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

Pull networking fixes from David Miller:

 1) The netlink attribute passed in to dev_set_alias() is not
    necessarily NULL terminated, don't use strlcpy() on it. From
    Alexander Potapenko.

 2) Fix implementation of atomics in arm64 bpf JIT, from Daniel
    Borkmann.

 3) Correct the release of netdevs and driver private data in certain
    circumstances.

 4) Sanitize netlink message length properly in decnet, from Mateusz
    Jurczyk.

 5) Don't leak kernel data in rtnl_fill_vfinfo() netlink blobs. From
    Yuval Mintz.

 6) Hash secret is never initialized in ipv6 ILA translation code, from
    Arnd Bergmann. I guess those clang warnings about unused inline
    functions are useful for something!

 7) Fix endian selection in bpf_endian.h, from Daniel Borkmann.

 8) Sanitize sockaddr length before dereferncing any fields in AF_UNIX
    and CAIF. From Mateusz Jurczyk.

 9) Fix timestamping for GMAC3 chips in stmmac driver, from Mario
    Molitor.

10) Do not leak netdev on dev_alloc_name() errors in mac80211, from
    Johannes Berg.

11) Fix locking in sctp_for_each_endpoint(), from Xin Long.

12) Fix wrong memset size on 32-bit in snmp6, from Christian Perle.

13) Fix use after free in ip_mc_clear_src(), from WANG Cong.

14) Fix regressions caused by ICMP rate limiting changes in 4.11, from
    Jesper Dangaard Brouer.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (91 commits)
  i40e: Fix a sleep-in-atomic bug
  net: don't global ICMP rate limit packets originating from loopback
  net/act_pedit: fix an error code
  net: update undefined ->ndo_change_mtu() comment
  net_sched: move tcf_lock down after gen_replace_estimator()
  caif: Add sockaddr length check before accessing sa_family in connect handler
  qed: fix dump of context data
  qmi_wwan: new Telewell and Sierra device IDs
  net: phy: Fix MDIO_THUNDER dependencies
  netconsole: Remove duplicate "netconsole: " logging prefix
  igmp: acquire pmc lock for ip_mc_clear_src()
  r8152: give the device version
  net: rps: fix uninitialized symbol warning
  mac80211: don't send SMPS action frame in AP mode when not needed
  mac80211/wpa: use constant time memory comparison for MACs
  mac80211: set bss_info data before configuring the channel
  mac80211: remove 5/10 MHz rate code from station MLME
  mac80211: Fix incorrect condition when checking rx timestamp
  mac80211: don't look at the PM bit of BAR frames
  i40e: fix handling of HW ATR eviction
  ...

Documentation/networking/scaling.txt

@@ -122,7 +122,7 @@ associated flow of the packet. The hash is either provided by hardware
 or will be computed in the stack. Capable hardware can pass the hash in
 the receive descriptor for the packet; this would usually be the same
 hash used for RSS (e.g. computed Toeplitz hash). The hash is saved in
-skb->rx_hash and can be used elsewhere in the stack as a hash of the
+skb->hash and can be used elsewhere in the stack as a hash of the
 packet’s flow.
 
 Each receive hardware queue has an associated list of CPUs to which

arch/arm64/net/bpf_jit_comp.c

@@ -36,6 +36,7 @@ int bpf_jit_enable __read_mostly;
 #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
 #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
 #define TCALL_CNT (MAX_BPF_JIT_REG + 2)
+#define TMP_REG_3 (MAX_BPF_JIT_REG + 3)
 
