Skip to contentSkip to conversation

mm: mempolicy: don't have to split pmd for huge zero page

PATCH Superseded Yang Shi 3 participants 11 messages Jun 4, 2021 – Jun 8, 2021

Subsystems (2)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Yang Shi

author
#0 lore raw

PATCH 1/1 mm: mempolicy: don't have to split pmd for huge zero page

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

---
 mm/mempolicy.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
mm/mempolicy.c +5 -4
index b5f4f584009b..205c1a768775 100644
@@ -436,7 +436,8 @@ static inline bool queue_pages_required(struct page *page,
 
 /*
  * queue_pages_pmd() has four possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. huge zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 2 - THP was split.
@@ -460,8 +461,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 	page = pmd_page(*pmd);
 	if (is_huge_zero_page(page)) {
 		spin_unlock(ptl);
-		__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
-		ret = 2;
+		walk->action = ACTION_CONTINUE;
 		goto out;
 	}
 	if (!queue_pages_required(page, qp))
@@ -488,7 +488,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
  * and move them to the pagelist if they do.
  *
  * queue_pages_pte_range() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
Signature · 1 line
2.26.2
reviewer Reviewed-by on v1 1/1
#1 lore raw
Quoted 9 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

LGTM. Thanks.

—
Best Regards,
Yan, Zi

#2 lore raw
In reply to Yang Shi
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Have you tested the patch?

Quoted 2 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

Quoted 41 lines
---
 mm/mempolicy.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
mm/mempolicy.c +5 -4
index b5f4f584009b..205c1a768775 100644
@@ -436,7 +436,8 @@ static inline bool queue_pages_required(struct page *page,
 
 /*
  * queue_pages_pmd() has four possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. huge zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 2 - THP was split.
@@ -460,8 +461,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 	page = pmd_page(*pmd);
 	if (is_huge_zero_page(page)) {
 		spin_unlock(ptl);
-		__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
-		ret = 2;
+		walk->action = ACTION_CONTINUE;
 		goto out;
 	}
 	if (!queue_pages_required(page, qp))
@@ -488,7 +488,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
  * and move them to the pagelist if they do.
  *
  * queue_pages_pte_range() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
Signature · 1 line
2.26.2
Signature · 2 lines
Michal Hocko
SUSE Labs
author
#3 lore raw
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Quoted 2 lines

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Quoted 7 lines
Quoted 3 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

The behavior before the patch for huge zero page is:
split huge zero pmd (insert base zero pfn to ptes) walk ptes
skip zero pfn

So why not just skip the huge zero page in the first place?

Quoted 46 lines
Quoted 41 lines
---
 mm/mempolicy.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
mm/mempolicy.c +5 -5
index b5f4f584009b..205c1a768775 100644
@@ -436,7 +436,8 @@ static inline bool queue_pages_required(struct page *page,
 
 /*
  * queue_pages_pmd() has four possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. huge zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 2 - THP was split.
@@ -460,8 +461,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
      page = pmd_page(*pmd);
      if (is_huge_zero_page(page)) {
              spin_unlock(ptl);
-             __split_huge_pmd(walk->vma, pmd, addr, false, NULL);
-             ret = 2;
+             walk->action = ACTION_CONTINUE;
              goto out;
      }
      if (!queue_pages_required(page, qp))
@@ -488,7 +488,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
  * and move them to the pagelist if they do.
  *
  * queue_pages_pte_range() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
--
Quoted 1 line

2.26.2

--
Michal Hocko
SUSE Labs

author
#4 lore raw
Quoted 25 lines · Yang Shi
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Quoted 7 lines

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Quoted 2 lines

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Just came up with a quick test, the test is trying to mbind 1G address space (use huge zero page) to another node, the result is:

w/o patch:
pgmigrate_success 0
pgmigrate_fail 0
thp_migration_success 0
thp_migration_fail 0
thp_migration_split 0

thp_split_pmd 512
thp_split_pud 0
thp_zero_page_alloc 1

w/ patch:
pgmigrate_success 0
pgmigrate_fail 0
thp_migration_success 0
thp_migration_fail 0
thp_migration_split 0

thp_split_pmd 0
thp_split_pud 0
thp_zero_page_alloc 1

We can tell neither huge zero nor base zero was migrated even before the patch. The patch just kills the pointless pmd split and we keep the huge zero page.

