Merge branch 'mlx5-xsk-updates-part4-and-more'

Saeed Mahameed says:

====================
mlx5 xsk updates part4 and more

1) Final part of xsk improvements,
in this series Maxim continues to improve xsk implementation
 a) XSK Busy polling support
 b) Use KLM to avoid Frame overrun in unaligned mode
 c) Optimize unaligned more for certain frame sizes
 d) Other straight forward minor optimizations.

part 1: https://lore.kernel.org/netdev/20220927203611.244301-1-saeed@kernel.org/
part 2: https://lore.kernel.org/netdev/20220929072156.93299-1-saeed@kernel.org/
part 3: https://lore.kernel.org/netdev/20220930162903.62262-1-saeed@kernel.org/

2) Oversize packets firmware counter, from Gal.

3) Set default grace period for health reporters based on function type

4) Some minor E-Switch improvements
====================

Link: https://lore.kernel.org/r/20221002045632.291612-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -109,12 +109,8 @@ struct page_pool;
 #define MLX5_MPWRQ_MAX_PAGES_PER_WQE \
 	rounddown_pow_of_two(MLX5_UMR_MAX_MTT_SPACE / sizeof(struct mlx5_mtt))
 
-#define MLX5_ALIGN_MTTS(mtts)		(ALIGN(mtts, 8))
-#define MLX5_ALIGNED_MTTS_OCTW(mtts)	((mtts) / 2)
-#define MLX5_MTT_OCTW(mtts)		(MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts)))
-#define MLX5_KSM_OCTW(ksms)             (ksms)
 #define MLX5E_MAX_RQ_NUM_MTTS	\
-	(ALIGN_DOWN(U16_MAX, 4) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
+	(ALIGN_DOWN(U16_MAX, 4) * 2) /* Fits into u16 and aligned by WQEBB. */
 #define MLX5E_MAX_RQ_NUM_KSMS (U16_MAX - 1) /* So that num_ksms fits into u16. */
 #define MLX5E_ORDER2_MAX_PACKET_MTU (order_base_2(10 * 1024))
 
@@ -681,6 +677,13 @@ struct mlx5e_hw_gro_data {
 	int second_ip_id;
 };
 
+enum mlx5e_mpwrq_umr_mode {
+	MLX5E_MPWRQ_UMR_MODE_ALIGNED,
+	MLX5E_MPWRQ_UMR_MODE_UNALIGNED,
+	MLX5E_MPWRQ_UMR_MODE_OVERSIZED,
+	MLX5E_MPWRQ_UMR_MODE_TRIPLE,
+};
+
 struct mlx5e_rq {
 	/* data path */
 	union {
@@ -708,7 +711,7 @@ struct mlx5e_rq {
 			u8                     pages_per_wqe;
 			u8                     umr_wqebbs;
 			u8                     mtts_per_wqe;
-			u8                     unaligned;
+			u8                     umr_mode;
 			struct mlx5e_shampo_hd *shampo;
 		} mpwqe;
 	};
@@ -1008,7 +1011,7 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
-					    bool unaligned);
+					    enum mlx5e_mpwrq_umr_mode umr_mode);
 
 void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq, u16 len, u16 start, bool close);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
@@ -1036,6 +1039,7 @@ struct mlx5e_rq_param;
 int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 		  struct mlx5e_xsk_param *xsk, int node,
 		  struct mlx5e_rq *rq);
+#define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
 int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
 void mlx5e_close_rq(struct mlx5e_rq *rq);
 int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);

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

@@ -56,13 +56,23 @@ struct mlx5e_create_sq_param {
 /* Striding RQ dynamic parameters */
 
