* Re: [PATCH] team: add rescheduling jiffy delay on !rtnl_trylock
From: Tejun Heo @ 2014-10-05 16:11 UTC (permalink / raw)
To: Paul E. McKenney; +Cc: Joe Lawrence, netdev, Jiri Pirko
In-Reply-To: <20141005140855.GO5015@linux.vnet.ibm.com>
Hello, Paul, Joe.
On Sun, Oct 05, 2014 at 07:08:55AM -0700, Paul E. McKenney wrote:
> > I wasn't sure if cond_resched_rcu_qs will be backported, so how should
> > -stable handle this condition?
>
> If it is needed to backport a fix, it can of course be backported.
> The various -stable maintainers also have the option of avoiding
> the need for a backport by expanding it inline. I am happy to let
> them choose. ;-)
Let's go for separate cond_resched + rcu_qs calls first and then apply
a separate patch to use cond_resched_rcu_qs() so that the first one
can be marked for -stable.
Thanks.
--
tejun
^ permalink raw reply
* [PATCH 15/16] 9p/trans_virtio: enable VQs early
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel
Cc: Eric Van Hensbergen, Ron Minnich, Latchesar Ionkov,
David S. Miller, v9fs-developer, netdev
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
virtio spec requires drivers to set DRIVER_OK before using VQs.
This is set automatically after probe returns, but virtio 9p device
adds self to channel list within probe, at which point VQ can be
used in violation of the spec.
To fix, call virtio_early_enable_vqs before using VQs.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
net/9p/trans_virtio.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 6940d8f..0e8bbb3 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -575,6 +575,8 @@ static int p9_virtio_probe(struct virtio_device *vdev)
/* Ceiling limit to avoid denial of service attacks */
chan->p9_max_pages = nr_free_buffer_pages()/4;
+ virtio_early_enable_vqs(vdev);
+
mutex_lock(&virtio_9p_lock);
list_add_tail(&chan->chan_list, &virtio_chan_list);
mutex_unlock(&virtio_9p_lock);
--
MST
^ permalink raw reply related
* [PATCH 12/16] virtio_net: enable VQs early
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel; +Cc: Rusty Russell, virtualization, netdev
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
virtio spec requires drivers to set DRIVER_OK before using VQs.
This is set automatically after probe returns, virtio net violated this
rule by using receive VQs within probe.
To fix, call virtio_early_enable_vqs before using VQs.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/virtio_net.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4c8c314..7afc990 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1792,6 +1792,8 @@ static int virtnet_probe(struct virtio_device *vdev)
goto free_vqs;
}
+ virtio_early_enable_vqs(vdev);
+
/* Last of all, set up some receive buffers. */
for (i = 0; i < vi->curr_queue_pairs; i++) {
try_fill_recv(&vi->rq[i], GFP_KERNEL);
--
MST
^ permalink raw reply related
* [PATCH 11/16] virtio_net: minor cleanup
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev, virtualization
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
goto done;
done:
return;
is ugly, it was put there to make diff review easier.
replace by open-coded return.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/virtio_net.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d80fef4..4c8c314 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1403,7 +1403,7 @@ static void virtnet_config_changed_work(struct work_struct *work)
if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS,
struct virtio_net_config, status, &v) < 0)
- goto done;
+ return;
if (v & VIRTIO_NET_S_ANNOUNCE) {
netdev_notify_peers(vi->dev);
@@ -1414,7 +1414,7 @@ static void virtnet_config_changed_work(struct work_struct *work)
v &= VIRTIO_NET_S_LINK_UP;
if (vi->status == v)
- goto done;
+ return;
vi->status = v;
@@ -1425,8 +1425,6 @@ static void virtnet_config_changed_work(struct work_struct *work)
netif_carrier_off(vi->dev);
netif_tx_stop_all_queues(vi->dev);
}
-done:
- return;
}
static void virtnet_config_changed(struct virtio_device *vdev)
--
MST
^ permalink raw reply related
* [PATCH 09/16] virtio-net: drop config_mutex
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev, virtualization
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
config_mutex served two purposes: prevent multiple concurrent config
change handlers, and synchronize access to config_enable flag.
Since commit dbf2576e37da0fcc7aacbfbb9fd5d3de7888a3c1
workqueue: make all workqueues non-reentrant
all workqueues are non-reentrant, and config_enable
is now gone.
Get rid of the unnecessary lock.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/virtio_net.c | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index fa17afa..d80fef4 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -132,9 +132,6 @@ struct virtnet_info {
/* Work struct for config space updates */
struct work_struct config_work;
- /* Lock for config space updates */
- struct mutex config_lock;
-
/* Does the affinity hint is set for virtqueues? */
bool affinity_hint_set;
@@ -1404,7 +1401,6 @@ static void virtnet_config_changed_work(struct work_struct *work)
container_of(work, struct virtnet_info, config_work);
u16 v;
- mutex_lock(&vi->config_lock);
if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS,
struct virtio_net_config, status, &v) < 0)
goto done;
@@ -1430,7 +1426,7 @@ static void virtnet_config_changed_work(struct work_struct *work)
netif_tx_stop_all_queues(vi->dev);
}
done:
- mutex_unlock(&vi->config_lock);
+ return;
}
static void virtnet_config_changed(struct virtio_device *vdev)
@@ -1751,7 +1747,6 @@ static int virtnet_probe(struct virtio_device *vdev)
u64_stats_init(&virtnet_stats->rx_syncp);
}
- mutex_init(&vi->config_lock);
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
/* If we can receive ANY GSO packets, we must allocate large ones. */
--
MST
^ permalink raw reply related
* [PATCH 08/16] virtio_net: drop config_enable
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel; +Cc: Rusty Russell, virtualization, netdev
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
Now that virtio core ensures config changes don't arrive during probing,
drop config_enable flag in virtio net.
