Tue, Oct 15, 2019 at 12:10:49AM CEST, pa...@netfilter.org wrote:
>Drivers perform a bitwise AND on the value and the mask. Update
>tc_setup_flow_action() to perform this operation so drivers do not need
>to do this.
>
>Remove sanity check for sane value and mask values from the nfp driver,
>the fro
Tue, Oct 15, 2019 at 12:10:48AM CEST, pa...@netfilter.org wrote:
>Userspace tc pedit action performs a bitwise NOT operation on the mask.
>All of the existing drivers in the tree undo this operation. Prepare the
>mangle mask in the way the drivers expect from the
>tc_setup_flow_action() function.
>
On Mon, Oct 14, 2019 at 01:20:35PM +0530, Vishal Kulkarni wrote:
> Release resources when attaching to ULD fail. Otherwise, data
> mismatch is seen between LLD and ULD later on, which lead to
> kernel panic when accessing resources that should not even
> exist in the first place.
>
> Fixes: 94cdb8
On 10/7/19 4:16 AM, Davide Caratti wrote:
> now that INET_DIAG_INFO requests can dump TCP ULP information, extend 'ss'
> to allow diagnosing kTLS when it is attached to a TCP socket. While at it,
> import kTLS uAPI definitions from the latest net-next tree.
>
> CC: Andrea Claudi
> Co-developed-by
Hi Michael,
Thanks for reviewing.
On 10/13/19 5:41 AM, Michael S. Tsirkin wrote:
On Sat, Oct 12, 2019 at 10:53:56AM +0900, prashantbhole.li...@gmail.com wrote:
From: Prashant Bhole
Currently vhost_net directly accesses ptr ring of tap driver to
fetch Rx packet pointers. In order to avoid it t
Hi Jason,
Thanks for reviewing.
On 10/12/19 4:44 PM, Jason Wang wrote:
On 2019/10/12 上午9:53, prashantbhole.li...@gmail.com wrote:
From: Prashant Bhole
In order to extend the usage of tun_msg_ctl structure, this patch
changes the member name from type to cmd. Also following definitions
are ch
BTF offset reloc was generalized in recent Clang into field relocation,
capturing extra u32 field, specifying what aspect of captured field
needs to be relocated. This changes .BTF.ext's record size for this
relocation from 12 bytes to 16 bytes. Given these format changes
happened in Clang before o
Add enum definition for Clang's __builtin_preserve_field_info()
second argument (info_kind). Currently only byte offset and existence
are supported. Corresponding Clang changes introducing this built-in can
be found at [0]
[0] https://reviews.llvm.org/D67980
Signed-off-by: Andrii Nakryiko
---
This patch set generalizes libbpf's CO-RE relocation support. It not supports
field existence relocations, in addition to existing field's byte offset
relocation.
This patch set upgrades the format of .BTF.ext's relocation record to match
latest Clang's format (12 -> 16 bytes). This is not a bre
Refactor all the various bpf_object__open variations to ultimately
specify common bpf_object_open_opts struct. This makes it easy to keep
extending this common struct w/ extra parameters without having to
update all the legacy APIs.
Signed-off-by: Andrii Nakryiko
---
tools/lib/bpf/libbpf.c | 71
Add a bunch of tests validating CO-RE is handling field existence
relocation. Relaxed CO-RE relocation mode is activated for these new
tests to prevent libbpf from rejecting BPF object for no-match
relocation, even though test BPF program is not going to use that
relocation, if field is missing.
S
Add support for BPF_FRK_EXISTS relocation kind to detect existence of
captured field in a destination BTF, allowing conditional logic to
handle incompatible differences between kernels.
Also introduce opt-in relaxed CO-RE relocation handling option, which
makes libbpf emit warning for failed reloc
From: Richard Cochran
Date: Sat, 12 Oct 2019 12:14:54 -0700
> On Sat, Oct 12, 2019 at 02:18:12AM +0300, Vladimir Oltean wrote:
>> This series creates a better separation between the driver core and the
>> PTP portion. Therefore, users who are not interested in PTP can get a
>> simpler and smaller
Murali Karicheri writes:
>
> My expectation is as follows
>
> AABCDE
>
> Where A is traffic from TC0, B is udp stream for port 1
> C is stream for port 2, D for 3 and E for 4.
