On Wed, Jun 19, 2019 at 06:40:16AM +, Jianbo Liu wrote:
> The 06/19/2019 13:04, Leon Romanovsky wrote:
> > On Wed, Jun 19, 2019 at 04:44:26AM +, Jianbo Liu wrote:
> > > The 06/18/2019 18:19, Leon Romanovsky wrote:
> > > > On Mon, Jun 17, 2019 at 07:23:30PM +, Saeed Mahameed wrote:
> > >
The 06/19/2019 13:42, Parav Pandit wrote:
>
>
> > -Original Message-
> > From: Jianbo Liu
> > Sent: Wednesday, June 19, 2019 10:42 AM
> > To: Parav Pandit
> > Cc: Saeed Mahameed ; Leon Romanovsky
> > ; netdev@vger.kernel.org; linux-
> > r...@vger.kernel.org; Eli Britstein ; Roi Dayan
> >
From: Jiri Pirko
Implement support for previously added flow dissector meta key.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
include/net/flow_offload.h | 6 ++
net/core/flow_offload.c| 7 +++
2 files changed, 13 insertions(+)
diff --git a/include/net/flow_offload.h
From: Ido Schimmel
Jiri says:
In case of using shared block, user might find it handy to be able to insert
filters to match on particular ingress device. This patchset exposes the
ingress ifindex through flow_dissector and flow_offload so mlxsw can use it to
push down to HW. See the selftests fo
From: Jiri Pirko
Use previously introduced infra to obtain and store ingress ifindex
instead doing it locally.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
net/sched/cls_flower.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/net/sched/cls_flow
From: Jiri Pirko
Benefit from the previously extended flow_dissector infrastructure and
offload matching on ingress port.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
.../net/ethernet/mellanox/mlxsw/spectrum.h| 9
.../ethernet/mellanox/mlxsw/spectrum_acl.c| 9 +---
From: Jiri Pirko
RX_ACL_SYSTEM_PORT is equal to SRC_SYS_PORT - 1. So before write to
block we need to adjust the key value. Introduce new "EXT" helper to
implement this.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
.../ethernet/mellanox/mlxsw/core_acl_flex_keys.c | 13 +++
From: Jiri Pirko
Add new key meta that contains ingress ifindex value and add a function
to dissect this from skb. The key and function is prepared to cover
other potential skb metadata values dissection.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
include/linux/skbuff.h |
From: Jiri Pirko
Extend tc_flower to test plain ingress device matching and also
tc_shblock to test ingress device matching on shared block.
Add new tc_flower_router.sh where ingress device matching on egress
(after routing) is done.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
.
From: Jiri Pirko
RX_ACL_SYSTEM_PORT is 8 bit but SRC_SYS_PORT is 16 bits. Internally,
SRC_SYS_PORT is used to carry the value. Relax the checker in case of
RX_ACL_SYSTEM_PORT and allow different size.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
.../ethernet/mellanox/mlxsw/core_a
From: Jiri Pirko
Fix the size of the SRC_SYS_PORT element to be 16.