 /* Map BPF registers to A64 registers */
 static const int bpf2a64[] = {
@@ -57,6 +58,7 @@ static const int bpf2a64[] = {
 	/* temporary registers for internal BPF JIT */
 	[TMP_REG_1] = A64_R(10),
 	[TMP_REG_2] = A64_R(11),
+	[TMP_REG_3] = A64_R(12),
 	/* tail_call_cnt */
 	[TCALL_CNT] = A64_R(26),
 	/* temporary register for blinding constants */
@@ -319,6 +321,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const u8 src = bpf2a64[insn->src_reg];
 	const u8 tmp = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
+	const u8 tmp3 = bpf2a64[TMP_REG_3];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
@@ -689,10 +692,10 @@ emit_cond_jmp:
 		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
 		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
 		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
-		emit(A64_STXR(isdw, tmp2, tmp, tmp2), ctx);
+		emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx);
 		jmp_offset = -3;
 		check_imm19(jmp_offset);
-		emit(A64_CBNZ(0, tmp2, jmp_offset), ctx);
+		emit(A64_CBNZ(0, tmp3, jmp_offset), ctx);
 		break;
 
 	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */

drivers/hsi/clients/ssi_protocol.c

@@ -1066,7 +1066,7 @@ static void ssip_pn_setup(struct net_device *dev)
 	dev->addr_len		= 1;
 	dev->tx_queue_len	= SSIP_TXQUEUE_LEN;
 
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 	dev->header_ops		= &phonet_header_ops;
 }
 

drivers/net/bonding/bond_3ad.c

@@ -90,10 +90,13 @@ enum ad_link_speed_type {
 	AD_LINK_SPEED_100MBPS,
 	AD_LINK_SPEED_1000MBPS,
 	AD_LINK_SPEED_2500MBPS,
+	AD_LINK_SPEED_5000MBPS,
 	AD_LINK_SPEED_10000MBPS,
+	AD_LINK_SPEED_14000MBPS,
 	AD_LINK_SPEED_20000MBPS,
 	AD_LINK_SPEED_25000MBPS,
 	AD_LINK_SPEED_40000MBPS,
+	AD_LINK_SPEED_50000MBPS,
 	AD_LINK_SPEED_56000MBPS,
 	AD_LINK_SPEED_100000MBPS,
 };
@@ -259,10 +262,13 @@ static inline int __check_agg_selection_timer(struct port *port)
  *     %AD_LINK_SPEED_100MBPS,
  *     %AD_LINK_SPEED_1000MBPS,
  *     %AD_LINK_SPEED_2500MBPS,
+ *     %AD_LINK_SPEED_5000MBPS,
  *     %AD_LINK_SPEED_10000MBPS
+ *     %AD_LINK_SPEED_14000MBPS,
  *     %AD_LINK_SPEED_20000MBPS
  *     %AD_LINK_SPEED_25000MBPS
  *     %AD_LINK_SPEED_40000MBPS
+ *     %AD_LINK_SPEED_50000MBPS
  *     %AD_LINK_SPEED_56000MBPS
  *     %AD_LINK_SPEED_100000MBPS
  */
@@ -296,10 +302,18 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_2500MBPS;
 			break;
 
+		case SPEED_5000:
+			speed = AD_LINK_SPEED_5000MBPS;
+			break;
+
 		case SPEED_10000:
 			speed = AD_LINK_SPEED_10000MBPS;
 			break;
 
+		case SPEED_14000:
+			speed = AD_LINK_SPEED_14000MBPS;
+			break;
+
 		case SPEED_20000:
 			speed = AD_LINK_SPEED_20000MBPS;
 			break;
@@ -312,6 +326,10 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_40000MBPS;
 			break;
 
+		case SPEED_50000:
+			speed = AD_LINK_SPEED_50000MBPS;
+			break;
+
 		case SPEED_56000:
 			speed = AD_LINK_SPEED_56000MBPS;
 			break;
@@ -707,9 +725,15 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_2500MBPS:
 			bandwidth = nports * 2500;
 			break;
+		case AD_LINK_SPEED_5000MBPS:
+			bandwidth = nports * 5000;
+			break;
 		case AD_LINK_SPEED_10000MBPS:
 			bandwidth = nports * 10000;
 			break;
+		case AD_LINK_SPEED_14000MBPS:
+			bandwidth = nports * 14000;
+			break;
 		case AD_LINK_SPEED_20000MBPS:
 			bandwidth = nports * 20000;
 			break;
@@ -719,6 +743,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_40000MBPS:
 			bandwidth = nports * 40000;
 			break;
+		case AD_LINK_SPEED_50000MBPS:
+			bandwidth = nports * 50000;
+			break;
 		case AD_LINK_SPEED_56000MBPS:
 			bandwidth = nports * 56000;
 			break;

