Merge tag 'net-6.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski: "Including fixes from BPF, netfilter, bluetooth and CAN. Current release - regressions: - eth: r8169: multiple fixes for PCIe ASPM-related problems - vrf: fix RCU lockdep splat in output path Previous releases - regressions: - gso: fall back to SW segmenting with GSO_UDP_L4 dodgy bit set - dsa: mv88e6xxx: do a final check before timing out when polling - nf_tables: fix sleep in atomic in nft_chain_validate Previous releases - always broken: - sched: fix undoing tcf_bind_filter() in multiple classifiers - bpf, arm64: fix BTI type used for freplace attached functions - can: gs_usb: fix time stamp counter initialization - nft_set_pipapo: fix improper element removal (leading to UAF) Misc: - net: support STP on bridge in non-root netns, STP prevents packet loops so not supporting it results in freezing systems of unsuspecting users, and in turn very upset noises being made - fix kdoc warnings - annotate various bits of TCP state to prevent data races" * tag 'net-6.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (95 commits) net: phy: prevent stale pointer dereference in phy_init() tcp: annotate data-races around fastopenq.max_qlen tcp: annotate data-races around icsk->icsk_user_timeout tcp: annotate data-races around tp->notsent_lowat tcp: annotate data-races around rskq_defer_accept tcp: annotate data-races around tp->linger2 tcp: annotate data-races around icsk->icsk_syn_retries tcp: annotate data-races around tp->keepalive_probes tcp: annotate data-races around tp->keepalive_intvl tcp: annotate data-races around tp->keepalive_time tcp: annotate data-races around tp->tsoffset tcp: annotate data-races around tp->tcp_tx_delay Bluetooth: MGMT: Use correct address for memcpy() Bluetooth: btusb: Fix bluetooth on Intel Macbook 2014 Bluetooth: SCO: fix sco_conn related locking and validity issues Bluetooth: hci_conn: return ERR_PTR instead of NULL when there is no link Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_remove_adv_monitor() Bluetooth: coredump: fix building with coredump disabled Bluetooth: ISO: fix iso_conn related locking and validity issues Bluetooth: hci_event: call disconnect callback before deleting conn ...
2026-03-06 15:25:10 -08:00 · 2023-07-20 14:46:39 -07:00
parent e599e16c16 75d42b351f
commit 57f1f9dd3a
84 changed files with 1155 additions and 716 deletions
--- a/.mailmap
+++ b/.mailmap
@@ -241,6 +241,7 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
 Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
+John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com>
 John Keeping <john@keeping.me.uk> <john@metanate.com>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
@@ -454,6 +455,8 @@ Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
 Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
 Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
+Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
+Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com>
 Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
 Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
 Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 	 *
 	 */

-	emit_bti(A64_BTI_C, ctx);
+	/* bpf function may be invoked by 3 instruction types:
+	 * 1. bl, attached via freplace to bpf prog via short jump
+	 * 2. br, attached via freplace to bpf prog via long jump
+	 * 3. blr, working as a function pointer, used by emit_call.
+	 * So BTI_JC should used here to support both br and blr.
+	 */
+	emit_bti(A64_BTI_JC, ctx);

 	emit(A64_MOV(1, A64_R(9), A64_LR), ctx);
 	emit(A64_NOP, ctx);
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4104,6 +4104,7 @@ static int btusb_probe(struct usb_interface *intf,
 	BT_DBG("intf %p id %p", intf, id);

 	if ((id->driver_info & BTUSB_IFNUM_2) &&
+	    (intf->cur_altsetting->desc.bInterfaceNumber != 0) &&
 	    (intf->cur_altsetting->desc.bInterfaceNumber != 2))
 		return -ENODEV;

--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -227,6 +227,8 @@ static int
 __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv,
 			  const u8 mode_req, bool nowait)
 {
+	const struct can_bittiming *bt = &priv->can.bittiming;
+	unsigned long timeout_us = MCP251XFD_POLL_TIMEOUT_US;
 	u32 con = 0, con_reqop, osc = 0;
 	u8 mode;
 	int err;
@@ -246,12 +248,16 @@ __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv,
 	if (mode_req == MCP251XFD_REG_CON_MODE_SLEEP || nowait)
 		return 0;

+	if (bt->bitrate)
+		timeout_us = max_t(unsigned long, timeout_us,
+				   MCP251XFD_FRAME_LEN_MAX_BITS * USEC_PER_SEC /
+				   bt->bitrate);
+
 	err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_CON, con,
 				       !mcp251xfd_reg_invalid(con) &&
 				       FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK,
 						 con) == mode_req,
-				       MCP251XFD_POLL_SLEEP_US,
-				       MCP251XFD_POLL_TIMEOUT_US);
+				       MCP251XFD_POLL_SLEEP_US, timeout_us);
 	if (err != -ETIMEDOUT && err != -EBADMSG)
 		return err;

--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -387,6 +387,7 @@ static_assert(MCP251XFD_TIMESTAMP_WORK_DELAY_SEC <
 #define MCP251XFD_OSC_STAB_TIMEOUT_US (10 * MCP251XFD_OSC_STAB_SLEEP_US)
 #define MCP251XFD_POLL_SLEEP_US (10)
 #define MCP251XFD_POLL_TIMEOUT_US (USEC_PER_MSEC)
+#define MCP251XFD_FRAME_LEN_MAX_BITS (736)

