4.4.244-rc1 review

index 1c1ecc1d49ad2..547a3a5ac57b5 100644
@@ -416,14 +416,16 @@ struct rb_event_info {
 
 /*
  * Used for which event context the event is in.
- *  NMI     = 0
- *  IRQ     = 1
- *  SOFTIRQ = 2
- *  NORMAL  = 3
+ *  TRANSITION = 0
+ *  NMI     = 1
+ *  IRQ     = 2
+ *  SOFTIRQ = 3
+ *  NORMAL  = 4
  *
  * See trace_recursive_lock() comment below for more details.
  */
 enum {
+	RB_CTX_TRANSITION,
 	RB_CTX_NMI,
 	RB_CTX_IRQ,
 	RB_CTX_SOFTIRQ,

@@ -2585,10 +2587,10 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * a bit of overhead in something as critical as function tracing,
  * we use a bitmask trick.
  *
- *  bit 0 =  NMI context
- *  bit 1 =  IRQ context
- *  bit 2 =  SoftIRQ context
- *  bit 3 =  normal context.
+ *  bit 1 =  NMI context
+ *  bit 2 =  IRQ context
+ *  bit 3 =  SoftIRQ context
+ *  bit 4 =  normal context.
  *
  * This works because this is the order of contexts that can
  * preempt other contexts. A SoftIRQ never preempts an IRQ

@@ -2611,6 +2613,30 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
  * The least significant bit can be cleared this way, and it
  * just so happens that it is the same bit corresponding to
  * the current context.
+ *
+ * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit
+ * is set when a recursion is detected at the current context, and if
+ * the TRANSITION bit is already set, it will fail the recursion.
+ * This is needed because there's a lag between the changing of
+ * interrupt context and updating the preempt count. In this case,
+ * a false positive will be found. To handle this, one extra recursion
+ * is allowed, and this is done by the TRANSITION bit. If the TRANSITION
+ * bit is already set, then it is considered a recursion and the function
+ * ends. Otherwise, the TRANSITION bit is set, and that bit is returned.
+ *
+ * On the trace_recursive_unlock(), the TRANSITION bit will be the first
+ * to be cleared. Even if it wasn't the context that set it. That is,
+ * if an interrupt comes in while NORMAL bit is set and the ring buffer
+ * is called before preempt_count() is updated, since the check will
+ * be on the NORMAL bit, the TRANSITION bit will then be set. If an
+ * NMI then comes in, it will set the NMI bit, but when the NMI code
+ * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * and leave the NMI bit set. But this is fine, because the interrupt
+ * code that set the TRANSITION bit will then clear the NMI bit when it
+ * calls trace_recursive_unlock(). If another NMI comes in, it will
+ * set the TRANSITION bit and continue.
+ *
+ * Note: The TRANSITION bit only handles a single transition between context.
  */
 
 static __always_inline int

@@ -2629,8 +2655,16 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 	} else
 		bit = RB_CTX_NORMAL;
 
-	if (unlikely(val & (1 << bit)))
-		return 1;
+	if (unlikely(val & (1 << bit))) {
+		/*
+		 * It is possible that this was called by transitioning
+		 * between interrupt context, and preempt_count() has not
+		 * been updated yet. In this case, use the TRANSITION bit.
+		 */
+		bit = RB_CTX_TRANSITION;
+		if (val & (1 << bit))
+			return 1;
+	}
 
 	val |= (1 << bit);
 	cpu_buffer->current_context = val;

index 1eb737c466ddc..8e8695eb652af 100644
@@ -751,7 +751,8 @@ again:
 	}
 	kfree(gl->gl_lksb.sb_lvbptr);
 	kmem_cache_free(cachep, gl);
-	atomic_dec(&sdp->sd_glock_disposal);
+	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+		wake_up(&sdp->sd_glock_wait);
 	*glp = tmp;
 
 	return ret;

index e101cac3d4a63..9ab7969ee7e30 100644
@@ -490,14 +490,14 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	struct queue_pages *qp = walk->private;
 	unsigned long flags = qp->flags;
 	int nid;
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 
 	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
 			continue;

@@ -521,7 +521,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		} else
 			break;
 	}
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	cond_resched();
 	return addr != end ? -EIO : 0;
 }

index 367d5af899e81..10239cffd70f8 100644
@@ -197,6 +197,10 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts)
  */
 static inline s64 timespec64_to_ns(const struct timespec64 *ts)
 {
+	/* Prevent multiplication overflow */
+	if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+		return KTIME_MAX;
+
 	return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
 }
 

index 67366515a29d2..f35e18e76f160 100644
@@ -3856,6 +3856,8 @@ process_slot:
 			ret = -EINTR;
 			goto out;
 		}
+
+		cond_resched();
 	}
 	ret = 0;
 

index 5bb5950d6276b..ed05cd7a4ef2c 100644
@@ -1554,6 +1554,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 	int err = -ENOENT;
 	__be32 minspi = htonl(low);
 	__be32 maxspi = htonl(high);
+	__be32 newspi = 0;
 	u32 mark = x->mark.v & x->mark.m;
 
 	spin_lock_bh(&x->lock);

@@ -1572,21 +1573,22 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 			xfrm_state_put(x0);
 			goto unlock;
 		}
-		x->id.spi = minspi;
+		newspi = minspi;
 	} else {
 		u32 spi = 0;
 		for (h = 0; h < high-low+1; h++) {
 			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
-				x->id.spi = htonl(spi);
+				newspi = htonl(spi);
 				break;
 			}
 			xfrm_state_put(x0);
 		}
 	}
-	if (x->id.spi) {
+	if (newspi) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
+		x->id.spi = newspi;
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
 		hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);

index 0ae4f73dc8eb5..5b392662d100b 100644
@@ -415,6 +415,7 @@ static void perf_event__mmap2_swap(union perf_event *event,
 	event->mmap2.maj   = bswap_32(event->mmap2.maj);
 	event->mmap2.min   = bswap_32(event->mmap2.min);
 	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+	event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
 
 	if (sample_id_all) {
 		void *data = &event->mmap2.filename;

index 63215b17247c8..379250dd0668e 100644
@@ -221,6 +221,8 @@ struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus,
 		return NULL;
 	if (ebus->idx != bus_idx)
 		return NULL;
+	if (addr < 0 || addr > 31)
+		return NULL;
 
 	list_for_each_entry(hlink, &ebus->hlink_list, list) {
 		for (i = 0; i < HDA_MAX_CODECS; i++) {

index 9dd968ee792e0..3c0f141262ad5 100644
@@ -466,7 +466,11 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx)
 	if (!skb)
 		return 0;
 
