Reviewed-by: Jiayu Hu
> -Original Message-
> From: Jiang, Cheng1
> Sent: Wednesday, March 17, 2021 1:41 PM
> To: maxime.coque...@redhat.com; Xia, Chenbo
> Cc: dev@dpdk.org; Hu, Jiayu ; Yang, YvonneX
> ; Wang, Yinan ; Jiang,
> Cheng1 ; sta...@dpdk.org
> Subject: [PATCH] examples/vhost: f
17/03/2021 00:34, Ferruh Yigit:
> On 3/16/2021 9:19 PM, Thomas Monjalon wrote:
> > 16/03/2021 20:18, Ferruh Yigit:
> >> On 3/11/2021 1:13 PM, Xueming Li wrote:
> >>> + # added in 21.05
> >>> + rte_eth_representor_info_get;
> >>
> >> New API documented in release notes, "API Changes" section, while
When parsing the virtio net header and packet header for dequeue offload,
we need to perform sanity check on the packet header to ensure:
- No out-of-boundary memory access.
- The packet header and virtio_net header are valid and aligned.
Fixes: d0cf91303d73 ("vhost: add Tx offload capabilitie
Add a specific path for RX AVX512 (flexible descriptor).
In this path, support the HW offload features, like,
checksum, VLAN stripping, RSS hash.
This path is chosen automatically according to the
configuration.
All the code for the above HW offload features is removed
from the legacy path.
Signe
Add a specific path for RX AVX512 (traditional).
In this path, support the HW offload features, like,
checksum, VLAN stripping, RSS hash.
This path is chosen automatically according to the
configuration.
All the code for the above HW offload features is removed
from the legacy path.
Signed-off-by
Add a specific path for TX AVX512.
In this path, support the HW offload features, like,
checksum insertion, VLAN insertion.
This path is chosen automatically according to the
configuration.
Signed-off-by: Wenzhuo Lu
---
drivers/net/iavf/iavf_rxtx.c| 50 ++
drivers/net/iavf/i
Add the offload flag for RX queues to know which offload
features are set.
Signed-off-by: Wenzhuo Lu
---
drivers/net/iavf/iavf_rxtx.c | 4
drivers/net/iavf/iavf_rxtx.h | 1 +
2 files changed, 5 insertions(+)
diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 8fa
Add specific paths for RX/TX AVX512, called offload paths.
In these paths, support the HW offload features, like,
checksum, VLAN, RSS offload.
These paths are chosen automatically according to the
configuration.
The code for the above HW offload features, which are
supported by offload paths, is r
On 3/16/21 8:38 PM, Ferruh Yigit wrote:
> On 3/12/2021 11:07 AM, Ivan Malov wrote:
>> One ought to reuse existing header structs in flow items.
>> This particular item contains non-header fields, so it's
>> important to keep the header fields in a separate struct.
>>
>
> Hi Ivan, Andrew, Thanks fo
Signed-off-by: Jiayu Hu
---
doc/guides/prog_guide/vhost_lib.rst | 13 ++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/doc/guides/prog_guide/vhost_lib.rst
b/doc/guides/prog_guide/vhost_lib.rst
index dc29229..333bd0a 100644
--- a/doc/guides/prog_guide/vhost_lib.rst
+++
Users register async copy device when vhost queue is enabled.
However, if VHOST_USER_F_PROTOCOL_FEATURES is not supported,
a deadlock occurs inside rte_vhost_async_channel_register(),
as vhost_user_msg_handler() already takes vq->access_lock
before processing VHOST_USER_SET_VRING_KICK message.
Thi
This patch removes unnecessary rte_free() for async_pkts_info
and async_descs_split.
Signed-off-by: Jiayu Hu
---
lib/librte_vhost/vhost_user.c | 7 ---
1 file changed, 7 deletions(-)
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index a60bb94..399675c 100644
---
This patch allocates vhost queue by rte_zmalloc() to avoid
undefined values.
Fixes: 8acd7c213353 ("vhost: fix virtqueues metadata allocation")
Signed-off-by: Jiayu Hu
---
lib/librte_vhost/vhost.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_vhost/vhost.c b/lib/
This patch set refactors async vhost control path.