> Each can be max of 4 msec. Is the expection correct? At least th
Vladimir Oltean writes:
>
> What do you mean taprio doesn't support tc filter blocks? What do you
> think there is to do in taprio to support that?
> I don't think Murali is asking for filter offloading, but merely for a
> way to direct frames to a certain traffic class on xmit from Linux.
> Some
On 10/10/2019 1:42 AM, Tonghao Zhang wrote:
On Wed, Oct 9, 2019 at 1:33 AM Gregory Rose wrote:
[snip]
Hi Tonghao,
I've applied your patch series and built a 5.4.0-rc1 kernel with them.
x@ubuntu-1604:~$ modinfo openvswitch
filename: /lib/modules/5.4.0-rc1+/kernel/net/openvswitch/openv
Added TDC test cases for Ethernet LAYERED_OP operations:
- set single source Ethernet MAC
- set single destination Ethernet MAC
- set single invalid destination Ethernet MAC
- set Ethernet type
- invert source/destination/type fields
- add operation on Ethernet type field
Signed-off-by: Roman Mash
On Mon, Oct 14, 2019 at 10:20:15PM +0200, Heiner Kallweit wrote:
> On 14.10.2019 21:51, Stefan Wahren wrote:
> > [add more recipients]
> >
> > Am 14.10.19 um 21:25 schrieb Daniel Wagner:
> >> Moving the phy_prepare_link() up in phy_connect_direct() ensures that
> >> phydev->adjust_link is set when
Userspace tc pedit action performs a bitwise NOT operation on the mask.
All of the existing drivers in the tree undo this operation. Prepare the
mangle mask in the way the drivers expect from the
tc_setup_flow_action() function.
Signed-off-by: Pablo Neira Ayuso
---
v5: no changes.
drivers/net/e
This patch allows for mangling packet fields using hardware offload
infrastructure.
Signed-off-by: Pablo Neira Ayuso
---
v5: no changes.
net/netfilter/nft_payload.c | 73 +
1 file changed, 73 insertions(+)
diff --git a/net/netfilter/nft_payload.c b/n
Drivers perform a bitwise AND on the value and the mask. Update
tc_setup_flow_action() to perform this operation so drivers do not need
to do this.
Remove sanity check for sane value and mask values from the nfp driver,
the front-end already guarantees this after this patch.
Signed-off-by: Pablo
This patch updates the mangle action representation:
Patch 1) Undo bitwise NOT operation on the mangle mask (coming from tc
pedit userspace).
Patch 2) mangle value &= mask from the front-end side.
Patch 3) adjust offset, length and coalesce consecutive pedit keys into
one singl
The flow mangle action is originally modeled after the tc pedit action,
this has a number of shortcomings:
1) The tc pedit offset must be set on the 32-bits boundaries. Many
protocol header field offsets are not aligned to 32-bits, eg. port
destination, port source and ethernet destination.
On Tue, Oct 15, 2019 at 12:00:23AM +0200, Pablo Neira Ayuso wrote:
> This patch updates the mangle action representation:
[...]
Scratch this patchset, it is garbled. Sorry about this.
The flow mangle action is originally modeled after the tc pedit action,
this has a number of shortcomings:
1) The tc pedit offset must be set on the 32-bits boundaries. Many
protocol header field offsets are not aligned to 32-bits, eg. port
destination, port source and ethernet destination.
Signed-off-by: Pablo Neira Ayuso
---
include/net/flow_offload.h| 3 ++
net/core/flow_offload.c | 85 +++
net/netfilter/nf_tables_offload.c | 6 ++-
net/sched/cls_flower.c| 4 ++
4 files changed, 97 insertions(+), 1 deletion(-)
Drivers perform a bitwise AND on the value and the mask. Update
tc_setup_flow_action() to perform this operation so drivers do not need
to do this.
Remove sanity check for sane value and mask values from the nfp driver,
the front-end already guarantees this after this patch.
Signed-off-by: Pablo
This patch updates the mangle action representation:
Patch 1) Undo bitwise NOT operation on the mangle mask (coming from tc
pedit userspace).
Patch 2) mangle value &= mask from the front-end side.
Patch 3) adjust offset, length and coalesce consecutive pedit keys into
one singl
This patch allows for mangling packet fields using hardware offload
infrastructure.