On removal, flush is now sufficient to guarantee that no change work is
queued.
This help simplify the driver, and will allow setting DRIVER_OK earlier
without losing config change notifications.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/virtio_net.c | 23 ++---------------------
1 file changed, 2 insertions(+), 21 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 59caa06..fa17afa 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -123,9 +123,6 @@ struct virtnet_info {
/* Host can handle any s/g split between our header and packet data */
bool any_header_sg;
- /* enable config space updates */
- bool config_enable;
-
/* Active statistics */
struct virtnet_stats __percpu *stats;
@@ -1408,9 +1405,6 @@ static void virtnet_config_changed_work(struct work_struct *work)
u16 v;
mutex_lock(&vi->config_lock);
- if (!vi->config_enable)
- goto done;
-
if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS,
struct virtio_net_config, status, &v) < 0)
goto done;
@@ -1758,7 +1752,6 @@ static int virtnet_probe(struct virtio_device *vdev)
}
mutex_init(&vi->config_lock);
- vi->config_enable = true;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
/* If we can receive ANY GSO packets, we must allocate large ones. */
@@ -1876,16 +1869,12 @@ static void virtnet_remove(struct virtio_device *vdev)
unregister_hotcpu_notifier(&vi->nb);
/* Prevent config work handler from accessing the device. */
- mutex_lock(&vi->config_lock);
- vi->config_enable = false;
- mutex_unlock(&vi->config_lock);
+ flush_work(&vi->config_work);
unregister_netdev(vi->dev);
remove_vq_common(vi);
- flush_work(&vi->config_work);
-
free_percpu(vi->stats);
free_netdev(vi->dev);
}
@@ -1899,9 +1888,7 @@ static int virtnet_freeze(struct virtio_device *vdev)
unregister_hotcpu_notifier(&vi->nb);
/* Prevent config work handler from accessing the device */
- mutex_lock(&vi->config_lock);
- vi->config_enable = false;
- mutex_unlock(&vi->config_lock);
+ flush_work(&vi->config_work);
netif_device_detach(vi->dev);
cancel_delayed_work_sync(&vi->refill);
@@ -1916,8 +1903,6 @@ static int virtnet_freeze(struct virtio_device *vdev)
remove_vq_common(vi);
- flush_work(&vi->config_work);
-
return 0;
}
@@ -1941,10 +1926,6 @@ static int virtnet_restore(struct virtio_device *vdev)
netif_device_attach(vi->dev);
- mutex_lock(&vi->config_lock);
- vi->config_enable = true;
- mutex_unlock(&vi->config_lock);
-
rtnl_lock();
virtnet_set_queues(vi, vi->curr_queue_pairs);
rtnl_unlock();
--
MST
^ permalink raw reply related
* [PATCH 16/16] virtio_net: fix use after free on allocation failure
From: Michael S. Tsirkin @ 2014-10-05 16:07 UTC (permalink / raw)
To: linux-kernel; +Cc: Rusty Russell, virtualization, netdev
In-Reply-To: <1412525038-15871-1-git-send-email-mst@redhat.com>
In the extremely unlikely event that driver initialization fails after
RX buffers are added, virtio net frees RX buffers while VQs are
still active, potentially causing device to use a freed buffer.
To fix, reset device first - same as we do on device removal.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/net/virtio_net.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7afc990..85e6098 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1830,6 +1830,8 @@ static int virtnet_probe(struct virtio_device *vdev)
return 0;
free_recv_bufs:
+ vi->vdev->config->reset(vdev);
+
free_receive_bufs(vi);
unregister_netdev(dev);
free_vqs:
--
MST
^ permalink raw reply related
* Re: [PATCH net-next 00/14] net/mlx4_en: Optimizations to TX flow
From: Eric Dumazet @ 2014-10-05 15:50 UTC (permalink / raw)
To: Amir Vadai
Cc: David S. Miller, Eric Dumazet, netdev, Yevgeny Petrilin,
Or Gerlitz, Ido Shamay
In-Reply-To: <54312F50.2060608@mellanox.com>
On Sun, 2014-10-05 at 14:45 +0300, Amir Vadai wrote:
> On 10/5/2014 12:35 PM, Amir Vadai wrote:
> > I am sending this patchset now since the merge window is near and don't want to
> > miss it.
>
> A small clarification, since I didn't explain myself precisely enough:
> This patchset is not a WIP and ready for merge. The open issues
> aren't directly related to the series and will be addressed in
> incremental manner.
+2
Thanks Amir for this hard work.
Note that now the validate calls (GSO segmentation) is performed outside
of qdisc or device lock ( 55a93b3ea780 qdisc: validate skb without
holding lock) , its very easy to add a dev->gso_min_segs
I already have a patch for this, I am sending it right now.
Thanks !
^ permalink raw reply
* [PATCH net-next] ipv4: igmp: fix v3 general query drop monitor false positive
From: Daniel Borkmann @ 2014-10-05 15:27 UTC (permalink / raw)
To: davem; +Cc: edumazet, netdev
In case we find a general query with non-zero number of sources, we
are dropping the skb as it's malformed.
RFC3376, section 4.1.8. Number of Sources (N):
This number is zero in a General Query or a Group-Specific Query,
and non-zero in a Group-and-Source-Specific Query.
Therefore, reflect that by using kfree_skb() instead of consume_skb().