 u8 mlx5e_mpwrq_page_shift(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk);
-u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_umr_wqebbs(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u8 mlx5e_mpwrq_mtts_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
-u32 mlx5e_mpwrq_max_num_entries(struct mlx5_core_dev *mdev, bool unaligned);
-u8 mlx5e_mpwrq_max_log_rq_pkts(struct mlx5_core_dev *mdev, u8 page_shift, bool unaligned);
+enum mlx5e_mpwrq_umr_mode
+mlx5e_mpwrq_umr_mode(struct mlx5_core_dev *mdev, struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwrq_umr_entry_size(enum mlx5e_mpwrq_umr_mode mode);
+u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
+			  enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
+			     enum mlx5e_mpwrq_umr_mode umr_mode);
+u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
+			   enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_umr_wqebbs(struct mlx5_core_dev *mdev, u8 page_shift,
+			  enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_mtts_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,
+			    enum mlx5e_mpwrq_umr_mode umr_mode);
+u32 mlx5e_mpwrq_max_num_entries(struct mlx5_core_dev *mdev,
+				enum mlx5e_mpwrq_umr_mode umr_mode);
+u8 mlx5e_mpwrq_max_log_rq_pkts(struct mlx5_core_dev *mdev, u8 page_shift,
+			       enum mlx5e_mpwrq_umr_mode umr_mode);
 
 /* Parameter calculations */
 

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

@@ -99,6 +99,15 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 
 	mlx5e_build_xsk_param(pool, &xsk);
 
+	if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+	    mlx5e_mpwrq_umr_mode(priv->mdev, &xsk) == MLX5E_MPWRQ_UMR_MODE_OVERSIZED) {
+		const char *recommendation = is_power_of_2(xsk.chunk_size) ?
+			"Upgrade firmware" : "Disable striding RQ";
+
+		mlx5_core_warn(priv->mdev, "Expected slowdown with XSK frame size %u. %s for better performance.\n",
+			       xsk.chunk_size, recommendation);
+	}
+
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		/* XSK objects will be created on open. */
 		goto validate_closed;
@@ -126,6 +135,9 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 
 	mlx5e_rx_res_xsk_update(priv->rx_res, &priv->channels, ix, true);
 
+	mlx5e_deactivate_rq(&c->rq);
+	mlx5e_flush_rq(&c->rq, MLX5_RQC_STATE_RDY);
+
 	return 0;
 
 err_remove_pool:
@@ -165,7 +177,13 @@ static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
 		goto remove_pool;
 
 	c = priv->channels.c[ix];
+
+	mlx5e_activate_rq(&c->rq);
+	mlx5e_trigger_napi_icosq(c);
+	mlx5e_wait_for_min_rx_wqes(&c->rq, MLX5E_RQ_WQES_TIMEOUT);
+
 	mlx5e_rx_res_xsk_update(priv->rx_res, &priv->channels, ix, false);
+
 	mlx5e_deactivate_xsk(c);
 	mlx5e_close_xsk(c);
 

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

@@ -41,7 +41,15 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
 	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, sizeof(struct mlx5e_umr_wqe));
 
-	if (unlikely(rq->mpwqe.unaligned)) {
+	if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED)) {
+		for (i = 0; i < batch; i++) {
+			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
+
+			umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
+				.ptag = cpu_to_be64(addr | MLX5_EN_WR),
+			};
+		}
+	} else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED)) {
 		for (i = 0; i < batch; i++) {
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
@@ -50,12 +58,46 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 				.va = cpu_to_be64(addr),
 			};
 		}
+	} else if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE)) {
+		u32 mapping_size = 1 << (rq->mpwqe.page_shift - 2);
+
+		for (i = 0; i < batch; i++) {
+			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
+
+			umr_wqe->inline_ksms[i << 2] = (struct mlx5_ksm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(addr),
+			};
+			umr_wqe->inline_ksms[(i << 2) + 1] = (struct mlx5_ksm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(addr + mapping_size),
+			};
+			umr_wqe->inline_ksms[(i << 2) + 2] = (struct mlx5_ksm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(addr + mapping_size * 2),
+			};
+			umr_wqe->inline_ksms[(i << 2) + 3] = (struct mlx5_ksm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(rq->wqe_overflow.addr),
+			};
+		}
 	} else {
+		__be32 pad_size = cpu_to_be32((1 << rq->mpwqe.page_shift) -
+					      rq->xsk_pool->chunk_size);
+		__be32 frame_size = cpu_to_be32(rq->xsk_pool->chunk_size);
+
 		for (i = 0; i < batch; i++) {
 			dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk);
 
