsuba pre-processing
vext.8 d16, d28, d28, #1 @ A1
vmull.p8 q8, d16, d6 @ F = A1*B
vext.8 d2, d6, d6, #1 @ B1
vmull.p8 q1, d28, d2 @ E = A*B1
vext.8 d18, d28, d28, #2 @ A2
vmull.p8 q9, d18, d6 @ H = A2*B
vext.8 d22, d6, d6, #2 @ B2
vmull.p8 q11, d28, d22 @ G = A*B2
vext.8 d20, d28, d28, #3 @ A3
veor q8, q8, q1 @ L = E + F
vmull.p8 q10, d20, d6 @ J = A3*B
vext.8 d2, d6, d6, #3 @ B3
veor q9, q9, q11 @ M = G + H
vmull.p8 q1, d28, d2 @ I = A*B3
veor d16, d16, d17 @ t0 = (L) (P0 + P1) << 8
vand d17, d17, d29
vext.8 d22, d6, d6, #4 @ B4
veor d18, d18, d19 @ t1 = (M) (P2 + P3) << 16
vand d19, d19, d30
vmull.p8 q11, d28, d22 @ K = A*B4
veor q10, q10, q1 @ N = I + J
veor d16, d16, d17
veor d18, d18, d19
veor d20, d20, d21 @ t2 = (N) (P4 + P5) << 24
vand d21, d21, d31
vext.8 q8, q8, q8, #15
veor d22, d22, d23 @ t3 = (K) (P6 + P7) << 32
vmov.i64 d23, #0
vext.8 q9, q9, q9, #14
veor d20, d20, d21
vmull.p8 q1, d28, d6 @ D = A*B
vext.8 q11, q11, q11, #12
vext.8 q10, q10, q10, #13
veor q8, q8, q9
veor q10, q10, q11
veor q1, q1, q8
veor q1, q1, q10
vext.8 d16, d27, d27, #1 @ A1
vmull.p8 q8, d16, d7 @ F = A1*B
vext.8 d4, d7, d7, #1 @ B1
vmull.p8 q2, d27, d4 @ E = A*B1
vext.8 d18, d27, d27, #2 @ A2
vmull.p8 q9, d18, d7 @ H = A2*B
vext.8 d22, d7, d7, #2 @ B2
vmull.p8 q11, d27, d22 @ G = A*B2
vext.8 d20, d27, d27, #3 @ A3
veor q8, q8, q2 @ L = E + F
vmull.p8 q10, d20, d7 @ J = A3*B
vext.8 d4, d7, d7, #3 @ B3
veor q9, q9, q11 @ M = G + H
vmull.p8 q2, d27, d4 @ I = A*B3
veor d16, d16, d17 @ t0 = (L) (P0 + P1) << 8
vand d17, d17, d29
vext.8 d22, d7, d7, #4 @ B4
veor d18, d18, d19 @ t1 = (M) (P2 + P3) << 16
vand d19, d19, d30
vmull.p8 q11, d27, d22 @ K = A*B4
veor q10, q10, q2 @ N = I + J
veor d16, d16, d17
veor d18, d18, d19
veor d20, d20, d21 @ t2 = (N) (P4 + P5) << 24
vand d21, d21, d31
vext.8 q8, q8, q8, #15
veor d22, d22, d23 @ t3 = (K) (P6 + P7) << 32
vmov.i64 d23, #0
vext.8 q9, q9, q9, #14
veor d20, d20, d21
vmull.p8 q2, d27, d7 @ D = A*B
vext.8 q11, q11, q11, #12
vext.8 q10, q10, q10, #13
veor q8, q8, q9
veor q10, q10, q11
veor q2, q2, q8
veor q2, q2, q10
veor q1,q1,q0 @ Karatsuba post-processing
veor q1,q1,q2
veor d1,d1,d2
veor d4,d4,d3 @ Xh|Xl - 256-bit result
@ equivalent of reduction_avx from ghash-x86_64.pl
vshl.i64 q9,q0,#57 @ 1st phase
vshl.i64 q10,q0,#62
veor q10,q10,q9 @
vshl.i64 q9,q0,#63
veor q10, q10, q9 @
veor d1,d1,d20 @
veor d4,d4,d21
vshr.u64 q10,q0,#1 @ 2nd phase
veor q2,q2,q0
veor q0,q0,q10 @
vshr.u64 q10,q10,#6
vshr.u64 q0,q0,#1 @
veor q0,q0,q2 @
veor q0,q0,q10 @
subs r3,#16
bne Loop_neon
#ifdef __ARMEL__
vrev64.8 q0,q0
#endif
sub r0,#16
vst1.64 d1,[r0]! @ write out Xi
vst1.64 d0,[r0]
bx lr @ bx lr
#endif
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,52,47,78,69,79,78,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif // !OPENSSL_NO_ASM

256
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/ghashv8-armx32.S
View File

@ -1,256 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.code 32
#undef __thumb2__
.globl _gcm_init_v8
.private_extern _gcm_init_v8
#ifdef __thumb2__
.thumb_func _gcm_init_v8
#endif
.align 4
_gcm_init_v8:
vld1.64 {q9},[r1] @ load input H
vmov.i8 q11,#0xe1
vshl.i64 q11,q11,#57 @ 0xc2.0
vext.8 q3,q9,q9,#8
vshr.u64 q10,q11,#63
vdup.32 q9,d18[1]
vext.8 q8,q10,q11,#8 @ t0=0xc2....01
vshr.u64 q10,q3,#63
vshr.s32 q9,q9,#31 @ broadcast carry bit
vand q10,q10,q8
vshl.i64 q3,q3,#1
vext.8 q10,q10,q10,#8
vand q8,q8,q9
vorr q3,q3,q10 @ H<<<=1
veor q12,q3,q8 @ twisted H
vst1.64 {q12},[r0]! @ store Htable[0]
@ calculate H^2
vext.8 q8,q12,q12,#8 @ Karatsuba pre-processing
.byte 0xa8,0x0e,0xa8,0xf2 @ pmull q0,q12,q12
veor q8,q8,q12
.byte 0xa9,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q12
.byte 0xa0,0x2e,0xa0,0xf2 @ pmull q1,q8,q8
vext.8 q9,q0,q2,#8 @ Karatsuba post-processing
veor q10,q0,q2
veor q1,q1,q9
veor q1,q1,q10
.byte 0x26,0x4e,0xe0,0xf2 @ pmull q10,q0,q11 @ 1st phase
vmov d4,d3 @ Xh|Xm - 256-bit result
vmov d3,d0 @ Xm is rotated Xl
veor q0,q1,q10
vext.8 q10,q0,q0,#8 @ 2nd phase
.byte 0x26,0x0e,0xa0,0xf2 @ pmull q0,q0,q11
veor q10,q10,q2
veor q14,q0,q10
vext.8 q9,q14,q14,#8 @ Karatsuba pre-processing
veor q9,q9,q14
vext.8 q13,q8,q9,#8 @ pack Karatsuba pre-processed
vst1.64 {q13,q14},[r0] @ store Htable[1..2]
bx lr
.globl _gcm_gmult_v8
.private_extern _gcm_gmult_v8
#ifdef __thumb2__
.thumb_func _gcm_gmult_v8
#endif
.align 4
_gcm_gmult_v8:
vld1.64 {q9},[r0] @ load Xi
vmov.i8 q11,#0xe1
vld1.64 {q12,q13},[r1] @ load twisted H, ...
vshl.u64 q11,q11,#57
#ifndef __ARMEB__
vrev64.8 q9,q9
#endif
vext.8 q3,q9,q9,#8
.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo
veor q9,q9,q3 @ Karatsuba pre-processing
.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi
.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vext.8 q9,q0,q2,#8 @ Karatsuba post-processing
veor q10,q0,q2
veor q1,q1,q9
veor q1,q1,q10
.byte 0x26,0x4e,0xe0,0xf2 @ pmull q10,q0,q11 @ 1st phase of reduction
vmov d4,d3 @ Xh|Xm - 256-bit result
vmov d3,d0 @ Xm is rotated Xl
veor q0,q1,q10
vext.8 q10,q0,q0,#8 @ 2nd phase of reduction
.byte 0x26,0x0e,0xa0,0xf2 @ pmull q0,q0,q11
veor q10,q10,q2
veor q0,q0,q10
#ifndef __ARMEB__
vrev64.8 q0,q0
#endif
vext.8 q0,q0,q0,#8
vst1.64 {q0},[r0] @ write out Xi
bx lr
.globl _gcm_ghash_v8
.private_extern _gcm_ghash_v8
#ifdef __thumb2__
.thumb_func _gcm_ghash_v8
#endif
.align 4
_gcm_ghash_v8:
vstmdb sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ 32-bit ABI says so
vld1.64 {q0},[r0] @ load [rotated] Xi
@ "[rotated]" means that
@ loaded value would have
@ to be rotated in order to
@ make it appear as in
@ algorithm specification
subs r3,r3,#32 @ see if r3 is 32 or larger
mov r12,#16 @ r12 is used as post-
@ increment for input pointer;
@ as loop is modulo-scheduled
@ r12 is zeroed just in time
@ to preclude overstepping
@ inp[len], which means that
@ last block[s] are actually
@ loaded twice, but last
@ copy is not processed
vld1.64 {q12,q13},[r1]! @ load twisted H, ..., H^2
vmov.i8 q11,#0xe1
vld1.64 {q14},[r1]
moveq r12,#0 @ is it time to zero r12?
vext.8 q0,q0,q0,#8 @ rotate Xi
vld1.64 {q8},[r2]! @ load [rotated] I[0]
vshl.u64 q11,q11,#57 @ compose 0xc2.0 constant
#ifndef __ARMEB__
vrev64.8 q8,q8
vrev64.8 q0,q0
#endif
vext.8 q3,q8,q8,#8 @ rotate I[0]
blo Lodd_tail_v8 @ r3 was less than 32
vld1.64 {q9},[r2],r12 @ load [rotated] I[1]
#ifndef __ARMEB__
vrev64.8 q9,q9
#endif
vext.8 q7,q9,q9,#8
veor q3,q3,q0 @ I[i]^=Xi
.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1
veor q9,q9,q7 @ Karatsuba pre-processing
.byte 0x8f,0xce,0xa9,0xf2 @ pmull2 q6,q12,q7
b Loop_mod2x_v8
.align 4
Loop_mod2x_v8:
vext.8 q10,q3,q3,#8
subs r3,r3,#32 @ is there more data?
.byte 0x86,0x0e,0xac,0xf2 @ pmull q0,q14,q3 @ H^2.lo·Xi.lo
movlo r12,#0 @ is it time to zero r12?
.byte 0xa2,0xae,0xaa,0xf2 @ pmull q5,q13,q9
veor q10,q10,q3 @ Karatsuba pre-processing
.byte 0x87,0x4e,0xad,0xf2 @ pmull2 q2,q14,q3 @ H^2.hi·Xi.hi
veor q0,q0,q4 @ accumulate
.byte 0xa5,0x2e,0xab,0xf2 @ pmull2 q1,q13,q10 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
vld1.64 {q8},[r2],r12 @ load [rotated] I[i+2]
veor q2,q2,q6
moveq r12,#0 @ is it time to zero r12?
veor q1,q1,q5
vext.8 q9,q0,q2,#8 @ Karatsuba post-processing
veor q10,q0,q2
veor q1,q1,q9
vld1.64 {q9},[r2],r12 @ load [rotated] I[i+3]
#ifndef __ARMEB__
vrev64.8 q8,q8
#endif
veor q1,q1,q10
.byte 0x26,0x4e,0xe0,0xf2 @ pmull q10,q0,q11 @ 1st phase of reduction
#ifndef __ARMEB__
vrev64.8 q9,q9
#endif
vmov d4,d3 @ Xh|Xm - 256-bit result
vmov d3,d0 @ Xm is rotated Xl
vext.8 q7,q9,q9,#8
vext.8 q3,q8,q8,#8
veor q0,q1,q10
.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1
veor q3,q3,q2 @ accumulate q3 early
vext.8 q10,q0,q0,#8 @ 2nd phase of reduction
.byte 0x26,0x0e,0xa0,0xf2 @ pmull q0,q0,q11
veor q3,q3,q10
veor q9,q9,q7 @ Karatsuba pre-processing
veor q3,q3,q0
.byte 0x8f,0xce,0xa9,0xf2 @ pmull2 q6,q12,q7
bhs Loop_mod2x_v8 @ there was at least 32 more bytes
veor q2,q2,q10
vext.8 q3,q8,q8,#8 @ re-construct q3
adds r3,r3,#32 @ re-construct r3
veor q0,q0,q2 @ re-construct q0
beq Ldone_v8 @ is r3 zero?
Lodd_tail_v8:
vext.8 q10,q0,q0,#8
veor q3,q3,q0 @ inp^=Xi
veor q9,q8,q10 @ q9 is rotated inp^Xi
.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo
veor q9,q9,q3 @ Karatsuba pre-processing
.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi
.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi)
vext.8 q9,q0,q2,#8 @ Karatsuba post-processing
veor q10,q0,q2
veor q1,q1,q9
veor q1,q1,q10
.byte 0x26,0x4e,0xe0,0xf2 @ pmull q10,q0,q11 @ 1st phase of reduction
vmov d4,d3 @ Xh|Xm - 256-bit result
vmov d3,d0 @ Xm is rotated Xl
veor q0,q1,q10
vext.8 q10,q0,q0,#8 @ 2nd phase of reduction
.byte 0x26,0x0e,0xa0,0xf2 @ pmull q0,q0,q11
veor q10,q10,q2
veor q0,q0,q10
Ldone_v8:
#ifndef __ARMEB__
vrev64.8 q0,q0
#endif
vext.8 q0,q0,q0,#8
vst1.64 {q0},[r0] @ write out Xi
vldmia sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ 32-bit ABI says so
bx lr
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif // !OPENSSL_NO_ASM

