Merge branch 'bnxt_en-update-for-net-next'

Michael Chan says:

====================
bnxt_en: Update for net-next

This patchset contains 2 features:

- The page pool implementation for the normal RX path (non-XDP) for
paged buffers in the aggregation ring.

- Saving of the ring error counters across reset.
====================

Link: https://lore.kernel.org/r/20230817231911.165035-1-michael.chan@broadcom.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -761,7 +761,6 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 					 unsigned int *offset,
 					 gfp_t gfp)
 {
-	struct device *dev = &bp->pdev->dev;
 	struct page *page;
 
 	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
@@ -774,12 +773,7 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	if (!page)
 		return NULL;
 
-	*mapping = dma_map_page_attrs(dev, page, *offset, BNXT_RX_PAGE_SIZE,
-				      bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
-	if (dma_mapping_error(dev, *mapping)) {
-		page_pool_recycle_direct(rxr->page_pool, page);
-		return NULL;
-	}
+	*mapping = page_pool_get_dma_addr(page) + *offset;
 	return page;
 }
 
@@ -877,48 +871,15 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 	struct rx_bd *rxbd =
 		&rxr->rx_agg_desc_ring[RX_RING(prod)][RX_IDX(prod)];
 	struct bnxt_sw_rx_agg_bd *rx_agg_buf;
-	struct pci_dev *pdev = bp->pdev;
 	struct page *page;
 	dma_addr_t mapping;
 	u16 sw_prod = rxr->rx_sw_agg_prod;
 	unsigned int offset = 0;
 
-	if (BNXT_RX_PAGE_MODE(bp)) {
-		page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
-
-		if (!page)
-			return -ENOMEM;
-
-	} else {
-		if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
-			page = rxr->rx_page;
-			if (!page) {
-				page = alloc_page(gfp);
-				if (!page)
-					return -ENOMEM;
-				rxr->rx_page = page;
-				rxr->rx_page_offset = 0;
-			}
-			offset = rxr->rx_page_offset;
-			rxr->rx_page_offset += BNXT_RX_PAGE_SIZE;
-			if (rxr->rx_page_offset == PAGE_SIZE)
-				rxr->rx_page = NULL;
-			else
-				get_page(page);
-		} else {
-			page = alloc_page(gfp);
-			if (!page)
-				return -ENOMEM;
-		}
+	page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
 
-		mapping = dma_map_page_attrs(&pdev->dev, page, offset,
-					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-					     DMA_ATTR_WEAK_ORDERING);
-		if (dma_mapping_error(&pdev->dev, mapping)) {
-			__free_page(page);
-			return -EIO;
-		}
-	}
+	if (!page)
+		return -ENOMEM;
 
 	if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
 		sw_prod = bnxt_find_next_agg_idx(rxr, sw_prod);
@@ -1031,8 +992,8 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
-			     bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
+				bp->rx_dir);
 	skb = build_skb(data_ptr - bp->rx_offset, BNXT_RX_PAGE_SIZE);
 	if (!skb) {
 		page_pool_recycle_direct(rxr->page_pool, page);
@@ -1065,8 +1026,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
-			     bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, BNXT_RX_PAGE_SIZE,
+				bp->rx_dir);
 
 	if (unlikely(!payload))
 		payload = eth_get_headlen(bp->dev, data_ptr, len);
@@ -1182,9 +1143,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
 			return 0;
 		}
 
-		dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-				     bp->rx_dir,
-				     DMA_ATTR_WEAK_ORDERING);
+		dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
+					bp->rx_dir);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -1204,6 +1164,7 @@ static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
 	total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
 					     agg_bufs, tpa, NULL);
 	if (!total_frag_len) {
+		skb_mark_for_recycle(skb);
 		dev_kfree_skb(skb);
 		return NULL;
 	}
@@ -1794,6 +1755,7 @@ static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 		return;
 	}
 	skb_record_rx_queue(skb, bnapi->index);
+	skb_mark_for_recycle(skb);
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
@@ -2978,10 +2940,6 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
 
 		rx_buf->data = NULL;
 		if (BNXT_RX_PAGE_MODE(bp)) {
-			mapping -= bp->rx_dma_offset;
-			dma_unmap_page_attrs(&pdev->dev, mapping,
-					     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-					     DMA_ATTR_WEAK_ORDERING);
 			page_pool_recycle_direct(rxr->page_pool, data);
 		} else {
 			dma_unmap_single_attrs(&pdev->dev, mapping,
@@ -3002,30 +2960,13 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr)
 		if (!page)
 			continue;
 