Jiayu Hu (4):
vhost: fix uninitialized vhost queue
vhost: remove unnecessary free
vhost: avoid deadlock on async register
doc: update async vhost register/unregister
doc/guides/prog_guide/vhost_lib.rst | 13 ++---
lib/librte_vhos
On Tue, Mar 16, 2021 at 07:04:16PM +, Carrillo, Erik G wrote:
> Thanks, Shijith. I'm posting a couple of follow-up comments in-line:
>
> > -Original Message-
> > From: Shijith Thotton
> > Sent: Sunday, March 14, 2021 11:46 AM
> > To: Carrillo, Erik G
> > Cc: Shijith Thotton ; Pavan
On Tue, 16 Mar 2021 22:33:18 -0700
Tyler Retzlaff wrote:
> Add missing extern "C" linkage for rte_reciprocal.h consistent with
> other eal headers.
>
> Signed-off-by: Tyler Retzlaff
Looks good all exported headers should have this
Acked-by: Stephen Hemminger
Not enough memory be allocated for dev->data->mac_address which
cause out of bound memory access when iterate all mac addresses by
dev_info.max_mac_addrs.
Fixes: f9cf4f864150 ("net/ice: support device initialization")
Cc: sta...@dpdk.org
Reported-by: Ferruh Yigit
Signed-off-by: Qi Zhang
---
dr
We use ioat ring space for determining if ioat callbacks can enqueue a
packet to ioat device. But there is one slot can't be used in ioat
ring due to the ioat driver design, so we need to reduce one slot in
ioat ring to prevent ring size mismatch in ioat callbacks.
Fixes: 2aa47e94bfb2 ("examples/v
Add missing extern "C" linkage for rte_reciprocal.h consistent with
other eal headers.
Signed-off-by: Tyler Retzlaff
---
lib/librte_eal/include/rte_reciprocal.h | 8
1 file changed, 8 insertions(+)
diff --git a/lib/librte_eal/include/rte_reciprocal.h
b/lib/librte_eal/include/rte_recip
New FDIR parsing are added to handle the fragmented IPv4/IPv6 packet.
Signed-off-by: Jeff Guo
---
drivers/net/ice/ice_fdir_filter.c | 87 ++-
1 file changed, 73 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ice/ice_fdir_filter.c
b/drivers/net/ice/ice_fdir_
New pattern and RSS hash flow parsing are added to handle fragmented
IPv4/IPv6 packet.
Signed-off-by: Jeff Guo
---
drivers/net/ice/ice_generic_flow.c | 21 +
drivers/net/ice/ice_generic_flow.h | 6
drivers/net/ice/ice_hash.c | 48 +-
3 files
Add support for IP fragment RSS hash and FDIR according to packet ID.
Separate IP fragment and IP other packet types.
Signed-off-by: Ting Xu
Signed-off-by: Jeff Guo
---
drivers/net/ice/base/ice_fdir.c | 50 +++--
drivers/net/ice/base/ice_fdir.h | 22 ---
Support RSS hash and FDIR for IP fragment packets in ICE PMD.
Jeff Guo (3):
net/ice/base: support IP fragment RSS and FDIR
net/ice: support RSS hash for IP fragment
net/ice: support FDIR for IP fragment packet
drivers/net/ice/base/ice_fdir.c| 50 -
drivers/net/ice/base/
New FDIR parsing are added to handle the fragmented IPv4/IPv6 packet.
Signed-off-by: Ting Xu
Signed-off-by: Jeff Guo
---
drivers/net/iavf/iavf_fdir.c | 278 ++-
drivers/net/iavf/iavf_generic_flow.h | 5 +
2 files changed, 190 insertions(+), 93 deletions(-)
dif
New pattern and RSS hash flow parsing are added to handle fragmented
IPv4/IPv6 packet.
Signed-off-by: Ting Xu
Signed-off-by: Jeff Guo
---
drivers/net/iavf/iavf_generic_flow.c | 24
drivers/net/iavf/iavf_generic_flow.h | 3 +++
drivers/net/iavf/iavf_hash.c | 33 +++
Support RSS hash and FDIR for IP fragment packets in IAVF PMD.
Jeff Guo (4):
app/testpmd: add packet id for IP fragment
common/iavf: add proto header for IP fragment
net/iavf: support RSS hash for IP fragment
net/iavf: support FDIR for IP fragment packet
app/test-pmd/cmdline_flow.c
Add the new items to support the flow configuration for IP fragment
packets.
