> -Original Message-
> From: dev On Behalf Of Jens Freimann
> Sent: Friday, September 7, 2018 2:20 AM
> To: dev@dpdk.org
> Cc: tiwei@intel.com; maxime.coque...@redhat.com
> Subject: [dpdk-dev] [PATCH v5 07/11] net/virtio: implement transmit path
> for packed queues
>
> This implemen
The field, 'cipher_iv.data' is allocated twice when cipher is not null.
Ideally the allocation should depend only on the field
'cperf_options.cipher_iv_sz'. This will make sure this code path gets
valid for ciphers which doesn't require IV.
Fixes: 0fbd75a99fc9 ("cryptodev: move IV parameters to se
Hi Tiwei,
On 09/05/2018 01:55 AM, Tiwei Bie wrote:
When VIRTIO_RING_F_EVENT_IDX is negotiated, we need to
update the avail event to enable the notification.
Fixes: 3f8ff12821e4 ("vhost: support interrupt mode")
Cc: sta...@dpdk.org
Signed-off-by: Tiwei Bie
---
lib/librte_vhost/Makefile | 1
Checked on ppc64, the build process is successful.
> -Original Message-
> From: Luca Boccassi [mailto:bl...@debian.org]
> Sent: 2018年9月8日 2:35
> To: dev@dpdk.org
> Cc: chao...@linux.vnet.ibm.com; christian.ehrha...@canonical.com;
> bruce.richard...@intel.com; tho...@monjalon.net
> Subject
Hi Maxime,
On Mon, Sep 10, 2018 at 09:22:00AM +0200, Maxime Coquelin wrote:
> Hi Tiwei,
>
> On 09/05/2018 01:55 AM, Tiwei Bie wrote:
> > When VIRTIO_RING_F_EVENT_IDX is negotiated, we need to
> > update the avail event to enable the notification.
> >
> > Fixes: 3f8ff12821e4 ("vhost: support inte
On 09/10/2018 09:36 AM, Tiwei Bie wrote:
Hi Maxime,
On Mon, Sep 10, 2018 at 09:22:00AM +0200, Maxime Coquelin wrote:
Hi Tiwei,
On 09/05/2018 01:55 AM, Tiwei Bie wrote:
When VIRTIO_RING_F_EVENT_IDX is negotiated, we need to
update the avail event to enable the notification.
Fixes: 3f8ff128
On 09/04/2018 12:12 PM, Ferruh Yigit wrote:
diff --git a/drivers/net/vhost/rte_eth_vhost.c
b/drivers/net/vhost/rte_eth_vhost.c
index e58f32211..aa6052221 100644
--- a/drivers/net/vhost/rte_eth_vhost.c
+++ b/drivers/net/vhost/rte_eth_vhost.c
@@ -1070,8 +1070,7 @@ eth_dev_info(struct rte_eth_de
On 09/08/2018 02:39 AM, Thomas Monjalon wrote:
After closing a port, it cannot be restarted.
So there is no reason to not free all associated resources.
The last step was done with rte_eth_dev_detach() which is deprecated.
Instead of removing the associated rte_device, the driver should check
if
On 09/10/2018 08:18 AM, David Marchand wrote:
__rte_mbuf_raw_free and __rte_pktmbuf_prefree_seg have been deprecated for
a long time now (early 17.05), are not part of the abi and are easily
replaced with existing api.
Signed-off-by: David Marchand
Acked-by: Andrew Rybchenko
On 09/10/2018 08:45 AM, David Marchand wrote:
Let's add a little helper that does the same as rte_mbuf_sanity_check but
without the panic.
Signed-off-by: David Marchand
---
<...>
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index a50b05c64..e12a4c765 100644
--- a/lib
On Mon, Sep 10, 2018 at 10:12 AM, Andrew Rybchenko
wrote:
> +/**
> + * Sanity checks on a mbuf.
> + *
> + * Almost like rte_mbuf_sanity_check(), but this function gives the reason
> + * if corruption is detected rather than panic.
> + *
> + * @param m
> + * The mbuf to be checked.
> + * @param i
On 09/10/2018 11:24 AM, David Marchand wrote:
On Mon, Sep 10, 2018 at 10:12 AM, Andrew Rybchenko
wrote:
+/**
+ * Sanity checks on a mbuf.
+ *
+ * Almost like rte_mbuf_sanity_check(), but this function gives the reason
+ * if corruption is detected rather than panic.
