Merge tag 'net-5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from xfrm, bpf, netfilter, and wireless.

  Current release - regressions:

   - xfrm: fix XFRM_MSG_MAPPING ABI breakage caused by inserting a new
     value in the middle of an enum

   - unix: fix an issue in unix_shutdown causing the other end
     read/write failures

   - phy: mdio: fix memory leak

  Current release - new code bugs:

   - mlx5e: improve MQPRIO resiliency against bad configs

  Previous releases - regressions:

   - bpf: fix integer overflow leading to OOB access in map element
     pre-allocation

   - stmmac: dwmac-rk: fix ethernet on rk3399 based devices

   - netfilter: conntrack: fix boot failure with
     nf_conntrack.enable_hooks=1

   - brcmfmac: revert using ISO3166 country code and 0 rev as fallback

   - i40e: fix freeing of uninitialized misc IRQ vector

   - iavf: fix double unlock of crit_lock

  Previous releases - always broken:

   - bpf, arm: fix register clobbering in div/mod implementation

   - netfilter: nf_tables: correct issues in netlink rule change event
     notifications

   - dsa: tag_dsa: fix mask for trunked packets

   - usb: r8152: don't resubmit rx immediately to avoid soft lockup on
     device unplug

   - i40e: fix endless loop under rtnl if FW fails to correctly respond
     to capability query

   - mlx5e: fix rx checksum offload coexistence with ipsec offload

   - mlx5: force round second at 1PPS out start time and allow it only
     in supported clock modes

   - phy: pcs: xpcs: fix incorrect CL37 AN sequence, EEE disable
     sequence

  Misc:

   - xfrm: slightly rejig the new policy uAPI to make it less cryptic"

* tag 'net-5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (66 commits)
  net: prefer socket bound to interface when not in VRF
  iavf: fix double unlock of crit_lock
  i40e: Fix freeing of uninitialized misc IRQ vector
  i40e: fix endless loop under rtnl
  dt-bindings: net: dsa: marvell: fix compatible in example
  ionic: move filter sync_needed bit set
  gve: report 64bit tx_bytes counter from gve_handle_report_stats()
  gve: fix gve_get_stats()
  rtnetlink: fix if_nlmsg_stats_size() under estimation
  gve: Properly handle errors in gve_assign_qpl
  gve: Avoid freeing NULL pointer
  gve: Correct available tx qpl check
  unix: Fix an issue in unix_shutdown causing the other end read/write failures
  net: stmmac: trigger PCS EEE to turn off on link down
  net: pcs: xpcs: fix incorrect steps on disable EEE
  netlink: annotate data races around nlk->bound
  net: pcs: xpcs: fix incorrect CL37 AN sequence
  net: sfp: Fix typo in state machine debug string
  net/sched: sch_taprio: properly cancel timer from taprio_destroy()
  net: bridge: fix under estimation in br_get_linkxstats_size()
  ...

CREDITS

@@ -971,6 +971,7 @@ D: PowerPC
 N: Daniel Drake
 E: dsd@gentoo.org
 D: USBAT02 CompactFlash support in usb-storage
+D: ZD1211RW wireless driver
 S: UK
 
 N: Oleg Drokin

Documentation/devicetree/bindings/net/dsa/marvell.txt

@@ -83,7 +83,7 @@ Example:
 		#interrupt-cells = <2>;
 
 		switch0: switch@0 {
-			compatible = "marvell,mv88e6390";
+			compatible = "marvell,mv88e6190";
 			reg = <0>;
 			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
 

MAINTAINERS

@@ -8609,9 +8609,8 @@ F:	Documentation/devicetree/bindings/iio/humidity/st,hts221.yaml
 F:	drivers/iio/humidity/hts221*
 
 HUAWEI ETHERNET DRIVER
-M:	Bin Luo <luobin9@huawei.com>
 L:	netdev@vger.kernel.org
-S:	Supported
+S:	Orphan
 F:	Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
 F:	drivers/net/ethernet/huawei/hinic/
 
@@ -17794,7 +17793,6 @@ F:	drivers/staging/nvec/
 
 STAGING - OLPC SECONDARY DISPLAY CONTROLLER (DCON)
 M:	Jens Frederich <jfrederich@gmail.com>
-M:	Daniel Drake <dsd@laptop.org>
 M:	Jon Nettleton <jon.nettleton@gmail.com>
 S:	Maintained
 W:	http://wiki.laptop.org/go/DCON
@@ -20700,7 +20698,6 @@ S:	Maintained
 F:	mm/zbud.c
 
