1 files changed, 35 insertions, 38 deletions

diff --git a/mm/memory.c b/mm/memory.c
index ca0003947115..d176154c243f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -837,6 +837,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                                          */
                                         make_migration_entry_read(&entry);
                                         pte = swp_entry_to_pte(entry);
+                                        if (pte_swp_soft_dirty(*src_pte))
+                                                pte = pte_swp_mksoft_dirty(pte);
                                         set_pte_at(src_mm, addr, src_pte, pte);
                                 }
                         }
@@ -3519,12 +3521,12 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-                                unsigned long addr, int current_nid)
+                                unsigned long addr, int page_nid)
 {
         get_page(page);
 
         count_vm_numa_event(NUMA_HINT_FAULTS);
-        if (current_nid == numa_node_id())
+        if (page_nid == numa_node_id())
                 count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
         return mpol_misplaced(page, vma, addr);
@@ -3535,7 +3537,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
         struct page *page = NULL;
         spinlock_t *ptl;
-        int current_nid = -1;
+        int page_nid = -1;
         int target_nid;
         bool migrated = false;
 
@@ -3565,15 +3567,10 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 return 0;
         }
 
-        current_nid = page_to_nid(page);
-        target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+        page_nid = page_to_nid(page);
+        target_nid = numa_migrate_prep(page, vma, addr, page_nid);
         pte_unmap_unlock(ptep, ptl);
         if (target_nid == -1) {
-                /*
-                 * Account for the fault against the current node if it not
-                 * being replaced regardless of where the page is located.
-                 */
-                current_nid = numa_node_id();
                 put_page(page);
                 goto out;
         }
@@ -3581,11 +3578,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         /* Migrate to the requested node */
         migrated = migrate_misplaced_page(page, target_nid);
         if (migrated)
-                current_nid = target_nid;
+                page_nid = target_nid;
 
 out:
-        if (current_nid != -1)
-                task_numa_fault(current_nid, 1, migrated);
+        if (page_nid != -1)
+                task_numa_fault(page_nid, 1, migrated);
         return 0;
 }
 
@@ -3600,7 +3597,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         unsigned long offset;
         spinlock_t *ptl;
         bool numa = false;
-        int local_nid = numa_node_id();
 
         spin_lock(&mm->page_table_lock);
         pmd = *pmdp;
@@ -3623,9 +3619,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
                 pte_t pteval = *pte;
                 struct page *page;
-                int curr_nid = local_nid;
+                int page_nid = -1;
                 int target_nid;
-                bool migrated;
+                bool migrated = false;
+
                 if (!pte_present(pteval))
                         continue;
                 if (!pte_numa(pteval))
@@ -3647,25 +3644,19 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 if (unlikely(page_mapcount(page) != 1))
                         continue;
 
-                /*
-                 * Note that the NUMA fault is later accounted to either
-                 * the node that is currently running or where the page is
-                 * migrated to.
-                 */
-                curr_nid = local_nid;
-                target_nid = numa_migrate_prep(page, vma, addr,
-                                               page_to_nid(page));
-                if (target_nid == -1) {
+                page_nid = page_to_nid(page);
+                target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+                pte_unmap_unlock(pte, ptl);
+                if (target_nid != -1) {
+                        migrated = migrate_misplaced_page(page, target_nid);
+                        if (migrated)
+                                page_nid = target_nid;
+                } else {
                         put_page(page);
-                        continue;
                 }
 
-                /* Migrate to the requested node */
-                pte_unmap_unlock(pte, ptl);
-                migrated = migrate_misplaced_page(page, target_nid);
-                if (migrated)
-                        curr_nid = target_nid;
-                task_numa_fault(curr_nid, 1, migrated);
+                if (page_nid != -1)
+                        task_numa_fault(page_nid, 1, migrated);
 
                 pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
         }
@@ -3863,15 +3854,21 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
          * space.  Kernel faults are handled more gracefully.
          */
         if (flags & FAULT_FLAG_USER)
-                mem_cgroup_enable_oom();
+                mem_cgroup_oom_enable();
 
         ret = __handle_mm_fault(mm, vma, address, flags);
 
-        if (flags & FAULT_FLAG_USER)
-                mem_cgroup_disable_oom();
-
-        if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)))
-                mem_cgroup_oom_synchronize();
+        if (flags & FAULT_FLAG_USER) {
+                mem_cgroup_oom_disable();
+                /*
+                 * The task may have entered a memcg OOM situation but
+                 * if the allocation error was handled gracefully (no
+                 * VM_FAULT_OOM), there is no need to kill anything.
+                 * Just clean up the OOM state peacefully.
+                 */
+                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+                        mem_cgroup_oom_synchronize(false);
+        }
 
         return ret;
 }