free(in);
return err;
}
Reviewed-by: Tariq Toukan
Thanks for your patch.
Tariq
On 2/18/2021 7:10 PM, Tariq Toukan wrote:
On 11/12/2020 6:33 PM, Ido Schimmel wrote:
On Thu, Nov 12, 2020 at 05:54:30PM +0200, Tariq Toukan wrote:
On 11/12/2020 5:46 PM, Ido Schimmel wrote:
On Thu, Nov 12, 2020 at 05:38:44PM +0200, Tariq Toukan wrote:
Hi all,
In the past ~2-3 weeks
On 2/22/2021 9:50 PM, Jesper Dangaard Brouer wrote:
Net-next at commit d310ec03a34e ("Merge tag 'perf-core-2021-02-17')
There is a divide error in drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
where it seems that num_tc_x_num_ch can become zero in a modulo operation:
if (unlikely(t
rr(dev, "rule mirroring mailbox is null\n");
+ mlx4_free_cmd_mailbox(dev, mailbox);
return -EINVAL;
}
memcpy(mailbox->buf, fs_rule->mirr_mbox, fs_rule->mirr_mbox_size);
Reviewed-by: Tariq Toukan
Thanks for your patch.
Tariq
On 11/12/2020 6:33 PM, Ido Schimmel wrote:
On Thu, Nov 12, 2020 at 05:54:30PM +0200, Tariq Toukan wrote:
On 11/12/2020 5:46 PM, Ido Schimmel wrote:
On Thu, Nov 12, 2020 at 05:38:44PM +0200, Tariq Toukan wrote:
Hi all,
In the past ~2-3 weeks, we started seeing the following WARNING and
No real dependency on XPS, but on RX queue mapping, which
is being selected by TLS_DEVICE.
Signed-off-by: Tariq Toukan
Reviewed-by: Maxim Mikityanskiy
---
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5
Compile-in the socket RX queue mapping field and logic when TLS_DEVICE
is enabled. This allows device drivers to pick the recorded socket's
RX queue and use it for streams distribution.
Signed-off-by: Tariq Toukan
Reviewed-by: Maxim Mikityanskiy
---
net/tls/Kconfig | 1 +
1 file chang
protect access to the sk_rx_queue_mapping field, while keeping
the function exposed unconditionally, just like sk_rx_queue_set()
and sk_rx_queue_clear().
Signed-off-by: Tariq Toukan
Reviewed-by: Maxim Mikityanskiy
---
include/net/sock.h | 12 ++--
net/Kconfig| 4
net/core
Hi,
Socket's RX queue mapping logic is useful also for non-XPS use cases.
This series breaks the dependency between the two, introducing a new
kernel config flag SOCK_RX_QUEUE_MAPPING.
Here we select this new kernel flag from TLS_DEVICE, as well as XPS.
Regards,
Tariq
Tariq Toukan (3):
commit message.
Other than that, I think now I'm fine with the patch.
Acked-by: Tariq Toukan
Thanks,
Tariq
CC: Tariq Toukan
CC: Boris Pismenny
Signed-off-by: Kuniyuki Iwashima
---
net/core/sock.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/net/co
-kun...@amazon.co.jp/
CC: Tariq Toukan
CC: Boris Pismenny
Signed-off-by: Kuniyuki Iwashima
---
net/core/sock.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/net/core/sock.c b/net/core/sock.c
index bbcd4b97eddd..cfbd62a5e079 100644
--- a/net/core/sock.c
+
With NETIF_F_HW_TLS_RX packets are decrypted in HW. This cannot be
logically done when RXCSUM offload is off.
Fixes: 14136564c8ee ("net: Add TLS RX offload feature")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
Documentation/networking/tls-offload.rst | 3 +++
net/
ndo_sk_get_lower_dev returns the lower netdev that corresponds to
a given socket.
Additionally, we implement a helper netdev_sk_get_lowest_dev() to get
the lowest one in chain.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/linux/netdevice.h | 4
net/core/dev.c
v_ops calls, introduce and use ndo_sk_get_slave()
to interact directly with the slave netdev.
- Remove bond copy of tlsdev_ops callbacks.
- In TLS module: Use netdev_sk_get_lowest_dev(), give exceptions to some checks
to allow bond support.
