Merge tag 'net-7.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter.

  Looks like our attempt to keep the PRs smaller have only prevented
  this one from getting even bigger. In the last 9 days there were
  405 postings explicitly tagged with [PATCH net], vs 687 with [PATCH
  net-next]. 37% of posted patches being fixes is pretty crazy, and
  that's likely undercounting because LLM "researchers" more often post
  fixes without knowing to tag the patches for specific trees. I don't
  have historic data.

  In any case, we keep adjusting the criteria. The next PR will be
  smaller.

  Current release - regressions:

   - net: defer netdev KOBJ_ADD uevent until the device is published,
     previously rtnl_lock would serialize the accesses vs publishing

   - net: explicitly cancel work to avoid races with ref tracker exit

   - qrtr: ns: raise lookup limit to 128

   - eth: hns3: fix speed configuration residue after driver reload

  Previous releases - regressions:

   - tcp: do not change rcv_ssthresh in tcp_measure_rcv_mss(), regressed
     flows with MSS and scaling_ratio variability

   - Revert "net: thunderbolt: Enable end-to-end flow control also in
     transmit", broke some platforms (no packets coming thru)

   - eth: stmmac: resume PHY before hardware setup when opening the
     interface

  Previous releases - always broken:

   - another pile of fixes for less common protocols (SCTP, TLS, SMC
     etc.)

   - close a couple of AF_PACKET bugs and ways it can build skbs
     problematic for the rest of the stack

   - bridge: mrp: fix uninitialised bytes on the wire

   - net: devmem: prevent net-iov / page mixing, avoid crashes

   - eth: atlantic: free RX pages of consumed but not refilled buffers"

* tag 'net-7.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (116 commits)
  igc: fix netdev not re-attached after resume if interface is down
  tls: don't abort the connection on signal-interrupted sends
  net: avoid theoretical races with ref drain
  net: Defer netdev KOBJ_ADD uevent until the device is published
  MAINTAINERS: dpll: zl3073x: replace Prathosh Satish with Min Li
  sctp: clear control chunk transport if it is being removed
  net/atm: fix slab-out-of-bounds read in vcc_setsockopt()
  s390/ism: Fix UAF of sba and ieq during ism_dev_exit()
  packet: use consistent hard_header_len in TX_RING send path
  packet: use consistent hard_header_len in non-ring send paths
  net: remove CAP_SYS_RAWIO zero-padding in dev_validate_header
  bnge: Fix resource leak in bnge_init_nic() error path
  ptp: ocp: Fix board ID over-read
  tls: rx: restore msg_iter before TLS 1.3 optimistic retry
  selftests: tls: add a test for splicing onto a full plaintext record
  tls: don't leave a full plaintext sk_msg ring unpushed
  xdp: reject clones that overrun skb_shared_info tailroom
  mptcp: reclaim forward-allocated memory on RX path errors
  mptcp: fastopen: only mark MPTFO subflows with SYN data
  mptcp: pm: fix memory leak from alloc-during-teardown race
  ...

31 files changed, 253 insertions, 75 deletions

diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index b7fe9ad73349..a1d41329209f 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -171,6 +171,7 @@ struct pdsc {
 	struct timer_list wdtimer;
 	unsigned int wdtimer_period;
 	struct work_struct health_work;
+	bool health_stopped;
 	struct devlink_health_reporter *fw_reporter;
 	u32 fw_recoveries;
 
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index 8d94a4d70395..9a2c64198d03 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -470,8 +470,10 @@ static void pdsc_stop_health_thread(struct pdsc *pdsc)
 		return;
 
 	timer_shutdown_sync(&pdsc->wdtimer);
-	if (pdsc->health_work.func)
-		cancel_work_sync(&pdsc->health_work);
+	if (pdsc->health_work.func && !pdsc->health_stopped) {
+		disable_work_sync(&pdsc->health_work);
+		pdsc->health_stopped = true;
+	}
 }
 
 static void pdsc_restart_health_thread(struct pdsc *pdsc)
@@ -479,6 +481,10 @@ static void pdsc_restart_health_thread(struct pdsc *pdsc)
 	if (pdsc->pdev->is_virtfn)
 		return;
 
