Hi Nelio,
Wednesday, May 2, 2018 5:43 PM, Nelio Laranjeiro:
> Subject: [dpdk-stable] [PATCH] net/mlx5: fix: flow validation
The title is wrong the : after the fix should be removed.
>
> Item spec and last are wrongly compared to the NIC capability causing a
> validation failure when the mask i
Signed-off-by: Ravi Kumar
---
drivers/crypto/ccp/meson.build | 21 +
drivers/crypto/meson.build | 2 +-
2 files changed, 22 insertions(+), 1 deletion(-)
create mode 100644 drivers/crypto/ccp/meson.build
diff --git a/drivers/crypto/ccp/meson.build b/drivers/crypto/ccp/me
Hi Ravi,
> -Original Message-
> From: Ravi Kumar [mailto:ravi1.ku...@amd.com]
> Sent: Thursday, May 3, 2018 6:57 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ;
> tho...@monjalon.net; hemant.agra...@nxp.com
> Subject: [PATCH 1/2] crypto/ccp: enable CCP crypto poll mode driver by defaul
> -Original Message-
> From: Kumar, Ravi1 [mailto:ravi1.ku...@amd.com]
> Sent: Thursday, May 3, 2018 7:02 AM
> To: De Lara Guarch, Pablo ; Thomas
> Monjalon
> Cc: dev@dpdk.org; hemant.agra...@nxp.com
> Subject: RE: [dpdk-dev] [PATCH v5 17/19] crypto/ccp: support cpu based md5
> and sha2
Hi Jeff
> From: Jeff Guo, Wednesday, April 18, 2018 4:38 PM
> Use testpmd for example, to show how an application smoothly handle
> failure when device being hot unplug. Once app detect the removal event,
> the callback would be called, it first stop the packet forwarding, then stop
> the
> port,
Signed-off-by: Olivier Matz
---
buildtools/auto-config-h.sh| 32 ++--
devtools/check-git-log.sh | 30 +-
devtools/check-includes.sh | 32 ++--
devtools/check-maintainers.sh | 30 +
Wednesday, May 2, 2018 9:50 AM, Nélio Laranjeiro:
> Subject: Re: [PATCH 2/2] net/mlx5: fix probe return value polarity
>
> On Wed, May 02, 2018 at 01:54:37AM +, Yongseok Koh wrote:
> >
> > > On May 1, 2018, at 4:18 AM, Shahaf Shuler
> wrote:
> > >
> > > mlx5 prefixed function returns a negati
It may be useful to pass arbitrary data to the callback (such
as device pointers), so add this to the mem event callback API.
Signed-off-by: Anatoly Burakov
Suggested-by: Maxime Coquelin
---
drivers/bus/fslmc/fslmc_vfio.c | 5 +++--
lib/librte_eal/common/eal_common_memalloc.c | 26
Hi Anatoly,
On 05/03/2018 09:47 AM, Anatoly Burakov wrote:
It may be useful to pass arbitrary data to the callback (such
as device pointers), so add this to the mem event callback API.
Signed-off-by: Anatoly Burakov
Suggested-by: Maxime Coquelin
---
drivers/bus/fslmc/fslmc_vfio.c
Upon success, mlx5_socket_connect should return the fd descriptor of the
primary process
Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
Signed-off-by: Yongseok Koh
Signed-off-by: Shahaf Shuler
Acked-by: Nelio Laranjeiro
---
On v2:
- No change.
---
drivers/net/mlx5/
mlx5 prefixed function returns a negative errno value.
the error handler on mlx5_pci_probe is doing the same.
Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
Cc: nelio.laranje...@6wind.com
Signed-off-by: Shahaf Shuler
---
On v2:
- fixed more polarity issues on different
On 02-May-18 9:13 PM, Olivier Matz wrote:
When populating a mempool with the default function, if there is not
enough virtually contiguous memory for the whole mempool, it will be
populated with several chunks. A chunk of the maximum available length
is requested with:
mz = rte_memzone_reserv
On 03-May-18 8:51 AM, Maxime Coquelin wrote:
Hi Anatoly,
On 05/03/2018 09:47 AM, Anatoly Burakov wrote:
It may be useful to pass arbitrary data to the callback (such
as device pointers), so add this to the mem event callback API.