Signed-off-by: Jiri Pirko
Signed-off-by: Ido Schimmel
---
drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h | 2 +-
.../net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c | 8
2 files changed, 5 insertions
The 06/19/2019 13:04, Leon Romanovsky wrote:
> On Wed, Jun 19, 2019 at 04:44:26AM +, Jianbo Liu wrote:
> > The 06/18/2019 18:19, Leon Romanovsky wrote:
> > > On Mon, Jun 17, 2019 at 07:23:30PM +, Saeed Mahameed wrote:
> > > > From: Jianbo Liu
> > > >
> > > > If vport metadata matching is e
> -Original Message-
> From: Jianbo Liu
> Sent: Wednesday, June 19, 2019 10:42 AM
> To: Parav Pandit
> Cc: Saeed Mahameed ; Leon Romanovsky
> ; netdev@vger.kernel.org; linux-
> r...@vger.kernel.org; Eli Britstein ; Roi Dayan
> ; Mark Bloch
> Subject: Re: [PATCH mlx5-next 05/15] net/mlx5
tree: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
master
head: 39f5886032380e49119786b23274b38e9b3aa99c
commit: c9bb6165a16e6d5498981a6c777b94a78e74462b [91/276] netfilter:
nf_conntrack_bridge: fix CONFIG_IPV6=y
config: i386-randconfig-n027-201924 (attached as .config)
The 06/18/2019 18:31, Parav Pandit wrote:
>
>
> > -Original Message-
> > From: netdev-ow...@vger.kernel.org On
> > Behalf Of Saeed Mahameed
> > Sent: Tuesday, June 18, 2019 12:53 AM
> > To: Saeed Mahameed ; Leon Romanovsky
> >
> > Cc: netdev@vger.kernel.org; linux-r...@vger.kernel.org;
On Wed, Jun 19, 2019 at 04:44:26AM +, Jianbo Liu wrote:
> The 06/18/2019 18:19, Leon Romanovsky wrote:
> > On Mon, Jun 17, 2019 at 07:23:30PM +, Saeed Mahameed wrote:
> > > From: Jianbo Liu
> > >
> > > If vport metadata matching is enabled in eswitch, the rule created
> > > must be changed
On Tue, Jun 18, 2019 at 06:25:46PM +, Saeed Mahameed wrote:
> On Tue, 2019-06-18 at 10:47 +, Parav Pandit wrote:
> > Hi Leon,
> >
> > > -Original Message-
> > > From: Leon Romanovsky
> > > Sent: Tuesday, June 18, 2019 4:12 PM
> > > To: Saeed Mahameed
> > > Cc: netdev@vger.kernel.or
On Tue, Jun 18, 2019 at 06:51:45PM +, Saeed Mahameed wrote:
> On Tue, 2019-06-18 at 20:15 +0300, Leon Romanovsky wrote:
> > From: Leon Romanovsky
> >
> > Changelog:
> > v0 -> v1:
>
> Normally 1st submission is V1 and 2nd is V2.
> so this should have been v1->v2.
"Normally" depends on the lan
The 06/18/2019 18:19, Leon Romanovsky wrote:
> On Mon, Jun 17, 2019 at 07:23:30PM +, Saeed Mahameed wrote:
> > From: Jianbo Liu
> >
> > If vport metadata matching is enabled in eswitch, the rule created
> > must be changed to match on the metadata, instead of source port.
> >
> > Signed-off-by
On 6/19/2019 12:40 AM, Pablo Neira Ayuso wrote:
> On Sat, Jun 15, 2019 at 08:14:21PM +0800, we...@ucloud.cn wrote:
> [...]
>> +static void nft_bridge_pvid_eval(const struct nft_expr *expr,
>> + struct nft_regs *regs,
>> + const struct nft_pk
From: Xin Long
Date: Mon, 17 Jun 2019 21:34:12 +0800
> There are two kinds of crashes reported many times by syzbot with no
> reproducer. Call Traces are like:
...
> They were caused by the fib_nh_common percpu member 'nhc_pcpu_rth_output'
> overwritten by another percpu variable 'dev->tstats' a
On Mon, Jun 17, 2019 at 11:26:28AM -0700, Alexei Starovoitov wrote:
> On Sun, Jun 16, 2019 at 11:59 PM Alexei Starovoitov
> wrote:
> >
> > On Thu, Jun 6, 2019 at 6:31 PM Andreas Steinmetz wrote:
> > >
> > > Below is the source in question. It may look a bit strange but I
> > > had to extract it f
On Mon, Jun 17, 2019 at 2:17 PM Daniel Borkmann wrote:
>
> On 06/17/2019 09:26 PM, Andrii Nakryiko wrote:
> > This patch set implements initial version (as discussed at LSF/MM2019
> > conference) of a new way to specify BPF maps, relying on BTF type
> > information,
> > which allows for easy exte
Drivers may rely on pci_disable_link_state() having disabled certain
ASPM link states. If OS can't control ASPM then pci_disable_link_state()
turns into a no-op w/o informing the caller. The driver therefore may
falsely assume the respective ASPM link states are disabled.
Let pci_disable_link_state
Certain chip version / board combinations have massive problems if
ASPM is active. If BIOS enables ASPM and doesn't let OS control it,
then we may have a problem with the current code. Therefore check the
return code of pci_disable_link_state() and don't enable ASPM in the
network chip if OS can't
Drivers like r8169 rely on pci_disable_link_state() having disabled
certain ASPM link states. If OS can't control ASPM then
pci_disable_link_state() turns into a no-op w/o informing the caller.
