When trying to release the mbufs, the function was incorrectly
iterating over the max size configured instead of the actual size
of the ring.
Fixes: 947d860c821f ("enic: improve Rx performance")
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
- add l4 ptypes to the ones we report as supporting
- report/use RTE_PTYPE_L3_IPV4_EXT_UNKNOWN and
RTE_PTYPE_L3_IPV6_EXT_UNKNOWN instead of RTE_PTYPE_L3_IPV4 and
RTE_PTYPE_L3_IPV6 as vic can't distinguish between packets with
extentions and those without extentions.
- correctly set the ptype bits set on packets that are both tcp/udp
and a frag
- set RTE_PTYPE_L4_NONFRAG on ip packets we know are not udp, tcp,
or fragments.
Fixes: 947d860c821f ("enic: improve Rx performance")
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
If configuration fails due to lack of resources, be more specific
about which resources are lacking - work queues, read queues or
completion queues. Return -EINVAL instead of -1 if more queeues
are requested than are available.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley <johndale@cisco.com>
If device configuration failed due to a lack of resources, such as
if more queues are requested than are available, the queue release
functions are called with NULL pointers which were being dereferenced.
Skip releasing queues if they are NULL pointers.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley <johndale@cisco.com>
Private/conflicting ol_flags where used to enable UDP/TCP Tx
offloads. Use the common flags in PKT_TX_L4_MASK to support them.
When updating flags, also do some minor code rearranging for
slightly better performane.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley <johndale@cisco.com>
The offload flags variable (ol_flags) in rte_mbuf structure is 64-bits,
so local copy of it must be 64-bits too. Moreover bit comparison between
16-bits variable and 64-bits value make no sense. This breaks Tx vlan
IP and L4 offloads.
Coverity issue: 13218
Fixes: fefed3d1e62c ("enic: new driver")
Suggested-by: Piotr Azarewicz <piotrx.t.azarewicz@intel.com>
Signed-off-by: John Daley <johndale@cisco.com>
Acked-by: Piotr Azarewicz <piotrx.t.azarewicz@intel.com>
Add an ASSERT macro for the enic driver which is enabled when the log
level is >= RTE_LOG_DEBUG. Assert that number of mbufs to return to
the pool in the Tx function is never greater than the max allowed.
Signed-off-by: John Daley <johndale@cisco.com>
Reduce host CPU overhead of Tx packet processing:
* Use local variables inside per-packet loop instead of fields in structs.
* Factor book keeping and conditionals out of the per-packet loop where
possible.
* Post buffers to the nic at a maximum of every 64 packets
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Mbufs were returned to the pool one at a time. Use rte_mempool_put_bulk
instead. There were multiple function calls for each buffer returned.
Refactor this code into just 2 functions.
Signed-off-by: John Daley <johndale@cisco.com>
The NIC can either DMA a separate completion message for each completed
send or periodically just DMA the index of the last completed send.
Switch to the latter method which improves cache locality and performance.
Signed-off-by: John Daley <johndale@cisco.com>
The list of mbufs held by the driver on Tx was allocated in chunks
(a hold-over from the enic kernel mode driver). The structure used
next pointers across chunks which led to cache misses.
Allocate the array used to hold mbufs in flight on Tx with
rte_zmalloc_socket(). Remove unnecessary fields from the structure
and use head and tail pointers instead of next pointers.
Signed-off-by: John Daley <johndale@cisco.com>
Functions existed which were never called. Removed them. Also
rename the 'pmd' from the name of the Tx function to improve clarity.
Signed-off-by: John Daley <johndale@cisco.com>
The Tx functions were in enic_ethdev.c and enic_main.c - files in which
they did not logically belong. To make things consistent with most
other drivers, we therefore extract them and place them with the equivalent
Rx functions into a file called enic_rxtx.c.
Signed-off-by: John Daley <johndale@cisco.com>
Truncated packets occur on enic if an mbuf is not big enough to
receive it or there aren't enough mbufs if rx scatter is in use.
