2016-07-01 17:26, Ferruh Yigit:
> struct rte_mempool changed its "ring" field to "pool_data"
>
> "ring" field is accessed by ivshmem library, and updated to "pool_data"
>
> This patch fixes the compile error:
>
> == Build lib/librte_ivshmem
> CC rte_ivshmem.o
>
On 1/7/2016 5:26 PM, Ferruh Yigit wrote:
> struct rte_mempool changed its "ring" field to "pool_data"
>
> "ring" field is accessed by ivshmem library, and updated to "pool_data"
>
> This patch fixes the compile error:
>
> == Build lib/librte_ivshmem
>CC rte_ivshmem.o
>
On 7/1/16, 12:16 PM, "dev on behalf of Wiles, Keith" wrote:
Well, after make sure I had CCACHE off and having the RTE_SDK variable set
correctly, it does appear we have a problem building DPDK/e1000 directory with
CLANG on my Ubuntu 16.04 updated as of today. If someone could please verify
struct rte_mempool changed its "ring" field to "pool_data"
"ring" field is accessed by ivshmem library, and updated to "pool_data"
This patch fixes the compile error:
== Build lib/librte_ivshmem
CC rte_ivshmem.o
.../lib/librte_ivshmem/rte_ivshmem.c:
In function 'add_mempool_to_metadata':
Well, after make sure I had CCACHE off and having the RTE_SDK variable set
correctly, it does appear we have a problem building DPDK/e1000 directory with
CLANG on my Ubuntu 16.04 updated as of today. If someone could please verify
the if this is something in my system. Using
[root at localhost ~]# modinfo i40e
filename:
/lib/modules/3.10.0-327.18.2.el7.x86_64/updates/drivers/net/ethernet/intel/i40e/i40e.ko
version:1.4.25
[root at localhost ~]# modinfo i40evf
filename:
/lib/modules/3.10.0-327.18.2.el7.x86_64/updates/drivers/net/ethernet/intel/i40evf/i40evf.ko
mmap the iomem range of the PCI device fails for kernels that
enabled CONFIG_IO_STRICT_DEVMEM option:
EAL: pci_map_resource():
cannot mmap(39, 0x7f1c5180, 0x10, 0x0):
Invalid argument (0x)
CONFIG_IO_STRICT_DEVMEM is introduced in Linux v4.5 and not
On 7/1/2016 4:52 PM, De Lara Guarch, Pablo wrote:
> Hi Ferruh,
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ferruh Yigit
>> Sent: Friday, July 01, 2016 4:08 PM
>> To: dev at dpdk.org
>> Cc: Stephen Hemminger
>> Subject: [dpdk-dev] [PATCH v2] igb_uio:
2016-07-01 15:39, Ferruh Yigit:
> On 7/1/2016 1:47 PM, Thomas Monjalon wrote:
> >> As a workaround igb_uio can stop reserving PCI memory resources, from
> >> kernel point of view io-memory region looks like idle and mmap works
> >> again.
> >>
> >> With this update device io-memory range is not
This patch-set includes,
1) General cleanup of compile time dependency.
2) made vector handler section based on run-time cpuflags
2) Added NEON support for optimized Rx handling
This patch-set is based on dpdk-next-virtio/master
v2:
- made vector handler selection based on run-time cpuflags
Added neon based Rx vector implementation.
Selection of the new handler based neon availability at runtime.
Updated the release notes and MAINTAINERS file.
Signed-off-by: Jerin Jacob
---
MAINTAINERS | 1 +
doc/guides/rel_notes/release_16_07.rst | 2 +
* Introduced cpuflag based run-time detection to
select the SSE based simple Rx handler
* Split out SSE instruction based virtio simple Rx
implementation to a separate file
Signed-off-by: Jerin Jacob
---
drivers/net/virtio/Makefile | 4 +
drivers/net/virtio/virtio_rxtx.c
Removed unnecessary compile time dependency on "use_simple_rxtx".
