- Free ILT lines used for XRC-SRQ's contexts.
- Free XRCD bitmap
Fixes: b8204ad878ce7 ("qed: changes to ILT to support XRC")
Fixes: 7bfb399eca460 ("qed: Add XRC to RoCE")
Signed-off-by: Michal Kalderon
Signed-off-by: Yuval Basson
---
drivers/net/ethernet/
> From: Yuval Basson
> Date: Tue, 19 May 2020 23:51:26 +0300
>
> > @@ -1748,24 +1839,26 @@ static int qed_rdma_modify_srq(void
> *rdma_cxt,
> > u16 opaque_fid, srq_id;
> > struct qed_bmap *bmap;
> > u32 returned_id;
> > + u16 offset;
This patch adds support for configuring XRC and provides the necessary
APIs for rdma upper layer driver (qedr) to enable the XRC feature.
Yuval Bason (2):
qed: changes to ILT to support XRC
qed: Add XRC to RoCE
drivers/net/ethernet/qlogic/qed/qed_cxt.c | 60 ++--
drivers/net
anups if XRC bitmpas allocation fail.
Signed-off-by: Michal Kalderon
Signed-off-by: Yuval Bason
---
drivers/net/ethernet/qlogic/qed/qed_rdma.c | 145 +
drivers/net/ethernet/qlogic/qed/qed_rdma.h | 19
drivers/net/ethernet/qlogic/qed/qed_roce.c | 29 +
First ILT page for TSDM client is allocated for XRC-SRQ's.
For regular SRQ's skip first ILT page that is reserved for
XRC-SRQ's.
Signed-off-by: Michal Kalderon
Signed-off-by: Yuval Bason
---
drivers/net/ethernet/qlogic/qed/qed_cxt.c | 60 +-
drive
First ILT page for TSDM client is allocated for XRC-SRQ's.
For regular SRQ's skip first ILT page that is reserved for
XRC-SRQ's.
Signed-off-by: Yuval Bason
---
drivers/net/ethernet/qlogic/qed/qed_cxt.c | 60 +-
drivers/net/ethernet/qlogic/qed/
-by: Michal Kalderon
Signed-off-by: Yuval Bason
---
drivers/net/ethernet/qlogic/qed/qed_rdma.c | 137 +
drivers/net/ethernet/qlogic/qed/qed_rdma.h | 19
drivers/net/ethernet/qlogic/qed/qed_roce.c | 29 ++
include/linux/qed/qed_rdma_if.h| 19
This patch adds support for configuring XRC and provides the necessary
APIs for rdma upper layer driver (qedr) to enable the XRC feature.
Yuval Bason (2):
qed: changes to ILT to support XRC.
qed: Add XRC to RoCE.
drivers/net/ethernet/qlogic/qed/qed_cxt.c | 62 +++--
drivers/net
ot;,
"pf": 0,
"vf": 0
}
}
}
$ devlink vdev show pci/:03:00.0/1
pci/:03:00.0/1: flavour pcivf pf 0 vf 0
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
include/net/devlink.h| 17
include/uapi/linux/devlink.h | 8 ++
net/core
Add devlink vdev creation to represent VFs, and implement hw_addr
get/set.
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
drivers/net/netdevsim/Makefile| 2 +-
drivers/net/netdevsim/dev.c | 9 ++-
drivers/net/netdevsim/netdevsim.h | 10
drivers/net/netdevsim/vdev.c
/:03:00.0/1": {
"flavour": "pcivf",
"pf": 0,
"vf": 0,
"port_index": 1,
"hw_addr": "00:23:35:af:35:34"
}
}
}
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
incl
Currently there is no limit to the number of VFs netdevsim can enable.
Vdevs that represent VFs can exist and be configured before user enabled
them.
max_vfs defines the number of vdevs the driver should create.
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
drivers/net/netdevsim/bus.c
.
