3.14.9-stable review

@@ -48,6 +48,7 @@ struct at91_rtc_config {
 
 static const struct at91_rtc_config *at91_rtc_config;
 static DECLARE_COMPLETION(at91_rtc_updated);
+static DECLARE_COMPLETION(at91_rtc_upd_rdy);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;

@@ -161,6 +162,8 @@ static int at91_rtc_settime(struct devic
 		1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec);
 
+	wait_for_completion(&at91_rtc_upd_rdy);
+
 	/* Stop Time/Calendar from counting */
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);

@@ -183,7 +186,9 @@ static int at91_rtc_settime(struct devic
 
 	/* Restart Time/Calendar */
 	cr = at91_rtc_read(AT91_RTC_CR);
+	at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
 	at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM));
+	at91_rtc_write_ier(AT91_RTC_SECEV);
 
 	return 0;
 }

@@ -290,8 +295,10 @@ static irqreturn_t at91_rtc_interrupt(in
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
-		if (rtsr & AT91_RTC_SECEV)
-			events |= (RTC_UF | RTC_IRQF);
+		if (rtsr & AT91_RTC_SECEV) {
+			complete(&at91_rtc_upd_rdy);
+			at91_rtc_write_idr(AT91_RTC_SECEV);
+		}
 		if (rtsr & AT91_RTC_ACKUPD)
 			complete(&at91_rtc_updated);
 

@@ -413,6 +420,11 @@ static int __init at91_rtc_probe(struct
 		return PTR_ERR(rtc);
 	platform_set_drvdata(pdev, rtc);
 
+	/* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy
+	 * completion.
+	 */
+	at91_rtc_write_ier(AT91_RTC_SECEV);
+
 	dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n");
 	return 0;
 }

@@ -2342,6 +2342,10 @@ static void target_release_cmd_kref(stru
  */
 int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd)
 {
+	if (!se_sess) {
+		se_cmd->se_tfo->release_cmd(se_cmd);
+		return 1;
+	}
 	return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref,
 			&se_sess->sess_cmd_lock);
 }

@@ -314,6 +314,16 @@ static int chap_server_compute_md5(
 		goto out;
 	}
 	/*
+	 * During mutual authentication, the CHAP_C generated by the
+	 * initiator must not match the original CHAP_C generated by
+	 * the target.
+	 */
+	if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+		pr_err("initiator CHAP_C matches target CHAP_C, failing"
+		       " login attempt\n");
+		goto out;
+	}
+	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
 	tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);

@@ -199,6 +199,7 @@ int ima_collect_measurement(struct integ
 			    struct evm_ima_xattr_data **xattr_value,
 			    int *xattr_len)
 {
+	const char *audit_cause = "failed";
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_dentry->d_name.name;
 	int result = 0;

@@ -213,6 +214,12 @@ int ima_collect_measurement(struct integ
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
 
+		if (file->f_flags & O_DIRECT) {
+			audit_cause = "failed(directio)";
+			result = -EACCES;
+			goto out;
+		}
+
 		/* use default hash algorithm */
 		hash.hdr.algo = ima_hash_algo;
 

@@ -233,9 +240,10 @@ int ima_collect_measurement(struct integ
 				result = -ENOMEM;
 		}
 	}
+out:
 	if (result)
 		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
-				    filename, "collect_data", "failed",
+				    filename, "collect_data", audit_cause,
 				    result, 0);
 	return result;
 }

@@ -217,8 +217,11 @@ static int process_measurement(struct fi
 		xattr_ptr = &xattr_value;
 
 	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
-	if (rc != 0)
+	if (rc != 0) {
+		if (file->f_flags & O_DIRECT)
+			rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
 		goto out_digsig;
+	}
 
 	pathname = !filename ? ima_d_path(&file->f_path, &pathbuf) : filename;
 	if (!pathname)

@@ -351,7 +351,7 @@ enum {
 	Opt_obj_user, Opt_obj_role, Opt_obj_type,
 	Opt_subj_user, Opt_subj_role, Opt_subj_type,
 	Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
-	Opt_appraise_type, Opt_fsuuid
+	Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
 };
 
 static match_table_t policy_tokens = {

@@ -373,6 +373,7 @@ static match_table_t policy_tokens = {
 	{Opt_uid, "uid=%s"},
 	{Opt_fowner, "fowner=%s"},
 	{Opt_appraise_type, "appraise_type=%s"},
+	{Opt_permit_directio, "permit_directio"},
 	{Opt_err, NULL}
 };
 

@@ -621,6 +622,9 @@ static int ima_parse_rule(char *rule, st
 			else
 				result = -EINVAL;
 			break;
+		case Opt_permit_directio:
+			entry->flags |= IMA_PERMIT_DIRECTIO;
+			break;
 		case Opt_err:
 			ima_log_string(ab, "UNKNOWN", p);
 			result = -EINVAL;

@@ -30,6 +30,7 @@
 #define IMA_ACTION_FLAGS	0xff000000
 #define IMA_DIGSIG		0x01000000
 #define IMA_DIGSIG_REQUIRED	0x02000000
+#define IMA_PERMIT_DIRECTIO	0x04000000
 
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_APPRAISE_SUBMASK)

@@ -25,6 +25,36 @@
 
 static struct crypto_shash *ima_shash_tfm;
 
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op->read && !file->f_op->aio_read)
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else
+		ret = do_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
 int ima_init_crypto(void)
 {
 	long rc;

@@ -98,7 +128,7 @@ static int ima_calc_file_hash_tfm(struct
 	while (offset < i_size) {
 		int rbuf_len;
 
-		rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
 		if (rbuf_len < 0) {
 			rc = rbuf_len;
 			break;

@@ -285,12 +285,20 @@ out:
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0)
+	    && (xattr_data->type == EVM_XATTR_HMAC))
+		return -EPERM;
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }

@@ -1360,7 +1360,7 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);

@@ -1428,7 +1428,7 @@ static int netlink_bind(struct socket *s
 
 	/* Only superuser is allowed to listen multicasts */
 	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)

@@ -1490,7 +1490,7 @@ static int netlink_connect(struct socket
 		return -EINVAL;
 
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
-	    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)

@@ -2096,7 +2096,7 @@ static int netlink_setsockopt(struct soc
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)

@@ -2247,7 +2247,7 @@ static int netlink_sendmsg(struct kiocb
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
 	} else {
 		dst_portid = nlk->dst_portid;

@@ -23,7 +23,7 @@ int sock_diag_check_cookie(void *sk, __u
 void sock_diag_save_cookie(void *sk, __u32 *cookie);
 
 int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
-int sock_diag_put_filterinfo(struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype);
 
 #endif

@@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *s
 }
 EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
 
