[dpdk-dev] [PATCH v5 0/3] net/virtio: support GUEST ANNOUNCE

v5: - Remove txvq parameter in virtio_inject_pkts. - Zero hw->special_buf after using it. - Return the retval of tx_pkt_burst(). - Allocate a mbuf pointer on stack directly. v4: - Move spinlock lock/unlock into dev_pause/resume. - Separate out a patch for packet injection. v3: - Remove Tx functio

[dpdk-dev] [PATCH v5 1/3] net/virtio: make control queue thread-safe

The virtio_send_command function may be called from app's configuration routine, but also from an interrupt handler called when live migration is done on the backup side. So this patch makes control queue thread-safe first. Signed-off-by: Xiao Wang --- drivers/net/virtio/virtio_ethdev.c | 7

[dpdk-dev] [PATCH v5 2/3] net/virtio: add packet injection method

This patch adds dev_pause, dev_resume and inject_pkts api to allow driver to pause the worker thread and inject special packets into Tx queue. The next patch will be based on this. Signed-off-by: Xiao Wang --- drivers/net/virtio/virtio_ethdev.c | 51 + driver

[dpdk-dev] [PATCH v5 3/3] net/virtio: support GUEST ANNOUNCE

When live migration is done, for the backup VM, either the virtio frontend or the vhost backend needs to send out gratuitous RARP packet to announce its new network location. This patch enables VIRTIO_NET_F_GUEST_ANNOUNCE feature to support live migration scenario where the vhost backend doesn't h

Re: [dpdk-dev] [PATCH V3 1/2] net/tap: convert to new Tx offloads API

Hi, Good job, this patch looks good to me. Acked-by: Pascal Mazon On 04/01/2018 20:18, Moti Haimovsky wrote: > Ethdev Tx offloads API has changed since: > commit cba7f53b717d ("ethdev: introduce Tx queue offloads API") > This commit support the new Tx offloads API. > > Signed-off-by: Moti Haimov

[dpdk-dev] [PATCH v4 02/15] net/avf: initialization of avf PMD

From: Jingjing Wu Signed-off-by: Jingjing Wu --- config/common_base | 5 + drivers/net/Makefile| 1 + drivers/net/avf/Makefile| 31 +++ drivers/net/avf/avf.h | 187 ++ drivers/net/avf/avf_ethdev.c

[dpdk-dev] [PATCH v4 00/15] add new AVF PMD

Adaptive Virtual Function (AVF) Driver is VF driver which supports for all future Intel devices without requiring a VM update. It promises the basic high speed connectivity. And since this happens to be an adaptive VF driver, every new drop of the VF driver would add more and more advanced featu

[dpdk-dev] [PATCH v4 03/15] net/avf: enable queue and device

From: Jingjing Wu enable device and queue setup ops like: - dev_configure - dev_start - dev_stop - dev_close - dev_infos_get - rx_queue_start - rx_queue_stop - tx_queue_start - tx_queue_stop - rx_queue_setup - rx_queue_release - tx_queue_setup - tx_queue_release Signed-off-by: Jing

[dpdk-dev] [PATCH v4 04/15] net/avf: enable basic Rx Tx func

Signed-off-by: Wenzhuo Lu --- MAINTAINERS | 1 + config/common_base | 6 +- doc/guides/nics/features/avf.ini | 22 ++ drivers/net/avf/Makefile | 3 + drivers/net/avf/avf_ethdev.c | 46 ++- drivers/net/avf/avf_log.h| 21 ++ drivers/ne

[dpdk-dev] [PATCH v4 06/15] net/avf: support stats

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 1 + drivers/net/avf/avf.h| 2 ++ drivers/net/avf/avf_ethdev.c | 27 +++ drivers/net/avf/avf_vchnl.c | 27 +++ 4 files changed, 57 insertion

[dpdk-dev] [PATCH v4 05/15] net/avf: enable link status update

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 3 +++ drivers/net/avf/avf.h| 2 ++ drivers/net/avf/avf_ethdev.c | 51 +++- drivers/net/avf/avf_vchnl.c | 38 +- 4 files cha

[dpdk-dev] [PATCH v4 07/15] net/avf: enable ops for MAC VLAN offload

From: Jingjing Wu - promiscuous_enable - promiscuous_disable - allmulticast_enable - allmulticast_disable - mac_addr_add - mac_addr_remove - mac_addr_set - vlan_filter_set - vlan_offload_set Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 5 + drivers/net/avf/avf.h

[dpdk-dev] [PATCH v4 08/15] net/avf: enable ops for RSS setting

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 2 + drivers/net/avf/avf_ethdev.c | 142 +++ 2 files changed, 144 insertions(+) diff --git a/doc/guides/nics/features/avf.ini b/doc/guides/nics/features/avf.ini index 1

[dpdk-dev] [PATCH v4 09/15] net/avf: enable ops for MTU setting

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 1 + drivers/net/avf/avf_ethdev.c | 30 ++ 2 files changed, 31 insertions(+) diff --git a/doc/guides/nics/features/avf.ini b/doc/guides/nics/features/avf.ini index 61527d7..cf1b