drivers/net/bonding/bond_main.c

@@ -4192,7 +4192,6 @@ static void bond_destructor(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
-	free_netdev(bond_dev);
 }
 
 void bond_setup(struct net_device *bond_dev)
@@ -4212,7 +4211,8 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->netdev_ops = &bond_netdev_ops;
 	bond_dev->ethtool_ops = &bond_ethtool_ops;
 
-	bond_dev->destructor = bond_destructor;
+	bond_dev->needs_free_netdev = true;
+	bond_dev->priv_destructor = bond_destructor;
 
 	SET_NETDEV_DEVTYPE(bond_dev, &bond_type);
 
@@ -4736,7 +4736,7 @@ int bond_create(struct net *net, const char *name)
 
 	rtnl_unlock();
 	if (res < 0)
-		bond_destructor(bond_dev);
+		free_netdev(bond_dev);
 	return res;
 }
 

drivers/net/caif/caif_hsi.c

@@ -1121,7 +1121,7 @@ static void cfhsi_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	dev->netdev_ops = &cfhsi_netdevops;
 	for (i = 0; i < CFHSI_PRIO_LAST; ++i)
 		skb_queue_head_init(&cfhsi->qhead[i]);

drivers/net/caif/caif_serial.c

@@ -428,7 +428,7 @@ static void caifdev_setup(struct net_device *dev)
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->mtu = CAIF_MAX_MTU;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&serdev->head);
 	serdev->common.link_select = CAIF_LINK_LOW_LATENCY;
 	serdev->common.use_frag = true;

drivers/net/caif/caif_spi.c

@@ -712,7 +712,7 @@ static void cfspi_setup(struct net_device *dev)
 	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->destructor = free_netdev;
+	dev->needs_free_netdev = true;
 	skb_queue_head_init(&cfspi->qhead);
 	skb_queue_head_init(&cfspi->chead);
 	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;

drivers/net/caif/caif_virtio.c

@@ -617,7 +617,7 @@ static void cfv_netdev_setup(struct net_device *netdev)
 	netdev->tx_queue_len = 100;
 	netdev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	netdev->mtu = CFV_DEF_MTU_SIZE;
-	netdev->destructor = free_netdev;
+	netdev->needs_free_netdev = true;
 }
 
 /* Create debugfs counters for the device */

drivers/net/can/dev.c

@@ -391,6 +391,9 @@ void can_change_state(struct net_device *dev, struct can_frame *cf,
 	can_update_state_error_stats(dev, new_state);
 	priv->state = new_state;
 
+	if (!cf)
+		return;
+
 	if (unlikely(new_state == CAN_STATE_BUS_OFF)) {
 		cf->can_id |= CAN_ERR_BUSOFF;
 		return;

drivers/net/can/peak_canfd/peak_canfd.c

@@ -489,7 +489,7 @@ int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv,
 				struct pucan_rx_msg *msg_list, int msg_count)
 {
 	void *msg_ptr = msg_list;
-	int i, msg_size;
+	int i, msg_size = 0;
 
 	for (i = 0; i < msg_count; i++) {
 		msg_size = peak_canfd_handle_msg(priv, msg_ptr);

drivers/net/can/slcan.c

@@ -417,7 +417,7 @@ static int slc_open(struct net_device *dev)
 static void slc_free_netdev(struct net_device *dev)
 {
 	int i = dev->base_addr;
-	free_netdev(dev);
+
 	slcan_devs[i] = NULL;
 }
 
