On Thu, Mar 21, 2019 at 9:55 PM Willem de Bruijn
wrote:
>
> On Thu, Mar 21, 2019 at 8:16 PM Eric Dumazet wrote:
> >
> > On hosts with many cpus we can observe a very serious contention
> > on spinlocks used in mm slab layer.
> >
> > The following can happen quite often :
> >
> > 1) TX path
> >
This is a first for me to appear on the Linux kernel netdev list, so please
bear with me while killing me...
For diagnosing Linux virtual networking I need to relate TAP/TUN network
interfacces to the user space processes they are served by. I'm aware of Kirill
Tkhai's TUN SIOCGSKNS ioctl patch
With commit c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array")
pfifo_fast no longer benefit from the TCQ_F_CAN_BYPASS optimization.
Due to retpolines the cost of the enqueue()/dequeue() pair has become
relevant and we observe measurable regression for the uncontended
scenario when the packet-rat
The queue is marked not empty after acquiring the seqlock,
and it's up to the NOLOCK qdisc clearing such flag on dequeue.
Since the empty status lays on the same cache-line of the
seqlock, it's always hot on cache during the updates.
This makes the empty flag update a little bit loosy. Given
the l
This patch series is aimed at improving xmit performances of lockless qdisc
in the uncontended scenario.
After the lockless refactor pfifo_fast can't leverage the BYPASS optimization.
Due to retpolines the overhead for the avoidables enqueue and dequeue operations
has increased and we see measurab
On Thu, Mar 21, 2019 at 6:50 PM Jiri Pirko wrote:
>
> From: Jiri Pirko
>
> devlink functions are in use, so include the related header file.
>
> Signed-off-by: Jiri Pirko
> ---
> drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/n
On 22. 03. 19 9:30, Paolo Abeni wrote:
This patch series is aimed at improving xmit performances of lockless qdisc
in the uncontended scenario.
After the lockless refactor pfifo_fast can't leverage the BYPASS optimization.
Due to retpolines the overhead for the avoidables enqueue and dequeue ope
On Thu, Mar 21, 2019 at 05:14:41PM -0700, Eric Dumazet wrote:
> On hosts with many cpus we can observe a very serious contention
> on spinlocks used in mm slab layer.
>
> The following can happen quite often :
>
> 1) TX path
> sendmsg() allocates one (fclone) skb on CPU A, sends a clone.
> AC
A new mirred action is created by the tcf_mirred_init function. This
contains a list head struct which is inserted into a global list on
successful creation of a new action. However, after a creation, it is
still possible to error out and call the tcf_idr_release function. This,
in turn, calls the
On Fri, Mar 22, 2019 at 4:28 AM Michael S. Tsirkin wrote:
>
>
> Just a thought: would it make sense to flush the cache
> in enter_memory_pressure?
>
Good question, thanks !
Willem asked me something similar yesterday.
The argument of keeping one skb for tx and one for rx makes some sense
to me,
On Thu, Mar 21, 2019 at 8:36 PM Alexei Starovoitov
wrote:
>
> On Wed, Mar 20, 2019 at 09:49:34PM -0700, Eric Dumazet wrote:
> >
> >
> > On 03/08/2019 04:29 PM, Alexei Starovoitov wrote:
> > > On Fri, Mar 8, 2019 at 12:33 PM Eric Dumazet
> > > wrote:
> > >>
> > >> Running test_progs on a LOCKDEP
From: David Ahern
The number of stubs is growing and has nothing to do with addrconf.
Move the definition of the stubs to a separate header file and update
users. In the move, drop the vxlan specific comment before ipv6_stub.
Code move only; no functional change intended.
Signed-off-by: David A
From: Johannes Berg
Tag all the nl80211 policies with strict_start_type so that
strict validation is done for all types that we have a policy
for.
Signed-off-by: Johannes Berg
---
net/wireless/nl80211.c | 22 ++
1 file changed, 22 insertions(+)
diff --git a/net/wireless/nl
From: Johannes Berg
Rather than using NLA_UNSPEC for this type of thing, use NLA_MIN_LEN
so we can make NLA_UNSPEC be NLA_REJECT under certain conditions for
future attributes.
While at it, also use NLA_EXACT_LEN for the struct example.