Signed-off-by: Anatoly Burakov
Suggested-by: Maxime Coquelin
-
On 5/3/2018 11:58 AM, Tan, Jianfeng wrote:
I have a question, hope you can clarify it a little bit. As I
understand, this FPGA bus are used for AFU device enumeration, and
each device on this bus needs a AFU driver to drive. But now we
register AFU drivers, but enumerate rte_ifpga_device. Why
On 03-May-18 12:16 AM, Yongseok Koh wrote:
This is the new design of Memory Region (MR) for mlx PMD, in order to:
- Accommodate the new memory hotplug model.
- Support non-contiguous Mempool.
Signed-off-by: Yongseok Koh
---
mlx5_flow_delete_drop_queue(dev);
+ mlx5_mr_release(d
It may be useful to pass arbitrary data to the callback (such
as device pointers), so add this to the mem event callback API.
Signed-off-by: Anatoly Burakov
Suggested-by: Maxime Coquelin
---
Notes:
v2:
- Fixed compile issue in VFIO
This is needed to fix virtio-user issues under
> -Original Message-
> From: Tan, Jianfeng
> Sent: Thursday, May 3, 2018 11:58 AM
> To: Xu, Rosen ; dev@dpdk.org
> Cc: Doherty, Declan ; Richardson, Bruce
> ; shreyansh.j...@nxp.com; Yigit, Ferruh
> ; Ananyev, Konstantin
> ; Zhang, Tianfei ;
> Wu, Hao ; gaetan.ri...@6wind.com
> Subject: Re
On Wednesday 02 May 2018 07:06 PM, Zhang, Tianfei wrote:
-Original Message-
From: Shreyansh Jain [mailto:shreyansh.j...@nxp.com]
Sent: Wednesday, May 2, 2018 5:47 PM
To: Xu, Rosen ; dev@dpdk.org; Yigit, Ferruh
Cc: Doherty, Declan ; Richardson, Bruce
; Ananyev, Konstantin
; Zhang, Tianf
As of device hot unplug, we need some preparatory measures, so that when
we encounter memory fault (like SIGBUS error) due to the unplug action,
we can recover instead of crash.
To handle device hot unplug is bus-specific behavior, this patch introduces
a bus ops so that each kind of bus can imple
At the prior, device event monitor framework have been introduced,
the typical usage is for device hot plug. If we want application
would not be break down when device hot plug in or out, we still need
some measures to help app to handle that, such as recovery device for
device detaching, so that a
This patch introduces a failure handler mechanism to handle device
hot unplug event. When device be hot plug out, the device resource
become invalid, if this resource is still be unexpected read/write,
system will crash. This patch let eal help application to handle
this fault, when sigbus error oc
when device being hot unplug, release a none exist uio resource will
result kernel null pointer error, so this patch will check if device
has been remove before release uio release procedure, if so just return
back.
Signed-off-by: Jeff Guo
---
v21->v20:
no change
---
kernel/linux/igb_uio/igb_uio
Use testpmd for example, to show how an application smoothly handle
failure when device being hot unplug. Once app detect the removal event,
the callback would be called, it first stop the packet forwarding, then
stop the port, close the port and finally detach the port.
Signed-off-by: Jeff Guo
-
Deallocation used the wrong function, which could have resulted in
race conditions because the function does not use locks internally.
Fixes: 1403f87d4fb8 ("malloc: enable memory hotplug support")
Cc: anatoly.bura...@intel.com
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/eal_common_
-Original Message-
> Date: Thu, 3 May 2018 06:03:01 +
> From: "Gujjar, Abhinandan S"
> To: Jerin Jacob
> CC: "hemant.agra...@nxp.com" ,
> "akhil.go...@nxp.com" , "dev@dpdk.org"
> , "Vangati, Narender" , "Rao,
> Nikhil" , "Eads, Gage"
> Subject: RE: [v2,1/6] eventdev: introduce eve
On Thu, May 03, 2018 at 07:07:54AM +, Shahaf Shuler wrote:
> Hi Nelio,
>
> Wednesday, May 2, 2018 5:43 PM, Nelio Laranjeiro:
> > Subject: [dpdk-stable] [PATCH] net/mlx5: fix: flow validation
>
> The title is wrong the : after the fix should be removed.
Right,
> > Item spec and last are wro
On 05/03/2018 09:03 AM, Qi Zhang wrote:
Tx offload will be converted to txq_flags automatically during
rte_eth_dev_info_get and rte_eth_tx_queue_info_get. So PMD can
clean the code to get rid of txq_flags at all while keep old APP
not be impacted.
