Merge 4.9.31 into android-4.9

Changes in 4.9.31
	dccp/tcp: do not inherit mc_list from parent
	driver: vrf: Fix one possible use-after-free issue
	ipv6/dccp: do not inherit ipv6_mc_list from parent
	s390/qeth: handle sysfs error during initialization
	s390/qeth: unbreak OSM and OSN support
	s390/qeth: avoid null pointer dereference on OSN
	s390/qeth: add missing hash table initializations
	bpf, arm64: fix faulty emission of map access in tail calls
	netem: fix skb_orphan_partial()
	net: fix compile error in skb_orphan_partial()
	tcp: avoid fragmenting peculiar skbs in SACK
	sctp: fix src address selection if using secondary addresses for ipv6
	sctp: do not inherit ipv6_{mc|ac|fl}_list from parent
	net/packet: fix missing net_device reference release
	net/mlx5e: Use the correct pause values for ethtool advertising
	net/mlx5e: Fix ethtool pause support and advertise reporting
	tcp: eliminate negative reordering in tcp_clean_rtx_queue
	net: Improve handling of failures on link and route dumps
	ipv6: Prevent overrun when parsing v6 header options
	ipv6: Check ip6_find_1stfragopt() return value properly.
	bridge: netlink: check vlan_default_pvid range
	qmi_wwan: add another Lenovo EM74xx device ID
	bridge: start hello_timer when enabling KERNEL_STP in br_stp_start
	ipv6: fix out of bound writes in __ip6_append_data()
	bonding: fix accounting of active ports in 3ad
	net/mlx5: Avoid using pending command interface slots
	net: phy: marvell: Limit errata to 88m1101
	vlan: Fix tcp checksum offloads in Q-in-Q vlans
	be2net: Fix offload features for Q-in-Q packets
	virtio-net: enable TSO/checksum offloads for Q-in-Q vlans
	tcp: avoid fastopen API to be used on AF_UNSPEC
	sctp: fix ICMP processing if skb is non-linear
	ipv4: add reference counting to metrics
	bpf: add bpf_clone_redirect to bpf_helper_changes_pkt_data
	sparc: Fix -Wstringop-overflow warning
	sparc/ftrace: Fix ftrace graph time measurement
	fs/ufs: Set UFS default maximum bytes per file
	powerpc/spufs: Fix hash faults for kernel regions
	drivers/tty: 8250: only call fintek_8250_probe when doing port I/O
	i2c: i2c-tiny-usb: fix buffer not being DMA capable
	crypto: skcipher - Add missing API setkey checks
	x86/MCE: Export memory_error()
	acpi, nfit: Fix the memory error check in nfit_handle_mce()
	Revert "ACPI / button: Change default behavior to lid_init_state=open"
	mmc: sdhci-iproc: suppress spurious interrupt with Multiblock read
	iscsi-target: Always wait for kthread_should_stop() before kthread exit
	ibmvscsis: Clear left-over abort_cmd pointers
	ibmvscsis: Fix the incorrect req_lim_delta
	HID: wacom: Have wacom_tpc_irq guard against possible NULL dereference
	nvme-rdma: support devices with queue size < 32
	nvme: use blk_mq_start_hw_queues() in nvme_kill_queues()
	nvme: avoid to use blk_mq_abort_requeue_list()
	scsi: mpt3sas: Force request partial completion alignment
	drm/radeon/ci: disable mclk switching for high refresh rates (v2)
	drm/radeon: Unbreak HPD handling for r600+
	drm/radeon: Fix vram_size/visible values in DRM_RADEON_GEM_INFO ioctl
	pcmcia: remove left-over %Z format
	ALSA: hda - apply STAC_9200_DELL_M22 quirk for Dell Latitude D430
	mm/migrate: fix refcount handling when !hugepage_migration_supported()
	mlock: fix mlock count can not decrease in race condition
	mm: consider memblock reservations for deferred memory initialization sizing
	RDMA/qib,hfi1: Fix MR reference count leak on write with immediate
	x86/boot: Use CROSS_COMPILE prefix for readelf
	ksm: prevent crash after write_protect_page fails
	slub/memcg: cure the brainless abuse of sysfs attributes
	mm/slub.c: trace free objects at KERN_INFO
	drm/gma500/psb: Actually use VBT mode when it is found
	xfs: Fix missed holes in SEEK_HOLE implementation
	xfs: use ->b_state to fix buffer I/O accounting release race
	xfs: fix off-by-one on max nr_pages in xfs_find_get_desired_pgoff()
	xfs: verify inline directory data forks
	xfs: rework the inline directory verifiers
	xfs: fix kernel memory exposure problems
	xfs: use dedicated log worker wq to avoid deadlock with cil wq
	xfs: fix over-copying of getbmap parameters from userspace
	xfs: actually report xattr extents via iomap
	xfs: drop iolock from reclaim context to appease lockdep
	xfs: fix integer truncation in xfs_bmap_remap_alloc
	xfs: handle array index overrun in xfs_dir2_leaf_readbuf()
	xfs: prevent multi-fsb dir readahead from reading random blocks
	xfs: fix up quotacheck buffer list error handling
	xfs: support ability to wait on new inodes
	xfs: update ag iterator to support wait on new inodes
	xfs: wait on new inodes during quotaoff dquot release
	xfs: reserve enough blocks to handle btree splits when remapping
	xfs: fix use-after-free in xfs_finish_page_writeback
	xfs: fix indlen accounting error on partial delalloc conversion
	xfs: BMAPX shouldn't barf on inline-format directories
	xfs: bad assertion for delalloc an extent that start at i_size
	xfs: xfs_trans_alloc_empty
	xfs: avoid mount-time deadlock in CoW extent recovery
	xfs: fix unaligned access in xfs_btree_visit_blocks
	xfs: Fix off-by-in in loop termination in xfs_find_get_desired_pgoff()
	Linux 4.9.31