$ devlink dev show
pci/:03:00.0
$ devlink vdev show
pci/:03:00.0/0
pci/:03:00.0/1
Signed-off-by: Yuval Avnery
Suggested-by: Parav Pandit
Acked-by: Jiri Pirko
---
include/net/devlink.h| 17 +++
include/uapi/linux/devlink.h | 7 +
net/core/devlink.c | 255
Test will assign hw_addr to all registered vdevs and query it.
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
.../drivers/net/netdevsim/devlink.sh | 55 ++-
1 file changed, 53 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/drivers/net
Add vdev creation and implement get/set ops for vdev hw_addr.
Add vdev linkage to devlink port registration.
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
.../net/ethernet/mellanox/mlx5/core/devlink.c | 91 +++
.../net/ethernet/mellanox/mlx5/core/devlink.h | 5
{
"vdev": {
"pci/:03:00.0/1": {
"flavour": "pcivf",
"pf": 0,
"vf": 0,
"port_index": 1,
"hw_addr": "00:23:35:af:35:34"
}
}
}
Patches 1-5 adds devlink support for vdev.
Patches 6-7 adds netdevsim implementation and test.
Patch 9 adds mlx5 vdev creation and hw_addr get/set.
Yuval Avnery (9):
devlink: Introduce vdev
devlink: Add PCI attributes support for vdev
devlink: Add port with vdev register support
d
th netdev ens2f0_0 flavour pcivf pfnum 0 vfnum 0
vdev_index 1
Signed-off-by: Yuval Avnery
Acked-by: Jiri Pirko
---
include/net/devlink.h | 5
net/core/devlink.c| 53 +++
2 files changed, 54 insertions(+), 4 deletions(-)
diff --git a/include/
Hello
My name is Yuval Rose. I have an urgent lucrative business
opportunity for you worth over 15 Milli0n US D0llars. I got your
details on the internet when I was searching for a reliable
person that can handle this deal and I believe you can handle it.
Waiting for your speedy reply for
On Wed, May 15, 2019 at 07:36:26PM +0300, Leon Romanovsky wrote:
> On Wed, May 15, 2019 at 06:30:51PM +0300, Yuval Shaia wrote:
> > On Tue, May 14, 2019 at 03:23:21PM +0300, Leon Romanovsky wrote:
> > > This is a call for proposals for the 4th RDMA mini-summit at the Li
On Tue, May 14, 2019 at 03:23:21PM +0300, Leon Romanovsky wrote:
> This is a call for proposals for the 4th RDMA mini-summit at the Linux
> Plumbers Conference in Lisbon, Portugal, which will be happening on
> September 9-11h, 2019.
>
> We are looking for topics with focus on active audience discu
This header is not in use - remove it.
Signed-off-by: Yuval Shaia
---
net/core/dev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b67f2aa59dd..21a8205a7896 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -131,7 +131,6 @@
#include
#include
priv argument is not used by the function, delete it.
Fixes: a89842811ea98 ("net/mlx5e: Merge per priority stats groups")
Signed-off-by: Yuval Shaia
---
v1 -> v2:
* Remove blank line as pointed by Leon.
v2 -> v3:
* Change prefix to mlx5e
---
drivers/net/ethern
On Thu, Aug 16, 2018 at 09:41:34AM +0300, Gal Pressman wrote:
> On 15-Aug-18 18:08, Yuval Shaia wrote:
> > priv argument is not used by the function, delete it.
> >
> > Fixes: a89842811ea98 ("net/mlx5e: Merge per priority stats groups")
> > Signed-off-by: Yu
priv argument is not used by the function, delete it.
Fixes: a89842811ea98 ("net/mlx5e: Merge per priority stats groups")
Signed-off-by: Yuval Shaia
---
v1 -> v2:
* Remove blank line as pointed by Leon.
---
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 4 ++--
1 fi
priv argument is not used by the function, delete it.
Fixes: a89842811ea98 ("net/mlx5e: Merge per priority stats groups")
Signed-off-by: Yuval Shaia
---
drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/d
; Fixes: 2a5e7a1344f4 ("net/mlx5e: Add dcbnl dscp to priority support")
> Signed-off-by: Huy Nguyen
> Cc: Yuval Shaia
> Reviewed-by: Parav Pandit
> Signed-off-by: Saeed Mahameed
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 --
> .../ethernet/mellanox/m
parent);
> - priv->dev->dev_id = port - 1;
Correct me if i'm wrong here but besides some changes in commit message
looks like patch 1/3 is the same as 2/3, isn't it?
Yuval
> priv->dev->dev_port = port - 1;
>
> result = ib_query_port(hca, port, &attr);
> --
> 2.18.0
>
Add dcbnl dscp to priority support")
> Signed-off-by: Huy Nguyen
> Cc: Yuval Shaia
> Reviewed-by: Parav Pandit
> Signed-off-by: Saeed Mahameed
FWIW:
Reviewed-by: Yuval Shaia
Tested-by: Yuval Shaia
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 --
>
> From: Jason Gunthorpe [mailto:j...@ziepe.ca]
> Sent: Monday, July 9, 2018 7:42 PM
>
> On Wed, May 30, 2018 at 04:11:37PM +0300, Yuval Bason wrote:
> > This patch adds support for configuring SRQ and provides the necessary
> > APIs for rdma upper layer driver (qedr) t
This patch adds support for configuring SRQ and provides the necessary
APIs for rdma upper layer driver (qedr) to enable the SRQ feature.
Signed-off-by: Michal Kalderon
Signed-off-by: Ariel Elior
Signed-off-by: Yuval Bason
---
Changes from v1:
- sparse warnings
- replace memset
From: Leon Romanovsky [mailto:l...@kernel.org]
Sent: Thursday, May 31, 2018 8:33 PM
> On Wed, May 30, 2018 at 04:11:37PM +0300, Yuval Bason wrote:
> > This patch adds support for configuring SRQ and provides the necessary
> > APIs for rdma upper layer driver (qedr) to enable
This patch adds support for configuring SRQ and provides the necessary
APIs for rdma upper layer driver (qedr) to enable the SRQ feature.
Signed-off-by: Michal Kalderon
Signed-off-by: Ariel Elior
Signed-off-by: Yuval Bason
---
drivers/net/ethernet/qlogic/qed/qed_cxt.c | 5 +-
drivers/net
> Tx-timeout mostly happens due to some issue in the device. In such cases,
> debug dump would be helpful for identifying the cause of the issue.
> This patch adds support to spill debug data during the Tx timeout. Here
> bnx2x_panic_dump() API is used instead of bnx2x_panic(), since we still
> wan
On Thu, May 10, 2018 at 09:02:26AM +0200, Christophe JAILLET wrote:
> If an error occurs, 'mlx4_en_destroy_netdev()' is called.
> It then calls 'mlx4_en_free_resources()' which does the needed resources
> cleanup.
>
> So, doing some explicit kfree in the error handling path would lead to
> some do
ng 'netdev_tx_t' in this driver too.
>
> Signed-off-by: Luc Van Oostenryck
Reviewed-by: Yuval Shaia
> ---
> drivers/net/ethernet/micrel/ks8851_mll.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/micrel/ks8851_mll
uot;control_action": {
Relocate the open/close of the JSON object to declare the object only
for the case that needs it.
Signed-off-by: Yuval Mintz
---
tc/m_action.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/tc/m_action.c b/tc/m_action.c
index 2f85d35..8993b93 1
On Mon, Mar 26, 2018 at 03:13:47AM -0700, Sudarsana Reddy Kalluru wrote:
> This patch adds the required driver support for updating the flash or
> non volatile memory of the adapter. At highlevel, flash upgrade comprises
> of reading the flash images from the input file, validating the images and
>
On Mon, Mar 26, 2018 at 03:13:45AM -0700, Sudarsana Reddy Kalluru wrote:
> This patch add support for populating the flash image attributes.
s/add/adds/
[...]
> -int qed_mcp_bist_nvm_test_get_image_att(struct qed_hwfn *p_hwfn,
> - struct qed_ptt *p_ptt,
> -
Fix use-after-free
Besides that - lgtm.
