Merge tag 'net-6.11-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter.

  There is a recently notified BT regression with no fix yet. I do not
  think a fix will land in the next week.

  Current release - regressions:

   - core: tighten bad gso csum offset check in virtio_net_hdr

   - netfilter: move nf flowtable bpf initialization in
     nf_flow_table_module_init()

   - eth: ice: stop calling pci_disable_device() as we use pcim

   - eth: fou: fix null-ptr-deref in GRO.

  Current release - new code bugs:

   - hsr: prevent NULL pointer dereference in hsr_proxy_announce()

  Previous releases - regressions:

   - hsr: remove seqnr_lock

   - netfilter: nft_socket: fix sk refcount leaks

   - mptcp: pm: fix uaf in __timer_delete_sync

   - phy: dp83822: fix NULL pointer dereference on DP83825 devices

   - eth: revert "virtio_net: rx enable premapped mode by default"

   - eth: octeontx2-af: Modify SMQ flush sequence to drop packets

  Previous releases - always broken:

   - eth: mlx5: fix bridge mode operations when there are no VFs

   - eth: igb: Always call igb_xdp_ring_update_tail() under Tx lock"

* tag 'net-6.11-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (36 commits)
  net: netfilter: move nf flowtable bpf initialization in nf_flow_table_module_init()
  net: tighten bad gso csum offset check in virtio_net_hdr
  netlink: specs: mptcp: fix port endianness
  net: dpaa: Pad packets to ETH_ZLEN
  mptcp: pm: Fix uaf in __timer_delete_sync
  net: libwx: fix number of Rx and Tx descriptors
  net: dsa: felix: ignore pending status of TAS module when it's disabled
  net: hsr: prevent NULL pointer dereference in hsr_proxy_announce()
  selftests: mptcp: include net_helper.sh file
  selftests: mptcp: include lib.sh file
  selftests: mptcp: join: restrict fullmesh endp on 1st sf
  netfilter: nft_socket: make cgroupsv2 matching work with namespaces
  netfilter: nft_socket: fix sk refcount leaks
  MAINTAINERS: Add ethtool pse-pd to PSE NETWORK DRIVER
  dt-bindings: net: tja11xx: fix the broken binding
  selftests: net: csum: Fix checksums for packets with non-zero padding
  net: phy: dp83822: Fix NULL pointer dereference on DP83825 devices
  virtio_net: disable premapped mode by default
  Revert "virtio_net: big mode skip the unmap check"
  Revert "virtio_net: rx remove premapped failover code"
  ...

34 files changed, 364 insertions, 190 deletions

diff --git a/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml
index 85bfa45f5122..a754a61adc2d 100644
--- a/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml
+++ b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml
@@ -14,8 +14,53 @@ maintainers:
 description:
   Bindings for NXP TJA11xx automotive PHYs
 
+properties:
+  compatible:
+    enum:
+      - ethernet-phy-id0180.dc40
+      - ethernet-phy-id0180.dc41
+      - ethernet-phy-id0180.dc48
+      - ethernet-phy-id0180.dd00
+      - ethernet-phy-id0180.dd01
+      - ethernet-phy-id0180.dd02
+      - ethernet-phy-id0180.dc80
+      - ethernet-phy-id0180.dc82
+      - ethernet-phy-id001b.b010
+      - ethernet-phy-id001b.b013
+      - ethernet-phy-id001b.b030
+      - ethernet-phy-id001b.b031
+
 allOf:
   - $ref: ethernet-phy.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - ethernet-phy-id0180.dc40
+              - ethernet-phy-id0180.dc41
+              - ethernet-phy-id0180.dc48
+              - ethernet-phy-id0180.dd00
+              - ethernet-phy-id0180.dd01
+              - ethernet-phy-id0180.dd02
+
+    then:
+      properties:
+        nxp,rmii-refclk-in:
+          type: boolean
+          description: |
+            The REF_CLK is provided for both transmitted and received data
+            in RMII mode. This clock signal is provided by the PHY and is
+            typically derived from an external 25MHz crystal. Alternatively,
+            a 50MHz clock signal generated by an external oscillator can be
+            connected to pin REF_CLK. A third option is to connect a 25MHz
+            clock to pin CLK_IN_OUT. So, the REF_CLK should be configured
+            as input or output according to the actual circuit connection.
+            If present, indicates that the REF_CLK will be configured as
+            interface reference clock input when RMII mode enabled.
+            If not present, the REF_CLK will be configured as interface
+            reference clock output when RMII mode enabled.
+            Only supported on TJA1100 and TJA1101.
 
 patternProperties:
   "^ethernet-phy@[0-9a-f]+$":
@@ -32,22 +77,6 @@ patternProperties:
         description:
           The ID number for the child PHY. Should be +1 of parent PHY.
 
-      nxp,rmii-refclk-in:
-        type: boolean
-        description: |
-          The REF_CLK is provided for both transmitted and received data
-          in RMII mode. This clock signal is provided by the PHY and is
-          typically derived from an external 25MHz crystal. Alternatively,
-          a 50MHz clock signal generated by an external oscillator can be
-          connected to pin REF_CLK. A third option is to connect a 25MHz
-          clock to pin CLK_IN_OUT. So, the REF_CLK should be configured
-          as input or output according to the actual circuit connection.
-          If present, indicates that the REF_CLK will be configured as
-          interface reference clock input when RMII mode enabled.
-          If not present, the REF_CLK will be configured as interface
-          reference clock output when RMII mode enabled.
-          Only supported on TJA1100 and TJA1101.
-
     required:
       - reg
 