+ *
+ * @param m
+ * The m
10/09/2018 10:03, Andrew Rybchenko:
> On 09/08/2018 02:39 AM, Thomas Monjalon wrote:
> > After closing a port, it cannot be restarted.
> > So there is no reason to not free all associated resources.
> >
> > The last step was done with rte_eth_dev_detach() which is deprecated.
> > Instead of removin
On 09/10/2018 11:42 AM, Thomas Monjalon wrote:
10/09/2018 10:03, Andrew Rybchenko:
On 09/08/2018 02:39 AM, Thomas Monjalon wrote:
After closing a port, it cannot be restarted.
So there is no reason to not free all associated resources.
The last step was done with rte_eth_dev_detach() which is
On 09/06/2018 03:01 PM, Dekel Peled wrote:
Patch 5355f443 added two definitions of DEV_TX_OFFLOAD_xxx.
If new Tx offload capabilities are defined, they also must be mentioned
in rte_tx_offload_names in rte_ethdev.c file.
This patch adds the required lines in aray rte_tx_offload_names.
Fixes: 53
From: Andrew Jackson
EF10 signed image layout header is generated from firmware sources.
Signed-off-by: Andrew Jackson
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_signed_image_layout.h | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/net/sfc/base/ef10_sign
From: Martin Harvey
Found by PreFAST warnings.
Fixes: 3f2f0189dd44 ("net/sfc/base: add signed image layout support")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_image.c | 3 ++-
drivers/net/sfc/base/efx.h| 3 ++-
2 fi
From: Martin Harvey
Found by PreFAST.
Fixes: 3f2f0189dd44 ("net/sfc/base: add signed image layout support")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_image.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git
Update net/sfc base driver (aka libefx).
There are a number of checkpatches.sh warnings/errors
because of coding style difference.
Andrew Jackson (1):
net/sfc/base: highlight that image layout header generated
Andrew Rybchenko (1):
net/sfc/base: fix build failure because of no declaration
A
From: Andy Moreton
Fixes: 19b64c6ac35f ("net/sfc/base: import libefx base")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_nic.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/sfc/base/efx_nic.c b/d
From: Martin Harvey
Fixes: d96a34d165b1 ("net/sfc/base: import NVRAM support")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h | 2 +-
drivers/net/sfc/base/ef10_nvram.c | 2 +-
drivers/net/sfc/base/efx_impl.h | 2 +-
dri
From: Martin Harvey
Fixes: 19b64c6ac35f ("net/sfc/base: import libefx base")
Fixes: d96a34d165b1 ("net/sfc/base: import NVRAM support")
Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
driv
From: Martin Harvey
Move empty definitions for platform-specific annotations from efsys.h
to EFX headers.
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Lee
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h| 1 +
drivers/net/sfc/base/efx_annote.h | 101
Functions declared in mcdi_mon.h are implemented in mcdi_mon.c.
The build fails if compiler options require declaration before definition.
Fixes: dfb3b1ce15f6 ("net/sfc/base: import monitors access via MCDI")
Cc: sta...@dpdk.org
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/mcdi_mon.
From: Vijay Srivastava
Fixes: 912e603706c5 ("net/sfc/base: add outer IP ID parameter to TSOv2
descriptor")
Cc: sta...@dpdk.org
Signed-off-by: Vijay Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_tx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
dif
From: Andy Moreton
Required by GLD cstyle.
Fixes: d4f4b8f9d260 ("net/sfc/base: make RxQ type data an union")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_rx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
From: Vijay Srivastava
Fixes: 17551f6dffcc ("net/sfc/base: add API to control UDP tunnel ports")
Cc: sta...@dpdk.org
Signed-off-by: Vijay Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_nic.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drive
From: Mark Spender
No need for probe messages when a TxQ is too full for a post to be done.
Existing drivers check if there is room in the queue before posting
descriptors, even though efx_tx_qdesc_post() does the check itself.
The new SFN Windows driver doesn't perform the check before calling
From: Paul Fox
Add definitions of dynamic config and expansion ROM backup
partitions.
Signed-off-by: Paul Fox
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_nvram.c | 2 ++
drivers/net/sfc/base/efx.h| 2 ++
2 files changed, 4 insertions(+)
diff --git a/drivers/net/sfc/
From: Martin Harvey
Remove obsolete monitor types since Falcon SFN4000 series adapters
no longer supported by libefx.
