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

Groups > linux.kernel > #1371895 > unrolled thread

[PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc()

Back to article view | Back to linux.kernel

Contents

  [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc() Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> - 2016-04-05 21:10 +0200
    Re: [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc() Michal Hocko <mhocko@kernel.org> - 2016-04-06 12:00 +0200
      Re: [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc() "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-04-06 12:30 +0200
        Re: [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc() Michal Hocko <mhocko@kernel.org> - 2016-04-06 13:30 +0200

#1371895 — [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc()

From f7b73c6b4508fe9b141a43d92be2f9dd7d3c4a58 Mon Sep 17 00:00:00 2001
From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Date: Thu, 24 Mar 2016 02:07:57 -0400
Subject: [PATCH 1/1] powerpc/mm: Add memory barrier in __hugepte_alloc()

__hugepte_alloc() uses kmem_cache_zalloc() to allocate a zeroed PTE
and proceeds to use the newly allocated PTE. Add a memory barrier to
make sure that the other CPUs see a properly initialized PTE.

Based on a fix suggested by James Dykman.

Reported-by: James Dykman <jdykman@us.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Tested-by: James Dykman <jdykman@us.ibm.com>
---
Note:
	The bug was encountered and fix tested on an older version
	of the kernel. Forward porting to mainline.
---
 arch/powerpc/mm/hugetlbpage.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index d991b9e..081f679 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 	if (! new)
 		return -ENOMEM;
 
+	/*
+	 * Make sure other cpus find the hugepd set only after a
+	 * properly initialized page table is visible to them.
+	 * For more details look for comment in __pte_alloc().
+	 */
+	smp_wmb();
+
 	spin_lock(&mm->page_table_lock);
 #ifdef CONFIG_PPC_FSL_BOOK3E
 	/*
-- 
1.8.3.1

[toc] | [next] | [standalone]

#1372353

On Tue 05-04-16 12:05:47, Sukadev Bhattiprolu wrote:
[...]
> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index d991b9e..081f679 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
>  	if (! new)
>  		return -ENOMEM;
>  
> +	/*
> +	 * Make sure other cpus find the hugepd set only after a
> +	 * properly initialized page table is visible to them.
> +	 * For more details look for comment in __pte_alloc().
> +	 */
> +	smp_wmb();
> +

what is the pairing memory barrier?

>  	spin_lock(&mm->page_table_lock);
>  #ifdef CONFIG_PPC_FSL_BOOK3E
>  	/*
> -- 
> 1.8.3.1

-- 
Michal Hocko
SUSE Labs

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

#1372375

Michal Hocko <mhocko@kernel.org> writes:

> [ text/plain ]
> On Tue 05-04-16 12:05:47, Sukadev Bhattiprolu wrote:
> [...]
>> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
>> index d991b9e..081f679 100644
>> --- a/arch/powerpc/mm/hugetlbpage.c
>> +++ b/arch/powerpc/mm/hugetlbpage.c
>> @@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
>>  	if (! new)
>>  		return -ENOMEM;
>>  
>> +	/*
>> +	 * Make sure other cpus find the hugepd set only after a
>> +	 * properly initialized page table is visible to them.
>> +	 * For more details look for comment in __pte_alloc().
>> +	 */
>> +	smp_wmb();
>> +
>
> what is the pairing memory barrier?
>
>>  	spin_lock(&mm->page_table_lock);
>>  #ifdef CONFIG_PPC_FSL_BOOK3E
>>  	/*

This is documented in __pte_alloc(). I didn't want to repeat the same
here.

	/*
	 * Ensure all pte setup (eg. pte page lock and page clearing) are
	 * visible before the pte is made visible to other CPUs by being
	 * put into page tables.
	 *
	 * The other side of the story is the pointer chasing in the page
	 * table walking code (when walking the page table without locking;
	 * ie. most of the time). Fortunately, these data accesses consist
	 * of a chain of data-dependent loads, meaning most CPUs (alpha
	 * being the notable exception) will already guarantee loads are
	 * seen in-order. See the alpha page table accessors for the
	 * smp_read_barrier_depends() barriers in page table walking code.
	 */
	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */


-aneesh

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

#1372407

On Wed 06-04-16 15:39:17, Aneesh Kumar K.V wrote:
> Michal Hocko <mhocko@kernel.org> writes:
> 
> > [ text/plain ]
> > On Tue 05-04-16 12:05:47, Sukadev Bhattiprolu wrote:
> > [...]
> >> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> >> index d991b9e..081f679 100644
> >> --- a/arch/powerpc/mm/hugetlbpage.c
> >> +++ b/arch/powerpc/mm/hugetlbpage.c
> >> @@ -81,6 +81,13 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
> >>  	if (! new)
> >>  		return -ENOMEM;
> >>  
> >> +	/*
> >> +	 * Make sure other cpus find the hugepd set only after a
> >> +	 * properly initialized page table is visible to them.
> >> +	 * For more details look for comment in __pte_alloc().
> >> +	 */
> >> +	smp_wmb();
> >> +
> >
> > what is the pairing memory barrier?
> >
> >>  	spin_lock(&mm->page_table_lock);
> >>  #ifdef CONFIG_PPC_FSL_BOOK3E
> >>  	/*
> 
> This is documented in __pte_alloc(). I didn't want to repeat the same
> here.
> 
> 	/*
> 	 * Ensure all pte setup (eg. pte page lock and page clearing) are
> 	 * visible before the pte is made visible to other CPUs by being
> 	 * put into page tables.
> 	 *
> 	 * The other side of the story is the pointer chasing in the page
> 	 * table walking code (when walking the page table without locking;
> 	 * ie. most of the time). Fortunately, these data accesses consist
> 	 * of a chain of data-dependent loads, meaning most CPUs (alpha
> 	 * being the notable exception) will already guarantee loads are
> 	 * seen in-order. See the alpha page table accessors for the
> 	 * smp_read_barrier_depends() barriers in page table walking code.
> 	 */
> 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */

OK, I have missed the reference to __pte_alloc. My bad!

-- 
Michal Hocko
SUSE Labs

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web