Signed-off-by: Qi Zhang
It is a step in right
Item spec and last are wrongly compared to the NIC capability causing a
validation failure when the mask is null.
This validation function should only verify the user is not configuring
unsupported matching fields.
Fixes: 2097d0d1e2cc ("net/mlx5: support basic flow items and actions")
Cc: sta...@d
Hi Olivier,
On 05/02/2018 11:13 PM, Olivier Matz wrote:
When populating a mempool with the default function, if there is not
enough virtually contiguous memory for the whole mempool, it will be
populated with several chunks. A chunk of the maximum available length
is requested with:
mz = rte
hi, matan
On 5/3/2018 3:25 PM, Matan Azrad wrote:
Hi Jeff
From: Jeff Guo, Wednesday, April 18, 2018 4:38 PM
Use testpmd for example, to show how an application smoothly handle
failure when device being hot unplug. Once app detect the removal event,
the callback would be called, it first stop
Signed-off-by: Jianfeng Tan
---
MAINTAINERS | 3 ---
1 file changed, 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index ce06e93..a482470 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -393,7 +393,6 @@ PCI bus driver
F: drivers/bus/pci/
VDEV bus driver
-M: Jianfeng Tan
F: drivers/bu
On Thu, May 03, 2018 at 10:59:37AM +0300, Shahaf Shuler wrote:
> mlx5 prefixed function returns a negative errno value.
> the error handler on mlx5_pci_probe is doing the same.
>
> Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
> Cc: nelio.laranje...@6wind.com
>
> Signed-o
Thanks a lot for your excellent contributions to DPDK community, Jianfeng.
See you later.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jianfeng Tan
> Sent: Thursday, May 3, 2018 5:52 PM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; maxime.coque...@redhat.co
Hi Anatoly,
As per the comment " Since file prefixes are not supported, tests cannot be run
in parallel"
Does this means we need not run parallel test group test cases for FreeBSD. So
the total test count for FreeBSD will be based on Non-Parallel test groups only.
Please confirm / share your v
On Thu, May 03, 2018 at 12:34:59PM +0300, Andrew Rybchenko wrote:
> Hi Olivier,
>
> On 05/02/2018 11:13 PM, Olivier Matz wrote:
> > When populating a mempool with the default function, if there is not
> > enough virtually contiguous memory for the whole mempool, it will be
> > populated with sever
Segment index was calculated incorrectly, causing free_seg to
attempt to free segments that do not exist.
Fixes: a5ff05d60fc5 ("mem: support unmapping pages at runtime")
Cc: anatoly.bura...@intel.com
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/linuxapp/eal/eal_memalloc.c | 3 +--
1 file c
Currently, page deallocation might fail if allocator cannot get page
fd, which will leave VA space still mapped, and will also not mark
page as free.
Fix page deallocation function to always unmap space before trying
to get rid of the page itself, and always mark page as free even if
page dealloca
Return value should be zero for success, but if unlock and unlink
have succeeded, return value was 1, which triggered failure message
in calling code.
Fixes: a5ff05d60fc5 ("mem: support unmapping pages at runtime")
Cc: anatoly.bura...@intel.com
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/
From: Gowrishankar Muthukrishnan
When there are multiple memsegs (each per hugepage), there are couple of
problems observed:
1. Same heap size index is always chosen to add new malloc_elems
again and again, while there is an increasing heap size actually.
Hence, when there is memall
From: Gowrishankar Muthukrishnan
During malloc heap init, if there are malloc_elems contiguous in
virt addresses, they could be merged so that, merged malloc_elem
would guarantee larger free memory size than its actual hugepage
size, it was created for.
Fixes: fafcc11985 ("mem: rework memzone to
From: Gowrishankar Muthukrishnan
When there are multiple memsegs created and adding new memseg would
cause bigger heap size, its index in free_head list should be based
on new size of heap. Currently, only the size of elem is accounted
as in malloc_elem_free_list_insert. As heap total size gets b
https://dpdk.org/tracker/show_bug.cgi?id=31
Bug ID: 31
Summary: Does not compile with musl libc:
lib/librte_eal/linuxapp/eal/eal_memory.c
Product: DPDK
Version: 18.05
Hardware: All
OS: Linux
Stat
There is no necessity to fill in TxQ flags since ethdev maps
Tx offloads to TxQ flags on device info get for apps which are
not converted yet to Tx offloads API.
