Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

12 files changed, 96 insertions, 53 deletions

diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 9075aa54e955..b06d9fe23a28 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -24,7 +24,7 @@ struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
 {
 	unsigned long flags;
 	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
-				__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_ZERO);
+				       __GFP_NOMEMALLOC | __GFP_NORETRY);
 	if (!page)
 		return NULL;
 
diff --git a/mm/debug.c b/mm/debug.c
index db1cd26d8752..5715448ab0b5 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -124,9 +124,7 @@ void dump_mm(const struct mm_struct *mm)
 #ifdef CONFIG_NUMA_BALANCING
 		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
 #endif
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
 		"tlb_flush_pending %d\n"
-#endif
 		"def_flags: %#lx(%pGv)\n",
 
 		mm, mm->mmap, mm->vmacache_seqnum, mm->task_size,
@@ -158,9 +156,7 @@ void dump_mm(const struct mm_struct *mm)
 #ifdef CONFIG_NUMA_BALANCING
 		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
 #endif
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
-		mm->tlb_flush_pending,
-#endif
+		atomic_read(&mm->tlb_flush_pending),
 		mm->def_flags, &mm->def_flags
 	);
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 86975dec0ba1..216114f6ef0b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1496,6 +1496,13 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
 	}
 
 	/*
+	 * The page_table_lock above provides a memory barrier
+	 * with change_protection_range.
+	 */
+	if (mm_tlb_flush_pending(vma->vm_mm))
+		flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
+	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and access rights restored.
 	 */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a1a0ac0ad6f6..31e207cb399b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4062,9 +4062,9 @@ out:
 	return ret;
 out_release_unlock:
 	spin_unlock(ptl);
-out_release_nounlock:
 	if (vm_shared)
 		unlock_page(page);
+out_release_nounlock:
 	put_page(page);
 	goto out;
 }
diff --git a/mm/ksm.c b/mm/ksm.c
index 4dc92f138786..db20f8436bc3 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1038,7 +1038,8 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 		goto out_unlock;
 
 	if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) ||
-	    (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) {
+	    (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) ||
+						mm_tlb_flush_pending(mm)) {
 		pte_t entry;
 
 		swapped = PageSwapCache(page);
diff --git a/mm/memory.c b/mm/memory.c
index f65beaad319b..e158f7ac6730 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -215,12 +215,8 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	return true;
 }
 
-/* tlb_gather_mmu
- *	Called to initialize an (on-stack) mmu_gather structure for page-table
- *	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, unsigned long start, unsigned long end)
+void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+				unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 
@@ -275,10 +271,14 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
  *	Called at the end of the shootdown operation to free up any resources
  *	that were required.
  */
-void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+void arch_tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end, bool force)
 {
 	struct mmu_gather_batch *batch, *next;
 
+	if (force)
+		__tlb_adjust_range(tlb, start, end - start);
+
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
@@ -398,6 +398,34 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
+/* tlb_gather_mmu
+ *	Called to initialize an (on-stack) mmu_gather structure for page-table
+ *	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,
+			unsigned long start, unsigned long end)
+{
+	arch_tlb_gather_mmu(tlb, mm, start, end);
+	inc_tlb_flush_pending(tlb->mm);
+}
+
+void tlb_finish_mmu(struct mmu_gather *tlb,
+		unsigned long start, unsigned long end)
+{
+	/*
+	 * If there are parallel threads are doing PTE changes on same range
+	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
+	 * flush by batching, a thread has stable TLB entry can fail to flush
+	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
+	 * forcefully if we detect parallel PTE batching threads.
+	 */
+	bool force = mm_tlb_flush_nested(tlb->mm);
+
+	arch_tlb_finish_mmu(tlb, start, end, force);
+	dec_tlb_flush_pending(tlb->mm);
+}
+
 /*
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
diff --git a/mm/migrate.c b/mm/migrate.c
index 627671551873..d68a41da6abb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1937,12 +1937,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		put_page(new_page);
 		goto out_fail;
 	}
-	/*
-	 * We are not sure a pending tlb flush here is for a huge page
-	 * mapping or not. Hence use the tlb range variant
-	 */
-	if (mm_tlb_flush_pending(mm))
-		flush_tlb_range(vma, mmun_start, mmun_end);
 