+	if (pdsc->health_stopped) {
+		enable_work(&pdsc->health_work);
+		pdsc->health_stopped = false;
+	}
 	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
 	mod_timer(&pdsc->wdtimer, jiffies + 1);
 }
@@ -555,7 +561,11 @@ static pci_ers_result_t pdsc_pci_error_detected(struct pci_dev *pdev,
 						pci_channel_state_t error)
 {
 	if (error == pci_channel_io_frozen) {
+		struct pdsc *pdsc = pci_get_drvdata(pdev);
+
 		pdsc_reset_prepare(pdev);
+		if (!pdev->is_virtfn)
+			cancel_work_sync(&pdsc->pci_reset_work);
 		return PCI_ERS_RESULT_NEED_RESET;
 	}
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 8ff07de2bd52..e1193c6719d9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -360,6 +360,35 @@ out:
 	return !!budget;
 }
 
+void aq_ring_tx_deinit(struct aq_ring_s *self)
+{
+	if (!self)
+		return;
+
+	for (; self->sw_head != self->sw_tail;
+		self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
+		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
+		struct device *ndev = aq_nic_get_dev(self->aq_nic);
+
+		if (buff->is_mapped) {
+			if (buff->is_sop) {
+				dma_unmap_single(ndev, buff->pa, buff->len,
+						 DMA_TO_DEVICE);
+			} else {
+				dma_unmap_page(ndev, buff->pa, buff->len,
+					       DMA_TO_DEVICE);
+			}
+		}
+
+		if (buff->is_eop) {
+			if (buff->skb)
+				dev_kfree_skb_any(buff->skb);
+			else if (buff->xdpf)
+				xdp_return_frame(buff->xdpf);
+		}
+	}
+}
+
 static void aq_rx_checksum(struct aq_ring_s *self,
 			   struct aq_ring_buff_s *buff,
 			   struct sk_buff *skb)
@@ -921,15 +950,29 @@ err_exit:
 
 void aq_ring_rx_deinit(struct aq_ring_s *self)
 {
-	if (!self)
+	unsigned int i;
+
+	if (!self || !self->buff_ring)
 		return;
 
-	for (; self->sw_head != self->sw_tail;
-		self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
-		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
+	/* Release every page still owned by the ring.
+	 *
+	 * Walking [sw_head, sw_tail) is not enough: refill is batched
+	 * (aq_ring_rx_fill() waits for AQ_CFG_RX_REFILL_THRES free slots),
+	 * so slots that were cleaned but not yet reposted accumulate in the
+	 * [sw_tail, sw_head) gap, and they keep their page for reuse. Walk
+	 * the whole ring and release whatever is left.
+	 */
+	for (i = 0; i < self->size; i++) {
+		struct aq_ring_buff_s *buff = &self->buff_ring[i];
+
+		if (!buff->rxdata.page)
+			continue;
 
 		aq_free_rxpage(&buff->rxdata, aq_nic_get_dev(self->aq_nic));
 	}
+
+	self->sw_head = self->sw_tail;
 }
 
 void aq_ring_free(struct aq_ring_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index a70b880ada67..6431cc62962f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -202,6 +202,7 @@ void aq_ring_update_queue_state(struct aq_ring_s *ring);
 void aq_ring_queue_wake(struct aq_ring_s *ring);
 void aq_ring_queue_stop(struct aq_ring_s *ring);
 bool aq_ring_tx_clean(struct aq_ring_s *self);
+void aq_ring_tx_deinit(struct aq_ring_s *self);
 int aq_xdp_xmit(struct net_device *dev, int num_frames,
 		struct xdp_frame **frames, u32 flags);
 int aq_ring_rx_clean(struct aq_ring_s *self,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index 2f9033ceed8c..05814fea0f5f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -275,7 +275,7 @@ void aq_vec_deinit(struct aq_vec_s *self)
 