The driver therefore may falsely assume the respective ASPM link
states are disabled. Let pci_disable_lin
On Tue, Jun 18, 2019 at 1:44 PM Linus Walleij wrote:
>
> On Fri, May 24, 2019 at 9:41 PM Rob Herring wrote:
>
> > > + reg:
> > > +maxItems: 1
> > > +description: Ethernet MMIO address range
> > > +
> > > + queue-rx:
> > > +$ref: '/schemas/types.yaml#/definitions/phandle-array'
> > >
From: Willem de Bruijn
Kselftest can be run against older kernels. Instead of failing hard
when a feature is unsupported, return the KSFT_SKIP exit code.
Specifically, do not fail hard on missing udp zerocopy.
The udp gso bench test runs multiple test cases from a single script.
Fail if any cas
On Fri, May 24, 2019 at 9:41 PM Rob Herring wrote:
> > + reg:
> > +maxItems: 1
> > +description: Ethernet MMIO address range
> > +
> > + queue-rx:
> > +$ref: '/schemas/types.yaml#/definitions/phandle-array'
> > +maxItems: 1
>
> This doesn't actually do what you think it is doing
Hi.
I have an active-backup bonded connection on a 5.1.6 kernel where the
slaves are an Ethernet interface and a wifi interface. The goal is to
have network transparent (i.e. same and IP address on both interfaces)
interface which takes advantage of high-speed and low-latency when it
can be physi
On Mon, 17 Jun 2019 19:43:53 +0100, Edward Cree wrote:
> On 14/06/2019 15:33, John Hurley wrote:
> > Instead of
> > returning TC_ACT_REINSERT, change the type to the new TC_ACT_CONSUMED
> > which tells the caller that the packet has been stolen by another process
> > and that no consume call is req
On 06/18, Alexei Starovoitov wrote:
> On Tue, Jun 18, 2019 at 11:09 AM Stanislav Fomichev wrote:
> >
> > On 06/18, Stanislav Fomichev wrote:
> > > On 06/18, Alexei Starovoitov wrote:
> > > > On Mon, Jun 17, 2019 at 11:01:01AM -0700, Stanislav Fomichev wrote:
> > > > > Implement new BPF_PROG_TYPE_C
On Tue, 2019-06-18 at 20:15 +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky
>
> Changelog:
> v0 -> v1:
Normally 1st submission is V1 and 2nd is V2.
so this should have been v1->v2.
For mlx5-next patches:
Acked-by: Saeed Mahameed
> * Fix the unbind / hot unplug flows to work properly
On Tue, 2019-06-18 at 20:26 +0300, Leon Romanovsky wrote:
> From: Mark Zhang
>
> Support bind a qp with counter. If counter is null then bind the qp
> to
> the default counter. Different QP state has different operation:
> - RESET: Set the counter field so that it will take effective
> during R
On Tue, 2019-06-18 at 20:26 +0300, Leon Romanovsky wrote:
> From: Mark Zhang
>
> Add rts2rts_qp_counters_set_id field in hca cap so that RTS2RTS
> qp modification can be used to change the counter of a QP.
>
> Signed-off-by: Mark Zhang
> Reviewed-by: Majd Dibbiny
> Signed-off-by: Leon Romanovs
New parameters added to Cadence ethernet controller DT binding
for USXGMII interface.
Signed-off-by: Parshuram Thombare
---
Documentation/devicetree/bindings/net/macb.txt | 3 +++
1 file changed, 3 insertions(+)
diff --git a/Documentation/devicetree/bindings/net/macb.txt
b/Documentation/device
The HiperSockets-based transport path in af_iucv is still too closely
entangled with qeth.
With commit a647a02512ca ("s390/qeth: speed-up L3 IQD xmit"), the
relevant xmit code in qeth has begun to use skb_cow_head(). So to avoid
unnecessary skb head expansions, af_iucv must learn to
1) respect dev-
On Tue, Jun 18, 2019 at 05:31:12PM +0200, Pablo Neira Ayuso wrote:
> > +{
> > + unsigned char optbuf[sizeof(struct ip_options) + 41];
>
> In other parts of the kernel this is + 40:
>
> net/ipv4/cipso_ipv4.c: unsigned char optbuf[sizeof(struct ip_options) + 40];
>
> here it is + 41.
