[PATCH net-next v4 17/24] eth: bnxt: store the rx buf size per queue

[Pavel Begunkov <asml.silence@gmail.com>]

From: Jakub Kicinski <kuba@kernel.org>

In normal operation only a subset of queues is configured for
zero-copy. Since zero-copy is the main use for larger buffer
sizes we need to configure the sizes per queue.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 50 ++++++++++---------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |  6 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h |  2 +-
 4 files changed, 32 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bd06171cc86c..e4dba91332ae 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -905,7 +905,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 
 static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
 {
-	return rxr->need_head_pool || rxr->bnapi->bp->rx_page_size < PAGE_SIZE;
+	return rxr->need_head_pool || rxr->rx_page_size < PAGE_SIZE;
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
@@ -915,9 +915,9 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 {
 	struct page *page;
 
-	if (bp->rx_page_size < PAGE_SIZE) {
+	if (rxr->rx_page_size < PAGE_SIZE) {
 		page = page_pool_dev_alloc_frag(rxr->page_pool, offset,
-						bp->rx_page_size);
+						rxr->rx_page_size);
 	} else {
 		page = page_pool_dev_alloc_pages(rxr->page_pool);
 		*offset = 0;
@@ -936,9 +936,9 @@ static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
 {
 	netmem_ref netmem;
 
-	if (bp->rx_page_size < PAGE_SIZE) {
+	if (rxr->rx_page_size < PAGE_SIZE) {
 		netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset,
-						     bp->rx_page_size, gfp);
+						     rxr->rx_page_size, gfp);
 	} else {
 		netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
 		*offset = 0;
@@ -1156,9 +1156,9 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, bp->rx_page_size,
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, rxr->rx_page_size,
 				bp->rx_dir);
-	skb = napi_build_skb(data_ptr - bp->rx_offset, bp->rx_page_size);
+	skb = napi_build_skb(data_ptr - bp->rx_offset, rxr->rx_page_size);
 	if (!skb) {
 		page_pool_recycle_direct(rxr->page_pool, page);
 		return NULL;
@@ -1190,7 +1190,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, bp->rx_page_size,
+	dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, rxr->rx_page_size,
 				bp->rx_dir);
 
 	if (unlikely(!payload))
@@ -1204,7 +1204,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 
 	skb_mark_for_recycle(skb);
 	off = (void *)data_ptr - page_address(page);
-	skb_add_rx_frag(skb, 0, page, off, len, bp->rx_page_size);
+	skb_add_rx_frag(skb, 0, page, off, len, rxr->rx_page_size);
 	memcpy(skb->data - NET_IP_ALIGN, data_ptr - NET_IP_ALIGN,
 	       payload + NET_IP_ALIGN);
 
@@ -1289,7 +1289,7 @@ static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
 		if (skb) {
 			skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
 					       cons_rx_buf->offset,
-					       frag_len, bp->rx_page_size);
+					       frag_len, rxr->rx_page_size);
 		} else {
 			skb_frag_t *frag = &shinfo->frags[i];
 
@@ -1314,7 +1314,7 @@ static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
 			if (skb) {
 				skb->len -= frag_len;
 				skb->data_len -= frag_len;
-				skb->truesize -= bp->rx_page_size;
+				skb->truesize -= rxr->rx_page_size;
 			}
 
 			--shinfo->nr_frags;
@@ -1329,7 +1329,7 @@ static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
 		}
 
 		page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
-						  bp->rx_page_size);
+						  rxr->rx_page_size);
 
 		total_frag_len += frag_len;
 		prod = NEXT_RX_AGG(prod);
@@ -2282,8 +2282,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
-						 rxr->page_pool, &xdp);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
@@ -3830,7 +3829,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	if (BNXT_RX_PAGE_MODE(bp))
 		pp.pool_size += bp->rx_ring_size / rx_size_fac;
 
-	pp.order = get_order(bp->rx_page_size);
+	pp.order = get_order(rxr->rx_page_size);
 	pp.nid = numa_node;
 	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
@@ -4325,6 +4324,8 @@ static void bnxt_init_ring_struct(struct bnxt *bp)
 		if (!rxr)
 			goto skip_rx;
 
