[v4] fix follow_page related issues

[PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Haiyue Wang 3 years, 7 months ago

Not all huge page APIs support FOLL_GET option, so the __NR_move_pages
will fail to get the page node information for huge page.

This is an temporary solution to mitigate the racing fix.

After supporting follow huge page by FOLL_GET is done, this fix can be
reverted safely.

Fixes: 4cd614841c06 ("mm: migration: fix possible do_pages_stat_array racing with memory offline")
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
---
 mm/migrate.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 6a1597c92261..581dfaad9257 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 
 	for (i = 0; i < nr_pages; i++) {
 		unsigned long addr = (unsigned long)(*pages);
+		unsigned int foll_flags = FOLL_DUMP;
 		struct vm_area_struct *vma;
 		struct page *page;
 		int err = -EFAULT;
@@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 		if (!vma)
 			goto set_status;
 
+		/* Not all huge page follow APIs support 'FOLL_GET' */
+		if (!is_vm_hugetlb_page(vma))
+			foll_flags |= FOLL_GET;
+
 		/* FOLL_DUMP to ignore special (like zero) pages */
-		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
+		page = follow_page(vma, addr, foll_flags);
 
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
@@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 
 		if (page && !is_zone_device_page(page)) {
 			err = page_to_nid(page);
-			put_page(page);
+			if (foll_flags & FOLL_GET)
+				put_page(page);
 		} else {
 			err = -ENOENT;
 		}
-- 
2.37.2

Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Alistair Popple 3 years, 7 months ago

On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> Not all huge page APIs support FOLL_GET option, so the __NR_move_pages
> will fail to get the page node information for huge page.

I think you should be explicit in the commit message about which functions do 
not support FOLL_GET as it's not obvious what support needs to be added before 
this fix can be reverted.

Thanks.

 - Alistair

> This is an temporary solution to mitigate the racing fix.
> 
> After supporting follow huge page by FOLL_GET is done, this fix can be
> reverted safely.
> 
> Fixes: 4cd614841c06 ("mm: migration: fix possible do_pages_stat_array racing 
with memory offline")
> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> ---
>  mm/migrate.c | 10 ++++++++--
>  1 file changed, 8 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 6a1597c92261..581dfaad9257 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct mm_struct *mm, 
unsigned long nr_pages,
>  
>  	for (i = 0; i < nr_pages; i++) {
>  		unsigned long addr = (unsigned long)(*pages);
> +		unsigned int foll_flags = FOLL_DUMP;
>  		struct vm_area_struct *vma;
>  		struct page *page;
>  		int err = -EFAULT;
> @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct mm_struct *mm, 
unsigned long nr_pages,
>  		if (!vma)
>  			goto set_status;
>  
> +		/* Not all huge page follow APIs support 'FOLL_GET' */
> +		if (!is_vm_hugetlb_page(vma))
> +			foll_flags |= FOLL_GET;
> +
>  		/* FOLL_DUMP to ignore special (like zero) pages */
> -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> +		page = follow_page(vma, addr, foll_flags);
>  
>  		err = PTR_ERR(page);
>  		if (IS_ERR(page))
> @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct mm_struct *mm, 
unsigned long nr_pages,
>  
>  		if (page && !is_zone_device_page(page)) {
>  			err = page_to_nid(page);
> -			put_page(page);
> +			if (foll_flags & FOLL_GET)
> +				put_page(page);
>  		} else {
>  			err = -ENOENT;
>  		}
>

RE: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Wang, Haiyue 3 years, 7 months ago

> -----Original Message-----
> From: Alistair Popple <apopple@nvidia.com>
> Sent: Monday, August 15, 2022 12:29
> To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue <haiyue.wang@intel.com>
> Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com; Huang, Ying
> <ying.huang@intel.com>; songmuchun@bytedance.com; naoya.horiguchi@linux.dev; alex.sierra@amd.com; Wang,
> Haiyue <haiyue.wang@intel.com>
> Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page
> 
> On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> > Not all huge page APIs support FOLL_GET option, so the __NR_move_pages
> > will fail to get the page node information for huge page.
> 
> I think you should be explicit in the commit message about which functions do
> not support FOLL_GET as it's not obvious what support needs to be added before
> this fix can be reverted.