>
> ...
>
Hi Dave,
I spent a few cycles on transmit problems for af_iucv over regular
netdevices - please apply the following fixes to -net.
The first patch allows for skb allocations outside of GFP_DMA, while the
second patch respects that drivers might use skb_cow_head() and/or want
additional dev->needed
af_iucv sockets over z/VM IUCV require that their skbs are allocated
in DMA memory. This restriction doesn't apply to connections over
HiperSockets. So only set this limit for z/VM IUCV sockets, thereby
increasing the likelihood that the large (and linear!) allocations for
HiperTransport messages s
Even when running as VM guest (ie pr_iucv != NULL), af_iucv can still
open HiperTransport-based connections. For robust operation these
connections require the af_iucv_netdev_notifier, so register it
unconditionally.
Also handle any error that register_netdevice_notifier() returns.
Fixes: 9fbd87d
On Tue, Jun 18, 2019 at 11:09 AM Stanislav Fomichev wrote:
>
> On 06/18, Stanislav Fomichev wrote:
> > On 06/18, Alexei Starovoitov wrote:
> > > On Mon, Jun 17, 2019 at 11:01:01AM -0700, Stanislav Fomichev wrote:
> > > > Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
> > > > BPF_CGROU
This patch replace phylib API's by phylink API's.
Signed-off-by: Parshuram Thombare
---
drivers/net/ethernet/cadence/Kconfig | 2 +-
drivers/net/ethernet/cadence/macb.h | 3 +
drivers/net/ethernet/cadence/macb_main.c | 312 +--
3 files changed, 182 insertions(+),
From: Wei Wang
Initialize rt6->rt6i_uncached on the following pre-allocated dsts:
net->ipv6.ip6_null_entry
net->ipv6.ip6_prohibit_entry
net->ipv6.ip6_blk_hole_entry
This is a preparation patch for later commits to be able to distinguish
dst entries in uncached list by doing:
!list_empty(rt6->rt6
From: Wei Wang
This new flag is to instruct the route lookup function to not take
refcnt on the dst entry. The user which does route lookup with this flag
must properly use rcu protection.
ip6_pol_route() is the major route lookup function for both tx and rx
path.
In this function:
Do not take re
From: Wei Wang
ip6_route_input() is the key function to do the route lookup in the
rx data path. All the callers to this function are already holding rcu
lock. So it is fairly easy to convert it to not take refcnt on the dst:
We pass in flag RT6_LOOKUP_F_DST_NOREF and do skb_dst_set_noref().
This
From: Wei Wang
For tx path, in most cases, we still have to take refcnt on the dst
cause the caller is caching the dst somewhere. But it still is
beneficial to make use of RT6_LOOKUP_F_DST_NOREF flag while doing the
route lookup. It is cause this flag prevents manipulating refcnt on
net->ipv6.ip6
From: Wei Wang
This patch specifically converts the rule lookup logic to honor this
flag and not release refcnt when traversing each rule and calling
lookup() on each routing table.
Similar to previous patch, we also need some special handling of dst
entries in uncached list because there is alwa
From: Wei Wang
Ipv6 route lookup code always grabs refcnt on the dst for the caller.
But for certain cases, grabbing refcnt is not always necessary if the
call path is rcu protected and the caller does not cache the dst.
Another issue in the route lookup logic is:
When there are multiple custom r
On Tue, 2019-06-18 at 10:47 +, Parav Pandit wrote:
> Hi Leon,
>
> > -Original Message-
> > From: Leon Romanovsky
> > Sent: Tuesday, June 18, 2019 4:12 PM
> > To: Saeed Mahameed
> > Cc: netdev@vger.kernel.org; linux-r...@vger.kernel.org; Bodong Wang
> > ; Parav Pandit ; Mark
> > Bloch
On 6/18/19 10:57 AM, Benedikt Spranger wrote:
> Hi,
>
> while puting a Banana Pi R1 board into operation I faced network hickups
> and get into serious trouble from my coworkers:
>
> Banana Pi network setup:
> PC (eth1) <--> BPi R1 (wan) / BPi R1 (lan4) <--> DUT (eth0)
> 10.0.32.1 10.0.32.2
On 6/18/19 10:57 AM, Benedikt Spranger wrote:
> From: Florian Fainelli
>
> When enabling Broadcom tags on earlier devices such as BCM53125, we need
> to also enable Managed mode, as well as configure which port is going to
> be the IMP port. If we did not do that, the switch would just pass
> thr
On 06/18, Stanislav Fomichev wrote:
> On 06/18, Alexei Starovoitov wrote:
> > On Mon, Jun 17, 2019 at 11:01:01AM -0700, Stanislav Fomichev wrote:
> > > Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
> > > BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.
