Merge tag 'mlx5-updates-2023-02-15' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2023-02-15

1) From Gal Tariq and Parav, Few cleanups for mlx5 driver.

2) From Vlad: Allow offloading of ct 'new' match based on [1]

[1] https://lore.kernel.org/netdev/[email protected]/

* tag 'mlx5-updates-2023-02-15' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: RX, Remove doubtful unlikely call
  net/mlx5e: Fix outdated TLS comment
  net/mlx5e: Remove unused function mlx5e_sq_xmit_simple
  net/mlx5e: Allow offloading of ct 'new' match
  net/mlx5e: Implement CT entry update
  net/mlx5: Simplify eq list traversal
  net/mlx5e: Remove redundant page argument in mlx5e_xdp_handle()
  net/mlx5e: Remove redundant page argument in mlx5e_xmit_xdp_buff()
  net/mlx5e: Switch to using napi_build_skb()
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -35,6 +35,7 @@
 #define MLX5_CT_STATE_REPLY_BIT BIT(4)
 #define MLX5_CT_STATE_RELATED_BIT BIT(5)
 #define MLX5_CT_STATE_INVALID_BIT BIT(6)
+#define MLX5_CT_STATE_NEW_BIT BIT(7)
 
 #define MLX5_CT_LABELS_BITS MLX5_REG_MAPPING_MBITS(LABELS_TO_REG)
 #define MLX5_CT_LABELS_MASK MLX5_REG_MAPPING_MASK(LABELS_TO_REG)
@@ -721,12 +722,14 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	DECLARE_MOD_HDR_ACTS_ACTIONS(actions_arr, MLX5_CT_MIN_MOD_ACTS);
 	DECLARE_MOD_HDR_ACTS(mod_acts, actions_arr);
 	struct flow_action_entry *meta;
+	enum ip_conntrack_info ctinfo;
 	u16 ct_state = 0;
 	int err;
 
 	meta = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
 	if (!meta)
 		return -EOPNOTSUPP;
+	ctinfo = meta->ct_metadata.cookie & NFCT_INFOMASK;
 
 	err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels,
 				     &attr->ct_attr.ct_labels_id);
@@ -742,7 +745,8 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 		ct_state |= MLX5_CT_STATE_NAT_BIT;
 	}
 
-	ct_state |= MLX5_CT_STATE_ESTABLISHED_BIT | MLX5_CT_STATE_TRK_BIT;
+	ct_state |= MLX5_CT_STATE_TRK_BIT;
+	ct_state |= ctinfo == IP_CT_NEW ? MLX5_CT_STATE_NEW_BIT : MLX5_CT_STATE_ESTABLISHED_BIT;
 	ct_state |= meta->ct_metadata.orig_dir ? 0 : MLX5_CT_STATE_REPLY_BIT;
 	err = mlx5_tc_ct_entry_set_registers(ct_priv, &mod_acts,
 					     ct_state,
@@ -871,6 +875,68 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	return err;
 }
 
+static int
+mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv,
+			      struct flow_rule *flow_rule,
+			      struct mlx5_ct_entry *entry,
+			      bool nat, u8 zone_restore_id)
+{
+	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
+	struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr;
+	struct mlx5e_mod_hdr_handle *mh;
+	struct mlx5_ct_fs_rule *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	old_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
+	if (!old_attr) {
+		err = -ENOMEM;
+		goto err_attr;
+	}
+	*old_attr = *attr;
+
+	err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, &mh, zone_restore_id,
+					      nat, mlx5_tc_ct_entry_has_nat(entry));
+	if (err) {
+		ct_dbg("Failed to create ct entry mod hdr");
+		goto err_mod_hdr;
+	}
+
+	mlx5_tc_ct_set_tuple_match(ct_priv, spec, flow_rule);
+	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, entry->tuple.zone, MLX5_CT_ZONE_MASK);
+
+	rule = ct_priv->fs_ops->ct_rule_add(ct_priv->fs, spec, attr, flow_rule);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		ct_dbg("Failed to add replacement ct entry rule, nat: %d", nat);
+		goto err_rule;
+	}
+
+	ct_priv->fs_ops->ct_rule_del(ct_priv->fs, zone_rule->rule);
+	zone_rule->rule = rule;
+	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, old_attr, zone_rule->mh);
+	zone_rule->mh = mh;
+
+	kfree(old_attr);
+	kvfree(spec);
+	ct_dbg("Replaced ct entry rule in zone %d", entry->tuple.zone);
+
+	return 0;
+
+err_rule:
+	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
+	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
+err_mod_hdr:
+	kfree(old_attr);
+err_attr:
+	kvfree(spec);
+	return err;
+}
+
 static bool
 mlx5_tc_ct_entry_valid(struct mlx5_ct_entry *entry)
 {
@@ -1065,6 +1131,52 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 	return err;
 }
 
