Symmetry is good and allows easy comparison that ipv4 and ipv6 are
doing the same thing. To that end, change ip_multipath_l3_keys to
set addresses at the end after the icmp compares, and move the
initialization of ipv6 flow keys to rt6_multipath_hash.
Signed-off-by: David Ahern
Hello,
On Fri, 2 Mar 2018 16:40:42 +0100, Antoine Tenart wrote:
> -/* Initialize Tx FIFO's */
> +/* Initialize Tx FIFO's
> + * The CP110's total tx-fifo size is 19kB.
> + * Use large-size 10kB for fast port but 3kB for others.
> + */
Is there a reason to hardcode 10KB for port 0, and 3KB for
On Fri, Mar 02, 2018 at 08:32:11AM -0800, David Ahern wrote:
> Hardware supports multipath selection using the standard L4 5-tuple
> instead of just L3 and the flow label. In addition, some network
> operators prefer IPv6 path selection to use the 5-tuple. To that end,
> add support to IPv6 for
On 02/03/18 18:32, David Ahern wrote:
> Make rt6_multipath_hash more of a direct parallel to fib_multipath_hash
> and reduce stack and overhead in the process: get_hash_from_flowi6 is
> just a wrapper around __get_hash_from_flowi6 with another stack
> allocation for flow_keys. Move setting the
On 02/03/18 18:32, David Ahern wrote:
> Rename NETEVENT_MULTIPATH_HASH_UPDATE to
> NETEVENT_IPV4_MPATH_HASH_UPDATE to denote it relates to a change
> in the IPv4 hash policy.
>
> Signed-off-by: David Ahern
> Reviewed-by: Ido Schimmel
> ---
>
On 02/03/18 18:32, David Ahern wrote:
> IPv6 does path selection for multipath routes deep in the lookup
> functions. The next patch adds L4 hash option and needs the skb
> for the forward path. To get the skb to the relevant FIB lookup
> functions it needs to go through the fib rules layer, so
From: Sven Eckelmann
commit 785ea1144182 ("batman-adv: Distributed ARP Table - create DHT helper
functions") introduced a return check of batadv_compare_eth which uses a
boolean return value since commit 16af73458aca ("batman-adv: main,
batadv_compare_eth return bool"). A
From: Sven Eckelmann
Also multiline macros should have their statements start on a tabstop. This
was detected by checkpatch.pl after commit a134f8de9f40 ("checkpatch:
improve the TABSTOP test to include declarations").
Signed-off-by: Sven Eckelmann
From: Matthias Schiffer
NIC drivers generally try to ensure that the "network header" is aligned
to a 4-byte boundary. This is not always possible: When Ethernet frames are
encapsulated in other packets with 4-byte aligned headers, the inner
Ethernet header will
in the git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-next-for-davem-20180302
for you to fetch changes up to a163dc22d515d17844435c8217ff66193d35b3fa:
batman-adv: always assume 2-byte packet alignment (2018-02-27 13:02:54 +0100
Signed-off-by: Simon Wunderlich
---
net/batman-adv/main.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index f7ba3f96d8f3..69bfedfad174 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@
On Fri, 2 Mar 2018 06:54:17 +
"Tian, Kevin" wrote:
> > From: Alex Williamson
> > Sent: Friday, March 2, 2018 4:22 AM
> > >
> > > I am pretty sure that you are describing is true of some, but not for
> > > all. I think the Amazon solutions and the virtio solution are
Fri, Mar 02, 2018 at 04:26:25PM CET, alexander.du...@gmail.com wrote:
>On Fri, Mar 2, 2018 at 12:36 AM, Jiri Pirko wrote:
>> Thu, Mar 01, 2018 at 09:08:43PM CET, sridhar.samudr...@intel.com wrote:
>>>This patch enables virtio_net to switch over to a VF datapath when a VF
On Thu, 2018-03-01 at 13:03 -0500, Paul Moore wrote:
> On March 1, 2018 9:36:37 AM Richard Haines et.com> wrote:
> > On Thu, 2018-03-01 at 08:42 -0500, Paul Moore wrote:
> > > On Thu, Mar 1, 2018 at 3:33 AM, Anders Roxell > > ro.o
> > > rg> wrote:
On Fri, Mar 2, 2018 at 8:37 AM, Samudrala, Sridhar
wrote:
>
>
> On 3/2/2018 8:20 AM, Jiri Pirko wrote:
>
> Fri, Mar 02, 2018 at 04:26:25PM CET, alexander.du...@gmail.com wrote:
>
> On Fri, Mar 2, 2018 at 12:36 AM, Jiri Pirko wrote:
>
> Thu, Mar 01,
On Fri, Mar 02, 2018 at 05:29:14PM +0800, Jason Wang wrote:
> XDP_REDIRECT support for mergeable buffer was removed since commit
> 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable()
> case"). This is because we don't reserve enough tailroom for struct
> skb_shared_info which
On 02/03/18 18:32, David Ahern wrote:
> As of commit e37b1e978bec5 ("ipv6: route: dissect flow in input path if
> fib rules need it") fib_multipath_hash takes an optional flow keys. If
> non-NULL it means the skb has already been dissected. If not set, then
> fib_multipath_hash needs to call
On 02/03/18 18:32, David Ahern wrote:
> Symmetry is good and allows easy comparison that ipv4 and ipv6 are
> doing the same thing. To that end, change ip_multipath_l3_keys to
> set addresses at the end after the icmp compares, and move the
> initialization of ipv6 flow keys to rt6_multipath_hash.
