Merge tag 'mlx5-fixes-2022-11-09' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2022-11-02

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2022-11-09' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: TC, Fix slab-out-of-bounds in parse_tc_actions
  net/mlx5e: E-Switch, Fix comparing termination table instance
  net/mlx5e: TC, Fix wrong rejection of packet-per-second policing
  net/mlx5e: Fix tc acts array not to be dependent on enum order
  net/mlx5e: Fix usage of DMA sync API
  net/mlx5e: Add missing sanity checks for max TX WQE size
  net/mlx5: fw_reset: Don't try to load device in case PCI isn't working
  net/mlx5: E-switch, Set to legacy mode if failed to change switchdev mode
  net/mlx5: Allow async trigger completion execution on single CPU systems
  net/mlx5: Bridge, verify LAG state when adding bond to bridge
====================

Link: https://lore.kernel.org/r/20221109184050.108379-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

13 files changed, 149 insertions, 115 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 46ba4c2faad2..2e0d59ca62b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1770,12 +1770,17 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int i;
 
-	for (i = 0; i < cmd->max_reg_cmds; i++)
-		while (down_trylock(&cmd->sem))
+	for (i = 0; i < cmd->max_reg_cmds; i++) {
+		while (down_trylock(&cmd->sem)) {
 			mlx5_cmd_trigger_completions(dev);
+			cond_resched();
+		}
+	}
 
-	while (down_trylock(&cmd->pages_sem))
+	while (down_trylock(&cmd->pages_sem)) {
 		mlx5_cmd_trigger_completions(dev);
+		cond_resched();
+	}
 
 	/* Unlock cmdif */
 	up(&cmd->pages_sem);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 39ef2a2561a3..8099a21e674c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -164,6 +164,36 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr
 	return err;
 }
 
+static int
+mlx5_esw_bridge_changeupper_validate_netdev(void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct net_device *upper = info->upper_dev;
+	struct net_device *lower;
+	struct list_head *iter;
+
+	if (!netif_is_bridge_master(upper) || !netif_is_lag_master(dev))
+		return 0;
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		struct mlx5_core_dev *mdev;
+		struct mlx5e_priv *priv;
+
+		if (!mlx5e_eswitch_rep(lower))
+			continue;
+
+		priv = netdev_priv(lower);
+		mdev = priv->mdev;
+		if (!mlx5_lag_is_active(mdev))
+			return -EAGAIN;
+		if (!mlx5_lag_is_shared_fdb(mdev))
+			return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb,
 						unsigned long event, void *ptr)
 {
@@ -171,6 +201,7 @@ static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb,
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
+		err = mlx5_esw_bridge_changeupper_validate_netdev(ptr);
 		break;
 
 	case NETDEV_CHANGEUPPER:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
index 305fde62a78d..3337241cfd84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c
@@ -6,70 +6,42 @@
 #include "en/tc_priv.h"
 #include "mlx5_core.h"
 
