[dpdk-dev] [PATCH v4] testpmd: Add port hotplug support

2015-01-19 Thread Tetsuya Mukawa
The patch introduces following commands. - port attach [ident] - port detach [port_id] - attach: attaching a port - detach: detaching a port - ident: pci address of physical device. Or device name and paramerters of virtual device. (ex. :02:00.0, eth_pcap0,iface=eth0) - p

[dpdk-dev] [PATCH v4] librte_pmd_pcap: Add port hotplug support

2015-01-19 Thread Tetsuya Mukawa
This patch adds finalization code to free resources allocated by the PMD. v4: - Change function name. Signed-off-by: Tetsuya Mukawa --- lib/librte_pmd_pcap/rte_eth_pcap.c | 40 ++ 1 file changed, 40 insertions(+) diff --git a/lib/librte_pmd_pcap/rte_eth_pca

[dpdk-dev] [PATCH v4 11/11] eal: Enable port hotplug framework in Linux

2015-01-19 Thread Tetsuya Mukawa
The patch enables CONFIG_RTE_LIBRTE_EAL_HOTPLUG in Linux configuration. Signed-off-by: Tetsuya Mukawa --- config/common_linuxapp | 5 + 1 file changed, 5 insertions(+) diff --git a/config/common_linuxapp b/config/common_linuxapp index 2f9643b..27d05be 100644 --- a/config/common_linuxapp +++

[dpdk-dev] [PATCH v4 10/11] eal/pci: Add rte_eal_dev_attach/detach() functions

2015-01-19 Thread Tetsuya Mukawa
These functions are used for attaching or detaching a port. When rte_eal_dev_attach() is called, the function tries to realize the device name as pci address. If this is done successfully, rte_eal_dev_attach() will attach physical device port. If not, attaches virtual devive port. When rte_eal_dev_

[dpdk-dev] [PATCH v4 09/11] ethdev: Add one dev_type paramerter to rte_eth_dev_allocate

2015-01-19 Thread Tetsuya Mukawa
This new parameter is needed to keep device type like physical or virtual. Port detaching processes are different between physical and virtual. This paramerter lets detaching function know a device type of the port. v4: - Fix comments of rte_eth_dev_type. Signed-off-by: Tetsuya Mukawa --- app/t

[dpdk-dev] [PATCH v4 08/11] eal/pci: Cleanup pci driver initialization code

2015-01-19 Thread Tetsuya Mukawa
- Add rte_eal_pci_close_one_dirver() The function is used for closing the specified driver and device. - Add pci_invoke_all_drivers() The function is based on pci_probe_all_drivers. But it can not only probe but also close drivers. - Add pci_close_all_drivers() The function tries to find a

[dpdk-dev] [PATCH v4 07/11] eal/pci: Add a function to remove the entry of devargs list

2015-01-19 Thread Tetsuya Mukawa
The function removes the specified devargs entry from devargs_list. Also the patch adds sanity checking to rte_eal_devargs_add(). v4: - Fix sanity check code Signed-off-by: Tetsuya Mukawa --- lib/librte_eal/common/eal_common_devargs.c | 57 + lib/librte_eal/common/i

[dpdk-dev] [PATCH v4 06/11] eal/linux/pci: Add functions for unmapping igb_uio resources

2015-01-19 Thread Tetsuya Mukawa
The patch adds functions for unmapping igb_uio resources. The patch is only for Linux and igb_uio environment. VFIO and BSD are not supported. v4: - Add paramerter checking. - Add header file to determine if hotplug can be enabled. Signed-off-by: Tetsuya Mukawa --- lib/librte_eal/common/Makefil

[dpdk-dev] [PATCH v4 05/11] ethdev: Add functions that will be used by port hotplug functions

2015-01-19 Thread Tetsuya Mukawa
The patch adds following functions. - rte_eth_dev_save() The function is used for saving current rte_eth_dev structures. - rte_eth_dev_get_changed_port() The function receives the rte_eth_dev structures, then compare these with current values to know which port is actually attached or deta

[dpdk-dev] [PATCH v4 04/11] eal, ethdev: Add a function and function pointers to close ether device

2015-01-19 Thread Tetsuya Mukawa
The patch adds function pointer to rte_pci_driver and eth_driver structure. These function pointers are used when ports are detached. Also the patch adds rte_eth_dev_uninit(). So far, it's not called by anywhere, but it will be called when port hotplug function is implemented. v4: - Add paramerter

[dpdk-dev] [PATCH v4 03/11] ethdev: Add rte_eth_dev_free to free specified device

2015-01-19 Thread Tetsuya Mukawa
This patch adds rte_eth_dev_free(). The function is used for changing a attached status of the device that has specified name. v4: - Add paramerter checking. Signed-off-by: Tetsuya Mukawa --- lib/librte_ether/rte_ethdev.c | 20 lib/librte_ether/rte_ethdev.h | 11 +++