-int sock_diag_put_filterinfo(struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
 			     struct sk_buff *skb, int attrtype)
 {
 	struct nlattr *attr;

@@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct sock
 	unsigned int len;
 	int err = 0;
 
-	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+	if (!may_report_filterinfo) {
 		nla_reserve(skb, attrtype, 0);
 		return 0;
 	}

@@ -128,6 +128,7 @@ static int pdiag_put_fanout(struct packe
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			struct packet_diag_req *req,
+			bool may_report_filterinfo,
 			struct user_namespace *user_ns,
 			u32 portid, u32 seq, u32 flags, int sk_ino)
 {

@@ -172,7 +173,8 @@ static int sk_diag_fill(struct sock *sk,
 		goto out_nlmsg_trim;
 
 	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
-	    sock_diag_put_filterinfo(sk, skb, PACKET_DIAG_FILTER))
+	    sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
 	return nlmsg_end(skb, nlh);

@@ -188,9 +190,11 @@ static int packet_diag_dump(struct sk_bu
 	struct packet_diag_req *req;
 	struct net *net;
 	struct sock *sk;
+	bool may_report_filterinfo;
 
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
+	may_report_filterinfo = ns_capable(net->user_ns, CAP_NET_ADMIN);
 
 	mutex_lock(&net->packet.sklist_lock);
 	sk_for_each(sk, &net->packet.sklist) {

@@ -200,6 +204,7 @@ static int packet_diag_dump(struct sk_bu
 			goto next;
 
 		if (sk_diag_fill(sk, skb, req,
+				 may_report_filterinfo,
 				 sk_user_ns(NETLINK_CB(cb->skb).sk),
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq, NLM_F_MULTI,

@@ -2278,6 +2278,11 @@ int sock_get_timestampns(struct sock *,
 int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
 		       int type);
 
+bool sk_ns_capable(const struct sock *sk,
+		   struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
+
 /*
  *	Enable debug/info messages
  */

55 lines not on this page · raw message

@@ -169,4 +169,11 @@ struct netlink_tap {
 extern int netlink_add_tap(struct netlink_tap *nt);
 extern int netlink_remove_tap(struct netlink_tap *nt);
 
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			  struct user_namespace *ns, int cap);
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *ns, int cap);
+bool netlink_capable(const struct sk_buff *skb, int cap);
+bool netlink_net_capable(const struct sk_buff *skb, int cap);
+
 #endif	/* __LINUX_NETLINK_H */

71 lines not on this page · raw message

@@ -466,7 +466,7 @@ static int crypto_user_rcv_msg(struct sk
 	type -= CRYPTO_MSG_BASE;
 	link = &crypto_dispatch[type];
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) &&

@@ -369,7 +369,7 @@ static void cn_proc_mcast_ctl(struct cn_
 		return;
 
 	/* Can only change if privileged. */
-	if (!capable(CAP_NET_ADMIN)) {
+	if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) {
 		err = EPERM;
 		goto out;
 	}

@@ -77,7 +77,7 @@ scsi_nl_rcv_msg(struct sk_buff *skb)
 			goto next_msg;
 		}
 
-		if (!capable(CAP_SYS_ADMIN)) {
+		if (!netlink_capable(skb, CAP_SYS_ADMIN)) {
 			err = -EPERM;
 			goto next_msg;
 		}

@@ -639,13 +639,13 @@ static int audit_netlink_ok(struct sk_bu
 	case AUDIT_TTY_SET:
 	case AUDIT_TRIM:
 	case AUDIT_MAKE_EQUIV:
-		if (!capable(CAP_AUDIT_CONTROL))
+		if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
 			err = -EPERM;
 		break;
 	case AUDIT_USER:
 	case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
-		if (!capable(CAP_AUDIT_WRITE))
+		if (!netlink_capable(skb, CAP_AUDIT_WRITE))
 			err = -EPERM;
 		break;
 	default:  /* bad msg */

@@ -804,7 +804,7 @@ static int cgw_create_job(struct sk_buff
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))

@@ -893,7 +893,7 @@ static int cgw_remove_job(struct sk_buff
 	u8 limhops = 0;
 	int err = 0;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (nlmsg_len(nlh) < sizeof(*r))

@@ -1428,7 +1428,8 @@ static int do_set_master(struct net_devi
 	return 0;
 }
 
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+		      struct net_device *dev, struct ifinfomsg *ifm,
 		      struct nlattr **tb, char *ifname, int modified)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;

@@ -1440,7 +1441,7 @@ static int do_setlink(struct net_device
 			err = PTR_ERR(net);
 			goto errout;
 		}
-		if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+		if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
 			err = -EPERM;
 			goto errout;
 		}

@@ -1694,7 +1695,7 @@ static int rtnl_setlink(struct sk_buff *
 	if (err < 0)
 		goto errout;
 
-	err = do_setlink(dev, ifm, tb, ifname, 0);
+	err = do_setlink(skb, dev, ifm, tb, ifname, 0);
 errout:
 	return err;
 }

@@ -1811,7 +1812,8 @@ err:
 }
 EXPORT_SYMBOL(rtnl_create_link);
 
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+		struct net *net, int group,
 		struct ifinfomsg *ifm,
 		struct nlattr **tb)
 {

@@ -1820,7 +1822,7 @@ static int rtnl_group_changelink(struct
 
 	for_each_netdev(net, dev) {
 		if (dev->group == group) {
-			err = do_setlink(dev, ifm, tb, NULL, 0);
+			err = do_setlink(skb, dev, ifm, tb, NULL, 0);
 			if (err < 0)
 				return err;
 		}

@@ -1962,12 +1964,12 @@ replay:
 				modified = 1;
 			}
 
-			return do_setlink(dev, ifm, tb, ifname, modified);
+			return do_setlink(skb, dev, ifm, tb, ifname, modified);
 		}
 
 		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
 			if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
-				return rtnl_group_changelink(net,
+				return rtnl_group_changelink(skb, net,
 						nla_get_u32(tb[IFLA_GROUP]),
 						ifm, tb);
 			return -ENODEV;

@@ -2354,7 +2356,7 @@ static int rtnl_fdb_del(struct sk_buff *
 	int err = -EINVAL;
 	__u8 *addr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);

@@ -2806,7 +2808,7 @@ static int rtnetlink_rcv_msg(struct sk_b
 	sz_idx = type>>2;
 	kind = type&3;
 
-	if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {

@@ -1669,7 +1669,7 @@ static int dcb_doit(struct sk_buff *skb,
 	struct nlmsghdr *reply_nlh = NULL;
 	const struct reply_func *fn;
 
-	if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+	if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,

@@ -574,7 +574,7 @@ static int dn_nl_deladdr(struct sk_buff
 	struct dn_ifaddr __rcu **ifap;
 	int err = -EINVAL;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))

