[dpdk-dev] [PATCH v2] ring: fix minor memory free issue

2015-11-06 Thread John McNamara
Fix minor memory free issue in error clean-up. Fixes: 651c505af862 ("ring: enhance device setup from rings") Reported-by Coverity (CID 119258) Signed-off-by: John McNamara --- V2: * Add fixline. drivers/net/ring/rte_eth_ring.c | 8 +--- 1 file changed, 5 insertions(+), 3 deletions(-)

[dpdk-dev] [PATCH] ring: fix minor memory free issue

2015-11-06 Thread John McNamara
Fix minor memory free issue in error clean-up. Reported-by Coverity (CID 119258) Signed-off-by: John McNamara --- drivers/net/ring/rte_eth_ring.c | 6 -- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ring/rte_eth_ring.c b/drivers/net/ring/rte_eth_ring.c index

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Bruce Richardson
On Fri, Nov 06, 2015 at 05:10:07PM +, Bruce Richardson wrote: > On Thu, Nov 05, 2015 at 04:09:18PM +0100, Adrien Mazarguil wrote: > > > > I won't argue against this as it's obviously more complex than the original > > method, however note that users of the RTE_PMD_DEBUG_TRACE() macro do not >

[dpdk-dev] [v2 1/1] librte_ether: fix coverity errors in rte_eth_copy_pci_info

2015-11-06 Thread Bernard Iremonger
add return statement to if branch Dereferencing NULL pointer reported by Coverity, CID 119256. Dereferencing NULL pointer reported by Coverity, CID 119257. Signed-off-by: Bernard Iremonger --- lib/librte_ether/rte_ethdev.c | 1 + 1 file changed, 1 insertion(+) diff --git

[dpdk-dev] [v2 0/1] librte_ether: fix coverity errors

2015-11-06 Thread Bernard Iremonger
Changes in v2: Add return statement to if branch instead of an else branch. Bernard Iremonger (1): librte_ether: fix coverity errors in rte_eth_copy_pci_info lib/librte_ether/rte_ethdev.c | 1 + 1 file changed, 1 insertion(+) -- 1.9.1

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Bruce Richardson
On Thu, Nov 05, 2015 at 04:09:18PM +0100, Adrien Mazarguil wrote: > > I won't argue against this as it's obviously more complex than the original > method, however note that users of the RTE_PMD_DEBUG_TRACE() macro do not > have to modify their code. They shouldn't care about the implementation.

[dpdk-dev] [PATCH 1/1] librte_ether: fix coverity errors in rte_eth_copy_pci_info

2015-11-06 Thread Iremonger, Bernard
Hi Thomas, > Subject: Re: [dpdk-dev] [PATCH 1/1] librte_ether: fix coverity errors in > rte_eth_copy_pci_info > > 2015-11-06 16:30, Bernard Iremonger: > > add else branch to if statement. > > I think a return statement would be more appropriate. > I will add return statement instead.

[dpdk-dev] [PATCH] test: fix eal_flags_autotest due to missing_n_flag test

2015-11-06 Thread Thomas Monjalon
2015-11-06 15:15, Pablo de Lara: > eal_flags_autotest was broken after commit > 19bfa4dd ("eal: make the -n argument optional"), > since the unit test was checking that app would not run > if -n flag was missing, which now it is possible. > > Also, subtest test_missing_n_flag() has been renamed >

[dpdk-dev] [PATCH v6 2/2] doc: add user-space ethtool sample app guide

2015-11-06 Thread Remy Horton
Signed-off-by: Remy Horton --- doc/guides/rel_notes/release_2_2.rst | 1 + doc/guides/sample_app_ug/ethtool.rst | 173 +++ doc/guides/sample_app_ug/index.rst | 1 + 3 files changed, 175 insertions(+) create mode 100644 doc/guides/sample_app_ug/ethtool.rst

[dpdk-dev] [PATCH v6 1/2] example: add user-space ethtool sample application

2015-11-06 Thread Remy Horton
Further enhancements to the userspace ethtool implementation that was submitted in 2.1 and packaged as a self-contained sample application. Implements an rte_ethtool shim layer based on rte_ethdev API, along with a command prompt driven demonstration application. Signed-off-by: Remy Horton ---

