Merge tag 'net-6.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni: "Including fixes from netfilter, wireless and ebpf. Current release - regressions: - netfilter: conntrack: gre: don't set assured flag for clash entries - wifi: iwlwifi: remove 'use_tfh' config to fix crash Previous releases - regressions: - ipv6: fix a potential refcount underflow for idev - icmp6: ifix null-ptr-deref of ip6_null_entry->rt6i_idev in icmp6_dev() - bpf: fix max stack depth check for async callbacks - eth: mlx5e: - check for NOT_READY flag state after locking - fix page_pool page fragment tracking for XDP - eth: igc: - fix tx hang issue when QBV gate is closed - fix corner cases for TSN offload - eth: octeontx2-af: Move validation of ptp pointer before its usage - eth: ena: fix shift-out-of-bounds in exponential backoff Previous releases - always broken: - core: prevent skb corruption on frag list segmentation - sched: - cls_fw: fix improper refcount update leads to use-after-free - sch_qfq: account for stab overhead in qfq_enqueue - netfilter: - report use refcount overflow - prevent OOB access in nft_byteorder_eval - wifi: mt7921e: fix init command fail with enabled device - eth: ocelot: fix oversize frame dropping for preemptible TCs - eth: fec: recycle pages for transmitted XDP frames" * tag 'net-6.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (79 commits) selftests: tc-testing: add test for qfq with stab overhead net/sched: sch_qfq: account for stab overhead in qfq_enqueue selftests: tc-testing: add tests for qfq mtu sanity check net/sched: sch_qfq: reintroduce lmax bound check for MTU wifi: cfg80211: fix receiving mesh packets without RFC1042 header wifi: rtw89: debug: fix error code in rtw89_debug_priv_send_h2c_set() net: txgbe: fix eeprom calculation error net/sched: make psched_mtu() RTNL-less safe net: ena: fix shift-out-of-bounds in exponential backoff netdevsim: fix uninitialized data in nsim_dev_trap_fa_cookie_write() net/sched: flower: Ensure both minimum and maximum ports are specified MAINTAINERS: Add another mailing list for QUALCOMM ETHQOS ETHERNET DRIVER docs: netdev: update the URL of the status page wifi: iwlwifi: remove 'use_tfh' config to fix crash xdp: use trusted arguments in XDP hints kfuncs bpf: cpumap: Fix memory leak in cpu_map_update_elem wifi: airo: avoid uninitialized warning in airo_get_rate() octeontx2-pf: Add additional check for MCAM rules net: dsa: Removed unneeded of_node_put in felix_parse_ports_node net: fec: use netdev_err_once() instead of netdev_err() ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2023-07-13 14:21:22 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2023-07-13 14:21:22 -0700
commit: b1983d427a53911ea71ba621d4bf994ae22b1536 (patch)
tree: 78edb0049c5d1a2243e738203d5de01b39513aff /drivers
parent: ebc27aaceeb9c4c988dbf321e849fcb75c6b55fa (diff)
parent: 9d23aac8a85f69239e585c8656c6fdb21be65695 (diff)
download: linux-b1983d427a53911ea71ba621d4bf994ae22b1536.tar.gz
linux-b1983d427a53911ea71ba621d4bf994ae22b1536.tar.bz2
linux-b1983d427a53911ea71ba621d4bf994ae22b1536.zip
58 files changed, 597 insertions, 368 deletions
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 70c0e2b1936b..8da46d284e35 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1286,7 +1286,6 @@ static int felix_parse_ports_node(struct felix *felix,
 		if (err < 0) {
 			dev_info(dev, "Unsupported PHY mode %s on port %d\n",
 				 phy_modes(phy_mode), port);
-			of_node_put(child);
 
 			/* Leave port_phy_modes[port] = 0, which is also
 			 * PHY_INTERFACE_MODE_NA. This will perform a
@@ -1786,16 +1785,15 @@ static int felix_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
 {
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
-	struct felix *felix = ocelot_to_felix(ocelot);
 
 	ocelot_port_set_maxlen(ocelot, port, new_mtu);
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
-	if (ocelot_port->taprio && felix->info->tas_guard_bands_update)
-		felix->info->tas_guard_bands_update(ocelot, port);
+	if (ocelot_port->taprio && ocelot->ops->tas_guard_bands_update)
+		ocelot->ops->tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 }
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index 96008c046da5..1d4befe7cfe8 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -57,7 +57,6 @@ struct felix_info {
 	void	(*mdio_bus_free)(struct ocelot *ocelot);
 	int	(*port_setup_tc)(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type, void *type_data);
-	void	(*tas_guard_bands_update)(struct ocelot *ocelot, int port);
 	void	(*port_sched_speed_set)(struct ocelot *ocelot, int port,
 					u32 speed);
 	void	(*phylink_mac_config)(struct ocelot *ocelot, int port,
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index bb39fedd46c7..1c113957fcf4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1209,15 +1209,17 @@ static u32 vsc9959_tas_tc_max_sdu(struct tc_taprio_qopt_offload *taprio, int tc)
 static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_mm_state *mm = &ocelot->mm[port];
 	struct tc_taprio_qopt_offload *taprio;
 	u64 min_gate_len[OCELOT_NUM_TC];
+	u32 val, maxlen, add_frag_size;
+	u64 needed_min_frag_time_ps;
 	int speed, picos_per_byte;
 	u64 needed_bit_time_ps;
-	u32 val, maxlen;
 	u8 tas_speed;
 	int tc;
 
-	lockdep_assert_held(&ocelot->tas_lock);
+	lockdep_assert_held(&ocelot->fwd_domain_lock);
 
 	taprio = ocelot_port->taprio;
 
@@ -1253,14 +1255,21 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	 */
 	needed_bit_time_ps = (u64)(maxlen + 24) * picos_per_byte;
 
+	/* Preemptible TCs don't need to pass a full MTU, the port will
+	 * automatically emit a HOLD request when a preemptible TC gate closes
+	 */
+	val = ocelot_read_rix(ocelot, QSYS_PREEMPTION_CFG, port);
+	add_frag_size = QSYS_PREEMPTION_CFG_MM_ADD_FRAG_SIZE_X(val);
+	needed_min_frag_time_ps = picos_per_byte *
+		(u64)(24 + 2 * ethtool_mm_frag_size_add_to_min(add_frag_size));
+
 	dev_dbg(ocelot->dev,
-		"port %d: max frame size %d needs %llu ps at speed %d\n",
-		port, maxlen, needed_bit_time_ps, speed);
+		"port %d: max frame size %d needs %llu ps, %llu ps for mPackets at speed %d\n",
+		port, maxlen, needed_bit_time_ps, needed_min_frag_time_ps,
+		speed);
 
 	vsc9959_tas_min_gate_lengths(taprio, min_gate_len);
 
-	mutex_lock(&ocelot->fwd_domain_lock);
-
 	for (tc = 0; tc < OCELOT_NUM_TC; tc++) {
 		u32 requested_max_sdu = vsc9959_tas_tc_max_sdu(taprio, tc);
 		u64 remaining_gate_len_ps;
@@ -1269,7 +1278,9 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 		remaining_gate_len_ps =
 			vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]);
 
-		if (remaining_gate_len_ps > needed_bit_time_ps) {
+		if ((mm->active_preemptible_tcs & BIT(tc)) ?
+		    remaining_gate_len_ps > needed_min_frag_time_ps :
+		    remaining_gate_len_ps > needed_bit_time_ps) {
 			/* Setting QMAXSDU_CFG to 0 disables oversized frame
 			 * dropping.
 			 */
@@ -1323,8 +1334,6 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
 	ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port);
 
 	ocelot->ops->cut_through_fwd(ocelot);
-
-	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
@@ -1351,7 +1360,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 		break;
 	}
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	ocelot_rmw_rix(ocelot,
 		       QSYS_TAG_CONFIG_LINK_SPEED(tas_speed),
@@ -1361,7 +1370,7 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port,
 	if (ocelot_port->taprio)
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void vsc9959_new_base_time(struct ocelot *ocelot, ktime_t base_time,
@@ -1409,7 +1418,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	int ret, i;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	if (taprio->cmd == TAPRIO_CMD_DESTROY) {
 		ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
@@ -1421,7 +1430,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 
 		vsc9959_tas_guard_bands_update(ocelot, port);
 
-		mutex_unlock(&ocelot->tas_lock);
+		mutex_unlock(&ocelot->fwd_domain_lock);
 		return 0;
 	} else if (taprio->cmd != TAPRIO_CMD_REPLACE) {
 		ret = -EOPNOTSUPP;
@@ -1504,7 +1513,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	ocelot_port->taprio = taprio_offload_get(taprio);
 	vsc9959_tas_guard_bands_update(ocelot, port);
 
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return 0;
 
@@ -1512,7 +1521,7 @@ err_reset_tc:
 	taprio->mqprio.qopt.num_tc = 0;
 	ocelot_port_mqprio(ocelot, port, &taprio->mqprio);
 err_unlock:
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 
 	return ret;
 }
@@ -1525,7 +1534,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 	int port;
 	u32 val;
 
-	mutex_lock(&ocelot->tas_lock);
+	mutex_lock(&ocelot->fwd_domain_lock);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		ocelot_port = ocelot->ports[port];
@@ -1563,7 +1572,7 @@ static void vsc9959_tas_clock_adjust(struct ocelot *ocelot)
 			       QSYS_TAG_CONFIG_ENABLE,
 			       QSYS_TAG_CONFIG, port);
 	}
-	mutex_unlock(&ocelot->tas_lock);
+	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static int vsc9959_qos_port_cbs_set(struct dsa_switch *ds, int port,
@@ -1634,6 +1643,18 @@ static int vsc9959_qos_query_caps(struct tc_query_caps_base *base)
 	}
 }
 
+static int vsc9959_qos_port_mqprio(struct ocelot *ocelot, int port,
+				   struct tc_mqprio_qopt_offload *mqprio)
+{
+	int ret;
+
+	mutex_lock(&ocelot->fwd_domain_lock);
+	ret = ocelot_port_mqprio(ocelot, port, mqprio);
+	mutex_unlock(&ocelot->fwd_domain_lock);
+
+	return ret;
+}
+
 static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 				 enum tc_setup_type type,
 				 void *type_data)
@@ -1646,7 +1667,7 @@ static int vsc9959_port_setup_tc(struct dsa_switch *ds, int port,
 	case TC_SETUP_QDISC_TAPRIO:
 		return vsc9959_qos_port_tas_set(ocelot, port, type_data);
 	case TC_SETUP_QDISC_MQPRIO:
-		return ocelot_port_mqprio(ocelot, port, type_data);
+		return vsc9959_qos_port_mqprio(ocelot, port, type_data);
 	case TC_SETUP_QDISC_CBS:
 		return vsc9959_qos_port_cbs_set(ds, port, type_data);
 	default:
@@ -2591,6 +2612,7 @@ static const struct ocelot_ops vsc9959_ops = {
 	.cut_through_fwd	= vsc9959_cut_through_fwd,
 	.tas_clock_adjust	= vsc9959_tas_clock_adjust,
 	.update_stats		= vsc9959_update_stats,
+	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 static const struct felix_info felix_info_vsc9959 = {
@@ -2616,7 +2638,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.port_modes		= vsc9959_port_modes,
 	.port_setup_tc		= vsc9959_port_setup_tc,
 	.port_sched_speed_set	= vsc9959_sched_speed_set,
-	.tas_guard_bands_update	= vsc9959_tas_guard_bands_update,
 };
 
 /* The INTB interrupt is shared between for PTP TX timestamp availability
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index f7d7cfb2fd86..09b80644c11b 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -588,6 +588,9 @@ qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data,
 	bool ack;
 	int ret;
 