[dpdk-dev] [PATCH v4 02/11] eal/pci: Consolidate pci address comparison APIs

2015-01-19 Thread Tetsuya Mukawa
This patch replaces pci_addr_comparison() and memcmp() of pci addresses by eal_compare_pci_addr(). v4: - Fix calculation method of eal_compare_pci_addr(). - Add parameter checking. Signed-off-by: Tetsuya Mukawa --- lib/librte_eal/bsdapp/eal/eal_pci.c | 16 +-- lib/librte_eal/c

[dpdk-dev] [PATCH v4 01/11] eal/pci, ethdev: Remove assumption that port will not be detached

2015-01-19 Thread Tetsuya Mukawa
To remove assumption, do like followings. This patch adds "RTE_PCI_DRV_DETACHABLE" to drv_flags of rte_pci_driver structure. The flags indicates the driver can detach devices at runtime. Also remove assumption that port will not be detached. To remove the assumption. - Add 'attached' member to rt

[dpdk-dev] [PATCH v4 00/11] Port Hotplug Framework

2015-01-19 Thread Tetsuya Mukawa
This patch series adds a dynamic port hotplug framework to DPDK. With the patches, DPDK apps can attach or detach ports at runtime. The basic concept of the port hotplug is like followings. - DPDK apps must have responsibility to manage ports. DPDK apps only know which ports are attached or deta

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Tetsuya Mukawa
On 2015/01/19 18:49, Qiu, Michael wrote: > Hi Tetsuya, > > I see two lines log like: > > EAL: cannot open VFIO container, error 2 (No such file or directory) > EAL: VFIO support could not be initialized > > It should not happen as I have a patch merged to master branch. > > There should have some

[dpdk-dev] [PATCH] lib/librte_ether: change socket_id passed to rte_memzone_reserve

2015-01-19 Thread Ferriter, Cian
I would be happy with the original suggestion. If the ethdev data for a port in use is in cache it removes the performance concern associated the current setup and my fix. The original suggestion also fixes the crash that I was seeing because of memory being reserved from a numa node with no "--

[dpdk-dev] [RFC 01/17] mbuf: add definitions of unified packet types

2015-01-19 Thread Olivier MATZ
Hi, On 01/19/2015 05:33 PM, Neil Horman wrote: > On Mon, Jan 19, 2015 at 11:23:07AM +0800, Helin Zhang wrote: >> As there are only 6 bit flags in ol_flags for indicating packet types, >> which is not enough to describe all the possible packet types hardware >> can recognize. For example, i40e hard

[dpdk-dev] [PATCH v2 11/17] librte_acl: add AVX2 as new rte_acl_classify() method

2015-01-19 Thread Thomas Monjalon
2015-01-12 19:16, Konstantin Ananyev: > +/* > + * Select highest avaialbe classify method as default one. Typo here. Actually, I've seen few typos when browsing your big patchset but I don't remember exactly where. Maybe that a tool like codespell could help. [...] > + else if (rte_cpu_get_f

[dpdk-dev] [PATCH v2 17/17] libte_acl: remove unused macros.

2015-01-19 Thread Thomas Monjalon
2015-01-12 19:16, Konstantin Ananyev: > /* > + * ACL RT structure is a set of multibit tries (with stride == 8) > + * represented by an array of transitions. The next position is calculated > + * based on the current position and the input byte. > + * Each transition is 64 bit value with the follo

[dpdk-dev] [PATCH v2 00/17] ACL: New AVX2 classify method and several other enhancements.

2015-01-19 Thread Thomas Monjalon
2015-01-14 13:39, Neil Horman: > On Mon, Jan 12, 2015 at 07:16:04PM +, Konstantin Ananyev wrote: > > v2 changes: > > - When build with the compilers that don't support AVX2 instructions, > > make rte_acl_classify_avx2() do nothing and return an error. > > - Remove unneeded 'ifdef __AVX2__' in a

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Tetsuya Mukawa
Hi Doherty, On 2015/01/19 17:53, Doherty, Declan wrote: >> -Original Message- >> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Tetsuya Mukawa >> Sent: Monday, January 19, 2015 7:11 AM >> To: dev at dpdk.org >> Subject: [dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code

[dpdk-dev] librte_power/rte_power.h causes link error

2015-01-19 Thread Ильдар Мустафин
Hi list, I got " multiple definition of 'rte_power_freq_min' " link error, while compiling my dpdk project. I think extern keyword was missed in rte_power.h header for some reason: /** ?* Scale down the frequency of a specific lcore to the lowest according to the ?* available frequencies. ?* Re