Lastly, there has been feedback asking how practical and useful this
facility actually is, and you must address that.
According to our marketing folks, there is end-user demand for this feature
or something like it.
The main benefit comes on numa systems, when you have high throughput
in the git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-net-for-davem-20180302
for you to fetch changes up to f22e08932c2960f29b5e828e745c9f3fb7c1bb86:
batman-adv: Fix internal interface indices types (2018-02-25 20:19:34 +0100
From: Matthias Schiffer
A more sophisticated implementation could try to combine fragment checksums
when all fragments have CHECKSUM_COMPLETE and are split at even offsets.
For now, we just set ip_summed to CHECKSUM_NONE to avoid "hw csum failure"
warnings in the
From: Sven Eckelmann
batman-adv uses internal indices for each enabled and active interface.
It is currently used by the B.A.T.M.A.N. IV algorithm to identifify the
correct position in the ogm_cnt bitmaps.
The type for the number of enabled interfaces (which defines the next
From: Matthias Schiffer
eth_type_trans() internally calls skb_pull(), which does not adjust the
skb checksum; skb_postpull_rcsum() is necessary to avoid log spam of the
form "bat0: hw csum failure" when packets with CHECKSUM_COMPLETE are
received.
Note that in
Hello,
On Fri, 2 Mar 2018 16:40:44 +0100, Antoine Tenart wrote:
> /* Attach long pool to rxq */
> @@ -4551,7 +4559,7 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, int pool,
> int pkt_size)
> struct mvpp2_bm_pool *new_pool = >priv->bm_pools[pool];
> int num;
>
> - if (pool <
On 02/03/18 18:32, David Ahern wrote:
> fib_multipath_hash only needs net struct to check a sysctl. Make it
> clear by passing net instead of fib_info. In the end this allows
> alignment between the ipv4 and ipv6 versions.
>
> Signed-off-by: David Ahern
> ---
>
On Thu, Mar 01, 2018 at 10:07:05PM +0200, Denys Fedoryshchenko wrote:
> On 2018-03-01 22:01, Guillaume Nault wrote:
> > diff --git a/drivers/net/ppp/ppp_generic.c
> > b/drivers/net/ppp/ppp_generic.c
> > index 255a5def56e9..2acf4b0eabd1 100644
> > --- a/drivers/net/ppp/ppp_generic.c
> > +++
On Fri, 2 Mar 2018 17:29:14 +0800
Jason Wang wrote:
> XDP_REDIRECT support for mergeable buffer was removed since commit
> 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable()
> case"). This is because we don't reserve enough tailroom for struct
>
PPP units don't hold any reference on the channels connected to it.
It is the channel's responsibility to ensure that it disconnects from
its unit before being destroyed.