@@ -60,6 +89,7 @@ examples:
         #size-cells = <0>;
 
         tja1101_phy0: ethernet-phy@4 {
+            compatible = "ethernet-phy-id0180.dc40";
             reg = <0x4>;
             nxp,rmii-refclk-in;
         };
diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index af525ed29792..30d8342cacc8 100644
--- a/Documentation/netlink/specs/mptcp_pm.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -109,7 +109,6 @@ attribute-sets:
       -
         name: port
         type: u16
-        byte-order: big-endian
       -
         name: flags
         type: u32
diff --git a/MAINTAINERS b/MAINTAINERS
index 10430778c998..f70987f7e462 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18407,6 +18407,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/pse-pd/
 F:	drivers/net/pse-pd/
+F:	net/ethtool/pse-pd.c
 
 PSTORE FILESYSTEM
 M:	Kees Cook <kees@kernel.org>
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index ba37a566da39..ecfa73725d25 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1474,10 +1474,13 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
 	/* Hardware errata -  Admin config could not be overwritten if
 	 * config is pending, need reset the TAS module
 	 */
-	val = ocelot_read(ocelot, QSYS_PARAM_STATUS_REG_8);
-	if (val & QSYS_PARAM_STATUS_REG_8_CONFIG_PENDING) {
-		ret = -EBUSY;
-		goto err_reset_tc;
+	val = ocelot_read_rix(ocelot, QSYS_TAG_CONFIG, port);
+	if (val & QSYS_TAG_CONFIG_ENABLE) {
+		val = ocelot_read(ocelot, QSYS_PARAM_STATUS_REG_8);
+		if (val & QSYS_PARAM_STATUS_REG_8_CONFIG_PENDING) {
+			ret = -EBUSY;
+			goto err_reset_tc;
+		}
 	}
 
 	ocelot_rmw_rix(ocelot,
diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h
index 63b3e02fab16..4968f6f0bdbc 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.h
+++ b/drivers/net/ethernet/faraday/ftgmac100.h
@@ -84,7 +84,7 @@
 			    FTGMAC100_INT_RPKT_BUF)
 
 /* All the interrupts we care about */
-#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF  |  \
+#define FTGMAC100_INT_ALL (FTGMAC100_INT_RXTX  |  \
 			   FTGMAC100_INT_BAD)
 
 /*
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index cfe6b57b1da0..4a55e521c17e 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2272,12 +2272,12 @@ static netdev_tx_t
 dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 {
 	const int queue_mapping = skb_get_queue_mapping(skb);
-	bool nonlinear = skb_is_nonlinear(skb);
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa_percpu_priv *percpu_priv;
 	struct netdev_queue *txq;
 	struct dpaa_priv *priv;
 	struct qm_fd fd;
+	bool nonlinear;
 	int offset = 0;
 	int err = 0;
 
@@ -2287,6 +2287,13 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 
 	qm_fd_clear_fd(&fd);
 
+	/* Packet data is always read as 32-bit words, so zero out any part of
+	 * the skb which might be sent if we have to pad the packet
+	 */
+	if (__skb_put_padto(skb, ETH_ZLEN, false))
+		goto enomem;
+
+	nonlinear = skb_is_nonlinear(skb);
 	if (!nonlinear) {
 		/* We're going to store the skb backpointer at the beginning
 		 * of the data buffer, so we need a privately owned skb
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 737c00b02dd0..2405e5ed9128 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2413,13 +2413,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	int err;
 
-	/* The Rx rule will only exist to remove if the LLDP FW
-	 * engine is currently stopped
-	 */
-	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
-	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
-		ice_cfg_sw_lldp(vsi, false, false);
-
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
 	if (err)
@@ -2764,6 +2757,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
 		ice_rss_clean(vsi);
 
 	ice_vsi_close(vsi);
+
+	/* The Rx rule will only exist to remove if the LLDP FW
+	 * engine is currently stopped
+	 */
+	if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
+	    !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+		ice_cfg_sw_lldp(vsi, false, false);
+
 	ice_vsi_decfg(vsi);
 
 	/* retain SW VSI data structure since it is needed to unregister and
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c7db88b517da..ea780d468579 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5363,7 +5363,6 @@ err_load:
 	ice_deinit(pf);
 err_init:
 	ice_adapter_put(pdev);
-	pci_disable_device(pdev);
 	return err;
 }
 
@@ -5470,7 +5469,6 @@ static void ice_remove(struct pci_dev *pdev)
 	ice_set_wake(pf);
 
 	ice_adapter_put(pdev);
-	pci_disable_device(pdev);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index fe8847184cb1..79d91e95358c 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3194,7 +3194,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
-			return 0;
+			return -EEXIST;
 
 		/* Update the previously created VSI list set with
 		 * the new VSI ID passed in
@@ -3264,7 +3264,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
 
 	list_head = &sw->recp_list[recp_id].filt_rules;
 	list_for_each_entry(list_itr, list_head, list_entry) {
-		if (list_itr->vsi_list_info) {
+		if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) {
 			map_info = list_itr->vsi_list_info;
 			if (test_bit(vsi_handle, map_info->vsi_map)) {
 				*vsi_list_id = map_info->vsi_list_id;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9dc7c60838ed..1ef4cb871452 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -33,6 +33,7 @@
 #include <linux/bpf_trace.h>
 #include <linux/pm_runtime.h>
 #include <linux/etherdevice.h>
+#include <linux/lockdep.h>
 #ifdef CONFIG_IGB_DCA
 #include <linux/dca.h>
 #endif
@@ -2914,8 +2915,11 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+/* This function assumes __netif_tx_lock is held by the caller. */
 static void igb_xdp_ring_update_tail(struct igb_ring *ring)
 {
+	lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
 	 */
@@ -3000,11 +3004,11 @@ static int igb_xdp_xmit(struct net_device *dev, int n,
 		nxmit++;
 	}
 
