rte_eth_rx_descritpr_status and rte_eth_tx_descriptor_status
are supported by igb VF.
Signed-off-by: Wei Zhao
---
v2:
-add release note document info
v3:
-rebase code and change git log
v4:
-rebase code
---
doc/guides/rel_notes/release_18_08.rst | 4 ++--
drivers/net/e1000/igb_ethdev.c
rte_eth_rx_descritpr_status and rte_eth_tx_descriptor_status
are supported by fm10K.
Signed-off-by: Wei Zhao
---
v2:
-fix DD check error in tx descriptor
v3:
-fix DD check index error
v4:
-fix error in RS bit list poll
v5:
-rebase code to branch and delete useless variable
v6:
-change relea
Add rte_kni_free to the virual KNI device.
Signed-off-by: Dan Gora
---
drivers/net/kni/rte_eth_kni.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/kni/rte_eth_kni.c b/drivers/net/kni/rte_eth_kni.c
index ab63ea427..24c6991e6 100644
--- a/drivers/net/kni/rte
Add rte_kni_free to the KNI example application.
Signed-off-by: Dan Gora
---
examples/kni/main.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/examples/kni/main.c b/examples/kni/main.c
index 4b162debb..75e23cd0f 100644
--- a/examples/kni/main.c
+++ b/examples/kni/main.c
Add a new API function to KNI, rte_kni_update_link() to allow DPDK
applications to update the link state for the KNI network interfaces
in the linux kernel.
Note that the default carrier state is set to off when the interface
is opened.
Signed-off-by: Dan Gora
---
kernel/linux/kni/kni_misc.c
Add support for testing rte_kni_free() function.
Signed-off-by: Dan Gora
---
test/test/test_kni.c | 20
1 file changed, 20 insertions(+)
diff --git a/test/test/test_kni.c b/test/test/test_kni.c
index 56773c8a2..ec051c07e 100644
--- a/test/test/test_kni.c
+++ b/test/test/tes
Increase the timeout to receive a response for KNI events handled
through kni_net_process_request to 10 seconds.
Certain actions, such as calling rte_eth_dev_start() can take more
than 3 seconds to return, in addition to any additional time needed
for the DPDK application to call rte_kni_handle_re
Check to ensure that the KNI interface is still in use before accessing
the KNI interface FIFOs to kernel space.
This will help to ensure that the user does not access the KNI
interface after rte_kni_release() has been called.
Signed-off-by: Dan Gora
---
lib/librte_kni/rte_kni.c | 6 +-
lib
Since the struct kni_dev is allocated as part of the netdev with
alloc_netdev, when free_netdev is called, this also frees the struct
kni_dev embedded in it.
This means that we cannot touch struct kni_dev after calling
free_netdev since that memory was already deallocated.
Separate unregistering
Add the new rte_kni_free() API function to the KNI library.
This function will be called by DPDK applications after
rte_kni_release() to free the KNI interface resources from the
kernel driver.
Signed-off-by: Dan Gora
---
lib/librte_kni/rte_kni.c | 32 +---
lib/librt
Currently the rte_kni kernel driver suffers from a problem where
when the interface is released, it generates a callback to the DPDK
application to change the interface state to Down. However, after the
DPDK application handles the callback and generates a response back to
the kernel, the rte_kni
Remove the unused fields 'status' and 'synchro' from the struct
kni_dev.
