Merge android-4.4.101 (f0b9d2d) into msm-4.4

* refs/heads/tmp-f0b9d2d
  Linux 4.4.101
  mm/pagewalk.c: report holes in hugetlb ranges
  mm/page_ext.c: check if page_ext is not prepared
  mm: check the return value of lookup_page_ext for all call sites
  coda: fix 'kernel memory exposure attempt' in fsync
  mm/page_alloc.c: broken deferred calculation
  ipmi: fix unsigned long underflow
  ocfs2: should wait dio before inode lock in ocfs2_setattr()
  nvme: Fix memory order on async queue deletion
  arm64: fix dump_instr when PAN and UAO are in use
  serial: omap: Fix EFR write on RTS deassertion
  ima: do not update security.ima if appraisal status is not INTEGRITY_PASS
  net/sctp: Always set scope_id in sctp_inet6_skb_msgname
  fealnx: Fix building error on MIPS
  sctp: do not peel off an assoc from one netns to another one
  af_netlink: ensure that NLMSG_DONE never fails in dumps
  vlan: fix a use-after-free in vlan_device_event()
  bonding: discard lowest hash bit for 802.3ad layer3+4
  netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed
  tcp: do not mangle skb->cb[] in tcp_make_synack()

Conflicts:
	mm/debug-pagealloc.c
	mm/page_ext.c
	mm/page_owner.c

Change-Id: I551aff1b4c8a0d72f64a234abb8ac88990fbc9e5
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 100
+SUBLEVEL = 101
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

drivers/char/ipmi/ipmi_msghandler.c

@@ -4029,7 +4029,8 @@ smi_from_recv_msg(ipmi_smi_t intf, struct ipmi_recv_msg *recv_msg,
 }
 
 static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
-			      struct list_head *timeouts, long timeout_period,
+			      struct list_head *timeouts,
+			      unsigned long timeout_period,
 			      int slot, unsigned long *flags,
 			      unsigned int *waiting_msgs)
 {
@@ -4042,8 +4043,8 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 	if (!ent->inuse)
 		return;
 
-	ent->timeout -= timeout_period;
-	if (ent->timeout > 0) {
+	if (timeout_period < ent->timeout) {
+		ent->timeout -= timeout_period;
 		(*waiting_msgs)++;
 		return;
 	}
@@ -4109,7 +4110,8 @@ static void check_msg_timeout(ipmi_smi_t intf, struct seq_table *ent,
 	}
 }
 
-static unsigned int ipmi_timeout_handler(ipmi_smi_t intf, long timeout_period)
+static unsigned int ipmi_timeout_handler(ipmi_smi_t intf,
+					 unsigned long timeout_period)
 {
 	struct list_head     timeouts;
 	struct ipmi_recv_msg *msg, *msg2;

drivers/net/bonding/bond_main.c

@@ -3166,7 +3166,7 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 
-	return hash;
+	return hash >> 1;
 }
 
 /*-------------------------- Device entry points ----------------------------*/

drivers/net/ethernet/fealnx.c

@@ -257,8 +257,8 @@ enum rx_desc_status_bits {
 	RXFSD = 0x00000800,	/* first descriptor */
 	RXLSD = 0x00000400,	/* last descriptor */
 	ErrorSummary = 0x80,	/* error summary */
-	RUNT = 0x40,		/* runt packet received */
-	LONG = 0x20,		/* long packet received */
+	RUNTPKT = 0x40,		/* runt packet received */
+	LONGPKT = 0x20,		/* long packet received */
 	FAE = 0x10,		/* frame align error */
 	CRC = 0x08,		/* crc error */
 	RXER = 0x04,		/* receive error */
@@ -1633,7 +1633,7 @@ static int netdev_rx(struct net_device *dev)
 					       dev->name, rx_status);
 
 				dev->stats.rx_errors++;	/* end of a packet. */
-				if (rx_status & (LONG | RUNT))
+				if (rx_status & (LONGPKT | RUNTPKT))
 					dev->stats.rx_length_errors++;
 				if (rx_status & RXER)
 					dev->stats.rx_frame_errors++;

drivers/nvme/host/pci.c

@@ -350,8 +350,8 @@ static void async_completion(struct nvme_queue *nvmeq, void *ctx,
 	struct async_cmd_info *cmdinfo = ctx;
 	cmdinfo->result = le32_to_cpup(&cqe->result);
 	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
-	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
 	blk_mq_free_request(cmdinfo->req);
+	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
 }
 
 static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,

drivers/tty/serial/omap-serial.c

@@ -693,7 +693,7 @@ static void serial_omap_set_mctrl(struct uart_port *port, unsigned int mctrl)
 	if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS))
 		up->efr |= UART_EFR_RTS;
 	else
-		up->efr &= UART_EFR_RTS;
+		up->efr &= ~UART_EFR_RTS;
 	serial_out(up, UART_EFR, up->efr);
 	serial_out(up, UART_LCR, lcr);
 