+		rxr->rx_page_size = bp->rx_page_size;
+
 		ring = &rxr->rx_ring_struct;
 		rmem = &ring->ring_mem;
 		rmem->nr_pages = bp->rx_nr_pages;
@@ -4484,7 +4485,7 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp,
 	ring = &rxr->rx_agg_ring_struct;
 	ring->fw_ring_id = INVALID_HW_RING_ID;
 	if ((bp->flags & BNXT_FLAG_AGG_RINGS)) {
-		type = ((u32)bp->rx_page_size << RX_BD_LEN_SHIFT) |
+		type = ((u32)rxr->rx_page_size << RX_BD_LEN_SHIFT) |
 			RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP;
 
 		bnxt_init_rxbd_pages(ring, type);
@@ -7051,6 +7052,7 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 
 static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
 				       struct hwrm_ring_alloc_input *req,
+				       struct bnxt_rx_ring_info *rxr,
 				       struct bnxt_ring_struct *ring)
 {
 	struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx];
@@ -7060,7 +7062,7 @@ static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
 	if (ring_type == HWRM_RING_ALLOC_AGG) {
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
 		req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
-		req->rx_buf_size = cpu_to_le16(bp->rx_page_size);
+		req->rx_buf_size = cpu_to_le16(rxr->rx_page_size);
 		enables |= RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID;
 	} else {
 		req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
@@ -7074,6 +7076,7 @@ static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
 }
 
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
+				    struct bnxt_rx_ring_info *rxr,
 				    struct bnxt_ring_struct *ring,
 				    u32 ring_type, u32 map_index)
 {
@@ -7130,7 +7133,8 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 			      cpu_to_le32(bp->rx_ring_mask + 1) :
 			      cpu_to_le32(bp->rx_agg_ring_mask + 1);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-			bnxt_set_rx_ring_params_p5(bp, ring_type, req, ring);
+			bnxt_set_rx_ring_params_p5(bp, ring_type, req,
+						   rxr, ring);
 		break;
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;
@@ -7278,7 +7282,7 @@ static int bnxt_hwrm_rx_ring_alloc(struct bnxt *bp,
 	u32 map_idx = bnapi->index;
 	int rc;
 
-	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	rc = hwrm_ring_alloc_send_msg(bp, rxr, ring, type, map_idx);
 	if (rc)
 		return rc;
 
@@ -7298,7 +7302,7 @@ static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp,
 	int rc;
 
 	map_idx = grp_idx + bp->rx_nr_rings;
-	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	rc = hwrm_ring_alloc_send_msg(bp, rxr, ring, type, map_idx);
 	if (rc)
 		return rc;
 
@@ -7322,7 +7326,7 @@ static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp,
 
 	ring = &cpr->cp_ring_struct;
 	ring->handle = BNXT_SET_NQ_HDL(cpr);
-	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	rc = hwrm_ring_alloc_send_msg(bp, NULL, ring, type, map_idx);
 	if (rc)
 		return rc;
 	bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
@@ -7337,7 +7341,7 @@ static int bnxt_hwrm_tx_ring_alloc(struct bnxt *bp,
 	const u32 type = HWRM_RING_ALLOC_TX;
 	int rc;
 
-	rc = hwrm_ring_alloc_send_msg(bp, ring, type, tx_idx);
+	rc = hwrm_ring_alloc_send_msg(bp, NULL, ring, type, tx_idx);
 	if (rc)
 		return rc;
 	bnxt_set_db(bp, &txr->tx_db, type, tx_idx, ring->fw_ring_id);
@@ -7363,7 +7367,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 
 		vector = bp->irq_tbl[map_idx].vector;
 		disable_irq_nosync(vector);
-		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+		rc = hwrm_ring_alloc_send_msg(bp, NULL, ring, type, map_idx);
 		if (rc) {
 			enable_irq(vector);
 			goto err_out;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3abe59e9b021..c8931de76de3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1107,6 +1107,7 @@ struct bnxt_rx_ring_info {
 
 	unsigned long		*rx_agg_bmap;
 	u16			rx_agg_bmap_size;
+	u16			rx_page_size;
 	bool                    need_head_pool;
 
 	dma_addr_t		rx_desc_mapping[MAX_RX_PAGES];
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c23c04007136..619235b151a4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -183,7 +183,7 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 			u16 cons, u8 *data_ptr, unsigned int len,
 			struct xdp_buff *xdp)
 {
-	u32 buflen = bp->rx_page_size;
+	u32 buflen = rxr->rx_page_size;
 	struct bnxt_sw_rx_bd *rx_buf;
 	struct pci_dev *pdev;
 	dma_addr_t mapping;
@@ -461,7 +461,7 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp)
+		   struct bnxt_rx_ring_info *rxr, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
@@ -469,7 +469,7 @@ bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
 		return NULL;
 
 	xdp_update_skb_frags_info(skb, num_frags, sinfo->xdp_frags_size,
-				  bp->rx_page_size * num_frags,
+				  rxr->rx_page_size * num_frags,
 				  xdp_buff_get_skb_flags(xdp));
 	return skb;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 220285e190fc..8933a0dec09a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -32,6 +32,6 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
-				   u8 num_frags, struct page_pool *pool,
+				   u8 num_frags, struct bnxt_rx_ring_info *rxr,
 				   struct xdp_buff *xdp);
 #endif
-- 
2.49.0