<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html lang="en" style="--code-editor-font: var(--default-mono-font, "GitLab Mono"), JetBrains Mono, Menlo, DejaVu Sans Mono, Liberation Mono, Consolas, Ubuntu Mono, Courier New, andale mono, lucida console, monospace;">
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
<title>
GitLab
</title>
<style data-premailer="ignore" type="text/css">
a { color: #1068bf; }
</style>
<style>img {
max-width: 100%; height: auto;
}
body {
font-size: .875rem;
}
body {
-webkit-text-shadow: hsla(0,0%,100%,.01) 0 0 1px;
}
body {
font-family: "GitLab Sans",-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Noto Sans",Ubuntu,Cantarell,"Helvetica Neue",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji"; font-size: inherit;
}
</style>
</head>
<body style="font-size: inherit; -webkit-text-shadow: hsla(0,0%,100%,.01) 0 0 1px; font-family: "GitLab Sans",-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Noto Sans",Ubuntu,Cantarell,"Helvetica Neue",sans-serif,"Apple Color Emoji","Segoe UI Emoji","Segoe UI Symbol","Noto Color Emoji";">
<div class="content">
<p style="color: #777777;">
<a href="https://gitlab.rtems.org/wmthornton-dev">Wayne Thornton</a>
<a href="https://gitlab.rtems.org/rtems/rtos/rtems/-/work_items/5650#note_154724">commented</a>:
</p>
<div class="md" style="position: relative; z-index: 1; color: #3a383f; word-wrap: break-word;">
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">Ok, after reviewing the options, I have come to the following conclusions:</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">When developers implement lock-free ring buffers, sequence locks, or custom RCU algorithms across cores using C11 <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;"><stdatomic.h></code>, standard C provides the memory ordering models, but neither C11 nor POSIX defines an instruction-level pipeline throttle for the spin-wait loop itself. Without that throttle, tight CAS or token-polling loops flood the MESI interconnect with continuous read requests, actively degrading the performance of the thread trying to release the lock. This is obviously a problem and the entire reason _CPU_Spin_wait() was introduced.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">Regarding finding an existing home within the current APIs that avoids creating a new <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_cpu_xxx</code> namespace, I think the SMP manager (<code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;"><rtems/smp.h></code>) is the perfect fit for this.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">Proposed Directive:</p>
<div class="gl-relative markdown-code-block js-markdown-code">
<pre class="code highlight js-syntax-highlight language-plaintext" v-pre="true" style="display: block; font-size: 14px; color: #3a383f; line-height: 1.6em; overflow-x: auto; border-radius: .25rem; position: relative; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: break-all; word-wrap: break-word; background-color: #fbfafd; margin: 0px 0 1rem; padding: 12px; border: 1px solid #dcdcde;"><code style="font-size: inherit; color: inherit; word-wrap: normal; word-break: keep-all; background-color: inherit; border-radius: .25rem; white-space: pre; margin-top: 0px; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; overflow-wrap: normal; padding: unset;"><span id="LC1" class="line" lang="plaintext" style="margin-top: 0px;">/* Appropriate Doxygen comments would be placed here */</span>
<span id="LC2" class="line" lang="plaintext">static inline void rtems_smp_spin_wait( void )</span>
<span id="LC3" class="line" lang="plaintext">{</span>
<span id="LC4" class="line" lang="plaintext"> _CPU_Spin_wait();</span>
<span id="LC5" class="line" lang="plaintext">}</span></code></pre>
<copy-code></copy-code><insert-code-snippet></insert-code-snippet>
</div>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">The physical benefits of pipeline throttling (mitigating cache-line bouncing, reducing interconnect saturation, and yielding ALU resources on SMT cores) are inherently SMP things. By placing the directive in <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;"><rtems/smp.h></code> it would live naturally alongside <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_smp_get_current_processor()</code> and <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_smp_processor_id()</code>.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">There would also be zero overhead introduced by defining <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_smp_spin_wait()</code> as a static inline wrapper around <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">_CPU_Spin_wait()</code> in <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;"><rtems/smp.h></code>. Applications would get portable pipeline throttling with zero function-call overhead in their inner loops.