 /* Misc */
 #define MCP251XFD_NAPI_WEIGHT 32
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -303,12 +303,6 @@ struct gs_can {
 	struct can_bittiming_const bt_const, data_bt_const;
 	unsigned int channel;	/* channel number */

-	/* time counter for hardware timestamps */
-	struct cyclecounter cc;
-	struct timecounter tc;
-	spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */
-	struct delayed_work timestamp;
-
 	u32 feature;
 	unsigned int hf_size_tx;

@@ -325,6 +319,13 @@ struct gs_usb {
 	struct gs_can *canch[GS_MAX_INTF];
 	struct usb_anchor rx_submitted;
 	struct usb_device *udev;
+
+	/* time counter for hardware timestamps */
+	struct cyclecounter cc;
+	struct timecounter tc;
+	spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */
+	struct delayed_work timestamp;
+
 	unsigned int hf_size_rx;
 	u8 active_channels;
 };
@@ -388,15 +389,15 @@ static int gs_cmd_reset(struct gs_can *dev)
 				    GFP_KERNEL);
 }

-static inline int gs_usb_get_timestamp(const struct gs_can *dev,
+static inline int gs_usb_get_timestamp(const struct gs_usb *parent,
 				       u32 *timestamp_p)
 {
 	__le32 timestamp;
 	int rc;

-	rc = usb_control_msg_recv(dev->udev, 0, GS_USB_BREQ_TIMESTAMP,
+	rc = usb_control_msg_recv(parent->udev, 0, GS_USB_BREQ_TIMESTAMP,
 				  USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE,
-				  dev->channel, 0,
+				  0, 0,
 				  &timestamp, sizeof(timestamp),
 				  USB_CTRL_GET_TIMEOUT,
 				  GFP_KERNEL);
@@ -410,20 +411,20 @@ static inline int gs_usb_get_timestamp(const struct gs_can *dev,

 static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev->tc_lock)
 {
-	struct gs_can *dev = container_of(cc, struct gs_can, cc);
+	struct gs_usb *parent = container_of(cc, struct gs_usb, cc);
 	u32 timestamp = 0;
 	int err;

-	lockdep_assert_held(&dev->tc_lock);
+	lockdep_assert_held(&parent->tc_lock);

 	/* drop lock for synchronous USB transfer */
-	spin_unlock_bh(&dev->tc_lock);
-	err = gs_usb_get_timestamp(dev, &timestamp);
-	spin_lock_bh(&dev->tc_lock);
+	spin_unlock_bh(&parent->tc_lock);
+	err = gs_usb_get_timestamp(parent, &timestamp);
+	spin_lock_bh(&parent->tc_lock);
 	if (err)
-		netdev_err(dev->netdev,
-			   "Error %d while reading timestamp. HW timestamps may be inaccurate.",
-			   err);
+		dev_err(&parent->udev->dev,
+			"Error %d while reading timestamp. HW timestamps may be inaccurate.",
+			err);

 	return timestamp;
 }
@@ -431,14 +432,14 @@ static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev
 static void gs_usb_timestamp_work(struct work_struct *work)
 {
 	struct delayed_work *delayed_work = to_delayed_work(work);
-	struct gs_can *dev;
+	struct gs_usb *parent;

-	dev = container_of(delayed_work, struct gs_can, timestamp);
-	spin_lock_bh(&dev->tc_lock);
-	timecounter_read(&dev->tc);
-	spin_unlock_bh(&dev->tc_lock);
+	parent = container_of(delayed_work, struct gs_usb, timestamp);
+	spin_lock_bh(&parent->tc_lock);
+	timecounter_read(&parent->tc);
+	spin_unlock_bh(&parent->tc_lock);

-	schedule_delayed_work(&dev->timestamp,
+	schedule_delayed_work(&parent->timestamp,
 			      GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ);
 }

@@ -446,37 +447,38 @@ static void gs_usb_skb_set_timestamp(struct gs_can *dev,
 				     struct sk_buff *skb, u32 timestamp)
 {
 	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
+	struct gs_usb *parent = dev->parent;
 	u64 ns;

-	spin_lock_bh(&dev->tc_lock);
-	ns = timecounter_cyc2time(&dev->tc, timestamp);
-	spin_unlock_bh(&dev->tc_lock);
+	spin_lock_bh(&parent->tc_lock);
+	ns = timecounter_cyc2time(&parent->tc, timestamp);
+	spin_unlock_bh(&parent->tc_lock);

 	hwtstamps->hwtstamp = ns_to_ktime(ns);
 }

-static void gs_usb_timestamp_init(struct gs_can *dev)
+static void gs_usb_timestamp_init(struct gs_usb *parent)
 {
-	struct cyclecounter *cc = &dev->cc;
+	struct cyclecounter *cc = &parent->cc;

 	cc->read = gs_usb_timestamp_read;
 	cc->mask = CYCLECOUNTER_MASK(32);
 	cc->shift = 32 - bits_per(NSEC_PER_SEC / GS_USB_TIMESTAMP_TIMER_HZ);
 	cc->mult = clocksource_hz2mult(GS_USB_TIMESTAMP_TIMER_HZ, cc->shift);

