Current PF host driver can serve DPDK VF well, but the
implementation is not complete to support Linux VF,
even both DPDK VF and Linux VF use same API set.
This patch set made below changes:
1. Make an enhancement on interface to serve VF, so
both Linux and DPDK VF can be well served.
2. Change
i40e PF host only support to work with DPDK VF driver, Linux
VF driver is not supported. This change will enhance in version
number returned.
Current version info returned won't be able to be recognized
by Linux VF driver, change to values that both DPDK VF and Linux
driver can recognize.
The exp
When VF requested to configure TX queue, a few parameters are
missed to be configured in PF host. This change have more
fields parsed and configured for TX context.
Signed-off-by: Chen Jing D(Mark)
---
drivers/net/i40e/i40e_pf.c |4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff
PF host didn't return correct VSI id to VF.
This change fix it.
Signed-off-by: Chen Jing D(Mark)
---
drivers/net/i40e/i40e_pf.c |3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/drivers/net/i40e/i40e_pf.c b/drivers/net/i40e/i40e_pf.c
index 229f71a..5314d9f 100644
--- a/d
i40e PF host only support to work with DPDK VF driver, Linux
VF driver is not supported. This change will enhance in
configuring IRQ link list.
This Change will identify VF client by number of vector
requested. DPDK VF will ask only single one while Linux VF
will request at least 2. It will have d
On Fri, Dec 30, 2016 at 04:26:27PM -0500, Charles (Chas) Williams wrote:
>
>
> On 12/29/2016 10:15 PM, Yuanhan Liu wrote:
> >On Thu, Dec 29, 2016 at 10:58:11AM -0500, Charles (Chas) Williams wrote:
> >>On 12/29/2016 03:52 AM, Yuanhan Liu wrote:
> >>>On Wed, Dec 28, 2016 at 04:10:52PM -0500, Charl
On Sun, Jan 01, 2017 at 02:01:56PM -0500, Charles (Chas) Williams wrote:
> If you create a vhost server device, it doesn't create the actual datagram
> socket until you call .dev_start(). If you call .dev_stop() is also
> deletes those sockets. For QEMU clients, this is a problem since QEMU
> doe
On 12/29/2016 12:38 PM, Santosh Shukla wrote:
Hi Shreyansh,
On Thu, Dec 29, 2016 at 10:46:35AM +0530, Shreyansh Jain wrote:
From: Hemant Agrawal
Adding NXP DPAA2 architecture specific mempool support
Each mempool instance is represented by a DPBP object
from the FSL-MC bus.
This patch also r
On Sun, Jan 01, 2017 at 02:01:57PM -0500, Charles (Chas) Williams wrote:
> .dev_start()/.dev_stop() roughly corresponds to the local device's
> port being up or down. This is different from the remote client being
> connected which is roughtly link up or down. Emulate the behavior by
> separately
Hi, Ferruh
Please see the question below. In my opinion, etrack_id is just a name used to
define the ID of one NIC.
In kernel version ethtool, it will print this ID in the line of firmware
verison.
I know what is etrack_id mean, but I really don't know why this named etrack_id.
Can you explain t
Been away, hence the somewhat late review..
On 16/12/2016 09:44, Olivier Matz wrote:
[..]
Today, each 'id' returned by rte_eth_xstats_get() is equal to the index
in the returned array, making this value useless. It also prevents a
driver from having different indexes for names and value, like in
On 23/12/2016 20:35, Olivier Matz wrote:
Reword the Api documentation of xstats ethdev.
CC: sta...@dpdk.org
Signed-off-by: Olivier Matz
Acked-by: Remy Horton
Hello,
we are also seeing this issue on one of our test systems while it does
not occur on other test systems with the same DPDK version (we tested
16.11 and current master).
The system that we can reproduce this issue on also has a X552 ixgbe NIC
which can forward the exact same traffic using th
On 12/25/2016 10:33 PM, Thomas Monjalon wrote:
> 2016-12-23 16:57, Jan Blunck:
>> This repost addresses the review comments of Thomas Monjalon to completely
>> remove the ethdev helper to further decrease the coupling of the ethdev and
>> the eal layers. This required me to squash together all patc
On 12/25/2016 10:33 PM, Thomas Monjalon wrote:
> 2016-12-23 16:57, Jan Blunck:
>> This repost addresses the review comments of Thomas Monjalon to completely
>> remove the ethdev helper to further decrease the coupling of the ethdev and
>> the eal layers. This required me to squash together all patc
Current Cryptodev AES-NI GCM PMD is implemented using Multi Buffer
Crypto library.This patch reimplement the device using ISA-L Crypto
library: https://github.com/01org/isa-l_crypto.
