Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1584093 > unrolled thread

[PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault.

Back to article view | Back to linux.kernel

Contents

  [PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault. "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2017-02-19 11:10 +0100
    Re: [PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault. "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2017-02-20 04:40 +0100
    Re: [PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault. Rik van Riel <riel@surriel.com> - 2017-02-20 15:00 +0100
    Re: [PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault. "Kirill A. Shutemov" <kirill@shutemov.name> - 2017-02-23 10:50 +0100

#1584093 — [PATCH] mm/thp/autonuma: Use TNF flag instead of vm fault.

We are using wrong flag value in task_numa_falt function. This can result in
us doing wrong numa fault statistics update, because we update num_pages_migrate
and numa_fault_locality etc based on the flag argument passed.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 mm/huge_memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5f3ad65c85de..8f1d93257fb9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1333,7 +1333,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 
 	if (page_nid != -1)
 		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
-				vmf->flags);
+				flags);
 
 	return 0;
 }
-- 
2.7.4

[toc] | [next] | [standalone]

#1584330

On February 19, 2017 6:00 PM Aneesh Kumar K.V wrote: 
> 
> We are using wrong flag value in task_numa_falt function. This can result in
> us doing wrong numa fault statistics update, because we update num_pages_migrate
> and numa_fault_locality etc based on the flag argument passed.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Fix: bae473a423 ("mm: introduce fault_env")
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>

> ---
>  mm/huge_memory.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 5f3ad65c85de..8f1d93257fb9 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1333,7 +1333,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
> 
>  	if (page_nid != -1)
>  		task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR,
> -				vmf->flags);
> +				flags);
> 
>  	return 0;
>  }
> --
> 2.7.4

[toc] | [prev] | [next] | [standalone]

#1584630

[Multipart message — attachments visible in raw view] — view raw

On Sun, 2017-02-19 at 15:29 +0530, Aneesh Kumar K.V wrote:
> We are using wrong flag value in task_numa_falt function. This can
> result in
> us doing wrong numa fault statistics update, because we update
> num_pages_migrate
> and numa_fault_locality etc based on the flag argument passed.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Reviewed-by: Rik van Riel <riel@redhat.com>

-- 
All Rights Reversed.

[toc] | [prev] | [next] | [standalone]

#1586783

On Sun, Feb 19, 2017 at 03:29:55PM +0530, Aneesh Kumar K.V wrote:
> We are using wrong flag value in task_numa_falt function. This can result in
> us doing wrong numa fault statistics update, because we update num_pages_migrate
> and numa_fault_locality etc based on the flag argument passed.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Ouch. My bad.

Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

-- 
 Kirill A. Shutemov

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web