-/* Must be aligned with enum flow_action_id. */
 static struct mlx5e_tc_act *tc_acts_fdb[NUM_FLOW_ACTIONS] = {
-	&mlx5e_tc_act_accept,
-	&mlx5e_tc_act_drop,
-	&mlx5e_tc_act_trap,
-	&mlx5e_tc_act_goto,
-	&mlx5e_tc_act_mirred,
-	&mlx5e_tc_act_mirred,
-	&mlx5e_tc_act_redirect_ingress,
-	NULL, /* FLOW_ACTION_MIRRED_INGRESS, */
-	&mlx5e_tc_act_vlan,
-	&mlx5e_tc_act_vlan,
-	&mlx5e_tc_act_vlan_mangle,
-	&mlx5e_tc_act_tun_encap,
-	&mlx5e_tc_act_tun_decap,
-	&mlx5e_tc_act_pedit,
-	&mlx5e_tc_act_pedit,
-	&mlx5e_tc_act_csum,
-	NULL, /* FLOW_ACTION_MARK, */
-	&mlx5e_tc_act_ptype,
-	NULL, /* FLOW_ACTION_PRIORITY, */
-	NULL, /* FLOW_ACTION_WAKE, */
-	NULL, /* FLOW_ACTION_QUEUE, */
-	&mlx5e_tc_act_sample,
-	&mlx5e_tc_act_police,
-	&mlx5e_tc_act_ct,
-	NULL, /* FLOW_ACTION_CT_METADATA, */
-	&mlx5e_tc_act_mpls_push,
-	&mlx5e_tc_act_mpls_pop,
-	NULL, /* FLOW_ACTION_MPLS_MANGLE, */
-	NULL, /* FLOW_ACTION_GATE, */
-	NULL, /* FLOW_ACTION_PPPOE_PUSH, */
-	NULL, /* FLOW_ACTION_JUMP, */
-	NULL, /* FLOW_ACTION_PIPE, */
-	&mlx5e_tc_act_vlan,
-	&mlx5e_tc_act_vlan,
+	[FLOW_ACTION_ACCEPT] = &mlx5e_tc_act_accept,
+	[FLOW_ACTION_DROP] = &mlx5e_tc_act_drop,
+	[FLOW_ACTION_TRAP] = &mlx5e_tc_act_trap,
+	[FLOW_ACTION_GOTO] = &mlx5e_tc_act_goto,
+	[FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_mirred,
+	[FLOW_ACTION_MIRRED] = &mlx5e_tc_act_mirred,
+	[FLOW_ACTION_REDIRECT_INGRESS] = &mlx5e_tc_act_redirect_ingress,
+	[FLOW_ACTION_VLAN_PUSH] = &mlx5e_tc_act_vlan,
+	[FLOW_ACTION_VLAN_POP] = &mlx5e_tc_act_vlan,
+	[FLOW_ACTION_VLAN_MANGLE] = &mlx5e_tc_act_vlan_mangle,
+	[FLOW_ACTION_TUNNEL_ENCAP] = &mlx5e_tc_act_tun_encap,
+	[FLOW_ACTION_TUNNEL_DECAP] = &mlx5e_tc_act_tun_decap,
+	[FLOW_ACTION_MANGLE] = &mlx5e_tc_act_pedit,
+	[FLOW_ACTION_ADD] = &mlx5e_tc_act_pedit,
+	[FLOW_ACTION_CSUM] = &mlx5e_tc_act_csum,
+	[FLOW_ACTION_PTYPE] = &mlx5e_tc_act_ptype,
+	[FLOW_ACTION_SAMPLE] = &mlx5e_tc_act_sample,
+	[FLOW_ACTION_POLICE] = &mlx5e_tc_act_police,
+	[FLOW_ACTION_CT] = &mlx5e_tc_act_ct,
+	[FLOW_ACTION_MPLS_PUSH] = &mlx5e_tc_act_mpls_push,
+	[FLOW_ACTION_MPLS_POP] = &mlx5e_tc_act_mpls_pop,
+	[FLOW_ACTION_VLAN_PUSH_ETH] = &mlx5e_tc_act_vlan,
+	[FLOW_ACTION_VLAN_POP_ETH] = &mlx5e_tc_act_vlan,
 };
 
-/* Must be aligned with enum flow_action_id. */
 static struct mlx5e_tc_act *tc_acts_nic[NUM_FLOW_ACTIONS] = {
-	&mlx5e_tc_act_accept,
-	&mlx5e_tc_act_drop,
-	NULL, /* FLOW_ACTION_TRAP, */
-	&mlx5e_tc_act_goto,
-	&mlx5e_tc_act_mirred_nic,
-	NULL, /* FLOW_ACTION_MIRRED, */
-	NULL, /* FLOW_ACTION_REDIRECT_INGRESS, */
-	NULL, /* FLOW_ACTION_MIRRED_INGRESS, */
-	NULL, /* FLOW_ACTION_VLAN_PUSH, */
-	NULL, /* FLOW_ACTION_VLAN_POP, */
-	NULL, /* FLOW_ACTION_VLAN_MANGLE, */
-	NULL, /* FLOW_ACTION_TUNNEL_ENCAP, */
-	NULL, /* FLOW_ACTION_TUNNEL_DECAP, */
-	&mlx5e_tc_act_pedit,
-	&mlx5e_tc_act_pedit,
-	&mlx5e_tc_act_csum,
-	&mlx5e_tc_act_mark,
-	NULL, /* FLOW_ACTION_PTYPE, */
-	NULL, /* FLOW_ACTION_PRIORITY, */
-	NULL, /* FLOW_ACTION_WAKE, */
-	NULL, /* FLOW_ACTION_QUEUE, */
-	NULL, /* FLOW_ACTION_SAMPLE, */
-	NULL, /* FLOW_ACTION_POLICE, */
-	&mlx5e_tc_act_ct,
+	[FLOW_ACTION_ACCEPT] = &mlx5e_tc_act_accept,
+	[FLOW_ACTION_DROP] = &mlx5e_tc_act_drop,
+	[FLOW_ACTION_GOTO] = &mlx5e_tc_act_goto,
+	[FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_mirred_nic,
+	[FLOW_ACTION_MANGLE] = &mlx5e_tc_act_pedit,
+	[FLOW_ACTION_ADD] = &mlx5e_tc_act_pedit,
+	[FLOW_ACTION_CSUM] = &mlx5e_tc_act_csum,
+	[FLOW_ACTION_MARK] = &mlx5e_tc_act_mark,
+	[FLOW_ACTION_CT] = &mlx5e_tc_act_ct,
 };
 
