[dpdk-dev] [PATCH v6 00/22] Support flow director programming on Fortville

> > The patch set supports flow director on fortville. > > It includes: > > - set up/tear down fortville resources to support flow director, such as > > queue and vsi. > > - support operation to add or delete 8 flow types of the flow director > > filters, they are ipv4, tcpv4, udpv4, sctpv4, ip

[dpdk-dev] [PATCH v6 8/8] i40evf: support of updating/querying redirection table

Hi Thomas Thank you for the fixes! I am using the checkpatch.pl of kernel 3.6.10. Yes, It seems that I need to update it to a newer version. Regards, Helin > -Original Message- > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > Sent: Tuesday, November 25, 2014 6:20 AM > To:

[dpdk-dev] reg: dpdk on virtual machine

On 11/24/2014 7:24 PM, Anand Angadi wrote: > Hi friends, > I wanted to know how to install dpdk on virtual machine and how to get > virtual intel dpdk NIC card(virthal hardware) > in virtual machine if anybody know about it please reply me. I think there is no difference if your VM is KVM based(

[dpdk-dev] [PATCH v4 01/14] Add compiling definations for IBM Power architecture

To make DPDK run on IBM Power architecture, configuration files for Power architecuture are added. Also, the compiling related .mk files are added. Signed-off-by: Chao Zhu --- config/common_linuxapp_powerpc | 394 +++ config/defconfig_ppc_64-power8-linuxapp-

[dpdk-dev] [PATCH v4 00/14] Patches for DPDK to support Power architecture

The set of patches add IBM Power architecture to the DPDK. It adds the required support to the EAL library. This set of patches doesn't support full DPDK function on Power processors. So a separate common configuration file is used for Power to turn off some un-migrated functions. To compile on PP

[dpdk-dev] [PATCH v4 04/14] Add CPU cycle operations for IBM Power architecture

IBM Power architecture doesn't have TSC register to get CPU cycles. This patch implements the time base register read instead of TSC register of x86 on IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_cycles.h| 88 1 files chan

[dpdk-dev] [PATCH v4 05/14] Add prefetch operation for IBM Power architecture

This patch add architecture specific prefetch operations for IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_prefetch.h | 61 1 files changed, 61 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/include/arc

[dpdk-dev] [PATCH v4 03/14] Add byte order operations for IBM Power architecture

This patch adds architecture specific byte order operations for IBM Power architecture. Power architecture support both big endian and little endian. This patch also adds a RTE_ARCH_BIG_ENDIAN micro. Signed-off-by: Chao Zhu --- config/defconfig_ppc_64-power8-linuxapp-gcc|1 + .../com

[dpdk-dev] [PATCH v4 02/14] Add atomic operations for IBM Power architecture

This patch adds architecture specific atomic operation file for IBM Power architecture CPU. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_atomic.h| 427 1 files changed, 427 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/inc

[dpdk-dev] [PATCH v4 07/14] Add vector memcpy for IBM Power architecture

The SSE based memory copy in DPDK only support x86. This patch adds altivec based memory copy functions for IBM Power architecture. This patch includes altivec.h which requires GCC version>= 4.8. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_memcpy.h| 226 ++

[dpdk-dev] [PATCH v4 06/14] Add spinlock operation for IBM Power architecture

This patch adds spinlock operations for IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_spinlock.h | 73 1 files changed, 73 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/include/arch/ppc_64/rte_spinlock

[dpdk-dev] [PATCH v4 08/14] Add CPU flag checking for IBM Power architecture

IBM Power processor doesn't have CPU flag hardware registers. This patch uses aux vector software register to get CPU flags and add CPU flag checking support for IBM Power architecture. Signed-off-by: Chao Zhu --- app/test/test_cpuflags.c | 35 .../common/include

[dpdk-dev] [PATCH v4 09/14] Remove iopl operation for IBM Power architecture

iopl() call is mostly for the i386 architecture. In Power and other architecture, it doesn't exist. This patch modified rte_eal_iopl_init() and make it return -1 for Power and other architecture. Thus rte_config.flags will not contain EAL_FLG_HIGH_IOPL flag for other architecture. Signed-off-by: C

[dpdk-dev] [PATCH v4 10/14] Add cache size define for IBM Power Architecture

IBM Power architecture has different cache line size (128 bytes) than x86 (64 bytes). This patch defines CACHE_LINE_SIZE to 128 bytes to override the default value 64 bytes to support IBM Power Architecture. Signed-off-by: Chao Zhu --- app/test/test_malloc.c |8 mk/arch/ppc_64/r