+static int
+mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv,
+			       struct flow_rule *flow_rule,
+			       struct mlx5_ct_entry *entry,
+			       u8 zone_restore_id)
+{
+	int err;
+
+	err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false,
+					    zone_restore_id);
+	if (err)
+		return err;
+
+	err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true,
+					    zone_restore_id);
+	if (err)
+		mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
+	return err;
+}
+
+static int
+mlx5_tc_ct_block_flow_offload_replace(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule,
+				      struct mlx5_ct_entry *entry, unsigned long cookie)
+{
+	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
+	int err;
+
+	err = mlx5_tc_ct_entry_replace_rules(ct_priv, flow_rule, entry, ft->zone_restore_id);
+	if (!err)
+		return 0;
+
+	/* If failed to update the entry, then look it up again under ht_lock
+	 * protection and properly delete it.
+	 */
+	spin_lock_bh(&ct_priv->ht_lock);
+	entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params);
+	if (entry) {
+		rhashtable_remove_fast(&ft->ct_entries_ht, &entry->node, cts_ht_params);
+		spin_unlock_bh(&ct_priv->ht_lock);
+		mlx5_tc_ct_entry_put(entry);
+	} else {
+		spin_unlock_bh(&ct_priv->ht_lock);
+	}
+	return err;
+}
+
 static int
 mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 				  struct flow_cls_offload *flow)
@@ -1073,23 +1185,27 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
 	struct flow_action_entry *meta_action;
 	unsigned long cookie = flow->cookie;
-	enum ip_conntrack_info ctinfo;
 	struct mlx5_ct_entry *entry;
 	int err;
 
 	meta_action = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
 	if (!meta_action)
 		return -EOPNOTSUPP;
-	ctinfo = meta_action->ct_metadata.cookie & NFCT_INFOMASK;
-	if (ctinfo == IP_CT_NEW)
-		return -EOPNOTSUPP;
 
 	spin_lock_bh(&ct_priv->ht_lock);
 	entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params);
 	if (entry && refcount_inc_not_zero(&entry->refcnt)) {
+		if (entry->restore_cookie == meta_action->ct_metadata.cookie) {
+			spin_unlock_bh(&ct_priv->ht_lock);
+			mlx5_tc_ct_entry_put(entry);
+			return -EEXIST;
+		}
+		entry->restore_cookie = meta_action->ct_metadata.cookie;
 		spin_unlock_bh(&ct_priv->ht_lock);
+
+		err = mlx5_tc_ct_block_flow_offload_replace(ft, flow_rule, entry, cookie);
 		mlx5_tc_ct_entry_put(entry);
-		return -EEXIST;
+		return err;
 	}
 	spin_unlock_bh(&ct_priv->ht_lock);
 
@@ -1327,7 +1443,7 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 		     struct mlx5_ct_attr *ct_attr,
 		     struct netlink_ext_ack *extack)
 {
-	bool trk, est, untrk, unest, new, rpl, unrpl, rel, unrel, inv, uninv;
+	bool trk, est, untrk, unnew, unest, new, rpl, unrpl, rel, unrel, inv, uninv;
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector_key_ct *mask, *key;
 	u32 ctstate = 0, ctstate_mask = 0;
@@ -1373,15 +1489,18 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 	rel = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_RELATED;
 	inv = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_INVALID;
 	untrk = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_TRACKED;
+	unnew = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_NEW;
 	unest = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED;
 	unrpl = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_REPLY;
 	unrel = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_RELATED;
 	uninv = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_INVALID;
 
 	ctstate |= trk ? MLX5_CT_STATE_TRK_BIT : 0;
+	ctstate |= new ? MLX5_CT_STATE_NEW_BIT : 0;
 	ctstate |= est ? MLX5_CT_STATE_ESTABLISHED_BIT : 0;
 	ctstate |= rpl ? MLX5_CT_STATE_REPLY_BIT : 0;
 	ctstate_mask |= (untrk || trk) ? MLX5_CT_STATE_TRK_BIT : 0;
+	ctstate_mask |= (unnew || new) ? MLX5_CT_STATE_NEW_BIT : 0;
 	ctstate_mask |= (unest || est) ? MLX5_CT_STATE_ESTABLISHED_BIT : 0;
 	ctstate_mask |= (unrpl || rpl) ? MLX5_CT_STATE_REPLY_BIT : 0;
 	ctstate_mask |= unrel ? MLX5_CT_STATE_RELATED_BIT : 0;
@@ -1399,12 +1518,6 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (new) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "matching on ct_state +new isn't supported");
-		return -EOPNOTSUPP;
-	}
-
 	if (mask->ct_zone)
 		mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG,
 					    key->ct_zone, MLX5_CT_ZONE_MASK);

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h

@@ -320,7 +320,6 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 	}
 }
 
-void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more);
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq);
 
 static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -57,8 +57,9 @@ int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
 
 static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
-		    struct page *page, struct xdp_buff *xdp)
+		    struct xdp_buff *xdp)
 {
+	struct page *page = virt_to_page(xdp->data);
 	struct skb_shared_info *sinfo = NULL;
 	struct mlx5e_xmit_data xdptxd;
 	struct mlx5e_xdp_info xdpi;
@@ -185,7 +186,7 @@ const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = {
 };
 