1518
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/sha1-armv4-large.S
View File

File diff suppressed because it is too large Load Diff

2846
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/sha256-armv4.S
View File

File diff suppressed because it is too large Load Diff

1899
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/sha512-armv4.S
View File

File diff suppressed because it is too large Load Diff

1265
contrib/boringssl-cmake/ios-arm/crypto/fipsmodule/vpaes-armv7.S
View File

File diff suppressed because it is too large Load Diff

376
contrib/boringssl-cmake/ios-arm/crypto/test/trampoline-armv4.S
View File

@ -1,376 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
.syntax unified
.text
@ abi_test_trampoline loads callee-saved registers from |state|, calls |func|
@ with |argv|, then saves the callee-saved registers into |state|. It returns
@ the result of |func|. The |unwind| argument is unused.
@ uint32_t abi_test_trampoline(void (*func)(...), CallerState *state,
@ const uint32_t *argv, size_t argc,
@ int unwind);
.globl _abi_test_trampoline
.private_extern _abi_test_trampoline
.align 4
_abi_test_trampoline:
@ Save parameters and all callee-saved registers. For convenience, we
@ save r9 on iOS even though it's volatile.
vstmdb sp!, {d8,d9,d10,d11,d12,d13,d14,d15}
stmdb sp!, {r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,lr}
@ Reserve stack space for six (10-4) stack parameters, plus an extra 4
@ bytes to keep it 8-byte-aligned (see AAPCS, section 5.3).
sub sp, sp, #28
@ Every register in AAPCS is either non-volatile or a parameter (except
@ r9 on iOS), so this code, by the actual call, loses all its scratch
@ registers. First fill in stack parameters while there are registers
@ to spare.
cmp r3, #4
bls Lstack_args_done
mov r4, sp @ r4 is the output pointer.
add r5, r2, r3, lsl #2 @ Set r5 to the end of argv.
add r2, r2, #16 @ Skip four arguments.
Lstack_args_loop:
ldr r6, [r2], #4
cmp r2, r5
str r6, [r4], #4
bne Lstack_args_loop
Lstack_args_done:
@ Load registers from |r1|.
vldmia r1!, {d8,d9,d10,d11,d12,d13,d14,d15}
#if defined(__APPLE__)
@ r9 is not volatile on iOS.
ldmia r1!, {r4,r5,r6,r7,r8,r10-r11}
#else
ldmia r1!, {r4,r5,r6,r7,r8,r9,r10,r11}
#endif
@ Load register parameters. This uses up our remaining registers, so we
@ repurpose lr as scratch space.
ldr r3, [sp, #40] @ Reload argc.
ldr lr, [sp, #36] @ Load argv into lr.
cmp r3, #3
bhi Larg_r3
beq Larg_r2
cmp r3, #1
bhi Larg_r1
beq Larg_r0
b Largs_done
Larg_r3:
ldr r3, [lr, #12] @ argv[3]
Larg_r2:
ldr r2, [lr, #8] @ argv[2]
Larg_r1:
ldr r1, [lr, #4] @ argv[1]
Larg_r0:
ldr r0, [lr] @ argv[0]
Largs_done:
@ With every other register in use, load the function pointer into lr
@ and call the function.
ldr lr, [sp, #28]
blx lr
@ r1-r3 are free for use again. The trampoline only supports
@ single-return functions. Pass r4-r11 to the caller.
ldr r1, [sp, #32]
vstmia r1!, {d8,d9,d10,d11,d12,d13,d14,d15}
#if defined(__APPLE__)
@ r9 is not volatile on iOS.
stmia r1!, {r4,r5,r6,r7,r8,r10-r11}
#else
stmia r1!, {r4,r5,r6,r7,r8,r9,r10,r11}
#endif
@ Unwind the stack and restore registers.
add sp, sp, #44 @ 44 = 28+16
ldmia sp!, {r4,r5,r6,r7,r8,r9,r10,r11,lr} @ Skip r0-r3 (see +16 above).
vldmia sp!, {d8,d9,d10,d11,d12,d13,d14,d15}
bx lr
.globl _abi_test_clobber_r0
.private_extern _abi_test_clobber_r0
.align 4
_abi_test_clobber_r0:
mov r0, #0
bx lr
.globl _abi_test_clobber_r1
.private_extern _abi_test_clobber_r1
.align 4
_abi_test_clobber_r1:
mov r1, #0
bx lr
.globl _abi_test_clobber_r2
.private_extern _abi_test_clobber_r2
.align 4
_abi_test_clobber_r2:
mov r2, #0
bx lr
.globl _abi_test_clobber_r3
.private_extern _abi_test_clobber_r3
.align 4
_abi_test_clobber_r3:
mov r3, #0
bx lr
.globl _abi_test_clobber_r4
.private_extern _abi_test_clobber_r4
.align 4
_abi_test_clobber_r4:
mov r4, #0
bx lr
.globl _abi_test_clobber_r5
.private_extern _abi_test_clobber_r5
.align 4
_abi_test_clobber_r5:
mov r5, #0
bx lr
.globl _abi_test_clobber_r6
.private_extern _abi_test_clobber_r6
.align 4
_abi_test_clobber_r6:
mov r6, #0
bx lr
.globl _abi_test_clobber_r7
.private_extern _abi_test_clobber_r7
.align 4
_abi_test_clobber_r7:
mov r7, #0
bx lr
.globl _abi_test_clobber_r8
.private_extern _abi_test_clobber_r8
.align 4
_abi_test_clobber_r8:
mov r8, #0
bx lr
.globl _abi_test_clobber_r9
.private_extern _abi_test_clobber_r9
.align 4
_abi_test_clobber_r9:
mov r9, #0
bx lr
.globl _abi_test_clobber_r10
.private_extern _abi_test_clobber_r10
.align 4
_abi_test_clobber_r10:
mov r10, #0
bx lr
.globl _abi_test_clobber_r11
.private_extern _abi_test_clobber_r11
.align 4
_abi_test_clobber_r11:
mov r11, #0
bx lr
.globl _abi_test_clobber_r12
.private_extern _abi_test_clobber_r12
.align 4
_abi_test_clobber_r12:
mov r12, #0
bx lr
.globl _abi_test_clobber_d0
.private_extern _abi_test_clobber_d0
.align 4
_abi_test_clobber_d0:
mov r0, #0
vmov s0, r0
vmov s1, r0
bx lr
.globl _abi_test_clobber_d1
.private_extern _abi_test_clobber_d1
.align 4
_abi_test_clobber_d1:
mov r0, #0
vmov s2, r0
vmov s3, r0
bx lr
.globl _abi_test_clobber_d2
.private_extern _abi_test_clobber_d2
.align 4
_abi_test_clobber_d2:
mov r0, #0
vmov s4, r0
vmov s5, r0
bx lr
.globl _abi_test_clobber_d3
.private_extern _abi_test_clobber_d3
.align 4
_abi_test_clobber_d3:
mov r0, #0
vmov s6, r0
vmov s7, r0
bx lr
.globl _abi_test_clobber_d4
.private_extern _abi_test_clobber_d4
.align 4
_abi_test_clobber_d4:
mov r0, #0
vmov s8, r0
vmov s9, r0
bx lr
.globl _abi_test_clobber_d5
.private_extern _abi_test_clobber_d5
.align 4
_abi_test_clobber_d5:
mov r0, #0
vmov s10, r0
vmov s11, r0
bx lr
.globl _abi_test_clobber_d6
.private_extern _abi_test_clobber_d6
.align 4
_abi_test_clobber_d6:
mov r0, #0
vmov s12, r0
vmov s13, r0
bx lr
.globl _abi_test_clobber_d7
.private_extern _abi_test_clobber_d7
.align 4
_abi_test_clobber_d7:
mov r0, #0
vmov s14, r0
vmov s15, r0
bx lr
.globl _abi_test_clobber_d8
.private_extern _abi_test_clobber_d8
.align 4
_abi_test_clobber_d8:
mov r0, #0
vmov s16, r0
vmov s17, r0
bx lr
.globl _abi_test_clobber_d9
.private_extern _abi_test_clobber_d9
.align 4
_abi_test_clobber_d9:
mov r0, #0
vmov s18, r0
vmov s19, r0
bx lr
.globl _abi_test_clobber_d10
.private_extern _abi_test_clobber_d10
.align 4
_abi_test_clobber_d10:
mov r0, #0
vmov s20, r0
vmov s21, r0
bx lr
.globl _abi_test_clobber_d11
.private_extern _abi_test_clobber_d11
.align 4
_abi_test_clobber_d11:
mov r0, #0
vmov s22, r0
vmov s23, r0
bx lr
.globl _abi_test_clobber_d12
.private_extern _abi_test_clobber_d12
.align 4
_abi_test_clobber_d12:
mov r0, #0
vmov s24, r0
vmov s25, r0
bx lr
.globl _abi_test_clobber_d13
.private_extern _abi_test_clobber_d13
.align 4
_abi_test_clobber_d13:
mov r0, #0
vmov s26, r0
vmov s27, r0
bx lr
.globl _abi_test_clobber_d14
.private_extern _abi_test_clobber_d14
.align 4
_abi_test_clobber_d14:
mov r0, #0
vmov s28, r0
vmov s29, r0
bx lr
.globl _abi_test_clobber_d15
.private_extern _abi_test_clobber_d15
.align 4
_abi_test_clobber_d15:
mov r0, #0
vmov s30, r0
vmov s31, r0
bx lr
#endif // !OPENSSL_NO_ASM