@@ -436,7 +436,8 @@ static const struct net_device_ops slc_netdev_ops = {
 static void slc_setup(struct net_device *dev)
 {
 	dev->netdev_ops		= &slc_netdev_ops;
-	dev->destructor		= slc_free_netdev;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= slc_free_netdev;
 
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
@@ -761,8 +762,6 @@ static void __exit slcan_exit(void)
 		if (sl->tty) {
 			printk(KERN_ERR "%s: tty discipline still running\n",
 			       dev->name);
-			/* Intentionally leak the control block. */
-			dev->destructor = NULL;
 		}
 
 		unregister_netdev(dev);

drivers/net/can/usb/gs_usb.c

@@ -265,6 +265,8 @@ static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev)
 			     sizeof(*dm),
 			     1000);
 
+	kfree(dm);
+
 	return rc;
 }
 

drivers/net/can/usb/peak_usb/pcan_usb_core.c

@@ -908,8 +908,6 @@ static int peak_usb_probe(struct usb_interface *intf,
 	const struct peak_usb_adapter *peak_usb_adapter = NULL;
 	int i, err = -ENOMEM;
 
-	usb_dev = interface_to_usbdev(intf);
-
 	/* get corresponding PCAN-USB adapter */
 	for (i = 0; i < ARRAY_SIZE(peak_usb_adapters_list); i++)
 		if (peak_usb_adapters_list[i]->device_id == usb_id_product) {
@@ -920,7 +918,7 @@ static int peak_usb_probe(struct usb_interface *intf,
 	if (!peak_usb_adapter) {
 		/* should never come except device_id bad usage in this file */
 		pr_err("%s: didn't find device id. 0x%x in devices list\n",
-			PCAN_USB_DRIVER_NAME, usb_dev->descriptor.idProduct);
+			PCAN_USB_DRIVER_NAME, usb_id_product);
 		return -ENODEV;
 	}
 

drivers/net/can/vcan.c

@@ -152,7 +152,7 @@ static const struct net_device_ops vcan_netdev_ops = {
 static void vcan_setup(struct net_device *dev)
 {
 	dev->type		= ARPHRD_CAN;
-	dev->mtu		= CAN_MTU;
+	dev->mtu		= CANFD_MTU;
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 0;
@@ -163,7 +163,7 @@ static void vcan_setup(struct net_device *dev)
 		dev->flags |= IFF_ECHO;
 
 	dev->netdev_ops		= &vcan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 static struct rtnl_link_ops vcan_link_ops __read_mostly = {

drivers/net/can/vxcan.c

@@ -150,13 +150,13 @@ static const struct net_device_ops vxcan_netdev_ops = {
 static void vxcan_setup(struct net_device *dev)
 {
 	dev->type		= ARPHRD_CAN;
-	dev->mtu		= CAN_MTU;
+	dev->mtu		= CANFD_MTU;
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
 	dev->tx_queue_len	= 0;
 	dev->flags		= (IFF_NOARP|IFF_ECHO);
 	dev->netdev_ops		= &vxcan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->needs_free_netdev	= true;
 }
 
 /* forward declaration for rtnl_create_link() */

drivers/net/dummy.c

@@ -328,7 +328,6 @@ static void dummy_free_netdev(struct net_device *dev)
 	struct dummy_priv *priv = netdev_priv(dev);
 
 	kfree(priv->vfinfo);
-	free_netdev(dev);
 }
 
 static void dummy_setup(struct net_device *dev)
@@ -338,7 +337,8 @@ static void dummy_setup(struct net_device *dev)
 	/* Initialize the device structure. */
 	dev->netdev_ops = &dummy_netdev_ops;
 	dev->ethtool_ops = &dummy_ethtool_ops;
-	dev->destructor = dummy_free_netdev;
+	dev->needs_free_netdev = true;
+	dev->priv_destructor = dummy_free_netdev;
 