 /* returns true if packet was consumed by xdp */
-bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct page *page,
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
 		      struct bpf_prog *prog, struct mlx5e_xdp_buff *mxbuf)
 {
 	struct xdp_buff *xdp = &mxbuf->xdp;
@@ -197,7 +198,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct page *page,
 	case XDP_PASS:
 		return false;
 	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, page, xdp)))
+		if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, xdp)))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
 		return true;
@@ -209,7 +210,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct page *page,
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
 		__set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
 		if (xdp->rxq->mem.type != MEM_TYPE_XSK_BUFF_POOL)
-			mlx5e_page_dma_unmap(rq, page);
+			mlx5e_page_dma_unmap(rq, virt_to_page(xdp->data));
 		rq->stats->xdp_redirect++;
 		return true;
 	default:

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h

@@ -52,7 +52,7 @@ struct mlx5e_xdp_buff {
 
 struct mlx5e_xsk_param;
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
-bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct page *page,
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
 		      struct bpf_prog *prog, struct mlx5e_xdp_buff *mlctx);
 void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c

@@ -289,7 +289,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 */
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (likely(prog && mlx5e_xdp_handle(rq, NULL, prog, mxbuf))) {
+	if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf))) {
 		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
@@ -323,7 +323,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 	net_prefetch(mxbuf->xdp.data);
 
 	prog = rcu_dereference(rq->xdp_prog);
-	if (likely(prog && mlx5e_xdp_handle(rq, NULL, prog, mxbuf)))
+	if (likely(prog && mlx5e_xdp_handle(rq, prog, mxbuf)))
 		return NULL; /* page/packet was consumed by XDP */
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse

drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h

@@ -124,7 +124,7 @@ static inline bool mlx5e_accel_tx_begin(struct net_device *dev,
 		mlx5e_udp_gso_handle_tx_skb(skb);
 
 #ifdef CONFIG_MLX5_EN_TLS
-	/* May send SKBs and WQEs. */
+	/* May send WQEs. */
 	if (mlx5e_ktls_skb_offloaded(skb))
 		if (unlikely(!mlx5e_ktls_handle_tx_skb(dev, sq, skb,
 						       &state->tls)))

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -1556,7 +1556,7 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 				       u32 frag_size, u16 headroom,
 				       u32 cqe_bcnt, u32 metasize)
 {
-	struct sk_buff *skb = build_skb(va, frag_size);
+	struct sk_buff *skb = napi_build_skb(va, frag_size);
 
 	if (unlikely(!skb)) {
 		rq->stats->buff_alloc_err++;
@@ -1610,7 +1610,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi,
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, au->page, prog, &mxbuf))
+		if (mlx5e_xdp_handle(rq, prog, &mxbuf))
 			return NULL; /* page/packet was consumed by XDP */
 
 		rx_headroom = mxbuf.xdp.data - mxbuf.xdp.data_hard_start;
@@ -1698,10 +1698,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 		wi++;
 	}
 
-	au = head_wi->au;
-
 	prog = rcu_dereference(rq->xdp_prog);
-	if (prog && mlx5e_xdp_handle(rq, au->page, prog, &mxbuf)) {
+	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 		if (test_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			int i;
 
@@ -1718,9 +1716,9 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 	if (unlikely(!skb))
 		return NULL;
 
-	page_ref_inc(au->page);
+	page_ref_inc(head_wi->au->page);
 
-	if (unlikely(xdp_buff_has_frags(&mxbuf.xdp))) {
+	if (xdp_buff_has_frags(&mxbuf.xdp)) {
 		int i;
 
 		/* sinfo->nr_frags is reset by build_skb, calculate again. */
@@ -2013,7 +2011,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 		net_prefetchw(va); /* xdp_frame data area */
 		mlx5e_fill_mxbuf(rq, cqe, va, rx_headroom, cqe_bcnt, &mxbuf);
-		if (mlx5e_xdp_handle(rq, au->page, prog, &mxbuf)) {
+		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 				__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 			return NULL; /* page/packet was consumed by XDP */

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -720,21 +720,6 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-void mlx5e_sq_xmit_simple(struct mlx5e_txqsq *sq, struct sk_buff *skb, bool xmit_more)
-{
-	struct mlx5e_tx_wqe_attr wqe_attr;
-	struct mlx5e_tx_attr attr;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi;
-
-	mlx5e_sq_xmit_prepare(sq, skb, NULL, &attr);
-	mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
-	pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
-	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
-	mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, &wqe->eth);
-	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, xmit_more);
-}
-
 static void mlx5e_tx_wi_dma_unmap(struct mlx5e_txqsq *sq, struct mlx5e_tx_wqe_info *wi,
 				  u32 *dma_fifo_cc)
 {