Rename MCDI monitors to be consistent with YML.
The code may be simplified and generalized since only MCDI monitors
remain.
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Ry
From: Martin Harvey
Size of provided memory should be consistent with specified size.
Fixes: dfb3b1ce15f6 ("net/sfc/base: import monitors access via MCDI")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/mcdi_mon.c | 11 +++
1
From: Martin Harvey
Found by PreFAST static analysis.
Fixes: 1dae25112a54 ("net/sfc/base: import built-in selftest")
Fixes: d96a34d165b1 ("net/sfc/base: import NVRAM support")
Cc: sta...@dpdk.org
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_phy.c
From: Martin Harvey
Description of sensors is generated from firmware sources.
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 5 +
drivers/net/sfc/base/efx_mcdi.h| 4 +
drivers/net/sfc/base/efx_mon.c |
From: Richard Houldsworth
Extend efx_mcdi_get_port_modes() to optionally pass on the default
port mode field. This provides a more direct way of handling the case
where the dynamic config does not specify the port mode than the
alternative of a lookup table indexed by MCFW subtype.
Signed-off-by
From: Andy Moreton
The efx_nic_hw_unavailable() checks ensure that if the NIC hardware
has failed or has been physically removed then libefx will stop
further attempts to access the hardware.
Add an interface for libefx clients to force unavailability, so the
hardware is treated as dead or remov
From: Martin Harvey
Signed-off-by: Martin Harvey
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 12 +++
drivers/net/sfc/base/efx_impl.h | 2 +
drivers/net/sfc/base/efx_mon.c | 17 +++-
drivers/net/sfc/base/mcdi_mon.c | 171
drivers/n
From: Richard Houldsworth
The SFN driver's PartitionControl WMI object requires an API to parse
and filter partition data in TLV format, particularly for the Dynamic
Config partition. The ef10_nvram_buffer functions provide this
functionality but are tied to use with license partition only.
Modif
From: Andy Moreton
Fixes: 05fce2ce8451 ("net/sfc/base: import libefx licensing")
Fixes: f67e4719147d ("net/sfc/base: fix coding style")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_lic.c | 39 --
1
From: Andy Moreton
Add efx_nic_hw_unavailable() routine to check for hardware presence
before continuing with NIC operations.
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 10 ++
drivers/net/sfc/base/ef10_impl.h | 4
drivers/n
From: Mark Spender
In SF bug 61297 it's been confirmed that the hardware does not always
calculate the TCP checksum correctly with TSO sends.
The value of the Total Length field (IPv4) or Payload Length field
(IPv6) is the critical factor. We're sufficiently confident that if
these fields are ze
From: Richard Houldsworth
Functions to process the DHCP option list format used by the expansion
ROM config buffers, to support extracting and updating of individual
options.
The initial use case is the driver presenting the global and per-PF
options as separate items, with the driver implementin
From: Ivan Malov
The function used to retrieve supported RSS flags has an
argument which should be named properly to indicate
that it's a pointer.
Fixes: 613cbe75ae99 ("net/sfc/base: add a new means to control RSS hash")
Cc: sta...@dpdk.org
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybch
From: Ivan Malov
Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
Cc: sta...@dpdk.org
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_filter.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/sfc/base/ef
From: Mark Spender
NIC config is initialized during NIC probe.
Fixes: 19b64c6ac35f ("net/sfc/base: import libefx base")
Cc: sta...@dpdk.org
Signed-off-by: Mark Spender
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_nic.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drive
From: Ivan Malov
The API which is used to list supported hash flags verifies
hash algorithm choice before writing the output. This check
is based on a switch() statement which has only two options
and no distinctive actions to be conducted for each of them.
Use simpler code instead of switch() to
From: Gautam Dawar
Introduce and use macro to make sure that MCDI buffers allocated
on stack are rounded up properly.
Fixes: 6f619653b9b1 ("net/sfc/base: import MCDI implementation")
Fixes: f7dc06bf35f2 ("net/sfc/base: import 5xxx/6xxx family support")
Fixes: e7cd430c864f ("net/sfc/base: import
From: Ivan Malov
RSS mode bits can be accessed a lot easier in the hash
type value provided that the variable type is uint32_t.
The macro helper can be removed to enhance readability.
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_rx.c | 24 ++-
From: Richard Houldsworth
The capability bits to request FEC modes are implicitly valid
when the corresponding FEC mode is a supported capability.
