Thu, Mar 28, 2019 at 10:40:02PM CET, jakub.kicin...@netronome.com wrote:
>On Thu, 28 Mar 2019 22:12:42 +0100, Jiri Pirko wrote:
>> From: Jiri Pirko
>>
>> To provide visibility of the ports, this patchset exposes switch ID
>> for devlink ports, which are part of a switch. The rest of the ports
>>
For multiple dimensional arrays like below,
int a[2][3]
both llvm and pahole generated one BTF_KIND_ARRAY type like
. element_type: int
. index_type: unsigned int
. number of elements: 6
Such a collapsed BTF_KIND_ARRAY type will cause the divergence
in BTF vs. the user code. In the compile
Hi Florian,
I love your patch! Perhaps something to improve:
[auto build test WARNING on ipsec-next/master]
url:
https://github.com/0day-ci/linux/commits/Florian-Westphal/xfrm-remove-xfrm_mode-indirections/20190329-041949
base: https://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec
I'm aware that I didn't cover the "spintest_user.c".
Because, spintest sample isn't running currently since there is no
such symbol called 'spin_lock'.
At "spintest_kern.c", it has 'kprobe/spin_lock' and
'kprobe/spin_unlock' and some
others kernel symbols like below.
SEC("kprobe/spin_unlock")PROG
Hi Florian,
I love your patch! Yet something to improve:
[auto build test ERROR on ipsec-next/master]
url:
https://github.com/0day-ci/linux/commits/Florian-Westphal/xfrm-remove-xfrm_mode-indirections/20190329-041949
base: https://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.
Hi Leandro,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Leandro-Dorileo/net-sched-taprio-cbs-Fix-using-invalid-link-speed/20190329-043825
config: i386-randconfig-l1-03290203 (attached as .config)
NULL or ZERO_SIZE_PTR will be returned for zero sized memory
request, and derefencing them will lead to a segfault
so it is unnecessory to call vzalloc for zero sized memory
request and not call functions which maybe derefence the
NULL allocated memory
this also fixes a possible memory leak if ph
On Thu, Mar 28, 2019 at 5:20 PM Leandro Dorileo
wrote:
> +static int taprio_dev_notifier(struct notifier_block *nb, unsigned long
> event,
> + void *ptr)
> +{
> + struct net_device *dev = netdev_notifier_info_to_dev(ptr);
> + struct taprio_sched *q;
> +
Test different scenarios of indirect variable-offset stack access: out of
bound access (>0), min_off below initialized part of the stack,
max_off+size above initialized part of the stack, initialized stack.
Example of output:
...
#856/p indirect variable-offset stack access, out of bound OK
Currently there is a difference in how verifier checks memory access for
helper arguments for PTR_TO_MAP_VALUE and PTR_TO_STACK with regard to
variable part of offset.
check_map_access, that is used for PTR_TO_MAP_VALUE, can handle variable
offsets just fine, so that BPF program can call a helper
The patch set adds support for stack access with variable offset from helpers.
Patch 1 is the main patch in the set and provides more details.
Patch 2 adds selftests for new functionality.
Andrey Ignatov (2):
bpf: Support variable offset stack access from helpers
selftests/bpf: Test variable
From: Jakub Kicinski
Date: Thu, 28 Mar 2019 17:27:50 -0700
> On Thu, 28 Mar 2019 17:04:53 -0700 (PDT), David Miller wrote:
>> From: Jakub Kicinski
>> Date: Wed, 27 Mar 2019 11:38:37 -0700
>>
>> > This series avoids a potential crash on nfp representor devices
>> > when netpoll is in use. If tr
On Thu, 28 Mar 2019 17:04:53 -0700 (PDT), David Miller wrote:
> From: Jakub Kicinski
> Date: Wed, 27 Mar 2019 11:38:37 -0700
>
> > This series avoids a potential crash on nfp representor devices
> > when netpoll is in use. If transmitting the frame through underlying
> > vNIC fails we'd return a
From: Ido Schimmel
Date: Thu, 28 Mar 2019 12:12:18 +
> This patchset mainly adds new forwarding test cases and performs small
> changes in existing infrastructure.