 	/* Fill in device structure with ethernet-generic values. */
 	dev->flags |= IFF_NOARP;

drivers/net/ethernet/amazon/ena/ena_com.c

@@ -61,6 +61,8 @@
 
 #define ENA_MMIO_READ_TIMEOUT 0xFFFFFFFF
 
+#define ENA_REGS_ADMIN_INTR_MASK 1
+
 /*****************************************************************************/
 /*****************************************************************************/
 /*****************************************************************************/
@@ -232,11 +234,9 @@ static struct ena_comp_ctx *__ena_com_submit_admin_cmd(struct ena_com_admin_queu
 	tail_masked = admin_queue->sq.tail & queue_size_mask;
 
 	/* In case of queue FULL */
-	cnt = admin_queue->sq.tail - admin_queue->sq.head;
+	cnt = atomic_read(&admin_queue->outstanding_cmds);
 	if (cnt >= admin_queue->q_depth) {
-		pr_debug("admin queue is FULL (tail %d head %d depth: %d)\n",
-			 admin_queue->sq.tail, admin_queue->sq.head,
-			 admin_queue->q_depth);
+		pr_debug("admin queue is full.\n");
 		admin_queue->stats.out_of_space++;
 		return ERR_PTR(-ENOSPC);
 	}
@@ -508,15 +508,20 @@ static int ena_com_comp_status_to_errno(u8 comp_status)
 static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_ctx,
 						     struct ena_com_admin_queue *admin_queue)
 {
-	unsigned long flags;
-	u32 start_time;
+	unsigned long flags, timeout;
 	int ret;
 
-	start_time = ((u32)jiffies_to_usecs(jiffies));
+	timeout = jiffies + ADMIN_CMD_TIMEOUT_US;
 
-	while (comp_ctx->status == ENA_CMD_SUBMITTED) {
-		if ((((u32)jiffies_to_usecs(jiffies)) - start_time) >
-		    ADMIN_CMD_TIMEOUT_US) {
+	while (1) {
+		spin_lock_irqsave(&admin_queue->q_lock, flags);
+		ena_com_handle_admin_completion(admin_queue);
+		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
+
+		if (comp_ctx->status != ENA_CMD_SUBMITTED)
+			break;
+
+		if (time_is_before_jiffies(timeout)) {
 			pr_err("Wait for completion (polling) timeout\n");
 			/* ENA didn't have any completion */
 			spin_lock_irqsave(&admin_queue->q_lock, flags);
@@ -528,10 +533,6 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c
 			goto err;
 		}
 
-		spin_lock_irqsave(&admin_queue->q_lock, flags);
-		ena_com_handle_admin_completion(admin_queue);
-		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
-
 		msleep(100);
 	}
 
@@ -1455,6 +1456,12 @@ void ena_com_admin_destroy(struct ena_com_dev *ena_dev)
 
 void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling)
 {
+	u32 mask_value = 0;
+
+	if (polling)
+		mask_value = ENA_REGS_ADMIN_INTR_MASK;
+
+	writel(mask_value, ena_dev->reg_bar + ENA_REGS_INTR_MASK_OFF);
 	ena_dev->admin_queue.polling = polling;
 }
 

drivers/net/ethernet/amazon/ena/ena_ethtool.c

@@ -80,7 +80,6 @@ static const struct ena_stats ena_stats_tx_strings[] = {
 	ENA_STAT_TX_ENTRY(tx_poll),
 	ENA_STAT_TX_ENTRY(doorbells),
 	ENA_STAT_TX_ENTRY(prepare_ctx_err),
-	ENA_STAT_TX_ENTRY(missing_tx_comp),
 	ENA_STAT_TX_ENTRY(bad_req_id),
 };
 
