mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Sieng-Piaw Liew <liew.s.piaw@gmail.com>
To: chris.snook@gmail.com, davem@davemloft.net, edumazet@google.com,
	kuba@kernel.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: Sieng-Piaw Liew <liew.s.piaw@gmail.com>
Subject: [PATCH net-next v2] net: ag71xx: switch to napi_build_skb() to reuse skbuff_heads
Date: Thu,  7 Jul 2022 22:10:56 +0800	[thread overview]
Message-ID: <20220707141056.2644-1-liew.s.piaw@gmail.com> (raw)
In-Reply-To: <20220706195213.6b751af8@kernel.org>

napi_build_skb() reuses NAPI skbuff_head cache in order to save some
cycles on freeing/allocating skbuff_heads on every new Rx or completed
Tx.
Use napi_consume_skb() to feed the cache with skbuff_heads of completed
Tx, so it's never empty. The budget parameter is added to indicate NAPI
context, as a value of zero can be passed in the case of netpoll.

Signed-off-by: Sieng-Piaw Liew <liew.s.piaw@gmail.com>
---
 drivers/net/ethernet/atheros/ag71xx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 1c6ea6766aa1..e461f4764066 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -786,7 +786,7 @@ static bool ag71xx_check_dma_stuck(struct ag71xx *ag)
 	return false;
 }
 
-static int ag71xx_tx_packets(struct ag71xx *ag, bool flush)
+static int ag71xx_tx_packets(struct ag71xx *ag, bool flush, int budget)
 {
 	struct ag71xx_ring *ring = &ag->tx_ring;
 	int sent = 0, bytes_compl = 0, n = 0;
@@ -825,7 +825,7 @@ static int ag71xx_tx_packets(struct ag71xx *ag, bool flush)
 		if (!skb)
 			continue;
 
-		dev_kfree_skb_any(skb);
+		napi_consume_skb(skb, budget);
 		ring->buf[i].tx.skb = NULL;
 
 		bytes_compl += ring->buf[i].tx.len;
@@ -970,7 +970,7 @@ static void ag71xx_fast_reset(struct ag71xx *ag)
 	mii_reg = ag71xx_rr(ag, AG71XX_REG_MII_CFG);
 	rx_ds = ag71xx_rr(ag, AG71XX_REG_RX_DESC);
 
-	ag71xx_tx_packets(ag, true);
+	ag71xx_tx_packets(ag, true, 0);
 
 	reset_control_assert(ag->mac_reset);
 	usleep_range(10, 20);
@@ -1657,7 +1657,7 @@ static int ag71xx_rx_packets(struct ag71xx *ag, int limit)
 		ndev->stats.rx_packets++;
 		ndev->stats.rx_bytes += pktlen;
 
-		skb = build_skb(ring->buf[i].rx.rx_buf, ag71xx_buffer_size(ag));
+		skb = napi_build_skb(ring->buf[i].rx.rx_buf, ag71xx_buffer_size(ag));
 		if (!skb) {
 			skb_free_frag(ring->buf[i].rx.rx_buf);
 			goto next;
@@ -1703,7 +1703,7 @@ static int ag71xx_poll(struct napi_struct *napi, int limit)
 	int tx_done, rx_done;
 	u32 status;
 
-	tx_done = ag71xx_tx_packets(ag, false);
+	tx_done = ag71xx_tx_packets(ag, false, limit);
 
 	netif_dbg(ag, rx_status, ndev, "processing RX ring\n");
 	rx_done = ag71xx_rx_packets(ag, limit);
-- 
2.17.1


  reply	other threads:[~2022-07-07 14:13 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-05  0:44 [PATCH] " Sieng-Piaw Liew
2022-07-07  2:52 ` Jakub Kicinski
2022-07-07 14:10   ` Sieng-Piaw Liew [this message]
2022-07-08 13:30     ` [PATCH net-next v2] " patchwork-bot+netdevbpf

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=20220707141056.2644-1-liew.s.piaw@gmail.com \
    --to=liew.s.piaw@gmail.com \
    --cc=chris.snook@gmail.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®