@@ -618,7 +618,7 @@ static int dn_nl_newaddr(struct sk_buff
 	struct dn_ifaddr *ifa;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))

@@ -505,7 +505,7 @@ static int dn_fib_rtm_delroute(struct sk
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))

@@ -530,7 +530,7 @@ static int dn_fib_rtm_newroute(struct sk
 	struct nlattr *attrs[RTA_MAX+1];
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if (!net_eq(net, &init_net))

@@ -107,7 +107,7 @@ static inline void dnrmg_receive_user_sk
 	if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		RCV_SKB_FAIL(-EPERM);
 
 	/* Eventually we might send routing messages too */

@@ -367,7 +367,7 @@ static void nfnetlink_rcv(struct sk_buff
 	    skb->len < nlh->nlmsg_len)
 		return;
 
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN)) {
 		netlink_ack(skb, nlh, -EPERM);
 		return;
 	}

@@ -561,7 +561,7 @@ static int genl_family_rcv_msg(struct ge
 		return -EOPNOTSUPP;
 
 	if ((ops->flags & GENL_ADMIN_PERM) &&
-	    !capable(CAP_NET_ADMIN))
+	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {

@@ -194,7 +194,7 @@ static int packet_diag_dump(struct sk_bu
 
 	net = sock_net(skb->sk);
 	req = nlmsg_data(cb->nlh);
-	may_report_filterinfo = ns_capable(net->user_ns, CAP_NET_ADMIN);
+	may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
 
 	mutex_lock(&net->packet.sklist_lock);
 	sk_for_each(sk, &net->packet.sklist) {

@@ -70,10 +70,10 @@ static int addr_doit(struct sk_buff *skb
 	int err;
 	u8 pnaddr;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();

@@ -233,10 +233,10 @@ static int route_doit(struct sk_buff *sk
 	int err;
 	u8 dst;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	ASSERT_RTNL();

@@ -908,7 +908,7 @@ static int tc_ctl_action(struct sk_buff
 	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
-	if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);

@@ -134,7 +134,7 @@ static int tc_ctl_tfilter(struct sk_buff
 	int err;
 	int tp_created = 0;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:

@@ -1084,7 +1084,7 @@ static int tc_get_qdisc(struct sk_buff *
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);

@@ -1151,7 +1151,7 @@ static int tc_modify_qdisc(struct sk_buf
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!capable(CAP_NET_ADMIN))
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:

@@ -1491,7 +1491,7 @@ static int tc_ctl_tclass(struct sk_buff
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);

@@ -47,7 +47,7 @@ static int handle_cmd(struct sk_buff *sk
 	int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
 	u16 cmd;
 
-	if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+	if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
 		cmd = TIPC_CMD_NOT_NET_ADMIN;
 	else
 		cmd = req_userhdr->cmd;

@@ -2350,7 +2350,7 @@ static int xfrm_user_rcv_msg(struct sk_b
 	link = &xfrm_dispatch[type];
 
 	/* All operations require privileges, even GET */
-	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||

@@ -16,9 +16,10 @@ static inline struct nlmsghdr *nlmsg_hdr
 }
 
 enum netlink_skb_flags {
-	NETLINK_SKB_MMAPED	= 0x1,		/* Packet data is mmaped */
-	NETLINK_SKB_TX		= 0x2,		/* Packet was sent by userspace */
-	NETLINK_SKB_DELIVERED	= 0x4,		/* Packet was delivered */
+	NETLINK_SKB_MMAPED	= 0x1,	/* Packet data is mmaped */
+	NETLINK_SKB_TX		= 0x2,	/* Packet was sent by userspace */
+	NETLINK_SKB_DELIVERED	= 0x4,	/* Packet was delivered */
+	NETLINK_SKB_DST		= 0x8,	/* Dst set in sendto or sendmsg */
 };
 
 struct netlink_skb_parms {

@@ -1373,7 +1373,9 @@ retry:
 bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
 			struct user_namespace *user_ns, int cap)
 {
-	return sk_ns_capable(nsp->sk, user_ns, cap);
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
 }
 EXPORT_SYMBOL(__netlink_ns_capable);
 

@@ -2293,6 +2295,7 @@ static int netlink_sendmsg(struct kiocb
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;

@@ -2314,6 +2317,7 @@ static int netlink_sendmsg(struct kiocb
 		if ((dst_group || dst_portid) &&
 		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;

@@ -2343,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {

@@ -1022,6 +1022,7 @@ static int qlcnic_dcb_peer_app_info(stru
 	struct qlcnic_dcb_cee *peer;
 	int i;
 
+	memset(info, 0, sizeof(*info));
 	*app_count = 0;
 
 	if (!test_bit(QLCNIC_DCB_STATE, &adapter->dcb->state))

@@ -716,15 +716,15 @@ static struct sock *udp_v6_mcast_next(st
 				if (inet->inet_dport != rmt_port)
 					continue;
 			}
-			if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
-			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
+			if (!ipv6_addr_any(&s->sk_v6_daddr) &&
+			    !ipv6_addr_equal(&s->sk_v6_daddr, rmt_addr))
 				continue;
 
 			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
 				continue;
 
-			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
+			if (!ipv6_addr_any(&s->sk_v6_rcv_saddr)) {
+				if (!ipv6_addr_equal(&s->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
 			if (!inet6_mc_check(s, loc_addr, rmt_addr))

@@ -201,8 +201,8 @@ int nla_parse(struct nlattr **tb, int ma
 	}
 
 	if (unlikely(rem > 0))
-		printk(KERN_WARNING "netlink: %d bytes leftover after parsing "
-		       "attributes.\n", rem);
+		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+				    rem, current->comm);
 
 	err = 0;
 errout:

@@ -147,8 +147,8 @@ static int br_handle_local_finish(struct
 	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	u16 vid = 0;
 
-	br_vlan_get_tag(skb, &vid);
-	if (p->flags & BR_LEARNING)
+	/* check if vlan is allowed, to avoid spoofing */
+	if (p->flags & BR_LEARNING && br_should_learn(p, skb, &vid))
 		br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false);
 	return 0;	 /* process further */
 }

@@ -581,6 +581,7 @@ bool br_allowed_ingress(struct net_bridg
 			struct sk_buff *skb, u16 *vid);
 bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v,
 		       const struct sk_buff *skb);
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid);
 struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       const struct net_port_vlans *v,
 			       struct sk_buff *skb);

@@ -647,6 +648,12 @@ static inline bool br_allowed_egress(str
 {
 	return true;
 }
+
+static inline bool br_should_learn(struct net_bridge_port *p,
+				   struct sk_buff *skb, u16 *vid)
+{
+	return true;
+}
 
 static inline struct sk_buff *br_handle_vlan(struct net_bridge *br,
 					     const struct net_port_vlans *v,