Signed-off-by: Jerin Jacob
---
drivers/net/virtio/Makefile | 3 ---
drivers/net/virtio/virtio_pci.h | 1 +
drivers/net/virtio/virtio_rxtx.c| 28 +---
This patch-set includes,
1) General cleanup of compile time dependency.
2) made vector handler section based on run-time cpuflags
2) Added NEON support for optimized Rx handling
This patch-set is based on dpdk-next-virtio/master at aaaf0c005
v2:
- made vector handler selection based on run-time
2016-07-01 15:38, Sergio Gonzalez Monroy:
> Since below commit, ACL library is outside the scope of --whole-archive
> and ACL autotest fails.
>
> RTE>>acl_autotest
> ACL: allocation of 25166728 bytes on socket 9 for ACL_acl_ctx failed
> ACL: rte_acl_add_rules(acl_ctx): rule #1 is invalid
>
2016-07-01 10:43, Olivier Matz:
> As discussed in http://dpdk.org/ml/archives/dev/2016-June/042229.html,
> clarify the behavior of rte_eth_dev_get_supported_ptypes().
>
> Signed-off-by: Olivier Matz
Konstantin had already reviewed this text in the above thread.
Applied, thanks
Are we sure
mmap the iomem range of the PCI device fails for kernels that
enabled CONFIG_IO_STRICT_DEVMEM option:
EAL: pci_map_resource():
cannot mmap(39, 0x7f1c5180, 0x10, 0x0):
Invalid argument (0x)
CONFIG_IO_STRICT_DEVMEM is introduced in Linux v4.4 and not
> > The old structure rte_eth_xstats contained names and values.
> > The new structure rte_eth_xstat contains ids and values.
> >
> > Fixes: bd6aa172cf35 ("ethdev: fetch extended statistics with integer ids")
> > Fixes: e2aae1c1ced9 ("ethdev: remove name from extended statistic fetch")
> >
> >
2016-06-29 16:47, Thomas Monjalon:
> The commit id of a fixed commit must be in the current branch.
> It avoids referencing a local branch or a next-* branch when
> pushing in the master.
>
> Signed-off-by: Thomas Monjalon
Applied
2016-06-30 13:45, Thomas Monjalon:
> If there is a change in the config directory the build test
> will refresh the tested build config to take into account new options.
> The git working directory and the last git commit are checked for a
> change in config/.
>
> Signed-off-by: Thomas Monjalon
2016-07-01 14:16, Remy Horton:
> For all drivers that currently implement xstats, the id field in the
> rte_eth_stats_name structure equals the entry's array index. This
> patch eliminates the redundant id field as a direct index lookup is
> faster than a search for the matching id field.
>
>
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Reshma Pattan
> Sent: Friday, July 01, 2016 11:28 AM
> To: dev at dpdk.org
> Cc: Pattan, Reshma
> Subject: [dpdk-dev] [PATCH] app/testpmd: add timer based fwd Rx queue
> flushing
>
> Testpmd can stuck inside
Hi Ferruh,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ferruh Yigit
> Sent: Friday, July 01, 2016 4:08 PM
> To: dev at dpdk.org
> Cc: Stephen Hemminger
> Subject: [dpdk-dev] [PATCH v2] igb_uio: fix possible mmap failure for Linux >
> v4.3
>
> mmap the
On 7/1/2016 1:47 PM, Thomas Monjalon wrote:
> Thank you Ferruh for taking care of igb_uio.
>
> 2016-07-01 12:35, Ferruh Yigit:
>> With kernels enabled CONFIG_IO_STRICT_DEVMEM option mmap the iomem area
>> to userspace fails:
>
> Maybe some words are missing.
> Please check punctuation of the
Since below commit, ACL library is outside the scope of --whole-archive
and ACL autotest fails.
RTE>>acl_autotest
ACL: allocation of 25166728 bytes on socket 9 for ACL_acl_ctx failed
ACL: rte_acl_add_rules(acl_ctx): rule #1 is invalid
Line 1584: SSE classify with zero categories failed!