-			umr_wqe->inline_mtts[i] = (struct mlx5_mtt) {
-				.ptag = cpu_to_be64(addr | MLX5_EN_WR),
+			umr_wqe->inline_klms[i << 1] = (struct mlx5_klm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(addr),
+				.bcount = frame_size,
+			};
+			umr_wqe->inline_klms[(i << 1) + 1] = (struct mlx5_klm) {
+				.key = rq->mkey_be,
+				.va = cpu_to_be64(rq->wqe_overflow.addr),
+				.bcount = pad_size,
 			};
 		}
 	}
@@ -66,9 +108,14 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
 
+	/* Optimized for speed: keep in sync with mlx5e_mpwrq_umr_entry_size. */
 	offset = ix * rq->mpwqe.mtts_per_wqe;
-	if (likely(!rq->mpwqe.unaligned))
-		offset = MLX5_ALIGNED_MTTS_OCTW(offset);
+	if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED))
+		offset = offset * sizeof(struct mlx5_mtt) / MLX5_OCTWORD;
+	else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_OVERSIZED))
+		offset = offset * sizeof(struct mlx5_klm) * 2 / MLX5_OCTWORD;
+	else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE))
+		offset = offset * sizeof(struct mlx5_ksm) * 4 / MLX5_OCTWORD;
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
 
 	icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {

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

@@ -5,7 +5,6 @@
 #define __MLX5_EN_XSK_RX_H__
 
 #include "en.h"
-#include <net/xdp_sock_drv.h>
 
 /* RX data path */
 
@@ -21,17 +20,4 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      struct mlx5e_wqe_frag_info *wi,
 					      u32 cqe_bcnt);
 
-static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err)
-{
-	if (!xsk_uses_need_wakeup(rq->xsk_pool))
-		return alloc_err;
-
-	if (unlikely(alloc_err))
-		xsk_set_rx_need_wakeup(rq->xsk_pool);
-	else
-		xsk_clear_rx_need_wakeup(rq->xsk_pool);
-
-	return false;
-}
-
 #endif /* __MLX5_EN_XSK_RX_H__ */

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

@@ -5,7 +5,6 @@
 #define __MLX5_EN_XSK_TX_H__
 
 #include "en.h"
-#include <net/xdp_sock_drv.h>
 
 /* TX data path */
 
@@ -13,15 +12,4 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
 
 bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget);
 
-static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq)
-{
-	if (!xsk_uses_need_wakeup(sq->xsk_pool))
-		return;
-
-	if (sq->pc != sq->cc)
-		xsk_clear_tx_need_wakeup(sq->xsk_pool);
-	else
-		xsk_set_tx_need_wakeup(sq->xsk_pool);
-}
-
 #endif /* __MLX5_EN_XSK_TX_H__ */

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

@@ -314,7 +314,9 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 	/* Limitation for regular RQ. XSK RQ may clamp the queue length in
 	 * mlx5e_mpwqe_get_log_rq_size.
 	 */
-	u8 max_log_mpwrq_pkts = mlx5e_mpwrq_max_log_rq_pkts(priv->mdev, PAGE_SHIFT, false);
+	u8 max_log_mpwrq_pkts = mlx5e_mpwrq_max_log_rq_pkts(priv->mdev,
+							    PAGE_SHIFT,
+							    MLX5E_MPWRQ_UMR_MODE_ALIGNED);
 
 	param->rx_max_pending = 1 << min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE,
 					   max_log_mpwrq_pkts);

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

@@ -41,6 +41,7 @@
 #include <net/gro.h>
 #include <net/udp.h>
 #include <net/tcp.h>
+#include <net/xdp_sock_drv.h>
 #include "en.h"
 #include "en/txrx.h"
 #include "en_tc.h"
@@ -681,7 +682,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 
-	offset = MLX5_ALIGNED_MTTS_OCTW(ix * rq->mpwqe.mtts_per_wqe);
+	offset = (ix * rq->mpwqe.mtts_per_wqe) * sizeof(struct mlx5_mtt) / MLX5_OCTWORD;
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
@@ -1709,9 +1710,10 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto free_wqe;
 	}
 
