On Wed, Jun 05, 2019 at 02:40:45PM +0200, Florian Westphal wrote:
>
> Steffen, as this is still only in your testing branch, I suggest you
> squash this snipped into commit 8dc6e3891a4be64c0cca5e8fe2c3ad33bc06543e
> ("xfrm: remove state and template sort indirections from xfrm_state_afinfo"),
> it
> -Original Message-
> From: David Miller
> Sent: Thursday, June 6, 2019 4:46 AM
> To: Ioana Ciocoi Radulescu
> Cc: netdev@vger.kernel.org; Ioana Ciornei
> Subject: Re: [PATCH net-next 2/3] dpaa2-eth: Support multiple traffic classes
> on Tx
>
> From: Ioana Radulescu
> Date: Wed, 5 Ju
On 06.06.2019 03:42, David Miller wrote:
> From: Robert Hancock
> Date: Tue, 4 Jun 2019 16:15:01 -0600
>
>> Add 1000BaseX to the link modes which are detected based on the
>> MII_ESTATUS register as per 802.3 Clause 22. This allows PHYs which
>> support 1000BaseX to work properly with drivers us
The opts[] array is of type u32. Therefore remove the wrong
cpu_to_le32(). The opts[] array members are converted to little endian
later when being assigned to the respective descriptor fields.
This is not a new issue, it just popped up due to r8169.c having
been renamed and more thoroughly checke
On Wed, 5 Jun 2019 16:15:20 -0700
David Ahern wrote:
> From: David Ahern
>
> Move the route add commands to a new function called setup_routing_old.
> The '_old' refers to the classic way of installing routes.
>
> Signed-off-by: David Ahern
Reviewed-by: Stefano Brivio
On Wed, 5 Jun 2019 16:15:19 -0700
David Ahern wrote:
> From: David Ahern
>
> Move the block of code that runs a test and prints the verdict to a
> new function, run_test.
>
> Signed-off-by: David Ahern
Reviewed-by: Stefano Brivio
On Wed, 5 Jun 2019 16:15:21 -0700
David Ahern wrote:
> From: David Ahern
>
> Add routing setup using nexthop objects and repeat tests with
> old and new routing.
>
> Signed-off-by: David Ahern
Reviewed-by: Stefano Brivio
On 6/6/2019 4:42 AM, Cong Wang wrote:
> On Tue, Jun 4, 2019 at 11:19 AM Eli Britstein wrote:
>>
>> On 6/4/2019 8:55 PM, Cong Wang wrote:
>>> On Sat, Jun 1, 2019 at 9:22 PM Eli Britstein wrote:
I think that's because QinQ, or VLAN is not an encapsulation. There is
no outer/inner packets
On Wed, Jun 05, 2019 at 01:23:49PM -0700, Jeff Kirsher wrote:
> + * It calculates when the system time will be on an exact second, and then
> + * aligns the start of the PPS signal to that value.
> + *
> + * This works by using the cycle counter shift and mult values in reverse,
> and
> + * assume
On Wed, Jun 05, 2019 at 07:28:38PM +, Shalom Toledo wrote:
> So, there is an HW machine which responsible for adding UTC timestamp on
> R-SPAN mirror packets and there is no connection to the HW free running
> counter.
If there is no connection, then the frequency adjustments to the HW
clock w
On Wed, Jun 05, 2019 at 06:55:18PM +, Shalom Toledo wrote:
> On 05/06/2019 20:23, Richard Cochran wrote:
> > On Wed, Jun 05, 2019 at 11:30:06AM +, Shalom Toledo wrote:
> >> On 04/06/2019 17:17, Richard Cochran wrote:
> >>> On Mon, Jun 03, 2019 at 03:12:39PM +0300, Ido Schimmel wrote:
>
small cleanup: "struct request_sock_queue *queue" parameter of
reqsk_queue_unlink
func is never used in the func, so we can remove it.
Signed-off-by: Zhiqiang Liu
>>>
>>> Applied, thanks.
>>>
>>
>> Hi, David Miller.
>> So sorry for forgetting to sign partner's name who fi
From: Zhiqiang Liu
Date: Thu, 6 Jun 2019 10:06:55 +0800
>> From: Zhiqiang Liu
>> Date: Wed, 5 Jun 2019 18:49:49 +0800
>>
>>> small cleanup: "struct request_sock_queue *queue" parameter of
>>> reqsk_queue_unlink
>>> func is never used in the func, so we can remove it.
