There is a corner case in which driver won't post
receive buffers when driver has processed all received packets
in single loop (i.e. hw_consumer == sw_consumer) and then
HW will start dropping packets since it did not see new receive
buffers posted.
This corner case is seen when size of Rx ring is less than or equals
Rx packet burst count for dev->rx_pkt_burst().
Fixes: 8f2312474529 ("net/qede: fix performance bottleneck in Rx path")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Acked-by: Rasesh Mody <rmody@marvell.com>
This patch fixes a regression introduced by
commit 49d3978d5723 ("net/qede: fix Tx tunnel offload support mask")
in which qede_xmit_prep_pkts() breaks the loop for successful
check of Tunneling offload flags instead of continuing, resulting
in tx_pkt_prepare return a failure.
Fixes: 49d3978d5723 ("net/qede: fix Tx tunnel offload support mask")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Incorrect placement of prefetch in Tx path is causing
a performance drop of around ~2% on AMD platform.
Fixes: 2ea6f76aff40 ("qede: add core driver")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Acked-by: Rasesh Mody <rmody@marvell.com>
Allocating replacement buffer per received packet is expensive.
Instead, process received packets first and allocate
replacement buffers in bulk later.
This improves performance by ~25% in terms of PPS on AMD
platforms.
Fixes: 2ea6f76aff40 ("qede: add core driver")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
Acked-by: Rasesh Mody <rmody@marvell.com>
Tunneling offloads are represented by multi-bit values. So, feature
wise tunneling offload can only be entirely supported/unsupported
using PKT_TX_TUNNEL_MASK. Its upon PMDs to further isolate which of
the tunneling offload types are supported by respective PMD.
Using subset of bits from PKT_TX_TUNNEL_MASK to indicate supported vs
unsupported offloads can lead to undesired result.
Use PKT_TX_TUNNEL_MASK in QEDE_TX_OFFLOAD_MASK and use independent
value of supported PKT_TX_TUNNEL_* in .tx_pkt_prepare() to mark
supported tunnel offloads.
Fixes: 44346c24b790 ("net/qede: fix VXLAN tunnel Tx offload flag setting")
Cc: stable@dpdk.org
Suggested-by: Ferruh Yigit <ferruh.yigit@intel.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Reviewed-by: Rasesh Mody <rasesh.mody@cavium.com>
Currently, if configuration fails (for example if a 100G card is used
with an odd number of RX/TX queues) QEDE crashes due to a null pointer
dereference.
This commit fixes it by checking that the pointer is not NULL before
using it.
Fixes: 7105b24f4bb8 ("net/qede: fix memory alloc for multiple port reconfig")
Cc: stable@dpdk.org
Signed-off-by: Timothy Redaelli <tredaelli@redhat.com>
Acked-by: Rasesh Mody <rasesh.mody@cavium.com>
This patch implement eth_dev_ops->rx_descriptor_status
callback.
Walk through receive completion ring to calculate receive
descriptors used by firmware and then provide the status of
offset accordingly.
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
- HW does not include CRC in received frame when passed to host,
so no need to consider CRC length while calculating Rx buffer size.
- In scattered Rx mode, driver may allocate Rx buffer larger than
the size of mbuf because it tries to adjust the buffer size to cache
line size by ceiling it. Fix this by flooring the size instead of
ceiling.
- Consider the rule imposed by HW regarding the minimum size of Rx buffer
in scattered Rx mode -
(MTU + Maximum L2 Header Size + 2) / ETH_RX_MAX_BUFF_PER_PKT
Fixes: f6033f2497e7 ("net/qede: fix minimum buffer size and scatter Rx check")
CC: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
We were using LICENSE.qede_pmd to reference inclusion of SPDX licensing
tag from all the source file. Remove the LICENSE.qede_pmd file and
directly include SPDX tags in source files.
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
- We don't support QinQ offload, so removing it now.
- Fix incorrect offload flags in default rxconf
Since qede PMD does not support per queue rx offload, it
should not set default_rxconf.offload flags in .dev_infos_get().
Although these offloads are enabled by default, they are per port
and not per queue.
Fixes: 946dfd18a4ec ("net/qede: convert to new Rx/Tx offloads API")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shahed.shaikh@cavium.com>
Multiple port reconfigurations can lead to memory allocation failures
due to hitting RTE memzone limit or no more room in config while
reserving memzone.
When freeing memzones, update the memzone mapping and the memzone count.