In practice, this is ensured by ppp_unregister_channel() disconnecting
the channel from the unit before dropping a reference on
On Thu, 1 Mar 2018 18:49:53 -0800
Alexander Duyck wrote:
> On Thu, Mar 1, 2018 at 3:58 PM, Alex Williamson
> wrote:
> > On Thu, 1 Mar 2018 14:42:40 -0800
> > Alexander Duyck wrote:
> >
> >> On Thu, Mar 1, 2018
From: Sven Eckelmann
The function batadv_iv_gw_dump stops the processing loop when
batadv_iv_gw_dump_entry returns a non-0 return code. This should only
happen when the buffer is full. Otherwise, an empty message may be
returned by batadv_gw_dump. This empty message
On 3/2/2018 6:42 AM, David Miller wrote:
From: "santosh.shilim...@oracle.com"
Date: Thu, 1 Mar 2018 22:22:07 -0800
Versioning comment typically goes below "---" and not part of
commit message.
I like them to be in the commit message most of the time.
> > > > +static int lan743x_phy_reset(struct lan743x_adapter *adapter) {
> > > > + u32 data;
> > > > +
> > > > + data = lan743x_csr_read(adapter, PMT_CTL);
> > > > + data |= PMT_CTL_ETH_PHY_RST_;
> > > > + lan743x_csr_write(adapter, PMT_CTL, data);
> > > > +
> > > > +
On 03/02/2018 02:51 AM, David Laight wrote:
> From: Florian Fainelli
>>
>> Do not use memcpy() which is not safe, but instead use strncpy() which
>> will make sure that the string is NUL terminated (in the Linux
>> implementation) if the string is smaller than the length specified. This
>> fixes
If the user didn't specify any control action, don't pop the command line
arguments: otherwise, parsing of the next argument (tipically the 'index'
keyword) results in an error, causing the following 'tc-testing' failures:
Test a6d6: Add skbedit action with index
Test 38f3: Delete skbedit
fib_multipath_hash only needs net struct to check a sysctl. Make it
clear by passing net instead of fib_info. In the end this allows
alignment between the ipv4 and ipv6 versions.
Signed-off-by: David Ahern
---
include/net/ip_fib.h | 2 +-
net/ipv4/fib_semantics.c | 2 +-
IPv6 does path selection for multipath routes deep in the lookup
functions. The next patch adds L4 hash option and needs the skb
for the forward path. To get the skb to the relevant FIB lookup
functions it needs to go through the fib rules layer, so add a
lookup_data argument to the fib_lookup_arg
For tests using veth interfaces, the test infrastructure can create
the netdevs if they do not exist. Arguably this is a preferred approach
since the tests require p$N and p$(N+1) to be pairs.
Signed-off-by: David Ahern
---
.../net/forwarding/forwarding.config.sample|
On 02/03/18 18:32, David Ahern wrote:
> __get_hash_from_flowi6 is still used for flowlabels, but the IPv4
> variant and the wrappers to both are not used. Remove them.
>
> Signed-off-by: David Ahern
> Reviewed-by: Ido Schimmel
> ---
> include/net/flow.h
On 02/03/18 18:32, David Ahern wrote:
> Some operators prefer IPv6 path selection to use a standard 5-tuple
> hash rather than just an L3 hash with the flow the label. To that end
> add support to IPv6 for multipath hash policy similar to bf4e0a3db97eb
> ("net: ipv4: add support for ECMP hash
When we exceed current packets limit and have more than one
segment in the list returned by skb_gso_segment(), netem drops
only the first one, skipping the rest, hence kmemleak reports:
unreferenced object 0x880b5d23b600 (size 1024):
comm "softirq", pid 0, jiffies 4384527763 (age 2770.629s)
Hello,
On Fri, 2 Mar 2018 16:40:40 +0100, Antoine Tenart wrote:
> +static struct {
> + int pkt_size;
> + int buf_num;
> +} mvpp2_pools[MVPP2_BM_POOLS_NUM];
Any reason for not doing:
} mvpp2_pools[MVPP2_BM_POOLS_NUM] = {
[MVPP2_BM_SHORT] = {
.pkt_size =
On 01/03/18 18:36, David Miller wrote:
> We really should have the ethtool interfaces under deep freeze until we
> convert it to netlink or similar.
> Second, this is a real hackish way to extend ethtool with new
> semantics. A structure changes layout based upon a flag bit setting
> in an
From: Sven Eckelmann
The function batadv_bla_claim_dump_bucket must be able to handle
non-complete dumps of a single bucket. It tries to do that by saving the
latest dumped index in *idx_skip to inform the caller about the current
state.
But the caller only assumes that
From: Sven Eckelmann
The function batadv_bla_backbone_dump_bucket must be able to handle
non-complete dumps of a single bucket. It tries to do that by saving the
latest dumped index in *idx_skip to inform the caller about the current
state.
