On 11/30/2016 04:52 AM, Hannes Frederic Sowa wrote:
> In the worst case this causes 2GB (order 19) allocations (x == 31) to
> happen in GFP_ATOMIC (due to write lock) context and could cause update
> failures to the routing table due to fragmentation. Are you sure the
> upper limit of 31 is reasona
Introduce classifying by metadata extracted by the tunnel device.
Outer header fields - source/dest ip and tunnel id, are extracted from
the metadata when classifying.
For example, the following will add a filter on the ingress Qdisc of shared
vxlan device named 'vxlan0'. To forward packets with o
This action could be used before redirecting packets to a shared tunnel
device, or when redirecting packets arriving from a such a device.
The 'unset' action is optional. It is used to explicitly unset the
metadata created by the tunnel device during decap. If not used, the
metadata will be releas
Hi,
This short series adds support for matching and setting metadata for ip tunnel
shared device using the TC system, introduced in kernel 4.9 [1].
Applied and tested on top of commit f3f339e9590a ("cleanup debris from revert")
Example usage:
$ tc filter add dev vxlan0 protocol ip parent :
Add the utility functions rta_getattr_be16() and rta_getattr_be32(), and
change existing code to use it.
Signed-off-by: Amir Vadai
---
bridge/fdb.c | 4 ++--
include/libnetlink.h | 9 +
ip/iplink_geneve.c | 2 +-
ip/iplink_vxlan.c| 2 +-
4 files changed, 13 insertions(+), 4
On Wed, Nov 30, 2016 at 9:17 AM, Amir Vadai wrote:
> On Tue, Nov 29, 2016 at 07:26:58PM -0800, Stephen Hemminger wrote:
(Sending again since I just discovered that Google Inbox is adding an
HTML part...)
>> The overall design is fine, just a couple nits with the code.
>>
>> > diff --git a/tc/f_fl
From: Nikita Yushchenko Sent: Wednesday,
November 30, 2016 2:36 PM
>To: Andy Duan ; David S. Miller
>; Troy Kisky ;
>Andrew Lunn ; Eric Nelson ; Philippe
>Reynes ; Johannes Berg ;
>netdev@vger.kernel.org
>Cc: Chris Healy ; Fabio Estevam
>; linux-ker...@vger.kernel.org
>Subject: Re: [patch
On Tue, Nov 29, 2016 at 3:30 PM, Jarno Rajahalme wrote:
> Do not always set skb->protocol to be the ethertype of the L3 header.
> For a packet with non-accelerated VLAN tags skb->protocol needs to be
> the ethertype of the outermost non-accelerated VLAN ethertype.
>
> Any VLAN offloading is undone
On Mon, Nov 28, 2016 at 10:58 PM, Eric Dumazet wrote:
> {
> @@ -496,8 +531,13 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev,
> wmb();
>
> /* we want to dirty this cache line once */
> - ACCESS_ONCE(ring->last_nr_txbb) = last_nr_txbb;
> - ACCESS_ONCE(ring-
On 2016/11/30 15:36, Nikita Yushchenko wrote:
>> But I think it is not necessary since the driver don't support jumbo frame.
>
> Hardcoded 1522 raises two separate issues.
>
> (1) When DSA is in use, frames processed by FEC chip contain DSA tag and
> thus can be larger than hardcoded limit of 152
On Tue, Nov 29, 2016 at 3:30 PM, Jarno Rajahalme wrote:
> Use is_skb_forwardable() instead of an explicit length check. This
> gets around the apparent MTU check failure in OVS test cases when
> skb->protocol is not properly set in case of non-accelerated VLAN
> skbs.
>
> Suggested-by: Pravin She
On Tue, Nov 29, 2016 at 07:26:58PM -0800, Stephen Hemminger wrote:
> The overall design is fine, just a couple nits with the code.
>
> > diff --git a/tc/f_flower.c b/tc/f_flower.c
> > index 2d31d1aa832d..1cf0750b5b83 100644
> > --- a/tc/f_flower.c
> > +++ b/tc/f_flower.c
>
> >
> > +static int f
On Wed, Nov 30, 2016 at 07:48:51AM +0100, Thomas Graf wrote:
> On 11/29/16 at 04:15pm, Alexei Starovoitov wrote:
> > On Tue, Nov 29, 2016 at 02:21:22PM +0100, Thomas Graf wrote:
> > ...