Signed-off-by: Johannes Berg
---
include/net/netlink.h |
From: Johannes Berg
Unfortunately, we cannot add strict parsing for all attributes, as
that would break existing userspace. We currently warn about it, but
that's about all we can do.
For new attributes, however, the story is better: nobody is using
them, so we can reject bad sizes.
Also, for n
This version gets us to where I wanted to be:
strict parsing
commandattribute attribute message
oldold --
oldnew X-
new*XX
Additionally, it does lots of cross-tree renam
From: Johannes Berg
This re-adds the parse and validate functions like nla_parse()
that are now actually strict after the previous rename and were
just split out to make sure everything is converted (and if not
compilation of the previous patch would fail.)
Signed-off-by: Johannes Berg
---
inc
From: Johannes Berg
Add options to strictly validate messages and dump messages,
sometimes perhaps validating dump messages non-strictly may
be required, so add an option for that as well.
Since none of this can really be applied to existing commands,
set the options everwhere using the followin
On Tue, Mar 19, 2019 at 03:39:19PM +, Jeremy Sowden wrote:
> Some fixes for the initialization and clean-up of the ipip tunnel.
>
> Jeremy Sowden (2):
> vti4: ipip tunnel deregistration fixes.
> vti4: removed duplicate log message.
Both patches applied, thanks!
tcp_clock_ns() (aka ktime_get_ns()) is using monotonic clock,
so the checks we had in tcp_mstamp_refresh() are no longer
relevant.
This patch removes cpu stall (when the cache line is not hot)
Signed-off-by: Eric Dumazet
---
net/ipv4/tcp_output.c | 8 ++--
1 file changed, 2 insertions(+), 6
Thu, Mar 21, 2019 at 06:42:55PM CET, pa...@mellanox.com wrote:
>
>
>> -Original Message-
>> From: Jiri Pirko
>> Sent: Thursday, March 21, 2019 12:24 PM
>> To: Parav Pandit
>> Cc: Jakub Kicinski ; Samudrala, Sridhar
>> ; da...@davemloft.net;
>> netdev@vger.kernel.org; oss-driv...@netronome
Fri, Mar 22, 2019 at 10:16:34AM CET, vasundhara-v.vo...@broadcom.com wrote:
>On Thu, Mar 21, 2019 at 6:50 PM Jiri Pirko wrote:
>>
>> From: Jiri Pirko
>>
>> devlink functions are in use, so include the related header file.
>>
>> Signed-off-by: Jiri Pirko
>> ---
>> drivers/net/ethernet/broadcom/b
Thu, Mar 21, 2019 at 08:08:24PM CET, jakub.kicin...@netronome.com wrote:
>On Thu, 21 Mar 2019 14:20:14 +0100, Jiri Pirko wrote:
>> From: Jiri Pirko
>>
>> The netdevice is guaranteed to not disappear so we can rely that
>> devlink_port and devlink won't disappear as well. No need to take
>> devlin
On 03/22/2019 01:30 AM, Paolo Abeni wrote:
> The queue is marked not empty after acquiring the seqlock,
> and it's up to the NOLOCK qdisc clearing such flag on dequeue.
> Since the empty status lays on the same cache-line of the
> seqlock, it's always hot on cache during the updates.
>
>
>
On 03/22/2019 01:30 AM, Paolo Abeni wrote:
> With commit c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array")
> pfifo_fast no longer benefit from the TCQ_F_CAN_BYPASS optimization.
> Due to retpolines the cost of the enqueue()/dequeue() pair has become
> relevant and we observe measurable regre
Conndscp is a new tc filter action module. It is designed to copy DSCPs
to conntrack marks and the reverse operation of conntrack mark contained
DSCPs to the diffserv field of suitable skbs.
The feature is intended for use and has been found useful for restoring
ingress classifications based on e
From: Boris Pismenny
Date: Thu, 21 Mar 2019 16:29:02 +0200
> User applications are forced to define the SOL_TLS manually at the
> moment, which is inappropriate. Add SOL_TLS to the uapi.
>
> Other protocols handle this similarly. For example see SOL_TIPC.
>
> Signed-off-by: Boris Pismenny
> --
From: Heiner Kallweit
Date: Thu, 21 Mar 2019 21:08:35 +0100
> Aquantia PHY's of the AQR107 family support the downshift feature.