[dpdk-dev] [PATCH v4 11/14] Add huge page size define for IBM Power architecture

IBM Power architecture has different huge page sizes (16MB, 16GB) than x86.This patch defines RTE_PGSIZE_16M and RTE_PGSIZE_16G in the rte_page_sizes enum variable and adds huge page size support of DPDK for IBM Power architecture. Signed-off-by: Chao Zhu --- app/test/test_memzone.c

[dpdk-dev] [PATCH v4 14/14] Fix the compiling of test-pmd on IBM Power Architecture

This patch fixes compiling problems on IBM Power architecture and turn on the test-pmd compiling option in configuration file. Actually, this is an big endian compiling fix. Signed-off-by: Chao Zhu --- app/test-pmd/config.c | 39 +-- config/common_l

[dpdk-dev] [PATCH v4 12/14] Add eal memory support for IBM Power Architecture

The mmap of hugepage files on IBM Power starts from high address to low address. This is different from x86. This patch modified the memory segment detection code to get the correct memory segment layout on Power architecture. This patch also added a commond ARCH_PPC_64 defination for 64 bit system

[dpdk-dev] [PATCH v4 13/14] test_memzone:fix finding the second smallest segment

Curent implementation in test_memzone.c has bugs in finding the second smallest memory segment. It's the last smallest memory segment, but it's not the second smallest memory segment. This bug may cause test failure in some cases. This patch fixes this bug. Signed-off-by: Chao Zhu --- app/test/t

[dpdk-dev] [PATCH v3 00/14] Patches for DPDK to support Power architecture

David, I submitted a updated patchset. I fixed all of the checkpatch errors, except one error(this error I think it is invalid). Thanks a lot! On 2014/11/24 23:05, David Marchand wrote: > Hello Chao, > > On Mon, Nov 24, 2014 at 2:22 AM, Chao Zhu > wrote: >

[dpdk-dev] [PATCH v3 08/14] Add CPU flag checking for IBM Power architecture

Neil, I didn't compiled ACL library on Power because SSE is not supported by Power. This is why ACL compiling was turned off on Power. rte_cpu_flag_t is an architecture specific value, each CPU has its own rte_cpu_flag_t . The Power one has no influence on x86, so I think there should be no bui

[dpdk-dev] [PATCH v3 01/14] Add compiling definations for IBM Power architecture

Neil, Current Power related patches are not a full functional one. Some of the libraries are not migrated. So common_linuxapp_powerpc is used to turn off the uncompiled part. This file is a copy of the common_linuxapp. And this file is intended to be removed when all of the libraries are migrate

[dpdk-dev] [PATCH v6 00/22] Support flow director programming on Fortville

Hi, Thomas Thanks a lot. > > I feel the flow director features could be better explained, and probably the > API won't be enough generic for the next driver implementing flow director. > But no comment from the community means it's OK to integrate. > > Now we move on this API and the old one mu

[dpdk-dev] [PATCH] eal: Add missing device ID for ixgbe

EAL misses 4 device ID but base codes support them, so add them into EAL. Signed-off-by: Changchun Ouyang --- lib/librte_eal/common/include/rte_pci_dev_ids.h | 8 1 file changed, 8 insertions(+) diff --git a/lib/librte_eal/common/include/rte_pci_dev_ids.h b/lib/librte_eal/common/inclu

[dpdk-dev] [PATCH] eal: Add missing device ID for ixgbe

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ouyang Changchun > Sent: Tuesday, November 25, 2014 1:03 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH] eal: Add missing device ID for ixgbe > > EAL misses 4 device ID but base codes support them, so a

[dpdk-dev] [PATCH v2] i40e: link flow control support

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of zhida zang > Sent: Thursday, November 20, 2014 4:59 PM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v2] i40e: link flow control support > > From: zzang > > Add link flow control support for i40e > > S

[dpdk-dev] [PATCH v3 6/6] DPDK changes for accommodating ENIC PMD

On 24/11/14 10:49 pm, "Neil Horman" wrote: >On Mon, Nov 24, 2014 at 04:12:48PM +, Sujith Sankar (ssujith) wrote: >> >> >> On 24/11/14 5:03 pm, "Neil Horman" wrote: >> >> >On Mon, Nov 24, 2014 at 05:45:54AM +, Sujith Sankar (ssujith) >>wrote: >> >> >> >> >> >> On 24/11/14 5:47 am,

[dpdk-dev] [PATCH v4 0/6] Cisco Systems Inc. VIC Ethernet PMD - ENIC PMD

ENIC PMD is the poll-mode driver for the Cisco Systems Inc. VIC to be used with DPDK suite. Sujith Sankar (6): ENIC PMD License ENIC PMD Makefile VNIC common code partially shared with ENIC kernel mode driver ENIC PMD specific code DPDK-ENIC PMD interface DPDK changes for accommodating