[dpdk-dev] [PATCH v4 12/15] net/avf: enable sse vector Rx Tx func

From: Jingjing Wu Signed-off-by: Jingjing Wu --- config/common_base| 1 + doc/guides/nics/features/avf_vec.ini | 36 ++ drivers/net/avf/Makefile | 1 + drivers/net/avf/avf.h | 4 + drivers/net/avf/avf_ethdev.c | 11 + drivers/ne

[dpdk-dev] [PATCH v4 11/15] net/i40e: support AVF basic interface

From: Jingjing Wu Enable Virtchnl offload Caps negotiation and RSS_PF offload to support AVF basic interface. Signed-off-by: Jingjing Wu --- drivers/net/i40e/i40e_ethdev.c | 69 drivers/net/i40e/i40e_ethdev.h | 5 ++ drivers/net/i40e/i40e_pf.c | 140

[dpdk-dev] [PATCH v4 10/15] net/avf: enable ops to check queue info and status

From: Jingjing Wu - rxq_info_get - txq_info_get - rx_queue_count - rx_descriptor_status - tx_descriptor_status Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 2 + drivers/net/avf/avf_ethdev.c | 5 ++ drivers/net/avf/avf_rxtx.c | 120 +++

[dpdk-dev] [PATCH v4 13/15] net/avf: enable bulk allocate Rx func

Signed-off-by: Wenzhuo Lu --- drivers/net/avf/avf.h| 1 + drivers/net/avf/avf_ethdev.c | 1 + drivers/net/avf/avf_rxtx.c | 300 +++ drivers/net/avf/avf_rxtx.h | 6 + 4 files changed, 308 insertions(+) diff --git a/drivers/net/avf/avf.h b/

[dpdk-dev] [PATCH v4 15/15] doc: update doc for avf driver

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/intel_vf.rst | 16 ++-- doc/guides/rel_notes/release_18_02.rst | 16 2 files changed, 30 insertions(+), 2 deletions(-) diff --git a/doc/guides/nics/intel_vf.rst b/doc/guides/nics/intel_vf.rs

[dpdk-dev] [PATCH v4 14/15] net/avf: enable Rx interrupt support

From: Jingjing Wu Signed-off-by: Jingjing Wu --- doc/guides/nics/features/avf.ini | 1 + doc/guides/nics/features/avf_vec.ini | 1 + drivers/net/avf/avf_ethdev.c | 204 --- 3 files changed, 170 insertions(+), 36 deletions(-) diff --git a/doc/guid

Re: [dpdk-dev] [PATCH V3 2/2] net/tap: convert to new Rx offloads API

Hi, As you did in the previous patch, you can use less parentheses for this line: + if (((port_offloads ^ offloads) & port_supp_offloads)) Otherwise ok. Best regards, Pascal On 04/01/2018 20:18, Moti Haimovsky wrote: > Ethdev Rx offloads API has changed since: > commit ce17eddefc20 ("ethdev: i

Re: [dpdk-dev] [PATCH] net/ixgbe: fix tunnel filter fail problem

Hi Wei, > -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wei Zhao > Sent: Friday, November 17, 2017 1:36 PM > To: dev@dpdk.org > Cc: Zhao1, Wei > Subject: [dpdk-dev] [PATCH] net/ixgbe: fix tunnel filter fail problem > > Add a mode type check for tunnel mode, i

Re: [dpdk-dev] standardize device identification

05/01/2018 08:52, Finn Christensen: > From: Thomas > > It may look like this: > > > > bus=BUS_NAME,id=BUS_ID/class=CLASS_NAME,dev_port=PORT_NUM, > > mac=MAC_ADDRESS/driver=DRIVER_NAME,driverspecificproperty=VALUE [...] > We also need to distinguish between multiple ports sitting on same PCI bus ID

Re: [dpdk-dev] [PATCH v4] sched: make RED scaling configurable

> > > > +int > > > > +rte_red_set_scaling(uint16_t max_red_queue_length); > > > > + > > > > +/** > > > > + * @brief Reset the RED scaling factor - only for use by RED > > > > +unit-tests > > > > + * > > > > + * @return Operation status > > > > + */ > > > > +void > > > > +rte_red_reset_scaling(void

[dpdk-dev] [PATCH v2 03/20] crypto/ccp: add basic pmd ops support for start, stop, config etc

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_dev.c | 9 ++ drivers/crypto/ccp/ccp_dev.h | 9 ++ drivers/crypto/ccp/ccp_pmd_ops.c | 61 +--- drivers/crypto/ccp/ccp_pmd_private.h | 43 + 4 files changed, 1

[dpdk-dev] [PATCH v2 04/20] crypto/ccp: add session related crypto pmd ops support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/Makefile | 3 +- drivers/crypto/ccp/ccp_crypto.c | 230 + drivers/crypto/ccp/ccp_crypto.h | 267 +++ drivers/crypto/ccp/ccp_dev.h | 129 +++ drivers/cr