-	netif_rx(skb);
+	skb_get(skb);
+	if (netif_rx(skb) == NET_RX_SUCCESS)
+		dev_consume_skb_any(skb);
+	else
+		dev_kfree_skb_any(skb);
 
 	return len;
 }

index 3c0f141262ad5..9579dae54af29 100644
@@ -439,9 +439,13 @@ struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8
 		 */
 		struct sk_buff *skb = priv->echo_skb[idx];
 		struct canfd_frame *cf = (struct canfd_frame *)skb->data;
-		u8 len = cf->len;
 
-		*len_ptr = len;
+		/* get the real payload length for netdev statistics */
+		if (cf->can_id & CAN_RTR_FLAG)
+			*len_ptr = 0;
+		else
+			*len_ptr = cf->len;
+
 		priv->echo_skb[idx] = NULL;
 
 		return skb;

index 51bb6532785c3..1a2111c775ae1 100644
@@ -60,21 +60,17 @@ static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
  */
 static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
 {
-	if (skb_shared(skb)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+	struct sk_buff *nskb;
 
-		if (likely(nskb)) {
-			can_skb_set_owner(nskb, skb->sk);
-			consume_skb(skb);
-			return nskb;
-		} else {
-			kfree_skb(skb);
-			return NULL;
-		}
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!nskb)) {
+		kfree_skb(skb);
+		return NULL;
 	}
 
-	/* we can assume to have an unshared skb with proper owner */
-	return skb;
+	can_skb_set_owner(nskb, skb->sk);
+	consume_skb(skb);
+	return nskb;
 }
 
 #endif /* !_CAN_SKB_H */

index 1b75d5304a2c1..2e62cdc7ec7ab 100644
@@ -475,12 +475,18 @@ static int pcan_usb_fd_decode_canmsg(struct pcan_usb_fd_if *usb_if,
 				     struct pucan_msg *rx_msg)
 {
 	struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)];
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct canfd_frame *cfd;
 	struct sk_buff *skb;
 	const u16 rx_msg_flags = le16_to_cpu(rm->flags);
 
+	if (pucan_msg_get_channel(rm) >= ARRAY_SIZE(usb_if->dev))
+		return -ENOMEM;
+
+	dev = usb_if->dev[pucan_msg_get_channel(rm)];
+	netdev = dev->netdev;
+
 	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) {
 		/* CANFD frame case */
 		skb = alloc_canfd_skb(netdev, &cfd);

@@ -527,15 +533,21 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if,
 				     struct pucan_msg *rx_msg)
 {
 	struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
-	struct pcan_usb_fd_device *pdev =
-			container_of(dev, struct pcan_usb_fd_device, dev);
+	struct pcan_usb_fd_device *pdev;
 	enum can_state new_state = CAN_STATE_ERROR_ACTIVE;
 	enum can_state rx_state, tx_state;
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct can_frame *cf;
 	struct sk_buff *skb;
 
+	if (pucan_stmsg_get_channel(sm) >= ARRAY_SIZE(usb_if->dev))
+		return -ENOMEM;
+
+	dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
+	pdev = container_of(dev, struct pcan_usb_fd_device, dev);
+	netdev = dev->netdev;
+
 	/* nothing should be sent while in BUS_OFF state */
 	if (dev->can.state == CAN_STATE_BUS_OFF)
 		return 0;

@@ -588,9 +600,14 @@ static int pcan_usb_fd_decode_error(struct pcan_usb_fd_if *usb_if,
 				    struct pucan_msg *rx_msg)
 {
 	struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)];
-	struct pcan_usb_fd_device *pdev =
-			container_of(dev, struct pcan_usb_fd_device, dev);
+	struct pcan_usb_fd_device *pdev;
+	struct peak_usb_device *dev;
+
+	if (pucan_ermsg_get_channel(er) >= ARRAY_SIZE(usb_if->dev))
+		return -EINVAL;
+
+	dev = usb_if->dev[pucan_ermsg_get_channel(er)];
+	pdev = container_of(dev, struct pcan_usb_fd_device, dev);
 
 	/* keep a trace of tx and rx error counters for later use */
 	pdev->bec.txerr = er->tx_err_cnt;

@@ -604,11 +621,17 @@ static int pcan_usb_fd_decode_overrun(struct pcan_usb_fd_if *usb_if,
 				      struct pucan_msg *rx_msg)
 {
 	struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)];
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct can_frame *cf;
 	struct sk_buff *skb;
 
+	if (pufd_omsg_get_channel(ov) >= ARRAY_SIZE(usb_if->dev))
+		return -EINVAL;
+
+	dev = usb_if->dev[pufd_omsg_get_channel(ov)];
+	netdev = dev->netdev;
+
 	/* allocate an skb to store the error frame */
 	skb = alloc_can_err_skb(netdev, &cf);
 	if (!skb)

@@ -726,6 +749,9 @@ static int pcan_usb_fd_encode_msg(struct peak_usb_device *dev,
 	u16 tx_msg_size, tx_msg_flags;
 	u8 can_dlc;
 
+	if (cfd->len > CANFD_MAX_DLEN)
+		return -EINVAL;
+
 	tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4);
 	tx_msg->size = cpu_to_le16(tx_msg_size);
 	tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX);

index 8c47cc8dc8965..22deddb2dbf5a 100644
@@ -150,14 +150,55 @@ void peak_usb_get_ts_tv(struct peak_time_ref *time_ref, u32 ts,
 	/* protect from getting timeval before setting now */
 	if (time_ref->tv_host.tv_sec > 0) {
 		u64 delta_us;
+		s64 delta_ts = 0;
+
+		/* General case: dev_ts_1 < dev_ts_2 < ts, with:
+		 *
+		 * - dev_ts_1 = previous sync timestamp
+		 * - dev_ts_2 = last sync timestamp
+		 * - ts = event timestamp
+		 * - ts_period = known sync period (theoretical)
+		 *             ~ dev_ts2 - dev_ts1
+		 * *but*:
+		 *
+		 * - time counters wrap (see adapter->ts_used_bits)
+		 * - sometimes, dev_ts_1 < ts < dev_ts2
+		 *
+		 * "normal" case (sync time counters increase):
+		 * must take into account case when ts wraps (tsw)
+		 *
+		 *      < ts_period > <          >
+		 *     |             |            |
+		 *  ---+--------+----+-------0-+--+-->
+		 *     ts_dev_1 |    ts_dev_2  |
+		 *              ts             tsw
+		 */
+		if (time_ref->ts_dev_1 < time_ref->ts_dev_2) {
+			/* case when event time (tsw) wraps */
+			if (ts < time_ref->ts_dev_1)
+				delta_ts = 1 << time_ref->adapter->ts_used_bits;
+
+		/* Otherwise, sync time counter (ts_dev_2) has wrapped:
+		 * handle case when event time (tsn) hasn't.
+		 *
+		 *      < ts_period > <          >
+		 *     |             |            |
+		 *  ---+--------+--0-+---------+--+-->
+		 *     ts_dev_1 |    ts_dev_2  |
+		 *              tsn            ts
+		 */
+		} else if (time_ref->ts_dev_1 < ts) {
+			delta_ts = -(1 << time_ref->adapter->ts_used_bits);
+		}
 
