From aab0c291a90f701b60f8c9a88cbcc265cba0ec8b Mon Sep 17 00:00:00 2001 From: Christian Ehrhardt Date: Thu, 8 Jun 2017 09:46:51 -0600 Subject: Imported Upstream version 16.11.2 Change-Id: I947038e46a2c747296dc7aa7522239733ca2f659 Signed-off-by: Christian Ehrhardt --- doc/guides/cryptodevs/qat.rst | 1 + doc/guides/nics/bnx2x.rst | 6 +- doc/guides/nics/thunderx.rst | 2 +- doc/guides/rel_notes/release_16_11.rst | 121 ++++++++++++++++++++++++++++ doc/guides/testpmd_app_ug/run_app.rst | 4 +- doc/guides/testpmd_app_ug/testpmd_funcs.rst | 4 +- 6 files changed, 131 insertions(+), 7 deletions(-) (limited to 'doc') diff --git a/doc/guides/cryptodevs/qat.rst b/doc/guides/cryptodevs/qat.rst index 52a9ae35..a7b28eb9 100644 --- a/doc/guides/cryptodevs/qat.rst +++ b/doc/guides/cryptodevs/qat.rst @@ -80,6 +80,7 @@ Limitations * SNOW 3G (UEA2) and KASUMI (F8) supported only if cipher length, cipher offset fields are byte-aligned. * SNOW 3G (UIA2) and KASUMI (F9) supported only if hash length, hash offset fields are byte-aligned. * No BSD support as BSD QAT kernel driver not available. +* Maximum additional authenticated data (AAD) for GCM is 240 bytes long. Installation diff --git a/doc/guides/nics/bnx2x.rst b/doc/guides/nics/bnx2x.rst index 6d1768a5..2e34942d 100644 --- a/doc/guides/nics/bnx2x.rst +++ b/doc/guides/nics/bnx2x.rst @@ -96,9 +96,11 @@ Config File Options The following options can be modified in the ``.config`` file. Please note that enabling debugging options may affect system performance. -- ``CONFIG_RTE_LIBRTE_BNX2X_PMD`` (default **y**) +- ``CONFIG_RTE_LIBRTE_BNX2X_PMD`` (default **n**) - Toggle compilation of bnx2x driver. + Toggle compilation of bnx2x driver. To use bnx2x PMD set this config parameter + to 'y'. Also, in order for firmware binary to load user will need zlib devel + package installed. - ``CONFIG_RTE_LIBRTE_BNX2X_DEBUG`` (default **n**) diff --git a/doc/guides/nics/thunderx.rst b/doc/guides/nics/thunderx.rst index 187c9a4a..b12cc8e3 100644 --- a/doc/guides/nics/thunderx.rst +++ b/doc/guides/nics/thunderx.rst @@ -156,7 +156,7 @@ managed by ``librte_pmd_thunderx_nicvf`` in the Linux operating system. .. code-block:: console ./arm64-thunderx-linuxapp-gcc/app/testpmd -c 0xf -n 4 -w 0002:01:00.2 \ - -- -i --disable-hw-vlan-filter --crc-strip --no-flush-rx \ + -- -i --disable-hw-vlan-filter --no-flush-rx \ --port-topology=loop Example output: diff --git a/doc/guides/rel_notes/release_16_11.rst b/doc/guides/rel_notes/release_16_11.rst index fbf2e368..85972b17 100644 --- a/doc/guides/rel_notes/release_16_11.rst +++ b/doc/guides/rel_notes/release_16_11.rst @@ -708,3 +708,124 @@ Fixes in 16.11 LTS Release * vhost: fix guest/host physical address mapping * vhost: fix long stall of negotiation * vhost: fix memory leak + +16.11.2 +~~~~~~~ + +* app/testpmd: fix TC mapping in DCB init config +* app/testpmd: fix crash at mbuf pool creation +* app/testpmd: fix exit without freeing resources +* app/testpmd: fix init config for multi-queue mode +* app/testpmd: fix number of mbufs in pool +* app: enable HW CRC strip by default +* crypto/openssl: fix AAD capabilities for AES-GCM +* crypto/openssl: fix AES-GCM capability +* crypto/qat: fix AES-GCM authentication length +* crypto/qat: fix IV zero physical address +* crypto/qat: fix dequeue statistics +* cryptodev: fix API digest length comments +* doc: add limitation of AAD size to QAT guide +* doc: explain zlib dependency for bnx2x +* eal/linux: fix build with glibc 2.25 +* eal: fix debug macro redefinition +* examples/ip_fragmentation: fix check of packet type +* examples/l2fwd-crypto: fix AEAD tests when AAD is zero +* examples/l2fwd-crypto: fix packets array index +* examples/l2fwd-crypto: fix padding calculation +* examples/l3fwd-power: fix Rx descriptor size +* examples/l3fwd-power: fix handling no Rx queue +* examples/load_balancer: fix Tx flush +* examples/multi_process: fix timer update +* examples/performance-thread: fix build on FreeBSD +* examples/performance-thread: fix build on FreeBSD 10.0 +* examples/performance-thread: fix compilation on Suse 11 SP2 +* examples/quota_watermark: fix requirement for 2M pages +* examples: enable HW CRC strip by default +* examples: fix build clean on FreeBSD +* kni: fix build with kernel 4.11 +* kni: fix crash caused by freeing mempool +* kni: fix possible memory leak +* mbuf: fix missing includes in exported header +* mk: fix lib filtering when linking app +* mk: fix quoting for ARM mtune argument +* mk: fix shell errors when building with clang +* net/bnx2x: fix transmit queue free threshold +* net/bonding: allow configuring jumbo frames without slaves +* net/bonding: fix updating slave link status +* net/cxgbe: fix possible null pointer dereference +* net/e1000/base: fix multicast setting in VF +* net/ena: cleanup if refilling of Rx descriptors fails +* net/ena: fix Rx descriptors allocation +* net/ena: fix delayed cleanup of Rx descriptors +* net/ena: fix return of hash control flushing +* net/fm10k: fix memory overflow in 32-bit SSE Rx +* net/fm10k: fix pointer cast +* net/i40e/base: fix potential out of bound array access +* net/i40e: add missing 25G link speed +* net/i40e: ensure vector mode is not used with QinQ +* net/i40e: fix TC bitmap of VEB +* net/i40e: fix VF link speed +* net/i40e: fix VF link status update +* net/i40e: fix allocation check +* net/i40e: fix compile error +* net/i40e: fix hash input set on X722 +* net/i40e: fix incorrect packet index reference +* net/i40e: fix mbuf alloc failed counter +* net/i40e: fix memory overflow in 32-bit SSE Rx +* net/i40e: fix setup when bulk is disabled +* net/igb: fix VF MAC address setting +* net/igb: fix VF MAC address setting +* net/ixgbe/base: fix build error +* net/ixgbe: fix Rx queue blocking issue +* net/ixgbe: fix TC bandwidth setting +* net/ixgbe: fix VF Rx mode for allmulticast disabled +* net/ixgbe: fix all queues drop setting of DCB +* net/ixgbe: fix memory overflow in 32-bit SSE Rx +* net/ixgbe: fix multi-queue mode check in SRIOV mode +* net/ixgbe: fix setting MTU on stopped device +* net/ixgbevf: set xstats id values +* net/mlx4: fix Rx after mbuf alloc failure +* net/mlx4: fix returned values upon failed probing +* net/mlx4: update link status upon probing with LSC +* net/mlx5: fix Tx when first segment size is too short +* net/mlx5: fix VLAN stripping indication +* net/mlx5: fix an uninitialized variable +* net/mlx5: fix returned values upon failed probing +* net/mlx5: fix reusing Rx/Tx queues +* net/mlx5: fix supported packets types +* net/nfp: fix packet/data length conversion +* net/pcap: fix using mbuf after freeing it +* net/qede/base: fix find zero bit macro +* net/qede: fix FW version string for VF +* net/qede: fix default MAC address handling +* net/qede: fix fastpath rings reset phase +* net/qede: fix missing UDP protocol in RSS offload types +* net/thunderx: fix 32-bit build +* net/thunderx: fix build on FreeBSD +* net/thunderx: fix deadlock in Rx path +* net/thunderx: fix stats access out of bounds +* net/virtio-user: fix address on 32-bit system +* net/virtio-user: fix overflow +* net/virtio: disable LSC interrupt if MSIX not enabled +* net/virtio: fix MSI-X for modern devices +* net/virtio: fix crash when closing twice +* net/virtio: fix link status always being up +* net/virtio: fix link status always down +* net/virtio: fix queue notify +* net/vmxnet3: fix build with gcc 7 +* net/vmxnet3: fix queue size changes +* net: fix stripped VLAN flag for offload emulation +* nic_uio: fix device binding at boot +* pci: fix device registration on FreeBSD +* test/cmdline: fix missing break in switch +* test/mempool: free mempool on exit +* test: enable HW CRC strip by default +* vfio: fix disabling INTx +* vfio: fix secondary process start +* vhost: change log levels in client mode +* vhost: fix dequeue zero copy +* vhost: fix false sharing +* vhost: fix fd leaks for vhost-user server mode +* vhost: fix max queues +* vhost: fix multiple queue not enabled for old kernels +* vhost: fix use after free diff --git a/doc/guides/testpmd_app_ug/run_app.rst b/doc/guides/testpmd_app_ug/run_app.rst index d7c51209..ac7d4582 100644 --- a/doc/guides/testpmd_app_ug/run_app.rst +++ b/doc/guides/testpmd_app_ug/run_app.rst @@ -281,9 +281,9 @@ The commandline options are: In perfect filter mode, when a rule is added with queue = -1, the packet will be enqueued into the RX drop-queue. If the drop-queue does not exist, the packet is dropped. The default value is N=127. -* ``--crc-strip`` +* ``--disable-crc-strip`` - Enable hardware CRC stripping. + Disable hardware CRC stripping. * ``--enable-lro`` diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/doc/guides/testpmd_app_ug/testpmd_funcs.rst index f1c269a3..70d2e4d7 100644 --- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst +++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst @@ -1257,9 +1257,9 @@ Set hardware CRC stripping on or off for all ports:: testpmd> port config all crc-strip (on|off) -CRC stripping is off by default. +CRC stripping is on by default. -The ``on`` option is equivalent to the ``--crc-strip`` command-line option. +The ``off`` option is equivalent to the ``--disable-crc-strip`` command-line option. port config - scatter ~~~~~~~~~~~~~~~~~~~~~~~ -- cgit 1.2.3-korg