Commit Graph

11 Commits

Author SHA1 Message Date
qinwei1 c4f3f8801f arm64: Support for FPU profiling with procfs
Summary:

   To reduce the count of FPU context switching will result at a
performance improve with system. it need to balance between
the using of FPU and counts of FPU trap
   the PR submit a base method to see performance counts for
the FPU with NuttX procfs
   Please read README.txt at chapter of FPU Support and Performance
for more information

Signed-off-by: qinwei1 <qinwei1@xiaomi.com>
2023-04-22 01:38:21 +08:00
hujun5 abbc661282 arch/arm64:add tickless configure
add configure CONFIG_SCHED_TICKLESS=y to qemu-armv8a:nsh_smp_tickless

Signed-off-by: hujun5 <hujun5@xiaomi.com>
2023-04-22 01:08:04 +08:00
qinwei1 d5c6b8a94b arm64: add 64-bit time for all arm64 platform
Summary
  For ARM64 architecture, the arch timer is 64-bit,
the CONFIG_SYSTEM_TIME64 need to be enabled just like
x86_64 and risc-v 64

Signed-off-by: qinwei1 <qinwei1@xiaomi.com>
2023-03-01 13:23:48 +08:00
qinwei1 4240723b78 arm64: add ARCH_EARLY_PRINT support
Summary:
  The aarch64 have EL0~El3 execute level and NS/S (security state),
the NuttX should be execute at EL1 in NS(ARmv8-A) or S(ARmv8-R)
state. but booting NuttX have different ELs and state while with
different platform, if NuttX runing at wrong ELs or state it will
be not normal anymore. So we need to print something in arm64_head.S
to debug this situation.
Enabling this option will need to implement up_earlyserialinit and
up_lowputc functions just you see in qemu, if you not sure,
keeping the option disable.

Signed-off-by: qinwei1 <qinwei1@xiaomi.com>
2023-03-01 13:23:48 +08:00
Xiang Xiao 2c5f653bfd Remove the tail spaces from all files except Documentation
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2023-02-26 13:24:24 -08:00
Masayuki Ishikawa 492fa5ba19 boards: qemu-armv8a: Enable the ping command for netnsh and netnsh_smp
Summary:
- This commit enables the ping command for netnsh and netnsh_smp

Impact:
- None

Testing:
- Tested with QEMU-7.1

Signed-off-by: Masayuki Ishikawa <Masayuki.Ishikawa@jp.sony.com>
2022-12-15 17:07:06 +08:00
chao an 4d52618128 qemu-armv8a/netnsh: Set iob buffer size to 1514 to improve performance
Signed-off-by: chao an <anchao@xiaomi.com>
2022-12-12 16:56:11 +09:00
Masayuki Ishikawa 3377aa23ca boards: qemu-armv8a: Add virtio-net to netnsh/netnsh_smp
Summary:
- This commit adds virtio-net to netnsh/netnsh_smp

Impact:
- None

Testing:
- Tested iperf and telnetd with QEMU-7.1

Signed-off-by: Masayuki Ishikawa <Masayuki.Ishikawa@jp.sony.com>
2022-11-29 13:16:44 +08:00
Lee Lup Yuen 6aba739f05 arch/arm64: Add support for Generic Interrupt Controller Version 2
Currently NuttX on Arm64 supports Generic Interrupt Controller (GIC) Versions 3 and 4: [`arm64_gicv3.c`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm64/src/common/arm64_gicv3.c), [`arm64_gic.h`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm64/src/common/arm64_gic.h). This PR adds support for GIC Version 2, which is needed by [Pine64 PinePhone](https://lupyuen.github.io/articles/interrupt) based on Allwinner A64 SoC.

This 64-bit implementation of GIC v2 is mostly identical to the existing GIC v2 for 32-bit Armv7-A ([`armv7-a/arm_gicv2.c`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm/src/armv7-a/arm_gicv2.c), [`armv7-a/gic.h`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm/src/armv7-a/gic.h)), with minor modifications to support 64-bit Registers (Interrupt Context).

-   `arch/arm64/Kconfig`: Under "ARM64 Options", we added an integer option `ARM_GIC_VERSION` ("GIC version") that selects the GIC Version. Valid values are 2, 3 and 4, default is 3.

-   `arch/arm64/src/common/arm64_gicv2.c`: Implements 64-bit GIC v2 based on 32-bit [`armv7-a/arm_gicv2.c`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm/src/armv7-a/arm_gicv2.c) and [`armv7-a/gic.h`](https://github.com/apache/incubator-nuttx/blob/master/arch/arm/src/armv7-a/gic.h), modified to support 64-bit Registers (Interrupt Context).

    Function and Macro Names have not been changed, for easier cross-referencing between the 32-bit and 64-bit implementations of GIC v2.

-   `arch/arm64/src/common/arm64_gicv3.c`: Added Conditional Compilation for GIC v3. This file will not be compiled if `ARM_GIC_VERSION` is 2.

-   `arch/arm64/src/common/arm64_gic.h`: Added the Version Identifier for GIC v2. At startup we read the GIC Version from hardware and verify that it matches `ARM_GIC_VERSION`.

-   `arch/arm64/include/qemu/chip.h`: Added the QEMU Base Addresses for GIC v2.

-   `arch/arm64/src/common/Make.defs`: Added the source file that implements GIC v2.

-   `boards/arm64/qemu/qemu-armv8a/README.txt`: Added the documentation for testing GIC v2 with QEMU.

-   `boards/arm64/qemu/qemu-armv8a/configs/nsh_gicv2/defconfig`: Added the Board Configuration `qemu-armv8a:nsh_gicv2` for testing GIC v2 with QEMU. Identical to `qemu-armv8a:nsh`, except that `ARM_GIC_VERSION` is 2.
2022-11-20 21:44:12 -08:00
Masayuki Ishikawa 18ce70c1e7 boards: qemu-armv8a: Fix pthread_attr_setstacksize failed in ostest
Summary:
- This commit adjusts CONFIG_TESTING_OSTEST_STACKSIZE to fix
  pthread_attr_setstacksize failed error in ostest

Impact:
- None

Testing:
- Tested with ostest

Signed-off-by: Masayuki Ishikawa <Masayuki.Ishikawa@jp.sony.com>
2022-10-15 08:46:01 +02:00
Hidenori Matsubayashi 28180b49d1 arm64: add Cortex-A57 and Cortex-A72 configurations
This change adds the following:
- Rename the board configuration name from qemu-a53 to qemu-v8a.
- Add the configurations for Cortex-A57 and Cortex-A72.

Signed-off-by: Hidenori Matsubayashi <hidenori.matsubayashi@gmail.com>
2022-10-14 09:27:35 +08:00