On Sun, Apr 18, 2021 at 10:06:41AM -0700, David Ahern wrote:
> On 4/16/21 8:55 AM, Ido Schimmel wrote:
> > From: Ido Schimmel
> >
> > Currently, a multi-part nexthop dump is restarted based on the number of
> > nexthops that have been dumped so far. This can result i
On Fri, Apr 16, 2021 at 09:08:16AM -0700, Jakub Kicinski wrote:
> On Fri, 16 Apr 2021 18:44:26 +0300 Ido Schimmel wrote:
> > Given that you have now standardized these stats, do you plan to feed
> > them into some monitoring system?
>
> Yes and no, I'm only intending
On Fri, Apr 16, 2021 at 12:27:39PM -0700, Jakub Kicinski wrote:
> +static int stats_prepare_data(const struct ethnl_req_info *req_base,
> + struct ethnl_reply_data *reply_base,
> + struct genl_info *info)
> +{
> + const struct stats_req_info *
On Fri, Apr 16, 2021 at 12:27:42PM -0700, Jakub Kicinski wrote:
> +/**
> + * struct ethtool_rmon_hist_range - byte range for histogram statistics
> + * @low: low bound of the bucket (inclusive)
> + * @high: high bound of the bucket (inclusive)
> + */
> +struct ethtool_rmon_hist_range {
> + u16
On Sat, Apr 17, 2021 at 12:18:08PM -0700, Jakub Kicinski wrote:
> On Sat, 17 Apr 2021 12:15:20 -0700 Jakub Kicinski wrote:
> > On Sat, 17 Apr 2021 21:53:40 +0300 Ido Schimmel wrote:
> > > On Sat, Apr 17, 2021 at 11:13:51AM -0700, Jakub Kicinski wrote:
> > > > On S
On Sat, Apr 17, 2021 at 11:47:28AM -0700, Jakub Kicinski wrote:
> On Sat, 17 Apr 2021 21:14:40 +0300 Ido Schimmel wrote:
> > > + if (!is_json_context()) {
> > > + fprintf(stdout, "rmon-%s-etherStatsPkts",
> > > + mnl_attr_get_t
On Sat, Apr 17, 2021 at 11:13:51AM -0700, Jakub Kicinski wrote:
> On Sat, 17 Apr 2021 10:57:42 -0700 Jakub Kicinski wrote:
> > > I tried to understand how you add new groups without user space
> > > changes and I think this statement is not entirely accurate.
> > >
> > > At minimum, user space nee
On Fri, Apr 16, 2021 at 09:02:52AM -0700, Jakub Kicinski wrote:
> # ethtool -S eth0 --groups eth-phy eth-mac rmon
> Stats for eth0:
> eth-phy-SymbolErrorDuringCarrier: 1
> eth-mac-FramesTransmittedOK: 1
> eth-mac-FrameTooLongErrors: 1
> rmon-etherStatsUndersizePkts: 1
> rmon-etherStatsJabbers: 1
>
On Fri, Apr 16, 2021 at 12:27:39PM -0700, Jakub Kicinski wrote:
> Add an interface for reading standard stats, including
> stats which don't have a corresponding control interface.
>
> Start with IEEE 802.3 PHY stats. There seems to be only
> one stat to expose there.
>
> Define API to not requir
On Thu, Apr 15, 2021 at 07:27:50PM -0700, Jakub Kicinski wrote:
> mlxsw has nicely grouped stats, add support for standard uAPI.
> I'm guessing the register access part. Compile tested only.
Jakub, wanted to let you know that it seems to be working. I'll review
the patches tomorrow/Sunday, as it's
On Fri, Apr 16, 2021 at 11:35:38AM -0700, Eric Dumazet wrote:
> From: Eric Dumazet
>
> We need to store cmlen instead of len in cm->cmsg_len.
>
> Fixes: 38ebcf5096a8 ("scm: optimize put_cmsg()")
> Signed-off-by: Eric Dumazet
> Reported-by: Jakub Kicinski
From: Ido Schimmel
Test that all the nexthops are flushed when a multi-part nexthop dump is
required for the flushing.
