linux-kernel - Re: [PATCH] mm, vmscan: prevent infinite loop for costly GFP_NOIO

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: Wed, 21 Feb 2024 10:52:52 -0500
From: Sven van Ashbrook <svenva@...omium.org>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: Andrew Morton <akpm@...ux-foundation.org>, bgeffon@...gle.com, 
	cujomalainey@...omium.org, kramasub@...omium.org, 
	linux-kernel@...r.kernel.org, linux-mm@...ck.org, linux-sound@...r.kernel.org, 
	perex@...ex.cz, stable@...r.kernel.org, tiwai@...e.com, tiwai@...e.de, 
	Michal Hocko <mhocko@...nel.org>, Mel Gorman <mgorman@...hsingularity.net>
Subject: Re: [PATCH] mm, vmscan: prevent infinite loop for costly GFP_NOIO |
 __GFP_RETRY_MAYFAIL allocations

Thanks so much ! We will stress test this on our side.

We do this by exhausting memory and triggering many suspend/resume
cycles. This reliably reproduces the problem (before this patch).

Of course, as we all know, absence of evidence (no more stalls in stress tests)
does not equal evidence of absence (stalls are gone in all code paths).