 /**
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index cb164b62f543..853f312cd757 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -11,6 +11,27 @@
 
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
 
+/* IPSEC inline data includes:
+ * 1. ESP trailer: up to 255 bytes of padding, 1 byte for pad length, 1 byte for
+ *    next header.
+ * 2. ESP authentication data: 16 bytes for ICV.
+ */
+#define MLX5E_MAX_TX_IPSEC_DS DIV_ROUND_UP(sizeof(struct mlx5_wqe_inline_seg) + \
+					   255 + 1 + 1 + 16, MLX5_SEND_WQE_DS)
+
+/* 366 should be big enough to cover all L2, L3 and L4 headers with possible
+ * encapsulations.
+ */
+#define MLX5E_MAX_TX_INLINE_DS DIV_ROUND_UP(366 - INL_HDR_START_SZ + VLAN_HLEN, \
+					    MLX5_SEND_WQE_DS)
+
+/* Sync the calculation with mlx5e_sq_calc_wqe_attr. */
+#define MLX5E_MAX_TX_WQEBBS DIV_ROUND_UP(MLX5E_TX_WQE_EMPTY_DS_COUNT + \
+					 MLX5E_MAX_TX_INLINE_DS + \
+					 MLX5E_MAX_TX_IPSEC_DS + \
+					 MAX_SKB_FRAGS + 1, \
+					 MLX5_SEND_WQEBB_NUM_DS)
+
 #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)
 
 static inline
@@ -424,6 +445,8 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 
 static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size)
 {
+	WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < mlx5e_get_max_sq_wqebbs(mdev));
+
 	/* A WQE must not cross the page boundary, hence two conditions:
 	 * 1. Its size must not exceed the page size.
 	 * 2. If the WQE size is X, and the space remaining in a page is less
@@ -436,7 +459,6 @@ static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_si
 		  "wqe_size %u is greater than max SQ WQEBBs %u",
 		  wqe_size, mlx5e_get_max_sq_wqebbs(mdev));
 
-
 	return MLX5E_STOP_ROOM(wqe_size);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 4685c652c97e..20507ef2f956 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -117,7 +117,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 	xdpi.page.rq = rq;
 
 	dma_addr = page_pool_get_dma_addr(page) + (xdpf->data - (void *)xdpf);
-	dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, DMA_TO_DEVICE);
+	dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, DMA_BIDIRECTIONAL);
 
 	if (unlikely(xdp_frame_has_frags(xdpf))) {
 		sinfo = xdp_get_shared_info_from_frame(xdpf);
@@ -131,7 +131,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 				skb_frag_off(frag);
 			len = skb_frag_size(frag);
 			dma_sync_single_for_device(sq->pdev, addr, len,
-						   DMA_TO_DEVICE);
+						   DMA_BIDIRECTIONAL);
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 364f04309149..e3a4f01bcceb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5694,6 +5694,13 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 		mlx5e_fs_set_state_destroy(priv->fs,
 					   !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
 
+	/* Validate the max_wqe_size_sq capability. */
+	if (WARN_ON_ONCE(mlx5e_get_max_sq_wqebbs(priv->mdev) < MLX5E_MAX_TX_WQEBBS)) {
+		mlx5_core_warn(priv->mdev, "MLX5E: Max SQ WQEBBs firmware capability: %u, needed %lu\n",
+			       mlx5e_get_max_sq_wqebbs(priv->mdev), MLX5E_MAX_TX_WQEBBS);
+		return -EIO;
+	}
+
 	/* max number of channels may have changed */
 	max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile);
 	if (priv->channels.params.num_channels > max_nch) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 58084650151f..a61a43fc8d5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -266,7 +266,7 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, union mlx5e_alloc_uni
 
 	addr = page_pool_get_dma_addr(au->page);
 	/* Non-XSK always uses PAGE_SIZE. */
-	dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, rq->buff.map_dir);
 	return true;
 }
 
@@ -282,8 +282,7 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, union mlx5e_alloc_u
 		return -ENOMEM;
 
