Re: [PATCH] nvme-pci: ignore bogus CRTO according to NVME 2.0 spec

[Felix Yan <felixonmars@archlinux.org>]

[-- Attachment #1.1: Type: text/plain, Size: 826 bytes --]

On 9/8/23 19:51, Keith Busch wrote:
> On Fri, Sep 08, 2023 at 06:54:42PM +0300, Felix Yan wrote:
>> NVME 2.0 spec section 3.1.3 suggests that "Software should not rely on
>> 0h being returned". Here we should safeguard timeout reads when CRTO is 0 and
>> fallback to the old NVME 1.4 compatible field.
> 
> Not sure I follow what you're saying here. We're not really relying on
> CRTO being 0. It was a non-zero capability bit that told the driver to
> use CRTO, and 0 is potentially a valid value a controller could report.

Sorry, I actually meant the opposite: If the whole CRTO field is zeroed, 
we probably shouldn't rely on it as per the spec says.

I understand that 0 could be a valid value, the spec _may_ be a little 
bit unclear here then, if I understand it correctly.

-- 
Regards,
Felix Yan


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 840 bytes --]