Signed-off-by: Andrew Rybchenko
---
It should be applied after [1].
txq_flags are still used in net/sfc to check if legacy application
https://dpdk.org/tracker/show_bug.cgi?id=32
Bug ID: 32
Summary: Does not cross-compile:
buildtools/check-experimental-syms.sh assumes
`objdump`
Product: DPDK
Version: 18.05
Hardware: All
https://dpdk.org/tracker/show_bug.cgi?id=33
Bug ID: 33
Summary: Does not compile with musl libc:
lib/librte_eal/linuxapp/eal/eal_hugepage_info.c
Product: DPDK
Version: 18.05
Hardware: All
OS: All
https://dpdk.org/tracker/show_bug.cgi?id=34
Bug ID: 34
Summary: Does not compile with musl libc:
lib/librte_eal/common/eal_common_fbarray.c
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Stat
Fix somes Testpmd issues regarding port hot-plug.
Matan Azrad (6):
app/testpmd: fix valid ports prints
app/testpmd: fix forward ports update
app/testpmd: fix forward ports Rx flush
app/testpmd: fix synchronic port hotplug
app/testpmd: fix removed device link status asking
app/testpmd:
There are several cases of an invalid port data access that causes the
printing of all the valid ports, for example, when the user asks to
receive a port information of an invalid port.
Wrongly, the port with id 0 is printed in all the above described
cases, regardless of its validity.
Print port
When the forward ports are changed either by new portlist\portmask
configurations or by a port detachment, all the old forward streams
are freed and new streams are allocated to be aligned with the new
forward ports.
If the number of the forward ports drops to 0, there is an attempt
to wrongly all
A port Rx queue flush is done when the packet forwarding starts in
order to clean the port statistics for a new traffic session.
The flush operation is wrongly called before the update of the new
forward ports, and may fail due to flush operation for an invalid port
configured by the old session.
When the user uses the synchronic hot-plug commands, attach\detach, in
order to insert\remove a port from the system, the forward ports list
update is missed in the current implementation.
Thus, an invalid port may be used for data-path in case of detach
because the detached port was not removed f
When a removable device is plugged-out, a RMV interrupt is invoked and
the application can catch the event in order to stop the device
management.
The Testpmd wrong behavior in this case is to detach the removed device
using the EAL detach API.
The EAL API does not invalidate the ethdev port and
Thursday, May 3, 2018 11:00 AM, Shahaf Shuler:
> Subject: [dpdk-dev] [PATCH v2 1/2] net/mlx5: fix socket connection return
> value
>
> Upon success, mlx5_socket_connect should return the fd descriptor of the
> primary process
>
> Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno value
In the RMV device event callback, there is a call for the removed
device stop operation which trigers a link status operation for the
removed device.
It may casue an error from the removed device PMD.
Skip the link status operation in the above described case.
Fixes: 284c908cc588 ("app/testpmd:
https://dpdk.org/tracker/show_bug.cgi?id=35
Bug ID: 35
Summary: Does not compile with musl libc:
drivers/bus/pci/linux/pci_uio.c
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Status: CONFIRM
Coverity issue: 272582
Fixes: 2147c0950580 ("ipc: clean up code")
Cc: jianfeng@intel.com
Signed-off-by: Anatoly Burakov
---
lib/librte_eal/common/eal_common_proc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/librte_eal/common/eal_common_proc.c
b/lib/librte_eal/common/eal_common_
https://dpdk.org/tracker/show_bug.cgi?id=36
Bug ID: 36
Summary: drivers/bus/pci/linux/pci_vfio.c does not compile when
compilation strictly fails on warnings
Product: DPDK
Version: 18.05
Hardware: All
OS: Al
Thursday, May 3, 2018 12:32 PM, Nelio Laranjeiro:
> Subject: [dpdk-stable] [PATCH v2] net/mlx5: fix flow validation
>
> Item spec and last are wrongly compared to the NIC capability causing a
> validation failure when the mask is null.
> This validation function should only verify the user is not
At the prior, device event monitor framework have been introduced,
the typical usage is for device hot plug. If we want application
would not be break down when device hot plug in or out, we still need
some measures to help app to handle that, such as recovery device for
device detaching, so that a
On 03-May-18 11:02 AM, Yang, Zhiyong wrote:
Thanks a lot for your excellent contributions to DPDK community, Jianfeng.