They show up as error packets but unlike other error packets (like
packets bad FCS) there are no nic drop counts incremented for them.
Truncated packets are calculated by subtracting hardware errors from
software errors. Note: this causes transient inaccuracies in the
ipackets count. Also, the length of truncated packets are counted
in ibytes even though truncated packets are dropped which can make
ibytes be slightly higher than it should be.
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Following the discussions from:
http://dpdk.org/ml/archives/dev/2015-July/021721.htmlhttp://dpdk.org/ml/archives/dev/2016-April/038143.html
Remove the unused flag from enic driver. Also, the enic driver is
now modified to drop bad packets instead of using a non-existent
flag to try and identify them as bad.
Fixes: 947d860c821f ("enic: improve Rx performance")
Fixes: 5776c30293bb ("enic: fix error packets handling")
Fixes: 50765c820e98 ("enic: remove packet error conditional")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Signed-off-by: John Daley <johndale@cisco.com>
rx_no_bufs is a hardware counter of packets dropped on the
interface due to no host buffers and should be used to update
r_stats->imissed counter instead of rx_nombuf.
Include rx_drop in ierrors. rx_drop is incremented if packets
arrive when the receive queue is disabled.
Add a structure and functions for initializing and clearing
software counters. Add count of Rx mbuf allocation failures
(rx_nombuf) as the first counter.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley <johndale@cisco.com>
The behavior of PKT_RX_VLAN_PKT was not very well defined, resulting in
PMDs not advertising the same flags in similar conditions.
Following discussion in [1], introduce 2 new flags PKT_RX_VLAN_STRIPPED
and PKT_RX_QINQ_STRIPPED that are better defined:
PKT_RX_VLAN_STRIPPED: a vlan has been stripped by the hardware and its
tci is saved in mbuf->vlan_tci. This can only happen if vlan stripping
is enabled in the RX configuration of the PMD.
For now, the old flag PKT_RX_VLAN_PKT is kept but marked as deprecated.
It should be removed from applications and PMDs in a future revision.
This patch also updates the drivers. For PKT_RX_VLAN_PKT:
- e1000, enic, i40e, mlx5, nfp, vmxnet3: done, PKT_RX_VLAN_PKT already
had the same meaning than PKT_RX_VLAN_STRIPPED, minor update is
required.
- fm10k: done, PKT_RX_VLAN_PKT already had the same meaning than
PKT_RX_VLAN_STRIPPED, and vlan stripping is always enabled on fm10k.
- ixgbe: modification done (vector and normal), the old flag was set
when a vlan was recognized, even if vlan stripping was disabled.
- the other drivers do not support vlan stripping.
For PKT_RX_QINQ_PKT, it was only supported on i40e, and the behavior was
already correct, so we can reuse the same bit value for
PKT_RX_QINQ_STRIPPED.
[1] http://dpdk.org/ml/archives/dev/2016-April/037837.html,
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Many drivers provide their own implementation of rte_mbuf_raw_alloc(),
duplicating the code. Introduce a new public function in rte_mbuf to
allocate a raw mbuf (uninitialized).
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
The code to provide mbufs for RX used m->data_off instead of
RTE_PKTMBUF_HEADROOM as the position inside the mbuf for the data to be
written. As the mbuf is uninitialised, this could potentially cause Rx
data to be placed at the wrong address in the mbuf - or even outside it.
Fixes: 947d860c821f ("enic: improve Rx performance")
Signed-off-by: John Daley <johndale@cisco.com>
The macro RTE_VERIFY always checks a condition.
It is optimized with "unlikely" hint.
While this macro is well suited for test applications, it is preferred
in libraries and examples to enable such check in debug mode.
That's why the macro RTE_ASSERT is introduced to call RTE_VERIFY only
if built with debug logs enabled.
A lot of assert macros were duplicated and enabled with a specific flag.
Removing these #ifdef allows to test these code branches more easily
and avoid dead code pitfalls.
The ENA_ASSERT is kept (in debug mode only) because it has more
parameters to log.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Some statistics were deprecated since release 2.1 (49f386542af4).