-		delta_us = ts - time_ref->ts_dev_2;
-		if (ts < time_ref->ts_dev_2)
-			delta_us &= (1 << time_ref->adapter->ts_used_bits) - 1;
+		/* add delay between last sync and event timestamps */
+		delta_ts += (signed int)(ts - time_ref->ts_dev_2);
 
-		delta_us += time_ref->ts_total;
+		/* add time from beginning to last sync */
+		delta_ts += time_ref->ts_total;
 
-		delta_us *= time_ref->adapter->us_per_ts_scale;
+		/* convert ticks number into microseconds */
+		delta_us = delta_ts * time_ref->adapter->us_per_ts_scale;
 		delta_us >>= time_ref->adapter->us_per_ts_shift;
 
 		*tv = time_ref->tv_host_0;

index 97a80238fdee3..b28bc7690d4b3 100644
@@ -4000,6 +4000,10 @@ int btree_write_cache_pages(struct address_space *mapping,
 			if (!ret) {
 				free_extent_buffer(eb);
 				continue;
+			} else if (ret < 0) {
+				done = 1;
+				free_extent_buffer(eb);
+				break;
 			}
 
 			ret = write_one_eb(eb, fs_info, wbc, &epd);

index fe04e748dfe4b..eb8c29f3e16ef 100644
@@ -40,6 +40,13 @@ struct pinctrl_dt_map {
 static void dt_free_map(struct pinctrl_dev *pctldev,
 		     struct pinctrl_map *map, unsigned num_maps)
 {
+	int i;
+
+	for (i = 0; i < num_maps; ++i) {
+		kfree_const(map[i].dev_name);
+		map[i].dev_name = NULL;
+	}
+
 	if (pctldev) {
 		const struct pinctrl_ops *ops = pctldev->desc->pctlops;
 		ops->dt_free_map(pctldev, map, num_maps);

@@ -73,7 +80,13 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 
 	/* Initialize common mapping table entry fields */
 	for (i = 0; i < num_maps; i++) {
-		map[i].dev_name = dev_name(p->dev);
+		const char *devname;
+
+		devname = kstrdup_const(dev_name(p->dev), GFP_KERNEL);
+		if (!devname)
+			goto err_free_map;
+
+		map[i].dev_name = devname;
 		map[i].name = statename;
 		if (pctldev)
 			map[i].ctrl_dev_name = dev_name(pctldev->dev);

@@ -81,11 +94,8 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 
 	/* Remember the converted mapping table entries */
 	dt_map = kzalloc(sizeof(*dt_map), GFP_KERNEL);
-	if (!dt_map) {
-		dev_err(p->dev, "failed to alloc struct pinctrl_dt_map\n");
-		dt_free_map(pctldev, map, num_maps);
-		return -ENOMEM;
-	}
+	if (!dt_map)
+		goto err_free_map;
 
 	dt_map->pctldev = pctldev;
 	dt_map->map = map;

@@ -93,6 +103,10 @@ static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 	list_add_tail(&dt_map->node, &p->dt_maps);
 
 	return pinctrl_register_map(map, num_maps, false);
+
+err_free_map:
+	dt_free_map(pctldev, map, num_maps);
+	return -ENOMEM;
 }
 
 struct pinctrl_dev *of_pinctrl_get(struct device_node *np)

index cdb263875efb3..18e10357f1d0b 100644
@@ -203,7 +203,7 @@ static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u16 vsi_id,
  *
  * check for the valid vector id
  **/
-static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u8 vector_id)
+static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u32 vector_id)
 {
 	struct i40e_pf *pf = vf->pf;
 

index 18e10357f1d0b..b4b4d46da1734 100644
@@ -188,7 +188,7 @@ static inline bool i40e_vc_isvalid_vsi_id(struct i40e_vf *vf, u16 vsi_id)
  * check for the valid queue id
  **/
 static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u16 vsi_id,
-					    u8 qid)
+					    u16 qid)
 {
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = i40e_find_vsi_from_id(pf, vsi_id);

index ec13e2ae6d16e..ee38299f9c578 100644
@@ -711,7 +711,8 @@ static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb,
 static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct flowi4 *fl4,
-				       struct ip_tunnel_info *info)
+				       struct ip_tunnel_info *info,
+				       __be16 dport, __be16 sport)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct rtable *rt = NULL;

@@ -720,6 +721,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_mark = skb->mark;
 	fl4->flowi4_proto = IPPROTO_UDP;
+	fl4->fl4_dport = dport;
+	fl4->fl4_sport = sport;
 
 	if (info) {
 		fl4->daddr = info->key.u.ipv4.dst;

@@ -754,7 +757,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 					   struct net_device *dev,
 					   struct flowi6 *fl6,
-					   struct ip_tunnel_info *info)
+					   struct ip_tunnel_info *info,
+					   __be16 dport, __be16 sport)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs6 = geneve->sock6;

@@ -764,6 +768,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
 	memset(fl6, 0, sizeof(*fl6));
 	fl6->flowi6_mark = skb->mark;
 	fl6->flowi6_proto = IPPROTO_UDP;
+	fl6->fl6_dport = dport;
+	fl6->fl6_sport = sport;
 
 	if (info) {
 		fl6->daddr = info->key.u.ipv6.dst;

@@ -834,13 +840,14 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 			goto tx_error;
 	}
 
-	rt = geneve_get_v4_rt(skb, dev, &fl4, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	rt = geneve_get_v4_rt(skb, dev, &fl4, info,
+			      geneve->dst_port, sport);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		goto tx_error;
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
 	if (info) {

@@ -916,13 +923,14 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	dst = geneve_get_v6_dst(skb, dev, &fl6, info);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	dst = geneve_get_v6_dst(skb, dev, &fl6, info,
+				geneve->dst_port, sport);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto tx_error;
 	}
 