Tariq Toukan (8):
net: netdevice: Add operation ndo_
Do not call the tls_dev_ops of upper devices. Instead, ask them
for the proper lowest device and communicate with it directly.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
net/tls/tls_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tls
feature flag is not directly controllable, but just reflects
the offload status based on the logic under bond_sk_check().
Here we just declare RX device offload support, and expose it via the
NETIF_F_HW_TLS_RX flag.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net
In preparation for more cases that call netdev_update_features().
While here, move the features logic to the stage where struct bond
is already updated, and pass it as the only parameter to function
bond_set_xfrm_features().
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers
Hash logic on L3 will be used in a downstream patch for one more use
case.
Take it to a function for a better code reuse.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers/net/bonding/bond_main.c | 16 +++-
1 file changed, 11 insertions(+), 5 deletions(-)
diff
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers/net/bonding/bond_main.c | 93 +
include/net/bonding.h | 2 +
2 files changed, 95 insertions(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 75
t the lower devs, there is no way for the bond interface
to disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by:
In the tls_dev_event handler, ignore tlsdev_ops requirement for bond
interfaces, they do not exist as the interaction is done directly with
the lower device.
Also, make the validate function pass when it's called with the upper
bond interface.
Signed-off-by: Tariq Toukan
Reviewed-by:
On 1/17/2021 4:54 AM, Jakub Kicinski wrote:
On Thu, 14 Jan 2021 20:01:32 +0200 Tariq Toukan wrote:
As the bond interface is being bypassed by the TLS module, interacting
directly against the slaves, there is no way for the bond interface to
disable its device offload capabilities, as long as
On 1/17/2021 4:51 AM, Jakub Kicinski wrote:
On Thu, 14 Jan 2021 20:01:28 +0200 Tariq Toukan wrote:
ndo_sk_get_slave returns the slave that corresponds to a given socket.
Additionally, we implement a helper netdev_sk_get_lowest_dev() to get
the lowest slave netdevice.
Please don't ad
ned-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers/net/bonding/bond_main.c | 93 +
include/net/bonding.h | 2 +
2 files changed, 95 insertions(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8b
ndo_sk_get_slave returns the slave that corresponds to a given socket.
Additionally, we implement a helper netdev_sk_get_lowest_dev() to get
the lowest slave netdevice.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/linux/netdevice.h | 4
net/core/dev.c
odule: Use netdev_sk_get_lowest_dev(), give exceptions to some checks
to allow bond support.
Tariq Toukan (8):
net: netdevice: Add operation ndo_sk_get_slave
net/bonding: Take IP hash logic into a helper
net/bonding: Implement ndo_sk_get_slave
net/bonding: Take update_features call out of XFRM func
Hash logic on L3 will be used in a downstream patch for one more use
case.
Take it to a function for a better code reuse.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers/net/bonding/bond_main.c | 16 +++-
1 file changed, 11 insertions(+), 5 deletions(-)
diff
re is no way for the bond interface to
disable its device offload capabilities, as long as the mode/policy
config allows it.
Hence, the feature flag is not directly controllable, but just reflects
the current offload status based on the logic under bond_sk_check().
Signed-off-by: Tariq Toukan
Rev
In preparation for more cases that call netdev_update_features().
While here, move the features logic to the stage where struct bond
is already updated, and pass it as the only parameter to function
bond_set_xfrm_features().
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
drivers
feature flag is not directly controllable, but just reflects
the offload status based on the logic under bond_sk_check().
Here we just declare RX device offload support, and expose it via the
NETIF_F_HW_TLS_RX flag.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net/bonding.h
Do not call the tls_dev_ops of upper devices. Instead, ask them
for the proper slave and communicate with it directly.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
net/tls/tls_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tls/tls_device.c b/net
In the tls_dev_event handler, ignore tlsdev_ops requirement for bond
interfaces, they do not exist as the interaction is done directly with
the slave.
Also, make the validate function pass when it's called with the upper
bond interface.
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pis
CSUM) is set.