 ZD1211RW WIRELESS DRIVER
-M:	Daniel Drake <dsd@gentoo.org>
 M:	Ulrich Kunitz <kune@deine-taler.de>
 L:	linux-wireless@vger.kernel.org
 L:	zd1211-devs@lists.sourceforge.net (subscribers-only)

arch/arm/net/bpf_jit_32.c

@@ -36,6 +36,10 @@
  *                        +-----+
  *                        |RSVD | JIT scratchpad
  * current ARM_SP =>      +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE)
+ *                        | ... | caller-saved registers
+ *                        +-----+
+ *                        | ... | arguments passed on stack
+ * ARM_SP during call =>  +-----|
  *                        |     |
  *                        | ... | Function call stack
  *                        |     |
@@ -63,6 +67,12 @@
  *
  * When popping registers off the stack at the end of a BPF function, we
  * reference them via the current ARM_FP register.
+ *
+ * Some eBPF operations are implemented via a call to a helper function.
+ * Such calls are "invisible" in the eBPF code, so it is up to the calling
+ * program to preserve any caller-saved ARM registers during the call. The
+ * JIT emits code to push and pop those registers onto the stack, immediately
+ * above the callee stack frame.
  */
 #define CALLEE_MASK	(1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
 			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \
@@ -70,6 +80,8 @@
 #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
 #define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
 
+#define CALLER_MASK	(1 << ARM_R0 | 1 << ARM_R1 | 1 << ARM_R2 | 1 << ARM_R3)
+
 enum {
 	/* Stack layout - these are offsets from (top of stack - 4) */
 	BPF_R2_HI,
@@ -464,6 +476,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
+	const int exclude_mask = BIT(ARM_R0) | BIT(ARM_R1);
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 
 #if __LINUX_ARM_ARCH__ == 7
@@ -495,11 +508,17 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 		emit(ARM_MOV_R(ARM_R0, rm), ctx);
 	}
 
+	/* Push caller-saved registers on stack */
+	emit(ARM_PUSH(CALLER_MASK & ~exclude_mask), ctx);
+
 	/* Call appropriate function */
 	emit_mov_i(ARM_IP, op == BPF_DIV ?
 		   (u32)jit_udiv32 : (u32)jit_mod32, ctx);
 	emit_blx_r(ARM_IP, ctx);
 
+	/* Restore caller-saved registers from stack */
+	emit(ARM_POP(CALLER_MASK & ~exclude_mask), ctx);
+
 	/* Save return value */
 	if (rd != ARM_R0)
 		emit(ARM_MOV_R(rd, ARM_R0), ctx);

arch/powerpc/boot/dts/fsl/t1023rdb.dts

@@ -154,7 +154,7 @@
 
 			fm1mac3: ethernet@e4000 {
 				phy-handle = <&sgmii_aqr_phy3>;
-				phy-connection-type = "sgmii-2500";
+				phy-connection-type = "2500base-x";
 				sleep = <&rcpm 0x20000000>;
 			};
 

drivers/net/ethernet/google/gve/gve.h

@@ -780,7 +780,7 @@ struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_priv *priv)
 				    gve_num_tx_qpls(priv));
 
 	/* we are out of rx qpls */
-	if (id == priv->qpl_cfg.qpl_map_size)
+	if (id == gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv))
 		return NULL;
 
 	set_bit(id, priv->qpl_cfg.qpl_id_map);

drivers/net/ethernet/google/gve/gve_main.c

@@ -41,6 +41,7 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 {
 	struct gve_priv *priv = netdev_priv(dev);
 	unsigned int start;
+	u64 packets, bytes;
 	int ring;
 