Since [1] duplicates in LDLIBS are removed. The side effect is that it
does not distinguish between libraries or linker flags.
This patch allows multiple linker flags in LDLIBS, such as
--whole-archive.
[1] Commit: edf4d331dcdb ("mk: eliminate duplicates from libraries list")
Signed-off-by:
Hi,
Sorry for the long delay.
On Fri, May 20, 2016 at 03:50:04PM +0300, Ilya Maximets wrote:
> In current implementation guest application can reinitialize vrings
> by executing start after stop. In the same time host application
> can still poll virtqueue while device stopped in guest and it
add release note for live migration of a VM with SRIOV VF
Signed-off-by: Bernard Iremonger
---
doc/guides/rel_notes/release_16_07.rst | 3 +++
1 file changed, 3 insertions(+)
diff --git a/doc/guides/rel_notes/release_16_07.rst
b/doc/guides/rel_notes/release_16_07.rst
index 569f562..350b259
Update: I pulled a new clone and now I do not see that problem, so please
ignore.
Regards,
Keith
Thank you Ferruh for taking care of igb_uio.
2016-07-01 12:35, Ferruh Yigit:
> With kernels enabled CONFIG_IO_STRICT_DEVMEM option mmap the iomem area
> to userspace fails:
Maybe some words are missing.
Please check punctuation of the whole commit message to make it easier
to understand.
> EAL:
I am seeing unused variable warnings/errors when building the current repo with
the clang compiler builds in the e1000/base directory.
Does anyone else see this problem?
Regards,
Keith
For all drivers that currently implement xstats, the id field in the
rte_eth_stats_name structure equals the entry's array index. This
patch eliminates the redundant id field as a direct index lookup is
faster than a search for the matching id field.
Signed-off-by: Remy Horton
---
On 29/06/2016 17:59, Thomas Monjalon wrote:
> The old structure rte_eth_xstats contained names and values.
> The new structure rte_eth_xstat contains ids and values.
>
> Fixes: bd6aa172cf35 ("ethdev: fetch extended statistics with integer ids")
> Fixes: e2aae1c1ced9 ("ethdev: remove name from
Hi,
I am trying to dma packets from NIC to memory on a PCIE device (not buffers
on hugepage.) Memory of the device is mapped to the physical memory via PCI
BAR.
I created a kernel module allocating/freeing memory on the device, and
applications can interact with the module via IOCTL so that apps
On 7/1/2016 12:29 PM, De Lara Guarch, Pablo wrote:
> Hi Pengyu,
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pengyu Ma
>> Sent: Friday, July 01, 2016 9:53 AM
>> To: thomas.monjalon at 6wind.com; dev at dpdk.org
>> Subject: [dpdk-dev] [PATCH] Fix
Hi,
Does anyone know DPDK works with JNI?
Thanks,
Junguk
> > David Hunt (2)
> > mempool: add stack (lifo) mempool handler
> > test: migrate custom handler test to stack handler
>
> Acked-by: Olivier Matz
Applied, thanks
2016-07-01 11:27, Sergio Gonzalez Monroy:
> On 01/07/2016 11:05, Thomas Monjalon wrote:
> > 2016-07-01 09:05, Sergio Gonzalez Monroy:
> >> On 30/06/2016 17:22, Thomas Monjalon wrote:
> >>> 2016-06-30 17:14, Sergio Gonzalez Monroy:
> On 30/06/2016 17:10, Thomas Monjalon wrote:
> >
With kernels enabled CONFIG_IO_STRICT_DEVMEM option mmap the iomem area
to userspace fails:
EAL: pci_map_resource():
cannot mmap(39, 0x7f1c5180, 0x10, 0x0):
Invalid argument (0x)
As a workaround igb_uio can stop reserving PCI memory resources, from
2016-07-01 10:57, Olivier MATZ:
>
> On 06/30/2016 10:05 PM, Thomas Monjalon wrote:
> > 2016-06-30 13:49, Bruce Richardson:
> >> The mempool_count and mempool_free_count behaved contrary to what their
> >> names suggested. The free_count function actually returned the number of
> >> elements that
2016-07-01 09:05, Sergio Gonzalez Monroy:
> On 30/06/2016 17:22, Thomas Monjalon wrote:
> > 2016-06-30 17:14, Sergio Gonzalez Monroy:
> >> On 30/06/2016 17:10, Thomas Monjalon wrote:
> >>> 2016-06-30 17:01, Sergio Gonzalez Monroy:
> --- a/mk/rte.app.mk
> +++ b/mk/rte.app.mk
> @@
On 7/1/2016 11:21 AM, Mcnamara, John wrote:
> Hi,
>
> We have seen an issue when using the igb_uio module in Fedora
> 24. However, it relates to kernel 4.5+ so it could occur in other
> distros/oses.