-	spin_lock_init(&dev->tc_lock);
-	spin_lock_bh(&dev->tc_lock);
-	timecounter_init(&dev->tc, &dev->cc, ktime_get_real_ns());
-	spin_unlock_bh(&dev->tc_lock);
+	spin_lock_init(&parent->tc_lock);
+	spin_lock_bh(&parent->tc_lock);
+	timecounter_init(&parent->tc, &parent->cc, ktime_get_real_ns());
+	spin_unlock_bh(&parent->tc_lock);

-	INIT_DELAYED_WORK(&dev->timestamp, gs_usb_timestamp_work);
-	schedule_delayed_work(&dev->timestamp,
+	INIT_DELAYED_WORK(&parent->timestamp, gs_usb_timestamp_work);
+	schedule_delayed_work(&parent->timestamp,
 			      GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ);
 }

-static void gs_usb_timestamp_stop(struct gs_can *dev)
+static void gs_usb_timestamp_stop(struct gs_usb *parent)
 {
-	cancel_delayed_work_sync(&dev->timestamp);
+	cancel_delayed_work_sync(&parent->timestamp);
 }

 static void gs_update_state(struct gs_can *dev, struct can_frame *cf)
@@ -560,6 +562,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb)
 	if (!netif_device_present(netdev))
 		return;

+	if (!netif_running(netdev))
+		goto resubmit_urb;
+
 	if (hf->echo_id == -1) { /* normal rx */
 		if (hf->flags & GS_CAN_FLAG_FD) {
 			skb = alloc_canfd_skb(dev->netdev, &cfd);
@@ -833,6 +838,7 @@ static int gs_can_open(struct net_device *netdev)
 		.mode = cpu_to_le32(GS_CAN_MODE_START),
 	};
 	struct gs_host_frame *hf;
+	struct urb *urb = NULL;
 	u32 ctrlmode;
 	u32 flags = 0;
 	int rc, i;
@@ -855,14 +861,18 @@ static int gs_can_open(struct net_device *netdev)
 	}

 	if (!parent->active_channels) {
+		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			gs_usb_timestamp_init(parent);
+
 		for (i = 0; i < GS_MAX_RX_URBS; i++) {
-			struct urb *urb;
 			u8 *buf;

 			/* alloc rx urb */
 			urb = usb_alloc_urb(0, GFP_KERNEL);
-			if (!urb)
-				return -ENOMEM;
+			if (!urb) {
+				rc = -ENOMEM;
+				goto out_usb_kill_anchored_urbs;
+			}

 			/* alloc rx buffer */
 			buf = kmalloc(dev->parent->hf_size_rx,
@@ -870,8 +880,8 @@ static int gs_can_open(struct net_device *netdev)
 			if (!buf) {
 				netdev_err(netdev,
 					   "No memory left for USB buffer\n");
-				usb_free_urb(urb);
-				return -ENOMEM;
+				rc = -ENOMEM;
+				goto out_usb_free_urb;
 			}

 			/* fill, anchor, and submit rx urb */
@@ -894,9 +904,7 @@ static int gs_can_open(struct net_device *netdev)
 				netdev_err(netdev,
 					   "usb_submit failed (err=%d)\n", rc);

-				usb_unanchor_urb(urb);
-				usb_free_urb(urb);
-				break;
+				goto out_usb_unanchor_urb;
 			}

 			/* Drop reference,
@@ -926,13 +934,9 @@ static int gs_can_open(struct net_device *netdev)
 		flags |= GS_CAN_MODE_FD;

 	/* if hardware supports timestamps, enable it */
-	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) {
+	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
 		flags |= GS_CAN_MODE_HW_TIMESTAMP;

-		/* start polling timestamp */
-		gs_usb_timestamp_init(dev);
-	}
-
 	/* finally start device */
 	dev->can.state = CAN_STATE_ERROR_ACTIVE;
 	dm.flags = cpu_to_le32(flags);
@@ -942,10 +946,9 @@ static int gs_can_open(struct net_device *netdev)
 				  GFP_KERNEL);
 	if (rc) {
 		netdev_err(netdev, "Couldn't start device (err=%d)\n", rc);
-		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
-			gs_usb_timestamp_stop(dev);
 		dev->can.state = CAN_STATE_STOPPED;
-		return rc;
+
+		goto out_usb_kill_anchored_urbs;
 	}

 	parent->active_channels++;
@@ -953,6 +956,22 @@ static int gs_can_open(struct net_device *netdev)
 		netif_start_queue(netdev);

 	return 0;
+
+out_usb_unanchor_urb:
+	usb_unanchor_urb(urb);
+out_usb_free_urb:
+	usb_free_urb(urb);
+out_usb_kill_anchored_urbs:
+	if (!parent->active_channels) {
+		usb_kill_anchored_urbs(&dev->tx_submitted);
+
+		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			gs_usb_timestamp_stop(parent);
+	}
+
+	close_candev(netdev);
+
+	return rc;
 }

 static int gs_usb_get_state(const struct net_device *netdev,
@@ -998,14 +1017,13 @@ static int gs_can_close(struct net_device *netdev)

 	netif_stop_queue(netdev);

-	/* stop polling timestamp */
-	if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
-		gs_usb_timestamp_stop(dev);
-
 	/* Stop polling */
 	parent->active_channels--;
 	if (!parent->active_channels) {
 		usb_kill_anchored_urbs(&parent->rx_submitted);
+
+		if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP)
+			gs_usb_timestamp_stop(parent);
 	}