Quoted 65 lines
Quoted 8 lines
Quoted 4 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

The behavior before the patch for huge zero page is:
split huge zero pmd (insert base zero pfn to ptes) walk ptes
skip zero pfn

So why not just skip the huge zero page in the first place?

Quoted 46 lines
Quoted 41 lines
---
 mm/mempolicy.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
mm/mempolicy.c +5 -5
index b5f4f584009b..205c1a768775 100644
@@ -436,7 +436,8 @@ static inline bool queue_pages_required(struct page *page,
 
 /*
  * queue_pages_pmd() has four possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. huge zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 2 - THP was split.
@@ -460,8 +461,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
      page = pmd_page(*pmd);
      if (is_huge_zero_page(page)) {
              spin_unlock(ptl);
-             __split_huge_pmd(walk->vma, pmd, addr, false, NULL);
-             ret = 2;
+             walk->action = ACTION_CONTINUE;
              goto out;
      }
      if (!queue_pages_required(page, qp))
@@ -488,7 +488,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
  * and move them to the pagelist if they do.
  *
  * queue_pages_pte_range() has three possible return values:
- * 0 - pages are placed on the right node or queued successfully.
+ * 0 - pages are placed on the right node or queued successfully, or
+ *     special page is met, i.e. zero page.
  * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
--
Quoted 1 line

2.26.2

--
Michal Hocko
SUSE Labs

#5 lore raw
In reply to Yang Shi
Quoted 14 lines · Yang Shi
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

Quoted 3 lines

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

My bad. I didn't have a look all the way down there. The naming suggested that this is purely page table operations and I have suspected that ptes just point to the offset of the THP.

But I am obviously wrong here. Sorry about that.

Quoted 8 lines

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Yeah, normal zero pages are skipped indeed. I haven't studied why this is the case yet. It surely sounds a bit suspicious because this is an explicit request to migrate memory and if the zero page is misplaced it should be moved. On the hand this would increase RSS so maybe this is the point.

Quoted 8 lines
Quoted 1 line

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Quoted 4 lines
Quoted 3 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Quoted 6 lines
Quoted 3 lines

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

Is there any actual workload that cares? This is quite a subtle area so I would be careful to do changes just because...

Signature · 2 lines
Michal Hocko
SUSE Labs
author
#6 lore raw
Quoted 32 lines · Michal Hocko
Quoted 14 lines · Yang Shi
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

Quoted 3 lines

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

My bad. I didn't have a look all the way down there. The naming suggested that this is purely page table operations and I have suspected that ptes just point to the offset of the THP.

But I am obviously wrong here. Sorry about that.

Quoted 6 lines

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Quoted 8 lines
Quoted 2 lines

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Yeah, normal zero pages are skipped indeed. I haven't studied why this is the case yet. It surely sounds a bit suspicious because this is an explicit request to migrate memory and if the zero page is misplaced it should be moved. On the hand this would increase RSS so maybe this is the point.

The zero page is a global shared page, I don't think "misplace" applies to it. It doesn't make too much sense to migrate a shared page. Actually there is page mapcount check in migrate_page_add() to skip shared normal pages as well.

Quoted 13 lines
Quoted 13 lines
Quoted 2 lines

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Quoted 7 lines
Quoted 3 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

Quoted 5 lines
Quoted 2 lines

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

Is there any actual workload that cares? This is quite a subtle area so I would be careful to do changes just because...

I'm not sure whether there is measurable improvement for actual workloads, but I believe this change does eliminate some unnecessary work.

I think the test shown in the previous email gives us some confidence that the change doesn't have regression.

Quoted 3 lines

--
Michal Hocko
SUSE Labs

#7 lore raw
Quoted 42 lines · Yang Shi
Quoted 32 lines · Michal Hocko
Quoted 14 lines · Yang Shi
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

Quoted 3 lines

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

My bad. I didn't have a look all the way down there. The naming suggested that this is purely page table operations and I have suspected that ptes just point to the offset of the THP.

But I am obviously wrong here. Sorry about that.

Quoted 6 lines

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Quoted 8 lines
Quoted 2 lines

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Yeah, normal zero pages are skipped indeed. I haven't studied why this is the case yet. It surely sounds a bit suspicious because this is an explicit request to migrate memory and if the zero page is misplaced it should be moved. On the hand this would increase RSS so maybe this is the point.