Drivers expect that it is only valid to advertise those
capabilities explicitly marked as supported. The capabilities
reported by firmware is modified
From: Vijay Srivastava
Signed-off-by: Vijay Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h | 6
drivers/net/sfc/base/ef10_phy.c | 60 +---
drivers/net/sfc/base/efx.h | 11 ++
drivers/net/sfc/base/efx_impl.h | 1 +
From: Ivan Malov
The efx_rx_scale_hash_flags_get interface is unsafe, as it does not
have an argument for the size of the output buffer used to return
the flags. While the only caller currently supplies a sufficiently
large buffer, this should be checked at runtime to avoid writing
past the end o
From: Ivan Malov
Client drivers may use either legacy flags, for example,
EFX_RX_HASH_TCPIPV4, or generalised flags, for example,
EFX_RX_HASH(IPV4_TCP, 4TUPLE), to configure RSS hash.
The libefx is able to recognise what scheme is used.
Legacy flags may be consumed directly by a chip-specific ha
From: Andy Moreton
This statistic should include 64byte and smaller frames.
Fix EF10 calculation to match Siena code.
Fixes: 8c7c723dfe7c ("net/sfc/base: import MAC statistics")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_mac.
From: Vijay Srivastava
Signed-off-by: Vijay Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h| 18 ++-
drivers/net/sfc/base/efx_filter.c | 90 +++
2 files changed, 95 insertions(+), 13 deletions(-)
diff --git a/drivers/net/sfc/ba
One more comment:
> -Original Message-
> From: dev On Behalf Of Jens Freimann
> Sent: Friday, September 7, 2018 2:20 AM
> To: dev@dpdk.org
> Cc: tiwei@intel.com; maxime.coque...@redhat.com
> Subject: [dpdk-dev] [PATCH v5 07/11] net/virtio: implement transmit path
> for packed queues
>
Right now, vector path is limited to only use on later platform.
This patch adds a devarg use-latest-vec to allow the users to
use the latest vector path that the platform supported. Namely,
using AVX2 vector path on broadwell is possible.
Signed-off-by: Xiaoyun Li
---
v4:
* Polish the codes.
v3
On Fri, Sep 07, 2018 at 05:11:21PM +, Shubhachint, Chaitanya wrote:
> Thank you for your reply Bruce.
> Still having issues with shared-lib DPDK. I tried both options and get two
> distinct issues.
> I tried running the l2fwd example with e1000 driver and get little farther.
> This time it
On Fri, Sep 07, 2018 at 07:35:02PM +0100, Luca Boccassi wrote:
> This has been only build-tested for now, on a native ppc64el POWER8E
> machine running Debian sid.
>
> Signed-off-by: Luca Boccassi
> ---
> The build box cannot be used to run DPDK as it doesn't have supported
> NICs and root access
> -Original Message-
> From: dev On Behalf Of Jens Freimann
> Sent: Friday, September 7, 2018 2:20 AM
> To: dev@dpdk.org
> Cc: tiwei@intel.com; maxime.coque...@redhat.com
> Subject: [dpdk-dev] [PATCH v5 08/11] net/virtio: implement receive path for
> packed queues
>
> Implement the
On 9/4/2018 7:21 AM, Shahaf Shuler wrote:
> Tuesday, August 28, 2018 9:59 PM, Yongseok Koh:
>> wrapping
>>
>>> On Aug 23, 2018, at 4:10 PM, Xueming Li wrote:
>>>
>>> Rxq cq_ci was 16 bits while hardware is expecting to wrap around 24
>>> bits, this caused interrupt failure after burst of packets.
IFCVF can help to log dirty page in live migration stage,
each queue's index can be read and configured to support
VHOST_USER_GET_VRING_BASE and VHOST_USER_SET_VRING_BASE.
Signed-off-by: Xiao Wang
---
drivers/net/ifc/base/ifcvf.c | 33 +++-
drivers/net/ifc/base/ifcvf.h | 7 +
For szedata2:
Acked-by: Jan Remes
Thanks, Jan
> --- a/drivers/net/szedata2/rte_eth_szedata2.c
> +++ b/drivers/net/szedata2/rte_eth_szedata2.c
> @@ -1056,8 +1056,7 @@ eth_dev_info(struct rte_eth_dev *dev,
> dev_info->max_rx_queues = internals->max_rx_queues;
> dev_info->max_tx_qu
Fixes: a3f8150eac6d ("net/ifcvf: add ifcvf vDPA driver")
Signed-off-by: Xiao Wang
---
drivers/net/ifc/ifcvf_vdpa.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ifc/ifcvf_vdpa.c b/drivers/net/ifc/ifcvf_vdpa.c
index 3c5430dc0..7d3085d8d 100644
--- a/drive
This has been only build-tested for now, on a native ppc64el POWER8E
machine running Debian sid.