The migration entailed the following additional support for:
* GMAC algorithm.
* 256-bit cipher key.
* Sessio
On 12/27/2016 10:09 AM, Jerin Jacob wrote:
> Removed unused "reg_info" global variable from ixgbe driver.
>
> cat build/app/testpmd.map | grep "Allocating common symbols" -A 15
> Allocating common symbols
> Common symbol sizefile
> reg_info0x18build/lib/librte_pmd_ixgbe.a(ixgbe_e
On 12/27/2016 10:09 AM, Jerin Jacob wrote:
> Removed explicit ixgbe driver linkage request from
> app/testpmd makefile to mk/rte.app.mk to
> 1)Maintain the correct link ordering(from higher level libraries
> to lower level libraries)
> 2)In shared lib configuration, any application can use ixgbe
>
On 01/03/2017 03:22 AM, Yuanhan Liu wrote:
On Sun, Jan 01, 2017 at 02:01:56PM -0500, Charles (Chas) Williams wrote:
If you create a vhost server device, it doesn't create the actual datagram
socket until you call .dev_start(). If you call .dev_stop() is also
deletes those sockets. For QEMU c
2017-01-03 12:24, Ferruh Yigit:
> On 12/25/2016 10:33 PM, Thomas Monjalon wrote:
> > Applied with some trivial fixes, thanks
>
> Getting following build error for mlx5 [1], it is mainly because verbs.h
> also using container_of macro.
>
> [1]
> In file included from
> .../x86_64-native-linuxapp-g
Hi Wei,
On Fri, Dec 30, 2016 at 03:53:06PM +0800, Wei Zhao wrote:
> check if the rule is a L2 tunnel rule, and get the L2 tunnel info.
>
> Signed-off-by: Wei Zhao
> Signed-off-by: Wenzhuo Lu
>
> ---
>
> v2:
> --add new error set function
> --change return value type of parser function
> ---
>
Hi Wei,
On Fri, Dec 30, 2016 at 03:53:07PM +0800, Wei Zhao wrote:
> check if the rule is a flow director rule, and get the flow director info.
>
> Signed-off-by: Wei Zhao
> Signed-off-by: Wenzhuo Lu
>
> ---
>
> v2:add new error set function
> ---
> drivers/net/ixgbe/ixgbe_ethdev.c | 1467
>
2017-01-03 14:02, Piotr Azarewicz:
> Current Cryptodev AES-NI GCM PMD is implemented using Multi Buffer
> Crypto library.This patch reimplement the device using ISA-L Crypto
> library: https://github.com/01org/isa-l_crypto.
>
> The migration entailed the following additional support for:
> * GMA
Hi, Wei Zhao
Would you please do git rebase master for this patch set?
When I do git pull and then git apply this patch, following errors are reported:
[root@dpdk4 dpdk-org]# git am
../patches/bundle-488-zhaowei-ixgbe-filter-api-v2.mbox
Applying: net/ixgbe: store SYN filter
Applying: net/ixgbe:
Hi, Wei Zhao
I think that you had better give a cover letter for such a series of patches.
You can give the changes between v2 and v1 in cover letter
and maybe no need describe it in each one.
Thanks &Best Regards
-Wei
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On B
On 1/3/2017 2:06 PM, Thomas Monjalon wrote:
> 2017-01-03 12:24, Ferruh Yigit:
>> On 12/25/2016 10:33 PM, Thomas Monjalon wrote:
>>> Applied with some trivial fixes, thanks
>>
>> Getting following build error for mlx5 [1], it is mainly because verbs.h
>> also using container_of macro.
>>
>> [1]
>> I
On 1/3/2017 9:05 AM, Yang, Qiming wrote:
> Hi, Ferruh
> Please see the question below. In my opinion, etrack_id is just a name used
> to define the ID of one NIC.
> In kernel version ethtool, it will print this ID in the line of firmware
> verison.