Quoted 4 lines

The zero page is a global shared page, I don't think "misplace" applies to it. It doesn't make too much sense to migrate a shared page. Actually there is page mapcount check in migrate_page_add() to skip shared normal pages as well.

I didn't really mean to migrate zero page itself. What I meant was to instanciate a new page when the global one is on a different NUMA node than the bind() requests. This can be either done by having per NUMA zero page or simply allocate a new page for the exclusive mapping.

Quoted 15 lines
Quoted 15 lines
Quoted 14 lines
Quoted 1 line

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Quoted 7 lines
Quoted 3 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

Quoted 6 lines
Quoted 2 lines

Is there any actual workload that cares? This is quite a subtle area so I would be careful to do changes just because...

I'm not sure whether there is measurable improvement for actual workloads, but I believe this change does eliminate some unnecessary work.

I can see why being consistent here is a good argument. On the other hand it would be imho better to look for reasons why zero pages are left misplaced before making the code consistent. From a very quick git archeology it seems that vm_normal_page has been used since MPOL_MF_MOVE was introduced. At the time (dc9aa5b9d65fd) vm_normal_page hasn't skipped through zero page AFAICS. I do not remember all the details about zero page (wrt. pte special) handling though so it might be hidden at some other place.

In any case the existing code doesn't really work properly. The question is whether anybody actually cares but this is definitely something worth looking into IMHO.

Quoted 2 lines

I think the test shown in the previous email gives us some confidence that the change doesn't have regression.

Yes, this is true.

Signature · 2 lines
Michal Hocko
SUSE Labs
author
#8 lore raw
Quoted 49 lines · Michal Hocko
Quoted 42 lines · Yang Shi
Quoted 32 lines · Michal Hocko
Quoted 14 lines · Yang Shi
Quoted 7 lines · Michal Hocko
Quoted 4 lines · Yang Shi

When trying to migrate pages to obey mempolicy, the huge zero page is split then the page table walk at PTE level just skips zero page. So it seems pointless to split huge zero page, it could be just skipped like base zero page.

Quoted 5 lines

My THP knowledge is not the best but this is incorrect AIACS. Huge zero page is not split. We do split the pmd which is mapping the said page. I suspect you refer to vm_normal_page when talking about a zero page but please be aware that huge zero page is not a normal zero page. It is allocated dynamically (see get_huge_zero_page).

Quoted 3 lines

For a normal huge page, yes, split_huge_pmd() just splits pmd. But actually the base zero pfn will be inserted to PTEs when splitting huge zero pmd. Please check __split_huge_zero_page_pmd() out.

My bad. I didn't have a look all the way down there. The naming suggested that this is purely page table operations and I have suspected that ptes just point to the offset of the THP.

But I am obviously wrong here. Sorry about that.

Quoted 6 lines

I should make this point clearer in the commit log. Sorry for the confusion.

Quoted 3 lines

So in the end you patch disables mbind of zero pages to a target node and that is a regression.

Quoted 8 lines
Quoted 2 lines

Do we really migrate zero page? IIUC zero page is just skipped by vm_normal_page() check in queue_pages_pte_range(), isn't it?

Yeah, normal zero pages are skipped indeed. I haven't studied why this is the case yet. It surely sounds a bit suspicious because this is an explicit request to migrate memory and if the zero page is misplaced it should be moved. On the hand this would increase RSS so maybe this is the point.

Quoted 4 lines

The zero page is a global shared page, I don't think "misplace" applies to it. It doesn't make too much sense to migrate a shared page. Actually there is page mapcount check in migrate_page_add() to skip shared normal pages as well.

Quoted 4 lines

I didn't really mean to migrate zero page itself. What I meant was to instanciate a new page when the global one is on a different NUMA node than the bind() requests. This can be either done by having per NUMA zero page or simply allocate a new page for the exclusive mapping.

IMHO, isn't it too overkilling?

Quoted 19 lines
Quoted 19 lines
Quoted 18 lines
Quoted 9 lines
Quoted 2 lines

Have you tested the patch?

No, just build test. I thought this change was straightforward.

