sorry for occasionally reply to old thread.
On Wed, Feb 20, 2019 at 11:02:42AM +, Vadim Lomovtsev wrote:
> The ThunderX CN88XX NIC Virtual Function driver uses mailbox interface
> to communicate to physical function driver. Each of VF has it's own pair
> of mailbox registers to
one work queue for each NIC VF for set_rx_mode
task and to let them work independently and replacing delayed_work
with work_struct.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h | 4 ++-
.../net/ethernet/cavium/thunder/nicvf_main.c | 30 ++-
2
To communicate to PF each of ThunderX NIC VF uses mailbox which is
pair of 64 bit registers available to both VFn and PF.
This commit is to change the xcast message structure in order to
fit it into 64 bit.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 6
-off-by: Vadim Lomovtsev
---
.../net/ethernet/cavium/thunder/nic_main.c| 114 ++
1 file changed, 12 insertions(+), 102 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 8ab71dae3988..c90252829ed3 10
e return type of nicvf_send_cfg_done() function
from int to void;
- 0007: update subject and remove unused variable 'netdev'
from nicvf_link_status_check_task() function;
Vadim Lomovtsev (8):
net: thunderx: correct typo in macro name
net: thunderx: replace global nicvf_rx_mode_wq work queu
messaging control data from concurrent access.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 2 ++
drivers/net/ethernet/cavium/thunder/nicvf_main.c | 13 ++---
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/cavium
Move the link change polling task to VF side in order to
prevent races between VF and PF while sending link change
message(s). This commit is to implement link change request
to be initiated by VF.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h | 2 +-
.../net
The rx_set_mode invokes number of messages to be send to PF for receive
mode configuration. In case if there any issues we need to stop sending
messages and release allocated memory.
This commit is to implement check of nicvf_msg_send_to_pf() result.
Signed-off-by: Vadim Lomovtsev
---
drivers
nicvf_send_msg_to_pf() routine.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 2 +-
drivers/net/ethernet/cavium/thunder/nicvf_main.c | 15 ---
2 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
Correct STREERING to STEERING at macro name for BGX steering register.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
drivers/net/ethernet/cavium/thunder/thunder_bgx.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers
Hi David,
On Mon, Feb 18, 2019 at 03:33:10PM -0800, David Miller wrote:
> From: Vadim Lomovtsev
> Date: Mon, 18 Feb 2019 09:52:14 +
>
> > @@ -169,6 +169,20 @@ static int nicvf_check_pf_ready(struct nicvf *nic)
> > return 1;
> > }
> >
> > +stat
Correct STREERING to STEERING at macro name for BGX steering register.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
drivers/net/ethernet/cavium/thunder/thunder_bgx.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers
From: Vadim Lomovtsev
The ThunderX CN88XX NIC Virtual Function driver uses mailbox interface
to communicate to physical function driver. Each of VF has it's own pair
of mailbox registers to read from and write to. The mailbox registers
has no protection from possible races, so it has
The rx_set_mode invokes number of messages to be send to PF for receive
mode configuration. In case if there any issues we need to stop sending
messages and release allocated memory.
This commit is to implement check of nicvf_msg_send_to_pf() result.
Signed-off-by: Vadim Lomovtsev
---
drivers
-off-by: Vadim Lomovtsev
---
.../net/ethernet/cavium/thunder/nic_main.c| 114 ++
1 file changed, 12 insertions(+), 102 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 8ab71dae3988..c90252829ed3 10
one work queue for each NIC VF for set_rx_mode
task and to let them work independently and replacing delayed_work
with work_struct.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h | 4 ++-
.../net/ethernet/cavium/thunder/nicvf_main.c | 30 ++-
2
To communicate to PF each of ThunderX NIC VF uses mailbox which is
pair of 64 bit registers available to both VFn and PF.
This commit is to change the xcast message structure in order to
fit it into 64 bit.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 6
nicvf_send_msg_to_pf() routine.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 2 +-
.../net/ethernet/cavium/thunder/nicvf_main.c | 18 +++---
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
b
Move the link change polling task to VF side in order to
prevent races between VF and PF while sending link change
message(s). This commit is to implement link change request
to be initiated by VF.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h | 2 +-
.../net
messaging control data from concurrent access.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 2 ++
drivers/net/ethernet/cavium/thunder/nicvf_main.c | 13 ++---
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/cavium
self-NACK here, some emails get's corrupted for some reasons,
along with some typos found.
sorry for inconvenience.
Vadim
On Wed, Feb 06, 2019 at 10:13:54AM +, Vadim Lomovtsev wrote:
> The ThunderX CN88XX NIC Virtual Function driver uses mailbox interface
> to communicate to ph
The rx_set_mode invokes number of messages to be send to PF for receive
mode configuration. In case if there any issues we need to stop sending
messages and release allocated memory.
This commit is to implement check of nicvf_msg_send_to_pf() result.
Signed-off-by: Vadim Lomovtsev
---
drivers
one work queue for each NIC VF for set_rx_mode
task and to let them work independently and replacing delayed_work
with work_struct.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h | 4 ++-
.../net/ethernet/cavium/thunder/nicvf_main.c | 30 ++-
2
To communicate to PF each of ThunderX NIC VF uses mailbox which is
pair of 64 bit registers available to both VFn and PF.
This commit is to change the xcast message structure in order to
fit it into 64 bit.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 6
This commit is to implement routines to read mailbox IRQ status
for particular VF at PF side, and for mailbox IRQ status
from PF at VF side.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 13 +
drivers/net/ethernet/cavium/thunder
Correct STREERING to STEERING at macro name for BGX steering register.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
drivers/net/ethernet/cavium/thunder/thunder_bgx.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers
nicvf_send_msg_to_pf() routine.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 2 +-
.../net/ethernet/cavium/thunder/nicvf_main.c | 18 +++---
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
b
.
This patch series is to address race condition with VF & PF communication.
Vadim Lomovtsev (8):
net: thunderx: correct typo in macro name
net: thunderx: replace global nicvf_rx_mode_wq work queue for all VFs
to private for each of them.
net: thunderx: make CFG_DONE message to run through gen
VF.
Signed-off-by: Vadim Lomovtsev
---
.../net/ethernet/cavium/thunder/nic_main.c| 39 ---
.../net/ethernet/cavium/thunder/nicvf_main.c | 3 ++
2 files changed, 20 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c
b/drivers/net
messaging control data from concurrent access.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic.h| 2 ++
drivers/net/ethernet/cavium/thunder/nicvf_main.c | 13 ++---
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/cavium
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put singl
From: Vadim Lomovtsev
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put single null check on kmalloc
return value
On Sun, Apr 08, 2018 at 12:42:00PM -0400, David Miller wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@caviumnetworks.com>
> Date: Fri, 6 Apr 2018 12:53:54 -0700
>
> > @@ -1929,7 +1929,7 @@ static void nicvf_set_rx_mode_task(struct work_
On Sun, Apr 08, 2018 at 12:42:00PM -0400, David Miller wrote:
> From: Vadim Lomovtsev
> Date: Fri, 6 Apr 2018 12:53:54 -0700
>
> > @@ -1929,7 +1929,7 @@ static void nicvf_set_rx_mode_task(struct work_struct
> > *work_arg)
> >
Hi Willy,
Thank you for your opinion, it's very helpful.
WBR,
Vadim
On Fri, Apr 06, 2018 at 09:21:46PM +0200, Willy Tarreau wrote:
> Hi Vadim,
>
> On Fri, Apr 06, 2018 at 11:29:16AM -0700, Vadim Lomovtsev wrote:
> > Hi all,
> >
> > I bring my Apol
Hi Willy,
Thank you for your opinion, it's very helpful.