[dpdk-dev] [PATCH v4 1/6] ENIC PMD License

Signed-off-by: Sujith Sankar --- lib/librte_pmd_enic/LICENSE | 27 +++ 1 file changed, 27 insertions(+) create mode 100644 lib/librte_pmd_enic/LICENSE diff --git a/lib/librte_pmd_enic/LICENSE b/lib/librte_pmd_enic/LICENSE new file mode 100644 index 000..0ad2216 --- /

[dpdk-dev] [PATCH v4 2/6] ENIC PMD Makefile

Signed-off-by: Sujith Sankar --- lib/librte_pmd_enic/Makefile | 67 1 file changed, 67 insertions(+) create mode 100644 lib/librte_pmd_enic/Makefile diff --git a/lib/librte_pmd_enic/Makefile b/lib/librte_pmd_enic/Makefile new file mode 100644 index 0

[dpdk-dev] [PATCH v4 3/6] VNIC common code partially shared with ENIC kernel mode driver

Signed-off-by: Sujith Sankar --- lib/librte_pmd_enic/vnic/cq_desc.h | 126 lib/librte_pmd_enic/vnic/cq_enet_desc.h | 261 lib/librte_pmd_enic/vnic/rq_enet_desc.h | 76 +++ lib/librte_pmd_enic/vnic/vnic_cq.c | 117 lib/librte_pmd_enic/vnic/vnic_cq.h | 1

[dpdk-dev] [PATCH v4 4/6] ENIC PMD specific code

Signed-off-by: Sujith Sankar --- lib/librte_pmd_enic/enic.h| 157 + lib/librte_pmd_enic/enic_clsf.c | 244 +++ lib/librte_pmd_enic/enic_compat.h | 142 + lib/librte_pmd_enic/enic_main.c | 1266 + lib/librte_pmd_enic/enic_res.c| 2

[dpdk-dev] [PATCH v4 5/6] DPDK-ENIC PMD interface

Signed-off-by: Sujith Sankar --- lib/librte_pmd_enic/enic_etherdev.c | 613 1 file changed, 613 insertions(+) create mode 100644 lib/librte_pmd_enic/enic_etherdev.c diff --git a/lib/librte_pmd_enic/enic_etherdev.c b/lib/librte_pmd_enic/enic_etherdev.c new f

[dpdk-dev] [PATCH v4 6/6] DPDK changes for accommodating ENIC PMD

Signed-off-by: Sujith Sankar --- config/common_linuxapp | 5 + lib/Makefile | 1 + lib/librte_eal/linuxapp/eal/eal_pci_vfio.c | 1 + mk/rte.app.mk | 4 4 files changed, 11 insertions(+) diff --git a/config/co

[dpdk-dev] [PATCH v3 0/2] lib/librte_pmd_i40e: set vlan filter fix

This patchset fixes "set vlan filter" issue. v2 changes: * add two macros I40E_VFTA_IDX and I40E_VFTA_BIT for VFTA array operation. v3 changes: * code style fix * rebase on latest commit Huawei Xie (2): vlan id set fix add I40E_VFTA_IDX and I40E_VFTA_BIT macros for VFTA related operation l

[dpdk-dev] [PATCH v3 1/2] lib/librte_pmd_i40e: set vlan id filter fix

">> 5" rather than ">> 4" Signed-off-by: Huawei Xie --- lib/librte_pmd_i40e/i40e_ethdev.c | 7 ++- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/lib/librte_pmd_i40e/i40e_ethdev.c b/lib/librte_pmd_i40e/i40e_ethdev.c index dacf2db..518597f 100644 --- a/lib/librte_pmd_i40e/i40e

[dpdk-dev] [PATCH v3 2/2] lib/librte_pmd_i40e: add I40E_VFTA_IDX and I40E_VFTA__BIT macros for VFTA related operation

Add two macros I40E_VFTA_IDX and I40E_VFTA_BIT for vlan filter search and set. Add vlan_id check in vlan filter search and set function. Signed-off-by: Huawei Xie --- lib/librte_pmd_i40e/i40e_ethdev.c | 17 ++--- lib/librte_pmd_i40e/i40e_ethdev.h | 9 + 2 files changed, 19 i

[dpdk-dev] reg: dpdk on virtual machine

We have tested DPDK inside VM in two different ways: - Using virtual interface. Thus we were able to develop DPDK apps on any machine. - Using PCI pass-through. Thus we were able to achieve maximum speed on DPDK-enabled NIC. Please check the following blog posts. DPDK bring-up in VM using virtual

[dpdk-dev] [PATCH v3 01/14] Add compiling definations for IBM Power architecture

On Tue, Nov 25, 2014 at 11:51:13AM +0800, Chao Zhu wrote: > Neil, > Current Power related patches are not a full functional one. Some of the > libraries are not migrated. So > common_linuxapp_powerpc is used to turn off the uncompiled part. Hi Chao, just to re-echo what Neil says - this would be b

[dpdk-dev] [PATCH] ethdev: fix doxygen comments about RSS

On Mon, Nov 24, 2014 at 11:09:40PM +0100, Thomas Monjalon wrote: > The parameters port_id didn't match with comments about port. > > Signed-off-by: Thomas Monjalon Acked-by: Bruce Richardson > --- > lib/librte_ether/rte_ethdev.h | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > >

[dpdk-dev] [PATCH v3 1/2] lib/librte_pmd_i40e: set vlan id filter fix

On Tue, Nov 25, 2014 at 03:28:56PM +0800, Huawei Xie wrote: > ">> 5" rather than ">> 4" you need to provide a reference for where this value comes from. Presumably this is based of the register description in the datasheet for the NIC, so perhaps you can add that. > > Signed-off-by: Huawei Xie

[dpdk-dev] [PATCH 10/10] eal: add option --master-lcore

Hi Thomas, thanks for your work. I have one (minor) comment for this patch that should be fixed in a later version. Acknowledged. Thanks, Simon On 22.11.2014 22:43, Thomas Monjalon wrote: > From: Simon Kuenzer > > Enable users to specify the lcore id that is used as master lcore. > > Signed

[dpdk-dev] [PATCH v3 01/14] Add compiling definations for IBM Power architecture

Bruce, Good point! I'll update the current patches. Thanks for your suggestions! On 2014/11/25 16:44, Bruce Richardson wrote: > On Tue, Nov 25, 2014 at 11:51:13AM +0800, Chao Zhu wrote: >> Neil, >> Current Power related patches are not a full functional one. Some of the >> libraries are not migra

[dpdk-dev] [PATCH v2] ADD mode 5(tlb) to link bonding pmd

Tested-by: Jiajia, SunX - Tested Commit: f7aaae2fe6f7f9a78eab7313d77e92b934693b5d - OS: Fedora20 3.11.10-301.fc20.x86_64 and 3.16.6-200.fc20.x86_64 - GCC: gcc version 4.8.2 - CPU: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz - NIC: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection [80

[dpdk-dev] [PATCH v6 00/22] Support flow director programming on Fortville

2014-11-25 04:51, Wu, Jingjing: > > Now we move on this API and the old one must be removed. > > Converting ixgbe to this new API must be the top priority. > > It must be clear to everyone that no new Fortville feature will be accepted > > until a full clean-up of the old filtering API. > > If I u

[dpdk-dev] [PATCH] eal: Add missing device ID for ixgbe

> > EAL misses 4 device ID but base codes support them, so add them into EAL. > > > > Signed-off-by: Changchun Ouyang > > Acked-by: Helin Zhang Applied Thanks -- Thomas

[dpdk-dev] [PATCH v5 0/2] bond: mode 4 support

Some information detail about mode mode 4 of link bonding: This mode is described in IEEE 802.3ad/AX standard described. It is also described here https://www.kernel.org/doc/Documentation/networking/bonding.txt. In this implementation we have an array of mode 4 setting for each slave. There is al

[dpdk-dev] [PATCH v4 6/6] DPDK changes for accommodating ENIC PMD

Hello Sujith, On Tue, Nov 25, 2014 at 5:30 PM, Sujith Sankar wrote: > diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c > b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c > index c776ddc..87e7862 100644 > --- a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c > +++ b/lib/librte_eal/linuxapp/eal/eal_

[dpdk-dev] [PATCH v4 0/6] Cisco Systems Inc. VIC Ethernet PMD - ENIC PMD

Hello Sujith, - This is a comment for the whole patchset. Patch subjects and commitlogs should comply with the "Contribute by sending patches" section of http://dpdk.org/dev. I would say, all your patches should be prefixed with "enic: ". - By the way, can you add some performance numbers as a r

[dpdk-dev] [PATCH v5 00/14] Patches for DPDK to support Power architecture

The set of patches add IBM Power architecture to the DPDK. It adds the required support to the EAL library. This set of patches doesn't support full DPDK function on Power processors. To compile on PPC64 architecture, GCC version >= 4.8 must be used. According to Bruce and Neil's comments, this v5

[dpdk-dev] [PATCH v5 10/14] Add cache size define for IBM Power Architecture

IBM Power architecture has different cache line size (128 bytes) than x86 (64 bytes). This patch defines CACHE_LINE_SIZE to 128 bytes to override the default value 64 bytes to support IBM Power Architecture. Signed-off-by: Chao Zhu --- app/test/test_malloc.c |8 mk/arch/ppc_64/r

[dpdk-dev] [PATCH v5 05/14] Add prefetch operation for IBM Power architecture

This patch add architecture specific prefetch operations for IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_prefetch.h | 61 1 files changed, 61 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/include/arc

