Re: [PATCH 2/8] mm: use walk_page_range() instead of custom page table walking code

[Stephen Wilson <wilsons@start.ca>]

On Mon, May 09, 2011 at 04:38:49PM +0900, KOSAKI Motohiro wrote:
> Hello,
> 
> sorry for the long delay.

Please, no apologies.  Thank you for the review!

> > In the specific case of show_numa_map(), the custom page table walking
> > logic implemented in mempolicy.c does not provide any special service
> > beyond that provided by walk_page_range().
> > 
> > Also, converting show_numa_map() to use the generic routine decouples
> > the function from mempolicy.c, allowing it to be moved out of the mm
> > subsystem and into fs/proc.
> > 
> > Signed-off-by: Stephen Wilson <wilsons@start.ca>
> > ---
> >  mm/mempolicy.c |   53 ++++++++++++++++++++++++++++++++++++++++++++++-------
> >  1 files changed, 46 insertions(+), 7 deletions(-)
> > 
> > diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> > index 5bfb03e..dfe27e3 100644
> > --- a/mm/mempolicy.c
> > +++ b/mm/mempolicy.c
> > @@ -2568,6 +2568,22 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
> >  	md->node[page_to_nid(page)]++;
> >  }
> >  
> > +static int gather_pte_stats(pte_t *pte, unsigned long addr,
> > +		unsigned long pte_size, struct mm_walk *walk)
> > +{
> > +	struct page *page;
> > +
> > +	if (pte_none(*pte))
> > +		return 0;
> > +
> > +	page = pte_page(*pte);
> > +	if (!page)
> > +		return 0;
> 
> original check_pte_range() has following logic.
> 
>         orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
>         do {
>                 struct page *page;
>                 int nid;
> 
>                 if (!pte_present(*pte))
>                         continue;
>                 page = vm_normal_page(vma, addr, *pte);
>                 if (!page)
>                         continue;
>                 /*
>                  * vm_normal_page() filters out zero pages, but there might
>                  * still be PageReserved pages to skip, perhaps in a VDSO.
>                  * And we cannot move PageKsm pages sensibly or safely yet.
>                  */
>                 if (PageReserved(page) || PageKsm(page))
>                         continue;
>                 gather_stats(page, private, pte_dirty(*pte));
> 
> Why did you drop a lot of check? Is it safe?

I must have been confused.  For one, walk_page_range() does not even
lock the pmd entry when iterating over the pte's.  I completely
overlooked that fact and so with that, the series is totally broken.

I am currently testing a slightly reworked set based on the following
variation.  When finished I will send v2 of the series which will
address all issues raised so far.

Thanks again for the review!



>From 013a1e0fc96f8370339209f16d81df4ded40dbf2 Mon Sep 17 00:00:00 2001
From: Stephen Wilson <wilsons@start.ca>
Date: Mon, 9 May 2011 14:39:27 -0400
Subject: [PATCH] mm: use walk_page_range() instead of custom page table
 walking code

Converting show_numa_map() to use the generic routine decouples
the function from mempolicy.c, allowing it to be moved out of the mm
subsystem and into fs/proc.

Also, include KSM pages in /proc/pid/numa_maps statistics.  The pagewalk
logic implemented by check_pte_range() failed to account for such pages
as they were not applicable to the page migration case.

Signed-off-by: Stephen Wilson <wilsons@start.ca>
---
 mm/mempolicy.c |   75 ++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 68 insertions(+), 7 deletions(-)

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 5bfb03e..945e85d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2531,6 +2531,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 }
 
 struct numa_maps {
+	struct vm_area_struct *vma;
 	unsigned long pages;
 	unsigned long anon;
 	unsigned long active;
@@ -2568,6 +2569,41 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
 	md->node[page_to_nid(page)]++;
 }
 
+static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
+		unsigned long end, struct mm_walk *walk)
+{
+	struct numa_maps *md;
+	spinlock_t *ptl;
+	pte_t *orig_pte;
+	pte_t *pte;
+
+	md = walk->private;
+	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	do {
+		struct page *page;
+		int nid;
+
+		if (!pte_present(*pte))
+			continue;
+
+		page = vm_normal_page(md->vma, addr, *pte);
+		if (!page)
+			continue;
+
+		if (PageReserved(page))
+			continue;
+
+		nid = page_to_nid(page);
+		if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+			continue;
+
+		gather_stats(page, md, pte_dirty(*pte));
+
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	pte_unmap_unlock(orig_pte, ptl);
+	return 0;
+}
+
 #ifdef CONFIG_HUGETLB_PAGE
 static void check_huge_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
@@ -2597,12 +2633,35 @@ static void check_huge_range(struct vm_area_struct *vma,
 		gather_stats(page, md, pte_dirty(*ptep));
 	}
 }
+
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	struct page *page;
+
+	if (pte_none(*pte))
+		return 0;
+
+	page = pte_page(*pte);
+	if (!page)
+		return 0;
+
+	gather_stats(page, walk->private, pte_dirty(*pte));
+	return 0;
+}
+
 #else
 static inline void check_huge_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
 		struct numa_maps *md)
 {
 }
+
+static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
+		unsigned long addr, unsigned long end, struct mm_walk *walk)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -2615,6 +2674,7 @@ int show_numa_map(struct seq_file *m, void *v)
 	struct numa_maps *md;
 	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
+	struct mm_walk walk = {};
 	struct mempolicy *pol;
 	int n;
 	char buffer[50];
@@ -2626,6 +2686,13 @@ int show_numa_map(struct seq_file *m, void *v)
 	if (!md)
 		return 0;
 
+	md->vma = vma;
+
+	walk.hugetlb_entry = gather_hugetbl_stats;
+	walk.pmd_entry = gather_pte_stats;
+	walk.private = md;
+	walk.mm = mm;
+
 	pol = get_vma_policy(priv->task, vma, vma->vm_start);
 	mpol_to_str(buffer, sizeof(buffer), pol, 0);
 	mpol_cond_put(pol);
@@ -2642,13 +2709,7 @@ int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " stack");
 	}
 
-	if (is_vm_hugetlb_page(vma)) {
-		check_huge_range(vma, vma->vm_start, vma->vm_end, md);
-		seq_printf(m, " huge");
-	} else {
-		check_pgd_range(vma, vma->vm_start, vma->vm_end,
-			&node_states[N_HIGH_MEMORY], MPOL_MF_STATS, md);
-	}
+	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
 		goto out;
-- 
1.7.4.4