 	if (priv->rx) {
@@ -48,10 +49,12 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 			do {
 				start =
 				  u64_stats_fetch_begin(&priv->rx[ring].statss);
-				s->rx_packets += priv->rx[ring].rpackets;
-				s->rx_bytes += priv->rx[ring].rbytes;
+				packets = priv->rx[ring].rpackets;
+				bytes = priv->rx[ring].rbytes;
 			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
 						       start));
+			s->rx_packets += packets;
+			s->rx_bytes += bytes;
 		}
 	}
 	if (priv->tx) {
@@ -59,10 +62,12 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
 			do {
 				start =
 				  u64_stats_fetch_begin(&priv->tx[ring].statss);
-				s->tx_packets += priv->tx[ring].pkt_done;
-				s->tx_bytes += priv->tx[ring].bytes_done;
+				packets = priv->tx[ring].pkt_done;
+				bytes = priv->tx[ring].bytes_done;
 			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
 						       start));
+			s->tx_packets += packets;
+			s->tx_bytes += bytes;
 		}
 	}
 }
@@ -82,6 +87,9 @@ static int gve_alloc_counter_array(struct gve_priv *priv)
 
 static void gve_free_counter_array(struct gve_priv *priv)
 {
+	if (!priv->counter_array)
+		return;
+
 	dma_free_coherent(&priv->pdev->dev,
 			  priv->num_event_counters *
 			  sizeof(*priv->counter_array),
@@ -142,6 +150,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv)
 
 static void gve_free_stats_report(struct gve_priv *priv)
 {
+	if (!priv->stats_report)
+		return;
+
 	del_timer_sync(&priv->stats_report_timer);
 	dma_free_coherent(&priv->pdev->dev, priv->stats_report_len,
 			  priv->stats_report, priv->stats_report_bus);
@@ -370,18 +381,19 @@ static void gve_free_notify_blocks(struct gve_priv *priv)
 {
 	int i;
 
-	if (priv->msix_vectors) {
-		/* Free the irqs */
-		for (i = 0; i < priv->num_ntfy_blks; i++) {
-			struct gve_notify_block *block = &priv->ntfy_blocks[i];
-			int msix_idx = i;
+	if (!priv->msix_vectors)
+		return;
 
-			irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
-					      NULL);
-			free_irq(priv->msix_vectors[msix_idx].vector, block);
-		}
-		free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
+	/* Free the irqs */
+	for (i = 0; i < priv->num_ntfy_blks; i++) {
+		struct gve_notify_block *block = &priv->ntfy_blocks[i];
+		int msix_idx = i;
+
+		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
+				      NULL);
+		free_irq(priv->msix_vectors[msix_idx].vector, block);
 	}
+	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
 	dma_free_coherent(&priv->pdev->dev,
 			  priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks),
 			  priv->ntfy_blocks, priv->ntfy_block_bus);
@@ -1185,9 +1197,10 @@ static void gve_handle_reset(struct gve_priv *priv)
 
 void gve_handle_report_stats(struct gve_priv *priv)
 {
-	int idx, stats_idx = 0, tx_bytes;
-	unsigned int start = 0;
 	struct stats *stats = priv->stats_report->stats;
+	int idx, stats_idx = 0;
+	unsigned int start = 0;
+	u64 tx_bytes;
 
 	if (!gve_get_report_stats(priv))
 		return;

drivers/net/ethernet/google/gve/gve_rx.c

@@ -104,8 +104,14 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 	if (!rx->data.page_info)
 		return -ENOMEM;
 
-	if (!rx->data.raw_addressing)
+	if (!rx->data.raw_addressing) {
 		rx->data.qpl = gve_assign_rx_qpl(priv);
+		if (!rx->data.qpl) {
+			kvfree(rx->data.page_info);
+			rx->data.page_info = NULL;
+			return -ENOMEM;
+		}
+	}
 	for (i = 0; i < slots; i++) {
 		if (!rx->data.raw_addressing) {
 			struct page *page = rx->data.qpl->pages[i];

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -4871,7 +4871,8 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf)
 {
 	int i;
 
-	i40e_free_misc_vector(pf);
+	if (test_bit(__I40E_MISC_IRQ_REQUESTED, pf->state))
+		i40e_free_misc_vector(pf);
 
 	i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector,
 		      I40E_IWARP_IRQ_PILE_ID);
@@ -10113,7 +10114,7 @@ static int i40e_get_capabilities(struct i40e_pf *pf,
 		if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) {
 			/* retry with a larger buffer */
 			buf_len = data_size;
-		} else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK) {
+		} else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) {
 			dev_info(&pf->pdev->dev,
 				 "capability discovery failed, err %s aq_err %s\n",
 				 i40e_stat_str(&pf->hw, err),

drivers/net/ethernet/intel/iavf/iavf_main.c

@@ -1965,7 +1965,6 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(iavf_wq,
 				   &adapter->watchdog_task,
 				   msecs_to_jiffies(10));