 	/* Non-XSK always uses PAGE_SIZE. */
-	addr = dma_map_page_attrs(rq->pdev, au->page, 0, PAGE_SIZE,
-				  rq->buff.map_dir, DMA_ATTR_SKIP_CPU_SYNC);
+	addr = dma_map_page(rq->pdev, au->page, 0, PAGE_SIZE, rq->buff.map_dir);
 	if (unlikely(dma_mapping_error(rq->pdev, addr))) {
 		page_pool_recycle_direct(rq->page_pool, au->page);
 		au->page = NULL;
@@ -427,14 +426,15 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 {
 	dma_addr_t addr = page_pool_get_dma_addr(au->page);
 
-	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len,
+				rq->buff.map_dir);
 	page_ref_inc(au->page);
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 			au->page, frag_offset, len, truesize);
 }
 
 static inline void
-mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
+mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb,
 		      struct page *page, dma_addr_t addr,
 		      int offset_from, int dma_offset, u32 headlen)
 {
@@ -442,7 +442,8 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
 	unsigned int len = ALIGN(headlen, sizeof(long));
 
-	dma_sync_single_for_cpu(pdev, addr + dma_offset, len, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(rq->pdev, addr + dma_offset, len,
+				rq->buff.map_dir);
 	skb_copy_to_linear_data(skb, from, len);
 }
 
@@ -1538,7 +1539,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 
 	addr = page_pool_get_dma_addr(au->page);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
-				      frag_size, DMA_FROM_DEVICE);
+				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
 
 	prog = rcu_dereference(rq->xdp_prog);
@@ -1587,7 +1588,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	addr = page_pool_get_dma_addr(au->page);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset,
-				      rq->buff.frame0_sz, DMA_FROM_DEVICE);
+				      rq->buff.frame0_sz, rq->buff.map_dir);
 	net_prefetchw(va); /* xdp_frame data area */
 	net_prefetch(va + rx_headroom);
 
@@ -1608,7 +1609,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 		addr = page_pool_get_dma_addr(au->page);
 		dma_sync_single_for_cpu(rq->pdev, addr + wi->offset,
-					frag_consumed_bytes, DMA_FROM_DEVICE);
+					frag_consumed_bytes, rq->buff.map_dir);
 
 		if (!xdp_buff_has_frags(&xdp)) {
 			/* Init on the first fragment to avoid cold cache access
@@ -1905,7 +1906,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	mlx5e_fill_skb_data(skb, rq, au, byte_cnt, frag_offset);
 	/* copy header */
 	addr = page_pool_get_dma_addr(head_au->page);
-	mlx5e_copy_skb_header(rq->pdev, skb, head_au->page, addr,
+	mlx5e_copy_skb_header(rq, skb, head_au->page, addr,
 			      head_offset, head_offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
@@ -1939,7 +1940,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	addr = page_pool_get_dma_addr(au->page);
 	dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset,
-				      frag_size, DMA_FROM_DEVICE);
+				      frag_size, rq->buff.map_dir);
 	net_prefetch(data);
 
 	prog = rcu_dereference(rq->xdp_prog);
@@ -1987,7 +1988,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) {
 		/* build SKB around header */
-		dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE);
+		dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, rq->buff.map_dir);
 		prefetchw(hdr);
 		prefetch(data);
 		skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0);
@@ -2009,7 +2010,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 		}
 
 		prefetchw(skb->data);
-		mlx5e_copy_skb_header(rq->pdev, skb, head->page, head->addr,
+		mlx5e_copy_skb_header(rq, skb, head->page, head->addr,
 				      head_offset + rx_headroom,
 				      rx_headroom, head_size);
 		/* skb linear part was allocated with headlen and aligned to long */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dd6fea9e9a5b..5a6aa61ec82a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3633,10 +3633,14 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr,
 	attr2->action = 0;
 	attr2->flags = 0;
 	attr2->parse_attr = parse_attr;
-	attr2->esw_attr->out_count = 0;
-	attr2->esw_attr->split_count = 0;
 	attr2->dest_chain = 0;
 	attr2->dest_ft = NULL;
+
+	if (ns_type == MLX5_FLOW_NAMESPACE_FDB) {
+		attr2->esw_attr->out_count = 0;
+		attr2->esw_attr->split_count = 0;
+	}
+
 	return attr2;
 }
 
@@ -4758,12 +4762,6 @@ int mlx5e_policer_validate(const struct flow_action *action,
 		return -EOPNOTSUPP;
 	}
 
-	if (act->police.rate_pkt_ps) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "QoS offload not support packets per second");
-		return -EOPNOTSUPP;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6adca01fbdc9..f7897ddb29c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -305,6 +305,8 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at
 	u16 ds_cnt_inl = 0;
 	u16 ds_cnt_ids = 0;
 
