Re: [ 29/48] mm: migration: add migrate_entry_wait_huge()

[Satoru Takeuchi]

Hi Naoya,

At Tue, 18 Jun 2013 09:17:55 -0700,
Greg Kroah-Hartman wrote:
> 
> From: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> 
> 3.9-stable review patch.  If anyone has any objections, please let me know.
> 
> ------------------
> 
> From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> 
> commit 30dad30922ccc733cfdbfe232090cf674dc374dc upstream.
> 
> When we have a page fault for the address which is backed by a hugepage
> under migration, the kernel can't wait correctly and do busy looping on
> hugepage fault until the migration finishes.  As a result, users who try
> to kick hugepage migration (via soft offlining, for example) occasionally
> experience long delay or soft lockup.
> 
> This is because pte_offset_map_lock() can't get a correct migration entry
> or a correct page table lock for hugepage.  This patch introduces
> migration_entry_wait_huge() to solve this.

I suspect that this code doesn't work correctly on i686 box with CONFIG_HIGHPTE.
If we call hugetlb_fault() -> migration_entry_wait_huge() -> __migration_entry_wait(),
this function tries to kunmap pte, in this case pte is not-kmapped pmd, via pte_unmap_unlock().
If CONFIG_DEBUG_HIGHMEM is also enabled, it results in BUG_ON() at __kunmap_atomic().

Correct me if I'm wrong.

Thanks,
Satoru

> 
> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
> Reviewed-by: Wanpeng Li <liwanp@xxxxxxxxxxxxxxxxxx>
> Reviewed-by: Michal Hocko <mhocko@xxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> 
> ---
>  include/linux/swapops.h |    3 +++
>  mm/hugetlb.c            |    2 +-
>  mm/migrate.c            |   23 ++++++++++++++++++-----
>  3 files changed, 22 insertions(+), 6 deletions(-)
> 
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -137,6 +137,7 @@ static inline void make_migration_entry_
>  
>  extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
>  					unsigned long address);
> +extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
>  #else
>  
>  #define make_migration_entry(page, write) swp_entry(0, 0)
> @@ -148,6 +149,8 @@ static inline int is_migration_entry(swp
>  static inline void make_migration_entry_read(swp_entry_t *entryp) { }
>  static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
>  					 unsigned long address) { }
> +static inline void migration_entry_wait_huge(struct mm_struct *mm,
> +					pte_t *pte) { }
>  static inline int is_write_migration_entry(swp_entry_t entry)
>  {
>  	return 0;
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2823,7 +2823,7 @@ int hugetlb_fault(struct mm_struct *mm,
>  	if (ptep) {
>  		entry = huge_ptep_get(ptep);
>  		if (unlikely(is_hugetlb_entry_migration(entry))) {
> -			migration_entry_wait(mm, (pmd_t *)ptep, address);
> +			migration_entry_wait_huge(mm, ptep);
>  			return 0;
>  		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
>  			return VM_FAULT_HWPOISON_LARGE |
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -200,15 +200,14 @@ static void remove_migration_ptes(struct
>   * get to the page and wait until migration is finished.
>   * When we return from this function the fault will be retried.
>   */
> -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
> -				unsigned long address)
> +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
> +				spinlock_t *ptl)
>  {
> -	pte_t *ptep, pte;
> -	spinlock_t *ptl;
> +	pte_t pte;
>  	swp_entry_t entry;
>  	struct page *page;
>  
> -	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
> +	spin_lock(ptl);
>  	pte = *ptep;
>  	if (!is_swap_pte(pte))
>  		goto out;
> @@ -236,6 +235,20 @@ out:
>  	pte_unmap_unlock(ptep, ptl);
>  }
>  
> +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
> +				unsigned long address)
> +{
> +	spinlock_t *ptl = pte_lockptr(mm, pmd);
> +	pte_t *ptep = pte_offset_map(pmd, address);
> +	__migration_entry_wait(mm, ptep, ptl);
> +}
> +
> +void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
> +{
> +	spinlock_t *ptl = &(mm)->page_table_lock;
> +	__migration_entry_wait(mm, pte, ptl);
> +}
> +
>  #ifdef CONFIG_BLOCK
>  /* Returns true if all buffers are successfully locked */
>  static bool buffer_migrate_lock_buffers(struct buffer_head *head,
> 
> 
> --
> To unsubscribe from this list: send the line "unsubscribe stable" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/