linux-kernel - Re: [GIT PULL] iov_iter: Improve page extraction (pin or just list)

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: <f2fb6cc5-ff95-ca51-b377-5e4bd239d5e8@kernel.dk>
Date:   Tue, 31 Jan 2023 07:50:45 -0700
From:   Jens Axboe <axboe@...nel.dk>
To:     David Hildenbrand <david@...hat.com>,
        David Howells <dhowells@...hat.com>
Cc:     John Hubbard <jhubbard@...dia.com>,
        Al Viro <viro@...iv.linux.org.uk>,
        Christoph Hellwig <hch@...radead.org>,
        Matthew Wilcox <willy@...radead.org>, Jan Kara <jack@...e.cz>,
        Jason Gunthorpe <jgg@...dia.com>,
        Logan Gunthorpe <logang@...tatee.com>,
        Jeff Layton <jlayton@...nel.org>, linux-block@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org
Subject: Re: [GIT PULL] iov_iter: Improve page extraction (pin or just list)

On 1/31/23 6:48?AM, David Hildenbrand wrote:
> On 31.01.23 14:41, David Howells wrote:
>> David Hildenbrand <david@...hat.com> wrote:
>>
>>>>> percpu counters maybe - add them up at the point of viewing?
>>>> They are percpu, see my last email. But for every 108 changes (on
>>>> my system), they will do two atomic_long_adds(). So not very
>>>> useful for anything but low frequency modifications.
>>>>
>>>
>>> Can we just treat the whole acquired/released accounting as a debug mechanism
>>> to detect missing releases and do it only for debug kernels?
>>>
>>>
>>> The pcpu counter is an s8, so we have to flush on a regular basis and cannot
>>> really defer it any longer ... but I'm curious if it would be of any help to
>>> only have a single PINNED counter that goes into both directions (inc/dec on
>>> pin/release), to reduce the flushing.
>>>
>>> Of course, once we pin/release more than ~108 pages in one go or we switch
>>> CPUs frequently it won't be that much of a help ...
>>
>> What are the stats actually used for?  Is it just debugging, or do we actually
>> have users for them (control groups spring to mind)?
> 
> As it's really just "how many pinning events" vs. "how many unpinning
> events", I assume it's only for debugging.
> 
> For example, if you pin the same page twice it would not get accounted
> as "a single page is pinned".

How about something like the below then? I can send it out as a real
patch, will run a sanity check on it first but would be surprised if
this doesn't fix it.


diff --git a/mm/gup.c b/mm/gup.c
index f45a3a5be53a..41abb16286ec 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -168,7 +168,9 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
 		 */
 		smp_mb__after_atomic();
 
+#ifdef CONFIG_DEBUG_VM
 		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs);
+#endif
 
 		return folio;
 	}
@@ -180,7 +182,9 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
 static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
 {
 	if (flags & FOLL_PIN) {
+#ifdef CONFIG_DEBUG_VM
 		node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs);
+#endif
 		if (folio_test_large(folio))
 			atomic_sub(refs, folio_pincount_ptr(folio));
 		else
@@ -236,8 +240,9 @@ int __must_check try_grab_page(struct page *page, unsigned int flags)
 		} else {
 			folio_ref_add(folio, GUP_PIN_COUNTING_BIAS);
 		}
-
+#ifdef CONFIG_DEBUG_VM
 		node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1);
+#endif
 	}
 
 	return 0;

-- 
Jens Axboe