[dpdk-dev] [PATCH v2 01/20] crypto/ccp: add AMD ccp crypto pmd support

Signed-off-by: Ravi Kumar --- config/common_base | 5 +++ drivers/crypto/Makefile| 1 + drivers/crypto/ccp/Makefile| 55 ++ drivers/crypto/ccp/rte_ccp_pmd.c | 62 ++ drivers

[dpdk-dev] [PATCH v2 02/20] crypto/ccp: add ccp device initialization and remove

CCP PMD is a virtual crypto PMD which schedules all the available actual hardware engines. The PMD creates a linked list of all CCP engines which will be scheduled in a round-robin fashion to the CPU core requesting crypto operations. --- drivers/crypto/ccp/Makefile | 3 + drivers/crypt

[dpdk-dev] [PATCH v2 06/20] crypto/ccp: add crypto enqueue and dequeue burst api support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 359 +++ drivers/crypto/ccp/ccp_crypto.h | 35 drivers/crypto/ccp/ccp_dev.c | 27 +++ drivers/crypto/ccp/ccp_dev.h | 9 + drivers/crypto/ccp/rte_ccp_pmd.c | 64 ++- 5 files

[dpdk-dev] [PATCH v2 05/20] crypto/ccp: add queue pair related pmd ops support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_pmd_ops.c | 149 +-- 1 file changed, 144 insertions(+), 5 deletions(-) diff --git a/drivers/crypto/ccp/ccp_pmd_ops.c b/drivers/crypto/ccp/ccp_pmd_ops.c index ad0a670..a02aa6f 100644 --- a/drivers/crypto/ccp/

[dpdk-dev] [PATCH v2 07/20] crypto/ccp: add support for RTE_CRYPTO_OP_SESSIONLESS

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/rte_ccp_pmd.c | 33 +++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/rte_ccp_pmd.c b/drivers/crypto/ccp/rte_ccp_pmd.c index fb6d41e..011240b 100644 --- a/drivers/crypto/ccp/rte_ccp_

[dpdk-dev] [PATCH v2 08/20] crypto/ccp: add stats related crypto pmd ops support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_pmd_ops.c | 34 -- 1 file changed, 32 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/ccp_pmd_ops.c b/drivers/crypto/ccp/ccp_pmd_ops.c index a02aa6f..d483a74 100644 --- a/drivers/crypto/ccp/ccp_pmd

[dpdk-dev] [PATCH v2 09/20] crypto/ccp: add ccp hwrng feature support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_dev.c | 20 drivers/crypto/ccp/ccp_dev.h | 11 +++ 2 files changed, 31 insertions(+) diff --git a/drivers/crypto/ccp/ccp_dev.c b/drivers/crypto/ccp/ccp_dev.c index fee90e3..d8c0ab4 100644 --- a/drivers/crypto/ccp/c

[dpdk-dev] [PATCH v2 12/20] crypto/ccp: add aes-cmac auth algo aupport

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 277 ++- drivers/crypto/ccp/ccp_pmd_ops.c | 21 +++ 2 files changed, 296 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/ccp/ccp_crypto.c b/drivers/crypto/ccp/ccp_crypto.c index 066076

[dpdk-dev] [PATCH v2 10/20] crypto/ccp: add aes cipher algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 197 ++- drivers/crypto/ccp/ccp_crypto.h | 13 +++ drivers/crypto/ccp/ccp_dev.h | 53 +++ drivers/crypto/ccp/ccp_pmd_ops.c | 60 4 files changed, 321 insertions(+), 2

[dpdk-dev] [PATCH v2 13/20] crypto/ccp: add aes-gcm aead algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 240 ++- drivers/crypto/ccp/ccp_pmd_ops.c | 30 + 2 files changed, 266 insertions(+), 4 deletions(-) diff --git a/drivers/crypto/ccp/ccp_crypto.c b/drivers/crypto/ccp/ccp_crypto.c index 6e59

[dpdk-dev] [PATCH v2 11/20] crypto/ccp: add 3des cipher algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 132 ++- drivers/crypto/ccp/ccp_crypto.h | 3 + drivers/crypto/ccp/ccp_pmd_ops.c | 20 ++ 3 files changed, 154 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/ccp/ccp_crypto.c b/

[dpdk-dev] [PATCH v2 14/20] crypto/ccp: add sha1 auth algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 367 +++ drivers/crypto/ccp/ccp_crypto.h | 23 +++ drivers/crypto/ccp/ccp_pmd_ops.c | 42 + 3 files changed, 432 insertions(+) diff --git a/drivers/crypto/ccp/ccp_crypto.c b/drivers/crypto

[dpdk-dev] [PATCH v2 18/20] doc: add document for AMD CCP crypto poll mode driver

Signed-off-by: Ravi Kumar --- doc/guides/cryptodevs/ccp.rst | 127 + doc/guides/cryptodevs/features/ccp.ini | 57 + doc/guides/cryptodevs/features/default.ini | 12 +++ doc/guides/cryptodevs/index.rst| 1 + 4 files changed,

[dpdk-dev] [PATCH v2 17/20] crypto/ccp: add cpu based md5 and sha2 family auth algo support

