<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p><br>
</p>
<div class="moz-cite-prefix">On 02/11/25 5:23 pm, Mukesh Kumar
Chaurasiya wrote:<br>
</div>
<blockquote type="cite"
cite="mid:20251102115358.1744304-1-mkchauras@linux.ibm.com">
<pre wrap="" class="moz-quote-pre">Adding support for the generic irq entry/exit handling for PowerPC. The
goal is to bring PowerPC in line with other architectures that already
use the common irq entry infrastructure, reducing duplicated code and
making it easier to share future changes in entry/exit paths.
This is slightly tested of ppc64le and ppc32.
The performance benchmarks from perf bench basic syscall are below:
| Metric | W/O Generic Framework | With Generic Framework | Change |
| ---------- | --------------------- | ---------------------- | ------ |
| Total time | 0.939 [sec] | 0.938 [sec] | ~0% |
| usecs/op | 0.093900 | 0.093882 | ~0% |
| ops/sec | 1,06,49,615 | 1,06,51,725 | ~0% |
Thats very close to performance earlier with arch specific handling.
Tests done:
- Build and boot on ppc64le pseries.
- Build and boot on ppc64le powernv8 powernv9 powernv10.
- Build and boot on ppc32.
- Performance benchmark done with perf syscall basic on pseries.
Changelog:
RFC -> PATCH
- Fix for ppc32 spitting out kuap lock warnings.
- ppc64le powernv8 crash fix.
- Review comments incorporated from previous RFC.
RFC <a class="moz-txt-link-freetext" href="https://lore.kernel.org/all/20250908210235.137300-2-mchauras@linux.ibm.com/">https://lore.kernel.org/all/20250908210235.137300-2-mchauras@linux.ibm.com/</a>
Mukesh Kumar Chaurasiya (8):
powerpc: rename arch_irq_disabled_regs
powerpc: Prepare to build with generic entry/exit framework
powerpc: introduce arch_enter_from_user_mode
powerpc: Introduce syscall exit arch functions
powerpc: add exit_flags field in pt_regs
powerpc: Prepare for IRQ entry exit
powerpc: Enable IRQ generic entry/exit path.
powerpc: Enable Generic Entry/Exit for syscalls.
arch/powerpc/Kconfig | 2 +
arch/powerpc/include/asm/entry-common.h | 539 ++++++++++++++++++++++++
arch/powerpc/include/asm/hw_irq.h | 4 +-
arch/powerpc/include/asm/interrupt.h | 401 +++---------------
arch/powerpc/include/asm/ptrace.h | 3 +
arch/powerpc/include/asm/stacktrace.h | 6 +
arch/powerpc/include/asm/syscall.h | 5 +
arch/powerpc/include/asm/thread_info.h | 1 +
arch/powerpc/include/uapi/asm/ptrace.h | 14 +-
arch/powerpc/kernel/asm-offsets.c | 1 +
arch/powerpc/kernel/interrupt.c | 258 +++---------
arch/powerpc/kernel/ptrace/ptrace.c | 142 +------
arch/powerpc/kernel/signal.c | 8 +
arch/powerpc/kernel/syscall.c | 119 +-----
arch/powerpc/kernel/traps.c | 2 +-
arch/powerpc/kernel/watchdog.c | 2 +-
arch/powerpc/perf/core-book3s.c | 2 +-
17 files changed, 693 insertions(+), 816 deletions(-)
create mode 100644 arch/powerpc/include/asm/entry-common.h
</pre>
</blockquote>
Hi,<br>
<br>
<p>I have reviewed and tested the generic IRQ entry/exist patch
series. Below are my observations:</p>
<p><br>
</p>
<p>
Test Coverage
</p>
<p>• Successfully ran LTP (specially syscall) and entire LTP test
suite, without observing any regressions or issues related to the
implementation.</p>
<p><br>
</p>
<p>
System Configuration
</p>
<p>• CPUs: 160
</p>
<p>• Kernel: v6.18.0-rc1+
</p>
<p>• Processor mode: Shared (uncapped)</p>
<p><br>
</p>
<p>
Performance Evaluation
</p>
<p>• Conducted benchmarking using perf bench syscall basic -l and
hackbench.
</p>
<p>• No functional regressions observed, and results were consistent
with expectations.</p>
<p><br>
</p>
<ul>
<li>Results for perf bench syscall**Loops = 100,000**</li>
</ul>
**Loops = 100,000**<br>
| Metric | W/O Generic Framework | With Generic
Framework | Improvement |<br>
|----------|-----------------------:|-----------------------:|------------:|<br>
| usecs/op | 0.125328 |
0.128839 | ~-2.80% |<br>
| ops/sec | 7,979,645 |
7,762,047 | ~-2.73% |<br>
<br>
**Loops = 1,000,000**<br>
| Metric | W/O Generic Framework | With Generic
Framework | Improvement |<br>
|----------|-----------------------:|-----------------------:|------------:|<br>
| usecs/op | 0.125015 |
0.127885 | ~-2.30% |<br>
| ops/sec | 7,999,051 |
7,819,546 | ~-2.24% |<br>
<br>
**Loops = 10,000,000**<br>
| Metric | W/O Generic Framework | With Generic Framework
| Improvement |<br>
|----------|-----------------------:|-----------------------:|------------:|<br>
| usecs/op | 0.124613 |
0.127426 | ~-2.26% |<br>
| ops/sec | 8,024,827 |
7,847,735 | ~-2.21% |<br>
<br>
**Overall (aggregated across all runs)**<br>
| Metric | W/O Generic Framework | With Generic Framework
| Improvement |<br>
| ---------- |
---------------------:|-----------------------:|------------:|<br>
| Total time | 1.384 [sec] | 1.415
[sec] | ~-2.27% |<br>
| usecs/op | 0.124656 |
0.127480 | ~-2.27% |<br>
| ops/sec | 8,022,098 |
7,844,423 | ~-2.21% |<br>
<br>
<p>A 2% performance degradation was observed with the perf bench
syscall.</p>
<p><br>
</p>
<ul>
<li>Results for hackbench</li>
</ul>
<br>
| Metric | W/O Generic Framework | With Generic Framework
| Improvement |<br>
|----------|----------------------
:|-----------------------:|------------:|<br>
| Min Time | 142.055 (sec). | 141.699 (sec)
| 0.25%<br>
| Max Time | 143.791 (sec). | 143.206 (sec)
| 0.41%<br>
| Avg Time | 142.925 (sec) | 142.472 (sec)
| 0.32%<br>
<br>
So overall 0.3 % improvement is observed across 10 runs.<br>
<br>
Please add below tag for the patch set.<br>
Tested-by: Samir M <a class="moz-txt-link-rfc2396E" href="mailto:samir@linux.ibm.com"><samir@linux.ibm.com></a><br>
Thank You !!<br>
<br>
<br>
Regards,<br>
Samir.
</body>
</html>