> I know what is etrack_id mean, but I really d
On 12/27/2016 12:30 PM, Qiming Yang wrote:
> This patch adds a new API 'rte_eth_dev_fw_info_get' for fetching
> firmware related information by a given device.
>
> Signed-off-by: Qiming Yang
> Acked-by: Remy Horton
> ---
> v2 changes:
> * modified some comment statements.
> v3 changes:
> * chang
On 12/27/2016 12:30 PM, Qiming Yang wrote:
> This patch adds a new function eth_igb_fw_version_get.
>
> Signed-off-by: Qiming Yang
> ---
> v3 changes:
> * use eth_igb_fw_version_get(struct rte_eth_dev *dev, u32 *fw_major,
>u32 *fw_minor, u32 *fw_minor, u32 *fw_patch, u32 *etrack_id) instead
On 12/27/2016 12:30 PM, Qiming Yang wrote:
> This patch add a new function ixgbe_fw_version_get.
>
> Signed-off-by: Qiming Yang
<...>
>
> static void
> +ixgbe_fw_version_get(struct rte_eth_dev *dev, __rte_unused u32 *fw_major,
> + __rte_unused u32 *fw_minor, __rte_unused u32 *fw_patch, u
This commit fixes unnecessary padding of aad for GCM using
scatter-gather list
Fixes: b71990ffa7e4 ("app/test: add SGL tests to cryptodev QAT suite")
Signed-off-by: Arek Kusztal
---
app/test/test_cryptodev.c | 12 +---
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/app/te
On 12/31/2016 7:41 AM, Mody, Rasesh wrote:
>> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
>> Sent: Friday, December 23, 2016 7:42 AM
>>
>> On 12/3/2016 9:11 AM, Rasesh Mody wrote:
>>> This patch consists of semantic/formatting changes. It also includes
>>> comment additions.
>>
>> As far as
On 1/3/2017 1:23 PM, Ferruh Yigit wrote:
> On 12/27/2016 10:09 AM, Jerin Jacob wrote:
>> Removed unused "reg_info" global variable from ixgbe driver.
>>
>> cat build/app/testpmd.map | grep "Allocating common symbols" -A 15
>> Allocating common symbols
>> Common symbol sizefile
>> reg_info
Thomas Monjalon writes:
> Hi Aaron,
>
> 2016-12-30 10:25, Aaron Conole:
>> In many cases, it's enough to simply let the application know that the
>> call to initialize DPDK has failed. A complete halt can then be
>> decided by the application based on error returned (and the app could
>> even at
error #188: enumerated type mixed with another type
This is get when an integer assigned to an enum variable.
Since this usage is common and causing many ICC compilation errors, and
other compilers accept this usage. Disabling the warning.
Signed-off-by: Ferruh Yigit
---
mk/toolchain/icc/rte.v
On 12/29/2016 3:15 PM, Nelio Laranjeiro wrote:
> Changes in v5:
>
> - Fix masking when only spec is present in item structure.
> - Fix first element of flow items array.
>
> Changes in v4:
>
> - Simplify flow parsing by using a graph.
> - Add VXLAN flow item.
> - Add mark flow action.
> -
.dev_start()/.dev_stop() roughly corresponds to the local device's port
being ready. This is different from the remote client being connected
which is roughly link up or down. Emulate the device start/stop behavior
by separately tracking the start/stop state to determine if we should
allow packet
If you create a vhost server device, it doesn't create the actual datagram
socket until you call .dev_start(). If you call .dev_stop() is also
deletes those sockets. For QEMU clients, this is a problem since QEMU
doesn't know how to re-attach to datagram sockets that have gone away.
To fix this,
On 12/28/2016 9:58 AM, Nelio Laranjeiro wrote:
> Flows redirected to a specific queue do not have a valid RSS hash result
> and the related mbuf flag must not be set.
>
> Fixes: ecf60761fc2a ("net/mlx5: return RSS hash result in mbuf")
>
> CC: sta...@dpdk.org
> Signed-off-by: Nelio Laranjeiro
>
This patch provides the initial implementation of the scheduler poll mode
driver using DPDK cryptodev framework.
Scheduler PMD is used to schedule and enqueue the crypto ops to the
hardware and/or software crypto devices attached to it (slaves). The
dequeue operation from the slave(s), and the pos
On 12/21/2016 8:29 AM, Wenzhuo Lu wrote:
> When VF receives a message from PF, it should check the return
> value. But in i40evf_execute_vf_cmd the value is ignored and not
> returned to the caller.