Auth operations can be performed on CPU without offloading to CCP if CONFIG_RTE_LIBRTE_PMD_CCP_CPU_AUTH is enabled in DPDK configuration. Signed-off-by: Ravi Kumar --- config/common_base | 1 + drivers/crypto/ccp/ccp_crypto.c | 278 ++- dr

[dpdk-dev] [PATCH v2 16/20] crypto/ccp: add sha3 family auth algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 667 +- drivers/crypto/ccp/ccp_crypto.h | 22 ++ drivers/crypto/ccp/ccp_pmd_ops.c | 168 + lib/librte_cryptodev/rte_crypto_sym.h | 17 + 4 files changed, 873 insertions(+), 1

[dpdk-dev] [PATCH v2 15/20] crypto/ccp: add sha2 family auth algo support

Signed-off-by: Ravi Kumar --- drivers/crypto/ccp/ccp_crypto.c | 270 +++ drivers/crypto/ccp/ccp_crypto.h | 48 +++ drivers/crypto/ccp/ccp_pmd_ops.c | 168 3 files changed, 486 insertions(+) diff --git a/drivers/crypto/ccp/ccp_cr

[dpdk-dev] [PATCH v2 20/20] doc: add ccp crypto poll mode driver to release notes

Signed-off-by: Ravi Kumar --- MAINTAINERS| 6 ++ doc/guides/rel_notes/release_18_02.rst | 5 + 2 files changed, 11 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index f0baeb4..54734f7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -588,6 +588,12 @@ M: Pa

[dpdk-dev] [PATCH v2 19/20] test/crypto: add test for AMD CCP crypto poll mode driver

Signed-off-by: Ravi Kumar --- test/test/test_cryptodev.c | 161 +++ test/test/test_cryptodev.h | 1 + test/test/test_cryptodev_aes_test_vectors.h | 93 ++-- test/test/test_cryptodev_blockcipher.c | 9 +- test/test

[dpdk-dev] [PATCH v2 01/16] net/axgbe: add minimal dev init and uninit support

Signed-off-by: Ravi Kumar --- MAINTAINERS | 6 + config/common_base | 6 + drivers/net/Makefile| 1 + drivers/net/axgbe/Makefile | 146 +++ drivers/net/axgbe/axgbe_common.h

[dpdk-dev] [PATCH v2 02/16] net/axgbe: add register map and related macros

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_common.h | 1644 ++ 1 file changed, 1644 insertions(+) diff --git a/drivers/net/axgbe/axgbe_common.h b/drivers/net/axgbe/axgbe_common.h index 168dbb5..294f2e4 100644 --- a/drivers/net/axgbe/axgbe_common.h +

[dpdk-dev] [PATCH v2 03/16] net/axgbe: add phy register map and helper macros

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_phy.h | 314 ++ 1 file changed, 314 insertions(+) create mode 100644 drivers/net/axgbe/axgbe_phy.h diff --git a/drivers/net/axgbe/axgbe_phy.h b/drivers/net/axgbe/axgbe_phy.h new file mode 100644 index

[dpdk-dev] [PATCH v2 04/16] net/axgbe: add structures for MAC initialization and reset

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/Makefile | 1 + drivers/net/axgbe/axgbe_dev.c| 167 +++ drivers/net/axgbe/axgbe_ethdev.c | 301 - drivers/net/axgbe/axgbe_ethdev.h | 349 +++ 4 files cha

[dpdk-dev] [PATCH v2 05/16] net/axgbe: add phy initialization and related apis

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/Makefile | 3 + drivers/net/axgbe/axgbe_dev.c | 188 + drivers/net/axgbe/axgbe_ethdev.c | 11 + drivers/net/axgbe/axgbe_ethdev.h | 172 drivers/net/axgbe/axgbe_i2c.c | 453 + drivers/net/

[dpdk-dev] [PATCH v2 06/16] net/axgbe: add phy programming apis

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_dev.c | 27 + drivers/net/axgbe/axgbe_mdio.c | 963 + drivers/net/axgbe/axgbe_phy_impl.c | 1397 3 files changed, 2387 insertions(+) diff --git a/drivers/net/axgbe/axgbe

[dpdk-dev] [PATCH v2 07/16] net/axgbe: add interrupt handler for autonegotiation

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_ethdev.c | 37 + 1 file changed, 37 insertions(+) diff --git a/drivers/net/axgbe/axgbe_ethdev.c b/drivers/net/axgbe/axgbe_ethdev.c index 0dc424d..daea0b2 100644 --- a/drivers/net/axgbe/axgbe_ethdev.c +++ b/

[dpdk-dev] [PATCH v2 10/16] net/axgbe: add transmit and receive data path apis

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/Makefile | 1 + drivers/net/axgbe/axgbe_ethdev.c | 22 +- drivers/net/axgbe/axgbe_rxtx.c | 429 + drivers/net/axgbe/axgbe_rxtx.h | 19 ++ drivers/net/axgbe/axgbe_rxtx_vec_sse.c |

[dpdk-dev] [PATCH v2 09/16] net/axgbe: add DMA programming and dev start and stop apis

