[3.11.y.z extended stable] Patch "hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned entry" has been added to staging queue

[Luis Henriques]

On Thu, Jul 10, 2014 at 12:18:16PM +0100, Luis Henriques wrote:
> This is a note to let you know that I have just added a patch titled
> 
>     hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned entry
> 
> to the linux-3.11.y-queue branch of the 3.11.y.z extended stable tree 
> which can be found at:
> 
>  http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.11.y-queue
> 
> If you, or anyone else, feels it should not be added to this tree, please 
> reply to this email.
> 
> For more information about the 3.11.y.z tree, see
> https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable
> 
> Thanks.
> -Luis

Looks like this introduces a regression, so I'm dropping it from the
3.11 queue.

Cheers,
--
Luís

> 
> ------
> 
> From 9348f75740bd7ccbe894145fd96759c74425e660 Mon Sep 17 00:00:00 2001
> From: Naoya Horiguchi <n-horiguchi at ah.jp.nec.com>
> Date: Mon, 23 Jun 2014 13:22:03 -0700
> Subject: hugetlb: fix copy_hugetlb_page_range() to handle migration/hwpoisoned
>  entry
> 
> commit 4a705fef986231a3e7a6b1a6d3c37025f021f49f upstream.
> 
> There's a race between fork() and hugepage migration, as a result we try
> to "dereference" a swap entry as a normal pte, causing kernel panic.
> The cause of the problem is that copy_hugetlb_page_range() can't handle
> "swap entry" family (migration entry and hwpoisoned entry) so let's fix
> it.
> 
> [akpm at linux-foundation.org: coding-style fixes]
> Signed-off-by: Naoya Horiguchi <n-horiguchi at ah.jp.nec.com>
> Acked-by: Hugh Dickins <hughd at google.com>
> Cc: Christoph Lameter <cl at linux.com>
> Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
> Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
> [ luis: backported to 3.11: adjusted context ]
> Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
> ---
>  mm/hugetlb.c | 71 ++++++++++++++++++++++++++++++++++++------------------------
>  1 file changed, 43 insertions(+), 28 deletions(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index f8e292add228..16c25a39939f 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -2321,6 +2321,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
>  		update_mmu_cache(vma, address, ptep);
>  }
> 
> +static int is_hugetlb_entry_migration(pte_t pte)
> +{
> +	swp_entry_t swp;
> +
> +	if (huge_pte_none(pte) || pte_present(pte))
> +		return 0;
> +	swp = pte_to_swp_entry(pte);
> +	if (non_swap_entry(swp) && is_migration_entry(swp))
> +		return 1;
> +	else
> +		return 0;
> +}
> +
> +static int is_hugetlb_entry_hwpoisoned(pte_t pte)
> +{
> +	swp_entry_t swp;
> +
> +	if (huge_pte_none(pte) || pte_present(pte))
> +		return 0;
> +	swp = pte_to_swp_entry(pte);
> +	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
> +		return 1;
> +	else
> +		return 0;
> +}
> 
>  int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
>  			    struct vm_area_struct *vma)
> @@ -2348,10 +2373,26 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
> 
>  		spin_lock(&dst->page_table_lock);
>  		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
> -		if (!huge_pte_none(huge_ptep_get(src_pte))) {
> +		entry = huge_ptep_get(src_pte);
> +		if (huge_pte_none(entry)) { /* skip none entry */
> +			;
> +		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
> +				    is_hugetlb_entry_hwpoisoned(entry))) {
> +			swp_entry_t swp_entry = pte_to_swp_entry(entry);
> +
> +			if (is_write_migration_entry(swp_entry) && cow) {
> +				/*
> +				 * COW mappings require pages in both
> +				 * parent and child to be set to read.
> +				 */
> +				make_migration_entry_read(&swp_entry);
> +				entry = swp_entry_to_pte(swp_entry);
> +				set_huge_pte_at(src, addr, src_pte, entry);
> +			}
> +			set_huge_pte_at(dst, addr, dst_pte, entry);
> +		} else {
>  			if (cow)
>  				huge_ptep_set_wrprotect(src, addr, src_pte);
> -			entry = huge_ptep_get(src_pte);
>  			ptepage = pte_page(entry);
>  			get_page(ptepage);
>  			page_dup_rmap(ptepage);
> @@ -2366,32 +2407,6 @@ nomem:
>  	return -ENOMEM;
>  }
> 
> -static int is_hugetlb_entry_migration(pte_t pte)
> -{
> -	swp_entry_t swp;
> -
> -	if (huge_pte_none(pte) || pte_present(pte))
> -		return 0;
> -	swp = pte_to_swp_entry(pte);
> -	if (non_swap_entry(swp) && is_migration_entry(swp))
> -		return 1;
> -	else
> -		return 0;
> -}
> -
> -static int is_hugetlb_entry_hwpoisoned(pte_t pte)
> -{
> -	swp_entry_t swp;
> -
> -	if (huge_pte_none(pte) || pte_present(pte))
> -		return 0;
> -	swp = pte_to_swp_entry(pte);
> -	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
> -		return 1;
> -	else
> -		return 0;
> -}
> -
>  void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
>  			    unsigned long start, unsigned long end,
>  			    struct page *ref_page)
> --
> 1.9.1
>