Dana Vardi [Thu, 1 Jul 2021 06:58:12 +0000 (09:58 +0300)]
crypto/mvsam: fix AES-GCM session parameters
For AEAD session and AES-GCM mode, IV offset will
set to include the Nonce.
In addition, the following operations order will define:
first encryption and then authentication.
Rebecca Troy [Wed, 30 Jun 2021 15:29:39 +0000 (15:29 +0000)]
test/crypto: rename slave to worker
Modifies the scheduler tests in the crypto unit test suite
to replace the usage of the word 'slave' with the more
appropriate word 'worker'.
The scheduler test functions were modified as follows:
test_scheduler_attach_slave_op is now called
test_scheduler_attach_worker_op,
test_scheduler_detach_slave_op is
test_scheduler_detach_worker_op.
Kai Ji [Tue, 29 Jun 2021 15:19:07 +0000 (16:19 +0100)]
crypto/aesni_gcm: fix performance on some AVX512 CPUs
This patch fixes the aesni_gcm performance issue on systems with AVX512
CPU flag presented but with VAES CPU flag missing, such as Skylake.
Fixes: 81fe96a0cece ("crypto/aesni_gcm: use architecture independent API") Cc: stable@dpdk.org Signed-off-by: Kai Ji <kai.ji@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Fan Zhang [Wed, 23 Jun 2021 16:20:15 +0000 (17:20 +0100)]
doc: update dependencies for SW crypto PMDs
This patch updates the dependency requirement information
for aesni-gcm, aesni-mb, snow3g, zuc, and kasumi PMDs. Previously
building these PMDs with Make will fail when the system is
installed intel-ipsec-mb library version 1.0 or newer.
Since Make build system is deprecated already, instead of fixing
the issue the documentation is updated to state it.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Add missing rte_mbuf size in mempool allocation for
out-of-place operation.
Fixes: bf9d6702eca9 ("app/crypto-perf: use single mempool") Cc: stable@dpdk.org Signed-off-by: Kai Ji <kai.ji@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Feifei Wang [Fri, 21 May 2021 02:00:04 +0000 (10:00 +0800)]
crypto/qat: fix Arm build with special memcpy
In Arm platform, when "RTE_ARCH_ARM64_MEMCPY" is set as true, gcc will
report variable uninitialized warning:
../drivers/crypto/qat/qat_sym_session.c: In function ‘partial_hash_compute’:
../lib/eal/include/generic/rte_byteorder.h:241:24: warning:
‘<U35a0>’ may be used uninitialized in this function
[-Wmaybe-uninitialized]
241 | #define rte_bswap32(x) __builtin_bswap32(x)
...
This is because "digest" will be initialized by "rte_memcpy" function
rather than "memcpy" if "RTE_ARCH_ARM64_MEMCPY" is set as true.
Furthermore, 'rte_memcpy' will initialize 'digest' with two steps
by invoking rte_mov_x functions. For example:
Huisong Li [Wed, 28 Apr 2021 08:36:59 +0000 (16:36 +0800)]
app/testpmd: change port link speed without stopping all
When we use the following cmd to modify the link speed of specified
port: "port config <port_id> speed xxx duplex xxx", we have to stop
all ports. It's not necessary.
Fixes: 82113036e4e5 ("ethdev: redesign link speed config") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com> Acked-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Xiaoyun Li <xiaoyun.li@intel.com>
Jan Viktorin [Wed, 23 Jun 2021 09:18:25 +0000 (11:18 +0200)]
ethdev: fix doc of flow action
The struct rte_flow_action was missing from DPDK API documentation.
Fixes: 3850cf0c8c37 ("ethdev: add tunnel encap/decap actions") Cc: stable@dpdk.org Signed-off-by: Jan Viktorin <viktorin@cesnet.cz> Acked-by: Ori Kam <orika@nvidia.com> Acked-by: Aman Deep Singh <aman.deep.singh@intel.com>
Huisong Li [Mon, 21 Jun 2021 07:38:45 +0000 (15:38 +0800)]
net/hns3: fix traffic management
In a multi-TC scenario, if the length of packets destined for different
TCs is different, for example, 64B and 1500B packets destined for TC0 and
TC1 respectively. There is a problem that the bandwidth of the TC to which
large packets are sent is preempted by the TC to which small packets are
sent on the Kunpeng 920 network engine. As a result, the TC bandwidth
accuracy is inaccurate.
