netdev - [net-next 15/15] net: e1000e: support txtd update delay via xmit

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1421980631-1955-16-git-send-email-jeffrey.t.kirsher@intel.com>
Date:	Thu, 22 Jan 2015 18:37:11 -0800
From:	Jeff Kirsher <jeffrey.t.kirsher@...el.com>
To:	davem@...emloft.net
Cc:	Florian Westphal <fw@...len.de>, netdev@...r.kernel.org,
	nhorman@...hat.com, sassmann@...hat.com, jogreene@...hat.com,
	Jeff Kirsher <jeffrey.t.kirsher@...el.com>
Subject: [net-next 15/15] net: e1000e: support txtd update delay via xmit_more

From: Florian Westphal <fw@...len.de>

Don't update Tx tail descriptor if queue hasn't been stopped
and we know at least one more skb will be sent right away.

Signed-off-by: Florian Westphal <fw@...len.de>
Tested-by: Aaron Brown <aaron.f.brown@...el.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index aa39a81..1e8c40f 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5444,16 +5444,6 @@ static void e1000_tx_queue(struct e1000_ring *tx_ring, int tx_flags, int count)
 	wmb();
 
 	tx_ring->next_to_use = i;
-
-	if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
-		e1000e_update_tdt_wa(tx_ring, i);
-	else
-		writel(i, tx_ring->tail);
-
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
 }
 
 #define MINIMUM_DHCP_PACKET_SIZE 282
@@ -5655,6 +5645,21 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				    (MAX_SKB_FRAGS *
 				     DIV_ROUND_UP(PAGE_SIZE,
 						  adapter->tx_fifo_limit) + 2));
+
+		if (!skb->xmit_more ||
+		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
+			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+				e1000e_update_tdt_wa(tx_ring,
+						     tx_ring->next_to_use);
+			else
+				writel(tx_ring->next_to_use, tx_ring->tail);
+
+			/* we need this if more than one processor can write
+			 * to our tail at a time, it synchronizes IO on
+			 *IA64/Altix systems
+			 */
+			mmiowb();
+		}
 	} else {
 		dev_kfree_skb_any(skb);
 		tx_ring->buffer_info[first].time_stamp = 0;
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html