1 files changed, 125 insertions, 77 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d5495762c945..5578ddcb465d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -58,8 +58,8 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <linux/pci-tph.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
@@ -477,6 +477,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct bnxt_tx_ring_info *txr;
 	struct bnxt_sw_tx_bd *tx_buf;
 	__le32 lflags = 0;
+	skb_frag_t *frag;
 
 	i = skb_get_queue_mapping(skb);
 	if (unlikely(i >= bp->tx_nr_rings)) {
@@ -563,7 +564,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC);
 
 	if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh &&
-	    !lflags) {
+	    skb_frags_readable(skb) && !lflags) {
 		struct tx_push_buffer *tx_push_buf = txr->tx_push;
 		struct tx_push_bd *tx_push = &tx_push_buf->push_bd;
 		struct tx_bd_ext *tx_push1 = &tx_push->txbd2;
@@ -598,9 +599,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb_copy_from_linear_data(skb, pdata, len);
 		pdata += len;
 		for (j = 0; j < last_frag; j++) {
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 			void *fptr;
 
+			frag = &skb_shinfo(skb)->frags[j];
 			fptr = skb_frag_address_safe(frag);
 			if (!fptr)
 				goto normal_tx;
@@ -708,8 +709,7 @@ normal_tx:
 			cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT);
 	txbd0 = txbd;
 	for (i = 0; i < last_frag; i++) {
-		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
+		frag = &skb_shinfo(skb)->frags[i];
 		prod = NEXT_TX(prod);
 		txbd = &txr->tx_desc_ring[TX_RING(bp, prod)][TX_IDX(prod)];
 
@@ -721,7 +721,8 @@ normal_tx:
 			goto tx_dma_error;
 
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
-		dma_unmap_addr_set(tx_buf, mapping, mapping);
+		netmem_dma_unmap_addr_set(skb_frag_netmem(frag), tx_buf,
+					  mapping, mapping);
 
 		txbd->tx_bd_haddr = cpu_to_le64(mapping);
 
@@ -778,9 +779,11 @@ tx_dma_error:
 	for (i = 0; i < last_frag; i++) {
 		prod = NEXT_TX(prod);
 		tx_buf = &txr->tx_buf_ring[RING_TX(bp, prod)];
-		dma_unmap_page(&pdev->dev, dma_unmap_addr(tx_buf, mapping),
-			       skb_frag_size(&skb_shinfo(skb)->frags[i]),
-			       DMA_TO_DEVICE);
+		frag = &skb_shinfo(skb)->frags[i];
+		netmem_dma_unmap_page_attrs(&pdev->dev,
+					    dma_unmap_addr(tx_buf, mapping),
+					    skb_frag_size(frag),
+					    DMA_TO_DEVICE, 0);
 	}
 
 tx_free:
@@ -809,6 +812,7 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 	u16 hw_cons = txr->tx_hw_cons;
 	unsigned int tx_bytes = 0;
 	u16 cons = txr->tx_cons;
+	skb_frag_t *frag;
 	int tx_pkts = 0;
 	bool rc = false;
 
@@ -848,13 +852,14 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 		last = tx_buf->nr_frags;
 
 		for (j = 0; j < last; j++) {
+			frag = &skb_shinfo(skb)->frags[j];
 			cons = NEXT_TX(cons);
 			tx_buf = &txr->tx_buf_ring[RING_TX(bp, cons)];
-			dma_unmap_page(
-				&pdev->dev,
-				dma_unmap_addr(tx_buf, mapping),
-				skb_frag_size(&skb_shinfo(skb)->frags[j]),
-				DMA_TO_DEVICE);
+			netmem_dma_unmap_page_attrs(&pdev->dev,
+						    dma_unmap_addr(tx_buf,
+								   mapping),
+						    skb_frag_size(frag),
+						    DMA_TO_DEVICE, 0);
 		}
 		if (unlikely(is_ts_pkt)) {
 			if (BNXT_CHIP_P5(bp)) {
@@ -1810,7 +1815,7 @@ static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code)
 {
 	struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code);
 
-	/* if vf-rep dev is NULL, the must belongs to the PF */
+	/* if vf-rep dev is NULL, it must belong to the PF */
 	return dev ? dev : bp->dev;
 }
 