Signed-off-by: Pablo Neira Ayuso
---
net/netfilter/nft_payload.c | 73 +
1 file changed, 73 insertions(+)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_
When a application sends many packets with the same txtime, they may
be transmitted out of order (different from the order in which they
were enqueued).
This happens because when inserting elements into the tree, when the
txtime of two packets are the same, the new packet is inserted at the
left s
On 14.10.2019 21:51, Stefan Wahren wrote:
> [add more recipients]
>
> Am 14.10.19 um 21:25 schrieb Daniel Wagner:
>> On Mon, Oct 14, 2019 at 05:30:04PM +0100, Russell King - ARM Linux admin
>> wrote:
>>> On Mon, Oct 14, 2019 at 04:06:04PM +0200, Daniel Wagner wrote:
Hi,
I've trying
On Mon, 7 Oct 2019 15:44:47 +0200
Nicolas Dichtel wrote:
> This patch enables to dump/get nsid from a netns into another netns.
>
> Example:
> $ ./test.sh
> + ip netns add foo
> + ip netns add bar
> + touch /var/run/netns/init_net
> + mount --bind /proc/1/ns/net /var/run/netns/init_net
> + ip n
On Mon, Oct 14, 2019 at 12:18 PM David Miller wrote:
>
> From: Alexei Starovoitov
> Date: Mon, 14 Oct 2019 12:06:20 -0700
>
> > The following pull-request contains BPF updates for your *net-next* tree.
> >
> > 12 days of development and
> > 85 files changed, 1889 insertions(+), 1020 deletions(-)
[add more recipients]
Am 14.10.19 um 21:25 schrieb Daniel Wagner:
> On Mon, Oct 14, 2019 at 05:30:04PM +0100, Russell King - ARM Linux admin
> wrote:
>> On Mon, Oct 14, 2019 at 04:06:04PM +0200, Daniel Wagner wrote:
>>> Hi,
>>>
>>> I've trying to boot a RPi 3 Model B+ in 64 bit mode. While I can
From: Alexei Starovoitov
Date: Mon, 14 Oct 2019 12:06:20 -0700
> The following pull-request contains BPF updates for your *net-next* tree.
>
> 12 days of development and
> 85 files changed, 1889 insertions(+), 1020 deletions(-)
This is nice, do you have a script which generates this?
> The mai
Hi David,
The following pull-request contains BPF updates for your *net-next* tree.
12 days of development and
85 files changed, 1889 insertions(+), 1020 deletions(-)
The main changes are:
1) auto-generation of bpf_helper_defs.h, from Andrii.
2) split of bpf_helpers.h into bpf_{helpers, helper
John Fastabend writes:
> Toke Høiland-Jørgensen wrote:
>> Alexei Starovoitov writes:
>>
>> > On Wed, Oct 09, 2019 at 10:03:43AM +0200, Toke Høiland-Jørgensen wrote:
>> >> Alexei Starovoitov writes:
>> >>
>> >> > Please implement proper indirect calls and jumps.
>> >>
>> >> I am still not con
On Mon, Oct 14, 2019 at 10:39 AM Peter Oskolkov wrote:
>
> On Sat, Oct 12, 2019 at 9:59 AM Alexei Starovoitov
> wrote:
> >
> > On Wed, Oct 9, 2019 at 1:31 AM Jiri Benc wrote:
> > >
> > > The dst in bpf_input() has lwtstate field set. As it is of the
> > > LWTUNNEL_ENCAP_BPF type, lwtstate->data
From: Sabrina Dubroca
Date: Fri, 11 Oct 2019 16:57:23 +0200
> This patchset introduces support for TCP encapsulation of IKE and ESP
> messages, as defined by RFC 8229 [0]. It is an evolution of what
> Herbert Xu proposed in January 2018 [1] that addresses the main
> criticism against it, by not i
tc_ctl_action() has the ability to loop forever if tcf_action_add()
returns -EAGAIN.
This special case has been done in case a module needed to be loaded,
but it turns out that tcf_add_notify() could also return -EAGAIN
if the socket sk_rcvbuf limit is hit.
We need to separate the two cases, and
After commit eeb84aa0d0aff ("net_sched: sch_fq: do not assume EDT
packets are ordered"), all skbs get a non zero time_to_send
in flow_queue_add()
This means @time_next_packet variable in fq_dequeue()
can no longer be zero.