Signed-off-by: Dan Gora
---
kernel/linux/kni/kni_dev.h | 4
1 file changed, 4 deletions(-)
diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index 6275ef27f..ed42989cc 100644
--- a/kernel/linux/kni/
Hi All,
The following patches are to fix a problem with detaching a KNI
interface using rte_kni_release and to add a new API function
to allow users to change the link status (up/down, speed, etc)
of the interface in the linux kernel. In previous versions, it
was impossible to release a KNI inter
> -Original Message-
> From: Zhang, Qi Z
> Sent: Wednesday, June 27, 2018 8:50 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Lu, Wenzhuo
> Subject: RE: [PATCH v4] net/fm10k: add support for check descriptor status
> APIs
>
> > > > diff --git a/doc/guides/rel_notes/release_18_08.rst
> > > > b
From: Andrew Rybchenko [mailto:arybche...@solarflare.com]
Sent: Friday, June 29, 2018 12:47 AM
To: Zhang, Qi Z ; tho...@monjalon.net; Burakov, Anatoly
Cc: Ananyev, Konstantin ; dev@dpdk.org;
Richardson, Bruce ; Yigit, Ferruh
; Shelton, Benjamin H ;
Vangati, Narender
Subject: Re: [dpdk-dev]
09/06/2018 00:41, Ferruh Yigit:
> Cc: Shahaf Shuler
>
> Signed-off-by: Ferruh Yigit
I start working on it.
This is the list of remaining work on this patch:
- rebase
- add commit message (and fix title)
- check git grep ETH_TXQ_FLAGS_NO
- check git grep txq_flags
From: Andrew Rybchenko [mailto:arybche...@solarflare.com]
Sent: Friday, June 29, 2018 12:33 AM
To: Zhang, Qi Z ; tho...@monjalon.net; Burakov, Anatoly
Cc: Ananyev, Konstantin ; dev@dpdk.org;
Richardson, Bruce ; Yigit, Ferruh
; Shelton, Benjamin H ;
Vangati, Narender
Subject: Re: [dpdk-dev]
Hello,
We are in process of migrating our design from DPDK 17.05 to 17.11 and we ran
into a small problem. Within our design, we have some hash tables with 4-byte
keys. While going through the changes done in 17.11, we have found there was an
added key_size check, which now requires key_size >=
27/06/2018 14:25, Zhang, Qi Z:
> From: Burakov, Anatoly
> >
> > Previously, we were putting an exclusive lock to prevent secondary processes
> > spinning up while we are sending our messages. However, using exclusive
> > locks had an effect of disallowing multiple simultaenous unrelated
> > messag
From: Andrew Rybchenko [mailto:arybche...@solarflare.com]
Sent: Thursday, June 28, 2018 10:34 PM
To: Zhang, Qi Z ; tho...@monjalon.net; Burakov, Anatoly
Cc: Ananyev, Konstantin ; dev@dpdk.org;
Richardson, Bruce ; Yigit, Ferruh
; Shelton, Benjamin H ;
Vangati, Narender
Subject: Re: [dpdk-dev
20/06/2018 19:15, Ferruh Yigit:
> On 6/20/2018 6:07 PM, Dan Gora wrote:
> > Hi Ferruh,
> >
> > The documentation for rte_eth_dev_configure() should get updated as
> > well to document this requirement to strip the unsupported RSS hash
> > function bits. The current documentation only refers to th
21/06/2018 15:14, Ferruh Yigit:
> --- a/lib/librte_ethdev/rte_ethdev.h
> +++ b/lib/librte_ethdev/rte_ethdev.h
> @@ -939,6 +939,11 @@ struct rte_eth_conf {
> #define DEV_RX_OFFLOAD_SCATTER 0x2000
> #define DEV_RX_OFFLOAD_TIMESTAMP 0x4000
> #define DEV_RX_OFFLOAD_SECURITY
Fixed a bug where kni_autotest would not start due to the lack of the
ETH_TXQ_FLAGS_IGNORE flag being set in the rte_eth_txconf structure
passed to rte_eth_tx_queue_setup.
This was introduced in commit 4b954bb16747 ("ethdev: remove new to
old offloads API helpers")
Signed-off-by: Dan Gora
---
t
Fix a segmentation fault which occurs when the kni_autotest is run
in the 'test' application.
This segmenation fault occurs when rte_kni_get() is called with a
NULL value for 'name'.