Fixes: ae0b04b238e2 ("net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled")
Signed-off-by: Tariq Toukan
Reported-by: Rohit Maheshwari
Reviewed-by: Maxim Mikityanskiy
---
Documentation/networking/tls-offload.rst | 2 +-
net/core/dev.c |
On 1/13/2021 5:35 AM, Alexander Duyck wrote:
On Tue, Jan 12, 2021 at 6:43 PM rohit maheshwari wrote:
On 07/01/21 12:47 AM, Jakub Kicinski wrote:
On Wed, 6 Jan 2021 23:23:27 +0530 Rohit Maheshwari wrote:
Mandating NETIF_F_HW_CSUM to enable TLS offload feature is wrong.
And it broke tls o
On 1/5/2021 10:29 PM, Jakub Kicinski wrote:
On Tue, 5 Jan 2021 22:27:49 +0530 Rohit Maheshwari wrote:
advertise NETIF_F_HW_CSUM instead of protocol specific values of
NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM. This change is added long
back in other drivers. This issue is seen recently when TLS
@@ -314,7 +314,7 @@ struct mlx4_en_tx_ring {
struct mlx4_en_rx_desc {
/* actual number of entries depends on rx ring stride */
- struct mlx4_wqe_data_seg data[0];
+ struct mlx4_wqe_data_seg data[];
};
struct mlx4_en_rx_ring {
Reviewed-by: Tariq Toukan
Thanks.
ndo_sk_get_slave returns a slave given a socket.
Additionally, we implement a helper netdev_sk_get_lowest_dev()
to get the lowest slave netdevice.
Signed-off-by: Tariq Toukan
---
include/linux/netdevice.h | 4
net/core/dev.c| 32
2 files
In the tls_dev_event handler, ignore tls_dev_ops requirement for bond
interfaces, they do not exist as the interaction is done directly with
the slave.
Also, make the validate function pass when it's called with the upper
bond interface.
Signed-off-by: Tariq Toukan
---
net/tls/tls_dev
its
own,
communication is done via the bond and not directly to the lowest device.
Regards,
Tariq
Tariq Toukan (6):
net: netdevice: Add operation ndo_sk_get_slave
net/tls: Device offload to use lowest netdevice in chain
net/tls: Except bond interface from some TLS checks
net/bonding:
Hash logic on L3 will be used in a downstream patch for one
more use case.
Take it to a function for a better code reuse.
Signed-off-by: Tariq Toukan
---
drivers/net/bonding/bond_main.c | 16 +++-
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/drivers/net/bonding
Support L3/4 sockets only, with xmit_hash_policy==LAYER34
and modes xor/802.3ad.
Signed-off-by: Tariq Toukan
---
drivers/net/bonding/bond_main.c | 90 +
1 file changed, 90 insertions(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding
Do not call the tls_dev_ops of upper devices. Instead, ask them
for the proper slave and communicate with it directly.
Signed-off-by: Tariq Toukan
---
net/tls/tls_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index
same exact slave for all the socket's SKBs.
We keep the bond feature bit independent from the slaves bits.
In case a non-capable slave is picked, the socket falls-back to
SW kTLS.
netdev_update_features() is taken out of the XFRM function so it
is called only once (if needed).
Signed-off-by: Ta
With NETIF_F_HW_TLS_TX packets are encrypted in HW. This cannot be
logically done when HW_CSUM offload is off.
Fixes: 2342a8512a1e ("net: Add TLS TX offload features")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
Documentation/networking/tls-offload.rst | 8 +++-
Roy Novich
Signed-off-by: Tariq Toukan
---
ethtool.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/ethtool.c b/ethtool.c
index 1d9067e774af..5cc875c64591 100644
--- a/ethtool.c
+++ b/ethtool.c
@@ -3287,7 +3287,7 @@ static int do_sset(struct cmd_co
c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
Reviewed-by: Tariq Toukan
Thanks.
lanox/mlx5/core/en.h |2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c |2 +-
drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |6 +-
3 files changed, 3 insertions(+), 7 deletions(-)
Reviewed-by: Tariq Toukan
Thanks.
must reduce the mask to the effective set,
which means that checking the affinity mask itself does not really tell
about the actual target CPUs.
Signed-off-by: Thomas Gleixner
Cc: Tariq Toukan
Cc: "David S. Miller"
Cc: Jakub Kicinski
Cc: netdev@vger.kernel.org
Cc: linux-r...@vger.
encapsulation does not mean that the kernel has no
limits.