> > > +#define LWT_BPF_MAX_HEADROOM 128
> >
> > why 128?
> > btw I'm thinking for XDP to use 256, so metadata ca
On 11/29/16 at 04:17pm, Alexei Starovoitov wrote:
> On Tue, Nov 29, 2016 at 02:21:23PM +0100, Thomas Graf wrote:
> > Adds a series of test to verify the functionality of attaching
> > BPF programs at LWT hooks.
> >
> > Also adds a sample which collects a histogram of packet sizes which
> > pass th
On Tue, Nov 29, 2016 at 2:14 PM, Paul Moore wrote:
> On Tue, Nov 29, 2016 at 5:11 PM, Paul Moore wrote:
>> From: Paul Moore
>>
>> Bring back commit bc51dddf98c9 ("netns: avoid disabling irq for netns
>> id") now that we've fixed some audit multicast issues that caused
>> problems with original a
On 11/29/16 at 04:15pm, Alexei Starovoitov wrote:
> On Tue, Nov 29, 2016 at 02:21:22PM +0100, Thomas Graf wrote:
> ...
> > +#define LWT_BPF_MAX_HEADROOM 128
>
> why 128?
> btw I'm thinking for XDP to use 256, so metadata can be stored in there.
It's an arbitrary limit to catch obvious misconfigur
> But I think it is not necessary since the driver don't support jumbo frame.
Hardcoded 1522 raises two separate issues.
(1) When DSA is in use, frames processed by FEC chip contain DSA tag and
thus can be larger than hardcoded limit of 1522. This issue is not
FEC-specific, any driver that hardco
On Tue, Nov 29, 2016 at 06:07:18PM -0700, David Ahern wrote:
> On 11/29/16 5:59 PM, Alexei Starovoitov wrote:
> > On Tue, Nov 29, 2016 at 05:43:08PM -0700, David Ahern wrote:
> >> On 11/29/16 1:01 PM, Alexei Starovoitov wrote:
> >>> Could you also expose sk_protcol and sk_type as read only fields?
On Tue, Nov 29, 2016 at 06:52:36PM -0800, John Fastabend wrote:
> On 16-11-29 04:15 PM, Alexei Starovoitov wrote:
> > On Tue, Nov 29, 2016 at 02:21:22PM +0100, Thomas Graf wrote:
> >> Registers new BPF program types which correspond to the LWT hooks:
> >> - BPF_PROG_TYPE_LWT_IN => dst_input()
>
On 2016年11月30日 10:53, Jason Wang wrote:
On 2016年11月29日 21:27, wangyunjian wrote:
Sorry, I didn't describe it clearly. In fact, the second subtraction
happens in the function handle_tx,
when tun_get_user fails and zcopy_used is ture. Fllowing the steps:
I get your meaning. Thanks for the r
On Tue, Nov 29, 2016 at 06:50:18PM -0800, John Fastabend wrote:
> On 16-11-29 04:37 PM, Alexei Starovoitov wrote:
> > On Tue, Nov 29, 2016 at 12:11:33PM -0800, John Fastabend wrote:
> >> virtio_net XDP support expects receive buffers to be contiguous.
> >> If this is not the case we enable a slowpa
We trigger uarg->callback() immediately after we decide do datacopy
even if caller want to do zerocopy. This will cause the callback
(vhost_net_zerocopy_callback) decrease the refcount. But when we meet
an error afterwards, the error handling in vhost handle_tx() will try
to decrease it again. This
We trigger uarg->callback() immediately after we decide do datacopy
even if caller want to do zerocopy. This will cause the callback
(vhost_net_zerocopy_callback) decrease the refcount. But when we meet
an error afterwards, the error handling in vhost handle_tx() will try
to decrease it again. This
On 2016-11-29 15:13, Cong Wang wrote:
> On Tue, Nov 29, 2016 at 8:48 AM, Richard Guy Briggs wrote:
> > On 2016-11-26 17:11, Cong Wang wrote:
> >> It is racy on audit_sock, especially on the netns exit path.