> Add support for it as standard PHY tunable so that it can be controlled
> via ethtool.
> The AQCS109 supports a proprietary 2-pair 1Gbps mode. If two such PHY's
> are
On 3/22/2019 3:24 PM, David Miller wrote:
> From: Boris Pismenny
> Date: Thu, 21 Mar 2019 16:29:02 +0200
>
>> User applications are forced to define the SOL_TLS manually at the
>> moment, which is inappropriate. Add SOL_TLS to the uapi.
>>
>> Other protocols handle this similarly. For example s
From: Heiner Kallweit
Date: Thu, 21 Mar 2019 21:23:14 +0100
> After the original patch network starts to crash on heavy load.
> It's not fully clear why this additional register read has such side
> effects, but removing it fixes the issue.
>
> Thanks also to Alex for his contribution and hints.
From: Heiner Kallweit
Date: Thu, 21 Mar 2019 21:41:48 +0100
> Replace the call to netif_wake_queue in rtl8169_start_xmit with
> netif_start_queue as we don't need to actually wake up the queue since
> we are still in mid transmit so we just need to reset the bit so it
> doesn't prevent the next t
From: Johannes Berg
Date: Thu, 21 Mar 2019 22:51:02 +0100
> From: Johannes Berg
>
> Since maxattr is common, the policy can't really differ sanely,
> so make it common as well.
>
> The only user that did in fact manage to make a non-common policy
> is taskstats, which has to be really careful
Hi Eric,
I love your patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Eric-Dumazet/tcp-add-rx-tx-cache-to-reduce-lock-contention/20190322-215506
config: i386-randconfig-x005-201911 (attached as .config)
compiler
On 22/03/2019 at 11:49, Alexander Dahl wrote:
> External E-Mail
>
>
> Hei hei,
>
> while bringing up support for a new SAMA5D27 based board I noticed something
> strange in the macb driver in both U-Boot and Linux. There's a function in
> both to determine if or not the IP block in the SoC is th
From: Soheil Hassas Yeganeh
Add documentation to the tcp_ca_state enum, since this enum is
exposed in uapi.
Signed-off-by: Neal Cardwell
Signed-off-by: Yuchung Cheng
Signed-off-by: Eric Dumazet
Signed-off-by: Soheil Hassas Yeganeh
Cc: Sowmini Varadhan
---
include/uapi/linux/tcp.h | 27
Hi Eric,
I love your patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Eric-Dumazet/tcp-add-rx-tx-cache-to-reduce-lock-contention/20190322-215506
config: x86_64-randconfig-x016-201911 (attached as .config)
compiler: gcc
This patch series is aimed at improving xmit performances of lockless qdisc
in the uncontended scenario.
After the lockless refactor pfifo_fast can't leverage the BYPASS optimization.
Due to retpolines the overhead for the avoidables enqueue and dequeue operations
has increased and we see measurab
With commit c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array")
pfifo_fast no longer benefit from the TCQ_F_CAN_BYPASS optimization.
Due to retpolines the cost of the enqueue()/dequeue() pair has become
relevant and we observe measurable regression for the uncontended
scenario when the packet-rat
The queue is marked not empty after acquiring the seqlock,
and it's up to the NOLOCK qdisc clearing such flag on dequeue.
Since the empty status lays on the same cache-line of the
seqlock, it's always hot on cache during the updates.
This makes the empty flag update a little bit loosy. Given
the l
On (03/22/19 10:59), Soheil Hassas Yeganeh wrote:
>
> Add documentation to the tcp_ca_state enum, since this enum is
> exposed in uapi.
Acked-by: Sowmini Varadhan
From: Willem de Bruijn
BPF allows for dynamic tunneling, choosing the tunnel destination and
features on-demand. Extend bpf_skb_adjust_room to allow for efficient
tunneling at the TC hooks.
Most features are required for large packets with GSO, as these will
be modified after this patch.
Patch
From: Willem de Bruijn
bpf_skb_adjust_room calls skb_cow on grow.
This expensive operation can be avoided in the fast path when the only
other clone has released the header. This is the common case for TCP,
where one headerless clone is kept on the retransmit queue.
It is safe to do so even whe
From: Willem de Bruijn
The bpf tunnel test encapsulates using bpf, then decapsulates using
a standard tunnel device to verify correctness.