Reviewed-by: Yuval Shaia
> ---
> drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
> b/drivers/net/e
On Tue, Mar 13, 2018 at 06:13:45PM +0200, Yuval Shaia wrote:
> On Tue, Mar 13, 2018 at 05:07:22PM +0200, Liran Alon wrote:
> > Before this commit, dev_forward_skb() always cleared packet's
> > per-network-namespace info. Even if the packet doesn't cross
> > network n
bedit mark 1337
> tc filter add dev veth-b parent : basic match 'meta(nf_mark eq 1337)'
> action simple "skb->mark 1337!"
> dmesg -C
> ping 12.0.0.2
> dmesg
>
> Before this change, the above will print nothing to dmesg.
> After this change, "s
t; >
> > Hm. I'm agree with you. This is hot path, and mroute sockets created from
> userspace
> > will delay userspace tasks close() and exit(). Since there may be many such
> sockets,
> > we may get a zombie task, which can't be reaped for ages. This slows down
> - /* Free Task CXT */
> + /* Free Task CXT ( Intentionally RoCE as task-id is shared between
> + * RoCE and iWARP
> + */
Broken parenthesis In comment...
Now that both ipmr and ip6mr are using the same mr_table structure,
we can have a common function to allocate & initialize a new instance.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute_base.h | 17 +
net/ipv4/ipmr.c
With the exception of the final dump, ipmr and ip6mr have the exact same
seq logic for traversing a given mr_table. Refactor that code and make
it common.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute_base.h | 69
net/ipv4
]
RFC -> v1:
- Corrected support for CONFIG_IP{,V6}_MROUTE_MULTIPLE_TABLES
- Addressed a couple of kbuild test robot issues
Yuval Mintz (11):
ipmr,ipmr6: Define a uniform vif_device
ip6mr: Make mroute_sk rcu-based
ip6mr: Align hash implementation to ipmr
mroute*: Make mr_table a com
] mr_mfc has to be the first
field inside every multicast routing abstraction utilizing it.
Signed-off-by: Yuval Mintz
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 21 +-
include/linux/mroute.h| 45 +---
include/linux/mroute6.h | 23
e
distinct suffix.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute.h | 21
include/linux/mroute6.h | 1 -
include/linux/mroute_base.h | 46 +++
include/net/netns/ipv6.h| 2 +-
net/ipv4/ipmr.c | 2 -
net/ipv6/ip6mr.c
Since commit 8fb472c09b9d ("ipmr: improve hash scalability") ipmr has
been using rhashtable as a basis for its mfc routes, but ip6mr is
currently still using the old private MFC hash implementation.
Align ip6mr to the current ipmr implementation.
Signed-off-by: Yuval Mintz
Acked-b
ed by ipmr.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute.h | 9 -
include/linux/mroute6.h | 3 ---
include/linux/mroute_base.h | 9 +
net/ipv6/ip6mr.c| 3 ---
4 files changed, 9 insertions(+), 15 deletions(-)
diff --git
Same as previously done with the mfc seq, the logic for the vif seq is
refactored to be shared between ipmr and ip6mr.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute_base.h | 33 ++
net/ipv4/ipmr.c | 49
common
flows, in this case - the hash parameters and a comparison key
representing a (*,*) route.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 52 +--
net/ipv4/ipmr.c | 71 ++-
net/ipv4/ipmr_base.c
In ipmr the mr_table socket is handled under RCU. Introduce the same
for ip6mr.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute6.h | 6 +++---
net/ipv6/ip6_output.c | 2 +-
net/ipv6/ip6mr.c| 45 +++--
3 files
vif_device fields in a new common source file. This requires modifying
the ipv{4,6] Kconfig and ipv4 makefile as we're introducing a new common
config option - CONFIG_IP_MROUTE_COMMON.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute.h
between the two.
Notice this requires creating an mr_table iterator for each, as the
for-each preprocessor macro can't be used by the common logic.