 	for (i = 0U; self->tx_rings > i; ++i) {
 		ring = self->ring[i];
-		aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]);
+		aq_ring_tx_deinit(&ring[AQ_VEC_TX_ID]);
 		aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c
index 67e93e17d4d9..0955b488b6fe 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_auxr.c
@@ -141,12 +141,15 @@ static void bnge_aux_dev_release(struct device *dev)
 {
 	struct bnge_auxr_priv *aux_priv =
 			container_of(dev, struct bnge_auxr_priv, aux_dev.dev);
-	struct bnge_dev *bd = pci_get_drvdata(aux_priv->auxr_dev->pdev);
+	struct bnge_auxr_dev *auxr_dev = aux_priv->auxr_dev;
+	struct bnge_dev *bd = pci_get_drvdata(to_pci_dev(dev->parent));
 
 	ida_free(&bnge_aux_dev_ids, aux_priv->id);
-	kfree(aux_priv->auxr_dev->auxr_info);
+	if (auxr_dev) {
+		kfree(auxr_dev->auxr_info);
+		kfree(auxr_dev);
+	}
 	bd->auxr_dev = NULL;
-	kfree(aux_priv->auxr_dev);
 	kfree(aux_priv);
 	bd->aux_priv = NULL;
 }
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
index 6f7ef506d4e1..ac4c93e5b634 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c
@@ -2768,8 +2768,6 @@ static int bnge_init_nic(struct bnge_net *bn)
 
 err_free_ring_grps:
 	bnge_free_ring_grps(bn);
-	return rc;
-
 err_free_rx_ring_pair_bufs:
 	bnge_free_rx_ring_pair_bufs(bn);
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c
index 0e94f092813e..4711dd4945ff 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_resc.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_resc.c
@@ -163,7 +163,8 @@ static int bnge_adjust_rings(struct bnge_dev *bd, u16 *rx,
 	u16 tx_chunks = bnge_num_tx_to_cp(bd, *tx);
 
 	if (tx_chunks != *tx) {
-		u16 tx_saved = tx_chunks, rc;
+		u16 tx_saved = tx_chunks;
+		int rc;
 
 		rc = bnge_fix_rings_count(rx, &tx_chunks, max_nq, sh);
 		if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7513618793da..25099077fe4f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4611,11 +4611,14 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp,
 		type = ((u32)rxr->rx_page_size << RX_BD_LEN_SHIFT) |
 			RX_BD_TYPE_RX_AGG_BD;
 
-		/* On P7, setting EOP will cause the chip to disable
-		 * Relaxed Ordering (RO) for TPA data.  Disable EOP for
-		 * potentially higher performance with RO.
+		/* Disable EOP if TPA is enabled to prevent overlapping zero
+		 * padding with the next segment's data.  On P7_PLUS, EOP will
+		 * automatically disable Relaxed Ordering (RO) to prevent
+		 * potential data corruption (and may degrade performance).  On
+		 * older chips, RO will not be automatically disabled and may
+		 * cause corruption.
 		 */
-		if (BNXT_CHIP_P5_AND_MINUS(bp) || !(bp->flags & BNXT_FLAG_TPA))
+		if (!(bp->flags & BNXT_FLAG_TPA))
 			type |= RX_BD_FLAGS_AGG_EOP;
 
 		bnxt_init_rxbd_pages(ring, type);
@@ -6704,22 +6707,36 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings)
 static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG);
-	u16 i, j;
+	u16 i, j, min_j = bp->rx_nr_rings - 1;
+
+	if (!vnic->rss_table)
+		goto skip_rss_tbl;
 
 	/* Fill the RSS indirection table with ring group ids */
 	for (i = 0, j = 0; i < HW_HASH_INDEX_SIZE; i++) {
 		if (!no_rss)
 			j = bp->rss_indir_tbl[i];
+		min_j = min(j, min_j);
 		vnic->rss_table[i] = cpu_to_le16(vnic->fw_grp_ids[j]);
 	}
+
+skip_rss_tbl:
+	if (vnic->rss_table && !no_rss)
+		vnic->default_rx_ring = min_j;
+	else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
+		vnic->default_rx_ring = vnic->vnic_id - 1;
+	else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
+		vnic->default_rx_ring = bp->rx_nr_rings - 1;
+	else
+		vnic->default_rx_ring = 0;
 }
 
 static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
 				    struct bnxt_vnic_info *vnic)
 {
+	u16 tbl_size, i, min_j = bp->rx_nr_rings - 1;
 	__le16 *ring_tbl = vnic->rss_table;
 	struct bnxt_rx_ring_info *rxr;
-	u16 tbl_size, i;
 