@@ -2989,6 +2994,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 cons;
 	int rx_pkts = 0;
 	u8 event = 0;
@@ -3042,6 +3048,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			else
 				rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
 							   &event);
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 			if (likely(rc >= 0))
 				rx_pkts += rc;
 			/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -3066,7 +3074,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (event & BNXT_REDIRECT_EVENT) {
+	if (flush_xdp) {
 		xdp_do_flush();
 		event &= ~BNXT_REDIRECT_EVENT;
 	}
@@ -3422,9 +3430,11 @@ static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp,
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 
 			tx_buf = &txr->tx_buf_ring[ring_idx];
-			dma_unmap_page(&pdev->dev,
-				       dma_unmap_addr(tx_buf, mapping),
-				       skb_frag_size(frag), DMA_TO_DEVICE);
+			netmem_dma_unmap_page_attrs(&pdev->dev,
+						    dma_unmap_addr(tx_buf,
+								   mapping),
+						    skb_frag_size(frag),
+						    DMA_TO_DEVICE, 0);
 		}
 		dev_kfree_skb(skb);
 	}
@@ -3800,12 +3810,14 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 				   struct bnxt_rx_ring_info *rxr,
 				   int numa_node)
 {
+	const unsigned int agg_size_fac = PAGE_SIZE / BNXT_RX_PAGE_SIZE;
+	const unsigned int rx_size_fac = PAGE_SIZE / SZ_4K;
 	struct page_pool_params pp = { 0 };
 	struct page_pool *pool;
 
-	pp.pool_size = bp->rx_agg_ring_size;
+	pp.pool_size = bp->rx_agg_ring_size / agg_size_fac;
 	if (BNXT_RX_PAGE_MODE(bp))
-		pp.pool_size += bp->rx_ring_size;
+		pp.pool_size += bp->rx_ring_size / rx_size_fac;
 	pp.nid = numa_node;
 	pp.napi = &rxr->bnapi->napi;
 	pp.netdev = bp->dev;
@@ -3823,7 +3835,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 
 	rxr->need_head_pool = page_pool_is_unreadable(pool);
 	if (bnxt_separate_head_pool(rxr)) {
-		pp.pool_size = max(bp->rx_ring_size, 1024);
+		pp.pool_size = min(bp->rx_ring_size / rx_size_fac, 1024);
 		pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 		pool = page_pool_create(&pp);
 		if (IS_ERR(pool))
@@ -7116,7 +7128,7 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	default:
 		netdev_err(bp->dev, "hwrm alloc invalid ring type %d\n",
 			   ring_type);
-		return -1;
+		return -EINVAL;
 	}
 
 	resp = hwrm_req_hold(bp, req);
@@ -10780,6 +10792,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru, int rxr_id)
+{
+	int rc;
+
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -11538,11 +11616,9 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 static int bnxt_request_irq(struct bnxt *bp)
 {
+	struct cpu_rmap *rmap = NULL;
 	int i, j, rc = 0;
 	unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
 
 	rc = bnxt_setup_int_mode(bp);
 	if (rc) {
@@ -11563,15 +11639,15 @@ static int bnxt_request_irq(struct bnxt *bp)
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
 
-#ifdef CONFIG_RFS_ACCEL
-		if (rmap && bp->bnapi[i]->rx_ring) {
+		if (IS_ENABLED(CONFIG_RFS_ACCEL) &&
+		    rmap && bp->bnapi[i]->rx_ring) {
 			rc = irq_cpu_rmap_add(rmap, irq->vector);
 			if (rc)
 				netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
 					    j);
 			j++;
 		}
-#endif
+
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 bp->bnapi[i]);
 		if (rc)
@@ -13995,7 +14071,7 @@ fw_reset:
 
 static void bnxt_timer(struct timer_list *t)
 {
-	struct bnxt *bp = from_timer(bp, t, timer);
+	struct bnxt *bp = timer_container_of(bp, t, timer);
 	struct net_device *dev = bp->dev;
 
 	if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state))
@@ -14055,28 +14131,13 @@ static void bnxt_unlock_sp(struct bnxt *bp)
 	netdev_unlock(bp->dev);
 }
 