WBR,
Vadim
On Fri, Apr 06, 2018 at 09:21:46PM +0200, Willy Tarreau wrote:
> Hi Vadim,
>
> On Fri, Apr 06, 2018 at 11:29:16AM -0700, Vadim Lomovtsev wrote:
> > Hi all,
> >
> > I bring my Apol
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put singl
From: Vadim Lomovtsev
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put single null check on kmalloc
return value
Hi all,
I bring my Apologise for wasting your time, but ..
May I ask for some clarification.. When we're speaking of 'posting patches
shortly'
does it mean to send them in next few hours ?
Or would it be more acceptable to post one version per day
even for very small changes in between ?
Hi all,
I bring my Apologise for wasting your time, but ..
May I ask for some clarification.. When we're speaking of 'posting patches
shortly'
does it mean to send them in next few hours ?
Or would it be more acceptable to post one version per day
even for very small changes in between ?
Self-NACK here, because of https://lkml.org/lkml/2018/4/6/724
Sorry for noise.
Vadim
On Fri, Apr 06, 2018 at 07:04:43AM -0700, Vadim Lomovtsev wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
>
> It is too expensive to pass u64 values via linked list, instead
&
Self-NACK here, because of https://lkml.org/lkml/2018/4/6/724
Sorry for noise.
Vadim
On Fri, Apr 06, 2018 at 07:04:43AM -0700, Vadim Lomovtsev wrote:
> From: Vadim Lomovtsev
>
> It is too expensive to pass u64 values via linked list, instead
> allocate array for them by overall n
On Fri, Apr 06, 2018 at 11:06:03AM -0400, David Miller wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@caviumnetworks.com>
> Date: Fri, 6 Apr 2018 04:14:25 -0700
>
> > diff --git a/drivers/net/ethernet/cavium/thunder/nic.h
> > b/drivers/net/ethernet/cavium/thunder/n
On Fri, Apr 06, 2018 at 11:06:03AM -0400, David Miller wrote:
> From: Vadim Lomovtsev
> Date: Fri, 6 Apr 2018 04:14:25 -0700
>
> > diff --git a/drivers/net/ethernet/cavium/thunder/nic.h
> > b/drivers/net/ethernet/cavium/thunder/nic.h
> > index 5fc46c
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put singl
From: Vadim Lomovtsev
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put single null check on kmalloc
return value
Hi Robin,
On Fri, Apr 06, 2018 at 12:48:40PM +0100, Robin Murphy wrote:
> On 06/04/18 12:14, Vadim Lomovtsev wrote:
> > From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
> >
> > It is too expensive to pass u64 values via linked list, instead
> > allocate array
Hi Robin,
On Fri, Apr 06, 2018 at 12:48:40PM +0100, Robin Murphy wrote:
> On 06/04/18 12:14, Vadim Lomovtsev wrote:
> > From: Vadim Lomovtsev
> >
> > It is too expensive to pass u64 values via linked list, instead
> > allocate array for them by overall number o
On Fri, Apr 06, 2018 at 06:47:26AM -0500, Gustavo A. R. Silva wrote:
>
>
> On 04/06/2018 06:43 AM, Vadim Lomovtsev wrote:
> > Hi Gustavo,
> >
> > On Fri, Apr 06, 2018 at 06:36:28AM -0500, Gustavo A. R. Silva wrote:
> > > Hi Vadim,
> > >
> &
On Fri, Apr 06, 2018 at 06:47:26AM -0500, Gustavo A. R. Silva wrote:
>
>
> On 04/06/2018 06:43 AM, Vadim Lomovtsev wrote:
> > Hi Gustavo,
> >
> > On Fri, Apr 06, 2018 at 06:36:28AM -0500, Gustavo A. R. Silva wrote:
> > > Hi Vadim,
> > >
> &
Hi Gustavo,
On Fri, Apr 06, 2018 at 06:36:28AM -0500, Gustavo A. R. Silva wrote:
> Hi Vadim,
>
> On 04/06/2018 06:14 AM, Vadim Lomovtsev wrote:
> > From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
> >
> > It is too expensive to pass u64 values via linked
Hi Gustavo,
On Fri, Apr 06, 2018 at 06:36:28AM -0500, Gustavo A. R. Silva wrote:
> Hi Vadim,
>
> On 04/06/2018 06:14 AM, Vadim Lomovtsev wrote:
> > From: Vadim Lomovtsev
> >
> > It is too expensive to pass u64 values via linked list, instead
> > allocate array
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put singl
From: Vadim Lomovtsev
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put single null check on kmalloc
return value
Hi Christoph,
Thank you for your feedback and time.
On Thu, Apr 05, 2018 at 08:07:48AM -0700, Christoph Hellwig wrote:
> > struct xcast_addr_list {
> > - struct list_head list;
> > int count;
> > + u64 mc[0];
>
> Please use the standard C99 syntax here:
>
>
Hi Christoph,
Thank you for your feedback and time.
On Thu, Apr 05, 2018 at 08:07:48AM -0700, Christoph Hellwig wrote:
> > struct xcast_addr_list {
> > - struct list_head list;
> > int count;
> > + u64 mc[0];
>
> Please use the standard C99 syntax here:
>
>
[correct Roberts' address]
On Thu, Apr 05, 2018 at 07:57:56AM -0700, Vadim Lomovtsev wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
>
> It is too expensive to pass u64 values via linked list, instead
> allocate array for them by overall number of mac add
[correct Roberts' address]
On Thu, Apr 05, 2018 at 07:57:56AM -0700, Vadim Lomovtsev wrote:
> From: Vadim Lomovtsev
>
> It is too expensive to pass u64 values via linked list, instead
> allocate array for them by overall number of mac addresses from netdev.
>
> This eventuall
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put singl
From: Vadim Lomovtsev
It is too expensive to pass u64 values via linked list, instead
allocate array for them by overall number of mac addresses from netdev.
This eventually removes multiple kmalloc() calls, aviod memory
fragmentation and allow to put single null check on kmalloc
return value
Hi guys,
Please give me couple days to workout solution for this.
I'll post patch for this as soon as I done with my testing.
WBR,
Vadim
On Tue, Apr 03, 2018 at 05:04:23PM -0500, Gustavo A. R. Silva wrote:
> Add null check on kmalloc() return value in order to prevent
> a null pointer
Hi guys,
Please give me couple days to workout solution for this.
I'll post patch for this as soon as I done with my testing.
WBR,
Vadim
On Tue, Apr 03, 2018 at 05:04:23PM -0500, Gustavo A. R. Silva wrote:
> Add null check on kmalloc() return value in order to prevent
> a null pointer
On Sat, Mar 31, 2018 at 10:07:30PM -0400, David Miller wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@caviumnetworks.com>
> Date: Fri, 30 Mar 2018 04:59:46 -0700
>
> > From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
> >
> > By default CN88XX BGX accep
On Sat, Mar 31, 2018 at 10:07:30PM -0400, David Miller wrote:
> From: Vadim Lomovtsev
> Date: Fri, 30 Mar 2018 04:59:46 -0700
>
> > From: Vadim Lomovtsev
> >
> > By default CN88XX BGX accepts all incoming multicast and broadcast
> > packets and filtering is
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC has set of registers which allows to configure
filter policy for ingress packets. There are three possible regimes
of filtering multicasts, broadcasts and unicasts: accept all, reject all
and accept filter allowed only.
C
From: Vadim Lomovtsev
The ThunderX NIC has set of registers which allows to configure
filter policy for ingress packets. There are three possible regimes
of filtering multicasts, broadcasts and unicasts: accept all, reject all
and accept filter allowed only.
Current implementation has enum
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC has two Ethernet Interfaces (BGX) each of them could has
up to four Logical MACs configured. Each of BGX has 32 filters to be
configured for filtering ingress packets. The number of filters available
to particular LMAC is
From: Vadim Lomovtsev
The ThunderX NIC has two Ethernet Interfaces (BGX) each of them could has
up to four Logical MACs configured. Each of BGX has 32 filters to be
configured for filtering ingress packets. The number of filters available
to particular LMAC is from 8 (if we have four LMACs
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The kernel calls ndo_set_rx_mode() callback supplying it will all necessary
info, such as device state flags, multicast mac addresses list and so on.