Fixes: d679c5324d9a ("igmp: avoid drop_monitor false positives")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
---
[ net-next as it's not really urgent. ]
net/ipv4/igmp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 4146153..fb70e3e 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -931,7 +931,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
in_dev->mr_qrv = ih3->qrv;
if (!group) { /* general query */
if (ih3->nsrcs)
- return false; /* no sources allowed */
+ return true; /* no sources allowed */
igmp_gq_start_timer(in_dev);
return false;
}
--
1.7.11.7
^ permalink raw reply related
* Re: [PATCH] team: add rescheduling jiffy delay on !rtnl_trylock
From: Paul E. McKenney @ 2014-10-05 14:08 UTC (permalink / raw)
To: Joe Lawrence; +Cc: Tejun Heo, netdev, Jiri Pirko
In-Reply-To: <54313F34.8090801@stratus.com>
On Sun, Oct 05, 2014 at 08:53:08AM -0400, Joe Lawrence wrote:
> On 10/04/2014 10:13 PM, Tejun Heo wrote:
> > Hello,
> >
> > On Sat, Oct 04, 2014 at 01:37:32AM -0700, Paul E. McKenney wrote:
> >> FWIW, there is a cond_resched_rcu_qs() that should be going into the next
> >> merge window that could be used in place of the above two lines. This is
> >> commit bde6c3aa9930 in -tip.
> >
> > That sounds even better.
> >
> > Joe, can you please send a patch with proper SOB and description?
> >
> > Thanks.
>
> New patch tested and posted on lkml w/everyone CC'd.
>
> I wasn't sure if cond_resched_rcu_qs will be backported, so how should
> -stable handle this condition?
If it is needed to backport a fix, it can of course be backported.
The various -stable maintainers also have the option of avoiding
the need for a backport by expanding it inline. I am happy to let
them choose. ;-)
Thanx, Paul
^ permalink raw reply
* Re: [PATCH] net: Add ndo_gso_check
From: Or Gerlitz @ 2014-10-05 14:04 UTC (permalink / raw)
To: Tom Herbert
Cc: Alexander Duyck, John Fastabend, Jeff Kirsher, David Miller,
Linux Netdev List, Thomas Graf, Pravin Shelar, Andy Zhou
In-Reply-To: <CA+mtBx9=+fGjwJCKpTW5EifmavC6VGnbuJdkc5tqzeEHz+5twA@mail.gmail.com>
On Thu, Oct 2, 2014 at 2:06 AM, Tom Herbert <therbert@google.com> wrote:
> On Wed, Oct 1, 2014 at 1:58 PM, Or Gerlitz <gerlitz.or@gmail.com> wrote:
>> On Tue, Sep 30, 2014 at 6:34 PM, Tom Herbert <therbert@google.com> wrote:
>>> On Tue, Sep 30, 2014 at 7:30 AM, Or Gerlitz <gerlitz.or@gmail.com> wrote:
[...]
> Solution #4: apply this patch and implement the check functions as
> needed in those 4 or 5 drivers. If a device can only do VXLAN/NVGRE
> then I believe the check function is something like:
>
> bool mydev_gso_check(struct sk_buff *skb, struct net_device *dev)
> {
> if ((skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) &&
> ((skb->inner_protocol_type != ENCAP_TYPE_ETHER ||
> skb->protocol != htons(ETH_P_TEB) ||
> skb_inner_mac_header(skb) - skb_transport_header(skb) != 12)
> return false;
>
> return true;
> }
Yep, such helper can can be basically made to work and let the 4-5
drivers that can
do GSO offloading for vxlan but not for any FOU/GUE packets signal
that to the stack.
Re the 12 constant, you were referring to the udp+vxlan headers? it's 8+8
Also, we need a way for drivers that can support VXLAN or NVGRE but
not concurrently
on the same port @ the same time to only let vxlan packet to pass
successfully through the helper.
There was that coloring scheme I suggested, but you didn't like it...
>>> Would any other driver maintainers like to chime in on this?
>> Alex? John?
Or.
^ permalink raw reply
* Re: [PATCH net-next 14/14] net/mlx4_en: Use the new tx_copybreak to set inline threshold
From: Sergei Shtylyov @ 2014-10-05 13:03 UTC (permalink / raw)
To: Amir Vadai, David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay
In-Reply-To: <1412501722-25092-15-git-send-email-amirv@mellanox.com>
Hello.
On 10/5/2014 1:35 PM, Amir Vadai wrote:
> From: Eric Dumazet <edumazet@google.com>
> Instead of setting inline threshold using module parameter only on
> driver load, use set_tunable() to set it dynamically.
> No need to store the threshold per ring, using instead the netdev global
> priv->prof->inline_thold
> Initial value still is set using the module parameter, therefore
> backward compatability is kept.
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Amir Vadai <amirv@mellanox.com>
> ---
> drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 44 +++++++++++++++++++++++++
> drivers/net/ethernet/mellanox/mlx4/en_tx.c | 1 -
> drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 -
> 3 files changed, 44 insertions(+), 2 deletions(-)
> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
> index 42c9f8b..ae83da9 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
[...]
> @@ -1297,6 +1339,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
> .get_ts_info = mlx4_en_get_ts_info,
> .set_priv_flags = mlx4_en_set_priv_flags,
> .get_priv_flags = mlx4_en_get_priv_flags,
> + .get_tunable = mlx4_en_get_tunable,
> + .set_tunable = mlx4_en_set_tunable,
If the above initializers aren't aligned with tabs, why should these two be?
