linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Paul Turner <pjt@google.com>,
	Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
	Christoph Lameter <cl@linux.com>, Rik van Riel <riel@redhat.com>,
	Mel Gorman <mgorman@suse.de>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Hugh Dickins <hughd@google.com>
Subject: [PATCH 06/27] mm: Count the number of pages affected in change_protection()
Date: Mon, 19 Nov 2012 03:14:23 +0100	[thread overview]
Message-ID: <1353291284-2998-7-git-send-email-mingo@kernel.org> (raw)
In-Reply-To: <1353291284-2998-1-git-send-email-mingo@kernel.org>

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 fa06804..8d86d5a 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);
-- 
1.7.11.7

--
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:[~2012-11-19  2:15 UTC|newest]

Thread overview: 101+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-19  2:14 [PATCH 00/27] Latest numa/core release, v16 Ingo Molnar
2012-11-19  2:14 ` [PATCH 01/27] mm/generic: Only flush the local TLB in ptep_set_access_flags() Ingo Molnar
2012-11-19  2:14 ` [PATCH 02/27] x86/mm: Only do a local tlb flush " Ingo Molnar
2012-11-19  2:14 ` [PATCH 03/27] x86/mm: Introduce pte_accessible() Ingo Molnar
2012-11-19  2:14 ` [PATCH 04/27] mm: Only flush the TLB when clearing an accessible pte Ingo Molnar
2012-11-19  2:14 ` [PATCH 05/27] x86/mm: Completely drop the TLB flush from ptep_set_access_flags() Ingo Molnar
2012-11-19  2:14 ` Ingo Molnar [this message]
2012-11-19  2:14 ` [PATCH 07/27] mm: Optimize the TLB flush of sys_mprotect() and change_protection() users Ingo Molnar
2012-11-19  2:14 ` [PATCH 08/27] sched, numa, mm: Add last_cpu to page flags Ingo Molnar
2012-11-19  2:14 ` [PATCH 09/27] sched, mm, numa: Create generic NUMA fault infrastructure, with architectures overrides Ingo Molnar
2012-11-19  2:14 ` [PATCH 10/27] sched: Make find_busiest_queue() a method Ingo Molnar
2012-11-19  2:14 ` [PATCH 11/27] sched, numa, mm: Describe the NUMA scheduling problem formally Ingo Molnar
2012-11-19  2:14 ` [PATCH 12/27] numa, mm: Support NUMA hinting page faults from gup/gup_fast Ingo Molnar
2012-11-19  2:14 ` [PATCH 13/27] mm/migrate: Introduce migrate_misplaced_page() Ingo Molnar
2012-11-19  2:14 ` [PATCH 14/27] sched, numa, mm, arch: Add variable locality exception Ingo Molnar
2012-11-19  2:14 ` [PATCH 15/27] sched, numa, mm: Add credits for NUMA placement Ingo Molnar
2012-11-19  2:14 ` [PATCH 16/27] sched, mm, x86: Add the ARCH_SUPPORTS_NUMA_BALANCING flag Ingo Molnar
2012-11-19  2:14 ` [PATCH 17/27] sched, numa, mm: Add the scanning page fault machinery Ingo Molnar
2012-11-19  2:14 ` [PATCH 18/27] sched: Add adaptive NUMA affinity support Ingo Molnar
2012-11-19  2:14 ` [PATCH 19/27] sched: Implement constant, per task Working Set Sampling (WSS) rate Ingo Molnar
2012-11-19  2:14 ` [PATCH 20/27] sched, numa, mm: Count WS scanning against present PTEs, not virtual memory ranges Ingo Molnar
2012-11-19  2:14 ` [PATCH 21/27] sched: Implement slow start for working set sampling Ingo Molnar
2012-11-19  2:14 ` [PATCH 22/27] sched, numa, mm: Interleave shared tasks Ingo Molnar
2012-11-19  2:14 ` [PATCH 23/27] sched: Implement NUMA scanning backoff Ingo Molnar
2012-11-19  2:14 ` [PATCH 24/27] sched: Improve convergence Ingo Molnar
2012-11-19  2:14 ` [PATCH 25/27] sched: Introduce staged average NUMA faults Ingo Molnar
2012-11-19  2:14 ` [PATCH 26/27] sched: Track groups of shared tasks Ingo Molnar
2012-11-19  2:14 ` [PATCH 27/27] sched: Use the best-buddy 'ideal cpu' in balancing decisions Ingo Molnar
2012-11-19 16:29 ` [PATCH 00/27] Latest numa/core release, v16 Mel Gorman
2012-11-19 19:13   ` Ingo Molnar
2012-11-19 21:18     ` Mel Gorman
2012-11-19 22:36       ` Ingo Molnar
2012-11-19 23:00         ` Mel Gorman
