Hi Jiayu,
On 9/20/2017 11:00 AM, Jiayu Hu wrote:
Hi Jianfeng,
Few questions are inline.
Thanks,
Jiayu
On Fri, Aug 25, 2017 at 09:40:46AM +, Jianfeng Tan wrote:
Previouly, there is only one way for primary/secondary to exchange
messages, that is, primary process writes info into some pre
Hi, Ferruh
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, September 20, 2017 6:36 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 1/2] net/i40e: queue region set and flush
>
> On 9/15/2017 4:13 AM, Wei Zhao wrote:
> > This feature enable queue region
Add a new support of reset stats statics in vf port.
Signed-off-by: Wei Zhao
---
drivers/net/i40e/i40e_ethdev_vf.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
b/drivers/net/i40e/i40e_ethdev_vf.c
index 806ff9e..13c472f 100644
--- a/drivers/net/i40e/i40e_
There is a bug in vf clear xstats command, it do not
record the statics data in offset struct member.So, vf
need to keep record of xstats data from pf and update
the statics according to offset.
Fixes: da61cd0849766 ("i40evf: add extended stats")
Signed-off-by: Wei Zhao
---
drivers/net/i40e/i40
Merge i40evf_dev_stats_get and i40evf_get_statistics to
be one function.Rename i40evf_update_stats like
i40evf_query_stats, and chang i40evf_update_vsi_stats
To be i40evf_update_stats.
Signed-off-by: Wei Zhao
---
drivers/net/i40e/i40e_ethdev_vf.c | 56 +--
1 f
The diff_pkts_rx and diff_pkts_tx statistic data
will be wrong when the first time after clear
xstats command if there is no protect.
Signed-off-by: Wei Zhao
---
app/test-pmd/config.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/app/test-pmd/config.c b/app/test-pmd/
Hi Jiayu,
On 9/18/2017 9:49 PM, Jiayu Hu wrote:
Hi Jianfeng,
On Fri, Aug 25, 2017 at 09:40:46AM +, Jianfeng Tan wrote:
Previouly, there is only one way for primary/secondary to exchange
messages, that is, primary process writes info into some predefind
file, and secondary process reads i
On Fri, Aug 25, 2017 at 09:40:51AM +, Jianfeng Tan wrote:
> static int
> +share_device(int vid)
> +{
> + uint32_t i, vring_num;
> + int len;
> + int fds[8];
> + struct rte_vhost_memory *mem;
> + struct vhost_params *params;
> + struct rte_vhost_vring vring;
> +
> +
Firstly, very sorry for so late review!
On Fri, Aug 25, 2017 at 09:40:50AM +, Jianfeng Tan wrote:
> To support kick in secondary process, we propose callfd_pri and
> kickfd_pri to store the value in primary process; and by a new
> API, rte_vhost_set_vring_effective_fd(), we can set effective
>
From: "Charles (Chas) Williams"
In certain situations, low speed interfaces, it may be desirable to
have the flow control provided by the kernel queueing disciplines.
Signed-off-by: Chas Williams
---
drivers/net/af_packet/rte_eth_af_packet.c | 24 ++--
1 file changed, 18 in
There is no lock in function malloc_heap_get_stats. When we call this function,
the elem may free by other thread.
the call stack:
Core was generated by `ovs-vswitchd unix:/usr/var/run/openvswitch/db.sock
-vconsole:emer -vsyslog:info'.
Program terminated with signal 11, Segmentation fault.
#0 m
Hi，Ferruh
> -Original Message-
> From: Yigit, Ferruh
> Sent: Thursday, September 14, 2017 9:31 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: Wu, Jingjing
> Subject: Re: [dpdk-dev] [PATCH v2 1/2] net/i40e: fix clear xstats bug in vf
> port
>
> On 9/1/2017 3:30 AM, Zhao1, Wei wrote:
> > Hi, Fe
On 09/20/2017 10:39 AM, Burakov, Anatoly wrote:
On 20-Sep-17 3:34 PM, Patrick MacArthur wrote:
On 09/20/2017 05:59 AM, Kuba Kozak wrote:
Add file descriptor value check before calling close() function.