[dpdk-dev] librte_power/rte_power.h causes link error

2015-01-19 Thread Thomas Monjalon
Hi, 2015-01-19 16:55, ?? : > Hi list, > > I got " multiple definition of 'rte_power_freq_min' " link error, while > compiling my dpdk project. > I think extern keyword was missed in rte_power.h header for some reason: You're right. It can be seen in this commit: http://dpd

[dpdk-dev] [RFC 01/17] mbuf: add definitions of unified packet types

2015-01-19 Thread Ananyev, Konstantin
> -Original Message- > From: Zhang, Helin > Sent: Monday, January 19, 2015 3:23 AM > To: dev at dpdk.org > Cc: Liang, Cunming; Liu, Jijiang; Ananyev, Konstantin; Zhang, Helin > Subject: [RFC 01/17] mbuf: add definitions of unified packet types > > As there are only 6 bit flags in ol_flag

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Tetsuya Mukawa
Hi, I've got following error using latest DPDK code. Does someone face the same issue? In my environment, It seems almost all DPDK apps (at lease l2fwd and testpmd) cannot work. EAL: Support maximum 128 logical core(s) by configuration. EAL: Detected 8

[dpdk-dev] [PATCH] librte_pmd_ixgbe: Add queue start failure check

2015-01-19 Thread Qiu, Michael
Any comments? On 2015/1/15 22:45, Qiu, Michael wrote: > For ixgbe, when queue start failure, for example, mbuf allocate > failure, the device will still start success, which could be > an issue. > > Add return status check of queue start to avoid this issue. > > Signed-off-by: Michael Qiu > --- >

[dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and csum forwarding engine

2015-01-19 Thread Olivier MATZ
Hi Konstantin, On 01/19/2015 02:04 PM, Ananyev, Konstantin wrote: >> case 2) calculate checksum of out_ip and out_udp >> >>mb->l2_len = len(out_eth) >>mb->l3_len = len(out_ip) >>mb->ol_flags |= PKT_TX_IPV4 | PKT_TX_IP_CSUM | PKT_TX_UDP_CKSUM >>set out_ip checksum to 0 in the packet

[dpdk-dev] [PATCH 7/7] app/testpmd: support new rss offloads

2015-01-19 Thread Helin Zhang
RSS offloads supported 'ip' and 'udp' only, which did not demonstrate all of the hardware capabilities. The modifications adds support of new RSS offloads of 'tcp', 'sctp', 'ether' and 'all'. Signed-off-by: Helin Zhang --- app/test-pmd/cmdline.c | 19 +++ 1 file changed, 15 inser

[dpdk-dev] [PATCH 6/7] ethdev: unification of RSS offload types

2015-01-19 Thread Helin Zhang
RSS offload types were defined seperately for 1/10G and 40G NICs, and have no relationship with flow types. The modifications are to unify all RSS offload types for all PMDs. Unified RSS offload types have new and common names which can be used for any PMD or applications, and decouple from specifi

[dpdk-dev] [PATCH 5/7] ethdev: unification of flow types

2015-01-19 Thread Helin Zhang
Flow types was defined actually for i40e hardware specifically, and wasn't able to be used for defining RSS offload types of all PMDs. It removed the enum flow types, and uses macros instead with new names. The new macros can be used for defining RSS offload types later. Also modifications are made

[dpdk-dev] [PATCH 4/7] ethdev: fix of calculating the size of flow type mask array

2015-01-19 Thread Helin Zhang
It wrongly calculates the size of the flow type mask array. The fix is to align the flow type maximum index ID with the number of element bit width, and then divide the number of element bit width. Signed-off-by: Helin Zhang --- lib/librte_ether/rte_eth_ctrl.h | 6 +- 1 file changed, 5 inser

[dpdk-dev] [PATCH 3/7] i40e: code style fix

2015-01-19 Thread Helin Zhang
Added code style fixes. Signed-off-by: Helin Zhang --- lib/librte_pmd_i40e/i40e_fdir.c | 7 ++- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/lib/librte_pmd_i40e/i40e_fdir.c b/lib/librte_pmd_i40e/i40e_fdir.c index 68511c8..c9e535b 100644 --- a/lib/librte_pmd_i40e/i40e_fdir.c

[dpdk-dev] [PATCH 2/7] ethdev: code style fix

2015-01-19 Thread Helin Zhang
Added code style fixes. Signed-off-by: Helin Zhang --- lib/librte_ether/rte_eth_ctrl.h | 32 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_ctrl.h index 5d9c387..4308eae 100644 --- a/lib/

[dpdk-dev] [PATCH 1/7] app/test-pmd: code style fix

2015-01-19 Thread Helin Zhang
Added code style fixes. Signed-off-by: Helin Zhang --- app/test-pmd/config.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index 97b6525..87dedf9 100644 --- a/app/test-pmd/config.c +++ b/app/test-pmd/config.c @@ -1918,11 +