Retrieve a pointer to the affinity mask itself and use that. It's still
using an interface which is usually not for random drivers, but definitely
less hideous than the previous hack.
Signed-off-by: Thomas Gleixner
Cc: Tariq Toukan
Cc: &qu
Hi,
This patchset by Moshe contains fixes to the mlx4 Eth driver,
addressing issues in restart flow.
Patch 1 protects the restart task from being rescheduled while active.
Please queue for -stable >= v2.6.
Patch 2 reconstructs SQs stuck in error state, and adds prints for improved
debuggabili
he Shemesh
Signed-off-by: Tariq Toukan
---
.../net/ethernet/mellanox/mlx4/en_netdev.c| 20 ---
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 ++-
2 files changed, 19 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
b/drivers/ne
and WQE for debug.
Fixes: bd2f631d7c60 ("net/mlx4_en: Notify user when TX ring in error state")
Signed-off-by: Moshe Shemesh
Signed-off-by: Tariq Toukan
---
.../net/ethernet/mellanox/mlx4/en_netdev.c| 1 +
drivers/net/ethernet/mellanox/mlx4/en_tx.c| 40 +++
d
From: Tariq Toukan
All usages of the definition MAX_MSIX_P_PORT were removed.
It's not in use anymore. Remove it.
Signed-off-by: Tariq Toukan
Reviewed-by: Moshe Shemesh
---
include/linux/mlx4/device.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/linux/mlx4/device.h b/in
On 11/25/2020 11:27 AM, Eric Dumazet wrote:
On Wed, Nov 25, 2020 at 10:06 AM Tariq Toukan wrote:
On 11/25/2020 5:25 AM, Herbert Xu wrote:
On Tue, Nov 24, 2020 at 11:48:35AM +0100, Eric Dumazet wrote:
Well, the 'increment' part was suggesting the function was adding
flags, no
On 11/25/2020 5:25 AM, Herbert Xu wrote:
On Tue, Nov 24, 2020 at 11:48:35AM +0100, Eric Dumazet wrote:
Well, the 'increment' part was suggesting the function was adding
flags, not removing them.
The idea of the increment part is that we're adding a constituent
device, not that we're adding
On 11/23/2020 8:20 PM, Jakub Kicinski wrote:
On Sun, 22 Nov 2020 14:48:04 +0200 Tariq Toukan wrote:
On 11/19/2020 6:38 PM, Jakub Kicinski wrote:
On Thu, 19 Nov 2020 17:59:38 +0200 Tariq Toukan wrote:
On 11/19/2020 2:02 AM, Jakub Kicinski wrote:
On Sun, 15 Nov 2020 15:42:49 +0200 Tariq
On 11/24/2020 12:48 PM, Eric Dumazet wrote:
On Mon, Nov 23, 2020 at 5:15 PM Tariq Toukan wrote:
On 11/23/2020 4:55 PM, Eric Dumazet wrote:
On Mon, Nov 23, 2020 at 3:13 PM Tariq Toukan wrote:
Calling netdev_increment_features() on upper/master device from
netdev_add_tso_features
On 11/23/2020 4:55 PM, Eric Dumazet wrote:
On Mon, Nov 23, 2020 at 3:13 PM Tariq Toukan wrote:
Calling netdev_increment_features() on upper/master device from
netdev_add_tso_features() implies unintentional clearance of ALL_FOR_ALL
features supported by all slaves. Fix it by passing
aster")
Signed-off-by: Tariq Toukan
---
include/linux/netdevice.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Hi,
I know that netdev_increment_features() does not set any feature that's
unmasked in the mask argument.
I wonder why it can clear them though, was it meant to be li
#x27; defined but not used [-Wunused-function]
47 | static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec,
struct sock *sk)
Fixes: 5229a96e59ec ("net/mlx5e: Accel, Expose flow steering API for rules
add/del")
Signed-off-by: Randy Dunlap
Reported-by: kernel test robot
Cc: Saeed Mah
On 11/19/2020 6:38 PM, Jakub Kicinski wrote:
On Thu, 19 Nov 2020 17:59:38 +0200 Tariq Toukan wrote:
On 11/19/2020 2:02 AM, Jakub Kicinski wrote:
On Sun, 15 Nov 2020 15:42:49 +0200 Tariq Toukan wrote:
This series opens TLS TX HW offload for bond interfaces.