Release Rx and Tx queue rings allocated during queue setup.
Fixes: a39001d90dbd ("net/qede: fix DMA memory leak")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Reviewed-by: Kevin Traynor <ktraynor@redhat.com>
Ethdev RX/TX offloads API has changed since:
commit ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
commit cba7f53b717d ("ethdev: introduce Tx queue offloads API")
This patch makes use of new offload flags as suggested and fix
the default RX/TX configuration. Also indent the code properly
around those changes.
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Fixes: 9e334305178f ("net/qede: fix MTU set and max Rx length")
Fixes: 22d07d939c3c ("net/qede/base: update")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Few adjustments are required to effectively handle VF vport create/delete
sequence. The problem is exposed by recent ethdev TX offload changes
which requires port to be in down state before applying TX offloads.
- Move vport creation from dev_init() to dev_configure()
- Force to stop vport if it was already started due to previous run
(restart case)
- Move link state enable/disable to dev_init() and dev_close()
respectively.
- For MTU change, recreate vport with new MTU value and restore old
config. This is necessary since VF MTU value can be changed only upon
vport creation.
Fixes: ec94dbc57362 ("qede: add base driver")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
This patch fixes issues related to MTU set and max_rx_pkt_len usage.
- Adjust MTU during device configuration when jumbo is enabled
- In qede_set_mtu():
Return not supported for VF as currently we do not support it.
Cache new mtu value in mtu_new for proper update.
Add check for RXQ allocation before calculating RX buffer size
if not allocated defer RX buffer size calculation till RXQ setup.
Add check for before performing device start/stop.
- Use max_rx_pkt_len appropriately
- Change QEDE_ETH_OVERHEAD macro to adjust driver specifics
Fixes: 4c4bdadfa9e7 ("net/qede: refactoring multi-queue implementation")
Fixes: 9a6d30ae6d46 ("net/qede: refactoring vport handling code")
Fixes: 1ef4c3a5c1f7 ("net/qede: prevent crash while changing MTU dynamically")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
- Fix incorrect header size. In the tunnel case, the outer L2/L3 lengths
should be included to calculate tunnel header_size.
- In TSO case, skip manipulating TX BD1 and TX BD2 data buffer fields
since those fields are already updated with header and payload lengths
respectively.
- Update TX BD debug data collection.
Fixes: 3d4bb4411683 ("net/qede: add fastpath support for VXLAN tunneling")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
- Add a check to verify tunnel IP header checksum is valid and mark MBUF
flag as appropriate.
- Bit of refactoring so that inner frame handling for tunneled packets can
be made common as regular (non-tunneled) packets.
- make qede_tunn_exist() as inline.
- remove RTE_PTYPE_L2_ETHER as default L2 pkt_type.
Fixes: 3d4bb4411683 ("net/qede: add fastpath support for VXLAN tunneling")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Fixes: 97cb466d65c9 ("mbuf: use 2 bytes for port and nb segments")
Cc: stable@dpdk.org
Signed-off-by: Ilya V. Matveychikov <matvejchikov@gmail.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The following inline functions and macros have been renamed to be
consistent with the IOVA wording:
rte_mbuf_data_dma_addr -> rte_mbuf_data_iova
rte_mbuf_data_dma_addr_default -> rte_mbuf_data_iova_default
rte_pktmbuf_mtophys -> rte_pktmbuf_iova
rte_pktmbuf_mtophys_offset -> rte_pktmbuf_iova_offset
The deprecated functions and macros are kept to avoid breaking the API.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
PKT_RX_VLAN_PKT and PKT_RX_QINQ_PKT are deprecated for a while.
As explained in [1], these flags were kept to let the applications and
PMDs move to the new flag. There is also a need to support Rx vlan
offload without vlan strip (at least for the ixgbe driver).
This patch renames the old flags for this feature, knowing that some
PMDs were using PKT_RX_VLAN_PKT and PKT_RX_QINQ_PKT to indicate that
the vlan tci has been saved in the mbuf structure.
It is likely that some PMDs do not set the proper flags when doing vlan
offload, and it would be worth making a pass on all of them.
Link: [1] http://dpdk.org/ml/archives/dev/2017-June/067712.html
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The compilation with gcc-6.3.0 and EXTRA_CFLAGS=-Og gives the following
error:
CC qede_rxtx.o
qede_rxtx.c: In function ‘qede_start_queues’:
qede_rxtx.c:797:9: error: ‘rc’ may be used uninitialized in this
function [-Werror=maybe-uninitialized]
return rc;
^~
If there is no Rx or Tx queue, rc will not be initialized. Fix it
by initializing rc to -1.