Coverity issue: 141297
Fixes: 811b6b25060f ("vfio: fix file descriptor leak in multi-process
On Wed, Sep 20, 2017 at 05:00:11PM +0800, Van Haaren, Harry wrote:
> > From: Yang, Yi Y
> > Sent: Wednesday, September 20, 2017 9:31 AM
> > To: Van Haaren, Harry
> > Cc: dev@dpdk.org; Yang, Yi Y
> > Subject: [PATCH] service: fix compilation error
> >
> > CC rte_service.o
> > ./dpdk/lib/librt
v1->v2
- Change title to more descriptive one
- Add issue reproduce information to git log body
On current master tree, normal DPDK make will result in
the below error:
error: ‘ids[0]’ may be used uninitialized in this
function [-Werror=maybe-uninitialized]
ret = rte_service_map_l
Hi Wei,
>
> Hi, Konstantin
>
> Without this patch, when a port is stopped, all mirror SW resource are
> cleared but HW settings are still there.
> And once the port is started again, creating mirror rule may fail due to
> remain HW settings.
>
> There is a testpmd use case which can show why
Hi everyone,
Here are the meeting notes for the last DPDK technical board meeting
held on 2017-09-15.
Attendees:
- Bruce Richardson
- Hemant Agrawal
- Jan Blunck
- Jerin Jacob
- Konstantin Ananyev
- Thomas Monjalon
- Yuanhan Liu
1) Discussion on dpdk.org git tree re-organization proposals:
htt
On Tue, 19 Sep 2017 22:01:23 +0200
Thomas Monjalon wrote:
> 19/09/2017 16:15, Ferruh Yigit:
> > On 9/19/2017 2:37 PM, Shreyansh Jain wrote:
> > > On Monday 18 September 2017 08:19 PM, Ferruh Yigit wrote:
> > >> On 9/9/2017 12:20 PM, Shreyansh Jain wrote:
> > >>> This layer is used by Bus dr
From: Gowrishankar Muthukrishnan
At present, creating bonding devices using --vdev is broken for PMD like
mlx5 as it is neither UIO nor VFIO based and hence PMD driver is unknown
to find_port_id_by_pci_addr(), as below.
testpmd --vdev 'net_bonding0,mode=1,slave=,socket_id=0'
PMD: bond_ethdev_p
On Wed, Sep 20, 2017 at 05:53:04PM +0200, Thomas Monjalon wrote:
> 20/09/2017 16:53, Van Haaren, Harry:
> > From: Pavan Nikhilesh Bhagavatula [mailto:pbhagavat...@caviumnetworks.com]
> > > On Fri, Sep 15, 2017 at 05:51:36PM +0200, Thomas Monjalon wrote:
> > > > 15/09/2017 16:59, Pavan Nikhilesh Bha
On Wed, Sep 20, 2017 at 04:39:22PM +, Dumitrescu, Cristian wrote:
>
>
> > -Original Message-
> > From: Pavan Nikhilesh Bhagavatula
> > [mailto:pbhagavat...@caviumnetworks.com]
> > Sent: Wednesday, September 20, 2017 4:45 PM
> > To: Dumitrescu, Cristian ;
> > step...@networkplumber.org
>
On 9/20/2017 3:11 PM, David C Harton wrote:
> From: David Harton
>
> Some devices do not support reset of eth stats. An application may
> need to know not to clear shadow stats if the device cannot.
>
> rte_eth_stats_reset is updated to provide a return code to share
> whether the device suppor
On 9/20/2017 3:01 PM, David Harton (dharton) wrote:
>
>
>> -Original Message-
>> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
>>
>> On 9/1/2017 3:26 AM, David Harton wrote:
>>> Some devices do not support reset of eth stats. An application may
>>> need to know not to clear shadow s
On 9/19/2017 11:24 AM, Shijith Thotton wrote:
> Issuing reset during uio device open caused PMD init failure for some
> NIC VFs (i40, ixgbe, qede) in host. So this initial reset is removed.