+	if (!skb)
+		return -ENOMEM;
+
 	reinit_completion(&mgmt_eth_data->rw_done);
 
 	/* Increment seq_num and set it in the copy pkt */
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 451c3a1b6255..633b321d7fdd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -35,6 +35,8 @@
 
 #define ENA_REGS_ADMIN_INTR_MASK 1
 
+#define ENA_MAX_BACKOFF_DELAY_EXP 16U
+
 #define ENA_MIN_ADMIN_POLL_US 100
 
 #define ENA_MAX_ADMIN_POLL_US 5000
@@ -536,6 +538,7 @@ static int ena_com_comp_status_to_errno(struct ena_com_admin_queue *admin_queue,
 
 static void ena_delay_exponential_backoff_us(u32 exp, u32 delay_us)
 {
+	exp = min_t(u32, exp, ENA_MAX_BACKOFF_DELAY_EXP);
 	delay_us = max_t(u32, ENA_MIN_ADMIN_POLL_US, delay_us);
 	delay_us = min_t(u32, delay_us * (1U << exp), ENA_MAX_ADMIN_POLL_US);
 	usleep_range(delay_us, 2 * delay_us);
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 1761df8fb7f9..10c7c232cc4e 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 
 	bgmac->in_init = true;
 
-	bgmac_chip_intrs_off(bgmac);
-
 	net_dev->irq = bgmac->irq;
 	SET_NETDEV_DEV(net_dev, bgmac->dev);
 	dev_set_drvdata(bgmac->dev, bgmac);
@@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac)
 	 */
 	bgmac_clk_enable(bgmac, 0);
 
+	bgmac_chip_intrs_off(bgmac);
+
 	/* This seems to be fixing IRQ by assigning OOB #6 to the core */
 	if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) {
 		if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 9939ccafb556..63a053dea819 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -355,7 +355,7 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_SIZE		1024	/* Must be power of two */
 #define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT		0x00800000
@@ -544,10 +544,23 @@ enum {
 	XDP_STATS_TOTAL,
 };
 
+enum fec_txbuf_type {
+	FEC_TXBUF_T_SKB,
+	FEC_TXBUF_T_XDP_NDO,
+};
+
+struct fec_tx_buffer {
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdp;
+	};
+	enum fec_txbuf_type type;
+};
+
 struct fec_enet_priv_tx_q {
 	struct bufdesc_prop bd;
 	unsigned char *tx_bounce[TX_RING_SIZE];
-	struct  sk_buff *tx_skbuff[TX_RING_SIZE];
+	struct fec_tx_buffer tx_buf[TX_RING_SIZE];
 
 	unsigned short tx_stop_threshold;
 	unsigned short tx_wake_threshold;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8fbe47703d47..ec9e4bdb0c06 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -397,7 +397,7 @@ static void fec_dump(struct net_device *ndev)
 			fec16_to_cpu(bdp->cbd_sc),
 			fec32_to_cpu(bdp->cbd_bufaddr),
 			fec16_to_cpu(bdp->cbd_datlen),
-			txq->tx_skbuff[index]);
+			txq->tx_buf[index].skb);
 		bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		index++;
 	} while (bdp != txq->bd.base);
@@ -654,7 +654,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	index = fec_enet_get_bd_index(last_bdp, &txq->bd);
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -672,9 +672,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	skb_tx_timestamp(skb);
 
-	/* Make sure the update to bdp and tx_skbuff are performed before
-	 * txq->bd.cur.
-	 */
+	/* Make sure the update to bdp is performed before txq->bd.cur. */
 	wmb();
 	txq->bd.cur = bdp;
 
@@ -862,7 +860,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	}
 
 	/* Save skb pointer */
-	txq->tx_skbuff[index] = skb;
+	txq->tx_buf[index].skb = skb;
 
 	skb_tx_timestamp(skb);
 	txq->bd.cur = bdp;
@@ -952,16 +950,33 @@ static void fec_enet_bd_init(struct net_device *dev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = cpu_to_fec16(0);
-			if (bdp->cbd_bufaddr &&
-			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-				dma_unmap_single(&fep->pdev->dev,
-						 fec32_to_cpu(bdp->cbd_bufaddr),
-						 fec16_to_cpu(bdp->cbd_datlen),
-						 DMA_TO_DEVICE);
-			if (txq->tx_skbuff[i]) {
-				dev_kfree_skb_any(txq->tx_skbuff[i]);
-				txq->tx_skbuff[i] = NULL;
+			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
+				if (bdp->cbd_bufaddr &&
+				    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+				if (txq->tx_buf[i].skb) {
+					dev_kfree_skb_any(txq->tx_buf[i].skb);
+					txq->tx_buf[i].skb = NULL;
+				}
+			} else {
+				if (bdp->cbd_bufaddr)
+					dma_unmap_single(&fep->pdev->dev,
+							 fec32_to_cpu(bdp->cbd_bufaddr),
+							 fec16_to_cpu(bdp->cbd_datlen),
+							 DMA_TO_DEVICE);
+
+				if (txq->tx_buf[i].xdp) {
+					xdp_return_frame(txq->tx_buf[i].xdp);
+					txq->tx_buf[i].xdp = NULL;
+				}
+
+				/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
 			}
+
 			bdp->cbd_bufaddr = cpu_to_fec32(0);
 			bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
 		}
@@ -1360,6 +1375,7 @@ static void
 fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 {
 	struct	fec_enet_private *fep;
+	struct xdp_frame *xdpf;
 	struct bufdesc *bdp;
 	unsigned short status;
 	struct	sk_buff	*skb;
@@ -1387,16 +1403,31 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 
 		index = fec_enet_get_bd_index(bdp, &txq->bd);
 
-		skb = txq->tx_skbuff[index];
-		txq->tx_skbuff[index] = NULL;
-		if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
-			dma_unmap_single(&fep->pdev->dev,
-					 fec32_to_cpu(bdp->cbd_bufaddr),
-					 fec16_to_cpu(bdp->cbd_datlen),
-					 DMA_TO_DEVICE);
-		bdp->cbd_bufaddr = cpu_to_fec32(0);
-		if (!skb)
-			goto skb_done;
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			skb = txq->tx_buf[index].skb;
+			txq->tx_buf[index].skb = NULL;
+			if (bdp->cbd_bufaddr &&
+			    !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!skb)
+				goto tx_buf_done;
+		} else {
+			xdpf = txq->tx_buf[index].xdp;
+			if (bdp->cbd_bufaddr)
+				dma_unmap_single(&fep->pdev->dev,
+						 fec32_to_cpu(bdp->cbd_bufaddr),
+						 fec16_to_cpu(bdp->cbd_datlen),
+						 DMA_TO_DEVICE);
+			bdp->cbd_bufaddr = cpu_to_fec32(0);
+			if (!xdpf) {
+				txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+				goto tx_buf_done;
+			}
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -1415,21 +1446,11 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 				ndev->stats.tx_carrier_errors++;
 		} else {
 			ndev->stats.tx_packets++;
-			ndev->stats.tx_bytes += skb->len;
-		}
-
-		/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
-		 * are to time stamp the packet, so we still need to check time
-		 * stamping enabled flag.
-		 */
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
-			     fep->hwts_tx_en) &&
-		    fep->bufdesc_ex) {
-			struct skb_shared_hwtstamps shhwtstamps;
-			struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
 
-			fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
-			skb_tstamp_tx(skb, &shhwtstamps);
+			if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB)
+				ndev->stats.tx_bytes += skb->len;
+			else
+				ndev->stats.tx_bytes += xdpf->len;
 		}
 
 		/* Deferred means some collisions occurred during transmit,
@@ -1438,10 +1459,32 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 		if (status & BD_ENET_TX_DEF)
 			ndev->stats.collisions++;
 
-		/* Free the sk buffer associated with this last transmit */
-		dev_kfree_skb_any(skb);
-skb_done:
-		/* Make sure the update to bdp and tx_skbuff are performed
+		if (txq->tx_buf[index].type == FEC_TXBUF_T_SKB) {
+			/* NOTE: SKBTX_IN_PROGRESS being set does not imply it's we who
+			 * are to time stamp the packet, so we still need to check time
+			 * stamping enabled flag.
+			 */
+			if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS &&
+				     fep->hwts_tx_en) && fep->bufdesc_ex) {
+				struct skb_shared_hwtstamps shhwtstamps;
+				struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+
+				fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
+				skb_tstamp_tx(skb, &shhwtstamps);
+			}
+
+			/* Free the sk buffer associated with this last transmit */
+			dev_kfree_skb_any(skb);
+		} else {
+			xdp_return_frame(xdpf);
+
+			txq->tx_buf[index].xdp = NULL;
+			/* restore default tx buffer type: FEC_TXBUF_T_SKB */
+			txq->tx_buf[index].type = FEC_TXBUF_T_SKB;
+		}
+
+tx_buf_done:
+		/* Make sure the update to bdp and tx_buf are performed
 		 * before dirty_tx
 		 */
 		wmb();
@@ -3249,9 +3292,19 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 		for (i = 0; i < txq->bd.ring_size; i++) {
 			kfree(txq->tx_bounce[i]);
 			txq->tx_bounce[i] = NULL;
-			skb = txq->tx_skbuff[i];
-			txq->tx_skbuff[i] = NULL;
-			dev_kfree_skb(skb);
+
+			if (txq->tx_buf[i].type == FEC_TXBUF_T_SKB) {
+				skb = txq->tx_buf[i].skb;
+				txq->tx_buf[i].skb = NULL;
+				dev_kfree_skb(skb);
+			} else {
+				if (txq->tx_buf[i].xdp) {
+					xdp_return_frame(txq->tx_buf[i].xdp);
+					txq->tx_buf[i].xdp = NULL;
+				}
+
+				txq->tx_buf[i].type = FEC_TXBUF_T_SKB;
+			}
 		}
 	}
 }
@@ -3296,8 +3349,7 @@ static int fec_enet_alloc_queue(struct net_device *ndev)
 		fep->total_tx_ring_size += fep->tx_queue[i]->bd.ring_size;
 
 		txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
-		txq->tx_wake_threshold =
-			(txq->bd.ring_size - txq->tx_stop_threshold) / 2;
+		txq->tx_wake_threshold = FEC_MAX_SKB_DESCS + 2 * MAX_SKB_FRAGS;
 
 		txq->tso_hdrs = dma_alloc_coherent(&fep->pdev->dev,
 					txq->bd.ring_size * TSO_HEADER_SIZE,
@@ -3732,12 +3784,18 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
 			return -EOPNOTSUPP;
 
+		if (!bpf->prog)
+			xdp_features_clear_redirect_target(dev);
+
 		if (is_run) {
 			napi_disable(&fep->napi);
 			netif_tx_disable(dev);
 		}
 
 		old_prog = xchg(&fep->xdp_prog, bpf->prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+
 		fec_restart(dev);
 
 		if (is_run) {
@@ -3745,8 +3803,8 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 			netif_tx_start_all_queues(dev);
 		}
 
-		if (old_prog)
-			bpf_prog_put(old_prog);
+		if (bpf->prog)
+			xdp_features_set_redirect_target(dev, false);
 
 		return 0;
 
@@ -3778,7 +3836,7 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 
 	entries_free = fec_enet_get_free_txdesc_num(txq);
 	if (entries_free < MAX_SKB_FRAGS + 1) {
-		netdev_err(fep->netdev, "NOT enough BD for SG!\n");
+		netdev_err_once(fep->netdev, "NOT enough BD for SG!\n");
 		return -EBUSY;
 	}
 