>>>
>>> Signed-off-by: Zhi
> From: Zhiqiang Liu
> Date: Wed, 5 Jun 2019 18:49:49 +0800
>
>> small cleanup: "struct request_sock_queue *queue" parameter of
>> reqsk_queue_unlink
>> func is never used in the func, so we can remove it.
>>
>> Signed-off-by: Zhiqiang Liu
>
> Applied, thanks.
>
Hi, David Miller.
So sorry fo
From: Eric Dumazet
Date: Wed, 5 Jun 2019 07:55:08 -0700
> First patch allows to reflect incoming IPv6 flowlabel
> on RST packets sent when no socket could handle the packet.
>
> Second patch makes sure we send the same flowlabel
> for RST or ACK packets on behalf of TIME_WAIT sockets.
Series a
From: Zhiqiang Liu
Date: Wed, 5 Jun 2019 18:49:49 +0800
> small cleanup: "struct request_sock_queue *queue" parameter of
> reqsk_queue_unlink
> func is never used in the func, so we can remove it.
>
> Signed-off-by: Zhiqiang Liu
Applied, thanks.
From: Russell King
Date: Wed, 05 Jun 2019 11:43:16 +0100
> + (state == PHY_UP || state == PHY_RESUMING)) {
drivers/net/phy/marvell10g.c: In function ‘mv3310_link_change_notify’:
drivers/net/phy/marvell10g.c:268:35: error: ‘PHY_RESUMING’ undeclared (first
use in this function); did you m
From: Ioana Radulescu
Date: Wed, 5 Jun 2019 12:57:25 +0300
> + queue_mapping %= dpaa2_eth_queue_count(priv);
You are now performing a very expensive modulus operation every single TX
packet, regardless of whether TC is in use or not.
The whole reason we store the queue mapping pre-cooked i
On Tue, Jun 4, 2019 at 11:19 AM Eli Britstein wrote:
>
>
> On 6/4/2019 8:55 PM, Cong Wang wrote:
> > On Sat, Jun 1, 2019 at 9:22 PM Eli Britstein wrote:
> >> I think that's because QinQ, or VLAN is not an encapsulation. There is
> >> no outer/inner packets, and if you want to mangle fields in the
From: Robert Hancock
Date: Tue, 4 Jun 2019 16:15:01 -0600
> Add 1000BaseX to the link modes which are detected based on the
> MII_ESTATUS register as per 802.3 Clause 22. This allows PHYs which
> support 1000BaseX to work properly with drivers using phylink.
>
> Previously 1000BaseX support was
From: Nathan Chancellor
Date: Wed, 5 Jun 2019 18:23:51 -0700
> On Wed, Jun 05, 2019 at 05:55:26PM -0700, David Miller wrote:
>> From: Hangbin Liu
>> Date: Wed, 5 Jun 2019 12:27:14 +0800
>>
>> > This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.
>> >
>> > Nathan reported the new beh
On Wed, Jun 05, 2019 at 05:55:26PM -0700, David Miller wrote:
> From: Hangbin Liu
> Date: Wed, 5 Jun 2019 12:27:14 +0800
>
> > This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.
> >
> > Nathan reported the new behaviour breaks Android, as Android just add
> > new rules and delete old
On Wed, Jun 5, 2019 at 12:27 AM Steinar H. Gunderson
wrote:
>
> On Tue, Jun 04, 2019 at 09:31:42PM -0700, Cong Wang wrote:
> >> This works fine for large packets, but the system in the other end
> >> drops smaller packets, such as ARP requests and small ICMP pings.
> > Is the other end Linux too?
On Wed, Jun 5, 2019 at 5:11 PM David Miller wrote:
>
> From: Tom Herbert
> Date: Mon, 3 Jun 2019 08:47:47 -0700
>
> > Define constants and add support to send ICMPv6 Parameter Problem
> > errors as specified in draft-ietf-6man-icmp-limits-02.
>
> Tom, I've kinda had enough of this pushing your a
small cleanup: "struct request_sock_queue *queue" parameter of
reqsk_queue_unlink
func is never used in the func, so we can remove it.
Signed-off-by: Zhiqiang Liu
Signed-off-by: Mao Wenan
Reviewed-by: Eric Dumazet
---
V1->V2: add partner signatures
net/ipv4/inet_connection_sock.c | 5 ++---
From: Hangbin Liu
Date: Wed, 5 Jun 2019 12:27:14 +0800
> This reverts commit e9919a24d3022f72bcadc407e73a6ef17093a849.