>
> The issue occurs after binding a nic to igb_uio:
>
> # ./tools/dpdk_nic_bind.py -b
This pachset set describes the procedure to Live migrate
a VM with Virtio and VF PMD's using the bonding PMD.
Bernard Iremonger (2):
doc: live migration of VM with Virtio and VF
doc: add live migration overview image
doc/guides/how_to/img/lm_overview.svg | 666
This patch adds an image of the Live Migration test configuration.
Signed-off-by: Bernard Iremonger
---
doc/guides/how_to/img/lm_overview.svg | 666 +
doc/guides/how_to/lm_bond_virtio_sriov.rst | 3 +
2 files changed, 669 insertions(+)
create mode 100644
This patch describes the procedure to be be followed
to perform Live Migration of a VM with Virtio and VF PMD's
using the bonding PMD.
It includes sample host and VM scripts used in the procedure,
and a sample switch configuration.
Signed-off-by: Bernard Iremonger
---
Hi Pengyu,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pengyu Ma
> Sent: Friday, July 01, 2016 9:53 AM
> To: thomas.monjalon at 6wind.com; dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] Fix misleading indentation in ethtool
You need to add the library
Testpmd can stuck inside do while loop of the flush_fwd_rx_queues()
function. As non-zero packets are returned always by rte_eth_rx_burst()
function when compiled with no optimizations and if input line rate is
high. "do while" loop must exit at one stage to proceed further to
enable packet
On 01/07/2016 11:05, Thomas Monjalon wrote:
> 2016-07-01 09:05, Sergio Gonzalez Monroy:
>> On 30/06/2016 17:22, Thomas Monjalon wrote:
>>> 2016-06-30 17:14, Sergio Gonzalez Monroy:
On 30/06/2016 17:10, Thomas Monjalon wrote:
> 2016-06-30 17:01, Sergio Gonzalez Monroy:
>> ---
On 01/07/2016 11:16, Elo, Matias (Nokia - FI/Espoo) wrote:
>> -Original Message-
>> From: Sergio Gonzalez Monroy [mailto:sergio.gonzalez.monroy at intel.com]
>> Sent: Friday, July 01, 2016 1:05 PM
>> To: Elo, Matias (Nokia - FI/Espoo) ;
>> dev at dpdk.org
>> Cc: ferruh.yigit at intel.com;
On 01/07/2016 10:42, Elo, Matias (Nokia - FI/Espoo) wrote:
>> What is not clear to me is motivation to use weak here instead of simply
>>> using >CONFIG_RTE_I40E_INC_VECTOR
>> macro to exclude stubs in i40e_rxtx.c. It will make library smaller and
>> avoid
>>> issues like this one
On 06/30/2016 10:05 PM, Thomas Monjalon wrote:
> 2016-06-30 13:49, Bruce Richardson:
>> The mempool_count and mempool_free_count behaved contrary to what their
>> names suggested. The free_count function actually returned the number of
>> elements that were allocated from the pool, not the
As discussed in http://dpdk.org/ml/archives/dev/2016-June/042229.html,
clarify the behavior of rte_eth_dev_get_supported_ptypes().