@@ -94,6 +93,7 @@ static const struct ena_stats ena_stats_rx_strings[] = {
 	ENA_STAT_RX_ENTRY(dma_mapping_err),
 	ENA_STAT_RX_ENTRY(bad_desc_num),
 	ENA_STAT_RX_ENTRY(rx_copybreak_pkt),
+	ENA_STAT_RX_ENTRY(empty_rx_ring),
 };
 
 static const struct ena_stats ena_stats_ena_com_strings[] = {

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -190,6 +190,7 @@ static void ena_init_io_rings(struct ena_adapter *adapter)
 		rxr->sgl_size = adapter->max_rx_sgl_size;
 		rxr->smoothed_interval =
 			ena_com_get_nonadaptive_moderation_interval_rx(ena_dev);
+		rxr->empty_rx_queue = 0;
 	}
 }
 
@@ -1078,6 +1079,26 @@ inline void ena_adjust_intr_moderation(struct ena_ring *rx_ring,
 	rx_ring->per_napi_bytes = 0;
 }
 
+static inline void ena_unmask_interrupt(struct ena_ring *tx_ring,
+					struct ena_ring *rx_ring)
+{
+	struct ena_eth_io_intr_reg intr_reg;
+
+	/* Update intr register: rx intr delay,
+	 * tx intr delay and interrupt unmask
+	 */
+	ena_com_update_intr_reg(&intr_reg,
+				rx_ring->smoothed_interval,
+				tx_ring->smoothed_interval,
+				true);
+
+	/* It is a shared MSI-X.
+	 * Tx and Rx CQ have pointer to it.
+	 * So we use one of them to reach the intr reg
+	 */
+	ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg);
+}
+
 static inline void ena_update_ring_numa_node(struct ena_ring *tx_ring,
 					     struct ena_ring *rx_ring)
 {
@@ -1108,7 +1129,6 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 {
 	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
 	struct ena_ring *tx_ring, *rx_ring;
-	struct ena_eth_io_intr_reg intr_reg;
 
 	u32 tx_work_done;
 	u32 rx_work_done;
@@ -1149,22 +1169,9 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
 			if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
 				ena_adjust_intr_moderation(rx_ring, tx_ring);
 
-			/* Update intr register: rx intr delay,
-			 * tx intr delay and interrupt unmask
-			 */
-			ena_com_update_intr_reg(&intr_reg,
-						rx_ring->smoothed_interval,
-						tx_ring->smoothed_interval,
-						true);
-
-			/* It is a shared MSI-X.
-			 * Tx and Rx CQ have pointer to it.
-			 * So we use one of them to reach the intr reg
-			 */
-			ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg);
+			ena_unmask_interrupt(tx_ring, rx_ring);
 		}
 
-
 		ena_update_ring_numa_node(tx_ring, rx_ring);
 
 		ret = rx_work_done;
@@ -1485,6 +1492,11 @@ static int ena_up_complete(struct ena_adapter *adapter)
 
 	ena_napi_enable_all(adapter);
 
+	/* Enable completion queues interrupt */
+	for (i = 0; i < adapter->num_queues; i++)
+		ena_unmask_interrupt(&adapter->tx_ring[i],
+				     &adapter->rx_ring[i]);
+
 	/* schedule napi in case we had pending packets
 	 * from the last time we disable napi
 	 */
@@ -1532,6 +1544,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid)
 			  "Failed to get TX queue handlers. TX queue num %d rc: %d\n",
 			  qid, rc);
 		ena_com_destroy_io_queue(ena_dev, ena_qid);
+		return rc;
 	}
 
 	ena_com_update_numa_node(tx_ring->ena_com_io_cq, ctx.numa_node);
@@ -1596,6 +1609,7 @@ static int ena_create_io_rx_queue(struct ena_adapter *adapter, int qid)
 			  "Failed to get RX queue handlers. RX queue num %d rc: %d\n",
 			  qid, rc);
 		ena_com_destroy_io_queue(ena_dev, ena_qid);
+		return rc;
 	}
 
 	ena_com_update_numa_node(rx_ring->ena_com_io_cq, ctx.numa_node);
@@ -1981,6 +1995,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_info->tx_descs = nb_hw_desc;
 	tx_info->last_jiffies = jiffies;
+	tx_info->print_once = 0;
 
 	tx_ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use,
 		tx_ring->ring_size);
@@ -2550,13 +2565,44 @@ err:
 		"Reset attempt failed. Can not reset the device\n");
 }
 