Fixes: 0c6bc8ef70ba ("kni: memzone pool for alloc and release")
Cc: marc.s...@bisdn.de
Signed-off-by: Dan Gora
-
Fix a segmentation fault which occurs when the kni_autotest is run
in the 'test' application.
This segmenation fault occurs whe rte_kni_get is called with a NULL
value for 'name'.
Here is how the segfault was reproduced:
[root]# insmod
/home/dg/dpdk/latest/x86_64-native-linuxapp-gcc/build/kerne
Add a new API function to KNI, rte_kni_update_link() to allow DPDK
applications to update the link state for the KNI network interfaces
in the linux kernel.
Note that the default carrier state is set to off when the interface
is opened.
Signed-off-by: Dan Gora
---
kernel/linux/kni/kni_misc.c
Add rte_kni_free to the virual KNI device.
Signed-off-by: Dan Gora
---
drivers/net/kni/rte_eth_kni.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/kni/rte_eth_kni.c b/drivers/net/kni/rte_eth_kni.c
index ab63ea427..24c6991e6 100644
--- a/drivers/net/kni/rte
Add rte_kni_free to the KNI example application.
Signed-off-by: Dan Gora
---
examples/kni/main.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/examples/kni/main.c b/examples/kni/main.c
index 4b162debb..75e23cd0f 100644
--- a/examples/kni/main.c
+++ b/examples/kni/main.c
Add support for testing rte_kni_free() function.
Signed-off-by: Dan Gora
---
test/test/test_kni.c | 20
1 file changed, 20 insertions(+)
diff --git a/test/test/test_kni.c b/test/test/test_kni.c
index 56773c8a2..ec051c07e 100644
--- a/test/test/test_kni.c
+++ b/test/test/tes
Check to ensure that the KNI interface is still in use before accessing
the KNI interface FIFOs to kernel space.
This will help to ensure that the user does not access the KNI
interface after rte_kni_release() has been called.
Signed-off-by: Dan Gora
---
lib/librte_kni/rte_kni.c | 6 +-
lib
Increase the timeout to receive a response for KNI events handled
through kni_net_process_request to 10 seconds.
Certain actions, such as calling rte_eth_dev_start() can take more
than 3 seconds to return, in addition to any additional time needed
for the DPDK application to call rte_kni_handle_re
Add the new rte_kni_free() API function to the KNI library.
This function will be called by DPDK applications after
rte_kni_release() to free the KNI interface resources from the
kernel driver.
Signed-off-by: Dan Gora
---
lib/librte_kni/rte_kni.c | 32 +---
lib/librt
Since the struct kni_dev is allocated as part of the netdev with
alloc_netdev, when free_netdev is called, this also frees the struct
kni_dev embedded in it.
This means that we cannot touch struct kni_dev after calling
free_netdev since that memory was already deallocated.
Separate unregistering
Currently the rte_kni kernel driver suffers from a problem where
when the interface is released, it generates a callback to the DPDK
application to change the interface state to Down. However, after the
DPDK application handles the callback and generates a response back to
the kernel, the rte_kni
Remove the unused fields 'status' and 'synchro' from the struct
kni_dev.
Signed-off-by: Dan Gora
---
kernel/linux/kni/kni_dev.h | 4
1 file changed, 4 deletions(-)
diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index 6275ef27f..ed42989cc 100644
--- a/kernel/linux/kni/
Hi All,
The following patches are to fix a problem with detaching a KNI
interface using rte_kni_release and to add a new API function
to allow users to change the link status (up/down, speed, etc)
of the interface in the linux kernel. In previous versions, it
was impossible to release a KNI inter
From: Somnath Kotur
Setting of VLAN filter cmd was being done with incorrect flag value.
We need to use inner vlan fields instead of outer vlan.