> Bus master enable is kept as part of open since we disable it in uio
> device release.
>
> Fixes: b58eedfc
This commit fixes the setting of relative rpath on dpdk-testpmd for drivers
($libdir/dpdk/drivers) to the correct absolute rpath
($prefix$libdir/dpdk/drivers)
Fixes: d123bba2dfbe ("build: add initial infrastructure for meson & ninja
builds")
Signed-off-by: Timothy Redaelli
---
This commit is
> -Original Message-
> From: Pavan Nikhilesh Bhagavatula
> [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Wednesday, September 20, 2017 4:45 PM
> To: Dumitrescu, Cristian ;
> step...@networkplumber.org
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2 1/3] eal: move bitmap from lib
On 9/19/2017 3:44 PM, Ferruh Yigit wrote:
> On 9/19/2017 12:47 PM, SebastianX Basierski wrote:
>> Fixed overflow by casting txq->cmd_ring.next2fill to uint64_t type.
>>
>> Coverity issue: 143457
>>
>> Fixes: 01fef6e3c181 ("net/vmxnet3: allow variable length Tx data ring")
Cc: sta...@dpdk.org
>>
>>
On 9/19/2017 1:46 PM, Pascal Mazon wrote:
<...>
> On 18/09/2017 20:47, Ferruh Yigit wrote:
>> From: Vipin Varghese
>>
>> tap_intr_handle_set() called by tap_dev_start(), and if LSC is disabled
>> (dev_conf.intr_conf.lsc == 0), it tries to unregister interrupt
>> callback without checking the inter
20/09/2017 16:53, Van Haaren, Harry:
> From: Pavan Nikhilesh Bhagavatula [mailto:pbhagavat...@caviumnetworks.com]
> > On Fri, Sep 15, 2017 at 05:51:36PM +0200, Thomas Monjalon wrote:
> > > 15/09/2017 16:59, Pavan Nikhilesh Bhagavatula:
> > > > On Fri, Sep 15, 2017 at 02:44:57PM +, Van Haaren, H
On 9/18/2017 3:49 PM, Shachar Beiser wrote:
> This removes the dependency on specific Mellanox OFED libraries by
> using the upstream rdma-core and linux upstream community code.
> Both rdma-core upstream and Mellanox OFED are Linux user-space packages:
> 1. Rdma-core is Linux upstream user-space
On Wed, Sep 20, 2017 at 03:40:46PM +, Dumitrescu, Cristian wrote:
>
>
> > -Original Message-
> > From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> > Sent: Wednesday, September 20, 2017 4:37 PM
> > To: Dumitrescu, Cristian ;
> > step...@networkplumber.org
> > Cc: dev@dpdk.
> -Original Message-
> From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Wednesday, September 20, 2017 4:37 PM
> To: Dumitrescu, Cristian ;
> step...@networkplumber.org
> Cc: dev@dpdk.org; Pavan Bhagavatula
>
> Subject: [dpdk-dev] [PATCH v2 1/3] eal: move bitmap from
Signed-off-by: Pavan Nikhilesh
---
MAINTAINERS | 5 +
1 file changed, 5 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index a0cd75e..3522497 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -143,6 +143,11 @@ F: lib/librte_eal/common/rte_service.c
F: doc/guides/prog_guide/service_cores.r
From: Pavan Bhagavatula
This patch adds a test for verifying the bitmap operations.
Signed-off-by: Pavan Nikhilesh
---
test/test/Makefile | 1 +
test/test/test_bitmap.c | 192
2 files changed, 193 insertions(+)
create mode 100644 test/te
From: Pavan Bhagavatula
The librte_sched uses rte_bitmap to manage large arrays of bits in an
optimized method so, moving it to eal/common would allow other libraries
and applications to use it.