[dpdk-dev] [PATCH v6 0/2] User-space ethtool sample application

2015-11-06 Thread Remy Horton
Further enhancements to the userspace ethtool implementation that was submitted in 2.1 and packaged as a self-contained sample application. Implements an rte_ethtool shim layer based on rte_ethdev API, along with a command prompt driven demonstration application. This patchset depends on: *

[dpdk-dev] [PATCH] autotest.py: increase memory for hash_autotest

2015-11-06 Thread Pablo de Lara
Hash_autotest is in test group 2 which had only 32 MB of memory, which is increased to 64 MB to make it run. Signed-off-by: Pablo de Lara --- app/test/autotest_data.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/test/autotest_data.py b/app/test/autotest_data.py index

[dpdk-dev] [PATCH v2] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Helin Zhang
This fixes the issue of not freeing memzone in a call to free the memory for adminq DMA. Signed-off-by: Helin Zhang --- doc/guides/rel_notes/release_2_2.rst | 5 + drivers/net/i40e/base/i40e_osdep.h | 2 +- drivers/net/i40e/i40e_ethdev.c | 14 +- 3 files changed, 15

[dpdk-dev] [PATCH] app/testpmd: fix wrong fdir help and doc

2015-11-06 Thread Wenzhuo Lu
After implementing the fdir new modes for x550, the CLIs are modified. Forgot to update the related help info and doc. Fixes: 53b2bb9b7ea7 ("app/testpmd: new flow director commands") Signed-off-by: Wenzhuo Lu --- app/test-pmd/cmdline.c | 35 +++-

[dpdk-dev] [PATCH 3/3] app/testpmd: fix ICC compile issue

2015-11-06 Thread Helin Zhang
It fixes compile issue on ICC 13.0.0. Error logs: app/test-pmd/cmdline.c(8160): error #188: enumerated type mixed with another type entry.input.flow.tunnel_flow.tunnel_type = Signed-off-by: Helin Zhang --- app/test-pmd/cmdline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff

[dpdk-dev] [PATCH 2/3] i40e: fix ICC compile issue

2015-11-06 Thread Helin Zhang
It fixes compile issue on ICC 13.0.0. Error logs: i40e_ethdev.c(7943): error #188: enumerated type mixed with another type PMD_INIT_LOG(ERR, Signed-off-by: Helin Zhang --- drivers/net/i40e/i40e_ethdev.c | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git

[dpdk-dev] [PATCH 1/3] bonding: fix ICC compile issue

2015-11-06 Thread Helin Zhang
It fixes compile issue on ICC 13.0.0. Error logs: rte_eth_bond_pmd.c(1327): error #188: enumerated type mixed with another type slave_eth_dev->data->dev_conf.rxmode.mq_mode |= ETH_MQ_RX_RSS; Signed-off-by: Helin Zhang --- drivers/net/bonding/rte_eth_bond_pmd.c | 3 ++- 1 file changed, 2

[dpdk-dev] [PATCH 0/3] fix compile issues

2015-11-06 Thread Helin Zhang
It fixes compile issues for bonding, i40e, and testpmd on ICC 13.0.0. Helin Zhang (3): bonding: fix ICC compile issue i40e: fix ICC compile issue app/testpmd: fix ICC compile issue app/test-pmd/cmdline.c | 2 +- drivers/net/bonding/rte_eth_bond_pmd.c | 3 ++-

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Richardson, Bruce
> -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarguil at 6wind.com] > > On Fri, Nov 06, 2015 at 02:39:31PM +, Richardson, Bruce wrote: > [...] > > > > Hi Adrien, > > > > > > > > I'm trying to dig into this a bit more now, and try out using a > > > > static inline

[dpdk-dev] [PATCH] test: fix eal_flags_autotest due to missing_n_flag test

2015-11-06 Thread Pablo de Lara
eal_flags_autotest was broken after commit 19bfa4dd ("eal: make the -n argument optional"), since the unit test was checking that app would not run if -n flag was missing, which now it is possible. Also, subtest test_missing_n_flag() has been renamed to test_invalid_n_flag(), as now -n flag is