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

@@ -252,6 +252,7 @@ struct mlx5e_params {
 	struct {
 		u16 mode;
 		u8 num_tc;
+		struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
 	} mqprio;
 	bool rx_cqe_compress_def;
 	bool tunneled_offload_en;
@@ -845,6 +846,7 @@ struct mlx5e_priv {
 	struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS];
 	struct mlx5e_channel_stats trap_stats;
 	struct mlx5e_ptp_stats     ptp_stats;
+	u16                        stats_nch;
 	u16                        max_nch;
 	u8                         max_opened_tc;
 	bool                       tx_ptp_opened;
@@ -1100,12 +1102,6 @@ int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
 				 struct ethtool_pauseparam *pauseparam);
 
 /* mlx5e generic netdev management API */
-static inline unsigned int
-mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile)
-{
-	return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
-}
-
 static inline bool
 mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev)
 {
@@ -1114,11 +1110,13 @@ mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev)
 }
 
 int mlx5e_priv_init(struct mlx5e_priv *priv,
+		    const struct mlx5e_profile *profile,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev);
 void mlx5e_priv_cleanup(struct mlx5e_priv *priv);
 struct net_device *
-mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs);
+mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
+		    unsigned int txqs, unsigned int rxqs);
 int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);

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

@@ -35,7 +35,7 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data,
 {
 	int ch, i = 0;
 
-	for (ch = 0; ch < priv->max_nch; ch++) {
+	for (ch = 0; ch < priv->stats_nch; ch++) {
 		void *buf = data + i;
 
 		if (WARN_ON_ONCE(buf +
@@ -51,7 +51,7 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data,
 static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv)
 {
 	return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) *
-		priv->max_nch);
+		priv->stats_nch);
 }
 
 static void mlx5e_hv_vhca_stats_work(struct work_struct *work)
@@ -100,7 +100,7 @@ static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent,
 	sagent = &priv->stats_agent;
 
 	block->version = MLX5_HV_VHCA_STATS_VERSION;
-	block->rings   = priv->max_nch;
+	block->rings   = priv->stats_nch;
 
 	if (!block->command) {
 		cancel_delayed_work_sync(&priv->stats_agent.work);

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

@@ -13,8 +13,6 @@ struct mlx5e_ptp_fs {
 	bool valid;
 };
 
-#define MLX5E_PTP_CHANNEL_IX 0
-
 struct mlx5e_ptp_params {
 	struct mlx5e_params params;
 	struct mlx5e_sq_param txq_sq_param;
@@ -509,6 +507,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats        = &c->priv->ptp_stats.rq;
+	rq->ix           = MLX5E_PTP_CHANNEL_IX;
 	rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev);
 	err = mlx5e_rq_set_handlers(rq, params, false);
 	if (err)

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

@@ -8,6 +8,8 @@
 #include "en_stats.h"
 #include <linux/ptp_classify.h>
 
+#define MLX5E_PTP_CHANNEL_IX 0
+
 struct mlx5e_ptpsq {
 	struct mlx5e_txqsq       txqsq;
 	struct mlx5e_cq          ts_cq;

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

@@ -2036,6 +2036,17 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable)
 	}
 
 	new_params = priv->channels.params;
+	/* Don't allow enabling TX-port-TS if MQPRIO mode channel  offload is
+	 * active, since it defines explicitly which TC accepts the packet.
+	 * This conflicts with TX-port-TS hijacking the PTP traffic to a specific
+	 * HW TX-queue.
+	 */
+	if (enable && new_params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) {
+		netdev_err(priv->netdev,
+			   "%s: MQPRIO mode channel offload is active, cannot set the TX-port-TS\n",
+			   __func__);
+		return -EINVAL;
+	}
 	MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_TX_PORT_TS, enable);
 	/* No need to verify SQ stop room as
 	 * ptpsq.txqsq.stop_room <= generic_sq->stop_room, and both

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

@@ -2264,7 +2264,7 @@ void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
 }
 
 static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc,
-				struct tc_mqprio_qopt_offload *mqprio)
+				struct netdev_tc_txq *tc_to_txq)
 {
 	int tc, err;
 
@@ -2282,11 +2282,8 @@ static int mlx5e_netdev_set_tcs(struct net_device *netdev, u16 nch, u8 ntc,
 	for (tc = 0; tc < ntc; tc++) {
 		u16 count, offset;
 
