On 12/4/2020 11:57 PM, Saeed Mahameed wrote:
We only forward ptp traffic to the new special queue but we create more
than one to avoid internal locking as we will utilize the tx softirq
percpu.
After double checking the code it seems Eran and Tariq have decided to
forward all UDP traffic, let
On 12/5/2020 1:17 AM, Jakub Kicinski wrote:
We only forward ptp traffic to the new special queue but we create more
than one to avoid internal locking as we will utilize the tx softirq
percpu.
In other words to make the driver implementation simpler we'll have
a pretty basic feature hidden be
On 12/5/2020 2:24 AM, Jakub Kicinski wrote:
On Fri, 04 Dec 2020 15:57:36 -0800 Saeed Mahameed wrote:
On Fri, 2020-12-04 at 15:17 -0800, Jakub Kicinski wrote:
On Fri, 04 Dec 2020 13:57:49 -0800 Saeed Mahameed wrote:
option 2) route PTP traffic to a special SQs per ring, this SQ
will
be
PTP p
On 12/7/2020 10:37 AM, Saeed Mahameed wrote:
On Sun, 2020-12-06 at 09:08 -0800, Richard Cochran wrote:
On Sun, Dec 06, 2020 at 03:37:47PM +0200, Eran Ben Elisha wrote:
Adding new enum to the ioctl means we have add
(HWTSTAMP_TX_ON_TIME_CRITICAL_ONLY for example) all the way -
drivers
Hi Jakub, Dave,
This series adds support for dissecting PTP L2 packet
header (EtherType 0x88F7).
For packet header dissecting, skb->protocol is needed. Add protocol
parsing operation to vlan ops, to guarantee skb->protocol is set,
as EtherType 0x88F7 occasionally follows a vlan header.
Er
Add parse protocol header ops for vlan device. Before this patch, vlan
tagged packet transmitted by af_packet had skb->protocol unset. Some
kernel methods (like __skb_flow_dissect()) rely on this missing information
for its packet processing.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Ta
Add support for parsing PTP L2 packet header. Such packet consists
of an L2 header (with ethertype of ETH_P_1588), PTP header, body
and an optional suffix.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Tariq Toukan
---
net/core/flow_dissector.c | 16
1 file changed, 16
Add parse protocol header ops for vlan device. Before this patch, vlan
tagged packet transmitted by af_packet had skb->protocol unset. Some
kernel methods (like __skb_flow_dissect()) rely on this missing information
for its packet processing.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Ta
header.
Changelog:
v2:
- Add more people to CC list.
Eran Ben Elisha (2):
net: vlan: Add parse protocol header ops
net: flow_dissector: Parse PTP L2 packet header
net/8021q/vlan_dev.c | 9 +
net/core/flow_dissector.c | 16
2 files changed, 25 insertions(+)
--
2.17.1
Add support for parsing PTP L2 packet header. Such packet consists
of an L2 header (with ethertype of ETH_P_1588), PTP header, body
and an optional suffix.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Tariq Toukan
---
net/core/flow_dissector.c | 16
1 file changed, 16
On 1/11/2021 5:49 PM, Andrew Lunn wrote:
On Mon, Jan 11, 2021 at 11:46:50AM +0200, Eran Ben Elisha wrote:
Hi Jakub, Dave,
This series adds support for dissecting PTP L2 packet
header (EtherType 0x88F7).
For packet header dissecting, skb->protocol is needed. Add protocol
parsing operat
header.
Changelog:
v2, v3:
- Add more people to the CC list.
