bnxt_en: add page_pool support

This removes contention over page allocation for XDP_REDIRECT actions by
adding page_pool support per queue for the driver.  The performance for
XDP_REDIRECT actions scales linearly with the number of cores performing
redirect actions when using the page pools instead of the standard page
allocator.

v2: Fix up the error path from XDP registration, noted by Ilias Apalodimas.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/Kconfig

@@ -199,6 +199,7 @@ config BNXT
 	select FW_LOADER
 	select LIBCRC32C
 	select NET_DEVLINK
+	select PAGE_POOL
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:

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

@@ -54,6 +54,7 @@
 #include <net/pkt_cls.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <net/page_pool.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -668,19 +669,20 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
+					 struct bnxt_rx_ring_info *rxr,
 					 gfp_t gfp)
 {
 	struct device *dev = &bp->pdev->dev;
 	struct page *page;
 
-	page = alloc_page(gfp);
+	page = page_pool_dev_alloc_pages(rxr->page_pool);
 	if (!page)
 		return NULL;
 
 	*mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir,
 				      DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(dev, *mapping)) {
-		__free_page(page);
+		page_pool_recycle_direct(rxr->page_pool, page);
 		return NULL;
 	}
 	*mapping += bp->rx_dma_offset;
@@ -716,7 +718,8 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	dma_addr_t mapping;
 
 	if (BNXT_RX_PAGE_MODE(bp)) {
-		struct page *page = __bnxt_alloc_rx_page(bp, &mapping, gfp);
+		struct page *page =
+			__bnxt_alloc_rx_page(bp, &mapping, rxr, gfp);
 
 		if (!page)
 			return -ENOMEM;
@@ -2360,7 +2363,7 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 				dma_unmap_page_attrs(&pdev->dev, mapping,
 						     PAGE_SIZE, bp->rx_dir,
 						     DMA_ATTR_WEAK_ORDERING);
-				__free_page(data);
+				page_pool_recycle_direct(rxr->page_pool, data);
 			} else {
 				dma_unmap_single_attrs(&pdev->dev, mapping,
 						       bp->rx_buf_use_size,
@@ -2497,6 +2500,8 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 		if (xdp_rxq_info_is_reg(&rxr->xdp_rxq))
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
+		rxr->page_pool = NULL;
+
 		kfree(rxr->rx_tpa);
 		rxr->rx_tpa = NULL;
 
@@ -2511,6 +2516,26 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 	}
 }
 
+static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	struct page_pool_params pp = { 0 };
+
+	pp.pool_size = bp->rx_ring_size;
+	pp.nid = dev_to_node(&bp->pdev->dev);
+	pp.dev = &bp->pdev->dev;
+	pp.dma_dir = DMA_BIDIRECTIONAL;
+
+	rxr->page_pool = page_pool_create(&pp);
+	if (IS_ERR(rxr->page_pool)) {
+		int err = PTR_ERR(rxr->page_pool);
+
+		rxr->page_pool = NULL;
+		return err;
+	}
+	return 0;
+}
+
 static int bnxt_alloc_rx_rings(struct bnxt *bp)
 {
 	int i, rc, agg_rings = 0, tpa_rings = 0;
@@ -2530,14 +2555,24 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 
 		ring = &rxr->rx_ring_struct;
 
-		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i);
+		rc = bnxt_alloc_rx_page_pool(bp, rxr);
-		if (rc < 0)
+		if (rc)
 			return rc;
 
+		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i);
+		if (rc < 0) {
+			page_pool_free(rxr->page_pool);
+			rxr->page_pool = NULL;
+			return rc;
+		}
+
 		rc = xdp_rxq_info_reg_mem_model(&rxr->xdp_rxq,
-						MEM_TYPE_PAGE_SHARED, NULL);
+						MEM_TYPE_PAGE_POOL,
+						rxr->page_pool);
 		if (rc) {
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
+			page_pool_free(rxr->page_pool);
+			rxr->page_pool = NULL;
 			return rc;
 		}
 

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

@@ -26,6 +26,8 @@
 #include <net/xdp.h>
 #include <linux/dim.h>
 
+struct page_pool;
+
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
 	#define TX_BD_TYPE					(0x3f << 0)
@@ -799,6 +801,7 @@ struct bnxt_rx_ring_info {
 	struct bnxt_ring_struct	rx_ring_struct;
 	struct bnxt_ring_struct	rx_agg_ring_struct;
 	struct xdp_rxq_info	xdp_rxq;
+	struct page_pool	*page_pool;
 };
 
 struct bnxt_cp_ring_info {

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

@@ -15,6 +15,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <net/page_pool.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_xdp.h"
@@ -191,7 +192,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 
 		if (xdp_do_redirect(bp->dev, &xdp, xdp_prog)) {
 			trace_xdp_exception(bp->dev, xdp_prog, act);
-			__free_page(page);
+			page_pool_recycle_direct(rxr->page_pool, page);
 			return true;
 		}