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
 	skb_reset_mac_header(skb);
 
 	if (info) {

@@ -1011,9 +1019,14 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 	struct dst_entry *dst;
 	struct flowi6 fl6;
 #endif
+	__be16 sport;
 
 	if (ip_tunnel_info_af(info) == AF_INET) {
-		rt = geneve_get_v4_rt(skb, dev, &fl4, info);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
+
+		rt = geneve_get_v4_rt(skb, dev, &fl4, info,
+				      geneve->dst_port, sport);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 

@@ -1021,7 +1034,11 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		info->key.u.ipv4.src = fl4.saddr;
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (ip_tunnel_info_af(info) == AF_INET6) {
-		dst = geneve_get_v6_dst(skb, dev, &fl6, info);
+		sport = udp_flow_src_port(geneve->net, skb,
+					  1, USHRT_MAX, true);
+
+		dst = geneve_get_v6_dst(skb, dev, &fl6, info,
+					geneve->dst_port, sport);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 

@@ -1032,8 +1049,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	info->key.tp_src = udp_flow_src_port(geneve->net, skb,
-					     1, USHRT_MAX, true);
+	info->key.tp_src = sport;
 	info->key.tp_dst = geneve->dst_port;
 	return 0;
 }

@@ -972,7 +972,7 @@ static bool ath9k_rx_prepare(struct ath9
 	struct ath_htc_rx_status *rxstatus;
 	struct ath_rx_status rx_stats;
 	bool decrypt_error = false;
-	__be16 rs_datalen;
+	u16 rs_datalen;
 	bool is_phyerr;
 
 	if (skb->len < HTC_RX_FRAME_HEADER_SIZE) {

index 1fdfec14a3ba1..5d4616061309e 100644
@@ -1773,6 +1773,7 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err;
 	}
 
+	pci_set_drvdata(pdev, dev);
 	spin_lock_init(&dev->lock);
 	dev->pdev = pdev;
 	dev->gadget.ops = &goku_ops;

@@ -1806,7 +1807,6 @@ static int goku_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 	dev->regs = (struct goku_udc_regs __iomem *) base;
 
-	pci_set_drvdata(pdev, dev);
 	INFO(dev, "%s\n", driver_desc);
 	INFO(dev, "version: " DRIVER_VERSION " %s\n", dmastr());
 	INFO(dev, "irq %d, pci mem %p\n", pdev->irq, base);

index 2736e9cfc2ee9..99dcbdc1ff3a4 100644
@@ -747,9 +747,9 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 		}
 
 		gfs2_free_clones(rgd);
+		return_all_reservations(rgd);
 		kfree(rgd->rd_bits);
 		rgd->rd_bits = NULL;
-		return_all_reservations(rgd);
 		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	}
 }

index 99dcbdc1ff3a4..faa5e0e2c4493 100644
@@ -1388,6 +1388,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 

index c568293cb6c1a..f1745c5cdf7b3 100644
@@ -1118,22 +1118,19 @@ static int cik_sdma_soft_reset(void *handle)
 {
 	u32 srbm_soft_reset = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	u32 tmp = RREG32(mmSRBM_STATUS2);
+	u32 tmp;
 
-	if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
-		/* sdma0 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
-	}
-	if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
-		/* sdma1 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
-	}
+	/* sdma0 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
+
+	/* sdma1 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
 
 	if (srbm_soft_reset) {
 		cik_sdma_print_status((void *)adev);

index 98c34c3adf392..4466413c5eecc 100644
@@ -1594,19 +1594,24 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 
 /* device xmit handlers */
 
+enum ieee80211_encrypt {
+	ENCRYPT_NO,
+	ENCRYPT_MGMT,
+	ENCRYPT_DATA,
+};
+
 static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb,
-				int head_need, bool may_encrypt)
+				int head_need,
+				enum ieee80211_encrypt encrypt)
 {
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_hdr *hdr;
 	bool enc_tailroom;
 	int tail_need = 0;
 
-	hdr = (struct ieee80211_hdr *) skb->data;
-	enc_tailroom = may_encrypt &&
-		       (sdata->crypto_tx_tailroom_needed_cnt ||
-			ieee80211_is_mgmt(hdr->frame_control));
+	enc_tailroom = encrypt == ENCRYPT_MGMT ||
+		       (encrypt == ENCRYPT_DATA &&
+			sdata->crypto_tx_tailroom_needed_cnt);
 
 	if (enc_tailroom) {
 		tail_need = IEEE80211_ENCRYPT_TAILROOM;

@@ -1639,21 +1644,27 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	int headroom;
-	bool may_encrypt;
+	enum ieee80211_encrypt encrypt;
 
-	may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT);
+	if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
+		encrypt = ENCRYPT_NO;
+	else if (ieee80211_is_mgmt(hdr->frame_control))
+		encrypt = ENCRYPT_MGMT;
+	else
+		encrypt = ENCRYPT_DATA;
 
 	headroom = local->tx_headroom;
-	if (may_encrypt)
+	if (encrypt != ENCRYPT_NO)
 		headroom += sdata->encrypt_headroom;
 	headroom -= skb_headroom(skb);
 	headroom = max_t(int, 0, headroom);
 
-	if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
+	if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return;
 	}
 
+	/* reload after potential resize */
 	hdr = (struct ieee80211_hdr *) skb->data;
 	info->control.vif = &sdata->vif;
 

@@ -2346,7 +2357,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 		head_need += sdata->encrypt_headroom;
 		head_need += local->tx_headroom;
 		head_need = max_t(int, 0, head_need);
-		if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+		if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
 			ieee80211_free_txskb(&local->hw, skb);
 			skb = NULL;
 			return ERR_PTR(-ENOMEM);

@@ -2756,7 +2767,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 	if (unlikely(ieee80211_skb_resize(sdata, skb,
 					  max_t(int, extra_head + hw_headroom -
 						     skb_headroom(skb), 0),
-					  false))) {
+					  ENCRYPT_NO))) {
 		kfree_skb(skb);
 		return true;
 	}

index bbddab248c489..6f7c3f6a5027b 100644
@@ -242,6 +242,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
+	/*
+	 * If we had used sta_info_pre_move_state() then we might not
+	 * have gone through the state transitions down again, so do
+	 * it here now (and warn if it's inserted).
+	 *
+	 * This will clear state such as fast TX/RX that may have been
+	 * allocated during state transitions.
+	 */
+	while (sta->sta_state > IEEE80211_STA_NONE) {
+		int ret;
+
+		WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+		ret = sta_info_move_state(sta, sta->sta_state - 1);
+		if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+			break;
+	}
+
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);
 

index 474923175b108..dcbf5cd44bb37 100644
@@ -2775,7 +2775,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd)
 		power_rule = &reg_rule->power_rule;
 
 		if (reg_rule->flags & NL80211_RRF_AUTO_BW)
-			snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+			snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO",
 				 freq_range->max_bandwidth_khz,
 				 reg_get_max_bandwidth(rd, reg_rule));
 		else

index 695d4e235438c..90832bf00538e 100644
@@ -351,7 +351,11 @@ extern bool amd_iommu_np_cache;
 /* Only true if all IOMMUs support device IOTLBs */
 extern bool amd_iommu_iotlb_sup;
 