To solve this problem, this patch made the following adjustments:
1/ During initialization, firmware reports the capability bit indicating
whether the TM function is supported.
2/ The command word for configuring TC and port rate limiting is added,
instead of reusing the existing command word. And firmware configured
to the correct module.
3/ When the PF driver is loaded, firmware completes the default
initialization of the TC and port.
Fixes: c09c7847d892 ("net/hns3: support traffic management") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Heinrich Kuhn [Wed, 9 Jun 2021 14:08:14 +0000 (16:08 +0200)]
net/nfp: fix multi-process PF probing
This patch creates a new function for handling PF probing of a secondary
process. A CPP handle is obtained for the CPP bridge service and the
service itself is also registered during secondary process
initialization. DPDK services aren't shared between processes so it is
not enough to only have the primary register the service if it is also
needed in a secondary process. This implies that both the primary and
secondary will have their own copy of the bridge service.
Fixes: 5e15e799d697 ("net/nfp: create separate entity for PF device") Cc: stable@dpdk.org Signed-off-by: Heinrich Kuhn <heinrich.kuhn@netronome.com> Signed-off-by: Simon Horman <simon.horman@corigine.com>
Heinrich Kuhn [Wed, 9 Jun 2021 14:08:13 +0000 (16:08 +0200)]
net/nfp: improve PF probing logic
When using rte_eth_dev_pci_generic_probe() during probing a
rte_eth_dev will be created with the name field corresponding to the PCI
address of the device. NFP4000/6000 devices only have a single PF (but
potentially multiple physical ports). This means that in a simple two
port example the rte_eth_devices[] array will be populated with two
devices: 0000:02:00.0 and 0000:02:00.0_port1. This is inconsistent and
not ideal. It will also cause issues when a secondary process tries to
attach to these ports.
This patch removes the use of rte_eth_dev_pci_generic_probe() and
allocates eth_dev's for each physical port during PF initialization,
giving them more consistent names.
Fixes: 5e15e799d697 ("net/nfp: create separate entity for PF device") Cc: stable@dpdk.org Signed-off-by: Heinrich Kuhn <heinrich.kuhn@netronome.com> Signed-off-by: Simon Horman <simon.horman@corigine.com>
Jie Zhou [Tue, 29 Jun 2021 20:50:21 +0000 (13:50 -0700)]
app/testpmd: disable flow director functions if unneeded
Function print_fdir_mask and print_fdir_flex_payload are only called
when either i40e or ixgbe presents. Extend existing #if defined to
include these two functions, to remove "unused function" compilation
warning.
Signed-off-by: Jie Zhou <jizh@linux.microsoft.com> Acked-by: Tal Shnaiderman <talshn@nvidia.com> Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Jie Zhou [Tue, 29 Jun 2021 20:50:20 +0000 (13:50 -0700)]
app/testpmd: replace POSIX-specific code
- Make printf format OS independent
- Replace htons with RTE_BE16
- Replace POSIX specific inet_aton with OS independent inet_pton
- Replace sleep with rte_delay_us_sleep
- Replace random with rte_rand
- #ifndef mman related code for now
- Fix header inclusion
- Include rte_os_shim.h in testpmd.h
- Remove redundant headers
Signed-off-by: Jie Zhou <jizh@linux.microsoft.com> Acked-by: Tal Shnaiderman <talshn@nvidia.com> Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Jie Zhou [Tue, 29 Jun 2021 20:50:19 +0000 (13:50 -0700)]
app/testpmd: fix type of FEC mode parsing output
Passing an uint32_t pointer to an enum pointer parameter causes
pointer-sign warning on Windows (converts between pointers to
integer types with different sign), since enum is implicitly
converted to int on Windows.
And the current enum pointer parameter of that function is actually
misleading and should be fixed as an uint32_t pointer parameter.
Fixes: b19da32e3151 ("app/testpmd: add FEC command") Cc: stable@dpdk.org Signed-off-by: Jie Zhou <jizh@linux.microsoft.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Olivier Matz [Wed, 30 Jun 2021 13:51:57 +0000 (15:51 +0200)]
net: introduce functions to verify L4 checksums
Since commit d5df2ae0428a ("net: fix unneeded replacement of TCP
checksum 0"), the functions rte_ipv4_udptcp_cksum() and
rte_ipv6_udptcp_cksum() can return either 0x0000 or 0xffff when used to
verify a packet containing a valid checksum.