-static void check_for_missing_tx_completions(struct ena_adapter *adapter)
+static int check_missing_comp_in_queue(struct ena_adapter *adapter,
+				       struct ena_ring *tx_ring)
 {
 	struct ena_tx_buffer *tx_buf;
 	unsigned long last_jiffies;
+	u32 missed_tx = 0;
+	int i;
+
+	for (i = 0; i < tx_ring->ring_size; i++) {
+		tx_buf = &tx_ring->tx_buffer_info[i];
+		last_jiffies = tx_buf->last_jiffies;
+		if (unlikely(last_jiffies &&
+			     time_is_before_jiffies(last_jiffies + TX_TIMEOUT))) {
+			if (!tx_buf->print_once)
+				netif_notice(adapter, tx_err, adapter->netdev,
+					     "Found a Tx that wasn't completed on time, qid %d, index %d.\n",
+					     tx_ring->qid, i);
+
+			tx_buf->print_once = 1;
+			missed_tx++;
+
+			if (unlikely(missed_tx > MAX_NUM_OF_TIMEOUTED_PACKETS)) {
+				netif_err(adapter, tx_err, adapter->netdev,
+					  "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
+					  missed_tx, MAX_NUM_OF_TIMEOUTED_PACKETS);
+				set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+				return -EIO;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void check_for_missing_tx_completions(struct ena_adapter *adapter)
+{
 	struct ena_ring *tx_ring;
-	int i, j, budget;
-	u32 missed_tx;
+	int i, budget, rc;
 
 	/* Make sure the driver doesn't turn the device in other process */
 	smp_rmb();
@@ -2572,31 +2618,9 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter)
 	for (i = adapter->last_monitored_tx_qid; i < adapter->num_queues; i++) {
 		tx_ring = &adapter->tx_ring[i];
 
-		for (j = 0; j < tx_ring->ring_size; j++) {
-			tx_buf = &tx_ring->tx_buffer_info[j];
-			last_jiffies = tx_buf->last_jiffies;
-			if (unlikely(last_jiffies && time_is_before_jiffies(last_jiffies + TX_TIMEOUT))) {
-				netif_notice(adapter, tx_err, adapter->netdev,
-					     "Found a Tx that wasn't completed on time, qid %d, index %d.\n",
-					     tx_ring->qid, j);
-
-				u64_stats_update_begin(&tx_ring->syncp);
-				missed_tx = tx_ring->tx_stats.missing_tx_comp++;
-				u64_stats_update_end(&tx_ring->syncp);
-
-				/* Clear last jiffies so the lost buffer won't
-				 * be counted twice.
-				 */
-				tx_buf->last_jiffies = 0;
-
-				if (unlikely(missed_tx > MAX_NUM_OF_TIMEOUTED_PACKETS)) {
-					netif_err(adapter, tx_err, adapter->netdev,
-						  "The number of lost tx completion is above the threshold (%d > %d). Reset the device\n",
-						  missed_tx, MAX_NUM_OF_TIMEOUTED_PACKETS);
-					set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
-				}
-			}
-		}
+		rc = check_missing_comp_in_queue(adapter, tx_ring);
+		if (unlikely(rc))
+			return;
 
 		budget--;
 		if (!budget)
@@ -2606,6 +2630,58 @@ static void check_for_missing_tx_completions(struct ena_adapter *adapter)
 	adapter->last_monitored_tx_qid = i % adapter->num_queues;
 }
 