-		/* For DCB mode, map netdev TCs to offset 0
-		 * We have our own UP to TXQ mapping for QoS
-		 */
-		count = mqprio ? mqprio->qopt.count[tc] : nch;
-		offset = mqprio ? mqprio->qopt.offset[tc] : 0;
+		count = tc_to_txq[tc].count;
+		offset = tc_to_txq[tc].offset;
 		netdev_set_tc_queue(netdev, tc, count, offset);
 	}
 
@@ -2315,19 +2312,24 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
 
 static int mlx5e_update_netdev_queues(struct mlx5e_priv *priv)
 {
+	struct netdev_tc_txq old_tc_to_txq[TC_MAX_QUEUE], *tc_to_txq;
 	struct net_device *netdev = priv->netdev;
 	int old_num_txqs, old_ntc;
 	int num_rxqs, nch, ntc;
 	int err;
+	int i;
 
 	old_num_txqs = netdev->real_num_tx_queues;
 	old_ntc = netdev->num_tc ? : 1;
+	for (i = 0; i < ARRAY_SIZE(old_tc_to_txq); i++)
+		old_tc_to_txq[i] = netdev->tc_to_txq[i];
 
 	nch = priv->channels.params.num_channels;
-	ntc = mlx5e_get_dcb_num_tc(&priv->channels.params);
+	ntc = priv->channels.params.mqprio.num_tc;
 	num_rxqs = nch * priv->profile->rq_groups;
+	tc_to_txq = priv->channels.params.mqprio.tc_to_txq;
 
-	err = mlx5e_netdev_set_tcs(netdev, nch, ntc, NULL);
+	err = mlx5e_netdev_set_tcs(netdev, nch, ntc, tc_to_txq);
 	if (err)
 		goto err_out;
 	err = mlx5e_update_tx_netdev_queues(priv);
@@ -2350,11 +2352,14 @@ err_txqs:
 	WARN_ON_ONCE(netif_set_real_num_tx_queues(netdev, old_num_txqs));
 
 err_tcs:
-	mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc, NULL);
+	WARN_ON_ONCE(mlx5e_netdev_set_tcs(netdev, old_num_txqs / old_ntc, old_ntc,
+					  old_tc_to_txq));
 err_out:
 	return err;
 }
 
+static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues);
+
 static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 					   struct mlx5e_params *params)
 {
@@ -2861,6 +2866,58 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
 	return 0;
 }
 
+static void mlx5e_mqprio_build_default_tc_to_txq(struct netdev_tc_txq *tc_to_txq,
+						 int ntc, int nch)
+{
+	int tc;
+
+	memset(tc_to_txq, 0, sizeof(*tc_to_txq) * TC_MAX_QUEUE);
+
+	/* Map netdev TCs to offset 0.
+	 * We have our own UP to TXQ mapping for DCB mode of QoS
+	 */
+	for (tc = 0; tc < ntc; tc++) {
+		tc_to_txq[tc] = (struct netdev_tc_txq) {
+			.count = nch,
+			.offset = 0,
+		};
+	}
+}
+
+static void mlx5e_mqprio_build_tc_to_txq(struct netdev_tc_txq *tc_to_txq,
+					 struct tc_mqprio_qopt *qopt)
+{
+	int tc;
+
+	for (tc = 0; tc < TC_MAX_QUEUE; tc++) {
+		tc_to_txq[tc] = (struct netdev_tc_txq) {
+			.count = qopt->count[tc],
+			.offset = qopt->offset[tc],
+		};
+	}
+}
+
+static void mlx5e_params_mqprio_dcb_set(struct mlx5e_params *params, u8 num_tc)
+{
+	params->mqprio.mode = TC_MQPRIO_MODE_DCB;
+	params->mqprio.num_tc = num_tc;
+	mlx5e_mqprio_build_default_tc_to_txq(params->mqprio.tc_to_txq, num_tc,
+					     params->num_channels);
+}
+
+static void mlx5e_params_mqprio_channel_set(struct mlx5e_params *params,
+					    struct tc_mqprio_qopt *qopt)
+{
+	params->mqprio.mode = TC_MQPRIO_MODE_CHANNEL;
+	params->mqprio.num_tc = qopt->num_tc;
+	mlx5e_mqprio_build_tc_to_txq(params->mqprio.tc_to_txq, qopt);
+}
+
+static void mlx5e_params_mqprio_reset(struct mlx5e_params *params)
+{
+	mlx5e_params_mqprio_dcb_set(params, 1);
+}
+
 static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
 				     struct tc_mqprio_qopt *mqprio)
 {
@@ -2874,8 +2931,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
 		return -EINVAL;
 
