Merge tag 'mlx5-updates-2017-09-03' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2017-09-03

This series from Tariq includes micro data path optimization for mlx5e
netdevice driver.

Mainly Tariq introduces the following changes to NAPI and RX handling
path of the driver:
 - RX ring structure reorganizing
 - Trivial code refactoring and optimization
 - NAPI busy-poll for when fast UMR is in progress
 - Non-atomic state operations in NAPI context
 - Remove unnecessary fields from fast path structures
 - page-cache micro optimization
 - Rely on NAPI to avoid missing an IRQ for RX/TX shared NAPI contexts
 - Stop NAPI when irq changes affinity
 - Distribute RSS table among all RX rings
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -291,10 +291,11 @@ struct mlx5e_tstamp {
 
 enum {
 	MLX5E_RQ_STATE_ENABLED,
-	MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
 	MLX5E_RQ_STATE_AM,
 };
 
+#define MLX5E_TEST_BIT(state, nr) (state & BIT(nr))
+
 struct mlx5e_cq {
 	/* data path - accessed per cqe */
 	struct mlx5_cqwq           wq;
@@ -342,7 +343,6 @@ enum {
 
 struct mlx5e_sq_wqe_info {
 	u8  opcode;
-	u8  num_wqebbs;
 };
 
 struct mlx5e_txqsq {
@@ -418,13 +418,8 @@ struct mlx5e_xdpsq {
 struct mlx5e_icosq {
 	/* data path */
 
-	/* dirtied @completion */
-	u16                        cc;
-
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
-	u32                        dma_fifo_pc;
-	u16                        prev_cc;
 
 	struct mlx5e_cq            cq;
 
@@ -438,7 +433,6 @@ struct mlx5e_icosq {
 	void __iomem              *uar_map;
 	u32                        sqn;
 	u16                        edge;
-	struct device             *pdev;
 	__be32                     mkey_be;
 	unsigned long              state;
 
@@ -507,7 +501,7 @@ struct mlx5e_rx_am { /* Adaptive Moderation */
  */
 #define MLX5E_CACHE_UNIT	(MLX5_MPWRQ_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \
 				 MLX5_MPWRQ_PAGES_PER_WQE : NAPI_POLL_WEIGHT)
-#define MLX5E_CACHE_SIZE	(2 * roundup_pow_of_two(MLX5E_CACHE_UNIT))
+#define MLX5E_CACHE_SIZE	(4 * roundup_pow_of_two(MLX5E_CACHE_UNIT))
 struct mlx5e_page_cache {
 	u32 head;
 	u32 tail;
@@ -516,7 +510,7 @@ struct mlx5e_page_cache {
 
 struct mlx5e_rq;
 typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*);
-typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq*, struct mlx5e_rx_wqe*, u16);
+typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 
 struct mlx5e_rq {
@@ -527,21 +521,26 @@ struct mlx5e_rq {
 		struct {
 			struct mlx5e_wqe_frag_info *frag_info;
 			u32 frag_sz;	/* max possible skb frag_sz */
-			bool page_reuse;
-			bool xdp_xmit;
+			union {
+				bool page_reuse;
+				bool xdp_xmit;
+			};
 		} wqe;
 		struct {
 			struct mlx5e_mpw_info *info;
 			void                  *mtt_no_align;
+			u16                    num_strides;
+			u8                     log_stride_sz;
+			bool                   umr_in_progress;
 		} mpwqe;
 	};
 	struct {
+		u16            headroom;
 		u8             page_order;
-		u32            wqe_sz;    /* wqe data buffer size */
 		u8             map_dir;   /* dma map direction */
 	} buff;
-	__be32                 mkey_be;
 
+	struct mlx5e_channel  *channel;
 	struct device         *pdev;
 	struct net_device     *netdev;
 	struct mlx5e_tstamp   *tstamp;
@@ -550,12 +549,11 @@ struct mlx5e_rq {
 	struct mlx5e_page_cache page_cache;
 