@@ -3811,7 +3869,8 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep,
 		ebdp->cbd_esc = cpu_to_fec32(estatus);
 	}
 
-	txq->tx_skbuff[index] = NULL;
+	txq->tx_buf[index].type = FEC_TXBUF_T_XDP_NDO;
+	txq->tx_buf[index].xdp = frame;
 
 	/* Make sure the updates to rest of the descriptor are performed before
 	 * transferring ownership.
@@ -4016,8 +4075,7 @@ static int fec_enet_init(struct net_device *ndev)
 
 	if (!(fep->quirks & FEC_QUIRK_SWAP_FRAME))
 		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
-				     NETDEV_XDP_ACT_REDIRECT |
-				     NETDEV_XDP_ACT_NDO_XMIT;
+				     NETDEV_XDP_ACT_REDIRECT;
 
 	fec_restart(ndev);
 
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 98eb78d98e9f..4b425bf71ede 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -964,5 +964,6 @@ void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
 extern const struct ethtool_ops gve_ethtool_ops;
 /* needed by ethtool */
+extern char gve_driver_name[];
 extern const char gve_version_str[];
 #endif /* _GVE_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index cfd4b8d284d1..233e5946905e 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -15,7 +15,7 @@ static void gve_get_drvinfo(struct net_device *netdev,
 {
 	struct gve_priv *priv = netdev_priv(netdev);
 
-	strscpy(info->driver, "gve", sizeof(info->driver));
+	strscpy(info->driver, gve_driver_name, sizeof(info->driver));
 	strscpy(info->version, gve_version_str, sizeof(info->version));
 	strscpy(info->bus_info, pci_name(priv->pdev), sizeof(info->bus_info));
 }
@@ -590,6 +590,9 @@ static int gve_get_link_ksettings(struct net_device *netdev,
 		err = gve_adminq_report_link_speed(priv);
 
 	cmd->base.speed = priv->link_speed;
+
+	cmd->base.duplex = DUPLEX_FULL;
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 8fb70db63b8b..e6f1711d9be0 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -33,6 +33,7 @@
 #define MIN_TX_TIMEOUT_GAP (1000 * 10)
 #define DQO_TX_MAX	0x3FFFF
 
+char gve_driver_name[] = "gve";
 const char gve_version_str[] = GVE_VERSION;
 static const char gve_version_prefix[] = GVE_VERSION_PREFIX;
 
@@ -2200,7 +2201,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		return err;
 
-	err = pci_request_regions(pdev, "gvnic-cfg");
+	err = pci_request_regions(pdev, gve_driver_name);
 	if (err)
 		goto abort_with_enabled;
 
@@ -2393,8 +2394,8 @@ static const struct pci_device_id gve_id_table[] = {
 	{ }
 };
 
-static struct pci_driver gvnic_driver = {
-	.name		= "gvnic",
+static struct pci_driver gve_driver = {
+	.name		= gve_driver_name,
 	.id_table	= gve_id_table,
 	.probe		= gve_probe,
 	.remove		= gve_remove,
@@ -2405,10 +2406,10 @@ static struct pci_driver gvnic_driver = {
 #endif
 };
 
-module_pci_driver(gvnic_driver);
+module_pci_driver(gve_driver);
 
 MODULE_DEVICE_TABLE(pci, gve_id_table);
 MODULE_AUTHOR("Google, Inc.");
-MODULE_DESCRIPTION("gVNIC Driver");
+MODULE_DESCRIPTION("Google Virtual NIC Driver");
 MODULE_LICENSE("Dual MIT/GPL");
 MODULE_VERSION(GVE_VERSION);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 93979ab18bc1..19a5e7f3a075 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5739,6 +5739,13 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
 	q_handle = vsi->tx_rings[queue_index]->q_handle;
 	tc = ice_dcb_get_tc(vsi, queue_index);
 
+	vsi = ice_locate_vsi_using_queue(vsi, queue_index);
+	if (!vsi) {
+		netdev_err(netdev, "Invalid VSI for given queue %d\n",
+			   queue_index);
+		return -EINVAL;
+	}
+
 	/* Set BW back to default, when user set maxrate to 0 */
 	if (!maxrate)
 		status = ice_cfg_q_bw_dflt_lmt(vsi->port_info, vsi->idx, tc,
@@ -7872,10 +7879,10 @@ static int
 ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 			 struct tc_mqprio_qopt_offload *mqprio_qopt)
 {
-	u64 sum_max_rate = 0, sum_min_rate = 0;
 	int non_power_of_2_qcount = 0;
 	struct ice_pf *pf = vsi->back;
 	int max_rss_q_cnt = 0;
+	u64 sum_min_rate = 0;
 	struct device *dev;
 	int i, speed;
 	u8 num_tc;
@@ -7891,6 +7898,7 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 	dev = ice_pf_to_dev(pf);
 	vsi->ch_rss_size = 0;
 	num_tc = mqprio_qopt->qopt.num_tc;
+	speed = ice_get_link_speed_kbps(vsi);
 
 	for (i = 0; num_tc; i++) {
 		int qcount = mqprio_qopt->qopt.count[i];
@@ -7931,7 +7939,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 		 */
 		max_rate = mqprio_qopt->max_rate[i];
 		max_rate = div_u64(max_rate, ICE_BW_KBPS_DIVISOR);
-		sum_max_rate += max_rate;
 
 		/* min_rate is minimum guaranteed rate and it can't be zero */
 		min_rate = mqprio_qopt->min_rate[i];
@@ -7944,6 +7951,12 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 			return -EINVAL;
 		}
 
+		if (max_rate && max_rate > speed) {
+			dev_err(dev, "TC%d: max_rate(%llu Kbps) > link speed of %u Kbps\n",
+				i, max_rate, speed);
+			return -EINVAL;
+		}
+
 		iter_div_u64_rem(min_rate, ICE_MIN_BW_LIMIT, &rem);
 		if (rem) {
 			dev_err(dev, "TC%d: Min Rate not multiple of %u Kbps",
@@ -7981,12 +7994,6 @@ ice_validate_mqprio_qopt(struct ice_vsi *vsi,
 	    (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i]))
 		return -EINVAL;
 
-	speed = ice_get_link_speed_kbps(vsi);
-	if (sum_max_rate && sum_max_rate > (u64)speed) {
-		dev_err(dev, "Invalid max Tx rate(%llu) Kbps > speed(%u) Kbps specified\n",
-			sum_max_rate, speed);
-		return -EINVAL;
-	}
 	if (sum_min_rate && sum_min_rate > (u64)speed) {
 		dev_err(dev, "Invalid min Tx rate(%llu) Kbps > speed (%u) Kbps specified\n",
 			sum_min_rate, speed);
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index b54052ef6050..4a34ef5f58d3 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -750,17 +750,16 @@ exit:
 /**
  * ice_locate_vsi_using_queue - locate VSI using queue (forward to queue action)
  * @vsi: Pointer to VSI
- * @tc_fltr: Pointer to tc_flower_filter
+ * @queue: Queue index
  *
- * Locate the VSI using specified queue. When ADQ is not enabled, always
- * return input VSI, otherwise locate corresponding VSI based on per channel
- * offset and qcount
+ * Locate the VSI using specified "queue". When ADQ is not enabled,
+ * always return input VSI, otherwise locate corresponding
+ * VSI based on per channel "offset" and "qcount"
  */
-static struct ice_vsi *
-ice_locate_vsi_using_queue(struct ice_vsi *vsi,
-			   struct ice_tc_flower_fltr *tc_fltr)
+struct ice_vsi *
+ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue)
 {
-	int num_tc, tc, queue;
+	int num_tc, tc;
 
 	/* if ADQ is not active, passed VSI is the candidate VSI */
 	if (!ice_is_adq_active(vsi->back))
@@ -770,7 +769,6 @@ ice_locate_vsi_using_queue(struct ice_vsi *vsi,
 	 * upon queue number)
 	 */
 	num_tc = vsi->mqprio_qopt.qopt.num_tc;
-	queue = tc_fltr->action.fwd.q.queue;
 
 	for (tc = 0; tc < num_tc; tc++) {
 		int qcount = vsi->mqprio_qopt.qopt.count[tc];
@@ -812,6 +810,7 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 	struct ice_pf *pf = vsi->back;
 	struct device *dev;
 	u32 tc_class;
+	int q;
 
 	dev = ice_pf_to_dev(pf);
 
@@ -840,7 +839,8 @@ ice_tc_forward_action(struct ice_vsi *vsi, struct ice_tc_flower_fltr *tc_fltr)
 		/* Determine destination VSI even though the action is
 		 * FWD_TO_QUEUE, because QUEUE is associated with VSI
 		 */
-		dest_vsi = tc_fltr->dest_vsi;
+		q = tc_fltr->action.fwd.q.queue;
+		dest_vsi = ice_locate_vsi_using_queue(vsi, q);
 		break;
 	default:
 		dev_err(dev,
@@ -1716,7 +1716,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr,
 	/* If ADQ is configured, and the queue belongs to ADQ VSI, then prepare
 	 * ADQ switch filter
 	 */
-	ch_vsi = ice_locate_vsi_using_queue(vsi, fltr);
+	ch_vsi = ice_locate_vsi_using_queue(vsi, fltr->action.fwd.q.queue);
 	if (!ch_vsi)
 		return -EINVAL;
 	fltr->dest_vsi = ch_vsi;
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
index 8bbc1a62bdb1..65d387163a46 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h
@@ -204,6 +204,7 @@ static inline int ice_chnl_dmac_fltr_cnt(struct ice_pf *pf)
 	return pf->num_dmac_chnl_fltrs;
 }
 
+struct ice_vsi *ice_locate_vsi_using_queue(struct ice_vsi *vsi, int queue);
 int
 ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi,
 		   struct flow_cls_offload *cls_flower);
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 00a5ee487812..9db384f66a8e 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -14,6 +14,7 @@
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/bitfield.h>
+#include <linux/hrtimer.h>
 
 #include "igc_hw.h"
 
@@ -101,6 +102,8 @@ struct igc_ring {
 	u32 start_time;
 	u32 end_time;
 	u32 max_sdu;
+	bool oper_gate_closed;		/* Operating gate. True if the TX Queue is closed */
+	bool admin_gate_closed;		/* Future gate. True if the TX Queue will be closed */
 
 	/* CBS parameters */
 	bool cbs_enable;                /* indicates if CBS is enabled */
@@ -160,6 +163,7 @@ struct igc_adapter {
 	struct timer_list watchdog_timer;
 	struct timer_list dma_err_timer;
 	struct timer_list phy_info_timer;
+	struct hrtimer hrtimer;
 
 	u32 wol;
 	u32 en_mng_pt;
@@ -184,10 +188,13 @@ struct igc_adapter {
 	u32 max_frame_size;
 	u32 min_frame_size;
 
+	int tc_setup_type;
 	ktime_t base_time;
 	ktime_t cycle_time;
-	bool qbv_enable;
+	bool taprio_offload_enable;
 	u32 qbv_config_change_errors;
+	bool qbv_transition;
+	unsigned int qbv_count;
 
 	/* OS defined structs */
 	struct pci_dev *pdev;
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 0e2cb00622d1..93bce729be76 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1708,6 +1708,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev,
 	/* twisted pair */
 	cmd->base.port = PORT_TP;
 	cmd->base.phy_address = hw->phy.addr;
+	ethtool_link_ksettings_add_link_mode(cmd, supported, TP);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, TP);
 
