Merge tag 'mlx5-fixes-2022-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2022-07-06

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2022-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Ring the TX doorbell on DMA errors
  net/mlx5e: Fix capability check for updating vnic env counters
  net/mlx5e: CT: Use own workqueue instead of mlx5e priv
  net/mlx5: Lag, correct get the port select mode str
  net/mlx5e: Fix enabling sriov while tc nic rules are offloaded
  net/mlx5e: kTLS, Fix build time constant test in RX
  net/mlx5e: kTLS, Fix build time constant test in TX
  net/mlx5: Lag, decouple FDB selection and shared FDB
  net/mlx5: TC, allow offload from uplink to other PF's VF
====================

Link: https://lore.kernel.org/r/20220706231309.38579-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 76 insertions, 38 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 25f51f80a9b4..ba171c7f0a67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -76,6 +76,7 @@ struct mlx5_tc_ct_priv {
 	struct mlx5_ct_fs *fs;
 	struct mlx5_ct_fs_ops *fs_ops;
 	spinlock_t ht_lock; /* protects ft entries */
+	struct workqueue_struct *wq;
 
 	struct mlx5_tc_ct_debugfs debugfs;
 };
@@ -941,14 +942,11 @@ static void mlx5_tc_ct_entry_del_work(struct work_struct *work)
 static void
 __mlx5_tc_ct_entry_put(struct mlx5_ct_entry *entry)
 {
-	struct mlx5e_priv *priv;
-
 	if (!refcount_dec_and_test(&entry->refcnt))
 		return;
 
-	priv = netdev_priv(entry->ct_priv->netdev);
 	INIT_WORK(&entry->work, mlx5_tc_ct_entry_del_work);
-	queue_work(priv->wq, &entry->work);
+	queue_work(entry->ct_priv->wq, &entry->work);
 }
 
 static struct mlx5_ct_counter *
@@ -1759,19 +1757,16 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg)
 static void
 mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
 {
-	struct mlx5e_priv *priv;
-
 	if (!refcount_dec_and_test(&ft->refcount))
 		return;
 
+	flush_workqueue(ct_priv->wq);
 	nf_flow_table_offload_del_cb(ft->nf_ft,
 				     mlx5_tc_ct_block_flow_offload, ft);
 	rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params);
 	rhashtable_free_and_destroy(&ft->ct_entries_ht,
 				    mlx5_tc_ct_flush_ft_entry,
 				    ct_priv);
-	priv = netdev_priv(ct_priv->netdev);
-	flush_workqueue(priv->wq);
 	mlx5_tc_ct_free_pre_ct_tables(ft);
 	mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id);
 	kfree(ft);
@@ -2176,6 +2171,12 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 	if (rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params))
 		goto err_ct_tuples_nat_ht;
 
+	ct_priv->wq = alloc_ordered_workqueue("mlx5e_ct_priv_wq", 0);
+	if (!ct_priv->wq) {
+		err = -ENOMEM;
+		goto err_wq;
+	}
+
 	err = mlx5_tc_ct_fs_init(ct_priv);
 	if (err)
 		goto err_init_fs;
@@ -2184,6 +2185,8 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
 	return ct_priv;
 
 err_init_fs:
+	destroy_workqueue(ct_priv->wq);
+err_wq:
 	rhashtable_destroy(&ct_priv->ct_tuples_nat_ht);
 err_ct_tuples_nat_ht:
 	rhashtable_destroy(&ct_priv->ct_tuples_ht);
@@ -2213,6 +2216,7 @@ mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 	if (!ct_priv)
 		return;
 
+	destroy_workqueue(ct_priv->wq);
 	mlx5_ct_tc_remove_dbgfs(ct_priv);
 	chains = ct_priv->chains;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 0bb0633b7542..27483aa7be8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -231,8 +231,7 @@ mlx5e_set_ktls_rx_priv_ctx(struct tls_context *tls_ctx,
 	struct mlx5e_ktls_offload_context_rx **ctx =
 		__tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_RX);
 
-	BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_rx *) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
+	BUILD_BUG_ON(sizeof(priv_rx) > TLS_DRIVER_STATE_SIZE_RX);
 
 	*ctx = priv_rx;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 4b6f0d1ea59a..f239fb2e832f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -68,8 +68,7 @@ mlx5e_set_ktls_tx_priv_ctx(struct tls_context *tls_ctx,
 	struct mlx5e_ktls_offload_context_tx **ctx =
 		__tls_driver_ctx(tls_ctx, TLS_OFFLOAD_CTX_DIR_TX);
 