Yes, make sense, will add them in new patch.

> 
> Thanks.
> 
>  - Alistair
> 
> > This is an temporary solution to mitigate the racing fix.
> >
> > After supporting follow huge page by FOLL_GET is done, this fix can be
> > reverted safely.
> >
> > Fixes: 4cd614841c06 ("mm: migration: fix possible do_pages_stat_array racing
> with memory offline")
> > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> > ---
> >  mm/migrate.c | 10 ++++++++--
> >  1 file changed, 8 insertions(+), 2 deletions(-)
> >
> > diff --git a/mm/migrate.c b/mm/migrate.c
> > index 6a1597c92261..581dfaad9257 100644
> > --- a/mm/migrate.c
> > +++ b/mm/migrate.c
> > @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct mm_struct *mm,
> unsigned long nr_pages,
> >
> >  	for (i = 0; i < nr_pages; i++) {
> >  		unsigned long addr = (unsigned long)(*pages);
> > +		unsigned int foll_flags = FOLL_DUMP;
> >  		struct vm_area_struct *vma;
> >  		struct page *page;
> >  		int err = -EFAULT;
> > @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct mm_struct *mm,
> unsigned long nr_pages,
> >  		if (!vma)
> >  			goto set_status;
> >
> > +		/* Not all huge page follow APIs support 'FOLL_GET' */
> > +		if (!is_vm_hugetlb_page(vma))
> > +			foll_flags |= FOLL_GET;
> > +
> >  		/* FOLL_DUMP to ignore special (like zero) pages */
> > -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> > +		page = follow_page(vma, addr, foll_flags);
> >
> >  		err = PTR_ERR(page);
> >  		if (IS_ERR(page))
> > @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct mm_struct *mm,
> unsigned long nr_pages,
> >
> >  		if (page && !is_zone_device_page(page)) {
> >  			err = page_to_nid(page);
> > -			put_page(page);
> > +			if (foll_flags & FOLL_GET)
> > +				put_page(page);
> >  		} else {
> >  			err = -ENOENT;
> >  		}
> >
> 
> 
>

Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Alistair Popple 3 years, 7 months ago

On Monday, 15 August 2022 2:40:48 PM AEST Wang, Haiyue wrote:
> > -----Original Message-----
> > From: Alistair Popple <apopple@nvidia.com>
> > Sent: Monday, August 15, 2022 12:29
> > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue 
<haiyue.wang@intel.com>
> > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com; 
Huang, Ying
> > <ying.huang@intel.com>; songmuchun@bytedance.com; 
naoya.horiguchi@linux.dev; alex.sierra@amd.com; Wang,
> > Haiyue <haiyue.wang@intel.com>
> > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on 
following huge page
> > 
> > On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> > > Not all huge page APIs support FOLL_GET option, so the __NR_move_pages
> > > will fail to get the page node information for huge page.
> > 
> > I think you should be explicit in the commit message about which functions 
do
> > not support FOLL_GET as it's not obvious what support needs to be added 
before
> > this fix can be reverted.
> 
> Yes, make sense, will add them in new patch.

Actually while you're at it I think it would be good to include a description 
of the impact of this failure in the commit message. Ie. You're answer to:

> What are the user-visible runtime effects of this bug?

As it documents what should be tested if this fix does actually ever get 
reverted.