[dpdk-dev] [PATCH v3 14/14] eal: arm: define rte_smp_mb(), rte_smp_wmb(), rte_smp_rmb() for arm

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- lib/librte_eal/common/include/arch/arm/rte_atomic.h | 6 ++ 1 file changed, 6 insertions(+) diff --git a/lib/librte_eal/common/include/arch/arm/rte_atomic.h b/lib/librte_eal/common/include/arch/arm/rte_atomic.h index f3f3b6e..454a12b 100644 ---

[dpdk-dev] [PATCH v3 13/14] eal: introduce rte_smp_*mb() for memory barriers to use between lcores

2015-11-06 Thread Jerin Jacob
This commit introduce rte_smp_mb(), rte_smp_wmb() and rte_smp_rmb(), in order to enable memory barriers between lcores. The patch does not provide any functional change for IA, the goal is to have infrastructure for weakly ordered machines like ARM to work on DPDK. Signed-off-by: Jerin Jacob

[dpdk-dev] [PATCH v3 12/14] maintainers: claim responsibility for ARMv8

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- MAINTAINERS | 5 + 1 file changed, 5 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a8933eb..c44b328 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -128,6 +128,11 @@ ARM v7 M: Jan Viktorin F: lib/librte_eal/common/include/arch/arm/ +ARM v8 +M:

[dpdk-dev] [PATCH v3 11/14] updated release note for armv8 support for DPDK 2.2

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- doc/guides/rel_notes/release_2_2.rst | 7 --- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/doc/guides/rel_notes/release_2_2.rst b/doc/guides/rel_notes/release_2_2.rst index 43a3a3c..a3587a2 100644 --- a/doc/guides/rel_notes/release_2_2.rst +++

[dpdk-dev] [PATCH v3 10/14] mk: add support for thunderx machine target based on armv8-a

2015-11-06 Thread Jerin Jacob
Created the new thunderx machine target to address difference in "cache line size" and "-mcpu=thunderx" vs default armv8-a machine target Signed-off-by: Jerin Jacob --- config/defconfig_arm64-thunderx-linuxapp-gcc | 56 +++ mk/machine/thunderx/rte.vars.mk |

[dpdk-dev] [PATCH v3 09/14] mk: add support for armv8 on top of armv7

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- config/defconfig_arm64-armv8a-linuxapp-gcc | 56 + mk/arch/arm64/rte.vars.mk | 58 ++ mk/machine/armv8a/rte.vars.mk | 58 ++ 3 files changed, 172

[dpdk-dev] [PATCH v3 08/14] acl: arm64: acl implementation using NEON gcc intrinsic

2015-11-06 Thread Jerin Jacob
verified with testacl and acl_autotest applications on arm64 architecture. Signed-off-by: Jerin Jacob --- app/test-acl/main.c | 4 + lib/librte_acl/Makefile | 5 + lib/librte_acl/acl.h | 4 + lib/librte_acl/acl_run_neon.c | 46 +++

[dpdk-dev] [PATCH v3 07/14] app: test_cpuflags: test the new cpu flags added for arm64

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- app/test/test_cpuflags.c | 26 ++ 1 file changed, 26 insertions(+) diff --git a/app/test/test_cpuflags.c b/app/test/test_cpuflags.c index 557458f..e8d0ce7 100644 --- a/app/test/test_cpuflags.c +++ b/app/test/test_cpuflags.c @@ -120,6

[dpdk-dev] [PATCH v3 06/14] eal: arm: ret_vector.h improvements

2015-11-06 Thread Jerin Jacob
added the definition of rte_xmm and xmm_t for acl noen implementation. removed the emulated _mm_* functions Signed-off-by: Jerin Jacob --- lib/librte_eal/common/include/arch/arm/rte_vect.h | 54 +++ 1 file changed, 15 insertions(+), 39 deletions(-) diff --git

[dpdk-dev] [PATCH v3 05/14] eal: arm64: rte_memcpy_64.h version based on libc memcpy

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- .../common/include/arch/arm/rte_memcpy.h | 4 + .../common/include/arch/arm/rte_memcpy_64.h| 93 ++ 2 files changed, 97 insertions(+) create mode 100644 lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h diff --git