Once encap is verified, also test decap, by replacing the tunnel
device on decap with another bpf program.
Signed-off-by: Willem de Bruijn
---
.../selftes
From: Willem de Bruijn
bpf_skb_adjust_room net allows inserting room in an skb.
Existing mode BPF_ADJ_ROOM_NET inserts room after the network header
by pulling the skb, moving the network header forward and zeroing the
new space.
Add new mode BPF_ADJUST_ROOM_MAC that inserts room after the mac
From: Willem de Bruijn
GRE is a commonly used protocol. Add GRE cases for both IPv4 and IPv6.
It also inserts different sized headers, which can expose some
unexpected edge cases.
Signed-off-by: Willem de Bruijn
---
.../selftests/bpf/progs/test_tc_tunnel.c | 148 +-
tools
From: Willem de Bruijn
Sync include/uapi/linux/bpf.h with tools/
Changes v1->v2:
- BPF_F_ADJ_ROOM_MASK moved, no longer in this commit
Signed-off-by: Willem de Bruijn
---
tools/include/uapi/linux/bpf.h | 32 +---
1 file changed, 29 insertions(+), 3 deletions(-)
From: Willem de Bruijn
The test only uses ipv4 so far, expand to ipv6.
This is mostly a boilerplate near copy of the ipv4 path.
Signed-off-by: Willem de Bruijn
---
tools/testing/selftests/bpf/config| 2 +
.../selftests/bpf/progs/test_tc_tunnel.c | 116 +++---
too
From: Willem de Bruijn
Segmentation offload takes a longer path. Verify that the feature
works with large packets.
The test succeeds if not setting dodgy in bpf_skb_adjust_room, as veth
TSO is permissive.
If not setting SKB_GSO_DODGY, this enables tunneled TSO offload on
supporting NICs.
The f
From: Willem de Bruijn
When pushing tunnel headers, annotate skbs in the same way as tunnel
devices.
For GSO packets, the network stack requires certain fields set to
segment packets with tunnel headers. gro_gse_segment depends on
transport and inner mac header, for instance.
Add an option to p
From: Willem de Bruijn
bpf_skb_adjust_room adjusts gso_size of gso packets to account for the
pushed or popped header room.
This is not allowed with UDP, where gso_size delineates datagrams. Add
an option to avoid these updates and allow this call for datagrams.
It can also be used with TCP, wh
From: Willem de Bruijn
Validate basic tunnel encapsulation using ipip.
Set up two namespaces connected by veth. Connect a client and server.
Do this with and without bpf encap.
Signed-off-by: Willem de Bruijn
---
tools/testing/selftests/bpf/Makefile | 3 +-
.../selftests/bpf/progs/t
From: Willem de Bruijn
Avoid moving the network layer header when prefixing tunnel headers.
This avoids an explicit call to bpf_skb_store_bytes and an implicit
move of the network header bytes in bpf_skb_adjust_room.
Signed-off-by: Willem de Bruijn
---
.../selftests/bpf/progs/test_tc_tunnel.c
From: Willem de Bruijn
Lower route MTU to ensure packets fit in device MTU after encap, then
skip the gso_size changes.
Signed-off-by: Willem de Bruijn
---
tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 11 ---
tools/testing/selftests/bpf/test_tc_tunnel.sh | 6 ++
2 fil
From: Willem de Bruijn
Make the tests correctly annotate skbs with tunnel metadata.
This makes the gso tests succeed. Enable them.
Signed-off-by: Willem de Bruijn
---
.../selftests/bpf/progs/test_tc_tunnel.c | 19 +++
tools/testing/selftests/bpf/test_tc_tunnel.sh | 10 +++
On 03/22/2019 08:01 AM, Paolo Abeni wrote:
> The queue is marked not empty after acquiring the seqlock,
> and it's up to the NOLOCK qdisc clearing such flag on dequeue.
> Since the empty status lays on the same cache-line of the
> seqlock, it's always hot on cache during the updates.
>
> This m
On 03/22/2019 08:00 AM, kbuild test robot wrote:
> Hi Eric,
>
> I love your patch! Yet something to improve:
>
> [auto build test ERROR on net-next/master]
>
> url:
> https://github.com/0day-ci/linux/commits/Eric-Dumazet/tcp-add-rx-tx-cache-to-reduce-lock-co
On 22. 03. 19 16:01, Paolo Abeni wrote:
The queue is marked not empty after acquiring the seqlock,
and it's up to the NOLOCK qdisc clearing such flag on dequeue.
