Merge branch 'linus' into x86/asm, to pick up recent fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

8 files changed, 112 insertions, 112 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 78a23c5c302d..be0ee11fa0d9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -262,7 +262,14 @@ config COMPACTION
 	select MIGRATION
 	depends on MMU
 	help
-	  Allows the compaction of memory for the allocation of huge pages.
+          Compaction is the only memory management component to form
+          high order (larger physically contiguous) memory blocks
+          reliably. The page allocator relies on compaction heavily and
+          the lack of the feature can lead to unexpected OOM killer
+          invocations for high order memory requests. You shouldn't
+          disable this option unless there really is a strong reason for
+          it and then we would be really interested to hear about that at
+          linux-mm@kvack.org.
 
 #
 # support for page migration
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2373f0a7d340..a6abd76baa72 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1078,7 +1078,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		goto out;
 
 	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!PageHead(page), page);
+	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
 	if (flags & FOLL_TOUCH)
 		touch_pmd(vma, addr, pmd);
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
@@ -1116,7 +1116,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	}
 skip_mlock:
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
-	VM_BUG_ON_PAGE(!PageCompound(page), page);
+	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
 	if (flags & FOLL_GET)
 		get_page(page);
 
@@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t _pmd;
-	bool young, write, dirty;
+	bool young, write, dirty, soft_dirty;
 	unsigned long addr;
 	int i;
 
@@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	write = pmd_write(*pmd);
 	young = pmd_young(*pmd);
 	dirty = pmd_dirty(*pmd);
+	soft_dirty = pmd_soft_dirty(*pmd);
 
 	pmdp_huge_split_prepare(vma, haddr, pmd);
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
@@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			swp_entry_t swp_entry;
 			swp_entry = make_migration_entry(page + i, write);
 			entry = swp_entry_to_pte(swp_entry);
+			if (soft_dirty)
+				entry = pte_swp_mksoft_dirty(entry);
 		} else {
 			entry = mk_pte(page + i, vma->vm_page_prot);
 			entry = maybe_mkwrite(entry, vma);
@@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 				entry = pte_wrprotect(entry);
 			if (!young)
 				entry = pte_mkold(entry);
+			if (soft_dirty)
+				entry = pte_mksoft_dirty(entry);
 		}
 		if (dirty)
 			SetPageDirty(page + i);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2ff0289ad061..9a6a51a7c416 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4082,24 +4082,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 	atomic_add(n, &memcg->id.ref);
 }
 
-static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
-{
-	while (!atomic_inc_not_zero(&memcg->id.ref)) {
-		/*
-		 * The root cgroup cannot be destroyed, so it's refcount must
-		 * always be >= 1.
-		 */
-		if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
-			VM_BUG_ON(1);
-			break;
-		}
-		memcg = parent_mem_cgroup(memcg);
-		if (!memcg)
-			memcg = root_mem_cgroup;
-	}
-	return memcg;
-}
-
 static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	if (atomic_sub_and_test(n, &memcg->id.ref)) {
@@ -5821,6 +5803,24 @@ static int __init mem_cgroup_init(void)
 subsys_initcall(mem_cgroup_init);
 
 #ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+	while (!atomic_inc_not_zero(&memcg->id.ref)) {
+		/*
+		 * The root cgroup cannot be destroyed, so it's refcount must
+		 * always be >= 1.
+		 */
+		if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+			VM_BUG_ON(1);
+			break;
+		}
+		memcg = parent_mem_cgroup(memcg);
+		if (!memcg)
+			memcg = root_mem_cgroup;
+	}
+	return memcg;
+}
+
 /**
  * mem_cgroup_swapout - transfer a memsw charge to swap
  * @page: page whose memsw charge to transfer
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d8c4e38fb5f4..2da72a5b6ecc 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2336,6 +2336,23 @@ out:
 	return ret;
 }
 
+/*
+ * Drop the (possibly final) reference to task->mempolicy.  It needs to be
+ * dropped after task->mempolicy is set to NULL so that any allocation done as
+ * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
+ * policy.
+ */
+void mpol_put_task_policy(struct task_struct *task)
+{
+	struct mempolicy *pol;
+
+	task_lock(task);
+	pol = task->mempolicy;
+	task->mempolicy = NULL;
+	task_unlock(task);
+	mpol_put(pol);
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3fbe73a6fe4b..a2214c64ed3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3137,54 +3137,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	return NULL;
 }
 