-	__netif_tx_unlock(nq);
-
 	if (unlikely(flags & XDP_XMIT_FLUSH))
 		igb_xdp_ring_update_tail(tx_ring);
 
+	__netif_tx_unlock(nq);
+
 	return nxmit;
 }
 
@@ -8864,12 +8868,14 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
 
 static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 {
+	unsigned int total_bytes = 0, total_packets = 0;
 	struct igb_adapter *adapter = q_vector->adapter;
 	struct igb_ring *rx_ring = q_vector->rx.ring;
-	struct sk_buff *skb = rx_ring->skb;
-	unsigned int total_bytes = 0, total_packets = 0;
 	u16 cleaned_count = igb_desc_unused(rx_ring);
+	struct sk_buff *skb = rx_ring->skb;
+	int cpu = smp_processor_id();
 	unsigned int xdp_xmit = 0;
+	struct netdev_queue *nq;
 	struct xdp_buff xdp;
 	u32 frame_sz = 0;
 	int rx_buf_pgcnt;
@@ -8997,7 +9003,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	if (xdp_xmit & IGB_XDP_TX) {
 		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
 
+		nq = txring_txq(tx_ring);
+		__netif_tx_lock(nq, cpu);
 		igb_xdp_ring_update_tail(tx_ring);
+		__netif_tx_unlock(nq);
 	}
 
 	u64_stats_update_begin(&rx_ring->rx_syncp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 03ee93fd9e94..db2db0738ee4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -319,6 +319,7 @@ struct nix_mark_format {
 
 /* smq(flush) to tl1 cir/pir info */
 struct nix_smq_tree_ctx {
+	u16 schq;
 	u64 cir_off;
 	u64 cir_val;
 	u64 pir_off;
@@ -328,8 +329,6 @@ struct nix_smq_tree_ctx {
 /* smq flush context */
 struct nix_smq_flush_ctx {
 	int smq;
-	u16 tl1_schq;
-	u16 tl2_schq;
 	struct nix_smq_tree_ctx smq_tree_ctx[NIX_TXSCH_LVL_CNT];
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 222f9e00b836..82832a24fbd8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2259,14 +2259,13 @@ static void nix_smq_flush_fill_ctx(struct rvu *rvu, int blkaddr, int smq,
 	schq = smq;
 	for (lvl = NIX_TXSCH_LVL_SMQ; lvl <= NIX_TXSCH_LVL_TL1; lvl++) {
 		smq_tree_ctx = &smq_flush_ctx->smq_tree_ctx[lvl];
+		smq_tree_ctx->schq = schq;
 		if (lvl == NIX_TXSCH_LVL_TL1) {
-			smq_flush_ctx->tl1_schq = schq;
 			smq_tree_ctx->cir_off = NIX_AF_TL1X_CIR(schq);
 			smq_tree_ctx->pir_off = 0;
 			smq_tree_ctx->pir_val = 0;
 			parent_off = 0;
 		} else if (lvl == NIX_TXSCH_LVL_TL2) {
-			smq_flush_ctx->tl2_schq = schq;
 			smq_tree_ctx->cir_off = NIX_AF_TL2X_CIR(schq);
 			smq_tree_ctx->pir_off = NIX_AF_TL2X_PIR(schq);
 			parent_off = NIX_AF_TL2X_PARENT(schq);
@@ -2301,8 +2300,8 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr,
 {
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
+	int tl2, tl2_schq;
 	u64 regoff;
-	int tl2;
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
@@ -2310,16 +2309,17 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr,
 
 	/* loop through all TL2s with matching PF_FUNC */
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL2];
+	tl2_schq = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL2].schq;
 	for (tl2 = 0; tl2 < txsch->schq.max; tl2++) {
 		/* skip the smq(flush) TL2 */
-		if (tl2 == smq_flush_ctx->tl2_schq)
+		if (tl2 == tl2_schq)
 			continue;
 		/* skip unused TL2s */
 		if (TXSCH_MAP_FLAGS(txsch->pfvf_map[tl2]) & NIX_TXSCHQ_FREE)
 			continue;
 		/* skip if PF_FUNC doesn't match */
 		if ((TXSCH_MAP_FUNC(txsch->pfvf_map[tl2]) & ~RVU_PFVF_FUNC_MASK) !=
-		    (TXSCH_MAP_FUNC(txsch->pfvf_map[smq_flush_ctx->tl2_schq] &
+		    (TXSCH_MAP_FUNC(txsch->pfvf_map[tl2_schq] &
 				    ~RVU_PFVF_FUNC_MASK)))
 			continue;
 		/* enable/disable XOFF */
@@ -2361,10 +2361,12 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
 			 int smq, u16 pcifunc, int nixlf)
 {
 	struct nix_smq_flush_ctx *smq_flush_ctx;
+	int err, restore_tx_en = 0, i;
 	int pf = rvu_get_pf(pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
-	int err, restore_tx_en = 0;
-	u64 cfg;
+	u16 tl2_tl3_link_schq;
+	u8 link, link_level;
+	u64 cfg, bmap = 0;
 
 	if (!is_rvu_otx2(rvu)) {
 		/* Skip SMQ flush if pkt count is zero */
@@ -2388,16 +2390,38 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
 	nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, true);
 	nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, false);
 
-	cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
-	/* Do SMQ flush and set enqueue xoff */
-	cfg |= BIT_ULL(50) | BIT_ULL(49);
-	rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
-
 	/* Disable backpressure from physical link,
 	 * otherwise SMQ flush may stall.
 	 */
 	rvu_cgx_enadis_rx_bp(rvu, pf, false);
 
