From: Peter Zijlstra <peterz@infradead.org>
To: mingo@redhat.com, tglx@linutronix.de, juri.lelli@redhat.com,
vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
bristot@redhat.com
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-api@vger.kernel.org, x86@kernel.org, peterz@infradead.org,
pjt@google.com, posk@google.com, avagin@google.com,
jannh@google.com, tdelisle@uwaterloo.ca, mark.rutland@arm.com,
posk@posk.io
Subject: [RFC][PATCH v2 1/5] mm: Avoid unmapping pinned pages
Date: Thu, 20 Jan 2022 16:55:18 +0100 [thread overview]
Message-ID: <20220120160822.666778608@infradead.org> (raw)
In-Reply-To: 20220120155517.066795336@infradead.org
Add a guarantee for Anon pages that pin_user_page*() ensures the
user-mapping of these pages stay preserved. In order to ensure this
all rmap users have been audited:
vmscan: already fails eviction due to page_maybe_dma_pinned()
migrate: migration will fail on pinned pages due to
expected_page_refs() not matching, however that is
*after* try_to_migrate() has already destroyed the
user mapping of these pages. Add an early exit for
this case.
numa-balance: as per the above, pinned pages cannot be migrated,
however numa balancing scanning will happily PROT_NONE
them to get usage information on these pages. Avoid
this for pinned pages.
None of the other rmap users (damon,page-idle,mlock,..) unmap the
page, they mostly just muck about with reference,dirty flags etc.
This same guarantee cannot be provided for Shared (file) pages due to
dirty page tracking.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
mm/migrate.c | 10 +++++++++-
mm/mprotect.c | 6 ++++++
2 files changed, 15 insertions(+), 1 deletion(-)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1472,7 +1472,15 @@ int migrate_pages(struct list_head *from
nr_subpages = thp_nr_pages(page);
cond_resched();
- if (PageHuge(page))
+ /*
+ * If the page has a pin then expected_page_refs() will
+ * not match and the whole migration will fail later
+ * anyway, fail early and preserve the mappings.
+ */
+ if (page_maybe_dma_pinned(page))
+ rc = -EAGAIN;
+
+ else if (PageHuge(page))
rc = unmap_and_move_huge_page(get_new_page,
put_new_page, private, page,
pass > 2, mode, reason,
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -106,6 +106,12 @@ static unsigned long change_pte_range(st
continue;
/*
+ * Can't migrate pinned pages, avoid touching them.
+ */
+ if (page_maybe_dma_pinned(page))
+ continue;
+
+ /*
* Don't mess with PTEs if page is already on the node
* a single-threaded process is running on.
*/
next prev parent reply other threads:[~2022-01-20 16:09 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-20 15:55 [RFC][PATCH v2 0/5] sched: User Managed Concurrency Groups Peter Zijlstra
2022-01-20 15:55 ` Peter Zijlstra [this message]
2022-01-20 18:03 ` [RFC][PATCH v2 1/5] mm: Avoid unmapping pinned pages Nadav Amit
2022-01-21 7:59 ` Peter Zijlstra
2022-01-20 18:25 ` David Hildenbrand
2022-01-21 7:51 ` Peter Zijlstra
2022-01-21 8:22 ` David Hildenbrand
2022-01-21 8:59 ` Peter Zijlstra
2022-01-21 9:04 ` David Hildenbrand
2022-01-21 11:40 ` Peter Zijlstra
2022-01-21 12:04 ` David Hildenbrand
2022-01-20 15:55 ` [RFC][PATCH v2 2/5] entry,x86: Create common IRQ operations for exceptions Peter Zijlstra
2022-01-21 16:34 ` Mark Rutland
2022-01-20 15:55 ` [RFC][PATCH v2 3/5] sched/umcg: add WF_CURRENT_CPU and externise ttwu Peter Zijlstra
2022-01-20 15:55 ` [RFC][PATCH v2 4/5] x86/uaccess: Implement unsafe_try_cmpxchg_user() Peter Zijlstra
2022-01-27 2:17 ` Sean Christopherson
2022-01-27 6:36 ` Sean Christopherson
2022-01-27 9:56 ` Peter Zijlstra
2022-01-27 23:33 ` Sean Christopherson
2022-01-28 0:17 ` Nick Desaulniers
2022-01-28 16:29 ` Sean Christopherson
2022-01-27 9:55 ` Peter Zijlstra
2022-01-20 15:55 ` [RFC][PATCH v2 5/5] sched: User Mode Concurency Groups Peter Zijlstra
2022-01-21 11:47 ` Peter Zijlstra
2022-01-21 15:18 ` Peter Zijlstra
2022-01-24 14:29 ` Peter Zijlstra
2022-01-24 16:44 ` Peter Zijlstra
2022-01-24 17:06 ` Peter Oskolkov
2022-01-25 14:59 ` Peter Zijlstra
2022-01-24 13:59 ` Peter Zijlstra
2022-01-21 12:26 ` Peter Zijlstra
2022-01-21 16:57 ` Mark Rutland
2022-01-24 9:48 ` Peter Zijlstra
2022-01-24 10:03 ` Peter Zijlstra
2022-01-24 10:07 ` Peter Zijlstra
2022-01-24 10:27 ` Mark Rutland
2022-01-24 14:46 ` Tao Zhou
2022-01-27 12:19 ` Peter Zijlstra
2022-01-27 18:33 ` Tao Zhou
2022-01-27 12:25 ` Peter Zijlstra
2022-01-27 18:47 ` Tao Zhou
2022-01-27 12:26 ` Peter Zijlstra
2022-01-27 18:31 ` Tao Zhou
2022-01-20 17:28 ` [RFC][PATCH v2 0/5] sched: User Managed Concurrency Groups Peter Oskolkov
2022-01-21 8:01 ` Peter Zijlstra
2022-01-21 18:01 ` Steven Rostedt
2022-01-24 8:20 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220120160822.666778608@infradead.org \
--to=peterz@infradead.org \
--cc=avagin@google.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=jannh@google.com \
--cc=juri.lelli@redhat.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mark.rutland@arm.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=pjt@google.com \
--cc=posk@google.com \
--cc=posk@posk.io \
--cc=rostedt@goodmis.org \
--cc=tdelisle@uwaterloo.ca \
--cc=tglx@linutronix.de \
--cc=vincent.guittot@linaro.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).