[dpdk-dev] [PATCH 0/7] unification of flow types and RSS offload types

2015-01-19 Thread Helin Zhang
It unifies the flow types and RSS offload types for all PMDs. Previously flow types are defined actually for i40e, and there has different RSS offloads tyeps for 1/10G and 40G seperately. This is not so convenient for application development, and not good for adding new PMDs. In addition, it enable

[dpdk-dev] FW: [PATCH v4 01/11] eal/pci, ethdev: Remove assumption that port will not be detached

2015-01-19 Thread Qiu, Michael
Hi, Tetsuya You see lots of places have below three lines: if (rte_eth_dev_validate_port(port_id) == DEV_INVALID) { PMD_DEBUG_TRACE("Invalid port_id=%d\n", port_id); return -EINVAL; } They are all the same(only few has the print log different), so

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Ravi Kerur
Looks like "make test" was added recently? I have "1.8.0" version and when I run "make test" after "make install T=x86_64-native-linuxapp-gcc" I get following errors root at user-PC:/home/rkerur/dpdk-new-5/dpdk# make test No test found, please do a 'make build' first, or specify O= root at user-PC

[dpdk-dev] [PATCH v2 4/4] testpmd: fix dcb in vt mode

2015-01-19 Thread Pawel Wodkowski
This patch incorporate fixes to support DCB in SRIOV mode for testpmd. Signed-off-by: Pawel Wodkowski --- app/test-pmd/cmdline.c |4 ++-- app/test-pmd/testpmd.c | 39 +-- app/test-pmd/testpmd.h | 10 -- 3 files changed, 31 insertions(+), 22 del

[dpdk-dev] [PATCH v2 3/4] pmd: add support for DCB in SRIOV mode for ixgbe driver.

2015-01-19 Thread Pawel Wodkowski
Add support for DCB in SRIOV mode. When no PFC is enabled this feature might be used as multiple queues for VF (up to 8 queues if VFs num is less or equal 16 or 4 if FVs num is less or equal 32). The PF must initializes RX in ETH_MQ_RX_VMDQ_DCB and TX in ETH_MQ_TX_VMDQ_DCB. VF should initialize Rx

[dpdk-dev] [PATCH v2 2/4] ethdev: prevent changing of nb_q_per_pool in rte_eth_dev_check_mq_mode()

2015-01-19 Thread Pawel Wodkowski
If SRIOV is used and device configuration does not use MQ the RTE_ETH_DEV_SRIOV(dev).nb_q_per_pool is set to 1 in rte_eth_dev_check_mq_mode(). This is bad becouse of two reasons: 1. Port reconfiguration from non-MQ mode to MQ mode is impossible 2. Confguring RX and TX side in different way is impos

[dpdk-dev] [PATCH v2 1/4] ethdev: Allow zero rx/tx queues in SRIOV mode

2015-01-19 Thread Pawel Wodkowski
Allow zero rx/tx queues to be passed to rte_eth_dev_configure(). This way PF might be used only for configuration purpose when no receive and/or transmit functionality is needed. Rationale: in SRIOV mode PF use first free VF to RX/TX (at least ixgbe based NICs). For example: if using 82599EB based

[dpdk-dev] [PATCH v2 0/4] Enable DCB in SRIOV mode for ixgbe driver

2015-01-19 Thread Pawel Wodkowski
v2: - Split patch for easer review. - Remove "pmd: add api version negotiation for ixgbe driver" and "pmd: extend mailbox api to report number of RX/TX queues" patches as those are already already marged from other patch v1: This patchset enables DCB in SRIOV (ETH_MQ_RX_VMDQ_DCB and ETH_MQ_TX

[dpdk-dev] [PATCH v2 2/2] Unit tests for mode 4

2015-01-19 Thread Tomasz Kulasek
This patch adds unit tests for mode 4. It is split into separate file to avoid problems with other modes that does not need to look into packets payload. This patch includes also a modification of maximum number of ports used in their tests for bonding modes 0-3 from 16 to 6. Signed-off-by: Tomasz

[dpdk-dev] [PATCH v2 1/2] Unit tests - test.h rework

2015-01-19 Thread Tomasz Kulasek
Signed-off-by: Tomasz Kulasek Signed-off-by: Pawel Wodkowski --- app/test/test.h | 112 --- 1 file changed, 66 insertions(+), 46 deletions(-) diff --git a/app/test/test.h b/app/test/test.h index 896f7db..5450986 100644 --- a/app/test/test.h +

[dpdk-dev] [PATCH v2 0/2] unit tests add mode 4 unit test

2015-01-19 Thread Tomasz Kulasek
Update v2: Patch split - separated test.h rework and unit test for mode 4 patch. Tomasz Kulasek (2): Unit tests - test.h rework Unit tests for mode 4 app/test/Makefile |1 + app/test/test.h| 112 +-- app/test/test_link_bonding.c |2 +- app/

[dpdk-dev] [PATCH v2 00/17] ACL: New AVX2 classify method and several other enhancements.

