linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrea Arcangeli <aarcange@redhat.com>
To: linux-mm@kvack.org
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
	Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
	Izik Eidus <ieidus@redhat.com>,
	Hugh Dickins <hugh.dickins@tiscali.co.uk>,
	Nick Piggin <npiggin@suse.de>, Rik van Riel <riel@redhat.com>,
	Mel Gorman <mel@csn.ul.ie>, Andi Kleen <andi@firstfloor.org>,
	Dave Hansen <dave@linux.vnet.ibm.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Ingo Molnar <mingo@elte.hu>, Mike Travis <travis@sgi.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Christoph Lameter <cl@linux-foundation.org>,
	Chris Wright <chrisw@sous-sol.org>Dave Hansen
	<dave@linux.vnet.ibm.com>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH 18 of 30] add pmd_huge_pte to mm_struct
Date: Thu, 21 Jan 2010 07:20:42 +0100	[thread overview]
Message-ID: <e96a00d0713899a06b10.1264054842@v2.random> (raw)
In-Reply-To: <patchbomb.1264054824@v2.random>

From: Andrea Arcangeli <aarcange@redhat.com>

This increase the size of the mm struct a bit but it is needed to preallocate
one pte for each hugepage so that split_huge_page will not require a fail path.
Guarantee of success is a fundamental property of split_huge_page to avoid
decrasing swapping reliability and to avoid adding -ENOMEM fail paths that
would otherwise force the hugepage-unaware VM code to learn rolling back in the
middle of its pte mangling operations (if something we need it to learn
handling pmd_trans_huge natively rather being capable of rollback). When
split_huge_page runs a pte is needed to succeed the split, to map the newly
splitted regular pages with a regular pte.  This way all existing VM code
remains backwards compatible by just adding a split_huge_page* one liner. The
memory waste of those preallocated ptes is negligible and so it is worth it.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -291,6 +291,9 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
+#endif
 };
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
diff --git a/kernel/fork.c b/kernel/fork.c
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -498,6 +498,9 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -638,6 +641,10 @@ struct mm_struct *dup_mm(struct task_str
 	mm->token_priority = 0;
 	mm->last_interval = 0;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	mm->pmd_huge_pte = NULL;
+#endif
+
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2010-01-21  6:51 UTC|newest]

