#
d0891021 |
| 21-Nov-2023 |
Andrew Jones <andrew.jones@linux.dev> |
Merge branch 'arm/queue' into 'master'
arm/arm64: PMU test fixes and a micro-bench improvement
See merge request kvm-unit-tests/kvm-unit-tests!49
|
#
8074c5c2 |
| 16-Nov-2023 |
heqiong <heqiong1557@phytium.com.cn> |
arm64: microbench: Improve measurement accuracy of tests
Reducing the impact of the cntvct_el0 register and isb() operation on microbenchmark test results to improve testing accuracy and reduce late
arm64: microbench: Improve measurement accuracy of tests
Reducing the impact of the cntvct_el0 register and isb() operation on microbenchmark test results to improve testing accuracy and reduce latency in test results.
Signed-off-by: heqiong <heqiong1557@phytium.com.cn> Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com> Signed-off-by: Andrew Jones <andrew.jones@linux.dev>
show more ...
|
#
1ceee557 |
| 22-Sep-2023 |
Andrew Jones <andrew.jones@linux.dev> |
Merge branch 'arm/queue' into 'master'
arm64: microbench: Benchmark with virtual instead of physical timer
See merge request kvm-unit-tests/kvm-unit-tests!47
|
#
62546beb |
| 23-Aug-2023 |
Colton Lewis <coltonlewis@google.com> |
arm64: microbench: Benchmark with virtual instead of physical timer
Use the virtual instead of the physical timer for measuring the time taken to execute the microbenchmark.
Internal testing discov
arm64: microbench: Benchmark with virtual instead of physical timer
Use the virtual instead of the physical timer for measuring the time taken to execute the microbenchmark.
Internal testing discovered a performance regression on this test starting with Linux commit 680232a94c12 "KVM: arm64: timers: Allow save/restoring of the physical timer". Oliver Upton speculates QEMU is changing the guest physical counter to have a nonzero offset since it gained the ability as of that commit. As a consequence KVM is trap-and-emulating here on architectures without FEAT_ECV.
While this isn't a correctness issue, the trap-and-emulate overhead of physical counter emulation on systems without ECV leads to surprising microbenchmark results.
Signed-off-by: Colton Lewis <coltonlewis@google.com> Signed-off-by: Andrew Jones <andrew.jones@linux.dev>
show more ...
|
#
e526bc78 |
| 01-Jul-2023 |
Andrew Jones <andrew.jones@linux.dev> |
Merge branch 'arm/queue' into 'master'
arm/arm64: EFI support, arm64 backtrace support, PMU test improvements, and more
See merge request kvm-unit-tests/kvm-unit-tests!43
|
#
bb4c17e3 |
| 30-May-2023 |
Nikos Nikoleris <nikos.nikoleris@arm.com> |
arm64: Add support for timer initialization through ACPI
For systems with ACPI support, we can discover timers through the ACPI GTDT table. This change implements the code to discover timers through
arm64: Add support for timer initialization through ACPI
For systems with ACPI support, we can discover timers through the ACPI GTDT table. This change implements the code to discover timers through the GTDT and adds ACPI support in timer_save_state. This change retains the default behavior; we check if a valid DT is provided, if not, we try to discover timers using ACPI.
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Andrew Jones <andrew.jones@linux.dev>
show more ...
|
#
2fffb37e |
| 21-Mar-2023 |
Andrew Jones <andrew.jones@linux.dev> |
Merge branch 'arm/queue' into 'master'
arm cleanups
See merge request kvm-unit-tests/kvm-unit-tests!41
|
#
c1ba5b2e |
| 03-Mar-2023 |
Shaoqin Huang <shahuang@redhat.com> |
arm64: microbench: Use gic_enable_irq() macro in microbench test
Use gic_enable_irq() to clean up code.
Signed-off-by: Shaoqin Huang <shahuang@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat
arm64: microbench: Use gic_enable_irq() macro in microbench test
Use gic_enable_irq() to clean up code.
Signed-off-by: Shaoqin Huang <shahuang@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Zenghui Yu <yuzenghui@huawei.com> Signed-off-by: Andrew Jones <andrew.jones@linux.dev>
show more ...
|
#
07da5bc1 |
| 15-Mar-2022 |
Andrew Jones <drjones@redhat.com> |
Merge branch 'arm/queue' into 'master'
arm/queue: configure and run script improvements
See merge request kvm-unit-tests/kvm-unit-tests!27
|
#
7a84b7b2 |
| 11-Mar-2022 |
Thomas Huth <thuth@redhat.com> |
arm: Fix typos
Correct typos which were discovered with the "codespell" utility.
Signed-off-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com>
|
#
30595179 |
| 08-Oct-2021 |
Ricardo Koller <ricarkol@google.com> |
arm64: Add mmio_addr arg to arm/micro-bench
Add a command line arg to arm/micro-bench to set the mmio_addr to other values besides the default QEMU one. Default to the QEMU value if no arg is passed
arm64: Add mmio_addr arg to arm/micro-bench
Add a command line arg to arm/micro-bench to set the mmio_addr to other values besides the default QEMU one. Default to the QEMU value if no arg is passed.
Signed-off-by: Ricardo Koller <ricarkol@google.com> Message-Id: <20211008174022.3028983-1-ricarkol@google.com> Signed-off-by: Andrew Jones <drjones@redhat.com>
show more ...
|
#
74ff0e96 |
| 18-May-2021 |
Paolo Bonzini <bonzini@gnu.org> |
Merge branch 'arm/queue' into 'master'
arm/arm64: target-efi prep
This series mostly prepares kvm-unit-tests/arm for targeting EFI platforms. The actually EFI support will come in another series, b
Merge branch 'arm/queue' into 'master'
arm/arm64: target-efi prep
This series mostly prepares kvm-unit-tests/arm for targeting EFI platforms. The actually EFI support will come in another series, but these patches are good for removing assumptions from our memory maps and about our PSCI conduit, even if we never merge EFI support.