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_dev.c| 844 +++ drivers/net/axgbe/axgbe_ethdev.c | 96 + 2 files changed, 940 insertions(+) diff --git a/drivers/net/axgbe/axgbe_dev.c b/drivers/net/axgbe/axgbe_dev.c index 528241e..a69a078 100644

[dpdk-dev] [PATCH v2 08/16] net/axgbe: add transmit and receive queue setup apis

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/Makefile | 1 + drivers/net/axgbe/axgbe_ethdev.c | 81 + drivers/net/axgbe/axgbe_ethdev.h | 36 drivers/net/axgbe/axgbe_rxtx.c | 363 +++ drivers/net/axgbe/axgbe_rxtx.h | 289 +++

[dpdk-dev] [PATCH v2 13/16] net/axgbe: add configure flow control while link adjustment

Signed-off-by: Ravi Kumar --- drivers/net/axgbe/axgbe_mdio.c | 13 + 1 file changed, 13 insertions(+) diff --git a/drivers/net/axgbe/axgbe_mdio.c b/drivers/net/axgbe/axgbe_mdio.c index 753dde9..07f4087 100644 --- a/drivers/net/axgbe/axgbe_mdio.c +++ b/drivers/net/axgbe/axgbe_mdio.c @

[dpdk-dev] [PATCH v2 14/16] net/axgbe: add promiscuous mode support

Signed-off-by: Ravi Kumar --- doc/guides/nics/axgbe.rst | 2 ++ doc/guides/nics/features/axgbe.ini | 2 ++ drivers/net/axgbe/axgbe_ethdev.c | 48 ++ 3 files changed, 52 insertions(+) diff --git a/doc/guides/nics/axgbe.rst b/doc/guides/nics/axgbe.r

[dpdk-dev] [PATCH v2 12/16] net/axgbe: add link status update

Signed-off-by: Ravi Kumar --- doc/guides/nics/features/axgbe.ini | 1 + drivers/net/axgbe/axgbe_ethdev.c | 33 + 2 files changed, 34 insertions(+) diff --git a/doc/guides/nics/features/axgbe.ini b/doc/guides/nics/features/axgbe.ini index f644128..2dbff18 10064

[dpdk-dev] [PATCH v2 11/16] doc: add documents for AMD axgbe Ethernet PMD

Signed-off-by: Ravi Kumar --- doc/guides/nics/axgbe.rst | 211 + doc/guides/nics/features/axgbe.ini | 14 +++ doc/guides/nics/index.rst | 1 + 3 files changed, 226 insertions(+) create mode 100644 doc/guides/nics/axgbe.rst create mode 100

[dpdk-dev] [PATCH v2 15/16] net/axgbe: add generic transmit and receive status support

Signed-off-by: Ravi Kumar --- doc/guides/nics/axgbe.rst | 1 + doc/guides/nics/features/axgbe.ini | 1 + drivers/net/axgbe/axgbe_ethdev.c | 51 ++ 3 files changed, 53 insertions(+) diff --git a/doc/guides/nics/axgbe.rst b/doc/guides/nics/axgbe.rst

[dpdk-dev] [PATCH v2 16/16] net/axgbe: add support for build 32-bit mode

Signed-off-by: Ravi Kumar --- doc/guides/nics/features/axgbe.ini | 1 + drivers/net/axgbe/axgbe_common.h | 49 ++ drivers/net/axgbe/axgbe_ethdev.c | 10 drivers/net/axgbe/axgbe_ethdev.h | 8 +++ drivers/net/axgbe/axgbe_rxtx.c | 12 +

Re: [dpdk-dev] [PATCH] net/virtio: init MTU in case no control channel

05/01/2018 01:54, zhike wang: > The max_mtu is kept as zero in case no CRTL channel, which leads > to failure when calling virtio_mtu_set(). > > Signed-off-by: zhike wang Please use uppercases in your name: Zhike Wang Thanks

[dpdk-dev] [PATCH] net/virtio: init MTU in case no control channel

From: zhike wang The max_mtu is kept as zero in case no CRTL channel, which leads to failure when calling virtio_mtu_set(). Signed-off-by: Zhike Wang --- drivers/net/virtio/virtio_ethdev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/v

Re: [dpdk-dev] [PATCH v2] net: update licence for network headers

28/12/2017 12:42, Hemant Agrawal: > On 12/22/2017 9:29 PM, Olivier Matz wrote: > > To be compliant with the DPDK licensing guidelines, switch to > > BSD-3-Clause. It can be done safely since the BSD headers from which > > these files derive also exist as a BSD-3-Clause license in FreeBSD. > > > > L

Re: [dpdk-dev] [PATCH 2/2] net: enable IOVA mode for PMDs

Hi Jianfeng, On 10/11/2017 12:33 PM, Jianfeng Tan wrote: If we want to enable IOVA mode, introduced by commit 93878cf0255e ("eal: introduce helper API for IOVA mode"), we need PMDs (for PCI devices) to expose this flag. Signed-off-by: Jianfeng Tan --- drivers/net/e1000/em_ethdev.c | 3 ++-

