1 files changed, 61 insertions, 121 deletions

diff --git a/mm/memory.c b/mm/memory.c
index ca000394711..bf8665849a5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -69,8 +69,8 @@
 
 #include "internal.h"
 
-#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
-#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_nid.
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
 #endif
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -453,8 +453,6 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 
 /*
  * This function frees user-level page tables of a process.
- *
- * Must be called with pagetable lock held.
  */
 void free_pgd_range(struct mmu_gather *tlb,
 			unsigned long addr, unsigned long end,
@@ -681,7 +679,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 	if (vma->vm_ops)
 		printk(KERN_ALERT "vma->vm_ops->fault: %pSR\n",
 		       vma->vm_ops->fault);
-	if (vma->vm_file && vma->vm_file->f_op)
+	if (vma->vm_file)
 		printk(KERN_ALERT "vma->vm_file->f_op->mmap: %pSR\n",
 		       vma->vm_file->f_op->mmap);
 	dump_stack();
@@ -837,6 +835,8 @@ 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);
 				}
 			}
@@ -2719,6 +2719,14 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		get_page(dirty_page);
 
 reuse:
+		/*
+		 * Clear the pages cpupid information as the existing
+		 * information potentially belongs to a now completely
+		 * unrelated process.
+		 */
+		if (old_page)
+			page_cpupid_xchg_last(old_page, (1 << LAST_CPUPID_SHIFT) - 1);
+
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -3519,13 +3527,16 @@ 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,
+				int *flags)
 {
 	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);
+		*flags |= TNF_FAULT_LOCAL;
+	}
 
 	return mpol_misplaced(page, vma, addr);
 }
@@ -3535,9 +3546,11 @@ 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 last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	int flags = 0;
 
 	/*
 	* The "pte" at this point cannot be used safely without
@@ -3564,123 +3577,44 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte_unmap_unlock(ptep, ptl);
 		return 0;
 	}
+	BUG_ON(is_zero_pfn(page_to_pfn(page)));
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	/*
+	 * Avoid grouping on DSO/COW pages in specific and RO pages
+	 * in general, RO pages shouldn't hurt as much anyway since
+	 * they can be in shared cache state.
+	 */
+	if (!pte_write(pte))
+		flags |= TNF_NO_GROUP;
+
+	/*
+	 * Flag if the page is shared between multiple address spaces. This
+	 * is later used when determining whether to group tasks together
+	 */
+	if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED))
+		flags |= TNF_SHARED;
+
+	last_cpupid = page_cpupid_last(page);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid, &flags);
 	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;
 	}
 
 	/* Migrate to the requested node */
-	migrated = migrate_misplaced_page(page, target_nid);
-	if (migrated)
-		current_nid = target_nid;
-
-out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
-	return 0;
-}
-
-/* NUMA hinting page fault entry point for regular pmds */
-#ifdef CONFIG_NUMA_BALANCING
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-		     unsigned long addr, pmd_t *pmdp)
-{
-	pmd_t pmd;
-	pte_t *pte, *orig_pte;
-	unsigned long _addr = addr & PMD_MASK;
-	unsigned long offset;
-	spinlock_t *ptl;
-	bool numa = false;
-	int local_nid = numa_node_id();
-
-	spin_lock(&mm->page_table_lock);
-	pmd = *pmdp;
-	if (pmd_numa(pmd)) {
-		set_pmd_at(mm, _addr, pmdp, pmd_mknonnuma(pmd));
-		numa = true;
+	migrated = migrate_misplaced_page(page, vma, target_nid);
+	if (migrated) {
+		page_nid = target_nid;
+		flags |= TNF_MIGRATED;
 	}
-	spin_unlock(&mm->page_table_lock);
-
-	if (!numa)
-		return 0;
 
-	/* we're in a page fault so some vma must be in the range */
-	BUG_ON(!vma);
-	BUG_ON(vma->vm_start >= _addr + PMD_SIZE);
-	offset = max(_addr, vma->vm_start) & ~PMD_MASK;
-	VM_BUG_ON(offset >= PMD_SIZE);
-	orig_pte = pte = pte_offset_map_lock(mm, pmdp, _addr, &ptl);
-	pte += offset >> PAGE_SHIFT;
-	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 target_nid;
-		bool migrated;
-		if (!pte_present(pteval))
-			continue;
-		if (!pte_numa(pteval))
-			continue;
-		if (addr >= vma->vm_end) {
-			vma = find_vma(mm, addr);
-			/* there's a pte present so there must be a vma */
-			BUG_ON(!vma);
-			BUG_ON(addr < vma->vm_start);
-		}
-		if (pte_numa(pteval)) {
-			pteval = pte_mknonnuma(pteval);
-			set_pte_at(mm, addr, pte, pteval);
-		}
-		page = vm_normal_page(vma, addr, pteval);
-		if (unlikely(!page))
-			continue;
-		/* only check non-shared pages */
-		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) {
-			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);
-
-		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
-	}
-	pte_unmap_unlock(orig_pte, ptl);
-
-	return 0;
-}
-#else
-static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
-		     unsigned long addr, pmd_t *pmdp)
-{
-	BUG();
+out:
+	if (page_nid != -1)
+		task_numa_fault(last_cpupid, page_nid, 1, flags);
 	return 0;
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * These routines also need to handle stuff like marking pages dirty
@@ -3820,8 +3754,8 @@ retry:
 		}
 	}
 
-	if (pmd_numa(*pmd))
-		return do_pmd_numa_page(mm, vma, address, pmd);
+	/* THP should already have been handled */
+	BUG_ON(pmd_numa(*pmd));
 
 	/*
 	 * Use __pte_alloc instead of pte_alloc_map, because we can't
@@ -3863,15 +3797,21 @@ 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;
 }