Signed-off-by: Pavan Nikhilesh
---
v2 changes:
- undo rte_bitmap.h cosmetic changes
- update main
Hi,
18/09/2017 11:10, Jasvinder Singh:
> The SoftNIC PMD is intended to provide SW fall-back options for specific
> ethdev APIs in a generic way to the NICs not supporting those features.
I agree it is important to have a solution in DPDK to better manage
SW fallbacks. One question is to know whe
This commit adds the new_event_threshold port attribute, so the entire port
configuration structure passed to rte_event_queue_setup can be queried.
Signed-off-by: Gage Eads
---
lib/librte_eventdev/rte_eventdev.c | 71 --
lib/librte_eventdev/rte_eventdev.h | 10
This commit adds three new queue attributes, so that the entire queue
configuration structure passed to rte_event_queue_setup can be queried.
Signed-off-by: Gage Eads
---
lib/librte_eventdev/rte_eventdev.c | 54 +--
lib/librte_eventdev/rte_eventdev.h | 16 -
test/test/test_even
The enqueue depth test was comparing the port's dequeue depth against its
enqueue depth.
Fixes: 410c5bccdadc ("eventdev: add port attribute function")
Signed-off-by: Gage Eads
---
test/test/test_eventdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/test/test/test_eventde
This patchset makes the full queue and port configuration structures accessible
through the attribute get functions, adds tests for the new attributes, and
fixes one bug in a port attribute get test.
This patchset is based on patches 29019 through 29023.
Gage Eads (3):
eventdev: extend queue at
Port info command prints information about all supported flow types,
including dynamically mapped ones.
Signed-off-by: Kirill Rybalchenko
Reviewed-by: Jingjing Wu
---
app/test-pmd/config.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/app/test-pmd/config.c b/app/
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Wednesday, September 20, 2017 10:50 AM
> To: dev@dpdk.org
> Cc: Doherty, Declan ; De Lara Guarch, Pablo
> ; hemant.agra...@nxp.com; Akhil Goyal
>
> Subject: [PATCH] crypto/openssl: fix compilation break with op
> From: Pavan Nikhilesh Bhagavatula [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Friday, September 15, 2017 6:38 PM
> To: Thomas Monjalon
> Cc: Van Haaren, Harry ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] eal: added new `rte_lcore_is_service_lcore`
> API.
>
> On Fri, Sep 15, 2017 at 05:
On 20-Sep-17 3:34 PM, Patrick MacArthur wrote:
On 09/20/2017 05:59 AM, Kuba Kozak wrote:
Add file descriptor value check before calling close() function.
Coverity issue: 141297
Fixes: 811b6b25060f ("vfio: fix file descriptor leak in multi-process")
Cc: patr...@patrickmacarthur.net
Cc: sta...@dp
Hi Anatoly,
"Burakov, Anatoly" wrote on 09/19/2017 01:40:51
PM:
> From: "Burakov, Anatoly"
> To: Jonas Pfefferle , dev@dpdk.org
> Date: 09/19/2017 01:41 PM
> Subject: Re: [dpdk-dev] [PATCH] vfio: refactor PCI BAR mapping
>
> Hi Jonas,
>
> On 17-Aug-17 12:35 PM, Jonas Pfefferle wrote:
> > Split
On 09/20/2017 05:59 AM, Kuba Kozak wrote:
Add file descriptor value check before calling close() function.
Coverity issue: 141297
Fixes: 811b6b25060f ("vfio: fix file descriptor leak in multi-process")
Cc: patr...@patrickmacarthur.net
Cc: sta...@dpdk.org
Signed-off-by: Kuba Kozak
---
lib/lib
Remove unnecessary check for new flow type for rss hash
filter update.
Signed-off-by: Kirill Rybalchenko
---
lib/librte_ether/rte_ethdev.c | 8
1 file changed, 8 deletions(-)
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
index a88916f..d2279b7 100644
--- a/
Add new commands to manipulate with dynamic flow type to
pctype mapping table in i40e PMD.