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
-	mlx5e_fp_alloc_wqe     alloc_wqe;
+	mlx5e_fp_post_rx_wqes  post_wqes;
 	mlx5e_fp_dealloc_wqe   dealloc_wqe;
 
 	unsigned long          state;
 	int                    ix;
-	u16                    rx_headroom;
 
 	struct mlx5e_rx_am     am; /* Adaptive Moderation */
 
@@ -565,19 +563,13 @@ struct mlx5e_rq {
 
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
+	__be32                 mkey_be;
 	u8                     wq_type;
-	u32                    mpwqe_stride_sz;
-	u32                    mpwqe_num_strides;
 	u32                    rqn;
-	struct mlx5e_channel  *channel;
 	struct mlx5_core_dev  *mdev;
 	struct mlx5_core_mkey  umr_mkey;
 } ____cacheline_aligned_in_smp;
 
-enum channel_flags {
-	MLX5E_CHANNEL_NAPI_SCHED = 1,
-};
-
 struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
@@ -589,7 +581,9 @@ struct mlx5e_channel {
 	struct net_device         *netdev;
 	__be32                     mkey_be;
 	u8                         num_tc;
-	unsigned long              flags;
+
+	/* data path - accessed per napi poll */
+	struct irq_desc *irq_desc;
 
 	/* control */
 	struct mlx5e_priv         *priv;
@@ -850,11 +844,9 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
-int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix);
-int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe,	u16 ix);
+bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
-void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq);
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 
 void mlx5e_rx_am(struct mlx5e_rq *rq);
@@ -933,8 +925,7 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 
-void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
-				   u32 *indirection_rqt, int len,
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
 				   int num_channels);
 int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 

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

@@ -663,8 +663,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
 	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(priv->mdev,
-					      new_channels.params.indirection_rqt,
+		mlx5e_build_default_indir_rqt(new_channels.params.indirection_rqt,
 					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {

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

@@ -208,6 +208,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
 		s->rx_cache_full  += rq_stats->cache_full;
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
+		s->rx_cache_waive += rq_stats->cache_waive;
 
 		for (j = 0; j < priv->channels.params.num_tc; j++) {
 			sq_stats = &c->sq[j].stats;
@@ -593,12 +594,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	}
 
 	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	rq->rx_headroom = params->rq_headroom;
+	rq->buff.headroom = params->rq_headroom;
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 
-		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
+		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
 		rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe;
@@ -615,11 +616,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
-		rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz);
-		rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides);
+		rq->mpwqe.log_stride_sz = params->mpwqe_log_stride_sz;
+		rq->mpwqe.num_strides = BIT(params->mpwqe_log_num_strides);
 
-		rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
-		byte_count = rq->buff.wqe_sz;
+		byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
 
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
@@ -638,7 +638,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
 		}
-		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
+		rq->post_wqes = mlx5e_post_rx_wqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
 #ifdef CONFIG_MLX5_EN_IPSEC
@@ -654,18 +654,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
-		rq->buff.wqe_sz = params->lro_en  ?
+		byte_count = params->lro_en  ?
 				params->lro_wqe_sz :
 				MLX5E_SW2HW_MTU(c->priv, c->netdev->mtu);
 #ifdef CONFIG_MLX5_EN_IPSEC
 		if (MLX5_IPSEC_DEV(mdev))
-			rq->buff.wqe_sz += MLX5E_METADATA_ETHER_LEN;
+			byte_count += MLX5E_METADATA_ETHER_LEN;
 #endif
 		rq->wqe.page_reuse = !params->xdp_prog && !params->lro_en;
-		byte_count = rq->buff.wqe_sz;
 
 		/* calc the required page order */
-		rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->rx_headroom + byte_count);
+		rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->buff.headroom + byte_count);
 		npages = DIV_ROUND_UP(rq->wqe.frag_sz, PAGE_SIZE);
 		rq->buff.page_order = order_base_2(npages);
 