-/* Same as bnxt_lock_sp() with additional rtnl_lock */
-static void bnxt_rtnl_lock_sp(struct bnxt *bp)
-{
-	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	rtnl_lock();
-	netdev_lock(bp->dev);
-}
-
-static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
-{
-	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	netdev_unlock(bp->dev);
-	rtnl_unlock();
-}
-
 /* Only called from bnxt_sp_task() */
 static void bnxt_reset(struct bnxt *bp, bool silent)
 {
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
 		bnxt_reset_task(bp, silent);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Only called from bnxt_sp_task() */
@@ -14084,9 +14145,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 {
 	int i;
 
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		bnxt_rtnl_unlock_sp(bp);
+		bnxt_unlock_sp(bp);
 		return;
 	}
 	/* Disable and flush TPA before resetting the RX ring */
@@ -14125,7 +14186,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 	}
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, true);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_fw_fatal_close(struct bnxt *bp)
@@ -15017,17 +15078,15 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
 		fallthrough;
 	case BNXT_FW_RESET_STATE_OPENING:
-		while (!rtnl_trylock()) {
+		while (!netdev_trylock(bp->dev)) {
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
 		}
-		netdev_lock(bp->dev);
 		rc = bnxt_open(bp->dev);
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
 			netdev_unlock(bp->dev);
-			rtnl_unlock();
 			goto ulp_start;
 		}
 
@@ -15047,7 +15106,6 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
 		netdev_unlock(bp->dev);
-		rtnl_unlock();
 		bnxt_ulp_start(bp, 0);
 		bnxt_reenable_sriov(bp);
 		netdev_lock(bp->dev);
@@ -15573,8 +15631,7 @@ static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int ta
 static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
@@ -15582,8 +15639,7 @@ static const struct udp_tunnel_nic_info bnxt_udp_tunnels = {
 }, bnxt_udp_tunnels_p7 = {
 	.set_port	= bnxt_udp_tunnel_set_port,
 	.unset_port	= bnxt_udp_tunnel_unset_port,
-	.flags		= UDP_TUNNEL_NIC_INFO_MAY_SLEEP |
-			  UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
+	.flags		= UDP_TUNNEL_NIC_INFO_OPEN_ONLY,
 	.tables		= {
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN,  },
 		{ .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, },
@@ -15927,6 +15983,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_vnic_info *vnic;
 	struct bnxt_napi *bnapi;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15977,28 +16034,22 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
+	mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
-
-	return 0;
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
 err_reset:
 	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
 		   rc);
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
-	netif_close(dev);
+	bnxt_reset_task(bp, true);
 	return rc;
 }
 
@@ -16013,10 +16064,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
 	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();
 	rxr = &bp->rx_ring[idx];
@@ -16713,6 +16764,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (BNXT_SUPPORTS_QUEUE_API(bp))
 		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
 	dev->request_ops_lock = true;
+	dev->netmem_tx = true;
 
 	rc = register_netdev(dev);
 	if (rc)
@@ -16814,7 +16866,6 @@ static int bnxt_resume(struct device *device)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	rtnl_lock();
 	netdev_lock(dev);
 	rc = pci_enable_device(bp->pdev);
 	if (rc) {
@@ -16859,7 +16910,6 @@ static int bnxt_resume(struct device *device)
 
 resume_exit:
 	netdev_unlock(bp->dev);
-	rtnl_unlock();
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
 		bnxt_reenable_sriov(bp);
@@ -16924,7 +16974,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	bnxt_free_ctx_mem(bp, false);
 	netdev_unlock(netdev);
 
-	/* Request a slot slot reset. */
+	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 
@@ -17025,7 +17075,6 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	int err;
 
 	netdev_info(bp->dev, "PCI Slot Resume\n");
-	rtnl_lock();
 	netdev_lock(netdev);
 
 	err = bnxt_hwrm_func_qcaps(bp);
@@ -17043,7 +17092,6 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 		netif_device_attach(netdev);
 
 	netdev_unlock(netdev);
-	rtnl_unlock();
 	bnxt_ulp_start(bp, err);
 	if (!err)
 		bnxt_reenable_sriov(bp);