Commands allow to print table, modify it and reset to default value.
v3:
changed command syntax from 'pctype mapping...' to
'port config pctype mapping...' and 'show port pctype mapping'
Signed-off-by: Kiri
Implement dynamic mapping of software flow types to hardware pctypes.
This allows to add new flow types and pctypes for DDP without changing
API of the driver. The mapping table is located in private
data area for particular network adapter and can be individually
modified with set of appropriate f
Add new functions which allow modify, return or reset to default
the contents of flow type to pctype dynamic mapping table.
v3:
function rte_pmd_i40e_flow_type_mapping_get returns now full
mapping table.
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/rte_pmd_i40e.c | 90 ++
Implement dynamic mapping of software flow types to hardware pctypes.
This allows to map new flow types to pctypes without changing
API of the driver.
v2:
Remove unnecessary check for new flow types.
Re-arrange patchset to avoid compillation errors.
Remove unnecessary usage of statically defined f
Add new definition in enum i40e_filter_pctype for
for invalid pctype
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/base/i40e_type.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/i40e/base/i40e_type.h
b/drivers/net/i40e/base/i40e_type.h
index dca725a
Remove unnecessary bit operations in I40E_PFQF_HENA
and I40E_VFQF_HENA registers
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/i40e_ethdev.c| 21 +++--
drivers/net/i40e/i40e_ethdev_vf.c | 22 --
2 files changed, 7 insertions(+), 36 deletions(-)
d
Hi, Konstantin
Without this patch, when a port is stopped, all mirror SW resource are cleared
but HW settings are still there.
And once the port is started again, creating mirror rule may fail due to remain
HW settings.
There is a testpmd use case which can show why this patch is needed.
1. bin
From: David Harton
Some devices do not support reset of eth stats. An application may
need to know not to clear shadow stats if the device cannot.
rte_eth_stats_reset is updated to provide a return code to share
whether the device supports reset or not.
Signed-off-by: David Harton
---
v6:
*
> -Original Message-
> From: Burakov, Anatoly
> Sent: Tuesday, September 12, 2017 10:36 AM
> To: dev@dpdk.org
> Cc: Doherty, Declan ; De Lara Guarch, Pablo
>
> Subject: [PATCH v2 0/2] New crypto acceleration benchmark mode
>
> This patchset adds a new "PMD cyclecount" test mode for test
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
>
> On 9/1/2017 3:26 AM, David Harton wrote:
> > Some devices do not support reset of eth stats. An application may
> > need to know not to clear shadow stats if the device cannot.
> >
> > rte_eth_stats_reset is u
On 9/14/2017 4:57 PM, Bruce Richardson wrote:
> Naming convention for net drivers is "rte_pmd__version.map"
>
> Signed-off-by: Bruce Richardson
This one not get, because xenvirt will be removed this release.
On 9/14/2017 4:57 PM, Bruce Richardson wrote:
> Naming convention for net drivers is "rte_pmd__version.map"
>
> Signed-off-by: Bruce Richardson
Applied to dpdk-next-net/master, thanks.
This commit bumps the library version to refect the ABI change
caused by removing the individual rte_event_port_count, queue_count,
and other get functions. These functions are superseded by the
get-attribute style API, which allows fetching values without API/ABI
changes.
Signed-off-by: Harry van
This commit adds an attribute to the eventdev, allowing applications
to retrieve if the eventdev is running or stopped. Note that no API
or ABI changes were required in adding the statistic, and code changes
are minimal.
Signed-off-by: Harry van Haaren
Acked-by: Jerin Jacob
---
lib/librte_event
This commit adds a generic queue attribute function. It also removes
the previous rte_event_queue_priority() and priority() functions, and
updates the map files and unit tests to use the new attr functions.
Signed-off-by: Harry van Haaren
---
v4: [feedback http://dpdk.org/dev/patchwork/patch/28
This commit adds a device attribute function, allowing flexible
fetching of device attributes, like port count or queue count.
