All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: davem@davemloft.net, michael.chan@broadcom.com
Cc: netdev@vger.kernel.org, edumazet@google.com, pabeni@redhat.com,
	andrew+netdev@lunn.ch, horms@kernel.org,
	pavan.chebbi@broadcom.com, Jakub Kicinski <kuba@kernel.org>
Subject: [PATCH net-next 3/6] eth: bnxt_en: allocate per-queue SW state on the queue's NUMA node
Date: Tue, 17 Nov 2026 18:39:02 -0800	[thread overview]
Message-ID: <20261118023905.3050661-4-kuba@kernel.org> (raw)
In-Reply-To: <20261118023905.3050661-1-kuba@kernel.org>

Allocate the SW rings, agg bitmap, TPA state, completion ring
page arrays, completion sub-ring structs, SW stats and the SW USO
header buffer on the NUMA node of the CPU which will service the queue.
This lowers the cost of cache misses for NAPI fast path (and xmit, for Tx).

Previous change already allocated the page pools on the right node.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 87 ++++++++++++++---------
 1 file changed, 52 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8e8ee02ca8d9..7c694d8e99f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3765,7 +3765,8 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 	}
 }
 
-static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
+static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem,
+			   int nid)
 {
 	struct pci_dev *pdev = bp->pdev;
 	u64 valid_bit = 0;
@@ -3810,8 +3811,9 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		}
 	}
 
+	/* Only the SW ring follows @nid, DMA memory is on the device's node */
 	if (rmem->vmem_size) {
-		*rmem->vmem = vzalloc(rmem->vmem_size);
+		*rmem->vmem = vzalloc_node(rmem->vmem_size, nid);
 		if (!(*rmem->vmem))
 			return -ENOMEM;
 	}
@@ -3862,25 +3864,27 @@ static void bnxt_free_tpa_info(struct bnxt *bp)
 }
 
 static int bnxt_alloc_one_tpa_info(struct bnxt *bp,
-				   struct bnxt_rx_ring_info *rxr)
+				   struct bnxt_rx_ring_info *rxr, int nid)
 {
 	struct rx_agg_cmp *agg;
 	int i;
 
-	rxr->rx_tpa = kzalloc_objs(struct bnxt_tpa_info,
-				   bp->max_tpa_roundup_size);
+	rxr->rx_tpa = kcalloc_node(bp->max_tpa_roundup_size,
+				   sizeof(*rxr->rx_tpa), GFP_KERNEL, nid);
 	if (!rxr->rx_tpa)
 		return -ENOMEM;
 
 	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 		return 0;
 	for (i = 0; i < bp->max_tpa_roundup_size; i++) {
-		agg = kzalloc_objs(*agg, MAX_SKB_FRAGS);
+		agg = kcalloc_node(MAX_SKB_FRAGS, sizeof(*agg),
+				   GFP_KERNEL, nid);
 		if (!agg)
 			return -ENOMEM;
 		rxr->rx_tpa[i].agg_arr = agg;
 	}
-	rxr->rx_tpa_idx_map = kzalloc_obj(*rxr->rx_tpa_idx_map);
+	rxr->rx_tpa_idx_map = kzalloc_node(sizeof(*rxr->rx_tpa_idx_map),
+					   GFP_KERNEL, nid);
 	if (!rxr->rx_tpa_idx_map)
 		return -ENOMEM;
 
@@ -3907,8 +3911,10 @@ static int bnxt_alloc_tpa_info(struct bnxt *bp)
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
+		int nid;
 
-		rc = bnxt_alloc_one_tpa_info(bp, rxr);
+		nid = bnxt_cp_num_to_node(bp, i);
+		rc = bnxt_alloc_one_tpa_info(bp, rxr, nid);
 		if (rc)
 			return rc;
 	}
@@ -4020,13 +4026,14 @@ static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr)
 	page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi);
 }
 
-static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
+static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp,
+				  struct bnxt_rx_ring_info *rxr, int nid)
 {
 	u16 mem_size;
 
 	rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1;
 	mem_size = rxr->rx_agg_bmap_size / 8;
-	rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
+	rxr->rx_agg_bmap = kzalloc_node(mem_size, GFP_KERNEL, nid);
 	if (!rxr->rx_agg_bmap)
 		return -ENOMEM;
 
@@ -4070,19 +4077,19 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 			return rc;
 		}
 
