1 files changed, 140 insertions, 169 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 1ce2e2a734f..1f2287eaa88 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
@@ -209,14 +209,15 @@ static int tlb_next_batch(struct mmu_gather *tlb)
  *	tear-down from @mm. The @fullmm argument is used when @mm is without
  *	users and we're going to destroy the full address space (exit/execve).
  */
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 
-	tlb->fullmm     = fullmm;
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
 	tlb->need_flush_all = 0;
-	tlb->start	= -1UL;
-	tlb->end	= 0;
+	tlb->start	= start;
+	tlb->end	= end;
 	tlb->need_flush = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
@@ -256,8 +257,6 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
 {
 	struct mmu_gather_batch *batch, *next;
 
-	tlb->start = start;
-	tlb->end   = end;
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
@@ -374,30 +373,6 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
 /*
- * If a p?d_bad entry is found while walking page tables, report
- * the error, before resetting entry to p?d_none.  Usually (but
- * very seldom) called out from the p?d_none_or_clear_bad macros.
- */
-
-void pgd_clear_bad(pgd_t *pgd)
-{
-	pgd_ERROR(*pgd);
-	pgd_clear(pgd);
-}
-
-void pud_clear_bad(pud_t *pud)
-{
-	pud_ERROR(*pud);
-	pud_clear(pud);
-}
-
-void pmd_clear_bad(pmd_t *pmd)
-{
-	pmd_ERROR(*pmd);
-	pmd_clear(pmd);
-}
-
-/*
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
  */
@@ -862,6 +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);
 				}
 			}
@@ -1099,7 +1076,6 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
-	unsigned long range_start = addr;
 
 again:
 	init_rss_vec(rss);
@@ -1141,9 +1117,12 @@ again:
 				continue;
 			if (unlikely(details) && details->nonlinear_vma
 			    && linear_page_index(details->nonlinear_vma,
-						addr) != page->index)
-				set_pte_at(mm, addr, pte,
-					   pgoff_to_pte(page->index));
+						addr) != page->index) {
+				pte_t ptfile = pgoff_to_pte(page->index);
+				if (pte_soft_dirty(ptent))
+					pte_file_mksoft_dirty(ptfile);
+				set_pte_at(mm, addr, pte, ptfile);
+			}
 			if (PageAnon(page))
 				rss[MM_ANONPAGES]--;
 			else {
@@ -1202,17 +1181,25 @@ again:
 	 * and page-free while holding it.
 	 */
 	if (force_flush) {
+		unsigned long old_end;
+
 		force_flush = 0;
 
-#ifdef HAVE_GENERIC_MMU_GATHER
-		tlb->start = range_start;
+		/*
+		 * Flush the TLB just for the previous segment,
+		 * then update the range to be the remaining
+		 * TLB range.
+		 */
+		old_end = tlb->end;
 		tlb->end = addr;
-#endif
+
 		tlb_flush_mmu(tlb);
-		if (addr != end) {
-			range_start = addr;
+
+		tlb->start = addr;
+		tlb->end = old_end;
+
+		if (addr != end)
 			goto again;
-		}
 	}
 