> > 
> > Thanks.
> > 
> >  - Alistair
> > 
> > > This is an temporary solution to mitigate the racing fix.
> > >
> > > After supporting follow huge page by FOLL_GET is done, this fix can be
> > > reverted safely.
> > >
> > > Fixes: 4cd614841c06 ("mm: migration: fix possible do_pages_stat_array 
racing
> > with memory offline")
> > > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> > > ---
> > >  mm/migrate.c | 10 ++++++++--
> > >  1 file changed, 8 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/mm/migrate.c b/mm/migrate.c
> > > index 6a1597c92261..581dfaad9257 100644
> > > --- a/mm/migrate.c
> > > +++ b/mm/migrate.c
> > > @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct mm_struct 
*mm,
> > unsigned long nr_pages,
> > >
> > >  	for (i = 0; i < nr_pages; i++) {
> > >  		unsigned long addr = (unsigned long)(*pages);
> > > +		unsigned int foll_flags = FOLL_DUMP;
> > >  		struct vm_area_struct *vma;
> > >  		struct page *page;
> > >  		int err = -EFAULT;
> > > @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct mm_struct 
*mm,
> > unsigned long nr_pages,
> > >  		if (!vma)
> > >  			goto set_status;
> > >
> > > +		/* Not all huge page follow APIs support 'FOLL_GET' */
> > > +		if (!is_vm_hugetlb_page(vma))
> > > +			foll_flags |= FOLL_GET;
> > > +
> > >  		/* FOLL_DUMP to ignore special (like zero) pages */
> > > -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> > > +		page = follow_page(vma, addr, foll_flags);
> > >
> > >  		err = PTR_ERR(page);
> > >  		if (IS_ERR(page))
> > > @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct mm_struct 
*mm,
> > unsigned long nr_pages,
> > >
> > >  		if (page && !is_zone_device_page(page)) {
> > >  			err = page_to_nid(page);
> > > -			put_page(page);
> > > +			if (foll_flags & FOLL_GET)
> > > +				put_page(page);
> > >  		} else {
> > >  			err = -ENOENT;
> > >  		}
> > >
> > 
> > 
> > 
> 
>

RE: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Wang, Haiyue 3 years, 7 months ago

> -----Original Message-----
> From: Alistair Popple <apopple@nvidia.com>
> Sent: Monday, August 15, 2022 13:17
> To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue <haiyue.wang@intel.com>
> Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com; Huang, Ying
> <ying.huang@intel.com>; songmuchun@bytedance.com; naoya.horiguchi@linux.dev; alex.sierra@amd.com
> Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page
> 
> On Monday, 15 August 2022 2:40:48 PM AEST Wang, Haiyue wrote:
> > > -----Original Message-----
> > > From: Alistair Popple <apopple@nvidia.com>
> > > Sent: Monday, August 15, 2022 12:29
> > > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue
> <haiyue.wang@intel.com>
> > > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com;
> Huang, Ying
> > > <ying.huang@intel.com>; songmuchun@bytedance.com;
> naoya.horiguchi@linux.dev; alex.sierra@amd.com; Wang,
> > > Haiyue <haiyue.wang@intel.com>
> > > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on
> following huge page
> > >
> > > On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> > > > Not all huge page APIs support FOLL_GET option, so the __NR_move_pages
> > > > will fail to get the page node information for huge page.
> > >
> > > I think you should be explicit in the commit message about which functions
> do
> > > not support FOLL_GET as it's not obvious what support needs to be added
> before
> > > this fix can be reverted.
> >
> > Yes, make sense, will add them in new patch.
> 
> Actually while you're at it I think it would be good to include a description
> of the impact of this failure in the commit message. Ie. You're answer to:
> 
> > What are the user-visible runtime effects of this bug?
> 
> As it documents what should be tested if this fix does actually ever get
> reverted.

An short example *.c code to capture the bug in commit message ?