-static inline bool
-should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
-		     enum compact_result compact_result,
-		     enum compact_priority *compact_priority,
-		     int compaction_retries)
-{
-	int max_retries = MAX_COMPACT_RETRIES;
-
-	if (!order)
-		return false;
-
-	/*
-	 * compaction considers all the zone as desperately out of memory
-	 * so it doesn't really make much sense to retry except when the
-	 * failure could be caused by insufficient priority
-	 */
-	if (compaction_failed(compact_result)) {
-		if (*compact_priority > MIN_COMPACT_PRIORITY) {
-			(*compact_priority)--;
-			return true;
-		}
-		return false;
-	}
-
-	/*
-	 * make sure the compaction wasn't deferred or didn't bail out early
-	 * due to locks contention before we declare that we should give up.
-	 * But do not retry if the given zonelist is not suitable for
-	 * compaction.
-	 */
-	if (compaction_withdrawn(compact_result))
-		return compaction_zonelist_suitable(ac, order, alloc_flags);
-
-	/*
-	 * !costly requests are much more important than __GFP_REPEAT
-	 * costly ones because they are de facto nofail and invoke OOM
-	 * killer to move on while costly can fail and users are ready
-	 * to cope with that. 1/4 retries is rather arbitrary but we
-	 * would need much more detailed feedback from compaction to
-	 * make a better decision.
-	 */
-	if (order > PAGE_ALLOC_COSTLY_ORDER)
-		max_retries /= 4;
-	if (compaction_retries <= max_retries)
-		return true;
-
-	return false;
-}
 #else
 static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
@@ -3195,6 +3147,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	return NULL;
 }
 
+#endif /* CONFIG_COMPACTION */
+
 static inline bool
 should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
 		     enum compact_result compact_result,
@@ -3221,7 +3175,6 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 	}
 	return false;
 }
-#endif /* CONFIG_COMPACTION */
 
 /* Perform direct synchronous page reclaim */
 static int
@@ -4407,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
 	do {
 		zone_type--;
 		zone = pgdat->node_zones + zone_type;
-		if (populated_zone(zone)) {
+		if (managed_zone(zone)) {
 			zoneref_set_zone(zone,
 				&zonelist->_zonerefs[nr_zones++]);
 			check_highest_zone(zone_type);
@@ -4645,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
 		for (j = 0; j < nr_nodes; j++) {
 			node = node_order[j];
 			z = &NODE_DATA(node)->node_zones[zone_type];
-			if (populated_zone(z)) {
+			if (managed_zone(z)) {
 				zoneref_set_zone(z,
 					&zonelist->_zonerefs[pos++]);
 				check_highest_zone(zone_type);
diff --git a/mm/readahead.c b/mm/readahead.c
index 65ec288dc057..c8a955b1297e 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/dax.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/blkdev.h>
@@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	if (!mapping || !mapping->a_ops)
 		return -EINVAL;
 
+	/*
+	 * Readahead doesn't make sense for DAX inodes, but we don't want it
+	 * to report a failure either.  Instead, we just return success and
+	 * don't do any work.
+	 */
+	if (dax_mapping(mapping))
+		return 0;
+
 	return force_page_cache_readahead(mapping, filp, index, nr);
 }
 
diff --git a/mm/usercopy.c b/mm/usercopy.c
index 8ebae91a6b55..089328f2b920 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -83,7 +83,7 @@ static bool overlaps(const void *ptr, unsigned long n, unsigned long low,
 	unsigned long check_high = check_low + n;
 
 	/* Does not overlap if entirely above or entirely below. */
-	if (check_low >= high || check_high < low)
+	if (check_low >= high || check_high <= low)
 		return false;
 
 	return true;
@@ -124,7 +124,7 @@ static inline const char *check_kernel_text_object(const void *ptr,
 static inline const char *check_bogus_address(const void *ptr, unsigned long n)
 {
 	/* Reject if object wraps past end of memory. */
-	if (ptr + n < ptr)
+	if ((unsigned long)ptr + n < (unsigned long)ptr)
 		return "<wrapped address>";
 
 	/* Reject if NULL or ZERO-allocation. */
@@ -134,31 +134,16 @@ static inline const char *check_bogus_address(const void *ptr, unsigned long n)
 	return NULL;
 }
 
-static inline const char *check_heap_object(const void *ptr, unsigned long n,
-					    bool to_user)
+/* Checks for allocs that are marked in some way as spanning multiple pages. */
+static inline const char *check_page_span(const void *ptr, unsigned long n,
+					  struct page *page, bool to_user)
 {
-	struct page *page, *endpage;
+#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN
 	const void *end = ptr + n - 1;
+	struct page *endpage;
 	bool is_reserved, is_cma;
 