 	/* advertising link modes */
 	if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 019ce91c45aa..9f93f0f4f752 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -711,7 +711,6 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter,
 	/* disable the queue */
 	wr32(IGC_TXDCTL(reg_idx), 0);
 	wrfl();
-	mdelay(10);
 
 	wr32(IGC_TDLEN(reg_idx),
 	     ring->count * sizeof(union igc_adv_tx_desc));
@@ -1017,7 +1016,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime,
 	ktime_t base_time = adapter->base_time;
 	ktime_t now = ktime_get_clocktai();
 	ktime_t baset_est, end_of_cycle;
-	u32 launchtime;
+	s32 launchtime;
 	s64 n;
 
 	n = div64_s64(ktime_sub_ns(now, base_time), cycle_time);
@@ -1030,7 +1029,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime,
 			*first_flag = true;
 			ring->last_ff_cycle = baset_est;
 
-			if (ktime_compare(txtime, ring->last_tx_cycle) > 0)
+			if (ktime_compare(end_of_cycle, ring->last_tx_cycle) > 0)
 				*insert_empty = true;
 		}
 	}
@@ -1573,16 +1572,12 @@ done:
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	if (tx_ring->max_sdu > 0) {
-		u32 max_sdu = 0;
-
-		max_sdu = tx_ring->max_sdu +
-			  (skb_vlan_tagged(first->skb) ? VLAN_HLEN : 0);
+	if (adapter->qbv_transition || tx_ring->oper_gate_closed)
+		goto out_drop;
 
-		if (first->bytecount > max_sdu) {
-			adapter->stats.txdrop++;
-			goto out_drop;
-		}
+	if (tx_ring->max_sdu > 0 && first->bytecount > tx_ring->max_sdu) {
+		adapter->stats.txdrop++;
+		goto out_drop;
 	}
 
 	if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) &&
@@ -3012,8 +3007,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		    time_after(jiffies, tx_buffer->time_stamp +
 		    (adapter->tx_timeout_factor * HZ)) &&
 		    !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) &&
-		    (rd32(IGC_TDH(tx_ring->reg_idx)) !=
-		     readl(tx_ring->tail))) {
+		    (rd32(IGC_TDH(tx_ring->reg_idx)) != readl(tx_ring->tail)) &&
+		    !tx_ring->oper_gate_closed) {
 			/* detected Tx unit hang */
 			netdev_err(tx_ring->netdev,
 				   "Detected Tx Unit Hang\n"
@@ -6102,7 +6097,10 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
 
 	adapter->base_time = 0;
 	adapter->cycle_time = NSEC_PER_SEC;
+	adapter->taprio_offload_enable = false;
 	adapter->qbv_config_change_errors = 0;
+	adapter->qbv_transition = false;
+	adapter->qbv_count = 0;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igc_ring *ring = adapter->tx_ring[i];
@@ -6110,6 +6108,8 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter)
 		ring->start_time = 0;
 		ring->end_time = NSEC_PER_SEC;
 		ring->max_sdu = 0;
+		ring->oper_gate_closed = false;
+		ring->admin_gate_closed = false;
 	}
 
 	return 0;
@@ -6121,27 +6121,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	bool queue_configured[IGC_MAX_TX_QUEUES] = { };
 	struct igc_hw *hw = &adapter->hw;
 	u32 start_time = 0, end_time = 0;
+	struct timespec64 now;
 	size_t n;
 	int i;
 
-	switch (qopt->cmd) {
-	case TAPRIO_CMD_REPLACE:
-		adapter->qbv_enable = true;
-		break;
-	case TAPRIO_CMD_DESTROY:
-		adapter->qbv_enable = false;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	if (!adapter->qbv_enable)
+	if (qopt->cmd == TAPRIO_CMD_DESTROY)
 		return igc_tsn_clear_schedule(adapter);
 
+	if (qopt->cmd != TAPRIO_CMD_REPLACE)
+		return -EOPNOTSUPP;
+
 	if (qopt->base_time < 0)
 		return -ERANGE;
 
-	if (igc_is_device_id_i225(hw) && adapter->base_time)
+	if (igc_is_device_id_i225(hw) && adapter->taprio_offload_enable)
 		return -EALREADY;
 
 	if (!validate_schedule(adapter, qopt))
@@ -6149,6 +6142,9 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 
 	adapter->cycle_time = qopt->cycle_time;
 	adapter->base_time = qopt->base_time;
+	adapter->taprio_offload_enable = true;
+
+	igc_ptp_read(adapter, &now);
 
 	for (n = 0; n < qopt->num_entries; n++) {
 		struct tc_taprio_sched_entry *e = &qopt->entries[n];
@@ -6184,7 +6180,10 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 				ring->start_time = start_time;
 			ring->end_time = end_time;
 
-			queue_configured[i] = true;
+			if (ring->start_time >= adapter->cycle_time)
+				queue_configured[i] = false;
+			else
+				queue_configured[i] = true;
 		}
 
 		start_time += e->interval;
@@ -6194,8 +6193,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	 * If not, set the start and end time to be end time.
 	 */
 	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		if (!is_base_time_past(qopt->base_time, &now)) {
+			ring->admin_gate_closed = false;
+		} else {
+			ring->oper_gate_closed = false;
+			ring->admin_gate_closed = false;
+		}
+
 		if (!queue_configured[i]) {
-			struct igc_ring *ring = adapter->tx_ring[i];
+			if (!is_base_time_past(qopt->base_time, &now))
+				ring->admin_gate_closed = true;
+			else
+				ring->oper_gate_closed = true;
 
 			ring->start_time = end_time;
 			ring->end_time = end_time;
@@ -6207,7 +6218,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 		struct net_device *dev = adapter->netdev;
 
 		if (qopt->max_sdu[i])
-			ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len;
+			ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len - ETH_TLEN;
 		else
 			ring->max_sdu = 0;
 	}
@@ -6327,6 +6338,8 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 {
 	struct igc_adapter *adapter = netdev_priv(dev);
 
+	adapter->tc_setup_type = type;
+
 	switch (type) {
 	case TC_QUERY_CAPS:
 		return igc_tc_query_caps(adapter, type_data);
@@ -6574,6 +6587,27 @@ static const struct xdp_metadata_ops igc_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
 };
 
+static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer)
+{
+	struct igc_adapter *adapter = container_of(timer, struct igc_adapter,
+						   hrtimer);
+	unsigned int i;
+
+	adapter->qbv_transition = true;
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		if (tx_ring->admin_gate_closed) {
+			tx_ring->admin_gate_closed = false;
+			tx_ring->oper_gate_closed = true;
+		} else {
+			tx_ring->oper_gate_closed = false;
+		}
+	}
+	adapter->qbv_transition = false;
+	return HRTIMER_NORESTART;
+}
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6752,6 +6786,9 @@ static int igc_probe(struct pci_dev *pdev,
 	INIT_WORK(&adapter->reset_task, igc_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igc_watchdog_task);
 
+	hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	adapter->hrtimer.function = &igc_qbv_scheduling_timer;
+
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
 	hw->mac.autoneg = true;
@@ -6855,6 +6892,7 @@ static void igc_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
+	hrtimer_cancel(&adapter->hrtimer);
 
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 32ef112f8291..f0b979a70655 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -356,16 +356,35 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
 			tsim &= ~IGC_TSICR_TT0;
 		}
 		if (on) {
+			struct timespec64 safe_start;
 			int i = rq->perout.index;
 
 			igc_pin_perout(igc, i, pin, use_freq);
-			igc->perout[i].start.tv_sec = rq->perout.start.sec;
+			igc_ptp_read(igc, &safe_start);
+
+			/* PPS output start time is triggered by Target time(TT)
+			 * register. Programming any past time value into TT
+			 * register will cause PPS to never start. Need to make
+			 * sure we program the TT register a time ahead in
+			 * future. There isn't a stringent need to fire PPS out
+			 * right away. Adding +2 seconds should take care of
+			 * corner cases. Let's say if the SYSTIML is close to
+			 * wrap up and the timer keeps ticking as we program the
+			 * register, adding +2seconds is safe bet.
+			 */
+			safe_start.tv_sec += 2;
+
+			if (rq->perout.start.sec < safe_start.tv_sec)
+				igc->perout[i].start.tv_sec = safe_start.tv_sec;
+			else
+				igc->perout[i].start.tv_sec = rq->perout.start.sec;
 			igc->perout[i].start.tv_nsec = rq->perout.start.nsec;
 			igc->perout[i].period.tv_sec = ts.tv_sec;
 			igc->perout[i].period.tv_nsec = ts.tv_nsec;
-			wr32(trgttimh, rq->perout.start.sec);
+			wr32(trgttimh, (u32)igc->perout[i].start.tv_sec);
 			/* For now, always select timer 0 as source. */
-			wr32(trgttiml, rq->perout.start.nsec | IGC_TT_IO_TIMER_SEL_SYSTIM0);
+			wr32(trgttiml, (u32)(igc->perout[i].start.tv_nsec |
+					     IGC_TT_IO_TIMER_SEL_SYSTIM0));
 			if (use_freq)
 				wr32(freqout, ns);
 			tsauxc |= tsauxc_mask;
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index 94a2b0dfb54d..a9c08321aca9 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -37,7 +37,7 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 {
 	unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED;
 
-	if (adapter->qbv_enable)
+	if (adapter->taprio_offload_enable)
 		new_flags |= IGC_FLAG_TSN_QBV_ENABLED;
 
 	if (is_any_launchtime(adapter))
@@ -114,7 +114,6 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
-	bool tsn_mode_reconfig = false;
 	u32 tqavctrl, baset_l, baset_h;
 	u32 sec, nsec, cycle;
 	ktime_t base_time, systim;
@@ -133,8 +132,28 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 		wr32(IGC_STQT(i), ring->start_time);
 		wr32(IGC_ENDQT(i), ring->end_time);
 
-		txqctl |= IGC_TXQCTL_STRICT_CYCLE |
-			IGC_TXQCTL_STRICT_END;
+		if (adapter->taprio_offload_enable) {
+			/* If taprio_offload_enable is set we are in "taprio"
+			 * mode and we need to be strict about the
+			 * cycles: only transmit a packet if it can be
+			 * completed during that cycle.
+			 *
+			 * If taprio_offload_enable is NOT true when
+			 * enabling TSN offload, the cycle should have
+			 * no external effects, but is only used internally
+			 * to adapt the base time register after a second
+			 * has passed.
+			 *
+			 * Enabling strict mode in this case would
+			 * unnecessarily prevent the transmission of
+			 * certain packets (i.e. at the boundary of a
+			 * second) and thus interfere with the launchtime
+			 * feature that promises transmission at a
+			 * certain point in time.
+			 */
+			txqctl |= IGC_TXQCTL_STRICT_CYCLE |
+				IGC_TXQCTL_STRICT_END;
+		}
 
 		if (ring->launchtime_enable)
 			txqctl |= IGC_TXQCTL_QUEUE_MODE_LAUNCHT;
@@ -228,11 +247,10 @@ skip_cbs:
 
 	tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS;
 
-	if (tqavctrl & IGC_TQAVCTRL_TRANSMIT_MODE_TSN)
-		tsn_mode_reconfig = true;
-
 	tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV;
 
+	adapter->qbv_count++;
+
 	cycle = adapter->cycle_time;
 	base_time = adapter->base_time;
 