>
> Patches #1-#3 add new test cases for multicast RPF check, PCP and VLAN
> matching using flower and tc VLAN modify action.
>
The Time Aware Priority Scheduler is heavily dependent to link speed,
it relies on it to calculate transmission bytes per cycle, we can't
properly calculate the so called budget if the device has failed
to report the link speed.
In that case we can't dequeue packets assuming a wrong budget.
This p
This set fixes miscalculations based on invalid link speed values.
Changes in v5:
+ Don't iterate over all the net_device maintained list (suggested by: Florian
Fainelli);
Changes in v4:
+ converted pr_info calls to netdev_dbg (suggested by: Florian Fainelli);
Changes in v3:
+ yet pr_info()
The Credit Based Shaper heavily depends on link speed to calculate
the scheduling credits, we can't properly calculate the credits if the
device has failed to report the link speed.
In that case we can't dequeue packets assuming a wrong port rate that will
result into an inconsistent credit distri
From: Jakub Kicinski
Date: Wed, 27 Mar 2019 11:38:37 -0700
> This series avoids a potential crash on nfp representor devices
> when netpoll is in use. If transmitting the frame through underlying
> vNIC fails we'd return an error code (by passing on error code from
> __dev_queue_xmit()) and caus
From: Eric Dumazet
Date: Wed, 27 Mar 2019 08:21:30 -0700
> net_hash_mix() currently uses kernel address of a struct net,
> and is used in many places that could be used to reveal this
> address to a patient attacker, thus defeating KASLR, for
> the typical case (initial net namespace, &init_net i
From: xiaofeis
Date: Wed, 27 Mar 2019 11:59:06 +0800
> Add flow_dissect for qca tagged packet to get the right hash.
>
> Signed-off-by: Xiaofei Shen
Applied.
From: Yi-Hung Wei
Date: Tue, 26 Mar 2019 11:31:14 -0700
> Add support for fine-grain timeout support to conntrack action.
> The new OVS_CT_ATTR_TIMEOUT attribute of the conntrack action
> specifies a timeout to be associated with this connection.
> If no timeout is specified, it acts as is, that
From: Yi-Hung Wei
Date: Tue, 26 Mar 2019 11:31:13 -0700
> This patch exports nf_ct_set_timeout() and nf_ct_destroy_timeout().
> The two functions are derived from xt_ct_destroy_timeout() and
> xt_ct_set_timeout() in xt_CT.c, and moved to nf_conntrack_timeout.c
> without any functional change.
> I
Hi Florian,
I love your patch! Yet something to improve:
[auto build test ERROR on ipsec-next/master]
url:
https://github.com/0day-ci/linux/commits/Florian-Westphal/xfrm-remove-xfrm_mode-indirections/20190329-041949
base: https://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.
On Thu, 28 Mar 2019 14:54:43 -0700, Jakub Kicinski wrote:
> Only decrypt_internal() performs zero copy on rx, all paths
> which don't hit decrypt_internal() must set zc to false,
> otherwise tls_sw_recvmsg() may return 0 causing the application
> to believe that that connection got closed.
>
> Cur
Only decrypt_internal() performs zero copy on rx, all paths
which don't hit decrypt_internal() must set zc to false,
otherwise tls_sw_recvmsg() may return 0 causing the application
to believe that that connection got closed.
Currently this happens with device offload when new record
is first read
On Thu, 28 Mar 2019 22:12:42 +0100, Jiri Pirko wrote:
> From: Jiri Pirko
>
> To provide visibility of the ports, this patchset exposes switch ID
> for devlink ports, which are part of a switch. The rest of the ports
> if any (in case of sr-iov for example) do not set switch ID.