See you later.
+1, you will be missed!
--
Thanks,
Anatoly
As of device hot unplug, we need some preparatory measures, so that when
we encounter memory fault (like SIGBUS error) due to the unplug action,
we can recover instead of crash.
To handle device hot unplug is bus-specific behavior, this patch introduces
a bus ops so that each kind of bus can imple
This patch introduces a failure handler mechanism to handle device
hot unplug event. When device be hot plug out, the device resource
become invalid, if this resource is still be unexpected read/write,
system will crash. This patch let eal help application to handle
this fault, when sigbus error oc
when device being hot unplug, release a none exist uio resource will
result kernel null pointer error, so this patch will check if device
has been remove before release uio release procedure, if so just return
back.
Signed-off-by: Jeff Guo
---
v21->v20:
no change
---
kernel/linux/igb_uio/igb_uio
Use testpmd for example, to show how an application smoothly handle
failure when device being hot unplug. Once app detect the removal event,
the callback would be called, it first stop the packet forwarding, then
stop the port, close the port and finally detach the port.
Signed-off-by: Jeff Guo
-
https://dpdk.org/tracker/show_bug.cgi?id=37
Bug ID: 37
Summary: DPAA / FSLMC do not compile on the musl libc
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Status: CONFIRMED
Severity: normal
On 03-May-18 11:03 AM, Parthasarathy, JananeeX M wrote:
Hi Anatoly,
As per the comment " Since file prefixes are not supported, tests cannot be run in
parallel"
Does this means we need not run parallel test group test cases for FreeBSD. So
the total test count for FreeBSD will be based on Non-
Excellent!
I unicasted Yong earlier when I saw the ACKs to vmxnet3 patches. I'll add you
there.
Thanks Louis,
Dave
> -Original Message-
> From: Louis Luo
> Sent: Wednesday, May 02, 2018 5:55 PM
> To: Thomas Monjalon ; David Harton (dharton)
>
> Cc: dev@dpdk.org; Yong Wang
> Subject:
https://dpdk.org/tracker/show_bug.cgi?id=38
Bug ID: 38
Summary: Does not compile with musl libc:
drivers/net/cxgbe/base/common.h
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Status: CONFIRM
https://dpdk.org/tracker/show_bug.cgi?id=39
Bug ID: 39
Summary: dpdk/drivers/net/enic/base/vnic_devcmd.h does not
compile on musl libc because of type `u_int32_t`
Product: DPDK
Version: 18.05
Hardware: All
O
Hi Guo
From: Guo, Jia, Thursday, May 3, 2018 12:36 PM
> hi, matan
>
>
> On 5/3/2018 3:25 PM, Matan Azrad wrote:
> > Hi Jeff
> >
> >> From: Jeff Guo, Wednesday, April 18, 2018 4:38 PM Use testpmd for
> >> example, to show how an application smoothly handle failure when
> >> device being hot unplu
Fix missing DEV_RX_OFFLOAD_CHECKSUM flag in RX offloads.
Remove depricated txq_flags field.
Fixes: a92870896b4a ("net/octeontx: use the new offload APIs")
Signed-off-by: Pavan Nikhilesh
---
drivers/net/octeontx/octeontx_ethdev.c | 5 +
drivers/net/octeontx/octeontx_ethdev.h | 3 ++-
2 files
On 23-Apr-18 12:05 AM, Thomas Monjalon wrote:
This patch has been forgotten.
Review please?
24/02/2018 04:26, Jianfeng Tan:
In some cases, we don't want to lock all memory.
Add an option --no-mlockall to avoid lock all memory.
Cc: wenzhuo...@intel.com
Cc: jingjing...@intel.com
Signed-off-by:
Signed-off-by: Pavan Nikhilesh
---
drivers/net/thunderx/nicvf_ethdev.c | 6 --
1 file changed, 6 deletions(-)
diff --git a/drivers/net/thunderx/nicvf_ethdev.c
b/drivers/net/thunderx/nicvf_ethdev.c
index b673b4716..2a8bdf38e 100644
--- a/drivers/net/thunderx/nicvf_ethdev.c
+++ b/drivers/net/
On Mon, Apr 30, 2018 at 05:59:54PM +0200, Maxime Coquelin wrote:
> This patch caches all dirty pages logging until the used ring index
> is updated. These dirty pages won't be accessed by the guest as
> long as the host doesn't give them back to it by updating the
> index.
