From: Mel Gorman <mgorman@suse.de>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>,
Andrea Arcangeli <aarcange@redhat.com>,
Ingo Molnar <mingo@kernel.org>
Cc: Rik van Riel <riel@redhat.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
Paul Turner <pjt@google.com>,
Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
Alex Shi <lkml.alex@gmail.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
Linux-MM <linux-mm@kvack.org>,
LKML <linux-kernel@vger.kernel.org>, Mel Gorman <mgorman@suse.de>
Subject: [PATCH 20/46] mm: mempolicy: Use _PAGE_NUMA to migrate pages
Date: Wed, 21 Nov 2012 10:21:26 +0000 [thread overview]
Message-ID: <1353493312-8069-21-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1353493312-8069-1-git-send-email-mgorman@suse.de>
Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
sufficiently different that the signed-off-bys were dropped
Combine our previous _PAGE_NUMA, 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.
Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
include/linux/huge_mm.h | 8 ++++----
mm/huge_memory.c | 32 +++++++++++++++++++++++++++++---
mm/memory.c | 32 +++++++++++++++++++++++++++-----
3 files changed, 60 insertions(+), 12 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a13ebb1..406f81c 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -160,8 +160,8 @@ static inline struct page *compound_trans_head(struct page *page)
return page;
}
-extern int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
- pmd_t pmd, pmd_t *pmdp);
+extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd, pmd_t *pmdp);
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
@@ -200,8 +200,8 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd,
return 0;
}
-static inline int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
- pmd_t pmd, pmd_t *pmdp);
+static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd, pmd_t *pmdp);
{
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7224efd..df1af09 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"
@@ -1018,16 +1019,39 @@ out:
}
/* NUMA hinting page fault entry point for trans huge pmds */
-int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
- pmd_t pmd, pmd_t *pmdp)
+int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd, pmd_t *pmdp)
{
- struct page *page;
+ struct page *page = NULL;
+ unsigned long haddr = addr & HPAGE_PMD_MASK;
+ int target_nid;
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
page = pmd_page(pmd);
+ get_page(page);
+ spin_unlock(&mm->page_table_lock);
+
+ target_nid = mpol_misplaced(page, vma, haddr);
+ if (target_nid == -1)
+ goto clear_pmdnuma;
+
+ /*
+ * 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 0;
+
+clear_pmdnuma:
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp)))
+ goto out_unlock;
+
pmd = pmd_mknonnuma(pmd);
set_pmd_at(mm, haddr, pmdp, pmd);
VM_BUG_ON(pmd_numa(*pmdp));
@@ -1035,6 +1059,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
out_unlock:
spin_unlock(&mm->page_table_lock);
+ if (page)
+ put_page(page);
return 0;
}
diff --git a/mm/memory.c b/mm/memory.c
index 277b6d8..6bebb41 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>
@@ -3451,8 +3452,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
{
- struct page *page;
+ struct page *page = NULL;
spinlock_t *ptl;
+ int current_nid, target_nid;
/*
* The "pte" at this point cannot be used safely without
@@ -3465,8 +3467,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
*/
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
- if (unlikely(!pte_same(*ptep, pte)))
- goto out_unlock;
+ if (unlikely(!pte_same(*ptep, pte))) {
+ pte_unmap_unlock(ptep, ptl);
+ goto out;
+ }
+
pte = pte_mknonnuma(pte);
set_pte_at(mm, addr, ptep, pte);
update_mmu_cache(vma, addr, ptep);
@@ -3477,8 +3482,25 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
return 0;
}
-out_unlock:
+ get_page(page);
+ current_nid = page_to_nid(page);
+ target_nid = mpol_misplaced(page, vma, addr);
pte_unmap_unlock(ptep, ptl);
+ if (target_nid == -1) {
+ /*
+ * Account for the fault against the current node if it not
+ * being replaced regardless of where the page is located.