Signed-off-by: Luca Boccassi
---
v2: fix indentation, drop march_opt in ppc build file
config/meson.build | 10 +-
config/ppc_64/meson.build
On Mon, 2018-09-10 at 11:50 +0100, Bruce Richardson wrote:
> On Fri, Sep 07, 2018 at 07:35:02PM +0100, Luca Boccassi wrote:
> > This has been only build-tested for now, on a native ppc64el
> > POWER8E
> > machine running Debian sid.
> >
> > Signed-off-by: Luca Boccassi
> > ---
> > The build box c
Hi
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ziye Yang
> Sent: Wednesday, September 5, 2018 6:39 AM
> To: dev@dpdk.org
> Cc: Ziye Yang
> Subject: [dpdk-dev] [PATCH v5] linuxapp, eal: Fix the memory leak issue of
> logid
>
> From: Ziye Yang
>
> This p
Hi Konstantin,
The global logid is used to prevent the memory leak. If we do not do this, but
directly free(logid), this pointer will still be used by openlog, which means
that we cannot free the logid anymore. And by adding the global variable, it
will not only solve the memory leak but also m
On 9/6/2018 5:56 PM, Juhamatti Kuusisaari wrote:
> Support for PCAP physical interface MAC with phy_mac=1 devarg.
>
> Signed-off-by: Juhamatti Kuusisaari
Hi Juhamatti,
Thanks for the patch.
Can you please add a little more details into commit log that why this new
feature is enabled, what is t
-Original Message-
>
> Removed DEV_RX_OFFLOAD_CRC_STRIP offload flag.
> Without any specific Rx offload flag, default behavior by PMDs is to
> strip CRC.
>
> PMDs that support keeping CRC should advertise DEV_RX_OFFLOAD_KEEP_CRC
> Rx offload capability.
>
> Applications that require keep
> -Original Message-
> From: Yang, Ziye
> Sent: Monday, September 10, 2018 12:58 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Ziye Yang
> Subject: RE: [dpdk-dev] [PATCH v5] linuxapp, eal: Fix the memory leak issue
> of logid
>
> Hi Konstantin,
>
> The global logid is used to pre
Hi Konstantin,
Thanks for your comments. I will revise the patch and submit another patch
later.
Best Regards
Ziye Yang
-Original Message-
From: Ananyev, Konstantin
Sent: Monday, September 10, 2018 8:19 PM
To: Yang, Ziye ; dev@dpdk.org
Cc: Ziye Yang
Subject: RE: [dpdk-dev] [PATCH
Will DSW be included in 18.11?
/M
On 2018-08-30 16:27, Mattias Rönnblom wrote:
The DSW event device is documented in DPDK Programmer's Guide.
Signed-off-by: Mattias Rönnblom
---
doc/guides/eventdevs/dsw.rst | 97 ++
doc/guides/eventdevs/index.rst | 1 +
On 08/24/2018 09:43 AM, Rami Rosen wrote:
This patch fixes wrong usage of bind command in vhost.rst.
Using "dpdk-devbind.py -b=uio_pci_generic :00:04.0" gives
an error of "unbind failed". It should be "-b uio_pci_generic" so
it will work correctly.
Signed-off-by: Rami Rosen
---
doc/gui
-Original Message-
> Date: Mon, 10 Sep 2018 14:59:51 +0200
> From: Mattias Rönnblom
> To: jerin.ja...@caviumnetworks.com
> CC: bruce.richard...@intel.com, dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 10/10] eventdev: include DSW event device
> documentation
> User-Agent: Mozilla/5.0 (X11
On Mon, Sep 10, 2018 at 12:32:43PM +0100, Luca Boccassi wrote:
> This has been only build-tested for now, on a native ppc64el POWER8E
> machine running Debian sid.