Without previous patch:
# ./fib_nexthops.sh
TEST: Large scale nexthop flushing [FAIL]
With previous patch:
# ./fib_nexthops.sh
TEST
From: Ido Schimmel
Patch #1 fixes a day-one bug in the nexthop code and allows "ip nexthop
flush" to work correctly with large number of nexthops that do not fit
in a single-part dump.
Patch #2 adds a test case.
Targeting at net-next since this use case never worked, the flow is
pret
From: Ido Schimmel
Currently, a multi-part nexthop dump is restarted based on the number of
nexthops that have been dumped so far. This can result in a lot of
nexthops not being dumped when nexthops are simultaneously deleted:
# ip nexthop | wc -l
65536
# ip nexthop flush
Dump was
On Thu, Apr 15, 2021 at 07:27:43PM -0700, Jakub Kicinski wrote:
> Continuing the effort of providing a unified access method
> to standard stats, and explicitly tying the definitions to
> the standards this series adds an API for general stats
> which do no fit into more targeted control APIs.
>
>
m of those addresses.
>
> Let us now add the 'is_local' bit to bridge FDB entries, and make all
> drivers ignore these entries by their own choice.
>
> Co-developed-by: Tobias Waldekranz
> Signed-off-by: Tobias Waldekranz
> Signed-off-by: Vladimir Oltea
Signed-off-by: Tobias Waldekranz
> Reviewed-by: Vladimir Oltean
> Signed-off-by: Vladimir Oltean
Reviewed-by: Ido Schimmel
On Fri, Apr 09, 2021 at 03:02:41PM +0200, Florian Westphal wrote:
> Michal Soltys wrote:
> > On 3/29/21 10:52 PM, Ido Schimmel wrote:
> > >
> > > ip_route_me_harder() does not set source / destination port in the
> > > flow key, so it explains why fib r
case firmware was not able to
perform protection, by hardware.
The temperature threshold set for hardware protection is always higher
than for firmware.
Signed-off-by: Vadim Pasternak
Signed-off-by: Ido Schimmel
---
.../ethernet/mellanox/mlxsw/core_thermal.c| 27 +--
1 file
On Tue, Apr 06, 2021 at 09:33:23AM +0800, Chunmei Xu wrote:
> since id is unique for nexthop, it is heavy to dump all nexthops.
> use existing delete_nexthop to support flush by id
>
> Signed-off-by: Chunmei Xu
Reviewed-by: Ido Schimmel
Tested-by: Ido Schimmel
Thanks
On Wed, Mar 31, 2021 at 10:22:34AM +0800, Chunmei Xu wrote:
> add id to struct filter to record the 'id',
> filter id only when id is set, otherwise flush all.
>
> Signed-off-by: Chunmei Xu
> ---
> ip/ipnexthop.c | 9 -
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> diff --git a/
On Tue, Mar 30, 2021 at 08:44:30PM +0800, xuchunmei wrote:
> Hi,
>
> I use iproute-5.10 with kernel-5.10.6, I found that ip-nexthop does not
> support flush by id, is it by design?
>
> Reproduce steps:
> # ip netns add me
> # ip -netns me addr add 127.0.0.1/8 dev lo
> # ip -netns me link set lo
From: Ido Schimmel
When cleared, the 'force' parameter in nexthop bucket replacement
notifications indicates that a driver should try to perform an atomic
replacement. Meaning, only update the contents of the bucket if it is
inactive.
Since mlxsw only queries buckets' activity on
On Mon, Mar 29, 2021 at 11:52:10PM +0300, Ido Schimmel wrote:
> On Sun, Mar 28, 2021 at 04:05:29PM +0200, Michal Soltys wrote:
> > Hi,
> >
> > I'm not sure how it behaved in earlier kernels (can check later), but it is
> > / looks bugged in at least recent 5.x+ o
On Sun, Mar 28, 2021 at 04:05:29PM +0200, Michal Soltys wrote:
> Hi,
>
> I'm not sure how it behaved in earlier kernels (can check later), but it is
> / looks bugged in at least recent 5.x+ ones (tests were done with 5.11.8 and
> 5.10.25).