This allows bond interfaces to
lop,
vhcr->in_param, &vhcr->out_param);
+ break;
default:
break;
Reviewed-by: Tariq Toukan
Thanks for your patch.
On 11/19/2020 2:02 AM, Jakub Kicinski wrote:
On Sun, 15 Nov 2020 15:42:49 +0200 Tariq Toukan wrote:
This series opens TLS TX HW offload for bond interfaces.
This allows bond interfaces to benefit from capable slave devices.
The first patch adds real_dev field in TLS context structure, and
Performance analysis counters are maintained under the MLX4_EN_PERF_STAT
definition, which is never set.
Clean them up, with all related structures and logic.
Signed-off-by: Tariq Toukan
Reviewed-by: Moshe Shemesh
---
.../net/ethernet/mellanox/mlx4/en_netdev.c| 1 -
drivers/net/ethernet
value reported at max_mcast_qp_attach.
3. Driver to init FW with multicast hash size of zero.
Fixes: a40ded604365 ("net/mlx4_core: Add masking for a few queries on HCA caps")
Signed-off-by: Aya Levin
Reviewed-by: Moshe Shemesh
Reviewed-by: Eran Ben Elisha
Signed-off-by: Ta
++-
net/core/dev.c| 2 +-
net/core/xdp.c| 3 ++-
net/xdp/xsk.c | 1 +
29 files changed, 47 insertions(+), 33 deletions(-)
Acked-by: Tariq Toukan
For the mlx4/5 parts.
Thanks,
Tariq
,
so we restrict the offload support to it:
((mode == balance-xor) or (mode == 802.3ad))
and xmit_hash_policy == layer3+4.
Regards,
Tariq
Tariq Toukan (2):
net/tls: Add real_dev field to TLS context
bond: Add TLS TX offload support
drivers/net/bonding/bond_main.c
m the slaves bits.
In case a non-capable slave is picked, the socket falls-back to
SW kTLS.
Signed-off-by: Tariq Toukan
Reviewed-by: Maxim Mikityanskiy
Reviewed-by: Boris Pismenny
---
drivers/net/bonding/bond_main.c| 203 -
drivers/net/bonding/bond_options.c
Save the real device for the TLS context.
Upper devices that support TLS offload should init real_dev
to point to the slave dev in tls_dev_add().
Lower device drivers should work only against real_dev.
Signed-off-by: Tariq Toukan
Reviewed-by: Maxim Mikityanskiy
Reviewed-by: Boris Pismenny
instead.
Fixes: ed9b7646b06a ("net/tls: Add asynchronous resync")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net/tls.h| 16 +++-
net/tls/tls_device.c | 37 +++--
2 files changed, 42 insertions(+), 11 deletions(-)
H
On 11/12/2020 5:46 PM, Ido Schimmel wrote:
On Thu, Nov 12, 2020 at 05:38:44PM +0200, Tariq Toukan wrote:
Hi all,
In the past ~2-3 weeks, we started seeing the following WARNING and traces
in our regression testing systems, almost every day.
Reproduction is not stable, and not isolated to a
Hi all,
In the past ~2-3 weeks, we started seeing the following WARNING and
traces in our regression testing systems, almost every day.
Reproduction is not stable, and not isolated to a specific test, so it's
hard to bisect.
Any idea what could this be?
Or what is the suspected offending pa
instead.
Fixes: ed9b7646b06a ("net/tls: Add asynchronous resync")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net/tls.h| 19 ++-
net/tls/tls_device.c | 35 +--
2 files changed, 43 insertions(+), 11 deletions(-)
H
On 11/11/2020 1:44 AM, Jakub Kicinski wrote:
On Sun, 8 Nov 2020 16:43:09 +0200 Tariq Toukan wrote:
@@ -528,3 +528,7 @@ Drivers should ignore the changes to TLS the device feature
flags.
These flags will be acted upon accordingly by the core ``ktls`` code.
