Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "9 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  fs/proc/proc_sysctl.c: Fix a NULL pointer dereference
  mm/page_alloc.c: fix never set ALLOC_NOFRAGMENT flag
  mm/page_alloc.c: avoid potential NULL pointer dereference
  mm, page_alloc: always use a captured page regardless of compaction result
  mm: do not boost watermarks to avoid fragmentation for the DISCONTIG memory model
  lib/test_vmalloc.c: do not create cpumask_t variable on stack
  lib/Kconfig.debug: fix build error without CONFIG_BLOCK
  zram: pass down the bvec we need to read into in the work struct
  mm/memory_hotplug.c: drop memory device reference after find_memory_block()

7 files changed, 39 insertions, 23 deletions

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 6af24cdb25cc..3f13d8599337 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to
 increase the success rate of future high-order allocations such as SLUB
 allocations, THP and hugetlbfs pages.
 
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
+To make it sensible with respect to the watermark_scale_factor
+parameter, the unit is in fractions of 10,000. The default value of
+15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
+watermark will be reclaimed in the event of a pageblock being mixed due
+to fragmentation. The level of reclaim is determined by the number of
+fragmentation events that occurred in the recent past. If this value is
+smaller than a pageblock then a pageblocks worth of pages will be reclaimed
+(e.g.  2MB on 64-bit x86). A boost factor of 0 will disable the feature.
 
 =============================================================
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 399cad7daae7..d58a359a6622 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -774,18 +774,18 @@ struct zram_work {
 	struct zram *zram;
 	unsigned long entry;
 	struct bio *bio;
+	struct bio_vec bvec;
 };
 
 #if PAGE_SIZE != 4096
 static void zram_sync_read(struct work_struct *work)
 {
-	struct bio_vec bvec;
 	struct zram_work *zw = container_of(work, struct zram_work, work);
 	struct zram *zram = zw->zram;
 	unsigned long entry = zw->entry;
 	struct bio *bio = zw->bio;
 
-	read_from_bdev_async(zram, &bvec, entry, bio);
+	read_from_bdev_async(zram, &zw->bvec, entry, bio);
 }
 
 /*
@@ -798,6 +798,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 {
 	struct zram_work work;
 
+	work.bvec = *bvec;
 	work.zram = zram;
 	work.entry = entry;
 	work.bio = bio;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d65390727541..7325baa8f9d4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1626,9 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header)
 	if (--header->nreg)
 		return;
 
-	if (parent)
+	if (parent) {
 		put_links(header);
-	start_unregistering(header);
+		start_unregistering(header);
+	}
+
 	if (!--header->count)
 		kfree_rcu(header, rcu);
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 00dbcdbc9a0d..d5a4a4036d2f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1929,6 +1929,7 @@ config TEST_KMOD
 	depends on m
 	depends on BLOCK && (64BIT || LBDAF)	  # for XFS, BTRFS
 	depends on NETDEVICES && NET_CORE && INET # for TUN
+	depends on BLOCK
 	select TEST_LKM
 	select XFS_FS
 	select TUN
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 83cdcaa82bf6..f832b095afba 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -383,14 +383,14 @@ static void shuffle_array(int *arr, int n)
 static int test_func(void *private)
 {
 	struct test_driver *t = private;
-	cpumask_t newmask = CPU_MASK_NONE;
 	int random_array[ARRAY_SIZE(test_case_array)];
 	int index, i, j, ret;
 	ktime_t kt;
 	u64 delta;
 
-	cpumask_set_cpu(t->cpu, &newmask);
-	set_cpus_allowed_ptr(current, &newmask);
+	ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu));
+	if (ret < 0)
+		pr_err("Failed to set affinity to %d CPU\n", t->cpu);
 
 	for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
 		random_array[i] = i;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0082d699be94..b236069ff0d8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	 */
 	mem = find_memory_block(__pfn_to_section(pfn));
 	nid = mem->nid;
+	put_device(&mem->dev);
 
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c6ce20aaf80b..c02cff1ed56e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = {
 
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
 int watermark_boost_factor __read_mostly = 15000;
+#endif
 int watermark_scale_factor = 10;
 
 static unsigned long nr_kernel_pages __initdata;
@@ -3419,8 +3432,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 		alloc_flags |= ALLOC_KSWAPD;
 
 #ifdef CONFIG_ZONE_DMA32
+	if (!zone)
+		return alloc_flags;
+
 	if (zone_idx(zone) != ZONE_NORMAL)
-		goto out;
+		return alloc_flags;
 
 	/*
 	 * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
@@ -3429,9 +3445,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 	 */
 	BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
 	if (nr_online_nodes > 1 && !populated_zone(--zone))
-		goto out;
+		return alloc_flags;
 
-out:
+	alloc_flags |= ALLOC_NOFRAGMENT;
 #endif /* CONFIG_ZONE_DMA32 */
 	return alloc_flags;
 }
@@ -3773,11 +3789,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
 
-	if (*compact_result <= COMPACT_INACTIVE) {
-		WARN_ON_ONCE(page);
-		return NULL;
-	}
-
 	/*
 	 * At least in one zone compaction wasn't deferred or skipped, so let's
 	 * count a compaction stall