@@ -241,6 +241,34 @@ bool br_allowed_egress(struct net_bridge
 	return false;
 }
 
+/* Called under RCU */
+bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
+{
+	struct net_bridge *br = p->br;
+	struct net_port_vlans *v;
+
+	if (!br->vlan_enabled)
+		return true;
+
+	v = rcu_dereference(p->vlan_info);
+	if (!v)
+		return false;
+
+	br_vlan_get_tag(skb, vid);
+	if (!*vid) {
+		*vid = br_get_pvid(v);
+		if (*vid == VLAN_N_VID)
+			return false;
+
+		return true;
+	}
+
+	if (test_bit(*vid, v->vlan_bitmap))
+		return true;
+
+	return false;
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */

@@ -486,4 +486,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");

@@ -61,6 +61,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG

@@ -1850,4 +1850,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");

@@ -177,16 +177,9 @@ static inline void inet_peer_refcheck(co
 /* can be called with or without local BH being disabled */
 static inline int inet_getid(struct inet_peer *p, int more)
 {
-	int old, new;
 	more++;
 	inet_peer_refcheck(p);
-	do {
-		old = atomic_read(&p->ip_id_count);
-		new = old + more;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&p->ip_id_count, old, new) != old);
-	return new;
+	return atomic_add_return(more, &p->ip_id_count) - more;
 }
 
 #endif /* _NET_INETPEER_H */

@@ -10,7 +10,7 @@
 void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
 {
 	static atomic_t ipv6_fragmentation_id;
-	int old, new;
+	int ident;
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (rt && !(rt->dst.flags & DST_NOPEER)) {

@@ -26,13 +26,8 @@ void ipv6_select_ident(struct frag_hdr *
 		}
 	}
 #endif
-	do {
-		old = atomic_read(&ipv6_fragmentation_id);
-		new = old + 1;
-		if (!new)
-			new = 1;
-	} while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
-	fhdr->identification = htonl(new);
+	ident = atomic_inc_return(&ipv6_fragmentation_id);
+	fhdr->identification = htonl(ident);
 }
 EXPORT_SYMBOL(ipv6_select_ident);
 

@@ -1732,6 +1732,7 @@ static int team_change_mtu(struct net_de
 	 * to traverse list in reverse under rcu_read_lock
 	 */
 	mutex_lock(&team->lock);
+	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
 		if (err) {

@@ -1740,6 +1741,7 @@ static int team_change_mtu(struct net_de
 			goto unwind;
 		}
 	}
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	dev->mtu = new_mtu;

@@ -1749,6 +1751,7 @@ static int team_change_mtu(struct net_de
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
+	team->port_mtu_change_allowed = false;
 	mutex_unlock(&team->lock);
 
 	return err;

@@ -2857,7 +2860,9 @@ static int team_device_event(struct noti
 		break;
 	case NETDEV_PRECHANGEMTU:
 		/* Forbid to change mtu of underlaying device */
-		return NOTIFY_BAD;
+		if (!port->team->port_mtu_change_allowed)
+			return NOTIFY_BAD;
+		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid to change type of underlaying device */
 		return NOTIFY_BAD;

@@ -194,6 +194,7 @@ struct team {
 	bool user_carrier_enabled;
 	bool queue_override_enabled;
 	struct list_head *qom_lists; /* array of queue override mapping lists */
+	bool port_mtu_change_allowed;
 	struct {
 		unsigned int count;
 		unsigned int interval; /* in ms */

@@ -2683,13 +2683,12 @@ static void tcp_process_loss(struct sock
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
 	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
-		if (flag & FLAG_ORIG_SACK_ACKED) {
-			/* Step 3.b. A timeout is spurious if not all data are
-			 * lost, i.e., never-retransmitted data are (s)acked.
-			 */
-			tcp_try_undo_loss(sk, true);
+		/* Step 3.b. A timeout is spurious if not all data are
+		 * lost, i.e., never-retransmitted data are (s)acked.
+		 */
+		if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
 			return;
-		}
+
 		if (after(tp->snd_nxt, tp->high_seq) &&
 		    (flag & FLAG_DATA_SACKED || is_dupack)) {
 			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */

@@ -539,7 +539,6 @@ static struct sh_eth_cpu_data sh7757_dat
 	.register_type	= SH_ETH_REG_FAST_SH4,
 
 	.eesipr_value	= DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
-	.rmcr_value	= RMCR_RNC,
 
 	.tx_check	= EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |

@@ -617,7 +616,6 @@ static struct sh_eth_cpu_data sh7757_dat
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000072f,
-	.rmcr_value	= RMCR_RNC,
 
 	.irq_flags	= IRQF_SHARED,
 	.apr		= 1,

@@ -745,7 +743,6 @@ static struct sh_eth_cpu_data r8a7740_da
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.apr		= 1,
 	.mpr		= 1,

@@ -777,7 +774,6 @@ static struct sh_eth_cpu_data r7s72100_d
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.no_psr		= 1,
 	.apr		= 1,

@@ -826,9 +822,6 @@ static void sh_eth_set_default_cpu_data(
 	if (!cd->fdr_value)
 		cd->fdr_value = DEFAULT_FDR_INIT;
 
-	if (!cd->rmcr_value)
-		cd->rmcr_value = DEFAULT_RMCR_VALUE;
-
 	if (!cd->tx_check)
 		cd->tx_check = DEFAULT_TX_CHECK;
 

@@ -1281,8 +1274,8 @@ static int sh_eth_dev_init(struct net_de
 	sh_eth_write(ndev, mdp->cd->fdr_value, FDR);
 	sh_eth_write(ndev, 0, TFTR);
 
-	/* Frame recv control */
-	sh_eth_write(ndev, mdp->cd->rmcr_value, RMCR);
+	/* Frame recv control (enable multiple-packets per rx irq) */
+	sh_eth_write(ndev, RMCR_RNC, RMCR);
 
 	sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);
 

@@ -320,7 +320,6 @@ enum TD_STS_BIT {
 enum RMCR_BIT {
 	RMCR_RNC = 0x00000001,
 };
-#define DEFAULT_RMCR_VALUE	0x00000000
 
 /* ECMR */
 enum FELIC_MODE_BIT {

@@ -467,7 +466,6 @@ struct sh_eth_cpu_data {
 	unsigned long fdr_value;
 	unsigned long fcftr_value;
 	unsigned long rpadir_value;
-	unsigned long rmcr_value;
 
 	/* interrupt checking mask */
 	unsigned long tx_check;