Signed-off-by: Ting Xu
Signed-off-by: Jeff Guo
---
app/test-pmd/cmdline_flow.c | 21 -
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/cmdline_flow.c b/app/test-pmd/cmdlin
Add new virtchnl protocol header type and fields for IP fragment packets
to support RSS hash and FDIR.
Signed-off-by: Ting Xu
Signed-off-by: Jeff Guo
---
drivers/common/iavf/virtchnl.h | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/common/iavf/virtchnl.h b/drivers/common/iavf/
The configure of TCP/UDP flow item should not affact other flow
configure which not include L4 layer. Fix and clean the protocol header
refinement function.
Fixes: 61abc5f611a0 ("net/iavf: support TCP/UDP flow item without input set")
Signed-off-by: Jeff Guo
---
v2:
fix coding style issue
---
d
在 2021/3/16 20:40, Ferruh Yigit 写道:
On 3/12/2021 11:51 AM, Min Hu (Connor) wrote:
From: Chengwen Feng
Currently, the driver support multiple IO burst function and auto
selection of the most appropriate function based on offload
configuration.
Most applications such as l2fwd/l3fwd don't pro
> -Original Message-
> From: Stephen Hemminger
> Sent: Wednesday, March 17, 2021 8:14 AM
> To: Suanming Mou
> Cc: dev@dpdk.org
> Subject: Re: [PATCH 1/2] ethdev: make flow API primary/secondary process safe
>
> On Tue, 16 Mar 2021 23:48:57 +
> Suanming Mou wrote:
>
> > Hi Stephe
On Tue, 16 Mar 2021 23:48:57 +
Suanming Mou wrote:
> Hi Stephen,
>
> > -Original Message-
> > From: Stephen Hemminger
> > Sent: Tuesday, March 16, 2021 3:27 AM
> > To: dev@dpdk.org
> > Cc: Stephen Hemminger ; Suanming Mou
> >
> > Subject: [PATCH 1/2] ethdev: make flow API primary/s
2021-03-16 12:09 (UTC+0100), Thomas Monjalon:
> 08/03/2021 19:32, Jie Zhou:
[...]
> > -Recommended version is either Meson 0.47.1 (baseline) or the latest
> > release.
> > +Recommended version is either Meson 0.57.0 (baseline) or the latest
> > release.
>
> I am OK with the change. What others
Hi Stephen,
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, March 16, 2021 3:27 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger ; Suanming Mou
>
> Subject: [PATCH 1/2] ethdev: make flow API primary/secondary process safe
>
> Posix mutex are not by default safe for protecti
On 3/16/2021 9:19 PM, Thomas Monjalon wrote:
16/03/2021 20:18, Ferruh Yigit:
On 3/11/2021 1:13 PM, Xueming Li wrote:
+ # added in 21.05
+ rte_eth_representor_info_get;
New API documented in release notes, "API Changes" section, while merging.
In general we don't mention new API
> -Original Message-
> From: Richardson, Bruce
> Sent: Tuesday, March 16, 2021 10:13 PM
> To: Thomas Monjalon
> Cc: Zhang, Qi Z ; Andrew Rybchenko
> ; Yigit, Ferruh ;
> dev@dpdk.org; Wang, Xiao W ; Wu, Jingjing
> ; Xing, Beilei ; Guo, Jia
> ; Yang, Qiming ; Wang, Haiyue
>
> Subject: R
In Windows probing, the value RTE_PCI_KDRV_NONE was used
instead of RTE_PCI_KDRV_UNKNOWN (mlx case),
and RTE_PCI_KDRV_NIC_UIO (FreeBSD) was re-used
instead of having a new RTE_PCI_KDRV_NET_UIO for Windows NetUIO.
While adding the new value RTE_PCI_KDRV_NET_UIO,
the enum of kernel driver categories
Hi Ivan,
> -Original Message-
> From: Ivan Malov
> Sent: Friday, March 12, 2021 11:32 AM
>
> One ought to reuse existing header structs in flow items.
> This particular item contains non-header fields, so it's
> important to keep the header fields in a separate struct.
>
> Signed-off-by
Hi Ivan,
> -Original Message-
> From: Ivan Malov
> Sent: Friday, March 12, 2021 11:32 AM
>
> One ought to reuse existing header structs in flow items.