TLS device feature flags only
On 11/9/2020 9:07 AM, kaixuxia wrote:
On 2020/11/8 16:20, Tariq Toukan wrote:
On 11/7/2020 8:53 AM, xiakaixu1...@gmail.com wrote:
From: Kaixu Xia
Fix the following coccinelle warnings:
Hi Kaixu,
Which coccinelle version gave this warning?
Hi Tariq,
The version is coccinelle
On 11/5/2020 6:00 PM, Jakub Kicinski wrote:
On Thu, 5 Nov 2020 15:22:53 +0200 Tariq Toukan wrote:
On 11/4/2020 11:25 PM, Jakub Kicinski wrote:
On Wed, 4 Nov 2020 12:21:41 +0200 Tariq Toukan wrote:
With NETIF_F_HW_TLS_TX packets are encrypted in HW. This cannot be
logically done when
With NETIF_F_HW_TLS_TX packets are encrypted in HW. This cannot be
logically done when HW_CSUM offload is off.
Fixes: 2342a8512a1e ("net: Add TLS TX offload features")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
Documentation/networking/tls-offload.rst | 4
net/
On 11/7/2020 8:53 AM, xiakaixu1...@gmail.com wrote:
From: Kaixu Xia
Fix the following coccinelle warnings:
Hi Kaixu,
Which coccinelle version gave this warning?
./drivers/net/ethernet/mellanox/mlx4/en_rx.c:687:1-17: WARNING: Assignment of
0/1 to bool variable
Reported-by: Tosk Robot
On 11/4/2020 11:25 PM, Jakub Kicinski wrote:
On Wed, 4 Nov 2020 12:21:41 +0200 Tariq Toukan wrote:
With NETIF_F_HW_TLS_TX packets are encrypted in HW. This cannot be
logically done when HW_CSUM offload is off.
Right. Do you expect drivers to nack clearing NETIF_F_HW_TLS_TX when
there are
With NETIF_F_HW_TLS_TX packets are encrypted in HW. This cannot be
logically done when HW_CSUM offload is off.
Fixes: 2342a8512a1e ("net: Add TLS TX offload features")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
net/core/dev.c | 5 +
1 file changed, 5 inserti
(enum mlx4_resource rt)
case RES_FS_RULE: return "RES_FS_RULE";
case RES_XRCD: return "RES_XRCD";
default: return "Unknown resource type !!!";
- };
+ }
}
static void rem_slave_vlans(struct mlx4_dev *dev, int slave);
Reviewed-by: Tariq Toukan
Thanks,
Tariq
sing
> > - do not try to recycle TX packets to the RX cache
> >
> > Signed-off-by: Jonathan Lemon
>
> Tariq, Saeed - how does this look to you?
Reviewed-by: Tariq Toukan
Thanks,
Tariq
Extend the workqueue API so that singlethread workqueues can be exposed
in sysfs. Guarantee max_active is 1 by turning it read-only.
This allows admins to control the cpumask of a workqueue, and apply
the desired system cpu separation/isolation policy.
Signed-off-by: Tariq Toukan
---
drivers
On 9/14/2020 11:02 PM, Jakub Kicinski wrote:
On Sun, 13 Sep 2020 13:12:05 +0300 Tariq Toukan wrote:
2. When MLX4_EN_PERF_STAT is not defined, we should totally remove the
local variable declaration, not only its usage.
I was actually wondering about this when working on the pause stat
On 9/13/2020 4:22 AM, David Miller wrote:
From: Luo Jiaxing
Date: Sat, 12 Sep 2020 16:08:15 +0800
We found a set but not used variable 'ring_cons' in mlx4_en_xmit(), it will
cause a warning when build the kernel. And after checking the commit record
of this function, we found that it was in
rt, NULL);
+ else if (!IS_ENABLED(CONFIG_MLX4_INFINIBAND) &&
+dev->caps.port_type[port] == MLX4_PORT_TYPE_IB)
+ devlink_port_type_ib_set(&info->devlink_port, NULL);
+
info->dev = dev;
info->port = port;
if (!mlx4_is_slave(dev)) {
Reviewed-by: Tariq Toukan
Many device drivers use the same prefetch code structure to
deal with small L1 cacheline size.
Take this code into a function and call it from the drivers.