-		if (BNXT_RX_PAGE_MODE(bp)) {
-			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-					     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-					     DMA_ATTR_WEAK_ORDERING);
-			rx_agg_buf->page = NULL;
-			__clear_bit(i, rxr->rx_agg_bmap);
+		rx_agg_buf->page = NULL;
+		__clear_bit(i, rxr->rx_agg_bmap);
 
-			page_pool_recycle_direct(rxr->page_pool, page);
-		} else {
-			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
-					     BNXT_RX_PAGE_SIZE, DMA_FROM_DEVICE,
-					     DMA_ATTR_WEAK_ORDERING);
-			rx_agg_buf->page = NULL;
-			__clear_bit(i, rxr->rx_agg_bmap);
-
-			__free_page(page);
-		}
+		page_pool_recycle_direct(rxr->page_pool, page);
 	}
 
 skip_rx_agg_free:
-	if (rxr->rx_page) {
-		__free_page(rxr->rx_page);
-		rxr->rx_page = NULL;
-	}
 	map = rxr->rx_tpa_idx_map;
 	if (map)
 		memset(map->agg_idx_bmap, 0, sizeof(map->agg_idx_bmap));
@@ -3244,11 +3185,15 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 {
 	struct page_pool_params pp = { 0 };
 
-	pp.pool_size = bp->rx_ring_size;
+	pp.pool_size = bp->rx_agg_ring_size;
+	if (BNXT_RX_PAGE_MODE(bp))
+		pp.pool_size += bp->rx_ring_size;
 	pp.nid = dev_to_node(&bp->pdev->dev);
 	pp.napi = &rxr->bnapi->napi;
 	pp.dev = &bp->pdev->dev;
-	pp.dma_dir = DMA_BIDIRECTIONAL;
+	pp.dma_dir = bp->rx_dir;
+	pp.max_len = PAGE_SIZE;
+	pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
 	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE)
 		pp.flags |= PP_FLAG_PAGE_FRAG;
 
@@ -9448,10 +9393,16 @@ static void bnxt_disable_napi(struct bnxt *bp)
 		return;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
-		struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+		struct bnxt_cp_ring_info *cpr;
 
-		napi_disable(&bp->bnapi[i]->napi);
-		if (bp->bnapi[i]->rx_ring)
+		cpr = &bnapi->cp_ring;
+		if (bnapi->tx_fault)
+			cpr->sw_stats.tx.tx_resets++;
+		if (bnapi->in_reset)
+			cpr->sw_stats.rx.rx_resets++;
+		napi_disable(&bnapi->napi);
+		if (bnapi->rx_ring)
 			cancel_work_sync(&cpr->dim.work);
 	}
 }
@@ -9468,8 +9419,6 @@ static void bnxt_enable_napi(struct bnxt *bp)
 		bnapi->tx_fault = 0;
 
 		cpr = &bnapi->cp_ring;
-		if (bnapi->in_reset)
-			cpr->sw_stats.rx.rx_resets++;
 		bnapi->in_reset = false;
 
 		bnapi->tx_pkts = 0;
@@ -10738,8 +10687,10 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
-	if (bp->bnapi && irq_re_init)
+	if (bp->bnapi && irq_re_init) {
 		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
+		bnxt_get_ring_err_stats(bp, &bp->ring_err_stats_prev);
+	}
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
 		bnxt_del_napi(bp);
@@ -10988,6 +10939,35 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	clear_bit(BNXT_STATE_READ_STATS, &bp->state);
 }
 