>
> Nathan reported the new behaviour breaks Android, as Android just add
> new rules and delete old ones.
>
> If we return 0 without adding dup rules, Android will remove the
From: Heiner Kallweit
Date: Tue, 4 Jun 2019 23:02:34 +0200
> In the early days of phylib we had a functionality that changed to the
> next lower speed in fixed mode if no link was established after a
> certain period of time. This functionality has been removed years ago,
> and state PHY_FORCING
From: Igor Russkikh
Date: Tue, 4 Jun 2019 13:23:49 +
> From: Nikita Danilov
>
> WoL magic packet configuration sometimes does not work due to
> couple of leakages found.
>
> Mainly there was a regression introduced during readx_poll refactoring.
>
> Next, fw request waiting time was too s
On 06/06/2019 02:13 AM, Alexei Starovoitov wrote:
> On Wed, Jun 5, 2019 at 5:09 PM Daniel Borkmann wrote:
>>
tools/bpf/bpftool/cgroup.c | 5 -
tools/include/uapi/linux/bpf.h | 2 ++
>>> Should the bpf.h sync to tools/ be in a separate patch?
>>
>> I was thinking about it, but c
On 06/06/2019 01:47 AM, Jakub Kicinski wrote:
> It seems like periodically someone posts patches to "fix"
> header includes. The issue is that samples expect the
> include path to have the uAPI headers (from usr/) first,
> and then tools/ headers, so that locally installed uAPI
> headers take prec
From: Vivien Didelot
Date: Mon, 3 Jun 2019 16:57:13 -0400
> ethtool_get_regs() allocates a buffer of size ops->get_regs_len(),
> and pass it to the kernel driver via ops->get_regs() for filling.
>
> There is no restriction about what the kernel drivers can or cannot do
> with the open ethtool_r
From: Neil Horman
Date: Mon, 3 Jun 2019 16:32:59 -0400
> syzbot found the following leak in sctp_process_init
> BUG: memory leak
> unreferenced object 0x88810ef68400 (size 1024):
...
> The problem was that the peer.cookie value points to an skb allocated
> area on the first pass through thi
On Wed, Jun 5, 2019 at 5:09 PM Daniel Borkmann wrote:
>
> >> tools/bpf/bpftool/cgroup.c | 5 -
> >> tools/include/uapi/linux/bpf.h | 2 ++
> > Should the bpf.h sync to tools/ be in a separate patch?
>
> I was thinking about it, but concluded for such small change, it's not
> really worth
From: Tom Herbert
Date: Mon, 3 Jun 2019 08:47:47 -0700
> Define constants and add support to send ICMPv6 Parameter Problem
> errors as specified in draft-ietf-6man-icmp-limits-02.
Tom, I've kinda had enough of this pushing your agenda by trying to
add support for ipv6 features that are in draft
On 06/06/2019 01:54 AM, Martin Lau wrote:
> On Wed, Jun 05, 2019 at 10:40:49PM +0200, Daniel Borkmann wrote:
>> Intention of cgroup bind/connect/sendmsg BPF hooks is to act transparently
>> to applications as also stated in original motivation in 7828f20e3779 ("Merge
>> branch 'bpf-cgroup-bind-conn
From: Zhu Yanjun
Date: Mon, 3 Jun 2019 08:48:19 -0400
> When KASAN is enabled, after several rds connections are
> created, then "rmmod rds_rdma" is run. The following will
> appear.
...
> This is rds connection memory leak. The root cause is:
> When "rmmod rds_rdma" is run, rds_ib_remove_one w
From: Zhu Yanjun
Date: Mon, 3 Jun 2019 00:28:01 -0400
> The variable cache_allocs is to indicate how many frags (KiB) are in one
> rds connection frag cache.
> The command "rds-info -Iv" will output the rds connection cache
> statistics as below:
> "
> RDS IB Connections:
> LocalAddr Remot
On Wed, Jun 05, 2019 at 04:47:22PM -0700, Jakub Kicinski wrote:
> It seems like periodically someone posts patches to "fix"
> header includes. The issue is that samples expect the
> include path to have the uAPI headers (from usr/) first,
> and then tools/ headers, so that locally installed uAPI
>
From: Xin Long
Date: Sun, 2 Jun 2019 19:10:46 +0800
> In Jianlin's testing, netperf was broken with 'Connection reset by peer',
> as the cookie check failed in rt6_check() and ip6_dst_check() always
> returned NULL.