Quoted 4 lines
Quoted 3 lines

Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case.

Quoted 6 lines
Quoted 3 lines

Btw. this changelog is missing a problem statement. I suspect there is no actual problem that it should fix and it is likely driven by reading the code. Right?

The actual problem is it is pointless to split a huge zero pmd. Yes, it is driven by visual inspection.

Is there any actual workload that cares? This is quite a subtle area so I would be careful to do changes just because...

Quoted 7 lines
Quoted 3 lines

I'm not sure whether there is measurable improvement for actual workloads, but I believe this change does eliminate some unnecessary work.

I can see why being consistent here is a good argument. On the other hand it would be imho better to look for reasons why zero pages are left misplaced before making the code consistent. From a very quick git

Typically the zero page is created from kernel's bss section, for example, x86. I'm supposed kernel image itself is loaded on node #0 always.

Quoted 5 lines

archeology it seems that vm_normal_page has been used since MPOL_MF_MOVE was introduced. At the time (dc9aa5b9d65fd) vm_normal_page hasn't skipped through zero page AFAICS. I do not remember all the details about zero page (wrt. pte special) handling though so it might be hidden at some other place.

I did some archeology, the findings are:

The zero page has PageReserved flag set, it was skipped by the explicit PageReserved check in mempolicy.c since commit f4598c8b3678 ("[PATCH] migration: make sure there is no attempt to migrate reserved pages."). The zero page was not used anymore by do_anonymous_page() since 2.6.24 by commit 557ed1fa2620 ("remove ZERO_PAGE"), then reinstated by commit a13ea5b759645 ("mm: reinstate ZERO_PAGE") and this commit added zero page check in vm_normal_page(), so mempolicy doesn't depend on PageReserved check to skip zero page anymore since then.

So the zero page is skipped by mempolicy.c since 2.6.16.

Quoted 12 lines

In any case the existing code doesn't really work properly. The question is whether anybody actually cares but this is definitely something worth looking into IMHO.

Quoted 2 lines

I think the test shown in the previous email gives us some confidence that the change doesn't have regression.

Yes, this is true.
--
Michal Hocko
SUSE Labs

Acked-by
#9 lore raw

On Tue 08-06-21 10:15:36, Yang Shi wrote:
[...]

Quoted 12 lines

I did some archeology, the findings are:

The zero page has PageReserved flag set, it was skipped by the explicit PageReserved check in mempolicy.c since commit f4598c8b3678 ("[PATCH] migration: make sure there is no attempt to migrate reserved pages."). The zero page was not used anymore by do_anonymous_page() since 2.6.24 by commit 557ed1fa2620 ("remove ZERO_PAGE"), then reinstated by commit a13ea5b759645 ("mm: reinstate ZERO_PAGE") and this commit added zero page check in vm_normal_page(), so mempolicy doesn't depend on PageReserved check to skip zero page anymore since then.

Quoted 1 line

So the zero page is skipped by mempolicy.c since 2.6.16.

Thanks a lot! This is really useful. Can you just add it to the changelog so others do not have to go through the painful archeology.

With that, feel free to add

Thanls!

Signature · 2 lines
Michal Hocko
SUSE Labs
author
#10 lore raw
Quoted 15 lines · Michal Hocko

On Tue 08-06-21 10:15:36, Yang Shi wrote:
[...]

Quoted 12 lines

I did some archeology, the findings are:

The zero page has PageReserved flag set, it was skipped by the explicit PageReserved check in mempolicy.c since commit f4598c8b3678 ("[PATCH] migration: make sure there is no attempt to migrate reserved pages."). The zero page was not used anymore by do_anonymous_page() since 2.6.24 by commit 557ed1fa2620 ("remove ZERO_PAGE"), then reinstated by commit a13ea5b759645 ("mm: reinstate ZERO_PAGE") and this commit added zero page check in vm_normal_page(), so mempolicy doesn't depend on PageReserved check to skip zero page anymore since then.

Quoted 7 lines
Quoted 1 line

So the zero page is skipped by mempolicy.c since 2.6.16.

Thanks a lot! This is really useful. Can you just add it to the changelog so others do not have to go through the painful archeology.

With that, feel free to add

Thanks. Will add that into v2.

Quoted 5 lines

Thanls!
--
Michal Hocko
SUSE Labs