> 
> > >
> > > Thanks.
> > >
> > >  - Alistair
> > >
> > > > This is an temporary solution to mitigate the racing fix.
> > > >
> > > > After supporting follow huge page by FOLL_GET is done, this fix can be
> > > > reverted safely.
> > > >
> > > > Fixes: 4cd614841c06 ("mm: migration: fix possible do_pages_stat_array
> racing
> > > with memory offline")
> > > > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> > > > ---
> > > >  mm/migrate.c | 10 ++++++++--
> > > >  1 file changed, 8 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/mm/migrate.c b/mm/migrate.c
> > > > index 6a1597c92261..581dfaad9257 100644
> > > > --- a/mm/migrate.c
> > > > +++ b/mm/migrate.c
> > > > @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct mm_struct
> *mm,
> > > unsigned long nr_pages,
> > > >
> > > >  	for (i = 0; i < nr_pages; i++) {
> > > >  		unsigned long addr = (unsigned long)(*pages);
> > > > +		unsigned int foll_flags = FOLL_DUMP;
> > > >  		struct vm_area_struct *vma;
> > > >  		struct page *page;
> > > >  		int err = -EFAULT;
> > > > @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct mm_struct
> *mm,
> > > unsigned long nr_pages,
> > > >  		if (!vma)
> > > >  			goto set_status;
> > > >
> > > > +		/* Not all huge page follow APIs support 'FOLL_GET' */
> > > > +		if (!is_vm_hugetlb_page(vma))
> > > > +			foll_flags |= FOLL_GET;
> > > > +
> > > >  		/* FOLL_DUMP to ignore special (like zero) pages */
> > > > -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> > > > +		page = follow_page(vma, addr, foll_flags);
> > > >
> > > >  		err = PTR_ERR(page);
> > > >  		if (IS_ERR(page))
> > > > @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct mm_struct
> *mm,
> > > unsigned long nr_pages,
> > > >
> > > >  		if (page && !is_zone_device_page(page)) {
> > > >  			err = page_to_nid(page);
> > > > -			put_page(page);
> > > > +			if (foll_flags & FOLL_GET)
> > > > +				put_page(page);
> > > >  		} else {
> > > >  			err = -ENOENT;
> > > >  		}
> > > >
> > >
> > >
> > >
> >
> >
> 
> 
>

Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Alistair Popple 3 years, 7 months ago

On Monday, 15 August 2022 3:20:28 PM AEST Wang, Haiyue wrote:
> > -----Original Message-----
> > From: Alistair Popple <apopple@nvidia.com>
> > Sent: Monday, August 15, 2022 13:17
> > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue 
<haiyue.wang@intel.com>
> > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com; 
Huang, Ying
> > <ying.huang@intel.com>; songmuchun@bytedance.com; 
naoya.horiguchi@linux.dev; alex.sierra@amd.com
> > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on 
following huge page
> > 
> > On Monday, 15 August 2022 2:40:48 PM AEST Wang, Haiyue wrote:
> > > > -----Original Message-----
> > > > From: Alistair Popple <apopple@nvidia.com>
> > > > Sent: Monday, August 15, 2022 12:29
> > > > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue
> > <haiyue.wang@intel.com>
> > > > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com;
> > Huang, Ying
> > > > <ying.huang@intel.com>; songmuchun@bytedance.com;
> > naoya.horiguchi@linux.dev; alex.sierra@amd.com; Wang,
> > > > Haiyue <haiyue.wang@intel.com>
> > > > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on
> > following huge page
> > > >
> > > > On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> > > > > Not all huge page APIs support FOLL_GET option, so the 
__NR_move_pages
> > > > > will fail to get the page node information for huge page.
> > > >
> > > > I think you should be explicit in the commit message about which 
functions
> > do
> > > > not support FOLL_GET as it's not obvious what support needs to be 
added
> > before
> > > > this fix can be reverted.
> > >
> > > Yes, make sense, will add them in new patch.
> > 
> > Actually while you're at it I think it would be good to include a 
description
> > of the impact of this failure in the commit message. Ie. You're answer to:
> > 
> > > What are the user-visible runtime effects of this bug?
> > 
> > As it documents what should be tested if this fix does actually ever get
> > reverted.
> 
> An short example *.c code to capture the bug in commit message ?

That's probably overkill. Just being a bit more explicit about the 
circumstances in which sys_move_pages() actually fails would be good. Eg. 
something like this:

"Without this sys_move_pages() will return -ENOENT for 1GB huge page
memory map when dumping the page node information for nodes != NULL"