 	/* Stop sending URBs */
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -506,7 +506,13 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr,
 		(data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >>
 			shifts[STATIC_MAC_FWD_PORTS];
 	alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0;
-	data_hi >>= 1;
+
+	/* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and
+	 * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the
+	 * static MAC table compared to doing write.
+	 */
+	if (ksz_is_ksz87xx(dev))
+		data_hi >>= 1;
 	alu->is_static = true;
 	alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0;
 	alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >>
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -331,13 +331,13 @@ static const u32 ksz8795_masks[] = {
 	[STATIC_MAC_TABLE_VALID]	= BIT(21),
 	[STATIC_MAC_TABLE_USE_FID]	= BIT(23),
 	[STATIC_MAC_TABLE_FID]		= GENMASK(30, 24),
-	[STATIC_MAC_TABLE_OVERRIDE]	= BIT(26),
-	[STATIC_MAC_TABLE_FWD_PORTS]	= GENMASK(24, 20),
+	[STATIC_MAC_TABLE_OVERRIDE]	= BIT(22),
+	[STATIC_MAC_TABLE_FWD_PORTS]	= GENMASK(20, 16),
 	[DYNAMIC_MAC_TABLE_ENTRIES_H]	= GENMASK(6, 0),
-	[DYNAMIC_MAC_TABLE_MAC_EMPTY]	= BIT(8),
+	[DYNAMIC_MAC_TABLE_MAC_EMPTY]	= BIT(7),
 	[DYNAMIC_MAC_TABLE_NOT_READY]	= BIT(7),
 	[DYNAMIC_MAC_TABLE_ENTRIES]	= GENMASK(31, 29),
-	[DYNAMIC_MAC_TABLE_FID]		= GENMASK(26, 20),
+	[DYNAMIC_MAC_TABLE_FID]		= GENMASK(22, 16),
 	[DYNAMIC_MAC_TABLE_SRC_PORT]	= GENMASK(26, 24),
 	[DYNAMIC_MAC_TABLE_TIMESTAMP]	= GENMASK(28, 27),
 	[P_MII_TX_FLOW_CTRL]		= BIT(5),
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -601,6 +601,13 @@ static inline void ksz_regmap_unlock(void *__mtx)
 	mutex_unlock(mtx);
 }

+static inline bool ksz_is_ksz87xx(struct ksz_device *dev)
+{
+	return dev->chip_id == KSZ8795_CHIP_ID ||
+	       dev->chip_id == KSZ8794_CHIP_ID ||
+	       dev->chip_id == KSZ8765_CHIP_ID;
+}
+
 static inline bool ksz_is_ksz88x3(struct ksz_device *dev)
 {
 	return dev->chip_id == KSZ8830_CHIP_ID;
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -109,6 +109,13 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg,
 			usleep_range(1000, 2000);
 	}

+	err = mv88e6xxx_read(chip, addr, reg, &data);
+	if (err)
+		return err;
+
+	if ((data & mask) == val)
+		return 0;
+
 	dev_err(chip->dev, "Timeout while waiting for switch\n");
 	return -ETIMEDOUT;
 }
--- a/drivers/net/dsa/qca/ar9331.c
+++ b/drivers/net/dsa/qca/ar9331.c
@@ -1002,6 +1002,8 @@ static const struct regmap_config ar9331_mdio_regmap_config = {
 	.val_bits = 32,
 	.reg_stride = 4,
 	.max_register = AR9331_SW_REG_PAGE,
+	.use_single_read = true,
+	.use_single_write = true,

 	.ranges = ar9331_regmap_range,
 	.num_ranges = ARRAY_SIZE(ar9331_regmap_range),
@@ -1018,8 +1020,6 @@ static struct regmap_bus ar9331_sw_bus = {
 	.val_format_endian_default = REGMAP_ENDIAN_NATIVE,
 	.read = ar9331_mdio_read,
 	.write = ar9331_sw_bus_write,
-	.max_raw_read = 4,
-	.max_raw_write = 4,
 };

 static int ar9331_sw_probe(struct mdio_device *mdiodev)
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -512,11 +512,6 @@ bnad_debugfs_init(struct bnad *bnad)
 	if (!bnad->port_debugfs_root) {
 		bnad->port_debugfs_root =
 			debugfs_create_dir(name, bna_debugfs_root);
-		if (!bnad->port_debugfs_root) {
-			netdev_warn(bnad->netdev,
-				    "debugfs root dir creation failed\n");
-			return;
-		}

 		atomic_inc(&bna_debugfs_port_count);

--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -255,8 +255,10 @@ struct iavf_adapter {
 	struct workqueue_struct *wq;
 	struct work_struct reset_task;
 	struct work_struct adminq_task;
+	struct work_struct finish_config;
 	struct delayed_work client_task;
 	wait_queue_head_t down_waitqueue;
+	wait_queue_head_t reset_waitqueue;
 	wait_queue_head_t vc_waitqueue;
 	struct iavf_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -518,8 +520,9 @@ int iavf_up(struct iavf_adapter *adapter);
 void iavf_down(struct iavf_adapter *adapter);
 int iavf_process_config(struct iavf_adapter *adapter);
 int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter);
-void iavf_schedule_reset(struct iavf_adapter *adapter);
+void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags);
 void iavf_schedule_request_stats(struct iavf_adapter *adapter);
+void iavf_schedule_finish_config(struct iavf_adapter *adapter);
 void iavf_reset(struct iavf_adapter *adapter);
 void iavf_set_ethtool_ops(struct net_device *netdev);
 void iavf_update_stats(struct iavf_adapter *adapter);
@@ -582,4 +585,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter);
 void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter);
 struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 					const u8 *macaddr);
+int iavf_wait_for_reset(struct iavf_adapter *adapter);
 #endif /* _IAVF_H_ */
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -484,6 +484,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 orig_flags, new_flags, changed_flags;
+	int ret = 0;
 	u32 i;