Fixes: 7fe5668d2ea3 ("net/bnxt: support VLAN filter and strip")
Cc: sta...@dpdk.org
Signed-off-by: Somnath Kotur
Signed-off-by: Ajit Khaparde
---
d
>
> > + PMD_DRV_LOG(INFO, "Calling Device uninit\n");
>
> This looks like can be a debug message, what do you think?
>
Yes. Changed it to debug.
>
> <...>
>
> > @@ -3456,7 +3469,7 @@ static int bnxt_pci_remove(struct rte_pci_device
> *pci_dev)
> > static struct rte_pci_driver bnxt_rte_pmd
Fixed size of fw_grp_ids in VNIC is limiting the number of Rx rings
being created. With this patch we are allocating fw_grp_ids dynamically,
allowing us to get over this artificial limit.
Fixes: 9738793f28ec ("net/bnxt: add VNIC functions and structs")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khap
From: Somnath Kotur
While moving a flow to a different destination queue,
the l2_filter_id being passed to the FW command was incorrect.
Fix it by re-using the matching filter's l2_filter_id since
that is supposed to be the same in this case.
Fixes: 5ef3b79fdfe6 ("net/bnxt: support flow filter o
If HWRM resource manager is enabled, check VF resources before proceeding.
Make sure there are enough resources allocated and return an error in case
of insufficient error.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h| 5
drivers/net/bnxt/bnxt_ethdev.c | 21 ++--
From: Somnath Kotur
The L2 filter id is needed in many scenarios particularly when
we are repurposing the same ntuple filter with different destination
queues. This patch reverts a commit in which the L2 filter id was being
reset in clear_ntuple_filter().
Fixes: 1383434c9089 ("net/bnxt: reset L2
In bnxt_free_filter_mem(), check the filter type and call the
appropriate HWRM command to clear the filter from HW.
Fixes: 5ef3b79fdfe6 ("net/bnxt: support flow filter ops")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: add sta...@dpdk.org in Cc.
---
drivers/net/bnxt/bnxt_filter.c
rte_mbuf_data_iova returns a 64-bit address. But we are incorrectly
using only 32-bits of that. Use rte_cpu_to_le_64 instead of
rte_cpu_to_le_32
Fixes: 6eb3cc2294fd ("net/bnxt: add initial Tx code")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_txr.c | 4 ++--
1 fil
allocate RSS context only if RSS mode is enabled.
Signed-off-by: Ajit Khaparde
--
v1->v2: fix commit log
---
drivers/net/bnxt/bnxt_ethdev.c | 16 ++--
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index
Packets destined to the to-be-stopped queue should not be dropped
(neither in HW nor in the driver), so re-program the RSS Table without
this queue on stop and add it back to the table on start unless it
is a Representor VF.
Since 0th entry is used for default ring, use fw_grp_id + 1 to change
the
There is no need to update bnxt_hwrm_vnic_plcmode_cfg if new MTU is
not greater than the max data the mbuf can accommodate.
Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: update commit log
---
drivers/net/bnxt/bnxt_ethdev.c | 12 +++
In preparation of more rte_flow support it has been decided to
separate out filter and flow into their own files. Functionally the
same.
Signed-off-by: Michael Wildt
Signed-off-by: Scott Branden
Signed-off-by: Ajit Khaparde
--
v1->v2: Fix commit log.
---
drivers/net/bnxt/Makefile |1 +
From: Rob Miller
update HWRM API to v1.9.2.9
Signed-off-by: Rob Miller
Reviewed-by: Scott Branden
Reviewed-by: Ajit Kumar Khaparde
Reviewed-by: Randy Schacher
Signed-off-by: Rob Miller
---
drivers/net/bnxt/hsi_struct_def_dpdk.h | 113 -
1 file changed, 111 i
From: Xiaoxin Peng
When using multi-mbuf to xmit large packets, we need to use total
packet lengths (sum of all segments) to set txbd->flags_type.
Packets will not be sent when using tx_pkt->data_len(The first
segment of packets).
Fixes: 6eb3cc2294fd ("net/bnxt: add initial Tx code")
Cc: sta...@
Add support for StingRay VF device 0xd800
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_ethdev.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index 15dab10bb..0bb3f29d9 100644
--- a/drivers/net/bn
Add more checks for checksum calculation offload.
Also check for tunnel frames and select the proper
buffer descriptor size.
Fixes: 6eb3cc2294fd ("net/bnxt: add initial Tx code")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoxin Peng
Signed-off-by: Ajit Khaparde
Reviewed-by: Jason He
Reviewed-by: Qin
From: Jay Ding
Passing an invalid fw_vnic_id to the firmware will cause the
bnxt_hwrm_vnic_plcmode_cfg command to fail.
Add a check for VNIC id before sending message to firmware.
Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: sta...@dpdk.org
Signed-off-by: Jay Ding
Reviewed-by: Randy S
From: Scott Branden
Move check_zero_bytes into new bnxt_util.h file.
Signed-off-by: Scott Branden
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/Makefile | 1 +
drivers/net/bnxt/bnxt_ethdev.c | 1 +
drivers/net/bnxt/bnxt_filter.c | 9 -
drivers/net/bnxt/bnxt_filter.h | 1 -
Patchset against dpdk-next-net. Please apply.
v1->v2:
Takes care of the various comments made in the previous version.
I am dropping the style changes for now. I will send them later
after addressing the coding convention issues.
Ajit Khaparde (16):
net/bnxt: fix clear port stats
net/bnxt: a
Set ring coalesce parameters for Stratus NIC.
Other skews don't necessarily need this.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h| 19
drivers/net/bnxt/bnxt_ethdev.c | 11 +
drivers/net/bnxt/bnxt_hwrm.c | 51 +++
We are not cleaning up all the memory and also not unregistering
the driver during device close operation. This patch fixes the issue.
Fixes: 893074951314 ("net/bnxt: free memory in close operation")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: Remove incorrectly added RTE_PCI_DRV
Batch more than one Tx requests such that only one completion
is generarted by the HW. We request a Tx completion for first
and last Tx request in the batch.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_cpr.h | 12 ++
drivers/net/bnxt/bnxt_txq.h | 1 +
drivers/net/bnxt/bnxt_txr.c
Set MIN and MAX descriptor count for TX and RX rings.
Signed-off-by: Ajit Khaparde
--
v1->v2: fix commit log
---
drivers/net/bnxt/bnxt.h| 3 +++
drivers/net/bnxt/bnxt_ethdev.c | 4
2 files changed, 7 insertions(+)
diff --git a/drivers/net/bnxt/bnxt.h b/drivers/net/bnxt/bnxt.h
index
PORT_CLR_STATS is not allowed for VFs, NPAR, MultiHost functions
or when SR-IOV is enabled.
Don't send the HWRM command in such cases.
Fixes: bfb9c2260be2 ("net/bnxt: support xstats get/reset")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2: Fix a checkpatch warning.
---
drivers/net
1) Use nb_rx_pkts instead of checking producer indices of Rx and
aggregator rings to decide if any Rx completions were processed.
2) Post Rx buffers early in Rx processing instead of waiting for
the budgeted burst quota.
3) Ring Rx CQ DB after Rx buffers are posted.
Signed-off-by: Ajit Khaparde
-
On Tue, Jun 26, 2018 at 8:27 AM, Ferruh Yigit
wrote:
> On 6/19/2018 10:30 PM, Ajit Khaparde wrote:
> > Patchset against dpdk-next-net contains bug fixes,
> > some code refactoring and style cleanup.
> >
> > Please apply.
> >
> > Ajit Khaparde (15):
> > net/bnxt: fix clear port stats
> > net/b
On Tue, Jun 26, 2018 at 8:28 AM, Ferruh Yigit
wrote:
> On 6/19/2018 10:30 PM, Ajit Khaparde wrote:
> > Add support for StingRay VF device 0xd800
>
> Can you please document new supported device on doc/guides/nics/bnxt.rst
>
I think we don't need it. We are just adding another VF device id.
The a
On Tue, Jun 26, 2018 at 8:30 AM, Ferruh Yigit
wrote:
> On 6/19/2018 10:30 PM, Ajit Khaparde wrote:
> > There is no need to update hardware configuration if new MTU is
> > not greater than the max data the mbuf can accommodate.
>
> If app sets a smaller MTU won't it expect that HW will drop receiv
On Tue, Jun 26, 2018 at 8:30 AM, Ferruh Yigit
wrote:
> On 6/19/2018 10:30 PM, Ajit Khaparde wrote:
> > From: Rob Miller
> >
> > update HWRM API to v1.9.2.9
>
> Does it make sense to update release notes to document this update?
>
Since there are a few more weeks for release,
there is a good cha
https://bugs.dpdk.org/show_bug.cgi?id=56
Yongseok Koh (ys...@mellanox.com) changed:
What|Removed |Added
Status|CONFIRMED |RESOLVED
CC|
On 6/28/2018 1:32 AM, Rasesh Mody wrote:
> Fixes: c49a438fce90 ("doc: update qede guide and features")
> Fixes: db86fbe54d90 ("doc: update qede PMD NIC guide")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Rasesh Mody
Applied to dpdk-next-net/master, thanks.
On 06/28/2018 03:56 PM, Qi Zhang wrote:
Introduce API rte_eth_dev_lock and rte_eth_dev_unlock to let
application lock or unlock on specific ethdev, a locked device
can't be detached, this help applicaiton to prevent unexpected
device detaching, especially in multi-process envrionment.
I think t
On 06/28/2018 03:56 PM, Qi Zhang wrote:
We are going to introduce the solution to handle different hotplug
cases in multi-process situation, it include below scenario:
1. Attach a share device from primary
2. Detach a share device from primary
3. Attach a share device from secondary
4. Detach a
On Thu, Jun 28, 2018 at 06:01:21PM +0200, Nelio Laranjeiro wrote:
> Introduce an helper for PMD to expand easily flows items list with RSS
> action into multiple flow items lists with priority information.
>
> For instance a user items list being "eth / end" with rss action types
> "ipv4-udp ipv6-
On 6/28/2018 4:19 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Fix missing or incorrect packet types discovered by DTS.
> - Non-IP inner packets
> Set the tunnel flag.
> - Inner Ethernet packets
> All supported tunnel packets have Ethernet as inner packets. So, set
> INNER_L2_ETHER for
On 6/28/2018 4:19 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Signed-off-by: Hyong Youb Kim
> Reviewed-by: John Daley
<...>
> @@ -183,7 +183,9 @@ int enic_get_vnic_config(struct enic *enic)
>* Default hardware capabilities. enic_dev_init() may add additional
>* flags if i
On 6/28/2018 4:19 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Add a much-simplified handler that works when all offloads are
> disabled, except mbuf fast free. When compared against the default
> handler, under ideal conditions, cycles per packet drop by 60+%.
>
> By default, the driver tri
On 6/28/2018 4:19 AM, John Daley wrote:
> From: Hyong Youb Kim
>
> Add a new devarg "ig-vlan-rewrite" to allow the user to set
> non-default rewrite mode. The UCS VIC may add/remove/modify the VLAN
> header of an ingress packet depending on the ingress VLAN rewrite
> mode.
>
> By default, the dr
Introduce an helper for PMD to expand easily flows items list with RSS
action into multiple flow items lists with priority information.
For instance a user items list being "eth / end" with rss action types
"ipv4-udp ipv6-udp end" needs to be expanded into three items lists:
- eth
- eth / ipv4
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Thursday, June 28, 2018 11:16 PM
> To: Liu, Yong ; Bie, Tiwei
> Cc: Wang, Zhihong ; dev@dpdk.org
> Subject: Re: [PATCH v3 08/11] net/virtio: add in-order Rx/Tx into
> selection
>
>
>
> On 06/28/20
Hi Moti
I started to review it but not finished all :)
Please see some comments\questions,
I will continue the review again in the next version, after addressing the next
comments and Adrien comments.
From: Mordechay Haimovsky
> + * No TSO SIZE is defined in DPDK, need to figure it
On 06/28/2018 11:52 PM, Marvin Liu wrote:
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
On 06/28/2018 11:52 PM, Marvin Liu wrote:
Virtio vdev parameter mrg_rxbuf and in_order can configure
VIRTIO_NET_F_MRG_RXBUF and VIRTIO_F_IN_ORDER feature bits. These feature
bits can effect [RT]x path selection.
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
On 06/28/2018 11:52 PM, Marvin Liu wrote:
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
On 06/28/2018 11:52 PM, Marvin Liu wrote:
After IN_ORDER Rx/Tx paths added, need to update Rx/Tx path selection
logic.
Rx path select logic: If IN_ORDER is disabled will select normal Rx
path. If IN_ORDER is enabled, Rx offload and merge-able are disabled
will select simple Rx path. Otherwise
On 06/28/2018 11:52 PM, Marvin Liu wrote:
IN_ORDER Rx function depends on merge-able feature. Descriptors
allocation and free will be done in bulk.
Virtio dequeue logic:
dequeue_burst_rx(burst mbufs)
for (each mbuf b) {
if (b need merge) {
merge rem
From: Agalya Babu RadhaKrishnan
1.added new logtype for zuc driver.
2.registered new logtype.
3.ZUC_LOG_ERR and CDEV_LOG_ERR are
replaced with new logtype name ZUC_PMD_LOG
Signed-off-by: Agalya Babu RadhaKrishnan
Reviewed-by: Reshma Pattan
Reviewed-by: Pablo de Lara Guarch
---
On 6/28/2018 2:15 PM, Rafal Kozik wrote:
> Write combining (WC) increases NIC performance by making better
> utilization of PCI bus, but cannot be used by all PMDs.
>
> It will be enabled only if RTE_PCI_DRV_WC_ACTIVATE will be set in
> drivers flags. For proper work also igb_uio driver must be lo
On 06/28/2018 11:52 PM, Marvin Liu wrote:
IN_ORDER virtio-user Tx function support Tx checksum offloading and
TSO which also support on normal Tx function. So extracts common part
into separated function for reuse.
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
From: Chaitanya Babu Talluri
1.added new logtype for aesni_gcm driver.
2.registered new logtype.
3.GCM_LOG_ERR and CDEV_LOG_ERR are replaced with
new logtype name AESNI_GCM_PMD_LOG.
Signed-off-by: Chaitanya Babu Talluri
Reviewed-by: Reshma Pattan
Reviewed-by: Pablo de Lara Guarch
---
v2:
On 06/28/2018 11:52 PM, Marvin Liu wrote:
Add new function for freeing IN_ORDER descriptors. As descriptors will
be allocated and freed sequentially when IN_ORDER feature was
negotiated. There will be no need to utilize chain for freed descriptors
management, only index update is enough.
Sign
On 06/28/2018 11:52 PM, Marvin Liu wrote:
Add parameters for configuring VIRTIO_NET_F_MRG_RXBUF and
VIRTIO_F_IN_ORDER feature bits. If feature is disabled, also update
corresponding unsupported feature bit.
Signed-off-by: Marvin Liu
Reviewed-by: Maxime Coquelin
Thanks,
Maxime
On 06/28/2018 11:52 PM, Marvin Liu wrote:
This patch introduces unsupported features mask for virtio-user device.
For virtio-user server mode, when reconnecting virtio-user will retrieve
vhost device features as base and then unmask unsupported features.