 	tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
 
@@ -6732,6 +6749,7 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
 			j = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
 		else
 			j = bp->rss_indir_tbl[i];
+		min_j = min(j, min_j);
 		rxr = &bp->rx_ring[j];
 
 		ring_id = rxr->rx_ring_struct.fw_ring_id;
@@ -6739,19 +6757,15 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
 		ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		*ring_tbl++ = cpu_to_le16(ring_id);
 	}
+	vnic->default_rx_ring = min_j;
 }
 
 static void
 __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
 			 struct bnxt_vnic_info *vnic)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-		bnxt_fill_hw_rss_tbl_p5(bp, vnic);
-		if (bp->flags & BNXT_FLAG_CHIP_P7)
-			req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT;
-	} else {
-		bnxt_fill_hw_rss_tbl(bp, vnic);
-	}
+	if (bp->flags & BNXT_FLAG_CHIP_P7)
+		req->flags |= VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT;
 
 	if (bp->rss_hash_delta) {
 		req->hash_type = cpu_to_le32(bp->rss_hash_delta);
@@ -6803,6 +6817,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp,
 	if (!set_rss)
 		return hwrm_req_send(bp, req);
 
+	bnxt_fill_hw_rss_tbl_p5(bp, vnic);
 	__bnxt_hwrm_vnic_set_rss(bp, req, vnic);
 	ring_tbl_map = vnic->rss_table_dma_addr;
 	nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings);
@@ -6939,8 +6954,9 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 		return rc;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[0];
+		struct bnxt_rx_ring_info *rxr;
 
+		rxr = &bp->rx_ring[vnic->default_rx_ring];
 		req->default_rx_ring_id =
 			cpu_to_le16(rxr->rx_ring_struct.fw_ring_id);
 		req->default_cmpl_ring_id =
@@ -6973,13 +6989,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 		req->cos_rule = cpu_to_le16(0xffff);
 	}
 
-	if (vnic->flags & BNXT_VNIC_RSS_FLAG)
-		ring = 0;
-	else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
-		ring = vnic->vnic_id - 1;
-	else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
-		ring = bp->rx_nr_rings - 1;
-
+	ring = vnic->default_rx_ring;
 	grp_idx = bp->rx_ring[ring].bnapi->index;
 	req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
 	req->lb_rule = cpu_to_le16(0xffff);
@@ -10866,6 +10876,7 @@ static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	}
 
 skip_rss_ctx:
+	bnxt_fill_hw_rss_tbl(bp, vnic);
 	/* configure default vnic, ring grp */
 	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
@@ -11090,6 +11101,11 @@ static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
 				   vnic->vnic_id, rc);
 			return rc;
 		}
+		if (rxr_id == vnic->default_rx_ring) {
+			rc = bnxt_hwrm_vnic_cfg(bp, vnic);
+			if (rc)
+				return rc;
+		}
 	}
 	vnic->mru = mru;
 	bnxt_hwrm_vnic_update(bp, vnic,
@@ -11171,6 +11187,9 @@ static int bnxt_setup_nitroa0_vnic(struct bnxt *bp)
 		return rc;
 	}
 
+	/* Setup the proper default RX ring */
+	bnxt_fill_hw_rss_tbl(bp, vnic);
+
 	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
 		netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
@@ -16217,6 +16236,7 @@ static int bnxt_queue_mem_alloc(struct net_device *dev,
 	clone->rx_next_cons = 0;
 	clone->need_head_pool = false;
 	clone->rx_page_size = qcfg->rx_page_size;
+	clone->rx_agg_bmap = NULL;
 
 	rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid);
 	if (rc)
@@ -16269,6 +16289,8 @@ err_free_tpa_info:
 	bnxt_free_one_tpa_info(bp, clone);
 err_free_rx_agg_ring:
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
+	kfree(clone->rx_agg_bmap);
+	clone->rx_agg_bmap = NULL;
 err_free_rx_ring:
 	bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem);
 err_rxq_info_unreg:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6335dfc14c98..44ea8fc7b766 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1334,6 +1334,7 @@ struct bnxt_vnic_info {
 #define BNXT_VNIC_RSSCTX_FLAG		0x40
 	struct ethtool_rxfh_context *rss_ctx;
 	u32		vnic_id;
+	u16		default_rx_ring;
 };
 