But the caller only assumes that
From: Sven Eckelmann
The function batadv_v_gw_dump stops the processing loop when
batadv_v_gw_dump_entry returns a non-0 return code. This should only
happen when the buffer is full. Otherwise, an empty message may be
returned by batadv_gw_dump. This empty message
On Fri, Mar 02, 2018 at 10:48:42AM -0500, Paul Moore wrote:
> On Thu, Mar 1, 2018 at 8:41 PM, Richard Guy Briggs wrote:
> > On 2018-03-01 14:41, Richard Guy Briggs wrote:
> FYI, I think you may have a problem with something in your outgoing
> mail path; I didn't receive the
Marcelo Ricardo Leitner writes:
> On Thu, Mar 01, 2018 at 01:45:30PM -0500, Roman Mashak wrote:
>> Signed-off-by: Roman Mashak
>> ---
>> net/sched/act_gact.c | 17 +
>> 1 file changed, 17 insertions(+)
>>
>> diff --git
Some operators prefer IPv6 path selection to use a standard 5-tuple
hash rather than just an L3 hash with the flow the label. To that end
add support to IPv6 for multipath hash policy similar to bf4e0a3db97eb
("net: ipv4: add support for ECMP hash policy choice"). The default
is still L3 which
Hardware supports multipath selection using the standard L4 5-tuple
instead of just L3 and the flow label. In addition, some network
operators prefer IPv6 path selection to use the 5-tuple. To that end,
add support to IPv6 for multipath hash policy similar to
bf4e0a3db97eb ("net: ipv4: add support
As of commit e37b1e978bec5 ("ipv6: route: dissect flow in input path if
fib rules need it") fib_multipath_hash takes an optional flow keys. If
non-NULL it means the skb has already been dissected. If not set, then
fib_multipath_hash needs to call skb_flow_dissect_flow_keys.
Simplify the logic by
__get_hash_from_flowi6 is still used for flowlabels, but the IPv4
variant and the wrappers to both are not used. Remove them.
Signed-off-by: David Ahern
Reviewed-by: Ido Schimmel
---
include/net/flow.h| 16
Similar to 28678f07f127d ("mlxsw: spectrum_router: Update multipath hash
parameters upon netevents") for IPv4, make sure the kernel and asic are
using the same hash algorithm for path selection.
Signed-off-by: David Ahern
Reviewed-by: Ido Schimmel
Add IPv6 multipath test using L4 hashing. Created with inputs from
Ido Schimmel.
Signed-off-by: David Ahern
Reviewed-by: Ido Schimmel
Tested-by: Ido Schimmel
---
.../selftests/net/forwarding/router_multipath.sh | 44
Rename NETEVENT_MULTIPATH_HASH_UPDATE to
NETEVENT_IPV4_MPATH_HASH_UPDATE to denote it relates to a change
in the IPv4 hash policy.
Signed-off-by: David Ahern
Reviewed-by: Ido Schimmel
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
Make rt6_multipath_hash more of a direct parallel to fib_multipath_hash
and reduce stack and overhead in the process: get_hash_from_flowi6 is
just a wrapper around __get_hash_from_flowi6 with another stack
allocation for flow_keys. Move setting the addresses, protocol and
label into
On Fri, Mar 02, 2018 at 08:32:12AM -0800, David Ahern wrote:
> fib_multipath_hash only needs net struct to check a sysctl. Make it
> clear by passing net instead of fib_info. In the end this allows
> alignment between the ipv4 and ipv6 versions.
>
> Signed-off-by: David Ahern
From: Sven Eckelmann
Signed-off-by: Sven Eckelmann
Signed-off-by: Simon Wunderlich
---
include/uapi/linux/batadv_packet.h | 2 +-
include/uapi/linux/batman_adv.h| 2 +-
net/batman-adv/Kconfig | 2 +-
This will allow functionality depending on the hardware being traffic
class aware to work. In particular the tc-flower offloading checks
verifies that this bit is set.
Signed-off-by: Vinicius Costa Gomes
---
drivers/net/ethernet/intel/igb/igb_main.c | 3 +++
1 file
This adds basic functions needed to implement offloading for filters
created by tc-flower.
