| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20130318154057.GS10192@dhcp22.suse.cz>
Date: Mon, 18 Mar 2013 16:40:57 +0100
From: Michal Hocko <mhocko@...e.cz>
To: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
Mel Gorman <mel@....ul.ie>, Hugh Dickins <hughd@...gle.com>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Andi Kleen <andi@...stfloor.org>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 5/9] migrate: enable migrate_pages() to migrate hugepage
On Thu 21-02-13 14:41:44, Naoya Horiguchi wrote:
> This patch extends check_range() to handle vma with VM_HUGETLB set.
> With this changes, we can migrate hugepage with migrate_pages(2).
> Note that for larger hugepages (covered by pud entries, 1GB for
> x86_64 for example), we simply skip it now.
>
> Signed-off-by: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
> ---
> include/linux/hugetlb.h | 6 ++++--
> mm/hugetlb.c | 10 ++++++++++
> mm/mempolicy.c | 46 ++++++++++++++++++++++++++++++++++------------
> 3 files changed, 48 insertions(+), 14 deletions(-)
>
> diff --git v3.8.orig/include/linux/hugetlb.h v3.8/include/linux/hugetlb.h
> index 8f87115..eb33df5 100644
> --- v3.8.orig/include/linux/hugetlb.h
> +++ v3.8/include/linux/hugetlb.h
> @@ -69,6 +69,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
> int dequeue_hwpoisoned_huge_page(struct page *page);
> void putback_active_hugepage(struct page *page);
> void putback_active_hugepages(struct list_head *l);
> +void migrate_hugepage_add(struct page *page, struct list_head *list);
> void copy_huge_page(struct page *dst, struct page *src);
>
> extern unsigned long hugepages_treat_as_movable;
> @@ -88,8 +89,8 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
> pmd_t *pmd, int write);
> struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
> pud_t *pud, int write);
> -int pmd_huge(pmd_t pmd);
> -int pud_huge(pud_t pmd);
> +extern int pmd_huge(pmd_t pmd);
> +extern int pud_huge(pud_t pmd);
extern is not needed here.
> unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
> unsigned long address, unsigned long end, pgprot_t newprot);
>
> @@ -134,6 +135,7 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page)
>
> #define putback_active_hugepage(p) 0
> #define putback_active_hugepages(l) 0
> +#define migrate_hugepage_add(p, l) 0
> static inline void copy_huge_page(struct page *dst, struct page *src)
> {
> }
> diff --git v3.8.orig/mm/hugetlb.c v3.8/mm/hugetlb.c
> index cb9d43b8..86ffcb7 100644
> --- v3.8.orig/mm/hugetlb.c
> +++ v3.8/mm/hugetlb.c
> @@ -3202,3 +3202,13 @@ void putback_active_hugepages(struct list_head *l)
> list_for_each_entry_safe(page, page2, l, lru)
> putback_active_hugepage(page);
> }
> +
> +void migrate_hugepage_add(struct page *page, struct list_head *list)
> +{
> + VM_BUG_ON(!PageHuge(page));
> + get_page(page);
> + spin_lock(&hugetlb_lock);
Why hugetlb_lock? Comment for this lock says that it protects
hugepage_freelists, nr_huge_pages, and free_huge_pages.
> + list_move_tail(&page->lru, list);
> + spin_unlock(&hugetlb_lock);
> + return;
> +}
> diff --git v3.8.orig/mm/mempolicy.c v3.8/mm/mempolicy.c
> index e2df1c1..8627135 100644
> --- v3.8.orig/mm/mempolicy.c
> +++ v3.8/mm/mempolicy.c
> @@ -525,6 +525,27 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
> return addr != end;
> }
>
> +static void check_hugetlb_pmd_range(struct vm_area_struct *vma, pmd_t *pmd,
> + const nodemask_t *nodes, unsigned long flags,
> + void *private)
> +{
> +#ifdef CONFIG_HUGETLB_PAGE
> + int nid;
> + struct page *page;
> +
> + spin_lock(&vma->vm_mm->page_table_lock);
> + page = pte_page(huge_ptep_get((pte_t *)pmd));
> + spin_unlock(&vma->vm_mm->page_table_lock);
I am a bit confused why page_table_lock is used here and why it doesn't
cover the page usage.
> + nid = page_to_nid(page);
> + if (node_isset(nid, *nodes) != !!(flags & MPOL_MF_INVERT)
> + && ((flags & MPOL_MF_MOVE && page_mapcount(page) == 1)
> + || flags & MPOL_MF_MOVE_ALL))
> + migrate_hugepage_add(page, private);
> +#else
> + BUG();
> +#endif
> +}
> +
> static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
> unsigned long addr, unsigned long end,
> const nodemask_t *nodes, unsigned long flags,
> @@ -536,6 +557,11 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
> pmd = pmd_offset(pud, addr);
> do {
> next = pmd_addr_end(addr, end);
> + if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) {
Why an explicit check for is_vm_hugetlb_page here? Isn't pmd_huge()
sufficient?
> + check_hugetlb_pmd_range(vma, pmd, nodes,
> + flags, private);
> + continue;
> + }
> split_huge_page_pmd(vma, addr, pmd);
> if (pmd_none_or_trans_huge_or_clear_bad(pmd))
> continue;
[...]
--
Michal Hocko
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists