bnxt_en: handle tpa_info in queue API implementation

Commit 7ed816be35ab ("eth: bnxt: use page pool for head frags") added a
page pool for header frags, which may be distinct from the existing pool
for the aggregation ring. Prior to this change, frags used in the TPA
ring rx_tpa were allocated from system memory e.g. napi_alloc_frag()
meaning their lifetimes were not associated with a page pool. They can
be returned at any time and so the queue API did not alloc or free
rx_tpa.

But now frags come from a separate head_pool which may be different to
page_pool. Without allocating and freeing rx_tpa, frags allocated from
the old head_pool may be returned to a different new head_pool which
causes a mismatch between the pp hold/release count.

Fix this problem by properly freeing and allocating rx_tpa in the queue
API implementation.

Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20241204041022.56512-4-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 23 insertions, 4 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8031ff31f837..6b963086c1d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3710,7 +3710,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 		page_pool_destroy(rxr->page_pool);
-		if (rxr->page_pool != rxr->head_pool)
+		if (bnxt_separate_head_pool())
 			page_pool_destroy(rxr->head_pool);
 		rxr->page_pool = rxr->head_pool = NULL;
 
@@ -15388,15 +15388,25 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 			goto err_free_rx_agg_ring;
 	}
 
+	if (bp->flags & BNXT_FLAG_TPA) {
+		rc = bnxt_alloc_one_tpa_info(bp, clone);
+		if (rc)
+			goto err_free_tpa_info;
+	}
+
 	bnxt_init_one_rx_ring_rxbd(bp, clone);
 	bnxt_init_one_rx_agg_ring_rxbd(bp, clone);
 
 	bnxt_alloc_one_rx_ring_skb(bp, clone, idx);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_alloc_one_rx_ring_page(bp, clone, idx);
+	if (bp->flags & BNXT_FLAG_TPA)
+		bnxt_alloc_one_tpa_info_data(bp, clone);
 
 	return 0;
 
+err_free_tpa_info:
+	bnxt_free_one_tpa_info(bp, clone);
 err_free_rx_agg_ring:
 	bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem);
 err_free_rx_ring:
@@ -15404,9 +15414,11 @@ err_free_rx_ring:
 err_rxq_info_unreg:
 	xdp_rxq_info_unreg(&clone->xdp_rxq);
 err_page_pool_destroy:
-	clone->page_pool->p.napi = NULL;
 	page_pool_destroy(clone->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_destroy(clone->head_pool);
 	clone->page_pool = NULL;
+	clone->head_pool = NULL;
 	return rc;
 }
 
@@ -15416,13 +15428,15 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_ring_struct *ring;
 
-	bnxt_free_one_rx_ring(bp, rxr);
-	bnxt_free_one_rx_agg_ring(bp, rxr);
+	bnxt_free_one_rx_ring_skbs(bp, rxr);
 
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
 	page_pool_destroy(rxr->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_destroy(rxr->head_pool);
 	rxr->page_pool = NULL;
+	rxr->head_pool = NULL;
 
 	ring = &rxr->rx_ring_struct;
 	bnxt_free_ring(bp, &ring->ring_mem);
@@ -15504,7 +15518,10 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	rxr->rx_agg_prod = clone->rx_agg_prod;
 	rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod;
 	rxr->rx_next_cons = clone->rx_next_cons;
+	rxr->rx_tpa = clone->rx_tpa;
+	rxr->rx_tpa_idx_map = clone->rx_tpa_idx_map;
 	rxr->page_pool = clone->page_pool;
+	rxr->head_pool = clone->head_pool;
 	rxr->xdp_rxq = clone->xdp_rxq;
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
@@ -15563,6 +15580,8 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	rxr->rx_next_cons = 0;
 	page_pool_disable_direct_recycling(rxr->page_pool);
+	if (bnxt_separate_head_pool())
+		page_pool_disable_direct_recycling(rxr->head_pool);
 
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);