> > 
> > > >
> > > > Thanks.
> > > >
> > > >  - Alistair
> > > >
> > > > > This is an temporary solution to mitigate the racing fix.
> > > > >
> > > > > After supporting follow huge page by FOLL_GET is done, this fix can 
be
> > > > > reverted safely.
> > > > >
> > > > > Fixes: 4cd614841c06 ("mm: migration: fix possible 
do_pages_stat_array
> > racing
> > > > with memory offline")
> > > > > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> > > > > ---
> > > > >  mm/migrate.c | 10 ++++++++--
> > > > >  1 file changed, 8 insertions(+), 2 deletions(-)
> > > > >
> > > > > diff --git a/mm/migrate.c b/mm/migrate.c
> > > > > index 6a1597c92261..581dfaad9257 100644
> > > > > --- a/mm/migrate.c
> > > > > +++ b/mm/migrate.c
> > > > > @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct 
mm_struct
> > *mm,
> > > > unsigned long nr_pages,
> > > > >
> > > > >  	for (i = 0; i < nr_pages; i++) {
> > > > >  		unsigned long addr = (unsigned long)(*pages);
> > > > > +		unsigned int foll_flags = FOLL_DUMP;
> > > > >  		struct vm_area_struct *vma;
> > > > >  		struct page *page;
> > > > >  		int err = -EFAULT;
> > > > > @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct 
mm_struct
> > *mm,
> > > > unsigned long nr_pages,
> > > > >  		if (!vma)
> > > > >  			goto set_status;
> > > > >
> > > > > +		/* Not all huge page follow APIs support 'FOLL_GET' 
*/
> > > > > +		if (!is_vm_hugetlb_page(vma))
> > > > > +			foll_flags |= FOLL_GET;
> > > > > +
> > > > >  		/* FOLL_DUMP to ignore special (like zero) pages */
> > > > > -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> > > > > +		page = follow_page(vma, addr, foll_flags);
> > > > >
> > > > >  		err = PTR_ERR(page);
> > > > >  		if (IS_ERR(page))
> > > > > @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct 
mm_struct
> > *mm,
> > > > unsigned long nr_pages,
> > > > >
> > > > >  		if (page && !is_zone_device_page(page)) {
> > > > >  			err = page_to_nid(page);
> > > > > -			put_page(page);
> > > > > +			if (foll_flags & FOLL_GET)
> > > > > +				put_page(page);
> > > > >  		} else {
> > > > >  			err = -ENOENT;
> > > > >  		}
> > > > >
> > > >
> > > >
> > > >
> > >
> > >
> > 
> > 
> > 
> 
>

RE: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page

Posted by Wang, Haiyue 3 years, 7 months ago

> -----Original Message-----
> From: Alistair Popple <apopple@nvidia.com>
> Sent: Monday, August 15, 2022 13:35
> To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue <haiyue.wang@intel.com>
> Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com; Huang, Ying
> <ying.huang@intel.com>; songmuchun@bytedance.com; naoya.horiguchi@linux.dev; alex.sierra@amd.com
> Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page
> 
> On Monday, 15 August 2022 3:20:28 PM AEST Wang, Haiyue wrote:
> > > -----Original Message-----
> > > From: Alistair Popple <apopple@nvidia.com>
> > > Sent: Monday, August 15, 2022 13:17
> > > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue
> <haiyue.wang@intel.com>
> > > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com;
> Huang, Ying
> > > <ying.huang@intel.com>; songmuchun@bytedance.com;
> naoya.horiguchi@linux.dev; alex.sierra@amd.com
> > > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on
> following huge page
> > >
> > > On Monday, 15 August 2022 2:40:48 PM AEST Wang, Haiyue wrote:
> > > > > -----Original Message-----
> > > > > From: Alistair Popple <apopple@nvidia.com>
> > > > > Sent: Monday, August 15, 2022 12:29
> > > > > To: linux-mm@kvack.org; linux-kernel@vger.kernel.org; Wang, Haiyue
> > > <haiyue.wang@intel.com>
> > > > > Cc: akpm@linux-foundation.org; david@redhat.com; linmiaohe@huawei.com;
> > > Huang, Ying
> > > > > <ying.huang@intel.com>; songmuchun@bytedance.com;
> > > naoya.horiguchi@linux.dev; alex.sierra@amd.com; Wang,
> > > > > Haiyue <haiyue.wang@intel.com>
> > > > > Subject: Re: [PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on
> > > following huge page
> > > > >
> > > > > On Monday, 15 August 2022 11:59:08 AM AEST Haiyue Wang wrote:
> > > > > > Not all huge page APIs support FOLL_GET option, so the
> __NR_move_pages
> > > > > > will fail to get the page node information for huge page.
> > > > >
> > > > > I think you should be explicit in the commit message about which
> functions
> > > do
> > > > > not support FOLL_GET as it's not obvious what support needs to be
> added
> > > before
> > > > > this fix can be reverted.
> > > >
> > > > Yes, make sense, will add them in new patch.
> > >
> > > Actually while you're at it I think it would be good to include a
> description
> > > of the impact of this failure in the commit message. Ie. You're answer to:
> > >
> > > > What are the user-visible runtime effects of this bug?
> > >
> > > As it documents what should be tested if this fix does actually ever get
> > > reverted.
> >
> > An short example *.c code to capture the bug in commit message ?
> 
> That's probably overkill. Just being a bit more explicit about the
> circumstances in which sys_move_pages() actually fails would be good. Eg.
> something like this:
> 
> "Without this sys_move_pages() will return -ENOENT for 1GB huge page
> memory map when dumping the page node information for nodes != NULL"