> > >
> > > BPF_CGROUP_SETSOCKOPT get a
Current struct pernet_operations exit() handlers are highly
discouraged to call synchronize_rcu().
There are cases where we need them, and exit_batch() does
not help the common case where a single netns is dismantled.
This patch leverages the existing synchronize_rcu() call
in cleanup_net()
Call
On Fri, Mar 8, 2019 at 5:23 PM Alin Năstac wrote:
> On Fri, Mar 8, 2019 at 5:04 PM Pablo Neira Ayuso wrote:
> > On Mon, Mar 04, 2019 at 09:40:12PM +0100, Arnd Bergmann wrote:
> > > With CONFIG_IPV6=m and CONFIG_NF_CONNTRACK_SIP=y, we now get a link
> > > failure:
> > >
> > > net/netfilter/nf_co
syzbot reported another issue caused by my recent patches. [1]
The issue here is that fqdir_exit() is initiating a work queue
and immediately returns. A bit later cleanup_net() was able
to free the MIB (percpu data) and the whole struct net was freed,
but we had active frag timers that fired and t
This series add a new pre_exit() method to struct pernet_operations
to solve a race in defrag units dismantle, without adding extra
delays to netns dismantles.
Eric Dumazet (2):
netns: add pre_exit method to struct pernet_operations
inet: fix various use-after-free in defrags units
include/n
Hi,
while puting a Banana Pi R1 board into operation I faced network hickups
and get into serious trouble from my coworkers:
Banana Pi network setup:
PC (eth1) <--> BPi R1 (wan) / BPi R1 (lan4) <--> DUT (eth0)
10.0.32.1 10.0.32.2 172.16.0.1 172.16.0.2
---8<---
#! /bin/bash
# cr
From: Florian Fainelli
When enabling Broadcom tags on earlier devices such as BCM53125, we need
to also enable Managed mode, as well as configure which port is going to
be the IMP port. If we did not do that, the switch would just pass
through the Broadcom tags on the wire and not act on them. We
From: Sebastian Andrzej Siewior
The broadcom tags are required to distinguish the traffic from external
ports and not use a bridge like setup (which is currently broken because
managed mode is now enabled). The tagged mode works for broadcast and
unicast traffic. The multicast missis are not hand
On Tue, Jun 18, 2019 at 05:19:51PM +0200, Jesper Dangaard Brouer wrote:
Hi, Jesper
On Tue, 18 Jun 2019 15:54:33 +0300 Ivan Khoronzhuk
wrote:
On Sun, Jun 16, 2019 at 10:56:25AM +, Tariq Toukan wrote:
>
>On 6/15/2019 12:33 PM, Ivan Khoronzhuk wrote:
>> On Thu, Jun 13, 2019 at 08:28:42PM +
From: Doug Ledford
Date: Tue, 18 Jun 2019 13:29:59 -0400
> On Tue, 2019-06-18 at 10:08 -0700, David Miller wrote:
>> From: Denis Kirjanov
>> Date: Mon, 17 Jun 2019 10:53:41 +0200
>>
>> > in IPoIB case we can't see a VF broadcast address for but
>> > can see for PF
>>
>> I just want to understa
On Tue, 2019-06-18 at 10:08 -0700, David Miller wrote:
> From: Denis Kirjanov
> Date: Mon, 17 Jun 2019 10:53:41 +0200
>
> > in IPoIB case we can't see a VF broadcast address for but
> > can see for PF
>
> I just want to understand why this need to see the VF broadcast
> address is IPoIB specific
From: Mark Zhang
This patch adds the ability to return the hwstats of per-port default
counters (which can also be queried through sysfs nodes).