The last deprecated counter to be used was imcasts.
The VF loopback statistics are also removed as they are used only
in igb and duplicated in extended statistics.
The new counters should be added to extended statistics.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Remy Horton <remy.horton@intel.com>
Update the 'imissed' counter with the number of packets dropped
by the NIC.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: John Daley <johndale@cisco.com>
Reviewed-by: Nelson Escobar <neescoba@cisco.com>
When the enic was disabled, link notification was correctly disabled
in the NIC but the software indicator that it was disabled was not
updated (vdev->notify_pa not set to 0). When the link came back up,
enic did not re-enable notification in the NIC.
This affected bonding when a enic slave device link bounced.
The fix is to unconditionally enable notification when the enic is
enabled.
Fixes: 9913fbb91df0 ("enic/base: common code")
Signed-off-by: John Daley <johndale@cisco.com>
Reviewed-by: Nelson Escobar <neescoba@cisco.com>
If the nb_pkts parameter to rte_eth_tx_burst() was greater than
the TX descriptor count, a completion was not being requested
from the NIC, so descriptors would not be released back to the
host causing a lock-up.
Introduce a limit of how many TX descriptors can be used in a single
call to the enic PMD burst TX function before requesting a completion.
Fixes: d739ba4c6abf ("enic: improve Tx packet rate")
Signed-off-by: John Daley <johndale@cisco.com>
On initialization, the rq descriptor count was set to the limit
of the vic. When the requested number of rx descriptors was
less than this count, enic_alloc_rq() was incorrectly setting
the count to the lower value. This results in later calls to
enic_alloc_rq() incorrectly using the lower value as the adapter
limit.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
If the packet_error bit in the completion descriptor is set, the
remainder of the descriptor and data are invalid. PKT_RX_MAC_ERR
was set in the mbuf->ol_flags if packet_error was set and used
later to indicate an error packet. But since PKT_RX_MAC_ERR is
defined as 0, mbuf flags and packet types and length were being
misinterpreted.
Make the function enic_cq_rx_to_pkt_err_flags() return true for error
packets and use the return value instead of mbuf->ol_flags to indicate
error packets. Also remove warning for error packets and rely on
rx_error stats.
Fixes: 947d860c821f ("enic: improve Rx performance")
Signed-off-by: John Daley <johndale@cisco.com>
In the receive path, the function to set mbuf ol_flags used the
mbuf packet_type before it was set.
Fixes: 947d860c821f ("enic: improve Rx performance")
Signed-off-by: John Daley <johndale@cisco.com>
Add checks to make sure we don't try to allocate more tx or rx queues
than we support.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Add the missing '\n' character to the end of a few print statements.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Acked-by: John Daley <johndale@cisco.com>
Add a new API rte_eth_dev_get_supported_ptypes to query what packet types
can be filled by a given device. The device should be already started or
its PMD RX burst function already decided, since the packet types supported
may vary depending on RX function.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The last packet of the tx burst function array was not being
emitted until the subsequent call. The nic descriptor index
was being set to the current tx descriptor instead of one past
the descriptor as required by the nic.
Fixes: d739ba4c6abf ("enic: improve Tx packet rate")
Signed-off-by: John Daley <johndale@cisco.com>
This is a wholesale replacement of the Enic PMD receive path in order
to improve performance and code clarity. The changes are:
- Simplify and reduce code path length of receive function.
- Put most of the fast-path receive functions in one file.
- Reduce the number of posted_index updates (pay attention to
rx_free_thresh)
- Remove the unneeded container structure around the RQ mbuf ring
- Prefetch next Mbuf and descriptors while processing the current one
- Use a lookup table for converting CQ flags to mbuf flags.
Signed-off-by: John Daley <johndale@cisco.com>
The enic PMD driver send function uses a constant offset instead
of relying on the data_off in the mbuf to find the start of the packet.