-#define MAX_IRQS_PER_TABLE	256
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define MAX_IRQS_PER_TABLE	512
 #define IRQ_TABLE_ALIGNMENT	128
 
 struct irq_remap_table {

index dc6221942b85f..ab66ea0a72bfb 100644
@@ -162,7 +162,7 @@ xfs_fs_map_blocks(
 		goto out_unlock;
 	error = invalidate_inode_pages2(inode->i_mapping);
 	if (WARN_ON_ONCE(error))
-		return error;
+		goto out_unlock;
 
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);

index b3bf8762f4e8c..77881432dd404 100644
@@ -1014,11 +1014,13 @@ EXPORT_SYMBOL_GPL(of_dma_get_range);
  */
 bool of_dma_is_coherent(struct device_node *np)
 {
-	struct device_node *node = of_node_get(np);
+	struct device_node *node;
 
 	if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
 		return true;
 
+	node = of_node_get(np);
+
 	while (node) {
 		if (of_property_read_bool(node, "dma-coherent")) {
 			of_node_put(node);

index 848ea6a399f23..cbda69e58e084 100644
@@ -903,6 +903,7 @@ static ssize_t cosa_write(struct file *file,
 			chan->tx_status = 1;
 			spin_unlock_irqrestore(&cosa->lock, flags);
 			up(&chan->wsem);
+			kfree(kbuf);
 			return -ERESTARTSYS;
 		}
 	}

index 2bbad9c1274c3..8baa3121e7a6b 100644
@@ -193,7 +193,7 @@ static inline int get_recursion_context(int *recursion)
 		rctx = 3;
 	else if (in_irq())
 		rctx = 2;
-	else if (in_softirq())
+	else if (in_serving_softirq())
 		rctx = 1;
 	else
 		rctx = 0;

@@ -1452,8 +1452,8 @@ static const struct mount_opts {
 							MOPT_SET | MOPT_Q},
 	{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
 		       EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
-	{Opt_usrjquota, 0, MOPT_Q},
-	{Opt_grpjquota, 0, MOPT_Q},
+	{Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
+	{Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
 	{Opt_offusrjquota, 0, MOPT_Q},
 	{Opt_offgrpjquota, 0, MOPT_Q},
 	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},

@@ -1892,6 +1892,7 @@ void ext4_inline_data_truncate(struct in
 
 	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
+		ext4_write_unlock_xattr(inode, &no_expand);
 		*has_inline = 0;
 		ext4_journal_stop(handle);
 		return;

@@ -1693,6 +1693,15 @@ static const struct usb_device_id acm_id
 	{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
+	{ USB_DEVICE(0x045b, 0x023c),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
+	{ USB_DEVICE(0x045b, 0x0248),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
+	{ USB_DEVICE(0x045b, 0x024D),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
 	{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; [email protected] */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},

@@ -156,11 +156,11 @@ static inline u8 mei_cl_me_id(const stru
  *
  * @cl: host client
  *
- * Return: mtu
+ * Return: mtu or 0 if client is not connected
  */
 static inline size_t mei_cl_mtu(const struct mei_cl *cl)
 {
-	return cl->me_cl->props.max_msg_length;
+	return cl->me_cl ? cl->me_cl->props.max_msg_length : 0;
 }
 
 /**

@@ -1751,6 +1751,7 @@ static void ocfs2_inode_init_once(void *
 
 	oi->ip_blkno = 0ULL;
 	oi->ip_clusters = 0;
+	oi->ip_next_orphan = NULL;
 
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 

@@ -408,7 +408,10 @@ static void exit_mm(struct task_struct *
 		up_read(&mm->mmap_sem);
 
 		self.task = tsk;
-		self.next = xchg(&core_state->dumper.next, &self);
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
 		/*
 		 * Implies mb(), the result of xchg() must be visible
 		 * to core_state->dumper.

@@ -350,6 +350,7 @@ int psb_irq_postinstall(struct drm_devic
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 

@@ -362,20 +363,12 @@ int psb_irq_postinstall(struct drm_devic
 	PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+		else
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	if (dev_priv->ops->hotplug_enable)
 		dev_priv->ops->hotplug_enable(dev, true);

@@ -388,6 +381,7 @@ void psb_irq_uninstall(struct drm_device
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 

@@ -396,14 +390,10 @@ void psb_irq_uninstall(struct drm_device
 
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
 				  _PSB_IRQ_MSVDX_FLAG |

@@ -144,7 +144,7 @@ static int amd_gpio_set_debounce(struct
 			pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
 		} else if (debounce < 250000) {
-			time = debounce / 15600;
+			time = debounce / 15625;
 			pin_reg |= time & DB_TMR_OUT_MASK;
 			pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg |= BIT(DB_TMR_LARGE_OFF);

@@ -154,14 +154,14 @@ static int amd_gpio_set_debounce(struct
 			pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg |= BIT(DB_TMR_LARGE_OFF);
 		} else {
-			pin_reg &= ~DB_CNTRl_MASK;
+			pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
 			ret = -EINVAL;
 		}
 	} else {
 		pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
 		pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
 		pin_reg &= ~DB_TMR_OUT_MASK;
-		pin_reg &= ~DB_CNTRl_MASK;
+		pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
 	}
 	writel(pin_reg, gpio_dev->base + offset * 4);
 	spin_unlock_irqrestore(&gpio_dev->lock, flags);

@@ -195,6 +195,7 @@ int __init swiotlb_init_with_tbl(char *t
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	if (verbose)
 		swiotlb_print_info();

@@ -225,9 +226,11 @@ swiotlb_init(int verbose)
 	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
 		return;
 
-	if (io_tlb_start)
+	if (io_tlb_start) {
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+		io_tlb_start = 0;
+	}
 	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }

@@ -326,6 +329,7 @@ swiotlb_late_init_with_tbl(char *tlb, un
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	swiotlb_print_info();
 

@@ -1079,7 +1079,6 @@ static void ipip6_tunnel_bind_dev(struct
 	if (tdev && !netif_is_l3_master(tdev)) {
 		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
 		dev->mtu = tdev->mtu - t_hlen;
 		if (dev->mtu < IPV6_MIN_MTU)
 			dev->mtu = IPV6_MIN_MTU;