> This particular item contains non-header fields, so it's
> important to keep the header fields in a separate struct.
>
> Signed-off-by
Add DLB v2.5 specific information such as credit metrics to xstats.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/dlb2_xstats.c | 41
1 file changed, 37 insertions(+), 4 deletions(-)
diff --git a/drivers/event/dlb2/dlb2_xstats.c b/drivers/event/dlb2/dlb
All references to the old register map have been removed,
so it is safe to rename the new combined file that supports
both DLB v2.0 and DLB v2.5. Also fixed all places where this
file is included.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_hw_types.h | 2
All dependencies on the old register map have been removed, so
it can now be deleted. The next commit will rename dlb2_regs_new.h
to dlb2_regs.h.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_regs.h | 2527
1 file changed, 2527 deletions(-)
delete
The original and a "new" file were maintained during the
early portions of the patch series in order to ensure that
all individual patches compiled cleanly. It is now safe to
rename the new file, and use it unconditionally in all DLB
source files.
Signed-off-by: Timothy McDaniel
---
.../event/dl
As support for DLB v2.5 was added, modifications were made to
dlb_hw_types_new.h, but the old file needed to be preserved during
the port in order to meet the requirement that individual patches in
a series each compile successfully. Since the DLB v2.5 support is
completely integrated, it is now sa
The file dlb_resource_new.c now contains all of the low level
functions required to support both DLB v2.0 and DLB v2.5, and
the original file (dlb_resource.c) was removed in the previous
commit, so rename dlb_resource_new.c to dlb_resource.c, and
update the meson build file so that the new file is
The file dlb_resource_new.c now contains all of the low level
functions required to support both DLB v2.0 and DLB v2.5, so
delete the temporary "old" file, and stop building it. The new
file (dlb_resource_new.c) will be renamed to dlb_resource.c in
the next commit.
Signed-off-by: Timothy McDaniel
A temporary version of dlb_resource.h (dlb_resource_new.h) was used
by the previous commits in this patch series. Merge the two files
now that DLB v2.5 support has been fully added to dlb_resource.c.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_osdep.h | 1 -
driver
Update sequence number management functions for DLB v2.5,
accounting for new combined register map and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 1 +
drivers/event/dlb2/pf/base/dlb2_resource.h| 4 +-
.../event/dlb2/pf/base
Update sparse cq mode mode functions for DLB v2.5, accounting for new
combined register map and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 22 ---
.../event/dlb2/pf/base/dlb2_resource_new.c| 39 +++
2 fi
Update low level hardware funcs with map/unmap interfaces,
accounting for new combined register file and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 1043 -
.../event/dlb2/pf/base/dlb2_resource_new.c| 50 +
2 f
Update get queue depth functions for DLB v2.5, accounting for
combined register map and new hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 29
.../event/dlb2/pf/base/dlb2_resource_new.c| 135 ++
2 files change
DLB v2.5 uses a different credit scheme than was used in DLB v2.0 .
Specifically, there is a single credit pool for both load balanced
and directed traffic, instead of a separate pool for each as is
found with DLB v2.0.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/dlb2.c | 311
Update low level functions to account for new register map
and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 123 -
.../event/dlb2/pf/base/dlb2_resource_new.c| 130 ++
2 files changed, 130 insertion
Update low level hardware functions to account for
new register map and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 355 ---
.../event/dlb2/pf/base/dlb2_resource_new.c| 418 ++
2 files changed, 418 in
Update low level functions to account for new register map
and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 331 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 298
2 files changed, 298 insertions
Updated low level hardware functions to account for new
register map and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 213 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 201 +
2 files changed, 201
Updated low level hardware functions to account for new
register map and access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 426 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 414 +
2 files changed, 414 insertio
Update create ldb port low level code to account for new
register map and hardware access macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 490 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 471 +
2 files changed, 47
Updated low level hardware functions to add DLB 2.5 support
for creating load balanced queues.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/pf/base/dlb2_resource.c| 397 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 391 +
2 files changed, 391 i
Convert to new register map and new register access
macros.