Signed-off-by: Mark Zhang
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/nldev.c | 98 -
drivers/infinib
From: Mark Zhang
Provide an option to enable/disable per-port counter auto mode through
RDMA netlink. Limit it to users with ADMIN capability only.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/nldev.c | 78 +++
From: Mark Zhang
Provide an option to get current counter mode through RDMA netlink.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/counters.c | 13 ++
drivers/infiniband/core/nldev.c| 66 +-
From: Mark Zhang
Provide an option to allow users to manually bind a qp with a counter
through RDMA netlink. Limit it to users with ADMIN capability only.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/nldev.c | 111 +++
From: Mark Zhang
In manual mode a QP is bound to a counter manually. If counter is not
specified then a new one will be allocated.
Manually mode is enabled when user binds a QP, and disabled when the
last manually bound QP is unbound.
When auto-mode is turned off and there are counters left, manu
From: Mark Zhang
Since a QP can only be bound to one counter, then if it is bound to a
separate counter, for backward compatibility purpose, the statistic
value must be:
* stat of default counter
+ stat of all running allocated counters
+ stat of all deallocated counters (history stats)
Signed-o
From: Mark Zhang
This patch adds the ability to return all available counters
together with their properties and hwstats.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/counters.c | 26 +++-
drivers/infiniband/core/device.c |
From: Mark Zhang
Add counter set id as a parameter so that this API can be used for
querying any q counter.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/main.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-
From: Mark Zhang
Add support for ib callback counter_alloc_stats() and
counter_update_stats().
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/main.c | 23 +++
1 file changed, 23 insertions(+)
diff --git a
From: Mark Zhang
Remove is_visible_in_pid_ns() from nldev.c and make it as a restrack API,
so that it can be taken advantage by other parts like counter.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/nldev.c| 15 ++-
From: Mark Zhang
Introduce statistic counter as a new resource. It allows a user
to monitor specific objects (e.g., QPs) by binding to a counter.
In some cases a user counter resource is created with task other then
"current", because its creation is done as part of rdmatool call.
Signed-off-by
From: Mark Zhang
Add support for ib callbacks counter_bind_qp(), counter_unbind_qp()
and counter_dealloc().
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/main.c | 44 +++
1 file changed, 44 insert
From: Mark Zhang
Support bind a qp with counter. If counter is null then bind the qp to
the default counter. Different QP state has different operation:
- RESET: Set the counter field so that it will take effective
during RST2INIT change;
- RTS: Issue an RTS2RTS change to update the QP counter;
From: Mark Zhang
Add rts2rts_qp_counters_set_id field in hca cap so that RTS2RTS
qp modification can be used to change the counter of a QP.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
include/linux/mlx5/mlx5_ifc.h | 4 +++-
1 file changed, 3 inserti
From: Mark Zhang
In auto mode all QPs belong to one category are bind automatically to
a single counter set. Currently only "qp type" is supported.
In this mode the qp counter is set in RST2INIT modification, and when
a qp is destroyed the counter is unbound.
Signed-off-by: Mark Zhang
Reviewed
From: Mark Zhang
Add rdma_restrack_attach_task() which is able to attach a task
other then "current" to a resource.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/restrack.c | 14 ++
drivers/infiniband/core/restrack.
From: Mark Zhang
Add an API to support set/clear per-port auto mode.
Signed-off-by: Mark Zhang
Reviewed-by: Majd Dibbiny
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/core/Makefile | 2 +-
drivers/infiniband/core/counters.c | 74 ++
drivers/infiniband/c
From: Leon Romanovsky
Changelog:
v3 -> v4:
* Add counter_dealloc() callback function
* Moved to kref implementation
* Fixed lock during spinlock
v2 -> v3:
* We didn't change use of atomics over kref for management of unbind
counter from QP. The reason to it that bind and unbind are non-s
From: Yishai Hadas
Add DEVX support for CQ events by creating and destroying the CQ via
mlx5_core and set an handler to manage its completions.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/devx.c | 40 +++
1 file changed
From: Yishai Hadas
Enable subscription for device events over DEVX.