Signed-off-by: Vinicius Costa Gomes
---
drivers/net/ethernet/intel/igb/igb_main.c | 66 +++
1 file changed, 66 insertions(+)
diff --git
This allows igb_add_filter()/igb_erase_filter() to work on filters
that include MAC addresses (both source and destination).
For now, this only exposes the functionality, the next commit glues
ethtool into this. Later in this series, these APIs are used to allow
offloading of cls_flower filters.
Makes it possible to direct packets to queues based on their source
address. Documents the expected usage of the 'flags' parameter.
Signed-off-by: Vinicius Costa Gomes
---
drivers/net/ethernet/intel/igb/e1000_defines.h | 1 +
drivers/net/ethernet/intel/igb/igb.h
This adds the capability of configuring the queue steering of arriving
packets based on their source and destination MAC addresses.
In practical terms this adds support for the following use cases,
characterized by these examples:
$ ethtool -N eth0 flow-type ether dst aa:aa:aa:aa:aa:aa action 0
Because the order of the parameters passes to 'hlist_add_behind()' was
inverted, the 'parent' node was added "behind" the 'input', as input
is not in the list, this causes the 'input' node to be lost.
Fixes: 0e71def25281 ("igb: add support of RX network flow classification")
Signed-off-by:
On Fri, 2 Mar 2018 21:16:48 +0300
Alexey Kodanev wrote:
> When we exceed current packets limit and have more than one
> segment in the list returned by skb_gso_segment(), netem drops
> only the first one, skipping the rest, hence kmemleak reports:
>
> unreferenced
On the RAH registers there are semantic differences on the meaning of
the "queue" parameter for traffic steering depending on the controller
model: there is the 82575 meaning, which "queue" means a RX Hardware
Queue, and the i350 meaning, where it is a reception pool.
The previous behaviour was
Hi,
Changes from v1:
- Addressed review comments from Alexander Duyck and Florian
Fainelli;
- Adding and removing cls_flower filters are now proposed in the same
patch;
- cls_flower filters are kept in a separated list from "ethtool"
filters (so that section of the original cover
This allows filters added by tc-flower and specifying MAC addresses,
Ethernet types, and the VLAN priority field, to be offloaded to the
controller.
This reuses most of the infrastructure used by ethtool, ethtool can be
used to read these filters, but modification and deletion can only be
done
On Fri, Mar 2, 2018 at 1:23 PM, Matthew Wilcox wrote:
> On Fri, Mar 02, 2018 at 10:48:42AM -0500, Paul Moore wrote:
>> On Thu, Mar 1, 2018 at 8:41 PM, Richard Guy Briggs wrote:
>> > On 2018-03-01 14:41, Richard Guy Briggs wrote:
>> FYI, I think you may have
Sample output:
# rdma resource
2: cxgb4_0: pd 5 cq 2 qp 2 cm_id 3 mr 7
3: mlx4_0: pd 7 cq 3 qp 3 cm_id 3 mr 7
# rdma resource show cm_id
link cxgb4_0/- lqpn 0 qp-type RC state LISTEN ps TCP pid 30485 comm rping
src-addr 0.0.0.0:7174
link cxgb4_0/2 lqpn 1048 qp-type RC state CONNECT ps TCP pid
On Fri, Mar 02, 2018 at 11:52:27AM -0800, Samudrala, Sridhar wrote:
>
>
> On 3/2/2018 11:41 AM, Michael S. Tsirkin wrote:
> > On Fri, Mar 02, 2018 at 07:26:25AM -0800, Alexander Duyck wrote:
> > > The design limits things to a 1:1 relationship since we just have the
> > > child and backup
On Fri, 2018-03-02 at 11:53 +0100, Lorenzo Bianconi wrote:
> Fix the following slab-out-of-bounds kasan report in
> ndisc_fill_redirect_hdr_option when the incoming ipv6 packet is not
> linear and the accessed data are not in the linear data region of orig_skb
>
> Reported-by: Jianlin Shi
Hi David,
The following patchset contains Netfilter fixes for your net tree,
they are:
1) Put back reference on CLUSTERIP configuration structure from the
error path, patch from Florian Westphal.
2) Put reference on CLUSTERIP configuration instead of freeing it,
another cpu may still be
From: Florian Westphal
Once struct is added to per-netns list it becomes visible to other cpus,
so we cannot use kfree().
Also delay setting entries refcount to 1 until after everything is
initialised so that when we call clusterip_config_put() in this spot
entries is still
From: Florian Westphal
We need to make sure the offsets are not out of range of the
total size.