>
> Signed-off-by: Luca Boccassi
> ---
> v2: fix indentation, drop march_opt in ppc build file
>
LGTM
Acked-by: Bruce Richardson
On 08/25/2018 09:22 PM, Rami Rosen wrote:
This patch removes an unnecessary definition of MAX_PRINT_BUFF
in examples/vhost/main.c, since it is no longer being used.
Fixes: 68363d85857d ("examples/vhost: remove the non-working zero copy code").
Signed-off-by: Rami Rosen
---
examples/vhost/
-Original Message-
> Date: Thu, 30 Aug 2018 11:03:16 +0530
> From: Hemant Agrawal
> To: dev@dpdk.org
> CC: jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com
> Subject: [PATCH 2/2] event/dpaa: add select based event support
> X-Mailer: git-send-email 2.7.4
>
> External Email
>
> Signed-
-Original Message-
> Date: Thu, 30 Aug 2018 11:33:57 +0530
> From: Hemant Agrawal
> To: dev@dpdk.org
> CC: jerin.ja...@caviumnetworks.com, nipun.gu...@nxp.com
> Subject: [PATCH 3/5] event/dpaa2: enchance timeout handling
> X-Mailer: git-send-email 2.7.4
>
Missing git commit log descripti
On 08/15/2018 04:54 PM, Ilya Maximets wrote:
'numa_realloc()' allocates 'zmbufs' even if zero copy mode
is not configured. This leads to memory leak, because array
is freed only for zero copy case.
Fixes: 2651726defb7 ("vhost: do deep copy while reallocating queue")
CC: sta...@dpdk.org
Signe
On 08/29/2018 05:55 PM, eric zhang wrote:
This patch checks negotiated features to see if necessary to offload
before set the tap device offload capabilities. It also checks if kernel
support the TUNSETOFFLOAD operation.
Signed-off-by: eric zhang
---
v3:
* make other offloading features dep
-Original Message-
> Date: Wed, 5 Sep 2018 19:21:05 +0530
> From: Nikhil Rao
> To: jerin.ja...@caviumnetworks.com
> CC: dev@dpdk.org, Nikhil Rao ,
> vipin.vargh...@intel.com, sta...@dpdk.org
> Subject: [PATCH v2 1/2] test/event: fix eth Rx adapter autotest for
> skeleton PMD
> X-Mailer:
Device reset may have the dependency, for example, a VF reset expects
PF ready, or a NIC function as a part of a SOC need to wait for other
parts of the system be ready, these are time-consuming tasks and will
block current thread.
So we claimed rte_eth_dev_reset as an async API, that makes things
From: Ziye Yang
This patch is used to fix the memory leak issue of logid.
We use the ASAN test in SPDK when intergrating DPDK and
find this memory leak issue.
By the way, we also fix several missed function call of
rte_atomic32_clear.
Signed-off-by: Ziye Yang
---
lib/librte_eal/linuxapp/eal/e
On 09/05/2018 01:55 AM, Tiwei Bie wrote:
When VIRTIO_RING_F_EVENT_IDX is negotiated, we need to
update the avail event to enable the notification.
Fixes: 3f8ff12821e4 ("vhost: support interrupt mode")
Cc:sta...@dpdk.org
Signed-off-by: Tiwei Bie
---
lib/librte_vhost/Makefile | 1 +
lib/li
Device reset may have the dependency, for example, a VF reset expects
PF ready, or a NIC function as a part of a SOC need to wait for other
parts of the system be ready, these are time-consuming tasks and will
block current thread.
So we claimed rte_eth_dev_reset as an async API, that makes things
rte_eth_dev_reset is claimed as an async API, so re-work
on the device reset handling.
Signed-off-by: Qi Zhang
---
app/test-pmd/testpmd.c | 50 +-
1 file changed, 49 insertions(+), 1 deletion(-)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/t
rte_eth_dev_reset should be implemented in an async way since it is
possible to be invoked in interrupt thread and sometimes to reset a
device need to wait for some dependency, for example, a VF expects for
PF ready or a NIC function as part of a SOC wait for the whole system
reset complete, and al
On 09/03/2018 12:12 PM, Ilya Maximets wrote:
There are a lot of cases where vhost-user massage handling
could fail and end up in a fully not recoverable state. For
example, allocation failures of shadow used ring and batched
copy array are not recoverable and leads to the segmentation
faults l
Device reset may have the dependency, for example, a VF reset expects
PF ready, or a NIC function as a part of a SOC need to wait for other
parts of the system be ready, these are time-consuming tasks and will
block current thread.