Since we have only 128 bits to communicate with PF we need to initiate
several requests
From: Vadim Lomovtsev
The kernel calls ndo_set_rx_mode() callback supplying it will all necessary
info, such as device state flags, multicast mac addresses list and so on.
Since we have only 128 bits to communicate with PF we need to initiate
several requests to PF with small/short operation
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
This commit is to add message handling for ndo_set_rx_mode()
callback at PF side.
Signed-off-by: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 45 +++---
1 file
From: Vadim Lomovtsev
This commit is to add message handling for ndo_set_rx_mode()
callback at PF side.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 45 +++---
1 file changed, 41 insertions(+), 4 deletions(-)
diff --git a/drivers/net
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ndo_set_rx_mode() is called from atomic context which causes
messages response timeouts while VF to PF communication via MSIx.
To get rid of that we're copy passed mc list, parse flags and queue
handling of kernel request to ordered wor
From: Vadim Lomovtsev
The ndo_set_rx_mode() is called from atomic context which causes
messages response timeouts while VF to PF communication via MSIx.
To get rid of that we're copy passed mc list, parse flags and queue
handling of kernel request to ordered workqueue.
Signed-off-by: Vadim
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The kernel calls ndo_set_rx_mode() callback from atomic context which
causes messaging timeouts between VF and PF (as they’re implemented via
MSIx). So in order to handle ndo_set_rx_mode() we need to get rid of it.
This commit impl
From: Vadim Lomovtsev
The kernel calls ndo_set_rx_mode() callback from atomic context which
causes messaging timeouts between VF and PF (as they’re implemented via
MSIx). So in order to handle ndo_set_rx_mode() we need to get rid of it.
This commit implements necessary workqueue related
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
By default CN88XX BGX accepts all incoming multicast and broadcast
packets and filtering is disabled. The nic driver doesn't provide
an ability to change such behaviour.
This series is to implement DMAC filtering management for CN88XX
nic
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC could be partitioned to up to 128 VFs and thus
represented to system. Each VF is mapped to pair BGX:LMAC, and each of VF
is configured by kernel individually. Eventually the bunch of VFs could be
mapped onto same pair BG
From: Vadim Lomovtsev
By default CN88XX BGX accepts all incoming multicast and broadcast
packets and filtering is disabled. The nic driver doesn't provide
an ability to change such behaviour.
This series is to implement DMAC filtering management for CN88XX
nic driver allowing user to enable
From: Vadim Lomovtsev
The ThunderX NIC could be partitioned to up to 128 VFs and thus
represented to system. Each VF is mapped to pair BGX:LMAC, and each of VF
is configured by kernel individually. Eventually the bunch of VFs could be
mapped onto same pair BGX:LMAC and thus could cause several
Hi David,
Thanks for feedback.
On Tue, Mar 27, 2018 at 01:28:22PM -0400, David Miller wrote:
> From: Vadim Lomovtsev <vadim.lomovt...@caviumnetworks.com>
> Date: Tue, 27 Mar 2018 08:07:29 -0700
>
> > From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
> >
>
Hi David,
Thanks for feedback.
On Tue, Mar 27, 2018 at 01:28:22PM -0400, David Miller wrote:
> From: Vadim Lomovtsev
> Date: Tue, 27 Mar 2018 08:07:29 -0700
>
> > From: Vadim Lomovtsev
> >
> > By default CN88XX BGX accepts all incoming multicast and broadcas
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC has two Ethernet Interfaces (BGX) each of them could has
up to four Logical MACs configured. Each of BGX has 32 filters to be
configured for filtering ingress packets. The number of filters available
to particular LMAC is
From: Vadim Lomovtsev
The ThunderX NIC has two Ethernet Interfaces (BGX) each of them could has
up to four Logical MACs configured. Each of BGX has 32 filters to be
configured for filtering ingress packets. The number of filters available
to particular LMAC is from 8 (if we have four LMACs
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
By default CN88XX BGX accepts all incoming multicast and broadcast
packets and filtering is disabled. The nic driver doesn't provide
an ability to change such behaviour.
This series is to implement DMAC filtering management for CN88XX
nic
From: Vadim Lomovtsev
By default CN88XX BGX accepts all incoming multicast and broadcast
packets and filtering is disabled. The nic driver doesn't provide
an ability to change such behaviour.
This series is to implement DMAC filtering management for CN88XX
nic driver allowing user to enable
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC could be partitioned to up to 128 VFs and thus
represented to system. Each VF is mapped to pair BGX:LMAC, and each of VF
is configured by kernel individually. Eventually the bunch of VFs could be
mapped onto same pair BG
From: Vadim Lomovtsev
The ThunderX NIC could be partitioned to up to 128 VFs and thus
represented to system. Each VF is mapped to pair BGX:LMAC, and each of VF
is configured by kernel individually. Eventually the bunch of VFs could be
mapped onto same pair BGX:LMAC and thus could cause several
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ndo_set_rx_mode() is called from atomic context which causes
messages response timeouts while VF to PF communication via MSIx.
To get rid of that we're copy passed mc list, parse flags and queue
handling of kernel request to ordered wor
From: Vadim Lomovtsev
The ndo_set_rx_mode() is called from atomic context which causes
messages response timeouts while VF to PF communication via MSIx.
To get rid of that we're copy passed mc list, parse flags and queue
handling of kernel request to ordered workqueue.
Signed-off-by: Vadim
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The kernel calls ndo_set_rx_mode() callback from atomic context which
causes messaging timeouts between VF and PF (as they’re implemented
via MSIx). So in order to handle ndo_set_rx_mode() we need to get rid of it.
This commit impl
From: Vadim Lomovtsev
The kernel calls ndo_set_rx_mode() callback from atomic context which
causes messaging timeouts between VF and PF (as they’re implemented
via MSIx). So in order to handle ndo_set_rx_mode() we need to get rid of it.
This commit implements necessary workqueue related
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
This commit is to add message handling for ndo_set_rx_mode()
callback at PF side.
Signed-off-by: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 45 +++---
1 file
From: Vadim Lomovtsev
This commit is to add message handling for ndo_set_rx_mode()
callback at PF side.
Signed-off-by: Vadim Lomovtsev
---
drivers/net/ethernet/cavium/thunder/nic_main.c | 45 +++---
1 file changed, 41 insertions(+), 4 deletions(-)
diff --git a/drivers/net
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The ThunderX NIC has set of registers which allows to configure
filter policy for ingress packets. There are three possible regimes
of filtering multicasts, broadcasts and unicasts: accept all, reject all
and accept filter allowed only.
C
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
The kernel calls ndo_set_rx_mode() callback supplying it will all necessary
info, such as device state flags, multicast mac addresses list and so on.
Since we have only 128 bits to communicate with PF we need to initiate
several requests
From: Vadim Lomovtsev
The ThunderX NIC has set of registers which allows to configure
filter policy for ingress packets. There are three possible regimes
of filtering multicasts, broadcasts and unicasts: accept all, reject all
and accept filter allowed only.
Current implementation has enum
From: Vadim Lomovtsev
The kernel calls ndo_set_rx_mode() callback supplying it will all necessary
info, such as device state flags, multicast mac addresses list and so on.
Since we have only 128 bits to communicate with PF we need to initiate
several requests to PF with small/short operation
From: Vadim Lomovtsev <vadim.lomovt...@cavium.com>
It was found that ethtool provides unexisting module name while
it queries the specified network device for associated driver
information. Then user tries to unload that module by provided
module name and fails.
This happens because e
From: Vadim Lomovtsev
It was found that ethtool provides unexisting module name while
it queries the specified network device for associated driver
information. Then user tries to unload that module by provided
module name and fails.
This happens because ethtool reads value of DRV_NAME macro
1 - 100 of 218 matches
Mail list logo