Below sentence in above
The default RSS hash key automatically provided by testpmd for RSS actions
specified without one is so weak that traffic can't spread properly on L4
with it (as seen with TCPv6).
It is only 30 bytes long, zero-padded to RSS_HASH_KEY_LENGTH (64 bytes),
later truncated to 40 bytes for most PMDs. The
Since the commit referenced below, specifying a RSS action without any
queues (e.g. "actions rss queues end / end") does not override the default
set automatically generated by testpmd.
In short, one cannot instantiate a RSS action with 0 target queues anymore
in order to determine how PMDs react
https://dpdk.org/tracker/show_bug.cgi?id=40
Bug ID: 40
Summary: drivers/net/nfp/nfpcore/nfp-common/nfp_platform.h:
does not compile with musl because it uses an internal
glibc header
Product: DPDK
Version: 18.05
> -Original Message-
> From: Zhang, Qi Z
> Sent: Thursday, May 3, 2018 7:03 AM
> To: Yigit, Ferruh ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Zhang, Qi Z
> Subject: [PATCH] ethdev: convert Tx offloads to Tx queue config
>
> Tx offload will be converted to txq_flags automatically duri
> -Original Message-
> From: Zhang, Qi Z
> Sent: Wednesday, May 2, 2018 4:16 AM
> To: Yigit, Ferruh
> Cc: Dai, Wei ; Lu, Wenzhuo ;
> Ananyev, Konstantin ;
> Wang, Xiao W ; dev@dpdk.org; Zhang, Qi Z
>
> Subject: [PATCH 0/3] remove dependence on Tx queue flags
>
> The patchset remove t
If mlockall() is called while allocated VA space is bigger than
amount of available RAM, FreeBSD kernel will deadlock and need
a hard reboot. We do allocate big amounts of memory because of
how new memory subsystem works, so calling mlockall() will cause
a deadlock. So, disable mlockall() by defaul
Add two new command-line parameters for either enabling or
disabling locking all memory at app startup.
Cc: wenzhuo...@intel.com
Cc: jingjing...@intel.com
Signed-off-by: Jianfeng Tan
Signed-off-by: Anatoly Burakov
---
app/test-pmd/parameters.c | 8
app/test-pmd/testpmd.c
Hi Peng Yuan,
Apologies for the delay, I'll answer below to the entire thread.
On Sat, Apr 28, 2018 at 07:45:31AM +, Peng, Yuan wrote:
> Hi，Adrien Mazarguil
>
> There is a bug of queue region with 18.05-rc1
> The test steps are as below:
> ./usertools/dpdk-devbind.py -b igb_uio 05:00.0
> ./x
If total memory is already bigger than max memory, an underflow
will occur on subtraction. Fix it by simply stopping whenever
we already have amount of memory that is bigger than maximum.
Fixes: 66cc45e293ed ("mem: replace memseg with memseg lists")
Cc: anatoly.bura...@intel.com
Signed-off-by: An
Bruce, Beilei,
Can you help me here?
Build targets in project: 263
Found ninja-1.8.2 at /usr/bin/ninja
[585/940] Compiling C object
'drivers/net/i40e/i40e_avx2_lib@sta/i40e_rxtx_vec_avx2.c.o'.
FAILED: drivers/net/i40e/i40e_avx2_lib@sta/i40e_rxtx_vec_avx2.c.o
ccache cc -Idrivers/net/i40e/i40e_
rte_eth_vhost_get_vid_from_port_id returns a value of 0 if called before
the first call to the new_device callback. A vid value >=0 suggests the
device is active which is not the case in this instance. Initialise vid
to a negative value to prevent this.
Signed-off-by: Ciara Loftus
Fixes: ee584e97
>
> >
> > On 04/27/2018 04:19 PM, Ciara Loftus wrote:
> > > rte_eth_vhost_get_vid_from_port_id returns a value of 0 if called before
> > > the first call to the new_device callback. A vid value >=0 suggests the
> > > device is active which is not the case in this instance. Initialise vid
> > > to
Signed-off-by: Fiona Trahe
---
doc/guides/cryptodevs/overview.rst | 10 ++
1 files changed, 10 insertions(+), 0 deletions(-)
diff --git a/doc/guides/cryptodevs/overview.rst
b/doc/guides/cryptodevs/overview.rst
index b3cb6ca..493cd5f 100644
--- a/doc/guides/cryptodevs/overview.rst
+++
On Wednesday 02 May 2018 10:45 PM, Nipun Gupta wrote:
There are two API's which are required by NXP specific Command Interface
Application (AIOP CMDIF). This patch exposes these two API's.