Since these functions should be used to calculate the checksum to set in
a packet, introduce 2 new helpers for checksum verification. They return
0 if the checksum is valid in the packet.
Olivier Matz [Wed, 30 Jun 2021 13:51:56 +0000 (15:51 +0200)]
net/tap: fix Rx checksum flags on TCP packets
Since commit d5df2ae0428a ("net: fix unneeded replacement of TCP
checksum 0"), the functions rte_ipv4_udptcp_cksum() or
rte_ipv6_udptcp_cksum() can return either 0x0000 or 0xffff when used to
verify a packet containing a valid checksum.
This new behavior broke the checksum verification in tap driver for TCP
packets: these packets are marked with PKT_RX_L4_CKSUM_BAD.
Fix this by checking the 2 possible values. A next commit will introduce
a checksum verification helper to simplify this a bit.
Fixes: d5df2ae0428a ("net: fix unneeded replacement of TCP checksum 0") Cc: stable@dpdk.org Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
net/cxgbe: add MAC match-all to track promiscuous traffic
Chelsio T6 ASIC doesn't track Rx promisc traffic dropped due to lack
of Rx buffers and hence the imissed counter doesn't increment. Add
support for RAW MAC filter to insert a wildcard matchall rule at
the end of MPS TCAM to make MPS track the promisc traffic. This
rule will only be added/removed when promisc mode is turned on/off
on the interface.
Chengwen Feng [Tue, 15 Jun 2021 01:34:29 +0000 (09:34 +0800)]
net/hns3: support Tx push quick doorbell for performance
Kunpeng 930 support Tx push mode which could improve performance.
It works like below:
1. Add PCIe bar45 which support driver direct write the Tx descriptor
or tail reg to it.
2. Support three operations: a) direct write one Tx descriptor, b)
direct write two Tx descriptors, c) direct write tail reg.
3. The original tail reg located at bar23, the above bar45 tail reg
could provide better bandwidth from the hardware perspective.
The hns3 driver only support direct write tail reg (also have the name
of quick doorbell), the detail:
Considering compatibility, firmware will report Tx push capa if the
hardware support it.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Huisong Li [Sun, 13 Jun 2021 02:31:55 +0000 (10:31 +0800)]
net/hns3: fix maximum queues on configuration failure
The "cfg_max_queues" maintains configured max queue numbers from user,
and is equal to the maximum of "nb_rx_queues" and "nb_tx_queues" in
"dev->data".
From the ethdev layer framework, "nb_rx/tx_queues" in "dev->data" were set
to zero in rte_eth_dev_configure() if ops.dev_configure in PMD fails to be
executed, In addition, if ops.dev_configure in HNS3 PMD failed, the fake
queues are also cleared on a device that does not support independent Rx/Tx
queues.
Therefore, the "cfg_max_queues" should be also set to zero when
dev_configure fails.
Fixes: fa29fe45a7b4 ("net/hns3: support queue start and stop") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Huisong Li [Sun, 13 Jun 2021 02:31:53 +0000 (10:31 +0800)]
net/hns3: fix fake queue rollback
When the device supports independent Rx/Tx queues, fake queues do not need
to be created in unequal Rx/Tx queues case. However, dev_configure fails
to be executed on the device supported independent Rx/Tx queues, the
current rollback code logic contains the fake queue. As a result, the fake
queue is created. When dev_configure is successfully called again, these
fake queues still exists and are configured to the hardware.
Fixes: fa29fe45a7b4 ("net/hns3: support queue start and stop") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Huisong Li [Sun, 13 Jun 2021 02:31:52 +0000 (10:31 +0800)]
net/hns3: fix delay for waiting to stop Rx/Tx
When the primary process executes dev_stop or is being reset, the packet
sending and receiving functions is changed. In this moment, the primary
process requests secondary processes to change their Rx/Tx functions, and
delays a period of time in case of crashes when queues are still in use.
The delay time depends on the number of queues actually used, instead of
the maximum number of queues supported by the device.
Fixes: 23d4b61fee5d ("net/hns3: support multiple process") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
git.droids-corp.org / dpdk.git / log