So we claimed rte_eth_dev_reset as an async API, that makes things
Change-Id: If1aecaac3335685f3bef79f47768ba8ae7765fbb
Signed-off-by: Zhang, Roy Fan
---
examples/ip_pipeline/Makefile | 1 +
examples/ip_pipeline/action.c | 11 +
examples/ip_pipeline/action.h | 1 +
examples/ip_pipeline/cli.c
Hi Nikolay,
On 07/19/2018 09:13 PM, Nikolay Nikolaev wrote:
Use the typedef version of struct VhostUserMsg. Also unify the related
parameter name.
Signed-off-by: Nikolay Nikolaev
---
lib/librte_vhost/vhost_user.c | 50 +
1 file changed, 25 insertion
On 04.09.2018 09:08, Zhang, Qi Z wrote:
> Hi Ilya:
>
>> -Original Message-
>> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ilya Maximets
>> Sent: Friday, August 31, 2018 8:40 PM
>> To: dev@dpdk.org
>> Cc: Lu, Wenzhuo ; Ananyev, Konstantin
>> ; Laurent Hardy
>> ; Dai, Wei ; Ilya Max
On 07/19/2018 09:13 PM, Nikolay Nikolaev wrote:
As VhostUserMsg structure is resued to generate the reply, move the
s/resued/reused/
relevant fields update into the respective message handling functions.
Signed-off-by: Nikolay Nikolaev
---
lib/librte_vhost/vhost_user.c | 26 +
On 05.09.2018 16:10, Stephen Hemminger wrote:
> On Mon, 3 Sep 2018 17:47:42 +0300
> Ilya Maximets wrote:
>
>>
>> +void __rte_experimental
>> +rte_delay_us_sleep(unsigned int us)
>> +{
>> +struct timespec wait[2];
>> +int ind = 0;
>> +
>> +wait[0].tv_sec = 0;
>> +if (us >= US_PE
On 07/19/2018 09:13 PM, Nikolay Nikolaev wrote:
Add new functions to handle the unsupported vhost message types:
- vhost_user_set_vring_err
- vhost_user_set_log_fd
Signed-off-by: Nikolay Nikolaev
---
lib/librte_vhost/vhost_user.c | 22 +-
1 file changed, 17 inser
On 09/10/2018 03:04 PM, Qi Zhang wrote:
> Device reset may have the dependency, for example, a VF reset expects
> PF ready, or a NIC function as a part of a SOC need to wait for other
> parts of the system be ready, these are time-consuming tasks and will
> block current thread.
>
> So we claimed
On 07/19/2018 09:13 PM, Nikolay Nikolaev wrote:
Each vhost-user message handling function will return an int result
which is described in the new enum vh_result: error, OK and reply.
All functions will now have two arguments, virtio_net double pointer
and VhostUserMsg pointer.
Signed-off-by:
On 07/19/2018 09:13 PM, Nikolay Nikolaev wrote:
Introduce vhost_message_handlers, which maps the message request
type to the message handler. Then replace the switch construct
with a map and call.
Signed-off-by: Nikolay Nikolaev
---
lib/librte_vhost/vhost_user.c | 143 +++-
-Original Message-
> Date: Fri, 17 Aug 2018 13:39:19 +0200
> From: Krzysztof Kanas
> To: dev@dpdk.org
> Cc: krzysztof.ka...@caviumnetworks.com,
> jerin.jacobkollanukka...@cavium.com, nithin.dabilpu...@cavium.com
> Subject: [dpdk-dev] [PATCH] app/testpmd: add commands for TM to mark pkts
>
On Fri, Sep 07, 2018 at 05:55:24PM +0100, Luca Boccassi wrote:
> Signed-off-by: Luca Boccassi
> ---
> v2: made doxygen dependency optional, skip doxygen build when not found
>
> doc/api/generate_doxygen.sh | 10 +++
> doc/api/meson.build | 54 +
>
On Fri, Sep 07, 2018 at 05:55:21PM +0100, Luca Boccassi wrote:
> This will make it possible to generate the file in the same way from
> Meson as well.
>
> Signed-off-by: Luca Boccassi
> ---
Couple of comments on patch 4, otherwise looks ok to me.
Series-acked-by: Bruce Richardson
1 - 100 of 152 matches
Mail list logo