 	/*
-	 * Some architectures (arm64) return true for virt_addr_valid() on
-	 * vmalloced addresses. Work around this by checking for vmalloc
-	 * first.
-	 */
-	if (is_vmalloc_addr(ptr))
-		return NULL;
-
-	if (!virt_addr_valid(ptr))
-		return NULL;
-
-	page = virt_to_head_page(ptr);
-
-	/* Check slab allocator for flags and size. */
-	if (PageSlab(page))
-		return __check_heap_object(ptr, n, page);
-
-	/*
 	 * Sometimes the kernel data regions are not marked Reserved (see
 	 * check below). And sometimes [_sdata,_edata) does not cover
 	 * rodata and/or bss, so check each range explicitly.
@@ -186,7 +171,7 @@ static inline const char *check_heap_object(const void *ptr, unsigned long n,
 		   ((unsigned long)end & (unsigned long)PAGE_MASK)))
 		return NULL;
 
-	/* Allow if start and end are inside the same compound page. */
+	/* Allow if fully inside the same compound (__GFP_COMP) page. */
 	endpage = virt_to_head_page(end);
 	if (likely(endpage == page))
 		return NULL;
@@ -199,20 +184,44 @@ static inline const char *check_heap_object(const void *ptr, unsigned long n,
 	is_reserved = PageReserved(page);
 	is_cma = is_migrate_cma_page(page);
 	if (!is_reserved && !is_cma)
-		goto reject;
+		return "<spans multiple pages>";
 
 	for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
 		page = virt_to_head_page(ptr);
 		if (is_reserved && !PageReserved(page))
-			goto reject;
+			return "<spans Reserved and non-Reserved pages>";
 		if (is_cma && !is_migrate_cma_page(page))
-			goto reject;
+			return "<spans CMA and non-CMA pages>";
 	}
+#endif
 
 	return NULL;
+}
+
+static inline const char *check_heap_object(const void *ptr, unsigned long n,
+					    bool to_user)
+{
+	struct page *page;
+
+	/*
+	 * Some architectures (arm64) return true for virt_addr_valid() on
+	 * vmalloced addresses. Work around this by checking for vmalloc
+	 * first.
+	 */
+	if (is_vmalloc_addr(ptr))
+		return NULL;
+
+	if (!virt_addr_valid(ptr))
+		return NULL;
+
+	page = virt_to_head_page(ptr);
+
+	/* Check slab allocator for flags and size. */
+	if (PageSlab(page))
+		return __check_heap_object(ptr, n, page);
 
-reject:
-	return "<spans multiple pages>";
+	/* Verify object does not incorrectly span multiple pages. */
+	return check_page_span(ptr, n, page, to_user);
 }
 
 /*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 374d95d04178..b1e12a1ea9cf 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec,
 
 	for (zid = sc->reclaim_idx; zid >= 0; zid--) {
 		zone = &pgdat->node_zones[zid];
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
@@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 		struct zone *zone = &pgdat->node_zones[zid];
 		unsigned long inactive_zone, active_zone;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		inactive_zone = zone_page_state(zone,
@@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 
 		for (z = 0; z < MAX_NR_ZONES; z++) {
 			struct zone *zone = &pgdat->node_zones[z];
-			if (!populated_zone(zone))
+			if (!managed_zone(zone))
 				continue;
 
 			total_high_wmark += high_wmark_pages(zone);
@@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	/* If compaction would go ahead or the allocation would succeed, stop */
 	for (z = 0; z <= sc->reclaim_idx; z++) {
 		struct zone *zone = &pgdat->node_zones[z];
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
@@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
 
 	for (i = 0; i <= ZONE_NORMAL; i++) {
 		zone = &pgdat->node_zones[i];
-		if (!populated_zone(zone) ||
+		if (!managed_zone(zone) ||
 		    pgdat_reclaimable_pages(pgdat) == 0)
 			continue;
 
@@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 	for (i = 0; i <= classzone_idx; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (!zone_balanced(zone, order, classzone_idx))
@@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
 	sc->nr_to_reclaim = 0;
 	for (z = 0; z <= sc->reclaim_idx; z++) {
 		zone = pgdat->node_zones + z;
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
@@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		if (buffer_heads_over_limit) {
 			for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
 				zone = pgdat->node_zones + i;
-				if (!populated_zone(zone))
+				if (!managed_zone(zone))
 					continue;
 
 				sc.reclaim_idx = i;
@@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
 		 */
 		for (i = classzone_idx; i >= 0; i--) {
 			zone = pgdat->node_zones + i;
-			if (!populated_zone(zone))
+			if (!managed_zone(zone))
 				continue;
 
 			if (zone_balanced(zone, sc.order, classzone_idx))
@@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	pg_data_t *pgdat;
 	int z;
 
-	if (!populated_zone(zone))
+	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
@@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	/* Only wake kswapd if all zones are unbalanced */
 	for (z = 0; z <= classzone_idx; z++) {
 		zone = pgdat->node_zones + z;
-		if (!populated_zone(zone))
+		if (!managed_zone(zone))
 			continue;
 
 		if (zone_balanced(zone, order, classzone_idx))