Merge branch 'linux-linaro-lsk-v4.9' into linux-linaro-lsk-v4.9-rtlinux-linaro-lsk-v4.9-rt-test

13 files changed, 185 insertions, 56 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index a8d2c7a73d54..113c2248c476 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -621,7 +621,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 	VM_BUG_ON_PAGE(!PageLocked(new), new);
 	VM_BUG_ON_PAGE(new->mapping, new);
 
-	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (!error) {
 		struct address_space *mapping = old->mapping;
 		void (*freepage)(struct page *);
@@ -677,7 +677,7 @@ static int __add_to_page_cache_locked(struct page *page,
 			return error;
 	}
 
-	error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+	error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
 	if (error) {
 		if (!huge)
 			mem_cgroup_cancel_charge(page, memcg, false);
@@ -1252,8 +1252,7 @@ no_page:
 		if (fgp_flags & FGP_ACCESSED)
 			__SetPageReferenced(page);
 
-		err = add_to_page_cache_lru(page, mapping, offset,
-				gfp_mask & GFP_RECLAIM_MASK);
+		err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (unlikely(err)) {
 			put_page(page);
 			page = NULL;
@@ -2001,7 +2000,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 		if (!page)
 			return -ENOMEM;
 
-		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL);
+		ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
 		if (ret == 0)
 			ret = mapping->a_ops->readpage(file, page);
 		else if (ret == -EEXIST)
diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index db77dcb38afd..375a103d7a56 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -52,6 +52,18 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 		ret = -EFAULT;
 		goto out;
 	}
+
+	/*
+	 * While get_vaddr_frames() could be used for transient (kernel
+	 * controlled lifetime) pinning of memory pages all current
+	 * users establish long term (userspace controlled lifetime)
+	 * page pinning. Treat get_vaddr_frames() like
+	 * get_user_pages_longterm() and disallow it for filesystem-dax
+	 * mappings.
+	 */
+	if (vma_is_fsdax(vma))
+		return -EOPNOTSUPP;
+
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
 		vec->got_ref = true;
 		vec->is_pfns = false;
diff --git a/mm/gup.c b/mm/gup.c
index c63a0341ae38..be4ccddac26f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -430,6 +430,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 	if (vm_flags & (VM_IO | VM_PFNMAP))
 		return -EFAULT;
 
+	if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma))
+		return -EFAULT;
+
 	if (write) {
 		if (!(vm_flags & VM_WRITE)) {
 			if (!(gup_flags & FOLL_FORCE))
@@ -982,6 +985,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 }
 EXPORT_SYMBOL(get_user_pages);
 
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas_arg)
+{
+	struct vm_area_struct **vmas = vmas_arg;
+	struct vm_area_struct *vma_prev = NULL;
+	long rc, i;
+
+	if (!pages)
+		return -EINVAL;
+
+	if (!vmas) {
+		vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *),
+			       GFP_KERNEL);
+		if (!vmas)
+			return -ENOMEM;
+	}
+
+	rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+	for (i = 0; i < rc; i++) {
+		struct vm_area_struct *vma = vmas[i];
+
+		if (vma == vma_prev)
+			continue;
+
+		vma_prev = vma;
+
+		if (vma_is_fsdax(vma))
+			break;
+	}
+
+	/*
+	 * Either get_user_pages() failed, or the vma validation
+	 * succeeded, in either case we don't need to put_page() before
+	 * returning.
+	 */
+	if (i >= rc)
+		goto out;
+
+	for (i = 0; i < rc; i++)
+		put_page(pages[i]);
+	rc = -EOPNOTSUPP;
+out:
+	if (vmas != vmas_arg)
+		kfree(vmas);
+	return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c234c078693c..e2982ea26090 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2279,11 +2279,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
-		lock_page(page);
+		if (!trylock_page(page))
+			goto next;
 		/* split_huge_page() removes page from list on success */
 		if (!split_huge_page(page))
 			split++;
 		unlock_page(page);
+next:
 		put_page(page);
 	}
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 5d7c006373d3..898eb26f5dc8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -528,7 +528,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			goto out;
 		}
 
-		VM_BUG_ON_PAGE(PageCompound(page), page);
+		/* TODO: teach khugepaged to collapse THP mapped with pte */
+		if (PageCompound(page)) {
+			result = SCAN_PAGE_COMPOUND;
+			goto out;
+		}
+
 		VM_BUG_ON_PAGE(!PageAnon(page), page);
 		VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5aa71a82ca73..851efb004857 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -921,6 +921,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	int ret;
 	int kill = 1, forcekill;
 	struct page *hpage = *hpagep;
+	bool mlocked = PageMlocked(hpage);
 