@@ -676,6 +675,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	for (i = 0; i < wq_sz; i++) {
 		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
 
+		if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT;
+
+			wqe->data.addr = cpu_to_be64(dma_offset);
+		}
+
 		wqe->data.byte_count = cpu_to_be32(byte_count);
 		wqe->data.lkey = rq->mkey_be;
 	}
@@ -882,7 +887,8 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 	u16 wqe_ix;
 
 	/* UMR WQE (if in progress) is always at wq->head */
-	if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+	    rq->mpwqe.umr_in_progress)
 		mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
 
 	while (!mlx5_wq_ll_is_empty(wq)) {
@@ -925,7 +931,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 		goto err_destroy_rq;
 
 	if (params->rx_am_enabled)
-		set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
+		c->rq.state |= BIT(MLX5E_RQ_STATE_AM);
 
 	return 0;
 
@@ -945,7 +951,6 @@ static void mlx5e_activate_rq(struct mlx5e_rq *rq)
 
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	sq->db.ico_wqe[pi].num_wqebbs = 1;
 	nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
 }
@@ -1047,7 +1052,6 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
 
-	sq->pdev      = c->pdev;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
@@ -1757,7 +1761,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	struct net_device *netdev = priv->netdev;
 	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
+	unsigned int irq;
 	int err;
+	int eqn;
 
 	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
@@ -1774,6 +1780,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 
+	mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	c->irq_desc = irq_to_desc(irq);
+
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
 	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
@@ -3693,7 +3702,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 
 		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
 		/* napi_schedule in case we have missed anything */
-		set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags);
 		napi_schedule(&c->napi);
 
 		if (old_prog)
@@ -3825,22 +3833,11 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev)
 	       2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/;
 }
 
-void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
-				   u32 *indirection_rqt, int len,
+void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len,
 				   int num_channels)
 {
-	int node = mdev->priv.numa_node;
-	int node_num_of_cores;
 	int i;
 
-	if (node == -1)
-		node = first_online_node;
-
-	node_num_of_cores = cpumask_weight(cpumask_of_node(node));
-
-	if (node_num_of_cores)
-		num_channels = min_t(int, num_channels, node_num_of_cores);
-
 	for (i = 0; i < len; i++)
 		indirection_rqt[i] = i % num_channels;
 }
@@ -3979,7 +3976,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	/* RSS */
 	params->rss_hfunc = ETH_RSS_HASH_XOR;
 	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
-	mlx5e_build_default_indir_rqt(mdev, params->indirection_rqt,
+	mlx5e_build_default_indir_rqt(params->indirection_rqt,
 				      MLX5E_INDIR_RQT_SIZE, max_channels);
 }
 

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

@@ -163,7 +163,7 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 
 static inline bool mlx5e_page_is_reserved(struct page *page)
 {
-	return page_is_pfmemalloc(page) || page_to_nid(page) != numa_node_id();
+	return page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id();
 }
 
 static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
@@ -177,8 +177,10 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
 		return false;
 	}
 
-	if (unlikely(page_is_pfmemalloc(dma_info->page)))
+	if (unlikely(mlx5e_page_is_reserved(dma_info->page))) {
+		rq->stats.cache_waive++;
 		return false;
+	}
 
 	cache->page_cache[cache->tail] = *dma_info;
 	cache->tail = tail_next;
@@ -252,7 +254,7 @@ static inline bool mlx5e_page_reuse(struct mlx5e_rq *rq,
 		!mlx5e_page_is_reserved(wi->di.page);
 }
 
-int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
+static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix];
 
@@ -263,8 +265,7 @@ int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
 		wi->offset = 0;
 	}
 
-	wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset +
-				     rq->rx_headroom);
+	wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset + rq->buff.headroom);
 	return 0;
 }
 