I don't feel good
On 2019-03-28 11:46, Paul Moore wrote:
> On Wed, Mar 27, 2019 at 9:12 PM Richard Guy Briggs wrote:
> >
> > On 2019-03-27 23:42, Ondrej Mosnacek wrote:
> > > On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs
> > > wrote:
> > > > Audit events could happen in a network namespace outside of a task
Hi Leandro,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Leandro-Dorileo/net-sched-taprio-cbs-Fix-using-invalid-link-speed/20190329-043825
config: alpha-allyesconfig (attached as .config)
com
Hi Leandro,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
url:
https://github.com/0day-ci/linux/commits/Leandro-Dorileo/net-sched-taprio-cbs-Fix-using-invalid-link-speed/20190329-043825
config: alpha-allyesconfig (attached as .config)
com
From: Jiri Pirko
Pass the switch ID down the to devlink through devlink_port_attrs_set()
so it can be used by devlink_compat_switch_id_get(). Leave
ndo_get_port_parent_id implementation only for legacy.
Signed-off-by: Jiri Pirko
---
net/dsa/dsa2.c | 4 +++-
net/dsa/slave.c | 1 -
2 files chan
From: Jiri Pirko
Remove implementation of get_port_parent_id ndo and rely on core calling
into devlink for the information directly.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/mellanox/mlxsw/minimal.c | 13 -
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 13
From: Jiri Pirko
Obtain HW id and pass it down to mlxsw_core_port_init() as it would be
used as switch_id in devlink and exposed to user.
Signed-off-by: Jiri Pirko
---
.../net/ethernet/mellanox/mlxsw/switchib.c| 22 ++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff
From: Jiri Pirko
Remove implementation of get_port_parent_id ndo and rely on core calling
into devlink for the information directly.
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnx
From: Jiri Pirko
Pass the switch ID down the to devlink through devlink_port_attrs_set()
so it can be used by devlink_compat_switch_id_get().
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/d
From: Jiri Pirko
Currently if the driver registers devlink port instance, he should set
the devlink port attributes as well. Then the devlink core is able to
obtain switch id itself, no need for driver to implement the ndo.
Once all drivers will implement devlink port registration, this ndo
shoul
From: Jiri Pirko
Remove implementation of get_port_parent_id ndo and rely on core calling
into devlink for the information directly.
Signed-off-by: Jiri Pirko
---
.../net/ethernet/netronome/nfp/nfp_net_common.c | 1 -
.../net/ethernet/netronome/nfp/nfp_net_repr.c| 1 -
drivers/net/ether
From: Jiri Pirko
Pass the switch ID down the to devlink through devlink_port_attrs_set()
so it can be used by devlink_compat_switch_id_get().
Signed-off-by: Jiri Pirko
---
rfc->v1:
- new patch
---
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 3 ++-
1 file changed, 2 insertions(+), 1 del
From: Jiri Pirko
Introduce devlink_compat_switch_id_get() helper which fills up switch_id
according to passed netdev pointer. Call it directly from
dev_get_port_parent_id() as a fallback when ndo_get_port_parent_id
is not defined for given netdev.
Signed-off-by: Jiri Pirko
---
rfc->v1:
- don't
From: Jiri Pirko
Pass the switch ID down the to devlink through devlink_port_attrs_set()
so it can be used by devlink_compat_switch_id_get().
Signed-off-by: Jiri Pirko
---
drivers/net/ethernet/mellanox/mlxsw/core.c | 6 --
drivers/net/ethernet/mellanox/mlxsw/core.h | 4 +++-
driver
From: Jiri Pirko
Extend devlink_port_attrs_set() to pass switch ID for ports which are
part of switch and store it in port attrs. For other ports, this is
NULL. During dump to userspace only valid switch ID is filled up.
Note that this allows the driver to group devlink ports into one or more
swi
From: Jiri Pirko
In order to save space in the struct, convert bools to bits.
Signed-off-by: Jiri Pirko
Reviewed-by: Florian Fainelli
---
include/net/devlink.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 31d5cec4d
From: Jiri Pirko
To provide visibility of the ports, this patchset exposes switch ID
for devlink ports, which are part of a switch. The rest of the ports
if any (in case of sr-iov for example) do not set switch ID.
Jiri Pirko (12):
net: devlink: convert devlink_port_attrs bools to bits
net:
On 28.03.2019 21:01, Andrew Lunn wrote:
>> +Sets the period after which the link is reported as down. Note that the
>> PHY may choose
>> +the closest supported value. Only on reading back you get the actual
>> value.