1994
contrib/boringssl-cmake/linux-aarch64/crypto/chacha/chacha-armv8.S
View File

File diff suppressed because it is too large Load Diff

785
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/aesv8-armx64.S
View File

@ -1,785 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(__aarch64__)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
#if __ARM_MAX_ARCH__>=7
.text
.arch armv8-a+crypto
.section .rodata
.align 5
.Lrcon:
.long 0x01,0x01,0x01,0x01
.long 0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d // rotate-n-splat
.long 0x1b,0x1b,0x1b,0x1b
.text
.globl aes_hw_set_encrypt_key
.hidden aes_hw_set_encrypt_key
.type aes_hw_set_encrypt_key,%function
.align 5
aes_hw_set_encrypt_key:
.Lenc_key:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
mov x3,#-1
cmp x0,#0
b.eq .Lenc_key_abort
cmp x2,#0
b.eq .Lenc_key_abort
mov x3,#-2
cmp w1,#128
b.lt .Lenc_key_abort
cmp w1,#256
b.gt .Lenc_key_abort
tst w1,#0x3f
b.ne .Lenc_key_abort
adrp x3,.Lrcon
add x3,x3,:lo12:.Lrcon
cmp w1,#192
eor v0.16b,v0.16b,v0.16b
ld1 {v3.16b},[x0],#16
mov w1,#8 // reuse w1
ld1 {v1.4s,v2.4s},[x3],#32
b.lt .Loop128
b.eq .L192
b .L256
.align 4
.Loop128:
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
b.ne .Loop128
ld1 {v1.4s},[x3]
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
tbl v6.16b,{v3.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v3.4s},[x2],#16
aese v6.16b,v0.16b
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
eor v3.16b,v3.16b,v6.16b
st1 {v3.4s},[x2]
add x2,x2,#0x50
mov w12,#10
b .Ldone
.align 4
.L192:
ld1 {v4.8b},[x0],#8
movi v6.16b,#8 // borrow v6.16b
st1 {v3.4s},[x2],#16
sub v2.16b,v2.16b,v6.16b // adjust the mask
.Loop192:
tbl v6.16b,{v4.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v4.8b},[x2],#8
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
dup v5.4s,v3.s[3]
eor v5.16b,v5.16b,v4.16b
eor v6.16b,v6.16b,v1.16b
ext v4.16b,v0.16b,v4.16b,#12
shl v1.16b,v1.16b,#1
eor v4.16b,v4.16b,v5.16b
eor v3.16b,v3.16b,v6.16b
eor v4.16b,v4.16b,v6.16b
st1 {v3.4s},[x2],#16
b.ne .Loop192
mov w12,#12
add x2,x2,#0x20
b .Ldone
.align 4
.L256:
ld1 {v4.16b},[x0]
mov w1,#7
mov w12,#14
st1 {v3.4s},[x2],#16
.Loop256:
tbl v6.16b,{v4.16b},v2.16b
ext v5.16b,v0.16b,v3.16b,#12
st1 {v4.4s},[x2],#16
aese v6.16b,v0.16b
subs w1,w1,#1
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v3.16b,v3.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v6.16b,v6.16b,v1.16b
eor v3.16b,v3.16b,v5.16b
shl v1.16b,v1.16b,#1
eor v3.16b,v3.16b,v6.16b
st1 {v3.4s},[x2],#16
b.eq .Ldone
dup v6.4s,v3.s[3] // just splat
ext v5.16b,v0.16b,v4.16b,#12
aese v6.16b,v0.16b
eor v4.16b,v4.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v4.16b,v4.16b,v5.16b
ext v5.16b,v0.16b,v5.16b,#12
eor v4.16b,v4.16b,v5.16b
eor v4.16b,v4.16b,v6.16b
b .Loop256
.Ldone:
str w12,[x2]
mov x3,#0
.Lenc_key_abort:
mov x0,x3 // return value
ldr x29,[sp],#16
ret
.size aes_hw_set_encrypt_key,.-aes_hw_set_encrypt_key
.globl aes_hw_set_decrypt_key
.hidden aes_hw_set_decrypt_key
.type aes_hw_set_decrypt_key,%function
.align 5
aes_hw_set_decrypt_key:
AARCH64_SIGN_LINK_REGISTER
stp x29,x30,[sp,#-16]!
add x29,sp,#0
bl .Lenc_key
cmp x0,#0
b.ne .Ldec_key_abort
sub x2,x2,#240 // restore original x2
mov x4,#-16
add x0,x2,x12,lsl#4 // end of key schedule
ld1 {v0.4s},[x2]
ld1 {v1.4s},[x0]
st1 {v0.4s},[x0],x4
st1 {v1.4s},[x2],#16
.Loop_imc:
ld1 {v0.4s},[x2]
ld1 {v1.4s},[x0]
aesimc v0.16b,v0.16b
aesimc v1.16b,v1.16b
st1 {v0.4s},[x0],x4
st1 {v1.4s},[x2],#16
cmp x0,x2
b.hi .Loop_imc
ld1 {v0.4s},[x2]
aesimc v0.16b,v0.16b
st1 {v0.4s},[x0]
eor x0,x0,x0 // return value
.Ldec_key_abort:
ldp x29,x30,[sp],#16
AARCH64_VALIDATE_LINK_REGISTER
ret
.size aes_hw_set_decrypt_key,.-aes_hw_set_decrypt_key
.globl aes_hw_encrypt
.hidden aes_hw_encrypt
.type aes_hw_encrypt,%function
.align 5
aes_hw_encrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
sub w3,w3,#2
ld1 {v1.4s},[x2],#16
.Loop_enc:
aese v2.16b,v0.16b
aesmc v2.16b,v2.16b
ld1 {v0.4s},[x2],#16
subs w3,w3,#2
aese v2.16b,v1.16b
aesmc v2.16b,v2.16b
ld1 {v1.4s},[x2],#16
b.gt .Loop_enc
aese v2.16b,v0.16b
aesmc v2.16b,v2.16b
ld1 {v0.4s},[x2]
aese v2.16b,v1.16b
eor v2.16b,v2.16b,v0.16b
st1 {v2.16b},[x1]
ret
.size aes_hw_encrypt,.-aes_hw_encrypt
.globl aes_hw_decrypt
.hidden aes_hw_decrypt
.type aes_hw_decrypt,%function
.align 5
aes_hw_decrypt:
AARCH64_VALID_CALL_TARGET
ldr w3,[x2,#240]
ld1 {v0.4s},[x2],#16
ld1 {v2.16b},[x0]
sub w3,w3,#2
ld1 {v1.4s},[x2],#16
.Loop_dec:
aesd v2.16b,v0.16b
aesimc v2.16b,v2.16b
ld1 {v0.4s},[x2],#16
subs w3,w3,#2
aesd v2.16b,v1.16b
aesimc v2.16b,v2.16b
ld1 {v1.4s},[x2],#16
b.gt .Loop_dec
aesd v2.16b,v0.16b
aesimc v2.16b,v2.16b
ld1 {v0.4s},[x2]
aesd v2.16b,v1.16b
eor v2.16b,v2.16b,v0.16b
st1 {v2.16b},[x1]
ret
.size aes_hw_decrypt,.-aes_hw_decrypt
.globl aes_hw_cbc_encrypt
.hidden aes_hw_cbc_encrypt
.type aes_hw_cbc_encrypt,%function
.align 5
aes_hw_cbc_encrypt:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
subs x2,x2,#16
mov x8,#16
b.lo .Lcbc_abort
csel x8,xzr,x8,eq
cmp w5,#0 // en- or decrypting?
ldr w5,[x3,#240]
and x2,x2,#-16
ld1 {v6.16b},[x4]
ld1 {v0.16b},[x0],x8
ld1 {v16.4s,v17.4s},[x3] // load key schedule...
sub w5,w5,#6
add x7,x3,x5,lsl#4 // pointer to last 7 round keys
sub w5,w5,#2
ld1 {v18.4s,v19.4s},[x7],#32
ld1 {v20.4s,v21.4s},[x7],#32
ld1 {v22.4s,v23.4s},[x7],#32
ld1 {v7.4s},[x7]
add x7,x3,#32
mov w6,w5
b.eq .Lcbc_dec
cmp w5,#2
eor v0.16b,v0.16b,v6.16b
eor v5.16b,v16.16b,v7.16b
b.eq .Lcbc_enc128
ld1 {v2.4s,v3.4s},[x7]
add x7,x3,#16
add x6,x3,#16*4
add x12,x3,#16*5
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
add x14,x3,#16*6
add x3,x3,#16*7
b .Lenter_cbc_enc
.align 4
.Loop_cbc_enc:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
st1 {v6.16b},[x1],#16
.Lenter_cbc_enc:
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v0.16b,v2.16b
aesmc v0.16b,v0.16b
ld1 {v16.4s},[x6]
cmp w5,#4
aese v0.16b,v3.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x12]
b.eq .Lcbc_enc192
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
ld1 {v16.4s},[x14]
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x3]
nop
.Lcbc_enc192:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
subs x2,x2,#16
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
csel x8,xzr,x8,eq
aese v0.16b,v18.16b
aesmc v0.16b,v0.16b
aese v0.16b,v19.16b
aesmc v0.16b,v0.16b
ld1 {v16.16b},[x0],x8
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
eor v16.16b,v16.16b,v5.16b
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
ld1 {v17.4s},[x7] // re-pre-load rndkey[1]
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
aese v0.16b,v23.16b
eor v6.16b,v0.16b,v7.16b
b.hs .Loop_cbc_enc
st1 {v6.16b},[x1],#16
b .Lcbc_done
.align 5
.Lcbc_enc128:
ld1 {v2.4s,v3.4s},[x7]
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
b .Lenter_cbc_enc128
.Loop_cbc_enc128:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
st1 {v6.16b},[x1],#16
.Lenter_cbc_enc128:
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
subs x2,x2,#16
aese v0.16b,v2.16b
aesmc v0.16b,v0.16b
csel x8,xzr,x8,eq
aese v0.16b,v3.16b
