netdev - [net-next v2 04/11] ixgbe: delay tail write to every 'n' packets

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: Windows password security audit tool. GUI, reports in PDF.

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

Date:   Sat, 29 Apr 2017 20:08:03 -0700
From:   Jeff Kirsher <jeffrey.t.kirsher@...el.com>
To:     davem@...emloft.net
Cc:     John Fastabend <john.r.fastabend@...el.com>,
        netdev@...r.kernel.org, nhorman@...hat.com, sassmann@...hat.com,
        jogreene@...hat.com, Jeff Kirsher <jeffrey.t.kirsher@...el.com>
Subject: [net-next v2 04/11] ixgbe: delay tail write to every 'n' packets

From: John Fastabend <john.r.fastabend@...el.com>

Current XDP implementation hits the tail on every XDP_TX return
code. This patch changes driver behavior to only hit the tail after
packet processing is complete.

With this patch I can run XDP drop programs @ 14+Mpps and XDP_TX
programs are at ~13.5Mpps.

Signed-off-by: John Fastabend <john.r.fastabend@...el.com>
Tested-by: Andrew Bowers <andrewx.bowers@...el.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 28 ++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cb5be7de2c91..3d7b09100945 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2283,6 +2283,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
+	bool xdp_xmit = false;
 
 	while (likely(total_rx_packets < budget)) {
 		union ixgbe_adv_rx_desc *rx_desc;
@@ -2322,10 +2323,12 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBE_XDP_TX)
+			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
+				xdp_xmit = true;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
-			else
+			} else {
 				rx_buffer->pagecnt_bias++;
+			}
 			total_rx_packets++;
 			total_rx_bytes += size;
 		} else if (skb) {
@@ -2393,6 +2396,16 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
+	if (xdp_xmit) {
+		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.
+		 */
+		wmb();
+		writel(ring->next_to_use, ring->tail);
+	}
+
 	u64_stats_update_begin(&rx_ring->syncp);
 	rx_ring->stats.packets += total_rx_packets;
 	rx_ring->stats.bytes += total_rx_bytes;
@@ -8238,14 +8251,8 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 	tx_desc->read.olinfo_status =
 		cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);
 
-	/* Force memory writes to complete before letting h/w know there
-	 * are new descriptors to fetch.  (Only applicable for weak-ordered
-	 * memory model archs, such as IA-64).
-	 *
-	 * We also need this memory barrier to make certain all of the
-	 * status bits have been updated before next_to_watch is written.
-	 */
-	wmb();
+	/* Avoid any potential race with xdp_xmit and cleanup */
+	smp_wmb();
 
 	/* set next_to_watch value indicating a packet is present */
 	i++;
@@ -8255,7 +8262,6 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 	tx_buffer->next_to_watch = tx_desc;
 	ring->next_to_use = i;
 
-	writel(i, ring->tail);
 	return IXGBE_XDP_TX;
 }
 
-- 
2.12.2