WBR, Sergei
^ permalink raw reply
* Re: [PATCH] team: add rescheduling jiffy delay on !rtnl_trylock
From: Joe Lawrence @ 2014-10-05 12:53 UTC (permalink / raw)
To: Tejun Heo, Paul E. McKenney; +Cc: netdev, Jiri Pirko
In-Reply-To: <20141005021325.GB8549@htj.dyndns.org>
On 10/04/2014 10:13 PM, Tejun Heo wrote:
> Hello,
>
> On Sat, Oct 04, 2014 at 01:37:32AM -0700, Paul E. McKenney wrote:
>> FWIW, there is a cond_resched_rcu_qs() that should be going into the next
>> merge window that could be used in place of the above two lines. This is
>> commit bde6c3aa9930 in -tip.
>
> That sounds even better.
>
> Joe, can you please send a patch with proper SOB and description?
>
> Thanks.
New patch tested and posted on lkml w/everyone CC'd.
I wasn't sure if cond_resched_rcu_qs will be backported, so how should
-stable handle this condition?
Regards,
-- Joe
^ permalink raw reply
* Re: [PATCH net-next 00/14] net/mlx4_en: Optimizations to TX flow
From: Amir Vadai @ 2014-10-05 11:45 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
On 10/5/2014 12:35 PM, Amir Vadai wrote:
> I am sending this patchset now since the merge window is near and don't want to
> miss it.
A small clarification, since I didn't explain myself precisely enough:
This patchset is not a WIP and ready for merge. The open issues
aren't directly related to the series and will be addressed in
incremental manner.
Amir
^ permalink raw reply
* Re: Off Topic: Request for Old Hardware
From: Maciej W. Rozycki @ 2014-10-05 11:23 UTC (permalink / raw)
To: whiteheadm; +Cc: netdev
In-Reply-To: <CAP8WD_ZvHC16mM-Ra2nFcUnyFQmwYLUN=YGHMDwNckZTynsM_g@mail.gmail.com>
On Tue, 23 Sep 2014, tedheadster wrote:
> If you have an ancient dual-processor 80486 system, please email me
> off-list. Yes, a few of these did indeed exist.
The 82489DX discrete APIC was originally designed for 80486 SMP systems
and Intel's Multiprocessor Specification explicitly provided for such
configurations. Unfortunately I was never able to track down such a
system to experiment with it and possibly make it work with Linux. Good
luck with finding one these days!
Maciej
^ permalink raw reply
* Re: bridge: Respect call-iptables sysctls everywhere
From: Herbert Xu @ 2014-10-05 10:18 UTC (permalink / raw)
To: Florian Westphal
Cc: netfilter-devel, bsd, stephen, netdev, eric.dumazet, davidn,
David S. Miller
In-Reply-To: <20141005091343.GA11246@breakpoint.cc>
On Sun, Oct 05, 2014 at 11:13:43AM +0200, Florian Westphal wrote:
> Herbert Xu <herbert@gondor.apana.org.au> wrote:
> > On Sat, Oct 04, 2014 at 08:06:47PM +0200, Florian Westphal wrote:
> > >
> > > Fair enough. We lose frag_max_size information from ipv4 defrag,
> >
> > While reviewing this code it occured to me that we have a serious
> > bug in that call-iptables sysctls aren't even respected in FORWARD
> > and POST_ROUTING. Here is a patch that fixes this.
>
> Upcalls to iptables in FORWARD/POSTROUTING depend on skb->nf_bridge
> being set up, which only happens when call-iptables=1.
Good point. So we can discard this patch.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* [PATCH net-next 14/14] net/mlx4_en: Use the new tx_copybreak to set inline threshold
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Instead of setting inline threshold using module parameter only on
driver load, use set_tunable() to set it dynamically.
No need to store the threshold per ring, using instead the netdev global
priv->prof->inline_thold
Initial value still is set using the module parameter, therefore
backward compatability is kept.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 44 +++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 1 -
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 1 -
3 files changed, 44 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 42c9f8b..ae83da9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1267,6 +1267,48 @@ static u32 mlx4_en_get_priv_flags(struct net_device *dev)
return priv->pflags;
}
+static int mlx4_en_get_tunable(struct net_device *dev,
+ const struct ethtool_tunable *tuna,
+ void *data)
+{
+ const struct mlx4_en_priv *priv = netdev_priv(dev);
+ int ret = 0;
+
+ switch (tuna->id) {
+ case ETHTOOL_TX_COPYBREAK:
+ *(u32 *)data = priv->prof->inline_thold;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static int mlx4_en_set_tunable(struct net_device *dev,
+ const struct ethtool_tunable *tuna,
+ const void *data)
+{
+ struct mlx4_en_priv *priv = netdev_priv(dev);
+ int val, ret = 0;
+
+ switch (tuna->id) {
+ case ETHTOOL_TX_COPYBREAK:
+ val = *(u32 *)data;
+ if (val < MIN_PKT_LEN || val > MAX_INLINE)
+ ret = -EINVAL;
+ else
+ priv->prof->inline_thold = val;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
const struct ethtool_ops mlx4_en_ethtool_ops = {
.get_drvinfo = mlx4_en_get_drvinfo,
@@ -1297,6 +1339,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
.get_ts_info = mlx4_en_get_ts_info,
.set_priv_flags = mlx4_en_set_priv_flags,
.get_priv_flags = mlx4_en_get_priv_flags,
+ .get_tunable = mlx4_en_get_tunable,
+ .set_tunable = mlx4_en_set_tunable,
};
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f0080c5..92a7cf4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -66,7 +66,6 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->size = size;
ring->size_mask = size - 1;
ring->stride = stride;
- ring->inline_thold = priv->prof->inline_thold;
tmp = size * sizeof(struct mlx4_en_tx_info);
ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index a904030..8fef658 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -295,7 +295,6 @@ struct mlx4_en_tx_ring {
bool bf_alloced;
struct netdev_queue *tx_queue;
int hwtstamp_tx_type;
- int inline_thold;
} ____cacheline_aligned_in_smp;
struct mlx4_en_rx_desc {
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 12/14] net/mlx4_en: Enable the compiler to make is_inline() inlined
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Reorganize code to call is_inline() once, so compiler can inline it
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 67 +++++++++++++++++-------------
1 file changed, 38 insertions(+), 29 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 2c03b55..f0080c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -531,29 +531,32 @@ static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
return ring->buf + index * TXBB_SIZE;
}
+/* Decide if skb can be inlined in tx descriptor to avoid dma mapping
+ *
+ * It seems strange we do not simply use skb_copy_bits().