>
> It's caused by Commit 93531c674315 ("net/ipv6: separate handling of FIB
> e
From: Xin Long
Date: Sun, 2 Jun 2019 19:10:24 +0800
> With the topo:
>
> h1 ---| rp1|
> | route rp3 |--- h3 (192.168.200.1)
> h2 ---| rp2|
>
> If rp1 bc_forwarding is set while rp2 bc_forwarding is not, after
> doing "ping 192.168.200.255" on h1,
On Wed, Jun 05, 2019 at 10:40:49PM +0200, Daniel Borkmann wrote:
> Intention of cgroup bind/connect/sendmsg BPF hooks is to act transparently
> to applications as also stated in original motivation in 7828f20e3779 ("Merge
> branch 'bpf-cgroup-bind-connect'"). When recently integrating the latter
>
From: Jeff Kirsher
Date: Wed, 5 Jun 2019 12:45:15 -0700
> From: Lihong Yang
>
> The VF configuration returned in i40e_ndo_get_vf_config is
> already stored by the PF. There is no dependency on any
> specific state of the VF to return the configuration.
> Drop the check against I40E_VF_STATE_IN
From: Jeff Kirsher
Date: Wed, 5 Jun 2019 12:45:16 -0700
> From: Lihong Yang
>
> The PF driver state flag __I40E_VIRTCHNL_OP_PENDING needs to be
> checked and set at the beginning of i40e_ndo_set_vf_mac. Otherwise,
> if there are error conditions before it, the flag will be cleared
> unexpected
It seems like periodically someone posts patches to "fix"
header includes. The issue is that samples expect the
include path to have the uAPI headers (from usr/) first,
and then tools/ headers, so that locally installed uAPI
headers take precedence. This means that if users didn't
run headers_ins
tree: https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git linux-next
head: aa5dc31069763f9b1afcfcf2583de258af44d72c
commit: eb43203ceabbab75b07a526b59b34bc170e0dc2c [12/19] vhost: access vq
metadata through kernel virtual address
config: mips-allyesconfig (attached as .config)
compil
From: Jeff Kirsher
Date: Wed, 5 Jun 2019 13:23:43 -0700
> This series contains updates to mainly ixgbe, with a few updates to
> i40e, net, ice and hns2 driver.
Pulled, thanks for the ETH_P_LLDP consolidation.
On Wed, 5 Jun 2019 17:39:23 +0200, Davide Caratti wrote:
> When an application configures kernel TLS on top of a TCP socket, it's
> now possible for inet_diag_handler to collect information regarding the
> protocol version and the cipher, in case INET_DIAG_INFO is requested.
>
> Signed-off-by: Da
From: Tal Gilboa
Renamed macros in use by external drivers.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/broadcom/bcmsysport.c | 4 ++--
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c | 2 +-
dri
From: Yamin Friedman
Added a measurement of completions per/msec to allow for completion based
dim algorithms.
In order to use dynamic interrupt moderation with RDMA we need to have a
different measurment than packets per second. This change is meant to
prepare for adding a new DIM method.
All
From: Tal Gilboa
In order to avoid confusion between the function and the similarly
named struct.
In preparation for removing the 'net' prefix from dim members.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/broadcom/bcmsysport.c| 4 ++--
drivers/net/
From: Tal Gilboa
Only renaming functions and structs which aren't used by an external code.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
include/linux/dim.h | 86
include/linux/net_dim.h | 87 -
From: Tal Gilboa
In preparation for supporting more implementations of the DIM
algorithm, I'm moving what would become common logic to a common
library. Downstream DIM implementations will use the common lib
for their implementation.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
Hi Dave, Doug & Jason
This series improves DIM - Dynamically-tuned Interrupt
Moderation- to be generic for netdev and RDMA use-cases.
From Tal and Yamin:
The first 7 patches provide the necessary refactoring to current net_dim
library which affect some net drivers who are using the API.
The last
From: Yamin Friedman
Added the interface in the infiniband driver that applies the rdma_dim
adaptive moderation. There is now a special function for allocating an
ib_cq that uses rdma_dim.