 	new_params = priv->channels.params;
-	new_params.mqprio.mode = TC_MQPRIO_MODE_DCB;
-	new_params.mqprio.num_tc = tc ? tc : 1;
+	mlx5e_params_mqprio_dcb_set(&new_params, tc ? tc : 1);
 
 	err = mlx5e_safe_switch_params(priv, &new_params,
 				       mlx5e_num_channels_changed_ctx, NULL, true);
@@ -2889,9 +2945,17 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv,
 					 struct tc_mqprio_qopt_offload *mqprio)
 {
 	struct net_device *netdev = priv->netdev;
+	struct mlx5e_ptp *ptp_channel;
 	int agg_count = 0;
 	int i;
 
+	ptp_channel = priv->channels.ptp;
+	if (ptp_channel && test_bit(MLX5E_PTP_STATE_TX, ptp_channel->state)) {
+		netdev_err(netdev,
+			   "Cannot activate MQPRIO mode channel since it conflicts with TX port TS\n");
+		return -EINVAL;
+	}
+
 	if (mqprio->qopt.offset[0] != 0 || mqprio->qopt.num_tc < 1 ||
 	    mqprio->qopt.num_tc > MLX5E_MAX_NUM_MQPRIO_CH_TC)
 		return -EINVAL;
@@ -2926,25 +2990,12 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int mlx5e_mqprio_channel_set_tcs_ctx(struct mlx5e_priv *priv, void *ctx)
-{
-	struct tc_mqprio_qopt_offload *mqprio = (struct tc_mqprio_qopt_offload *)ctx;
-	struct net_device *netdev = priv->netdev;
-	u8 num_tc;
-
-	if (priv->channels.params.mqprio.mode != TC_MQPRIO_MODE_CHANNEL)
-		return -EINVAL;
-
-	num_tc = priv->channels.params.mqprio.num_tc;
-	mlx5e_netdev_set_tcs(netdev, 0, num_tc, mqprio);
-
-	return 0;
-}
-
 static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
 					 struct tc_mqprio_qopt_offload *mqprio)
 {
+	mlx5e_fp_preactivate preactivate;
 	struct mlx5e_params new_params;
+	bool nch_changed;
 	int err;
 
 	err = mlx5e_mqprio_channel_validate(priv, mqprio);
@@ -2952,12 +3003,12 @@ static int mlx5e_setup_tc_mqprio_channel(struct mlx5e_priv *priv,
 		return err;
 
 	new_params = priv->channels.params;
-	new_params.mqprio.mode = TC_MQPRIO_MODE_CHANNEL;
-	new_params.mqprio.num_tc = mqprio->qopt.num_tc;
-	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_mqprio_channel_set_tcs_ctx, mqprio, true);
+	mlx5e_params_mqprio_channel_set(&new_params, &mqprio->qopt);
 
-	return err;
+	nch_changed = mlx5e_get_dcb_num_tc(&priv->channels.params) > 1;
+	preactivate = nch_changed ? mlx5e_num_channels_changed_ctx :
+		mlx5e_update_netdev_queues_ctx;
+	return mlx5e_safe_switch_params(priv, &new_params, preactivate, NULL, true);
 }
 
 static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
@@ -3065,7 +3116,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 {
 	int i;
 
-	for (i = 0; i < priv->max_nch; i++) {
+	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
 		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
@@ -4186,13 +4237,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 rx_cq_period_mode;
 
-	priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile);
-
 	params->sw_mtu = mtu;
 	params->hard_mtu = MLX5E_ETH_HARD_MTU;
 	params->num_channels = min_t(unsigned int, MLX5E_MAX_NUM_CHANNELS / 2,
 				     priv->max_nch);
-	params->mqprio.num_tc = 1;
+	mlx5e_params_mqprio_reset(params);
 
 	/* Set an initial non-zero value, so that mlx5e_select_queue won't
 	 * divide by zero if called before first activating channels.
@@ -4682,8 +4731,35 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.rx_ptp_support    = true,
 };
 
