mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Nils Hoppmann <niho@de.ibm.com>,
	Julian Wiedmann <jwi@linux.vnet.ibm.com>,
	"David S. Miller" <davem@davemloft.net>
Subject: [PATCH 4.9 13/27] s390/qeth: fix GSO throughput regression
Date: Fri, 15 Dec 2017 10:51:56 +0100	[thread overview]
Message-ID: <20171215092258.590012381@linuxfoundation.org> (raw)
In-Reply-To: <20171215092257.674368056@linuxfoundation.org>

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Julian Wiedmann <jwi@linux.vnet.ibm.com>


[ Upstream commit 6d69b1f1eb7a2edf8a3547f361c61f2538e054bb ]

Using GSO with small MTUs currently results in a substantial throughput
regression - which is caused by how qeth needs to map non-linear skbs
into its IO buffer elements:
compared to a linear skb, each GSO-segmented skb effectively consumes
twice as many buffer elements (ie two instead of one) due to the
additional header-only part. This causes the Output Queue to be
congested with low-utilized IO buffers.

Fix this as follows:
If the MSS is low enough so that a non-SG GSO segmentation produces
order-0 skbs (currently ~3500 byte), opt out from NETIF_F_SG. This is
where we anticipate the biggest savings, since an SG-enabled
GSO segmentation produces skbs that always consume at least two
buffer elements.

Larger MSS values continue to get a SG-enabled GSO segmentation, since
1) the relative overhead of the additional header-only buffer element
becomes less noticeable, and
2) the linearization overhead increases.

With the throughput regression fixed, re-enable NETIF_F_SG by default to
reap the significant CPU savings of GSO.

Fixes: 5722963a8e83 ("qeth: do not turn on SG per default")
Reported-by: Nils Hoppmann <niho@de.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/s390/net/qeth_core.h      |    3 +++
 drivers/s390/net/qeth_core_main.c |   31 +++++++++++++++++++++++++++++++
 drivers/s390/net/qeth_l2_main.c   |    2 ++
 drivers/s390/net/qeth_l3_main.c   |    2 ++
 4 files changed, 38 insertions(+)

--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1004,6 +1004,9 @@ struct qeth_cmd_buffer *qeth_get_setassp
 int qeth_set_features(struct net_device *, netdev_features_t);
 int qeth_recover_features(struct net_device *);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -19,6 +19,11 @@
 #include <linux/mii.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <linux/netdev_features.h>
+#include <linux/skbuff.h>
+
 #include <net/iucv/af_iucv.h>
 #include <net/dsfield.h>
 
@@ -6240,6 +6245,32 @@ netdev_features_t qeth_fix_features(stru
 }
 EXPORT_SYMBOL_GPL(qeth_fix_features);
 
+netdev_features_t qeth_features_check(struct sk_buff *skb,
+				      struct net_device *dev,
+				      netdev_features_t features)
+{
+	/* GSO segmentation builds skbs with
+	 *	a (small) linear part for the headers, and
+	 *	page frags for the data.
+	 * Compared to a linear skb, the header-only part consumes an
+	 * additional buffer element. This reduces buffer utilization, and
+	 * hurts throughput. So compress small segments into one element.
+	 */
+	if (netif_needs_gso(skb, features)) {
+		/* match skb_segment(): */
+		unsigned int doffset = skb->data - skb_mac_header(skb);
+		unsigned int hsize = skb_shinfo(skb)->gso_size;
+		unsigned int hroom = skb_headroom(skb);
+
+		/* linearize only if resulting skb allocations are order-0: */
+		if (SKB_DATA_ALIGN(hroom + doffset + hsize) <= SKB_MAX_HEAD(0))
+			features &= ~NETIF_F_SG;
+	}
+
+	return vlan_features_check(skb, features);
+}
+EXPORT_SYMBOL_GPL(qeth_features_check);
+
 static int __init qeth_core_init(void)
 {
 	int rc;
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1084,6 +1084,7 @@ static const struct net_device_ops qeth_
 	.ndo_stop		= qeth_l2_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l2_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl	   	= qeth_l2_do_ioctl,
@@ -1128,6 +1129,7 @@ static int qeth_l2_setup_netdev(struct q
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->hw_features = NETIF_F_SG;
 		card->dev->vlan_features = NETIF_F_SG;
+		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
 		if (qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) {
 			card->dev->hw_features |= NETIF_F_IP_CSUM;
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -3066,6 +3066,7 @@ static const struct net_device_ops qeth_
 	.ndo_stop		= qeth_l3_stop,
 	.ndo_get_stats		= qeth_get_stats,
 	.ndo_start_xmit		= qeth_l3_hard_start_xmit,
+	.ndo_features_check	= qeth_features_check,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_multicast_list,
 	.ndo_do_ioctl		= qeth_l3_do_ioctl,
@@ -3122,6 +3123,7 @@ static int qeth_l3_setup_netdev(struct q
 				card->dev->vlan_features = NETIF_F_SG |
 					NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 					NETIF_F_TSO;
+				card->dev->features |= NETIF_F_SG;
 			}
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {

  parent reply	other threads:[~2017-12-15 10:17 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-15  9:51 [PATCH 4.9 00/27] 4.9.70-stable review Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 02/27] s390/qeth: fix early exit from error path Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 03/27] tipc: fix memory leak in tipc_accept_from_sock() Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 05/27] sit: update frag_off info Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 06/27] packet: fix crash in fanout_demux_rollover() Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 07/27] net/packet: fix a race in packet_bind() and packet_notifier() Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 10/27] stmmac: reset last TSO segment size after device open Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 12/27] s390/qeth: build max size GSO skbs on L2 devices Greg Kroah-Hartman
2017-12-15  9:51 ` Greg Kroah-Hartman [this message]
2017-12-15  9:51 ` [PATCH 4.9 14/27] s390/qeth: fix thinko in IPv4 multicast address tracking Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 15/27] tipc: call tipc_rcv() only if bearer is up in tipc_udp_recv() Greg Kroah-Hartman
2017-12-15  9:51 ` [PATCH 4.9 16/27] Fix handling of verdicts after NF_QUEUE Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 17/27] ipmi: Stop timers before cleaning up the module Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 18/27] s390: always save and restore all registers on context switch Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 19/27] usb: gadget: ffs: Forbid usb_ep_alloc_request from sleeping Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 20/27] fix kcm_clone() Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 21/27] KVM: arm/arm64: vgic-its: Preserve the revious read from the pending table Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 22/27] powerpc/64: Fix checksum folding in csum_tcpudp_nofold and ip_fast_csum_nofold Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 23/27] kbuild: do not call cc-option before KBUILD_CFLAGS initialization Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 24/27] ipvlan: fix ipv6 outbound device Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 25/27] audit: ensure that audit=1 actually enables audit for PID 1 Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 26/27] md: free unused memory after bitmap resize Greg Kroah-Hartman
2017-12-15  9:52 ` [PATCH 4.9 27/27] RDMA/cxgb4: Annotate r2 and stag as __be32 Greg Kroah-Hartman
2017-12-15 17:40 ` [PATCH 4.9 00/27] 4.9.70-stable review Guenter Roeck
2017-12-15 21:12 ` Shuah Khan
2017-12-16  5:55 ` Naresh Kamboju

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=20171215092258.590012381@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=davem@davemloft.net \
    --cc=jwi@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=niho@de.ibm.com \
    --cc=stable@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

Powered by JetHome