>
> Hi Heiner
>
> 'Only on reading back the tunable do you get the act
> + Sets the period after which the link is reported as down. Note that the
> PHY may choose
> + the closest supported value. Only on reading back you get the actual
> value.
Hi Heiner
'Only on reading back the tunable do you get the actual value.'
would be better.
> .TE
> .PD
> .R
From: Jeff Kirsher
Date: Tue, 26 Mar 2019 20:34:37 -0700
> This series contains updates to igb, ixgbe, i40e and fm10k.
Pulled, thanks Jeff.
From: Julian Wiedmann
Date: Thu, 28 Mar 2019 16:39:18 +0100
> please apply the following patchset to net-next. This reworks the control
> IO code in qeth so that we no longer need to poll for cmd completion,
> and refactors the IDX setup code to also use this improved IO path.
Series applied, th
From: Jiri Pirko
Date: Thu, 28 Mar 2019 13:56:34 +0100
> From: Jiri Pirko
>
> phys_port_name may be assembled by a helper in devlink. It is currently
> the case only for mlxsw driver. Benefit from the get_devlink_port ndo
> and call into devlink directly from dev_get_phys_port_name(). That save
On Thu, Mar 28, 2019 at 05:59:50PM +, Petr Machata wrote:
Hi Petr
> - PHY driver: dev->phydev->drv->get_link_down_reason
> Certain PHY drivers might want to have a custom handling for some
> PHY-specific insight. Something like:
>
> modified include/linux/phy.h
> @@ -636,4 +636
Add description of new PHY tunable Fast Link Down to ethtool man page.
Signed-off-by: Heiner Kallweit
---
ethtool.8.in | 28 ++--
1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/ethtool.8.in b/ethtool.8.in
index b878521..c2a97f2 100644
--- a/ethtool.8.in
++
In preparation of adding support for Fast Link Down as PHY tunable
let's simplify the handling of PHY tunable downshift a little.
Signed-off-by: Heiner Kallweit
---
ethtool.c | 43 +--
1 file changed, 13 insertions(+), 30 deletions(-)
diff --git a/ethtool
Sync ethtool-copy.h with linux-next from 03/28/2019. This provides
access to the new PHY tunable for Fast Link Down support.
Signed-off-by: Heiner Kallweit
---
ethtool-copy.h | 44 ++--
1 file changed, 22 insertions(+), 22 deletions(-)
diff --git a/ethtoo
This patch adds support for PHY tunable Fast Link Down. Like downshift
it uses an u8 parameter.
Signed-off-by: Heiner Kallweit
---
ethtool.c | 55 +--
1 file changed, 53 insertions(+), 2 deletions(-)
diff --git a/ethtool.c b/ethtool.c
index f6
This series adds support for Fast Link Down as new PHY tunable.
See [0] for the kernel part incl. the Marvell PHY driver as
first user.
[0] https://marc.info/?t=15535390081&r=1&w=2
Heiner Kallweit (4):
ethtool: sync ethtool-copy.h with linux-next from 03/28/2019
ethtool: simplify handling
On 3/28/19 9:50 AM, Alexei Starovoitov wrote:
>
> patch 5 isn't pretty still and you didn't answer my question
> why pointer to fib6_flags is worse than duplicated check.
fib6_flags (prefix flags) has nothing to do with a fib6_nh
initialization, and I do want to add a 6th input argument for somet
Andrew Lunn writes:
> I argued this is a PHY layer status information. We don't really want
> to have to modify every MAC driver to call into phylib/phylink. Yes,
> we can have a netdev_ops for those drivers which ignore the Linux PHY
> layer, but ideally we want to transparently call into the
On 3/28/19 5:56 AM, Jiri Pirko wrote:
> From: Jiri Pirko
>
> Since each non-legacy slave has its own devlink port instance
> correctly set, rely on devlink core to generate correct phys port name.
>
> Signed-off-by: Jiri Pirko
Reviewed-by: Florian Fainelli
--
Florian
On 3/28/19 5:56 AM, Jiri Pirko wrote:
> From: Jiri Pirko
>
> In order for devlink compat functions to work, implement
> ndo_get_devlink_port. Legacy slaves does not have devlink port instances
> created for themselves.