Since the empty status lays on the same cache-line of the
seqlock, it's always hot on cache during the updates.
This makes the empty f
On Fri, Mar 22, 2019 at 8:15 AM Willem de Bruijn
wrote:
>
> +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
> +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
> +#define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
> +BPF_F_ADJ_ROO
On Fri, 22 Mar 2019 08:40:17 +0100
"Harald Albrecht" wrote:
> This is a first for me to appear on the Linux kernel netdev list, so please
> bear with me while killing me...
>
> For diagnosing Linux virtual networking I need to relate TAP/TUN network
> interfacces to the user space processes th
Not sure if this a new problem, or just another case of
"don't expect fragmented packets to be reliable".
Begin forwarded message:
Date: Thu, 21 Mar 2019 22:42:41 +
From: bugzilla-dae...@bugzilla.kernel.org
To: step...@networkplumber.org
Subject: [Bug 202997] New: High UDP traffic results in
On Fri, Mar 22, 2019 at 11:44 AM Alexei Starovoitov
wrote:
>
> On Fri, Mar 22, 2019 at 8:15 AM Willem de Bruijn
> wrote:
> >
> > +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
> > +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2)
> > +#define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_
From: Eric Dumazet
Per listen(fd, backlog) rules, there is really no point accepting a SYN,
sending a SYNACK, and dropping the following ACK packet if accept queue
is full, because application is not draining accept queue fast enough.
This behavior is fooling TCP clients that believe they establ
On hosts with many cpus we can observe a very serious contention
on spinlocks used in mm slab layer.
The following can happen quite often :
1) TX path
sendmsg() allocates one (fclone) skb on CPU A, sends a clone.
ACK is received on CPU B, and consumes the skb that was in the retransmit
queu
We prefer static_branch_unlikely() over static_key_false() these days.
Signed-off-by: Eric Dumazet
Acked-by: Soheil Hassas Yeganeh
Acked-by: Willem de Bruijn
---
drivers/net/tun.c | 2 +-
include/linux/netdevice.h | 4 ++--
include/net/sock.h | 2 +-
net/core/dev.c
On hosts with a lot of cores, RPC workloads suffer from heavy contention on
slab spinlocks.
20.69% [kernel] [k] queued_spin_lock_slowpath
5.64% [kernel] [k] _raw_spin_lock
3.83% [kernel] [k] syscall_return_via_sysret
3.48% [kernel] [k] __entry_text_s
Often times, recvmsg() system calls and BH handling for a particular
TCP socket are done on different cpus.
This means the incoming skb had to be allocated on a cpu,
but freed on another.
This incurs a high spinlock contention in slab layer for small rpc,
but also a high number of cache line ping
Hi Eric,
I love your patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Eric-Dumazet/net-convert-rps_needed-and-rfs_needed-to-new-static-branch-api/20190322-211954
config: ia64-allmodconfig (attached as .config)
compiler
On Fri, Mar 22, 2019 at 8:48 AM Willem de Bruijn
wrote:
>
> On Fri, Mar 22, 2019 at 11:44 AM Alexei Starovoitov
> wrote:
> >
> > On Fri, Mar 22, 2019 at 8:15 AM Willem de Bruijn
> > wrote:
> > >
> > > +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1)
> > > +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6
On Thu, Mar 21, 2019 at 3:51 PM Saeed Mahameed wrote:
>
> Hi Dave,
>
> This series includes mlx5 updates.
> For more information please see tag log below.
>
> Please pull and let me know if there is any problem.
>
Hi Dave, I would like to re-spin and send V3 to move one patch out of
this series i
On Fri, Mar 22, 2019 at 06:06:09AM -0700, David Ahern wrote:
> From: David Ahern
>
> The number of stubs is growing and has nothing to do with addrconf.
> Move the definition of the stubs to a separate header file and update
> users. In the move, drop the vxlan specific comment before ipv6_stub.
On 3/22/19 5:14 PM, Alexei Starovoitov wrote:
> On Fri, Mar 22, 2019 at 06:06:09AM -0700, David Ahern wrote:
>> From: David Ahern
>>
>> The number of stubs is growing and has nothing to do with addrconf.