aesmc v0.16b,v0.16b
aese v0.16b,v18.16b
aesmc v0.16b,v0.16b
aese v0.16b,v19.16b
aesmc v0.16b,v0.16b
ld1 {v16.16b},[x0],x8
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
eor v16.16b,v16.16b,v5.16b
aese v0.16b,v23.16b
eor v6.16b,v0.16b,v7.16b
b.hs .Loop_cbc_enc128
st1 {v6.16b},[x1],#16
b .Lcbc_done
.align 5
.Lcbc_dec:
ld1 {v18.16b},[x0],#16
subs x2,x2,#32 // bias
add w6,w5,#2
orr v3.16b,v0.16b,v0.16b
orr v1.16b,v0.16b,v0.16b
orr v19.16b,v18.16b,v18.16b
b.lo .Lcbc_dec_tail
orr v1.16b,v18.16b,v18.16b
ld1 {v18.16b},[x0],#16
orr v2.16b,v0.16b,v0.16b
orr v3.16b,v1.16b,v1.16b
orr v19.16b,v18.16b,v18.16b
.Loop3x_cbc_dec:
aesd v0.16b,v16.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aesd v0.16b,v17.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt .Loop3x_cbc_dec
aesd v0.16b,v16.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
eor v4.16b,v6.16b,v7.16b
subs x2,x2,#0x30
eor v5.16b,v2.16b,v7.16b
csel x6,x2,x6,lo // x6, w6, is zero at this point
aesd v0.16b,v17.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
eor v17.16b,v3.16b,v7.16b
add x0,x0,x6 // x0 is adjusted in such way that
// at exit from the loop v1.16b-v18.16b
// are loaded with last "words"
orr v6.16b,v19.16b,v19.16b
mov x7,x3
aesd v0.16b,v20.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v20.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v20.16b
aesimc v18.16b,v18.16b
ld1 {v2.16b},[x0],#16
aesd v0.16b,v21.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v21.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v21.16b
aesimc v18.16b,v18.16b
ld1 {v3.16b},[x0],#16
aesd v0.16b,v22.16b
aesimc v0.16b,v0.16b
aesd v1.16b,v22.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v22.16b
aesimc v18.16b,v18.16b
ld1 {v19.16b},[x0],#16
aesd v0.16b,v23.16b
aesd v1.16b,v23.16b
aesd v18.16b,v23.16b
ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0]
add w6,w5,#2
eor v4.16b,v4.16b,v0.16b
eor v5.16b,v5.16b,v1.16b
eor v18.16b,v18.16b,v17.16b
ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1]
st1 {v4.16b},[x1],#16
orr v0.16b,v2.16b,v2.16b
st1 {v5.16b},[x1],#16
orr v1.16b,v3.16b,v3.16b
st1 {v18.16b},[x1],#16
orr v18.16b,v19.16b,v19.16b
b.hs .Loop3x_cbc_dec
cmn x2,#0x30
b.eq .Lcbc_done
nop
.Lcbc_dec_tail:
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt .Lcbc_dec_tail
aesd v1.16b,v16.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v16.16b
aesimc v18.16b,v18.16b
aesd v1.16b,v17.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v17.16b
aesimc v18.16b,v18.16b
aesd v1.16b,v20.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v20.16b
aesimc v18.16b,v18.16b
cmn x2,#0x20
aesd v1.16b,v21.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v21.16b
aesimc v18.16b,v18.16b
eor v5.16b,v6.16b,v7.16b
aesd v1.16b,v22.16b
aesimc v1.16b,v1.16b
aesd v18.16b,v22.16b
aesimc v18.16b,v18.16b
eor v17.16b,v3.16b,v7.16b
aesd v1.16b,v23.16b
aesd v18.16b,v23.16b
b.eq .Lcbc_dec_one
eor v5.16b,v5.16b,v1.16b
eor v17.16b,v17.16b,v18.16b
orr v6.16b,v19.16b,v19.16b
st1 {v5.16b},[x1],#16
st1 {v17.16b},[x1],#16
b .Lcbc_done
.Lcbc_dec_one:
eor v5.16b,v5.16b,v18.16b
orr v6.16b,v19.16b,v19.16b
st1 {v5.16b},[x1],#16
.Lcbc_done:
st1 {v6.16b},[x4]
.Lcbc_abort:
ldr x29,[sp],#16
ret
.size aes_hw_cbc_encrypt,.-aes_hw_cbc_encrypt
.globl aes_hw_ctr32_encrypt_blocks
.hidden aes_hw_ctr32_encrypt_blocks
.type aes_hw_ctr32_encrypt_blocks,%function
.align 5
aes_hw_ctr32_encrypt_blocks:
// Armv8.3-A PAuth: even though x30 is pushed to stack it is not popped later.
AARCH64_VALID_CALL_TARGET
stp x29,x30,[sp,#-16]!
add x29,sp,#0
ldr w5,[x3,#240]
ldr w8, [x4, #12]
ld1 {v0.4s},[x4]
ld1 {v16.4s,v17.4s},[x3] // load key schedule...
sub w5,w5,#4
mov x12,#16
cmp x2,#2
add x7,x3,x5,lsl#4 // pointer to last 5 round keys
sub w5,w5,#2
ld1 {v20.4s,v21.4s},[x7],#32
ld1 {v22.4s,v23.4s},[x7],#32
ld1 {v7.4s},[x7]
add x7,x3,#32
mov w6,w5
csel x12,xzr,x12,lo
#ifndef __ARMEB__
rev w8, w8
#endif
orr v1.16b,v0.16b,v0.16b
add w10, w8, #1
orr v18.16b,v0.16b,v0.16b
add w8, w8, #2
orr v6.16b,v0.16b,v0.16b
rev w10, w10
mov v1.s[3],w10
b.ls .Lctr32_tail
rev w12, w8
sub x2,x2,#3 // bias
mov v18.s[3],w12
b .Loop3x_ctr32
.align 4
.Loop3x_ctr32:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
aese v18.16b,v16.16b
aesmc v18.16b,v18.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
aese v18.16b,v17.16b
aesmc v18.16b,v18.16b
ld1 {v17.4s},[x7],#16
b.gt .Loop3x_ctr32
aese v0.16b,v16.16b
aesmc v4.16b,v0.16b
aese v1.16b,v16.16b
aesmc v5.16b,v1.16b
ld1 {v2.16b},[x0],#16
orr v0.16b,v6.16b,v6.16b
aese v18.16b,v16.16b
aesmc v18.16b,v18.16b
ld1 {v3.16b},[x0],#16
orr v1.16b,v6.16b,v6.16b
aese v4.16b,v17.16b
aesmc v4.16b,v4.16b
aese v5.16b,v17.16b
aesmc v5.16b,v5.16b
ld1 {v19.16b},[x0],#16
mov x7,x3
aese v18.16b,v17.16b
aesmc v17.16b,v18.16b
orr v18.16b,v6.16b,v6.16b
add w9,w8,#1
aese v4.16b,v20.16b
aesmc v4.16b,v4.16b
aese v5.16b,v20.16b
aesmc v5.16b,v5.16b
eor v2.16b,v2.16b,v7.16b
add w10,w8,#2
aese v17.16b,v20.16b
aesmc v17.16b,v17.16b
eor v3.16b,v3.16b,v7.16b
add w8,w8,#3
aese v4.16b,v21.16b
aesmc v4.16b,v4.16b
aese v5.16b,v21.16b
aesmc v5.16b,v5.16b
eor v19.16b,v19.16b,v7.16b
rev w9,w9
aese v17.16b,v21.16b
aesmc v17.16b,v17.16b
mov v0.s[3], w9
rev w10,w10
aese v4.16b,v22.16b
aesmc v4.16b,v4.16b
aese v5.16b,v22.16b
aesmc v5.16b,v5.16b
mov v1.s[3], w10
rev w12,w8
aese v17.16b,v22.16b
aesmc v17.16b,v17.16b
mov v18.s[3], w12
subs x2,x2,#3
aese v4.16b,v23.16b
aese v5.16b,v23.16b
aese v17.16b,v23.16b
eor v2.16b,v2.16b,v4.16b
ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0]
st1 {v2.16b},[x1],#16
eor v3.16b,v3.16b,v5.16b
mov w6,w5
st1 {v3.16b},[x1],#16
eor v19.16b,v19.16b,v17.16b
ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1]
st1 {v19.16b},[x1],#16
b.hs .Loop3x_ctr32
adds x2,x2,#3
b.eq .Lctr32_done
cmp x2,#1
mov x12,#16
csel x12,xzr,x12,eq
.Lctr32_tail:
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
ld1 {v16.4s},[x7],#16
subs w6,w6,#2
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
ld1 {v17.4s},[x7],#16
b.gt .Lctr32_tail
aese v0.16b,v16.16b
aesmc v0.16b,v0.16b
aese v1.16b,v16.16b
aesmc v1.16b,v1.16b
aese v0.16b,v17.16b
aesmc v0.16b,v0.16b
aese v1.16b,v17.16b
aesmc v1.16b,v1.16b
ld1 {v2.16b},[x0],x12
aese v0.16b,v20.16b
aesmc v0.16b,v0.16b
aese v1.16b,v20.16b
aesmc v1.16b,v1.16b
ld1 {v3.16b},[x0]
aese v0.16b,v21.16b
aesmc v0.16b,v0.16b
aese v1.16b,v21.16b
aesmc v1.16b,v1.16b
eor v2.16b,v2.16b,v7.16b
aese v0.16b,v22.16b
aesmc v0.16b,v0.16b
aese v1.16b,v22.16b
aesmc v1.16b,v1.16b
eor v3.16b,v3.16b,v7.16b
aese v0.16b,v23.16b
aese v1.16b,v23.16b
cmp x2,#1
eor v2.16b,v2.16b,v0.16b
eor v3.16b,v3.16b,v1.16b
st1 {v2.16b},[x1],#16
b.eq .Lctr32_done
st1 {v3.16b},[x1]
.Lctr32_done:
ldr x29,[sp],#16
ret
.size aes_hw_ctr32_encrypt_blocks,.-aes_hw_ctr32_encrypt_blocks
#endif
#endif
#endif // !OPENSSL_NO_ASM
.section .note.GNU-stack,"",%progbits

1436
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/armv8-mont.S
View File

File diff suppressed because it is too large Load Diff

346
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/ghash-neon-armv8.S
View File