-	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+	skb = INDIRECT_CALL_3(rq->wqe.skb_from_cqe,
 			      mlx5e_skb_from_cqe_linear,
 			      mlx5e_skb_from_cqe_nonlinear,
+			      mlx5e_xsk_skb_from_cqe_linear,
 			      rq, wi, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
@@ -2180,9 +2182,10 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 
 	cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
 
-	skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
+	skb = INDIRECT_CALL_3(rq->mpwqe.skb_from_cqe_mpwrq,
 			      mlx5e_skb_from_cqe_mpwrq_linear,
 			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
+			      mlx5e_xsk_skb_from_cqe_mpwrq_linear,
 			      rq, wi, cqe_bcnt, head_offset, page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;

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

@@ -641,17 +641,26 @@ static const struct counter_desc vnic_env_stats_dev_oob_desc[] = {
 		VNIC_ENV_OFF(vport_env.internal_rq_out_of_buffer) },
 };
 
+static const struct counter_desc vnic_env_stats_drop_desc[] = {
+	{ "rx_oversize_pkts_buffer",
+		VNIC_ENV_OFF(vport_env.eth_wqe_too_small) },
+};
+
 #define NUM_VNIC_ENV_STEER_COUNTERS(dev) \
 	(MLX5_CAP_GEN(dev, nic_receive_steering_discard) ? \
 	 ARRAY_SIZE(vnic_env_stats_steer_desc) : 0)
 #define NUM_VNIC_ENV_DEV_OOB_COUNTERS(dev) \
 	(MLX5_CAP_GEN(dev, vnic_env_int_rq_oob) ? \
 	 ARRAY_SIZE(vnic_env_stats_dev_oob_desc) : 0)
+#define NUM_VNIC_ENV_DROP_COUNTERS(dev) \
+	(MLX5_CAP_GEN(dev, eth_wqe_too_small) ? \
+	 ARRAY_SIZE(vnic_env_stats_drop_desc) : 0)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(vnic_env)
 {
 	return NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev) +
-		NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev);
+	       NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev) +
+	       NUM_VNIC_ENV_DROP_COUNTERS(priv->mdev);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vnic_env)
@@ -665,6 +674,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(vnic_env)
 	for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       vnic_env_stats_dev_oob_desc[i].format);
+
+	for (i = 0; i < NUM_VNIC_ENV_DROP_COUNTERS(priv->mdev); i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN,
+		       vnic_env_stats_drop_desc[i].format);
+
 	return idx;
 }
 
@@ -679,6 +693,11 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(vnic_env)
 	for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++)
 		data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
 						  vnic_env_stats_dev_oob_desc, i);
+
+	for (i = 0; i < NUM_VNIC_ENV_DROP_COUNTERS(priv->mdev); i++)
+		data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out,
+						  vnic_env_stats_drop_desc, i);
+
 	return idx;
 }
 

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

@@ -273,6 +273,10 @@ struct mlx5e_qcounter_stats {
 	u32 rx_if_down_packets;
 };
 
+#define VNIC_ENV_GET(vnic_env_stats, c) \
+	MLX5_GET(query_vnic_env_out, (vnic_env_stats)->query_vnic_env_out, \
+		 vport_env.c)
+
 struct mlx5e_vnic_env_stats {
 	__be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
 };

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

@@ -4463,7 +4463,7 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	int err = 0;
 
 	if (!mlx5_esw_hold(priv->mdev))
-		return -EAGAIN;
+		return -EBUSY;
 
 	mlx5_esw_get(priv->mdev);
 

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

@@ -31,6 +31,7 @@
  */
 
 #include <linux/irq.h>
+#include <net/xdp_sock_drv.h>
 #include "en.h"
 #include "en/txrx.h"
 #include "en/xdp.h"
@@ -86,26 +87,36 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
 
 static bool mlx5e_napi_xsk_post(struct mlx5e_xdpsq *xsksq, struct mlx5e_rq *xskrq)
 {
+	bool need_wakeup = xsk_uses_need_wakeup(xskrq->xsk_pool);
 	bool busy_xsk = false, xsk_rx_alloc_err;
 
