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 06/46] mm: Count the number of pages affected in change_protection()
Date: Wed, 21 Nov 2012 10:21:12 +0000 [thread overview]
Message-ID: <1353493312-8069-7-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1353493312-8069-1-git-send-email-mgorman@suse.de>
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
This will be used for three kinds of purposes:
- to optimize mprotect()
- to speed up working set scanning for working set areas that
have not been touched
- to more accurately scan per real working set
No change in functionality from this patch.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/linux/hugetlb.h | 8 +++++--
include/linux/mm.h | 3 +++
mm/hugetlb.c | 10 ++++++--
mm/mprotect.c | 58 +++++++++++++++++++++++++++++++++++------------
4 files changed, 61 insertions(+), 18 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2251648..06e691b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -87,7 +87,7 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int write);
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd);
-void hugetlb_change_protection(struct vm_area_struct *vma,
+unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot);
#else /* !CONFIG_HUGETLB_PAGE */
@@ -132,7 +132,11 @@ static inline void copy_huge_page(struct page *dst, struct page *src)
{
}
-#define hugetlb_change_protection(vma, address, end, newprot)
+static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
+ unsigned long address, unsigned long end, pgprot_t newprot)
+{
+ return 0;
+}
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcaab4e..1856c62 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1078,6 +1078,9 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
extern unsigned long do_mremap(unsigned long addr,
unsigned long old_len, unsigned long new_len,
unsigned long flags, unsigned long new_addr);
+extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgprot_t newprot,
+ int dirty_accountable);
extern int mprotect_fixup(struct vm_area_struct *vma,
struct vm_area_struct **pprev, unsigned long start,
unsigned long end, unsigned long newflags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 59a0059..712895e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3014,7 +3014,7 @@ same_page:
return i ? i : -EFAULT;
}
-void hugetlb_change_protection(struct vm_area_struct *vma,
+unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot)
{
struct mm_struct *mm = vma->vm_mm;
@@ -3022,6 +3022,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
pte_t *ptep;
pte_t pte;
struct hstate *h = hstate_vma(vma);
+ unsigned long pages = 0;
BUG_ON(address >= end);
flush_cache_range(vma, address, end);
@@ -3032,12 +3033,15 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
ptep = huge_pte_offset(mm, address);
if (!ptep)
continue;
- if (huge_pmd_unshare(mm, &address, ptep))
+ if (huge_pmd_unshare(mm, &address, ptep)) {
+ pages++;
continue;
+ }
if (!huge_pte_none(huge_ptep_get(ptep))) {
pte = huge_ptep_get_and_clear(mm, address, ptep);
pte = pte_mkhuge(pte_modify(pte, newprot));
set_huge_pte_at(mm, address, ptep, pte);
+ pages++;
}
}
spin_unlock(&mm->page_table_lock);
@@ -3049,6 +3053,8 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
*/
flush_tlb_range(vma, start, end);
mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+
+ return pages << h->order;
}
int hugetlb_reserve_pages(struct inode *inode,
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a409926..1e265be 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -35,12 +35,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
}
#endif
-static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
+static unsigned long change_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable)
{
pte_t *pte, oldpte;
spinlock_t *ptl;
+ unsigned long pages = 0;
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
@@ -60,6 +61,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
ptent = pte_mkwrite(ptent);
ptep_modify_prot_commit(mm, addr, pte, ptent);
+ pages++;
} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
swp_entry_t entry = pte_to_swp_entry(oldpte);
@@ -72,18 +74,22 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
set_pte_at(mm, addr, pte,
swp_entry_to_pte(entry));
}
+ pages++;
}
} while (pte++, addr += PAGE_SIZE, addr != end);
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
+
+ return pages;
}
-static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable)
{
pmd_t *pmd;
unsigned long next;
+ unsigned long pages = 0;
pmd = pmd_offset(pud, addr);
do {
@@ -91,35 +97,42 @@ static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
if (pmd_trans_huge(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE)
split_huge_page_pmd(vma->vm_mm, pmd);
- else if (change_huge_pmd(vma, pmd, addr, newprot))
+ else if (change_huge_pmd(vma, pmd, addr, newprot)) {
+ pages += HPAGE_PMD_NR;
continue;
+ }
/* fall through */
}
if (pmd_none_or_clear_bad(pmd))
continue;
- change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
+ pages += change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
dirty_accountable);
} while (pmd++, addr = next, addr != end);
+
+ return pages;
}
-static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable)
{
pud_t *pud;
unsigned long next;
+ unsigned long pages = 0;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
- change_pmd_range(vma, pud, addr, next, newprot,
+ pages += change_pmd_range(vma, pud, addr, next, newprot,
dirty_accountable);
} while (pud++, addr = next, addr != end);
+
+ return pages;
}
-static void change_protection(struct vm_area_struct *vma,
+static unsigned long change_protection_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable)
{
@@ -127,6 +140,7 @@ static void change_protection(struct vm_area_struct *vma,
pgd_t *pgd;
unsigned long next;
unsigned long start = addr;
+ unsigned long pages = 0;
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
@@ -135,10 +149,30 @@ static void change_protection(struct vm_area_struct *vma,
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- change_pud_range(vma, pgd, addr, next, newprot,
+ pages += change_pud_range(vma, pgd, addr, next, newprot,
dirty_accountable);
} while (pgd++, addr = next, addr != end);
+
flush_tlb_range(vma, start, end);
+
+ return pages;
+}
+
+unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, pgprot_t newprot,
+ int dirty_accountable)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long pages;
+
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ if (is_vm_hugetlb_page(vma))
+ pages = hugetlb_change_protection(vma, start, end, newprot);
+ else
+ pages = change_protection_range(vma, start, end, newprot, dirty_accountable);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+
+ return pages;
}
int
@@ -213,12 +247,8 @@ success:
dirty_accountable = 1;
}
- mmu_notifier_invalidate_range_start(mm, start, end);
- if (is_vm_hugetlb_page(vma))
- hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
- else
- change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
- mmu_notifier_invalidate_range_end(mm, start, end);
+ change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
+
vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
vm_stat_account(mm, newflags, vma->vm_file, nrpages);
perf_event_mmap(vma);
--
1.7.9.2
next prev parent reply other threads:[~2012-11-21 10:31 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 ` Mel Gorman [this message]
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 ` [PATCH 20/46] mm: mempolicy: Use _PAGE_NUMA to migrate pages Mel Gorman
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=1353493312-8069-7-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).