Thread overview: 79+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-01-21  6:20 [PATCH 00 of 30] Transparent Hugepage support #3 Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 01 of 30] define MADV_HUGEPAGE Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 02 of 30] compound_lock Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 03 of 30] alter compound get_page/put_page Andrea Arcangeli
2010-01-21 17:35   ` Dave Hansen
2010-01-23 17:39     ` Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 04 of 30] clear compound mapping Andrea Arcangeli
2010-01-21 17:43   ` Dave Hansen
2010-01-23 17:55     ` Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 05 of 30] add native_set_pmd_at Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 06 of 30] add pmd paravirt ops Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 07 of 30] no paravirt version of pmd ops Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 08 of 30] export maybe_mkwrite Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 09 of 30] comment reminder in destroy_compound_page Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 10 of 30] config_transparent_hugepage Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 11 of 30] add pmd mangling functions to x86 Andrea Arcangeli
2010-01-21 17:47   ` Dave Hansen
2010-01-21 19:14     ` Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 12 of 30] add pmd mangling generic functions Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 13 of 30] special pmd_trans_* functions Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 14 of 30] bail out gup_fast on splitting pmd Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 15 of 30] pte alloc trans splitting Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 16 of 30] add pmd mmu_notifier helpers Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 17 of 30] clear page compound Andrea Arcangeli
2010-01-21  6:20 ` Andrea Arcangeli [this message]
2010-01-21  6:20 ` [PATCH 19 of 30] ensure mapcount is taken on head pages Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 20 of 30] split_huge_page_mm/vma Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 21 of 30] split_huge_page paging Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 22 of 30] pmd_trans_huge migrate bugcheck Andrea Arcangeli
2010-01-21 20:40   ` Christoph Lameter
2010-01-21 23:01     ` Andrea Arcangeli
2010-01-21 23:17       ` Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 23 of 30] clear_copy_huge_page Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 24 of 30] kvm mmu transparent hugepage support Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 25 of 30] transparent hugepage core Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 26 of 30] madvise(MADV_HUGEPAGE) Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 27 of 30] memcg compound Andrea Arcangeli
2010-01-21  7:07   ` KAMEZAWA Hiroyuki
2010-01-21 15:44     ` Andrea Arcangeli
2010-01-21 23:55       ` KAMEZAWA Hiroyuki
2010-01-21  6:20 ` [PATCH 28 of 30] memcg huge memory Andrea Arcangeli
2010-01-21  7:16   ` KAMEZAWA Hiroyuki
2010-01-21 16:08     ` Andrea Arcangeli
2010-01-22  0:13       ` KAMEZAWA Hiroyuki
2010-01-27 11:27         ` Balbir Singh
2010-01-28  0:50           ` Daisuke Nishimura
2010-01-28 11:39           ` Andrea Arcangeli
2010-01-28 12:23             ` Balbir Singh
2010-01-28 12:36               ` Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 29 of 30] transparent hugepage vmstat Andrea Arcangeli
2010-01-21  6:20 ` [PATCH 30 of 30] khugepaged Andrea Arcangeli
2010-01-22 14:46 ` [PATCH 00 of 30] Transparent Hugepage support #3 Christoph Lameter
2010-01-22 15:19   ` Andrea Arcangeli
2010-01-22 16:51     ` Christoph Lameter
2010-01-23 17:58       ` Andrea Arcangeli
2010-01-25 21:50         ` Christoph Lameter
2010-01-25 22:46           ` Andrea Arcangeli
2010-01-26 15:47             ` Christoph Lameter
2010-01-26 16:11               ` Andrea Arcangeli
2010-01-26 16:30                 ` Christoph Lameter
2010-01-26 16:45                   ` Andrea Arcangeli
2010-01-26 18:23                     ` Christoph Lameter
2010-01-26 17:09                   ` Avi Kivity
2010-01-26  0:52           ` Rik van Riel
2010-01-26  6:53             ` Gleb Natapov
2010-01-26 12:35               ` Andrea Arcangeli
2010-01-26 15:55                 ` Christoph Lameter
2010-01-26 16:19                   ` Andrea Arcangeli
2010-01-26 15:54             ` Christoph Lameter
2010-01-26 16:16               ` Andrea Arcangeli
2010-01-26 16:24                 ` Andi Kleen
2010-01-26 16:37                 ` Christoph Lameter
2010-01-26 16:42                 ` Mel Gorman
2010-01-26 16:52                   ` Andrea Arcangeli
2010-01-26 17:26                     ` Mel Gorman
2010-01-26 19:46                       ` Andrea Arcangeli
2010-01-26 23:07               ` Rik van Riel
2010-01-27 18:33                 ` Christoph Lameter
2010-01-26 11:24 ` Mel Gorman

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=e96a00d0713899a06b10.1264054842@v2.random \
    --to=aarcange@redhat.com \
    --cc=agl@us.ibm.com \
    --cc=andi@firstfloor.org \
    --cc=avi@redhat.com \
    --cc=benh@kernel.crashing.org \
    --cc=chrisw@sous-sol.org \
    --cc=cl@linux-foundation.org \
    --cc=dave@linux.vnet.ibm.com \
    --cc=hugh.dickins@tiscali.co.uk \
    --cc=ieidus@redhat.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=mingo@elte.hu \
    --cc=mtosatti@redhat.com \
    --cc=npiggin@suse.de \
    --cc=riel@redhat.com \
    --cc=travis@sgi.com \
    /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).