Merge tag 'mlx5-fixes-2019-04-09' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
Mellanox, mlx5 fixes 2019-04-09

This series provides some fixes to mlx5 driver.

I've cc'ed some of the checksum fixes to Eric Dumazet and i would like to get
his feedback before you pull.

For -stable v4.19
('net/mlx5: FPGA, tls, idr remove on flow delete')
('net/mlx5: FPGA, tls, hold rcu read lock a bit longer')

For -stable v4.20
('net/mlx5e: Rx, Check ip headers sanity')
('Revert "net/mlx5e: Enable reporting checksum unnecessary also for L3 packets"')
('net/mlx5e: Rx, Fixup skb checksum for packets with tail padding')

For -stable v5.0
('net/mlx5e: Switch to Toeplitz RSS hash by default')
('net/mlx5e: Protect against non-uplink representor for encap')
('net/mlx5e: XDP, Avoid checksum complete when XDP prog is loaded')
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -858,6 +858,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs);
  * switching channels
  */
 typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
 int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 			       struct mlx5e_channels *new_chs,
 			       mlx5e_fp_hw_modify hw_modify);

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

@@ -186,12 +186,17 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
 
 static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
 {
-	int err;
+	int err = 0;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
 	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 

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

@@ -39,6 +39,10 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 			return -EOPNOTSUPP;
 	}
 
+	if (!(mlx5e_eswitch_rep(*out_dev) &&
+	      mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 

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

@@ -1768,7 +1768,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	struct mlx5e_channel *c;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+	    priv->channels.params.xdp_prog)
 		return 0;
 
 	for (i = 0; i < channels->num; i++) {

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

@@ -951,7 +951,11 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+	/* We disable csum_complete when XDP is enabled since
+	 * XDP programs might manipulate packets which will render
+	 * skb->checksum incorrect.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
 	return 0;
@@ -2937,6 +2941,14 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 	return 0;
 }
 
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channels new_channels = {};
+
+	new_channels.params = priv->channels.params;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
@@ -4161,11 +4173,10 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	if (!report_failed)
 		goto unlock;
 
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
+	err = mlx5e_safe_reopen_channels(priv);
 	if (err)
 		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
 			   err);
 
 unlock:
@@ -4553,7 +4564,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 {
 	enum mlx5e_traffic_types tt;
 
-	rss_params->hfunc = ETH_RSS_HASH_XOR;
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
 			    sizeof(rss_params->toeplitz_hash_key));
 	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,

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

@@ -692,7 +692,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
 {
 	*proto = ((struct ethhdr *)skb->data)->h_proto;
 	*proto = __vlan_get_protocol(skb, *proto, network_depth);
-	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+	if (*proto == htons(ETH_P_IP))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+	if (*proto == htons(ETH_P_IPV6))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+	return false;
 }
 
 static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
@@ -712,17 +719,6 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
 	rq->stats->ecn_mark += !!rc;
 }
 
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
-	const void *fcs_bytes;
-	u32 _fcs_bytes;
-
-	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
-				       ETH_FCS_LEN, &_fcs_bytes);
-
-	return __get_unaligned_cpu32(fcs_bytes);
-}
-
 static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 {
 	void *ip_p = skb->data + network_depth;
@@ -733,6 +729,68 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 
 #define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
 
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+		       struct mlx5e_rq_stats *stats)
+{
+	stats->csum_complete_tail_slow++;
+	skb->csum = csum_block_add(skb->csum,
+				   skb_checksum(skb, offset, len, 0),
+				   offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+		  struct mlx5e_rq_stats *stats)
+{
+	u8 tail_padding[MAX_PADDING];
+	int len = skb->len - offset;
+	void *tail;
+
+	if (unlikely(len > MAX_PADDING)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	tail = skb_header_pointer(skb, offset, len, tail_padding);
+	if (unlikely(!tail)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	stats->csum_complete_tail++;
+	skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+		       struct mlx5e_rq_stats *stats)
+{
+	struct ipv6hdr *ip6;
+	struct iphdr   *ip4;
+	int pkt_len;
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		ip4 = (struct iphdr *)(skb->data + network_depth);
+		pkt_len = network_depth + ntohs(ip4->tot_len);
+		break;
+	case htons(ETH_P_IPV6):
+		ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+		pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+		break;
+	default:
+		return;
+	}
+
+	if (likely(pkt_len >= skb->len))
+		return;
+
+	tail_padding_csum(skb, pkt_len, stats);
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -752,7 +810,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+	/* True when explicitly set via priv flag, or XDP prog is loaded */
+	if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
 		goto csum_unnecessary;
 
 	/* CQE csum doesn't cover padding octets in short ethernet
@@ -780,18 +839,15 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
-		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_block_add(skb->csum,
-						   (__force __wsum)mlx5e_get_fcs(skb),
-						   skb->len - ETH_FCS_LEN);
+
+		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
 		stats->csum_complete++;
 		return;
 	}
 
 csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
-		   ((cqe->hds_ip_ext & CQE_L4_OK) ||
-		    (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;

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

@@ -59,6 +59,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
@@ -151,6 +153,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+		s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
@@ -1190,6 +1194,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },

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

@@ -71,6 +71,8 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
+	u64 rx_csum_complete_tail;
+	u64 rx_csum_complete_tail_slow;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
@@ -181,6 +183,8 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_complete_tail;
+	u64 csum_complete_tail_slow;
 	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;

drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c

@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
 					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -217,22 +203,22 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	void *cmd;
 	int ret;
 
-	rcu_read_lock();
-	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
-
-	if (!flow) {
-		WARN_ONCE(1, "Received NULL pointer for handle\n");
-		return -EINVAL;
-	}
-
 	buf = kzalloc(size, GFP_ATOMIC);
 	if (!buf)
 		return -ENOMEM;
 
 	cmd = (buf + 1);
 
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
@@ -253,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -261,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -272,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -283,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -297,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }