Path: ...!weretis.net!feeder9.news.weretis.net!news.nk.ca!rocksolid2!i2pn2.org!.POSTED!not-for-mail
From: mitchalsup@aol.com (MitchAlsup1)
Newsgroups: comp.arch
Subject: Re: MSI interrupts
Date: Thu, 27 Mar 2025 21:47:03 +0000
Organization: Rocksolid Light
Message-ID: <34434320650f5844b18b1c0b684acf43@www.novabbs.org>
References: <vqto79$335c6$1@dont-email.me> <b1c74762d01f71cc1b8ac838dcf6d4fa@www.novabbs.org> <vrvukp$n29$1@reader1.panix.com> <7a093bbb356e3bda3782c15ca27e98a7@www.novabbs.org> <vs41ap$n43$1@reader1.panix.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: i2pn2.org;
	logging-data="2030063"; mail-complaints-to="usenet@i2pn2.org";
	posting-account="o5SwNDfMfYu6Mv4wwLiW6e/jbA93UAdzFodw5PEa6eU";
User-Agent: Rocksolid Light
X-Rslight-Posting-User: cb29269328a20fe5719ed6a1c397e21f651bda71
X-Spam-Checker-Version: SpamAssassin 4.0.0
X-Rslight-Site: $2y$10$.B20EjE9jVgX8hRR9vLozO5.U/GccFK2vLmhp8paoOP.u3IHnMAUa
Bytes: 4599
Lines: 128

On Thu, 27 Mar 2025 17:19:21 +0000, Dan Cross wrote:

> In article <7a093bbb356e3bda3782c15ca27e98a7@www.novabbs.org>,
> MitchAlsup1 <mitchalsup@aol.com> wrote:
-------------------
> Or maybe even just swapping places between two elements in a
> linked list.  For example:
>
> void
> swap_places(Node **head, Node *a, Node *b)
> {
>         Node *hp, *an, *ap, *bn, *bp;
>
>         assert(head != NULL);
>         assert(a != NULL);
>         assert(b != NULL);
>
>         if (a == b)
>                 return;
>
> 	  esmLOCKprefetch(*head);

This should be a load not prefetch--you want the value of *head

>         if (*head == a) 	// see !
>                 *head = b;
>         else if (*head == b)
>                 *head = a;

There is a ESM rule that states:: all participating cache lines
must be touched before any participating cache lines can be
modified.

Also note: Participating cache lines are checked for write permission
at touch time, and on cache miss, read with intent to modify.
>
>         an = esmLOCKload(a->next);
>         ap = esmLOCKload(a->prev);
>         bn = esmLOCKload(b->next);
>         bp = esmLOCKload(b->prev);
>
>         b->next = an;
>         if (an != NULL) {
>                 esmLOCKprefetch(an->prev);
>                 an->prev = b;
> 		}
>         b->prev = ap;
>         if (ap != NULL) {
>                 esmLOCKprefetch(ap->next);
>                 ap->next = b;
> 		}
>
>         a->next = bn;
>         if (bn != NULL) {
> 				esmLOCKprefetch(bn->prev);
>                 bn->prev = a;
> 		}
>         if (bp != NULL) {
> 		        esmLOCKprefetch(bp->next);
>                 bp->next = a;
> 		}
>         esmLOCKstore(a->prev, bp);
> }
>
>
> 	- Dan C.

What I think you want:: (ignoring the 9 participants limit)

> void
> swap_places(Node **head, Node *a, Node *b)
> {
>         Node *hp, *an, *ap, *bn, *bp;
>
>         assert(head != NULL);
>         assert(a != NULL);
>         assert(b != NULL);
>
>         if (a == b)
>                 return;

top_of_ATOMIC_event:

// this is the recovery point is you don't use esmINTERFERENCE()
// the very next instruction begins the event.

>         esmLOCKprefetch( an = esmLOCKload(a->next) );
>         esmLOCKprefetch( ap = esmLOCKload(a->prev) );
>         esmLOCKprefetch( bn = esmLOCKload(b->next) );
>         esmLOCKprefetch( bp = esmLOCKload(b->prev) );

 	  Node *Ehead = esmLOCKload(*head);

// by placing all the the touching before any manifestation, you put
// all the touch latency* in the code before it has tried to damage any
// participating memory location. (*) and TLB latency and 2nd party
// observation of your event.

// this would be the point where you would insert if( esmINTERFERENCE(
))
// if you wanted control at a known failure point rather than at the
// top of the event on failure.

>         if (Ehead == a)
>                 *head = b;
>         else if (Ehead == b)
>                 *head = a;
>
>         b->next = an;
>         if (an != NULL) {
>                 an->prev = b;
> 		}
>         b->prev = ap;
>         if (ap != NULL) {
>                 ap->next = b;
> 		}
>
>         a->next = bn;
>         if (bn != NULL) {
>                 bn->prev = a;
> 		}
>         if (bp != NULL) {
>                 bp->next = a;
> 		}
>         esmLOCKstore(a->prev, bp);
> }

// now manifestation has lowest possible latency (as seen by this core
alone)