Signed-off-by: Eric Dumazet
---
net/sched/sch_fq.c | 3 +--
1 file chang
On Sat, Oct 12, 2019 at 9:59 AM Alexei Starovoitov
wrote:
>
> On Wed, Oct 9, 2019 at 1:31 AM Jiri Benc wrote:
> >
> > The dst in bpf_input() has lwtstate field set. As it is of the
> > LWTUNNEL_ENCAP_BPF type, lwtstate->data is struct bpf_lwt. When the bpf
> > program returns BPF_LWT_REROUTE, ip_
On 9/30/19 11:45 AM, Ben Greear wrote:
On 9/22/19 12:23 PM, David Ahern wrote:
On 9/20/19 9:57 AM, Ben Greear wrote:
On 9/10/19 6:08 PM, Ben Greear wrote:
On 9/10/19 3:17 PM, Ben Greear wrote:
Today we were testing creating 200 virtual station vdevs on ath9k,
and using
VRF for the routing.
On Sun, Oct 13, 2019 at 05:23:01PM -0700, Wei Wang wrote:
> On Fri, Oct 11, 2019 at 11:56 PM Martin Lau wrote:
> >
> > On Fri, Oct 11, 2019 at 10:54:13AM -0700, Wei Wang wrote:
> > > On Fri, Oct 11, 2019 at 8:42 AM Ido Schimmel wrote:
> > > >
> > > > On Fri, Oct 11, 2019 at 09:36:51AM -0500, Jess
> -Original Message-
> From: Richard Cochran
> Sent: Saturday, October 12, 2019 4:27 PM
> To: Keller, Jacob E
> Cc: netdev@vger.kernel.org; Intel Wired LAN
> ;
> Kirsher, Jeffrey T ; Brandon Streiff
>
> Subject: Re: [net-next v3 3/7] mv88e6xxx: reject unsupported external
> timestamp fl
Toke Høiland-Jørgensen wrote:
> Alexei Starovoitov writes:
>
> > On Wed, Oct 09, 2019 at 10:03:43AM +0200, Toke Høiland-Jørgensen wrote:
> >> Alexei Starovoitov writes:
> >>
> >> > Please implement proper indirect calls and jumps.
> >>
> >> I am still not convinced this will actually solve our
On 10/11/19 1:35 PM, David Ahern wrote:
On 10/11/19 7:57 AM, Ben Greear wrote:
The down-up cycling is done on purpose - to clear out neigh entries and
routes associated with the device under the old VRF. All entries must be
created with the device in the new VRF.
I believe I found another thin
> --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
> +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c
> @@ -8,12 +8,24 @@
> */
>
> +static inline int aq_ptp_tm_offset_egress_get(struct aq_ptp_s *aq_ptp)
> +{
> + return atomic_read(&aq_ptp->offset_egress);
> +}
> +
> +static inline
> +static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic,
> +struct hwtstamp_config *config)
> +{
> + if (config->flags)
> + return -EINVAL;
> +
> + switch (config->tx_type) {
> + case HWTSTAMP_TX_OFF:
> + case HWTSTAMP_TX_ON:
> +
On Tue, Oct 08, 2019 at 10:56:45AM +, Igor Russkikh wrote:
> From: Dmitry Bezrukov
>
> Checkpatch and styling fixes on parts of code touched by ptp
>
> Signed-off-by: Dmitry Bezrukov
> Signed-off-by: Igor Russkikh
Reviewed-by: Andrew Lunn
Andrew
> @@ -978,7 +992,9 @@ void aq_nic_deinit(struct aq_nic_s *self)
> self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
> aq_vec_deinit(aq_vec);
>
> + aq_ptp_ring_deinit(self);
> aq_ptp_unregister(self);
> + aq_ptp_ring_free(self);
> aq_ptp_free(self);
Hi Vinicius,
Would like to branch off to a separate discussion on taprio testing
with multiple streams. Below is what I have discussed earlier in the
context of the other thread on 'Re: taprio testing - Any help?'