 	/*
 	 * Here we are interested only in user-mapped pages, so skip any
@@ -985,6 +986,13 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		       pfn, page_mapcount(hpage));
 
 	/*
+	 * try_to_unmap() might put mlocked page in lru cache, so call
+	 * shake_page() again to ensure that it's flushed.
+	 */
+	if (mlocked)
+		shake_page(hpage, 0);
+
+	/*
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
 	 * killing is needed or not.  Only kill when the page
diff --git a/mm/memory.c b/mm/memory.c
index e2e68767a373..d2db2c4eb0a4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2848,6 +2848,17 @@ static int __do_fault(struct fault_env *fe, pgoff_t pgoff,
 	return ret;
 }
 
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 static int pte_alloc_one_map(struct fault_env *fe)
 {
 	struct vm_area_struct *vma = fe->vma;
@@ -2871,18 +2882,27 @@ static int pte_alloc_one_map(struct fault_env *fe)
 map_pte:
 	/*
 	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
-	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
-	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
-	 * in a different thread of this mm, in turn leading to a misleading
-	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
-	 * regular pmd that we can walk with pte_offset_map() and we can do that
-	 * through an atomic read in C, which is what pmd_trans_unstable()
-	 * provides.
+	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault in a different thread of
+	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+	 * All we have to ensure is that it is a regular pmd that we can walk
+	 * with pte_offset_map() and we can do that through an atomic read in
+	 * C, which is what pmd_trans_unstable() provides.
 	 */
-	if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd))
+	if (pmd_devmap_trans_unstable(fe->pmd))
 		return VM_FAULT_NOPAGE;
 
+	/*
+	 * At this point we know that our vmf->pmd points to a page of ptes
+	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
+	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+	 * be valid and we will re-check to make sure the vmf->pte isn't
+	 * pte_none() under vmf->ptl protection when we return to
+	 * alloc_set_pte().
+	 */
 	fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address,
 			&fe->ptl);
 	return 0;
@@ -3456,7 +3476,7 @@ static int handle_pte_fault(struct fault_env *fe)
 		fe->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd))
+		if (pmd_devmap_trans_unstable(fe->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 439cc63ad903..807236aed275 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2506,13 +2506,13 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		current->nr_dirtied--;
 		dec_node_page_state(page, NR_DIRTIED);
 		dec_wb_stat(wb, WB_DIRTIED);
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2618,15 +2618,15 @@ void cancel_dirty_page(struct page *page)
 	if (mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		lock_page_memcg(page);
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 
 		if (TestClearPageDirty(page))
 			account_page_cleaned(page, mapping, wb);
 
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		unlock_page_memcg(page);
 	} else {
 		ClearPageDirty(page);
@@ -2658,7 +2658,7 @@ int clear_page_dirty_for_io(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
-		bool locked;
+		struct wb_lock_cookie cookie = {};
 
 		/*
 		 * Yes, Virginia, this is indeed insane.
@@ -2695,7 +2695,7 @@ int clear_page_dirty_for_io(struct page *page)
 		 * always locked coming in here, so we get the desired
 		 * exclusion.
 		 */
-		wb = unlocked_inode_to_wb_begin(inode, &locked);
+		wb = unlocked_inode_to_wb_begin(inode, &cookie);
 		if (TestClearPageDirty(page)) {
 			mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);
 			dec_node_page_state(page, NR_FILE_DIRTY);
@@ -2703,7 +2703,7 @@ int clear_page_dirty_for_io(struct page *page)
 			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
-		unlocked_inode_to_wb_end(inode, locked);
+		unlocked_inode_to_wb_end(inode, &cookie);
 		return ret;
 	}
 	return TestClearPageDirty(page);
diff --git a/mm/percpu.c b/mm/percpu.c
index 4e739fcf91bf..88b57ee35ba3 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -70,6 +70,7 @@
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
 #include <linux/kmemleak.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
diff --git a/mm/shmem.c b/mm/shmem.c
index 2123bfc39ef2..42ca5df2c0e3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -466,36 +466,45 @@ next:
 		info = list_entry(pos, struct shmem_inode_info, shrinklist);
 		inode = &info->vfs_inode;
 
-		if (nr_to_split && split >= nr_to_split) {
-			iput(inode);
-			continue;
-		}
+		if (nr_to_split && split >= nr_to_split)
+			goto leave;
 