See merge request kvm-unit-tests/kvm-unit-tests!8
show more ...
|
#
0ee5bea5 |
| 13-May-2021 |
Andrew Jones <drjones@redhat.com> |
arm64: micro-bench: ioremap userspace_emulated_addr
We should explicitly ioremap the userspace emulated address used in the benchmark.
Reported-by: Alexandru Elisei <alexandru.elisei@arm.com> Revie
arm64: micro-bench: ioremap userspace_emulated_addr
We should explicitly ioremap the userspace emulated address used in the benchmark.
Reported-by: Alexandru Elisei <alexandru.elisei@arm.com> Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com> Tested-by: Alexandru Elisei <alexandru.elisei@arm.com> Signed-off-by: Andrew Jones <drjones@redhat.com>
show more ...
|
#
f583d924 |
| 30-Mar-2021 |
Paolo Bonzini <bonzini@gnu.org> |
Merge branch 'arm/queue' into 'master'
arm/arm64: Fixes, improvements, and prep for target-efi
See merge request kvm-unit-tests/kvm-unit-tests!6
|
#
f58a73af |
| 18-Dec-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: fix unexpected PPI
For the origin value of CNTV_CVAL_EL0 architecturally UNKNOWN, we may receive an unexpected PPI before we actual trigger the timer interrupt. So we should set A
arm64: microbench: fix unexpected PPI
For the origin value of CNTV_CVAL_EL0 architecturally UNKNOWN, we may receive an unexpected PPI before we actual trigger the timer interrupt. So we should set ARCH_TIMER_CTL_IMASK in timer_prep.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com>
show more ...
|
#
3a2b5f34 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Add timer_post() to get actual PPI latency
For we get the time duration of (10msec timer + injection latency) in timer_exec(), we substract the value of 10msec in timer_post() to
arm64: microbench: Add timer_post() to get actual PPI latency
For we get the time duration of (10msec timer + injection latency) in timer_exec(), we substract the value of 10msec in timer_post() to get the actual latency.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> [ Adapt to the modified post() interface. ] Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
6450d9d6 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Add test->post() to further process test results
Under certain circumstances, we need to further process microbench test results, so we add test->post() in the microbench framewor
arm64: microbench: Add test->post() to further process test results
Under certain circumstances, we need to further process microbench test results, so we add test->post() in the microbench framework, later patch will use that.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> [ Drop total_ns from post() input arguments. ] Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
4c77d77b |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Add vtimer latency test
Trigger PPIs by setting up a 10msec timer and test the latency.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> [ Replaced GICv3 assumption in timer_
arm64: microbench: Add vtimer latency test
Trigger PPIs by setting up a 10msec timer and test the latency.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> [ Replaced GICv3 assumption in timer_prep() with switch on gic_version() ] Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
174ddaa5 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Add time limit for each individual test
Besides using separate running times parameter, we add time limit for loop_test to make sure each test should be done in a certain time(5 s
arm64: microbench: Add time limit for each individual test
Besides using separate running times parameter, we add time limit for loop_test to make sure each test should be done in a certain time(5 sec here).
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> [ Initialize total_ns to zero. ] Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
b8d5a5b0 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Allow each test to specify its running times
For some test in micro-bench can be time consuming, we add a micro-bench test parameter to allow each individual test to specify its r
arm64: microbench: Allow each test to specify its running times
For some test in micro-bench can be time consuming, we add a micro-bench test parameter to allow each individual test to specify its running times.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
0c9afed1 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: its: Add LPI latency test
Triggers LPIs through the INT command and test the latency. Mostly inherited form commit 0ef02cd6cbaa(arm/arm64: ITS: INT functional tests).
Signed-off-
arm64: microbench: its: Add LPI latency test
Triggers LPIs through the INT command and test the latency. Mostly inherited form commit 0ef02cd6cbaa(arm/arm64: ITS: INT functional tests).
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
9c537510 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: gic: Add ipi latency test for gicv4.1 support kvm
If gicv4.1(sgi hardware injection) is supported in kvm, we test ipi injection via hw/sw way separately.
Signed-off-by: Jingyi Wa
arm64: microbench: gic: Add ipi latency test for gicv4.1 support kvm
If gicv4.1(sgi hardware injection) is supported in kvm, we test ipi injection via hw/sw way separately.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
7fc8ebfb |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Generalize ipi test names
Later patches will use these functions for gic(ipi/lpi/timer) tests.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.
arm64: microbench: Generalize ipi test names
Later patches will use these functions for gic(ipi/lpi/timer) tests.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
2ca3364b |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: get correct ipi received num
If ipi_exec() fails because of timeout, we shouldn't increase the number of ipi received.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Review
arm64: microbench: get correct ipi received num
If ipi_exec() fails because of timeout, we shouldn't increase the number of ipi received.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
#
a3d5d6b9 |
| 31-Jul-2020 |
Jingyi Wang <wangjingyi11@huawei.com> |
arm64: microbench: Add timer_post() to get actual PPI latency
For we get the time duration of (10msec timer + injection latency) in timer_exec(), we substract the value of 10msec in timer_post() to
arm64: microbench: Add timer_post() to get actual PPI latency
For we get the time duration of (10msec timer + injection latency) in timer_exec(), we substract the value of 10msec in timer_post() to get the actual latency.
Signed-off-by: Jingyi Wang <wangjingyi11@huawei.com> [ Adapt to the modified post() interface. ] Signed-off-by: Andrew Jones <drjones@redhat.com>
show more ...
|