Signed-off-by: Yuval Mintz
Acked-by: Nikolay Aleksandrov
---
include/linux/mroute_base.h | 29
net/ipv4/ipmr.c
On Wed, Feb 28, 2018 at 12:38:20AM +0200, Nikolay Aleksandrov wrote:
> On 27/02/18 20:58, Yuval Mintz wrote:
> > mfc_cache and mfc6_cache are almost identical - the main difference is
> > in the origin/group addresses and comparison-key. Make a common
> > structure enca
> >> > If so, for how long? They should certainly be removed eventually. How
> >> > do we ensure we don't forget?
> >> >
> >> > Seems to me it would be better to remove them right now.
> >>
> >> I can do that unless someone objects.
> >
> >I don't object, but FWIW keep in mind extack errors don't s
e
distinct suffix.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 21
include/linux/mroute6.h | 1 -
include/linux/mroute_base.h | 46 +++
include/net/netns/ipv6.h| 2 +-
net/ipv4/ipmr.c | 2 -
net/ipv6/ip6mr.c
] mr_mfc has to be the first
field inside every multicast routing abstraction utilizing it.
Signed-off-by: Yuval Mintz
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 21 +-
include/linux/mroute.h| 45 +---
include/linux/mroute6.h | 23
ed by ipmr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 9 -
include/linux/mroute6.h | 3 ---
include/linux/mroute_base.h | 9 +
net/ipv6/ip6mr.c| 3 ---
4 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/include/linux/mroute.h b/inc
between the two.
Notice this requires creating an mr_table iterator for each, as the
for-each preprocessor macro can't be used by the common logic.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 29
net/ipv4/ipmr.c
Since commit 8fb472c09b9d ("ipmr: improve hash scalability") ipmr has
been using rhashtable as a basis for its mfc routes, but ip6mr is
currently still using the old private MFC hash implementation.
Align ip6mr to the current ipmr implementation.
Signed-off-by: Yuval Mintz
---
inc
With the exception of the final dump, ipmr and ip6mr have the exact same
seq logic for traversing a given mr_table. Refactor that code and make
it common.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 69
net/ipv4/ipmr.c | 93
common
flows, in this case - the hash parameters and a comparison key
representing a (*,*) route.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 52 +--
net/ipv4/ipmr.c | 71 ++-
net/ipv4/ipmr_base.c
In ipmr the mr_table socket is handled under RCU. Introduce the same
for ip6mr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute6.h | 6 +++---
net/ipv6/ip6_output.c | 2 +-
net/ipv6/ip6mr.c| 45 +++--
3 files changed, 31 insertions(+), 22
Same as previously done with the mfc seq, the logic for the vif seq is
refactored to be shared between ipmr and ip6mr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 33 ++
net/ipv4/ipmr.c | 49
vif_device fields in a new common source file. This requires modifying
the ipv{4,6] Kconfig and ipv4 makefile as we're introducing a new common
config option - CONFIG_IP_MROUTE_COMMON.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 13 +---
include/linux/mroute6.h
Now that both ipmr and ip6mr are using the same mr_table structure,
we can have a common function to allocate & initialize a new instance.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 17 +
net/ipv4/ipmr.c | 27 ++-
net/
bot issues
Yuval Mintz (11):
ipmr,ipmr6: Define a uniform vif_device
ip6mr: Make mroute_sk rcu-based
ip6mr: Align hash implementation to ipmr
mroute*: Make mr_table a common struct
ipmr, ip6mr: Unite creation of new mr_table
ipmr, ip6mr: Make mfc_cache a common structure
ipmr, ip6mr: Un
Since commit 8fb472c09b9d ("ipmr: improve hash scalability") ipmr has
been using rhashtable as a basis for its mfc routes, but ip6mr is
currently still using the old private MFC hash implementation.
Align ip6mr to the current ipmr implementation.