-		rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+		rc = bnxt_alloc_ring(bp, &ring->ring_mem, cpu_node);
 		if (rc)
 			return rc;
 
 		ring->grp_idx = i;
 		if (agg_rings) {
 			ring = &rxr->rx_agg_ring_struct;
-			rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+			rc = bnxt_alloc_ring(bp, &ring->ring_mem, cpu_node);
 			if (rc)
 				return rc;
 
 			ring->grp_idx = i;
-			rc = bnxt_alloc_rx_agg_bmap(bp, rxr);
+			rc = bnxt_alloc_rx_agg_bmap(bp, rxr, cpu_node);
 			if (rc)
 				return rc;
 		}
@@ -4107,9 +4114,9 @@ static void bnxt_free_tx_inline_buf(struct bnxt_tx_ring_info *txr,
 
 static int bnxt_alloc_tx_inline_buf(struct bnxt_tx_ring_info *txr,
 				    struct pci_dev *pdev,
-				    unsigned int size)
+				    unsigned int size, int nid)
 {
-	txr->tx_inline_buf = kmalloc(size, GFP_KERNEL);
+	txr->tx_inline_buf = kmalloc_node(size, GFP_KERNEL, nid);
 	if (!txr->tx_inline_buf)
 		return -ENOMEM;
 
@@ -4183,11 +4190,13 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 	for (i = 0, j = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring;
+		int nid;
 		u8 qidx;
 
 		ring = &txr->tx_ring_struct;
 
-		rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+		nid = bnxt_cp_num_to_node(bp, txr->bnapi->index);
+		rc = bnxt_alloc_ring(bp, &ring->ring_mem, nid);
 		if (rc)
 			return rc;
 
@@ -4213,7 +4222,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		if (!(bp->flags & BNXT_FLAG_UDP_GSO_CAP)) {
 			rc = bnxt_alloc_tx_inline_buf(txr, pdev,
 						      BNXT_SW_USO_MAX_SEGS *
-						      TSO_HEADER_SIZE);
+						      TSO_HEADER_SIZE, nid);
 			if (rc)
 				return rc;
 		}
@@ -4240,12 +4249,15 @@ static void bnxt_free_cp_arrays(struct bnxt_cp_ring_info *cpr)
 	ring->ring_mem.dma_arr = NULL;
 }
 
-static int bnxt_alloc_cp_arrays(struct bnxt_cp_ring_info *cpr, int n)
+static int bnxt_alloc_cp_arrays(struct bnxt_cp_ring_info *cpr, int n,
+				int nid)
 {
-	cpr->cp_desc_ring = kzalloc_objs(*cpr->cp_desc_ring, n);
+	cpr->cp_desc_ring = kcalloc_node(n, sizeof(*cpr->cp_desc_ring),
+					 GFP_KERNEL, nid);
 	if (!cpr->cp_desc_ring)
 		return -ENOMEM;
-	cpr->cp_desc_mapping = kzalloc_objs(*cpr->cp_desc_mapping, n);
+	cpr->cp_desc_mapping = kcalloc_node(n, sizeof(*cpr->cp_desc_mapping),
+					    GFP_KERNEL, nid);
 	if (!cpr->cp_desc_mapping)
 		return -ENOMEM;
 	return 0;
@@ -4272,11 +4284,12 @@ static int bnxt_alloc_all_cp_arrays(struct bnxt *bp)
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
-		int rc;
+		int nid, rc;
 
 		if (!bnapi)
 			continue;
-		rc = bnxt_alloc_cp_arrays(&bnapi->cp_ring, n);
+		nid = bnxt_cp_num_to_node(bp, i);
+		rc = bnxt_alloc_cp_arrays(&bnapi->cp_ring, n, nid);
 		if (rc)
 			return rc;
 	}
@@ -4321,13 +4334,13 @@ static void bnxt_free_cp_rings(struct bnxt *bp)
 }
 
 static int bnxt_alloc_cp_sub_ring(struct bnxt *bp,
-				  struct bnxt_cp_ring_info *cpr)
+				  struct bnxt_cp_ring_info *cpr, int nid)
 {
 	struct bnxt_ring_mem_info *rmem;
 	struct bnxt_ring_struct *ring;
 	int rc;
 
-	rc = bnxt_alloc_cp_arrays(cpr, bp->cp_nr_pages);
+	rc = bnxt_alloc_cp_arrays(cpr, bp->cp_nr_pages, nid);
 	if (rc) {
 		bnxt_free_cp_arrays(cpr);
 		return -ENOMEM;
@@ -4339,7 +4352,7 @@ static int bnxt_alloc_cp_sub_ring(struct bnxt *bp,
 	rmem->pg_arr = (void **)cpr->cp_desc_ring;
 	rmem->dma_arr = cpr->cp_desc_mapping;
 	rmem->flags = BNXT_RMEM_RING_PTE_FLAG;
-	rc = bnxt_alloc_ring(bp, rmem);
+	rc = bnxt_alloc_ring(bp, rmem, NUMA_NO_NODE);
 	if (rc) {
 		bnxt_free_ring(bp, rmem);
 		bnxt_free_cp_arrays(cpr);
@@ -4360,7 +4373,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr, *cpr2;
 		struct bnxt_ring_struct *ring;
-		int cp_count = 0, k;
+		int cp_count = 0, k, nid;
 		int rx = 0, tx = 0;
 
 		if (!bnapi)
@@ -4370,7 +4383,7 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		cpr->bnapi = bnapi;
 		ring = &cpr->cp_ring_struct;
 