@@ -301,6 +301,27 @@ static const u16 sh_eth_offset_fast_sh4[
 };
 
 static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = {
+	[EDMR]		= 0x0000,
+	[EDTRR]		= 0x0004,
+	[EDRRR]		= 0x0008,
+	[TDLAR]		= 0x000c,
+	[RDLAR]		= 0x0010,
+	[EESR]		= 0x0014,
+	[EESIPR]	= 0x0018,
+	[TRSCER]	= 0x001c,
+	[RMFCR]		= 0x0020,
+	[TFTR]		= 0x0024,
+	[FDR]		= 0x0028,
+	[RMCR]		= 0x002c,
+	[EDOCR]		= 0x0030,
+	[FCFTR]		= 0x0034,
+	[RPADIR]	= 0x0038,
+	[TRIMD]		= 0x003c,
+	[RBWAR]		= 0x0040,
+	[RDFAR]		= 0x0044,
+	[TBRAR]		= 0x004c,
+	[TDFAR]		= 0x0050,
+
 	[ECMR]		= 0x0160,
 	[ECSR]		= 0x0164,
 	[ECSIPR]	= 0x0168,

@@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start
 #define BNE		(F2(0, 2) | CONDNE)
 
 #ifdef CONFIG_SPARC64
-#define BNE_PTR		(F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BNE_PTR		BNE
+#define BE_PTR		BNE
 #endif
 
 #define SETHI(K, REG)	\

@@ -600,7 +600,7 @@ void bpf_jit_compile(struct sk_filter *f
 			case BPF_S_ANC_IFINDEX:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load32(r_A, struct net_device, ifindex, r_A);
 				break;

@@ -613,7 +613,7 @@ void bpf_jit_compile(struct sk_filter *f
 			case BPF_S_ANC_HATYPE:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;

@@ -85,7 +85,7 @@ static void bpf_flush_icache(void *start
 #ifdef CONFIG_SPARC64
 #define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BE_PTR		BNE
+#define BE_PTR		BE
 #endif
 
 #define SETHI(K, REG)	\

@@ -1043,7 +1043,6 @@ static int macvlan_device_event(struct n
 		list_for_each_entry_safe(vlan, next, &port->vlans, list)
 			vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
 		unregister_netdevice_many(&list_kill);
-		list_del(&list_kill);
 		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlaying device to change its type. */

@@ -6548,6 +6548,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {

@@ -6557,6 +6560,7 @@ void unregister_netdevice_many(struct li
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);

@@ -7012,7 +7016,6 @@ static void __net_exit default_device_ex
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }
 

@@ -1735,7 +1735,6 @@ static int rtnl_dellink(struct sk_buff *
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 

@@ -1761,7 +1761,6 @@ void ieee80211_remove_interfaces(struct
 	}
 	mutex_unlock(&local->iflist_mtx);
 	unregister_netdevice_many(&unreg_list);
-	list_del(&unreg_list);
 
 	list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
 		list_del(&sdata->list);

@@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb,
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;

@@ -560,12 +560,12 @@ static int ipip6_err(struct sk_buff *skb
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;

@@ -66,10 +66,17 @@
 #define EFX_USE_QWORD_IO 1
 #endif
 
+/* Hardware issue requires that only 64-bit naturally aligned writes
+ * are seen by hardware. Its not strictly necessary to restrict to
+ * x86_64 arch, but done for safety since unusual write combining behaviour
+ * can break PIO.
+ */
+#ifdef CONFIG_X86_64
 /* PIO is a win only if write-combining is possible */
 #ifdef ARCH_HAS_IOREMAP_WC
 #define EFX_USE_PIO 1
 #endif
+#endif
 
 #ifdef EFX_USE_QWORD_IO
 static inline void _efx_writeq(struct efx_nic *efx, __le64 value,

@@ -189,6 +189,18 @@ struct efx_short_copy_buffer {
 	u8 buf[L1_CACHE_BYTES];
 };
 
+/* Copy in explicit 64-bit writes. */
+static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
+{
+	u64 *src64 = src;
+	u64 __iomem *dest64 = dest;
+	size_t l64 = len / 8;
+	size_t i;
+
+	for (i = 0; i < l64; i++)
+		writeq(src64[i], &dest64[i]);
+}
+
 /* Copy to PIO, respecting that writes to PIO buffers must be dword aligned.
  * Advances piobuf pointer. Leaves additional data in the copy buffer.
  */

@@ -198,7 +210,7 @@ static void efx_memcpy_toio_aligned(stru
 {
 	int block_len = len & ~(sizeof(copy_buf->buf) - 1);
 
-	memcpy_toio(*piobuf, data, block_len);
+	efx_memcpy_64(*piobuf, data, block_len);
 	*piobuf += block_len;
 	len -= block_len;
 

@@ -230,7 +242,7 @@ static void efx_memcpy_toio_aligned_cb(s
 		if (copy_buf->used < sizeof(copy_buf->buf))
 			return;
 
-		memcpy_toio(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 		*piobuf += sizeof(copy_buf->buf);
 		data += copy_to_buf;
 		len -= copy_to_buf;

@@ -245,7 +257,7 @@ static void efx_flush_copy_buffer(struct
 {
 	/* if there's anything in it, write the whole buffer, including junk */
 	if (copy_buf->used)
-		memcpy_toio(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 }
 
 /* Traverse skb structure and copy fragments in to PIO buffer.

@@ -304,8 +316,8 @@ efx_enqueue_skb_pio(struct efx_tx_queue
 		 */
 		BUILD_BUG_ON(L1_CACHE_BYTES >
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
-		memcpy_toio(tx_queue->piobuf, skb->data,
-			    ALIGN(skb->len, L1_CACHE_BYTES));
+		efx_memcpy_64(tx_queue->piobuf, skb->data,
+			      ALIGN(skb->len, L1_CACHE_BYTES));
 	}
 
 	EFX_POPULATE_QWORD_5(buffer->option,

@@ -86,18 +86,26 @@ out:
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
 
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
 void ip4_datagram_release_cb(struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
 	__be32 daddr = inet->inet_daddr;
+	struct dst_entry *dst;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
-		return;
-
 	rcu_read_lock();
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+		rcu_read_unlock();
+		return;
+	}
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;

@@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
 				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
-	if (!IS_ERR(rt))
-		__sk_dst_set(sk, &rt->dst);
+
+	dst = !IS_ERR(rt) ? &rt->dst : NULL;
+	sk_dst_set(sk, dst);
+
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);

@@ -330,7 +330,7 @@ void sctp_association_free(struct sctp_a
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening

@@ -1166,6 +1166,7 @@ static int rtnl_dump_ifinfo(struct sk_bu
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];

@@ -1173,8 +1174,17 @@ static int rtnl_dump_ifinfo(struct sk_bu
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);