+/* trigger napi schedule after 2 consecutive detections */
+#define EMPTY_RX_REFILL 2
+/* For the rare case where the device runs out of Rx descriptors and the
+ * napi handler failed to refill new Rx descriptors (due to a lack of memory
+ * for example).
+ * This case will lead to a deadlock:
+ * The device won't send interrupts since all the new Rx packets will be dropped
+ * The napi handler won't allocate new Rx descriptors so the device will be
+ * able to send new packets.
+ *
+ * This scenario can happen when the kernel's vm.min_free_kbytes is too small.
+ * It is recommended to have at least 512MB, with a minimum of 128MB for
+ * constrained environment).
+ *
+ * When such a situation is detected - Reschedule napi
+ */
+static void check_for_empty_rx_ring(struct ena_adapter *adapter)
+{
+	struct ena_ring *rx_ring;
+	int i, refill_required;
+
+	if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags))
+		return;
+
+	if (test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
+		return;
+
+	for (i = 0; i < adapter->num_queues; i++) {
+		rx_ring = &adapter->rx_ring[i];
+
+		refill_required =
+			ena_com_sq_empty_space(rx_ring->ena_com_io_sq);
+		if (unlikely(refill_required == (rx_ring->ring_size - 1))) {
+			rx_ring->empty_rx_queue++;
+
+			if (rx_ring->empty_rx_queue >= EMPTY_RX_REFILL) {
+				u64_stats_update_begin(&rx_ring->syncp);
+				rx_ring->rx_stats.empty_rx_ring++;
+				u64_stats_update_end(&rx_ring->syncp);
+
+				netif_err(adapter, drv, adapter->netdev,
+					  "trigger refill for ring %d\n", i);
+
+				napi_schedule(rx_ring->napi);
+				rx_ring->empty_rx_queue = 0;
+			}
+		} else {
+			rx_ring->empty_rx_queue = 0;
+		}
+	}
+}
+
 /* Check for keep alive expiration */
 static void check_for_missing_keep_alive(struct ena_adapter *adapter)
 {
@@ -2660,6 +2736,8 @@ static void ena_timer_service(unsigned long data)
 
 	check_for_missing_tx_completions(adapter);
 
+	check_for_empty_rx_ring(adapter);
+
 	if (debug_area)
 		ena_dump_stats_to_buf(adapter, debug_area);
 
@@ -2840,6 +2918,11 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev)
 {
 	int release_bars;
 
+	if (ena_dev->mem_bar)
+		devm_iounmap(&pdev->dev, ena_dev->mem_bar);
+
+	devm_iounmap(&pdev->dev, ena_dev->reg_bar);
+
 	release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK;
 	pci_release_selected_regions(pdev, release_bars);
 }
@@ -2927,8 +3010,9 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free_ena_dev;
 	}
 
-	ena_dev->reg_bar = ioremap(pci_resource_start(pdev, ENA_REG_BAR),
-				   pci_resource_len(pdev, ENA_REG_BAR));
+	ena_dev->reg_bar = devm_ioremap(&pdev->dev,
+					pci_resource_start(pdev, ENA_REG_BAR),
+					pci_resource_len(pdev, ENA_REG_BAR));
 	if (!ena_dev->reg_bar) {
 		dev_err(&pdev->dev, "failed to remap regs bar\n");
 		rc = -EFAULT;
@@ -2948,8 +3032,9 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ena_set_push_mode(pdev, ena_dev, &get_feat_ctx);
 
 	if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) {
-		ena_dev->mem_bar = ioremap_wc(pci_resource_start(pdev, ENA_MEM_BAR),
-					      pci_resource_len(pdev, ENA_MEM_BAR));
+		ena_dev->mem_bar = devm_ioremap_wc(&pdev->dev,
+						   pci_resource_start(pdev, ENA_MEM_BAR),
+						   pci_resource_len(pdev, ENA_MEM_BAR));
 		if (!ena_dev->mem_bar) {
 			rc = -EFAULT;
 			goto err_device_destroy;