 struct bnxt_rss_ctx {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 5d41dc1bc782..b89293dfd2d1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -495,12 +495,15 @@ static int bnxt_ptp_enable(struct ptp_clock_info *ptp_info,
 		return rc;
 	case PTP_CLK_REQ_PPS:
 		/* Configure PHC PPS IN */
-		rc = bnxt_ptp_cfg_pin(bp, 0, BNXT_PPS_PIN_PPS_IN);
+		pin_id = 0;
+		if (!on)
+			break;
+		rc = bnxt_ptp_cfg_pin(bp, pin_id, BNXT_PPS_PIN_PPS_IN);
 		if (rc)
 			return rc;
 		rc = bnxt_ptp_cfg_event(bp, BNXT_PPS_EVENT_INTERNAL);
 		if (!rc)
-			ptp->pps_info.pins[0].event = BNXT_PPS_EVENT_INTERNAL;
+			ptp->pps_info.pins[pin_id].event = BNXT_PPS_EVENT_INTERNAL;
 		return rc;
 	default:
 		netdev_err(ptp->bp->dev, "Unrecognized PIN function\n");
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index e7125b818087..d98f7e7ccab9 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -3011,8 +3011,9 @@ static void enic_remove(struct pci_dev *pdev)
 	if (netdev) {
 		struct enic *enic = netdev_priv(netdev);
 
-		cancel_work_sync(&enic->reset);
-		cancel_work_sync(&enic->change_mtu_work);
+		disable_work_sync(&enic->reset);
+		disable_work_sync(&enic->tx_hang_reset);
+		disable_work_sync(&enic->change_mtu_work);
 		unregister_netdev(netdev);
 		enic_dev_deinit(enic);
 		vnic_dev_close(enic->vdev);
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index e3e7f2270560..02282dc86faf 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1282,7 +1282,6 @@ static void hix5hd2_dev_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct hix5hd2_priv *priv = netdev_priv(ndev);
 
-	netif_napi_del(&priv->napi);
 	unregister_netdev(ndev);
 	mdiobus_unregister(priv->bus);
 	mdiobus_free(priv->bus);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fc8587c80813..164c3ecf195c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -9498,12 +9498,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	if (ret)
 		goto err_ptp_uninit;
 
-	if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER) {
+	if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_COPPER)
 		hdev->hw.mac.req_autoneg = hdev->hw.mac.autoneg;
-		if (hdev->hw.mac.autoneg == AUTONEG_DISABLE &&
-		    hdev->hw.mac.speed != SPEED_UNKNOWN)
-			hdev->hw.mac.req_speed = hdev->hw.mac.speed;
-	}
 
 	ret = hclge_set_autoneg_speed_dup(hdev);
 	if (ret) {
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index b3883a5a7d7a..39043d8ca1bf 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3082,7 +3082,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		meta_req.tx_buffer = bi;
 		meta_req.meta = meta;
 		meta_req.used_desc = 0;
-		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
+		xsk_tx_metadata_request(pool, &meta, &igc_xsk_tx_metadata_ops,
 					&meta_req);
 
 		/* xsk_tx_metadata_request() may have updated next_to_use */
@@ -7585,11 +7585,13 @@ static int __igc_resume(struct device *dev, bool rpm)
 		err = __igc_open(netdev, true);
 		if (!rpm)
 			rtnl_unlock();
-		if (!err)
-			netif_device_attach(netdev);
+		if (err)
+			return err;
 	}
 