>
> Signed-off-by: Jiri Pirko
Reviewed-by: Florian Fainelli
Thanks for ma
On Thu, 28 Mar 2019 09:12:19 +0100
Olga Albisser wrote:
> Additional details can be found in the draft:
> https://www.ietf.org/id/draft-ietf-tsvwg-aqm-dualq-coupled
>
> Signed-off-by: Olga Albisser
> Signed-off-by: Koen De Schepper
> Signed-off-by: Oliver Tilmans
> Signed-off-by: Bob Briscoe
On 03/27/2019 03:45 PM, Daniel T. Lee wrote:
> Since, ksym_search added with verification logic for symbols existence,
> it could return NULL when the kernel symbols are not loaded.
>
> This commit will add NULL check logic after ksym_search.
>
> Signed-off-by: Daniel T. Lee
> ---
> Changes in v
Add 36 pedit action tests to check pedit options described in tc-pedit(8)
man page. Test cases can be specified by categories: actions, pedit,
raw_op, layered_op. RAW_OP cases check offset option for u8, u16 and u32
offset size. LAYERED_OP cases check fields option for eth, ip, ip6,
tcp and udp hea
On 03/28/2019 12:33 PM, luca.bocca...@gmail.com wrote:
> From: Luca Boccassi
>
> Generate a libbpf.pc file at build time so that users can rely
> on pkg-config to find the library, its CFLAGS and LDFLAGS.
>
> Signed-off-by: Luca Boccassi
> Acked-by: Andrey Ignatov
Applied, thanks!
On Thu, Mar 28, 2019 at 8:54 AM Daniel Borkmann wrote:
>
> Both btf.h and xsk.h headers are not installed quietly due to
> missing '\' for the call to QUIET_INSTALL. Lets fix it.
>
> Before:
>
> # make install_headers
> INSTALL headers
> if [ ! -d '''/usr/local/include/bpf' ]; then instal
On Thu, 28 Mar 2019 at 16:39, Daniel Borkmann wrote:
>
> On 03/27/2019 02:51 PM, Björn Töpel wrote:
> > The DPDK project is moving forward with its AF_XDP PMD, and during
> > that process some libbpf issues surfaced [1].
>
> Great to hear!
>
> > This series address two, minor, packaging issues for
Classful qdiscs can't access directly the child qdiscs backlog
length: if such qdisc is NOLOCK, per CPU values should be
accounted instead.
Most qdiscs no not respect the above. As a result, qstats fetching
for most classful qdisc is currently incorrect: if the child qdisc is
NOLOCK, it always rep
Currently, stats accounting for NOLOCK qdisc enslaved to classful (lock)
qdiscs is buggy. Per CPU values are ignored in most places, as a result,
stats dump in the above scenario always report 0 length backlog and parent
backlog len is not updated correctly on NOLOCK qdisc removal.
The first patch
Both btf.h and xsk.h headers are not installed quietly due to
missing '\' for the call to QUIET_INSTALL. Lets fix it.
Before:
# make install_headers
INSTALL headers
if [ ! -d '''/usr/local/include/bpf' ]; then install -d -m 755
'''/usr/local/include/bpf'; fi; install btf.h -m 644 '''/us
The same code to flush qdisc tree and purge the qdisc queue
is duplicated in many places and in most cases it does not
respect NOLOCK qdisc: the global backlog len is used and the
per CPU values are ignored.
This change addresses the above, factoring-out the relevant
code and using the helpers int
On Wed, Mar 27, 2019 at 08:53:58PM -0700, David Ahern wrote:
> From: David Ahern
>
> With fib_nh_common in place, move common initialization and release
> code into helpers used by both ipv4 and ipv6. For the moment, the init
> is just the lwt encap and the release is both the netdev reference an
This converts the IDX code to use qeth_send_control_data(), replacing
a bunch of duplicated IO code and unbounded waits. It also allows the
IDX sequence to benefit from the improved timeout & notify
infrastructure, so that we can eliminate the DOWN -> ACTIVATING -> UP
transition in the channel stat
Current code makes it look like qeth_send_control_data_cb() is some
sort of default callback for all cmds. But in practice, it is only used
for half of the cmd buffers we issue.