@@ -296,7 +297,7 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 
 static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
 {
-	return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
+	return rq->mpwqe.num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
 }
 
 static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
@@ -305,7 +306,7 @@ static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
 					    u32 page_idx, u32 frag_offset,
 					    u32 len)
 {
-	unsigned int truesize =	ALIGN(len, rq->mpwqe_stride_sz);
+	unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz));
 
 	dma_sync_single_for_cpu(rq->pdev,
 				wi->umr.dma_info[page_idx].addr + frag_offset,
@@ -358,7 +359,6 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 	/* fill sq edge with nops to avoid wqe wrap around */
 	while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
 		sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
-		sq->db.ico_wqe[pi].num_wqebbs = 1;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
 
@@ -369,41 +369,35 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
 			    MLX5_OPCODE_UMR);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
-	sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
 	sq->pc += num_wqebbs;
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl);
 }
 
 static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
-				    struct mlx5e_rx_wqe *wqe,
 				    u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-	u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT;
 	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
+	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
 	int err;
 	int i;
 
-	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
 		err = mlx5e_page_alloc_mapped(rq, dma_info);
 		if (unlikely(err))
 			goto err_unmap;
 		wi->umr.mtt[i] = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
 		page_ref_add(dma_info->page, pg_strides);
-		wi->skbs_frags[i] = 0;
 	}
 
+	memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE);
 	wi->consumed_strides = 0;
-	wqe->data.addr = cpu_to_be64(dma_offset);
 
 	return 0;
 
 err_unmap:
 	while (--i >= 0) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+		dma_info--;
 		page_ref_sub(dma_info->page, pg_strides);
 		mlx5e_page_release(rq, dma_info, true);
 	}
@@ -414,27 +408,21 @@ err_unmap:
 void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 {
 	int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
+	struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0];
 	int i;
 
-	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
-		struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
-
+	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
 		page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
 		mlx5e_page_release(rq, dma_info, true);
 	}
 }
 
-void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
+static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
 {
 	struct mlx5_wq_ll *wq = &rq->wq;
 	struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
 
-	clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
-
-	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) {
-		mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
-		return;
-	}
+	rq->mpwqe.umr_in_progress = false;
 
 	mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
 
@@ -444,16 +432,18 @@ void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
 	mlx5_wq_ll_update_db_record(wq);
 }
 
-int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
+static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	int err;
 
-	err = mlx5e_alloc_rx_umr_mpwqe(rq, wqe, ix);
-	if (unlikely(err))
+	err = mlx5e_alloc_rx_umr_mpwqe(rq, ix);
+	if (unlikely(err)) {
+		rq->stats.buff_alloc_err++;
 		return err;
-	set_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
+	}
+	rq->mpwqe.umr_in_progress = true;
 	mlx5e_post_umr_wqe(rq, ix);
-	return -EBUSY;
+	return 0;
 }
 
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
@@ -463,94 +453,150 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	mlx5e_free_rx_mpwqe(rq, wi);
 }
 
-#define RQ_CANNOT_POST(rq) \
-	(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \
-	 test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
-
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 {
 	struct mlx5_wq_ll *wq = &rq->wq;
+	int err;
 
-	if (unlikely(RQ_CANNOT_POST(rq)))
+	if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
 		return false;
 
-	while (!mlx5_wq_ll_is_full(wq)) {
+	if (mlx5_wq_ll_is_full(wq))
+		return false;
+
+	do {
 		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
-		int err;
 
-		err = rq->alloc_wqe(rq, wqe, wq->head);
-		if (err == -EBUSY)
-			return true;
+		err = mlx5e_alloc_rx_wqe(rq, wqe, wq->head);
 		if (unlikely(err)) {
 			rq->stats.buff_alloc_err++;
 			break;
 		}
 
 		mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
-	}
+	} while (!mlx5_wq_ll_is_full(wq));
 
 	/* ensure wqes are visible to device before updating doorbell record */
 	dma_wmb();
 
 	mlx5_wq_ll_update_db_record(wq);
 