Signed-off-by: Olivier Matz
---
lib/librte_ether/rte_ethdev.h | 15 +++
1 file changed, 15 insertions(+)
diff --git a/lib/librte_ether/rte_ethdev.h
Hi,
We have seen an issue when using the igb_uio module in Fedora
24. However, it relates to kernel 4.5+ so it could occur in other
distros/oses.
The issue occurs after binding a nic to igb_uio:
# ./tools/dpdk_nic_bind.py -b igb_uio :03:00.0
# ./x86_64-native-linuxapp-gcc/app/test
Hi Dave,
On 07/01/2016 09:46 AM, David Hunt wrote:
> This patch set adds a lifo stack handler to the external mempool
> manager.
>
> This patch utilises the mempool handler feature which allows the addition
> of new mempool handlers to DPDK.
>
> v6 changes:
> * removed unneeded mp_ext
> -Original Message-
> From: Sergio Gonzalez Monroy [mailto:sergio.gonzalez.monroy at intel.com]
> Sent: Friday, July 01, 2016 1:05 PM
> To: Elo, Matias (Nokia - FI/Espoo) ;
> dev at dpdk.org
> Cc: ferruh.yigit at intel.com; damarion at cisco.com
> Subject: Re: [dpdk-dev] weak functions in
On Wed, Jun 29, 2016 at 09:05:33AM +, Jianfeng Tan wrote:
> - if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_CQ_NUM) == 1)
> - rte_kvargs_process(kvlist, VIRTIO_USER_ARG_CQ_NUM,
> -_integer_arg, );
> + if (rte_kvargs_count(kvlist,
On 29/06/2016 17:40, Thomas Monjalon wrote:
[..]
> I don't think it is possible to standardize stats ids, for two reasons:
> - it is hard to maintain and avoid conflicts between drivers
> - the drivers would have to lookup the names which degrades performance
I designed it that way to keep
On Wed, Jun 29, 2016 at 03:23:03AM +, Jianfeng Tan wrote:
> On some older systems, such as SUSE 11, the compiling error shows
> as:
>.../dpdk/drivers/net/virtio/virtio_user/virtio_user_dev.c:67:22:
> error: ?O_CLOEXEC? undeclared (first use in this function)
>
> The fix is to use
On Wed, Jun 29, 2016 at 03:20:06AM +, Jianfeng Tan wrote:
> With current config structure, all configuration parameters put into
> common_base with a default value, and overwritten in environment file
> if required, CONFIG_RTE_VIRTIO_USER is missing in common_base.
>
> This fix is simple, by
The ixgbe driver does not compile if CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n
because the macro has not the proper number of parameters. To reproduce
the issue:
make config T=x86_64-native-linuxapp-gcc
sed -i
's,CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=y,CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n,'
On Tue, Jun 28, 2016 at 11:58:28AM +0800, Yuanhan Liu wrote:
> This is a small series fixes 3 coverity issues.
Series applied to dpdk-next-virtio.
--yliu
>
> John, I'm wondering maybe maybe we could add the next-net and
> next-virtio tree into the coverity test as well? So that we could
On Thu, Jun 30, 2016 at 03:58:31PM +, Mcnamara, John wrote:
> > -Original Message-
> > From: Yuanhan Liu [mailto:yuanhan.liu at linux.intel.com]
> > Sent: Tuesday, June 28, 2016 4:58 AM
> > To: dev at dpdk.org
> > Cc: Xie, Huawei ; Mcnamara, John
> > ; Yuanhan Liu
> > Subject: [PATCH
> > >>> What is not clear to me is motivation to use weak here instead of simply
> > using >CONFIG_RTE_I40E_INC_VECTOR
> > >>> macro to exclude stubs in i40e_rxtx.c. It will make library smaller and
> > >>> avoid
> > issues like this one
> > >>> which are quite hard to troubleshoot.
