From: Julian Wiedmann <jwi@linux.vnet.ibm.com>
To: David Miller <davem@davemloft.net>
Cc: <netdev@vger.kernel.org>, <linux-s390@vger.kernel.org>,
Martin Schwidefsky <schwidefsky@de.ibm.com>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Stefan Raspl <raspl@linux.vnet.ibm.com>,
Ursula Braun <ubraun@linux.vnet.ibm.com>,
Julian Wiedmann <jwi@linux.vnet.ibm.com>
Subject: [PATCH net 2/3] s390/qeth: fix GSO throughput regression
Date: Fri, 1 Dec 2017 10:14:50 +0100 [thread overview]
Message-ID: <20171201091451.52270-3-jwi@linux.vnet.ibm.com> (raw)
In-Reply-To: <20171201091451.52270-1-jwi@linux.vnet.ibm.com>
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>
---
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(+)
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 9cd569ef43ec..15015a24f8ad 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -987,6 +987,9 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
int qeth_set_features(struct net_device *, netdev_features_t);
void qeth_recover_features(struct net_device *dev);
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);
int qeth_vm_request_mac(struct qeth_card *card);
int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 49b9efeba1bd..d9b0e07d4fa7 100644
--- 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>
@@ -6438,6 +6443,32 @@ netdev_features_t qeth_fix_features(struct net_device *dev,
}
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;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index d2537c09126d..85162712d207 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -960,6 +960,7 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
.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_do_ioctl,
@@ -1010,6 +1011,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
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;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index e79936b50698..46a841258fc8 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2918,6 +2918,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
.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_do_ioctl,
@@ -2958,6 +2959,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
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) {
--
2.13.5
next prev parent reply other threads:[~2017-12-01 9:15 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-01 9:14 [PATCH net 0/3] s390/qeth: fixes 2017-12-01 Julian Wiedmann
2017-12-01 9:14 ` [PATCH net 1/3] s390/qeth: fix thinko in IPv4 multicast address tracking Julian Wiedmann
2017-12-01 9:14 ` Julian Wiedmann [this message]
2017-12-01 9:14 ` [PATCH net 3/3] s390/qeth: build max size GSO skbs on L2 devices Julian Wiedmann
2017-12-03 2:35 ` [PATCH net 0/3] s390/qeth: fixes 2017-12-01 David Miller
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=20171201091451.52270-3-jwi@linux.vnet.ibm.com \
--to=jwi@linux.vnet.ibm.com \
--cc=davem@davemloft.net \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-s390@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=raspl@linux.vnet.ibm.com \
--cc=schwidefsky@de.ibm.com \
--cc=ubraun@linux.vnet.ibm.com \
/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;
as well as URLs for NNTP newsgroup(s).