@@ -249,17 +267,29 @@ skip_cbs:
 		 * Gate Control List (GCL) is running.
 		 */
 		if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
-		    tsn_mode_reconfig)
+		    (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) &&
+		    (adapter->qbv_count > 1))
 			adapter->qbv_config_change_errors++;
 	} else {
-		/* According to datasheet section 7.5.2.9.3.3, FutScdDis bit
-		 * has to be configured before the cycle time and base time.
-		 * Tx won't hang if there is a GCL is already running,
-		 * so in this case we don't need to set FutScdDis.
-		 */
-		if (igc_is_device_id_i226(hw) &&
-		    !(rd32(IGC_BASET_H) || rd32(IGC_BASET_L)))
-			tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS;
+		if (igc_is_device_id_i226(hw)) {
+			ktime_t adjust_time, expires_time;
+
+		       /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit
+			* has to be configured before the cycle time and base time.
+			* Tx won't hang if a GCL is already running,
+			* so in this case we don't need to set FutScdDis.
+			*/
+			if (!(rd32(IGC_BASET_H) || rd32(IGC_BASET_L)))
+				tqavctrl |= IGC_TQAVCTRL_FUTSCDDIS;
+
+			nsec = rd32(IGC_SYSTIML);
+			sec = rd32(IGC_SYSTIMH);
+			systim = ktime_set(sec, nsec);
+
+			adjust_time = adapter->base_time;
+			expires_time = ktime_sub_ns(adjust_time, systim);
+			hrtimer_start(&adapter->hrtimer, expires_time, HRTIMER_MODE_REL);
+		}
 	}
 
 	wr32(IGC_TQAVCTRL, tqavctrl);
@@ -305,7 +335,11 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 
-	if (netif_running(adapter->netdev) && igc_is_device_id_i225(hw)) {
+	/* Per I225/6 HW Design Section 7.5.2.1, transmit mode
+	 * cannot be changed dynamically. Require reset the adapter.
+	 */
+	if (netif_running(adapter->netdev) &&
+	    (igc_is_device_id_i225(hw) || !adapter->qbv_count)) {
 		schedule_work(&adapter->reset_task);
 		return 0;
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ff5647bcdfca..acf4f6ba73a6 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1511,7 +1511,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 			 */
 			if (txq_number == 1)
 				txq_map = (cpu == pp->rxq_def) ?
-					MVNETA_CPU_TXQ_ACCESS(1) : 0;
+					MVNETA_CPU_TXQ_ACCESS(0) : 0;
 
 		} else {
 			txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
@@ -4356,7 +4356,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 		 */
 		if (txq_number == 1)
 			txq_map = (cpu == elected_cpu) ?
-				MVNETA_CPU_TXQ_ACCESS(1) : 0;
+				MVNETA_CPU_TXQ_ACCESS(0) : 0;
 		else
 			txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
 				MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
index 3411e2e47d46..0ee420a489fc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c
@@ -208,7 +208,7 @@ struct ptp *ptp_get(void)
 	/* Check driver is bound to PTP block */
 	if (!ptp)
 		ptp = ERR_PTR(-EPROBE_DEFER);
-	else
+	else if (!IS_ERR(ptp))
 		pci_dev_get(ptp->pdev);
 
 	return ptp;
@@ -388,11 +388,10 @@ static int ptp_extts_on(struct ptp *ptp, int on)
 static int ptp_probe(struct pci_dev *pdev,
 		     const struct pci_device_id *ent)
 {
-	struct device *dev = &pdev->dev;
 	struct ptp *ptp;
 	int err;
 
-	ptp = devm_kzalloc(dev, sizeof(*ptp), GFP_KERNEL);
+	ptp = kzalloc(sizeof(*ptp), GFP_KERNEL);
 	if (!ptp) {
 		err = -ENOMEM;
 		goto error;
@@ -428,20 +427,19 @@ static int ptp_probe(struct pci_dev *pdev,
 	return 0;
 
 error_free:
-	devm_kfree(dev, ptp);
+	kfree(ptp);
 
 error:
 	/* For `ptp_get()` we need to differentiate between the case
 	 * when the core has not tried to probe this device and the case when
-	 * the probe failed.  In the later case we pretend that the
-	 * initialization was successful and keep the error in
+	 * the probe failed.  In the later case we keep the error in
 	 * `dev->driver_data`.
 	 */
 	pci_set_drvdata(pdev, ERR_PTR(err));
 	if (!first_ptp_block)
 		first_ptp_block = ERR_PTR(err);
 
-	return 0;
+	return err;
 }
 
 static void ptp_remove(struct pci_dev *pdev)
@@ -449,16 +447,17 @@ static void ptp_remove(struct pci_dev *pdev)
 	struct ptp *ptp = pci_get_drvdata(pdev);
 	u64 clock_cfg;
 
-	if (cn10k_ptp_errata(ptp) && hrtimer_active(&ptp->hrtimer))
-		hrtimer_cancel(&ptp->hrtimer);
-
 	if (IS_ERR_OR_NULL(ptp))
 		return;
 
+	if (cn10k_ptp_errata(ptp) && hrtimer_active(&ptp->hrtimer))
+		hrtimer_cancel(&ptp->hrtimer);
+
 	/* Disable PTP clock */
 	clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG);
 	clock_cfg &= ~PTP_CLOCK_CFG_PTP_EN;
 	writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG);
+	kfree(ptp);
 }
 
 static const struct pci_device_id ptp_id_table[] = {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 8dbc35c481f6..73df2d564545 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -3252,7 +3252,7 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	rvu->ptp = ptp_get();
 	if (IS_ERR(rvu->ptp)) {
 		err = PTR_ERR(rvu->ptp);
-		if (err == -EPROBE_DEFER)
+		if (err)
 			goto err_release_regions;
 		rvu->ptp = NULL;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 0d745ae1cc9a..04b0e885f9d2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -4069,21 +4069,14 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 	}
 
 	/* install/uninstall promisc entry */
-	if (promisc) {
+	if (promisc)
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base,
 					      pfvf->rx_chan_cnt);
-
-		if (rvu_npc_exact_has_match_table(rvu))
-			rvu_npc_exact_promisc_enable(rvu, pcifunc);
-	} else {
+	else
 		if (!nix_rx_multicast)
 			rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false);
 
-		if (rvu_npc_exact_has_match_table(rvu))
-			rvu_npc_exact_promisc_disable(rvu, pcifunc);
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
index 9f11c1e40737..6fe67f3a7f6f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
@@ -1164,8 +1164,10 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i
 {
 	struct npc_exact_table *table;
 	u16 *cnt, old_cnt;
+	bool promisc;
 
 	table = rvu->hw->table;
+	promisc = table->promisc_mode[drop_mcam_idx];
 
 	cnt = &table->cnt_cmd_rules[drop_mcam_idx];
 	old_cnt = *cnt;
@@ -1177,13 +1179,18 @@ static u16 __rvu_npc_exact_cmd_rules_cnt_update(struct rvu *rvu, int drop_mcam_i
 
 	*enable_or_disable_cam = false;
 
-	/* If all rules are deleted, disable cam */
+	if (promisc)
+		goto done;
+
+	/* If all rules are deleted and not already in promisc mode;
+	 * disable cam
+	 */
 	if (!*cnt && val < 0) {
 		*enable_or_disable_cam = true;
 		goto done;
 	}
 
-	/* If rule got added, enable cam */
+	/* If rule got added and not already in promisc mode; enable cam */
 	if (!old_cnt && val > 0) {
 		*enable_or_disable_cam = true;
 		goto done;
@@ -1462,6 +1469,12 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc)
 	*promisc = false;
 	mutex_unlock(&table->lock);
 
+	/* Enable drop rule */
+	rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX,
+					   true);
+
+	dev_dbg(rvu->dev, "%s: disabled  promisc mode (cgx=%d lmac=%d)\n",
+		__func__, cgx_id, lmac_id);
 	return 0;
 }
 
@@ -1503,6 +1516,12 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc)
 	*promisc = true;
 	mutex_unlock(&table->lock);
 
+	/*  disable drop rule */
+	rvu_npc_enable_mcam_by_entry_index(rvu, drop_mcam_idx, NIX_INTF_RX,
+					   false);
+
+	dev_dbg(rvu->dev, "%s: Enabled promisc mode (cgx=%d lmac=%d)\n",
+		__func__, cgx_id, lmac_id);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
index 10e11262d48a..2d7713a1a153 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c
@@ -872,6 +872,14 @@ static int otx2_prepare_flow_request(struct ethtool_rx_flow_spec *fsp,
 				return -EINVAL;
 
 			vlan_etype = be16_to_cpu(fsp->h_ext.vlan_etype);
+
+			/* Drop rule with vlan_etype == 802.1Q
+			 * and vlan_id == 0 is not supported
+			 */
+			if (vlan_etype == ETH_P_8021Q && !fsp->m_ext.vlan_tci &&
+			    fsp->ring_cookie == RX_CLS_FLOW_DISC)
+				return -EINVAL;
+
 			/* Only ETH_P_8021Q and ETH_P_802AD types supported */
 			if (vlan_etype != ETH_P_8021Q &&
 			    vlan_etype != ETH_P_8021AD)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 8a13df592af6..5e56b6c3e60a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -597,6 +597,21 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
 			return -EOPNOTSUPP;
 		}
 
+		if (!match.mask->vlan_id) {
+			struct flow_action_entry *act;
+			int i;
+
+			flow_action_for_each(i, act, &rule->action) {
+				if (act->id == FLOW_ACTION_DROP) {
+					netdev_err(nic->netdev,
+						   "vlan tpid 0x%x with vlan_id %d is not supported for DROP rule.\n",
+						   ntohs(match.key->vlan_tpid),
+						   match.key->vlan_id);
+					return -EOPNOTSUPP;
+				}
+			}
+		}
+
 		if (match.mask->vlan_id ||
 		    match.mask->vlan_dei ||
 		    match.mask->vlan_priority) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
index 03cb79adf912..be83ad9db82a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c
@@ -594,7 +594,7 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs)
 
 	err = fs_any_create_table(fs);
 	if (err)
-		return err;
+		goto err_free_any;
 
 	err = fs_any_enable(fs);
 	if (err)
@@ -606,8 +606,8 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs)
 
 err_destroy_table:
 	fs_any_destroy_table(fs_any);
-
-	kfree(fs_any);
+err_free_any:
 	mlx5e_fs_set_any(fs, NULL);
+	kfree(fs_any);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 3cbebfba582b..b0b429a0321e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -729,8 +729,10 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, dev_to_node(mlx5_core_dma_dev(mdev)));
 	cparams = kvzalloc(sizeof(*cparams), GFP_KERNEL);
-	if (!c || !cparams)
-		return -ENOMEM;
+	if (!c || !cparams) {
+		err = -ENOMEM;
+		goto err_free;
+	}
 
 	c->priv     = priv;
 	c->mdev     = priv->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index a254e728ac95..fadfa8b50beb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1545,7 +1545,8 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 
 	attr->ct_attr.ct_action |= act->ct.action; /* So we can have clear + ct */
 	attr->ct_attr.zone = act->ct.zone;
-	attr->ct_attr.nf_ft = act->ct.flow_table;
+	if (!(act->ct.action & TCA_CT_ACT_CLEAR))
+		attr->ct_attr.nf_ft = act->ct.flow_table;
 	attr->ct_attr.act_miss_cookie = act->miss_cookie;
 
 	return 0;
@@ -1990,6 +1991,9 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att
 	if (!priv)
 		return -EOPNOTSUPP;
 
+	if (attr->ct_attr.offloaded)
+		return 0;
+
 	if (attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR) {
 		err = mlx5_tc_ct_entry_set_registers(priv, &attr->parse_attr->mod_hdr_acts,
 						     0, 0, 0, 0);
@@ -1999,11 +2003,15 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 	}
 
-	if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */
+	if (!attr->ct_attr.nf_ft) { /* means only ct clear action, and not ct_clear,ct() */
+		attr->ct_attr.offloaded = true;
 		return 0;
+	}
 
 	mutex_lock(&priv->control_lock);
 	err = __mlx5_tc_ct_flow_offload(priv, attr);
+	if (!err)
+		attr->ct_attr.offloaded = true;
 	mutex_unlock(&priv->control_lock);
 
 	return err;
@@ -2021,7 +2029,7 @@ void
 mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5_flow_attr *attr)
 {
-	if (!attr->ct_attr.ft) /* no ct action, return */
+	if (!attr->ct_attr.offloaded) /* no ct action, return */
 		return;
 	if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 8e9316fa46d4..b66c5f98067f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -29,6 +29,7 @@ struct mlx5_ct_attr {
 	u32 ct_labels_id;
 	u32 act_miss_mapping;
 	u64 act_miss_cookie;
+	bool offloaded;
 	struct mlx5_ct_ft *ft;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index f0e6095809fa..40589cebb773 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -662,8 +662,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
 				 * as we know this is a page_pool page.
 				 */
-				page_pool_put_defragged_page(page->pp,
-							     page, -1, true);
+				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
 
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
index 88a5aed9d678..c7d191f66ad1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c
@@ -190,6 +190,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft,
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 704b022cd1f0..41d37159e027 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -390,10 +390,18 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	if (rq->xsk_pool)
+	if (rq->xsk_pool) {
 		mlx5e_xsk_free_rx_wqe(wi);
-	else
+	} else {
 		mlx5e_free_rx_wqe(rq, wi);
+
+		/* Avoid a second release of the wqe pages: dealloc is called
+		 * for the same missing wqes on regular RQ flush and on regular
+		 * RQ close. This happens when XSK RQs come into play.
+		 */
+		for (int i = 0; i < rq->wqe.info.num_frags; i++, wi++)
+			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+	}
 }
 
 static void mlx5e_xsk_free_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
@@ -1743,11 +1751,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
-		if (test_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			struct mlx5e_wqe_frag_info *pwi;
 
 			for (pwi = head_wi; pwi < wi; pwi++)
-				pwi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+				pwi->frag_page->frags++;
 		}
 		return NULL; /* page/packet was consumed by XDP */
 	}
@@ -1817,12 +1825,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
-		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			/* do not return page to cache,
-			 * it will be returned on XDP_TX completion.
-			 */
-			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
-		}
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+			wi->frag_page->frags++;
 		goto wq_cyc_pop;
 	}
 
@@ -1868,12 +1872,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
-		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			/* do not return page to cache,
-			 * it will be returned on XDP_TX completion.
-			 */
-			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
-		}
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+			wi->frag_page->frags++;
 		goto wq_cyc_pop;
 	}
 
@@ -2052,12 +2052,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	if (prog) {
 		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-				int i;
+				struct mlx5e_frag_page *pfp;
+
+				for (pfp = head_page; pfp < frag_page; pfp++)
+					pfp->frags++;
 
-				for (i = 0; i < sinfo->nr_frags; i++)
-					/* non-atomic */
-					__set_bit(page_idx + i, wi->skip_release_bitmap);
-				return NULL;
+				wi->linear_page.frags++;
 			}
 			mlx5e_page_release_fragmented(rq, &wi->linear_page);
 			return NULL; /* page/packet was consumed by XDP */
@@ -2155,7 +2155,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				 cqe_bcnt, &mxbuf);
 		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
-				__set_bit(page_idx, wi->skip_release_bitmap); /* non-atomic */
+				frag_page->frags++;
 			return NULL; /* page/packet was consumed by XDP */
 		}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 41dc26800f48..8d0a3f69693e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1639,7 +1639,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow)
 	uplink_priv = &rpriv->uplink_priv;
 
 	mutex_lock(&uplink_priv->unready_flows_lock);
-	unready_flow_del(flow);
+	if (flow_flag_test(flow, NOT_READY))
+		unready_flow_del(flow);
 	mutex_unlock(&uplink_priv->unready_flows_lock);
 }
 
@@ -1932,8 +1933,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	esw_attr = attr->esw_attr;
 	mlx5e_put_flow_tunnel_id(flow);
 
-	if (flow_flag_test(flow, NOT_READY))
-		remove_unready_flow(flow);
+	remove_unready_flow(flow);
 
 	if (mlx5e_is_offloaded_flow(flow)) {
 		if (flow_flag_test(flow, SLOW))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index faec7d7a4400..243c455f1029 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -807,6 +807,9 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
 	vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce);
 
+	if (!MLX5_CAP_GEN_MAX(esw->dev, hca_cap_2))
+		goto out_free;
+
 	memset(query_ctx, 0, query_out_sz);
 	err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx,
 					    MLX5_CAP_GENERAL_2);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c
index 20bb5eb266c1..52199d39657e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c
@@ -68,14 +68,19 @@ static struct thermal_zone_device_ops mlx5_thermal_ops = {
 
 int mlx5_thermal_init(struct mlx5_core_dev *mdev)
 {
+	char data[THERMAL_NAME_LENGTH];
 	struct mlx5_thermal *thermal;
-	struct thermal_zone_device *tzd;
-	const char *data = "mlx5";
+	int err;
 
-	tzd = thermal_zone_get_zone_by_name(data);
-	if (!IS_ERR(tzd))
+	if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev))
 		return 0;
 
+	err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device));
+	if (err < 0 || err >= sizeof(data)) {
+		mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err);
+		return -EINVAL;
+	}
+
 	thermal = kzalloc(sizeof(*thermal), GFP_KERNEL);
 	if (!thermal)
 		return -ENOMEM;
@@ -89,10 +94,10 @@ int mlx5_thermal_init(struct mlx5_core_dev *mdev)
 								 &mlx5_thermal_ops,
 								 NULL, 0, MLX5_THERMAL_POLL_INT_MSEC);
 	if (IS_ERR(thermal->tzdev)) {
-		dev_err(mdev->device, "Failed to register thermal zone device (%s) %ld\n",
-			data, PTR_ERR(thermal->tzdev));
+		err = PTR_ERR(thermal->tzdev);
+		mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err);
 		kfree(thermal);
-		return -EINVAL;
+		return err;
 	}
 
 	mdev->thermal = thermal;
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 24c994baad13..329e374b9539 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -46,7 +46,7 @@ config LAN743X
 	tristate "LAN743x support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
-	select PHYLIB
+	select FIXED_PHY
 	select CRC16
 	select CRC32
 	help
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 2fa833d041ba..56ccbd4c37fe 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -2927,7 +2927,6 @@ int ocelot_init(struct ocelot *ocelot)
 
 	mutex_init(&ocelot->mact_lock);
 	mutex_init(&ocelot->fwd_domain_lock);
-	mutex_init(&ocelot->tas_lock);
 	spin_lock_init(&ocelot->ptp_clock_lock);
 	spin_lock_init(&ocelot->ts_id_lock);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_mm.c b/drivers/net/ethernet/mscc/ocelot_mm.c
index fb3145118d68..c815ae64e39d 100644
--- a/drivers/net/ethernet/mscc/ocelot_mm.c
+++ b/drivers/net/ethernet/mscc/ocelot_mm.c
@@ -67,10 +67,13 @@ void ocelot_port_update_active_preemptible_tcs(struct ocelot *ocelot, int port)
 		val = mm->preemptible_tcs;
 
 	/* Cut through switching doesn't work for preemptible priorities,
-	 * so first make sure it is disabled.
+	 * so first make sure it is disabled. Also, changing the preemptible
+	 * TCs affects the oversized frame dropping logic, so that needs to be
+	 * re-triggered. And since tas_guard_bands_update() also implicitly
+	 * calls cut_through_fwd(), we don't need to explicitly call it.
 	 */
 	mm->active_preemptible_tcs = val;
-	ocelot->ops->cut_through_fwd(ocelot);
+	ocelot->ops->tas_guard_bands_update(ocelot, port);
 
 	dev_dbg(ocelot->dev,
 		"port %d %s/%s, MM TX %s, preemptible TCs 0x%x, active 0x%x\n",
@@ -89,17 +92,14 @@ void ocelot_port_change_fp(struct ocelot *ocelot, int port,
 {
 	struct ocelot_mm_state *mm = &ocelot->mm[port];
 
-	mutex_lock(&ocelot->fwd_domain_lock);
+	lockdep_assert_held(&ocelot->fwd_domain_lock);
 
 	if (mm->preemptible_tcs == preemptible_tcs)
-		goto out_unlock;
+		return;
 
 	mm->preemptible_tcs = preemptible_tcs;
 
 	ocelot_port_update_active_preemptible_tcs(ocelot, port);
-
-out_unlock:
-	mutex_unlock(&ocelot->fwd_domain_lock);
 }
 
 static void ocelot_mm_update_port_status(struct ocelot *ocelot, int port)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
index b8678da1cce5..ab7d217b98b3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
@@ -353,12 +353,6 @@ err_out_reset:
 	ionic_reset(ionic);
 err_out_teardown:
 	ionic_dev_teardown(ionic);
-	pci_clear_master(pdev);
-	/* Don't fail the probe for these errors, keep
-	 * the hw interface around for inspection
-	 */
-	return 0;
-
 err_out_unmap_bars:
 	ionic_unmap_bars(ionic);
 err_out_pci_release_regions:
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 7c20a44e549b..612b0015dc43 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -475,11 +475,6 @@ static void ionic_qcqs_free(struct ionic_lif *lif)
 static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq,
 				      struct ionic_qcq *n_qcq)
 {
-	if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) {
-		ionic_intr_free(n_qcq->cq.lif->ionic, n_qcq->intr.index);
-		n_qcq->flags &= ~IONIC_QCQ_F_INTR;
-	}
-
 	n_qcq->intr.vector = src_qcq->intr.vector;
 	n_qcq->intr.index = src_qcq->intr.index;
 	n_qcq->napi_qcq = src_qcq->napi_qcq;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index 12405d71c5ee..0772eb14eabf 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -186,9 +186,6 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum)
 	if (eeprom_ptrs)
 		kvfree(eeprom_ptrs);
 
-	if (*checksum > TXGBE_EEPROM_SUM)
-		return -EINVAL;
-
 	*checksum = TXGBE_EEPROM_SUM - *checksum;
 
 	return 0;
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 6045bece2654..b4d3b9cde8bd 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -184,13 +184,10 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file,
 	cookie_len = (count - 1) / 2;
 	if ((count - 1) % 2)
 		return -EINVAL;
-	buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
-	if (!buf)
-		return -ENOMEM;
 
-	ret = simple_write_to_buffer(buf, count, ppos, data, count);
-	if (ret < 0)
-		goto free_buf;
+	buf = memdup_user(data, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len,
 			    GFP_KERNEL | __GFP_NOWARN);
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index 7c4cc5f5e1eb..dbd13f7aa3e6 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -6157,8 +6157,11 @@ static int airo_get_rate(struct net_device *dev,
 	struct iw_param *vwrq = &wrqu->bitrate;
 	struct airo_info *local = dev->ml_priv;
 	StatusRid status_rid;		/* Card status info */
+	int ret;
 