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">On uniprocessor builds, <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">_CPU_Spin_wait()</code> seamlessly degrades to <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">RTEMS_COMPILER_MEMORY_BARRIER()</code>, ensuring that ISR-to-thread polling loops in shared memory maintain compiler visibility without incurring hardware penalties.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">The other option I can find is to place the directive in the task manager (<code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;"><rtems/rtems/tasks.h></code>), but I don't know that this is an option I would prefer.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">Proposed Directive:</p>
<div class="gl-relative markdown-code-block js-markdown-code">
<pre class="code highlight js-syntax-highlight language-plaintext" v-pre="true" style="display: block; font-size: 14px; color: #3a383f; line-height: 1.6em; overflow-x: auto; border-radius: .25rem; position: relative; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: break-all; word-wrap: break-word; background-color: #fbfafd; margin: 0px 0 1rem; padding: 12px; border: 1px solid #dcdcde;"><code style="font-size: inherit; color: inherit; word-wrap: normal; word-break: keep-all; background-color: inherit; border-radius: .25rem; white-space: pre; margin-top: 0px; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; overflow-wrap: normal; padding: unset;"><span id="LC1" class="line" lang="plaintext" style="margin-top: 0px;">/* Appropriate Doxygen comments would be placed here */</span>
<span id="LC2" class="line" lang="plaintext">static inline void rtems_task_spin_wait( void )</span>
<span id="LC3" class="line" lang="plaintext">{</span>
<span id="LC4" class="line" lang="plaintext"> _CPU_Spin_wait();</span>
<span id="LC5" class="line" lang="plaintext">}</span></code></pre>
<copy-code></copy-code><insert-code-snippet></insert-code-snippet>
</div>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">Since tasks are the entities executing user-level polling loops, positioning it in the task manager makes it universally visible to all application developers regardless of whether they are thinking about SMP topology.</p>
<p dir="auto" style="color: #3a383f; margin: 0px 0px 1rem;" align="initial">This however is a risk since directives in the task manager typically imply operating system state transitions or kernel-level scheduling interventions (<code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; margin-top: 0px; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_task_wake_after</code>, <code style="font-size: 90%; color: #18171d; word-wrap: break-word; background-color: #ececef; border-radius: .25rem; font-weight: inherit; overflow-wrap: break-word; white-space: break-spaces; font-family: "GitLab Mono", "JetBrains Mono", "Menlo", "DejaVu Sans Mono", "Liberation Mono", "Consolas", "Ubuntu Mono", "Courier New", "andale mono", "lucida console", monospace; font-variant-ligatures: none; word-break: keep-all; padding: 0.125rem 0.25rem;">rtems_task_suspend</code>). A static inline hardware hint that does not trap into the executive might feel structurally out of place among scheduling directives and potentially lead to confusion from developers.</p>
<p dir="auto" style="color: #3a383f; margin: 0px;" align="initial">I cannot find any other <em style="margin-top: 0px;">valid</em> locations that I believe such a directive would be appropriate.</p>
</div>
</div>
<div class="footer" style="margin-top: 10px;">
<p style="font-size: small; color: #626168;">
—
<br>
<a href="https://gitlab.rtems.org/rtems/rtos/rtems/-/work_items/5650#note_154724">View it on GitLab</a>.
<br>
You're receiving this email because of your account on <a target="_blank" rel="noopener noreferrer" href="https://gitlab.rtems.org">gitlab.rtems.org</a>. <a href="https://gitlab.rtems.org/-/sent_notifications/4-7dndv674drmxg2mqebitofv8j-1d/unsubscribe" target="_blank" rel="noopener noreferrer">Unsubscribe</a> from this thread · <a href="https://gitlab.rtems.org/-/profile/notifications" target="_blank" rel="noopener noreferrer" class="mng-notif-link">Manage all notifications</a> · <a href="https://gitlab.rtems.org/help" target="_blank" rel="noopener noreferrer" class="help-link">Help</a>
<span style="color: transparent; font-size: 0; display: none; overflow: hidden; opacity: 0; width: 0; height: 0; max-width: 0; max-height: 0;">
Notification message regarding https://gitlab.rtems.org/rtems/rtos/rtems/-/work_items/5650#note_154724 at 1784232824
</span>
<script type="application/ld+json">{"@context":"http://schema.org","@type":"EmailMessage","action":{"@type":"ViewAction","name":"View Work item","url":"https://gitlab.rtems.org/rtems/rtos/rtems/-/work_items/5650#note_154724"}}</script>
</p>
</div>
</body>
</html>