This commit adds vmxnet3 TSO support.
Verified with test-pmd (set fwd csum) that both tso and
non-tso pkts can be successfully transmitted and all
segmentes for a tso pkt are correct on the receiver side.
Signed-off-by: Yong Wang <yongwang@vmware.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Tx data ring support was removed in a previous change that
added multi-seg transmit. This change adds it back.
According to the original commit (2e849373), 64B pkt
rate with l2fwd improved by ~20% on an Ivy Bridge
server at which point we start to hit some bottleneck
on the rx side.
I also re-did the same test on a different setup (Haswell
processor, ~2.3GHz clock rate) on top of the master
and still observed ~17% performance gains.
Fixes: 7ba5de417e ("vmxnet3: support multi-segment transmit")
Signed-off-by: Yong Wang <yongwang@vmware.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
All the error checks in virtqueue_enqueue_xmit are already done
by the caller. Therefore they can be removed to improve performance.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
Virtio supports a feature that allows sender to put transmit
header prepended to data. It requires that the mbuf be writeable, correct
alignment, and the feature has been negotiatied. If all this works out,
then it will be the optimum way to transmit a single segment packet.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
The virtio ring in QEMU/KVM is usually limited to 256 entries
and the normal way that virtio driver was queuing mbufs required
nsegs + 1 ring elements. By using the indirect ring element feature
if available, each packet will take only one ring slot even for
multi-segment packets.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Igor Ryzhov <iryzhov@nfware.com>
Acked-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Applied with coding standards fixes:
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
The virtio_net_hdr desc all pointed to the same buffer. It doesn't cause
issue because in the simple TX mode we don't use the header. This patch
makes the header desc point to different buffer.
Fixes: b4ae9c505f ("virtio: optimize ring layout")
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This initialisation of nb_rx_queues and nb_tx_queues has been removed
from eth_virtio_dev_init.
The nb_rx_queues and nb_tx_queues were being initialised in
eth_virtio_dev_init before the tx_queues and rx_queues arrays were
allocated.
The arrays are allocated when the ethdev port is configured and the
nb_tx_queues and nb_rx_queues are initialised.
If any of the following functions were called before the ethdev
port was configured there was a segmentation fault because
rx_queues and tx_queues were NULL:
rte_eth_stats_get
rte_eth_stats_reset
rte_eth_xstats_get
rte_eth_xstats_reset
Fixes: 823ad64795 ("virtio: support multiple queues")
Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Fix the issue that virtio device cannot be started after stopped.
The field, hw->started, should be changed by virtio_dev_start/stop instead
of virtio_dev_close.
Fixes: a85786dc81 ("virtio: fix states handling during initialization")
Reported-by: Pavel Fedin <p.fedin@samsung.com>
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Tested-by: Pavel Fedin <p.fedin@samsung.com>
Mmap PCI resource file and add inline functions for reading from and
writing to PCI resource address space.
Add description of IBUF and OBUF address space.
Add configuration option for setting which firmware type will be used.
Right address space values for IBUFs and OBUFs offsets are used
according to configuration option CONFIG_RTE_LIBRTE_PMD_SZEDATA2_AS.
Setting link up/down and getting info about link status is done through
mmapped PCI resource address space.
Signed-off-by: Matej Vido <vido@cesnet.cz>
PMD was of type PMD_VDEV which means that PCI device is not recognised
automatically during EAL initialization, but it has to be created by
EAL option --vdev.
Now, PMD is of type PMD_PDEV which means that PCI device is probed
and recognised during EAL initialization automatically.
Path to szedata2 device file is matched with device and the count
of available RX and TX DMA channels is found out during device
initialization.
Initialization, starting and stopping of queues is changed to better
correspond with Ethernet device API model. Function callbacks
(rx|tx)_queue_(start|stop) are added. Unnecessary items are removed
from ethernet device private data structure.
Signed-off-by: Matej Vido <vido@cesnet.cz>
When using start-stop functionality the per queue fields need to
be properly reset.
Fixes: b812daadad ("nfp: add Rx and Tx")
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Even with tx checksum offload available, do not set the flag by default.
Fixes: b812daadad ("nfp: add Rx and Tx")
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
The mbuf ol_flags field was changed to uin64_t with DPDK version 1.8
Fixes: b812daadad ("nfp: add Rx and Tx")
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
The file sys/io.h was included but it can be unavailable in some
non-x86 toolchains.