-	readStatusRid(local, &status_rid, 1);
+	ret = readStatusRid(local, &status_rid, 1);
+	if (ret)
+		return -EBUSY;
 
 	vwrq->value = le16_to_cpu(status_rid.currentXmitRate) * 500000;
 	/* If more than one rate, set auto */
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index aa4320ca4c30..d594694206b3 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -84,7 +84,6 @@ const struct iwl_ht_params iwl_22000_ht_params = {
 	.mac_addr_from_csr = 0x380,					\
 	.ht_params = &iwl_22000_ht_params,				\
 	.nvm_ver = IWL_22000_NVM_VERSION,				\
-	.trans.use_tfh = true,						\
 	.trans.rf_id = true,						\
 	.trans.gen2 = true,						\
 	.nvm_type = IWL_NVM_EXT,					\
@@ -122,7 +121,6 @@ const struct iwl_ht_params iwl_22000_ht_params = {
 
 const struct iwl_cfg_trans_params iwl_qu_trans_cfg = {
 	.mq_rx_supported = true,
-	.use_tfh = true,
 	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
@@ -134,7 +132,6 @@ const struct iwl_cfg_trans_params iwl_qu_trans_cfg = {
 
 const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg = {
 	.mq_rx_supported = true,
-	.use_tfh = true,
 	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
@@ -146,7 +143,6 @@ const struct iwl_cfg_trans_params iwl_qu_medium_latency_trans_cfg = {
 
 const struct iwl_cfg_trans_params iwl_qu_long_latency_trans_cfg = {
 	.mq_rx_supported = true,
-	.use_tfh = true,
 	.rf_id = true,
 	.gen2 = true,
 	.device_family = IWL_DEVICE_FAMILY_22000,
@@ -200,7 +196,6 @@ const struct iwl_cfg_trans_params iwl_ax200_trans_cfg = {
 	.device_family = IWL_DEVICE_FAMILY_22000,
 	.base_params = &iwl_22000_base_params,
 	.mq_rx_supported = true,
-	.use_tfh = true,
 	.rf_id = true,
 	.gen2 = true,
 	.bisr_workaround = 1,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 742096c5a36a..241a9e3f2a1a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -256,7 +256,6 @@ enum iwl_cfg_trans_ltr_delay {
  * @xtal_latency: power up latency to get the xtal stabilized
  * @extra_phy_cfg_flags: extra configuration flags to pass to the PHY
  * @rf_id: need to read rf_id to determine the firmware image
- * @use_tfh: use TFH
  * @gen2: 22000 and on transport operation
  * @mq_rx_supported: multi-queue rx support
  * @integrated: discrete or integrated
@@ -271,7 +270,6 @@ struct iwl_cfg_trans_params {
 	u32 xtal_latency;
 	u32 extra_phy_cfg_flags;
 	u32 rf_id:1,
-	    use_tfh:1,
 	    gen2:1,
 	    mq_rx_supported:1,
 	    integrated:1,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index bedd78a47f67..4e4a60ddf9b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2021 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2021, 2023 Intel Corporation
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fh_h__
@@ -71,7 +71,7 @@
 static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
 					     unsigned int chnl)
 {
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		WARN_ON_ONCE(chnl >= 64);
 		return TFH_TFDQ_CBB_TABLE + 8 * chnl;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index b1af9359cea5..4bd759432d44 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2021 Intel Corporation
+ * Copyright (C) 2019-2021, 2023 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/bsearch.h>
@@ -42,7 +42,7 @@ struct iwl_trans *iwl_trans_alloc(unsigned int priv_size,
 
 	WARN_ON(!ops->wait_txq_empty && !ops->wait_tx_queues_empty);
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		trans->txqs.tfd.addr_size = 64;
 		trans->txqs.tfd.max_tbs = IWL_TFH_NUM_TBS;
 		trans->txqs.tfd.size = sizeof(struct iwl_tfh_tfd);
@@ -101,7 +101,7 @@ int iwl_trans_init(struct iwl_trans *trans)
 
 	/* Some things must not change even if the config does */
 	WARN_ON(trans->txqs.tfd.addr_size !=
-		(trans->trans_cfg->use_tfh ? 64 : 36));
+		(trans->trans_cfg->gen2 ? 64 : 36));
 
 	snprintf(trans->dev_cmd_pool_name, sizeof(trans->dev_cmd_pool_name),
 		 "iwl_cmd_pool:%s", dev_name(trans->dev));
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index b83df0631279..b18c91c5dd5d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1450,7 +1450,7 @@ static inline bool iwl_mvm_has_new_station_api(const struct iwl_fw *fw)
 static inline bool iwl_mvm_has_new_tx_api(struct iwl_mvm *mvm)
 {
 	/* TODO - replace with TLV once defined */
-	return mvm->trans->trans_cfg->use_tfh;
+	return mvm->trans->trans_cfg->gen2;
 }
 
 static inline bool iwl_mvm_has_unified_ucode(struct iwl_mvm *mvm)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index eacbbdbffb5e..3e988da44973 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -819,7 +819,7 @@ static int iwl_pcie_load_cpu_sections_8000(struct iwl_trans *trans,
 
 	iwl_enable_interrupts(trans);
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		if (cpu == 1)
 			iwl_write_prph(trans, UREG_UCODE_LOAD_STATUS,
 				       0xFFFF);
@@ -3394,7 +3394,7 @@ iwl_trans_pcie_dump_data(struct iwl_trans *trans,
 			u8 tfdidx;
 			u32 caplen, cmdlen;
 
-			if (trans->trans_cfg->use_tfh)
+			if (trans->trans_cfg->gen2)
 				tfdidx = idx;
 			else
 				tfdidx = ptr;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 1337fa95f657..790e5b124740 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -364,7 +364,7 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans)
 	for (txq_id = 0; txq_id < trans->trans_cfg->base_params->num_of_queues;
 	     txq_id++) {
 		struct iwl_txq *txq = trans->txqs.txq[txq_id];
-		if (trans->trans_cfg->use_tfh)
+		if (trans->trans_cfg->gen2)
 			iwl_write_direct64(trans,
 					   FH_MEM_CBBC_QUEUE(trans, txq_id),
 					   txq->dma_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
index fbacbe9ada15..5bb3cc3367c9 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c
@@ -985,7 +985,7 @@ void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 	bool active;
 	u8 fifo;
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
 			txq->read_ptr, txq->write_ptr);
 		/* TODO: access new SCD registers and dump them */
@@ -1040,7 +1040,7 @@ int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
 	if (WARN_ON(txq->entries || txq->tfds))
 		return -EINVAL;
 
-	if (trans->trans_cfg->use_tfh)
+	if (trans->trans_cfg->gen2)
 		tfd_sz = trans->txqs.tfd.size * slots_num;
 
 	timer_setup(&txq->stuck_timer, iwl_txq_stuck_timer, 0);
@@ -1347,7 +1347,7 @@ static inline dma_addr_t iwl_txq_gen1_tfd_tb_get_addr(struct iwl_trans *trans,
 	dma_addr_t addr;
 	dma_addr_t hi_len;
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		struct iwl_tfh_tfd *tfh_tfd = _tfd;
 		struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx];
 
@@ -1408,7 +1408,7 @@ void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
 
 	meta->tbs = 0;
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
 
 		tfd_fh->num_tbs = 0;
@@ -1625,7 +1625,7 @@ void iwl_txq_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		txq->entries[read_ptr].skb = NULL;
 
-		if (!trans->trans_cfg->use_tfh)
+		if (!trans->trans_cfg->gen2)
 			iwl_txq_gen1_inval_byte_cnt_tbl(trans, txq);
 
 		iwl_txq_free_tfd(trans, txq);
diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.h b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
index eca53bfd326d..1e4a24ab9bab 100644
--- a/drivers/net/wireless/intel/iwlwifi/queue/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2020-2022 Intel Corporation
+ * Copyright (C) 2020-2023 Intel Corporation
  */
 #ifndef __iwl_trans_queue_tx_h__
 #define __iwl_trans_queue_tx_h__
@@ -38,7 +38,7 @@ static inline void iwl_wake_queue(struct iwl_trans *trans,
 static inline void *iwl_txq_get_tfd(struct iwl_trans *trans,
 				    struct iwl_txq *txq, int idx)
 {
-	if (trans->trans_cfg->use_tfh)
+	if (trans->trans_cfg->gen2)
 		idx = iwl_txq_get_cmd_index(txq, idx);
 
 	return (u8 *)txq->tfds + trans->txqs.tfd.size * idx;
@@ -135,7 +135,7 @@ static inline u8 iwl_txq_gen1_tfd_get_num_tbs(struct iwl_trans *trans,
 {
 	struct iwl_tfd *tfd;
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		struct iwl_tfh_tfd *tfh_tfd = _tfd;
 
 		return le16_to_cpu(tfh_tfd->num_tbs) & 0x1f;
@@ -151,7 +151,7 @@ static inline u16 iwl_txq_gen1_tfd_tb_get_len(struct iwl_trans *trans,
 	struct iwl_tfd *tfd;
 	struct iwl_tfd_tb *tb;
 
-	if (trans->trans_cfg->use_tfh) {
+	if (trans->trans_cfg->gen2) {
 		struct iwl_tfh_tfd *tfh_tfd = _tfd;
 		struct iwl_tfh_tb *tfh_tb = &tfh_tfd->tbs[idx];
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
index f0a80c2b476a..4153cd6c2a01 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c
@@ -231,10 +231,6 @@ int mt7921_dma_init(struct mt7921_dev *dev)
 	if (ret)
 		return ret;
 
-	ret = mt7921_wfsys_reset(dev);
-	if (ret)
-		return ret;
-
 	/* init tx queue */
 	ret = mt76_connac_init_tx_queues(dev->phy.mt76, MT7921_TXQ_BAND0,
 					 MT7921_TX_RING_SIZE,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index c69ce6df4956..f55caa00ac69 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -476,12 +476,6 @@ static int mt7921_load_firmware(struct mt7921_dev *dev)
 {
 	int ret;
 
-	ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY);
-	if (ret && mt76_is_mmio(&dev->mt76)) {
-		dev_dbg(dev->mt76.dev, "Firmware is already download\n");
-		goto fw_loaded;
-	}
-
 	ret = mt76_connac2_load_patch(&dev->mt76, mt7921_patch_name(dev));
 	if (ret)
 		return ret;
@@ -504,8 +498,6 @@ static int mt7921_load_firmware(struct mt7921_dev *dev)
 		return -EIO;
 	}
 
-fw_loaded:
-
 #ifdef CONFIG_PM
 	dev->mt76.hw->wiphy->wowlan = &mt76_connac_wowlan_support;
 #endif /* CONFIG_PM */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index ddb1fa4ee01d..95610a117d2f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -325,6 +325,10 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 	bus_ops->rmw = mt7921_rmw;
 	dev->mt76.bus = bus_ops;
 
+	ret = mt7921e_mcu_fw_pmctrl(dev);
+	if (ret)
+		goto err_free_dev;
+
 	ret = __mt7921e_mcu_drv_pmctrl(dev);
 	if (ret)
 		goto err_free_dev;
@@ -333,6 +337,10 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		    (mt7921_l1_rr(dev, MT_HW_REV) & 0xff);
 	dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev);
 
+	ret = mt7921_wfsys_reset(dev);
+	if (ret)
+		goto err_free_dev;
+
 	mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0);
 
 	mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff);
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 1db2d59d33ff..a4bbac916e22 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3026,17 +3026,18 @@ static ssize_t rtw89_debug_priv_send_h2c_set(struct file *filp,
 	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	u8 *h2c;
+	int ret;
 	u16 h2c_len = count / 2;
 
 	h2c = rtw89_hex2bin_user(rtwdev, user_buf, count);
 	if (IS_ERR(h2c))
 		return -EFAULT;
 
-	rtw89_fw_h2c_raw(rtwdev, h2c, h2c_len);
+	ret = rtw89_fw_h2c_raw(rtwdev, h2c, h2c_len);
 
 	kfree(h2c);
 
-	return count;
+	return ret ? ret : count;
 }
 
 static int
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 9b5fccdbc7d6..6df7f377d2f9 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -36,7 +36,7 @@ static const struct smcd_ops ism_ops;
 static struct ism_client *clients[MAX_CLIENTS];	/* use an array rather than */
 						/* a list for fast mapping  */
 static u8 max_client;
-static DEFINE_SPINLOCK(clients_lock);
+static DEFINE_MUTEX(clients_lock);
 struct ism_dev_list {
 	struct list_head list;
 	struct mutex mutex; /* protects ism device list */
@@ -47,14 +47,22 @@ static struct ism_dev_list ism_dev_list = {
 	.mutex = __MUTEX_INITIALIZER(ism_dev_list.mutex),
 };
 