Reduce the confusion by only setting this callback for cmds that
actually want it, and while at it give the callback a na
.ndo_set_rx_mode gets called in process context, but while holding the
addr_list spinlock. Which means we currently can't sleep while
re-programming the HW, and need to poll for IO completion. That's bad,
in particular since receiving the cmd response can fail silently and
we're then polling until
From: Sven Eckelmann
The throughput_override sysfs file is not below the meshif but below a
hardif. The kobj has therefore not a pointer which can be used to find the
batadv_priv data. The pointer stored in the hardif object must be used
instead to find the correct meshif private data.
Fixes: 7e
As trivial cleanup before adding more users to qeth_notify_reply(),
move the setup of reply->rc from the caller into the helper.
Signed-off-by: Julian Wiedmann
---
drivers/s390/net/qeth_core_main.c | 22 --
1 file changed, 8 insertions(+), 14 deletions(-)
diff --git a/driver
The L2 and L3 .ndo_set_rx_mode callbacks maintain an address cache
to decide which addresses have changed since the last modeset.
When the card is set offline, qeth_l?_stop_card() drains this cache.
This happens only after 1) the net_device has been detached, and
2) any pending RX modeset has comp
On Thu, 2019-03-28 at 15:36 +0300, Mika Westerberg wrote:
> Now that the driver can handle every possible tunnel types there is no
> point to log everything as info level so turn these to happen at debug
> level instead.
trivia:
> diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path
To avoid concurrency issues, some parts of the cmd setup are delayed
until qeth_send_control_data() holds the IO channel's irq_pending
"lock". Rather than hard-coding those setup steps for each cmd type,
have the cmd provide a callback. This will make it easier to also issue
IDX commands via qeth_s
All users of the lock are running in process context now.
Signed-off-by: Julian Wiedmann
---
drivers/s390/net/qeth_core.h | 2 +-
drivers/s390/net/qeth_core_main.c | 1 -
drivers/s390/net/qeth_l3_main.c | 34 +-
drivers/s390/net/qeth_l3_sys.c| 20
The inet6addr_chain is atomic. So instead of starting the cmd IO for
SETIP / DELIP straight from the notifier callback, run it from a
workqueue. This is the last step towards removal of cmd IO completion
polling.
Signed-off-by: Julian Wiedmann
---
drivers/s390/net/qeth_core.h | 1 +
driver
All callers are running in process context now, so we can safely sleep
in qeth_send_control_data() while waiting for a cmd to complete.
Signed-off-by: Julian Wiedmann
---
drivers/s390/net/qeth_core.h | 11 +--
drivers/s390/net/qeth_core_main.c | 60 --
Extract a little helper, so that high-level callers can manipulate the
IP table without worrying about the locking. This will make it easier
to convert the code to a different locking primitive later on.
Signed-off-by: Julian Wiedmann
---
drivers/s390/net/qeth_l3_main.c | 33 +---
Hi Dave,
please apply the following patchset to net-next. This reworks the control
IO code in qeth so that we no longer need to poll for cmd completion,
and refactors the IDX setup code to also use this improved IO path.
Thanks,
Julian
Julian Wiedmann (10):
s390/qeth: defer RX modesetting
s
On 03/27/2019 02:51 PM, Björn Töpel wrote:
> The DPDK project is moving forward with its AF_XDP PMD, and during
> that process some libbpf issues surfaced [1].
Great to hear!
> This series address two, minor, packaging issues for libbpf. The
> header file xsk.h was missing from the instal_headers
The page_pool API has no users for it's DMA capabilities yet.
Unmapping DMA addresses used by network drivers will be needed for real
users.
commit 1567b85eb8ad ("net: page_pool: don't use page->private to store
dma_addr_t")
uses 'struct page' to store the addresses.
This patch provides a helper
The page_pool API has no users for it's DMA capabilities yet.
Retrieving DMA addresses used by network drivers will be needed for real
users.
commit 1567b85eb8ad ("net: page_pool: don't use page->private to store
dma_addr_t")
uses 'struct page' to store the addresses.