2015-01-19 Thread Neil Horman
On Mon, Jan 19, 2015 at 06:16:02PM +0100, Thomas Monjalon wrote: > 2015-01-14 13:39, Neil Horman: > > On Mon, Jan 12, 2015 at 07:16:04PM +, Konstantin Ananyev wrote: > > > v2 changes: > > > - When build with the compilers that don't support AVX2 instructions, > > > make rte_acl_classify_avx2()

[dpdk-dev] [PATCH v4 00/11] Port Hotplug Framework

2015-01-19 Thread Qiu, Michael
Hi, Tetsuya What I miss? I haven't got the first patch, just start with "PATCH 2/11". Does this only happens with my mail client? Thanks, Michael On 2015/1/19 18:42, Tetsuya Mukawa wrote: > This patch series adds a dynamic port hotplug framework to DPDK. > With the patches, DPDK apps can attach

[dpdk-dev] [RFC 01/17] mbuf: add definitions of unified packet types

2015-01-19 Thread Neil Horman
On Mon, Jan 19, 2015 at 06:27:02PM +0100, Olivier MATZ wrote: > Hi, > > On 01/19/2015 05:33 PM, Neil Horman wrote: > > On Mon, Jan 19, 2015 at 11:23:07AM +0800, Helin Zhang wrote: > >> As there are only 6 bit flags in ol_flags for indicating packet types, > >> which is not enough to describe all t

[dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and csum forwarding engine

2015-01-19 Thread Ananyev, Konstantin
Hi Olivier, > -Original Message- > From: Olivier MATZ [mailto:olivier.matz at 6wind.com] > Sent: Friday, January 16, 2015 5:28 PM > To: Ananyev, Konstantin; Liu, Jijiang > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3 0/3] enhance TX checksum command and csum > forwarding engine

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Qiu, Michael
On 2015/1/19 18:06, Tetsuya Mukawa wrote: > On 2015/01/19 18:49, Qiu, Michael wrote: >> Hi Tetsuya, >> >> I see two lines log like: >> >> EAL: cannot open VFIO container, error 2 (No such file or directory) >> EAL: VFIO support could not be initialized >> >> It should not happen as I have a patch

[dpdk-dev] [PATCH v2 3/3] PMD Ring - Fix for MAC per device management

2015-01-19 Thread Tomasz Kulasek
Initialization procedure fix to allow per device MAC configuration. Signed-off-by: Tomasz Kulasek Signed-off-by: Pawel Wodkowski --- lib/librte_pmd_ring/rte_eth_ring.c | 30 +- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/lib/librte_pmd_ring/rte_e

[dpdk-dev] [PATCH v2 2/3] PMD Ring - Add MAC addr add/remove functions

2015-01-19 Thread Tomasz Kulasek
Added MAC addr add/remove dummy callbacks. Signed-off-by: Tomasz Kulasek Signed-off-by: Pawel Wodkowski --- lib/librte_pmd_ring/rte_eth_ring.c | 16 1 file changed, 16 insertions(+) diff --git a/lib/librte_pmd_ring/rte_eth_ring.c b/lib/librte_pmd_ring/rte_eth_ring.c index 9

[dpdk-dev] [PATCH v2 1/3] PMD Ring - Add link up/down functions

2015-01-19 Thread Tomasz Kulasek
Link up and down implementation. Signed-off-by: Tomasz Kulasek Signed-off-by: Pawel Wodkowski --- lib/librte_pmd_ring/rte_eth_ring.c | 16 1 file changed, 16 insertions(+) diff --git a/lib/librte_pmd_ring/rte_eth_ring.c b/lib/librte_pmd_ring/rte_eth_ring.c index 4f1b6ed..92

[dpdk-dev] [PATCH v2 0/3] PMD ring MAC management, fix initialization, link up/down

2015-01-19 Thread Tomasz Kulasek
Patch split into smaller parts to separate features from previous version. Tomasz Kulasek (3): PMD Ring - Add link up/down functions PMD Ring - Add MAC addr add/remove functions PMD Ring - Fix for per device management lib/librte_pmd_ring/rte_eth_ring.c | 62 +

[dpdk-dev] more maintainers with sub-trees

2015-01-19 Thread Vlad Zolotarov
On 12/23/14 19:08, Thomas Monjalon wrote: > Hello all, > > We now have 2 new maintainers managing their own sub-tree for some > specific areas of DPDK: > - Stephen Hemminger will maintain the driver bnx2x Cool! > - Helin Zhang will maintain the driver i40e > > These repositories can