> >
> > I think that is the only place it is racy. The other places audit_sock
> > is set
Hi David,
On Wed, Nov 30, 2016 at 5:35 AM, David Miller wrote:
> From: Harini Katakam
> Date: Mon, 28 Nov 2016 14:53:49 +0530
>
>> In macb_reset_hw, use read-modify-write to disable RX and TX.
>> This way exiting settings and reserved bits wont be disturbed.
>> Use the same method for clearing s
From: Johan Hovold
Date: Mon, 28 Nov 2016 19:24:53 +0100
> This series fixes failures to deregister and free fixed-link phydevs
> that have been registered using the of_phy_register_fixed_link()
> interface.
>
> All but two drivers currently fail to do this and this series fixes most
> of them w
On Tue, Nov 29, 2016 at 9:15 AM, David Lebrun wrote:
> When multiple nexthops are available for a given route, the routing engine
> chooses a nexthop by computing the flow hash through get_hash_from_flowi6
> and by taking that value modulo the number of nexthops. The resulting value
> indexes the
Hi,
On Tue, Nov 29, 2016, at 18:15, David Lebrun wrote:
> When multiple nexthops are available for a given route, the routing
> engine
> chooses a nexthop by computing the flow hash through get_hash_from_flowi6
> and by taking that value modulo the number of nexthops. The resulting
> value
> index
Hello,
On Wed, Nov 30, 2016, at 01:22, David Miller wrote:
> From: Hannes Frederic Sowa
> Date: Fri, 25 Nov 2016 18:09:00 +0100
>
> > During review we discussed on how to handle major errors in the kernel:
> >
> > The old code and the new code still can report back success even though
> > the k
The overall design is fine, just a couple nits with the code.
> diff --git a/tc/f_flower.c b/tc/f_flower.c
> index 2d31d1aa832d..1cf0750b5b83 100644
> --- a/tc/f_flower.c
> +++ b/tc/f_flower.c
>
> +static int flower_parse_key_id(char *str, int type, struct nlmsghdr *n)
str is not modified, the
Currently loop index 'idx' is used as the index in the neigh list of interest.
It's increased only when the neigh is dumped. It's not the absolute index in
the list. Because there is no info to record which neigh has already be scanned
by previous loop. This will cause the filtered out neighs to be
On Sun, 27 Nov 2016 13:21:02 +0200
Roi Dayan wrote:
> Add missing usage help for devlink dev eswitch subcommand.
>
> Signed-off-by: Roi Dayan
> Reviewed-by: Or Gerlitz
Ok. Applied both, will show in next merge
The change fixes AX88772x resume failure by
- Restore incorrect AX88772A PHY registers when resetting
- Need to stop MAC operation when suspending
- Need to restart MII when restoring PHY
Signed-off-by: Allan Chou
Signed-off-by: Robert Foss
Tested-by: Robert Foss
Tested-by: Jon Hunter
Tested-b
On 2016年11月29日 21:27, wangyunjian wrote:
Sorry, I didn't describe it clearly. In fact, the second subtraction happens in
the function handle_tx,
when tun_get_user fails and zcopy_used is ture. Fllowing the steps:
I get your meaning. Thanks for the reporting. Will post patches (since
macvtap
On 16-11-29 04:15 PM, Alexei Starovoitov wrote:
> On Tue, Nov 29, 2016 at 02:21:22PM +0100, Thomas Graf wrote:
>> Registers new BPF program types which correspond to the LWT hooks:
>> - BPF_PROG_TYPE_LWT_IN => dst_input()
>> - BPF_PROG_TYPE_LWT_OUT => dst_output()
>> - BPF_PROG_TYPE_LWT_XM
On 16-11-29 04:37 PM, Alexei Starovoitov wrote:
> On Tue, Nov 29, 2016 at 12:11:33PM -0800, John Fastabend wrote:
>> virtio_net XDP support expects receive buffers to be contiguous.
>> If this is not the case we enable a slowpath to allow connectivity
>> to continue but at a significan performance
On 11/29/16 6:27 PM, 张胜举 wrote:
> This has less changes, but I preferred to add a new function to do the
> filter logic, this is the same as your code @rtnl_dump_ifinfo().