This patch provides a helper
> On Mar 28, 2019, at 5:35 AM, Björn Töpel wrote:
>
> Magnus and I took the route to simplify the sample, to make it easier
> for new users. I still think that was the right path. Should there be
> a sample showcasing all the knobs/pulleys?
One problem I ran into yesterday is that the bpf prog
(just a couple of checkpatch-like comments)
2019-03-27, 18:31:38 +0100, Florian Westphal wrote:
> diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
> index 6802d1aee424..cff048ad8562 100644
> --- a/net/ipv4/xfrm4_output.c
> +++ b/net/ipv4/xfrm4_output.c
> @@ -72,6 +72,8 @@ int xfrm4_o
From: Mark Bloch
Move from IB device (representor) per virtual function to single IB device
with port per virtual function (port 1 represents the uplink). As number
of ports is a static property of an IB device, declare the IB device with
as many port as the possible according to the PCI bus.
Si
From: Mark Bloch
In preparation of moving into a model of single IB device multiple ports
move rep to be part of the port structure. We mark a representor device
by setting is_rep, no functional change with this patch.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infin
From: Mark Bloch
Currently the steering for SQs created on representors is done on creation,
once we move to representors as ports of an IB device we need the port
argument which is given only at the modify QP stage, adjust the code
appropriately.
Signed-off-by: Mark Bloch
Signed-off-by: Leon R
From: Mark Bloch
The design of representors is such that once an IB representor is created,
the netdev of representor already exists, we can use that fact to simplify
the netdev affinity code.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/ib_rep.c |
From: Mark Bloch
Now that we have a single IB device with multipul ports we can remove
the VF representor profile.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/ib_rep.c | 39 ---
drivers/infiniband/hw/mlx5/main.c| 46
From: Mark Bloch
On allocation we use the array size and on destruction num_ports,
use the array size of destruction as well, in this context the array
corresponds to the native/actual ports on the NIC so no need to adjust
this logic for representors.
Signed-off-by: Mark Bloch
Signed-off-by: Le
From: Mark Bloch
We store the SMI information in the core device's struct, make sure
we set that information only once (and not per port), while here make
the for loop based on the actual size of the array.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx
From: Mark Bloch
In downstream patches we will need access to the ports before doing
any stages, in order to set net device per representor.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/ib_rep.c | 12 ++--
drivers/infiniband/hw/mlx5/main.c
From: Mark Bloch
Simplify the code and move the deallocation of the IB device into the
remove function.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/ib_rep.c | 5 +
drivers/infiniband/hw/mlx5/main.c | 4 ++--
2 files changed, 3 insertions(+), 6
From: Mark Bloch
Create a new prio in the FDB, it will be used when inserting steering rules
into the FDB from the RDMA side. We create a new PRIO so rules from the
net side and rules from the RDMA side won't be inserted to the same PRIO,
each side has it's own sandbox to play in.
Signed-off-by:
From: Mark Bloch
Netdev info is stored in a separate array and holds data relevant on a
per port basis, move it to be part of the port struct.
Signed-off-by: Mark Bloch
Signed-off-by: Leon Romanovsky
---
drivers/infiniband/hw/mlx5/main.c| 30 ++--
drivers/infiniban
From: Mark Bloch
When creating the FDB prios, use the enum values already defined and not
the hardcoded values.
Signed-off-by: Mark Bloch
Reviewed-by: Maor Gottlieb
Signed-off-by: Leon Romanovsky
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 5 -
drivers/net/ethernet/m
From: Leon Romanovsky
>From Mark,
Hi,
This series starts from two refactoring patches performed in mlx5_core
and they are part of a larger series intended to expose the ability
to insert FDB steering rules by the RDMA side.
They are followed by patches which move IB representors to single IB
d
> > > > > > > > > If skb_vlan_tag_present(skb) returns true, we set proto to
> > > > > > > > > skb->protocol
> > > > > > > > > and move on.
> > > > > > > > >
> > > > > > > > > But, we would need vlan_proto/present/tci in the flow_keys in
> > > > > > > > > the future.
> > > > > > > > > We don't cu
1 - 100 of 149 matches
Mail list logo