>> Move the definition of the stubs to a separate header file and update
>> users. In the move
On Fri, Mar 22, 2019 at 12:11 PM Alexei Starovoitov
wrote:
>
> On Fri, Mar 22, 2019 at 8:48 AM Willem de Bruijn
> wrote:
> >
> > On Fri, Mar 22, 2019 at 11:44 AM Alexei Starovoitov
> > wrote:
> > >
> > > On Fri, Mar 22, 2019 at 8:15 AM Willem de Bruijn
> > > wrote:
> > > >
> > > > +#define BPF_
On 3/22/2019 5:56 PM, Eric Dumazet wrote:
On hosts with many cpus we can observe a very serious contention
on spinlocks used in mm slab layer.
The following can happen quite often :
1) TX path
sendmsg() allocates one (fclone) skb on CPU A, sends a clone.
ACK is received on CPU B, and c
Thu, Mar 21, 2019 at 06:34:22PM CET, pa...@mellanox.com wrote:
>
>
>> -Original Message-
>> From: Jiri Pirko
>> Sent: Thursday, March 21, 2019 12:21 PM
>> To: Parav Pandit
>> Cc: Jakub Kicinski ; Samudrala, Sridhar
>> ; da...@davemloft.net;
>> netdev@vger.kernel.org; oss-driv...@netronome
On Fri, Mar 22, 2019 at 9:37 AM Tariq Toukan wrote:
>
>
>
> Hi Eric,
>
> Does this have any effect on non tcp traffic?
Of course not :)
From: Jiri Pirko
Set the attrs properly so delink has enough info to generate physical
port names.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
b/drivers/
From: Jiri Pirko
Add missing called to mutex_destroy() for two mutexes used
in devlink code.
Signed-off-by: Jiri Pirko
---
net/core/devlink.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 78e22cea4cc7..3dc51ddf7451 100644
--- a/net/core/dev
From: Jiri Pirko
Mostly cosmetics and janitor work.
Jiri Pirko (15):
net: devlink: add couple of missing mutex_destroy() calls
bnxt: add missing net/devlink.h include
dsa: add missing net/devlink.h include
bnxt: set devlink port attrs properly
bnxt: call devlink_port_type_eth_set() bef
From: Jiri Pirko
devlink functions are in use, so include the related header file.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
b/drivers/net/ethernet/broad
From: Jiri Pirko
devlink functions are in use, so include the related header file.
Signed-off-by: Jiri Pirko
Reviewed-by: Andrew Lunn
---
net/dsa/dsa2.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index c00ee464afc7..4558de672b4f 100644
--- a/net/dsa/ds
From: Jiri Pirko
__devlink_port_type_set() returns void, it makes no sense to pass it on,
so don't do that.
Signed-off-by: Jiri Pirko
---
net/core/devlink.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 1e125c3b890c..
From: Jiri Pirko
Since the port attributes are static and cannot change during the port
lifetime, WARN_ON if some driver calls it after registration. Also, no
need to call notifications as it is noop anyway due to check of
devlink_port->registered there.
Signed-off-by: Jiri Pirko
---
net/core/
From: Jiri Pirko
The netdevice is guaranteed to not disappear so we can rely that
devlink_port and devlink won't disappear as well. No need to take
devlink_mutex so don't take it here.
Signed-off-by: Jiri Pirko
---
net/core/devlink.c | 18 --
1 file changed, 8 insertions(+), 10
From: Jiri Pirko
Since attrs are static during the existence of devlink port, set the
before registration of the port.
Signed-off-by: Jiri Pirko
---
v1->v2:
- fixed comment for port numbering
---
net/dsa/dsa2.c | 47 ++-
1 file changed, 26 insertions
From: Jiri Pirko
Call devlink_port_type_eth_set() before devlink_port_register(). Bnxt
instances won't change type during lifetime. This avoids one extra
userspace devlink notification.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 2 +-
1 file changed, 1 in
From: Jiri Pirko
Add spinlock to protect port type and type_dev pointer consistency.
Without that, userspace may see inconsistent type and type_dev
combinations.