Eran Ben Elisha (2):
net: vlan: Add parse protocol header ops
net: flow_dissector: Parse PTP L2 packet header
net/8021q/vlan_dev.c | 9 +
net/core/flow_dissector.c | 16
2 files changed, 25 insertions(+)
--
2.17.1
Add parse protocol header ops for vlan device. Before this patch, vlan
tagged packet transmitted by af_packet had skb->protocol unset. Some
kernel methods (like __skb_flow_dissect()) rely on this missing information
for its packet processing.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Ta
Add support for parsing PTP L2 packet header. Such packet consists
of an L2 header (with ethertype of ETH_P_1588), PTP header, body
and an optional suffix.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Tariq Toukan
---
net/core/flow_dissector.c | 16
1 file changed, 16
On 1/12/2021 3:49 PM, Richard Cochran wrote:
On Mon, Jan 11, 2021 at 08:17:48PM +0200, Eran Ben Elisha wrote:
Add support for parsing PTP L2 packet header. Such packet consists
of an L2 header (with ethertype of ETH_P_1588), PTP header, body
and an optional suffix.
Signed-off-by: Eran Ben
Add support for parsing PTP L2 packet header. Such packet consists
of an L2 header (with ethertype of ETH_P_1588), PTP header, body
and an optional suffix.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Tariq Toukan
---
net/core/flow_dissector.c | 16
1 file changed, 16
header.
Changelog:
v4:
- Drop a redundant length check when fetching ptp header from skb.
v2, v3:
- Add more people to the CC list.
Eran Ben Elisha (2):
net: vlan: Add parse protocol header ops
net: flow_dissector: Parse PTP L2 packet header
net/8021q/vlan_dev.c | 9 +
net/core/flow_disse
Add parse protocol header ops for vlan device. Before this patch, vlan
tagged packet transmitted by af_packet had skb->protocol unset. Some
kernel methods (like __skb_flow_dissect()) rely on this missing information
for its packet processing.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Ta
On 2/19/2021 11:57 AM, Dan Carpenter wrote:
The value of "sec" comes from the user. Negative values will lead to
shift wrapping inside the perout_conf_real_time() function and triggger
a UBSan warning.
Add a check and return -EINVAL to prevent that from happening.
Fixes: 432119de33d9 ("net/
On 1/29/2021 2:18 PM, Colin Ian King wrote:
Hi,
Static analysis with Coverity has detected an issue with the following
commit:
commit 0aa128475d33d2d0095947eeab6b3e4d22dbd578
Author: Daniel Jurgens
Date: Fri Jan 22 23:13:53 2021 +0200
net/mlx5: Maintain separate page trees for ECPF
On 3/6/2021 4:42 AM, Jakub Kicinski wrote:
Currently devlink health does not give user any clear information
of what kind of remediation ->recover callback will perform. This
makes it difficult to understand the impact of enabling auto-
-remediation, and the severity of the error itself.
To a
On 3/8/2021 7:59 PM, Jakub Kicinski wrote:
On Mon, 8 Mar 2021 09:16:00 -0800 Jakub Kicinski wrote:
+ DLH_REMEDY_BAD_PART,
BAD_PART probably indicates that the reporter (or any command line
execution) cannot recover the issue.
As the suggested remedy is static per reporter's recover met
On 3/8/2021 7:16 PM, Jakub Kicinski wrote:
On Sun, 7 Mar 2021 17:59:58 +0200 Eran Ben Elisha wrote:
On 3/6/2021 4:42 AM, Jakub Kicinski wrote:
Currently devlink health does not give user any clear information
of what kind of remediation ->recover callback will perform. This
makes
On 3/11/2021 5:26 AM, Jakub Kicinski wrote:
Pending vendors adding the right reporters. <<
Would you like Nvidia to reply with the remedy per reporter or to
actually prepare the patch?
Extend the applicability of devlink health reporters
beyond what can be locally remedied. Add failure
On 3/11/2021 5:26 AM, Jakub Kicinski wrote:
Currently devlink health does not give user any clear information
of what kind of remediation ->recover callback will perform. This
makes it difficult to understand the impact of enabling auto-
-remediation, and the severity of the error itself.