I'd prefer it to stay in line as it is now. You can save the cycles of
filtering on already viewed entries without an overha
From: Vitaly Kuznetsov
Date: Mon, 28 Nov 2016 18:25:44 +0100
> When we change MTU or the number of channels on a netvsc device we get the
> following logged:
>
> hv_netvsc bf5edba8...: net device safe to remove
> hv_netvsc: hv_netvsc channel opened successfully
> hv_netvsc bf5edba8...: Send s
From: Jiri Pirko
Date: Mon, 28 Nov 2016 18:01:22 +0100
> Couple of enhancements and fixes from Ido.
Series applied, thanks Jiri.
From: Arnaldo Carvalho de Melo
Date: Mon, 28 Nov 2016 12:36:58 -0300
> As it may get stale and lead to use after free.
>
> Acked-by: Eric Dumazet
> Cc: Alexander Duyck
> Cc: Andrey Konovalov
> Fixes: cbc53e08a793 ("GSO: Add GSO type for fixed IPv4 ID")
> Signed-off-by: Arnaldo Carvalho de Mel
From: Jiri Pirko
Date: Mon, 28 Nov 2016 15:40:13 +0100
> From: Jiri Pirko
>
> Be symmetric to hashtable insert and remove filter from hashtable only
> in case skip sw flag is not set.
>
> Fixes: e69985c67c33 ("net/sched: cls_flower: Introduce support in SKIP SW
> flag")
> Signed-off-by: Jiri
From: Eric Dumazet
Date: Mon, 28 Nov 2016 06:26:49 -0800
> From: Eric Dumazet
>
> pskb_may_pull() can reallocate skb->head, we need to reload dh pointer
> in dccp_invalid_packet() or risk use after free.
>
> Bug found by Andrey Konovalov using syzkaller.
>
> Signed-off-by: Eric Dumazet
> Rep
From: Arnd Bergmann
Date: Mon, 28 Nov 2016 15:26:04 +0100
> The newly added switchib driver fails to link if MLXSW_PCI=m:
>
> drivers/net/ethernet/mellanox/mlxsw/mlxsw_switchib.o: In
> function^Cmlxsw_sib_module_exit':
> switchib.c:(.exit.text+0x8): undefined reference to
> `mlxsw_pci_driver_u
From: Geert Uytterhoeven
Date: Mon, 28 Nov 2016 15:18:31 +0100
> If device_release_driver(&phydev->mdio.dev) is called, it releases all
> resources belonging to the PHY device. Hence the subsequent call to
> phy_led_triggers_unregister() will access already freed memory when
> unregistering the L
From: Zumeng Chen
Date: Mon, 28 Nov 2016 21:55:00 +0800
> When a hardware issue happened as described by inline comments, the register
> write pattern looks like the following:
>
>
> + wmb();
>
>
> There might be a memory barrier between these two write operations, so add wmb
> to ensure an f
> -Original Message-
> From: David Ahern [mailto:d...@cumulusnetworks.com]
> Sent: Wednesday, November 30, 2016 12:23 AM
> To: Zhang Shengju ;
> netdev@vger.kernel.org
> Subject: Re: [net-next] neigh: remove duplicate check for same neigh
>
> On 11/29/16 1:22 AM, Zhang Shengju wrote:
> > @
On 11/29/2016 05:13 PM, David Miller wrote:
> From: Florian Fainelli
> Date: Tue, 29 Nov 2016 16:43:20 -0800
>
>> On 11/29/2016 04:38 PM, David Miller wrote:
>>> From: Jerome Brunet
>>> Date: Mon, 28 Nov 2016 10:46:45 +0100
>>>
This patchset fixes an issue with the OdroidC2 board (DWMAC + R
From: Florian Fainelli
Date: Tue, 29 Nov 2016 16:43:20 -0800
> On 11/29/2016 04:38 PM, David Miller wrote:
>> From: Jerome Brunet
>> Date: Mon, 28 Nov 2016 10:46:45 +0100
>>
>>> This patchset fixes an issue with the OdroidC2 board (DWMAC + RTL8211F).