-	return err;
+	netif_device_attach(netdev);
+
+	return 0;
 }
 
 static int igc_resume(struct device *dev)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 0b46ec29e64e..039fd47ebf52 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -54,10 +54,12 @@ static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
 	if (burst) {
 		*burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0;
 		tmp = burst - rounddown_pow_of_two(burst);
-		if (burst < max_mantissa)
+		if (burst <= max_mantissa) {
 			*burst_mantissa = tmp * 2;
-		else
+		} else {
+			WARN_ON(*burst_exp < 7);
 			*burst_mantissa = tmp / (1ULL << (*burst_exp - 7));
+		}
 	} else {
 		*burst_exp = MAX_BURST_EXPONENT;
 		*burst_mantissa = max_mantissa;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
index 2989a77e3b42..1ad0e62a8433 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c
@@ -684,6 +684,9 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw)
 	struct prestera_fw_header *hdr;
 	u32 magic;
 
+	if (fw->bin->size < sizeof(*hdr))
+		return -EINVAL;
+
 	hdr = (struct prestera_fw_header *)fw->bin->data;
 
 	magic = be32_to_cpu(hdr->magic_number);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index adcc73e2a5b3..1493d8106c1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1025,13 +1025,11 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 
 	tracer = kvzalloc_obj(*tracer);
 	if (!tracer)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
-	if (!tracer->work_queue) {
-		err = -ENOMEM;
+	if (!tracer->work_queue)
 		goto free_tracer;
-	}
 
 	tracer->dev = dev;
 
@@ -1073,7 +1071,7 @@ destroy_workqueue:
 	destroy_workqueue(tracer->work_queue);
 free_tracer:
 	kvfree(tracer);
-	return ERR_PTR(err);
+	return NULL;
 }
 
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
@@ -1084,7 +1082,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 	struct mlx5_core_dev *dev;
 	int err;
 
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return 0;
 
 	if (!tracer->str_db.loaded)
@@ -1134,7 +1132,7 @@ err_cancel_work:
 /* Stop tracer + Cleanup HW resources */
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 {
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return;
 
 	mutex_lock(&tracer->state_lock);
@@ -1163,7 +1161,7 @@ unlock:
 /* Free software resources (Buffers, etc ..) */
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 {
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return;
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
@@ -1215,7 +1213,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
 	struct mlx5_core_dev *dev;
 	int err;
 
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return 0;
 
 	dev = tracer->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 6867a5aed42c..822859c360e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -483,7 +483,7 @@ typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
 typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
 					struct mlx5e_xmit_data *,
 					int,
-					struct xsk_tx_metadata *);
+					struct xsk_tx_metadata **);
 
 struct mlx5e_xdpsq {
 	/* data path */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 28cab4bf525c..7bfe7cdc5770 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -30,6 +30,7 @@ enum {
 	MLX5E_TC_FLOW_FLAG_FAILED                = MLX5E_TC_FLOW_BASE + 9,
 	MLX5E_TC_FLOW_FLAG_SAMPLE                = MLX5E_TC_FLOW_BASE + 10,
 	MLX5E_TC_FLOW_FLAG_USE_ACT_STATS         = MLX5E_TC_FLOW_BASE + 11,
+	MLX5E_TC_FLOW_FLAG_PEER                  = MLX5E_TC_FLOW_BASE + 12,
 };
 
 struct mlx5e_tc_flow_parse_attr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index d8c7cb8837d7..77ea51bfbaae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -452,11 +452,11 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-		     int check_result, struct xsk_tx_metadata *meta);
+		     int check_result, struct xsk_tx_metadata **meta);
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-			   int check_result, struct xsk_tx_metadata *meta)
+			   int check_result, struct xsk_tx_metadata **meta)
 {
 	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
@@ -504,7 +504,10 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 		 * and it's safe to complete it at any time.
 		 */
 		mlx5e_xdp_mpwqe_session_start(sq);
-		xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, &session->wqe->eth);
+		if (meta)
+			xsk_tx_metadata_request(sq->xsk_pool, meta,
+						&mlx5e_xsk_tx_metadata_ops,
+						&session->wqe->eth);
 	}
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
@@ -535,7 +538,7 @@ INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
 
 INDIRECT_CALLABLE_SCOPE bool
 mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
-		     int check_result, struct xsk_tx_metadata *meta)
+		     int check_result, struct xsk_tx_metadata **meta)
 {
 	struct mlx5e_xmit_data_frags *xdptxdf =
 		container_of(xdptxd, struct mlx5e_xmit_data_frags, xd);
@@ -649,7 +652,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	sq->pc += num_wqebbs;
 