Each subscription is added to the two level XA data structure according
to its event number and the DEVX object information in case was given
with the given target fd.
Those events will be reported over the given fd once will o
From: Yishai Hadas
Register DEVX with with mlx5_core to get async events. This will enable
to dispatch the applicable events to its consumers in down stream
patches.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/devx.c| 30 +
From: Yishai Hadas
Implement DEVX dispatching event by looking up for the applicable
subscriptions for the reported event and using their target fd to
signal/set the event.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/devx.c | 362 +
From: Yishai Hadas
Expose an extra device definitions for objects events.
It includes: object_type values for legacy objects and generic data
header for any other object.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
include/linux/mlx5/mlx5_ifc.h | 21 +
From: Yishai Hadas
Expose the API to register for ANY event, mlx5_ib will be able to use
this functionality for its needs.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 ++
drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h |
From: Yishai Hadas
Introduce MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD and its initial
implementation.
This object is from type class FD and will be used to read DEVX
async events.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/devx.c | 112 +++
From: Yishai Hadas
Report EQE data upon CQ completion to let upper layers use this data.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/cq.c | 2 +-
drivers/infiniband/hw/mlx5/main.c | 2 +-
drivers/infiniband/hw
From: Yishai Hadas
Use the reported device capabilities for the supported user events (i.e.
affiliated and un-affiliated) to set the EQ mask.
As the event mask can be up to 256 defined by 4 entries of u64 change
the applicable code to work accordingly.
Signed-off-by: Yishai Hadas
Signed-off-by
From: Yishai Hadas
Report a CQ error event only when a handler was set.
This enables mlx5_ib to not set a handler upon CQ creation and use some
other mechanism to get this event as of other events by the
mlx5_eq_notifier_register API.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
From: Yishai Hadas
Enhance mlx5_core_create_cq() to get the command out buffer from the
callers to let them use the output.
Signed-off-by: Yishai Hadas
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/cq.c | 3 ++-
drivers/net/ethernet/mellanox/mlx5/core/cq.c
From: Leon Romanovsky
Changelog:
v0 -> v1:
* Fix the unbind / hot unplug flows to work properly.
* Fix Ref count handling on the eventfd mode in some flow.
* Rebased to latest rdma-next
Thanks
>From Yishai:
From: Yishai Hadas
The firmware command to destroy a CQ might fail when the object is
referenced by other object and the ref count is managed by the firmware.
To enable a second successful destruction post the first failure need to
change mlx5_eq_del_cq() to be a void function.
As an error in
From: Denis Kirjanov
Date: Mon, 17 Jun 2019 10:53:41 +0200
> in IPoIB case we can't see a VF broadcast address for but
> can see for PF
I just want to understand why this need to see the VF broadcast
address is IPoIB specific?
From: Tuong Lien
Date: Mon, 17 Jun 2019 11:56:12 +0700
> It appears that a FAILOVER_MSG can come from peer even when the failure
> link is resetting (i.e. just after the 'node_write_unlock()'...). This
> means the failover procedure on the node has not been started yet.
> The situation is as foll
From: "Mauro S. M. Rodrigues"
Date: Thu, 13 Jun 2019 16:25:40 -0300
> Some transceivers may comply with SFF-8472 even though they do not
> implement the Digital Diagnostic Monitoring (DDM) interface described in
> the spec. The existence of such area is specified by the 6th bit of byte
> 92, set
On Fri, 14 Jun 2019 13:24:59 -0400
Pete Morici wrote:
> Signed-off-by: Pete Morici
Looks fine, applied
On Sun, 16 Jun 2019 14:46:02 -0700
Michael Forney wrote:
> This variable has the same name as `struct xfrm_filter filter` in
> ip/ipxfrm.c, but overrides that definition since `struct rtfilter`
> is larger.
>
> This is visible when built with -Wl,--warn-common in LDFLAGS:
>
> /usr/bin/ld:
On Sat, 15 Jun 2019 13:40:56 +0200
Denis Kirjanov wrote:
> diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h
> index 86d961c9..aaa48818 100644
> --- a/include/uapi/linux/netdevice.h
> +++ b/include/uapi/linux/netdevice.h
> @@ -30,7 +30,7 @@
> #include
> #include
>
1 - 100 of 225 matches
Mail list logo