>>> The platform seems to enter LPI on the R
On 11/29/16 5:59 PM, Alexei Starovoitov wrote:
> On Tue, Nov 29, 2016 at 05:43:08PM -0700, David Ahern wrote:
>> On 11/29/16 1:01 PM, Alexei Starovoitov wrote:
>>> Could you also expose sk_protcol and sk_type as read only fields?
>>
>> Those are bitfields in struct sock, so can't use offsetof or si
From: Cyrille Pitchen
Date: Mon, 28 Nov 2016 14:40:55 +0100
> On macb only (not gem), when a RX queue corruption was detected from
> macb_rx(), the RX queue was reset: during this process the RX ring
> buffer descriptor was initialized by macb_init_rx_ring() but we forgot
> to also set bp->rx_tai
On Tue, Nov 29, 2016 at 05:43:08PM -0700, David Ahern wrote:
> On 11/29/16 1:01 PM, Alexei Starovoitov wrote:
> > Could you also expose sk_protcol and sk_type as read only fields?
>
> Those are bitfields in struct sock, so can't use offsetof or sizeof. Any
> existing use cases that try to load a
From: Pavel Machek
Date: Mon, 28 Nov 2016 12:55:59 +0100
> Fix comments, add some new, and make debugfs output consistent.
>
> Signed-off-by: Pavel Machek
Applied to net-next, thanks.
From: Daniel Mack
Date: Mon, 28 Nov 2016 14:11:04 +0100
> There's a 'not' missing in one paragraph. Add it.
>
> Signed-off-by: Daniel Mack
> Reported-by: Rami Rosen
> Fixes: 3007098494be ("cgroup: add support for eBPF programs")
Applied, thanks.
From: Gao Feng
The mtu_adj is initialized to zero when alloc mem, there is no any
assignment to mtu_adj. It is only used in ipvlan_adjust_mtu as one
right value.
So it is useless member of struct ipvl_dev, then remove it.
Signed-off-by: Gao Feng
---
drivers/net/ipvlan/ipvlan.h | 1 -
driv
From: Herbert Xu
Date: Mon, 28 Nov 2016 19:22:12 +0800
> netlink: Call cb->done from a worker thread
>
> The cb->done interface expects to be called in process context.
> This was broken by the netlink RCU conversion. This patch fixes
> it by adding a worker struct to make the cb->done call whe
From: Amir Vadai
Date: Mon, 28 Nov 2016 12:56:40 +0200
> Add a validation function to make sure offset is valid:
> 1. Not below skb head (could happen when offset is negative).
> 2. Validate both 'offset' and 'at'.
>
> Signed-off-by: Amir Vadai
Applied and queued up for -stable, thanks.
On 11/29/2016 04:38 PM, David Miller wrote:
> From: Jerome Brunet
> Date: Mon, 28 Nov 2016 10:46:45 +0100
>
>> This patchset fixes an issue with the OdroidC2 board (DWMAC + RTL8211F).
>> The platform seems to enter LPI on the Rx path too often while performing
>> relatively high TX transfer. This
On 11/29/16 1:01 PM, Alexei Starovoitov wrote:
> Could you also expose sk_protcol and sk_type as read only fields?
Those are bitfields in struct sock, so can't use offsetof or sizeof. Any
existing use cases that try to load a bitfield in a bpf that I can look at?
From: yegorsli...@googlemail.com
Date: Mon, 28 Nov 2016 10:47:52 +0100
> From: Yegor Yefremov
>
> This patch adds support for ethtool's '-r' command. Restarting
> N-WAY negotiation can be useful to activate newly changed EEE
> settings etc.
>
> Signed-off-by: Yegor Yefremov
This doesn't apply
From: Jerome Brunet
Date: Mon, 28 Nov 2016 10:46:45 +0100
> This patchset fixes an issue with the OdroidC2 board (DWMAC + RTL8211F).
> The platform seems to enter LPI on the Rx path too often while performing
> relatively high TX transfer. This eventually break the link (both Tx and
> Rx), and re
On Tue, Nov 29, 2016 at 12:11:33PM -0800, John Fastabend wrote:
> virtio_net XDP support expects receive buffers to be contiguous.