Also check that they are in ascending order.
The WARN_ON triggered by syzkaller (it sets panic_on_warn) is
changed to also bail out, no point in continuing parsing.
Briefly tested
From: Florian Westphal
ebt_among is special, it has a dynamic match size and is exempt
from the central size checks.
Therefore it must check that the size of the match structure
provided from userspace is sane by making sure em->match_size
is at least the minimum size of the
From: Taehee Yoo
In the ip_rcv, IPSTATS_MIB_CSUMERRORS is increased when
checksum error is occurred.
bridge netfilter routine should increase IPSTATS_MIB_CSUMERRORS.
Signed-off-by: Taehee Yoo
Signed-off-by: Pablo Neira Ayuso
---
From: Florian Westphal
This needs to put() the entry to avoid a resource leak in error path.
Signed-off-by: Florian Westphal
Signed-off-by: Pablo Neira Ayuso
---
net/ipv4/netfilter/ipt_CLUSTERIP.c | 8 ++--
1 file changed, 6
From: Florian Westphal
All of these conditions are not fatal and should have
been WARN_ONs from the get-go.
Convert them to WARN_ONs and bail out.
Signed-off-by: Florian Westphal
Signed-off-by: Pablo Neira Ayuso
---
From: Felix Fietkau
Add a missing call to csum_replace4 like on SNAT.
Signed-off-by: Felix Fietkau
Signed-off-by: Pablo Neira Ayuso
---
net/ipv4/netfilter/nf_flow_table_ipv4.c | 1 +
1 file changed, 1 insertion(+)
diff --git
From: Florian Westphal
l4proto->manip_pkt() can cause reallocation of skb head so pointer
to the ipv6 header must be reloaded.
Reported-and-tested-by:
Fixes: 58a317f1061c89 ("netfilter: ipv6: add IPv6 NAT support")
On Fri, Mar 2, 2018 at 11:42 AM, Michael S. Tsirkin wrote:
> On Fri, Mar 02, 2018 at 05:20:17PM +0100, Jiri Pirko wrote:
>> >Yeah, this code essentially calls out the "shareable" code with a
>> >comment at the start and end of the section what defines the
>> >virtio_bypass
On Thu, Mar 1, 2018 at 11:21 PM, Stefan Assmann wrote:
> On 2018-03-01 19:40, Alexander Duyck wrote:
>> On Thu, Mar 1, 2018 at 8:12 AM, wrote:
>> > + intel-wired-...@lists.osuosl.org
>> >
>> >
>> > On 2018-03-01 21:41, p...@codeaurora.org wrote:
>> >>
On Thu, Mar 1, 2018 at 12:08 PM, Sridhar Samudrala
wrote:
> This patch enables virtio_net to switch over to a VF datapath when a VF
> netdev is present with the same MAC address. It allows live migration
> of a VM with a direct attached VF without the need to setup a
On Thu, Mar 01, 2018 at 05:13:38PM +1100, Daniel Axtens wrote:
> tbf_enqueue() checks the size of a packet before enqueuing it.
> However, the GSO size check does not consider the GSO_BY_FRAGS
> case, and so will drop GSO SCTP packets, causing a massive drop
> in throughput.
>
> Use
On Thu, Mar 01, 2018 at 05:13:37PM +1100, Daniel Axtens wrote:
> If you take a GSO skb, and split it into packets, will the network
> length (L3 headers + L4 headers + payload) of those packets be small
> enough to fit within a given MTU?
>
> skb_gso_validate_mtu gives you the answer to that
On Fri, 2 Mar 2018 15:24:29 +, Edward Cree wrote:
> On Tue, Feb 27, 2018 at 3:47 PM, Jakub Kicinski wrote:
>
> > Please, let's stop extending ethtool_rx_flow APIs. I bit my tongue
> > when Intel was adding their "redirection to VF" based on ethtool ntuples
> > and look now
Conceptually this is right.
And I'm 100% fine with dev mtu change triggering pmtu decrease.
I'm not so sold on the pmtu increase.
PMTUD is one of those things that never ever works right in practice.