+	/* Sync the calculation with MLX5E_MAX_TX_WQEBBS. */
+
 	if (attr->insz)
 		ds_cnt_ids = DIV_ROUND_UP(sizeof(struct mlx5_wqe_inline_seg) + attr->insz,
 					  MLX5_SEND_WQE_DS);
@@ -317,6 +319,9 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at
 			inl += VLAN_HLEN;
 
 		ds_cnt_inl = DIV_ROUND_UP(inl, MLX5_SEND_WQE_DS);
+		if (WARN_ON_ONCE(ds_cnt_inl > MLX5E_MAX_TX_INLINE_DS))
+			netdev_warn(skb->dev, "ds_cnt_inl = %u > max %u\n", ds_cnt_inl,
+				    (u16)MLX5E_MAX_TX_INLINE_DS);
 		ds_cnt += ds_cnt_inl;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index c59107fa9e6d..2169486c4bfb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1387,12 +1387,14 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw)
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
 		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
-	esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED;
-	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
-		esw_offloads_disable(esw);
-	else if (esw->mode == MLX5_ESWITCH_LEGACY)
-		esw_legacy_disable(esw);
-	mlx5_esw_acls_ns_cleanup(esw);
+	if (esw->fdb_table.flags & MLX5_ESW_FDB_CREATED) {
+		esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED;
+		if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+			esw_offloads_disable(esw);
+		else if (esw->mode == MLX5_ESWITCH_LEGACY)
+			esw_legacy_disable(esw);
+		mlx5_esw_acls_ns_cleanup(esw);
+	}
 
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
 		devl_rate_nodes_destroy(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 4e50df3139c6..728ca9f2bb9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2310,7 +2310,7 @@ out_free:
 static int esw_offloads_start(struct mlx5_eswitch *esw,
 			      struct netlink_ext_ack *extack)
 {
-	int err, err1;
+	int err;
 
 	esw->mode = MLX5_ESWITCH_OFFLOADS;
 	err = mlx5_eswitch_enable_locked(esw, esw->dev->priv.sriov.num_vfs);
@@ -2318,11 +2318,6 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed setting eswitch to offloads");
 		esw->mode = MLX5_ESWITCH_LEGACY;
-		err1 = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS);
-		if (err1) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Failed setting eswitch back to legacy");
-		}
 		mlx5_rescan_drivers(esw->dev);
 	}
 	if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
@@ -3389,19 +3384,12 @@ err_metadata:
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
-	int err, err1;
+	int err;
 
 	esw->mode = MLX5_ESWITCH_LEGACY;
 	err = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS);
-	if (err) {
+	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
-		esw->mode = MLX5_ESWITCH_OFFLOADS;
-		err1 = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS);
-		if (err1) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Failed setting eswitch back to offloads");
-		}
-	}
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index ee568bf34ae2..108a3503f413 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -30,9 +30,9 @@ mlx5_eswitch_termtbl_hash(struct mlx5_flow_act *flow_act,
 		     sizeof(dest->vport.num), hash);
 	hash = jhash((const void *)&dest->vport.vhca_id,
 		     sizeof(dest->vport.num), hash);
-	if (dest->vport.pkt_reformat)
-		hash = jhash(dest->vport.pkt_reformat,
-			     sizeof(*dest->vport.pkt_reformat),
+	if (flow_act->pkt_reformat)
+		hash = jhash(flow_act->pkt_reformat,
+			     sizeof(*flow_act->pkt_reformat),
 			     hash);
 	return hash;
 }
@@ -53,9 +53,11 @@ mlx5_eswitch_termtbl_cmp(struct mlx5_flow_act *flow_act1,
 	if (ret)
 		return ret;
 
-	return dest1->vport.pkt_reformat && dest2->vport.pkt_reformat ?
-	       memcmp(dest1->vport.pkt_reformat, dest2->vport.pkt_reformat,
-		      sizeof(*dest1->vport.pkt_reformat)) : 0;
+	if (flow_act1->pkt_reformat && flow_act2->pkt_reformat)
+		return memcmp(flow_act1->pkt_reformat, flow_act2->pkt_reformat,
+			      sizeof(*flow_act1->pkt_reformat));
+
+	return !(flow_act1->pkt_reformat == flow_act2->pkt_reformat);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 07c583996c29..9d908a0ccfef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -152,7 +152,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 		mlx5_unload_one(dev);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
-		mlx5_load_one(dev, false);
+		else
+			mlx5_load_one(dev, false);
 		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));