To
On 3/11/2021 6:49 PM, Jakub Kicinski wrote:
On Thu, 11 Mar 2021 16:23:09 +0200 Eran Ben Elisha wrote:
On 3/11/2021 5:26 AM, Jakub Kicinski wrote:
Pending vendors adding the right reporters. <<
Would you like Nvidia to reply with the remedy per reporter or to
actually prepare the
On 8/23/2019 1:43 AM, Haiyang Zhang wrote:
>
>
>> -Original Message-
>> From: David Miller
>> Sent: Thursday, August 22, 2019 3:39 PM
>> To: Haiyang Zhang
>> Cc: sas...@kernel.org; sae...@mellanox.com; l...@kernel.org;
>> era...@mellanox.com; lorenzo.pieral...@arm.com; bhelg...@google
t;net/mlx5: Add wrappers for HyperV PCIe operations")
Reported-by: Leon Romanovsky
Signed-off-by: Eran Ben Elisha
---
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c
b/d
From: Aya Levin
Rename devlink health attributes for better reflect the attributes use.
Add COUNT prefix on error counter attribute and recovery counter
attribute.
Fixes: 7afe335a8bed ("devlink: Add health get command")
Signed-off-by: Aya Levin
Signed-off-by: Eran Ben Elisha
Acke
This series includes two small fixes from Aya for the devlink health
infrastructure introduced earlier in this window.
First patch rename some UAPI attributes to better reflect their use.
Second patch reduces the amount of data passed from the devlink to the
netlink layer upon get reporter command
gured on a reporter that did not provide
a recover operation, thus not needed to return them.
Fixes: 7afe335a8bed ("devlink: Add health get command")
Signed-off-by: Aya Levin
Signed-off-by: Eran Ben Elisha
Acked-by: Jiri Pirko
---
net/core/devlink.c | 6 --
1 file changed
are opened
After that flow, the original error was "solved", and tx reporter state
should be healthy. However, as it was resolved as a side effect, and not
via tx reporter recover method, driver needs to inform devlink health
about it.
Signed-off-by: Eran Ben Elisha
Acked-by: Jiri Pirko
devlink_health_reporter_state enum definition to devlink.h so it could
be used from drivers as a parameter of devlink_health_reporter_state_update.
In addition, add trace_devlink_health_reporter_state_update to provide user
notification for reporter state change.
Signed-off-by: Eran Ben Elisha
Acked-by: Jiri Pirko
This patchset includes a fix [patch 01] to the devlink health state update, in
case recover was aborted.
In addition, it includes a small enhancement to the infrastructure in order to
allow direct state update in run-time, and use it from mlx5e tx reporter.
Eran Ben Elisha (3):
devlink: Update
.
In addition, save the previous health_state in a temporary variable, then use
it in the abort check comparison instead of using reporter->health_state which
might be already changed.
Fixes: c8e1da0bf923 ("devlink: Add health report functionality")
Signed-off-by: Eran Ben Elisha
A
ftirqd/1-16[001] ..s2 144.043173: net_dev_xmit_timeout: dev=ens3
> driver=e1000 queue=0
>
> Cc: Eran Ben Elisha
> Cc: Jiri Pirko
> Signed-off-by: Cong Wang
> ---
> include/trace/events/net.h | 23 +++
> net/sched/sch_generic.c| 2 ++
> 2 files
3: net_dev_xmit_timeout: dev=ens3
> driver=e1000 queue=0
>
> Cc: Eran Ben Elisha
> Cc: Jiri Pirko
> Signed-off-by: Cong Wang
Reviewed-by: Eran Ben Elisha
On Sun, Apr 1, 2018 at 7:35 PM, Eric Dumazet wrote:
>
>
> On 04/01/2018 06:17 AM, Tariq Toukan wrote:
>> From: Eran Ben Elisha
>>
>> Add GRO capability for IPv6 GRE tunnel and ip6erspan tap, via gro_cells
>> infrastructure.
>>
>> Performance testing
>>> Seems good, but why isn't this handled directly in GRO native layer ?
>> ip6_tunnel and ip6_gre do not share initialization flow functions (unlike
>> ipv4).
>> Changing the ipv6 init infrastructure should not be part of this
>> patch. we prefer to keep this one minimal, simple and safe.
>
>
>
Add devlink-health man page. Devlink-health tool will control device
health attributes, sensors, actions and logging.
Signed-off-by: Eran Ben Elisha
---
Copy paste man output to here for easier review process of the RFC.
DEVLINK-HEALTH(8
and actions.
Eran Ben Elisha (1):
man: Add devlink health man page
man/man8/devlink-health.8 | 171 ++
1 file changed, 171 insertions(+)
create mode 100644 man/man8/devlink-health.8
--
1.8.3.1
On 9/13/2018 1:27 PM, Tobin C. Harding wrote:
On Thu, Sep 13, 2018 at 11:18:16AM +0300, Eran Ben Elisha wrote:
Add devlink-health man page. Devlink-health tool will control device
health attributes, sensors, actions and logging.
Signed-off-by: Eran Ben Elisha
On 9/13/2018 3:08 PM, Andrew Lunn wrote:
devlink health sensor set pci/:01:00.0 name TX_COMP_ERROR action
reset off action dump on
Sets TX_COMP_ERROR sensor parameters for a specific device.
I hope the real sensors have more understandable names. If i remember
correc
On 9/13/2018 4:24 PM, Andrew Lunn wrote:
On Thu, Sep 13, 2018 at 03:49:37PM +0300, Eran Ben Elisha wrote:
On 9/13/2018 3:08 PM, Andrew Lunn wrote:
devlink health sensor set pci/:01:00.0 name TX_COMP_ERROR action
reset off action dump on
Sets TX_COMP_ERROR sensor
On 9/13/2018 6:12 PM, Andrew Lunn wrote:
devlink health sensor set pci/:01:00.0 name TX_COMP_ERROR action
reset off action dump on
Sets TX_COMP_ERROR sensor parameters for a specific device.
This is what I had in mind:
1. command interface error
2. command interface
On 9/13/2018 8:36 PM, Jakub Kicinski wrote:
On Thu, 13 Sep 2018 11:18:15 +0300, Eran Ben Elisha wrote:
The health spec is targeted for Real Time Alerting, in order to know when
something bad had happened to a PCI device
By spec you mean some standards body spec you implement or this
On Mon, Jan 15, 2018 at 1:52 AM, Stephen Rothwell wrote:
> Hi all,
>
> Today's linux-next merge of the net-next tree got a conflict in:
>
> include/linux/mlx5/mlx5_ifc.h
>
> between commit:
>
> 8978cc921fc7 ("{net,ib}/mlx5: Don't disable local loopback multicast
> traffic when needed")
>
> fr
reporter_tx.c.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Saeed Mahameed
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 18 +-
.../ethernet/mellanox/mlx5/core/en/reporter.h | 14 +
.../mellanox/mlx5/core/en/reporter_tx.c | 321
From: Moshe Shemesh
Refactor print health info code, split to two functions:
1. mlx5_get_health_info() - writes the health info into a buffer.
2. mlx5_print_health_info() - prints the health info to kernel log.
This refactoring is done to enable using the health info data by devlink
health repo
run it
manually.
Signed-off-by: Moshe Shemesh
Signed-off-by: Eran Ben Elisha
Reviewed-by: Saeed Mahameed
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 19 +++
.../net/ethernet/mellanox/mlx5/core/devlink.h | 1 +
.../net/ethernet/mellanox/mlx5/core/health.c | 23
From: Moshe Shemesh
Create mlx5_devlink_health_reporter for FW reporter. The FW reporter
implements devlink_health_reporter diagnose callback.
Signed-off-by: Moshe Shemesh
Reviewed-by: Saeed Mahameed
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 114 ++
.../net/ethernet/
From: Aya Levin
This patch adds a new file to add information about devlink health
mechanism.