Signed-off-by: Timothy McDaniel
---
.../event/dlb2/pf/base/dlb2_hw_types_new.h|1 +
drivers/event/dlb2/pf/base/dlb2_resource.c| 1494 --
.../event/dlb2/pf/base/dlb2_resource_new.c| 2551 +
3 files
Update domain creation logic to account for DLB v2.5
credit scheme, new register map, and new register access
macros.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/dlb2_user.h| 13 +-
drivers/event/dlb2/pf/base/dlb2_resource.c| 645
.../event/dlb2/p
DLB v2.5 uses a new credit scheme, where directed and load balanced
credits are unified, instead of having separate directed and load
balanced credit pools.
Signed-off-by: Timothy McDaniel
---
drivers/event/dlb2/dlb2.c | 20 --
drivers/event/dlb2/dlb2_user.h
This commit adds dlb v2.5 probe support, and updates
parameter parsing.
The dlb v2.5 device differs from dlb v2, in that the
number of resources (ports, queues, ...) is different,
so macros have been added to take the device version
into account.
This commit also cleans up a few issues in the ori
This patch series adds support for DLB v2.5 to
the current DLB V2.0 PMD. The resulting PMD supports
both hardware versions.
The main differences between the DLB v2.5 and v2.0 hardware
are:
- Number of queues/ports
- DLB v2.5 uses a combined credit pool, whereas DLB v2.0
splits credits into 2 poo
04/03/2021 08:14, Dmitry Kozlyuk:
> 2021-02-28 22:52, Khoa To:
> > EAL -a and -b options are used to specify which PCI devices are
> > explicitly allowed or blocked during PCI bus scan. This evaluation
> > is missing in the Windows implementation of rte_pci_scan.
> >
> > This patch provides this
16/03/2021 20:18, Ferruh Yigit:
> On 3/11/2021 1:13 PM, Xueming Li wrote:
> > + # added in 21.05
> > + rte_eth_representor_info_get;
>
> New API documented in release notes, "API Changes" section, while merging.
In general we don't mention new API in release notes.
What is the intent Ferruh?
This file has redundant BSD license text that is already
replaces by the use of SPDX license id. Having both is unnecessary
and potentially confusing.
Signed-off-by: Stephen Hemminger
---
app/test/test_timer_racecond.c | 26 --
1 file changed, 26 deletions(-)
diff --git
Trivial file, but add SPDX license tag per policy
Signed-off-by: Stephen Hemminger
---
doc/guides/custom.css | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/custom.css b/doc/guides/custom.css
index c87c60611929..a1572eaf9da6 100644
--- a/doc/guides/custom.css
+++ b/doc/guides/cust
The JSON file format does not support comments so there is no good
way to add SPDX license identifier. This solves false positives
that arrive from the use of JSON in crypto dev tests.
Signed-off-by: Stephen Hemminger
---
devtools/check-spdx-tag.sh | 2 +-
1 file changed, 1 insertion(+), 1 dele
These files were added without requires SPDX headers.
Fixes: 7525ebd8ebb0 ("common/mlx5: add glue functions on Windows")
Cc: tal...@nvidia.com
Signed-off-by: Stephen Hemminger
---
drivers/common/mlx5/windows/mlx5_win_defs.h | 4 ++--
drivers/common/mlx5/windows/mlx5_win_ext.h | 4 ++--
2 files
This resolves all the left over warnings and errors reported
by the check-spdx-tag script.
Stephen Hemminger (4):
common/mlx5: add missing SPDX tag for windows headers
devtools/check-spdx-tag.sh: ignore JSON files
doc: add SPDX tag to custom CSS file
app/test: remove license boilerplate
2021-03-16 11:59 (UTC-0700), Stephen Hemminger:
> On Sun, 14 Feb 2021 05:16:11 +0300
> Dmitry Kozlyuk wrote:
>
> > +rte_time_get_us(struct rte_time_us *now)
> > +{
> > + struct timeval sys;
> > +
> > + gettimeofday(&sys, NULL);
> > + now->sec = sys.tv_sec;
> > + now->usec = sys.tv_usec;
>
From: Pavan Nikhilesh
Include vector configuration into the structure
``rte_event_eth_rx_adapter_queue_conf`` used when configuring rest
of the Rx adapter ethernet device Rx queue parameters.
This simplifies event vector configuration as it avoids splitting
configuration per Rx queue.