-	return !mlx5_wq_ll_is_full(wq);
+	return !!err;
+}
+
+static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
+					     struct mlx5e_icosq *sq,
+					     struct mlx5e_rq *rq,
+					     struct mlx5_cqe64 *cqe)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1;
+	struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
+
+	mlx5_cqwq_pop(&cq->wq);
+
+	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
+		WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n",
+			  cqe->op_own);
+		return;
+	}
+
+	if (likely(icowi->opcode == MLX5_OPCODE_UMR)) {
+		mlx5e_post_rx_mpwqe(rq);
+		return;
+	}
+
+	if (unlikely(icowi->opcode != MLX5_OPCODE_NOP))
+		WARN_ONCE(true,
+			  "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n",
+			  icowi->opcode);
+}
+
+static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
+{
+	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
+	struct mlx5_cqe64 *cqe;
+
+	if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+		return;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (likely(!cqe))
+		return;
+
+	/* by design, there's only a single cqe */
+	mlx5e_poll_ico_single_cqe(cq, sq, rq, cqe);
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+}
+
+bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+
+	if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
+		return false;
+
+	mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq);
+
+	if (mlx5_wq_ll_is_full(wq))
+		return false;
+
+	if (!rq->mpwqe.umr_in_progress)
+		mlx5e_alloc_rx_mpwqe(rq, wq->head);
+
+	return true;
 }
 
 static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 				 u32 cqe_bcnt)
 {
 	struct ethhdr	*eth = (struct ethhdr *)(skb->data);
-	struct iphdr	*ipv4;
-	struct ipv6hdr	*ipv6;
 	struct tcphdr	*tcp;
 	int network_depth = 0;
 	__be16 proto;
 	u16 tot_len;
+	void *ip_p;
 
 	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
-	int tcp_ack = ((l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
-		       (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA));
+	u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) ||
+		(l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA);
 
 	skb->mac_len = ETH_HLEN;
 	proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
 
-	ipv4 = (struct iphdr *)(skb->data + network_depth);
-	ipv6 = (struct ipv6hdr *)(skb->data + network_depth);
 	tot_len = cqe_bcnt - network_depth;
+	ip_p = skb->data + network_depth;
 
 	if (proto == htons(ETH_P_IP)) {
-		tcp = (struct tcphdr *)(skb->data + network_depth +
-					sizeof(struct iphdr));
-		ipv6 = NULL;
-		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
-	} else {
-		tcp = (struct tcphdr *)(skb->data + network_depth +
-					sizeof(struct ipv6hdr));
-		ipv4 = NULL;
-		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
-	}
-
-	if (get_cqe_lro_tcppsh(cqe))
-		tcp->psh                = 1;
+		struct iphdr *ipv4 = ip_p;
 
-	if (tcp_ack) {
-		tcp->ack                = 1;
-		tcp->ack_seq            = cqe->lro_ack_seq_num;
-		tcp->window             = cqe->lro_tcp_win;
-	}
+		tcp = ip_p + sizeof(struct iphdr);
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 
-	if (ipv4) {
 		ipv4->ttl               = cqe->lro_min_ttl;
 		ipv4->tot_len           = cpu_to_be16(tot_len);
 		ipv4->check             = 0;
 		ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
 						       ipv4->ihl);
 	} else {
+		struct ipv6hdr *ipv6 = ip_p;
+
+		tcp = ip_p + sizeof(struct ipv6hdr);
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+
 		ipv6->hop_limit         = cqe->lro_min_ttl;
 		ipv6->payload_len       = cpu_to_be16(tot_len -
 						      sizeof(struct ipv6hdr));
 	}
+
+	tcp->psh = get_cqe_lro_tcppsh(cqe);
+
+	if (tcp_ack) {
+		tcp->ack                = 1;
+		tcp->ack_seq            = cqe->lro_ack_seq_num;
+		tcp->window             = cqe->lro_tcp_win;
+	}
 }
 
 static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
@@ -776,9 +822,9 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
 	struct mlx5e_dma_info *di = &wi->di;
+	u16 rx_headroom = rq->buff.headroom;
 	struct sk_buff *skb;
 	void *va, *data;
-	u16 rx_headroom = rq->rx_headroom;
 	bool consumed;
 	u32 frag_size;
 