@@ -1371,7 +1370,6 @@ static void ipip6_tunnel_setup(struct ne
 	dev->destructor		= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->flags		= IFF_NOARP;
 	netif_keep_dst(dev);

@@ -1513,7 +1513,8 @@ static int iucv_sock_shutdown(struct soc
 		break;
 	}
 
-	if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
+	if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) &&
+	    sk->sk_state == IUCV_CONNECTED) {
 		if (iucv->transport == AF_IUCV_TRANS_IUCV) {
 			txmsg.class = 0;
 			txmsg.tag = 0;

@@ -823,7 +823,7 @@ static int x25_connect(struct socket *so
 	sock->state = SS_CONNECTED;
 	rc = 0;
 out_put_neigh:
-	if (rc) {
+	if (rc && x25->neighbour) {
 		read_lock_bh(&x25_list_lock);
 		x25_neigh_put(x25->neighbour);
 		x25->neighbour = NULL;

@@ -307,7 +307,7 @@ struct sock *cookie_v4_check(struct sock
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	struct flowi4 fl4;

@@ -391,8 +391,13 @@ struct sock *cookie_v4_check(struct sock
 
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
 
-	tcp_select_initial_window(tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));

@@ -144,7 +144,7 @@ struct sock *cookie_v6_check(struct sock
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
 

@@ -237,7 +237,13 @@ struct sock *cookie_v6_check(struct sock
 	}
 
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
-	tcp_select_initial_window(tcp_full_space(sk), req->mss,
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
+
+	tcp_select_initial_window(full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));

@@ -678,7 +678,6 @@ retry:
 		r->initialized = 1;
 		r->entropy_total = 0;
 		if (r == &nonblocking_pool) {
-			prandom_reseed_late();
 			process_random_ready_list();
 			wake_up_all(&urandom_init_wait);
 			pr_notice("random: %s pool is initialized\n", r->name);

@@ -923,7 +922,6 @@ void add_interrupt_randomness(int irq, i
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
-	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if ((fast_pool->count < 64) &&
 	    !time_after(now, fast_pool->last + HZ))

@@ -16,12 +16,44 @@ void prandom_bytes(void *buf, size_t nby
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+#if BITS_PER_LONG == 64
+/*
+ * The core SipHash round function.  Each line can be executed in
+ * parallel given enough CPU resources.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol64(v1, 13),  v2 += v3, v3 = rol64(v3, 16), \
+	v1 ^= v0, v0 = rol64(v0, 32),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol64(v3, 21),  v2 += v1, v1 = rol64(v1, 17), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol64(v2, 32)  \
+)
+
+#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261)
+#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573)
+
+#elif BITS_PER_LONG == 32
+/*
+ * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash.
+ * This is weaker, but 32-bit machines are not used for high-traffic
+ * applications, so there is less output for an attacker to analyze.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol32(v1,  5),  v2 += v3, v3 = rol32(v3,  8), \
+	v1 ^= v0, v0 = rol32(v0, 16),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol32(v3,  7),  v2 += v1, v1 = rol32(v1, 13), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol32(v2, 16)  \
+)
+#define PRND_K0 0x6c796765
+#define PRND_K1 0x74656462
+
+#else
+#error Unsupported BITS_PER_LONG
+#endif
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
-DECLARE_PER_CPU(struct rnd_state, net_rand_state);
-
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);

@@ -1432,13 +1432,6 @@ void update_process_times(int user_tick)
 #endif
 	scheduler_tick();
 	run_posix_cpu_timers(p);
-
-	/* The current CPU might make use of net randoms without receiving IRQs
-	 * to renew them often enough. Let's update the net_rand_state from a
-	 * non-constant value that's not affine to the number of calls to make
-	 * sure it's updated when there's some activity (we don't care in idle).
-	 */
-	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /*

504 lines not on this page · raw message

@@ -1223,6 +1223,14 @@ static int ssb_prctl_set(struct task_str
 	return 0;
 }
 
+static bool is_spec_ib_user_controlled(void)
+{
+	return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP;
+}
+
 static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	switch (ctrl) {

@@ -1230,17 +1238,26 @@ static int ib_prctl_set(struct task_stru
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return 0;
-		/*
-		 * Indirect branch speculation is always disabled in strict
-		 * mode. It can neither be enabled if it was force-disabled
-		 * by a  previous prctl call.
 
+		/*
+		 * With strict mode for both IBPB and STIBP, the instruction
+		 * code paths avoid checking this task flag and instead,
+		 * unconditionally run the instruction. However, STIBP and IBPB
+		 * are independent and either can be set to conditionally
+		 * enabled regardless of the mode of the other.
+		 *
+		 * If either is set to conditional, allow the task flag to be
+		 * updated, unless it was force-disabled by a previous prctl
+		 * call. Currently, this is possible on an AMD CPU which has the
+		 * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the
+		 * kernel is booted with 'spectre_v2_user=seccomp', then
+		 * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and
+		 * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED.
 		 */
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		if (!is_spec_ib_user_controlled() ||
 		    task_spec_ib_force_disable(task))
 			return -EPERM;
+
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
 		break;

@@ -1253,10 +1270,10 @@ static int ib_prctl_set(struct task_stru
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+
+		if (!is_spec_ib_user_controlled())
 			return 0;
+
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);

@@ -1319,20 +1336,17 @@ static int ib_prctl_get(struct task_stru
 	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 	    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 		return PR_SPEC_ENABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
-		return PR_SPEC_DISABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
+	else if (is_spec_ib_user_controlled()) {
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	} else
+	} else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+		return PR_SPEC_DISABLE;
+	else
 		return PR_SPEC_NOT_AFFECTED;
 }
 

@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/irqnr.h>
 #include <linux/pci.h>
+#include <linux/spinlock.h>
 
 #ifdef CONFIG_X86
 #include <asm/desc.h>

@@ -70,6 +71,23 @@ const struct evtchn_ops *evtchn_ops;
  */
 static DEFINE_MUTEX(irq_mapping_update_lock);
 
+/*
+ * Lock protecting event handling loop against removing event channels.
+ * Adding of event channels is no issue as the associated IRQ becomes active
+ * only after everything is setup (before request_[threaded_]irq() the handler
+ * can't be entered for an event, as the event channel will be unmasked only
+ * then).
+ */
+static DEFINE_RWLOCK(evtchn_rwlock);
+
+/*
+ * Lock hierarchy:
+ *
+ * irq_mapping_update_lock
+ *   evtchn_rwlock
+ *     IRQ-desc lock
+ */
+
 static LIST_HEAD(xen_irq_list_head);
 