Signed-off
From: Pavan Nikhilesh
The Rx adapter event vector configuration will be merged into
Rx adapter queue configuration to simplify enabling event
vectorization.
Signed-off-by: Pavan Nikhilesh
---
doc/guides/rel_notes/deprecation.rst | 9 +
1 file changed, 9 insertions(+)
diff --git a/doc/
From: Pavan Nikhilesh
Add event vector support in pipeline tests. By default this mode
is disabled, it can be enabled by using the option --enable_vector.
example:
dpdk-test-eventdev -l 7-23 -s 0xff00 -- --prod_type_ethdev
--nb_pkts=0 --verbose 2 --test=pipeline_atq --stlist=a
From: Pavan Nikhilesh
Add event vector support for event eth Tx adapter, the implementation
receives events from the single linked queue and based on
rte_event_vector::union_valid transmits the vector of mbufs to a given
port, queue pair.
Signed-off-by: Pavan Nikhilesh
---
.../rte_event_eth_tx
From: Pavan Nikhilesh
Add event vector support for event eth Rx adapter, the implementation
creates vector flows based on port and queue identifier of the received
mbufs.
Signed-off-by: Pavan Nikhilesh
---
lib/librte_eventdev/eventdev_pmd.h| 60 ++-
.../rte_event_eth_rx_adapter.c
From: Pavan Nikhilesh
Introduce event vector transmit capability for event eth
tx adapter.
The capability indicates that the Tx adapter is capable of
transmitting event vectors.
When rte_event_vector::union_valid is set, the Tx adapter should
transmit all the packets to the rte_event_vector::por
From: Pavan Nikhilesh
Introduce event ethernet Rx adapter event vector capability.
If an event eth Rx adapter has the capability of
RTE_EVENT_ETH_RX_ADAPTER_CAP_EVENT_VECTOR then a given Rx queue
can be configured to enable event vectorization by passing the
flag RTE_EVENT_ETH_RX_ADAPTER_QUEUE_E
From: Pavan Nikhilesh
Introduce rte_event_vector datastructure which is capable of holding
multiple uintptr_t of the same flow thereby allowing applications
to vectorize their pipeline and reducing the complexity of pipelining
the events across multiple stages.
This approach also reduces the sche
From: Pavan Nikhilesh
In traditional event programming model, events are identified by a
flow-id and a uintptr_t. The flow-id uniquely identifies a given event
and determines the order of scheduling based on schedule type, the
uintptr_t holds a single object.
Event devices also support burst mod
On 3/11/2021 1:13 PM, Xueming Li wrote:
SubFunction [1] is a portion of the PCI device, a SF netdev has its own
dedicated queues(txq, rxq). A SF netdev supports E-Switch representation
offload similar to existing PF and VF representors. A SF shares PCI
level resources with other SFs and/or with i
On 3/11/2021 1:13 PM, Xueming Li wrote:
The NIC can have multiple PCIe links and can be attached to multiple
hosts, for example the same single NIC can be shared for multiple server
units in the rack. On each PCIe link NIC can provide multiple PFs and
VFs/SFs based on these ones. The full represe
>On Tue, Mar 16, 2021 at 9:19 PM wrote:
>>
>> From: Pavan Nikhilesh
>>
>> Introduce rte_event_vector datastructure which is capable of holding
>> multiple uintptr_t of the same flow thereby allowing applications
>> to vectorize their pipeline and reducing the complexity of pipelining
>> the event
Thanks, Shijith. I'm posting a couple of follow-up comments in-line:
> -Original Message-
> From: Shijith Thotton
> Sent: Sunday, March 14, 2021 11:46 AM
> To: Carrillo, Erik G
> Cc: Shijith Thotton ; Pavan Nikhilesh
> ; Jerin Jacob ;
> dev@dpdk.org
> Subject: [PATCH v2 1/3] eventdev: i
On Sun, 14 Feb 2021 05:16:11 +0300
Dmitry Kozlyuk wrote:
> +rte_time_get_us(struct rte_time_us *now)
> +{
> + struct timeval sys;
> +
> + gettimeofday(&sys, NULL);
> + now->sec = sys.tv_sec;
> + now->usec = sys.tv_usec;
> +}
Why would drivers want the default (wall clock) time in
On 15/03/2021 11:34, Conor Walsh wrote:
This patch implements the Forwarding Information Base (FIB) library
in l3fwd using the function calls and infrastructure introduced in
the previous patch.
Signed-off-by: Conor Walsh
Acked-by: Konstantin Ananyev
---
examples/l3fwd/l3fwd_fib.c | 480 +
On 3/16/2021 6:35 PM, Elad Nachman wrote:
Hi,
Owing to my current development schedule and obligations, I see no opportunity
to make this set of changes in the near future.
I can do on top of your work if you don't mind?
Sorry,
Elad.
בתאריך יום ב׳, 15 במרץ 2021, 19:17, מאת Ferruh Yigit
Hi,
Owing to my current development schedule and obligations, I see no
opportunity to make this set of changes in the near future.
Sorry,
Elad.
בתאריך יום ב׳, 15 במרץ 2021, 19:17, מאת Ferruh Yigit <
ferruh.yi...@intel.com>:
> On 2/25/2021 2:32 PM, Elad Nachman wrote:
> > This part of the seri
This patch adds tests for predictable RSS feature
Signed-off-by: Vladimir Medvedkin
---
app/test/test_thash.c | 383 +-
1 file changed, 377 insertions(+), 6 deletions(-)
diff --git a/app/test/test_thash.c b/app/test/test_thash.c
index a6aadd1..e55
This patch implements predictable RSS functionality.
Signed-off-by: Vladimir Medvedkin
---
lib/librte_hash/rte_thash.c | 532 ++--
1 file changed, 516 insertions(+), 16 deletions(-)
diff --git a/lib/librte_hash/rte_thash.c b/lib/librte_hash/rte_thash.c
in
This patch adds predictable RSS API.
It is based on the idea of searching partial Toeplitz hash collisions.
Signed-off-by: Vladimir Medvedkin
---
lib/librte_hash/meson.build | 3 +-
lib/librte_hash/rte_thash.c | 96 ++
lib/librte_hash/rte_thash.h | 138
This patch series introduces predictable RSS feature.
It is based on the idea of searching for partial hash collisions
within Toeplitz hash.
The Toeplitz hash function is a homomorphism between (G, ^) and (H, ^),
where (G, ^) - is a group of tuples and (H, ^) is a group of hashes
with respect to X
On Tue, Mar 16, 2021 at 9:19 PM wrote:
>
> From: Pavan Nikhilesh
>
> Introduce rte_event_vector datastructure which is capable of holding
> multiple uintptr_t of the same flow thereby allowing applications
> to vectorize their pipeline and reducing the complexity of pipelining
> the events across
On 3/12/2021 11:07 AM, Ivan Malov wrote:
One ought to reuse existing header structs in flow items.
This particular item contains non-header fields, so it's
important to keep the header fields in a separate struct.
Hi Ivan, Andrew, Thanks for following this up and updates.
For record, existing
On 3/12/2021 11:07 AM, Ivan Malov wrote:
One ought to reuse existing header structs in flow items.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Ferruh Yigit
On 3/12/2021 11:07 AM, Ivan Malov wrote:
These fields have network byte order. Highlight it using dedicated type.
Signed-off-by: Ivan Malov
Reviewed-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Ferruh Yigit
On 3/16/2021 5:10 PM, Ivan Malov wrote:
Hi,
> WARNING:TYPO_SPELLING: 'referes' may be misspelled - perhaps 'refers'?
> #652: FILE: drivers/net/sfc/sfc_mae.c:2407:
> + /* One of the pointers (ipv4, ipv6) referes to a dummy area. */
It looks like an oversight. What a terrible typo. Ferruh,
+Cc Akhil, Anoob, Konstantin, Radu & Declan
16/03/2021 17:28, Slava Ovsiienko:
> The DPDK ethernet device might support the offload for security
> operations. Since ConnectX-6DX the hardware implements the
> cryptographic options required to provide the IPsec protocol
> offload and there is an int
Hi,
> WARNING:TYPO_SPELLING: 'referes' may be misspelled - perhaps 'refers'?
> #652: FILE: drivers/net/sfc/sfc_mae.c:2407:
> + /* One of the pointers (ipv4, ipv6) referes to a dummy area. */
It looks like an oversight. What a terrible typo. Ferruh, shall I send
v4 to fix that? I sincerely apol
1 - 100 of 229 matches
Mail list logo