-		rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+		rc = bnxt_alloc_ring(bp, &ring->ring_mem, NUMA_NO_NODE);
 		if (rc)
 			return rc;
 
@@ -4392,14 +4405,16 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 			tx = 1;
 		}
 
-		cpr->cp_ring_arr = kzalloc_objs(*cpr, cp_count);
+		nid = bnxt_cp_num_to_node(bp, i);
+		cpr->cp_ring_arr = kcalloc_node(cp_count, sizeof(*cpr),
+						GFP_KERNEL, nid);
 		if (!cpr->cp_ring_arr)
 			return -ENOMEM;
 		cpr->cp_ring_count = cp_count;
 
 		for (k = 0; k < cp_count; k++) {
 			cpr2 = &cpr->cp_ring_arr[k];
-			rc = bnxt_alloc_cp_sub_ring(bp, cpr2);
+			rc = bnxt_alloc_cp_sub_ring(bp, cpr2, nid);
 			if (rc)
 				return rc;
 			cpr2->bnapi = bnapi;
@@ -5411,8 +5426,10 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+		int nid = bnxt_cp_num_to_node(bp, i);
 
-		cpr->sw_stats = kzalloc_obj(*cpr->sw_stats);
+		cpr->sw_stats = kzalloc_node(sizeof(*cpr->sw_stats), GFP_KERNEL,
+					     nid);
 		if (!cpr->sw_stats)
 			return -ENOMEM;
 
@@ -9201,7 +9218,7 @@ static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
 	rmem->flags = BNXT_RMEM_VALID_PTE_FLAG;
 	if (rmem->depth >= 1)
 		rmem->flags |= BNXT_RMEM_USE_FULL_PAGE_FLAG;
-	return bnxt_alloc_ring(bp, rmem);
+	return bnxt_alloc_ring(bp, rmem, NUMA_NO_NODE);
 }
 
 static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
@@ -16501,23 +16518,23 @@ static int bnxt_queue_mem_alloc(struct net_device *dev,
 		goto err_rxq_info_unreg;
 
 	ring = &clone->rx_ring_struct;
-	rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+	rc = bnxt_alloc_ring(bp, &ring->ring_mem, nid);
 	if (rc)
 		goto err_free_rx_ring;
 
 	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
 		ring = &clone->rx_agg_ring_struct;
-		rc = bnxt_alloc_ring(bp, &ring->ring_mem);
+		rc = bnxt_alloc_ring(bp, &ring->ring_mem, nid);
 		if (rc)
 			goto err_free_rx_agg_ring;
 
-		rc = bnxt_alloc_rx_agg_bmap(bp, clone);
+		rc = bnxt_alloc_rx_agg_bmap(bp, clone, nid);
 		if (rc)
 			goto err_free_rx_agg_ring;
 	}
 
 	if (bp->flags & BNXT_FLAG_TPA) {
-		rc = bnxt_alloc_one_tpa_info(bp, clone);
+		rc = bnxt_alloc_one_tpa_info(bp, clone, nid);
 		if (rc)
 			goto err_free_tpa_info;
 	}
-- 
2.56.1


  parent reply	other threads:[~2026-11-18  2:39 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-18  2:38 [PATCH net-next 0/6] eth: bnxt_en: allocate memory on the right NUMA node Jakub Kicinski
2026-11-18  2:39 ` [PATCH net-next 1/6] eth: bnxt_en: order event data before setting the sp_event bit Jakub Kicinski
2026-11-18  2:39 ` [PATCH net-next 2/6] eth: bnxt_en: follow explicitly set IRQ affinity when placing page pool Jakub Kicinski
2026-11-18  2:39 ` Jakub Kicinski [this message]
2026-11-18  2:39 ` [PATCH net-next 4/6] eth: bnxt_en: explicitly keep device-only memory on the device's node Jakub Kicinski
2026-11-18  2:39 ` [PATCH net-next 5/6] eth: bnxt_en: allocate fast path DMA rings on the queue's NUMA node Jakub Kicinski
2026-11-18  2:39 ` [PATCH net-next 6/6] eth: bnxt_en: restart Rx queues when their IRQ moves to another " Jakub Kicinski

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261118023905.3050661-4-kuba@kernel.org \
    --to=kuba@kernel.org \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=michael.chan@broadcom.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=pavan.chebbi@broadcom.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.