 /* IRQ <-> VIRQ mapping. */

@@ -104,7 +122,7 @@ static void clear_evtchn_to_irq_row(unsi
 	unsigned col;
 
 	for (col = 0; col < EVTCHN_PER_ROW; col++)
-		evtchn_to_irq[row][col] = -1;
+		WRITE_ONCE(evtchn_to_irq[row][col], -1);
 }
 
 static void clear_evtchn_to_irq_all(void)

@@ -141,7 +159,7 @@ static int set_evtchn_to_irq(unsigned ev
 		clear_evtchn_to_irq_row(row);
 	}
 
-	evtchn_to_irq[row][col] = irq;
+	WRITE_ONCE(evtchn_to_irq[row][col], irq);
 	return 0;
 }
 

@@ -151,7 +169,7 @@ int get_evtchn_to_irq(unsigned evtchn)
 		return -1;
 	if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL)
 		return -1;
-	return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)];
+	return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]);
 }
 
 /* Get info for IRQ */

@@ -260,10 +278,14 @@ static void xen_irq_info_cleanup(struct
  */
 unsigned int evtchn_from_irq(unsigned irq)
 {
-	if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)))
+	const struct irq_info *info = NULL;
+
+	if (likely(irq < nr_irqs))
+		info = info_for_irq(irq);
+	if (!info)
 		return 0;
 
-	return info_for_irq(irq)->evtchn;
+	return info->evtchn;
 }
 
 unsigned irq_from_evtchn(unsigned int evtchn)

@@ -447,16 +469,21 @@ static int __must_check xen_allocate_irq
 static void xen_free_irq(unsigned irq)
 {
 	struct irq_info *info = info_for_irq(irq);
+	unsigned long flags;
 
 	if (WARN_ON(!info))
 		return;
 
+	write_lock_irqsave(&evtchn_rwlock, flags);
+
 	list_del(&info->list);
 
 	set_info_for_irq(irq, NULL);
 
 	WARN_ON(info->refcnt > 0);
 
+	write_unlock_irqrestore(&evtchn_rwlock, flags);
+
 	kfree(info);
 
 	/* Legacy IRQ descriptors are managed by the arch. */

@@ -1241,6 +1268,8 @@ static void __xen_evtchn_do_upcall(void)
 	int cpu = get_cpu();
 	unsigned count;
 
+	read_lock(&evtchn_rwlock);
+
 	do {
 		vcpu_info->evtchn_upcall_pending = 0;
 

@@ -1256,6 +1285,7 @@ static void __xen_evtchn_do_upcall(void)
 	} while (count != 1 || vcpu_info->evtchn_upcall_pending);
 
 out:
+	read_unlock(&evtchn_rwlock);
 
 	put_cpu();
 }

@@ -90,6 +90,8 @@ static void evtchn_2l_unmask(unsigned po
 
 	BUG_ON(!irqs_disabled());
 
+	smp_wmb();	/* All writes before unmask must be visible. */
+
 	if (unlikely((cpu != cpu_from_evtchn(port))))
 		do_hypercall = 1;
 	else {

@@ -227,19 +227,25 @@ static bool evtchn_fifo_is_masked(unsign
 	return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
 }
 /*
- * Clear MASKED, spinning if BUSY is set.
+ * Clear MASKED if not PENDING, spinning if BUSY is set.
+ * Return true if mask was cleared.
  */
-static void clear_masked(volatile event_word_t *word)
+static bool clear_masked_cond(volatile event_word_t *word)
 {
 	event_word_t new, old, w;
 
 	w = *word;
 
 	do {
+		if (w & (1 << EVTCHN_FIFO_PENDING))
+			return false;
+
 		old = w & ~(1 << EVTCHN_FIFO_BUSY);
 		new = old & ~(1 << EVTCHN_FIFO_MASKED);
 		w = sync_cmpxchg(word, old, new);
 	} while (w != old);
+
+	return true;
 }
 
 static void evtchn_fifo_unmask(unsigned port)

@@ -248,8 +254,7 @@ static void evtchn_fifo_unmask(unsigned
 
 	BUG_ON(!irqs_disabled());
 
-	clear_masked(word);
-	if (evtchn_fifo_is_pending(port)) {
+	if (!clear_masked_cond(word)) {
 		struct evtchn_unmask unmask = { .port = port };
 		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
 	}

@@ -112,6 +112,7 @@ static bool (*pirq_needs_eoi)(unsigned i
 static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY];
 
 static struct irq_chip xen_dynamic_chip;
+static struct irq_chip xen_lateeoi_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);

@@ -404,6 +405,33 @@ void notify_remote_via_irq(int irq)
 }
 EXPORT_SYMBOL_GPL(notify_remote_via_irq);
 
+static void xen_irq_lateeoi_locked(struct irq_info *info)
+{
+	evtchn_port_t evtchn;
+
+	evtchn = info->evtchn;
+	if (!VALID_EVTCHN(evtchn))
+		return;
+
+	unmask_evtchn(evtchn);
+}
+
+void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
+{
+	struct irq_info *info;
+	unsigned long flags;
+
+	read_lock_irqsave(&evtchn_rwlock, flags);
+
+	info = info_for_irq(irq);
+
+	if (info)
+		xen_irq_lateeoi_locked(info);
+
+	read_unlock_irqrestore(&evtchn_rwlock, flags);
+}
+EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
+
 static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;

@@ -875,7 +903,7 @@ int xen_pirq_from_irq(unsigned irq)
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
-int bind_evtchn_to_irq(unsigned int evtchn)
+static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip)
 {
 	int irq;
 	int ret;

@@ -892,7 +920,7 @@ int bind_evtchn_to_irq(unsigned int evtc
 		if (irq < 0)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+		irq_set_chip_and_handler_name(irq, chip,
 					      handle_edge_irq, "event");
 
 		ret = xen_irq_info_evtchn_setup(irq, evtchn);

@@ -913,8 +941,19 @@ out:
 
 	return irq;
 }
+
+int bind_evtchn_to_irq(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
+
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;

@@ -956,8 +995,9 @@ static int bind_ipi_to_irq(unsigned int
 	return irq;
 }
 
-int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   unsigned int remote_port)
+static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain,
+					       evtchn_port_t remote_port,
+					       struct irq_chip *chip)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;

@@ -968,10 +1008,26 @@ int bind_interdomain_evtchn_to_irq(unsig
 	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
 					  &bind_interdomain);
 
-	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+	return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port,
+					       chip);
+}
+
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_dynamic_chip);
 }
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
 
+int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
+					   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi);
+
 static int find_virq(unsigned int virq, unsigned int cpu)
 {
 	struct evtchn_status status;