Signed-off-by: Jiri Pirko
v1->v2:
- rebased
---
include/net/devlink.h | 4
net/core/devlink.c| 17 +
2 fil
From: Jiri Pirko
Some drivers are becoming more dependent on NET_DEVLINK being selected
in configuration. With upcoming compat functions, the behavior would be
wrong in case devlink was not compiled in. So make the drivers select
NET_DEVLINK and rely on the functions being there, not just stubs.
From: Jiri Pirko
Similar to other driver, move the port type set after netdev registration
is done. Along with that, clear the type before unregistration.
Signed-off-by: Jiri Pirko
---
v1->v2:
- new patch
---
drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 11 ++-
drivers/net/ether
From: Jiri Pirko
Move the type set of devlink port after it is registered.
Signed-off-by: Jiri Pirko
---
v1->v2:
- new patch
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink
From: Jiri Pirko
Since attrs are static during the existence of devlink port, set the
before registration of the port.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/mellanox/mlxsw/core.c | 12 ++--
drivers/net/ethernet/mellanox/mlxsw/core.h | 8
drivers/net/ether
From: Jiri Pirko
Port needs to be registered first before the type is set. Warn and
bail-out in case it is not.
Signed-off-by: Jiri Pirko
---
v1->v2:
- new patch
---
net/core/devlink.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index f77a68f72
On Fri, Mar 22, 2019 at 05:17:52PM +0100, David Ahern wrote:
> On 3/22/19 5:14 PM, Alexei Starovoitov wrote:
> > On Fri, Mar 22, 2019 at 06:06:09AM -0700, David Ahern wrote:
> >> From: David Ahern
> >>
> >> The number of stubs is growing and has nothing to do with addrconf.
> >> Move the definitio
On Thu, 21 Mar 2019 09:32:39 +0100
Tobias Jungel wrote:
> This adds configuration for the IFLA_BRPORT_MCAST_TO_UCAST flag that
> allows multicast packets to be replicated as unicast packets.
>
> Signed-off-by: Tobias Jungel
Applied.
And this motivated me to fix the long lines in the man pages
On Fri, Mar 22, 2019 at 5:37 AM John Hurley wrote:
>
> A new mirred action is created by the tcf_mirred_init function. This
> contains a list head struct which is inserted into a global list on
> successful creation of a new action. However, after a creation, it is
> still possible to error out an
From: Yashaswini Raghuram Prathivadi Bhayankaram
The LAN_EN bit for a switch rule determines if the packet can go out
on the wire or not. Set the LAN_EN flag in the switch action for all
directional rules.
Signed-off-by: Yashaswini Raghuram Prathivadi Bhayankaram
Signed-off-by: Anirudh Venkat
From: Akeem G Abodunrin
Don't let the VF know it's not trusted when it tries to add more than
permitted additional MAC addresses.
Signed-off-by: Akeem G Abodunrin
Signed-off-by: Anirudh Venkataramanan
Tested-by: Andrew Bowers
Signed-off-by: Jeff Kirsher
---
drivers/net/ethernet/intel/ice/ic
This series contains updates to ice driver only.
Akeem enables MAC anti-spoofing by default when a new VSI is being
created. Fixes an issue when reclaiming VF resources back to the pool
after reset, by freeing VF resources separately using the first VF
vector index to traverse the list, instead o
From: Victor Raj
This patch does some clean up in the Tx scheduler code:
1. Adjust the stack variable usage
2. Modify the debug prints to display the FW error
3. Add additional debug prints while adding/removing VSIs
Signed-off-by: Victor Raj
Reviewed-by: Bruce Allan
Signed-off-by: Anirudh Ve
From: Bruce Allan
Put the return type on a separate line for function prototypes and
signatures that would exceed the 80-character limit if both were on
the same line.
Signed-off-by: Bruce Allan
Signed-off-by: Anirudh Venkataramanan
Tested-by: Andrew Bowers
Signed-off-by: Jeff Kirsher
---
d
From: Akeem G Abodunrin
This patch enables MAC anti-spoof by default, with creation of VF VSIs or
when the VF VSIs are being re-initialized.
Signed-off-by: Akeem G Abodunrin
Signed-off-by: Anirudh Venkataramanan
Tested-by: Andrew Bowers
Signed-off-by: Jeff Kirsher
---
drivers/net/ethernet/i
1 - 100 of 192 matches
Mail list logo