There's too many icmp blackholes, rate limits, overloaded management
cpus in switches,
On Fri, Mar 02, 2018 at 05:20:17PM +0100, Jiri Pirko wrote:
> >Yeah, this code essentially calls out the "shareable" code with a
> >comment at the start and end of the section what defines the
> >virtio_bypass functionality. It would just be a matter of mostly
> >cutting and pasting to put it into
On 3/2/2018 11:41 AM, Michael S. Tsirkin wrote:
On Fri, Mar 02, 2018 at 07:26:25AM -0800, Alexander Duyck wrote:
The design limits things to a 1:1 relationship since we just have the
child and backup pointers, but I don't think I am seeing exception
handling to prevent us from overwriting the
Sample output:
# rdma resource show cq
link cxgb4_0/- cqe 46 users 2 pid 30503 comm rping
link cxgb4_0/- cqe 46 users 2 pid 30498 comm rping
link mlx4_0/- cqe 63 users 2 pid 30494 comm rping
link mlx4_0/- cqe 63 users 2 pid 30489 comm rping
link mlx4_0/- cqe 1023 users 2 poll_ctx WORKQUEUE pid 0
From: Steve Wise
Pull in the latest rdma_netlink.h which has support for
the rdma nldev resource tracking objects being added
with this patch series.
Signed-off-by: Steve Wise
---
include/uapi/rdma/rdma_netlink.h | 44
Hello,
While testing bpf-next, I noticed that I was reading garbage when
accessing some task_struct members, and the issue seems caused by the
recent commit 2bc2f688fdf8 ("Makefile: move stack-protector
availability out of Kconfig") which removes CONFIG_CC_STACKPROTECTOR
from autoconf.h.
When I
Initialize the rd struct so port_idx is 0 unless set otherwise.
Otherwise, strict_port queries end up passing an uninitialized PORT
nlattr.
Signed-off-by: Steve Wise
---
rdma/rdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/rdma/rdma.c
Sample output:
Without CAP_NET_ADMIN capability:
link mlx4_0/- users 0 pid 0 comm [ib_srpt]
link mlx4_0/- users 0 pid 0 comm [ib_srp]
link mlx4_0/- users 1 pid 0 comm [ib_core]
link cxgb4_0/- users 0 pid 0 comm [ib_srp]
With CAP_NET_ADMIN capability:
link mlx4_0/- local_dma_lkey 0x8000 users 0
Sample output:
Without CAP_NET_ADMIN:
$ rdma resource show mr mrlen 65536
link mlx4_0/- mrlen 65536 pid 0 comm [nvme_rdma]
link cxgb4_0/- mrlen 65536 pid 0 comm [nvme_rdma]
With CAP_NET_ADMIN:
# rdma resource show mr mrlen 65536
link mlx4_0/- rkey 0x12702 lkey 0x12702 iova 0x85724a000 mrlen
On Thu, Mar 01, 2018 at 05:13:40PM +1100, Daniel Axtens wrote:
> They're very hard to use properly as they do not consider the
> GSO_BY_FRAGS case. Code should use skb_gso_validate_network_len
> and skb_gso_validate_mac_len as they do consider this case.
>
> Make the seglen functions static,
On Thu, Mar 01, 2018 at 05:13:39PM +1100, Daniel Axtens wrote:
> Replace skb_gso_network_seglen() with
> skb_gso_validate_network_len(), as it considers the GSO_BY_FRAGS
> case.
>
> Signed-off-by: Daniel Axtens
Reviewed-by: Marcelo Ricardo Leitner
>
On Fri, Mar 2, 2018 at 2:25 PM, Paul Moore wrote:
> On Fri, Mar 2, 2018 at 1:23 PM, Matthew Wilcox wrote:
>> On Fri, Mar 02, 2018 at 10:48:42AM -0500, Paul Moore wrote:
>>> On Thu, Mar 1, 2018 at 8:41 PM, Richard Guy Briggs wrote:
>>> >
On Fri, Mar 02, 2018 at 07:26:25AM -0800, Alexander Duyck wrote:
> The design limits things to a 1:1 relationship since we just have the
> child and backup pointers, but I don't think I am seeing exception
> handling to prevent us from overwriting the child pointers so there
> may be a leak there.
On Fri, Mar 02, 2018 at 12:09:57PM -0800, Gianluca Borello wrote:
> Hello,
>
> While testing bpf-next, I noticed that I was reading garbage when
> accessing some task_struct members, and the issue seems caused by the
> recent commit 2bc2f688fdf8 ("Makefile: move stack-protector
> availability out
1 - 100 of 248 matches
Mail list logo