@ -1,346 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(__aarch64__)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.globl gcm_init_neon
.hidden gcm_init_neon
.type gcm_init_neon,%function
.align 4
gcm_init_neon:
AARCH64_VALID_CALL_TARGET
// This function is adapted from gcm_init_v8. xC2 is t3.
ld1 {v17.2d}, [x1] // load H
movi v19.16b, #0xe1
shl v19.2d, v19.2d, #57 // 0xc2.0
ext v3.16b, v17.16b, v17.16b, #8
ushr v18.2d, v19.2d, #63
dup v17.4s, v17.s[1]
ext v16.16b, v18.16b, v19.16b, #8 // t0=0xc2....01
ushr v18.2d, v3.2d, #63
sshr v17.4s, v17.4s, #31 // broadcast carry bit
and v18.16b, v18.16b, v16.16b
shl v3.2d, v3.2d, #1
ext v18.16b, v18.16b, v18.16b, #8
and v16.16b, v16.16b, v17.16b
orr v3.16b, v3.16b, v18.16b // H<<<=1
eor v5.16b, v3.16b, v16.16b // twisted H
st1 {v5.2d}, [x0] // store Htable[0]
ret
.size gcm_init_neon,.-gcm_init_neon
.globl gcm_gmult_neon
.hidden gcm_gmult_neon
.type gcm_gmult_neon,%function
.align 4
gcm_gmult_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v3.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]
adrp x9, .Lmasks // load constants
add x9, x9, :lo12:.Lmasks
ld1 {v24.2d, v25.2d}, [x9]
rev64 v3.16b, v3.16b // byteswap Xi
ext v3.16b, v3.16b, v3.16b, #8
eor v7.8b, v5.8b, v6.8b // Karatsuba pre-processing
mov x3, #16
b .Lgmult_neon
.size gcm_gmult_neon,.-gcm_gmult_neon
.globl gcm_ghash_neon
.hidden gcm_ghash_neon
.type gcm_ghash_neon,%function
.align 4
gcm_ghash_neon:
AARCH64_VALID_CALL_TARGET
ld1 {v0.16b}, [x0] // load Xi
ld1 {v5.1d}, [x1], #8 // load twisted H
ld1 {v6.1d}, [x1]
adrp x9, .Lmasks // load constants
add x9, x9, :lo12:.Lmasks
ld1 {v24.2d, v25.2d}, [x9]
rev64 v0.16b, v0.16b // byteswap Xi
ext v0.16b, v0.16b, v0.16b, #8
eor v7.8b, v5.8b, v6.8b // Karatsuba pre-processing
.Loop_neon:
ld1 {v3.16b}, [x2], #16 // load inp
rev64 v3.16b, v3.16b // byteswap inp
ext v3.16b, v3.16b, v3.16b, #8
eor v3.16b, v3.16b, v0.16b // inp ^= Xi
.Lgmult_neon:
// Split the input into v3 and v4. (The upper halves are unused,
// so it is okay to leave them alone.)
ins v4.d[0], v3.d[1]
ext v16.8b, v5.8b, v5.8b, #1 // A1
pmull v16.8h, v16.8b, v3.8b // F = A1*B
ext v0.8b, v3.8b, v3.8b, #1 // B1
pmull v0.8h, v5.8b, v0.8b // E = A*B1
ext v17.8b, v5.8b, v5.8b, #2 // A2
pmull v17.8h, v17.8b, v3.8b // H = A2*B
ext v19.8b, v3.8b, v3.8b, #2 // B2
pmull v19.8h, v5.8b, v19.8b // G = A*B2
ext v18.8b, v5.8b, v5.8b, #3 // A3
eor v16.16b, v16.16b, v0.16b // L = E + F
pmull v18.8h, v18.8b, v3.8b // J = A3*B
ext v0.8b, v3.8b, v3.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v0.8h, v5.8b, v0.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v3.8b, v3.8b, #4 // B4
eor v18.16b, v18.16b, v0.16b // N = I + J
pmull v19.8h, v5.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v0.8h, v5.8b, v3.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v0.16b, v0.16b, v16.16b
eor v0.16b, v0.16b, v18.16b
eor v3.8b, v3.8b, v4.8b // Karatsuba pre-processing
ext v16.8b, v7.8b, v7.8b, #1 // A1
pmull v16.8h, v16.8b, v3.8b // F = A1*B
ext v1.8b, v3.8b, v3.8b, #1 // B1
pmull v1.8h, v7.8b, v1.8b // E = A*B1
ext v17.8b, v7.8b, v7.8b, #2 // A2
pmull v17.8h, v17.8b, v3.8b // H = A2*B
ext v19.8b, v3.8b, v3.8b, #2 // B2
pmull v19.8h, v7.8b, v19.8b // G = A*B2
ext v18.8b, v7.8b, v7.8b, #3 // A3
eor v16.16b, v16.16b, v1.16b // L = E + F
pmull v18.8h, v18.8b, v3.8b // J = A3*B
ext v1.8b, v3.8b, v3.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v1.8h, v7.8b, v1.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v3.8b, v3.8b, #4 // B4
eor v18.16b, v18.16b, v1.16b // N = I + J
pmull v19.8h, v7.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v1.8h, v7.8b, v3.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v1.16b, v1.16b, v16.16b
eor v1.16b, v1.16b, v18.16b
ext v16.8b, v6.8b, v6.8b, #1 // A1
pmull v16.8h, v16.8b, v4.8b // F = A1*B
ext v2.8b, v4.8b, v4.8b, #1 // B1
pmull v2.8h, v6.8b, v2.8b // E = A*B1
ext v17.8b, v6.8b, v6.8b, #2 // A2
pmull v17.8h, v17.8b, v4.8b // H = A2*B
ext v19.8b, v4.8b, v4.8b, #2 // B2
pmull v19.8h, v6.8b, v19.8b // G = A*B2
ext v18.8b, v6.8b, v6.8b, #3 // A3
eor v16.16b, v16.16b, v2.16b // L = E + F
pmull v18.8h, v18.8b, v4.8b // J = A3*B
ext v2.8b, v4.8b, v4.8b, #3 // B3
eor v17.16b, v17.16b, v19.16b // M = G + H
pmull v2.8h, v6.8b, v2.8b // I = A*B3
// Here we diverge from the 32-bit version. It computes the following
// (instructions reordered for clarity):
//
// veor $t0#lo, $t0#lo, $t0#hi @ t0 = P0 + P1 (L)
// vand $t0#hi, $t0#hi, $k48
// veor $t0#lo, $t0#lo, $t0#hi
//
// veor $t1#lo, $t1#lo, $t1#hi @ t1 = P2 + P3 (M)
// vand $t1#hi, $t1#hi, $k32
// veor $t1#lo, $t1#lo, $t1#hi
//
// veor $t2#lo, $t2#lo, $t2#hi @ t2 = P4 + P5 (N)
// vand $t2#hi, $t2#hi, $k16
// veor $t2#lo, $t2#lo, $t2#hi
//
// veor $t3#lo, $t3#lo, $t3#hi @ t3 = P6 + P7 (K)
// vmov.i64 $t3#hi, #0
//
// $kN is a mask with the bottom N bits set. AArch64 cannot compute on
// upper halves of SIMD registers, so we must split each half into
// separate registers. To compensate, we pair computations up and
// parallelize.
ext v19.8b, v4.8b, v4.8b, #4 // B4
eor v18.16b, v18.16b, v2.16b // N = I + J
pmull v19.8h, v6.8b, v19.8b // K = A*B4
// This can probably be scheduled more efficiently. For now, we just
// pair up independent instructions.
zip1 v20.2d, v16.2d, v17.2d
zip1 v22.2d, v18.2d, v19.2d
zip2 v21.2d, v16.2d, v17.2d
zip2 v23.2d, v18.2d, v19.2d
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
and v21.16b, v21.16b, v24.16b
and v23.16b, v23.16b, v25.16b
eor v20.16b, v20.16b, v21.16b
eor v22.16b, v22.16b, v23.16b
zip1 v16.2d, v20.2d, v21.2d
zip1 v18.2d, v22.2d, v23.2d
zip2 v17.2d, v20.2d, v21.2d
zip2 v19.2d, v22.2d, v23.2d
ext v16.16b, v16.16b, v16.16b, #15 // t0 = t0 << 8
ext v17.16b, v17.16b, v17.16b, #14 // t1 = t1 << 16
pmull v2.8h, v6.8b, v4.8b // D = A*B
ext v19.16b, v19.16b, v19.16b, #12 // t3 = t3 << 32
ext v18.16b, v18.16b, v18.16b, #13 // t2 = t2 << 24
eor v16.16b, v16.16b, v17.16b
eor v18.16b, v18.16b, v19.16b
eor v2.16b, v2.16b, v16.16b
eor v2.16b, v2.16b, v18.16b
ext v16.16b, v0.16b, v2.16b, #8
eor v1.16b, v1.16b, v0.16b // Karatsuba post-processing
eor v1.16b, v1.16b, v2.16b
eor v1.16b, v1.16b, v16.16b // Xm overlaps Xh.lo and Xl.hi
ins v0.d[1], v1.d[0] // Xh|Xl - 256-bit result
// This is a no-op due to the ins instruction below.
// ins v2.d[0], v1.d[1]
// equivalent of reduction_avx from ghash-x86_64.pl
shl v17.2d, v0.2d, #57 // 1st phase
shl v18.2d, v0.2d, #62
eor v18.16b, v18.16b, v17.16b //
shl v17.2d, v0.2d, #63
eor v18.16b, v18.16b, v17.16b //
// Note Xm contains {Xl.d[1], Xh.d[0]}.
eor v18.16b, v18.16b, v1.16b
ins v0.d[1], v18.d[0] // Xl.d[1] ^= t2.d[0]
ins v2.d[0], v18.d[1] // Xh.d[0] ^= t2.d[1]
ushr v18.2d, v0.2d, #1 // 2nd phase
eor v2.16b, v2.16b,v0.16b
eor v0.16b, v0.16b,v18.16b //
ushr v18.2d, v18.2d, #6
ushr v0.2d, v0.2d, #1 //
eor v0.16b, v0.16b, v2.16b //
eor v0.16b, v0.16b, v18.16b //
subs x3, x3, #16
bne .Loop_neon
rev64 v0.16b, v0.16b // byteswap Xi and write
ext v0.16b, v0.16b, v0.16b, #8
st1 {v0.16b}, [x0]
ret
.size gcm_ghash_neon,.-gcm_ghash_neon
.section .rodata
.align 4
.Lmasks:
.quad 0x0000ffffffffffff // k48
.quad 0x00000000ffffffff // k32
.quad 0x000000000000ffff // k16
.quad 0x0000000000000000 // k0
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,100,101,114,105,118,101,100,32,102,114,111,109,32,65,82,77,118,52,32,118,101,114,115,105,111,110,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif
#endif // !OPENSSL_NO_ASM
.section .note.GNU-stack,"",%progbits

252
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/ghashv8-armx64.S
View File