Re: [dpdk-dev] [PATCH] MAINTAINERS fix style

Any idea when Checkpatch started to enforce this? Looks like it was slipped in recently.. --ignore=MAINTAINERS_STYLE :) On 04/01/2018 23:48, Stephen Hemminger wrote: Checkpatch is complaining because the DPDK MAINTAINERS file style does not match the Linux style. Linux style is to always have

Re: [dpdk-dev] [PATCH 1/2] mempool: indicate the usages of multi memzones

On Tuesday 19 December 2017 04:32 PM, Olivier MATZ wrote: > On Tue, Dec 19, 2017 at 04:16:33PM +0530, Hemant Agrawal wrote: >> Hi Olivier, >> >> On 12/19/2017 3:54 PM, Olivier MATZ wrote: >>> Hi Hemant, >>> >>> On Wed, Dec 06, 2017 at 06:01:12PM +0530, Hemant Agrawal wrote: This is required f

Re: [dpdk-dev] [PATCH] relicense various bits of the dpdk

04/12/2017 16:55, Neil Horman: > +#SPDX-License-Identifier:BSD-3-Clause > +#Copyright(c) 2015 Neil Horman. All rights reserved. > +#Copyright(c) 2017 6WIND S.A. > +#All rights reserved [...] > /*- > - * BSD LICENSE > + * SPDX-License-Identifier: BSD-3-Clause > * >

Re: [dpdk-dev] [PATCH v2 1/2] kni: convert license headers to SPDX tags

19/12/2017 01:05, Ferruh Yigit: > --- a/lib/librte_kni/rte_kni.c > +++ b/lib/librte_kni/rte_kni.c > @@ -1,34 +1,6 @@ > -/*- > - * BSD LICENSE > - * > - * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. > - * All rights reserved. > - * > - * Redistribution and use in source an

Re: [dpdk-dev] [PATCH] bus/fslmc: change the eqcr stashing threshold to 1

On Wednesday 03 January 2018 09:09 PM, Nipun Gupta wrote: Changing the EQCR stashing threshold boosts the performance of l3fwd application on LS2088 by more than 20% as it helps in burst packet processing at the Tx side. CPU is immediately informed about the empty EQCR entries once consumed by th

Re: [dpdk-dev] standardize device identification

-Original Message- From: Thomas Monjalon [mailto:tho...@monjalon.net] Sent: 5. januar 2018 09:40 To: Finn Christensen Cc: dev@dpdk.org; Yuanhan Liu ; Adrien Mazarguil ; Ciara Loftus ; Kevin Traynor ; step...@networkplumber.org; ferruh.yi...@intel.com Su

Re: [dpdk-dev] [PATCH] MAINTAINERS fix style

05/01/2018 11:46, Remy Horton: > Any idea when Checkpatch started to enforce this? Looks like it was > slipped in recently.. commit 628f91a28649d063a048629d9d15b3e5c4dcaa37 Author: Joe Perches Date: Mon Jul 10 15:52:07 2017 -0700 checkpatch: warn when a MAINTAINERS entry isn't [A-Z]:\t

[dpdk-dev] [PATCH] devtools: ignore checkpatch warning for maintainers file

The script checkpatch.pl from Linux is enforcing a tab in the MAINTAINERS file (Linux commit 628f91a28649). It can be ignored in our wrapper checkpatches.sh. Suggested-by: Remy Horton Signed-off-by: Thomas Monjalon --- devtools/checkpatches.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletio

Re: [dpdk-dev] standardize device identification

05/01/2018 12:09, Finn Christensen: > From: Thomas Monjalon > Which property can help to distinguish Napatech ports? > Can you use class=eth,dev_port=X ? > The dev_port property will use /sys/class/net/DEV/dev_port on Linux. Is it > OK for you? > > Actually, what we were thinking o

Re: [dpdk-dev] [PATCH 2/2] net: enable IOVA mode for PMDs

On 01/05/2018 11:32 AM, Maxime Coquelin wrote: Hi Jianfeng, On 10/11/2017 12:33 PM, Jianfeng Tan wrote: If we want to enable IOVA mode, introduced by commit 93878cf0255e ("eal: introduce helper API for IOVA mode"), we need PMDs (for PCI devices) to expose this flag. Signed-off-by: Jianfeng T

Re: [dpdk-dev] [PATCH 2/2] net: enable IOVA mode for PMDs

Hi Maxim, On Friday 05 January 2018 04:02 PM, Maxime Coquelin wrote: > Hi Jianfeng, > > On 10/11/2017 12:33 PM, Jianfeng Tan wrote: >> If we want to enable IOVA mode, introduced by >> commit 93878cf0255e ("eal: introduce helper API for IOVA mode"), >> we need PMDs (for PCI devices) to expose this

Re: [dpdk-dev] [PATCH] net/i40e: fix VSI MAC filter on primary address change

Thank you for the patch! Comments inline. On Wed, Jan 3, 2018 at 5:29 PM, Olivier Matz wrote: > > drivers/net/i40e/i40e_ethdev.c | 29 + > 1 file changed, 29 insertions(+) > > diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ > ethdev.c > index 811c

Re: [dpdk-dev] [PATCH 2/2] net: enable IOVA mode for PMDs

Hi Santosh On 01/05/2018 01:10 PM, santosh wrote: Hi Maxim, On Friday 05 January 2018 04:02 PM, Maxime Coquelin wrote: Hi Jianfeng, On 10/11/2017 12:33 PM, Jianfeng Tan wrote: If we want to enable IOVA mode, introduced by commit 93878cf0255e ("eal: introduce helper API for IOVA mode"), we n

[dpdk-dev] [PATCH 3/5] net/ixgbevf: save IXGBE_VTEIMS to intr->mask for performance.