[dpdk-dev] [PATCH v3 04/14] eal: arm64: add armv8-a version of rte_cycles_64.h

2015-11-06 Thread Jerin Jacob
cntcvt_el0 ticks are not based on cpu clk unlike rdtsc in x86. Its a fixed clock running based at constant speed. Though its a armv8-a implementer choice, typically it runs at 50 or 100 MHz Signed-off-by: Jerin Jacob --- .../common/include/arch/arm/rte_cycles.h | 4 ++

[dpdk-dev] [PATCH v3 03/14] eal: arm64: add armv8-a version of rte_prefetch_64.h

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- .../common/include/arch/arm/rte_prefetch.h | 4 ++ .../common/include/arch/arm/rte_prefetch_64.h | 61 ++ 2 files changed, 65 insertions(+) create mode 100644 lib/librte_eal/common/include/arch/arm/rte_prefetch_64.h diff --git

[dpdk-dev] [PATCH v3 02/14] eal: arm64: add armv8-a version of rte_cpuflags_64.h

2015-11-06 Thread Jerin Jacob
Signed-off-by: Jerin Jacob --- .../common/include/arch/arm/rte_cpuflags.h | 4 + .../common/include/arch/arm/rte_cpuflags_64.h | 152 + 2 files changed, 156 insertions(+) create mode 100644 lib/librte_eal/common/include/arch/arm/rte_cpuflags_64.h diff --git

[dpdk-dev] [PATCH v3 01/14] eal: arm64: add armv8-a version of rte_atomic_64.h

2015-11-06 Thread Jerin Jacob
except rte_?wb() functions other functions are used from RTE_FORCE_INTRINSICS=y scheme Signed-off-by: Jerin Jacob --- .../common/include/arch/arm/rte_atomic.h | 4 + .../common/include/arch/arm/rte_atomic_64.h| 88 ++ 2 files changed, 92 insertions(+)

[dpdk-dev] [PATCH v3 00/14] DPDK armv8-a support

2015-11-06 Thread Jerin Jacob
This is the v3 patchset for ARMv8 that now sits on top of the v6 patch (based on upstream 82fb702077f67585d64a07de0080e5cb6a924a72) of the ARMv7 code by RehiveTech. It adds code into the same arm include directory, reducing code duplication. Tested on an ThunderX arm 64-bit arm server board, with

[dpdk-dev] [PATCH] doc: add entry for enic PMD Tx improvement to the 2.2 release notes.

2015-11-06 Thread johndale
Signed-off-by: johndale --- doc/guides/rel_notes/release_2_2.rst | 3 +++ 1 file changed, 3 insertions(+) diff --git a/doc/guides/rel_notes/release_2_2.rst b/doc/guides/rel_notes/release_2_2.rst index 59dda59..8bc5fca 100644 --- a/doc/guides/rel_notes/release_2_2.rst +++

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Richardson, Bruce
> -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarguil at 6wind.com] > > Hi Bruce, > > On Fri, Nov 06, 2015 at 11:52:44AM +, Bruce Richardson wrote: > > +Adrien on To: line > > > > Email user/client fail on original. :-( > > > > - Forwarded message from Bruce

[dpdk-dev] [PATCH 3/3] i40e: refactor xstats queue handling

2015-11-06 Thread Harry van Haaren
This patch refactors the queue and priority statistic handling. Generic queue stats are presented by rte_eth_xstats_get(), and the i40e_xstats_get() exposes only the extra stats. Signed-off-by: Harry van Haaren --- drivers/net/i40e/i40e_ethdev.c | 112 -

[dpdk-dev] [PATCH 2/3] ixgbe: refactor xstats queue handling

2015-11-06 Thread Harry van Haaren
This patch refactors the queue handling. Generic queue stats are handled by rte_eth_xstats_get() and the ixgbe_xstats_get() exposes only the extra stats. Signed-off-by: Harry van Haaren --- drivers/net/ixgbe/ixgbe_ethdev.c | 132 --- 1 file changed, 53

[dpdk-dev] [PATCH 1/3] ethdev: xstats generic Q stats refactor

2015-11-06 Thread Harry van Haaren
This patch refactors the generic queue stats to be exposed by rte_ethdev_xstats_get(). Signed-off-by: Harry van Haaren --- lib/librte_ether/rte_ethdev.c | 10 ++ 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c