>
> Fixes: 95cd21f45d1b ("i40evf: allocate virtchnl commands buffer per VF")
>
> Signed-off-by: We
This patch provides the initial implementation of the scheduler poll mode
driver using DPDK cryptodev framework.
Scheduler PMD is used to schedule and enqueue the crypto ops to the
hardware and/or software crypto devices attached to it (slaves). The
dequeue operation from the slave(s), and the pos
On Tue, Jan 03, 2017 at 04:15:42PM +, Ferruh Yigit wrote:
> error #188: enumerated type mixed with another type
>
> This is get when an integer assigned to an enum variable.
>
> Since this usage is common and causing many ICC compilation errors, and
> other compilers accept this usage. Disabl
On 1/2/2017 3:40 PM, Thomas Monjalon wrote:
> 2016-12-27 08:03, Ilya Maximets:
>> Hello.
>> Ferruh, Thomas, is there a chance for this to be accepted to 17.02?
>> Maybe I should resend this patch-set without 'RFC' tag?
>
> Yes it should be integrated in 17.02.
> Ferruh, any news?
>
I was waiting
This will be used by later changes to determine the underlying linux
interface.
Signed-off-by: Chas Williams
---
drivers/net/af_packet/rte_eth_af_packet.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/af_packet/rte_eth_af_packet.
Add promiscuous support to the AF_PACKET PMD. The underlying linux
device's IF_PROMISC flag is toggled to enable or disable.
Signed-off-by: Charles (Chas) Williams
---
drivers/net/af_packet/rte_eth_af_packet.c | 40 +++
1 file changed, 40 insertions(+)
diff --git a/
AF_PACKET has some flags to check on the receive side for 802.1Q
information. If present, we copy into the mbuf. For transmit, we
insert any 802.1Q information into the packet before copying to the ring.
Signed-off-by: Charles (Chas) Williams
---
drivers/net/af_packet/rte_eth_af_packet.c | 14
The underlying linux device's MTU is changed subject to the frame size
limitations during device creation.
Signed-off-by: Charles (Chas) Williams
---
drivers/net/af_packet/rte_eth_af_packet.c | 29 +
1 file changed, 29 insertions(+)
diff --git a/drivers/net/af_packet
2016-12-26 18:53, Shreyansh Jain:
> --- a/lib/librte_eal/linuxapp/eal/eal.c
> +++ b/lib/librte_eal/linuxapp/eal/eal.c
> @@ -844,6 +845,9 @@ rte_eal_init(int argc, char **argv)
> if (rte_eal_intr_init() < 0)
> rte_panic("Cannot init interrupt-handling thread\n");
>
> +
2016-12-26 18:53, Shreyansh Jain:
> +DPDK_17.02 {
> + global:
> +
> + rte_bus_list;
> + rte_eal_bus_add_device;
> + rte_eal_bus_add_driver;
> + rte_eal_bus_get;
> + rte_eal_bus_dump;
> + rte_eal_bus_register;
> + rte_eal_bus_insert_device;
> + rte_eal_bus_remove_
2016-12-26 18:53, Shreyansh Jain:
> --- a/lib/librte_eal/common/include/rte_dev.h
> +++ b/lib/librte_eal/common/include/rte_dev.h
> @@ -152,6 +162,8 @@ struct rte_driver {
> struct rte_bus *bus; /**< Bus serviced by this driver */
> const char *name; /**< Dri
2016-12-26 18:54, Shreyansh Jain:
> --- a/lib/librte_eal/common/include/rte_pci.h
> +++ b/lib/librte_eal/common/include/rte_pci.h
> @@ -373,6 +373,21 @@ rte_eal_compare_pci_addr(const struct rte_pci_addr *addr,
> int rte_eal_pci_scan(void);
>
> /**
> + * Match the PCI Driver and Device using th
2016-12-26 18:54, Shreyansh Jain:
> PCI scan and match now work on rte_device/rte_driver rather than PCI
> specific objects. These functions can now be plugged to the generic
> bus callbacks for scanning and matching devices/drivers.