If dpdk APPs call the rte_eth_dev_rx_intr_enable or rte_eth_dev_rx_intr_disable frequently, and ixgbe vf will read the IXGBE_VTEIMS register everytime. We can optimize the driver function. The patch save the IXGBE_VTEIMS to mask to avoid read frequently. Signed-off-by: Tonghao Zhang --- drivers/

[dpdk-dev] [PATCH 4/5] net/ixgbevf: add check for rte_intr_enable.

When we bind the ixgbevf to vfio and call the rte_eth_dev_rx_intr_enable and rte_eth_dev_rx_intr_disable frequently, the interrupt setting (msi_set_mask_bit) will take more CPU as show below. rte_intr_enable call the ioctl to map the fd to interrupts frequently. perf top: 5.45% [kernel] [k] msi

[dpdk-dev] [PATCH 1/5] net/ixgbevf: unregister irq handler when other interrupts not allowed.

When we bind the ixgbe VF (e.g 82599 card) to igb_uio and enable the rx-interrupt, there will be more than one epoll_wait on intr_handle.fd. One is in "eal-intr-thread" thread, and the others are in the thread which call the "rte_epoll_wait". The problem is that sometiems "eal-intr-thread" thread w

[dpdk-dev] [PATCH 5/5] vhost: add reconnect thread name for client mode.

This patch adds the name for vhost-user reconnect thread. It can help us to know whether the thread is running. Signed-off-by: Tonghao Zhang Signed-off-by: Tonghao Zhang --- lib/librte_vhost/socket.c | 8 1 file changed, 8 insertions(+) diff --git a/lib/librte_vhost/socket.c b/lib/lib

Re: [dpdk-dev] [PATCHv3 0/4] dpdk: enhance EXPERIMENTAL api tagging

04/01/2018 13:56, Neil Horman: > On Sat, Dec 30, 2017 at 12:15:17PM -0500, Neil Horman wrote: > > Thomas- > > I just noticed that the ci tests are failing on the intel compiler, > > which > > makes very little sense to me, as the error is a permission error on a bash > > script that added in

[dpdk-dev] [PATCH 1/5] net/ixgbevf: unregister irq handler when other interrupts not allowed.

When we bind the ixgbe VF (e.g 82599 card) to igb_uio and enable the rx-interrupt, there will be more than one epoll_wait on intr_handle.fd. One is in "eal-intr-thread" thread, and the others are in the thread which call the "rte_epoll_wait". The problem is that sometiems "eal-intr-thread" thread w

[dpdk-dev] [PATCH 2/5] net/ixgbevf: set the inter-interrupt interval for EITR.

Set EITR interval as default. This patch can improve the performance when we enable the rx-intrrupt to process the packets because we hope rx-intrrupt reduce CPU. The 200us value of EITR makes the performance better with the low CPU. Signed-off-by: Tonghao Zhang --- drivers/net/ixgbe/ixgbe_ethd

[dpdk-dev] [PATCH 3/5] net/ixgbevf: save IXGBE_VTEIMS to intr->mask for performance.

If dpdk APPs call the rte_eth_dev_rx_intr_enable or rte_eth_dev_rx_intr_disable frequently, and ixgbe vf will read the IXGBE_VTEIMS register everytime. We can optimize the driver function. The patch save the IXGBE_VTEIMS to mask to avoid read frequently. Signed-off-by: Tonghao Zhang --- drivers/

[dpdk-dev] [PATCH 4/5] net/ixgbevf: add check for rte_intr_enable.

When we bind the ixgbevf to vfio and call the rte_eth_dev_rx_intr_enable and rte_eth_dev_rx_intr_disable frequently, the interrupt setting (msi_set_mask_bit) will take more CPU as show below. rte_intr_enable call the ioctl to map the fd to interrupts frequently. perf top: 5.45% [kernel] [k] msi

[dpdk-dev] [PATCH 5/5] vhost: add reconnect thread name for client mode.