The unit tests and .map file are updated to the new function.
Signed-off-by: Harry van Haaren
Acked-by: Jerin Jacob
---
v4: [feedback http://dpdk.org/dev/patchwork/pat
This commit reworks the port functions to retrieve information
about the port, like the enq or deq depths. Note that "port count"
is a device attribute, and is added in a later patch for dev attributes.
Signed-off-by: Harry van Haaren
---
v4: feedback from http://dpdk.org/dev/patchwork/patch/28
This patchset refactors the eventdev API to be more flexible
and capable. In particular, the API is capable of returning an
error value if an invalid device, port or attribute ID is passed
in, which was not possible with the previous APIs.
The implementation of this patchset is based on a v1 patch
On Wed, Sep 20, 2017 at 01:27:41PM +, Dumitrescu, Cristian wrote:
> > -Original Message-
> > From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> > Sent: Thursday, September 7, 2017 3:40 PM
> > To: Dumitrescu, Cristian ;
> > step...@networkplumber.org
> > Cc: dev@dpdk.org; P
The unscrutinized value may be incorrectly assumed to be within a certain
range by later operations.
In vhost_user_read: An unscrutinized value from an untrusted source used
in a trusted context - the value of sz_payload may be harmfull and we need
limit them to the max value of payload.
Coverity
> -Original Message-
> From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Thursday, September 7, 2017 3:40 PM
> To: Dumitrescu, Cristian ;
> step...@networkplumber.org
> Cc: dev@dpdk.org; Pavan Nikhilesh
> Subject: [dpdk-dev] [PATCH 1/2] eal: move bitmap from lib sched
On Wed, Sep 20, 2017 at 01:10:53PM +, Dumitrescu, Cristian wrote:
> Hi Pavan,
Hi Cristian,
>
> I think moving rte_reciprocal.[hc] to a common code area like EAL is a very
> good idea, so thanks for doing this work!
>
> One ask from my side: please do not change the existing code.
> 1. Keep the
On 9/19/2017 10:45 PM, Chas Williams wrote:
> From: "Charles (Chas) Williams"
>
> In certain situations, low speed interfaces, it may be desirable to
> have the flow control provided by the kernel queueing disciplines.
Out of curiosity, do you have any compression of performance numbers
with and
Hi Pavan,
Same ask as for the first patch:
-Do not change existing code in rte_reciprocal.[hc]: no _u32 suffix, please
-Do not add lots of CR+LF to existing code
> -Original Message-
> From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> Sent: Wednesday, September 6, 2017 11:2
From: Alan Dewar
The RED code stores the maximum threshold is a 32-bit integer as a
pseudo fixed-point floating number with 10 fractional bits. Twelve
other bits are used to encode the filter weight, leaving just 10 bits
for the queue length. This limits the maximum queue length supported
by RE
Hi Pavan,
I think moving rte_reciprocal.[hc] to a common code area like EAL is a very
good idea, so thanks for doing this work!
One ask from my side: please do not change the existing code.
1. Keep the existing name for the 32-bit API functions and data structures (no
_u32 name suffix), add the
Acked-by: Pascal Mazon
On 20/09/2017 15:03, Thomas Monjalon wrote:
> The flow API is supported in TAP PMD if flower is supported in Linux.
> Some commands are combined to suggest a convenient check of its support
> by the running kernel.
>
> Signed-off-by: Thomas Monjalon
> ---
> doc/guides/nic
The flow API is supported in TAP PMD if flower is supported in Linux.
Some commands are combined to suggest a convenient check of its support
by the running kernel.
Signed-off-by: Thomas Monjalon
---
doc/guides/nics/tap.rst | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
diff --gi
On Wed, Sep 20, 2017 at 01:05:19PM +0100, Luca Boccassi wrote:
> On Wed, 2017-09-20 at 11:51 +0100, Bruce Richardson wrote:
> > No major changes, just cleanups.