+ */
+ current_nid = numa_node_id();
+ put_page(page);
+ goto out;
+ }
+
+ /* Migrate to the requested node */
+ if (migrate_misplaced_page(page, target_nid))
+ current_nid = target_nid;
+
+out:
return 0;
}
@@ -3647,7 +3669,7 @@ retry:
barrier();
if (pmd_trans_huge(orig_pmd)) {
if (pmd_numa(*pmd))
- return do_huge_pmd_numa_page(mm, address,
+ return do_huge_pmd_numa_page(mm, vma, address,
orig_pmd, pmd);
if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) {
--
1.7.9.2
next prev parent reply other threads:[~2012-11-21 10:28 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-21 10:21 [PATCH 00/46] Automatic NUMA Balancing V4 Mel Gorman
2012-11-21 10:21 ` [PATCH 01/46] x86: mm: only do a local tlb flush in ptep_set_access_flags() Mel Gorman
2012-11-21 10:21 ` [PATCH 02/46] x86: mm: drop TLB flush from ptep_set_access_flags Mel Gorman
2012-11-21 10:21 ` [PATCH 03/46] mm,generic: only flush the local TLB in ptep_set_access_flags Mel Gorman
2012-11-21 10:21 ` [PATCH 04/46] x86/mm: Introduce pte_accessible() Mel Gorman
2012-11-21 10:21 ` [PATCH 05/46] mm: Only flush the TLB when clearing an accessible pte Mel Gorman
2012-11-21 10:21 ` [PATCH 06/46] mm: Count the number of pages affected in change_protection() Mel Gorman
2012-11-21 10:21 ` [PATCH 07/46] mm: Optimize the TLB flush of sys_mprotect() and change_protection() users Mel Gorman
2012-11-21 10:21 ` [PATCH 08/46] mm: compaction: Move migration fail/success stats to migrate.c Mel Gorman
2012-11-21 10:21 ` [PATCH 09/46] mm: migrate: Add a tracepoint for migrate_pages Mel Gorman
2012-11-21 10:21 ` [PATCH 10/46] mm: compaction: Add scanned and isolated counters for compaction Mel Gorman
2012-11-21 10:21 ` [PATCH 11/46] mm: numa: define _PAGE_NUMA Mel Gorman
2012-11-21 10:21 ` [PATCH 12/46] mm: numa: pte_numa() and pmd_numa() Mel Gorman
2012-11-21 10:21 ` [PATCH 13/46] mm: numa: Support NUMA hinting page faults from gup/gup_fast Mel Gorman
2012-11-21 10:21 ` [PATCH 14/46] mm: numa: split_huge_page: transfer the NUMA type from the pmd to the pte Mel Gorman
2012-11-21 10:21 ` [PATCH 15/46] mm: numa: Create basic numa page hinting infrastructure Mel Gorman
2012-11-21 10:21 ` [PATCH 16/46] mm: mempolicy: Make MPOL_LOCAL a real policy Mel Gorman
2012-11-21 10:21 ` [PATCH 17/46] mm: mempolicy: Add MPOL_MF_NOOP Mel Gorman
2012-11-21 10:21 ` [PATCH 18/46] mm: mempolicy: Check for misplaced page Mel Gorman
2012-11-21 10:21 ` [PATCH 19/46] mm: migrate: Introduce migrate_misplaced_page() Mel Gorman
2012-11-21 10:21 ` Mel Gorman [this message]
2012-11-21 10:21 ` [PATCH 21/46] mm: mempolicy: Add MPOL_MF_LAZY Mel Gorman
2012-11-21 10:21 ` [PATCH 22/46] mm: mempolicy: Implement change_prot_numa() in terms of change_protection() Mel Gorman
2012-11-21 10:21 ` [PATCH 23/46] mm: mempolicy: Hide MPOL_NOOP and MPOL_MF_LAZY from userspace for now Mel Gorman
2012-11-21 10:21 ` [PATCH 24/46] mm: numa: Add fault driven placement and migration Mel Gorman
2012-11-21 10:21 ` [PATCH 25/46] mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Mel Gorman
