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

Cross-merge networking fixes after downstream PR.

No conflicts (sort of) and no adjacent changes.

This merge reverts commit b3c9e65eb227 ("net: hsr: remove seqnr_lock")
from net, as it was superseded by
commit 430d67bdcb04 ("net: hsr: Use the seqnr lock for frames received via interlink port.")
in net-next.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

17 files changed, 209 insertions, 122 deletions

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 73d053501fb1..0102a82e88cc 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 1d0208b5db7d..e15dd3d858df 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2273,12 +2273,12 @@ 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;
 
@@ -2288,6 +2288,13 @@ 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 570425772b63..06e712cdc3d9 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2433,13 +2433,6 @@ 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)
@@ -2806,6 +2799,14 @@ 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 59c0e88153c0..eeb48cc48e08 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5351,7 +5351,6 @@ err_load:
 	ice_deinit(pf);
 err_init:
 	ice_adapter_put(pdev);
-	pci_disable_device(pdev);
 	return err;
 }
 
@@ -5459,7 +5458,6 @@ 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 43b1d83686d1..5016ba82e142 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 4d123dae912c..1966736f98b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -137,6 +137,10 @@ 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,
@@ -202,6 +206,12 @@ 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 4b88d969a66c..c6e951b8ebdb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2223,6 +2223,7 @@ 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 61ffa8851d7b..6f4781ec2b36 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++;
 		}
@@ -5911,7 +5910,7 @@ 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);
 		}
@@ -6109,8 +6108,6 @@ 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();