Performance improvement (ConnectX-5 100GbE, x86) running FIO benchmark over
NVMf between two equal end-host
From: Tal Gilboa
Removed 'net' prefix from functions and structs used by external drivers.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/broadcom/bcmsysport.c| 16 +-
drivers/net/ethernet/broadcom/bcmsysport.h| 2 +-
drivers/net/ethernet/bro
From: Tal Gilboa
Moved all logic from dim.h and net_dim.h to dim.c and net_dim.c.
This is both more structurally appealing and would allow to only
expose externally used functions.
Signed-off-by: Tal Gilboa
Signed-off-by: Saeed Mahameed
---
MAINTAINERS | 1
From: Yamin Friedman
rdma_dim implements a different algorithm than net_dim and is based on
completions which is how we can implement interrupt moderation in RDMA.
The algorithm optimizes for number of completions and ratio between
completions and events.
It also has a feature for fast reduction
From: David Ahern
This is the final set of the initial nexthop object work. When I
started this idea almost 2 years ago, it took 18 seconds to inject
700k+ IPv4 routes with 1 hop and about 28 seconds for 4-paths. Some
of that time was due to inefficiencies in 'ip', but most of it was
kernel side
From: David Ahern
Add support for RTA_NH_ID attribute to allow a user to specify a
nexthop id to use with a route. fc_nh_id is added to fib_config to
hold the value passed in the RTA_NH_ID attribute. If a nexthop id
is given, the gateway, device, encap and multipath attributes can
not be set.
Up
From: David Ahern
Add a hook in rt6_flush_exceptions, rt6_remove_exception_rt,
rt6_update_exception_stamp_rt, and rt6_age_exceptions to handle
nexthop struct in a fib6_info.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 109 +--
1 file ch
From: David Ahern
Use nexthop_for_each_fib6_nh to call fib6_nh_mtu_change for each
fib6_nh in a nexthop for rt6_mtu_change_route. For __ip6_rt_update_pmtu,
we need to find the nexthop that correlates to the device and gateway
in the rt6_info.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 2
From: David Ahern
Add a second pass to icmp_redirect.sh to use nexthop objects for
routes.
Signed-off-by: David Ahern
---
tools/testing/selftests/net/icmp_redirect.sh | 49
1 file changed, 49 insertions(+)
diff --git a/tools/testing/selftests/net/icmp_redirect.sh
From: David Ahern
Use nexthop_for_each_fib6_nh to walk all fib6_nh in a nexthop when
dropping 'from' reference in pcpu routes.
Signed-off-by: David Ahern
---
net/ipv6/ip6_fib.c | 31 +++
1 file changed, 27 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/ip6_fib
From: David Ahern
Add a hook in fib6_info_uses_dev to handle nexthop struct in a fib6_info.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 18 ++
1 file changed, 18 insertions(+)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index aaa10e716115..6f4bd971df70 100644
--- a/
From: David Ahern
Move the route add commands to a new function called setup_routing_old.
The '_old' refers to the classic way of installing routes.
Signed-off-by: David Ahern
---
tools/testing/selftests/net/pmtu.sh | 26 +++---
1 file changed, 15 insertions(+), 11 deletion
From: David Ahern
Add a hook in __find_rr_leaf to handle nexthop struct in a fib6_info.
nexthop_for_each_fib6_nh is used to walk each fib6_nh in a nexthop and
call find_match. On a match, use the fib6_nh saved in the callback arg
to setup fib6_result.
Signed-off-by: David Ahern
---
net/ipv6/ro
From: David Ahern
Be optimistic about re-using a fib_info when nexthop id is given and
the route does not use metrics. Avoids a memory allocation which in
most cases is expected to be freed anyways.
Signed-off-by: David Ahern
---
net/ipv4/fib_semantics.c | 71 ++
From: David Ahern
Move the block of code that runs a test and prints the verdict to a
new function, run_test.
Signed-off-by: David Ahern
---
tools/testing/selftests/net/pmtu.sh | 63 +
1 file changed, 36 insertions(+), 27 deletions(-)
diff --git a/tools/tes
From: David Ahern
Add support for RTA_NH_ID attribute to allow a user to specify a
nexthop id to use with a route. fc_nh_id is added to fib6_config to
hold the value passed in the RTA_NH_ID attribute. If a nexthop id
is given, the gateway, device, encap and multipath attributes can
not be set.
U
From: David Ahern
Add a hook in rt6_device_match to handle nexthop struct in a fib6_info.