@ -1,252 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(__aarch64__)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
.arch armv8-a+crypto
.globl gcm_init_v8
.hidden gcm_init_v8
.type gcm_init_v8,%function
.align 4
gcm_init_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x1] //load input H
movi v19.16b,#0xe1
shl v19.2d,v19.2d,#57 //0xc2.0
ext v3.16b,v17.16b,v17.16b,#8
ushr v18.2d,v19.2d,#63
dup v17.4s,v17.s[1]
ext v16.16b,v18.16b,v19.16b,#8 //t0=0xc2....01
ushr v18.2d,v3.2d,#63
sshr v17.4s,v17.4s,#31 //broadcast carry bit
and v18.16b,v18.16b,v16.16b
shl v3.2d,v3.2d,#1
ext v18.16b,v18.16b,v18.16b,#8
and v16.16b,v16.16b,v17.16b
orr v3.16b,v3.16b,v18.16b //H<<<=1
eor v20.16b,v3.16b,v16.16b //twisted H
st1 {v20.2d},[x0],#16 //store Htable[0]
//calculate H^2
ext v16.16b,v20.16b,v20.16b,#8 //Karatsuba pre-processing
pmull v0.1q,v20.1d,v20.1d
eor v16.16b,v16.16b,v20.16b
pmull2 v2.1q,v20.2d,v20.2d
pmull v1.1q,v16.1d,v16.1d
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v22.16b,v0.16b,v18.16b
ext v17.16b,v22.16b,v22.16b,#8 //Karatsuba pre-processing
eor v17.16b,v17.16b,v22.16b
ext v21.16b,v16.16b,v17.16b,#8 //pack Karatsuba pre-processed
st1 {v21.2d,v22.2d},[x0] //store Htable[1..2]
ret
.size gcm_init_v8,.-gcm_init_v8
.globl gcm_gmult_v8
.hidden gcm_gmult_v8
.type gcm_gmult_v8,%function
.align 4
gcm_gmult_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v17.2d},[x0] //load Xi
movi v19.16b,#0xe1
ld1 {v20.2d,v21.2d},[x1] //load twisted H, ...
shl v19.2d,v19.2d,#57
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ext v3.16b,v17.16b,v17.16b,#8
pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo
eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi
pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi)
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
st1 {v0.2d},[x0] //write out Xi
ret
.size gcm_gmult_v8,.-gcm_gmult_v8
.globl gcm_ghash_v8
.hidden gcm_ghash_v8
.type gcm_ghash_v8,%function
.align 4
gcm_ghash_v8:
AARCH64_VALID_CALL_TARGET
ld1 {v0.2d},[x0] //load [rotated] Xi
//"[rotated]" means that
//loaded value would have
//to be rotated in order to
//make it appear as in
//algorithm specification
subs x3,x3,#32 //see if x3 is 32 or larger
mov x12,#16 //x12 is used as post-
//increment for input pointer;
//as loop is modulo-scheduled
//x12 is zeroed just in time
//to preclude overstepping
//inp[len], which means that
//last block[s] are actually
//loaded twice, but last
//copy is not processed
ld1 {v20.2d,v21.2d},[x1],#32 //load twisted H, ..., H^2
movi v19.16b,#0xe1
ld1 {v22.2d},[x1]
csel x12,xzr,x12,eq //is it time to zero x12?
ext v0.16b,v0.16b,v0.16b,#8 //rotate Xi
ld1 {v16.2d},[x2],#16 //load [rotated] I[0]
shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant
#ifndef __ARMEB__
rev64 v16.16b,v16.16b
rev64 v0.16b,v0.16b
#endif
ext v3.16b,v16.16b,v16.16b,#8 //rotate I[0]
b.lo .Lodd_tail_v8 //x3 was less than 32
ld1 {v17.2d},[x2],x12 //load [rotated] I[1]
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ext v7.16b,v17.16b,v17.16b,#8
eor v3.16b,v3.16b,v0.16b //I[i]^=Xi
pmull v4.1q,v20.1d,v7.1d //H·Ii+1
eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing
pmull2 v6.1q,v20.2d,v7.2d
b .Loop_mod2x_v8
.align 4
.Loop_mod2x_v8:
ext v18.16b,v3.16b,v3.16b,#8
subs x3,x3,#32 //is there more data?
pmull v0.1q,v22.1d,v3.1d //H^2.lo·Xi.lo
csel x12,xzr,x12,lo //is it time to zero x12?
pmull v5.1q,v21.1d,v17.1d
eor v18.16b,v18.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v22.2d,v3.2d //H^2.hi·Xi.hi
eor v0.16b,v0.16b,v4.16b //accumulate
pmull2 v1.1q,v21.2d,v18.2d //(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
ld1 {v16.2d},[x2],x12 //load [rotated] I[i+2]
eor v2.16b,v2.16b,v6.16b
csel x12,xzr,x12,eq //is it time to zero x12?
eor v1.16b,v1.16b,v5.16b
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
ld1 {v17.2d},[x2],x12 //load [rotated] I[i+3]
#ifndef __ARMEB__
rev64 v16.16b,v16.16b
#endif
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
#ifndef __ARMEB__
rev64 v17.16b,v17.16b
#endif
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
ext v7.16b,v17.16b,v17.16b,#8
ext v3.16b,v16.16b,v16.16b,#8
eor v0.16b,v1.16b,v18.16b
pmull v4.1q,v20.1d,v7.1d //H·Ii+1
eor v3.16b,v3.16b,v2.16b //accumulate v3.16b early
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v3.16b,v3.16b,v18.16b
eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing
eor v3.16b,v3.16b,v0.16b
pmull2 v6.1q,v20.2d,v7.2d
b.hs .Loop_mod2x_v8 //there was at least 32 more bytes
eor v2.16b,v2.16b,v18.16b
ext v3.16b,v16.16b,v16.16b,#8 //re-construct v3.16b
adds x3,x3,#32 //re-construct x3
eor v0.16b,v0.16b,v2.16b //re-construct v0.16b
b.eq .Ldone_v8 //is x3 zero?
.Lodd_tail_v8:
ext v18.16b,v0.16b,v0.16b,#8
eor v3.16b,v3.16b,v0.16b //inp^=Xi
eor v17.16b,v16.16b,v18.16b //v17.16b is rotated inp^Xi
pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo
eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing
pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi
pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi)
ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing
eor v18.16b,v0.16b,v2.16b
eor v1.16b,v1.16b,v17.16b
eor v1.16b,v1.16b,v18.16b
pmull v18.1q,v0.1d,v19.1d //1st phase of reduction
ins v2.d[0],v1.d[1]
ins v1.d[1],v0.d[0]
eor v0.16b,v1.16b,v18.16b
ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction
pmull v0.1q,v0.1d,v19.1d
eor v18.16b,v18.16b,v2.16b
eor v0.16b,v0.16b,v18.16b
.Ldone_v8:
#ifndef __ARMEB__
rev64 v0.16b,v0.16b
#endif
ext v0.16b,v0.16b,v0.16b,#8
st1 {v0.2d},[x0] //write out Xi
ret
.size gcm_ghash_v8,.-gcm_ghash_v8
.byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
.align 2
.align 2
#endif
#endif // !OPENSSL_NO_ASM
.section .note.GNU-stack,"",%progbits

1239
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/sha1-armv8.S
View File

File diff suppressed because it is too large Load Diff

1217
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/sha256-armv8.S
View File

File diff suppressed because it is too large Load Diff

1087
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/sha512-armv8.S
View File

File diff suppressed because it is too large Load Diff

1235
contrib/boringssl-cmake/linux-aarch64/crypto/fipsmodule/vpaes-armv8.S
View File

File diff suppressed because it is too large Load Diff

761
contrib/boringssl-cmake/linux-aarch64/crypto/test/trampoline-armv8.S
View File