This patch adds the name for vhost-user reconnect thread. It can help us to know whether the thread is running. Signed-off-by: Tonghao Zhang --- lib/librte_vhost/socket.c | 8 1 file changed, 8 insertions(+) diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c index d44a0

Re: [dpdk-dev] standardize device identification

>-Original Message- >From: Thomas Monjalon [mailto:tho...@monjalon.net] >Sent: 5. januar 2018 13:02 >To: Finn Christensen >Cc: dev@dpdk.org; Yuanhan Liu ; Adrien Mazarguil >; Ciara Loftus ; Kevin >Traynor ; step...@networkplumber.org; >ferruh.yi...@intel.com >Subject: Re: [dpdk-dev] stand

Re: [dpdk-dev] [RFC 01/14] ethdev: add link status read/write functions

Stephen, Qiming was suggesting a name change for the functions. What do you think? 13/10/2017 17:12, Stephen Hemminger: > On Wed, 11 Oct 2017 08:32:12 + > "Yang, Qiming" wrote: > > > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger > > > Sent: Saturday, July 15, 2017

Re: [dpdk-dev] [RFC 00/14] link status API improvement and bugfixes

14/07/2017 20:30, Stephen Hemminger: > While writing new driver, I noticed a lot of unnecessary duplication of > code in drivers for handling the eth_dev link status information. While > consolidating this, it also became obvious that several drivers have > bugs in this are because they don't retur

Re: [dpdk-dev] [RFC 02/14] virtio: use eth_link_read/write (and bug fix)

17/07/2017 18:28, Stephen Hemminger: > On Mon, 17 Jul 2017 19:14:16 +0300 > Andrew Rybchenko wrote: > > > On 07/17/2017 07:01 PM, Stephen Hemminger wrote: > > > On Sun, 16 Jul 2017 15:33:26 +0300 > > > Andrew Rybchenko wrote: > > > > > >>> + link.link_autoneg = ETH_LINK_SPEED_FIXED; >

Re: [dpdk-dev] [PATCH] devtools: ignore checkpatch warning for maintainers file

On 05/01/2018 11:43, Thomas Monjalon wrote: The script checkpatch.pl from Linux is enforcing a tab in the MAINTAINERS file (Linux commit 628f91a28649). It can be ignored in our wrapper checkpatches.sh. Suggested-by: Remy Horton Signed-off-by: Thomas Monjalon --- devtools/checkpatches.sh | 3

Re: [dpdk-dev] standardize device identification

05/01/2018 15:14, Finn Christensen: > From: Thomas Monjalon [mailto:tho...@monjalon.net] > >05/01/2018 12:09, Finn Christensen: > >> From: Thomas Monjalon > >> Which property can help to distinguish Napatech ports? > >> Can you use class=eth,dev_port=X ? > >> The dev_port property will

Re: [dpdk-dev] [PATCHv3 0/4] dpdk: enhance EXPERIMENTAL api tagging

On Fri, Jan 05, 2018 at 03:08:52PM +0100, Thomas Monjalon wrote: > 04/01/2018 13:56, Neil Horman: > > On Sat, Dec 30, 2017 at 12:15:17PM -0500, Neil Horman wrote: > > > Thomas- > > > I just noticed that the ci tests are failing on the intel compiler, > > > which > > > makes very little sense

Re: [dpdk-dev] [PATCH] net/mlx4: verify Tx max sges

On Thu, Jan 04, 2018 at 06:12:03PM +0200, Moti Haimovsky wrote: > Max number of Tx scatter-gather entries is a property of the device > and is queried at init. This value was not changed in a while and > most probably will not be changed in the future, Therefore and > in order to enhance Tx perform

[dpdk-dev] [PATCH] ethdev: fix link autonegotiation value

There are 3 kind of link data in ethdev: - capabilities (rte_eth_dev_info) - configuration (rte_eth_conf) - status (rte_eth_link) A bit-field is used for capabilities (rte_eth_dev_info.speed_capa) and configuration (rte_eth_conf.link_speeds). Bits are defined in ETH_LINK_SP

Re: [dpdk-dev] [PATCH v5 3/3] net/virtio: support GUEST ANNOUNCE

On Fri, Jan 05, 2018 at 08:46:57AM -0800, Xiao Wang wrote: [...] > +static int > +make_rarp_packet(struct rte_mbuf *rarp_mbuf, const struct ether_addr *mac) > +{ > + struct ether_hdr *eth_hdr; > + struct arp_hdr *rarp; Please just use one space between the type and var instead of two. >

Re: [dpdk-dev] [PATCH v5 2/3] net/virtio: add packet injection method

On Fri, Jan 05, 2018 at 08:46:56AM -0800, Xiao Wang wrote: [...] > +/* > + * Recover hw state to let worker thread continue. > + */ > +void > +virtio_dev_resume(struct rte_eth_dev *dev) > +{ > + struct virtio_hw *hw = dev->data->dev_private; > + > + hw->started = 1; > + rte_spinlock_unl

Re: [dpdk-dev] [PATCH v2 04/10] app/testpmd: convert to new Ethdev Tx offloads API

-- Oryginal message -- Ethdev Tx offloads API has changed since: commit cba7f53b717d ("ethdev: introduce Tx queue offloads API") Convert the application to use the new API. This patch mandates the port to be stopped when configure the Tx offloads. This is because the PMD must be aware to the

Re: [dpdk-dev] [RFC 01/14] ethdev: add link status read/write functions

On Fri, 05 Jan 2018 15:24:48 +0100 Thomas Monjalon wrote: > Stephen, > Qiming was suggesting a name change for the functions. > What do you think? > > 13/10/2017 17:12, Stephen Hemminger: > > On Wed, 11 Oct 2017 08:32:12 + > > "Yang, Qiming" wrote: > > > > > > From: dev [mailto:dev-boun.

  1   2   >