-	BUILD_BUG_ON(sizeof(struct mlx5e_ktls_offload_context_tx *) >
-		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
+	BUILD_BUG_ON(sizeof(priv_tx) > TLS_DRIVER_STATE_SIZE_TX);
 
 	*ctx = priv_tx;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 57fa0489eeb8..1e87bb2b7541 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -688,7 +688,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vnic_env)
 	u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard))
+	if (!mlx5e_stats_grp_vnic_env_num_stats(priv))
 		return;
 
 	MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3a39a50146dd..9ca2c8763237 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3793,7 +3793,7 @@ static bool is_lag_dev(struct mlx5e_priv *priv,
 
 static bool is_multiport_eligible(struct mlx5e_priv *priv, struct net_device *out_dev)
 {
-	if (mlx5e_eswitch_uplink_rep(out_dev) &&
+	if (same_hw_reps(priv, out_dev) &&
 	    MLX5_CAP_PORT_SELECTION(priv->mdev, port_select_flow_table) &&
 	    MLX5_CAP_GEN(priv->mdev, create_lag_when_not_master_up))
 		return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 50d14cec4894..9a7250be229f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -341,6 +341,26 @@ static void mlx5e_tx_check_stop(struct mlx5e_txqsq *sq)
 	}
 }
 
+static void mlx5e_tx_flush(struct mlx5e_txqsq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi;
+
+	/* Must not be called when a MPWQE session is active but empty. */
+	mlx5e_tx_mpwqe_ensure_complete(sq);
+
+	pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	wi = &sq->db.wqe_info[pi];
+
+	*wi = (struct mlx5e_tx_wqe_info) {
+		.num_wqebbs = 1,
+	};
+
+	wqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
+}
+
 static inline void
 mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     const struct mlx5e_tx_attr *attr,
@@ -459,6 +479,7 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 
 static bool mlx5e_tx_skb_supports_mpwqe(struct sk_buff *skb, struct mlx5e_tx_attr *attr)
@@ -560,6 +581,13 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5e_xmit_data txd;
 
+	txd.data = skb->data;
+	txd.len = skb->len;
+
+	txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr)))
+		goto err_unmap;
+
 	if (!mlx5e_tx_mpwqe_session_is_active(sq)) {
 		mlx5e_tx_mpwqe_session_start(sq, eseg);
 	} else if (!mlx5e_tx_mpwqe_same_eseg(sq, eseg)) {
@@ -569,18 +597,9 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 
 	sq->stats->xmit_more += xmit_more;
 
-	txd.data = skb->data;
-	txd.len = skb->len;
-
-	txd.dma_addr = dma_map_single(sq->pdev, txd.data, txd.len, DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(sq->pdev, txd.dma_addr)))
-		goto err_unmap;
 	mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE);
-
 	mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb);
-
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
-
 	mlx5e_tx_skb_update_hwts_flags(skb);
 
 	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) {
@@ -602,6 +621,7 @@ err_unmap:
 	mlx5e_dma_unmap_wqe_err(sq, 1);
 	sq->stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
@@ -1006,5 +1026,6 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 err_drop:
 	stats->dropped++;
 	dev_kfree_skb_any(skb);
+	mlx5e_tx_flush(sq);
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 9d17206d1625..fabe49a35a5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -11,6 +11,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "fs_ft_pool.h"
 #include "esw/qos.h"
 
 enum {
@@ -95,8 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-	ft_attr.max_fte = table_size;
+	ft_attr.max_fte = POOL_NEXT_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
@@ -105,6 +105,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 		goto out;
 	}
 	esw->fdb_table.legacy.fdb = fdb;
+	table_size = fdb->max_fte;
 