[dpdk-dev] Sharing NIC port between Linux and DPDK

2015-01-19 Thread Deepak Sehrawat
Hi All, What are the various means available (as of now) to share a NIC port between Linux and DPDK applications? Idea is to separate control packets and data packets; using Linux userspace application to process control packets while DPDK application to access/process data packets (same NIC port

[dpdk-dev] [PATCH v5 0/6] Enable VF RSS for Niantic

2015-01-19 Thread Vlad Zolotarov
On 01/18/15 23:58, Thomas Monjalon wrote: > 2015-01-08 11:56, Vlad Zolotarov: >> I've acked PATCH1 and PATCH2 already before and since there are no >> changes in them, pls., consider them ACKed... ;) > Thank you for the great review. > > Note to everybody reading that: > Vlad approved the 2 first

[dpdk-dev] [RFC 01/17] mbuf: add definitions of unified packet types

2015-01-19 Thread Neil Horman
On Mon, Jan 19, 2015 at 11:23:07AM +0800, Helin Zhang wrote: > As there are only 6 bit flags in ol_flags for indicating packet types, > which is not enough to describe all the possible packet types hardware > can recognize. For example, i40e hardware can recognize more than 150 > packet types. Unif

[dpdk-dev] Segmentation fault in ixgbe_rxtx_vec.c:444 with 1.8.0

2015-01-19 Thread Martin Weiser
Hi everybody, we quite recently updated one of our applications to DPDK 1.8.0 and are now seeing a segmentation fault in ixgbe_rxtx_vec.c:444 after a few minutes. I just did some quick debugging and I only have a very limited understanding of the code in question but it seems that the 'continue' i

[dpdk-dev] [RFC 17/17] mbuf: remove old packet type bit masks for ol_flags

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- lib/librte_mbuf/rte_mbuf.c | 6 -- lib/librte_mbuf/rte_mbuf.h | 10 ++ 2 files changed, 2 insertion

[dpdk-dev] [RFC 16/17] examples/l3fwd: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- examples/l3fwd/main.c | 64 +-- 1 file changed, 37 insertions(+)

[dpdk-dev] [RFC 15/17] examples/l3fwd-power: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- examples/l3fwd-power/main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/examples/l3

[dpdk-dev] [RFC 14/17] examples/l3fwd-acl: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- examples/l3fwd-acl/main.c | 19 ++- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git

[dpdk-dev] [RFC 13/17] examples/ip_reassembly: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- examples/ip_reassembly/main.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/example

[dpdk-dev] [RFC 12/17] examples/ip_fragmentation: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- examples/ip_fragmentation/main.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/exam

[dpdk-dev] [RFC 11/17] app/test: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- app/test/packet_burst_generator.c | 10 -- 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a

[dpdk-dev] [RFC 10/17] app/test-pmd: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- app/test-pmd/csumonly.c | 6 +++--- app/test-pmd/rxonly.c | 9 +++-- 2 files changed, 6 insertions(+), 9 d

[dpdk-dev] [RFC 09/17] app/test-pipeline: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks and relevant macros of packet type for ol_flags are replaced by unified packet type and relevant macros. Signed-off-by: Helin Zhang --- app/test-pipeline/pipeline_hash.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/app/te

[dpdk-dev] [RFC 08/17] vmxnet3: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/librte_pmd_vmxnet3/vmxnet3_rxtx.c b/l

[dpdk-dev] [RFC 07/17] enic: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_enic/enic_main.c | 14 -- 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/lib/librte_pmd_enic/enic_main.c b/lib

[dpdk-dev] [RFC 06/17] bond: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_bond/rte_eth_bond_pmd.c | 9 - 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/lib/librte_pmd_bond/rte_eth_bond_pmd

[dpdk-dev] [RFC 05/17] i40e: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang Signed-off-by: Jijiang Liu --- lib/librte_pmd_i40e/i40e_rxtx.c | 778 ++-- 1 file changed, 504 insertions(+), 274 delet

[dpdk-dev] [RFC 04/17] ixgbe: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type for Vector PMD. Signed-off-by: Cunming Liang Signed-off-by: Helin Zhang --- lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 39 +++ 1 file changed, 21 insertio

[dpdk-dev] [RFC 03/17] ixgbe: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 141 +- 1 file changed, 107 insertions(+), 34 deletions(-) diff --git a/lib/lib

[dpdk-dev] [RFC 02/17] e1000: support of unified packet type

2015-01-19 Thread Helin Zhang
To unify packet types among all PMDs, bit masks of packet type for ol_flags are replaced by unified packet type. Signed-off-by: Helin Zhang --- lib/librte_pmd_e1000/igb_rxtx.c | 95 ++--- 1 file changed, 80 insertions(+), 15 deletions(-) diff --git a/lib/libr