The new rt6_nh_dev_match uses nexthop_for_each_fib6_nh to walk each
fib6_nh in a nexthop and call __rt6_device_match. On match,
rt6_nh_dev_match returns the fib6_nh and rt6_device_match uses it to
setup fib6
From: David Ahern
Add tests where multiple FIB entries use the same nexthop object. Generate
per-cpu cached routes for each by running ping on each cpu, and then
generate exceptions unique to each prefix (remote host) with different
mtus.
Signed-off-by: David Ahern
---
.../selftests/net/fib_ne
From: David Ahern
Use nexthop_for_each_fib6_nh and fib6_nh_find_match to find the
fib6_nh in a nexthop that correlates to the device and gateway
in the rt6_info.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 20 +++-
1 file changed, 19 insertions(+), 1 deletion(-)
diff --g
From: David Ahern
Add a hook in __ip6_route_redirect to handle a nexthop struct in a
fib6_info. Use nexthop_for_each_fib6_nh and fib6_nh_redirect_match
to call ip6_redirect_nh_match for each fib6_nh looking for a match.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 39 +
From: David Ahern
Add support for atomically upating a nexthop config.
When updating a nexthop, walk the lists of associated fib entries and
verify the new config is valid. After replace, bump the sequence counters
for FIB entries to invalidate any dst entries.
Signed-off-by: David Ahern
---
From: David Ahern
Add routing setup using nexthop objects and repeat tests with
old and new routing.
Signed-off-by: David Ahern
---
tools/testing/selftests/net/pmtu.sh | 158
1 file changed, 126 insertions(+), 32 deletions(-)
diff --git a/tools/testing/sel
From: David Ahern
IPv6 has traditionally had a single fib6_nh per fib6_info. With
nexthops we can have multiple fib6_nh associated with a fib6_info.
Add a nexthop helper to invoke a callback for each fib6_nh in a
'struct nexthop'. If the callback returns non-0, the loop is
stopped and the return
From: David Ahern
Add a hook in rt6_nlmsg_size to handle nexthop struct in a fib6_info.
rt6_nh_nlmsg_size is used to sum the space needed for all nexthops in
the fib entry.
Signed-off-by: David Ahern
---
net/ipv6/route.c | 49 +
1 file changed, 3
On Wed, 5 Jun 2019 17:39:22 +0200, Davide Caratti wrote:
> currently, only getsockopt(TCP_ULP) can be invoked to know if a ULP is on
> top of a TCP socket. Extend idiag_get_aux() and idiag_get_aux_size(),
> introduced by commit b37e88407c1d ("inet_diag: allow protocols to provide
> additional data
On Wed, Jun 05, 2019 at 08:57:56AM -0700, Jonathan Lemon wrote:
> Currently, the AF_XDP code uses a separate map in order to
> determine if an xsk is bound to a queue. Instead of doing this,
> have bpf_map_lookup_elem() return a xdp_sock.
>
> Rearrange some xdp_sock members to eliminate structure
Hi,
I wanted to follow up from last week. Did you receive the email I sent you?
Our company manufactures USB Flash Drives, printed with your logo. They
make the perfect marketing tool for your business or organization.
We offer low minimum quantities, and all memory sizes. Over 150 Stock
Model
On Wed, Jun 05, 2019 at 02:16:30PM -0700, Stanislav Fomichev wrote:
> On 06/05, Martin Lau wrote:
> > On Wed, Jun 05, 2019 at 12:17:24PM -0700, Stanislav Fomichev wrote:
> > > On 06/05, Martin Lau wrote:
> > > > On Tue, Jun 04, 2019 at 02:35:18PM -0700, Stanislav Fomichev wrote:
> > > > > Implement
On 06/05, Andrii Nakryiko wrote:
> On Wed, Jun 5, 2019 at 1:54 PM Stanislav Fomichev wrote:
> >
> > On 06/05, Andrii Nakryiko wrote:
> > > On Tue, Jun 4, 2019 at 2:35 PM Stanislav Fomichev wrote:
> > > >
> > > > Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
> > > > BPF_CGROUP_{G,S}E
It seems like periodically someone posts patches to "fix"
header includes. The issue is that samples expect the
include path to have the uAPI headers (from usr/) first,
and then tools/ headers, so that locally installed uAPI
headers take precedence. This means that if users didn't
run headers_ins
On 06/05, Martin Lau wrote:
> On Wed, Jun 05, 2019 at 12:17:24PM -0700, Stanislav Fomichev wrote:
> > On 06/05, Martin Lau wrote:
> > > On Tue, Jun 04, 2019 at 02:35:18PM -0700, Stanislav Fomichev wrote:
> > > > Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
> > > > BPF_CGROUP_{G,S}ETS
FW may prefer to handle some communication via a mailbox
or the vNIC may simply not have a control queue (VFs).