-	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
+	if (meta)
+		xsk_tx_metadata_request(sq->xsk_pool, meta,
+					&mlx5e_xsk_tx_metadata_ops, eseg);
 
 	sq->doorbell_cseg = cseg;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 3c54f8962664..5b8f4094d553 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -114,11 +114,11 @@ extern const struct xsk_tx_metadata_ops mlx5e_xsk_tx_metadata_ops;
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 							  struct mlx5e_xmit_data *xdptxd,
 							  int check_result,
-							  struct xsk_tx_metadata *meta));
+							  struct xsk_tx_metadata **meta));
 INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
 						    struct mlx5e_xmit_data *xdptxd,
 						    int check_result,
-						    struct xsk_tx_metadata *meta));
+						    struct xsk_tx_metadata **meta));
 INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq));
 INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq));
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 8aeab4b21035..3d19dad8f868 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -105,7 +105,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 
 		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
 				      mlx5e_xmit_xdp_frame, sq, &xdptxd,
-				      check_result, meta);
+				      check_result, &meta);
 		if (unlikely(!ret)) {
 			if (sq->mpwqe.wqe)
 				mlx5e_xdp_mpwqe_complete(sq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7d47a1da8b6b..f0407a850ea8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1939,8 +1939,10 @@ err_free_txqsq:
 void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 {
 	sq->txq = netdev_get_tx_queue(sq->netdev, sq->txq_ix);
+	/* Reset BQL only when the SQ has no bytes in flight. */
+	if (sq->cc == sq->pc)
+		netdev_tx_reset_queue(sq->txq);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	netdev_tx_reset_queue(sq->txq);
 	netif_tx_start_queue(sq->txq);
 	netif_queue_set_napi(sq->netdev, sq->txq_ix, NETDEV_QUEUE_TYPE_TX, sq->cq.napi);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1bc7b9019124..b290beb4369a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2161,7 +2161,8 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 	if (mlx5e_is_eswitch_flow(flow)) {
 		struct mlx5_devcom_comp_dev *devcom = flow->priv->mdev->priv.eswitch->devcom;
 
-		if (!mlx5_devcom_for_each_peer_begin(devcom)) {
+		if (flow_flag_test(flow, PEER) ||
+		    !mlx5_devcom_for_each_peer_begin(devcom)) {
 			mlx5e_tc_del_fdb_flow(priv, flow);
 			return;
 		}
@@ -4628,6 +4629,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
 	else
 		in_mdev = priv->mdev;
 
+	flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_PEER);
 	parse_attr = flow->attr->parse_attr;
 	peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
 					 parse_attr->filter_dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 907ee83a722d..247e5d85ec36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3986,7 +3986,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 }
 
-static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
+static void esw_changed_event_handler(struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_pf_info host_pf_info;
 	u16 new_num_vfs;
@@ -3999,6 +3999,11 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
 	host_pf_info = mlx5_esw_get_host_pf_info(esw->dev, out);
 	new_num_vfs = host_pf_info.num_of_vfs;
 
+	if (host_pf_info.pf_disabled) {
+		mlx5_sf_table_esw_changed_event_handler(esw->dev);
+		mlx5_sf_hw_table_esw_changed_event_handler(esw->dev);
+	}
+
 	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_info.pf_disabled)
 		goto free;
 
@@ -4091,8 +4096,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb,
 	esw_funcs = mlx5_nb_cof(nb, struct mlx5_esw_functions, nb);
 	esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);
 
-	ret = mlx5_esw_add_work(esw, esw_vfs_changed_event_handler,
-				GFP_ATOMIC);
+	ret = mlx5_esw_add_work(esw, esw_changed_event_handler, GFP_ATOMIC);
 	if (ret)
 		return NOTIFY_DONE;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index b6cecbcc392d..4564d460416b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -561,3 +561,32 @@ bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
 