>
> Consider following setup:
>
> # ip -o ad sh
> 1: lo
d Ahern
Reviewed-by: Ido Schimmel
From: Ido Schimmel
The driver can only offload matchall rules that do not match on a
protocol. Test that matchall rules that match on a protocol are vetoed.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
---
.../drivers/net/mlxsw/tc_restrictions.sh| 17 +
1 file
From: Ido Schimmel
Perform the priority check earlier in the function instead of repeating
it for every action. This fixes a bug that allowed matchall rules with
sample action to be added in front of flower rules on egress.
Fixes: 54d0e963f683 ("mlxsw: spectrum_matchall: Add support for e
From: Ido Schimmel
Test that two sampling rules cannot be configured on the same port with
the same trigger.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
---
.../selftests/drivers/net/mlxsw/tc_sample.sh | 30 +++
1 file changed, 30 insertions(+)
diff --git a/tools
From: Ido Schimmel
The per-port sampling triggers (i.e., ingress / egress) cannot be
enabled twice. Meaning, the below configuration will not result in
packets being sampled twice:
# tc filter add dev swp1 ingress matchall skip_sw action sample rate 100 group
1
# tc filter add dev swp1
From: Ido Schimmel
Previous patch moved the protocol check out of the action check, so
these if statements can now be converted to a switch statement. Perform
the conversion.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c | 9
From: Ido Schimmel
Perform the protocol check earlier in the function instead of repeating
it for every action. Example:
# tc filter add dev swp1 ingress proto ip matchall skip_sw action sample group
1 rate 100
Error: matchall rules only supported with 'all' protocol.
We hav
From: Ido Schimmel
This patchset fixes two bugs in recent sampling submissions.
The first fix, in patch #3, prevents matchall rules with sample action
to be added in front of flower rules on egress. Patches #1-#2 are
preparations meant at avoiding similar bugs in the future. Patch #4 is a
On Mon, Mar 29, 2021 at 11:29:25AM +0300, Ido Schimmel wrote:
> From: Ido Schimmel
>
> Patch #1 fixes a discrepancy between the software and hardware data
> paths with regards to ECN marking after decapsulation. See the changelog
> for a detailed description.
>
> Patch #2
From: Ido Schimmel
Test that all possible combinations of inner and outer ECN bits result
in the correct inner ECN marking according to RFC 6040 4.2.
Signed-off-by: Ido Schimmel
---
.../selftests/net/forwarding/vxlan_bridge_1d.sh | 13 -
1 file changed, 12 insertions(+), 1
From: Ido Schimmel
Cited commit changed the behavior of the software data path with regards
to the ECN marking of decapsulated packets. However, the commit did not
change other callers of __INET_ECN_decapsulate(), namely mlxsw. The
driver is using the function in order to ensure that the
From: Ido Schimmel
Test that all possible combinations of inner and outer ECN bits result
in the correct inner ECN marking according to RFC 6040 4.2.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
---
.../selftests/net/forwarding/vxlan_bridge_1d.sh | 13 -
1 file
From: Ido Schimmel
Patch #1 fixes a discrepancy between the software and hardware data
paths with regards to ECN marking after decapsulation. See the changelog
for a detailed description.
Patch #2 extends the ECN decap test to cover all possible combinations
of inner and outer ECN markings. The
From: Ido Schimmel
Cited commit changed the behavior of the software data path with regards
to the ECN marking of decapsulated packets. However, the commit did not
change other callers of __INET_ECN_decapsulate(), namely mlxsw. The
driver is using the function in order to ensure that the
From: Ido Schimmel
Patch #1 fixes a discrepancy between the software and hardware data
paths with regards to ECN marking after decapsulation. See the changelog
for a detailed description.