[dpdk-dev] [PATCH 0/3] xstats queue handling

2015-11-06 Thread Harry van Haaren
This patchset modifies how queue statistics are presented by rte_eth_xstats_get() and each PMD's xstats_get(). Generic stats from the rte_eth_stats struct are presented by rte, and each PMD can augment those stats with extra stats that are available (if any). Currently ixgbe and i40e are the

[dpdk-dev] [PATCH] reserve 'make install' for future use

2015-11-06 Thread Thomas Monjalon
2015-11-06 12:57, Bruce Richardson: > So, any thoughts or comments on this? There has been lots of discussion in > this > general area but nothing yet going into the release to try and improve the > situation. > > Are we just going to kick the problem down the road to the 2.3 release? I plan

[dpdk-dev] [PATCH] vhost: eventfd_link's minor number shall be specified

2015-11-06 Thread Xiaobo Chi
eventfd_link_misc's minor number shall be MISC_DYNAMIC_MINOR to let Linux kernel dynamically assign one while loading. Signed-off-by: Xiaobo Chi --- lib/librte_vhost/eventfd_link/eventfd_link.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/librte_vhost/eventfd_link/eventfd_link.c

[dpdk-dev] [PATCH] scripts: add git hook scripts for checkpatch and auto doc generation

2015-11-06 Thread Ferruh Yigit
On Fri, Nov 06, 2015 at 01:48:51PM +, Ferruh Yigit wrote: > Sorry for duplication, previous patch is not in the patchwork, this is the > exact same patch and re-sent for patchwork. > Incase anybody interested patchwork error seems because of a special char in message header "Received" field.

[dpdk-dev] [PATCH] mk: fix ABI versioning compile error for combined shared library

2015-11-06 Thread Ferruh Yigit
Fixes following error: LD libdpdk.so /usr/bin/ld: /root/dpdk/build/lib/libdpdk.so: version node not found for symbol @DPDK_x.y Defines version symbols in a fixed path libdpdk.map file and this value hardcoded into makefile Signed-off-by: Ferruh Yigit --- drivers/net/Makefile | 3 +++

[dpdk-dev] [PATCH] mk: fix ABI versioning compile error for combined shared library

2015-11-06 Thread Ferruh Yigit
Sorry for duplication, previous patch is not in the patchwork, this is the exact same patch and re-sent for patchwork. Ferruh Yigit (1): mk: fix ABI versioning compile error for combined shared library drivers/net/Makefile | 3 +++ lib/Makefile | 3 +++ lib/libdpdk.map | 12

[dpdk-dev] [PATCH] scripts: add git hook scripts for checkpatch and auto doc generation

2015-11-06 Thread Ferruh Yigit
These scripts are to automate some common tasks, scripts needs to be deployed to specific folder to become active. Scripts: post-commit: Triggers after commit complete, re-generates api and guides html documents. "RTE_DOC_OUT" environment variable configures document output folder. Same script

[dpdk-dev] [PATCH] scripts: add git hook scripts for checkpatch and auto doc generation

2015-11-06 Thread Ferruh Yigit
Sorry for duplication, previous patch is not in the patchwork, this is the exact same patch and re-sent for patchwork. Ferruh Yigit (1): scripts: add git hook scripts for checkpatch and auto doc generation scripts/git-hooks/deploy.sh | 19 +++ scripts/git-hooks/post-commit |

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Adrien Mazarguil
Hi Bruce, On Fri, Nov 06, 2015 at 11:52:44AM +, Bruce Richardson wrote: > +Adrien on To: line > > Email user/client fail on original. :-( > > - Forwarded message from Bruce Richardson > - > > Date: Fri, 6 Nov 2015 11:49:05 + > From: Bruce Richardson > To: Stephen Hemminger ,

[dpdk-dev] [PATCH] reserve 'make install' for future use

2015-11-06 Thread Bruce Richardson
So, any thoughts or comments on this? There has been lots of discussion in this general area but nothing yet going into the release to try and improve the situation. Are we just going to kick the problem down the road to the 2.3 release? /Bruce On Fri, Nov 06, 2015 at 10:24:13AM +, Bruce