 	orig_flags = READ_ONCE(adapter->flags);
@@ -531,12 +532,14 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
 	/* issue a reset to force legacy-rx change to take effect */
 	if (changed_flags & IAVF_FLAG_LEGACY_RX) {
 		if (netif_running(netdev)) {
-			adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-			queue_work(adapter->wq, &adapter->reset_task);
+			iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+			ret = iavf_wait_for_reset(adapter);
+			if (ret)
+				netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset");
 		}
 	}

-	return 0;
+	return ret;
 }

 /**
@@ -627,6 +630,7 @@ static int iavf_set_ringparam(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 new_rx_count, new_tx_count;
+	int ret = 0;

 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
@@ -671,11 +675,13 @@ static int iavf_set_ringparam(struct net_device *netdev,
 	}

 	if (netif_running(netdev)) {
-		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-		queue_work(adapter->wq, &adapter->reset_task);
+		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+		ret = iavf_wait_for_reset(adapter);
+		if (ret)
+			netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset");
 	}

-	return 0;
+	return ret;
 }

 /**
@@ -1830,7 +1836,7 @@ static int iavf_set_channels(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 num_req = ch->combined_count;
-	int i;
+	int ret = 0;

 	if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
 	    adapter->num_tc) {
@@ -1852,22 +1858,13 @@ static int iavf_set_channels(struct net_device *netdev,

 	adapter->num_req_queues = num_req;
 	adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
-	iavf_schedule_reset(adapter);
+	iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);

-	/* wait for the reset is done */
-	for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) {
-		msleep(IAVF_RESET_WAIT_MS);
-		if (adapter->flags & IAVF_FLAG_RESET_PENDING)
-			continue;
-		break;
-	}
-	if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) {
-		adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
-		adapter->num_active_queues = num_req;
-		return -EOPNOTSUPP;
-	}
+	ret = iavf_wait_for_reset(adapter);
+	if (ret)
+		netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset");

-	return 0;
+	return ret;
 }

 /**
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -166,6 +166,45 @@ static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev)
 	return netdev_priv(pci_get_drvdata(pdev));
 }

+/**
+ * iavf_is_reset_in_progress - Check if a reset is in progress
+ * @adapter: board private structure
+ */
+static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter)
+{
+	if (adapter->state == __IAVF_RESETTING ||
+	    adapter->flags & (IAVF_FLAG_RESET_PENDING |
+			      IAVF_FLAG_RESET_NEEDED))
+		return true;
+
+	return false;
+}
+
+/**
+ * iavf_wait_for_reset - Wait for reset to finish.
+ * @adapter: board private structure
+ *
+ * Returns 0 if reset finished successfully, negative on timeout or interrupt.
+ */
+int iavf_wait_for_reset(struct iavf_adapter *adapter)
+{
+	int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue,
+					!iavf_is_reset_in_progress(adapter),
+					msecs_to_jiffies(5000));
+
+	/* If ret < 0 then it means wait was interrupted.
+	 * If ret == 0 then it means we got a timeout while waiting
+	 * for reset to finish.
+	 * If ret > 0 it means reset has finished.
+	 */
+	if (ret > 0)
+		return 0;
+	else if (ret < 0)
+		return -EINTR;
+	else
+		return -EBUSY;
+}
+
 /**
 * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code
 * @hw:   pointer to the HW structure
@@ -262,12 +301,14 @@ static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
 /**
 * iavf_schedule_reset - Set the flags and schedule a reset event
 * @adapter: board private structure
+ * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED
 **/
-void iavf_schedule_reset(struct iavf_adapter *adapter)
+void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags)
 {
-	if (!(adapter->flags &
-	      (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
-		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
+	if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) &&
+	    !(adapter->flags &
+	    (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
+		adapter->flags |= flags;
 		queue_work(adapter->wq, &adapter->reset_task);
 	}
 }
@@ -295,7 +336,7 @@ static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct iavf_adapter *adapter = netdev_priv(netdev);

 	adapter->tx_timeout_count++;
-	iavf_schedule_reset(adapter);
+	iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
 }

 /**
@@ -1651,10 +1692,10 @@ static int iavf_set_interrupt_capability(struct iavf_adapter *adapter)
 		adapter->msix_entries[vector].entry = vector;

 	err = iavf_acquire_msix_vectors(adapter, v_budget);
+	if (!err)
+		iavf_schedule_finish_config(adapter);

 out:
-	netif_set_real_num_rx_queues(adapter->netdev, pairs);
-	netif_set_real_num_tx_queues(adapter->netdev, pairs);
 	return err;
 }

@@ -1828,19 +1869,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter)
 static void iavf_free_q_vectors(struct iavf_adapter *adapter)
 {
 	int q_idx, num_q_vectors;
-	int napi_vectors;

 	if (!adapter->q_vectors)
 		return;

 	num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-	napi_vectors = adapter->num_active_queues;

 	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
 		struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx];