+	link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL) & 0x01 ?
+			NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2;
+	tl2_tl3_link_schq = smq_flush_ctx->smq_tree_ctx[link_level].schq;
+	link = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL1].schq;
+
+	/* SMQ set enqueue xoff */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
+	cfg |= BIT_ULL(50);
+	rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
+
+	/* Clear all NIX_AF_TL3_TL2_LINK_CFG[ENA] for the TL3/TL2 queue */
+	for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) {
+		cfg = rvu_read64(rvu, blkaddr,
+				 NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link));
+		if (!(cfg & BIT_ULL(12)))
+			continue;
+		bmap |= (1 << i);
+		cfg &= ~BIT_ULL(12);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg);
+	}
+
+	/* Do SMQ flush and set enqueue xoff */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
+	cfg |= BIT_ULL(50) | BIT_ULL(49);
+	rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
+
 	/* Wait for flush to complete */
 	err = rvu_poll_reg(rvu, blkaddr,
 			   NIX_AF_SMQX_CFG(smq), BIT_ULL(49), true);
@@ -2406,6 +2430,17 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
 			 "NIXLF%d: SMQ%d flush failed, txlink might be busy\n",
 			 nixlf, smq);
 
+	/* Set NIX_AF_TL3_TL2_LINKX_CFG[ENA] for the TL3/TL2 queue */
+	for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) {
+		if (!(bmap & (1 << i)))
+			continue;
+		cfg = rvu_read64(rvu, blkaddr,
+				 NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link));
+		cfg |= BIT_ULL(12);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg);
+	}
+
 	/* clear XOFF on TL2s */
 	nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, true);
 	nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 36845872ae94..1cf3c54d343e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -139,6 +139,10 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT);
 	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100BASE_TX, legacy,
+				       ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_T, legacy,
+				       ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
 	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy,
 				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT);
 	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy,
@@ -204,6 +208,12 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
 				       ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_8_400GBASE_CR8, ext,
+				       ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT);
 	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_1_100GBASE_CR_KR, ext,
 				       ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
 				       ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 255bc8b749f9..8587cd572da5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -319,7 +319,7 @@ int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
 		return -EPERM;
 
 	mutex_lock(&esw->state_lock);
-	if (esw->mode != MLX5_ESWITCH_LEGACY) {
+	if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw)) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}
@@ -339,7 +339,7 @@ int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 	if (!mlx5_esw_allowed(esw))
 		return -EPERM;
 
-	if (esw->mode != MLX5_ESWITCH_LEGACY)
+	if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw))
 		return -EOPNOTSUPP;
 
 	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 20146a2dc7f4..02a3563f51ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -312,6 +312,25 @@ static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw,
 	return err;
 }
 
+static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
+{
+	switch (type) {
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_TSAR;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
+	}
+	return false;
+}
+
 static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
 					      struct mlx5_vport *vport,
 					      u32 max_rate, u32 bw_share)
@@ -323,6 +342,9 @@ static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
 	void *vport_elem;
 	int err;
 
+	if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT))
+		return -EOPNOTSUPP;
+
 	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
@@ -421,6 +443,7 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_esw_rate_group *group;
+	__be32 *attr;
 	u32 divider;
 	int err;
 
@@ -428,6 +451,12 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex
 	if (!group)
 		return ERR_PTR(-ENOMEM);
 
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
+
 	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
 		 esw->qos.root_tsar_ix);
 	err = mlx5_create_scheduling_element_cmd(esw->dev,
@@ -526,25 +555,6 @@ static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw,
 	return err;
 }
 
-static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
-{
-	switch (type) {
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_TSAR;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
-	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
-		return MLX5_CAP_QOS(dev, esw_element_type) &
-		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
-	}
-	return false;
-}
-
 static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
@@ -555,7 +565,8 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
+	if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR) ||
+	    !(MLX5_CAP_QOS(dev, esw_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR))
 		return -EOPNOTSUPP;
 
 	MLX5_SET(scheduling_context, tsar_ctx, element_type,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5b7e6f4b5c7e..2ec33c4a2a3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2217,6 +2217,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101f) },			/* ConnectX-6 LX */
 	{ PCI_VDEVICE(MELLANOX, 0x1021) },			/* ConnectX-7 */
 	{ PCI_VDEVICE(MELLANOX, 0x1023) },			/* ConnectX-8 */
+	{ PCI_VDEVICE(MELLANOX, 0x1025) },			/* ConnectX-9 */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d6) },			/* BlueField-2 integrated ConnectX-6 Dx network controller */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
index 8bce730b5c5b..db2bd3ad63ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
@@ -28,6 +28,9 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id,
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
 
+	if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP))
+		return -EOPNOTSUPP;
+
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP);
@@ -44,6 +47,10 @@ int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id,
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
 	void *attr;
 
+	if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_TSAR) ||
+	    !(MLX5_CAP_QOS(mdev, nic_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR))
+		return -EOPNOTSUPP;
+
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
 	MLX5_SET(scheduling_context, sched_ctx, element_type,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 1d57b047817b..b54bffda027b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -426,9 +426,9 @@ enum WX_MSCA_CMD_value {
 #define WX_MIN_RXD                   128
 #define WX_MIN_TXD                   128
 
-/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
-#define WX_REQ_RX_DESCRIPTOR_MULTIPLE   8
-#define WX_REQ_TX_DESCRIPTOR_MULTIPLE   8
+/* Number of Transmit and Receive Descriptors must be a multiple of 128 */
+#define WX_REQ_RX_DESCRIPTOR_MULTIPLE   128
+#define WX_REQ_TX_DESCRIPTOR_MULTIPLE   128
 
 #define WX_MAX_JUMBO_FRAME_SIZE      9432 /* max payload 9414 */
 #define VMDQ_P(p)                    p
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index efeb643c1373..fc247f479257 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -271,8 +271,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
 				DP83822_ENERGY_DET_INT_EN |
 				DP83822_LINK_QUAL_INT_EN);
 