+static unsigned int
+mlx5e_calc_max_nch(struct mlx5_core_dev *mdev, struct net_device *netdev,
+		   const struct mlx5e_profile *profile)
+
+{
+	unsigned int max_nch, tmp;
+
+	/* core resources */
+	max_nch = mlx5e_get_max_num_channels(mdev);
+
+	/* netdev rx queues */
+	tmp = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
+	max_nch = min_t(unsigned int, max_nch, tmp);
+
+	/* netdev tx queues */
+	tmp = netdev->num_tx_queues;
+	if (mlx5_qos_is_supported(mdev))
+		tmp -= mlx5e_qos_max_leaf_nodes(mdev);
+	if (MLX5_CAP_GEN(mdev, ts_cqe_to_dest_cqn))
+		tmp -= profile->max_tc;
+	tmp = tmp / profile->max_tc;
+	max_nch = min_t(unsigned int, max_nch, tmp);
+
+	return max_nch;
+}
+
 /* mlx5e generic netdev management API (move to en_common.c) */
 int mlx5e_priv_init(struct mlx5e_priv *priv,
+		    const struct mlx5e_profile *profile,
 		    struct net_device *netdev,
 		    struct mlx5_core_dev *mdev)
 {
@@ -4691,6 +4767,8 @@ int mlx5e_priv_init(struct mlx5e_priv *priv,
 	priv->mdev        = mdev;
 	priv->netdev      = netdev;
 	priv->msglevel    = MLX5E_MSG_LEVEL;
+	priv->max_nch     = mlx5e_calc_max_nch(mdev, netdev, profile);
+	priv->stats_nch   = priv->max_nch;
 	priv->max_opened_tc = 1;
 
 	if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL))
@@ -4734,7 +4812,8 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 }
 
 struct net_device *
-mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int rxqs)
+mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile,
+		    unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *netdev;
 	int err;
@@ -4745,7 +4824,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, unsigned int txqs, unsigned int
 		return NULL;
 	}
 
-	err = mlx5e_priv_init(netdev_priv(netdev), netdev, mdev);
+	err = mlx5e_priv_init(netdev_priv(netdev), profile, netdev, mdev);
 	if (err) {
 		mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err);
 		goto err_free_netdev;
@@ -4787,7 +4866,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	clear_bit(MLX5E_STATE_DESTROYING, &priv->state);
 
 	/* max number of channels may have changed */
-	max_nch = mlx5e_get_max_num_channels(priv->mdev);
+	max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile);
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
 		/* Reducing the number of channels - RXFH has to be reset, and
@@ -4795,7 +4874,18 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 		 */
 		priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
 		priv->channels.params.num_channels = max_nch;
+		if (priv->channels.params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) {
+			mlx5_core_warn(priv->mdev, "MLX5E: Disabling MQPRIO channel mode\n");
+			mlx5e_params_mqprio_reset(&priv->channels.params);
+		}
 	}
+	if (max_nch != priv->max_nch) {
+		mlx5_core_warn(priv->mdev,
+			       "MLX5E: Updating max number of channels from %u to %u\n",
+			       priv->max_nch, max_nch);
+		priv->max_nch = max_nch;
+	}
+
 	/* 1. Set the real number of queues in the kernel the first time.
 	 * 2. Set our default XPS cpumask.
 	 * 3. Build the RQT.
@@ -4860,7 +4950,7 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
-	err = mlx5e_priv_init(priv, netdev, mdev);
+	err = mlx5e_priv_init(priv, new_profile, netdev, mdev);
 	if (err) {
 		mlx5_core_err(mdev, "mlx5e_priv_init failed, err=%d\n", err);
 		return err;
@@ -4886,20 +4976,12 @@ priv_cleanup:
 int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 				const struct mlx5e_profile *new_profile, void *new_ppriv)
 {
-	unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile);
 	const struct mlx5e_profile *orig_profile = priv->profile;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *orig_ppriv = priv->ppriv;
 	int err, rollback_err;
 
