linux-kernel - Re: [PATCH] scatterlist: Speed up for_each

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]

Date:   Mon, 28 Oct 2019 09:37:32 -0700
From:   Sultan Alsawaf <sultan@...neltoast.com>
To:     Christoph Hellwig <hch@...radead.org>
Cc:     Jason Gunthorpe <jgg@...pe.ca>,
        "Martin K. Petersen" <martin.petersen@...cle.com>,
        Thomas Hellstrom <thellstrom@...are.com>,
        Palmer Dabbelt <palmer@...ive.com>,
        Sakari Ailus <sakari.ailus@...ux.intel.com>,
        Ming Lei <ming.lei@...hat.com>,
        Gal Pressman <galpress@...zon.com>,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH] scatterlist: Speed up for_each_sg() loop macro

On Mon, Oct 28, 2019 at 09:28:16AM -0700, Christoph Hellwig wrote:
> And there is nothing forcing a particular layout, there just happens
> to be a layout that the generic allocator gives you.  I'm not even
> sure the original patch handles the SCSI case of small inlines segments
> properly.

I'm doubtful; are there really sg users that craft their own sglists and then
use for_each_sg() on them? But like I mentioned in the email I sent a
few minutes ago, this can be alleviated with a more comprehensive version of
this patch that alters all for_each_sg() users and thus ensures that only
sg_table pointers can be used with the macro. Anyone who would munge their own
sg_table together would simply be insane :)

Or there could be a separate macro for iterating through each sg in an sg_table.
There are lots of ways to go about this.

Sultan