> If this is not the case we enable a slowpath to allow connectivity
> to continue but at a significan performance overhead associated with
> linearizing data. To make
On Tue, Nov 29, 2016 at 09:23:10PM +0100, Daniel Borkmann wrote:
> On 11/29/2016 07:51 PM, Alexei Starovoitov wrote:
> >On Tue, Nov 29, 2016 at 03:38:18PM +, Jakub Kicinski wrote:
> [...]
> So next step is to improve verifier messages to be more human friendly.
> The step after is to in
Eric Dumazet wrote:
> On Tue, 2016-11-29 at 16:45 +0100, Florian Westphal wrote:
> > Eric says: "By looking at tcpdump, and TS val of xmit packets of multiple
> > flows, we can deduct the relative qdisc delays (think of fq pacing).
> > This should work even if we have one flow per remote peer."
>
From: Hannes Frederic Sowa
Date: Fri, 25 Nov 2016 18:09:00 +0100
> During review we discussed on how to handle major errors in the kernel:
>
> The old code and the new code still can report back success even though
> the kernel got back an EFAULT while copying from kernel space to user
> space (
On Tue, Nov 29, 2016 at 04:27:03PM -0600, Grygorii Strashko wrote:
> netif_set_real_num_tx/rx_queues() are required to be called with rtnl_lock
> taken, otherwise ASSERT_RTNL() warning will be triggered - which happens
> now during System resume from suspend:
> cpsw_resume()
> |- cpsw_ndo_open()
>
On Tue, Nov 29, 2016 at 02:21:23PM +0100, Thomas Graf wrote:
> Adds a series of test to verify the functionality of attaching
> BPF programs at LWT hooks.
>
> Also adds a sample which collects a histogram of packet sizes which
> pass through an LWT hook.
>
> $ ./lwt_len_hist.sh
> Starting netserv
On Tue, Nov 29, 2016 at 02:21:22PM +0100, Thomas Graf wrote:
> Registers new BPF program types which correspond to the LWT hooks:
> - BPF_PROG_TYPE_LWT_IN => dst_input()
> - BPF_PROG_TYPE_LWT_OUT => dst_output()
> - BPF_PROG_TYPE_LWT_XMIT => lwtunnel_xmit()
>
> The separate program types
From: Harini Katakam
Date: Mon, 28 Nov 2016 14:53:49 +0530
> In macb_reset_hw, use read-modify-write to disable RX and TX.
> This way exiting settings and reserved bits wont be disturbed.
> Use the same method for clearing statistics as well.
>
> Signed-off-by: Harini Katakam
This doesn't make
From: Niklas Cassel
Date: Thu, 24 Nov 2016 15:36:33 +0100
> From: Niklas Cassel
>
> The dwmac4 IP can synthesized with 1-8 number of tx queues.
> On an IP synthesized with DWC_EQOS_NUM_TXQ > 1, all txqueues are disabled
> by default. For these IPs, the bitfield TXQEN is R/W.
>
> Always enable
> > It seems phy_unregister_fixup() will be needed for module network driver.
> > phy_fixup_list keeps the list even after unloading module.
> > Do you know any update is waiting for submission? If not, I'll make patch.
>
> Oh, yes, that's a good point, we need such a thing, so far fixups have
> b
From: Peter Robinson
Date: Mon, 28 Nov 2016 07:12:37 +
> Add dependencies on the architectures that support these devices and
> add compile test to ensure ongoing code build coverage.
>
> Signed-off-by: Peter Robinson
Applied.
On 11/29/2016 03:55 PM, woojung@microchip.com wrote:
>> There are two ways to get these settings propagated to the PHY driver:
>>
>> - using a board fixup which is going to be invoked during
>> drv->config_init() time
>>
>> - specifying a phydev->dev_flags and reading it from the PHY driver to
> There are two ways to get these settings propagated to the PHY driver:
>
> - using a board fixup which is going to be invoked during
> drv->config_init() time
>
> - specifying a phydev->dev_flags and reading it from the PHY driver to
> act upon and configure the PHY based on that value, there a
> On Nov 28, 2016, at 11:21 PM, Pravin Shelar wrote:
>
> On Mon, Nov 28, 2016 at 6:41 PM, Jarno Rajahalme wrote:
>> Do not set skb->protocol to be the ethertype of the L3 header, unless
>> the packet only has the L3 header. For a non-hardware offloaded VLAN
>> frame skb->protocol needs to be o
On Wed, 2016-11-30 at 00:19 +0200, Saeed Mahameed wrote:
> From: Tariq Toukan
>
> Add new type of struct mlx5_frag_buf which is used to allocate fragmented
> buffers rather than contiguous, and make the Completion Queues (CQs) use
> it as they are big (default of 2MB per CQ in Striding RQ).