[dpdk-dev] [PATCH v5 04/14] Add CPU cycle operations for IBM Power architecture

IBM Power architecture doesn't have TSC register to get CPU cycles. This patch implements the time base register read instead of TSC register of x86 on IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_cycles.h| 88 1 files chan

[dpdk-dev] [PATCH v5 13/14] test_memzone:fix finding the second smallest segment

Curent implementation in test_memzone.c has bugs in finding the second smallest memory segment. It's the last smallest memory segment, but it's not the second smallest memory segment. This bug may cause test failure in some cases. This patch fixes this bug. Signed-off-by: Chao Zhu --- app/test/t

[dpdk-dev] [PATCH v5 02/14] Add atomic operations for IBM Power architecture

This patch adds architecture specific atomic operation file for IBM Power architecture CPU. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_atomic.h| 427 1 files changed, 427 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/inc

[dpdk-dev] [PATCH v5 14/14] Fix the compiling of test-pmd on IBM Power Architecture

This patch fixes compiling problems on IBM Power architecture and turn on the test-pmd compiling option in configuration file. Actually, this is an big endian compiling fix. Signed-off-by: Chao Zhu --- app/test-pmd/config.c | 39 +-- 1 files changed, 25 inse

[dpdk-dev] [PATCH v5 07/14] Add vector memcpy for IBM Power architecture

The SSE based memory copy in DPDK only support x86. This patch adds altivec based memory copy functions for IBM Power architecture. This patch includes altivec.h which requires GCC version>= 4.8. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_memcpy.h| 226 ++

[dpdk-dev] [PATCH v5 03/14] Add byte order operations for IBM Power architecture

This patch adds architecture specific byte order operations for IBM Power architecture. Power architecture support both big endian and little endian. This patch also adds a RTE_ARCH_BIG_ENDIAN micro. Signed-off-by: Chao Zhu --- config/defconfig_ppc_64-power8-linuxapp-gcc|1 + .../com

[dpdk-dev] [PATCH v5 11/14] Add huge page size define for IBM Power architecture

IBM Power architecture has different huge page sizes (16MB, 16GB) than x86.This patch defines RTE_PGSIZE_16M and RTE_PGSIZE_16G in the rte_page_sizes enum variable and adds huge page size support of DPDK for IBM Power architecture. Signed-off-by: Chao Zhu --- app/test/test_memzone.c

[dpdk-dev] [PATCH v5 08/14] Add CPU flag checking for IBM Power architecture

IBM Power processor doesn't have CPU flag hardware registers. This patch uses aux vector software register to get CPU flags and add CPU flag checking support for IBM Power architecture. Signed-off-by: Chao Zhu --- app/test/test_cpuflags.c | 35 .../common/include

[dpdk-dev] [PATCH v5 12/14] Add eal memory support for IBM Power Architecture

The mmap of hugepage files on IBM Power starts from high address to low address. This is different from x86. This patch modified the memory segment detection code to get the correct memory segment layout on Power architecture. This patch also added a commond ARCH_PPC_64 defination for 64 bit system

[dpdk-dev] [PATCH v5 09/14] Remove iopl operation for IBM Power architecture

iopl() call is mostly for the i386 architecture. In Power and other architecture, it doesn't exist. This patch modified rte_eal_iopl_init() and make it return -1 for Power and other architecture. Thus rte_config.flags will not contain EAL_FLG_HIGH_IOPL flag for other architecture. Signed-off-by: C

[dpdk-dev] [PATCH v5 01/14] Add compiling definations for IBM Power architecture

To make DPDK run on IBM Power architecture, configuration files for Power architecuture are added. Also, the compiling related .mk files are added. Signed-off-by: Chao Zhu --- config/defconfig_ppc_64-power8-linuxapp-gcc | 70 +++ mk/arch/ppc_64/rte.vars.mk

[dpdk-dev] [PATCH v5 06/14] Add spinlock operation for IBM Power architecture

This patch adds spinlock operations for IBM Power architecture. Signed-off-by: Chao Zhu --- .../common/include/arch/ppc_64/rte_spinlock.h | 73 1 files changed, 73 insertions(+), 0 deletions(-) create mode 100644 lib/librte_eal/common/include/arch/ppc_64/rte_spinlock

[dpdk-dev] [PATCH 01/10] eal: move internal headers in source directory

On Sat, Nov 22, 2014 at 10:43:33PM +0100, Thomas Monjalon wrote: > The directory include/ should be reserved to public headers. > > Signed-off-by: Thomas Monjalon Acked-by: Bruce Richardson > --- > lib/librte_eal/bsdapp/eal/Makefile | 1 + > lib/librte_eal/common/{includ

