| 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
| ||
|
Message-Id: <1353083121-4560-19-git-send-email-mingo@kernel.org>
Date: Fri, 16 Nov 2012 17:25:20 +0100
From: Ingo Molnar <mingo@...nel.org>
To: linux-kernel@...r.kernel.org, linux-mm@...ck.org
Cc: Paul Turner <pjt@...gle.com>,
Lee Schermerhorn <Lee.Schermerhorn@...com>,
Christoph Lameter <cl@...ux.com>,
Rik van Riel <riel@...hat.com>, Mel Gorman <mgorman@...e.de>,
Andrew Morton <akpm@...ux-foundation.org>,
Andrea Arcangeli <aarcange@...hat.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Thomas Gleixner <tglx@...utronix.de>,
Hugh Dickins <hughd@...gle.com>
Subject: [PATCH 18/19] mm/mpol: Use special PROT_NONE to migrate pages
From: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Combine our previous PROT_NONE, mpol_misplaced and
migrate_misplaced_page() pieces into an effective migrate on fault
scheme.
Note that (on x86) we rely on PROT_NONE pages being !present and avoid
the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves
the page-migration performance.
Suggested-by: Rik van Riel <riel@...hat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Reviewed-by: Rik van Riel <riel@...hat.com>
Cc: Paul Turner <pjt@...gle.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Andrea Arcangeli <aarcange@...hat.com>
Link: http://lkml.kernel.org/n/tip-e98gyl8kr9jzooh2s4piuils@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@...nel.org>
---
mm/huge_memory.c | 41 +++++++++++++++++++++++++++++++++++-
mm/memory.c | 63 ++++++++++++++++++++++++++++++++++++++++----------------
2 files changed, 85 insertions(+), 19 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6924edf..c4c0a57 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -18,6 +18,7 @@
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
+#include <linux/migrate.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
@@ -741,12 +742,48 @@ void do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned int flags, pmd_t entry)
{
unsigned long haddr = address & HPAGE_PMD_MASK;
+ struct page *page = NULL;
+ int node;
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(*pmd, entry)))
goto out_unlock;
- /* do fancy stuff */
+ if (unlikely(pmd_trans_splitting(entry))) {
+ spin_unlock(&mm->page_table_lock);
+ wait_split_huge_page(vma->anon_vma, pmd);
+ return;
+ }
+
+#ifdef CONFIG_NUMA
+ page = pmd_page(entry);
+ VM_BUG_ON(!PageCompound(page) || !PageHead(page));
+
+ get_page(page);
+ spin_unlock(&mm->page_table_lock);
+
+ /*
+ * XXX should we serialize against split_huge_page ?
+ */
+
+ node = mpol_misplaced(page, vma, haddr);
+ if (node == -1)
+ goto do_fixup;
+
+ /*
+ * Due to lacking code to migrate thp pages, we'll split
+ * (which preserves the special PROT_NONE) and re-take the
+ * fault on the normal pages.
+ */
+ split_huge_page(page);
+ put_page(page);
+ return;
+
+do_fixup:
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(*pmd, entry)))
+ goto out_unlock;
+#endif
/* change back to regular protection */
entry = pmd_modify(entry, vma->vm_page_prot);
@@ -755,6 +792,8 @@ void do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
out_unlock:
spin_unlock(&mm->page_table_lock);
+ if (page)
+ put_page(page);
}
int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
diff --git a/mm/memory.c b/mm/memory.c
index a660fd0..0d26a28 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -57,6 +57,7 @@
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
+#include <linux/migrate.h>
#include <asm/io.h>
#include <asm/pgalloc.h>
@@ -1467,8 +1468,10 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
static bool pte_numa(struct vm_area_struct *vma, pte_t pte)
{
/*
- * If we have the normal vma->vm_page_prot protections we're not a
- * 'special' PROT_NONE page.
+ * For NUMA page faults, we use PROT_NONE ptes in VMAs with
+ * "normal" vma->vm_page_prot protections. Genuine PROT_NONE
+ * VMAs should never get here, because the fault handling code
+ * will notice that the VMA has no read or write permissions.
*
* This means we cannot get 'special' PROT_NONE faults from genuine
* PROT_NONE maps, nor from PROT_WRITE file maps that do dirty
@@ -3473,35 +3476,59 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, pmd_t *pmd,
unsigned int flags, pte_t entry)
{
+ struct page *page = NULL;
+ int node, page_nid = -1;
spinlock_t *ptl;
- int ret = 0;
-
- if (!pte_unmap_same(mm, pmd, ptep, entry))
- goto out;
- /*
- * Do fancy stuff...
- */
-
- /*
- * OK, nothing to do,.. change the protection back to what it
- * ought to be.
- */
- ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ ptl = pte_lockptr(mm, pmd);
+ spin_lock(ptl);
if (unlikely(!pte_same(*ptep, entry)))
- goto unlock;
+ goto out_unlock;
+ page = vm_normal_page(vma, address, entry);
+ if (page) {
+ get_page(page);
+ page_nid = page_to_nid(page);
+ node = mpol_misplaced(page, vma, address);
+ if (node != -1)
+ goto migrate;
+ }
+
+out_pte_upgrade_unlock:
flush_cache_page(vma, address, pte_pfn(entry));
ptep_modify_prot_start(mm, address, ptep);
entry = pte_modify(entry, vma->vm_page_prot);
ptep_modify_prot_commit(mm, address, ptep, entry);
+ /* No TLB flush needed because we upgraded the PTE */
+
update_mmu_cache(vma, address, ptep);
-unlock:
+
+out_unlock:
pte_unmap_unlock(ptep, ptl);
out:
- return ret;
+ if (page)
+ put_page(page);
+
+ return 0;
+
+migrate:
+ pte_unmap_unlock(ptep, ptl);
+
+ if (!migrate_misplaced_page(page, node)) {
+ page_nid = node;
+ goto out;
+ }
+
+ ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ if (!pte_same(*ptep, entry)) {
+ put_page(page);
+ page = NULL;
+ goto out_unlock;
+ }
+
+ goto out_pte_upgrade_unlock;
}
/*
--
1.7.11.7
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists