On Wed, Jan 06, 2021 at 11:33:50AM +0100, Jesper Dangaard Brouer wrote:
> On Tue, 5 Jan 2021 18:43:08 +0100
> Marek Behún wrote:
>
> > On Tue, 5 Jan 2021 18:24:37 +0100
> > Sven Auhagen wrote:
> >
> > > On Tue, Jan 05, 2021 at 06:19:21PM +0100, Ma
On Tue, Dec 01, 2020 at 09:58:52AM +0100, Jesper Dangaard Brouer wrote:
> On Tue, 1 Dec 2020 08:23:23 +
> "Penigalapati, Sandeep" wrote:
>
> > Tested-by: Sandeep Penigalapati
>
> Very happy that you are testing this.
>
> Have you also tested that samples/bpf/ xdp_redirect_cpu program works
From: Sven Auhagen
Since we share the transmit queue with the network stack,
it is possible that we run into a transmit queue timeout.
This will reset the queue.
This happens under high load when XDP is using the
transmit queue pretty much exclusively.
netdev_start_xmit() sets the trans_start
From: Sven Auhagen
Since it is a new XDP implementation change xdp_do_flush_map
to xdp_do_flush.
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1
From: Sven Auhagen
add metasize if it is set in xdp
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net
From: Sven Auhagen
Increase the packet header padding to include double VLAN tagging.
This patch uses a macro for this.
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb.h
From: Sven Auhagen
Add an extack error message when the RX buffer size is too small
for the frame size.
Tested-by: Sandeep Penigalapati
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel
From: Sven Auhagen
The igb XDP xmit back function should only return
defined error codes.
Reported-by: Dan Carpenter
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a
From: Sven Auhagen
This patch series addresses some of the comments that came back
after the igb XDP patch was accepted.
Most of it is code cleanup.
The last patch contains a fix for a tx queue timeout
that can occur when using xdp.
Change from v3:
* extack message on error add netdev
On Wed, Nov 11, 2020 at 11:35:44AM +0100, Paul Menzel wrote:
> Dear Sven,
>
>
> Am 11.11.20 um 11:10 schrieb Sven Auhagen:
> > On Wed, Nov 11, 2020 at 08:11:46AM +0100, Paul Menzel wrote:
>
> > > Am 19.10.20 um 10:05 schrieb sven.auha...@voleatech.
On Wed, Nov 11, 2020 at 08:11:46AM +0100, Paul Menzel wrote:
> Dear Sven,
>
>
> Am 19.10.20 um 10:05 schrieb sven.auha...@voleatech.de:
> > From: Sven Auhagen
> >
> > Add an extack error message when the RX buffer size is too small
> > for the frame
On Wed, Nov 11, 2020 at 08:11:46AM +0100, Paul Menzel wrote:
> Dear Sven,
>
>
> Am 19.10.20 um 10:05 schrieb sven.auha...@voleatech.de:
> > From: Sven Auhagen
> >
> > Add an extack error message when the RX buffer size is too small
> > for the frame
From: Sven Auhagen
Since it is a new XDP implementation change xdp_do_flush_map
to xdp_do_flush.
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1
From: Sven Auhagen
add metasize if it is set in xdp
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net
From: Sven Auhagen
The igb XDP xmit back function should only return
defined error codes.
Reported-by: Dan Carpenter
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a
From: Sven Auhagen
Since we share the transmit queue with the network stack,
it is possible that we run into a transmit queue timeout.
This will reset the queue.
This happens under high load when XDP is using the
transmit queue pretty much exclusively.
netdev_start_xmit() sets the trans_start
From: Sven Auhagen
Add an extack error message when the RX buffer size is too small
for the frame size.
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 12
From: Sven Auhagen
Increase the packet header padding to include double VLAN tagging.
This patch uses a macro for this.
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
Acked-by: Maciej Fijalkowski
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb.h
From: Sven Auhagen
This patch series addresses some of the comments that came back
after the igb XDP patch was accepted.
Most of it is code cleanup.
The last patch contains a fix for a tx queue timeout
that can occur when using xdp.