-		if (q_idx < napi_vectors)
-			netif_napi_del(&q_vector->napi);
+		netif_napi_del(&q_vector->napi);
 	}
 	kfree(adapter->q_vectors);
 	adapter->q_vectors = NULL;
@@ -1877,9 +1915,7 @@ static int iavf_init_interrupt_scheme(struct iavf_adapter *adapter)
 		goto err_alloc_queues;
 	}

-	rtnl_lock();
 	err = iavf_set_interrupt_capability(adapter);
-	rtnl_unlock();
 	if (err) {
 		dev_err(&adapter->pdev->dev,
 			"Unable to setup interrupt capabilities\n");
@@ -1932,15 +1968,16 @@ static void iavf_free_rss(struct iavf_adapter *adapter)
 /**
 * iavf_reinit_interrupt_scheme - Reallocate queues and vectors
 * @adapter: board private structure
+ * @running: true if adapter->state == __IAVF_RUNNING
 *
 * Returns 0 on success, negative on failure
 **/
-static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter)
+static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool running)
 {
 	struct net_device *netdev = adapter->netdev;
 	int err;

-	if (netif_running(netdev))
+	if (running)
 		iavf_free_traffic_irqs(adapter);
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
@@ -1964,6 +2001,78 @@ err:
 	return err;
 }

+/**
+ * iavf_finish_config - do all netdev work that needs RTNL
+ * @work: our work_struct
+ *
+ * Do work that needs both RTNL and crit_lock.
+ **/
+static void iavf_finish_config(struct work_struct *work)
+{
+	struct iavf_adapter *adapter;
+	int pairs, err;
+
+	adapter = container_of(work, struct iavf_adapter, finish_config);
+
+	/* Always take RTNL first to prevent circular lock dependency */
+	rtnl_lock();
+	mutex_lock(&adapter->crit_lock);
+
+	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
+	    adapter->netdev_registered &&
+	    !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) {
+		netdev_update_features(adapter->netdev);
+		adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
+	}
+
+	switch (adapter->state) {
+	case __IAVF_DOWN:
+		if (!adapter->netdev_registered) {
+			err = register_netdevice(adapter->netdev);
+			if (err) {
+				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
+					err);
+
+				/* go back and try again.*/
+				iavf_free_rss(adapter);
+				iavf_free_misc_irq(adapter);
+				iavf_reset_interrupt_capability(adapter);
+				iavf_change_state(adapter,
+						  __IAVF_INIT_CONFIG_ADAPTER);
+				goto out;
+			}
+			adapter->netdev_registered = true;
+		}
+
+		/* Set the real number of queues when reset occurs while
+		 * state == __IAVF_DOWN
+		 */
+		fallthrough;
+	case __IAVF_RUNNING:
+		pairs = adapter->num_active_queues;
+		netif_set_real_num_rx_queues(adapter->netdev, pairs);
+		netif_set_real_num_tx_queues(adapter->netdev, pairs);
+		break;
+
+	default:
+		break;
+	}
+
+out:
+	mutex_unlock(&adapter->crit_lock);
+	rtnl_unlock();
+}
+
+/**
+ * iavf_schedule_finish_config - Set the flags and schedule a reset event
+ * @adapter: board private structure
+ **/
+void iavf_schedule_finish_config(struct iavf_adapter *adapter)
+{
+	if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
+		queue_work(adapter->wq, &adapter->finish_config);
+}
+
 /**
 * iavf_process_aq_command - process aq_required flags
 * and sends aq command
@@ -2371,7 +2480,7 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter)
 			adapter->vsi_res->num_queue_pairs);
 		adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED;
 		adapter->num_req_queues = adapter->vsi_res->num_queue_pairs;
-		iavf_schedule_reset(adapter);
+		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);

 		return -EAGAIN;
 	}
@@ -2601,22 +2710,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)

 	netif_carrier_off(netdev);
 	adapter->link_up = false;
-
-	/* set the semaphore to prevent any callbacks after device registration
-	 * up to time when state of driver will be set to __IAVF_DOWN
-	 */
-	rtnl_lock();
-	if (!adapter->netdev_registered) {
-		err = register_netdevice(netdev);
-		if (err) {
-			rtnl_unlock();
-			goto err_register;
-		}
-	}
-
-	adapter->netdev_registered = true;
-
 	netif_tx_stop_all_queues(netdev);
+
 	if (CLIENT_ALLOWED(adapter)) {
 		err = iavf_lan_add_device(adapter);
 		if (err)
@@ -2629,7 +2724,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)

 	iavf_change_state(adapter, __IAVF_DOWN);
 	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
-	rtnl_unlock();

 	iavf_misc_irq_enable(adapter);
 	wake_up(&adapter->down_waitqueue);
@@ -2649,10 +2743,11 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 		/* request initial VLAN offload settings */
 		iavf_set_vlan_offload_features(adapter, 0, netdev->features);

+	iavf_schedule_finish_config(adapter);
 	return;
+
 err_mem:
 	iavf_free_rss(adapter);
-err_register:
 	iavf_free_misc_irq(adapter);
 err_sw_init:
 	iavf_reset_interrupt_capability(adapter);
@@ -2679,26 +2774,9 @@ static void iavf_watchdog_task(struct work_struct *work)
 		goto restart_watchdog;
 	}