-		/* Private data pointer is NULL on DP83825 */
-		if (!dp83822 || !dp83822->fx_enabled)
+		if (!dp83822->fx_enabled)
 			misr_status |= DP83822_ANEG_COMPLETE_INT_EN |
 				       DP83822_DUP_MODE_CHANGE_INT_EN |
 				       DP83822_SPEED_CHANGED_INT_EN;
@@ -292,8 +291,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
 				DP83822_PAGE_RX_INT_EN |
 				DP83822_EEE_ERROR_CHANGE_INT_EN);
 
-		/* Private data pointer is NULL on DP83825 */
-		if (!dp83822 || !dp83822->fx_enabled)
+		if (!dp83822->fx_enabled)
 			misr_status |= DP83822_ANEG_ERR_INT_EN |
 				       DP83822_WOL_PKT_INT_EN;
 
@@ -691,10 +689,9 @@ static int dp83822_read_straps(struct phy_device *phydev)
 	return 0;
 }
 
-static int dp83822_probe(struct phy_device *phydev)
+static int dp8382x_probe(struct phy_device *phydev)
 {
 	struct dp83822_private *dp83822;
-	int ret;
 
 	dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822),
 			       GFP_KERNEL);
@@ -703,6 +700,20 @@ static int dp83822_probe(struct phy_device *phydev)
 
 	phydev->priv = dp83822;
 
+	return 0;
+}
+
+static int dp83822_probe(struct phy_device *phydev)
+{
+	struct dp83822_private *dp83822;
+	int ret;
+
+	ret = dp8382x_probe(phydev);
+	if (ret)
+		return ret;
+
+	dp83822 = phydev->priv;
+
 	ret = dp83822_read_straps(phydev);
 	if (ret)
 		return ret;
@@ -717,14 +728,11 @@ static int dp83822_probe(struct phy_device *phydev)
 
 static int dp83826_probe(struct phy_device *phydev)
 {
-	struct dp83822_private *dp83822;
-
-	dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822),
-			       GFP_KERNEL);
-	if (!dp83822)
-		return -ENOMEM;
+	int ret;
 
-	phydev->priv = dp83822;
+	ret = dp8382x_probe(phydev);
+	if (ret)
+		return ret;
 
 	dp83826_of_init(phydev);
 
@@ -795,6 +803,7 @@ static int dp83822_resume(struct phy_device *phydev)
 		PHY_ID_MATCH_MODEL(_id),			\
 		.name		= (_name),			\
 		/* PHY_BASIC_FEATURES */			\
+		.probe          = dp8382x_probe,		\
 		.soft_reset	= dp83822_phy_reset,		\
 		.config_init	= dp8382x_config_init,		\
 		.get_wol = dp83822_get_wol,			\
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c6af18948092..5a1c1ec5a64b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -356,6 +356,9 @@ struct receive_queue {
 	struct xdp_rxq_info xsk_rxq_info;
 
 	struct xdp_buff **xsk_buffs;
+
+	/* Do dma by self */
+	bool do_dma;
 };
 
 /* This structure can contain rss message with maximum settings for indirection table and keysize
@@ -885,7 +888,7 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
 	void *buf;
 
 	buf = virtqueue_get_buf_ctx(rq->vq, len, ctx);
-	if (buf)
+	if (buf && rq->do_dma)
 		virtnet_rq_unmap(rq, buf, *len);
 
 	return buf;
@@ -898,6 +901,11 @@ static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
 	u32 offset;
 	void *head;
 
+	if (!rq->do_dma) {
+		sg_init_one(rq->sg, buf, len);
+		return;
+	}
+
 	head = page_address(rq->alloc_frag.page);
 
 	offset = buf - head;
@@ -923,42 +931,44 @@ static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
 
 	head = page_address(alloc_frag->page);
 
-	dma = head;
+	if (rq->do_dma) {
+		dma = head;
+
+		/* new pages */
+		if (!alloc_frag->offset) {
+			if (rq->last_dma) {
+				/* Now, the new page is allocated, the last dma
+				 * will not be used. So the dma can be unmapped
+				 * if the ref is 0.
+				 */
+				virtnet_rq_unmap(rq, rq->last_dma, 0);
+				rq->last_dma = NULL;
+			}
 
-	/* new pages */
-	if (!alloc_frag->offset) {
-		if (rq->last_dma) {
-			/* Now, the new page is allocated, the last dma
-			 * will not be used. So the dma can be unmapped
-			 * if the ref is 0.
-			 */
-			virtnet_rq_unmap(rq, rq->last_dma, 0);
-			rq->last_dma = NULL;
-		}
+			dma->len = alloc_frag->size - sizeof(*dma);
 
-		dma->len = alloc_frag->size - sizeof(*dma);
+			addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1,
+							      dma->len, DMA_FROM_DEVICE, 0);
+			if (virtqueue_dma_mapping_error(rq->vq, addr))
+				return NULL;
 
-		addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1,
-						      dma->len, DMA_FROM_DEVICE, 0);
-		if (virtqueue_dma_mapping_error(rq->vq, addr))
-			return NULL;
+			dma->addr = addr;
+			dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
 
-		dma->addr = addr;
-		dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
+			/* Add a reference to dma to prevent the entire dma from
+			 * being released during error handling. This reference
+			 * will be freed after the pages are no longer used.
+			 */
+			get_page(alloc_frag->page);
+			dma->ref = 1;
+			alloc_frag->offset = sizeof(*dma);
 
-		/* Add a reference to dma to prevent the entire dma from
-		 * being released during error handling. This reference
-		 * will be freed after the pages are no longer used.
-		 */
-		get_page(alloc_frag->page);
-		dma->ref = 1;
-		alloc_frag->offset = sizeof(*dma);
+			rq->last_dma = dma;
+		}
 