Fixes: 4c4bdadfa9e7 ("net/qede: refactoring multi-queue implementation")
Cc: stable@dpdk.org
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Harish Patil <harish.patil@cavium.com>
Upgrade QEDE PMD FW to version 8.30.12.0.
The firmware upgrade change details are as:
- Add support for steering by IP and UDP destination port.
- Add source QP field for GSI offload.
- Add UFP support.
- Add support for outer IPv4 TX CSO with unknown tunnel type (in addition
to inner header CSO).
- Support flow ID in accelerated RFS flow.
- Allow Doorbell on empty SPQ and LL2 TX queue (for doorbell recovery).
- Enable PCI Relaxed Ordering for L2 RX data placement.
- Additional enhancements and bug fixes
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Status Block reallocation - allow a PF and its child VF to change SB
between them using new base driver APIs.
The changes that are inside base driver flows are:
New APIs ecore_int_igu_reset_cam() and ecore_int_igu_reset_cam_default()
added to reset IGU CAM.
a. During hw_prepare(), driver would re-initialize the IGU CAM.
b. During hw_stop(), driver would initialize the IGU CAM to default.
Use igu_sb_id instead of sb_idx [protocol index] to allow setting of
the timer-resolution in CAU[coalescing algorithm unit] for all SBs,
sb_idx could limit SBs 0-11 only to be able change their timer-resolution.
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Force recalculation of tunnel L4 chksum when inner L3/L4 chksum gets
updated due to HW offload.
Fixes: aab21617502e ("net/qede: add Tx offloads for MPLS-in-UDP packets")
Signed-off-by: Harish Patil <harish.patil@cavium.com>
'commit 4c4bdadfa9e7 ("net/qede: refactoring multi-queue implementation")'
introduced a regression where default RSS configuration is incorrect in
the case of 100G mode. Currently we are passing absolute queue ids while
creating RX/TX queues. But in CMT mode we need to provide queue id
relative to the engine id. So this fix takes into account num_hwfns
while creating queues.
Fixes: 4c4bdadfa9e7 ("net/qede: refactoring multi-queue implementation")
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Convert DP_NOTICE() to DP_ERR() as appropriate in PMD files.
Change DP_NOTICE() macro to make use of boolean flag to log
it as error message or informational message.
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Implement the macro OSAL_DMA_FREE_COHERENT to release DMA memories.
Track all DMA memory allocations using an array of memzone pointers and
use that to free memory resources along with other resource deallocation.
With this change there is no need to alter the base code to additionally
pass an unique string needed for memzone creation.
Fixes: ec94dbc57362 ("qede: add base driver")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Add support for inner/outer L3/L4 TX csum offload for MPLS-in-UDP packets.
The driver checks for PKT_TX_TUNNEL_MPLSINUDP in Tx ol_flags and updates TX
BD elements with appropriate offsets/length of tunnel headers.
The pseudo csum calculation is removed from qede_xmit_prep_pkts() since its
not needed.
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Fixing typos across dpdk source code using codespell utility.
Skipped the ethdev driver's base code fixes to keep the base
code intact.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Refactor TX routine such that TX BD updates can all be grouped together.
Based on the TX offloads requested the TX bitfields are calculated in
a temporary variable and TX BDs are updated at the end. This will minimize
the if checks also. This change is done to easily accommodate newer TX
offload operations in the future.
Signed-off-by: Harish Patil <harish.patil@cavium.com>
This patch fixes missing PKT_TX_TUNNEL_VXLAN Tx offload flag from the
supported Tx offloads and an incorrect tunnel TX BD bit setting.
Fixes: 3d4bb4411683 ("net/qede: add fastpath support for VXLAN tunneling")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
This patch does the following refactoring and cleanup:
- As part of multi-queue support a struct member called 'type' was added
in struct qede_fastpath in order to identify whether a queue is RX or
TX and take actions based on that. This was unnecessary in the first
place since pointers to RX and TX queues are already available in
rte_eth_dev->data. So all usage of fp->type is removed.
- Remove remaining additional layer of internal callbacks for RX/TX
queues and fastpath related operations from the qed_eth_ops_pass.
With this change the files qede_eth_if.[c,h] are no longer needed.