[dpdk-dev] [PATCH v2 2/2] vhost: Add VHOST PMD

2015-11-06 Thread Tetsuya Mukawa
On 2015/11/06 11:22, Yuanhan Liu wrote: > On Mon, Nov 02, 2015 at 12:58:57PM +0900, Tetsuya Mukawa wrote: > ... >> + >> +static uint16_t >> +eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) >> +{ >> +struct vhost_queue *r = q; >> +uint16_t nb_rx = 0; >> + >> +if

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Bruce Richardson
+Adrien on To: line Email user/client fail on original. :-( - Forwarded message from Bruce Richardson - Date: Fri, 6 Nov 2015 11:49:05 + From: Bruce Richardson To: Stephen Hemminger , Thomas Monjalon , dev at dpdk.org Subject: Re: [dpdk-dev] [PATCH v3

[dpdk-dev] [PATCH v3 2/4] ethdev: move error checking macros to header

2015-11-06 Thread Bruce Richardson
On Thu, Nov 05, 2015 at 04:09:18PM +0100, Adrien Mazarguil wrote: > Bruce is asking for a consensus about -pedantic, whether we want to do the > extra effort to support it in DPDK. Since I like checking for -pedantic > errors, it's enabled for mlx4 and mlx5 when compiling these drivers in >

[dpdk-dev] [PATCH] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Helin Zhang
This fixes the issue of not freeing memzone in a call to free the memory for adminq DMA. Signed-off-by: Helin Zhang --- doc/guides/rel_notes/release_2_2.rst | 5 + drivers/net/i40e/base/i40e_osdep.h | 2 +- drivers/net/i40e/i40e_ethdev.c | 12 +++- 3 files changed, 13

[dpdk-dev] [PATCH v2] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Thomas Monjalon
2015-11-06 15:57, Helin Zhang: > This fixes the issue of not freeing memzone in a call to free the > memory for adminq DMA. > > Signed-off-by: Helin Zhang Please could you add a "Fixes:" line? Thanks

[dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt ring

2015-11-06 Thread Tetsuya Mukawa
On 2015/11/05 19:21, Xie, Huawei wrote: > If no objections, would remove the internal cmpset enqueue, should get > some improved performance. > > No idea why commit message is lost: > DPDK doesn't support receiving/transmitting packets from/to the same > port/queue. > Vhost pmd wraps vhost device

[dpdk-dev] [PATCH] mk: rename 'make install' to 'make sdk'

2015-11-06 Thread Bruce Richardson
Since 'make install' is the standard command for installing packages into the filesystem of a system - generally in /usr/local/ - it's use to trigger compilation of the DPDK SDK was both confusing and preventing a "true" 'make install' command from being implemented. As a first step to improving

[dpdk-dev] [PATCH] reserve 'make install' for future use

2015-11-06 Thread Bruce Richardson
There has been some discussion on the list about various ways to get DPDK more standardised in how it compiles and how it can be installed into a system as a set of binaries. One of the issues we face in that is that the 'make install' command is used in DPDK to compile a copy of the SDK but not

[dpdk-dev] [PATCH v2 2/2] vhost: Add VHOST PMD

2015-11-06 Thread Yuanhan Liu
On Mon, Nov 02, 2015 at 12:58:57PM +0900, Tetsuya Mukawa wrote: ... > + > +static uint16_t > +eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) > +{ > + struct vhost_queue *r = q; > + uint16_t nb_rx = 0; > + > + if (unlikely(rte_atomic32_read(>allow_queuing) == 0)) > +

[dpdk-dev] [PATCH] app/testpmd: fix wrong fdir help and doc

2015-11-06 Thread De Lara Guarch, Pablo
> -Original Message- > From: Lu, Wenzhuo > Sent: Friday, November 06, 2015 7:50 AM > To: dev at dpdk.org > Cc: De Lara Guarch, Pablo; Lu, Wenzhuo > Subject: [PATCH] app/testpmd: fix wrong fdir help and doc > > After implementing the fdir new modes for x550, the CLIs are modified. >

[dpdk-dev] [PATCH v3 08/14] acl: arm64: acl implementation using NEON gcc intrinsic