 	return addr;
@@ -1397,7 +1384,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
 	unsigned long end = start + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, start, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, start, end);
 	for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
@@ -1423,7 +1410,7 @@ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long addr
 	unsigned long end = address + size;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, address, end);
 	update_hiwater_rss(mm);
 	mmu_notifier_invalidate_range_start(mm, address, end);
 	unmap_single_vma(&tlb, vma, address, end, details);
@@ -1496,7 +1483,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		goto no_page_table;
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		BUG_ON(flags & FOLL_GET);
+		if (flags & FOLL_GET)
+			goto out;
 		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
 		goto out;
 	}
@@ -1507,8 +1495,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		goto no_page_table;
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		BUG_ON(flags & FOLL_GET);
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
+		if (flags & FOLL_GET) {
+			/*
+			 * Refcount on tail pages are not well-defined and
+			 * shouldn't be taken. The caller should handle a NULL
+			 * return when trying to follow tail pages.
+			 */
+			if (PageHead(page))
+				get_page(page);
+			else {
+				page = NULL;
+				goto out;
+			}
+		}
 		goto out;
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
@@ -2721,6 +2721,14 @@ 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);
@@ -3115,6 +3123,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		exclusive = 1;
 	}
 	flush_icache_page(vma, page);
+	if (pte_swp_soft_dirty(orig_pte))
+		pte = pte_mksoft_dirty(pte);
 	set_pte_at(mm, address, page_table, pte);
 	if (page == swapcache)
 		do_page_add_anon_rmap(page, vma, address, exclusive);
@@ -3408,6 +3418,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+			pte_mksoft_dirty(entry);
 		if (anon) {
 			inc_mm_counter_fast(mm, MM_ANONPAGES);
 			page_add_new_anon_rmap(page, vma, address);
@@ -3517,13 +3529,16 @@ 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);
 }
@@ -3533,9 +3548,11 @@ 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
@@ -3562,123 +3579,44 @@ 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)));
+
+	/*
+	 * 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;
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	/*
+	 * 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;
-	}
-	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);
+	migrated = migrate_misplaced_page(page, vma, target_nid);
+	if (migrated) {
+		page_nid = target_nid;
+		flags |= TNF_MIGRATED;
 	}
-	pte_unmap_unlock(orig_pte, ptl);
 
+out:
+	if (page_nid != -1)
+		task_numa_fault(last_cpupid, page_nid, 1, flags);
 	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();
-	return 0;
-}
-#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * These routines also need to handle stuff like marking pages dirty
@@ -3693,7 +3631,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-int handle_pte_fault(struct mm_struct *mm,
+static int handle_pte_fault(struct mm_struct *mm,
 		     struct vm_area_struct *vma, unsigned long address,
 		     pte_t *pte, pmd_t *pmd, unsigned int flags)
 {
@@ -3752,22 +3690,14 @@ unlock:
 /*
  * By the time we get here, we already hold the mm semaphore
  */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+			     unsigned long address, unsigned int flags)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
-	__set_current_state(TASK_RUNNING);
-
-	count_vm_event(PGFAULT);
-	mem_cgroup_count_vm_event(mm, PGFAULT);
-
-	/* do counter updates before entering really critical section. */
-	check_sync_rss_stat(current);
-
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
@@ -3780,9 +3710,12 @@ retry:
 	if (!pmd)
 		return VM_FAULT_OOM;
 	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+		int ret = VM_FAULT_FALLBACK;
 		if (!vma->vm_ops)
-			return do_huge_pmd_anonymous_page(mm, vma, address,
-							  pmd, flags);
+			ret = do_huge_pmd_anonymous_page(mm, vma, address,
+					pmd, flags);
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
 	} else {
 		pmd_t orig_pmd = *pmd;
 		int ret;
@@ -3823,8 +3756,8 @@ 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
@@ -3848,6 +3781,43 @@ retry:
 	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
 
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		    unsigned long address, unsigned int flags)
+{
+	int ret;
+
+	__set_current_state(TASK_RUNNING);
+
+	count_vm_event(PGFAULT);
+	mem_cgroup_count_vm_event(mm, PGFAULT);
+
+	/* do counter updates before entering really critical section. */
+	check_sync_rss_stat(current);
+
+	/*
+	 * Enable the memcg OOM handling for faults triggered in user
+	 * space.  Kernel faults are handled more gracefully.
+	 */
+	if (flags & FAULT_FLAG_USER)
+		mem_cgroup_oom_enable();
+
+	ret = __handle_mm_fault(mm, vma, address, flags);
+
+	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;
+}
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.
@@ -4066,6 +4036,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 
 	return len;
 }
+EXPORT_SYMBOL_GPL(generic_access_phys);
 #endif
 
 /*