>
>
Use is_skb_forwardable() instead of an explicit length check. This
gets around the apparent MTU check failure in OVS test cases when
skb->protocol is not properly set in case of non-accelerated VLAN
skbs.
Suggested-by: Pravin Shelar
Fixes: 5108bbaddc ("openvswitch: add processing of L3 packets")
Add a break statement to prevent fall-through from
OVS_KEY_ATTR_ETHERNET to OVS_KEY_ATTR_TUNNEL. Without the break
actions setting ethernet addresses fail to validate with log messages
complaining about invalid tunnel attributes.
Fixes: 0a6410fbde ("openvswitch: netlink: support L3 packets")
Sign
Do not always set skb->protocol to be the ethertype of the L3 header.
For a packet with non-accelerated VLAN tags skb->protocol needs to be
the ethertype of the outermost non-accelerated VLAN ethertype.
Any VLAN offloading is undone on the OVS netlink interface, and any
VLAN tags added by userspac
On Tue, Nov 29, 2016 at 07:57:51AM +0100, Brice Goglin wrote:
>Hello
>
>My Dell PowerEdge R815 doesn't have IPMI anymore when I boot a 4.8
>kernel, the BMC doesn't even ping anymore. Its Ethernet devices are 4 of
>those:
>
>01:00.0 Ethernet controller: Broadcom Corporation NetXtreme II BCM5709 Giga
> There are two ways to get these settings propagated to the PHY driver:
>
> - using a board fixup which is going to be invoked during
> drv->config_init() time
>
> - specifying a phydev->dev_flags and reading it from the PHY driver to
> act upon and configure the PHY based on that value, there a
On Tue, Nov 29, 2016 at 9:46 AM, Robert Shearman wrote:
> With certain distributions of routes it can take a long time to add
> and delete further routes at scale. For example, with a route for
> 10.37.96.0/20 present it takes 47s to add ~200k contiguous /24 routes
> from 8.0.0.0/24 through to 11.
On Tue, Nov 29, 2016 at 8:48 AM, Richard Guy Briggs wrote:
> On 2016-11-26 17:11, Cong Wang wrote:
>> It is racy on audit_sock, especially on the netns exit path.
>
> I think that is the only place it is racy. The other places audit_sock
> is set is when the socket failure has just triggered a re
From: "Wei Hu (Xavier)"
If send queue is still working when qp is in reset state by modify qp
in destroy qp function, hardware will hold on and don't work in hip06
SoC. In current codes, RoCE driver check hardware pointer of sending and
hardware pointer of processing to ensure that hardware has p
From: Lijun Ou
This patch mainly fix the name for IB device in order
to match with libhns.
Signed-off-by: Lijun Ou
Signed-off-by: Salil Mehta
---
drivers/infiniband/hw/hns/hns_roce_main.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce
Hi David,
As we are preparing to post V3 of the qed (drivers/net/) and qedi
(drivers/scsi/), I would like to get your opinion on the "qedi" part. As
qedi (the iSCSI driver) is dependent on the accompanying "qed" changes,
qedi changes have to follow or be together with qed changes. Martin is ok
From: Shaobo Xu
If the resources of cq are freed while executing the user case, hardware
can not been notified in hip06 SoC. Then hardware will hold on when it
writes the cq buffer which has been released.
In order to slove this problem, RoCE driver checks the CQE counter, and
ensure that the ou
From: "Wei Hu (Xavier)"
In hns_roce driver, we need not call iboe_get_mtu to reduce
IB headers from effective IBoE MTU because hr_dev->caps.max_mtu
has already been reduced.