+ * This would allow to inline all skbs iff skb->len <= inline_thold
+ *
+ * Note that caller already checked skb was not a gso packet
+ */
static bool is_inline(int inline_thold, const struct sk_buff *skb,
const struct skb_shared_info *shinfo,
void **pfrag)
{
void *ptr;
- if (inline_thold && !skb_is_gso(skb) && skb->len <= inline_thold) {
- if (shinfo->nr_frags == 1) {
- ptr = skb_frag_address_safe(&shinfo->frags[0]);
- if (unlikely(!ptr))
- return 0;
-
- if (pfrag)
- *pfrag = ptr;
+ if (skb->len > inline_thold || !inline_thold)
+ return false;
- return 1;
- } else if (unlikely(shinfo->nr_frags))
- return 0;
- else
- return 1;
+ if (shinfo->nr_frags == 1) {
+ ptr = skb_frag_address_safe(&shinfo->frags[0]);
+ if (unlikely(!ptr))
+ return false;
+ *pfrag = ptr;
+ return true;
}
-
- return 0;
+ if (shinfo->nr_frags)
+ return false;
+ return true;
}
static int inline_size(const struct sk_buff *skb)
@@ -570,12 +573,15 @@ static int inline_size(const struct sk_buff *skb)
static int get_real_size(const struct sk_buff *skb,
const struct skb_shared_info *shinfo,
struct net_device *dev,
- int *lso_header_size)
+ int *lso_header_size,
+ bool *inline_ok,
+ void **pfrag)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
int real_size;
if (shinfo->gso_size) {
+ *inline_ok = false;
if (skb->encapsulation)
*lso_header_size = (skb_inner_transport_header(skb) - skb->data) + inner_tcp_hdrlen(skb);
else
@@ -595,10 +601,14 @@ static int get_real_size(const struct sk_buff *skb,
}
} else {
*lso_header_size = 0;
- if (!is_inline(priv->prof->inline_thold, skb, shinfo, NULL))
- real_size = CTRL_SIZE + (shinfo->nr_frags + 1) * DS_SIZE;
- else
+ *inline_ok = is_inline(priv->prof->inline_thold, skb,
+ shinfo, pfrag);
+
+ if (*inline_ok)
real_size = inline_size(skb);
+ else
+ real_size = CTRL_SIZE +
+ (shinfo->nr_frags + 1) * DS_SIZE;
}
return real_size;
@@ -694,9 +704,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
u16 vlan_tag = 0;
int i_frag;
int lso_header_size;
- void *fragptr;
+ void *fragptr = NULL;
bool bounce = false;
bool send_doorbell;
+ bool inline_ok;
u32 ring_cons;
if (!priv->port_up)
@@ -708,7 +719,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
/* fetch ring->cons far ahead before needing it to avoid stall */
ring_cons = ACCESS_ONCE(ring->cons);
- real_size = get_real_size(skb, shinfo, dev, &lso_header_size);
+ real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
+ &inline_ok, &fragptr);
if (unlikely(!real_size))
goto tx_drop;
@@ -781,15 +793,15 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
/* valid only for none inline segments */
tx_info->data_offset = (void *)data - (void *)tx_desc;
+ tx_info->inl = inline_ok;
+
tx_info->linear = (lso_header_size < skb_headlen(skb) &&
- !is_inline(ring->inline_thold, skb, shinfo, NULL)) ? 1 : 0;
+ !inline_ok) ? 1 : 0;
tx_info->nr_maps = shinfo->nr_frags + tx_info->linear;
data += tx_info->nr_maps - 1;
- if (is_inline(ring->inline_thold, skb, shinfo, &fragptr)) {
- tx_info->inl = 1;
- } else {
+ if (!tx_info->inl) {
dma_addr_t dma = 0;
u32 byte_count = 0;
@@ -827,7 +839,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
wmb();
data->byte_count = cpu_to_be32(byte_count);
}
- tx_info->inl = 0;
/* tx completion can avoid cache line miss for common cases */
tx_info->map0_dma = dma;
tx_info->map0_byte_count = byte_count;
@@ -899,11 +910,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes);
AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
- if (tx_info->inl) {
+ if (tx_info->inl)
build_inline_wqe(tx_desc, skb, shinfo, real_size, &vlan_tag,
tx_ind, fragptr);
- tx_info->inl = 1;
- }
if (skb->encapsulation) {
struct iphdr *ipv4 = (struct iphdr *)skb_inner_network_header(skb);
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 08/14] net/mlx4_en: mlx4_en_xmit() reads ring->cons once, and ahead of time to avoid stalls
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d9aaeb2..99875c8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -691,10 +691,17 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
void *fragptr;
bool bounce = false;
bool send_doorbell;
+ u32 ring_cons;
if (!priv->port_up)
goto tx_drop;
+ tx_ind = skb_get_queue_mapping(skb);
+ ring = priv->tx_ring[tx_ind];
+
+ /* fetch ring->cons far ahead before needing it to avoid stall */
+ ring_cons = ACCESS_ONCE(ring->cons);
+
real_size = get_real_size(skb, dev, &lso_header_size);
if (unlikely(!real_size))
goto tx_drop;
@@ -708,13 +715,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop;
}
- tx_ind = skb->queue_mapping;
- ring = priv->tx_ring[tx_ind];
if (vlan_tx_tag_present(skb))
vlan_tag = vlan_tx_tag_get(skb);
/* Check available TXBBs And 2K spare for prefetch */
- if (unlikely(((int)(ring->prod - ring->cons)) >