-	/* sanity */
-	if (new_max_nch != priv->max_nch) {
-		netdev_warn(netdev, "%s: Replacing profile with different max channels\n",
-			    __func__);
-		return -EINVAL;
-	}
-
 	/* cleanup old profile */
 	mlx5e_detach_netdev(priv);
 	priv->profile->cleanup(priv);
@@ -4995,7 +5077,7 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 	nch = mlx5e_get_max_num_channels(mdev);
 	txqs = nch * profile->max_tc + ptp_txqs + qos_sqs;
 	rxqs = nch * profile->rq_groups;
-	netdev = mlx5e_create_netdev(mdev, txqs, rxqs);
+	netdev = mlx5e_create_netdev(mdev, profile, txqs, rxqs);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
 		return -ENOMEM;

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

@@ -596,7 +596,6 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
-	priv->max_nch = mlx5e_calc_max_nch(priv, priv->profile);
 	params = &priv->channels.params;
 
 	params->num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS;
@@ -1169,7 +1168,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	nch = mlx5e_get_max_num_channels(dev);
 	txqs = nch * profile->max_tc;
 	rxqs = nch * profile->rq_groups;
-	netdev = mlx5e_create_netdev(dev, txqs, rxqs);
+	netdev = mlx5e_create_netdev(dev, profile, txqs, rxqs);
 	if (!netdev) {
 		mlx5_core_warn(dev,
 			       "Failed to create representor netdev for vport %d\n",

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

@@ -1001,14 +1001,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		goto csum_unnecessary;
 
 	if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
-		u8 ipproto = get_ip_proto(skb, network_depth, proto);
-
-		if (unlikely(ipproto == IPPROTO_SCTP))
+		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
 
-		if (unlikely(mlx5_ipsec_is_rx_flow(cqe)))
-			goto csum_none;
-
 		stats->csum_complete++;
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);

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

@@ -34,6 +34,7 @@
 #include "en.h"
 #include "en_accel/tls.h"
 #include "en_accel/en_accel.h"
+#include "en/ptp.h"
 
 static unsigned int stats_grps_num(struct mlx5e_priv *priv)
 {
@@ -450,7 +451,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 
 	memset(s, 0, sizeof(*s));
 
-	for (i = 0; i < priv->max_nch; i++) {
+	for (i = 0; i < priv->stats_nch; i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			&priv->channel_stats[i];
 		int j;
@@ -2076,7 +2077,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(ptp)
 	if (priv->rx_ptp_opened) {
 		for (i = 0; i < NUM_PTP_RQ_STATS; i++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
-				ptp_rq_stats_desc[i].format);
+				ptp_rq_stats_desc[i].format, MLX5E_PTP_CHANNEL_IX);
 	}
 	return idx;
 }
@@ -2119,7 +2120,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; }
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
 {
-	int max_nch = priv->max_nch;
+	int max_nch = priv->stats_nch;
 
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
@@ -2133,7 +2134,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels)
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
 {
 	bool is_xsk = priv->xsk.ever_used;
-	int max_nch = priv->max_nch;
+	int max_nch = priv->stats_nch;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)
@@ -2175,7 +2176,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels)
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels)
 {
 	bool is_xsk = priv->xsk.ever_used;
-	int max_nch = priv->max_nch;
+	int max_nch = priv->stats_nch;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c

@@ -79,12 +79,16 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 	int dest_num = 0;
 	int err = 0;
 
-	if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) {
+	if (vport->egress.legacy.drop_counter) {
+		drop_counter = vport->egress.legacy.drop_counter;
+	} else if (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) {
 		drop_counter = mlx5_fc_create(esw->dev, false);
-		if (IS_ERR(drop_counter))
+		if (IS_ERR(drop_counter)) {
 			esw_warn(esw->dev,
 				 "vport[%d] configure egress drop rule counter err(%ld)\n",
 				 vport->vport, PTR_ERR(drop_counter));
+			drop_counter = NULL;
+		}
 		vport->egress.legacy.drop_counter = drop_counter;
 	}
 
@@ -123,7 +127,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
 
 	/* Attach egress drop flow counter */
-	if (!IS_ERR_OR_NULL(drop_counter)) {
+	if (drop_counter) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 		drop_ctr_dst.counter_id = mlx5_fc_id(drop_counter);
@@ -162,7 +166,7 @@ void esw_acl_egress_lgcy_cleanup(struct mlx5_eswitch *esw,
 	esw_acl_egress_table_destroy(vport);
 
 clean_drop_counter:
-	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_counter)) {
+	if (vport->egress.legacy.drop_counter) {
 		mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
 		vport->egress.legacy.drop_counter = NULL;
 	}