Signed-off-by: Yuval Mintz
---
inc
Same as previously done with the mfc seq, the logic for the vif seq is
refactored to be shared between ipmr and ip6mr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 33 ++
net/ipv4/ipmr.c | 49
] mr_mfc has to be the first
field inside every multicast routing abstraction utilizing it.
Signed-off-by: Yuval Mintz
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 21 +-
include/linux/mroute.h| 45 +---
include/linux/mroute6.h | 23
offloading as well, as almost all structures
related to the offloading would be shared between the two protocols.
Yuval Mintz (11):
ipmr,ipmr6: Define a uniform vif_device
ip6mr: Make mroute_sk rcu-based
ip6mr: Align hash implementation to ipmr
mroute*: Make mr_table a common struct
ipmr
between the two.
Notice this requires creating an mr_table iterator for each, as the
for-each preprocessor macro can't be used by the common logic.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 29 +
net/ipv4/ipmr.c
e
distinct suffix.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 21 ---
include/linux/mroute6.h | 1 -
include/linux/mroute_base.h | 46 +++
include/net/netns/ipv6.h| 2 +-
net/ipv4/ipmr.c | 2 -
net/ipv6/ip6mr.c
Now that both ipmr and ip6mr are using the same mr_table structure,
we can have a common function to allocate & initialize a new instance.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 17 +
net/ipv4/ipmr.c | 27 ++-
net/
ed by ipmr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 9 -
include/linux/mroute6.h | 3 ---
include/linux/mroute_base.h | 9 +
net/ipv6/ip6mr.c| 3 ---
4 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/include/linux/mroute.h b/inc
With the exception of the final dump, ipmr and ip6mr have the exact same
seq logic for traversing a given mr_table. Refactor that code and make
it common.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 69
net/ipv4/ipmr.c | 93
In ipmr the mr_table socket is handled under RCU. Introduce the same
for ip6mr.
Signed-off-by: Yuval Mintz
---
include/linux/mroute6.h | 6 +++---
net/ipv6/ip6_output.c | 2 +-
net/ipv6/ip6mr.c| 43 ++-
3 files changed, 30 insertions(+), 21
vif_device fields in a new common source file. This requires modifying
the ipv{4,6] Kconfig and ipv4 makefile as we're introducing a new common
config option - CONFIG_IP_MROUTE_COMMON.
Signed-off-by: Yuval Mintz
---
include/linux/mroute.h | 13 +---
include/linux/mroute6.h
common
flows, in this case - the hash parameters and a comparison key
representing a (*,*) route.
Signed-off-by: Yuval Mintz
---
include/linux/mroute_base.h | 52 +--
net/ipv4/ipmr.c | 71 ++-
net/ipv4/ipmr_base.c
> > > Hm. You you need this just because you didn't add the backlog
> > > pointer to destroy? AFAIK on destroy we are free to reset stats as
> > > well, thus simplifying your driver... Let me know if I
> > > misunderstand.
> >
> > This is meant exactly for the scenario where qdisc didn't get
> >
se of a qdisc that stops being offloaded but is not destroyed, backlog
> > value needs to be updated about the un-offloading.
> > For that reason an unoffload function is being added to the ops struct.
> >
> > Signed-off-by: Nogah Frankel
> > Reviewed-by: Yuval Mintz
> > > > +struct tc_prio_qopt_offload_params {
> > > > + int bands;
> > > > + u8 priomap[TC_PRIO_MAX + 1];
> > > > + /* In case that a prio qdisc is offloaded and now is changed to
> > > > a
> > > > +* non-offloadedable config, it needs to update the backlog
> > > > value
> > +struct tc_prio_qopt_offload_params {
> > + int bands;
> > + u8 priomap[TC_PRIO_MAX + 1];
> > + /* In case that a prio qdisc is offloaded and now is changed to a
> > +* non-offloadedable config, it needs to update the backlog value
> > +* to negate the HW backlog value.