+ if (unlikely(((int)(ring->prod - ring_cons)) >
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
/* every full Tx ring stops queue */
netif_tx_stop_queue(ring->tx_queue);
@@ -728,7 +733,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
*/
wmb();
- if (unlikely(((int)(ring->prod - ring->cons)) <=
+ ring_cons = ACCESS_ONCE(ring->cons);
+ if (unlikely(((int)(ring->prod - ring_cons)) <=
ring->size - HEADROOM - MAX_DESC_TXBBS)) {
netif_tx_wake_queue(ring->tx_queue);
ring->wake_queue++;
@@ -741,7 +747,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
/* Track current inflight packets for performance analysis */
AVG_PERF_COUNTER(priv->pstats.inflight_avg,
- (u32) (ring->prod - ring->cons - 1));
+ (u32)(ring->prod - ring_cons - 1));
/* Packet is good - grab an index and transmit it */
index = ring->prod & ring->size_mask;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 10/14] net/mlx4_en: Use local var for skb_headlen(skb)
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Access skb_headlen() once in tx flow
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index aa05b09..e00841a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -612,6 +612,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
{
struct mlx4_wqe_inline_seg *inl = &tx_desc->inl;
int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl;
+ unsigned int hlen = skb_headlen(skb);
if (skb->len <= spc) {
if (likely(skb->len >= MIN_PKT_LEN)) {
@@ -621,19 +622,19 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
memset(((void *)(inl + 1)) + skb->len, 0,
MIN_PKT_LEN - skb->len);
}
- skb_copy_from_linear_data(skb, inl + 1, skb_headlen(skb));
+ skb_copy_from_linear_data(skb, inl + 1, hlen);
if (shinfo->nr_frags)
- memcpy(((void *)(inl + 1)) + skb_headlen(skb), fragptr,
+ memcpy(((void *)(inl + 1)) + hlen, fragptr,
skb_frag_size(&shinfo->frags[0]));
} else {
inl->byte_count = cpu_to_be32(1 << 31 | spc);
- if (skb_headlen(skb) <= spc) {
- skb_copy_from_linear_data(skb, inl + 1, skb_headlen(skb));
- if (skb_headlen(skb) < spc) {
- memcpy(((void *)(inl + 1)) + skb_headlen(skb),
- fragptr, spc - skb_headlen(skb));
- fragptr += spc - skb_headlen(skb);
+ if (hlen <= spc) {
+ skb_copy_from_linear_data(skb, inl + 1, hlen);
+ if (hlen < spc) {
+ memcpy(((void *)(inl + 1)) + hlen,
+ fragptr, spc - hlen);
+ fragptr += spc - hlen;
}
inl = (void *) (inl + 1) + spc;
memcpy(((void *)(inl + 1)), fragptr, skb->len - spc);
@@ -641,9 +642,9 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
skb_copy_from_linear_data(skb, inl + 1, spc);
inl = (void *) (inl + 1) + spc;
skb_copy_from_linear_data_offset(skb, spc, inl + 1,
- skb_headlen(skb) - spc);
+ hlen - spc);
if (shinfo->nr_frags)
- memcpy(((void *)(inl + 1)) + skb_headlen(skb) - spc,
+ memcpy(((void *)(inl + 1)) + hlen - spc,
fragptr,
skb_frag_size(&shinfo->frags[0]));
}
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 04/14] net/mlx4_en: tx_info allocated with kmalloc() instead of vmalloc()
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Try to allocate using kmalloc_node() first, only on failure use
vmalloc()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 322cda3..1447906 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -68,7 +68,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->inline_thold = priv->prof->inline_thold;
tmp = size * sizeof(struct mlx4_en_tx_info);
- ring->tx_info = vmalloc_node(tmp, node);
+ ring->tx_info = kmalloc_node(tmp, GFP_KERNEL | __GFP_NOWARN, node);
if (!ring->tx_info) {
ring->tx_info = vmalloc(tmp);
if (!ring->tx_info) {
@@ -151,7 +151,7 @@ err_bounce:
kfree(ring->bounce_buf);
ring->bounce_buf = NULL;
err_info:
- vfree(ring->tx_info);
+ kvfree(ring->tx_info);
ring->tx_info = NULL;
err_ring:
kfree(ring);
@@ -174,7 +174,7 @@ void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
mlx4_free_hwq_res(mdev->dev, &ring->wqres, ring->buf_size);
kfree(ring->bounce_buf);
ring->bounce_buf = NULL;
- vfree(ring->tx_info);
+ kvfree(ring->tx_info);
ring->tx_info = NULL;
kfree(ring);
*pring = NULL;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 11/14] net/mlx4_en: tx_info->ts_requested was not cleared
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Properly clear tx_info->ts_requested
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e00841a..2c03b55 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -837,6 +837,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
* For timestamping add flag to skb_shinfo and
* set flag for further reference
*/
+ tx_info->ts_requested = 0;
if (unlikely(ring->hwtstamp_tx_type == HWTSTAMP_TX_ON &&
shinfo->tx_flags & SKBTX_HW_TSTAMP)) {
shinfo->tx_flags |= SKBTX_IN_PROGRESS;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 05/14] net/mlx4_en: Avoid a cache line miss in TX completion for single frag skb's
