linux-kernel - Re: [PATCH 1/6] genirq: platform wide interrupt moderation: Documentation, Kconfig, irq

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <86o6p6t67m.wl-maz@kernel.org>
Date: Thu, 13 Nov 2025 13:25:33 +0000
From: Marc Zyngier <maz@...nel.org>
To: Luigi Rizzo <lrizzo@...gle.com>
Cc: Thomas Gleixner <tglx@...utronix.de>,
	Luigi Rizzo <rizzo.unipi@...il.com>,
	Paolo Abeni <pabeni@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Sean Christopherson <seanjc@...gle.com>,
	Jacob Pan <jacob.jun.pan@...ux.intel.com>,
	linux-kernel@...r.kernel.org,
	linux-arch@...r.kernel.org,
	Bjorn Helgaas <bhelgaas@...gle.com>,
	Willem de Bruijn <willemb@...gle.com>
Subject: Re: [PATCH 1/6] genirq: platform wide interrupt moderation: Documentation, Kconfig, irq_desc

On Wed, 12 Nov 2025 19:24:03 +0000,
Luigi Rizzo <lrizzo@...gle.com> wrote:

[...]

> The system does not rely on any special hardware feature except from
> MSI-X Pending Bit Array (PBA), a mandatory component of MSI-X

Is this stuff PCI specific? if so, Why? What is the actual dependency
on PBA? It is it just that you are relying on the ability to mask
interrupts without losing them, something that is pretty much a given
on any architecture?

[...]

> +Platform Wide software interrupt moderation is a variant of moderation
> +that adjusts the delay based on platform-wide metrics, instead of
> +considering each source separately.  It then uses hrtimers to implement
> +adaptive, per-CPU moderation in software, without requiring any specific
> +hardware support other than Pending Bit Array, a standard feature
> +of MSI-X.
> +
> +To understand the motivation for this feature, we start with some
> +background on interrupt moderation.

This reads like marketing blurb. This is an API documentation, and it
shouldn't be a description of your motivations for building it the way
you did. I'd suggest you stick to the API, and keep the motivations
for the cover letter.

> +
> +* **Interrupt** is a mechanism to **notify** the CPU of **events**
> +  that should be handled by software, for example, **completions**
> +  of I/O requests (network tx/rx, disk read/writes...).

That's only half of the truth, as this description only applies to
*edge* interrupts. Level interrupts report a change in *state*, not an
event.

How do you plan to deal with interrupt moderation for level
interrupts?

	M.

-- 
Without deviation from the norm, progress is not possible.