Signed-off-by: Aya Levin
Signed-off-by: Eran Ben Elisha
---
Documentation/networking/devlink-health.txt | 86 +
1 file changed, 86 insertions(+)
create mode 100644 Documentation
From: Feras Daoud
If a FW assert is considered fatal, indicated by a new bit in the health
buffer, reset the FW. After the reset go through the normal recovery
flow. Only one PF needs to issue the reset, so an attempt is made to
prevent the 2nd function from also issuing the reset.
It's not an er
From: Moshe Shemesh
Add access functions to core dump register to enable trigger FW core
dump.
Signed-off-by: Moshe Shemesh
Reviewed-by: Saeed Mahameed
---
.../mellanox/mlx5/core/diag/fw_tracer.c | 32 +++
include/linux/mlx5/driver.h | 1 +
include/lin
From: Alex Vesker
Crdump allows the driver to create a snapshot of the FW PCI
crspace. This is useful in case of catastrophic issues which
require FW reset. The snapshot can be used for later debug.
The snapshot is exposed using devlink, cr-space
address regions are registered on init and snapsh
already stored)
* Auto recovery attempt is being done. depends on:
- Auto Recovery configuration
- Grace period vs. time since last recover
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h | 9
include/trace/events/devlink.h | 62
From: Feras Daoud
New mlx5 adapters allow the driver to reset the FW in the event of an
error, this action called "SW Reset". When an SW reset is issued on any
PF all PFs enter reset state which is a recoverable condition. The
existing recovery flow was designed to allow the recovery of a VF afte
eporter by
devlink_health_reporter_priv function.
For each reporter, devlink will hold a metadata of statistics,
buffers and status.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h | 59
net/core/devlink.
From: Moshe Shemesh
Add support of dump callback for mlx5 FW reporter.
Once we trigger FW dump, the FW will write the core dump to its raw data
buffer. The tracer translates the raw data to traces and save it to a
buffer. Once dump is done, the saved traces data is filled as objects
into the dump
-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h| 76 ++
include/uapi/linux/devlink.h | 8 +
net/core/devlink.c | 501 +++
3 files changed, 585 insertions(+)
diff --git a/include/net/devlink.h b/include/net
recover pci/:00:09 reporter TX
$devlink health show
pci/:00:09.0:
name TX state healthy #err 1 #recover 1 last_dump_ts N/A dump_available false
attributes:
grace_period 500 auto_recover false
Signed-off-by: Eran Ben Elisha
Reviewed-by: Saeed Mahameed
---
.../ethernet/mellanox
.
Signed-off-by: Moshe Shemesh
Signed-off-by: Eran Ben Elisha
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 91 +++
1 file changed, 91 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index
From: Moshe Shemesh
Use devlink_health_report() to report any symptom of FW issue as FW
counter miss or new health syndrom.
Signed-off-by: Moshe Shemesh
Reviewed-by: Saeed Mahameed
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 21 +++
.../net/ethernet/mellanox/mlx5/core/
From: Alex Vesker
The Vendor Specific Capability (VSC) is used to activate a gateway
interfacing with the device. The gateway is used to read or write
device configurations, which are organized in different domains (spaces).
A configuration access may result in multiple actions, reads, writes.
E
dded.
Alex Vesker (2):
net/mlx5: Add Vendor Specific Capability access gateway
net/mlx5: Add Crdump FW snapshot support
Aya Levin (1):
devlink: Add Documentation/networking/devlink-health.txt
Eran Ben Elisha (11):
devlink: Add health buffer support
devlink: Add health reporter create/dest
From: Feras Daoud
Initial kernel documentation for mlx5 core driver.
This change includes also documentation for the new devlink region
param : DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT.
Signed-off-by: Feras Daoud
Signed-off-by: Saeed Mahameed
---
Documentation/networking/mlx5.rst | 39 +++
Add devlink health get command to provide reporter/s data for user space.
Add the ability to get data per reporter or dump data from all available
reporters.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 12 +++
net/core/devlink.c | 152
From: Feras Daoud
Since the FW can be shared between different PFs/VFs it is common
that more than one health poll will detected a failure, this can
lead to multiple resets which are unneeded.
The solution is to use a FW locking mechanism using semaphore space
to provide a way to allow only one
From: Moshe Shemesh
Create mlx5_devlink_health_reporter for FW fatal reporter.
The FW fatal reporter is added in addition to the fw reporter and
implements only the recover callback.
The point of having two reporters for FW issues, is that we
don't want to run FW recover on any issue, but only fa
user.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 51
2 files changed, 52 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 1c186fd
the reporter
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 36
2 files changed, 37 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index
Add devlink health recover command to the uapi, in order to allow the user
to execute a recover operation over a specific reporter.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 20
2 files
From: Moshe Shemesh
This parameter enables capturing region snapshot of the crspace
during critical errors. The default value of this parameter is
disabled, it can be enabled using devlink param commands.
It is possible to configure during runtime and also driver init.
Signed-off-by: Alex Vesker
fill it
via the buffer descriptors API. Devlink will parse it and convert it to
netlink nla API in order to pass it to the user.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 2 +
net/core/devlink.c
Centralize all devlink related callbacks in one file.
In the downstream patch, some more functionality will be added, this
patch is preparing the driver infrastructure for it.
Currently, move devlink un/register functions calls into this file.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe
On 1/17/2019 8:52 PM, Jiri Pirko wrote:
> Thu, Jan 17, 2019 at 04:04:54PM CET, era...@mellanox.com wrote:
>
>
> 27 patches is way too many to review in one go.
> Please split to at least 2 patchsets. Thanks!
>
Ack, will post v2 soon.
recover pci/:00:09 reporter TX
$devlink health show
pci/:00:09.0:
name TX state healthy #err 1 #recover 1 last_dump_ts N/A dump_available false
attributes:
grace_period 500 auto_recover false
Signed-off-by: Eran Ben Elisha
Reviewed-by: Saeed Mahameed
---
.../ethernet/mellanox
fill it
via the buffer descriptors API. Devlink will parse it and convert it to
netlink nla API in order to pass it to the user.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 2 +
net/core/devlink.c
already stored)
* Auto recovery attempt is being done. depends on:
- Auto Recovery configuration
- Grace period vs. time since last recover
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h | 9
include/trace/events/devlink.h | 62
Add devlink health get command to provide reporter/s data for user space.
Add the ability to get data per reporter or dump data from all available
reporters.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 12 +++
net/core/devlink.c | 152
FW* reporters to decrease the amount of patches in the patchset
Aya Levin (1):
devlink: Add Documentation/networking/devlink-health.txt
Eran Ben Elisha (10):
devlink: Add health buffer support
devlink: Add health reporter create/destroy functionality
devlink: Add health report functionality
de
From: Aya Levin
This patch adds a new file to add information about devlink health
mechanism.
Signed-off-by: Aya Levin
Signed-off-by: Eran Ben Elisha
---
Documentation/networking/devlink-health.txt | 86 +
1 file changed, 86 insertions(+)
create mode 100644 Documentation
-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h| 76 ++
include/uapi/linux/devlink.h | 8 +
net/core/devlink.c | 501 +++
3 files changed, 585 insertions(+)
diff --git a/include/net/devlink.h b/include/net
eporter by
devlink_health_reporter_priv function.
For each reporter, devlink will hold a metadata of statistics,
buffers and status.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h | 59
net/core/devlink.
Add devlink health recover command to the uapi, in order to allow the user
to execute a recover operation over a specific reporter.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 20
2 files
user.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 51
2 files changed, 52 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 1c186fd
the reporter
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 36
2 files changed, 37 insertions(+)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index
reporter_tx.c.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Saeed Mahameed
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 18 +-
.../ethernet/mellanox/mlx5/core/en/reporter.h | 14 +
.../mellanox/mlx5/core/en/reporter_tx.c | 321
On 1/20/2019 12:03 PM, Jiri Pirko wrote:
> Thu, Jan 17, 2019 at 10:59:10PM CET, era...@mellanox.com wrote:
>
> [...]