-	/* Handle the race between the application querying need_wakeup and the
-	 * driver setting it:
-	 * 1. Update need_wakeup both before and after the TX. If it goes to
-	 * "yes", it can only happen with the first update.
-	 * 2. If the application queried need_wakeup before we set it, the
-	 * packets will be transmitted anyway, even w/o a wakeup.
-	 * 3. Give a chance to clear need_wakeup after new packets were queued
-	 * for TX.
+	/* If SQ is empty, there are no TX completions to trigger NAPI, so set
+	 * need_wakeup. Do it before queuing packets for TX to avoid race
+	 * condition with userspace.
 	 */
-	mlx5e_xsk_update_tx_wakeup(xsksq);
+	if (need_wakeup && xsksq->pc == xsksq->cc)
+		xsk_set_tx_need_wakeup(xsksq->xsk_pool);
 	busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET);
-	mlx5e_xsk_update_tx_wakeup(xsksq);
+	/* If we queued some packets for TX, no need for wakeup anymore. */
+	if (need_wakeup && xsksq->pc != xsksq->cc)
+		xsk_clear_tx_need_wakeup(xsksq->xsk_pool);
 
+	/* If WQ is empty, RX won't trigger NAPI, so set need_wakeup. Do it
+	 * before refilling to avoid race condition with userspace.
+	 */
+	if (need_wakeup && !mlx5e_rqwq_get_cur_sz(xskrq))
+		xsk_set_rx_need_wakeup(xskrq->xsk_pool);
 	xsk_rx_alloc_err = INDIRECT_CALL_2(xskrq->post_wqes,
 					   mlx5e_post_rx_mpwqes,
 					   mlx5e_post_rx_wqes,
 					   xskrq);
-	busy_xsk |= mlx5e_xsk_update_rx_wakeup(xskrq, xsk_rx_alloc_err);
+	/* Ask for wakeup if WQ is not full after refill. */
+	if (!need_wakeup)
+		busy_xsk |= xsk_rx_alloc_err;
+	else if (xsk_rx_alloc_err)
+		xsk_set_rx_need_wakeup(xskrq->xsk_pool);
+	else
+		xsk_clear_rx_need_wakeup(xskrq->xsk_pool);
 
 	return busy_xsk;
 }

drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c

@@ -924,12 +924,16 @@ int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw,
 				    struct mlx5_esw_rate_group *group,
 				    struct netlink_ext_ack *extack)
 {
-	int err;
+	int err = 0;
 
 	mutex_lock(&esw->state_lock);
+	if (!vport->qos.enabled && !group)
+		goto unlock;
+
 	err = esw_qos_vport_enable(esw, vport, 0, 0, extack);
 	if (!err)
 		err = esw_qos_vport_update_group(esw, vport, group, extack);
+unlock:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }

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

@@ -483,25 +483,27 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 	    !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) {
 		esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
 		(*i)++;
-	} else if (attr->dest_ft) {
-		esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
-		(*i)++;
 	} else if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) {
 		esw_setup_slow_path_dest(dest, flow_act, esw, *i);
 		(*i)++;
 	} else if (attr->flags & MLX5_ATTR_FLAG_ACCEPT) {
 		esw_setup_accept_dest(dest, flow_act, chains, *i);
 		(*i)++;
-	} else if (attr->dest_chain) {
-		err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain,
-					   1, 0, *i);
-		(*i)++;
 	} else if (esw_is_indir_table(esw, attr)) {
 		err = esw_setup_indir_table(dest, flow_act, esw, attr, spec, true, i);
 	} else if (esw_is_chain_src_port_rewrite(esw, esw_attr)) {
 		err = esw_setup_chain_src_port_rewrite(dest, flow_act, esw, chains, attr, i);
 	} else {
 		*i = esw_setup_vport_dests(dest, flow_act, esw, esw_attr, *i);
+
+		if (attr->dest_ft) {
+			err = esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
+			(*i)++;
+		} else if (attr->dest_chain) {
+			err = esw_setup_chain_dest(dest, flow_act, chains, attr->dest_chain,
+						   1, 0, *i);
+			(*i)++;
+		}
 	}
 
 	return err;