@@ -911,7 +957,7 @@ static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
 					   struct sk_buff *skb)
 {
 	u16 stride_ix      = mpwrq_get_cqe_stride_index(cqe);
-	u32 wqe_offset     = stride_ix * rq->mpwqe_stride_sz;
+	u32 wqe_offset     = stride_ix << rq->mpwqe.log_stride_sz;
 	u32 head_offset    = wqe_offset & (PAGE_SIZE - 1);
 	u32 page_idx       = wqe_offset >> PAGE_SHIFT;
 	u32 head_page_idx  = page_idx;
@@ -979,7 +1025,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 mpwrq_cqe_out:
-	if (likely(wi->consumed_strides < rq->mpwqe_num_strides))
+	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
 
 	mlx5e_free_rx_mpwqe(rq, wi);
@@ -989,21 +1035,23 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
+	struct mlx5e_xdpsq *xdpsq;
+	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
-	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
+	if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED)))
 		return 0;
 
 	if (cq->decmprs_left)
 		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
 
-	for (; work_done < budget; work_done++) {
-		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		return 0;
 
-		if (!cqe)
-			break;
+	xdpsq = &rq->xdpsq;
 
+	do {
 		if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
 			work_done +=
 				mlx5e_decompress_cqes_start(rq, cq,
@@ -1014,7 +1062,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		mlx5_cqwq_pop(&cq->wq);
 
 		rq->handle_rx_cqe(rq, cqe);
-	}
+	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	if (xdpsq->db.doorbell) {
 		mlx5e_xmit_xdp_doorbell(xdpsq);
@@ -1032,13 +1080,18 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 {
 	struct mlx5e_xdpsq *sq;
+	struct mlx5_cqe64 *cqe;
 	struct mlx5e_rq *rq;
 	u16 sqcc;
 	int i;
 
 	sq = container_of(cq, struct mlx5e_xdpsq, cq);
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+	if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+		return false;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
 		return false;
 
 	rq = container_of(sq, struct mlx5e_rq, xdpsq);
@@ -1048,15 +1101,11 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	 */
 	sqcc = sq->cc;
 
-	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
-		struct mlx5_cqe64 *cqe;
+	i = 0;
+	do {
 		u16 wqe_counter;
 		bool last_wqe;
 
-		cqe = mlx5_cqwq_get_cqe(&cq->wq);
-		if (!cqe)
-			break;
-
 		mlx5_cqwq_pop(&cq->wq);
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
@@ -1074,7 +1123,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 			/* Recycle RX page */
 			mlx5e_page_release(rq, di, true);
 		} while (!last_wqe);
-	}
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 

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

@@ -84,6 +84,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_full;
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
+	u64 rx_cache_waive;
 
 	/* Special handling counters */
 	u64 link_down_events_phy;
@@ -123,6 +124,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) },
 };
 
@@ -354,6 +356,7 @@ struct mlx5e_rq_stats {
 	u64 cache_full;
 	u64 cache_empty;
 	u64 cache_busy;
+	u64 cache_waive;
 };
 
 static const struct counter_desc rq_stats_desc[] = {
@@ -377,6 +380,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
 };
 
 struct mlx5e_sq_stats {

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

@@ -394,6 +394,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_txqsq *sq;
+	struct mlx5_cqe64 *cqe;
 	u32 dma_fifo_cc;
 	u32 nbytes;
 	u16 npkts;
@@ -402,7 +403,11 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_txqsq, cq);
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+	if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED)))
+		return false;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
 		return false;
 
 	npkts = 0;
@@ -416,15 +421,11 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	/* avoid dirtying sq cache line every cqe */
 	dma_fifo_cc = sq->dma_fifo_cc;
 
