During fork, the page table need to be copied from parent to child. A PMD swap mapping need to be copied too and the swap reference count need to be increased.
When the huge swap cluster has been split already, we need to split the PMD swap mapping and fallback to PTE copying. When swap count continuation failed to allocate a page with GFP_ATOMIC, we need to unlock the spinlock and try again with GFP_KERNEL. Signed-off-by: "Huang, Ying" <ying.hu...@intel.com> Cc: "Kirill A. Shutemov" <kirill.shute...@linux.intel.com> Cc: Andrea Arcangeli <aarca...@redhat.com> Cc: Michal Hocko <mho...@kernel.org> Cc: Johannes Weiner <han...@cmpxchg.org> Cc: Shaohua Li <s...@kernel.org> Cc: Hugh Dickins <hu...@google.com> Cc: Minchan Kim <minc...@kernel.org> Cc: Rik van Riel <r...@redhat.com> Cc: Dave Hansen <dave.han...@linux.intel.com> Cc: Naoya Horiguchi <n-horigu...@ah.jp.nec.com> Cc: Zi Yan <zi....@cs.rutgers.edu> Cc: Daniel Jordan <daniel.m.jor...@oracle.com> --- mm/huge_memory.c | 72 ++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 57 insertions(+), 15 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 83140c895b58..077d569da13e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -986,6 +986,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (unlikely(!pgtable)) goto out; +retry: dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -993,26 +994,67 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); - VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (is_write_migration_entry(entry)) { - make_migration_entry_read(&entry); - pmd = swp_entry_to_pmd(entry); - if (pmd_swp_soft_dirty(*src_pmd)) - pmd = pmd_swp_mksoft_dirty(pmd); - set_pmd_at(src_mm, addr, src_pmd, pmd); +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + if (is_migration_entry(entry)) { + if (is_write_migration_entry(entry)) { + make_migration_entry_read(&entry); + pmd = swp_entry_to_pmd(entry); + if (pmd_swp_soft_dirty(*src_pmd)) + pmd = pmd_swp_mksoft_dirty(pmd); + set_pmd_at(src_mm, addr, src_pmd, pmd); + } + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); + ret = 0; + goto out_unlock; } - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); - mm_inc_nr_ptes(dst_mm); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - set_pmd_at(dst_mm, addr, dst_pmd, pmd); - ret = 0; - goto out_unlock; - } #endif + if (IS_ENABLED(CONFIG_THP_SWAP) && !non_swap_entry(entry)) { + ret = swap_duplicate(&entry, HPAGE_PMD_NR); + if (!ret) { + add_mm_counter(dst_mm, MM_SWAPENTS, + HPAGE_PMD_NR); + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, + pgtable); + set_pmd_at(dst_mm, addr, dst_pmd, pmd); + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + } else if (ret == -ENOTDIR) { + /* + * The huge swap cluster has been split, split + * the PMD swap mapping and fallback to PTE + */ + __split_huge_swap_pmd(vma, addr, src_pmd); + pte_free(dst_mm, pgtable); + } else if (ret == -ENOMEM) { + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + ret = add_swap_count_continuation(entry, + GFP_KERNEL); + if (ret < 0) { + ret = -ENOMEM; + pte_free(dst_mm, pgtable); + goto out; + } + goto retry; + } else + VM_BUG_ON(1); + goto out_unlock; + } + VM_BUG_ON(1); + } if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); -- 2.18.1