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

@@ -702,11 +702,25 @@ static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
 		.dump = mlx5_fw_fatal_reporter_dump,
 };
 
-#define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000
+#define MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD 180000
+#define MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD 60000
+#define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000
+#define MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD
+
 static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct devlink *devlink = priv_to_devlink(dev);
+	u64 grace_period;
+
+	if (mlx5_core_is_ecpf(dev)) {
+		grace_period = MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD;
+	} else if (mlx5_core_is_pf(dev)) {
+		grace_period = MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD;
+	} else {
+		/* VF or SF */
+		grace_period = MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD;
+	}
 
 	health->fw_reporter =
 		devlink_health_reporter_create(devlink, &mlx5_fw_reporter_ops,
@@ -718,7 +732,7 @@ static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 	health->fw_fatal_reporter =
 		devlink_health_reporter_create(devlink,
 					       &mlx5_fw_fatal_reporter_ops,
-					       MLX5_REPORTER_FW_GRACEFUL_PERIOD,
+					       grace_period,
 					       dev);
 	if (IS_ERR(health->fw_fatal_reporter))
 		mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %ld\n",
@@ -843,9 +857,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 
 	health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms);
 	add_timer(&health->timer);
-
-	if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc))
-		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 }
 
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
@@ -862,6 +873,14 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 	del_timer_sync(&health->timer);
 }
 
+void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc))
+		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
+}
+
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;

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

@@ -1092,7 +1092,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
-static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout)
 {
 	int err;
 
@@ -1130,10 +1130,12 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto err_cmd_cleanup;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_core_set_issi(dev);
@@ -1185,8 +1187,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 		mlx5_core_err(dev, "query hca failed\n");
 		goto reclaim_boot_pages;
 	}
-
-	mlx5_start_health_poll(dev);
+	mlx5_start_health_fw_log_up(dev);
 
 	return 0;
 
@@ -1194,6 +1195,8 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, u64 timeout)
 	mlx5_reclaim_startup_pages(dev);
 err_disable_hca:
 	mlx5_core_disable_hca(dev, 0);
+stop_health_poll:
+	mlx5_stop_health_poll(dev, boot);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
@@ -1205,7 +1208,6 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 {
 	int err;
 
-	mlx5_stop_health_poll(dev, boot);
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n");
@@ -1213,6 +1215,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	}
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
+	mlx5_stop_health_poll(dev, boot);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
 
@@ -1362,7 +1365,7 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	mutex_lock(&dev->intf_state_mutex);
 	dev->state = MLX5_DEVICE_STATE_UP;
 
-	err = mlx5_function_setup(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
+	err = mlx5_function_setup(dev, true, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
 	if (err)
 		goto err_function;
 
@@ -1450,7 +1453,7 @@ int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery)
 		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_ON_RECOVERY_TIMEOUT);
 	else
 		timeout = mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT);
-	err = mlx5_function_setup(dev, timeout);
+	err = mlx5_function_setup(dev, false, timeout);
 	if (err)
 		goto err_function;
 

include/linux/mlx5/driver.h

@@ -1017,6 +1017,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
+void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
@@ -1288,4 +1289,8 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 	return mlx5_is_roce_on(dev);
 }
 
+enum {
+	MLX5_OCTWORD = 16,
+};
+
 #endif /* MLX5_DRIVER_H */

include/linux/mlx5/mlx5_ifc.h

@@ -1491,7 +1491,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_120[0xa];
 	u8         log_max_ra_req_dc[0x6];
-	u8         reserved_at_130[0x9];
+	u8         reserved_at_130[0x2];
+	u8         eth_wqe_too_small[0x1];
+	u8         reserved_at_133[0x6];
 	u8         vnic_env_cq_overrun[0x1];
 	u8         log_max_ra_res_dc[0x6];
 
@@ -3537,7 +3539,9 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits {
 
 	u8         cq_overrun[0x20];
 
-	u8         reserved_at_220[0xde0];
+	u8         eth_wqe_too_small[0x20];
+
+	u8         reserved_at_220[0xdc0];
 };
 
 struct mlx5_ifc_traffic_counter_bits {