Signed-off-by: Marvin Liu
Reviewed
On 06/28/2018 03:56 PM, Qi Zhang wrote:
Add driver API rte_eth_release_port_private to support the
requirement that an ethdev only be released on secondary process,
so only local state be set to unused , share data will not be
Extra space before comma above.
reset so primary process can still
On 06/28/2018 11:52 PM, Marvin Liu wrote:
If VIRTIO_F_IN_ORDER has been negotiated, driver will use descriptors in
ring order: starting from offset 0 in the table, and wrapping around at
the end of the table. Also introduce use_inorder_[rt]x flag for
selection of IN_ORDER [RT]x handlers.
Sign
On 06/28/2018 11:52 PM, Marvin Liu wrote:
If devices always use descriptors in the same order in which they have
been made available. These devices can offer the VIRTIO_F_IN_ORDER
feature. If negotiated, this knowledge allows devices to notify the use
of a batch of buffers to virtio driver by
On 6/28/2018 2:15 PM, Rafal Kozik wrote:
> Write combining (WC) increases NIC performance by making better
> utilization of PCI bus, but cannot be use by all PMDs.
>
> To get internal_addr memory need to be mapped. But as memory could not be
> mapped twice: with and without WC, it should be skippe
Hi Moti,
On Thu, Jun 28, 2018 at 03:48:57PM +0300, Moti Haimovsky wrote:
> Implement support for hardware TSO.
>
> Signed-off-by: Moti Haimovsky
I only glanced at the code but overall TSO logic appears to be sound;
assuming it went through non-regression I think it's OK. Please see below
for a
Hi Shally,
> -Original Message-
> From: Verma, Shally [mailto:shally.ve...@cavium.com]
> Sent: Thursday, June 28, 2018 2:40 PM
> To: De Lara Guarch, Pablo ; Doherty, Declan
> ; akhil.go...@nxp.com; ravi1.ku...@amd.com;
> Jacob, Jerin ; Zhang, Roy Fan
> ; Trahe, Fiona ;
> t...@semihalf.com;
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Wednesday, June 27, 2018 4:20 PM
> To: Liu, Yong ; Bie, Tiwei
> Cc: Wang, Zhihong ; dev@dpdk.org
> Subject: Re: [PATCH v2 7/8] net/virtio: add IN_ORDER Rx/Tx into selection
>
>
>
> On 06/25/2018 0
Signed-off-by: Marvin Liu
diff --git a/doc/guides/nics/virtio.rst b/doc/guides/nics/virtio.rst
index 46e292c4d..1b88cec96 100644
--- a/doc/guides/nics/virtio.rst
+++ b/doc/guides/nics/virtio.rst
@@ -201,7 +201,7 @@ The packet transmission flow is:
Virtio PMD Rx/Tx Callbacks
Virtio vdev parameter mrg_rxbuf and in_order can configure
VIRTIO_NET_F_MRG_RXBUF and VIRTIO_F_IN_ORDER feature bits. These feature
bits can effect [RT]x path selection.
Signed-off-by: Marvin Liu
diff --git a/doc/guides/nics/virtio.rst b/doc/guides/nics/virtio.rst
index a42d1bb30..46e292c4d 1006
Signed-off-by: Marvin Liu
diff --git a/drivers/net/virtio/virtio_ethdev.h
b/drivers/net/virtio/virtio_ethdev.h
index 8ab1267b0..69da18d9c 100644
--- a/drivers/net/virtio/virtio_ethdev.h
+++ b/drivers/net/virtio/virtio_ethdev.h
@@ -36,6 +36,7 @@
1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE | \
After IN_ORDER Rx/Tx paths added, need to update Rx/Tx path selection
logic.
Rx path select logic: If IN_ORDER is disabled will select normal Rx
path. If IN_ORDER is enabled, Rx offload and merge-able are disabled
will select simple Rx path. Otherwise will select IN_ORDER Rx path.
Tx path select
1 - 100 of 219 matches
Mail list logo