-	if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
-	    adapter->netdev_registered &&
-	    !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) &&
-	    rtnl_trylock()) {
-		netdev_update_features(adapter->netdev);
-		rtnl_unlock();
-		adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
-	}
-
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		iavf_change_state(adapter, __IAVF_COMM_FAILED);

-	if (adapter->flags & IAVF_FLAG_RESET_NEEDED) {
-		adapter->aq_required = 0;
-		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		mutex_unlock(&adapter->crit_lock);
-		queue_work(adapter->wq, &adapter->reset_task);
-		return;
-	}
-
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
 		iavf_startup(adapter);
@@ -2826,11 +2904,10 @@ static void iavf_watchdog_task(struct work_struct *work)
 	/* check for hw reset */
 	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
 	if (!reg_val) {
-		adapter->flags |= IAVF_FLAG_RESET_PENDING;
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
-		queue_work(adapter->wq, &adapter->reset_task);
+		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING);
 		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(adapter->wq,
 				   &adapter->watchdog_task, HZ * 2);
@@ -2940,11 +3017,6 @@ static void iavf_reset_task(struct work_struct *work)
 	int i = 0, err;
 	bool running;

-	/* Detach interface to avoid subsequent NDO callbacks */
-	rtnl_lock();
-	netif_device_detach(netdev);
-	rtnl_unlock();
-
 	/* When device is being removed it doesn't make sense to run the reset
 	 * task, just return in such a case.
 	 */
@@ -2952,7 +3024,7 @@ static void iavf_reset_task(struct work_struct *work)
 		if (adapter->state != __IAVF_REMOVE)
 			queue_work(adapter->wq, &adapter->reset_task);

-		goto reset_finish;
+		return;
 	}

 	while (!mutex_trylock(&adapter->client_lock))
@@ -3010,11 +3082,6 @@ static void iavf_reset_task(struct work_struct *work)
 		iavf_disable_vf(adapter);
 		mutex_unlock(&adapter->client_lock);
 		mutex_unlock(&adapter->crit_lock);
-		if (netif_running(netdev)) {
-			rtnl_lock();
-			dev_close(netdev);
-			rtnl_unlock();
-		}
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}

@@ -3056,7 +3123,7 @@ continue_reset:

 	if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) ||
 	    (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) {
-		err = iavf_reinit_interrupt_scheme(adapter);
+		err = iavf_reinit_interrupt_scheme(adapter, running);
 		if (err)
 			goto reset_err;
 	}
@@ -3151,10 +3218,11 @@ continue_reset:

 	adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;

+	wake_up(&adapter->reset_waitqueue);
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);

-	goto reset_finish;
+	return;
 reset_err:
 	if (running) {
 		set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
@@ -3164,21 +3232,7 @@ reset_err:

 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
-
-	if (netif_running(netdev)) {
-		/* Close device to ensure that Tx queues will not be started
-		 * during netif_device_attach() at the end of the reset task.
-		 */
-		rtnl_lock();
-		dev_close(netdev);
-		rtnl_unlock();
-	}
-
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
-reset_finish:
-	rtnl_lock();
-	netif_device_attach(netdev);
-	rtnl_unlock();
 }

 /**
@@ -3227,9 +3281,7 @@ static void iavf_adminq_task(struct work_struct *work)
 	} while (pending);
 	mutex_unlock(&adapter->crit_lock);

-	if ((adapter->flags &
-	     (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
-	    adapter->state == __IAVF_RESETTING)
+	if (iavf_is_reset_in_progress(adapter))
 		goto freedom;

 	/* check for error indications */
@@ -4315,6 +4367,7 @@ static int iavf_close(struct net_device *netdev)
 static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
+	int ret = 0;

 	netdev_dbg(netdev, "changing MTU from %d to %d\n",
 		   netdev->mtu, new_mtu);
@@ -4325,11 +4378,15 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 	}

 	if (netif_running(netdev)) {
-		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-		queue_work(adapter->wq, &adapter->reset_task);
+		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
+		ret = iavf_wait_for_reset(adapter);
+		if (ret < 0)
+			netdev_warn(netdev, "MTU change interrupted waiting for reset");
+		else if (ret)
+			netdev_warn(netdev, "MTU change timed out waiting for reset");
 	}

-	return 0;
+	return ret;
 }

 #define NETIF_VLAN_OFFLOAD_FEATURES	(NETIF_F_HW_VLAN_CTAG_RX | \
@@ -4922,6 +4979,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)

 	INIT_WORK(&adapter->reset_task, iavf_reset_task);
 	INIT_WORK(&adapter->adminq_task, iavf_adminq_task);
+	INIT_WORK(&adapter->finish_config, iavf_finish_config);
 	INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task);
 	INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task);
 	queue_delayed_work(adapter->wq, &adapter->watchdog_task,
@@ -4930,6 +4988,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating transition to down status */
 	init_waitqueue_head(&adapter->down_waitqueue);

+	/* Setup the wait queue for indicating transition to running state */
+	init_waitqueue_head(&adapter->reset_waitqueue);
+
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);

@@ -5061,13 +5122,15 @@ static void iavf_remove(struct pci_dev *pdev)
 		usleep_range(500, 1000);
 	}
 	cancel_delayed_work_sync(&adapter->watchdog_task);
+	cancel_work_sync(&adapter->finish_config);