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Add frag0_dma/frag0_byte_count into mlx4_en_tx_info to avoid a cache
line miss in TX completion for frames having one dma element. (We avoid
reading back the tx descriptor)
Note this could be extended to 2/3 dma elements later, as we have free
room in mlx4_en_tx_info
Also, mlx4_en_free_tx_desc() no longer accesses skb_shinfo(). We use a
new nr_maps fields in mlx4_en_tx_info to avoid 2 or 3 cache misses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 83 +++++++++++++++-------------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 +
2 files changed, 49 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1447906..edc4a88 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -259,38 +259,40 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
int index, u8 owner, u64 timestamp)
{
- struct mlx4_en_dev *mdev = priv->mdev;
struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
struct mlx4_wqe_data_seg *data = (void *) tx_desc + tx_info->data_offset;
- struct sk_buff *skb = tx_info->skb;
- struct skb_frag_struct *frag;
void *end = ring->buf + ring->buf_size;
- int frags = skb_shinfo(skb)->nr_frags;
+ struct sk_buff *skb = tx_info->skb;
+ int nr_maps = tx_info->nr_maps;
int i;
- struct skb_shared_hwtstamps hwts;
- if (timestamp) {
- mlx4_en_fill_hwtstamps(mdev, &hwts, timestamp);
+ if (unlikely(timestamp)) {
+ struct skb_shared_hwtstamps hwts;
+
+ mlx4_en_fill_hwtstamps(priv->mdev, &hwts, timestamp);
skb_tstamp_tx(skb, &hwts);
}
/* Optimize the common case when there are no wraparounds */
if (likely((void *) tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
if (!tx_info->inl) {
- if (tx_info->linear) {
+ if (tx_info->linear)
dma_unmap_single(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- be32_to_cpu(data->byte_count),
- PCI_DMA_TODEVICE);
- ++data;
- }
-
- for (i = 0; i < frags; i++) {
- frag = &skb_shinfo(skb)->frags[i];
+ tx_info->map0_dma,
+ tx_info->map0_byte_count,
+ PCI_DMA_TODEVICE);
+ else
+ dma_unmap_page(priv->ddev,
+ tx_info->map0_dma,
+ tx_info->map0_byte_count,
+ PCI_DMA_TODEVICE);
+ for (i = 1; i < nr_maps; i++) {
+ data++;
dma_unmap_page(priv->ddev,
- (dma_addr_t) be64_to_cpu(data[i].addr),
- skb_frag_size(frag), PCI_DMA_TODEVICE);
+ (dma_addr_t)be64_to_cpu(data->addr),
+ be32_to_cpu(data->byte_count),
+ PCI_DMA_TODEVICE);
}
}
} else {
@@ -299,23 +301,25 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
data = ring->buf + ((void *)data - end);
}
- if (tx_info->linear) {
+ if (tx_info->linear)
dma_unmap_single(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- be32_to_cpu(data->byte_count),
- PCI_DMA_TODEVICE);
- ++data;
- }
-
- for (i = 0; i < frags; i++) {
+ tx_info->map0_dma,
+ tx_info->map0_byte_count,
+ PCI_DMA_TODEVICE);
+ else
+ dma_unmap_page(priv->ddev,
+ tx_info->map0_dma,
+ tx_info->map0_byte_count,
+ PCI_DMA_TODEVICE);
+ for (i = 1; i < nr_maps; i++) {
+ data++;
/* Check for wraparound before unmapping */
if ((void *) data >= end)
data = ring->buf;
- frag = &skb_shinfo(skb)->frags[i];
dma_unmap_page(priv->ddev,
- (dma_addr_t) be64_to_cpu(data->addr),
- skb_frag_size(frag), PCI_DMA_TODEVICE);
- ++data;
+ (dma_addr_t)be64_to_cpu(data->addr),
+ be32_to_cpu(data->byte_count),
+ PCI_DMA_TODEVICE);
}
}
}
@@ -751,19 +755,22 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_info->linear = (lso_header_size < skb_headlen(skb) &&
!is_inline(ring->inline_thold, skb, NULL)) ? 1 : 0;
- data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1;
+ tx_info->nr_maps = skb_shinfo(skb)->nr_frags + tx_info->linear;
+ data += tx_info->nr_maps - 1;
if (is_inline(ring->inline_thold, skb, &fragptr)) {
tx_info->inl = 1;
} else {
+ dma_addr_t dma = 0;
+ u32 byte_count = 0;
+
/* Map fragments if any */
for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
const struct skb_frag_struct *frag;
- dma_addr_t dma;
-
frag = &skb_shinfo(skb)->frags[i];
+ byte_count = skb_frag_size(frag);
dma = skb_frag_dma_map(ddev, frag,
- 0, skb_frag_size(frag),
+ 0, byte_count,
DMA_TO_DEVICE);
if (dma_mapping_error(ddev, dma))
goto tx_drop_unmap;
@@ -771,14 +778,13 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
data->addr = cpu_to_be64(dma);
data->lkey = ring->mr_key;
wmb();
- data->byte_count = cpu_to_be32(skb_frag_size(frag));
+ data->byte_count = cpu_to_be32(byte_count);
--data;
}
/* Map linear part if needed */
if (tx_info->linear) {
- u32 byte_count = skb_headlen(skb) - lso_header_size;
- dma_addr_t dma;
+ byte_count = skb_headlen(skb) - lso_header_size;
dma = dma_map_single(ddev, skb->data +
lso_header_size, byte_count,
@@ -792,6 +798,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