-		rq->last_dma = dma;
+		++dma->ref;
 	}
 
-	++dma->ref;
-
 	buf = head + alloc_frag->offset;
 
 	get_page(alloc_frag->page);
@@ -967,19 +977,6 @@ static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
 	return buf;
 }
 
-static void virtnet_rq_set_premapped(struct virtnet_info *vi)
-{
-	int i;
-
-	/* disable for big mode */
-	if (!vi->mergeable_rx_bufs && vi->big_packets)
-		return;
-
-	for (i = 0; i < vi->max_queue_pairs; i++)
-		/* error should never happen */
-		BUG_ON(virtqueue_set_dma_premapped(vi->rq[i].vq));
-}
-
 static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 {
 	struct virtnet_info *vi = vq->vdev->priv;
@@ -993,7 +990,7 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 		return;
 	}
 
-	if (!vi->big_packets || vi->mergeable_rx_bufs)
+	if (rq->do_dma)
 		virtnet_rq_unmap(rq, buf, 0);
 
 	virtnet_rq_free_buf(vi, rq, buf);
@@ -2430,7 +2427,8 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0) {
-		virtnet_rq_unmap(rq, buf, 0);
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
 	}
 
@@ -2544,7 +2542,8 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	ctx = mergeable_len_to_ctx(len + room, headroom);
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0) {
-		virtnet_rq_unmap(rq, buf, 0);
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
 	}
 
@@ -2701,7 +2700,7 @@ static int virtnet_receive_packets(struct virtnet_info *vi,
 		}
 	} else {
 		while (packets < budget &&
-		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+		       (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) {
 			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, stats);
 			packets++;
 		}
@@ -5892,7 +5891,7 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 	int i;
 	for (i = 0; i < vi->max_queue_pairs; i++)
 		if (vi->rq[i].alloc_frag.page) {
-			if (vi->rq[i].last_dma)
+			if (vi->rq[i].do_dma && vi->rq[i].last_dma)
 				virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0);
 			put_page(vi->rq[i].alloc_frag.page);
 		}
@@ -6090,8 +6089,6 @@ static int init_vqs(struct virtnet_info *vi)
 	if (ret)
 		goto err_free;
 
-	virtnet_rq_set_premapped(vi);
-
 	cpus_read_lock();
 	virtnet_set_affinity(vi);
 	cpus_read_unlock();
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index cab228cf51c6..cfdf984a95a8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1027,7 +1027,8 @@ struct mlx5_ifc_qos_cap_bits {
 
 	u8         max_tsar_bw_share[0x20];
 
-	u8         reserved_at_100[0x20];
+	u8         nic_element_type[0x10];
+	u8         nic_tsar_type[0x10];
 
 	u8         reserved_at_120[0x3];
 	u8         log_meter_aso_granularity[0x5];
@@ -3966,6 +3967,7 @@ enum {
 	ELEMENT_TYPE_CAP_MASK_VPORT		= 1 << 1,
 	ELEMENT_TYPE_CAP_MASK_VPORT_TC		= 1 << 2,
 	ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC	= 1 << 3,
+	ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP	= 1 << 4,
 };
 
 struct mlx5_ifc_scheduling_context_bits {
@@ -4675,6 +4677,12 @@ enum {
 	TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
 };
 
+enum {
+	TSAR_TYPE_CAP_MASK_DWRR		= 1 << 0,
+	TSAR_TYPE_CAP_MASK_ROUND_ROBIN	= 1 << 1,
+	TSAR_TYPE_CAP_MASK_ETS		= 1 << 2,
+};
+
 struct mlx5_ifc_tsar_element_bits {
 	u8         reserved_at_0[0x8];
 	u8         tsar_type[0x8];
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6c395a2600e8..276ca543ef44 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -173,7 +173,8 @@ retry:
 			break;
 		case SKB_GSO_TCPV4:
 		case SKB_GSO_TCPV6:
-			if (skb->csum_offset != offsetof(struct tcphdr, check))
+			if (skb->ip_summed == CHECKSUM_PARTIAL &&
+			    skb->csum_offset != offsetof(struct tcphdr, check))
 				return -EINVAL;
 			break;
 		}
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index e4cc6b78dcfc..049e22bdaafb 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -231,9 +231,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb->dev = master->dev;
 		skb_reset_mac_header(skb);
 		skb_reset_mac_len(skb);
-		spin_lock_bh(&hsr->seqnr_lock);
 		hsr_forward_skb(skb, master);
-		spin_unlock_bh(&hsr->seqnr_lock);
 	} else {
 		dev_core_stats_tx_dropped_inc(dev);
 		dev_kfree_skb_any(skb);
@@ -314,14 +312,10 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 	set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version);
 
 	/* From HSRv1 on we have separate supervision sequence numbers. */
-	spin_lock_bh(&hsr->seqnr_lock);
-	if (hsr->prot_version > 0) {
-		hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr);
-		hsr->sup_sequence_nr++;
-	} else {
-		hsr_stag->sequence_nr = htons(hsr->sequence_nr);
-		hsr->sequence_nr++;
-	}
+	if (hsr->prot_version > 0)
+		hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr));
+	else
+		hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sequence_nr));
 
 	hsr_stag->tlv.HSR_TLV_type = type;
 	/* TODO: Why 12 in HSRv0? */
@@ -343,13 +337,11 @@ static void send_hsr_supervision_frame(struct hsr_port *port,
 		ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox);
 	}
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, port);
-	spin_unlock_bh(&hsr->seqnr_lock);
+
 	return;
 }
 
@@ -374,9 +366,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0));
 