2012-11-20  0:41           ` Rik van Riel
2012-11-21 10:58             ` Mel Gorman
2012-11-20  1:02         ` Linus Torvalds
2012-11-20  7:17           ` Ingo Molnar
2012-11-20  7:37             ` David Rientjes
2012-11-20  7:48               ` Ingo Molnar
2012-11-20  8:01               ` Ingo Molnar
2012-11-20  8:11                 ` David Rientjes
2012-11-21 11:14               ` Mel Gorman
2012-11-20 10:20             ` Mel Gorman
2012-11-20 10:47               ` Mel Gorman
2012-11-20 15:29             ` [PATCH] mm, numa: Turn 4K pte NUMA faults into effective hugepage ones Ingo Molnar
2012-11-20 16:09               ` [PATCH, v2] " Ingo Molnar
2012-11-20 16:31                 ` Rik van Riel
2012-11-20 16:52                   ` Ingo Molnar
2012-11-21 12:08                     ` Mel Gorman
2012-11-21  8:12                   ` Ingo Molnar
2012-11-21  2:41                 ` David Rientjes
2012-11-21  9:34                   ` Ingo Molnar
2012-11-21 11:40                 ` Mel Gorman
2012-11-23  1:26                 ` Alex Shi
2012-11-20 17:56               ` numa/core regressions fixed - more testers wanted Ingo Molnar
2012-11-21  1:54                 ` Andrew Theurer
2012-11-21  3:22                   ` Rik van Riel
2012-11-21  4:10                     ` Hugh Dickins
2012-11-21 17:59                       ` Andrew Theurer
2012-11-21 11:52                   ` Mel Gorman
2012-11-21 22:15                     ` Andrew Theurer
2012-11-21  3:33                 ` David Rientjes
2012-11-21  9:38                   ` Ingo Molnar
2012-11-21 11:06                   ` Ingo Molnar
2012-11-21  8:39                 ` Alex Shi
2012-11-22  1:21                   ` Ingo Molnar
2012-11-23 13:31                     ` Ingo Molnar
2012-11-23 15:23                       ` Alex Shi
2012-11-26  2:11                       ` Alex Shi
2012-11-28 14:21                         ` Alex Shi
2012-11-20 10:40         ` [PATCH 00/27] Latest numa/core release, v16 Ingo Molnar
2012-11-20 11:40           ` Mel Gorman
2012-11-21 10:38     ` Mel Gorman
2012-11-21 19:37       ` Andrea Arcangeli
2012-11-21 19:56         ` Mel Gorman
2012-11-19 20:07   ` Ingo Molnar
2012-11-19 21:37     ` Mel Gorman
2012-11-20  0:50   ` David Rientjes
2012-11-20  1:05     ` David Rientjes
2012-11-20  6:00       ` Ingo Molnar
2012-11-20  6:20         ` David Rientjes
2012-11-20  7:44           ` Ingo Molnar
2012-11-20  7:48             ` Paul Turner
2012-11-20  8:20             ` David Rientjes
2012-11-20  9:06               ` Ingo Molnar
2012-11-20  9:41                 ` [patch] x86/vsyscall: Add Kconfig option to use native vsyscalls, switch to it Ingo Molnar
2012-11-20 23:01                   ` Andy Lutomirski
2012-11-21  0:43                   ` David Rientjes
2012-11-20 12:02                 ` [PATCH] x86/mm: Don't flush the TLB on #WP pmd fixups Ingo Molnar
2012-11-20 12:31                   ` Ingo Molnar
2012-11-21 11:47                     ` Mel Gorman
2012-11-21  1:22                   ` David Rientjes
2012-11-21 17:02                 ` [PATCH 00/27] Latest numa/core release, v16 Linus Torvalds
2012-11-21 17:10                   ` Ingo Molnar
2012-11-21 17:20                     ` Ingo Molnar
2012-11-22  4:31                       ` David Rientjes
2012-11-21 17:40                     ` Ingo Molnar
2012-11-21 22:04                     ` Linus Torvalds
2012-11-21 22:46                       ` Ingo Molnar
2012-11-21 17:45                   ` Rik van Riel
2012-11-21 18:04                   ` Ingo Molnar

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=1353291284-2998-7-git-send-email-mingo@kernel.org \
    --to=mingo@kernel.org \
    --cc=Lee.Schermerhorn@hp.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --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).