 	/* Addresses group : Full match unicast/multicast addresses */
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
index 15e41dc84d53..b8feaf0f5c4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c
@@ -44,7 +44,7 @@ static int port_sel_mode_show(struct seq_file *file, void *priv)
 	ldev = dev->priv.lag;
 	mutex_lock(&ldev->lock);
 	if (__mlx5_lag_is_active(ldev))
-		mode = mlx5_get_str_port_sel_mode(ldev);
+		mode = mlx5_get_str_port_sel_mode(ldev->mode, ldev->mode_flags);
 	else
 		ret = -EINVAL;
 	mutex_unlock(&ldev->lock);
@@ -72,6 +72,7 @@ static int state_show(struct seq_file *file, void *priv)
 static int flags_show(struct seq_file *file, void *priv)
 {
 	struct mlx5_core_dev *dev = file->private;
+	bool fdb_sel_mode_native;
 	struct mlx5_lag *ldev;
 	bool shared_fdb;
 	bool lag_active;
@@ -79,14 +80,21 @@ static int flags_show(struct seq_file *file, void *priv)
 	ldev = dev->priv.lag;
 	mutex_lock(&ldev->lock);
 	lag_active = __mlx5_lag_is_active(ldev);
-	if (lag_active)
-		shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
+	if (!lag_active)
+		goto unlock;
+
+	shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
+	fdb_sel_mode_native = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE,
+				       &ldev->mode_flags);
 
+unlock:
 	mutex_unlock(&ldev->lock);
 	if (!lag_active)
 		return -EINVAL;
 
 	seq_printf(file, "%s:%s\n", "shared_fdb", shared_fdb ? "on" : "off");
+	seq_printf(file, "%s:%s\n", "fdb_selection_mode",
+		   fdb_sel_mode_native ? "native" : "affinity");
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 2a8fc547eb37..5d41e19378e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -68,14 +68,15 @@ static int get_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
 static int mlx5_cmd_create_lag(struct mlx5_core_dev *dev, u8 *ports, int mode,
 			       unsigned long flags)
 {
-	bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags);
+	bool fdb_sel_mode = test_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE,
+				     &flags);
 	int port_sel_mode = get_port_sel_mode(mode, flags);
 	u32 in[MLX5_ST_SZ_DW(create_lag_in)] = {};
 	void *lag_ctx;
 
 	lag_ctx = MLX5_ADDR_OF(create_lag_in, in, ctx);
 	MLX5_SET(create_lag_in, in, opcode, MLX5_CMD_OP_CREATE_LAG);
-	MLX5_SET(lagc, lag_ctx, fdb_selection_mode, shared_fdb);
+	MLX5_SET(lagc, lag_ctx, fdb_selection_mode, fdb_sel_mode);
 	if (port_sel_mode == MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY) {
 		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_1, ports[0]);
 		MLX5_SET(lagc, lag_ctx, tx_remap_affinity_2, ports[1]);
@@ -471,8 +472,13 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
 
 	*flags = 0;
-	if (shared_fdb)
+	if (shared_fdb) {
 		set_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, flags);
+		set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags);
+	}
+
+	if (mode == MLX5_LAG_MODE_MPESW)
+		set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags);
 
 	if (roce_lag)
 		return mlx5_lag_set_port_sel_mode_roce(ldev, flags);
@@ -481,9 +487,9 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	return 0;
 }
 
-char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev)
+char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)
 {
-	int port_sel_mode = get_port_sel_mode(ldev->mode, ldev->mode_flags);
+	int port_sel_mode = get_port_sel_mode(mode, flags);
 
 	switch (port_sel_mode) {
 	case MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY: return "queue_affinity";
@@ -507,7 +513,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 	if (tracker)
 		mlx5_lag_print_mapping(dev0, ldev, tracker, flags);
 	mlx5_core_info(dev0, "shared_fdb:%d mode:%s\n",
-		       shared_fdb, mlx5_get_str_port_sel_mode(ldev));
+		       shared_fdb, mlx5_get_str_port_sel_mode(mode, flags));
 
 	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map, mode, flags);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index c81b173156d2..ce2ce8ccbd70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -24,6 +24,7 @@ enum {
 enum {
 	MLX5_LAG_MODE_FLAG_HASH_BASED,
 	MLX5_LAG_MODE_FLAG_SHARED_FDB,
+	MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE,
 };
 
 enum mlx5_lag_mode {
@@ -114,7 +115,7 @@ bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev);
 void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev);
 int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev);
 
-char *mlx5_get_str_port_sel_mode(struct mlx5_lag *ldev);
+char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags);
 void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
 			   u8 *ports, int *num_enabled);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index ee4b25a50315..f643202b29c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -41,7 +41,6 @@ void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev)
 int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev = dev->priv.lag;
-	bool shared_fdb;
 	int err = 0;
 
 	if (!ldev)
@@ -55,8 +54,8 @@ int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev)
 		err = -EINVAL;
 		goto out;
 	}
-	shared_fdb = mlx5_shared_fdb_supported(ldev);
-	err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, shared_fdb);
+
+	err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false);
 	if (err)
 		mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err);