These sentences looks weird :)
PCI functions must work with PCI
2016-12-26 18:54, Shreyansh Jain:
> Three macros:
> FOREACH_BUS
> FOREACH_DEVICE_ON_BUS
> FOREACH_DRIVER_ON_BUS
> are introduced to make looping over bus (on global list), devices and
> drivers (on a specific bus) prettier.
Nice
2016-12-26 18:53, Shreyansh Jain:
> Link to v1: [10]
> Link to v2: [11]
> Link to v3: [13]
> Link to v4: [14]
>
> :: Introduction ::
>
> DPDK has been inherently a PCI inclined framework. Because of this, the
> design of device tree (or list) within DPDK is also PCI inclined. A
> non-PCI device d
For Linux kernel 4.0 and newer, the ability to obtain
physical page frame numbers for unprivileged users from
/proc/self/pagemap was removed. Instead, when an IOMMU
is present, simply choose our own DMA addresses instead.
Signed-off-by: Ben Walker
---
lib/librte_eal/common/eal_private.h | 1
On Thu, 2016-12-29 at 17:14 -0800, Stephen Hemminger wrote:
> If kernel broke pinning of hugepages, then it is an upstream kernel bug.
The kernel, under a myriad of circumstances, will change the mapping of virtual
to physical addresses for hugepages. This behavior began somewhere around kernel
3.
For Linux kernel 4.0 and newer, the ability to obtain
physical page frame numbers for unprivileged users from
/proc/self/pagemap was removed. Instead, when an IOMMU
is present, simply choose our own DMA addresses instead.
Signed-off-by: Ben Walker
---
lib/librte_eal/common/eal_private.h | 1
Hi, Daiwei
> -Original Message-
> From: Dai, Wei
> Sent: Tuesday, January 3, 2017 10:33 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Lu, Wenzhuo ; Zhao1, Wei
>
> Subject: RE: [dpdk-dev] [PATCH v2 01/18] net/ixgbe: store SYN filter
>
> Hi, Wei Zhao
>
> I think that you had better give a cove
Hi, weid
> -Original Message-
> From: Dai, Wei
> Sent: Tuesday, January 3, 2017 10:28 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Lu, Wenzhuo ; Zhao1, Wei
>
> Subject: RE: [dpdk-dev] [PATCH v2 02/18] net/ixgbe: store flow director filter
>
> Hi, Wei Zhao
>
> Would you please do git rebase
You can see the kernel version ethtool, use command 'ethtool -i '
driver: ixgbe
version: 4.2.1-k
firmware-version: 0x61bf0001
Ixgbe's FW version do not have the major and minor number, and the original
purpose of this function is get FW version, so I think it's enough.
-Original Message---
In function vhost_new_device(), current code dose not free 'dev'
in "i == MAX_VHOST_DEVICE" condition statements. It will lead to a
memory leak.
Signed-off-by: Yong Wang
---
lib/librte_vhost/vhost.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/v
See the reply below.
-Original Message-
From: Yigit, Ferruh
Sent: Tuesday, January 3, 2017 11:03 PM
To: Yang, Qiming ; dev@dpdk.org;
thomas.monja...@6wind.com
Cc: Horton, Remy
Subject: Re: [PATCH v3 2/4] net/e1000: add firmware version get
On 12/27/2016 12:30 PM, Qiming Yang wrote:
> T
The patch set depends on Adrien's Generic flow API(rte_flow).
The patches mainly finish following functions:
1) Store and restore all kinds of filters.
2) Parse all kinds of filters.
3) Add flow validate function.
4) Add flow create function.
5) Add flow destroy function.
6) Add flow flush functio
Currently there's no ethertype filter stored in SW.
This patch stores ethertype filter with cuckoo hash
in SW, also adds protection if an ethertype filter
has been added.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/Makefile | 1 +
drivers/net/i40e/i40e_ethdev.c | 166 +
Currently there's no tunnel filter stored in SW.