 	/* Prepare a page as a migration target */
 	__SetPageLocked(new_page);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 4180ad8cc9c5..bd0f409922cb 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -244,7 +244,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
-	set_tlb_flush_pending(mm);
+	inc_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -256,7 +256,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
-	clear_tlb_flush_pending(mm);
+	dec_tlb_flush_pending(mm);
 
 	return pages;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fc32aa81f359..6d00f746c2fd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4458,8 +4458,9 @@ long si_mem_available(void)
 	 * Part of the reclaimable slab consists of items that are in use,
 	 * and cannot be freed. Cap this estimate at the low watermark.
 	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+	available += global_node_page_state(NR_SLAB_RECLAIMABLE) -
+		     min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
+			 wmark_low);
 
 	if (available < 0)
 		available = 0;
@@ -4602,8 +4603,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state(NR_FILE_DIRTY),
 		global_node_page_state(NR_WRITEBACK),
 		global_node_page_state(NR_UNSTABLE_NFS),
-		global_page_state(NR_SLAB_RECLAIMABLE),
-		global_page_state(NR_SLAB_UNRECLAIMABLE),
+		global_node_page_state(NR_SLAB_RECLAIMABLE),
+		global_node_page_state(NR_SLAB_UNRECLAIMABLE),
 		global_node_page_state(NR_FILE_MAPPED),
 		global_node_page_state(NR_SHMEM),
 		global_page_state(NR_PAGETABLE),
@@ -7668,7 +7669,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/* Make sure the range is really isolated. */
 	if (test_pages_isolated(outer_start, end, false)) {
-		pr_info("%s: [%lx, %lx) PFNs busy\n",
+		pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
 			__func__, outer_start, end);
 		ret = -EBUSY;
 		goto done;
diff --git a/mm/rmap.c b/mm/rmap.c
index c8993c63eb25..c1286d47aa1f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -888,10 +888,10 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 		.flags = PVMW_SYNC,
 	};
 	int *cleaned = arg;
+	bool invalidation_needed = false;
 
 	while (page_vma_mapped_walk(&pvmw)) {
 		int ret = 0;
-		address = pvmw.address;
 		if (pvmw.pte) {
 			pte_t entry;
 			pte_t *pte = pvmw.pte;
@@ -899,11 +899,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 			if (!pte_dirty(*pte) && !pte_write(*pte))
 				continue;
 
-			flush_cache_page(vma, address, pte_pfn(*pte));
-			entry = ptep_clear_flush(vma, address, pte);
+			flush_cache_page(vma, pvmw.address, pte_pfn(*pte));
+			entry = ptep_clear_flush(vma, pvmw.address, pte);
 			entry = pte_wrprotect(entry);
 			entry = pte_mkclean(entry);
-			set_pte_at(vma->vm_mm, address, pte, entry);
+			set_pte_at(vma->vm_mm, pvmw.address, pte, entry);
 			ret = 1;
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
@@ -913,11 +913,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
 				continue;
 
-			flush_cache_page(vma, address, page_to_pfn(page));
-			entry = pmdp_huge_clear_flush(vma, address, pmd);
+			flush_cache_page(vma, pvmw.address, page_to_pfn(page));
+			entry = pmdp_huge_clear_flush(vma, pvmw.address, pmd);
 			entry = pmd_wrprotect(entry);
 			entry = pmd_mkclean(entry);
-			set_pmd_at(vma->vm_mm, address, pmd, entry);
+			set_pmd_at(vma->vm_mm, pvmw.address, pmd, entry);
 			ret = 1;
 #else
 			/* unexpected pmd-mapped page? */
@@ -926,11 +926,16 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 		}
 
 		if (ret) {
-			mmu_notifier_invalidate_page(vma->vm_mm, address);
 			(*cleaned)++;
+			invalidation_needed = true;
 		}
 	}
 
+	if (invalidation_needed) {
+		mmu_notifier_invalidate_range(vma->vm_mm, address,
+				address + (1UL << compound_order(page)));
+	}
+
 	return true;
 }
 
@@ -1323,7 +1328,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	};
 	pte_t pteval;
 	struct page *subpage;
-	bool ret = true;
+	bool ret = true, invalidation_needed = false;
 	enum ttu_flags flags = (enum ttu_flags)arg;
 
 	/* munlock has nothing to gain from examining un-locked vmas */
@@ -1363,11 +1368,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		VM_BUG_ON_PAGE(!pvmw.pte, page);
 