[dpdk-dev] [RFC 01/17] mbuf: add definitions of unified packet types

2015-01-19 Thread Helin Zhang
As there are only 6 bit flags in ol_flags for indicating packet types, which is not enough to describe all the possible packet types hardware can recognize. For example, i40e hardware can recognize more than 150 packet types. Unified packet type is composed of tunnel type, L3 type, L4 type and inne

[dpdk-dev] [RFC 00/17] unified packet type

2015-01-19 Thread Helin Zhang
Currently only 6 bits which are stored in ol_flags are used to indicate the packet types. This is not enough, as some NIC hardware can recognize quite a lot of packet types, e.g i40e hardware can recognize more than 150 packet types. Hiding those packet types hides hardware offload capabilities whi

[dpdk-dev] RSS Reta redirection not working on 82599 NIC(Niantic)

2015-01-19 Thread Kamraan Nasim
Hello, Following from a previous thread, I took up Bruce Richardson's advice to modify the RSS redirection table(RETA) to exclude entries pointing to a specific queue: For e.g, this is the RETA table before any modifications are done: *Default *Reta table: 0 1 2 0 1 2 0 1 2 0 1 2 0 1 2 0 1 2 0 1

[dpdk-dev] Should the other queues at same port work when one queue is full ?

2015-01-19 Thread Bruce Richardson
On Sun, Jan 18, 2015 at 07:12:31PM +0800, XU Liang wrote: > I configured the 82599 ports to work in multi-queue mode and flow director to > assign different TCP connections to different queues. A multi-process > application receive packets from queues and each?process reads a queue. When > I kil

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread David Marchand
On Mon, Jan 19, 2015 at 10:30 AM, Qiu, Michael wrote: > > This could be, but I hope every contributor could do basic check like > build and run of at lease one app like test-pmd, then it will reduce > most of failure we faced. > testpmd is fine, but make test should be preferred as it requires n

[dpdk-dev] [PATCH v6 4/6] ether: Check VMDq RSS mode

2015-01-19 Thread Wodkowski, PawelX
> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ouyang Changchun > Sent: Monday, January 12, 2015 6:59 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v6 4/6] ether: Check VMDq RSS mode > > Check mq mode for VMDq RSS, handle it correctly instead of retu

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Thomas Monjalon
2015-01-19 08:21, David Marchand: > On Mon, Jan 19, 2015 at 3:45 AM, Zhang, Helin > wrote: > > > It seems that your fix result in cannot launching applications. > > I don't suspect the correction of your fix, but somewhere else needs to be > > corrected together with your fix. > > > > Logs: > >

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Qiu, Michael
On 2015/1/19 17:50, David Marchand wrote: On Mon, Jan 19, 2015 at 10:30 AM, Qiu, Michael mailto:michael.qiu at intel.com>> wrote: This could be, but I hope every contributor could do basic check like build and run of at lease one app like test-pmd, then it will reduce most of failure we faced. te

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Thomas Monjalon
2015-01-19 17:56, Tetsuya Mukawa: > On 2015/01/19 17:53, Doherty, Declan wrote: > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Tetsuya Mukawa > >> Hi, > >> > >> I've got following error using latest DPDK code. > >> Does someone face the same issue? > >> In my environment, It seems almo

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Qiu, Michael
On 2015/1/19 17:50, David Marchand wrote: On Mon, Jan 19, 2015 at 10:30 AM, Qiu, Michael mailto:michael.qiu at intel.com>> wrote: This could be, but I hope every contributor could do basic check like build and run of at lease one app like test-pmd, then it will reduce most of failure we faced. te

[dpdk-dev] [PATCH] eal / malloc : alignment parameter check failing due to changes in rte_is_power_of_2

2015-01-19 Thread Thomas Monjalon
2015-01-18 19:26, Doherty, Declan: > From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com] > > 2015-01-16 15:10, Declan Doherty: > > > In commit 2fc8d6d the behaviour of function rte_is_power_of_2 was > > > changed to not return true for 0. memzone_reserve_aligned_thread_unsafe > > > and rte_

[dpdk-dev] [PATCH 4/4] lib/librte_eal: Optimized memcpy in arch/x86/rte_memcpy.h for both SSE and AVX platforms

2015-01-19 Thread zhihong.w...@intel.com
Main code changes: 1. Differentiate architectural features based on CPU flags a. Implement separated move functions for SSE/AVX/AVX2 to make full utilization of cache bandwidth b. Implement separated copy flow specifically optimized for target architecture 2. Rewrite the memcpy functi

[dpdk-dev] [PATCH 3/4] app/test: Extended test coverage in test_memcpy_perf.c

2015-01-19 Thread zhihong.w...@intel.com
Main code changes: 1. Added more typical data points for a thorough performance test 2. Added unaligned test cases since it's common in DPDK usage Signed-off-by: Zhihong Wang --- app/test/test_memcpy_perf.c | 238 +--- 1 file changed, 156 insertions(+),