-		page = find_lock_page(inode->i_mapping,
+		page = find_get_page(inode->i_mapping,
 				(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
 		if (!page)
 			goto drop;
 
+		/* No huge page at the end of the file: nothing to split */
 		if (!PageTransHuge(page)) {
-			unlock_page(page);
 			put_page(page);
 			goto drop;
 		}
 
+		/*
+		 * Leave the inode on the list if we failed to lock
+		 * the page at this time.
+		 *
+		 * Waiting for the lock may lead to deadlock in the
+		 * reclaim path.
+		 */
+		if (!trylock_page(page)) {
+			put_page(page);
+			goto leave;
+		}
+
 		ret = split_huge_page(page);
 		unlock_page(page);
 		put_page(page);
 
-		if (ret) {
-			/* split failed: leave it on the list */
-			iput(inode);
-			continue;
-		}
+		/* If split failed leave the inode on the list */
+		if (ret)
+			goto leave;
 
 		split++;
 drop:
 		list_del_init(&info->shrinklist);
 		removed++;
+leave:
 		iput(inode);
 	}
 
diff --git a/mm/slab.c b/mm/slab.c
index 1f82d16a0518..c59844dbd034 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4096,7 +4096,8 @@ next:
 	next_reap_node();
 out:
 	/* Set up the next iteration */
-	schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
+	schedule_delayed_work_on(smp_processor_id(), work,
+				round_jiffies_relative(REAPTIMEOUT_AC));
 }
 
 #ifdef CONFIG_SLABINFO
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4365de74bdb0..557ad1367595 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2841,8 +2841,10 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
-		if (!managed_zone(zone) ||
-		    pgdat_reclaimable_pages(pgdat) == 0)
+		if (!managed_zone(zone))
+			continue;
+
+		if (!zone_reclaimable_pages(zone))
 			continue;
 
 		pfmemalloc_reserve += min_wmark_pages(zone);
@@ -2964,7 +2966,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	unsigned long nr_reclaimed;
 	struct scan_control sc = {
 		.nr_to_reclaim = SWAP_CLUSTER_MAX,
-		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+		.gfp_mask = memalloc_noio_flags(gfp_mask),
 		.reclaim_idx = gfp_zone(gfp_mask),
 		.order = order,
 		.nodemask = nodemask,
@@ -2979,12 +2981,12 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	 * 1 is returned so that the page allocator does not OOM kill at this
 	 * point.
 	 */
-	if (throttle_direct_reclaim(gfp_mask, zonelist, nodemask))
+	if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
 		return 1;
 
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
-				gfp_mask,
+				sc.gfp_mask,
 				sc.reclaim_idx);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -3747,16 +3749,15 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
-	int classzone_idx = gfp_zone(gfp_mask);
 	struct scan_control sc = {
 		.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
-		.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
+		.gfp_mask = memalloc_noio_flags(gfp_mask),
 		.order = order,
 		.priority = NODE_RECLAIM_PRIORITY,
 		.may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
 		.may_swap = 1,
-		.reclaim_idx = classzone_idx,
+		.reclaim_idx = gfp_zone(gfp_mask),
 	};
 
 	cond_resched();
@@ -3766,7 +3767,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	 * and RECLAIM_UNMAP.
 	 */
 	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
-	lockdep_set_current_reclaim_state(gfp_mask);
+	lockdep_set_current_reclaim_state(sc.gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c3585f345c22..00f9620e21ff 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1363,8 +1363,6 @@ static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
 			return zone == compare;
 	}
 
-	/* The zone must be somewhere! */
-	WARN_ON_ONCE(1);
 	return false;
 }
 
@@ -1399,18 +1397,24 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   zone->present_pages,
 		   zone->managed_pages);
 
-	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		seq_printf(m, "\n      %-12s %lu", vmstat_text[i],
-				zone_page_state(zone, i));
-
 	seq_printf(m,
 		   "\n        protection: (%ld",
 		   zone->lowmem_reserve[0]);
 	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
 		seq_printf(m, ", %ld", zone->lowmem_reserve[i]);
-	seq_printf(m,
-		   ")"
-		   "\n  pagesets");
+	seq_putc(m, ')');
+
+	/* If unpopulated, no other information is useful */
+	if (!populated_zone(zone)) {
+		seq_putc(m, '\n');
+		return;
+	}
+
+	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+		seq_printf(m, "\n      %-12s %lu", vmstat_text[i],
+				zone_page_state(zone, i));
+
+	seq_printf(m, "\n  pagesets");
 	for_each_online_cpu(i) {
 		struct per_cpu_pageset *pageset;