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

mm/ksm.c

@@ -1002,8 +1002,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 		goto out;
 
 	if (PageTransCompound(page)) {
-		err = split_huge_page(page);
-		if (err)
+		if (split_huge_page(page))
 			goto out_unlock;
 	}
 

mm/memblock.c

@@ -1696,6 +1696,29 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name
 	}
 }
 
+extern unsigned long __init_memblock
+memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
+{
+	struct memblock_region *rgn;
+	unsigned long size = 0;
+	int idx;
+
+	for_each_memblock_type((&memblock.reserved), rgn) {
+		phys_addr_t start, end;
+
+		if (rgn->base + rgn->size < start_addr)
+			continue;
+		if (rgn->base > end_addr)
+			continue;
+
+		start = rgn->base;
+		end = start + rgn->size;
+		size += end - start;
+	}
+
+	return size;
+}
+
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");

mm/memory-failure.c

@@ -1587,12 +1587,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 			pfn, ret, page->flags);
-		/*
-		 * We know that soft_offline_huge_page() tries to migrate
-		 * only one hugepage pointed to by hpage, so we need not
-		 * run through the pagelist here.
-		 */
-		putback_active_hugepage(hpage);
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
 		if (ret > 0)
 			ret = -EIO;
 	} else {

mm/mlock.c

@@ -285,7 +285,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked;
+	int delta_munlocked = -nr;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
@@ -305,6 +305,8 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 				continue;
 			else
 				__munlock_isolation_failed(page);
+		} else {
+			delta_munlocked++;
 		}
 
