thp: implement split_huge_pmd()

Original split_huge_page() combined two operations: splitting PMDs into
tables of PTEs and splitting underlying compound page.  This patch
implements split_huge_pmd() which split given PMD without splitting
other PMDs this page mapped with or underlying compound page.

Without tail page refcounting, implementation of split_huge_pmd() is
pretty straight-forward.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 124 insertions, 0 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1588f688b75d..22ab365cce52 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2666,6 +2666,130 @@ static int khugepaged(void *none)
         return 0;
 }
 
+static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
+                unsigned long haddr, pmd_t *pmd)
+{
+        struct mm_struct *mm = vma->vm_mm;
+        pgtable_t pgtable;
+        pmd_t _pmd;
+        int i;
+
+        /* leave pmd empty until pte is filled */
+        pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+
+        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+        pmd_populate(mm, &_pmd, pgtable);
+
+        for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+                pte_t *pte, entry;
+                entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot);
+                entry = pte_mkspecial(entry);
+                pte = pte_offset_map(&_pmd, haddr);
+                VM_BUG_ON(!pte_none(*pte));
+                set_pte_at(mm, haddr, pte, entry);
+                pte_unmap(pte);
+        }
+        smp_wmb(); /* make pte visible before pmd */
+        pmd_populate(mm, pmd, pgtable);
+        put_huge_zero_page();
+}
+
+static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+                unsigned long haddr)
+{
+        struct mm_struct *mm = vma->vm_mm;
+        struct page *page;
+        pgtable_t pgtable;
+        pmd_t _pmd;
+        bool young, write;
+        int i;
+
+        VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
+        VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+        VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
+        VM_BUG_ON(!pmd_trans_huge(*pmd));
+
+        count_vm_event(THP_SPLIT_PMD);
+
+        if (vma_is_dax(vma)) {
+                pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+                if (is_huge_zero_pmd(_pmd))
+                        put_huge_zero_page();
+                return;
+        } else if (is_huge_zero_pmd(*pmd)) {
+                return __split_huge_zero_page_pmd(vma, haddr, pmd);
+        }
+
+        page = pmd_page(*pmd);
+        VM_BUG_ON_PAGE(!page_count(page), page);
+        atomic_add(HPAGE_PMD_NR - 1, &page->_count);
+        write = pmd_write(*pmd);
+        young = pmd_young(*pmd);
+
+        /* leave pmd empty until pte is filled */
+        pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+
+        pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+        pmd_populate(mm, &_pmd, pgtable);
+
+        for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+                pte_t entry, *pte;
+                /*
+                 * Note that NUMA hinting access restrictions are not
+                 * transferred to avoid any possibility of altering
+                 * permissions across VMAs.
+                 */
+                entry = mk_pte(page + i, vma->vm_page_prot);
+                entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+                if (!write)
+                        entry = pte_wrprotect(entry);
+                if (!young)
+                        entry = pte_mkold(entry);
+                pte = pte_offset_map(&_pmd, haddr);
+                BUG_ON(!pte_none(*pte));
+                set_pte_at(mm, haddr, pte, entry);
+                atomic_inc(&page[i]._mapcount);
+                pte_unmap(pte);
+        }
+
+        /*
+         * Set PG_double_map before dropping compound_mapcount to avoid
+         * false-negative page_mapped().
+         */
+        if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
+                for (i = 0; i < HPAGE_PMD_NR; i++)
+                        atomic_inc(&page[i]._mapcount);
+        }
+
+        if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+                /* Last compound_mapcount is gone. */
+                __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+                if (TestClearPageDoubleMap(page)) {
+                        /* No need in mapcount reference anymore */
+                        for (i = 0; i < HPAGE_PMD_NR; i++)
+                                atomic_dec(&page[i]._mapcount);
+                }
+        }
+
+        smp_wmb(); /* make pte visible before pmd */
+        pmd_populate(mm, pmd, pgtable);
+}
+
+void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+                unsigned long address)
+{
+        spinlock_t *ptl;
+        struct mm_struct *mm = vma->vm_mm;
+        unsigned long haddr = address & HPAGE_PMD_MASK;
+
+        mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
+        ptl = pmd_lock(mm, pmd);
+        if (likely(pmd_trans_huge(*pmd)))
+                __split_huge_pmd_locked(vma, pmd, haddr);
+        spin_unlock(ptl);
+        mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
+}
+
 static void split_huge_pmd_address(struct vm_area_struct *vma,
                                     unsigned long address)
 {