Patch #2 extends the ECN decap test to cover all possible combinations
of inner and outer ECN markings. The
gt; Signed-off-by: Simon Horman
FWIW (I see it was already merged):
Reviewed-by: Ido Schimmel
Thanks!
On Sat, Mar 27, 2021 at 10:33:34PM +, Colin King wrote:
> From: Colin Ian King
>
> The variable force is being initialized with a value that is
> never read and it is being updated later with a new value. The
> initialization is redundant and can be removed.
>
> Addresses-Coverity: ("Unused
From: Ido Schimmel
Test that unsupported resilient nexthop group configurations are
rejected and that offload / trap indication is correctly set on nexthop
buckets in a resilient group.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
---
.../selftests/drivers/net/mlxsw/rtnetlink.sh
From: Ido Schimmel
Allow the driver to instruct the device to only overwrite an adjacency
entry if its activity is cleared. Currently, adjacency entry is always
overwritten, regardless of activity.
This will be used by subsequent patches to prevent replacement of active
nexthop buckets.
Signed
From: Ido Schimmel
The number of nexthop buckets in a resilient nexthop group never
changes, so when the gateway address of a nexthop cannot be resolved,
the nexthop buckets are programmed to trap packets to the CPU in order
to trigger resolution. For example:
# ip nexthop add id 1 via
From: Ido Schimmel
So far, mlxsw only updated hardware flags ('offload' / 'trap') on
nexthop objects. For resilient nexthop groups, these flags need to be
updated on individual nexthop buckets as well.
Update these flags whenever updating the flags of the encapsulatin
From: Ido Schimmel
Now that mlxsw supports resilient nexthop groups, allow them to be
programmed after validating that their configuration conforms to the
device's limitations (e.g., number of buckets is within predefined
range).
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Ma
From: Ido Schimmel
The RATRAD register is used to dump and optionally clear activity bits
of router adjacency table entries. Will be used by the next patch to
query and clear the activity of nexthop buckets in a resilient nexthop
group.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
From: Ido Schimmel
The kernel periodically checks the idle time of nexthop buckets to
determine if they are idle and can be re-populated with a new nexthop.
When the resilient nexthop group is offloaded to hardware, the kernel
will not see activity on nexthop buckets unless it is reported from
From: Ido Schimmel
Have the caller pass a pointer to the payload of the RATR register to
the function updating a single nexthop / adjacency entry.
In a subsequent patch, this will allow the caller to make sure
replacement was successful by querying the state of the adjacency entry
after
From: Ido Schimmel
Replace a single nexthop bucket upon receiving a
'NEXTHOP_EVENT_BUCKET_REPLACE' notification.
When the 'force' parameter is not set, instruct the device to only
overwrite an adjacency entry if its activity is cleared, so as not to
break existing flows
From: Ido Schimmel
Parse the configuration of resilient nexthop groups to existing mlxsw
data structures. Unlike non-resilient groups, nexthops without a valid
MAC or router interface (RIF) are programmed with a trap action instead
of not being programmed at all.
Signed-off-by: Ido Schimmel
From: Ido Schimmel
This patchset adds support for resilient nexthop groups in mlxsw. As far
as the hardware is concerned, resilient groups are the same as regular
groups. The differences lie in how mlxsw manages the individual
adjacency entries (nexthop buckets) that make up the group.
The
From: Ido Schimmel
Cited commit added a new attribute before the existing group reference
count attribute, thereby changing its value and breaking existing
applications on new kernels.
Before:
# psample -l
libpsample ERROR psample_group_foreach: failed to recv message: Operation not
From: Ido Schimmel
Nexthops that need to be programmed with a trap action might not have a
valid router interface (RIF) associated with them. Therefore, use the
loopback RIF created during initialization to program them to the
device.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
From: Ido Schimmel
Currently, the action associated with the nexthop is assumed to be
'forward' unless the 'discard' bit is set.