+static void ism_setup_forwarding(struct ism_client *client, struct ism_dev *ism)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ism->lock, flags);
+	ism->subs[client->id] = client;
+	spin_unlock_irqrestore(&ism->lock, flags);
+}
+
 int ism_register_client(struct ism_client *client)
 {
 	struct ism_dev *ism;
-	unsigned long flags;
 	int i, rc = -ENOSPC;
 
 	mutex_lock(&ism_dev_list.mutex);
-	spin_lock_irqsave(&clients_lock, flags);
+	mutex_lock(&clients_lock);
 	for (i = 0; i < MAX_CLIENTS; ++i) {
 		if (!clients[i]) {
 			clients[i] = client;
@@ -65,12 +73,14 @@ int ism_register_client(struct ism_client *client)
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&clients_lock, flags);
+	mutex_unlock(&clients_lock);
+
 	if (i < MAX_CLIENTS) {
 		/* initialize with all devices that we got so far */
 		list_for_each_entry(ism, &ism_dev_list.list, list) {
 			ism->priv[i] = NULL;
 			client->add(ism);
+			ism_setup_forwarding(client, ism);
 		}
 	}
 	mutex_unlock(&ism_dev_list.mutex);
@@ -86,25 +96,32 @@ int ism_unregister_client(struct ism_client *client)
 	int rc = 0;
 
 	mutex_lock(&ism_dev_list.mutex);
-	spin_lock_irqsave(&clients_lock, flags);
-	clients[client->id] = NULL;
-	if (client->id + 1 == max_client)
-		max_client--;
-	spin_unlock_irqrestore(&clients_lock, flags);
 	list_for_each_entry(ism, &ism_dev_list.list, list) {
+		spin_lock_irqsave(&ism->lock, flags);
+		/* Stop forwarding IRQs and events */
+		ism->subs[client->id] = NULL;
 		for (int i = 0; i < ISM_NR_DMBS; ++i) {
 			if (ism->sba_client_arr[i] == client->id) {
-				pr_err("%s: attempt to unregister client '%s'"
-				       "with registered dmb(s)\n", __func__,
-				       client->name);
+				WARN(1, "%s: attempt to unregister '%s' with registered dmb(s)\n",
+				     __func__, client->name);
 				rc = -EBUSY;
-				goto out;
+				goto err_reg_dmb;
 			}
 		}
+		spin_unlock_irqrestore(&ism->lock, flags);
 	}
-out:
 	mutex_unlock(&ism_dev_list.mutex);
 
+	mutex_lock(&clients_lock);
+	clients[client->id] = NULL;
+	if (client->id + 1 == max_client)
+		max_client--;
+	mutex_unlock(&clients_lock);
+	return rc;
+
+err_reg_dmb:
+	spin_unlock_irqrestore(&ism->lock, flags);
+	mutex_unlock(&ism_dev_list.mutex);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ism_unregister_client);
@@ -328,6 +345,7 @@ int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb,
 		     struct ism_client *client)
 {
 	union ism_reg_dmb cmd;
+	unsigned long flags;
 	int ret;
 
 	ret = ism_alloc_dmb(ism, dmb);
@@ -351,7 +369,9 @@ int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb,
 		goto out;
 	}
 	dmb->dmb_tok = cmd.response.dmb_tok;
+	spin_lock_irqsave(&ism->lock, flags);
 	ism->sba_client_arr[dmb->sba_idx - ISM_DMB_BIT_OFFSET] = client->id;
+	spin_unlock_irqrestore(&ism->lock, flags);
 out:
 	return ret;
 }
@@ -360,6 +380,7 @@ EXPORT_SYMBOL_GPL(ism_register_dmb);
 int ism_unregister_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 {
 	union ism_unreg_dmb cmd;
+	unsigned long flags;
 	int ret;
 
 	memset(&cmd, 0, sizeof(cmd));
@@ -368,7 +389,9 @@ int ism_unregister_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
 
 	cmd.request.dmb_tok = dmb->dmb_tok;
 
+	spin_lock_irqsave(&ism->lock, flags);
 	ism->sba_client_arr[dmb->sba_idx - ISM_DMB_BIT_OFFSET] = NO_CLIENT;
+	spin_unlock_irqrestore(&ism->lock, flags);
 
 	ret = ism_cmd(ism, &cmd);
 	if (ret && ret != ISM_ERROR)
@@ -491,6 +514,7 @@ static u16 ism_get_chid(struct ism_dev *ism)
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct ism_event *entry;
+	struct ism_client *clt;
 	int i;
 
 	while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) {
@@ -499,21 +523,21 @@ static void ism_handle_event(struct ism_dev *ism)
 
 		entry = &ism->ieq->entry[ism->ieq_idx];
 		debug_event(ism_debug_info, 2, entry, sizeof(*entry));
-		spin_lock(&clients_lock);
-		for (i = 0; i < max_client; ++i)
-			if (clients[i])
-				clients[i]->handle_event(ism, entry);
-		spin_unlock(&clients_lock);
+		for (i = 0; i < max_client; ++i) {
+			clt = ism->subs[i];
+			if (clt)
+				clt->handle_event(ism, entry);
+		}
 	}
 }
 
 static irqreturn_t ism_handle_irq(int irq, void *data)
 {
 	struct ism_dev *ism = data;
-	struct ism_client *clt;
 	unsigned long bit, end;
 	unsigned long *bv;
 	u16 dmbemask;
+	u8 client_id;
 
 	bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET];
 	end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET;
@@ -530,8 +554,10 @@ static irqreturn_t ism_handle_irq(int irq, void *data)
 		dmbemask = ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET];
 		ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0;
 		barrier();
-		clt = clients[ism->sba_client_arr[bit]];
-		clt->handle_irq(ism, bit + ISM_DMB_BIT_OFFSET, dmbemask);
+		client_id = ism->sba_client_arr[bit];
+		if (unlikely(client_id == NO_CLIENT || !ism->subs[client_id]))
+			continue;
+		ism->subs[client_id]->handle_irq(ism, bit + ISM_DMB_BIT_OFFSET, dmbemask);
 	}
 
 	if (ism->sba->e) {
@@ -548,20 +574,9 @@ static u64 ism_get_local_gid(struct ism_dev *ism)
 	return ism->local_gid;
 }
 
-static void ism_dev_add_work_func(struct work_struct *work)
-{
-	struct ism_client *client = container_of(work, struct ism_client,
-						 add_work);
-
-	client->add(client->tgt_ism);
-	atomic_dec(&client->tgt_ism->add_dev_cnt);
-	wake_up(&client->tgt_ism->waitq);
-}
-
 static int ism_dev_init(struct ism_dev *ism)
 {
 	struct pci_dev *pdev = ism->pdev;
-	unsigned long flags;
 	int i, ret;
 
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
@@ -594,25 +609,16 @@ static int ism_dev_init(struct ism_dev *ism)
 		/* hardware is V2 capable */
 		ism_create_system_eid();
 
-	init_waitqueue_head(&ism->waitq);
-	atomic_set(&ism->free_clients_cnt, 0);
-	atomic_set(&ism->add_dev_cnt, 0);
-
-	wait_event(ism->waitq, !atomic_read(&ism->add_dev_cnt));
-	spin_lock_irqsave(&clients_lock, flags);
-	for (i = 0; i < max_client; ++i)
+	mutex_lock(&ism_dev_list.mutex);
+	mutex_lock(&clients_lock);
+	for (i = 0; i < max_client; ++i) {
 		if (clients[i]) {
-			INIT_WORK(&clients[i]->add_work,
-				  ism_dev_add_work_func);
-			clients[i]->tgt_ism = ism;
-			atomic_inc(&ism->add_dev_cnt);
-			schedule_work(&clients[i]->add_work);
+			clients[i]->add(ism);
+			ism_setup_forwarding(clients[i], ism);
 		}
-	spin_unlock_irqrestore(&clients_lock, flags);
-
-	wait_event(ism->waitq, !atomic_read(&ism->add_dev_cnt));
+	}
+	mutex_unlock(&clients_lock);
 
-	mutex_lock(&ism_dev_list.mutex);
 	list_add(&ism->list, &ism_dev_list.list);
 	mutex_unlock(&ism_dev_list.mutex);
 
@@ -687,36 +693,24 @@ err_dev:
 	return ret;
 }
 
-static void ism_dev_remove_work_func(struct work_struct *work)
-{
-	struct ism_client *client = container_of(work, struct ism_client,
-						 remove_work);
-
-	client->remove(client->tgt_ism);
-	atomic_dec(&client->tgt_ism->free_clients_cnt);
-	wake_up(&client->tgt_ism->waitq);
-}
-
-/* Callers must hold ism_dev_list.mutex */
 static void ism_dev_exit(struct ism_dev *ism)
 {
 	struct pci_dev *pdev = ism->pdev;
 	unsigned long flags;
 	int i;
 
-	wait_event(ism->waitq, !atomic_read(&ism->free_clients_cnt));
-	spin_lock_irqsave(&clients_lock, flags);
+	spin_lock_irqsave(&ism->lock, flags);
 	for (i = 0; i < max_client; ++i)
-		if (clients[i]) {
-			INIT_WORK(&clients[i]->remove_work,
-				  ism_dev_remove_work_func);
-			clients[i]->tgt_ism = ism;
-			atomic_inc(&ism->free_clients_cnt);
-			schedule_work(&clients[i]->remove_work);
-		}
-	spin_unlock_irqrestore(&clients_lock, flags);
+		ism->subs[i] = NULL;
+	spin_unlock_irqrestore(&ism->lock, flags);
 
-	wait_event(ism->waitq, !atomic_read(&ism->free_clients_cnt));
+	mutex_lock(&ism_dev_list.mutex);
+	mutex_lock(&clients_lock);
+	for (i = 0; i < max_client; ++i) {
+		if (clients[i])
+			clients[i]->remove(ism);
+	}
+	mutex_unlock(&clients_lock);
 
 	if (SYSTEM_EID.serial_number[0] != '0' ||
 	    SYSTEM_EID.type[0] != '0')
@@ -727,15 +721,14 @@ static void ism_dev_exit(struct ism_dev *ism)
 	kfree(ism->sba_client_arr);
 	pci_free_irq_vectors(pdev);
 	list_del_init(&ism->list);
+	mutex_unlock(&ism_dev_list.mutex);
 }
 
 static void ism_remove(struct pci_dev *pdev)
 {
 	struct ism_dev *ism = dev_get_drvdata(&pdev->dev);
 
-	mutex_lock(&ism_dev_list.mutex);
 	ism_dev_exit(ism);
-	mutex_unlock(&ism_dev_list.mutex);
 
 	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
author	Linus Torvalds <torvalds@linux-foundation.org>	2023-07-13 14:21:22 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2023-07-13 14:21:22 -0700
commit	b1983d427a53911ea71ba621d4bf994ae22b1536 (patch)
tree	78edb0049c5d1a2243e738203d5de01b39513aff /drivers
parent	ebc27aaceeb9c4c988dbf321e849fcb75c6b55fa (diff)
parent	9d23aac8a85f69239e585c8656c6fdb21be65695 (diff)
download	linux-b1983d427a53911ea71ba621d4bf994ae22b1536.tar.gz linux-b1983d427a53911ea71ba621d4bf994ae22b1536.tar.bz2 linux-b1983d427a53911ea71ba621d4bf994ae22b1536.zip