@@ -2085,9 +2095,13 @@ static u16 rtnl_calcit(struct sk_buff *s
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}

@@ -2282,9 +2282,9 @@ static void vxlan_setup(struct net_devic
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
 	else
-		dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;

@@ -2667,8 +2667,7 @@ static int vxlan_newlink(struct net *net
 		if (!tb[IFLA_MTU])
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;

@@ -1833,6 +1833,10 @@ static struct sock *__udp4_lib_mcast_dem
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;

@@ -2275,13 +2275,8 @@ static int __mlx4_init_one(struct pci_de
 	/* Allow large DMA segments, up to the firmware limit of 1 GB */
 	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
-
-	dev       = &priv->dev;
+	dev       = pci_get_drvdata(pdev);
+	priv      = mlx4_priv(dev);
 	dev->pdev = pdev;
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);

@@ -2465,8 +2460,7 @@ slave_start:
 	mlx4_sense_init(dev);
 	mlx4_start_sense(dev);
 
-	priv->pci_dev_data = pci_dev_data;
-	pci_set_drvdata(pdev, dev);
+	priv->removed = 0;
 
 	return 0;
 

@@ -2532,84 +2526,108 @@ err_disable_pdev:
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct mlx4_priv *priv;
+	struct mlx4_dev *dev;
+
 	printk_once(KERN_INFO "%s", mlx4_version);
 
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev       = &priv->dev;
+	pci_set_drvdata(pdev, dev);
+	priv->pci_dev_data = id->driver_data;
+
 	return __mlx4_init_one(pdev, id->driver_data);
 }
 
-static void mlx4_remove_one(struct pci_dev *pdev)
+static void __mlx4_remove_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               pci_dev_data;
 	int p;
 
-	if (dev) {
-		/* in SRIOV it is not allowed to unload the pf's
-		 * driver while there are alive vf's */
-		if (mlx4_is_master(dev)) {
-			if (mlx4_how_many_lives_vf(dev))
-				printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
-		}
-		mlx4_stop_sense(dev);
-		mlx4_unregister_device(dev);
+	if (priv->removed)
+		return;
 
-		for (p = 1; p <= dev->caps.num_ports; p++) {
-			mlx4_cleanup_port_info(&priv->port[p]);
-			mlx4_CLOSE_PORT(dev, p);
-		}
+	pci_dev_data = priv->pci_dev_data;
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_SLAVES_ONLY);
+	/* in SRIOV it is not allowed to unload the pf's
+	 * driver while there are alive vf's */
+	if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev))
+		printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+	mlx4_stop_sense(dev);
+	mlx4_unregister_device(dev);
+
+	for (p = 1; p <= dev->caps.num_ports; p++) {
+		mlx4_cleanup_port_info(&priv->port[p]);
+		mlx4_CLOSE_PORT(dev, p);
+	}
 
-		mlx4_cleanup_counters_table(dev);
-		mlx4_cleanup_qp_table(dev);
-		mlx4_cleanup_srq_table(dev);
-		mlx4_cleanup_cq_table(dev);
-		mlx4_cmd_use_polling(dev);
-		mlx4_cleanup_eq_table(dev);
-		mlx4_cleanup_mcg_table(dev);
-		mlx4_cleanup_mr_table(dev);
-		mlx4_cleanup_xrcd_table(dev);
-		mlx4_cleanup_pd_table(dev);
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_SLAVES_ONLY);
 
-		if (mlx4_is_master(dev))
-			mlx4_free_resource_tracker(dev,
-						   RES_TR_FREE_STRUCTS_ONLY);
+	mlx4_cleanup_counters_table(dev);
+	mlx4_cleanup_qp_table(dev);
+	mlx4_cleanup_srq_table(dev);
+	mlx4_cleanup_cq_table(dev);
+	mlx4_cmd_use_polling(dev);
+	mlx4_cleanup_eq_table(dev);
+	mlx4_cleanup_mcg_table(dev);
+	mlx4_cleanup_mr_table(dev);
+	mlx4_cleanup_xrcd_table(dev);
+	mlx4_cleanup_pd_table(dev);
 
-		iounmap(priv->kar);
-		mlx4_uar_free(dev, &priv->driver_uar);
-		mlx4_cleanup_uar_table(dev);
-		if (!mlx4_is_slave(dev))
-			mlx4_clear_steering(dev);
-		mlx4_free_eq_table(dev);
-		if (mlx4_is_master(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_close_hca(dev);
-		if (mlx4_is_slave(dev))
-			mlx4_multi_func_cleanup(dev);
-		mlx4_cmd_cleanup(dev);
-
-		if (dev->flags & MLX4_FLAG_MSI_X)
-			pci_disable_msix(pdev);
-		if (dev->flags & MLX4_FLAG_SRIOV) {
-			mlx4_warn(dev, "Disabling SR-IOV\n");
-			pci_disable_sriov(pdev);
-		}
+	if (mlx4_is_master(dev))
+		mlx4_free_resource_tracker(dev,
+					   RES_TR_FREE_STRUCTS_ONLY);
 
-		if (!mlx4_is_slave(dev))
-			mlx4_free_ownership(dev);
+	iounmap(priv->kar);
+	mlx4_uar_free(dev, &priv->driver_uar);
+	mlx4_cleanup_uar_table(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_clear_steering(dev);
+	mlx4_free_eq_table(dev);
+	if (mlx4_is_master(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_close_hca(dev);
+	if (mlx4_is_slave(dev))
+		mlx4_multi_func_cleanup(dev);
+	mlx4_cmd_cleanup(dev);
 
-		kfree(dev->caps.qp0_tunnel);
-		kfree(dev->caps.qp0_proxy);
-		kfree(dev->caps.qp1_tunnel);
-		kfree(dev->caps.qp1_proxy);
-
-		kfree(priv);
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		pci_set_drvdata(pdev, NULL);
+	if (dev->flags & MLX4_FLAG_MSI_X)
+		pci_disable_msix(pdev);
+	if (dev->flags & MLX4_FLAG_SRIOV) {
+		mlx4_warn(dev, "Disabling SR-IOV\n");
+		pci_disable_sriov(pdev);
 	}
+
+	if (!mlx4_is_slave(dev))
+		mlx4_free_ownership(dev);
+
+	kfree(dev->caps.qp0_tunnel);
+	kfree(dev->caps.qp0_proxy);
+	kfree(dev->caps.qp1_tunnel);
+	kfree(dev->caps.qp1_proxy);
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	memset(priv, 0, sizeof(*priv));
+	priv->pci_dev_data = pci_dev_data;
+	priv->removed = 1;
+}
+
+static void mlx4_remove_one(struct pci_dev *pdev)
+{
+	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	__mlx4_remove_one(pdev);
+	kfree(priv);
+	pci_set_drvdata(pdev, NULL);
 }
 
 int mlx4_restart_one(struct pci_dev *pdev)

