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) {
next prev 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.