Could you please review the below and let me know if I am doing
anything wrong to c
On Sat, Oct 12, 2019 at 01:08:26PM -0700, Pravin Shelar wrote:
> On Wed, Oct 9, 2019 at 9:31 PM Martin Varghese
> wrote:
> >
> > On Wed, Oct 09, 2019 at 08:29:51AM -0700, Pravin Shelar wrote:
> > > On Mon, Oct 7, 2019 at 9:41 PM Martin Varghese
> > > wrote:
> > > >
> > > > From: Martin Varghese
On Tue, Oct 08, 2019 at 10:56:38AM +, Igor Russkikh wrote:
> From: Dmitry Bezrukov
>
> Make some other bit-enums more clear about positioning,
> this helps on debugging and development
>
> Signed-off-by: Dmitry Bezrukov
> Signed-off-by: Igor Russkikh
Reviewed-by: Andrew Lunn
Andrew
On 10/14/19 7:02 AM, Bartschies, Thomas wrote:
> Hello,
>
> it took a while to build a testsystem for bisecting the issue. Finally I've
> identified the patch that causes my problems.
> BTW. The fq packet network scheduler is in use.
>
> It's
> [PATCH net-next] tcp/fq: move back to CLOCK_MON
On 10/13/2019 05:10 PM, Vladimir Oltean wrote:
Hi Vinicius,
On Sat, 12 Oct 2019 at 00:28, Vinicius Costa Gomes
wrote:
Hi,
Murali Karicheri writes:
Hi Vinicius,
On 10/11/2019 04:12 PM, Vinicius Costa Gomes wrote:
Hi Murali,
Murali Karicheri writes:
Hi,
I am testing the taprio (802.1
Release resources when attaching to ULD fail. Otherwise, data
mismatch is seen between LLD and ULD later on, which lead to
kernel panic when accessing resources that should not even
exist in the first place.
Fixes: 94cdb8bb993a ("cxgb4: Add support for dynamic allocation of resources
for ULD")
Si
On Sun, Oct 13, 2019 at 11:24:04PM +0200, Marek Vasut wrote:
> The KSZ8795 PHY ID is in fact used by KSZ8794/KSZ8795/KSZ8765 switches.
> Update the PHY ID and name to reflect that, as this family of switches
> is commonly refered to as KSZ87xx
>
> Signed-off-by: Marek Vasut
Reviewed-by: Andrew L
On Sun, Oct 13, 2019 at 11:24:03PM +0200, Marek Vasut wrote:
> The KSZ8051 PHY and the KSZ8794/KSZ8795/KSZ8765 switch share exactly the
> same PHY ID. Since KSZ8051 is higher in the ksphy_driver[] list of PHYs
> in the micrel PHY driver, it is used even with the KSZ87xx switch. This
> is wrong, sin
Hello,
it took a while to build a testsystem for bisecting the issue. Finally I've
identified the patch that causes my problems.
BTW. The fq packet network scheduler is in use.
It's
[PATCH net-next] tcp/fq: move back to CLOCK_MONOTONIC
In the recent TCP/EDT patch series, I switched TCP and sch
From: Neil Horman
> Sent: 14 October 2019 13:42
> To: Xin Long
> Cc: David Laight ; network dev
> ; linux-s...@vger.kernel.org; Marcelo
> Ricardo Leitner ; da...@davemloft.net
> Subject: Re: [PATCHv2 net-next 3/5] sctp: add
> SCTP_EXPOSE_POTENTIALLY_FAILED_STATE sockopt
>
> On Mon, Oct 14, 201
syzbot found that if __inet_inherit_port() returns an error,
we call tcp_done() after inet_csk_prepare_forced_close(),
meaning the socket lock is no longer held.
We might fix this in a different way in net-next, but
for 5.4 it seems safer to relax the lockdep check.
Fixes: d983ea6f16b8 ("tcp: add
> On Mon, 14 Oct 2019 12:49:52 +0200
> Lorenzo Bianconi wrote:
>
> > Add basic XDP support to mvneta driver for devices that rely on software
> > buffer management. Currently supported verdicts are:
> > - XDP_DROP
> > - XDP_PASS
> > - XDP_REDIRECT
> > - XDP_ABORTED
> >
> > - iptables drop:
> > $
We need to extend the rcu_read_lock() section in rxrpc_error_report()
and use rcu_dereference_sk_user_data() instead of plain access
to sk->sk_user_data to make sure all rules are respected.
The compiler wont reload sk->sk_user_data at will, and RCU rules
prevent memory beeing freed too soon.