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Salil Mehta
---
drivers/infiniband/hw/hns/hns_roce_main.c | 16 ++--
From: Shaobo Xu
If the resources of mr are freed while executing the user case, hardware
can not been notified in hip06 SoC. Then hardware will hold on when it
reads the payload by the PA which has been released.
In order to slove this problem, RoCE driver creates 8 reserved loopback
QPs to ensu
From: "Wei Hu (Xavier)"
It deleted the redundant memset operation because the memory allocated
by ib_alloc_device has been set zero.
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Salil Mehta
---
drivers/infiniband/hw/hns/hns_roce_main.c |3 ---
1 file changed, 3 deletions(-)
diff --git a
This patch-set contains bug fixes for the HNS RoCE driver.
Lijun Ou (1):
IB/hns: Fix the IB device name
Shaobo Xu (2):
IB/hns: Fix the bug when free mr
IB/hns: Fix the bug when free cq
Wei Hu (Xavier) (3):
IB/hns: Fix the bug when destroy qp
IB/hns: Fix the bug of setting port mtu
IB
If compiling with signed checks enabled, there will be warnings
generated by the ETHTOOL_RX_FLOW_SPEC_RING(_VF) masks. These are
currently marked as signed constants, which will generate warnings when
masking with unsigned values. Avoid this by marking them explicitly as
unsigned values.
Signed-of
On Tue, 2016-11-29 at 12:06 -0800, Linus Torvalds wrote:
> On Nov 29, 2016 11:58 AM, "Eric Dumazet"
> wrote:
> >
> > nv_do_nic_poll() is simply buggy and needs a fix.
> >
> > synchronize_irq() can sleep.
>
> Yes, but why did it start showing up now? None of this has changed as
> far as I can see?
netif_set_real_num_tx/rx_queues() are required to be called with rtnl_lock
taken, otherwise ASSERT_RTNL() warning will be triggered - which happens
now during System resume from suspend:
cpsw_resume()
|- cpsw_ndo_open()
|- netif_set_real_num_tx/rx_queues()
|- ASSERT_RTNL();
Hence, fix it by
From: Roi Dayan
We will never find a flow with the same cookie as cls_flower always
allocates a new flow and the cookie is the allocated memory address.
Fixes: e3a2b7ed018e ("net/mlx5e: Support offload cls_flower with drop action")
Signed-off-by: Roi Dayan
Reviewed-by: Hadar Hen Zion
Signed-of
From: Tariq Toukan
In next patch we are going to create a UMR MKey per RQ, we need
mlx5e_create_umr_mkey declared before mlx5e_create_rq.
Signed-off-by: Tariq Toukan
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 74 +++
1 file change
From: Tariq Toukan
In Striding RQ implementation, we used a single UMR
(User-Mode Memory Registration) memory key for all RQs.
When the product of RQs number*size gets high, we hit a
limitation of u16 field size in FW.
Here we move to using a UMR memory key per RQ, so we can
scale to any number
From: Roi Dayan
Handling flow encap entry should be inside tc del flow
and is only relevant for offloaded eswitch TC rules.
Fixes: 11a457e9b6c1 ("net/mlx5e: Add basic TC tunnel set action for SRIOV
offloads")
Signed-off-by: Roi Dayan
Reviewed-by: Or Gerlitz
Signed-off-by: Saeed Mahameed
---
From: Roi Dayan
Change the function that deletes offloaded TC rule to get
struct mlx5e_tc_flow instance which contains both the flow
handle and flow attributes. This is a cleanup needed for
downstream patches, it doesn't change any functionality.
Signed-off-by: Roi Dayan
Reviewed-by: Or Gerlitz
Hi Dave,
The following series from Tariq and Roi, provides some critical fixes
and updates for the mlx5e driver.
>From Tariq:
- Fix driver coherent memory huge allocation issues by fragmenting
completion queues, in a way that is transparent to the netdev driver by
providing a new buffer t
From: Tariq Toukan
Add new type of struct mlx5_frag_buf which is used to allocate fragmented
buffers rather than contiguous, and make the Completion Queues (CQs) use
it as they are big (default of 2MB per CQ in Striding RQ).
This fixes the failures of type:
"mlx5e_open_locked: mlx5e_open_channel
1 - 100 of 321 matches
Mail list logo
