sched, numa, mm: Implement THP migration

Add THP migration for the NUMA working set scanning fault case.

It uses the page lock to serialize. No migration pte dance is
necessary because the pte is already unmapped when we decide
to migrate.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-yv9vbiz2s455zxq1ffzx3fye@git.kernel.org
[ Significant fixes and changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c4c0a5799aaf7b23cb4637d1d5dfbeeb0ce87982..931caf4d6e275a119044a017fcc8ec272f81ad7e 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -742,12 +742,13 @@ void do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                           unsigned int flags, pmd_t entry)
 {
        unsigned long haddr = address & HPAGE_PMD_MASK;
+       struct page *new_page = NULL;
        struct page *page = NULL;
-       int node;
+       int node, lru;
 
        spin_lock(&mm->page_table_lock);
        if (unlikely(!pmd_same(*pmd, entry)))
-               goto out_unlock;
+               goto unlock;
 
        if (unlikely(pmd_trans_splitting(entry))) {
                spin_unlock(&mm->page_table_lock);
@@ -755,45 +756,117 @@ void do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                return;
        }
 
-#ifdef CONFIG_NUMA
        page = pmd_page(entry);
-       VM_BUG_ON(!PageCompound(page) || !PageHead(page));
+       if (page) {
+               VM_BUG_ON(!PageCompound(page) || !PageHead(page));
 
-       get_page(page);
-       spin_unlock(&mm->page_table_lock);
+               get_page(page);
+               node = mpol_misplaced(page, vma, haddr);
+               if (node != -1)
+                       goto migrate;
+       }
 
-       /*
-        * XXX should we serialize against split_huge_page ?
-        */
+fixup:
+       /* change back to regular protection */
+       entry = pmd_modify(entry, vma->vm_page_prot);
+       set_pmd_at(mm, haddr, pmd, entry);
+       update_mmu_cache_pmd(vma, address, entry);
 
-       node = mpol_misplaced(page, vma, haddr);
-       if (node == -1)
-               goto do_fixup;
+unlock:
+       spin_unlock(&mm->page_table_lock);
+       if (page)
+               put_page(page);
 
-       /*
-        * Due to lacking code to migrate thp pages, we'll split
-        * (which preserves the special PROT_NONE) and re-take the
-        * fault on the normal pages.
-        */
-       split_huge_page(page);
-       put_page(page);
        return;
 
-do_fixup:
+migrate:
+       spin_unlock(&mm->page_table_lock);
+
+       lock_page(page);
        spin_lock(&mm->page_table_lock);
-       if (unlikely(!pmd_same(*pmd, entry)))
-               goto out_unlock;
-#endif
+       if (unlikely(!pmd_same(*pmd, entry))) {
+               spin_unlock(&mm->page_table_lock);
+               unlock_page(page);
+               put_page(page);
+               return;
+       }
+       spin_unlock(&mm->page_table_lock);
 
-       /* change back to regular protection */
-       entry = pmd_modify(entry, vma->vm_page_prot);
-       if (pmdp_set_access_flags(vma, haddr, pmd, entry, 1))
-               update_mmu_cache_pmd(vma, address, entry);
+       new_page = alloc_pages_node(node,
+           (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT,
+           HPAGE_PMD_ORDER);
 
-out_unlock:
+       if (!new_page)
+               goto alloc_fail;
+
+       lru = PageLRU(page);
+
+       if (lru && isolate_lru_page(page)) /* does an implicit get_page() */
+               goto alloc_fail;
+
+       if (!trylock_page(new_page))
+               BUG();
+
+       /* anon mapping, we can simply copy page->mapping to the new page: */
+       new_page->mapping = page->mapping;
+       new_page->index = page->index;
+
+       migrate_page_copy(new_page, page);
+
+       WARN_ON(PageLRU(new_page));
+
+       spin_lock(&mm->page_table_lock);
+       if (unlikely(!pmd_same(*pmd, entry))) {
+               spin_unlock(&mm->page_table_lock);
+               if (lru)
+                       putback_lru_page(page);
+
+               unlock_page(new_page);
+               ClearPageActive(new_page);      /* Set by migrate_page_copy() */
+               new_page->mapping = NULL;
+               put_page(new_page);             /* Free it */
+
+               unlock_page(page);
+               put_page(page);                 /* Drop the local reference */
+
+               return;
+       }
+
+       entry = mk_pmd(new_page, vma->vm_page_prot);
+       entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+       entry = pmd_mkhuge(entry);
+
+       page_add_new_anon_rmap(new_page, vma, haddr);
+
+       set_pmd_at(mm, haddr, pmd, entry);
+       update_mmu_cache_pmd(vma, address, entry);
+       page_remove_rmap(page);
        spin_unlock(&mm->page_table_lock);
-       if (page)
+
+       put_page(page);                 /* Drop the rmap reference */
+
+       if (lru)
+               put_page(page);         /* drop the LRU isolation reference */
+
+       unlock_page(new_page);
+       unlock_page(page);
+       put_page(page);                 /* Drop the local reference */
+
+       return;
+
+alloc_fail:
+       if (new_page)
+               put_page(new_page);
+
+       unlock_page(page);
+
+       spin_lock(&mm->page_table_lock);
+       if (unlikely(!pmd_same(*pmd, entry))) {
                put_page(page);
+               page = NULL;
+               goto unlock;
+       }
+       goto fixup;
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,

diff --git a/mm/migrate.c b/mm/migrate.c
index 32999491b6bf334c50483225111425775a143ddd..72d10560caf6d61746bf5c1747a2d63e6fab1fc2 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -417,7 +417,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
  */
 void migrate_page_copy(struct page *newpage, struct page *page)
 {
-       if (PageHuge(page))
+       if (PageHuge(page) || PageTransHuge(page))
                copy_huge_page(newpage, page);
        else
                copy_highpage(newpage, page);