Signed-off-by: Nipun Gupta
---
doc/api/doxy-api-index.md | 1 +
doc/api/doxy-
On Wednesday 02 May 2018 10:39 PM, Nipun Gupta wrote:
DPAA2 QDMA driver uses MC DPDMAI object. This driver enables
the user (app) to perform data DMA without involving CPU in
the DMA process
Signed-off-by: Nipun Gupta
Acked-by: Shreyansh Jain
---
MAINTAINERS
On Wednesday 02 May 2018 10:45 PM, Nipun Gupta wrote:
Signed-off-by: Nipun Gupta
---
MAINTAINERS| 4 +
config/common_base | 5 +
config/common_linuxapp | 1 +
drivers/raw/Makefile
Hi experts!
This is my first post on this list, apologize if I am posting in the wrong dpdk
list, or if this is not relevant.
I am using spdk, hence dpdk. Following the termination of CentOS6 support, I
did some work in order to get dpdk to work on CentOS6 (gcc version 4.4.7).
I had to remove
Update net/sfc base driver to provide a new stats available on
XtremeScale X2 (aka Medford2) NICs. No new code is required in
net/sfc PMD.
HLB_IDLE and HLB_TIMEOUT stats are useful for packet drops and
performance investigations.
There are few checkpatches.sh warnings due to coding style differen
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/base/efx.h | 5 -
drivers/net/sfc/base/efx_mac.c | 5 -
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/net/sfc/base/efx.h b/drivers/net/sfc/base/efx.h
index 332c6d06f..7f4e59e99 1006
These stats are availble on Medford2 DPDK firmware variant
which support equal stride super-buffer Rx mode. RXDP_HLB_IDLE
capability bit is set when the stats are available.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/base/ef10_mac.c | 18 ++
dr
Fixes: 400ba3daeeb1 ("net/sfc/base: decode Medford2 FEC stats if available")
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/base/ef10_mac.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/sfc/base/ef10_mac.c b/drivers/net/sfc/base/e
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/base/ef10_mac.c | 21 +
1 file changed, 21 insertions(+)
diff --git a/drivers/net/sfc/base/ef10_mac.c b/drivers/net/sfc/base/ef10_mac.c
index 3a62fd09c..e3adcac53 100644
--- a/drivers/net/sfc/base/
> -Original Message-
> From: Shreyansh Jain [mailto:shreyansh.j...@nxp.com]
> Sent: Thursday, May 3, 2018 5:13 PM
> To: Zhang, Tianfei ; Xu, Rosen
> ; dev@dpdk.org; Yigit, Ferruh
> Cc: Doherty, Declan ; Richardson, Bruce
> ; Ananyev, Konstantin
> ; Wu, Hao ;
> gaetan.ri...@6wind.com
> Sub
Hi Jasvinder,
Looks good, a few things to fix below:
> -Original Message-
> From: Singh, Jasvinder
> Sent: Friday, March 9, 2018 6:41 PM
> To: dev@dpdk.org
> Cc: Dumitrescu, Cristian
> Subject: [PATCH 1/2] librte_sched: add post-init pipe profile api
>
> Add new API function to add more
Inside test_reorder_insert()
rte_mempool_get_bulk() and rte_mempool_put_bulk() are used
to allocate and free the mbufs and then rte_reorder_free()
is called which again freeing the mbufs using rte_pktmbuf_free().
The mixed use of rte_mempool_put_bulk() and rte_pktmbuf_free()
causing duplicate mbuf
03/05/2018 12:49, Burakov, Anatoly:
> On 03-May-18 11:02 AM, Yang, Zhiyong wrote:
> > Thanks a lot for your excellent contributions to DPDK community, Jianfeng.
> > See you later.
>
> +1, you will be missed!
+1
Thanks a lot Jianfeng
This patch is accepted and applied.
1 - 100 of 157 matches
Mail list logo