[dpdk-dev] [PATCH v3 03/13] mbuf: reorder tx ol_flags

2014-11-20 23:58, Olivier Matz: > The tx mbuf flags are now ordered from the lowest value to the > the highest. Add comments to explain where to add new flags. > > By the way, move the PKT_TX_VXLAN_CKSUM at the right place. > > Signed-off-by: Olivier Matz Acked-by: Thomas Monjalon

[dpdk-dev] [PATCH v3 06/13] mbuf: add functions to get the name of an ol_flag

> In test-pmd (rxonly.c), the code is able to dump the list of ol_flags. > The issue is that the list of flags in the application has to be > synchronized with the flags defined in rte_mbuf.h. > > This patch introduces 2 new functions rte_get_rx_ol_flag_name() > and rte_get_tx_ol_flag_name() that

[dpdk-dev] [PATCH 02/10] eal: factorize common headers

On Sat, Nov 22, 2014 at 10:43:34PM +0100, Thomas Monjalon wrote: > No need to have different headers for Linux and BSD. > These files are identicals with exception of internal config which has > uio and vfio fields only useful for Linux. > > Signed-off-by: Thomas Monjalon Acked-by: Bruce Richard

[dpdk-dev] [PATCH 03/10] eal: fix header guards

On Sat, Nov 22, 2014 at 10:43:35PM +0100, Thomas Monjalon wrote: > Some guards are missing or have a wrong name. > Others have LINUXAPP in their name but are now common. > > Signed-off-by: Thomas Monjalon One minor comment below. Acked-by: Bruce Richardson > --- > lib/librte_eal/common/eal_f

[dpdk-dev] [PATCH 04/10] eal: factorize internal config reset

On Sat, Nov 22, 2014 at 10:43:36PM +0100, Thomas Monjalon wrote: > Now that internal config structure is common to Linux and BSD, > we can have a common function to initialize it. > > Signed-off-by: Thomas Monjalon Acked-by: Bruce Richardson > --- > lib/librte_eal/bsdapp/eal/eal.c

[dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name of an ol_flag

Hi Helin, > -Original Message- > From: Ananyev, Konstantin > Sent: Wednesday, November 19, 2014 11:07 AM > To: Olivier MATZ; dev at dpdk.org > Cc: jigsaw at gmail.com; Zhang, Helin > Subject: RE: [dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name > of an ol_flag > > > > >

[dpdk-dev] [PATCH 05/10] eal: factorize options sanity check

On Sat, Nov 22, 2014 at 10:43:37PM +0100, Thomas Monjalon wrote: > No need to have duplicated check for common options. > > Some flags are set for options -c and -m in order to simplify the > checks. > > Signed-off-by: Thomas Monjalon Acked-by: Bruce Richardson > --- > lib/librte_eal/bsdapp/

[dpdk-dev] [PATCH 06/10] eal: factorize configuration adjustment

On Sat, Nov 22, 2014 at 10:43:38PM +0100, Thomas Monjalon wrote: > Some adjustments are done after options parsing and are common > to Linux and BSD. > > Remove process_type adjustment in rte_config_init() because > it is already done in eal_parse_args(). > eal_proc_type_detect() is kept duplicate

[dpdk-dev] [PATCH 07/10] eal: add core list input format

On Sat, Nov 22, 2014 at 10:43:39PM +0100, Thomas Monjalon wrote: > From: Didier Pallard > > In current version, used cores can only be specified using a bitmask. > It will now be possible to specify cores in 2 different ways: > - Using a bitmask (-c [0x]nnn): bitmask must be in hex format > - Usi

[dpdk-dev] [PATCH v4 6/6] DPDK changes for accommodating ENIC PMD

David, I tested it now, and it looks like the length is proper in dev->men_resource[0].len without this change. Not sure what changed in my workspace as I clearly remember seeing it wrong and hence added the extra statement in the lib. I shall remove it in v5. Thanks for pointing it out, David.

[dpdk-dev] [PATCH 08/10] config: support 128 cores

On Sat, Nov 22, 2014 at 10:43:40PM +0100, Thomas Monjalon wrote: > From: Didier Pallard > > New platforms have more than 64 cores. > Now that cores can be specified with a list, we are not limited anymore to 64. > Set default max cores number to 128. > > Signed-off-by: Didier Pallard > Acked-by

[dpdk-dev] [PATCH v4 0/6] Cisco Systems Inc. VIC Ethernet PMD - ENIC PMD

Hi David, As suggested, I shall make the modification in the subject in v6. About performance numbers, I?m working on ENIC PMD documentation (in rst format), and it will have performance numbers along with some other relevant details. Thanks, -Sujith From: David Marchand Date: Tuesday, 25 No