> > +*
> >>> Many of the ASIC's internal resources are limited and are shared
> between
> >>> several hardware procedures. For example, unified hash-based memory
> can
> >>> be used for many lookup purposes, like FDB and LPM. In many cases the
> user
> >>> can provide a partitioning scheme for such a reso
> Many of the ASIC's internal resources are limited and are shared
> between
> several hardware procedures. For example, unified hash-based memory
> can
> be used for many lookup purposes, like FDB and LPM. In many cases the
> user
> can provide a partitioning scheme for such a
> >> Many of the ASIC's internal resources are limited and are shared between
> >> several hardware procedures. For example, unified hash-based memory
> can
> >> be used for many lookup purposes, like FDB and LPM. In many cases the
> user
> >> can provide a partitioning scheme for such a resource i
> >Use the newly added TCA_HW_OFFLOAD indication from kernel
> >to print a consistent 'offloaded' message to user when listing qdiscs.
> >
> >Signed-off-by: Yuval Mintz
>
> Reviewed-by: Jiri Pirko
Just now saw the Stephen's e-mail regarding iproute
Use the newly added TCA_HW_OFFLOAD indication from kernel
to print a consistent 'offloaded' message to user when listing qdiscs.
Signed-off-by: Yuval Mintz
---
include/uapi/linux/rtnetlink.h | 1 +
tc/tc_qdisc.c | 4
2 files changed, 5 insertions(+)
diff --git
eof(struct rds_rdma_args)))
> + return -EINVAL;
> args = CMSG_DATA(cmsg);
> *rdma_bytes += args->remote_vec.bytes;
> }
Reviewed-by: Yuval Shaia
> --
> 2.4.11
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
igned-off-by: Yuval Mintz
---
Do Notice this is going to create [easy-to-solve-]conflicts with net-next,
Due to 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking").
That's also why the numbering here are apparently inconsistent [skipping
0x100].
---
include/net/sc
ty to RED qdisc")
Signed-off-by: Yuval Mintz
---
include/uapi/linux/pkt_sched.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index af3cc2f..37b5096 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/p
Let RED utilize the new internal flag, TCQ_F_OFFLOADED,
to mark a given qdisc as offloaded instead of using a dedicated
indication.
Also, change internal logic into looking at said flag when possible.
Fixes: 602f3baf2218 ("net_sch: red: Add offload ability to RED qdisc")
Signed-off
OADED as its no longer needed.
Dave,
A bit unorthodox as it's not a fix per-se, but it's the last chance
for killing the unneeded uapi and replacing it with something better
before getting stuck with it forever.
Cheers,
Yuval
Yuval Mintz (3):
net: sched: Add TCA_HW_OFFLOAD
net: s
> Introduce NETIF_F_GRO_HW feature flag for NICs that support hardware
> GRO. With this flag, we can now independently turn on or off hardware
> GRO when GRO is on. Hardware GRO guarantees that packets can be
> re-segmented by TSO/GSO to reconstruct the original packet stream.
>
> Cc: Ariel Elio
> Advertise NETIF_F_GRO_HW and turn on or off hardware GRO based on
> NETIF_F_GRO_FW flag.
>
> Cc: Ariel Elior
> Cc: everest-linux...@cavium.com
> Signed-off-by: Michael Chan
> ---
> drivers/net/ethernet/qlogic/qede/qede_filter.c | 9 ++---
> drivers/net/ethernet/qlogic/qede/qede_main.c |
On Thu, Nov 09, 2017 at 04:38:13PM +, Salil Mehta wrote:
> This patch migrates the HNS3 driver code from use of depricated PCI
> MSI/MSI-X interrupt vector allocation/free APIs to new common APIs.
>
> Signed-off-by: Salil Mehta
> Suggested-by: Christoph Hellwig
> ---
>
On Wed, Nov 08, 2017 at 11:56:06AM +, Salil Mehta wrote:
> This patch migrates the HNS3 driver code from use of depricated PCI
> MSI/MSI-X interrupt vector allocation/free APIs to new common APIs.
>
> Signed-off-by: Salil Mehta
> Suggested-by: Christoph Hellwig
> ---
> .../ethernet/hisilico
1 - 100 of 1095 matches
Mail list logo