 	/* From HSRv1 on we have separate supervision sequence numbers. */
-	spin_lock_bh(&hsr->seqnr_lock);
-	hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr);
-	hsr->sup_sequence_nr++;
+	hsr_stag->sequence_nr = htons(atomic_inc_return(&hsr->sup_sequence_nr));
 	hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD;
 	hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload);
 
@@ -384,13 +374,10 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 	hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
 	ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr);
 
-	if (skb_put_padto(skb, ETH_ZLEN)) {
-		spin_unlock_bh(&hsr->seqnr_lock);
+	if (skb_put_padto(skb, ETH_ZLEN))
 		return;
-	}
 
 	hsr_forward_skb(skb, master);
-	spin_unlock_bh(&hsr->seqnr_lock);
 }
 
 /* Announce (supervision frame) timer function
@@ -427,6 +414,9 @@ static void hsr_proxy_announce(struct timer_list *t)
 	 * of SAN nodes stored in ProxyNodeTable.
 	 */
 	interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK);
+	if (!interlink)
+		goto done;
+
 	list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) {
 		if (hsr_addr_is_redbox(hsr, node->macaddress_A))
 			continue;
@@ -441,6 +431,7 @@ static void hsr_proxy_announce(struct timer_list *t)
 		mod_timer(&hsr->announce_proxy_timer, jiffies + interval);
 	}
 
+done:
 	rcu_read_unlock();
 }
 
@@ -621,11 +612,9 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	if (res < 0)
 		return res;
 
-	spin_lock_init(&hsr->seqnr_lock);
 	/* Overflow soon to find bugs easier: */
-	hsr->sequence_nr = HSR_SEQNR_START;
-	hsr->sup_sequence_nr = HSR_SUP_SEQNR_START;
-	hsr->interlink_sequence_nr = HSR_SEQNR_START;
+	atomic_set(&hsr->sequence_nr, HSR_SEQNR_START);
+	atomic_set(&hsr->sup_sequence_nr, HSR_SUP_SEQNR_START);
 
 	timer_setup(&hsr->announce_timer, hsr_announce, 0);
 	timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index b38060246e62..6f63c8a775c4 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -599,9 +599,7 @@ static void handle_std_frame(struct sk_buff *skb,
 	if (port->type == HSR_PT_MASTER ||
 	    port->type == HSR_PT_INTERLINK) {
 		/* Sequence nr for the master/interlink node */
-		lockdep_assert_held(&hsr->seqnr_lock);
-		frame->sequence_nr = hsr->sequence_nr;
-		hsr->sequence_nr++;
+		frame->sequence_nr = atomic_inc_return(&hsr->sequence_nr);
 	}
 }
 
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index ab1f8d35d9dc..6f7bbf01f3e4 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -202,11 +202,9 @@ struct hsr_priv {
 	struct timer_list	prune_timer;
 	struct timer_list	prune_proxy_timer;
 	int announce_count;
-	u16 sequence_nr;
-	u16 interlink_sequence_nr; /* Interlink port seq_nr */
-	u16 sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
+	atomic_t sequence_nr;
+	atomic_t sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
 	enum hsr_version prot_version;	/* Indicate if HSRv0, HSRv1 or PRPv1 */
-	spinlock_t seqnr_lock;	/* locking for sequence_nr */
 	spinlock_t list_lock;	/* locking for node list */
 	struct hsr_proto_ops	*proto_ops;
 #define PRP_LAN_ID	0x5     /* 0x1010 for A and 0x1011 for B. Bit 0 is set
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index f6ff0b61e08a..8aea4ff5f49e 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -163,7 +163,7 @@ static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN,
 		    hsr->sup_multicast_addr) ||
-	    nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr))
+	    nla_put_u16(skb, IFLA_HSR_SEQ_NR, atomic_read(&hsr->sequence_nr)))
 		goto nla_put_failure;
 	if (hsr->prot_version == PRP_V1)
 		proto = HSR_PROTOCOL_PRP;
diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
index 78b869b31492..3e30745e2c09 100644
--- a/net/ipv4/fou_core.c
+++ b/net/ipv4/fou_core.c
@@ -336,11 +336,11 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
 	struct gro_remcsum grc;
 	u8 proto;
 
+	skb_gro_remcsum_init(&grc);
+
 	if (!fou)
 		goto out;
 
-	skb_gro_remcsum_init(&grc);
-
 	off = skb_gro_offset(skb);
 	len = off + sizeof(*guehdr);
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f891bc714668..ad935d34c973 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -334,15 +334,21 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *entry;
 	struct sock *sk = (struct sock *)msk;
+	struct timer_list *add_timer = NULL;
 
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-	if (entry && (!check_id || entry->addr.id == addr->id))
+	if (entry && (!check_id || entry->addr.id == addr->id)) {
 		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+		add_timer = &entry->add_timer;
+	}
+	if (!check_id && entry)
+		list_del(&entry->list);
 	spin_unlock_bh(&msk->pm.lock);
 
-	if (entry && (!check_id || entry->addr.id == addr->id))
-		sk_stop_timer_sync(sk, &entry->add_timer);
+	/* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */
+	if (add_timer)
+		sk_stop_timer_sync(sk, add_timer);
 
 	return entry;
 }
@@ -1462,7 +1468,6 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 
 	entry = mptcp_pm_del_add_timer(msk, addr, false);
 	if (entry) {
-		list_del(&entry->list);
 		kfree(entry);
 		return true;
 	}
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 5c1ff07eaee0..df72b0376970 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -670,8 +670,14 @@ static int __init nf_flow_table_module_init(void)
 	if (ret)
 		goto out_offload;
 
+	ret = nf_flow_register_bpf();
+	if (ret)
+		goto out_bpf;
+
 	return 0;
 