@@ -2619,7 +2637,7 @@ int mlx4_restart_one(struct pci_dev *pde
 	int		  pci_dev_data;
 
 	pci_dev_data = priv->pci_dev_data;
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 	return __mlx4_init_one(pdev, pci_dev_data);
 }
 

@@ -2674,7 +2692,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table)
 static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;

@@ -2682,11 +2700,11 @@ static pci_ers_result_t mlx4_pci_err_det
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	const struct pci_device_id *id;
-	int ret;
+	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               ret;
 
-	id = pci_match_id(mlx4_pci_table, pdev);
-	ret = __mlx4_init_one(pdev, id->driver_data);
+	ret = __mlx4_init_one(pdev, priv->pci_dev_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }

@@ -796,6 +796,7 @@ struct mlx4_priv {
 	spinlock_t		ctx_lock;
 
 	int			pci_dev_data;
+	int                     removed;
 
 	struct list_head        pgdir_list;
 	struct mutex            pgdir_mutex;

@@ -2718,7 +2718,7 @@ static struct pci_driver mlx4_driver = {
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
-	.shutdown	= mlx4_remove_one,
+	.shutdown	= __mlx4_remove_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };

@@ -360,6 +360,8 @@ static inline void apic_clear_irr(int ve
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
 		++apic->isr_count;
 	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);

@@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec,
 	apic->highest_isr_cache = vec;
 }
 
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+	int result;
+
+	/*
+	 * Note that isr_count is always 1, and highest_isr_cache
+	 * is always -1, with APIC virtualization enabled.
+	 */
+	if (!apic->isr_count)
+		return -1;
+	if (likely(apic->highest_isr_cache != -1))
+		return apic->highest_isr_cache;
+
+	result = find_highest_vector(apic->regs + APIC_ISR);
+	ASSERT(result == -1 || result >= 16);
+
+	return result;
+}
+
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+	struct kvm_vcpu *vcpu;
+	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
+
+	/*
+	 * We do get here for APIC virtualization enabled if the guest
+	 * uses the Hyper-V APIC enlightenment.  In this case we may need
+	 * to trigger a new interrupt delivery by writing the SVI field;
+	 * on the other hand isr_count and highest_isr_cache are unused
+	 * and must be left alone.
+	 */
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+					       apic_find_highest_isr(apic));
+	else {
 		--apic->isr_count;
-	BUG_ON(apic->isr_count < 0);
-	apic->highest_isr_cache = -1;
+		BUG_ON(apic->isr_count < 0);
+		apic->highest_isr_cache = -1;
+	}
 }
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)

@@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kv
 	__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
 }
 
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
-	int result;
-
-	/* Note that isr_count is always 1 with vid enabled */
-	if (!apic->isr_count)
-		return -1;
-	if (likely(apic->highest_isr_cache != -1))
-		return apic->highest_isr_cache;
-
-	result = find_highest_vector(apic->regs + APIC_ISR);
-	ASSERT(result == -1 || result >= 16);
-
-	return result;
-}
-
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;

@@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vc
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	/* Note that we never get here with APIC virtualization enabled.  */
+
 	if (vector == -1)
 		return -1;
 

@@ -25,24 +25,28 @@
 
 #include "generic.h"
 
-#define AT91_RTC_IDR	0x24	/* Interrupt Disable Register */
-#define AT91_RTC_IMR	0x28	/* Interrupt Mask Register */
+#define AT91_RTC_IDR		0x24	/* Interrupt Disable Register */
+#define AT91_RTC_IMR		0x28	/* Interrupt Mask Register */
+#define AT91_RTC_IRQ_MASK	0x1f	/* Available IRQs mask */
 
 void __init at91_sysirq_mask_rtc(u32 rtc_base)
 {
 	void __iomem *base;
-	u32 mask;
 
 	base = ioremap(rtc_base, 64);
 	if (!base)
 		return;
 
-	mask = readl_relaxed(base + AT91_RTC_IMR);
-	if (mask) {
-		pr_info("AT91: Disabling rtc irq\n");
-		writel_relaxed(mask, base + AT91_RTC_IDR);
-		(void)readl_relaxed(base + AT91_RTC_IMR);	/* flush */
-	}
+	/*
+	 * sam9x5 SoCs have the following errata:
+	 * "RTC: Interrupt Mask Register cannot be used
+	 *  Interrupt Mask Register read always returns 0."
+	 *
+	 * Hence we're not relying on IMR values to disable
+	 * interrupts.
+	 */
+	writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR);
+	(void)readl_relaxed(base + AT91_RTC_IMR);	/* flush */
 
 	iounmap(base);
 }

@@ -304,7 +304,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(st
 	if (cpu_has_veic || cpu_has_vint) {
 		size = 0x200 + VECTORSPACING * 64;
 	} else {
-		size = 0x200;
+		size = 0x4000;
 	}
 
 	/* Save Linux EBASE */

@@ -1512,18 +1512,15 @@ static int acm_suspend(struct usb_interf
 	struct acm *acm = usb_get_intfdata(intf);
 	int cnt;
 
+	spin_lock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 	if (PMSG_IS_AUTO(message)) {
-		int b;
-
-		spin_lock_irq(&acm->write_lock);
-		b = acm->transmitting;
-		spin_unlock_irq(&acm->write_lock);
-		if (b)
+		if (acm->transmitting) {
+			spin_unlock(&acm->write_lock);
+			spin_unlock_irq(&acm->read_lock);
 			return -EBUSY;
+		}
 	}
-
-	spin_lock_irq(&acm->read_lock);
-	spin_lock(&acm->write_lock);
 	cnt = acm->susp_count++;
 	spin_unlock(&acm->write_lock);
 	spin_unlock_irq(&acm->read_lock);

@@ -1539,27 +1539,20 @@ static int acm_resume(struct usb_interfa
 	struct acm *acm = usb_get_intfdata(intf);
 	struct acm_wb *wb;
 	int rv = 0;
-	int cnt;
 
 	spin_lock_irq(&acm->read_lock);
-	acm->susp_count -= 1;
-	cnt = acm->susp_count;
-	spin_unlock_irq(&acm->read_lock);
+	spin_lock(&acm->write_lock);
 
-	if (cnt)
-		return 0;
+	if (--acm->susp_count)
+		goto out;
 
 	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) {
-		rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
+		rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
 