> >
> > Bruce Richardson (3):
> > build: sort meson options alphabetically
> > build: fix driver install path
> > build/x86: add SS
> -Original Message-
> From: Iremonger, Bernard
> Sent: Thursday, September 7, 2017 5:43 PM
> To: dev@dpdk.org; Yigit, Ferruh ; Ananyev,
> Konstantin ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com
> Cc: Iremonger, Bernard ; sta...@dpdk.org
> Subject: [PATCH v5 2/6] librte_table: fi
On Mon, Sep 18, 2017 at 02:49:52PM +, Shachar Beiser wrote:
> This removes the dependency on specific Mellanox OFED libraries by
> using the upstream rdma-core and linux upstream community code.
> Both rdma-core upstream and Mellanox OFED are Linux user-space packages:
> 1. Rdma-core is Linux
> -Original Message-
> From: Singh, Jasvinder
> Sent: Monday, September 18, 2017 4:30 PM
> To: Iremonger, Bernard ; dev@dpdk.org;
> Yigit, Ferruh ; Ananyev, Konstantin
> ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com
> Cc: Iremonger, Bernard ; sta...@dpdk.org
> Subject: RE: [dpdk-d
On Wed, 2017-09-20 at 11:51 +0100, Bruce Richardson wrote:
> No major changes, just cleanups.
>
> Bruce Richardson (3):
> build: sort meson options alphabetically
> build: fix driver install path
> build/x86: add SSE cpuflags
>
> config/x86/meson.build | 10 ++
> meson.build
> -Original Message-
> From: Rongqiang XIE [mailto:xie.rongqi...@zte.com.cn]
> Sent: Wednesday, August 23, 2017 8:06 AM
> To: Dumitrescu, Cristian
> Cc: dev@dpdk.org; Rongqiang XIE
> Subject: [PATCH] lib/librte_pipeline:fix the array index out of bound
>
> In function rte_pipeline_comp
On 20-Sep-17 12:23 PM, Santosh Shukla wrote:
Introducing rte_pci_get_iommu_class API which helps to get iommu class
of PCI device on the bus and returns preferred iova mapping mode for
PCI bus.
Patch also adds rte_pci_get_iommu_class definition for:
- bsdapp: api returns default iova mode.
- lin
Hi Hemant,
On 9/15/2017 11:02 AM, Hemant Agrawal wrote:
Hi,
On 9/14/2017 1:56 PM, Akhil Goyal wrote:
..
diff --git a/lib/librte_security/rte_security.c
b/lib/librte_security/rte_security.c
new file mode 100644
index 000..5776246
--- /dev/null
+++ b/lib/librte_security/rte_security.c
@@ -0
There is no reason to prevent ring from being larger than 0x0FFF.
Increase the maximum size to 0x7FFF, which is the maximum possible
without changing the code and the structure definition (size is stored
on a uint32_t).
Link: http://dpdk.org/ml/archives/dev/2017-September/074701.html
Sugg
The define RTE_RING_SZ_MASK is the maximum size supported by the
rte_ring. The size is checked at ring creation.
There is no reason today to mask the result of
rte_ring_sp_enqueue_burst() or rte_ring_sc_dequeue_burst() with this
value. The flag RTE_RING_QUOT_EXCEED was previously included in the
r
+Timothy, since git doesn't seem to automatically add reporters on CC.