+out_bpf:
+	nf_flow_table_offload_exit();
 out_offload:
 	unregister_pernet_subsys(&nf_flow_table_net_ops);
 	return ret;
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 8b541a080342..b0f199171932 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -101,7 +101,7 @@ static int __init nf_flow_inet_module_init(void)
 	nft_register_flowtable_type(&flowtable_ipv6);
 	nft_register_flowtable_type(&flowtable_inet);
 
-	return nf_flow_register_bpf();
+	return 0;
 }
 
 static void __exit nf_flow_inet_module_exit(void)
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index f30163e2ca62..12cdff640492 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -9,7 +9,8 @@
 
 struct nft_socket {
 	enum nft_socket_keys		key:8;
-	u8				level;
+	u8				level;		/* cgroupv2 level to extract */
+	u8				level_user;	/* cgroupv2 level provided by userspace */
 	u8				len;
 	union {
 		u8			dreg;
@@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo
 	memcpy(dest, &cgid, sizeof(u64));
 	return true;
 }
+
+/* process context only, uses current->nsproxy. */
+static noinline int nft_socket_cgroup_subtree_level(void)
+{
+	struct cgroup *cgrp = cgroup_get_from_path("/");
+	int level;
+
+	if (!cgrp)
+		return -ENOENT;
+
+	level = cgrp->level;
+
+	cgroup_put(cgrp);
+
+	if (WARN_ON_ONCE(level > 255))
+		return -ERANGE;
+
+	if (WARN_ON_ONCE(level < 0))
+		return -EINVAL;
+
+	return level;
+}
 #endif
 
 static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt)
@@ -110,13 +133,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			*dest = READ_ONCE(sk->sk_mark);
 		} else {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 	case NFT_SOCKET_WILDCARD:
 		if (!sk_fullsock(sk)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		nft_socket_wildcard(pkt, regs, sk, dest);
 		break;
@@ -124,7 +147,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 	case NFT_SOCKET_CGROUPV2:
 		if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
 			regs->verdict.code = NFT_BREAK;
-			return;
+			goto out_put_sk;
 		}
 		break;
 #endif
@@ -133,6 +156,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		regs->verdict.code = NFT_BREAK;
 	}
 
+out_put_sk:
 	if (sk != skb->sk)
 		sock_gen_put(sk);
 }
@@ -173,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	case NFT_SOCKET_MARK:
 		len = sizeof(u32);
 		break;
-#ifdef CONFIG_CGROUPS
+#ifdef CONFIG_SOCK_CGROUP_DATA
 	case NFT_SOCKET_CGROUPV2: {
 		unsigned int level;
+		int err;
 
 		if (!tb[NFTA_SOCKET_LEVEL])
 			return -EINVAL;
@@ -184,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 		if (level > 255)
 			return -EOPNOTSUPP;
 
+		err = nft_socket_cgroup_subtree_level();
+		if (err < 0)
+			return err;
+
+		priv->level_user = level;
+
+		level += err;
+		/* Implies a giant cgroup tree */
+		if (WARN_ON_ONCE(level > 255))
+			return -EOPNOTSUPP;
+
 		priv->level = level;
 		len = sizeof(u64);
 		break;
@@ -208,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb,
 	if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg))
 		return -1;
 	if (priv->key == NFT_SOCKET_CGROUPV2 &&
-	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level)))
+	    nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user)))
 		return -1;
 	return 0;
 }
diff --git a/tools/testing/selftests/net/lib/csum.c b/tools/testing/selftests/net/lib/csum.c
index b9f3fc3c3426..e0a34e5e8dd5 100644
--- a/tools/testing/selftests/net/lib/csum.c
+++ b/tools/testing/selftests/net/lib/csum.c
@@ -654,10 +654,16 @@ static int recv_verify_packet_ipv4(void *nh, int len)
 {
 	struct iphdr *iph = nh;
 	uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto;
+	uint16_t ip_len;
 
 	if (len < sizeof(*iph) || iph->protocol != proto)
 		return -1;
 
+	ip_len = ntohs(iph->tot_len);
+	if (ip_len > len || ip_len < sizeof(*iph))
+		return -1;
+
+	len = ip_len;
 	iph_addr_p = &iph->saddr;
 	if (proto == IPPROTO_TCP)
 		return recv_verify_packet_tcp(iph + 1, len - sizeof(*iph));
@@ -669,16 +675,22 @@ static int recv_verify_packet_ipv6(void *nh, int len)
 {
 	struct ipv6hdr *ip6h = nh;
 	uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto;
+	uint16_t ip_len;
 
 	if (len < sizeof(*ip6h) || ip6h->nexthdr != proto)
 		return -1;
 
+	ip_len = ntohs(ip6h->payload_len);
+	if (ip_len > len - sizeof(*ip6h))
+		return -1;
+
+	len = ip_len;
 	iph_addr_p = &ip6h->saddr;
 
 	if (proto == IPPROTO_TCP)
-		return recv_verify_packet_tcp(ip6h + 1, len - sizeof(*ip6h));
+		return recv_verify_packet_tcp(ip6h + 1, len);
 	else
-		return recv_verify_packet_udp(ip6h + 1, len - sizeof(*ip6h));
+		return recv_verify_packet_udp(ip6h + 1, len);
 }
 
 /* return whether auxdata includes TP_STATUS_CSUM_VALID */
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 7b936a926859..5d796622e730 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -11,6 +11,8 @@ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
 
 TEST_FILES := mptcp_lib.sh settings
 
+TEST_INCLUDES := ../lib.sh ../net_helper.sh
+
 EXTRA_CLEAN := *.pcap
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index a4762c49a878..cde041c93906 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3064,7 +3064,9 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 1 3
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
+		if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then
+			pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
+		fi
 		fullmesh=1 speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3