Merge branch 'slab/rcu' into slab/next

Conflicts:
	mm/slub.c

1 files changed, 42 insertions, 30 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e187454d82f6..dbe99a5f2073 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -650,10 +650,10 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag)
 
 static inline struct page *alloc_hugepage_vma(int defrag,
                                               struct vm_area_struct *vma,
-                                              unsigned long haddr)
+                                              unsigned long haddr, int nd)
 {
         return alloc_pages_vma(alloc_hugepage_gfpmask(defrag),
-                               HPAGE_PMD_ORDER, vma, haddr);
+                               HPAGE_PMD_ORDER, vma, haddr, nd);
 }
 
 #ifndef CONFIG_NUMA
@@ -678,7 +678,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 if (unlikely(khugepaged_enter(vma)))
                         return VM_FAULT_OOM;
                 page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-                                          vma, haddr);
+                                          vma, haddr, numa_node_id());
                 if (unlikely(!page))
                         goto out;
                 if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
@@ -799,8 +799,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
         }
 
         for (i = 0; i < HPAGE_PMD_NR; i++) {
-                pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
-                                          vma, address);
+                pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE,
+                                               vma, address, page_to_nid(page));
                 if (unlikely(!pages[i] ||
                              mem_cgroup_newpage_charge(pages[i], mm,
                                                        GFP_KERNEL))) {
@@ -902,7 +902,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
         if (transparent_hugepage_enabled(vma) &&
             !transparent_hugepage_debug_cow())
                 new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-                                              vma, haddr);
+                                              vma, haddr, numa_node_id());
         else
                 new_page = NULL;
 
@@ -1162,7 +1162,12 @@ static void __split_huge_page_refcount(struct page *page)
                 /* after clearing PageTail the gup refcount can be released */
                 smp_mb();
 
-                page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
+                /*
+                 * retain hwpoison flag of the poisoned tail page:
+                 *   fix for the unsuitable process killed on Guest Machine(KVM)
+                 *   by the memory-failure.
+                 */
+                page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
                 page_tail->flags |= (page->flags &
                                      ((1L << PG_referenced) |
                                       (1L << PG_swapbacked) |
@@ -1740,7 +1745,8 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 static void collapse_huge_page(struct mm_struct *mm,
                                unsigned long address,
                                struct page **hpage,
-                               struct vm_area_struct *vma)
+                               struct vm_area_struct *vma,
+                               int node)
 {
         pgd_t *pgd;
         pud_t *pud;
@@ -1768,7 +1774,8 @@ static void collapse_huge_page(struct mm_struct *mm,
          * mmap_sem in read mode is good idea also to allow greater
          * scalability.
          */
-        new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address);
+        new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
+                                      node);
         if (unlikely(!new_page)) {
                 up_read(&mm->mmap_sem);
                 *hpage = ERR_PTR(-ENOMEM);
@@ -1806,6 +1813,8 @@ static void collapse_huge_page(struct mm_struct *mm,
         /* VM_PFNMAP vmas may have vm_ops null but vm_file set */
         if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
                 goto out;
+        if (is_vma_temporary_stack(vma))
+                goto out;
         VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
 
         pgd = pgd_offset(mm, address);
@@ -1847,7 +1856,6 @@ static void collapse_huge_page(struct mm_struct *mm,
                 set_pmd_at(mm, address, pmd, _pmd);
                 spin_unlock(&mm->page_table_lock);
                 anon_vma_unlock(vma->anon_vma);
-                mem_cgroup_uncharge_page(new_page);
                 goto out;
         }
 
@@ -1893,6 +1901,7 @@ out_up_write:
         return;
 
 out:
+        mem_cgroup_uncharge_page(new_page);
 #ifdef CONFIG_NUMA
         put_page(new_page);
 #endif
@@ -1912,6 +1921,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
         struct page *page;
         unsigned long _address;
         spinlock_t *ptl;
+        int node = -1;
 
         VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
@@ -1942,6 +1952,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
                 page = vm_normal_page(vma, _address, pteval);
                 if (unlikely(!page))
                         goto out_unmap;
+                /*
+                 * Chose the node of the first page. This could
+                 * be more sophisticated and look at more pages,
+                 * but isn't for now.
+                 */
+                if (node == -1)
+                        node = page_to_nid(page);
                 VM_BUG_ON(PageCompound(page));
                 if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
                         goto out_unmap;
@@ -1958,7 +1975,7 @@ out_unmap:
         pte_unmap_unlock(pte, ptl);
         if (ret)
                 /* collapse_huge_page will return with the mmap_sem released */
-                collapse_huge_page(mm, address, hpage, vma);
+                collapse_huge_page(mm, address, hpage, vma, node);
 out:
         return ret;
 }
@@ -2027,32 +2044,27 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
                 if ((!(vma->vm_flags & VM_HUGEPAGE) &&
                      !khugepaged_always()) ||
                     (vma->vm_flags & VM_NOHUGEPAGE)) {
+                skip:
                         progress++;
                         continue;
                 }
-
                 /* VM_PFNMAP vmas may have vm_ops null but vm_file set */
-                if (!vma->anon_vma || vma->vm_ops || vma->vm_file) {
-                        khugepaged_scan.address = vma->vm_end;
-                        progress++;
-                        continue;
-                }
+                if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+                        goto skip;
+                if (is_vma_temporary_stack(vma))
+                        goto skip;
+
                 VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
 
                 hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
                 hend = vma->vm_end & HPAGE_PMD_MASK;
-                if (hstart >= hend) {
-                        progress++;
-                        continue;
-                }
+                if (hstart >= hend)
+                        goto skip;
+                if (khugepaged_scan.address > hend)
+                        goto skip;
                 if (khugepaged_scan.address < hstart)
                         khugepaged_scan.address = hstart;
-                if (khugepaged_scan.address > hend) {
-                        khugepaged_scan.address = hend + HPAGE_PMD_SIZE;
-                        progress++;
-                        continue;
-                }
-                BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
+                VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
 
                 while (khugepaged_scan.address < hend) {
                         int ret;
@@ -2081,7 +2093,7 @@ breakouterloop:
 breakouterloop_mmap_sem:
 
         spin_lock(&khugepaged_mm_lock);
-        BUG_ON(khugepaged_scan.mm_slot != mm_slot);
+        VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
         /*
          * Release the current mm_slot if this mm is about to die, or
          * if we scanned all vmas of this mm.
@@ -2236,9 +2248,9 @@ static int khugepaged(void *none)
 
         for (;;) {
                 mutex_unlock(&khugepaged_mutex);
-                BUG_ON(khugepaged_thread != current);
+                VM_BUG_ON(khugepaged_thread != current);
                 khugepaged_loop();
-                BUG_ON(khugepaged_thread != current);
+                VM_BUG_ON(khugepaged_thread != current);
 
                 mutex_lock(&khugepaged_mutex);
                 if (!khugepaged_enabled())