OK, understood, will try to add more information about the error. ;-)

> 
> > >
> > > > >
> > > > > Thanks.
> > > > >
> > > > >  - Alistair
> > > > >
> > > > > > This is an temporary solution to mitigate the racing fix.
> > > > > >
> > > > > > After supporting follow huge page by FOLL_GET is done, this fix can
> be
> > > > > > reverted safely.
> > > > > >
> > > > > > Fixes: 4cd614841c06 ("mm: migration: fix possible
> do_pages_stat_array
> > > racing
> > > > > with memory offline")
> > > > > > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> > > > > > ---
> > > > > >  mm/migrate.c | 10 ++++++++--
> > > > > >  1 file changed, 8 insertions(+), 2 deletions(-)
> > > > > >
> > > > > > diff --git a/mm/migrate.c b/mm/migrate.c
> > > > > > index 6a1597c92261..581dfaad9257 100644
> > > > > > --- a/mm/migrate.c
> > > > > > +++ b/mm/migrate.c
> > > > > > @@ -1848,6 +1848,7 @@ static void do_pages_stat_array(struct
> mm_struct
> > > *mm,
> > > > > unsigned long nr_pages,
> > > > > >
> > > > > >  	for (i = 0; i < nr_pages; i++) {
> > > > > >  		unsigned long addr = (unsigned long)(*pages);
> > > > > > +		unsigned int foll_flags = FOLL_DUMP;
> > > > > >  		struct vm_area_struct *vma;
> > > > > >  		struct page *page;
> > > > > >  		int err = -EFAULT;
> > > > > > @@ -1856,8 +1857,12 @@ static void do_pages_stat_array(struct
> mm_struct
> > > *mm,
> > > > > unsigned long nr_pages,
> > > > > >  		if (!vma)
> > > > > >  			goto set_status;
> > > > > >
> > > > > > +		/* Not all huge page follow APIs support 'FOLL_GET'
> */
> > > > > > +		if (!is_vm_hugetlb_page(vma))
> > > > > > +			foll_flags |= FOLL_GET;
> > > > > > +
> > > > > >  		/* FOLL_DUMP to ignore special (like zero) pages */
> > > > > > -		page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
> > > > > > +		page = follow_page(vma, addr, foll_flags);
> > > > > >
> > > > > >  		err = PTR_ERR(page);
> > > > > >  		if (IS_ERR(page))
> > > > > > @@ -1865,7 +1870,8 @@ static void do_pages_stat_array(struct
> mm_struct
> > > *mm,
> > > > > unsigned long nr_pages,
> > > > > >
> > > > > >  		if (page && !is_zone_device_page(page)) {
> > > > > >  			err = page_to_nid(page);
> > > > > > -			put_page(page);
> > > > > > +			if (foll_flags & FOLL_GET)
> > > > > > +				put_page(page);
> > > > > >  		} else {
> > > > > >  			err = -ENOENT;
> > > > > >  		}
> > > > > >
> > > > >
> > > > >
> > > > >
> > > >
> > > >
> > >
> > >
> > >
> >
> >
> 
> 
>

[PATCH v4 1/2] mm: migration: fix the FOLL_GET failure on following huge page
[PATCH v4 2/2] mm: fix the handling Non-LRU pages returned by follow_page