 		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
-		address = pvmw.address;
-
 
 		if (!(flags & TTU_IGNORE_ACCESS)) {
-			if (ptep_clear_flush_young_notify(vma, address,
+			if (ptep_clear_flush_young_notify(vma, pvmw.address,
 						pvmw.pte)) {
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
@@ -1376,7 +1379,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		}
 
 		/* Nuke the page table entry. */
-		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+		flush_cache_page(vma, pvmw.address, pte_pfn(*pvmw.pte));
 		if (should_defer_flush(mm, flags)) {
 			/*
 			 * We clear the PTE but do not flush so potentially
@@ -1386,11 +1389,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * transition on a cached TLB entry is written through
 			 * and traps if the PTE is unmapped.
 			 */
-			pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+			pteval = ptep_get_and_clear(mm, pvmw.address,
+						    pvmw.pte);
 
 			set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
 		} else {
-			pteval = ptep_clear_flush(vma, address, pvmw.pte);
+			pteval = ptep_clear_flush(vma, pvmw.address, pvmw.pte);
 		}
 
 		/* Move the dirty bit to the page. Now the pte is gone. */
@@ -1405,12 +1409,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			if (PageHuge(page)) {
 				int nr = 1 << compound_order(page);
 				hugetlb_count_sub(nr, mm);
-				set_huge_swap_pte_at(mm, address,
+				set_huge_swap_pte_at(mm, pvmw.address,
 						     pvmw.pte, pteval,
 						     vma_mmu_pagesize(vma));
 			} else {
 				dec_mm_counter(mm, mm_counter(page));
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
 			}
 
 		} else if (pte_unused(pteval)) {
@@ -1434,7 +1438,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 		} else if (PageAnon(page)) {
 			swp_entry_t entry = { .val = page_private(subpage) };
 			pte_t swp_pte;
@@ -1460,7 +1464,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				 * If the page was redirtied, it cannot be
 				 * discarded. Remap the page to page table.
 				 */
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
 				SetPageSwapBacked(page);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
@@ -1468,7 +1472,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			}
 
 			if (swap_duplicate(entry) < 0) {
-				set_pte_at(mm, address, pvmw.pte, pteval);
+				set_pte_at(mm, pvmw.address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
@@ -1484,14 +1488,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);
-			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
 		} else
 			dec_mm_counter(mm, mm_counter_file(page));
 discard:
 		page_remove_rmap(subpage, PageHuge(page));
 		put_page(page);
-		mmu_notifier_invalidate_page(mm, address);
+		invalidation_needed = true;
 	}
+
+	if (invalidation_needed)
+		mmu_notifier_invalidate_range(mm, address,
+				address + (1UL << compound_order(page)));
 	return ret;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index b0aa6075d164..6540e5982444 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1022,7 +1022,11 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 			 */
 			if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
 				spin_lock(&sbinfo->shrinklist_lock);
-				if (list_empty(&info->shrinklist)) {
+				/*
+				 * _careful to defend against unlocked access to
+				 * ->shrink_list in shmem_unused_huge_shrink()
+				 */
+				if (list_empty_careful(&info->shrinklist)) {
 					list_add_tail(&info->shrinklist,
 							&sbinfo->shrinklist);
 					sbinfo->shrinklist_len++;
@@ -1817,7 +1821,11 @@ alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
 			 * to shrink under memory pressure.
 			 */
 			spin_lock(&sbinfo->shrinklist_lock);
-			if (list_empty(&info->shrinklist)) {
+			/*
+			 * _careful to defend against unlocked access to
+			 * ->shrink_list in shmem_unused_huge_shrink()
+			 */
+			if (list_empty_careful(&info->shrinklist)) {
 				list_add_tail(&info->shrinklist,
 						&sbinfo->shrinklist);
 				sbinfo->shrinklist_len++;
diff --git a/mm/util.c b/mm/util.c
index 7b07ec852e01..9ecddf568fe3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -633,7 +633,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		 * which are reclaimable, under pressure.  The dentry
 		 * cache and most inode caches should fall into this
 		 */
-		free += global_page_state(NR_SLAB_RECLAIMABLE);
+		free += global_node_page_state(NR_SLAB_RECLAIMABLE);
 
 		/*
 		 * Leave reserved pages. The pages are not for anonymous pages.