Change from v2:
* Move SOB line to end
* Remove SOB
On Sun, Oct 18, 2020 at 03:39:51PM +0200, Maciej Fijalkowski wrote:
> On Sat, Oct 17, 2020 at 09:12:32AM +0200, sven.auha...@voleatech.de wrote:
> > From: Sven Auhagen
> >
> > This patch series addresses some of the comments that came back
> > after the igb XDP patch w
On Sun, Oct 18, 2020 at 12:03:36PM -0700, Jakub Kicinski wrote:
> On Sun, 18 Oct 2020 15:39:51 +0200 Maciej Fijalkowski wrote:
> > - next time please specify the tree in the subject that you're targetting
> > this set to land; is it net or net-next? net-next is currently closed so
> > you proba
From: Sven Auhagen
The igb XDP xmit back function should only return
defined error codes.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
b/drivers/net
From: Sven Auhagen
add metasize if it is set in xdp
Signed-off-by: Sven Auhagen
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
---
drivers/net/ethernet/intel/igb/igb_main.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
b
From: Sven Auhagen
This patch series addresses some of the comments that came back
after the igb XDP patch was accepted.
Most of it is code cleanup.
The last patch contains a fix for a tx queue timeout
that can occur when using xdp.
Signed-off-by: Sven Auhagen
Change from v1:
* Drop patch
From: Sven Auhagen
Since it is a new XDP implementation change xdp_do_flush_map
to xdp_do_flush.
Signed-off-by: Sven Auhagen
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion
From: Sven Auhagen
Increase the packet header padding to include double VLAN tagging.
This patch uses a macro for this.
Signed-off-by: Sven Auhagen
Suggested-by: Maciej Fijalkowski
---
drivers/net/ethernet/intel/igb/igb.h | 5 +
drivers/net/ethernet/intel/igb/igb_main.c | 7
From: Sven Auhagen
Add an extack error message when the RX buffer size is too small
for the frame size.
Signed-off-by: Sven Auhagen
Suggested-by: Maciej Fijalkowski
Reviewed-by: Maciej Fijalkowski
---
drivers/net/ethernet/intel/igb/igb_main.c | 12 +++-
1 file changed, 7 insertions
From: Sven Auhagen
Since we share the transmit queue with the slow path,
it is possible that we run into a transmit queue timeout.
This will reset the queue.
This happens under high load when the fast path is using the
transmit queue pretty much exclusively.
By setting the transmit queues
On Wed, Oct 07, 2020 at 11:32:57PM +0200, Maciej Fijalkowski wrote:
> On Wed, Oct 07, 2020 at 05:25:04PM +0200, sven.auha...@voleatech.de wrote:
> > From: Sven Auhagen
> >
> > Also use the new helper function igb_rx_buffer_flip in
> > igb_build_skb/igb_add_rx_frag.
&
On Wed, Oct 07, 2020 at 11:06:15PM +0200, Maciej Fijalkowski wrote:
> On Wed, Oct 07, 2020 at 05:25:01PM +0200, sven.auha...@voleatech.de wrote:
> > From: Sven Auhagen
> >
> > Increase the packet header padding to include double VLAN tagging.
> > This patch uses a macr
From: Sven Auhagen
Also use the new helper function igb_rx_buffer_flip in
igb_build_skb/igb_add_rx_frag.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 87 +--
1 file changed, 35 insertions(+), 52 deletions(-)
diff --git a/drivers/net/ethernet
From: Sven Auhagen
Since we share the transmit queue with the slow path,
it is possible that we run into a transmit queue timeout.
This will reset the queue.
This happens under high load when the fast path is using the
transmit queue pretty much exclusively.
Signed-off-by: Sven Auhagen
From: Sven Auhagen
Increase the packet header padding to include double VLAN tagging.
This patch uses a macro for this.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb.h | 5 +
drivers/net/ethernet/intel/igb/igb_main.c | 7 +++
2 files changed, 8 insertions
From: Sven Auhagen
Since it is a new XDP implementation change xdp_do_flush_map
to xdp_do_flush.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
b/drivers
From: Sven Auhagen
add metasize if it is set in xdp
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
b/drivers/net/ethernet/intel/igb/igb_main.c
index 088f9ddb0093
From: Sven Auhagen
Add an extack error message when the RX buffer size is too small
for the frame size.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 12 +++-
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb
From: Sven Auhagen
The igb XDP xmit back function should only return
defined error codes.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/intel/igb/igb_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c
b/drivers/net
From: Sven Auhagen
This patch series addresses some of the comments that came back
after the igb XDP patch was accepted.