Instead, simplify this by introducing a dedicated field to represent the
action of the nexthop. This will allow us to more easily introduce more
a
From: Ido Schimmel
Avoid updating neighbour and adjacency entries in hardware when the
neighbour is already connected and its MAC address did not change. This
can happen, for example, when neighbour transitions between valid states
such as 'NUD_REACHABLE' and 'NUD_DELAY'.
From: Ido Schimmel
The device supports a fixed set of adjacency group sizes. Encode these
sizes in an array, so that the next patch will be able to split it
between Spectrum-1 and Spectrum-{2,3}, which support different size
ranges.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
From: Ido Schimmel
Spectrum-{2,3} support different adjacency group size ranges compared to
Spectrum-1. Add an array describing these ranges and change the common
code to use the array which was set during the per-ASIC initialization.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
From: Ido Schimmel
There are several differences in the router module between Spectrum-1
and Spectrum-{2,3}. Currently, this is only apparent in the router
interface (RIF) operations that are split between these ASICs.
A subsequent patch is going to introduce another difference between
these
From: Ido Schimmel
Encapsulate this functionality in a separate function, so that it could
be invoked by follow-up patches, when replacing a nexthop bucket that is
part of a resilient nexthop group.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
---
.../ethernet/mellanox/mlxsw
From: Ido Schimmel
The validation of a nexthop group entry is also necessary for resilient
nexthop groups, so break the validation to a separate function to allow
for code reuse in subsequent patches.
Signed-off-by: Ido Schimmel
Reviewed-by: Petr Machata
---
.../ethernet/mellanox/mlxsw
From: Ido Schimmel
This patchset contains preparations for resilient nexthop groups support in
mlxsw. A follow-up patchset will add support and selftests. Most of the
patches are trivial and small to make review easier.
Patchset overview:
Patch #1 removes RTNL assertion in nexthop notifier
From: Ido Schimmel
Currently, nexthops are programmed with either forward or discard action
(for blackhole nexthops). Nexthops that do not have a valid MAC address
(neighbour) or router interface (RIF) are simply not written to the
adjacency table.
In resilient nexthop groups, the size of the
From: Ido Schimmel
mlxsw_sp_nexthop_update() is used to update the configuration of
Ethernet-type nexthops, as opposed to mlxsw_sp_nexthop_ipip_update(),
which is used to update IPinIP-type nexthops.
Rename the function to mlxsw_sp_nexthop_eth_update(), so that it is
consistent with
From: Ido Schimmel
The comments assume that nexthops are simple Ethernet nexthops
that are programmed to forward packets to the associated neighbour. This
is no longer the case, as both IPinIP and blackhole nexthops are now
supported.
Adjust the comments to reflect these changes.
Signed-off-by
From: Ido Schimmel
The helper mlxsw_sp_nexthop_offload() is actually interested in finding
out if the nexthop is both written to the adjacency table and forwarding
packets (as opposed to discarding them).
Rename it to mlxsw_sp_nexthop_is_forward() and remove
mlxsw_sp_nexthop_is_discard
From: Ido Schimmel
The helper returns the MAC address associated with the nexthop. It is
only valid when the nexthop forwards packets and when it is an Ethernet
nexthop. Reflect this in the checks the helper is performing.
This is not an issue because the sole caller of the function only
From: Ido Schimmel
Remove the RTNL assertion in the nexthop notifier block. The assertion
is not needed given RTNL is never assumed to be taken.
This is a preparation for future patches where mlxsw will start handling
nexthop events that are not always sent with RTNL held.
Signed-off-by: Ido
On Fri, Mar 19, 2021 at 10:33:14PM +0800, Hangbin Liu wrote:
> The ECN bit defines ECT(1) = 1, ECT(0) = 2. So inner 0x02 + outer 0x01
> should be inner ECT(0) + outer ECT(1). Based on the description of
> __INET_ECN_decapsulate, the final decapsulate value should be
> ECT(1). So fix the test expect
hen port joins /
leaves an 802.1ad bridge in different ASICs.
