diff options
| author |   Naoya Horiguchi <naoya.horiguchi@nec.com> | 2022-07-14 13:24:14 +0900 |
|---|---|---|
| committer |   Andrew Morton <akpm@linux-foundation.org> | 2022-08-08 18:06:43 -0700 |
| commit | 3a194f3f8ad01bce00bd7174aaba1563bcc827eb (patch) | |
| tree | fceab93f83fadb0d5567805024fde0589c649c26 | |
| parent | mm/hugetlb: check gigantic_page_runtime_supported() in return_unused_surplus_pages() (diff) | |
| download | linux-dev-3a194f3f8ad01bce00bd7174aaba1563bcc827eb.tar.xz linux-dev-3a194f3f8ad01bce00bd7174aaba1563bcc827eb.zip | |
mm/hugetlb: make pud_huge() and follow_huge_pud() aware of non-present pud entry
follow_pud_mask() does not support non-present pud entry now. As long as
I tested on x86_64 server, follow_pud_mask() still simply returns
no_page_table() for non-present_pud_entry() due to pud_bad(), so no severe
user-visible effect should happen. But generally we should call
follow_huge_pud() for non-present pud entry for 1GB hugetlb page.
Update pud_huge() and follow_huge_pud() to handle non-present pud entries.
The changes are similar to previous works for pud entries commit
e66f17ff7177 ("mm/hugetlb: take page table lock in follow_huge_pmd()") and
commit cbef8478bee5 ("mm/hugetlb: pmd_huge() returns true for non-present
hugepage").
Link: https://lkml.kernel.org/r/20220714042420.1847125-3-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Liu Shixin <liushixin2@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
| -rw-r--r-- | arch/x86/mm/hugetlbpage.c | 8 | ||||
| -rw-r--r-- | mm/hugetlb.c | 32 |
2 files changed, 37 insertions, 3 deletions
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 509408da0da1..6b3033845c6d 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -30,9 +30,15 @@ int pmd_huge(pmd_t pmd) (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } +/* + * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal + * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. + * Otherwise, returns 0. + */ int pud_huge(pud_t pud) { - return !!(pud_val(pud) & _PAGE_PSE); + return !pud_none(pud) && + (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ee6655e47213..9b79806be17b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6985,10 +6985,38 @@ struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { - if (flags & (FOLL_GET | FOLL_PIN)) + struct page *page = NULL; + spinlock_t *ptl; + pte_t pte; + + if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; - return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); +retry: + ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud); + if (!pud_huge(*pud)) + goto out; + pte = huge_ptep_get((pte_t *)pud); + if (pte_present(pte)) { + page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(pte)) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pud, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); + return page; } struct page * __weak |