2015-11-06 Thread Ananyev, Konstantin
> -Original Message- > From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com] > Sent: Friday, November 06, 2015 9:40 AM > To: dev at dpdk.org > Cc: thomas.monjalon at 6wind.com; Hunt, David; viktorin at rehivetech.com; > Ananyev, Konstantin; Jerin Jacob > Subject: [dpdk-dev]

[dpdk-dev] BUG: DPDK i40e does not work with VFIO

2015-11-06 Thread Stephen Hemminger
On Thu, 5 Nov 2015 09:19:25 -0800 Stephen Hemminger wrote: > On my machine, i40e will not startup if using VFIO. > > PMD: rte_i40evf_pmd_init(): >> > PMD: rte_i40e_pmd_init(): >> > PMD: eth_i40e_dev_init(): >> > PMD: i40e_set_symmetric_hash_enable_per_port(): Symmetric hash has already >

[dpdk-dev] [PATCH v2] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Wu, Jingjing
> -Original Message- > From: Zhang, Helin > Sent: Friday, November 06, 2015 3:57 PM > To: dev at dpdk.org > Cc: Wu, Jingjing; Zhang, Helin > Subject: [PATCH v2] i40e: fix the issue of not freeing memzone > > This fixes the issue of not freeing memzone in a call to free the memory for >

[dpdk-dev] [PATCH v6 0/7] support for netronome nfp-6xxx card

2015-11-06 Thread Alejandro Lucero
Yes. There was a bug in 1.8 affecting how BARs are used in the device, but this should be fixed in 2.2 On Thu, Nov 5, 2015 at 11:42 PM, Stephen Hemminger < stephen at networkplumber.org> wrote: > On Thu, 05 Nov 2015 11:59:59 +0100 > Vincent JARDIN wrote: > > > > > On 05/11/2015 11:43,

[dpdk-dev] [PATCH v3 6/8] driver/virtio:enqueue vhost TX offload

2015-11-06 Thread Xu, Qian Q
Tested-by: Qian Xu - Test Commit: c4d404d7c1257465176deb5bb8c84e627d2d5eee - OS/Kernel: Fedora 21/4.1.8 - GCC: gcc (GCC) 4.9.2 20141101 (Red Hat 4.9.2-1) - CPU: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz - NIC: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01) - Target:

[dpdk-dev] [PATCH 2/3] i40e: fix ICC compile issue

2015-11-06 Thread De Lara Guarch, Pablo
Hi Helin, > -Original Message- > From: Zhang, Helin > Sent: Friday, November 06, 2015 7:49 AM > To: dev at dpdk.org > Cc: De Lara Guarch, Pablo; Zhang, Helin > Subject: [PATCH 2/3] i40e: fix ICC compile issue > > It fixes compile issue on ICC 13.0.0. > > Error logs: >

[dpdk-dev] [PATCH 1/3] bonding: fix ICC compile issue

2015-11-06 Thread De Lara Guarch, Pablo
Hi Helin, > -Original Message- > From: Zhang, Helin > Sent: Friday, November 06, 2015 7:49 AM > To: dev at dpdk.org > Cc: De Lara Guarch, Pablo; Zhang, Helin > Subject: [PATCH 1/3] bonding: fix ICC compile issue > > It fixes compile issue on ICC 13.0.0. > > Error logs: >

[dpdk-dev] [PATCH] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Zhang, Helin
> -Original Message- > From: Wu, Jingjing > Sent: Friday, November 6, 2015 1:40 PM > To: Zhang, Helin; dev at dpdk.org > Subject: RE: [PATCH] i40e: fix the issue of not freeing memzone > > > - static uint64_t id = 0; > > const struct rte_memzone *mz = NULL; > > char

[dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt ring

2015-11-06 Thread Xie, Huawei
On 11/6/2015 9:48 AM, Changchun Ouyang wrote: > > > > From: huawei.xie at intel.com > > To: huawei.xie at intel.com; dev at dpdk.org > > Date: Thu, 5 Nov 2015 10:21:41 + > > CC: haifeng.lin at intel.com; ann.zhuangyanying at huawei.com > > Subject: Re: [dpdk-dev] [RFC PATCH] vhost: remove