[dpdk-dev] [PATCH 09/10] eal: get relative core index

On Sat, Nov 22, 2014 at 10:43:41PM +0100, Thomas Monjalon wrote: > From: Patrick Lu > > EAL -c option allows the user to enable any lcore in the system. > Often times, the user app wants to know 1st enabled core, 2nd > enabled core, etc, rather than phyical core ID (rte_lcore_id().) > > The new

[dpdk-dev] [PATCH v8 0/7] link bonding

> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon > Sent: Monday, November 24, 2014 9:54 PM > To: Doherty, Declan > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v8 0/7] link bonding > > 2014-11-24 16:33, Declan Doherty: > > v8: > > - Mis

[dpdk-dev] [PATCH v8 0/7] link bonding

2014-11-25 10:56, Jastrzebski, MichalX K: > I noticed some problems with applying link bonding mode 4 patches after you > applied Declan's patches. > Link bonding mode 4 0001-bond-add-mode-4-support.patch won't apply because of > this error: > Checking patch lib/librte_pmd_bond/rte_eth_bond_priv

[dpdk-dev] reg: dpdk on virtual machine

On 11/25/2014 11:13 AM, Anand Angadi wrote: > On 11/25/2014 7:15 AM, Qiu, Michael wrote: >> On 11/24/2014 7:24 PM, Anand Angadi wrote: >>> Hi friends, >>> I wanted to know how to install dpdk on virtual machine and how to get >>> virtual intel dpdk NIC card(virthal hardware) >>> in virtual machine

[dpdk-dev] [PATCH v3 6/6] DPDK changes for accommodating ENIC PMD

On Tue, Nov 25, 2014 at 06:13:26AM +, Sujith Sankar (ssujith) wrote: > > > On 24/11/14 10:49 pm, "Neil Horman" wrote: > > >On Mon, Nov 24, 2014 at 04:12:48PM +, Sujith Sankar (ssujith) wrote: > >> > >> > >> On 24/11/14 5:03 pm, "Neil Horman" wrote: > >> > >> >On Mon, Nov 24, 2014 at

[dpdk-dev] [PATCH v2] i40e: link flow control support

On 11/20/2014 5:00 PM, zhida zang wrote: > From: zzang > > Add link flow control support for i40e > > Signed-off-by: zhida zang > --- > lib/librte_pmd_i40e/i40e_ethdev.c | 155 > +- > lib/librte_pmd_i40e/i40e_ethdev.h | 10 +++ > 2 files changed, 162 inserti

[dpdk-dev] [PATCH v3 08/14] Add CPU flag checking for IBM Power architecture

On Tue, Nov 25, 2014 at 11:27:31AM +0800, Chao Zhu wrote: > Neil, > > I didn't compiled ACL library on Power because SSE is not supported by > Power. This is why ACL compiling was > turned off on Power. rte_cpu_flag_t is an architecture specific value, each > CPU has its own rte_cpu_flag_t . The P

[dpdk-dev] [PATCH v4 6/6] DPDK changes for accommodating ENIC PMD

On Tue, Nov 25, 2014 at 11:46 AM, Sujith Sankar (ssujith) wrote: > David, > > I tested it now, and it looks like the length is proper in > dev->men_resource[0].len without this change. > Not sure what changed in my workspace as I clearly remember seeing it > wrong and hence added the extra statem

[dpdk-dev] [PATCH] bond: fix doxygen

2014-11-24 22:24, Thomas Monjalon: > There is no parameter delay_ms in *_delay_get functions. > > Signed-off-by: Thomas Monjalon Applied -- Thomas

[dpdk-dev] [PATCH v3 07/13] testpmd: fix use of offload flags in testpmd

> -Original Message- > From: Olivier Matz [mailto:olivier.matz at 6wind.com] > Sent: Thursday, November 20, 2014 10:59 PM > To: dev at dpdk.org > Cc: olivier.matz at 6wind.com; Walukiewicz, Miroslaw; Liu, Jijiang; Liu, > Yong; jigsaw at gmail.com; Richardson, Bruce; Ananyev, Konstantin >

[dpdk-dev] [PATCH] ethdev: fix doxygen comments about RSS

> > The parameters port_id didn't match with comments about port. > > > > Signed-off-by: Thomas Monjalon > > Acked-by: Bruce Richardson Applied -- Thomas

[dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name of an ol_flag

HI Konstantin > -Original Message- > From: Ananyev, Konstantin > Sent: Tuesday, November 25, 2014 6:38 PM > To: 'Olivier MATZ'; 'dev at dpdk.org' > Cc: 'jigsaw at gmail.com'; Zhang, Helin > Subject: RE: [dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name > of > an ol_flag > >