+static void bnxt_get_one_ring_err_stats(struct bnxt *bp,
+					struct bnxt_total_ring_err_stats *stats,
+					struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_sw_stats *sw_stats = &cpr->sw_stats;
+	u64 *hw_stats = cpr->stats.sw_stats;
+
+	stats->rx_total_l4_csum_errors += sw_stats->rx.rx_l4_csum_errors;
+	stats->rx_total_resets += sw_stats->rx.rx_resets;
+	stats->rx_total_buf_errors += sw_stats->rx.rx_buf_errors;
+	stats->rx_total_oom_discards += sw_stats->rx.rx_oom_discards;
+	stats->rx_total_netpoll_discards += sw_stats->rx.rx_netpoll_discards;
+	stats->rx_total_ring_discards +=
+		BNXT_GET_RING_STATS64(hw_stats, rx_discard_pkts);
+	stats->tx_total_resets += sw_stats->tx.tx_resets;
+	stats->tx_total_ring_discards +=
+		BNXT_GET_RING_STATS64(hw_stats, tx_discard_pkts);
+	stats->total_missed_irqs += sw_stats->cmn.missed_irqs;
+}
+
+void bnxt_get_ring_err_stats(struct bnxt *bp,
+			     struct bnxt_total_ring_err_stats *stats)
+{
+	int i;
+
+	for (i = 0; i < bp->cp_nr_rings; i++)
+		bnxt_get_one_ring_err_stats(bp, stats, &bp->bnapi[i]->cp_ring);
+}
+
 static bool bnxt_mc_list_updated(struct bnxt *bp, u32 *rx_mask)
 {
 	struct net_device *dev = bp->dev;

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -919,9 +919,6 @@ struct bnxt_rx_ring_info {
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
 
-	struct page		*rx_page;
-	unsigned int		rx_page_offset;
-
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
 	dma_addr_t		rx_agg_desc_mapping[MAX_RX_AGG_PAGES];
 
@@ -942,15 +939,32 @@ struct bnxt_rx_sw_stats {
 	u64			rx_netpoll_discards;
 };
 
+struct bnxt_tx_sw_stats {
+	u64			tx_resets;
+};
+
 struct bnxt_cmn_sw_stats {
 	u64			missed_irqs;
 };
 
 struct bnxt_sw_stats {
 	struct bnxt_rx_sw_stats rx;
+	struct bnxt_tx_sw_stats tx;
 	struct bnxt_cmn_sw_stats cmn;
 };
 
+struct bnxt_total_ring_err_stats {
+	u64			rx_total_l4_csum_errors;
+	u64			rx_total_resets;
+	u64			rx_total_buf_errors;
+	u64			rx_total_oom_discards;
+	u64			rx_total_netpoll_discards;
+	u64			rx_total_ring_discards;
+	u64			tx_total_resets;
+	u64			tx_total_ring_discards;
+	u64			total_missed_irqs;
+};
+
 struct bnxt_stats_mem {
 	u64		*sw_stats;
 	u64		*hw_masks;
@@ -2021,6 +2035,8 @@ struct bnxt {
 	u8			pri2cos_idx[8];
 	u8			pri2cos_valid;
 
+	struct bnxt_total_ring_err_stats ring_err_stats_prev;
+
 	u16			hwrm_max_req_len;
 	u16			hwrm_max_ext_req_len;
 	unsigned int		hwrm_cmd_timeout;
@@ -2347,6 +2363,8 @@ int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 void bnxt_reenable_sriov(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_get_ring_err_stats(struct bnxt *bp,
+			     struct bnxt_total_ring_err_stats *stats);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 			 u32 *reg_buf);
 void bnxt_fw_exception(struct bnxt *bp);

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -339,13 +339,16 @@ enum {
 	RX_NETPOLL_DISCARDS,
 };
 