Fixes: fefed3d1e62c ("enic: new driver")
Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
fix the error reported by checkpatch:
"ERROR: return is not a function, parentheses are not required"
remove parentheses in return like:
"return (logical expressions)"
remove parentheses in return a function like:
"return (rte_mempool_lookup(...))"
Fixes: 6307b909b8e0 ("lib: remove extra parenthesis after return")
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Report an error when something went wrong.
Signed-off-by: Julien Meunier <julien.meunier@6wind.com>
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Sujith Sankar <ssujith@cisco.com>
Following the same approach taken with dev_started field
in rte_eth_dev_data structure, this patch adds two new fields
in it, rx_queue_state and tx_queue_state arrays, which track
which queues have been started and which not.
This is important to avoid trying to start/stop twice a queue,
which will result in undefined behaviour
(which may cause RX/TX disruption).
Mind that only the PMDs which have queue_start/stop functions
have been changed to update this field, as the functions will
check the queue state before switching it.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Use new function rte_eth_copy_pci_info.
Copy device info for the following pdevs:
bnx2x
cxgbe
e1000
enic
fm10k
i40e
ixgbe
mlx4
mlx5
virtio
vmxnet3
Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
For every packet sent, a completion was being requested and the
posted_index register on the nic was being updated. Instead, request a
completion and update the posted index once per burst after all
packets have been sent by the burst function.
Signed-off-by: John Daley <johndale@cisco.com>
Acked-by: Sujith Sankar <ssujith@cisco.com>
If dpdk is run with memory only available on socket != 0, then hash
creation will fail and flow director feature won't be available.
Fix this by asking for allocation on caller socket.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked by: Sujith Sankar <ssujith@cisco.com>
Seen by code review.
If dpdk is run with memory only available on socket != 0, then enic pmd
refuses to initialize ports as this pmd requires some memory on socket 0.
Fix this by setting socket to SOCKET_ID_ANY, so that allocations happen on
the caller socket.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked by: Sujith Sankar <ssujith@cisco.com>
Old flow director API have been replaced by rte_eth_dev_filter_ctrl
since release 2.0. And no driver in current code support these functions.
All the removed functions are listed below:
- rte_eth_dev_fdir_add_perfect_filter;
- rte_eth_dev_fdir_add_signature_filter;
- rte_eth_dev_fdir_get_infos;
- rte_eth_dev_fdir_remove_perfect_filter;
- rte_eth_dev_fdir_remove_signature_filter;
- rte_eth_dev_fdir_set_masks;
- rte_eth_dev_fdir_update_perfect_filter;
- rte_eth_dev_fdir_update_signature_filter;
The library version was already incremented in a previous patch.
Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
[Thomas: fix mlx4 and update release notes]
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
RTE_HASH_KEY_LENGTH_MAX was deprecated, and the hash table
actually is hosting bigger keys than that size, so key length
has been increased to properly allocate all keys.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Sujith Sankar <ssujith@cisco.com>
The extended unified packet type is now part of the standard ABI.
As mbuf struct is changed, the mbuf library version is incremented.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Move malloc inside eal and create a new section in MAINTAINERS file for
Memory Allocation in EAL.
Create a dummy malloc library to avoid breaking applications that have
librte_malloc in their DT_NEEDED entries.
This is the first step towards using malloc to allocate memory directly
from memsegs. Thus, memzones would allocate memory through malloc,
allowing to free memzones.
Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
To unify packet types among all PMDs, bit masks of packet type for
'ol_flags' are replaced by unified packet type.
To avoid breaking ABI compatibility, all the changes would be
enabled by RTE_NEXT_ABI.
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
The cuckoo hash has a fixed number of entries per bucket, so the
configuration parameter for this is unused. We change this field in the
parameters struct to "reserved" to indicate that there is now no such
parameter value, while at the same time keeping ABI consistency.
Fixes: 48a399119619 ("hash: replace with cuckoo hash implementation")
Suggested-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Upcoming drivers will need to be able to support other bus types.
This is a transparent change to how struct eth_driver is initialized.
It has not function or ABI layout impact, but makes adding a later
bus type (Xen, Hyper-V, ...) much easier.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