@@ -1067,14 +1123,15 @@ static void unbind_from_irq(unsigned int
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
-int bind_evtchn_to_irqhandler(unsigned int evtchn,
-			      irq_handler_t handler,
-			      unsigned long irqflags,
-			      const char *devname, void *dev_id)
+static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname, void *dev_id,
+					  struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_evtchn_to_irq(evtchn);
+	irq = bind_evtchn_to_irq_chip(evtchn, chip);
 	if (irq < 0)
 		return irq;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);

@@ -1085,18 +1142,38 @@ int bind_evtchn_to_irqhandler(unsigned i
 
 	return irq;
 }
+
+int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
+			      irq_handler_t handler,
+			      unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
 
-int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  unsigned int remote_port,
-					  irq_handler_t handler,
-					  unsigned long irqflags,
-					  const char *devname,
-					  void *dev_id)
+int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
+				      irq_handler_t handler,
+				      unsigned long irqflags,
+				      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi);
+
+static int bind_interdomain_evtchn_to_irqhandler_chip(
+		unsigned int remote_domain, evtchn_port_t remote_port,
+		irq_handler_t handler, unsigned long irqflags,
+		const char *devname, void *dev_id, struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+	irq = bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						  chip);
 	if (irq < 0)
 		return irq;
 

@@ -1108,8 +1185,33 @@ int bind_interdomain_evtchn_to_irqhandle
 
 	return irq;
 }
+
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  evtchn_port_t remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
 
+int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
+						  evtchn_port_t remote_port,
+						  irq_handler_t handler,
+						  unsigned long irqflags,
+						  const char *devname,
+						  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi);
+
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname, void *dev_id)

@@ -1639,6 +1741,21 @@ static struct irq_chip xen_dynamic_chip
 	.irq_mask_ack		= mask_ack_dynirq,
 
 	.irq_set_affinity	= set_affinity_irq,
+	.irq_retrigger		= retrigger_dynirq,
+};
+
+static struct irq_chip xen_lateeoi_chip __read_mostly = {
+	/* The chip name needs to contain "xen-dyn" for irqbalance to work. */
+	.name			= "xen-dyn-lateeoi",
+
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= mask_ack_dynirq,
+	.irq_mask_ack		= mask_ack_dynirq,
+
+	.irq_set_affinity	= set_affinity_irq,
 	.irq_retrigger		= retrigger_dynirq,
 };
 

@@ -12,11 +12,16 @@
 
 unsigned xen_evtchn_nr_channels(void);
 
-int bind_evtchn_to_irq(unsigned int evtchn);
-int bind_evtchn_to_irqhandler(unsigned int evtchn,
+int bind_evtchn_to_irq(evtchn_port_t evtchn);
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn);
+int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
 			      irq_handler_t handler,
 			      unsigned long irqflags, const char *devname,
 			      void *dev_id);
+int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
+				      irq_handler_t handler,
+				      unsigned long irqflags, const char *devname,
+				      void *dev_id);
 int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu);
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,

@@ -29,13 +34,21 @@ int bind_ipi_to_irqhandler(enum ipi_vect
 			   const char *devname,
 			   void *dev_id);
 int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   unsigned int remote_port);
+				   evtchn_port_t remote_port);
+int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
+					   evtchn_port_t remote_port);
 int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  unsigned int remote_port,
+					  evtchn_port_t remote_port,
 					  irq_handler_t handler,
 					  unsigned long irqflags,
 					  const char *devname,
 					  void *dev_id);
+int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
+						  evtchn_port_t remote_port,
+						  irq_handler_t handler,
+						  unsigned long irqflags,
+						  const char *devname,
+						  void *dev_id);
 
 /*
  * Common unbind function for all event sources. Takes IRQ to unbind from.

@@ -44,6 +57,14 @@ int bind_interdomain_evtchn_to_irqhandle
  */
 void unbind_from_irqhandler(unsigned int irq, void *dev_id);
 
+/*
+ * Send late EOI for an IRQ bound to an event channel via one of the *_lateeoi
+ * functions above.
+ */
+void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags);
+/* Signal an event was spurious, i.e. there was no action resulting from it. */
+#define XEN_EOI_FLAG_SPURIOUS	0x00000001
+
 #define XEN_IRQ_PRIORITY_MAX     EVTCHN_FIFO_PRIORITY_MAX
 #define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT
 #define XEN_IRQ_PRIORITY_MIN     EVTCHN_FIFO_PRIORITY_MIN

@@ -173,7 +173,7 @@ static inline void shrink_free_pagepool(
 
 #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
 
-static int do_block_io_op(struct xen_blkif *blkif);
+static int do_block_io_op(struct xen_blkif *blkif, unsigned int *eoi_flags);
 static int dispatch_rw_block_io(struct xen_blkif *blkif,
 				struct blkif_request *req,
 				struct pending_req *pending_req);

@@ -594,6 +594,8 @@ int xen_blkif_schedule(void *arg)
 	struct xen_vbd *vbd = &blkif->vbd;
 	unsigned long timeout;
 	int ret;
+	bool do_eoi;
+	unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS;
 
 	while (!kthread_should_stop()) {
 		if (try_to_freeze())

@@ -617,16 +619,23 @@ int xen_blkif_schedule(void *arg)
 		if (timeout == 0)
 			goto purge_gnt_list;
 
+		do_eoi = blkif->waiting_reqs;
+
 		blkif->waiting_reqs = 0;
 		smp_mb(); /* clear flag *before* checking for work */
 
-		ret = do_block_io_op(blkif);
+		ret = do_block_io_op(blkif, &eoi_flags);
 		if (ret > 0)
 			blkif->waiting_reqs = 1;
 		if (ret == -EACCES)
 			wait_event_interruptible(blkif->shutdown_wq,
 						 kthread_should_stop());
 
+		if (do_eoi && !blkif->waiting_reqs) {
+			xen_irq_lateeoi(blkif->irq, eoi_flags);
+			eoi_flags |= XEN_EOI_FLAG_SPURIOUS;
+		}
+
 purge_gnt_list:
 		if (blkif->vbd.feature_gnt_persistent &&
 		    time_after(jiffies, blkif->next_lru)) {

@@ -1094,7 +1103,7 @@ static void end_block_io_op(struct bio *
  * and transmute  it to the block API to hand it over to the proper block disk.
  */
 static int
-__do_block_io_op(struct xen_blkif *blkif)
+__do_block_io_op(struct xen_blkif *blkif, unsigned int *eoi_flags)
 {
 	union blkif_back_rings *blk_rings = &blkif->blk_rings;
 	struct blkif_request req;