This patch stores tunnel filter in SW with cuckoo
hash, also adds protection if a tunnel filter has
been added.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 169 -
drivers/net/i40e/i40e_et
Add support of restoring ethertype filter in case filter
dropped accidentally, as all filters need to be added and
removed by user obviously for generic filter API.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 44 ++
1 file changed, 44 i
Currently there's no flow director filter stored in SW. This
patch stores flow director filters in SW with cuckoo hash,
also adds protection if a flow director filter has been added.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 48 +++
drivers/net/i40e/i40e_et
This patch adds i40e_flow_validation function to check if
a flow is valid according to the flow pattern.
i40e_parse_ethertype_filter is added first, it also gets
the ethertype info.
i40e_flow.c is added to handle all generic filter events.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/Makefile
Add support of restoring flow director filter.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 1 +
drivers/net/i40e/i40e_ethdev.h | 1 +
drivers/net/i40e/i40e_fdir.c | 31 +++
3 files changed, 33 insertions(+)
diff --git a/drivers/net/i40e/i40e_e
Add support of restoring tunnel filter.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 21 +
1 file changed, 21 insertions(+)
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index 189d110..67e1b37 100644
--- a/drivers/net/i40e/i4
This patch adds i40e_parse_fdir_filter to check if a rule
is a flow director rule according to the flow pattern,
and the function also gets the flow director info.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 56 +---
drivers/net/i40e/i40e_ethdev.h | 55
drivers/net/i40
This patch adds i40e_flow_create function to create a
rule. It will check if a flow matches ethertype filter
or flow director filter or tunnel filter, if the flow
matches some kind of filter, then set the filter to HW.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 16 ++---
This patch adds i40e_parse_tunnel_filter to check if
a rule is a tunnel rule according to items of the flow
pattern, and the function also gets the tunnel info.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 394 +++
1 file changed, 394 inse
This patch adds i40e_flow_destroy function to destroy
a flow for users.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 33 +
1 file changed, 33 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e/i40e_flow.c
index 3114368..ec
This patch adds i40e_dev_destroy_ethertype_filter function
to destroy a ethertype filter for users.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 42 ++
1 file changed, 42 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/n
This patch supports destroying a flow directory filter
for users.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e/i40e_flow.c
index f334844..2674c2c 100644
--- a/drivers/net/i40e/i
This patch adds i40e_dev_destroy_tunnel_filter function
to destroy a tunnel filter for users.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 41 +
1 file changed, 41 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e
This patch adds i40e_flow_flush function to flush all
filters for users. And flow director flush function
is involved first.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.h | 1 +
drivers/net/i40e/i40e_fdir.c | 4 +---
drivers/net/i40e/i40e_flow.c | 51 +++
This patch adds i40e_tunnel_filter_flush function
to flush all tunnel filters, including filters in
SW and HW.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 37 +
1 file changed, 37 insertions(+)
diff --git a/drivers/net/i40e/i40e_flow.c b/dri
This patch adds i40e_ethertype_filter_flush function
to flush all ethertype filters, including filters in
SW and HW.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 41 -
1 file changed, 40 insertions(+), 1 deletion(-)
diff --git a/drivers/n
Yes, in my opinion it is. And I use this name already exist in the share code
from ND team.
-Original Message-
From: Yigit, Ferruh
Sent: Tuesday, January 3, 2017 10:49 PM
To: Yang, Qiming
Cc: dev@dpdk.org; Horton, Remy ; Thomas Monjalon
Subject: Re: [PATCH v3 1/4] ethdev: add firmware
virtio_user is not properly reset when users call vtpci_reset(),
as it ignores VIRTIO_CONFIG_STATUS_RESET status in
virtio_user_set_status().
This might lead to initialization failure as it starts to re-init
the device before sending RESET messege to backend. Besides, previous
callfds and kickfds
To support vhost kernel as the backend of net_virtio_user in coming
patches, we move vhost_user specific structs and macros into
vhost_user.c, and only keep common definitions in vhost.h.
Besides, remove VHOST_USER_MQ feature check.
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_user
Before the commit 86d59b21468a ("net/virtio: support LRO"), features
in virtio PMD, is decided and properly set at device initialization
and will not be changed. But afterward, features could be changed in
virtio_dev_configure(), and will be re-negotiated if it's changed.
In virtio_user, device fe
v3:
- Drop the patch to postpone driver ok sending patch, superseded it
with a bug fix to disable all virtqueues and re-init the device.
(you might wonder why not just send reset owner msg. Under my test,
it causes spinlock deadlock problem when killing the program).
- Avoid compil
Add a struct virtio_user_backend_ops to abstract three kinds of backend
operations:
- setup, create the unix socket connection;
- send_request, sync messages with backend;
- enable_qp, enable some queue pair.
Signed-off-by: Jianfeng Tan
---
drivers/net/virtio/virtio_user/vhost.h
When used with vhost kernel backend, we can offload at both directions.