[dpdk-dev] [PATCH] i40e: fix the issue of not freeing memzone

2015-11-06 Thread Wu, Jingjing
> - static uint64_t id = 0; > const struct rte_memzone *mz = NULL; > char z_name[RTE_MEMZONE_NAMESIZE]; > > if (!mem) > return I40E_ERR_PARAM; > > - id++; > - snprintf(z_name, sizeof(z_name), "i40e_dma_%"PRIu64, id); > + snprintf(z_name,

[dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt ring

2015-11-06 Thread Xie, Huawei
On 11/6/2015 9:43 AM, Tetsuya Mukawa wrote: > On 2015/11/05 19:21, Xie, Huawei wrote: >> If no objections, would remove the internal cmpset enqueue, should get >> some improved performance. >> >> No idea why commit message is lost: >> DPDK doesn't support receiving/transmitting packets from/to the

[dpdk-dev] [RFC 5/5] vhost/container: change mode of vhost listening socket

2015-11-06 Thread Jianfeng Tan
Change vhost listening socket mode so that users in groups and others can connect to vhost listening socket. Signed-off-by: Huawei Xie Signed-off-by: Jianfeng Tan --- lib/librte_vhost/vhost_user/vhost-net-user.c | 5 + 1 file changed, 5 insertions(+) diff --git

[dpdk-dev] [RFC 4/5] virtio/container: adjust memory initialization process

2015-11-06 Thread Jianfeng Tan
When using virtio for container, we should specify --no-huge so that in memory initialization, shm_open() is used to alloc memory from tmpfs filesystem /dev/shm/. Signed-off-by: Huawei Xie Signed-off-by: Jianfeng Tan --- lib/librte_eal/common/include/rte_memory.h | 5 +++

[dpdk-dev] [RFC 3/5] virtio/container: unify desc->addr assignment

2015-11-06 Thread Jianfeng Tan
Unify desc->addr assignment using RTE_MBUF_DATA_DMA_ADDR. virtio for vm uses physical address, while virtio for container uses virtual address. Signed-off-by: Huawei Xie Signed-off-by: Jianfeng Tan --- drivers/net/virtio/virtio_rxtx.c| 9 -

[dpdk-dev] [RFC 2/5] virtio/container: add a new virtual device named eth_cvio

2015-11-06 Thread Jianfeng Tan
Add a new virtual device named eth_cvio, it can be used just like eth_ring, eth_null, etc. Configured paramters include number of rx, tx, cq, path of vhost unix socket, and queue size. The major difference with virtio for vm is that here we use virtual address instead of physical address for vhost

[dpdk-dev] [RFC 1/5] virtio/container: add handler for ioport rd/wr

2015-11-06 Thread Jianfeng Tan
Add handler to turn ioport rd/wr into vhost user unix socket msgs. Add field, like kickfd, callfd in struct virtio_hw. Add CONFIG_RTE_VIRTIO_VDEV to control virtio vdev, disabled by default. Signed-off-by: Huawei Xie Signed-off-by: Jianfeng Tan --- config/common_linuxapp | 5 +

[dpdk-dev] [RFC 0/5] virtio support for container

2015-11-06 Thread Jianfeng Tan
This patchset only acts as a PoC to request the community for comments. This patchset is to provide high performance networking interface (virtio) for container-based DPDK applications. The way of starting DPDK applications in containers with ownership of NIC devices exclusively is beyond the

[dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt ring

2015-11-06 Thread Changchun Ouyang
> From: huawei.xie at intel.com > To: huawei.xie at intel.com; dev at dpdk.org > Date: Thu, 5 Nov 2015 10:21:41 + > CC: haifeng.lin at intel.com; ann.zhuangyanying at huawei.com > Subject: Re: [dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt > ring > > If no objections,

[dpdk-dev] [PATCH] vhost: fix mmap failure as len not aligned with hugepage size

2015-11-06 Thread Changchun Ouyang
> From: jianfeng.tan at intel.com > To: dev at dpdk.org > Date: Fri, 30 Oct 2015 07:51:53 +0800 > Subject: [dpdk-dev] [PATCH] vhost: fix mmap failure as len not aligned with > hugepage size > > This patch fixes a bug under lower version linux kernel, mmap() fails when > length is not aligned