Merge tag 'mlx5-fixes-2020-09-18' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes-2020-09-18

This series introduces some fixes to mlx5 driver.

Please pull and let me know if there is any problem.

v1->v2:
 Remove missing patch from -stable list.

For -stable v5.1
 ('net/mlx5: Fix FTE cleanup')

For -stable v5.3
 ('net/mlx5e: TLS, Do not expose FPGA TLS counter if not supported')
 ('net/mlx5e: Enable adding peer miss rules only if merged eswitch is supported')

For -stable v5.7
 ('net/mlx5e: Fix memory leak of tunnel info when rule under multipath not ready')

For -stable v5.8
 ('net/mlx5e: Use RCU to protect rq->xdp_prog')
 ('net/mlx5e: Fix endianness when calculating pedit mask first bit')
 ('net/mlx5e: Use synchronize_rcu to sync with NAPI')
====================

Signed-off-by: David S. Miller <[email protected]>

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

@@ -600,7 +600,7 @@ struct mlx5e_rq {
 	struct dim         dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
-	struct bpf_prog       *xdp_prog;
+	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
@@ -1005,7 +1005,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);

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

@@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work)
 					       monitor_counters_work);
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_update_ndo_stats(priv);
+	mlx5e_stats_update_ndo_stats(priv);
 	mutex_unlock(&priv->state_lock);
 	mlx5e_monitor_counter_arm(priv);
 }

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

@@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 	int err;
 	int i;
 
-	if (!MLX5_CAP_GEN(dev, pcam_reg))
-		return -EOPNOTSUPP;
-
-	if (!MLX5_CAP_PCAM_REG(dev, pplm))
-		return -EOPNOTSUPP;
+	if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm))
+		return false;
 
 	MLX5_SET(pplm_reg, in, local_port, 1);
 	err =  mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0);

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

@@ -699,6 +699,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 err_rule:
 	mlx5e_mod_hdr_detach(ct_priv->esw->dev,
 			     &esw->offloads.mod_hdr, zone_rule->mh);
+	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
 	kfree(spec);
 	return err;
@@ -958,12 +959,22 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 	return 0;
 }
 
+void mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr)
+{
+	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
+
+	if (!ct_priv || !ct_attr->ct_labels_id)
+		return;
+
+	mapping_remove(ct_priv->labels_mapping, ct_attr->ct_labels_id);
+}
+
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
 	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);

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

@@ -87,12 +87,15 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv);
 void
 mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv);
 
+void
+mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr);
+
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack);
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack);
 int
 mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 			    struct mlx5_flow_spec *spec);
@@ -130,12 +133,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
 {
 }
 
+static inline void
+mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {}
+
 static inline int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 

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

@@ -20,6 +20,11 @@ enum mlx5e_icosq_wqe_type {
 };
 
 /* General */
+static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb)
+{
+	return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST;
+}
+
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
 void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);

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

@@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      u32 *len, struct xdp_buff *xdp)
 {
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct bpf_prog *prog = rcu_dereference(rq->xdp_prog);
 	u32 act;
 	int err;
 

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

@@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 {
 	struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
 	u32 cqe_bcnt32 = cqe_bcnt;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	xsk_buff_dma_sync_for_cpu(xdp);
 	prefetch(xdp->data);
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
-	rcu_read_unlock();
-
 	/* Possible flows:
 	 * - XDP_REDIRECT to XSKMAP:
 	 *   The page is owned by the userspace from now.
@@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 * allocated first from the Reuse Ring, so it has enough space.
 	 */
 
-	if (likely(consumed)) {
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) {
 		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 */
@@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      u32 cqe_bcnt)
 {
 	struct xdp_buff *xdp = wi->di->xsk;
-	bool consumed;
 
 	/* wi->offset is not used in this function, because xdp->data and the
 	 * DMA address point directly to the necessary place. Furthermore, the
@@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 		return NULL;
 	}
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
-	rcu_read_unlock();
-
-	if (likely(consumed))
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp)))
 		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/xsk/setup.c

@@ -106,8 +106,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-	napi_synchronize(&c->napi);
-	synchronize_rcu(); /* Sync with the XSK wakeup. */
+	synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c

@@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx)
 
 /* Re-sync */
 /* Runs in work context */
-static struct mlx5_wqe_ctrl_seg *
+static int
 resync_post_get_progress_params(struct mlx5e_icosq *sq,
 				struct mlx5e_ktls_offload_context_rx *priv_rx)
 {
@@ -258,15 +258,19 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 				       PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) {
 		err = -ENOMEM;
-		goto err_out;
+		goto err_free;
 	}
 
 	buf->priv_rx = priv_rx;
 
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
+
+	spin_lock(&sq->channel->async_icosq_lock);
+
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+		spin_unlock(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
-		goto err_out;
+		goto err_dma_unmap;
 	}
 
 	pi = mlx5e_icosq_get_next_pi(sq, 1);
@@ -294,12 +298,18 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	};
 	icosq_fill_wi(sq, pi, &wi);
 	sq->pc++;
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
+	spin_unlock(&sq->channel->async_icosq_lock);
 
-	return cseg;
+	return 0;
 
+err_dma_unmap:
+	dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+err_free:
+	kfree(buf);
 err_out:
 	priv_rx->stats->tls_resync_req_skip++;
-	return ERR_PTR(err);
+	return err;
 }
 
 /* Function is called with elevated refcount.
@@ -309,10 +319,8 @@ static void resync_handle_work(struct work_struct *work)
 {
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
-	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5e_channel *c;
 	struct mlx5e_icosq *sq;
-	struct mlx5_wq_cyc *wq;
 
 	resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work);
 	priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync);
@@ -324,18 +332,9 @@ static void resync_handle_work(struct work_struct *work)
 
 	c = resync->priv->channels.c[priv_rx->rxq];
 	sq = &c->async_icosq;
-	wq = &sq->wq;
-
-	spin_lock(&c->async_icosq_lock);
 
-	cseg = resync_post_get_progress_params(sq, priv_rx);
-	if (IS_ERR(cseg)) {
+	if (resync_post_get_progress_params(sq, priv_rx))
 		refcount_dec(&resync->refcnt);
-		goto unlock;
-	}
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
-unlock:
-	spin_unlock(&c->async_icosq_lock);
 }
 
 static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync,
@@ -386,16 +385,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
 	u8 tracker_state, auth_state, *ctx;
+	struct device *dev;
 	u32 hw_seq;
 
 	priv_rx = buf->priv_rx;
 	resync = &priv_rx->resync;
-
+	dev = resync->priv->mdev->device;
 	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
 		goto out;
 
-	dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr,
-				PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE,
+				DMA_FROM_DEVICE);
 
 	ctx = buf->progress.ctx;
 	tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state);
@@ -411,6 +411,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	priv_rx->stats->tls_resync_req_end++;
 out:
 	refcount_dec(&resync->refcnt);
+	dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	kfree(buf);
 }
 
@@ -659,7 +660,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx)
 	priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx);
 	set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags);
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL);
-	napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi);
+	synchronize_rcu(); /* Sync with NAPI */
 	if (!cancel_work_sync(&priv_rx->rule.work))
 		/* completion is needed, as the priv_rx in the add flow
 		 * is maintained on the wqe info (wi), not on the socket.

drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c

@@ -35,7 +35,6 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "accel/tls.h"
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
 
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
 	unsigned int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
 	int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)