As others system includes in the file nfp_net.c, it seems useless,
so the easy fix is to remove them.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Change rxq_cq_to_ol_flags() to set checksum flags according to packet type,
so for non L3/L4 packets the mbuf chksum_bad flags will not be set.
Fixes: 67fa62bc67 ("mlx5: support checksum offload")
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
RSS configuration should not be freed when priv is NULL.
Fixes: 2f97422e77 ("mlx5: support RSS hash update and get")
Signed-off-by: Or Ami <ora@mellanox.com>
The first and last memory pool elements are usually cache-aligned but not
page-aligned, particularly when using huge pages.
Hardware performance can be improved significantly by registering memory
regions starting and ending on page boundaries.
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Avoid dereferencing pointers twice to get to fast Verbs functions by
storing them directly in RX/TX queue structures.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Allows HW to strip the 802.1Q header from incoming frames and report it
through the mbuf structure.
This feature requires MLNX_OFED >= 3.2.
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Upcoming flow director support will reuse this function to generate filter
rules.
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Until now, broadcast frames were handled like unicast. Moving the related
flow to the special flows table frees up the related unicast MAC entry.
The same method is used to handle IPv6 multicast frames.
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Merge redundant code by adding a static initialization table to manage
promiscuous and allmulticast (special) flows.
New function priv_rehash_flows() implements the logic to enable/disable
relevant flows in one place from any context.
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
In the documentation it is specified that the hardware only supports a
number of RX queues if it is a power of 2.
Since ibv_exp_create_qp may not return an error when the number of
queues is unsupported by hardware, sanitize the value in dev_configure.
Signed-off-by: Robin Jarry <robin.jarry@6wind.com>
When compiling with clang 3.6, the mlx4 driver gives the following error
message about an unneeded function.
CC mlx4.o
.../drivers/net/mlx4/mlx4.c:136:20: fatal error: function
'wr_id_t_check' is not needed and will not be emitted
[-Wunneeded-internal-declaration]
static inline void wr_id_t_check(void)
^
1 error generated.
The function is to compile-time check the size of wr_id_t, so use
the standard DPDK BUILD_BUG_ON macro to do so in the init function
instead.
Fixes: 7fae69eeff ("mlx4: new poll mode driver")
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
This patch enables reading sglort (global resource tag) info into the
mbuf for RX and inserting an FTAG (Fabric Tag) at the beginning of the
packet for TX. The vlan_tci_outer field selected from rte_mbuf structure
for sglort is not used in fm10k now.
In FTAG based forwarding mode, the switch will forward packets according
to glort info in FTAG rather than mac and vlan table.
To activate this feature, user needs to pass a devargs parameter to eal
for fm10k device like "-w 0000:84:00.0,enable_ftag=1". Currently this
feature is supported only on PF, because FM10K_PFVTCTL register is
read-only for VF.
Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Remove the unused element request_lport_map in struct fm10k_mac_ops.
Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Some cleanups to better reflect the code that was actually pushed out to
the upstream Linux community.
Among the above cleanups, a few macros such as FM10K_RXINT_TIMER_SHIFT are
removed, but they are needed in dpdk/fm10k, so we have to put all these
necessary macros into fm10k_osdep.h.
Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
Per comments from an upstream kernel patch, and looking at how TLV
LE_STRUCT code works, we actually want these structures to be 4byte
aligned, not 1byte aligned.
In practice, 1byte alignment has worked so far because all our
structures end up being a multiple of 4. But if a future TLV
structure were added that had a u8 or similar sticking on the end things
would break. Fix this by using 4byte alignment which will prevent the
TLV LE_STRUCT code from breaking. Update the comment explaining that we
need 4byte alignment of our structures.
Fixes: 925c862cbc ("fm10k/base: pack TLV overlay structures")
Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
The comment for fm10k_iov_msg_lport_state_pf was changed during
review of kernel driver, and the new wording is slightly clearer.
Re-write the comment in base code based on this new wording.
Fix a number of mailbox comment issues with function header comments,
lower-case acronyms (i.e. FIFO, TLV), incorrect function names in
DEBUGFUNC(), duplicate comments and a stubbed-out header comment for
fm10k_sm_mbx_init.
Signed-off-by: Wang Xiao W <xiao.w.wang@intel.com>
Tested-by: Heng Ding <hengx.ding@intel.com>
Acked-by: Jing Chen <jing.d.chen@intel.com>