Fix
On Mon, 14 Oct 2019 12:49:52 +0200
Lorenzo Bianconi wrote:
> Add basic XDP support to mvneta driver for devices that rely on software
> buffer management. Currently supported verdicts are:
> - XDP_DROP
> - XDP_PASS
> - XDP_REDIRECT
> - XDP_ABORTED
>
> - iptables drop:
> $iptables -t raw -I PRERO
On Mon, Oct 14, 2019 at 02:14:43PM +0800, Xin Long wrote:
> SCTP-PF was implemented based on a Internet-Draft in 2012:
>
> https://tools.ietf.org/html/draft-nishida-tsvwg-sctp-failover-05
>
> It's been updated quite a few by rfc7829 in 2016.
>
> This patchset adds the following features:
>
>
On Mon, Oct 14, 2019 at 04:36:34PM +0800, Xin Long wrote:
> On Thu, Oct 10, 2019 at 12:18 AM Neil Horman wrote:
> >
> > On Tue, Oct 08, 2019 at 11:28:32PM +0800, Xin Long wrote:
> > > On Tue, Oct 8, 2019 at 9:02 PM David Laight
> > > wrote:
> > > >
> > > > From: Xin Long
> > > > > Sent: 08 Octob
Alexei Starovoitov writes:
> On Wed, Oct 09, 2019 at 10:03:43AM +0200, Toke Høiland-Jørgensen wrote:
>> Alexei Starovoitov writes:
>>
>> > Please implement proper indirect calls and jumps.
>>
>> I am still not convinced this will actually solve our problem; but OK, I
>> can give it a shot.
>
>
>> +
>> +if (aq_nic->aq_ptp)
>
> Shouldn't the test for (aq_nic->aq_ptp) also effect
> info->so_timestamping and info->tx_types ?
You are right, it should.
It should also fallback to software ethtool_op_get_ts_info in
case HW is not PTP capable.
Will fix that.
Regards,
Igor
Hi Richard,
Thanks for your review, will update the patchset after the comments.
>> +{
>> +struct aq_ptp_s *aq_ptp = container_of(ptp, struct aq_ptp_s, ptp_info);
>> +struct aq_nic_s *aq_nic = aq_ptp->aq_nic;
>> +
>> +mutex_lock(&aq_nic->fwreq_mutex);
>
> Here you use a different lo
On Fri, Oct 11, 2019 at 1:31 PM Simon Horman wrote:
>
> On Thu, Oct 10, 2019 at 05:45:14PM +0800, Xin Long wrote:
> > On Wed, Oct 9, 2019 at 3:55 PM Simon Horman
> > wrote:
> > >
> > > On Tue, Oct 08, 2019 at 11:16:12PM +0800, Xin Long wrote:
> > > > This patch is to add LWTUNNEL_IP_OPTS into lw
Use the page_pool api for allocations and DMA handling instead of
__dev_alloc_page()/dma_map_page() and free_page()/dma_unmap_page().
Pages are unmapped using page_pool_release_page before packets
go into the network stack.
The page_pool API offers buffer recycling capabilities for XDP but
allocat
Move data buffer prefetch in mvneta_swbm_rx_frame after
dma_sync_single_range_for_cpu
Signed-off-by: Ilias Apalodimas
Signed-off-by: Jesper Dangaard Brouer
Signed-off-by: Lorenzo Bianconi
---
drivers/net/ethernet/marvell/mvneta.c | 7 +++
1 file changed, 3 insertions(+), 4 deletions(-)
di
mvneta driver can run on not cache coherent devices so it is
necessary to sync DMA buffers before sending them to the device
in order to avoid memory corruptions. Running perf analysis we can
see a performance cost associated with this DMA-sync (anyway it is
already there in the original driver cod
Allow tx buffer array to contain both skb and xdp buffers in order to
enable xdp frame recycling adding XDP_TX verdict support
Signed-off-by: Lorenzo Bianconi
---
drivers/net/ethernet/marvell/mvneta.c | 66 +--
1 file changed, 43 insertions(+), 23 deletions(-)
diff --git
Implement XDP_TX verdict and ndo_xdp_xmit net_device_ops function
pointer
Signed-off-by: Lorenzo Bianconi
---
drivers/net/ethernet/marvell/mvneta.c | 126 --
1 file changed, 119 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c
b/drivers/n
Add basic XDP support to mvneta driver for devices that rely on software
buffer management. Currently supported verdicts are:
- XDP_DROP
- XDP_PASS
- XDP_REDIRECT
- XDP_ABORTED
- iptables drop:
$iptables -t raw -I PREROUTING -p udp --dport 9 -j DROP
$nstat -n && sleep 1 && nstat
IpInReceives
Introduce mvneta_update_stats routine to collect {rx/tx} statistics
(packets and bytes). This is a preliminary patch to add XDP support to
mvneta driver
Signed-off-by: Lorenzo Bianconi
---
drivers/net/ethernet/marvell/mvneta.c | 41 +--
1 file changed, 20 insertions(+), 2
Refactor mvneta_rx_swbm code introducing mvneta_swbm_rx_frame and
mvneta_swbm_add_rx_fragment routines. Rely on build_skb in oreder to
allocate skb since the previous patch introduced buffer recycling using
the page_pool API.