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
.../ethernet/mellanox/mlxsw/spectrum_nve.h| 1 -
.../mellanox/mlxsw/spectrum_nve_vxlan.c | 15 ++
.../mellanox/mlxsw/spectrum_switchdev.c | 52 +
From: Amit Cohen
Configure VxLAN with an 802.1ad bridge and VxLAN with an 802.1d bridge
at the same time in same switch, verify that traffic passed as expected.
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
.../net/forwarding/dual_vxlan_bridge.sh | 366 ++
1
through it, instead
of the default 802.1q EtherType.
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 16
drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 2 ++
2 files changed, 18 insertions(+)
diff --git a/drivers
;.
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
.../net/ethernet/mellanox/mlxsw/spectrum.c| 3 +++
.../net/ethernet/mellanox/mlxsw/spectrum.h| 6 +
.../mellanox/mlxsw/spectrum_switchdev.c | 22 +++
3 files changed, 31 insertions(+)
diff --git a/d
From: Amit Cohen
q_in_vni_veto.sh is not needed anymore because VxLAN with an 802.1ad
bridge and VxLAN with an 802.1d bridge can coexist.
Remove the test.
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
.../net/mlxsw/spectrum-2/q_in_vni_veto.sh | 77 ---
1 file
vely. This allows using dual VxLAN bridges (802.1d and 802.1ad at
the same time).
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 36 +++
1 file changed, 36 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxs
From: Ido Schimmel
This patchset allows user space to simultaneously configure both 802.1d
and 802.1ad VxLAN bridges on Spectrum-2 and later ASICs. 802.1ad VxLAN
bridges are still forbidden on Spectrum-1.
The reason for the current limitation is that up until now the EtherType
that was pushed
and 802.1ad at the same
time).
Signed-off-by: Amit Cohen
Signed-off-by: Ido Schimmel
---
drivers/net/ethernet/mellanox/mlxsw/reg.h | 9 +
1 file changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h
b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 44f836246e33
From: Ido Schimmel
Test that packets are sampled when tc-sample is used with matchall
egress binding and flower classifier. Verify that when performing
sampling on egress the end-to-end latency is reported as metadata.
Signed-off-by: Ido Schimmel
---
.../selftests/drivers/net/mlxsw
From: Ido Schimmel
Make sure egress sampling configuration only fails on Spectrum-1, given
that mlxsw now supports it on Spectrum-{2,3}.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
---
tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh | 4 +++-
1 file changed, 3 insertions
From: Ido Schimmel
Implement support for action sample when used with a flower classifier
by implementing the required sampler_add() / sampler_del() callbacks and
registering an Rx listener for the sampled packets.
The sampler_add() callback returns an error for Spectrum-1 as the
functionality
From: Ido Schimmel
Allow user space to install a matchall classifier with sample action on
egress. This is only supported on Spectrum-2 onwards, so Spectrum-1 will
continue to return an error.
Programming the hardware to sample on egress is identical to ingress
sampling with the sole change of
From: Ido Schimmel
Add core functionality required to support mirror sampler action in the
policy engine. The switch driver (e.g., 'mlxsw_spectrum') is required to
implement the sampler_add() / sampler_del() callbacks that perform the
necessary configuration before the sampler act
From: Ido Schimmel
Start using the previously introduced sampling triggers hash table to
store sampling parameters instead of storing them as attributes of the
sampled port.
This makes it easier to introduce new sampling triggers.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
From: Ido Schimmel
Currently, mlxsw supports a single sampling trigger type (i.e., received
packet). When sampling is configured on an ingress port, the sampling
parameters (e.g., pointer to the psample group) are stored as an
attribute of the port, so that they could be passed to
From: Ido Schimmel
The entry will be required by the next patches, so pass it. No
functional changes intended.
Signed-off-by: Ido Schimmel
Reviewed-by: Jiri Pirko
---
.../net/ethernet/mellanox/mlxsw/spectrum.h| 9 ---
.../mellanox/mlxsw/spectrum_matchall.c| 27
From: Ido Schimmel
Due to the differences between Spectrum-1 and later ASICs, some of the
checks currently performed at the common code (where extack is
available) will need to be pushed to the per-ASIC operations.
As a preparation, propagate extack further to maintain proper error
reporting
From: Ido Schimmel
So far mlxsw only supported ingress sampling using matchall classifier.
This series adds support for egress sampling and policy-based sampling
using flower classifier on Spectrum-2 and newer ASICs. As such, it is
now possible to issue these commands:
# tc filter add dev swp1
From: Ido Schimmel
Push some sampling checks to the per-ASIC operations, as they are no
longer relevant for all ASICs.
The sampling rate validation against the MPSC maximum rate is only
relevant for Spectrum-1, as Spectrum-2 and later ASICs no longer use
MPSC register for sampling.
The ingress
On Tue, Mar 16, 2021 at 04:04:31PM +0200, Vladimir Oltean wrote:
> On Tue, Mar 16, 2021 at 04:01:13PM +0200, Ido Schimmel wrote:
> > On Tue, Mar 16, 2021 at 01:24:18PM +0200, Vladimir Oltean wrote:
> > > +When the bridge has VLAN filtering enabled and a PVID is not config
implementation.
>
> Signed-off-by: Vladimir Oltean
> Reviewed-by: Florian Fainelli
Reviewed-by: Ido Schimmel
On Tue, Mar 16, 2021 at 01:24:18PM +0200, Vladimir Oltean wrote:
> +When the bridge has VLAN filtering enabled and a PVID is not configured on
> the
> +ingress port, untagged 802.1p tagged packets must be dropped. When the bridge
I think you meant "untagged and 802.1p tagged packets" ?
Looks goo
+ Petr
On Tue, Mar 16, 2021 at 06:22:08AM +1100, Tim Rice wrote:
> Hey all,
>
> Sorry if this isn't the right place to report Iproute2 bugs. It was implied
> by README.devel as well as a couple of entries I saw in bugzilla.
>
> I use iproute2 batch mode to construct network namespaces. Example
Sorry for the delay. Was AFK yesterday
On Mon, Mar 15, 2021 at 03:41:56PM +0100, Simon Horman wrote:
> On Sun, Mar 14, 2021 at 10:17:37AM +0200, Ido Schimmel wrote:
> > On Fri, Mar 12, 2021 at 03:08:28PM +0100, Simon Horman wrote:
> > > This series enhances the TC policer action
bwantysiliogogogoch"
>
> A village on the island of Anglesey (Wales), known to have the longest
> name in Europe.
>
> Signed-off-by: Daniel Lezcano
> Reviewed-by: Lukasz Luba
Tested-by: Ido Schimmel
From: Ido Schimmel
Make use of the previously added metadata and report it to the psample
module. The metadata is read from the skb's control block, which was
initialized by the bus driver (i.e., 'mlxsw_pci') after decoding the
packet's Completion Queue Element (CQE).
From: Ido Schimmel
Test that packets are sampled when tc-sample is used and that reported
metadata is correct. Two sets of hosts (with and without LAG) are used,
since metadata extraction in mlxsw is a bit different when LAG is
involved.
# ./tc_sample.sh
TEST: tc sample rate (forward
From: Ido Schimmel
Since commit 7d8e8f3433dc ("mlxsw: core: Increase scope of RCU read-side
critical section"), all Rx handlers are called from an RCU read-side
critical section.
Remove the unnecessary rcu_read_lock() / rcu_read_unlock().
Signed-off-by: Ido Schimmel
Reviewed-by:
From: Ido Schimmel
Packets that are mirrored / sampled to the CPU have extra metadata
encoded in their corresponding Completion Queue Element (CQE). Retrieve
this metadata from the CQE and set it in the skb control block so that
it could be accessed by the switch driver (i.e., 'mlxsw_spe
From: Ido Schimmel
The function resolves the psample sampling group from the Rx port
because this is the only form of sampling the driver currently supports.
Subsequent patches are going to add support for Tx-based and
policy-based sampling, in which case the sampling group would not be
resolved
1 - 100 of 2616 matches
Mail list logo