- Add new per-queue start/stop APIs instead of clubbing it all together.
- Remove multiple TXQs references (num_tc and fp->txqs) since CoS is not
supported.
- Enable sharing of the status block for each queue pair.
- Remove enum qede_dev_state and instead make use of existing port
states RTE_ETH_QUEUE_STATE_STOPPED/RTE_ETH_QUEUE_STATE_STARTED.
- Move qede_dev_start() and qede_dev_stop() to qede_ethdev.c from
qede_rxtc.c.
Signed-off-by: Harish Patil <harish.patil@cavium.com>
The refactoring is mainly for two reasons:
- To remove an additional layer of internal callbacks for all vport
related operations from the struct qed_eth_ops_pass. Instead, we
can invoke base APIs directly.
- Splitting a single large vport-update configuration into multiple and
independent vport-update operations. Each configuration would touch
only the required config bits that needs an update.
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Changes included in this fix
- limit CFLAGS to base files
- fix to remove/mark unused members
- add checks for debug config option
- make qede_set_mtu() and qede_udp_dst_port_del() static and others
non-static as appropriate
- move local APIs qede_vlan_offload_set() and qede_rx_cqe_to_pkt_type()
- initialize variables as required
Fixes: ec94dbc57362 ("qede: add base driver")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
Use new mbuf flags PKT_RX_VLAN_STRIPPED and PKT_RX_QINQ_STRIPPED
introduced by the patch:
commit b37b528d957c ("mbuf: add new Rx flags for stripped VLAN")
Signed-off-by: Harish Patil <harish.patil@cavium.com>
This defect is a functional issue where the RX CQE pointer remains
uninitialized in the LRO code path which can cause null pointer exception
while accessing VLAN or RSS hash value from CQE.
Coverity issue: 143474
Fixes: 29540be7efce ("net/qede: support LRO/TSO offloads")
Signed-off-by: Harish Patil <harish.patil@cavium.com>
- Add a common routine to handle ETH_RX_CQE_TYPE_TPA_CONT and
ETH_RX_CQE_TYPE_TPA_END.
- Remove enum qede_agg_state since there is no need to maintain
aggregation state.
- Modify the segment chaining logic by tracking head and tail
TPA segments of each aggregation.
- Add more debug and comments.
- Mark the packet as PKT_RX_LRO.
Fixes: 29540be7efce ("net/qede: support LRO/TSO offloads")
Signed-off-by: Harish Patil <harish.patil@cavium.com>
Perform reset of the fastpath RX/TX rings after stopping device port and
not while starting the ports.
Fixes: cfe28a988565 ("net/qede: support unequal number of Rx/Tx queues")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@cavium.com>
The driver can handle dynamic MTU change without needing the port to be
stopped explicitly by the application. However, there is currently no
check to prevent I/Os from happening on a different thread while the
port is going thru' reset internally. This patch fixes this issue by
assigning RX/TX burst functions to a dummy function and also reconfigure
RX bufsize for each rx queue based on the new MTU value.
Fixes: 200645ac7909 ("net/qede: set MTU")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@qlogic.com>
The newer SR-IOV PF drivers expects RX/TX queues to be created before
applying RSS configuration. This patch addresses this requirement by
deferring RSS configuration till the queues are created. Even though
this issue is only seen in SR-IOV context, the changes will be made
applicable to PF also to keep the behavior consistent between VF/PF.
Fixes: 7ab35bf6b97b ("net/qede: fix RSS")
Cc: stable@dpdk.org
Signed-off-by: Harish Patil <harish.patil@qlogic.com>
This patch includes slowpath configuration and fastpath changes
to support LRO and TSO. A bit of revamping is needed in order
to make use of existing packet classification schemes in Rx fastpath
and for SG element processing in Tx.
Signed-off-by: Harish Patil <harish.patil@qlogic.com>
L2 handler changes:
This is change to remove the queue-id/qzone difference for Tx queues.
It does that by mainly doing:
a. VFs queues are no longer determined by the SBs they're using.
Instead, the ecore-client needs to maintain those and choose the values
to be used by VF when initializing it.
b. Eliminate the HW-cid array in the hw-function.
To do that, have all the rx/tx functionality turn into 'handle' base -
when queue would be started the caller would get a (void*) handle,
which it would later use with ecore for configuring various
queue-related stop [update, close].
Signed-off-by: Rasesh Mody <rasesh.mody@cavium.com>