On Wed, Sep 20, 2017 at 11:51:06AM +0100, Bruce Richardson wrote:
> To comply with the "hier" standard [Ref: man 7 hier], the driver .so files
> should not be placed in $datadir. Therefore we install them in a
> sub-directory o
Check iova mode and accordingly return phy addr.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Reviewed-by: Maxime Coquelin
Reviewed-by: Anatoly Burakov
Tested-by: Hemant Agrawal
---
lib/librte_eal/common/rte_malloc.c | 9 -
1 file changed, 8 insertions(+), 1 deletion(-)
Check iova mode and accordingly return phy addr.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Reviewed-by: Maxime Coquelin
Reviewed-by: Anatoly Burakov
Tested-by: Hemant Agrawal
---
lib/librte_eal/linuxapp/eal/eal_memory.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/li
For auto detection purpose:
* Below calls moved up in the eal initialization order:
- eal_option_device_parse
- rte_bus_scan
Based on the result of rte_bus_scan_iommu_class - select iova
mapping mode.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Reviewed-by: Maxime C
Check iova mode and accordingly map iova to pa or va.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Reviewed-by: Maxime Coquelin
Acked-by: Anatoly Burakov
Tested-by: Hemant Agrawal
---
lib/librte_eal/linuxapp/eal/eal_vfio.c | 10 --
1 file changed, 8 insertions(+), 2 delet
Introducing rte_eal_iova_mode() helper API. This API
used by non-eal library for detecting iova mode.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Reviewed-by: Maxime Coquelin
Tested-by: Hemant Agrawal
---
lib/librte_eal/bsdapp/eal/eal.c | 6 ++
lib/librte_eal
API(rte_bus_get_iommu_class) helps to automatically detect and select
appropriate iova mapping scheme for iommu capable device on that bus.
Algorithm for iova scheme selection for bus:
0. Iterate through bus_list.
1. Collect each bus iova mode value and update into 'mode' var.
2. Mode selection sc
Export rte_pci_match() function as it needed in the followup patch.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
Acked-by: Maxime Coquelin
Reviewed-by: Anatoly Burakov
Tested-by: Hemant Agrawal
---
lib/librte_eal/bsdapp/eal/rte_eal_version.map | 7 +++
lib/librte_eal/commo
v9:
- Added Tested-By: to series.
- Includes minor changes related to linuxapp api stub in [02/09]
(Suggested by Anatoly)
- Series rebased on tip commit : aee62e90
v8:
Includes minor review changes per v7 review comment from Anatoly.
Patches rebased on Tip commit:3d2e0448eb.
v7:
Includes no maj
Get iommu class of PCI device on the bus and returns preferred iova
mapping mode for that bus.
Patch also introduces RTE_PCI_DRV_IOVA_AS_VA drv flag.
Flag used when driver needs to operate in iova=va mode.
Algorithm for iova scheme selection for PCI bus:
0. If no device bound then return with RTE
Introducing rte_pci_get_iommu_class API which helps to get iommu class
of PCI device on the bus and returns preferred iova mapping mode for
PCI bus.
Patch also adds rte_pci_get_iommu_class definition for:
- bsdapp: api returns default iova mode.
- linuxapp: Has stub implementation, Followup patch
Hi Chas,
On Thu, Sep 07, 2017 at 05:21:51PM -0400, Charles (Chas) Williams wrote:
> After commit 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool") is it
> much harder to detect a "double free". If the developer makes a copy
> of an mbuf pointer and frees it twice, this condition is never detec
On 9/1/2017 5:23 PM, Kirill Rybalchenko wrote:
> Port info command prints information about all supported flow types,
> including dynamically mapped ones.
>
> Signed-off-by: Kirill Rybalchenko
> ---
> app/test-pmd/config.c | 9 ++---
> 1 file changed, 6 insertions(+), 3 deletions(-)
>
> dif
On 9/19/2017 2:29 AM, Rasesh Mody wrote:
> Hi,
>
> This patch set adds support for new firmware 8.30.12.0, includes
> enahncements, code cleanup and bug fixes. This patch set updates
> PMD version to 2.6.0.1.
>
> Thanks!
> Rasesh
>
> Rasesh Mody (53):
> net/qede/base: add NVM config options
>
Hi John,
On 9/18/2017 9:08 PM, Mcnamara, John wrote:
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Akhil Goyal
Sent: Thursday, September 14, 2017 9:27 AM
To: dev@dpdk.org
Cc: Doherty, Declan ; De Lara Guarch, Pablo
; hemant.agra...@nxp.com; Nicolau, Radu
; bor
1 - 100 of 156 matches
Mail list logo