- From vhost kernel to virtio_user, the offload is enabled so that
DPDK app can trust the flow is checksum-correct; and if DPDK app
sends it through another port, the checksum needs to be
recalculated or offloaded
With vhost kernel, to enable multiqueue, we need backend device
in kernel support multiqueue feature. Specifically, with tap
as the backend, as linux/Documentation/networking/tuntap.txt shows,
we check if tap supports IFF_MULTI_QUEUE feature.
And for vhost kernel, each queue pair has a vhost fd, a
This patch add support vhost kernel as the backend for virtio_user.
Three main hook functions are added:
- vhost_kernel_setup() to open char device, each vq pair needs one
vhostfd;
- vhost_kernel_ioctl() to communicate control messages with vhost
kernel module;
- vhost_kernel_enable_q
On Tue, Jan 03, 2017 at 10:57:55PM -0500, Yong Wang wrote:
> In function vhost_new_device(), current code dose not free 'dev'
> in "i == MAX_VHOST_DEVICE" condition statements. It will lead to a
> memory leak.
Nice catch!
Here are few minor stuff you might need pay attention to for future
contrib
On Wed, Jan 04, 2017 at 03:59:21AM +, Jianfeng Tan wrote:
> virtio_user is not properly reset when users call vtpci_reset(),
> as it ignores VIRTIO_CONFIG_STATUS_RESET status in
> virtio_user_set_status().
>
> This might lead to initialization failure as it starts to re-init
> the device befor
On Wed, Jan 04, 2017 at 03:59:22AM +, Jianfeng Tan wrote:
> To support vhost kernel as the backend of net_virtio_user in coming
> patches, we move vhost_user specific structs and macros into
> vhost_user.c, and only keep common definitions in vhost.h.
>
> Besides, remove VHOST_USER_MQ feature
On Wed, Jan 04, 2017 at 03:59:23AM +, Jianfeng Tan wrote:
> +struct virtio_user_backend_ops ops_user;
Better to qualify it with "extern const" ...
--yliu
On Wed, Jan 04, 2017 at 03:59:24AM +, Jianfeng Tan wrote:
> +static int
> +vhost_kernel_ioctl(struct virtio_user_dev *dev,
> +enum vhost_user_request req,
> +void *arg)
> +{
> + int i, ret = -1;
> + uint64_t req_kernel;
> + struct vhost_memory_kernel
> -Original Message-
> From: Xing, Beilei
> Sent: Wednesday, January 4, 2017 11:23 AM
> To: Wu, Jingjing ; Zhang, Helin
> Cc: dev@dpdk.org
> Subject: [PATCH v5 00/17] net/i40e: consistent filter API
>
> The patch set depends on Adrien's Generic flow API(rte_flow).
>
> The patches mainl
Hi Yuanhan,
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Wednesday, January 4, 2017 2:03 PM
> To: Tan, Jianfeng
> Cc: dev@dpdk.org; Yigit, Ferruh; Liang, Cunming
> Subject: Re: [PATCH v3 3/7] net/virtio_user: move vhost user specific code
>
> On We
> Yuanhan Liu
> 2017/01/04 12:02
>
> to
>
> Yong Wang ,
>
> cc
>
> dev@dpdk.org
>
> subject
>
> Re: [PATCH] lib/librte_vhost: fix memory leak
>
> On Tue, Jan 03, 2017 at 10:57:55PM -0500, Yong Wang wrote:
> > In function vhost_new_device(), current code dose not free 'dev'
> > in "i == MA
On 12/30/2016 2:27 PM, Yuanhan Liu wrote:
On Thu, Dec 29, 2016 at 07:30:39AM +, Jianfeng Tan wrote:
This patch mainly allocates structure to store queue/irq mapping,
and configure queue/irq mapping down through PCI ops. It also creates
eventfds for each Rx queue and tell the kernel about t
On Wed, Jan 04, 2017 at 06:46:34AM +, Tan, Jianfeng wrote:
> Hi Yuanhan,
>
> > -Original Message-
> > From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> > Sent: Wednesday, January 4, 2017 2:03 PM
> > To: Tan, Jianfeng
> > Cc: dev@dpdk.org; Yigit, Ferruh; Liang, Cunming
> > Subjec
1 - 100 of 115 matches
Mail list logo