@ -1,761 +0,0 @@
// This file is generated from a similarly-named Perl script in the BoringSSL
// source tree. Do not edit by hand.
#if !defined(__has_feature)
#define __has_feature(x) 0
#endif
#if __has_feature(memory_sanitizer) && !defined(OPENSSL_NO_ASM)
#define OPENSSL_NO_ASM
#endif
#if !defined(OPENSSL_NO_ASM)
#if defined(__aarch64__)
#if defined(BORINGSSL_PREFIX)
#include <boringssl_prefix_symbols_asm.h>
#endif
#include <openssl/arm_arch.h>
.text
// abi_test_trampoline loads callee-saved registers from |state|, calls |func|
// with |argv|, then saves the callee-saved registers into |state|. It returns
// the result of |func|. The |unwind| argument is unused.
// uint64_t abi_test_trampoline(void (*func)(...), CallerState *state,
// const uint64_t *argv, size_t argc,
// uint64_t unwind);
.type abi_test_trampoline, %function
.globl abi_test_trampoline
.hidden abi_test_trampoline
.align 4
abi_test_trampoline:
.Labi_test_trampoline_begin:
AARCH64_SIGN_LINK_REGISTER
// Stack layout (low to high addresses)
// x29,x30 (16 bytes)
// d8-d15 (64 bytes)
// x19-x28 (80 bytes)
// x1 (8 bytes)
// padding (8 bytes)
stp x29, x30, [sp, #-176]!
mov x29, sp
// Saved callee-saved registers and |state|.
stp d8, d9, [sp, #16]
stp d10, d11, [sp, #32]
stp d12, d13, [sp, #48]
stp d14, d15, [sp, #64]
stp x19, x20, [sp, #80]
stp x21, x22, [sp, #96]
stp x23, x24, [sp, #112]
stp x25, x26, [sp, #128]
stp x27, x28, [sp, #144]
str x1, [sp, #160]
// Load registers from |state|, with the exception of x29. x29 is the
// frame pointer and also callee-saved, but AAPCS64 allows platforms to
// mandate that x29 always point to a frame. iOS64 does so, which means
// we cannot fill x29 with entropy without violating ABI rules
// ourselves. x29 is tested separately below.
ldp d8, d9, [x1], #16
ldp d10, d11, [x1], #16
ldp d12, d13, [x1], #16
ldp d14, d15, [x1], #16
ldp x19, x20, [x1], #16
ldp x21, x22, [x1], #16
ldp x23, x24, [x1], #16
ldp x25, x26, [x1], #16
ldp x27, x28, [x1], #16
// Move parameters into temporary registers.
mov x9, x0
mov x10, x2
mov x11, x3
// Load parameters into registers.
cbz x11, .Largs_done
ldr x0, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x1, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x2, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x3, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x4, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x5, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x6, [x10], #8
subs x11, x11, #1
b.eq .Largs_done
ldr x7, [x10], #8
.Largs_done:
blr x9
// Reload |state| and store registers.
ldr x1, [sp, #160]
stp d8, d9, [x1], #16
stp d10, d11, [x1], #16
stp d12, d13, [x1], #16
stp d14, d15, [x1], #16
stp x19, x20, [x1], #16
stp x21, x22, [x1], #16
stp x23, x24, [x1], #16
stp x25, x26, [x1], #16
stp x27, x28, [x1], #16
// |func| is required to preserve x29, the frame pointer. We cannot load
// random values into x29 (see comment above), so compare it against the
// expected value and zero the field of |state| if corrupted.
mov x9, sp
cmp x29, x9
b.eq .Lx29_ok
str xzr, [x1]
.Lx29_ok:
// Restore callee-saved registers.
ldp d8, d9, [sp, #16]
ldp d10, d11, [sp, #32]
ldp d12, d13, [sp, #48]
ldp d14, d15, [sp, #64]
ldp x19, x20, [sp, #80]
ldp x21, x22, [sp, #96]
ldp x23, x24, [sp, #112]
ldp x25, x26, [sp, #128]
ldp x27, x28, [sp, #144]
ldp x29, x30, [sp], #176
AARCH64_VALIDATE_LINK_REGISTER
ret
.size abi_test_trampoline,.-abi_test_trampoline
.type abi_test_clobber_x0, %function
.globl abi_test_clobber_x0
.hidden abi_test_clobber_x0
.align 4
abi_test_clobber_x0:
AARCH64_VALID_CALL_TARGET
mov x0, xzr
ret
.size abi_test_clobber_x0,.-abi_test_clobber_x0
.type abi_test_clobber_x1, %function
.globl abi_test_clobber_x1
.hidden abi_test_clobber_x1
.align 4
abi_test_clobber_x1:
AARCH64_VALID_CALL_TARGET
mov x1, xzr
ret
.size abi_test_clobber_x1,.-abi_test_clobber_x1
.type abi_test_clobber_x2, %function
.globl abi_test_clobber_x2
.hidden abi_test_clobber_x2
.align 4
abi_test_clobber_x2:
AARCH64_VALID_CALL_TARGET
mov x2, xzr
ret
.size abi_test_clobber_x2,.-abi_test_clobber_x2
.type abi_test_clobber_x3, %function
.globl abi_test_clobber_x3
.hidden abi_test_clobber_x3
.align 4
abi_test_clobber_x3:
AARCH64_VALID_CALL_TARGET
mov x3, xzr
ret
.size abi_test_clobber_x3,.-abi_test_clobber_x3
.type abi_test_clobber_x4, %function
.globl abi_test_clobber_x4
.hidden abi_test_clobber_x4
.align 4
abi_test_clobber_x4:
AARCH64_VALID_CALL_TARGET
mov x4, xzr
ret
.size abi_test_clobber_x4,.-abi_test_clobber_x4
.type abi_test_clobber_x5, %function
.globl abi_test_clobber_x5
.hidden abi_test_clobber_x5
.align 4
abi_test_clobber_x5:
AARCH64_VALID_CALL_TARGET
mov x5, xzr
ret
.size abi_test_clobber_x5,.-abi_test_clobber_x5
.type abi_test_clobber_x6, %function
.globl abi_test_clobber_x6
.hidden abi_test_clobber_x6
.align 4
abi_test_clobber_x6:
AARCH64_VALID_CALL_TARGET
mov x6, xzr
ret
.size abi_test_clobber_x6,.-abi_test_clobber_x6
.type abi_test_clobber_x7, %function
.globl abi_test_clobber_x7
.hidden abi_test_clobber_x7
.align 4
abi_test_clobber_x7:
AARCH64_VALID_CALL_TARGET
mov x7, xzr
ret
.size abi_test_clobber_x7,.-abi_test_clobber_x7
.type abi_test_clobber_x8, %function
.globl abi_test_clobber_x8
.hidden abi_test_clobber_x8
.align 4
abi_test_clobber_x8:
AARCH64_VALID_CALL_TARGET
mov x8, xzr
ret
.size abi_test_clobber_x8,.-abi_test_clobber_x8
.type abi_test_clobber_x9, %function
.globl abi_test_clobber_x9
.hidden abi_test_clobber_x9
.align 4
abi_test_clobber_x9:
AARCH64_VALID_CALL_TARGET
mov x9, xzr
ret
.size abi_test_clobber_x9,.-abi_test_clobber_x9
.type abi_test_clobber_x10, %function
.globl abi_test_clobber_x10
.hidden abi_test_clobber_x10
.align 4
abi_test_clobber_x10:
AARCH64_VALID_CALL_TARGET
mov x10, xzr
ret
.size abi_test_clobber_x10,.-abi_test_clobber_x10
.type abi_test_clobber_x11, %function
.globl abi_test_clobber_x11
.hidden abi_test_clobber_x11
.align 4
abi_test_clobber_x11:
AARCH64_VALID_CALL_TARGET
mov x11, xzr
ret
.size abi_test_clobber_x11,.-abi_test_clobber_x11
.type abi_test_clobber_x12, %function
.globl abi_test_clobber_x12
.hidden abi_test_clobber_x12
.align 4
abi_test_clobber_x12:
AARCH64_VALID_CALL_TARGET
mov x12, xzr
ret
.size abi_test_clobber_x12,.-abi_test_clobber_x12
.type abi_test_clobber_x13, %function
.globl abi_test_clobber_x13
.hidden abi_test_clobber_x13
.align 4
abi_test_clobber_x13:
AARCH64_VALID_CALL_TARGET
mov x13, xzr
ret
.size abi_test_clobber_x13,.-abi_test_clobber_x13
.type abi_test_clobber_x14, %function
.globl abi_test_clobber_x14
.hidden abi_test_clobber_x14
.align 4
abi_test_clobber_x14:
AARCH64_VALID_CALL_TARGET
mov x14, xzr
ret
.size abi_test_clobber_x14,.-abi_test_clobber_x14
.type abi_test_clobber_x15, %function
.globl abi_test_clobber_x15
.hidden abi_test_clobber_x15
.align 4
abi_test_clobber_x15:
AARCH64_VALID_CALL_TARGET
mov x15, xzr
ret
.size abi_test_clobber_x15,.-abi_test_clobber_x15
.type abi_test_clobber_x16, %function
.globl abi_test_clobber_x16
.hidden abi_test_clobber_x16
.align 4
abi_test_clobber_x16:
AARCH64_VALID_CALL_TARGET
mov x16, xzr
ret
.size abi_test_clobber_x16,.-abi_test_clobber_x16
.type abi_test_clobber_x17, %function
.globl abi_test_clobber_x17
.hidden abi_test_clobber_x17
.align 4
abi_test_clobber_x17:
AARCH64_VALID_CALL_TARGET
mov x17, xzr
ret
.size abi_test_clobber_x17,.-abi_test_clobber_x17
.type abi_test_clobber_x19, %function
.globl abi_test_clobber_x19
.hidden abi_test_clobber_x19
.align 4
abi_test_clobber_x19:
AARCH64_VALID_CALL_TARGET
mov x19, xzr
ret
.size abi_test_clobber_x19,.-abi_test_clobber_x19
.type abi_test_clobber_x20, %function
.globl abi_test_clobber_x20
.hidden abi_test_clobber_x20
.align 4
abi_test_clobber_x20:
AARCH64_VALID_CALL_TARGET
mov x20, xzr
ret
.size abi_test_clobber_x20,.-abi_test_clobber_x20
.type abi_test_clobber_x21, %function
.globl abi_test_clobber_x21
.hidden abi_test_clobber_x21
.align 4
abi_test_clobber_x21:
AARCH64_VALID_CALL_TARGET
mov x21, xzr
ret
.size abi_test_clobber_x21,.-abi_test_clobber_x21
.type abi_test_clobber_x22, %function
.globl abi_test_clobber_x22
.hidden abi_test_clobber_x22
.align 4
abi_test_clobber_x22:
AARCH64_VALID_CALL_TARGET
mov x22, xzr
ret
.size abi_test_clobber_x22,.-abi_test_clobber_x22
.type abi_test_clobber_x23, %function
.globl abi_test_clobber_x23
.hidden abi_test_clobber_x23
.align 4
abi_test_clobber_x23:
AARCH64_VALID_CALL_TARGET
mov x23, xzr
ret
.size abi_test_clobber_x23,.-abi_test_clobber_x23
.type abi_test_clobber_x24, %function
.globl abi_test_clobber_x24
.hidden abi_test_clobber_x24
.align 4
abi_test_clobber_x24:
AARCH64_VALID_CALL_TARGET
mov x24, xzr
ret
.size abi_test_clobber_x24,.-abi_test_clobber_x24
.type abi_test_clobber_x25, %function
.globl abi_test_clobber_x25
.hidden abi_test_clobber_x25
.align 4
abi_test_clobber_x25:
AARCH64_VALID_CALL_TARGET
mov x25, xzr
ret
.size abi_test_clobber_x25,.-abi_test_clobber_x25
.type abi_test_clobber_x26, %function
.globl abi_test_clobber_x26
.hidden abi_test_clobber_x26
.align 4
abi_test_clobber_x26:
AARCH64_VALID_CALL_TARGET
mov x26, xzr
ret
.size abi_test_clobber_x26,.-abi_test_clobber_x26
.type abi_test_clobber_x27, %function
.globl abi_test_clobber_x27
.hidden abi_test_clobber_x27
.align 4
abi_test_clobber_x27:
AARCH64_VALID_CALL_TARGET
mov x27, xzr
ret
.size abi_test_clobber_x27,.-abi_test_clobber_x27
.type abi_test_clobber_x28, %function
.globl abi_test_clobber_x28
.hidden abi_test_clobber_x28
.align 4
abi_test_clobber_x28:
AARCH64_VALID_CALL_TARGET
mov x28, xzr
ret
