| 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
| ||
|
Message-Id: <1507103667-6084-1-git-send-email-horms+renesas@verge.net.au>
Date: Wed, 4 Oct 2017 09:54:27 +0200
From: Simon Horman <horms+renesas@...ge.net.au>
To: David Miller <davem@...emloft.net>,
Sergei Shtylyov <sergei.shtylyov@...entembedded.com>
Cc: Magnus Damm <magnus.damm@...il.com>, netdev@...r.kernel.org,
linux-renesas-soc@...r.kernel.org,
Simon Horman <horms+renesas@...ge.net.au>
Subject: [PATCH v2 net-next] ravb: RX checksum offload
Add support for RX checksum offload. This is enabled by default and
may be disabled and re-enabled using ethtool:
# ethtool -K eth0 rx off
# ethtool -K eth0 rx on
The RAVB provides a simple checksumming scheme which appears to be
completely compatible with CHECKSUM_COMPLETE: sum of all packet data after
the L2 header is appended to packet data; this may be trivially read by the
driver and used to update the skb accordingly.
In terms of performance throughput is close to gigabit line-rate both with
and without RX checksum offload enabled. Perf output, however, appears to
indicate that significantly less time is spent in do_csum(). This is as
expected.
Test results with RX checksum offload enabled:
# /usr/bin/perf_3.16 record -o /run/perf.data -a netperf -t TCP_MAERTS -H 10.4.3.162
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.4.3.162 () port 0 AF_INET : demo
enable_enobufs failed: getprotobyname
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 937.54
Summary of output of perf report:
18.28% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore
10.34% ksoftirqd/0 [kernel.kallsyms] [k] __pi_memcpy
9.83% ksoftirqd/0 [kernel.kallsyms] [k] ravb_poll
7.89% ksoftirqd/0 [kernel.kallsyms] [k] skb_put
4.01% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive
3.37% netperf [kernel.kallsyms] [k] __arch_copy_to_user
3.17% swapper [kernel.kallsyms] [k] arch_cpu_idle
2.55% swapper [kernel.kallsyms] [k] tick_nohz_idle_enter
2.04% ksoftirqd/0 [kernel.kallsyms] [k] __pi___inval_dcache_area
2.03% swapper [kernel.kallsyms] [k] _raw_spin_unlock_irq
1.96% ksoftirqd/0 [kernel.kallsyms] [k] __netdev_alloc_skb
1.59% ksoftirqd/0 [kernel.kallsyms] [k] __slab_alloc.isra.83
Test results without RX checksum offload enabled:
# /usr/bin/perf_3.16 record -o /run/perf.data -a netperf -t TCP_MAERTS -H 10.4.3.162
MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.4.3.162 () port 0 AF_INET : demo
enable_enobufs failed: getprotobyname
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 940.20
Summary of output of perf report:
17.10% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore
10.99% ksoftirqd/0 [kernel.kallsyms] [k] __pi_memcpy
8.87% ksoftirqd/0 [kernel.kallsyms] [k] ravb_poll
8.16% ksoftirqd/0 [kernel.kallsyms] [k] skb_put
7.42% ksoftirqd/0 [kernel.kallsyms] [k] do_csum
3.91% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive
2.31% swapper [kernel.kallsyms] [k] arch_cpu_idle
2.16% ksoftirqd/0 [kernel.kallsyms] [k] __pi___inval_dcache_area
2.14% ksoftirqd/0 [kernel.kallsyms] [k] __netdev_alloc_skb
1.93% netperf [kernel.kallsyms] [k] __arch_copy_to_user
1.79% swapper [kernel.kallsyms] [k] tick_nohz_idle_enter
1.63% ksoftirqd/0 [kernel.kallsyms] [k] __slab_alloc.isra.83
Above results collected on an R-Car Gen 3 Salvator-X/r8a7796 ES1.0.
Also tested on a R-Car Gen 3 Salvator-X/r8a7795 ES1.0.
By inspection this also appears to be compatible with the ravb found
on R-Car Gen 2 SoCs, however, this patch is currently untested on such
hardware.
Signed-off-by: Simon Horman <horms+renesas@...ge.net.au>
---
v2
Address review of v1 by Sergei Shtylyov
* set features rather than oring them with (zero) existing values:
* Set/unset using a single call to ravb_modify()
---
drivers/net/ethernet/renesas/ravb_main.c | 55 +++++++++++++++++++++++++++++++-
1 file changed, 54 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index fdf30bfa403b..a8822a756e08 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -403,8 +403,9 @@ static void ravb_emac_init(struct net_device *ndev)
/* Receive frame limit set register */
ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
- /* PAUSE prohibition */
+ /* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) |
+ (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
ECMR_TE | ECMR_RE, ECMR);
ravb_set_rate(ndev);
@@ -520,6 +521,19 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)
}
}
+static void ravb_rx_csum(struct sk_buff *skb)
+{
+ u8 *hw_csum;
+
+ /* The hardware checksum is 2 bytes appended to packet data */
+ if (unlikely(skb->len < 2))
+ return;
+ hw_csum = skb_tail_pointer(skb) - 2;
+ skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb_trim(skb, skb->len - 2);
+}
+
/* Packet receive function for Ethernet AVB */
static bool ravb_rx(struct net_device *ndev, int *quota, int q)
{
@@ -587,8 +601,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q)
ts.tv_nsec = le32_to_cpu(desc->ts_n);
shhwtstamps->hwtstamp = timespec64_to_ktime(ts);
}
+
skb_put(skb, pkt_len);
skb->protocol = eth_type_trans(skb, ndev);
+ if (ndev->features & NETIF_F_RXCSUM)
+ ravb_rx_csum(skb);
napi_gro_receive(&priv->napi[q], skb);
stats->rx_packets++;
stats->rx_bytes += pkt_len;
@@ -1842,6 +1859,38 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
return phy_mii_ioctl(phydev, req, cmd);
}
+static void ravb_set_rx_csum(struct net_device *ndev, bool enable)
+{
+ struct ravb_private *priv = netdev_priv(ndev);
+ unsigned long flags;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ /* Disable TX and RX */
+ ravb_rcv_snd_disable(ndev);
+
+ /* Modify RX Checksum setting */
+ ravb_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0);
+
+ /* Enable TX and RX */
+ ravb_rcv_snd_enable(ndev);
+
+ spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int ravb_set_features(struct net_device *ndev,
+ netdev_features_t features)
+{
+ netdev_features_t changed = ndev->features ^ features;
+
+ if (changed & NETIF_F_RXCSUM)
+ ravb_set_rx_csum(ndev, features & NETIF_F_RXCSUM);
+
+ ndev->features = features;
+
+ return 0;
+}
+
static const struct net_device_ops ravb_netdev_ops = {
.ndo_open = ravb_open,
.ndo_stop = ravb_close,
@@ -1853,6 +1902,7 @@ static const struct net_device_ops ravb_netdev_ops = {
.ndo_do_ioctl = ravb_do_ioctl,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_features = ravb_set_features,
};
/* MDIO bus init function */
@@ -2004,6 +2054,9 @@ static int ravb_probe(struct platform_device *pdev)
if (!ndev)
return -ENOMEM;
+ ndev->features = NETIF_F_RXCSUM;
+ ndev->hw_features = NETIF_F_RXCSUM;
+
pm_runtime_enable(&pdev->dev);
pm_runtime_get_sync(&pdev->dev);
--
2.1.4
Powered by blists - more mailing lists