> > >> Since
On Thu, Jun 30, 2016 at 08:25:14PM +0200, Thomas Monjalon wrote:
> 2016-06-30 19:03, John McNamara:
> > This patch converts the NIC feature table in the overview doc into a set of
> > ini files and adds some functions into the Sphinx conf.py file to convert
> > them
> > back into an RST table.
>
Hi David,
On 06/30/2016 08:05 PM, David Hunt wrote:
> After introducing the stack handler in the previous commit,
> we now have very similar code to the custom handler in test_mempool.c,
> which creates a custom mempool based on simple mallocs.
> The stack handler is a cleaner example of adding a
Fixes a bug where rte_eth_vhost_get_queue_event would not return enabled queues
after a guest application restart.
Fixes: ee584e9710b9 ("vhost: add driver on top of the library")
Signed-off-by: Rich Lane
---
drivers/net/vhost/rte_eth_vhost.c | 10 ++
1 file changed, 10 insertions(+)
Hi Daniel,
>>> --- a/lib/librte_cmdline/cmdline_rdline.c
>>> +++ b/lib/librte_cmdline/cmdline_rdline.c
>>> @@ -377,7 +377,10 @@ rdline_char_in(struct rdline *rdl, char c)
>>> case CMDLINE_KEY_CTRL_K:
>>> cirbuf_get_buf_head(>right, rdl->kill_buf,
>>
On 30/06/2016 17:22, Thomas Monjalon wrote:
> 2016-06-30 17:14, Sergio Gonzalez Monroy:
>> On 30/06/2016 17:10, Thomas Monjalon wrote:
>>> 2016-06-30 17:01, Sergio Gonzalez Monroy:
--- a/mk/rte.app.mk
+++ b/mk/rte.app.mk
@@ -76,12 +76,13 @@ _LDLIBS-$(CONFIG_RTE_LIBRTE_IP_FRAG)
> The ixgbe driver does not compile if CONFIG_RTE_IXGBE_RX_OLFLAGS_ENABLE=n
> because the macro has not the proper number of parameters. To reproduce
> the issue:
>
> make config T=x86_64-native-linuxapp-gcc
> sed -i
>
When the specified cores and memory lie on different numa socket with
physical NIC, vhost fails to set up rx queue, and exits without any
hints. This could leads to confusion of users.
This patch fixes it by adding some error messages when calling ether
APIs returns errors.
Fixes: 4796ad63ba1f
After introducing the stack handler in the previous commit,
we now have very similar code to the custom handler in test_mempool.c,
which creates a custom mempool based on simple mallocs.
The stack handler is a cleaner example of adding a new mempool handler,
so this commit replaces the custom
This is a mempool handler that is useful for pipelining apps, where
the mempool cache doesn't really work - example, where we have one
core doing rx (and alloc), and another core doing Tx (and return). In
such a case, the mempool ring simply cycles through all the mbufs,
resulting in a LLC miss on
This patch set adds a lifo stack handler to the external mempool
manager.
This patch utilises the mempool handler feature which allows the addition
of new mempool handlers to DPDK.
v6 changes:
* removed unneeded mp_ext variable.
* added in a free for mp_stack after we're finished with it.
gcc complains about:
build/lib/librte_eal/linuxapp/kni/e1000_phy.c:3303:2:
error: this 'if' clause does not guard... [-Werror=misleading-indentation]
Code indentation is misleadingly indented as whether
the following content is guarded by if or not.
With the reference of the context, add the
Hi Thomas,
> > >
> > > Looking at your special case, if the user did set an isolcpus option
> > > for another use, with no -c/-l, I understand the dpdk application
> > > won't care too much about it.
> > > So, this seems like somehow rude to the rest of the system and
> unwanted.
> >
> > The case
This patch explains current virtio PMD Rx/Tx callbacks, to help understand
what's the difference, and how to enable the right ones.
Signed-off-by: Zhihong Wang
Acked-by: John McNamara
--
Changes in v3:
1. Rephrase for clearer description.
--
Changes in v2:
1.
76 matches
Mail list logo