[dpdk-dev] [PATCH 03/10] eal: fix header guards

Thanks for your review, Bruce. More comments below. 2014-11-25 10:28, Bruce Richardson: > On Sat, Nov 22, 2014 at 10:43:35PM +0100, Thomas Monjalon wrote: > > Some guards are missing or have a wrong name. > > Others have LINUXAPP in their name but are now common. > > > > Signed-off-by: Thomas Mon

[dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name of an ol_flag

Hi Helin, On 11/25/2014 01:15 PM, Zhang, Helin wrote: I would be in favor of removing them, or at least the following ones (I don't understand how they can help the application): - PKT_RX_OVERSIZE: Num of desc of an RX pkt oversize. - PKT_RX_HBUF_OVERFLOW: Header buffer ov

[dpdk-dev] [PATCH 10/10] eal: add option --master-lcore

Hi Simon, 2014-11-25 10:09, Simon Kuenzer: > thanks for your work. I have one (minor) comment for this patch that > should be fixed in a later version. > > + /* default master lcore is the first one */ > > + if (cfg->master_lcore == 0) > > + cfg->master_lcore = rte_get_next_lcore(-

[dpdk-dev] checkpatch script

Hi Thomas, As we have seen the issues we have had on previous patches due to checkpatch, would it be possible to include the up-to-date script in the repo? I have realized that people either do not check their patches or check them with an old version that do not catch some errors that the late

[dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name of an ol_flag

Hi Olivier > -Original Message- > From: Olivier MATZ [mailto:olivier.matz at 6wind.com] > Sent: Tuesday, November 25, 2014 8:38 PM > To: Zhang, Helin; Ananyev, Konstantin; 'dev at dpdk.org' > Cc: 'jigsaw at gmail.com' > Subject: Re: [dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get th

[dpdk-dev] [PATCH 03/10] eal: fix header guards

On Tue, Nov 25, 2014 at 01:23:55PM +0100, Thomas Monjalon wrote: > Thanks for your review, Bruce. > More comments below. > > 2014-11-25 10:28, Bruce Richardson: > > On Sat, Nov 22, 2014 at 10:43:35PM +0100, Thomas Monjalon wrote: > > > Some guards are missing or have a wrong name. > > > Others hav

[dpdk-dev] [PATCH 10/10] eal: add option --master-lcore

On Tue, Nov 25, 2014 at 01:45:22PM +0100, Thomas Monjalon wrote: > Hi Simon, > > 2014-11-25 10:09, Simon Kuenzer: > > thanks for your work. I have one (minor) comment for this patch that > > should be fixed in a later version. > > > > + /* default master lcore is the first one */ > > > + if (cfg

[dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name of an ol_flag

> -Original Message- > From: Zhang, Helin > Sent: Tuesday, November 25, 2014 12:15 PM > To: Ananyev, Konstantin; 'Olivier MATZ'; 'dev at dpdk.org' > Cc: 'jigsaw at gmail.com' > Subject: RE: [dpdk-dev] [PATCH v2 06/13] mbuf: add functions to get the name > of an ol_flag > > HI Konstantin

[dpdk-dev] [RFC PATCH 1/6] eal: common direct ring access API

Signed-off-by: Cunming Liang --- lib/librte_eal/common/Makefile | 5 + lib/librte_eal/common/include/rte_pci_bifurc.h | 186 + 2 files changed, 191 insertions(+) create mode 100644 lib/librte_eal/common/include/rte_pci_bifurc.h diff --git a/lib/librte_

[dpdk-dev] [RFC PATCH 4/6] bifurc: add driver to scan bifurcated netdev

Signed-off-by: Cunming Liang --- config/common_linuxapp | 5 + lib/Makefile | 1 + lib/librte_bifurc/Makefile | 58 + lib/librte_bifurc/rte_bifurc.c | 284 + lib/librte_bifurc/rte_bifurc.h | 90 + mk/

[dpdk-dev] [RFC PATCH 6/6] ixgbe: PMD for bifurc ixgbe net device

Signed-off-by: Cunming Liang --- lib/librte_pmd_ixgbe/Makefile | 13 +- lib/librte_pmd_ixgbe/ixgbe_bifurcate.c | 303 + lib/librte_pmd_ixgbe/ixgbe_bifurcate.h | 57 +++ lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 40 - lib/librte_pmd_ixgbe/ixgbe_rx

[dpdk-dev] [RFC PATCH 3/6] pci: allow VDEV as pci device during device driver probe

Signed-off-by: Cunming Liang --- lib/librte_eal/common/include/rte_pci.h | 4 lib/librte_eal/linuxapp/eal/eal_pci.c | 42 + lib/librte_ether/rte_ethdev.c | 3 +-- 3 files changed, 32 insertions(+), 17 deletions(-) diff --git a/lib/librte_eal/com

  1   2   >