This patch fixes even an issue in the original driver where dma buffers
a
Add XDP support to mvneta driver for devices that rely on software
buffer management. Supported verdicts are:
- XDP_DROP
- XDP_PASS
- XDP_REDIRECT
- XDP_TX
Moreover set ndo_xdp_xmit net_device_ops function pointer in order to support
redirecting from other device (e.g. virtio-net).
Convert mvneta d
Le 26/06/2019 à 22:26, David Miller a écrit :
> From: Nicolas Dichtel
> Date: Mon, 24 Jun 2019 16:01:07 +0200
>
>> The first patch prepares the fix, it constify rt6_nexthop().
>> The detail of the bug is explained in the second patch.
>>
>> v1 -> v2:
>> - fix compilation warnings
>> - split the
Le 05/09/2019 à 12:21, Steffen Klassert a écrit :
> 1) Several xfrm interface fixes from Nicolas Dichtel:
>- Avoid an interface ID corruption on changelink.
>- Fix wrong intterface names in the logs.
>- Fix a list corruption when changing network namespaces.
>- Fix unregistation of
This patch set adds a couple of fixes around updating configuration on MAC
change. Depending on when MC connects the DPNI to a MAC, both the MAC
address and TX FQIDs should be updated everytime there is a change in
configuration.
Changes in v2:
- used reverse christmas tree ordering in patch 2/2
From: Ioana Radulescu
Depending on when MC connects the DPNI to a MAC, Tx FQIDs may
not be available during probe time.
Read the FQIDs each time the link goes up to avoid using invalid
values. In case an error occurs or an invalid value is retrieved,
fall back to QDID-based enqueueing.
Fixes: 1
From: Florin Chiculita
Add IRQ for the DPNI endpoint change event, resolving the issue
when a dynamically created DPNI gets a randomly generated hw address
when the endpoint is a DPMAC object.
Signed-off-by: Florin Chiculita
Signed-off-by: Ioana Ciornei
---
Changes in v2:
- none
drivers/net
From: Xin Long
> Sent: 14 October 2019 09:37
...
> RFC actually keeps adding new notifications,
That RFC keeps moving the goalposts.
Even the structures are guaranteed to have holes.
> and a user shouldn't expect
> the specific notifications coming in some exact orders. They should just
> ignore
On Thu, Oct 10, 2019 at 12:18 AM Neil Horman wrote:
>
> On Tue, Oct 08, 2019 at 11:28:32PM +0800, Xin Long wrote:
> > On Tue, Oct 8, 2019 at 9:02 PM David Laight wrote:
> > >
> > > From: Xin Long
> > > > Sent: 08 October 2019 12:25
> > > >
> > > > This is a sockopt defined in section 7.3 of rfc78
On Sat, Oct 12, 2019 at 6:55 PM Alexei Starovoitov
wrote:
>
> On Fri, Oct 11, 2019 at 1:58 PM John Fastabend
> wrote:
> >
> > Magnus Karlsson wrote:
> > > On Tue, Oct 8, 2019 at 9:29 PM John Fastabend
> > > wrote:
> > > >
> > > > Magnus Karlsson wrote:
> > > > > When the need_wakeup flag was a
On Fri, Oct 11, 2019 at 7:05 AM wrote:
>
> From: Tonghao Zhang
>
> The full looking up on flow table traverses all mask array.
> If mask-array is too large, the number of invalid flow-mask
> increase, performance will be drop.
>
> This patch optimizes mask-array operation:
>
> * Inserting, insert
89 matches
Mail list logo