Most of it is code cleanup.
The last patch contains a fix for a tx queue timeout
that can occur when using xdp.
Signed-off-by: Sven Auhagen
Sven Auhagen (7):
igb: XDP
achine:
Intel(R) Atom(TM) CPU C2338 @ 1.74GHz (2 Cores)
2x Intel I211
Routing Original Driver Network Stack: 382 Kpps
Routing XDP Redirect (xdp_fwd_kern): 1.48 Mpps
XDP Drop: 1.48 Mpps
Using XDP we can achieve line rate forwarding even on
an older Intel Atom CPU.
Signed-off-by: Sven Auhagen
---
achine:
Intel(R) Atom(TM) CPU C2338 @ 1.74GHz (2 Cores)
2x Intel I211
Routing Original Driver Network Stack: 382 Kpps
Routing XDP Redirect (xdp_fwd_kern): 1.48 Mpps
XDP Drop: 1.48 Mpps
Using XDP we can achieve line rate forwarding even on
on older Intel Atom CPU.
Signed-off-by: Sven Auhagen
---
achine:
Intel(R) Atom(TM) CPU C2338 @ 1.74GHz (2 Cores)
2x Intel I211
Routing Original Driver Network Stack: 382 Kpps
Routing XDP Redirect (xdp_fwd_kern): 1.48 Mpps
XDP Drop: 1.48 Mpps
Using XDP we can achieve line rate forwarding even on
on older Intel Atom CPU.
Signed-off-by: Sven Auhagen
---
achine:
Intel(R) Atom(TM) CPU C2338 @ 1.74GHz (2 Cores)
2x Intel I211
Routing Original Driver Network Stack: 382 Kpps
Routing XDP Redirect (xdp_fwd_kern): 1.48 Mpps
XDP Drop: 1.48 Mpps
Using XDP we can achieve line rate forwarding even on
on older Intel Atom CPU.
Signed-off-by: Sven Auhagen
---
Add ethtool statistics for XDP.
This patch is a follow up for the mvpp2 XDP patch
upstreamed yesterday.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/marvell/mvpp2/mvpp2.h| 8 +
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 148 +++---
2 files changed, 138 insertions
("mvpp2: percpu buffers")
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2b
On Sun, Jun 14, 2020 at 10:23:43AM +0200, Jesper Dangaard Brouer wrote:
> On Sun, 14 Jun 2020 09:11:28 +0200
> Sven Auhagen wrote:
>
> > The packet header prefetch is at an offset
> > now. Correct the prefetch address.
> >
> > Signed-off-by: Sven Auhagen
On Mon, Jun 15, 2020 at 12:23:20AM +, Matteo Croce wrote:
> On Sun, Jun 14, 2020 at 7:19 AM Sven Auhagen
> wrote:
> >
> > The ethtool rx and tx queue statistics are reporting wrong values.
> > Fix reading out the correct ones.
> >
> > Signed-off-by: Sven
The remove function does not destroy all
BM Pools when per cpu pool is active.
When reloading the mvpp2 as a module the BM Pools
are still active in hardware and due to the bug
have twice the size now old + new.
This eventually leads to a kernel crash.
Signed-off-by: Sven Auhagen
---
drivers
The ethtool rx and tx queue statistics are reporting wrong values.
Fix reading out the correct ones.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2
The packet header prefetch is at an offset
now. Correct the prefetch address.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet/marvell/mvneta.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c
b/drivers/net/ethernet/marvell/mvneta.c
For XDP the MVNETA_SKB_HEADROOM is used as an offset for
the received data.
The MVNETA manual states that the last 3 bits assumed to be 0.
This is currently the case but lets make it explicit in the definition
to prevent future problems.
Signed-off-by: Sven Auhagen
---
drivers/net/ethernet
50 matches
Mail list logo