-		spin_lock_irq(&acm->write_lock);
 		if (acm->delayed_wb) {
 			wb = acm->delayed_wb;
 			acm->delayed_wb = NULL;
-			spin_unlock_irq(&acm->write_lock);
 			acm_start_wb(acm, wb);
-		} else {
-			spin_unlock_irq(&acm->write_lock);
 		}
 
 		/*

@@ -1567,12 +1560,14 @@ static int acm_resume(struct usb_interfa
 		 * do the write path at all cost
 		 */
 		if (rv < 0)
-			goto err_out;
+			goto out;
 
-		rv = acm_submit_read_urbs(acm, GFP_NOIO);
+		rv = acm_submit_read_urbs(acm, GFP_ATOMIC);
 	}
+out:
+	spin_unlock(&acm->write_lock);
+	spin_unlock_irq(&acm->read_lock);
 
-err_out:
 	return rv;
 }
 

@@ -571,6 +571,8 @@ static void acm_port_destruct(struct tty
 static void acm_port_shutdown(struct tty_port *port)
 {
 	struct acm *acm = container_of(port, struct acm, port);
+	struct urb *urb;
+	struct acm_wb *wb;
 	int i;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);

@@ -579,6 +581,16 @@ static void acm_port_shutdown(struct tty
 	if (!acm->disconnected) {
 		usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
+
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+			wb = urb->context;
+			wb->use = 0;
+			usb_autopm_put_interface_async(acm->control);
+		}
+
 		usb_kill_urb(acm->ctrlurb);
 		for (i = 0; i < ACM_NW; i++)
 			usb_kill_urb(acm->wb[i].urb);

@@ -646,12 +658,9 @@ static int acm_tty_write(struct tty_stru
 
 	usb_autopm_get_interface_async(acm->control);
 	if (acm->susp_count) {
-		if (!acm->delayed_wb)
-			acm->delayed_wb = wb;
-		else
-			usb_autopm_put_interface_async(acm->control);
+		usb_anchor_urb(wb->urb, &acm->delayed);
 		spin_unlock_irqrestore(&acm->write_lock, flags);
-		return count;	/* A white lie */
+		return count;
 	}
 	usb_mark_last_busy(acm->dev);
 

@@ -1267,6 +1276,7 @@ made_compressed_probe:
 		acm->bInterval = epread->bInterval;
 	tty_port_init(&acm->port);
 	acm->port.ops = &acm_port_ops;
+	init_usb_anchor(&acm->delayed);
 
 	buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
 	if (!buf) {

@@ -1537,7 +1547,7 @@ static int acm_suspend(struct usb_interf
 static int acm_resume(struct usb_interface *intf)
 {
 	struct acm *acm = usb_get_intfdata(intf);
-	struct acm_wb *wb;
+	struct urb *urb;
 	int rv = 0;
 
 	spin_lock_irq(&acm->read_lock);

@@ -1549,10 +1559,12 @@ static int acm_resume(struct usb_interfa
 	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) {
 		rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
 
-		if (acm->delayed_wb) {
-			wb = acm->delayed_wb;
-			acm->delayed_wb = NULL;
-			acm_start_wb(acm, wb);
+		for (;;) {
+			urb = usb_get_from_anchor(&acm->delayed);
+			if (!urb)
+				break;
+
+			acm_start_wb(acm, urb->context);
 		}
 
 		/*

@@ -120,7 +120,7 @@ struct acm {
 	unsigned int throttled:1;			/* actually throttled */
 	unsigned int throttle_req:1;			/* throttle requested */
 	u8 bInterval;
-	struct acm_wb *delayed_wb;			/* write queued for a device about to be woken */
+	struct usb_anchor delayed;			/* writes queued for a device about to be woken */
 };
 
 #define CDC_DATA_INTERFACE_TYPE	0x0a

@@ -122,13 +122,23 @@ static void acm_release_minor(struct acm
 static int acm_ctrl_msg(struct acm *acm, int request, int value,
 							void *buf, int len)
 {
-	int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
+	int retval;
+
+	retval = usb_autopm_get_interface(acm->control);
+	if (retval)
+		return retval;
+
+	retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
 		request, USB_RT_ACM, value,
 		acm->control->altsetting[0].desc.bInterfaceNumber,
 		buf, len, 5000);
+
 	dev_dbg(&acm->control->dev,
 			"%s - rq 0x%02x, val %#x, len %#x, result %d\n",
 			__func__, request, value, len, retval);
+
+	usb_autopm_put_interface(acm->control);
+
 	return retval < 0 ? retval : 0;
 }
 

@@ -1548,8 +1548,7 @@ static int acm_suspend(struct usb_interf
 	if (cnt)
 		return 0;
 
-	if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags))
-		stop_data_traffic(acm);
+	stop_data_traffic(acm);
 
 	return 0;
 }

@@ -666,7 +666,13 @@ static int acm_tty_write(struct tty_stru
 	memcpy(wb->buf, buf, count);
 	wb->len = count;
 
-	usb_autopm_get_interface_async(acm->control);
+	stat = usb_autopm_get_interface_async(acm->control);
+	if (stat) {
+		wb->use = 0;
+		spin_unlock_irqrestore(&acm->write_lock, flags);
+		return stat;
+	}
+
 	if (acm->susp_count) {
 		usb_anchor_urb(wb->urb, &acm->delayed);
 		spin_unlock_irqrestore(&acm->write_lock, flags);

@@ -506,6 +506,7 @@ static int acm_port_activate(struct tty_
 {
 	struct acm *acm = container_of(port, struct acm, port);
 	int retval = -ENODEV;
+	int i;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 

@@ -554,6 +555,8 @@ static int acm_port_activate(struct tty_
 	return 0;
 
 error_submit_read_urbs:
+	for (i = 0; i < acm->rx_buflimit; i++)
+		usb_kill_urb(acm->read_urbs[i]);
 	acm->ctrlout = 0;
 	acm_set_control(acm, acm->ctrlout);
 error_set_control:

@@ -587,12 +587,13 @@ static void acm_port_shutdown(struct tty
 	struct urb *urb;
 	struct acm_wb *wb;
 	int i;
+	int pm_err;
 
 	dev_dbg(&acm->control->dev, "%s\n", __func__);
 
 	mutex_lock(&acm->mutex);
 	if (!acm->disconnected) {
-		usb_autopm_get_interface(acm->control);
+		pm_err = usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
 
 		for (;;) {

@@ -610,7 +611,8 @@ static void acm_port_shutdown(struct tty
 		for (i = 0; i < acm->rx_buflimit; i++)
 			usb_kill_urb(acm->read_urbs[i]);
 		acm->control->needs_remote_wakeup = 0;
-		usb_autopm_put_interface(acm->control);
+		if (!pm_err)
+			usb_autopm_put_interface(acm->control);
 	}
 	mutex_unlock(&acm->mutex);
 }