data->byte_count = cpu_to_be32(byte_count);
}
tx_info->inl = 0;
+ /* tx completion can avoid cache line miss for common cases */
+ tx_info->map0_dma = dma;
+ tx_info->map0_byte_count = byte_count;
}
/*
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ab34461..a904030 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -216,12 +216,15 @@ enum cq_type {
struct mlx4_en_tx_info {
struct sk_buff *skb;
+ dma_addr_t map0_dma;
+ u32 map0_byte_count;
u32 nr_txbb;
u32 nr_bytes;
u8 linear;
u8 data_offset;
u8 inl;
u8 ts_requested;
+ u8 nr_maps;
} ____cacheline_aligned_in_smp;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 13/14] ethtool: Ethtool parameter to dynamically change tx_copybreak
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
Use new ethtool [sg]et_tunable() to set tx_copybread (inline threshold)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
include/uapi/linux/ethtool.h | 1 +
net/core/ethtool.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 7a364f2..99b4305 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -212,6 +212,7 @@ struct ethtool_value {
enum tunable_id {
ETHTOOL_ID_UNSPEC,
ETHTOOL_RX_COPYBREAK,
+ ETHTOOL_TX_COPYBREAK,
};
enum tunable_type_id {
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 27e61b8..1600aa2 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1625,6 +1625,7 @@ static int ethtool_tunable_valid(const struct ethtool_tunable *tuna)
{
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
+ case ETHTOOL_TX_COPYBREAK:
if (tuna->len != sizeof(u32) ||
tuna->type_id != ETHTOOL_TUNABLE_U32)
return -EINVAL;
--
1.8.3.4
^ permalink raw reply related
* [PATCH net-next 03/14] net/mlx4_en: Avoid calling bswap in tx fast path
From: Amir Vadai @ 2014-10-05 9:35 UTC (permalink / raw)
To: David S. Miller, Eric Dumazet
Cc: netdev, Yevgeny Petrilin, Or Gerlitz, Ido Shamay, Amir Vadai
In-Reply-To: <1412501722-25092-1-git-send-email-amirv@mellanox.com>
From: Eric Dumazet <edumazet@google.com>
- doorbell_qpn is stored in the cpu_to_be32() way to avoid bswap() in fast
path.
- mdev->mr.key stored in ring->mr_key to also avoid bswap() and access to
cold cache line.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/en_tx.c | 17 ++++++++++-------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 3 ++-
2 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index eaf23eb..322cda3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -195,7 +195,8 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
memset(ring->buf, 0, ring->buf_size);
ring->qp_state = MLX4_QP_STATE_RST;
- ring->doorbell_qpn = ring->qp.qpn << 8;
+ ring->doorbell_qpn = cpu_to_be32(ring->qp.qpn << 8);
+ ring->mr_key = cpu_to_be32(mdev->mr.key);
mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn,
ring->cqn, user_prio, &ring->context);
@@ -654,7 +655,6 @@ static void mlx4_bf_copy(void __iomem *dst, const void *src,
netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct mlx4_en_dev *mdev = priv->mdev;
struct device *ddev = priv->ddev;
struct mlx4_en_tx_ring *ring;
struct mlx4_en_tx_desc *tx_desc;
@@ -769,7 +769,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop_unmap;
data->addr = cpu_to_be64(dma);
- data->lkey = cpu_to_be32(mdev->mr.key);
+ data->lkey = ring->mr_key;
wmb();
data->byte_count = cpu_to_be32(skb_frag_size(frag));
--data;
@@ -787,7 +787,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
goto tx_drop_unmap;
data->addr = cpu_to_be64(dma);
- data->lkey = cpu_to_be32(mdev->mr.key);
+ data->lkey = ring->mr_key;
wmb();
data->byte_count = cpu_to_be32(byte_count);
}
@@ -879,9 +879,12 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue);
+ real_size = (real_size / 16) & 0x3f;
+
if (ring->bf_enabled && desc_size <= MAX_BF && !bounce &&
!vlan_tx_tag_present(skb) && send_doorbell) {
- tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn);
+ tx_desc->ctrl.bf_qpn = ring->doorbell_qpn |
+ cpu_to_be32(real_size);
op_own |= htonl((bf_index & 0xffff) << 8);
/* Ensure new descriptor hits memory
@@ -911,8 +914,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
tx_desc->ctrl.owner_opcode = op_own;
if (send_doorbell) {
wmb();
- iowrite32be(ring->doorbell_qpn,
- ring->bf.uar->map + MLX4_SEND_DOORBELL);
+ iowrite32(ring->doorbell_qpn,
+ ring->bf.uar->map + MLX4_SEND_DOORBELL);
} else {
ring->xmit_more++;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b7bde95..ab34461 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -279,7 +279,8 @@ struct mlx4_en_tx_ring {
u16 stride;
u16 cqn; /* index of port CQ associated with this ring */
u32 buf_size;
- u32 doorbell_qpn;
+ __be32 doorbell_qpn;
+ __be32 mr_key;
void *buf;
struct mlx4_en_tx_info *tx_info;
u8 *bounce_buf;
--
1.8.3.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox