Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Segregate namespaces properly in conntrack dumps, from Liping Zhang.

 2) tcp listener refcount fix in netfilter tproxy, from Eric Dumazet.

 3) Fix timeouts in qed driver due to xmit_more, from Yuval Mintz.

 4) Fix use-after-free in tcp_xmit_retransmit_queue().

 5) Userspace header fixups (use of __u32, missing includes, etc.) from
    Mikko Rapeli.

 6) Further refinements to fragmentation wrt gso and tunnels, from
    Shmulik Ladkani.

 7) Trigger poll correctly for zero length UDP packets, from Eric
    Dumazet.

 8) TCP window scaling fix, also from Eric Dumazet.

 9) SLAB_DESTROY_BY_RCU is not relevant any more for UDP sockets.

10) Module refcount leak in qdisc_create_dflt(), from Eric Dumazet.

11) Fix deadlock in cp_rx_poll() of 8139cp driver, from Gao Feng.

12) Memory leak in rhashtable's alloc_bucket_locks(), from Eric Dumazet.

13) Add new device ID to alx driver, from Owen Lin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
  Add Killer E2500 device ID in alx driver.
  net: smc91x: fix SMC accesses
  Documentation: networking: dsa: Remove platform device TODO
  net/mlx5: Increase number of ethtool steering priorities
  net/mlx5: Add error prints when validate ETS failed
  net/mlx5e: Fix memory leak if refreshing TIRs fails
  net/mlx5e: Add ethtool counter for TX xmit_more
  net/mlx5e: Fix ethtool -g/G rx ring parameter report with striding RQ
  net/mlx5e: Don't wait for SQ completions on close
  net/mlx5e: Don't post fragmented MPWQE when RQ is disabled
  net/mlx5e: Don't wait for RQ completions on close
  net/mlx5e: Limit UMR length to the device's limitation
  rhashtable: fix a memory leak in alloc_bucket_locks()
  sfc: fix potential stack corruption from running past stat bitmask
  team: loadbalance: push lacpdus to exact delivery
  net: hns: dereference ppe_cb->ppe_common_cb if it is non-null
  8139cp: Fix one possible deadloop in cp_rx_poll
  i40e: Change some init flow for the client
  Revert "phy: IRQ cannot be shared"
  net: dsa: bcm_sf2: Fix race condition while unmasking interrupts
  ...

53 files changed, 596 insertions, 332 deletions

diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 463bed8cbe4c..dd446e466699 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -205,8 +205,8 @@ static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val,	\
 static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
 {									\
-	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 	priv->irq##which##_mask &= ~(mask);				\
+	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
 }									\
 static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \
 						u32 mask)		\
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index d1d9d3cf9139..710679067594 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2656,15 +2656,19 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 			return ret;
 	}
 
+	/* Rate Control: disable ingress rate limiting. */
 	if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
 	    mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
-	    mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
 	    mv88e6xxx_6320_family(chip)) {
-		/* Rate Control: disable ingress rate limiting. */
 		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
 					   PORT_RATE_CONTROL, 0x0001);
 		if (ret)
 			return ret;
+	} else if (mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip)) {
+		ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
+					   PORT_RATE_CONTROL, 0x0000);
+		if (ret)
+			return ret;
 	}
 
 	/* Port Control 1: disable trunking, disable sending
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 6453148d066a..4eb17daefc4f 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1545,6 +1545,8 @@ static const struct pci_device_id alx_pci_tbl[] = {
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400),
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
+	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2500),
+	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162),
 	  .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
 	{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) },
diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h
index 0959e6824cb6..1fc2d852249f 100644
--- a/drivers/net/ethernet/atheros/alx/reg.h
+++ b/drivers/net/ethernet/atheros/alx/reg.h
@@ -38,6 +38,7 @@
 #define ALX_DEV_ID_AR8161				0x1091
 #define ALX_DEV_ID_E2200				0xe091
 #define ALX_DEV_ID_E2400				0xe0a1
+#define ALX_DEV_ID_E2500				0xe0b1
 #define ALX_DEV_ID_AR8162				0x1090
 #define ALX_DEV_ID_AR8171				0x10A1
 #define ALX_DEV_ID_AR8172				0x10A0
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 9a9745c4047c..625235db644f 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -159,7 +159,7 @@ static int bgmac_probe(struct bcma_device *core)
 
 	if (!bgmac_is_bcm4707_family(core)) {
 		mii_bus = bcma_mdio_mii_register(core, bgmac->phyaddr);
-		if (!IS_ERR(mii_bus)) {
+		if (IS_ERR(mii_bus)) {
 			err = PTR_ERR(mii_bus);
 			goto err;
 		}
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index afb10e326b4f..fab35a593898 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -170,7 +170,6 @@
 #define   NIC_QSET_SQ_0_7_DOOR			(0x010838)
 #define   NIC_QSET_SQ_0_7_STATUS		(0x010840)
 #define   NIC_QSET_SQ_0_7_DEBUG			(0x010848)
-#define   NIC_QSET_SQ_0_7_CNM_CHG		(0x010860)
 #define   NIC_QSET_SQ_0_7_STAT_0_1		(0x010900)
 
 #define   NIC_QSET_RBDR_0_1_CFG			(0x010C00)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index d2d8ef270142..ad4fddb55421 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -382,7 +382,10 @@ static void nicvf_get_regs(struct net_device *dev,
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q);
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q);
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q);
-		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q);
+		/* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which
+		 * produces bus errors when read
+		 */
+		p[i++] = 0;
 		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q);
 		reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3);
 		p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index c45de49dc963..c762a8c8c954 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4335,6 +4335,11 @@ static void cfg_queues(struct adapter *adap)
 #endif
 	int ciq_size;
 
+	/* Reduce memory usage in kdump environment, disable all offload.
+	 */
+	if (is_kdump_kernel())
+		adap->params.offload = 0;
+
 	for_each_port(adap, i)
 		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
 #ifdef CONFIG_CHELSIO_T4_DCB
@@ -4365,11 +4370,6 @@ static void cfg_queues(struct adapter *adap)
 	if (q10g > netif_get_num_default_rss_queues())
 		q10g = netif_get_num_default_rss_queues();
 
-	/* Reduce memory usage in kdump environment, disable all offload.
-	 */
-	if (is_kdump_kernel())
-		adap->params.offload = 0;
-
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index d20935dc8399..4b4f5bc0e279 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2922,17 +2922,25 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 {
 	unsigned int size = lstatus & BD_LENGTH_MASK;
 	struct page *page = rxb->page;
+	bool last = !!(lstatus & BD_LFLAG(RXBD_LAST));
 
 	/* Remove the FCS from the packet length */
-	if (likely(lstatus & BD_LFLAG(RXBD_LAST)))
+	if (last)
 		size -= ETH_FCS_LEN;
 
-	if (likely(first))
+	if (likely(first)) {
 		skb_put(skb, size);
-	else
-		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-				rxb->page_offset + RXBUF_ALIGNMENT,
-				size, GFAR_RXB_TRUESIZE);
+	} else {
+		/* the last fragments' length contains the full frame length */
+		if (last)
+			size -= skb->len;
+
+		/* in case the last fragment consisted only of the FCS */
+		if (size > 0)
+			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+					rxb->page_offset + RXBUF_ALIGNMENT,
+					size, GFAR_RXB_TRUESIZE);
+	}
 
 	/* try reuse page */
 	if (unlikely(page_count(page) != 1))
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 373fd094f2f3..6e8a9c8467b9 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -100,7 +100,8 @@ extern const char gfar_driver_version[];
 #define DEFAULT_RX_LFC_THR  16
 #define DEFAULT_LFC_PTVVAL  4
 
-#define GFAR_RXB_SIZE 1536
+/* prevent fragmenation by HW in DSA environments */
+#define GFAR_RXB_SIZE roundup(1536 + 8, 64)
 #define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \
 			  + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 #define GFAR_RXB_TRUESIZE 2048
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index ff8b6a468b24..6ea872287307 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -328,9 +328,10 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb)
 static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
 {
 	u32 port;
-	struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
 
 	if (ppe_cb->ppe_common_cb) {
+		struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
+
 		port = ppe_cb->index;
 		dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0);
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index e1370c556a3c..618f18436618 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -199,6 +199,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi)
 void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi)
 {
 	struct i40e_client_instance *cdev;
+	int ret = 0;
 
 	if (!vsi)
 		return;
@@ -211,7 +212,14 @@ void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi)
 					"Cannot locate client instance open routine\n");
 				continue;
 			}
-			cdev->client->ops->open(&cdev->lan_info, cdev->client);
+			if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+				       &cdev->state))) {
+				ret = cdev->client->ops->open(&cdev->lan_info,
+							      cdev->client);
+				if (!ret)
+					set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+						&cdev->state);
+			}
 		}
 	}
 	mutex_unlock(&i40e_client_instance_mutex);
@@ -407,12 +415,14 @@ struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf,
  * i40e_client_add_instance - add a client instance struct to the instance list
  * @pf: pointer to the board struct
  * @client: pointer to a client struct in the client list.
+ * @existing: if there was already an existing instance
  *
- * Returns cdev ptr on success, NULL on failure
+ * Returns cdev ptr on success or if already exists, NULL on failure
  **/
 static
 struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
-						      struct i40e_client *client)
+						     struct i40e_client *client,
+						     bool *existing)
 {
 	struct i40e_client_instance *cdev;
 	struct netdev_hw_addr *mac = NULL;
@@ -421,7 +431,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
 	mutex_lock(&i40e_client_instance_mutex);
 	list_for_each_entry(cdev, &i40e_client_instances, list) {
 		if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
-			cdev = NULL;
+			*existing = true;
 			goto out;
 		}
 	}
@@ -505,6 +515,7 @@ void i40e_client_subtask(struct i40e_pf *pf)
 {
 	struct i40e_client_instance *cdev;
 	struct i40e_client *client;
+	bool existing = false;
 	int ret = 0;
 
 	if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
@@ -528,18 +539,25 @@ void i40e_client_subtask(struct i40e_pf *pf)
 			/* check if L2 VSI is up, if not we are not ready */
 			if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
 				continue;
+		} else {
+			dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n",
+				 client->name);
 		}
 
 		/* Add the client instance to the instance list */
-		cdev = i40e_client_add_instance(pf, client);
+		cdev = i40e_client_add_instance(pf, client, &existing);
 		if (!cdev)
 			continue;
 
-		/* Also up the ref_cnt of no. of instances of this client */
-		atomic_inc(&client->ref_cnt);
-		dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
-			 client->name, pf->hw.pf_id,
-			 pf->hw.bus.device, pf->hw.bus.func);
+		if (!existing) {
+			/* Also up the ref_cnt for no. of instances of this
+			 * client.
+			 */
+			atomic_inc(&client->ref_cnt);
+			dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
+				 client->name, pf->hw.pf_id,
+				 pf->hw.bus.device, pf->hw.bus.func);
+		}
 
 		/* Send an Open request to the client */
 		atomic_inc(&cdev->ref_cnt);
@@ -588,7 +606,8 @@ int i40e_lan_add_device(struct i40e_pf *pf)
 		 pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func);
 
 	/* Since in some cases register may have happened before a device gets
-	 * added, we can schedule a subtask to go initiate the clients.
+	 * added, we can schedule a subtask to go initiate the clients if
+	 * they can be launched at probe time.
 	 */
 	pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
 	i40e_service_event_schedule(pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c6ac7a61812f..828ed28c3c14 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5431,7 +5431,6 @@ int i40e_open(struct net_device *netdev)
 	wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
 
 	udp_tunnel_get_rx_info(netdev);
-	i40e_notify_client_of_netdev_open(vsi);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index b4217f30e89c..c47b605e8651 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -2958,8 +2958,10 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq)
 	}
 
 	/* was that the last pool using this rar? */
-	if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0)
+	if (mpsar_lo == 0 && mpsar_hi == 0 &&
+	    rar != 0 && rar != hw->mac.san_mac_rar_index)
 		hw->mac.ops.clear_rar(hw, rar);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d6e2a1cae19a..c2ec01a22d55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -143,13 +143,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx)
 	return cmd->cmd_buf + (idx << cmd->log_stride);
 }
 
-static u8 xor8_buf(void *buf, int len)
+static u8 xor8_buf(void *buf, size_t offset, int len)
 {
 	u8 *ptr = buf;
 	u8 sum = 0;
 	int i;
+	int end = len + offset;
 
-	for (i = 0; i < len; i++)
+	for (i = offset; i < end; i++)
 		sum ^= ptr[i];
 
 	return sum;
@@ -157,41 +158,49 @@ static u8 xor8_buf(void *buf, int len)
 
 static int verify_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+	int xor_len = sizeof(*block) - sizeof(block->data) - 1;
+
+	if (xor8_buf(block, rsvd0_off, xor_len) != 0xff)
 		return -EINVAL;
 
-	if (xor8_buf(block, sizeof(*block)) != 0xff)
+	if (xor8_buf(block, 0, sizeof(*block)) != 0xff)
 		return -EINVAL;
 
 	return 0;
 }
 
-static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token,
-			   int csum)
+static void calc_block_sig(struct mlx5_cmd_prot_block *block)
 {
-	block->token = token;
-	if (csum) {
-		block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) -
-					    sizeof(block->data) - 2);
-		block->sig = ~xor8_buf(block, sizeof(*block) - 1);
-	}
+	int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2;
+	size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+
+	block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len);
+	block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1);
 }
 
-static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum)
+static void calc_chain_sig(struct mlx5_cmd_msg *msg)
 {
 	struct mlx5_cmd_mailbox *next = msg->next;
-
-	while (next) {
-		calc_block_sig(next->buf, token, csum);
+	int size = msg->len;
+	int blen = size - min_t(int, sizeof(msg->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
+
+	for (i = 0; i < n && next; i++)  {
+		calc_block_sig(next->buf);
 		next = next->next;
 	}
 }
 
 static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
 {
-	ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay));
-	calc_chain_sig(ent->in, ent->token, csum);
-	calc_chain_sig(ent->out, ent->token, csum);
+	ent->lay->sig = ~xor8_buf(ent->lay, 0,  sizeof(*ent->lay));
+	if (csum) {
+		calc_chain_sig(ent->in);
+		calc_chain_sig(ent->out);
+	}
 }
 
 static void poll_timeout(struct mlx5_cmd_work_ent *ent)
@@ -222,12 +231,17 @@ static int verify_signature(struct mlx5_cmd_work_ent *ent)
 	struct mlx5_cmd_mailbox *next = ent->out->next;
 	int err;
 	u8 sig;
+	int size = ent->out->len;
+	int blen = size - min_t(int, sizeof(ent->out->first.data), size);
+	int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+		/ MLX5_CMD_DATA_BLOCK_SIZE;
+	int i = 0;
 
-	sig = xor8_buf(ent->lay, sizeof(*ent->lay));
+	sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
 	if (sig != 0xff)
 		return -EINVAL;
 
-	while (next) {
+	for (i = 0; i < n && next; i++) {
 		err = verify_block_sig(next->buf);
 		if (err)
 			return err;
@@ -656,7 +670,6 @@ static void cmd_work_handler(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->alloc_lock, flags);
 	}
 
-	ent->token = alloc_token(cmd);
 	cmd->ent_arr[ent->idx] = ent;
 	lay = get_inst(cmd, ent->idx);
 	ent->lay = lay;
@@ -766,7 +779,8 @@ static u8 *get_status_ptr(struct mlx5_outbox_hdr *out)
 static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 			   struct mlx5_cmd_msg *out, void *uout, int uout_size,
 			   mlx5_cmd_cbk_t callback,
-			   void *context, int page_queue, u8 *status)
+			   void *context, int page_queue, u8 *status,
+			   u8 token)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -783,6 +797,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	if (IS_ERR(ent))
 		return PTR_ERR(ent);
 
+	ent->token = token;
+
 	if (!callback)
 		init_completion(&ent->done);
 
@@ -854,7 +870,8 @@ static const struct file_operations fops = {
 	.write	= dbg_write,
 };
 
-static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
+static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size,
+			    u8 token)
 {
 	struct mlx5_cmd_prot_block *block;
 	struct mlx5_cmd_mailbox *next;
@@ -880,6 +897,7 @@ static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
 		memcpy(block->data, from, copy);
 		from += copy;
 		size -= copy;
+		block->token = token;
 		next = next->next;
 	}
 
@@ -949,7 +967,8 @@ static void free_cmd_box(struct mlx5_core_dev *dev,
 }
 
 static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
-					       gfp_t flags, int size)
+					       gfp_t flags, int size,
+					       u8 token)
 {
 	struct mlx5_cmd_mailbox *tmp, *head = NULL;
 	struct mlx5_cmd_prot_block *block;
@@ -978,6 +997,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
 		tmp->next = head;
 		block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
 		block->block_num = cpu_to_be32(n - i - 1);
+		block->token = token;
 		head = tmp;
 	}
 	msg->next = head;
@@ -1352,7 +1372,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 	}
 
 	if (IS_ERR(msg))
-		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
+		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
 
 	return msg;
 }
@@ -1377,6 +1397,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	int err;
 	u8 status = 0;
 	u32 drv_synd;
+	u8 token;
 
 	if (pci_channel_offline(dev->pdev) ||
 	    dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -1395,20 +1416,22 @@ static