Suggested-by: Jakub Kicinski
Signed-off-by: Tariq Toukan
Reviewed-by: Saeed Mahameed
---
drivers/net/ethernet/chelsio/cxgb3/sge.c
A single cacheline might not contain the packet header for
small L1_CACHE_BYTES values.
Use net_prefetch() as it issues an additional prefetch
in this case.
Signed-off-by: Tariq Toukan
Reviewed-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c| 4 ++--
drivers/net
A single cacheline might not contain the packet header for
small L1_CACHE_BYTES values.
Use net_prefetch() as it issues an additional prefetch
in this case.
Signed-off-by: Tariq Toukan
Reviewed-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +-
1 file changed, 1
t-for-davem-20200824' of
git://git.open-mesh.org/linux-merge
Thanks,
Tariq.
Tariq Toukan (3):
net: Take common prefetch code structure into a function
net/mlx5e: RX, Add a prefetch command for small L1_CACHE_BYTES
net/mlx4_en: RX, Add a prefetch command for small L1_CACHE_BYTES
d
On 7/9/2020 4:58 PM, Tariq Toukan wrote:
On 7/9/2020 4:18 AM, Jakub Kicinski wrote:
Convert to new infra, make use of the ability to sleep in the callback.
Signed-off-by: Jakub Kicinski
---
.../net/ethernet/mellanox/mlx4/en_netdev.c | 107 --
drivers/net/ethernet
On 7/9/2020 4:18 AM, Jakub Kicinski wrote:
Convert to new infra, make use of the ability to sleep in the callback.
Signed-off-by: Jakub Kicinski
---
.../net/ethernet/mellanox/mlx4/en_netdev.c| 107 --
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 -
2 files chan
On 6/28/2020 12:17 AM, Saeed Mahameed wrote:
From: Boris Pismenny
This reverts commit b3ae2459f89773adcbf16fef4b68deaaa3be1929.
Revert the force resync API.
Not in use. To be replaced by a better async resync API downstream.
Signed-off-by: Boris Pismenny
Signed-off-by: Tariq Toukan
return -ENOMEM;
tls->rx_wq = create_singlethread_workqueue("mlx5e_tls_rx");
- if (!tls->rx_wq)
+ if (!tls->rx_wq) {
+ kfree(tls);
return -ENOMEM;
+ }
priv->tls = tls;
return 0;
Reviewed-by: Tariq Toukan
Thanks.
_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) |
-(len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
+((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
rx_ctx->resync_async->loglen = 0;
}
Reviewed-by: Tariq Toukan
Thanks!
property guarantee for device-offloaded TLS sockets.
Remove the call to sk_tx_queue_clear() in sk_set_socket(), and add it
explicitly only where needed.
Fixes: e022f0b4a03f ("net: Introduce sk_tx_queue_mapping")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net/
On 6/22/2020 7:56 PM, Eric Dumazet wrote:
On 6/22/20 9:24 AM, Tariq Toukan wrote:
On 6/22/2020 6:53 PM, Eric Dumazet wrote:
On 6/21/20 7:09 AM, Tariq Toukan wrote:
sock_orphan() call to sk_set_socket() implies clearing the sock TX queue.
This might cause unexpected out-of-order
On 6/22/2020 6:53 PM, Eric Dumazet wrote:
On 6/21/20 7:09 AM, Tariq Toukan wrote:
sock_orphan() call to sk_set_socket() implies clearing the sock TX queue.
This might cause unexpected out-of-order transmit, as outstanding packets
can pick a different TX queue and bypass the ones already
t;net: Introduce sk_tx_queue_mapping")
Signed-off-by: Tariq Toukan
Reviewed-by: Boris Pismenny
---
include/net/sock.h | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
Please queue for -stable.
diff --git a/include/net/sock.h b/include/net/sock.h
index c53cc42b5ab9..23e43f3d7
On 6/2/2020 9:31 PM, Jakub Kicinski wrote:
On Tue, 2 Jun 2020 14:32:44 +0300 Tariq Toukan wrote:
On 6/2/2020 1:12 AM, Jakub Kicinski wrote:
This is a rare corner case anyway, where more than 1k tcp
connections sharing the same RX ring will request resync at the
same exact moment.
IDK
1 - 100 of 784 matches
Mail list logo