 		/*
@@ -316,7 +318,6 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 		pagevec_add(&pvec_putback, pvec->pages[i]);
 		pvec->pages[i] = NULL;
 	}
-	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(zone_lru_lock(zone));
 

mm/page_alloc.c

@@ -286,6 +286,26 @@ int page_group_by_mobility_disabled __read_mostly;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
+	unsigned long max_initialise;
+	unsigned long reserved_lowmem;
+
+	/*
+	 * Initialise at least 2G of a node but also take into account that
+	 * two large system hashes that can take up 1GB for 0.25TB/node.
+	 */
+	max_initialise = max(2UL << (30 - PAGE_SHIFT),
+		(pgdat->node_spanned_pages >> 8));
+
+	/*
+	 * Compensate the all the memblock reservations (e.g. crash kernel)
+	 * from the initial estimation to make sure we will initialize enough
+	 * memory to boot.
+	 */
+	reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
+			pgdat->node_start_pfn + max_initialise);
+	max_initialise += reserved_lowmem;
+
+	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -308,20 +328,11 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 				unsigned long pfn, unsigned long zone_end,
 				unsigned long *nr_initialised)
 {
-	unsigned long max_initialise;
-
 	/* Always populate low zones for address-contrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-	/*
-	 * Initialise at least 2G of a node but also take into account that
-	 * two large system hashes that can take up 1GB for 0.25TB/node.
-	 */
-	max_initialise = max(2UL << (30 - PAGE_SHIFT),
-		(pgdat->node_spanned_pages >> 8));
-
 	(*nr_initialised)++;
-	if ((*nr_initialised > max_initialise) &&
+	if ((*nr_initialised > pgdat->static_init_size) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;
@@ -5911,7 +5922,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	/* pg_data_t should be reset to zero when it's allocated */
 	WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
 
-	reset_deferred_meminit(pgdat);
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
 	pgdat->per_cpu_nodestats = NULL;
@@ -5933,6 +5943,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 		(unsigned long)pgdat->node_mem_map);
 #endif
 
+	reset_deferred_meminit(pgdat);
 	free_area_init_core(pgdat);
 }
 

mm/slub.c

@@ -496,10 +496,11 @@ static inline int check_valid_pointer(struct kmem_cache *s,
 	return 1;
 }
 
-static void print_section(char *text, u8 *addr, unsigned int length)
+static void print_section(char *level, char *text, u8 *addr,
+			  unsigned int length)
 {
 	metadata_access_enable();
-	print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
+	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
 			length, 1);
 	metadata_access_disable();
 }
@@ -636,14 +637,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	       p, p - addr, get_freepointer(s, p));
 
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+		print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
+			      s->red_left_pad);
 	else if (p > addr + 16)
-		print_section("Bytes b4 ", p - 16, 16);
+		print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
 
-	print_section("Object ", p, min_t(unsigned long, s->object_size,
-				PAGE_SIZE));
+	print_section(KERN_ERR, "Object ", p,
+		      min_t(unsigned long, s->object_size, PAGE_SIZE));
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p + s->object_size,
+		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
 
 	if (s->offset)
@@ -658,7 +660,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 
 	if (off != size_from_object(s))
 		/* Beginning of the filler is the free pointer */
-		print_section("Padding ", p + off, size_from_object(s) - off);
+		print_section(KERN_ERR, "Padding ", p + off,
+			      size_from_object(s) - off);
 
 	dump_stack();
 }
@@ -820,7 +823,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding ", end - remainder, remainder);
+	print_section(KERN_ERR, "Padding ", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
 	return 0;
@@ -973,7 +976,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 			page->freelist);
 
 		if (!alloc)
-			print_section("Object ", (void *)object,
+			print_section(KERN_INFO, "Object ", (void *)object,
 					s->object_size);
 
 		dump_stack();
@@ -5452,6 +5455,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 		char mbuf[64];
 		char *buf;
 		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+		ssize_t len;
 
 		if (!attr || !attr->store || !attr->show)
 			continue;
@@ -5476,8 +5480,9 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 			buf = buffer;
 		}
 
-		attr->show(root_cache, buf);
-		attr->store(s, buf, strlen(buf));
+		len = attr->show(root_cache, buf);
+		if (len > 0)
+			attr->store(s, buf, len);
 	}
 
 	if (buffer)