+	rtnl_lock();
 	if (adapter->netdev_registered) {
-		rtnl_lock();
 		unregister_netdevice(netdev);
 		adapter->netdev_registered = false;
-		rtnl_unlock();
 	}
+	rtnl_unlock();
+
 	if (CLIENT_ALLOWED(adapter)) {
 		err = iavf_lan_del_device(adapter);
 		if (err)
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1961,9 +1961,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		case VIRTCHNL_EVENT_RESET_IMPENDING:
 			dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n");
 			if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) {
-				adapter->flags |= IAVF_FLAG_RESET_PENDING;
 				dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
-				queue_work(adapter->wq, &adapter->reset_task);
+				iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING);
 			}
 			break;
 		default:
@@ -2237,6 +2236,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,

 		iavf_process_config(adapter);
 		adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES;
+		iavf_schedule_finish_config(adapter);

 		iavf_set_queue_vlan_tag_loc(adapter);

@@ -2285,6 +2285,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);
+		wake_up(&adapter->reset_waitqueue);
 		adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED;
 		break;
 	case VIRTCHNL_OP_DISABLE_QUEUES:
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -800,6 +800,8 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)

 	ice_for_each_q_vector(vsi, v_idx)
 		ice_free_q_vector(vsi, v_idx);
+
+	vsi->num_q_vectors = 0;
 }

 /**
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2681,8 +2681,13 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,

 	ring->rx_max_pending = ICE_MAX_NUM_DESC;
 	ring->tx_max_pending = ICE_MAX_NUM_DESC;
-	ring->rx_pending = vsi->rx_rings[0]->count;
-	ring->tx_pending = vsi->tx_rings[0]->count;
+	if (vsi->tx_rings && vsi->rx_rings) {
+		ring->rx_pending = vsi->rx_rings[0]->count;
+		ring->tx_pending = vsi->tx_rings[0]->count;
+	} else {
+		ring->rx_pending = 0;
+		ring->tx_pending = 0;
+	}

 	/* Rx mini and jumbo rings are not supported */
 	ring->rx_mini_max_pending = 0;
@@ -2716,6 +2721,10 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
 		return -EINVAL;
 	}

+	/* Return if there is no rings (device is reloading) */
+	if (!vsi->tx_rings || !vsi->rx_rings)
+		return -EBUSY;
+
 	new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE);
 	if (new_tx_cnt != ring->tx_pending)
 		netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n",
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2972,39 +2972,12 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		return -ENODEV;
 	pf = vsi->back;

-	/* do not unregister while driver is in the reset recovery pending
-	 * state. Since reset/rebuild happens through PF service task workqueue,
-	 * it's not a good idea to unregister netdev that is associated to the
-	 * PF that is running the work queue items currently. This is done to
-	 * avoid check_flush_dependency() warning on this wq
-	 */
-	if (vsi->netdev && !ice_is_reset_in_progress(pf->state) &&
-	    (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) {
-		unregister_netdev(vsi->netdev);
-		clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
-	}
-
-	if (vsi->type == ICE_VSI_PF)
-		ice_devlink_destroy_pf_port(pf);
-
 	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
 		ice_rss_clean(vsi);

 	ice_vsi_close(vsi);
 	ice_vsi_decfg(vsi);

-	if (vsi->netdev) {
-		if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) {
-			unregister_netdev(vsi->netdev);
-			clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
-		}
-		if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) {
-			free_netdev(vsi->netdev);
-			vsi->netdev = NULL;
-			clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
-		}
-	}
-
 	/* retain SW VSI data structure since it is needed to unregister and
 	 * free VSI netdev when PF is not in reset recovery pending state,\
 	 * for ex: during rmmod.
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4430,9 +4430,9 @@ static int ice_start_eth(struct ice_vsi *vsi)
 	if (err)
 		return err;

-	rtnl_lock();
 	err = ice_vsi_open(vsi);
-	rtnl_unlock();
+	if (err)
+		ice_fltr_remove_all(vsi);

 	return err;
 }
@@ -4895,6 +4895,7 @@ int ice_load(struct ice_pf *pf)
 	params = ice_vsi_to_params(vsi);
 	params.flags = ICE_VSI_FLAG_INIT;

+	rtnl_lock();
 	err = ice_vsi_cfg(vsi, &params);
 	if (err)
 		goto err_vsi_cfg;
@@ -4902,6 +4903,7 @@ int ice_load(struct ice_pf *pf)
 	err = ice_start_eth(ice_get_main_vsi(pf));
 	if (err)
 		goto err_start_eth;
+	rtnl_unlock();

 	err = ice_init_rdma(pf);
 	if (err)
@@ -4916,9 +4918,11 @@ int ice_load(struct ice_pf *pf)

 err_init_rdma:
 	ice_vsi_close(ice_get_main_vsi(pf));
+	rtnl_lock();
 err_start_eth:
 	ice_vsi_decfg(ice_get_main_vsi(pf));
 err_vsi_cfg:
+	rtnl_unlock();
 	ice_deinit_dev(pf);
 	return err;
 }
@@ -4931,8 +4935,10 @@ void ice_unload(struct ice_pf *pf)
 {
 	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	rtnl_lock();
 	ice_stop_eth(ice_get_main_vsi(pf));
 	ice_vsi_decfg(ice_get_main_vsi(pf));
+	rtnl_unlock();
 	ice_deinit_dev(pf);
 }

--- a/Show More
+++ b/Show More