fs/coda/upcall.c

@@ -446,8 +446,7 @@ int venus_fsync(struct super_block *sb, struct CodaFid *fid)
 	UPARG(CODA_FSYNC);
 
 	inp->coda_fsync.VFid = *fid;
-	error = coda_upcall(coda_vcp(sb), sizeof(union inputArgs),
-			    &outsize, inp);
+	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
 	CODA_FREE(inp, insize);
 	return error;

fs/ocfs2/file.c

@@ -1166,6 +1166,13 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 	size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
 	if (size_change) {
+		/*
+		 * Here we should wait dio to finish before inode lock
+		 * to avoid a deadlock between ocfs2_setattr() and
+		 * ocfs2_dio_end_io_write()
+		 */
+		inode_dio_wait(inode);
+
 		status = ocfs2_rw_lock(inode, 1);
 		if (status < 0) {
 			mlog_errno(status);
@@ -1186,8 +1193,6 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		if (status)
 			goto bail_unlock;
 
-		inode_dio_wait(inode);
-
 		if (i_size_read(inode) >= attr->ia_size) {
 			if (ocfs2_should_order_data(inode)) {
 				status = ocfs2_begin_ordered_truncate(inode,

include/linux/mmzone.h

@@ -715,7 +715,8 @@ typedef struct pglist_data {
 	 * is the first PFN that needs to be initialised.
 	 */
 	unsigned long first_deferred_pfn;
-	unsigned long static_init_size;
+	/* Number of non-deferred pages */
+	unsigned long static_init_pgcnt;
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 } pg_data_t;
 

include/linux/skbuff.h

@@ -3400,6 +3400,13 @@ static inline void nf_reset_trace(struct sk_buff *skb)
 #endif
 }
 
+static inline void ipvs_reset(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IP_VS)
+	skb->ipvs_property = 0;
+#endif
+}
+
 /* Note: This doesn't put any conntrack and bridge info in dst. */
 static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src,
 			     bool copy)

mm/page_alloc.c

@@ -286,28 +286,37 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+
+/*
+ * Determine how many pages need to be initialized durig early boot
+ * (non-deferred initialization).
+ * The value of first_deferred_pfn will be set later, once non-deferred pages
+ * are initialized, but for now set it ULONG_MAX.
+ */
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
-	unsigned long max_initialise;
-	unsigned long reserved_lowmem;
+	phys_addr_t start_addr, end_addr;
+	unsigned long max_pgcnt;
+	unsigned long reserved;
 
 	/*
 	 * 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));
+	max_pgcnt = 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;
+	start_addr = PFN_PHYS(pgdat->node_start_pfn);
+	end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
+	reserved = memblock_reserved_memory_within(start_addr, end_addr);
+	max_pgcnt += PHYS_PFN(reserved);
 
-	pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
+	pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
 	pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -343,7 +352,7 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 		return true;
 	/* Initialise at least 2G of the highest zone */
 	(*nr_initialised)++;
-	if ((*nr_initialised > pgdat->static_init_size) &&
+	if ((*nr_initialised > pgdat->static_init_pgcnt) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
 		pgdat->first_deferred_pfn = pfn;
 		return false;

mm/page_ext.c

@@ -103,7 +103,6 @@ struct page_ext *lookup_page_ext(struct page *page)
 	struct page_ext *base;
 
 	base = NODE_DATA(page_to_nid(page))->node_page_ext;
-#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING)
 	/*
 	 * The sanity checks the page allocator does upon freeing a
 	 * page can reach here before the page_ext arrays are
@@ -115,7 +114,6 @@ struct page_ext *lookup_page_ext(struct page *page)
 	 */
 	if (unlikely(!base))
 		return NULL;
-#endif
 	offset = pfn - round_down(node_start_pfn(page_to_nid(page)),
 					MAX_ORDER_NR_PAGES);
 	return base + offset;
@@ -180,7 +178,6 @@ struct page_ext *lookup_page_ext(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 	struct mem_section *section = __pfn_to_section(pfn);
-#if defined(CONFIG_DEBUG_VM) || defined(CONFIG_PAGE_POISONING)
 	/*
 	 * The sanity checks the page allocator does upon freeing a
 	 * page can reach here before the page_ext arrays are
@@ -192,7 +189,6 @@ struct page_ext *lookup_page_ext(struct page *page)
 	 */
 	if (!section->page_ext)
 		return NULL;
-#endif
 	return section->page_ext + pfn;
 }
 

mm/pagewalk.c

@@ -142,8 +142,12 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end,
 	do {
 		next = hugetlb_entry_end(h, addr, end);
 		pte = huge_pte_offset(walk->mm, addr & hmask);
-		if (pte && walk->hugetlb_entry)
+
+		if (pte)
 			err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
+		else if (walk->pte_hole)
+			err = walk->pte_hole(addr, next, walk);
+
 		if (err)
 			break;
 	} while (addr = next, addr != end);

net/8021q/vlan.c

@@ -376,6 +376,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			dev->name);
 		vlan_vid_add(dev, htons(ETH_P_8021Q), 0);
 	}
+	if (event == NETDEV_DOWN &&
+	    (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
 
 	vlan_info = rtnl_dereference(dev->vlan_info);
 	if (!vlan_info)
@@ -423,9 +426,6 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 		struct net_device *tmp;
 		LIST_HEAD(close_list);
 