.size abi_test_clobber_x28,.-abi_test_clobber_x28
.type abi_test_clobber_x29, %function
.globl abi_test_clobber_x29
.hidden abi_test_clobber_x29
.align 4
abi_test_clobber_x29:
AARCH64_VALID_CALL_TARGET
mov x29, xzr
ret
.size abi_test_clobber_x29,.-abi_test_clobber_x29
.type abi_test_clobber_d0, %function
.globl abi_test_clobber_d0
.hidden abi_test_clobber_d0
.align 4
abi_test_clobber_d0:
AARCH64_VALID_CALL_TARGET
fmov d0, xzr
ret
.size abi_test_clobber_d0,.-abi_test_clobber_d0
.type abi_test_clobber_d1, %function
.globl abi_test_clobber_d1
.hidden abi_test_clobber_d1
.align 4
abi_test_clobber_d1:
AARCH64_VALID_CALL_TARGET
fmov d1, xzr
ret
.size abi_test_clobber_d1,.-abi_test_clobber_d1
.type abi_test_clobber_d2, %function
.globl abi_test_clobber_d2
.hidden abi_test_clobber_d2
.align 4
abi_test_clobber_d2:
AARCH64_VALID_CALL_TARGET
fmov d2, xzr
ret
.size abi_test_clobber_d2,.-abi_test_clobber_d2
.type abi_test_clobber_d3, %function
.globl abi_test_clobber_d3
.hidden abi_test_clobber_d3
.align 4
abi_test_clobber_d3:
AARCH64_VALID_CALL_TARGET
fmov d3, xzr
ret
.size abi_test_clobber_d3,.-abi_test_clobber_d3
.type abi_test_clobber_d4, %function
.globl abi_test_clobber_d4
.hidden abi_test_clobber_d4
.align 4
abi_test_clobber_d4:
AARCH64_VALID_CALL_TARGET
fmov d4, xzr
ret
.size abi_test_clobber_d4,.-abi_test_clobber_d4
.type abi_test_clobber_d5, %function
.globl abi_test_clobber_d5
.hidden abi_test_clobber_d5
.align 4
abi_test_clobber_d5:
AARCH64_VALID_CALL_TARGET
fmov d5, xzr
ret
.size abi_test_clobber_d5,.-abi_test_clobber_d5
.type abi_test_clobber_d6, %function
.globl abi_test_clobber_d6
.hidden abi_test_clobber_d6
.align 4
abi_test_clobber_d6:
AARCH64_VALID_CALL_TARGET
fmov d6, xzr
ret
.size abi_test_clobber_d6,.-abi_test_clobber_d6
.type abi_test_clobber_d7, %function
.globl abi_test_clobber_d7
.hidden abi_test_clobber_d7
.align 4
abi_test_clobber_d7:
AARCH64_VALID_CALL_TARGET
fmov d7, xzr
ret
.size abi_test_clobber_d7,.-abi_test_clobber_d7
.type abi_test_clobber_d8, %function
.globl abi_test_clobber_d8
.hidden abi_test_clobber_d8
.align 4
abi_test_clobber_d8:
AARCH64_VALID_CALL_TARGET
fmov d8, xzr
ret
.size abi_test_clobber_d8,.-abi_test_clobber_d8
.type abi_test_clobber_d9, %function
.globl abi_test_clobber_d9
.hidden abi_test_clobber_d9
.align 4
abi_test_clobber_d9:
AARCH64_VALID_CALL_TARGET
fmov d9, xzr
ret
.size abi_test_clobber_d9,.-abi_test_clobber_d9
.type abi_test_clobber_d10, %function
.globl abi_test_clobber_d10
.hidden abi_test_clobber_d10
.align 4
abi_test_clobber_d10:
AARCH64_VALID_CALL_TARGET
fmov d10, xzr
ret
.size abi_test_clobber_d10,.-abi_test_clobber_d10
.type abi_test_clobber_d11, %function
.globl abi_test_clobber_d11
.hidden abi_test_clobber_d11
.align 4
abi_test_clobber_d11:
AARCH64_VALID_CALL_TARGET
fmov d11, xzr
ret
.size abi_test_clobber_d11,.-abi_test_clobber_d11
.type abi_test_clobber_d12, %function
.globl abi_test_clobber_d12
.hidden abi_test_clobber_d12
.align 4
abi_test_clobber_d12:
AARCH64_VALID_CALL_TARGET
fmov d12, xzr
ret
.size abi_test_clobber_d12,.-abi_test_clobber_d12
.type abi_test_clobber_d13, %function
.globl abi_test_clobber_d13
.hidden abi_test_clobber_d13
.align 4
abi_test_clobber_d13:
AARCH64_VALID_CALL_TARGET
fmov d13, xzr
ret
.size abi_test_clobber_d13,.-abi_test_clobber_d13
.type abi_test_clobber_d14, %function
.globl abi_test_clobber_d14
.hidden abi_test_clobber_d14
.align 4
abi_test_clobber_d14:
AARCH64_VALID_CALL_TARGET
fmov d14, xzr
ret
.size abi_test_clobber_d14,.-abi_test_clobber_d14
.type abi_test_clobber_d15, %function
.globl abi_test_clobber_d15
.hidden abi_test_clobber_d15
.align 4
abi_test_clobber_d15:
AARCH64_VALID_CALL_TARGET
fmov d15, xzr
ret
.size abi_test_clobber_d15,.-abi_test_clobber_d15
.type abi_test_clobber_d16, %function
.globl abi_test_clobber_d16
.hidden abi_test_clobber_d16
.align 4
abi_test_clobber_d16:
AARCH64_VALID_CALL_TARGET
fmov d16, xzr
ret
.size abi_test_clobber_d16,.-abi_test_clobber_d16
.type abi_test_clobber_d17, %function
.globl abi_test_clobber_d17
.hidden abi_test_clobber_d17
.align 4
abi_test_clobber_d17:
AARCH64_VALID_CALL_TARGET
fmov d17, xzr
ret
.size abi_test_clobber_d17,.-abi_test_clobber_d17
.type abi_test_clobber_d18, %function
.globl abi_test_clobber_d18
.hidden abi_test_clobber_d18
.align 4
abi_test_clobber_d18:
AARCH64_VALID_CALL_TARGET
fmov d18, xzr
ret
.size abi_test_clobber_d18,.-abi_test_clobber_d18
.type abi_test_clobber_d19, %function
.globl abi_test_clobber_d19
.hidden abi_test_clobber_d19
.align 4
abi_test_clobber_d19:
AARCH64_VALID_CALL_TARGET
fmov d19, xzr
ret
.size abi_test_clobber_d19,.-abi_test_clobber_d19
.type abi_test_clobber_d20, %function
.globl abi_test_clobber_d20
.hidden abi_test_clobber_d20
.align 4
abi_test_clobber_d20:
AARCH64_VALID_CALL_TARGET
fmov d20, xzr
ret
.size abi_test_clobber_d20,.-abi_test_clobber_d20
.type abi_test_clobber_d21, %function
.globl abi_test_clobber_d21
.hidden abi_test_clobber_d21
.align 4
abi_test_clobber_d21:
AARCH64_VALID_CALL_TARGET
fmov d21, xzr
ret
.size abi_test_clobber_d21,.-abi_test_clobber_d21
.type abi_test_clobber_d22, %function
.globl abi_test_clobber_d22
.hidden abi_test_clobber_d22
.align 4
abi_test_clobber_d22:
AARCH64_VALID_CALL_TARGET
fmov d22, xzr
ret
.size abi_test_clobber_d22,.-abi_test_clobber_d22
.type abi_test_clobber_d23, %function
.globl abi_test_clobber_d23
.hidden abi_test_clobber_d23
.align 4
abi_test_clobber_d23:
AARCH64_VALID_CALL_TARGET
fmov d23, xzr
ret
.size abi_test_clobber_d23,.-abi_test_clobber_d23
.type abi_test_clobber_d24, %function
.globl abi_test_clobber_d24
.hidden abi_test_clobber_d24
.align 4
abi_test_clobber_d24:
AARCH64_VALID_CALL_TARGET
fmov d24, xzr
ret
.size abi_test_clobber_d24,.-abi_test_clobber_d24
.type abi_test_clobber_d25, %function
.globl abi_test_clobber_d25
.hidden abi_test_clobber_d25
.align 4
abi_test_clobber_d25:
AARCH64_VALID_CALL_TARGET
fmov d25, xzr
ret
.size abi_test_clobber_d25,.-abi_test_clobber_d25
.type abi_test_clobber_d26, %function
.globl abi_test_clobber_d26
.hidden abi_test_clobber_d26
.align 4
abi_test_clobber_d26:
AARCH64_VALID_CALL_TARGET
fmov d26, xzr
ret
.size abi_test_clobber_d26,.-abi_test_clobber_d26
.type abi_test_clobber_d27, %function
.globl abi_test_clobber_d27
.hidden abi_test_clobber_d27
.align 4
abi_test_clobber_d27:
AARCH64_VALID_CALL_TARGET
fmov d27, xzr
ret
.size abi_test_clobber_d27,.-abi_test_clobber_d27
.type abi_test_clobber_d28, %function
.globl abi_test_clobber_d28
.hidden abi_test_clobber_d28
.align 4
abi_test_clobber_d28:
AARCH64_VALID_CALL_TARGET
fmov d28, xzr
ret
.size abi_test_clobber_d28,.-abi_test_clobber_d28
.type abi_test_clobber_d29, %function
.globl abi_test_clobber_d29
.hidden abi_test_clobber_d29
.align 4
abi_test_clobber_d29:
AARCH64_VALID_CALL_TARGET
fmov d29, xzr
ret
.size abi_test_clobber_d29,.-abi_test_clobber_d29
.type abi_test_clobber_d30, %function
.globl abi_test_clobber_d30
.hidden abi_test_clobber_d30
.align 4
abi_test_clobber_d30:
AARCH64_VALID_CALL_TARGET
fmov d30, xzr
ret
.size abi_test_clobber_d30,.-abi_test_clobber_d30
.type abi_test_clobber_d31, %function
.globl abi_test_clobber_d31
.hidden abi_test_clobber_d31
.align 4
abi_test_clobber_d31:
AARCH64_VALID_CALL_TARGET
fmov d31, xzr
ret
.size abi_test_clobber_d31,.-abi_test_clobber_d31
.type abi_test_clobber_v8_upper, %function
.globl abi_test_clobber_v8_upper
.hidden abi_test_clobber_v8_upper
.align 4
abi_test_clobber_v8_upper:
AARCH64_VALID_CALL_TARGET
fmov v8.d[1], xzr
ret
.size abi_test_clobber_v8_upper,.-abi_test_clobber_v8_upper
.type abi_test_clobber_v9_upper, %function
.globl abi_test_clobber_v9_upper
.hidden abi_test_clobber_v9_upper
.align 4
abi_test_clobber_v9_upper:
AARCH64_VALID_CALL_TARGET
fmov v9.d[1], xzr
ret
.size abi_test_clobber_v9_upper,.-abi_test_clobber_v9_upper
.type abi_test_clobber_v10_upper, %function
.globl abi_test_clobber_v10_upper
.hidden abi_test_clobber_v10_upper
.align 4
abi_test_clobber_v10_upper:
AARCH64_VALID_CALL_TARGET
fmov v10.d[1], xzr
ret
.size abi_test_clobber_v10_upper,.-abi_test_clobber_v10_upper
.type abi_test_clobber_v11_upper, %function
.globl abi_test_clobber_v11_upper
.hidden abi_test_clobber_v11_upper
.align 4
abi_test_clobber_v11_upper:
AARCH64_VALID_CALL_TARGET
fmov v11.d[1], xzr
ret
.size abi_test_clobber_v11_upper,.-abi_test_clobber_v11_upper
.type abi_test_clobber_v12_upper, %function
.globl abi_test_clobber_v12_upper
.hidden abi_test_clobber_v12_upper
.align 4
abi_test_clobber_v12_upper:
AARCH64_VALID_CALL_TARGET
fmov v12.d[1], xzr
ret
.size abi_test_clobber_v12_upper,.-abi_test_clobber_v12_upper
.type abi_test_clobber_v13_upper, %function
.globl abi_test_clobber_v13_upper
.hidden abi_test_clobber_v13_upper
.align 4
abi_test_clobber_v13_upper:
AARCH64_VALID_CALL_TARGET
fmov v13.d[1], xzr
ret
.size abi_test_clobber_v13_upper,.-abi_test_clobber_v13_upper
.type abi_test_clobber_v14_upper, %function
.globl abi_test_clobber_v14_upper
.hidden abi_test_clobber_v14_upper
.align 4
abi_test_clobber_v14_upper:
AARCH64_VALID_CALL_TARGET
fmov v14.d[1], xzr
ret
.size abi_test_clobber_v14_upper,.-abi_test_clobber_v14_upper
.type abi_test_clobber_v15_upper, %function
.globl abi_test_clobber_v15_upper
.hidden abi_test_clobber_v15_upper
.align 4
abi_test_clobber_v15_upper:
AARCH64_VALID_CALL_TARGET
fmov v15.d[1], xzr
ret
.size abi_test_clobber_v15_upper,.-abi_test_clobber_v15_upper
#endif
#endif // !OPENSSL_NO_ASM
.section .note.GNU-stack,"",%progbits

Some files were not shown because too many files have changed in this diff Show More