-	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
-		struct mlx5_cqe64 *cqe;
+	i = 0;
+	do {
 		u16 wqe_counter;
 		bool last_wqe;
 
-		cqe = mlx5_cqwq_get_cqe(&cq->wq);
-		if (!cqe)
-			break;
-
 		mlx5_cqwq_pop(&cq->wq);
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
@@ -467,7 +468,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			sqcc += wi->num_wqebbs;
 			napi_consume_skb(skb, napi_budget);
 		} while (!last_wqe);
-	}
+
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 

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

@@ -30,66 +30,18 @@
  * SOFTWARE.
  */
 
+#include <linux/irq.h>
 #include "en.h"
 
-static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
-					     struct mlx5e_icosq *sq,
-					     struct mlx5_cqe64 *cqe,
-					     u16 *sqcc)
+static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1;
-	struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
-	struct mlx5e_rq *rq = &sq->channel->rq;
-
-	prefetch(rq);
-	mlx5_cqwq_pop(&cq->wq);
-	*sqcc += icowi->num_wqebbs;
-
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
-		WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n",
-			  cqe->op_own);
-		return;
-	}
-
-	if (likely(icowi->opcode == MLX5_OPCODE_UMR)) {
-		mlx5e_post_rx_mpwqe(rq);
-		return;
-	}
-
-	if (unlikely(icowi->opcode != MLX5_OPCODE_NOP))
-		WARN_ONCE(true,
-			  "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n",
-			  icowi->opcode);
-}
-
-static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
-{
-	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
-	struct mlx5_cqe64 *cqe;
-	u16 sqcc;
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return;
-
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
-	if (likely(!cqe))
-		return;
+	int current_cpu = smp_processor_id();
+	const struct cpumask *aff;
+	struct irq_data *idata;
 
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	/* by design, there's only a single cqe */
-	mlx5e_poll_ico_single_cqe(cq, sq, cqe, &sqcc);
-
-	mlx5_cqwq_update_db_record(&cq->wq);
-
-	/* ensure cq space is freed before enabling more cqes */
-	wmb();
-
-	sq->cc = sqcc;
+	idata = irq_desc_get_irq_data(c->irq_desc);
+	aff = irq_data_get_affinity_mask(idata);
+	return cpumask_test_cpu(current_cpu, aff);
 }
 
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
@@ -100,8 +52,6 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	int work_done;
 	int i;
 
-	clear_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags);
-
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
@@ -111,25 +61,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
 	busy |= work_done == budget;
 
-	mlx5e_poll_ico_cq(&c->icosq.cq);
+	busy |= c->rq.post_wqes(&c->rq);
 
-	busy |= mlx5e_post_rx_wqes(&c->rq);
-
-	if (busy)
-		return budget;
-
-	napi_complete_done(napi, work_done);
+	if (busy) {
+		if (likely(mlx5e_channel_no_affinity_change(c)))
+			return budget;
+		if (work_done == budget)
+			work_done--;
+	}
 
-	/* avoid losing completion event during/after polling cqs */
-	if (test_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags)) {
-		napi_schedule(napi);
+	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
-	}
 
 	for (i = 0; i < c->num_tc; i++)
 		mlx5e_cq_arm(&c->sq[i].cq);
 
-	if (test_bit(MLX5E_RQ_STATE_AM, &c->rq.state))
+	if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM))
 		mlx5e_rx_am(&c->rq);
 
 	mlx5e_cq_arm(&c->rq.cq);
@@ -143,7 +90,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
 	cq->event_ctr++;
-	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
 	napi_schedule(cq->napi);
 }
 

include/linux/mlx5/device.h

@@ -709,7 +709,7 @@ static inline int mlx5_get_cqe_format(struct mlx5_cqe64 *cqe)
 	return (cqe->op_own >> 2) & 0x3;
 }
 
-static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
+static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
 {
 	return (cqe->lro_tcppsh_abort_dupack >> 6) & 1;
 }