>
>> +static void
>> +devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list,
>> + u64 size);
>
> Avoid fwd declarations.
>
>
>>
On 1/20/2019 8:45 PM, David Miller wrote:
> From: Jiri Pirko
> Date: Sun, 20 Jan 2019 12:08:50 +0100
>
>> I haven't have time to review this due to travel. I think it was mistake
>> to merge this as the buffer api is wrong in my opinion. I would vote for
>> revert if possible.
>
> Let's spend
On 1/20/2019 1:27 PM, Jiri Pirko wrote:
> Thu, Jan 17, 2019 at 10:59:12PM CET, era...@mellanox.com wrote:
>
> [...]
>
>> +
>> +TRACE_EVENT(devlink_health_recover_aborted,
>> +TP_PROTO(const struct devlink *devlink, const char *reporter_name,
>> + bool health_state, u64 time_sinc
On 1/21/2019 10:21 AM, Wei Yongjun wrote:
> Fix to return a negative error code -EMSGSIZE from the error handling
> case, otherwise 0 or uninitialized value may be returned.
>
> Fixes: cb5ccfbe73b3 ("devlink: Add health buffer support")
> Signed-off-by: Wei Yongjun
Thanks for the fix!
However,
>>
>> The SQ recover from error CQE flow is not a new feature in the driver,
>> this patch re-organize the functions and adapt them for the devlink
>> health API. For this purpose, move code from en_main.c to a new file
>> named reporter_tx.c.
>>
>> Signed-o
On 1/21/2019 2:11 PM, Jiri Pirko wrote:
> Mon, Jan 21, 2019 at 12:32:07PM CET, era...@mellanox.com wrote:
>>
>>
>> On 1/20/2019 1:06 PM, Jiri Pirko wrote:
>>> Thu, Jan 17, 2019 at 10:59:18PM CET, era...@mellanox.com wrote:
>
> [...]
>
>
+static int
+mlx5e_tx_reporter_build_diag
It is not in use anymore and can be safely removed from the kernel code.
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h| 76 --
include/uapi/linux/devlink.h | 8 -
net/core/devlink.c | 501 ---
3
evlink health and mlx5e TX reporter.
Also, added some helpers together with the new API, which reduce the code
required by the driver to fill dump and diagnose significantly.
Eventually, it also deletes the old API.
In addition, it includes some small fixes in the devlink and mlx5e TX reporter.
Er
No need for spaces around "=" in the logger print.
Fixes: c7af343b4e33 ("devlink: Add health report functionality")
Signed-off-by: Eran Ben Elisha
Reported-by: Jiri Pirko
Reviewed-by: Moshe Shemesh
---
include/trace/events/devlink.h | 2 +-
1 file changed, 1 insertion(+),
Fix a bug where reporter->devlink attribute was used after the reporter
was freed.
Fixes: 880ee82f0313 ("devlink: Add health reporter create/destroy
functionality")
Signed-off-by: Eran Ben Elisha
Reviewed-by: Moshe Shemesh
---
net/core/devlink.c | 6 --
1 file changed, 4 ins
As part of the recover flow, driver calls mlx5e_open_locked, which
eventually calls netif_set_real_num_tx_queues. RTNL lock must be held as
part of this flow in advance, like in other flows in the driver.
Fixes: aba25279c100 ("net/mlx5e: Add TX reporter support")
Signed-off-by: Eran
-by: Eran Ben Elisha
CC: Wei Yongjun
Reviewed-by: Moshe Shemesh
---
include/net/devlink.h| 70 ++
include/uapi/linux/devlink.h | 8 +
net/core/devlink.c | 455 +++
3 files changed, 533 insertions(+)
diff --git a/include/net/devlink.h b
1 - 100 of 196 matches
Mail list logo