2012-11-21 10:21 ` [PATCH 26/46] sched, numa, mm: Count WS scanning against present PTEs, not virtual memory ranges Mel Gorman
2012-11-21 10:21 ` [PATCH 27/46] mm: sched: numa: Implement slow start for working set sampling Mel Gorman
2012-11-21 10:21 ` [PATCH 28/46] mm: numa: Add pte updates, hinting and migration stats Mel Gorman
2012-11-21 10:21 ` [PATCH 29/46] mm: numa: Migrate on reference policy Mel Gorman
2012-11-21 10:21 ` [PATCH 30/46] mm: numa: Migrate pages handled during a pmd_numa hinting fault Mel Gorman
2012-11-21 10:21 ` [PATCH 31/46] mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting Mel Gorman
2012-11-21 10:21 ` [PATCH 32/46] mm: numa: Rate limit the amount of memory that is migrated between nodes Mel Gorman
2012-11-21 10:21 ` [PATCH 33/46] mm: numa: Rate limit setting of pte_numa if node is saturated Mel Gorman
2012-11-21 10:21 ` [PATCH 34/46] sched: numa: Slowly increase the scanning period as NUMA faults are handled Mel Gorman
2012-11-21 10:21 ` [PATCH 35/46] mm: numa: Introduce last_nid to the page frame Mel Gorman
2012-11-21 10:21 ` [PATCH 36/46] mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships Mel Gorman
2012-11-21 18:25 ` Ingo Molnar
2012-11-21 19:15 ` Mel Gorman
2012-11-21 19:39 ` Mel Gorman
2012-11-21 19:46 ` Rik van Riel
2012-11-22 0:05 ` Ingo Molnar
2012-11-21 10:21 ` [PATCH 37/46] mm: numa: Add THP migration for the NUMA working set scanning fault case Mel Gorman
2012-11-21 11:24 ` Mel Gorman
2012-11-21 12:21 ` Mel Gorman
2012-11-21 10:21 ` [PATCH 38/46] sched: numa: Introduce tsk_home_node() Mel Gorman
2012-11-21 10:21 ` [PATCH 39/46] sched: numa: Make find_busiest_queue() a method Mel Gorman
2012-11-21 10:21 ` [PATCH 40/46] sched: numa: Implement home-node awareness Mel Gorman
2012-11-21 10:21 ` [PATCH 41/46] sched: numa: Introduce per-mm and per-task structures Mel Gorman
2012-11-21 10:21 ` [PATCH 42/46] sched: numa: CPU follows memory Mel Gorman
2012-11-21 10:21 ` [PATCH 43/46] sched: numa: Rename mempolicy to HOME Mel Gorman
2012-11-21 10:21 ` [PATCH 44/46] sched: numa: Consider only one CPU per node for CPU-follows-memory Mel Gorman
2012-11-21 10:21 ` [PATCH 45/46] balancenuma: no task swap in finding placement Mel Gorman
2012-11-21 10:21 ` [PATCH 46/46] Simple CPU follow Mel Gorman
2012-11-21 16:53 ` [PATCH 00/46] Automatic NUMA Balancing V4 Mel Gorman
2012-11-21 17:03 ` Ingo Molnar
2012-11-21 17:20 ` Mel Gorman
2012-11-21 17:33 ` Ingo Molnar
2012-11-21 18:02 ` Mel Gorman
2012-11-21 18:21 ` Ingo Molnar
2012-11-21 19:01 ` Mel Gorman
2012-11-21 23:27 ` Ingo Molnar
2012-11-22 9:32 ` Mel Gorman
2012-11-22 9:05 ` Ingo Molnar
2012-11-22 9:43 ` Mel Gorman
2012-11-22 12:56 ` 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=1353493312-8069-21-git-send-email-mgorman@suse.de \
--to=mgorman@suse.de \
--cc=Lee.Schermerhorn@hp.com \
--cc=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lkml.alex@gmail.com \
--cc=mingo@kernel.org \
--cc=pjt@google.com \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).