-static struct {
-	u64			counter;
-	char			string[ETH_GSTRING_LEN];
-} bnxt_sw_func_stats[] = {
-	{0, "rx_total_discard_pkts"},
-	{0, "tx_total_discard_pkts"},
-	{0, "rx_total_netpoll_discards"},
+static const char *const bnxt_ring_err_stats_arr[] = {
+	"rx_total_l4_csum_errors",
+	"rx_total_resets",
+	"rx_total_buf_errors",
+	"rx_total_oom_discards",
+	"rx_total_netpoll_discards",
+	"rx_total_ring_discards",
+	"tx_total_resets",
+	"tx_total_ring_discards",
+	"total_missed_irqs",
 };
 
 #define NUM_RING_RX_SW_STATS		ARRAY_SIZE(bnxt_rx_sw_stats_str)
@@ -495,7 +498,7 @@ static const struct {
 	BNXT_TX_STATS_PRI_ENTRIES(tx_packets),
 };
 
-#define BNXT_NUM_SW_FUNC_STATS	ARRAY_SIZE(bnxt_sw_func_stats)
+#define BNXT_NUM_RING_ERR_STATS	ARRAY_SIZE(bnxt_ring_err_stats_arr)
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
 #define BNXT_NUM_STATS_PRI			\
 	(ARRAY_SIZE(bnxt_rx_bytes_pri_arr) +	\
@@ -532,7 +535,7 @@ static int bnxt_get_num_stats(struct bnxt *bp)
 {
 	int num_stats = bnxt_get_num_ring_stats(bp);
 
-	num_stats += BNXT_NUM_SW_FUNC_STATS;
+	num_stats += BNXT_NUM_RING_ERR_STATS;
 
 	if (bp->flags & BNXT_FLAG_PORT_STATS)
 		num_stats += BNXT_NUM_PORT_STATS;
@@ -583,18 +586,17 @@ static bool is_tx_ring(struct bnxt *bp, int ring_num)
 static void bnxt_get_ethtool_stats(struct net_device *dev,
 				   struct ethtool_stats *stats, u64 *buf)
 {
-	u32 i, j = 0;
+	struct bnxt_total_ring_err_stats ring_err_stats = {0};
 	struct bnxt *bp = netdev_priv(dev);
+	u64 *curr, *prev;
 	u32 tpa_stats;
+	u32 i, j = 0;
 
 	if (!bp->bnapi) {
-		j += bnxt_get_num_ring_stats(bp) + BNXT_NUM_SW_FUNC_STATS;
+		j += bnxt_get_num_ring_stats(bp);
 		goto skip_ring_stats;
 	}
 
-	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
-		bnxt_sw_func_stats[i].counter = 0;
-
 	tpa_stats = bnxt_get_num_tpa_ring_stats(bp);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
@@ -631,19 +633,16 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 		sw = (u64 *)&cpr->sw_stats.cmn;
 		for (k = 0; k < NUM_RING_CMN_SW_STATS; j++, k++)
 			buf[j] = sw[k];
-
-		bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter +=
-			BNXT_GET_RING_STATS64(sw_stats, rx_discard_pkts);
-		bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter +=
-			BNXT_GET_RING_STATS64(sw_stats, tx_discard_pkts);
-		bnxt_sw_func_stats[RX_NETPOLL_DISCARDS].counter +=
-			cpr->sw_stats.rx.rx_netpoll_discards;
 	}
 
-	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
-		buf[j] = bnxt_sw_func_stats[i].counter;
+	bnxt_get_ring_err_stats(bp, &ring_err_stats);
 
 skip_ring_stats:
+	curr = &ring_err_stats.rx_total_l4_csum_errors;
+	prev = &bp->ring_err_stats_prev.rx_total_l4_csum_errors;
+	for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++, j++, curr++, prev++)
+		buf[j] = *curr + *prev;
+
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		u64 *port_stats = bp->port_stats.sw_stats;
 
@@ -745,8 +744,8 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				buf += ETH_GSTRING_LEN;
 			}
 		}
-		for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) {
-			strcpy(buf, bnxt_sw_func_stats[i].string);
+		for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++) {
+			strscpy(buf, bnxt_ring_err_stats_arr[i], ETH_GSTRING_LEN);
 			buf += ETH_GSTRING_LEN;
 		}