Add a way of exchanging ccm-compatible messages via a
mailbox.
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Merwe
---
drivers/net/ethernet/netronome/nfp/Makefile | 1 +
Currently drivers have to ensure the alignment of their tls state
structure, which leads to unnecessary layers of getters and
encapsulated structures in each driver.
Simplify all this by marking the driver state as aligned (driver_state
members are currently aligned, so no hole is added, besides A
Subsequent patches will add support for more TX metadata fields.
Prepare for this by handling an additional double word - firmware
handle as metadata type 7.
Signed-off-by: Dirk van der Merwe
Signed-off-by: Jakub Kicinski
---
.../ethernet/netronome/nfp/nfp_net_common.c | 44 ++
8 bytes of driver state has been enough so far, but for drivers
which have to store 8 byte handle it's no longer practical to
store the state directly in the context.
Drivers generally don't need much extra state on RX side, while
TX side has to be tracking TCP sequence numbers. Split the
lengths
From: Dirk van der Merwe
This patch adds the functionality to add and delete TLS connections on
the NFP, received from the kernel TLS callbacks.
Make use of the common control message (CCM) infrastructure to propagate
the kernel state to firmware.
Signed-off-by: Dirk van der Merwe
Signed-off-b
Add FW ABI defines and code for basic init of TLS offload.
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Merwe
---
drivers/net/ethernet/netronome/Kconfig| 1 +
drivers/net/ethernet/netronome/nfp/Makefile | 5 +
drivers/net/ethernet/netronome/nfp/ccm.h | 4 +
.../e
We will need to release the bar lock from a workqueue
so move from a mutex to a semaphore. This lock should
not be too hot. Unfortunately semaphores don't have
lockdep support.
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Merwe
---
drivers/net/ethernet/netronome/nfp/nfp_net.h
From: Dirk van der Merwe
Prepend connection handle to each transmitted TLS packet.
For each connection, the driver tracks the next sequence number
expected. If an out of order packet is observed, the driver calls into
the TLS kernel code to reencrypt that particular skb.
Signed-off-by: Dirk van
On Wed, Jun 5, 2019 at 1:54 PM Stanislav Fomichev wrote:
>
> On 06/05, Andrii Nakryiko wrote:
> > On Tue, Jun 4, 2019 at 2:35 PM Stanislav Fomichev wrote:
> > >
> > > Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
> > > BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.
> > >
> > > BPF_CGROUP_S
Count TX TLS packets: successes, out of order, and dropped due to
missing record info. Make sure the RX and TX completion statistics
don't share cache lines with TX ones as much as possible. With TLS
stats they are no longer reasonably aligned.
Signed-off-by: Dirk van der Merwe
Signed-off-by: J
Parse TLV containing a bitmask of supported crypto operations.
The TLV contains a capability bitmask (supported operations)
and enabled bitmask. Each operation describes the crypto
protocol quite exhaustively (protocol, AEAD, direction).
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Me
From: Dirk van der Merwe
While offloading TLS connections, drivers need to handle the case where
out of order packets need to be transmitted.
Other drivers obtain the entire TLS record for the specific skb to
provide as context to hardware for encryption. However, other designs
may also want to
Hi!
This series adds initial TLS offload support to the nfp driver.
Only TX side is added for now. We need minor adjustments to
the core tls code:
- expose the per-skb fallback helper;
- grow the driver context slightly;
- add a helper to get to the driver state more easily.
We only support TX
Parse the mailbox TLV. When control message queue is not available
we can fall back to passing the control messages via the vNIC
mailbox.
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Merwe
---
drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c | 4
drivers/net/ethernet/netronome
Currently if we need to modify the head of the skb and allocation
fails we would free the skb and not increment the error counter.
Make sure all errors are counted.
Signed-off-by: Jakub Kicinski
Reviewed-by: Dirk van der Merwe
---
drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 12 +--
Apologies for the delay in getting this out. I've been busy
with other things and this change was a little trickier than
I expected.
This patch restores the original behaviour for tdc prior to the
introduction of the plugin system, where the network namespace
functionality was split from the main
1 - 100 of 224 matches
Mail list logo