 	return xa_empty(&table->function_ids);
 }
+
+void mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+	unsigned long index;
+	struct mlx5_sf *sf;
+
+	trace_mlx5_sf_host_pf_disabled(dev);
+
+	if (!table)
+		return;
+
+	mutex_lock(&table->sf_state_lock);
+	xa_for_each(&table->function_ids, index, sf) {
+		if (!sf->controller)
+			continue;
+
+		if (sf->hw_state == MLX5_VHCA_STATE_IN_USE)
+			sf->hw_state = MLX5_VHCA_STATE_ACTIVE;
+		else if (sf->hw_state == MLX5_VHCA_STATE_TEARDOWN_REQUEST)
+			sf->hw_state = MLX5_VHCA_STATE_ALLOCATED;
+		else
+			continue;
+		trace_mlx5_sf_update_state(table->dev, sf->port_index,
+					   sf->controller, sf->hw_fn_id,
+					   sf->hw_state);
+	}
+	mutex_unlock(&table->sf_state_lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
index 302ce00da5a9..9dc88a7e30ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/diag/sf_tracepoint.h
@@ -11,6 +11,14 @@
 #include <linux/mlx5/driver.h>
 #include "sf/vhca_event.h"
 
+TRACE_EVENT(mlx5_sf_host_pf_disabled,
+	    TP_PROTO(const struct mlx5_core_dev *dev),
+	    TP_ARGS(dev),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))),
+	    TP_fast_assign(__assign_str(devname);),
+	    TP_printk("(%s)\n", __get_str(devname))
+);
+
 TRACE_EVENT(mlx5_sf_add,
 	    TP_PROTO(const struct mlx5_core_dev *dev,
 		     unsigned int port_index,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index 0bc9146a3598..95a8b1e64ba4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -459,3 +459,25 @@ bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev)
 {
 	return !!dev->priv.sf_hw_table;
 }
+
+void mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_hw_table *table;
+	struct mlx5_sf_hwc_table *hwc;
+	int i;
+
+	table = dev->priv.sf_hw_table;
+	if (!table)
+		return;
+
+	mutex_lock(&table->table_lock);
+	hwc = &table->hwc[MLX5_SF_HWC_EXT_HOST];
+	for (i = 0; i < hwc->max_fn; i++) {
+		struct mlx5_sf_hw *sf_hw;
+
+		sf_hw = &hwc->sfs[i];
+		if (sf_hw->allocated && sf_hw->pending_delete)
+			mlx5_sf_hw_table_hwc_sf_free(dev, hwc, i);
+	}
+	mutex_unlock(&table->table_lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index d8a934a0e968..ed784682b9b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -15,12 +15,14 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev);
 
 int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev);
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
 bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
+void mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev);
 
 int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     const struct devlink_port_new_attrs *add_attr,
@@ -60,6 +62,11 @@ static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 {
 }
 
+static inline void
+mlx5_sf_hw_table_esw_changed_event_handler(struct mlx5_core_dev *dev)
+{
+}
+
 static inline int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev)
 {
 	return 0;
@@ -83,6 +90,11 @@ static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
 	return true;
 }
 
+static inline void
+mlx5_sf_table_esw_changed_event_handler(struct mlx5_core_dev *dev)
+{
+}
+
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3801f9d45278..a71f0df26378 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2748,8 +2748,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		meta_req.set_ic = &set_ic;
 		meta_req.tbs = tx_q->tbs;
 		meta_req.edesc = &tx_q->dma_entx[entry];
-		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
-					&meta_req);
+		xsk_tx_metadata_request(pool, &meta,
+					&stmmac_xsk_tx_metadata_ops, &meta_req);
 		if (set_ic) {
 			tx_q->tx_count_frames = 0;
 			stmmac_set_tx_ic(priv, tx_desc);
@@ -4134,6 +4134,15 @@ static int __stmmac_open(struct net_device *dev,
 			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
 	memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf));
 
+	/* The PHY is suspended when the interface is reopened without
+	 * disconnecting the PHY, e.g. on MTU change. IEEE 802.3 allows PHYs
+	 * to stop their receive clock while powered down, but the DMA
+	 * software reset in stmmac_hw_setup() requires a running receive
+	 * clock, and phylink_start() below resumes the PHY only after the
+	 * hardware setup. Resume a suspended PHY here first.
+	 */
+	phylink_prepare_resume(priv->phylink);
+
 	stmmac_reset_queues_param(priv);
 
 	ret = stmmac_hw_setup(dev);