-		if (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
-			vlan_vid_del(dev, htons(ETH_P_8021Q), 0);
-
 		/* Put all VLANs for this dev in the down state too.  */
 		vlan_group_for_each_dev(grp, i, vlandev) {
 			flgs = vlandev->flags;

net/core/skbuff.c

@@ -4255,6 +4255,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	if (!xnet)
 		return;
 
+	ipvs_reset(skb);
 	skb_orphan(skb);
 	skb->mark = 0;
 }

net/ipv4/tcp_output.c

@@ -3018,13 +3018,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	tcp_ecn_make_synack(req, th);
 	th->source = htons(ireq->ir_num);
 	th->dest = ireq->ir_rmt_port;
-	/* Setting of flags are superfluous here for callers (and ECE is
-	 * not even correctly set)
-	 */
-	tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
-			     TCPHDR_SYN | TCPHDR_ACK);
-
-	th->seq = htonl(TCP_SKB_CB(skb)->seq);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	th->seq = htonl(tcp_rsk(req)->snt_isn);
 	/* XXX data is queued and acked as is. No buffer/window check */
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
 

net/netlink/af_netlink.c

@@ -2057,7 +2057,7 @@ static int netlink_dump(struct sock *sk)
 	struct sk_buff *skb = NULL;
 	struct nlmsghdr *nlh;
 	struct module *module;
-	int len, err = -ENOBUFS;
+	int err = -ENOBUFS;
 	int alloc_min_size;
 	int alloc_size;
 
@@ -2105,9 +2105,11 @@ static int netlink_dump(struct sock *sk)
 	skb_reserve(skb, skb_tailroom(skb) - alloc_size);
 	netlink_skb_set_owner_r(skb, sk);
 
-	len = cb->dump(skb, cb);
+	if (nlk->dump_done_errno > 0)
+		nlk->dump_done_errno = cb->dump(skb, cb);
 
-	if (len > 0) {
+	if (nlk->dump_done_errno > 0 ||
+	    skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
 		mutex_unlock(nlk->cb_mutex);
 
 		if (sk_filter(sk, skb))
@@ -2117,13 +2119,15 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI);
-	if (!nlh)
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
+			       sizeof(nlk->dump_done_errno), NLM_F_MULTI);
+	if (WARN_ON(!nlh))
 		goto errout_skb;
 
 	nl_dump_check_consistent(cb, nlh);
 
-	memcpy(nlmsg_data(nlh), &len, sizeof(len));
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
+	       sizeof(nlk->dump_done_errno));
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
@@ -2188,6 +2192,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->skb = skb;
 
 	nlk->cb_running = true;
+	nlk->dump_done_errno = INT_MAX;
 
 	mutex_unlock(nlk->cb_mutex);
 

net/netlink/af_netlink.h

@@ -38,6 +38,7 @@ struct netlink_sock {
 	wait_queue_head_t	wait;
 	bool			bound;
 	bool			cb_running;
+	int			dump_done_errno;
 	struct netlink_callback	cb;
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;

net/sctp/ipv6.c

@@ -806,6 +806,8 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
 			struct sctp_ulpevent *ev = sctp_skb2event(skb);
 			addr->v6.sin6_scope_id = ev->iif;
+		} else {
+			addr->v6.sin6_scope_id = 0;
 		}
 	}
 

net/sctp/socket.c

@@ -4453,6 +4453,10 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp)
 	struct socket *sock;
 	int err = 0;
 
+	/* Do not peel off from one netns to another one. */
+	if (!net_eq(current->nsproxy->net_ns, sock_net(sk)))
+		return -EINVAL;
+
 	/* Do not peel off from one netns to another one. */
 	if (!net_eq(current->nsproxy->net_ns, sock_net(sk)))
 		return -EINVAL;

security/integrity/ima/ima_appraise.c

@@ -297,6 +297,9 @@ void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
 	if (iint->flags & IMA_DIGSIG)
 		return;
 
+	if (iint->ima_file_status != INTEGRITY_PASS)
+		return;
+
 	rc = ima_collect_measurement(iint, file, NULL, NULL);
 	if (rc < 0)
 		return;