[dpdk-dev] [PATCH 2/4] app/test: Removed unnecessary test cases in test_memcpy.c

2015-01-19 Thread zhihong.w...@intel.com
Removed unnecessary test cases for base move functions since the function "func_test" covers them all. Signed-off-by: Zhihong Wang --- app/test/test_memcpy.c | 52 +- 1 file changed, 1 insertion(+), 51 deletions(-) diff --git a/app/test/test_memc

[dpdk-dev] [PATCH 1/4] app/test: Disabled VTA for memcpy test in app/test/Makefile

2015-01-19 Thread zhihong.w...@intel.com
VTA is for debugging only, it increases compile time and binary size, especially when there're a lot of inlines. So disable it since memcpy test contains a lot of inline calls. Signed-off-by: Zhihong Wang --- app/test/Makefile | 6 ++ 1 file changed, 6 insertions(+) diff --git a/app/test/M

[dpdk-dev] [PATCH 0/4] DPDK memcpy optimization

2015-01-19 Thread zhihong.w...@intel.com
This patch set optimizes memcpy for DPDK for both SSE and AVX platforms. It also extends memcpy test coverage with unaligned cases and more test points. Optimization techniques are summarized below: 1. Utilize full cache bandwidth 2. Enforce aligned stores 3. Apply load address alignment based

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Qiu, Michael
Hi Tetsuya, I see two lines log like: EAL: cannot open VFIO container, error 2 (No such file or directory) EAL: VFIO support could not be initialized It should not happen as I have a patch merged to master branch. There should have something wrong, could you please help me to debug this? All

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Qiu, Michael
On 2015/1/19 17:14, Thomas Monjalon wrote: > 2015-01-19 08:21, David Marchand: >> On Mon, Jan 19, 2015 at 3:45 AM, Zhang, Helin >> wrote: >> >>> It seems that your fix result in cannot launching applications. >>> I don't suspect the correction of your fix, but somewhere else needs to be >>> corre

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread De Lara Guarch, Pablo
> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of David Marchand > Sent: Monday, January 19, 2015 7:21 AM > To: Zhang, Helin > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2] Fix rte_is_power_of_2 > > Hello, > > On Mon, Jan 19, 2015 at 3:45 AM, Zhan

[dpdk-dev] [PATCH v6 3/6] ixgbe: Get VF queue number

2015-01-19 Thread Wodkowski, PawelX
> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Ouyang Changchun > Sent: Monday, January 12, 2015 6:59 AM > To: dev at dpdk.org > Subject: [dpdk-dev] [PATCH v6 3/6] ixgbe: Get VF queue number > > Get the available Rx and Tx queue number when receiving > IXG

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread Ravi Kerur
Sorry for the inconvenience. I was not aware of "make test" utility which does more elaborate testing. I will make a note of it and make sure future patches will go through it. I had done basic testing with testpmd as the changes were minimal. Thanks, Ravi On Mon, Jan 19, 2015 at 1:13 AM, Thomas

[dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code.

2015-01-19 Thread Doherty, Declan
> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Tetsuya Mukawa > Sent: Monday, January 19, 2015 7:11 AM > To: dev at dpdk.org > Subject: [dpdk-dev] rte_eal_init() causes PANIC using latest DPDK code. > > Hi, > > I've got following error using latest DPDK co

[dpdk-dev] Why nothing since 1.8.0?

2015-01-19 Thread Neil Horman
On Sun, Jan 18, 2015 at 09:48:33PM +, O'driscoll, Tim wrote: > > -Original Message- > > From: Neil Horman [mailto:nhorman at tuxdriver.com] > > Sent: Sunday, January 18, 2015 6:25 PM > > To: O'driscoll, Tim > > Cc: Thomas Monjalon; dev at dpdk.org > > Subject: Re: [dpdk-dev] Why nothing

[dpdk-dev] [PATCH v2] Fix rte_is_power_of_2

2015-01-19 Thread David Marchand
Hello, On Mon, Jan 19, 2015 at 3:45 AM, Zhang, Helin wrote: > It seems that your fix result in cannot launching applications. > I don't suspect the correction of your fix, but somewhere else needs to be > corrected together with your fix. > > Logs: > /

[dpdk-dev] [PATCH 0/4] DPDK memcpy optimization

2015-01-19 Thread Neil Horman
On Mon, Jan 19, 2015 at 09:53:30AM +0800, zhihong.wang at intel.com wrote: > This patch set optimizes memcpy for DPDK for both SSE and AVX platforms. > It also extends memcpy test coverage with unaligned cases and more test > points. > > Optimization techniques are summarized below: > > 1. Utili

  1   2   >