Instead of reading Ethernet RFC 2819 pXtoYoctets counters from
hardware which counts RX octets, count tx_stat_pXtoYoctets from
Ethernet extended counters which counts TX octets.
TX jumbo counters should be accumulated only after the PPCNT
counters were fetched from hardware with their latest value.
Submitted by: slavash@
MFC after: 3 days
Sponsored by: Mellanox Technologies
Add support for DIM based on Linux,
with some minor adaptions specific to FreeBSD.
Linux commit
f97c3dc3c0e8d23a5c4357d182afeef4c67f5c33
MFC after: 3 days
Sponsored by: Mellanox Technologies
Drivers can now pass up numa domain information via the
mbuf numa domain field. This information is then used
by TCP syncache_socket() to associate that information
with the inpcb. The domain information is then fed back
into transmitted mbufs in ip{6}_output(). This mechanism
is nearly identical to what is done to track RSS hash values
in the inp_flowid.
Follow on changes will use this information for lacp egress
port selection, binding TCP pacers to the appropriate NUMA
domain, etc.
Reviewed by: markj, kib, slavash, bz, scottl, jtl, tuexen
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20028
This commit adds new if_alloc_domain() and if_alloc_dev() methods to
allocate ifnets. When called with a domain on a NUMA machine,
ifalloc_domain() will record the NUMA domain in the ifnet, and it will
allocate the ifnet struct from memory which is local to that NUMA
node. Similarly, if_alloc_dev() is a wrapper for if_alloc_domain
which uses a driver supplied device_t to call ifalloc_domain() with
the appropriate domain.
Note that the new if_numa_domain field fits in an alignment pad in
struct ifnet, and so does not alter the size of the structure.
Reviewed by: glebius, kib, markj
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D19930
This allows efficient filtering at packet ingress on mlx5en.
Note that the packets are filtered (and potentially dropped) *before*
the driver has committed to (re)allocating an mbuf for the
packet. Dropped packets are treated essentially the same as an
error. Nothing is allocated, and the existing buffer is recycled. This
allows us to drop malicious packets at close to line rate with very
little CPU use.
Reviewed by: hselasky, slavash, kib
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D19063
The backpressure indication is implemented using an unlimited rate type of
mbuf send tag. When the upper layers typically the socket layer has obtained such
a tag, it can then query the destination driver queue for the current
amount of space available in the send queue.
A single mbuf send tag may be referenced multiple times and a refcount has been added
to the mlx5e_priv structure to track its usage. Because the send tag resides
in the mlx5e_channel structure, there is no need to wait for refcounts to reach
zero until the mlx4en(4) driver is detached. The channels structure is persistant
during the lifetime of the mlx5en(4) driver it belongs to and can so be accessed
without any need of synchronization.
The mlx5e_snd_tag structure was extended to contain a type field, because there are now
two different tag types which end up in the driver which need to be distinguished.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
In order to enable HW LRO, both the "hw_lro" sysctl in the mlx5en(4) config
space must be set, and the ifconfig(8) LRO capability must be set. Any other
settings will disable HW LRO.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
Add counter for all transmitted and received bytes. Currently only all
transmitted and received packets were counted. Fix description of RX LRO
counters while at it.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
By allocating the worst case size channel structure array
at attach time we can eliminate various NULL checks in the
fast path. And also reduce the chance for use-after-free
issues in the transmit fast path.
This change is also a requirement for implementing
backpressure support.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
Writing to the debug stats variable must be locked,
else serialization will be lost which might cause
various kernel panics due to creating and destroying
sysctls out of order.
Make sure the sysctl context is initialized after freeing
the sysctl nodes, else they can be freed twice.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
Inspect the ethernet compliance code to figure out actual cable type by reading
the PDDR module info register.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
This can happen when connections are short lived and leads to
a firmware error printout in dmesg, syndrome 0x51cfb0, because
the SQ is in the wrong state.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
1) Don't exceed the drivers own hardcoded TX inline limit.
The blueflame register size can be much greater than the hardcoded limit
for inlining. Make sure we don't exceed the drivers own limit, because this
also means that the maximum number of TX fragments becomes invalid and
then memory size assumptions in the TX path no longer hold up.
2) Make sure the mlx5_query_min_inline() function returns an error code.
3) Header inlining is required when using TSO.
4) Catch failure to compute inline header size for TSO.
5) Add support for UDP when computing inline header size.
6) Fix for inlining issues with regards to DSCP.
Make sure we inline 4 bytes beyond the ethernet and/or
VLAN header to workaround a hardware bug extracting
the DSCP field from the IPv4/v6 header.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
The hardware queues are deep enough currently and using the DRBR and associated
callbacks only leads to more task switching in the TX path. The is also a race
setting the queue_state which can lead to hung TX rings.
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
Add support for setting the bandwidth limit as a ratio rather than in bits per
second. The ratio must be an integer number between 1 and 100 inclusivly.
Implement the needed firmware commands and SYSCTLs through mlx5en(4).
Submitted by: hselasky@
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
Driver description should be set by core and not by the Ethernet driver.
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
This counter will represent transmitted packets which has more than
1518 octets.
The NIC has multiple hardware counters for counting transmitted
packets larger than 1518 octets. Each counter counts the packets
in specific range.
We accumulate those counters to have a single counter.
Approved by: hselasky (mentor)
MFC after: 1 week
Sponsored by: Mellanox Technologies
The receive side scaling stride parameter is a value which define the interval
between active receive side queues. The traffic for the inactive queues is
redirected to the nearest active queue by use of modulus. The default value
of this parameter is one, which means all receive side queues are used.
The point of this feature is to redirect more traffic to fewer receive side
queues in order to take more advantage of sorted large receive offload,
sorted LRO. The sorted LRO works better when more packets are accumulated
per service interval.
MFC after: 3 days
Approved by: re (marius)
Sponsored by: Mellanox Technologies
Inspecting the PRM no more than 0x3F data segments, DS, of size 16 bytes is
allowed.
Worst case scenario summary of DS usage:
Header is fixed: 2 DS
Maximum inlining: 98 => (98 - 2) / 16 = 6 DS
Remainder: 0x3F - 2 - 6 = 55 DS (mbuf frags)
Previously a value of 56 DS was used and this would work in the
normal case because not all inline data area was used up.
MFC after: 3 days
Approved by: re (marius)
Sponsored by: Mellanox Technologies
Query the minimal inline mode supported by the card.
When creating a send queue, cache the queried mode and optimize the transmit
if no inlining is required. In this case, we can avoid touching the headers
cache line and avoid dirtying several more lines by copying headers into
the send WQEs. Also, if no inline headers are used, hardware assists in
the VLAN tag framing.
Submitted by: kib@, slavash@
MFC after: 1 week
Sponsored by: Mellanox Technologies
The scatter list is formed by the chunks of MCLBYTES each, and larger
than default packets are returned to the stack as the mbuf chain.
Submitted by: kib@
MFC after: 1 week
Sponsored by: Mellanox Technologies
To access the data, set sysctl dev.mce.N.conf.debug_stats to 1.
This enables the sysctl node dev.mce.N.hw_ctx_debug. Its content is
the mapping of each channel' number to used receive queue and associated
completion queue, set of the transmit queues numbers and corresponding
completion queues.
Trimmed example output:
channel 30 rq 188 cq 1085
channel 30 tc 0 sq 187 cq 1084
channel 31 rq 191 cq 1087
channel 31 tc 0 sq 190 cq 1086
MFC after: 1 week
Sponsored by: Mellanox Technologies
The DSCP feature is controlled using a set of sysctl(8) fields under
the qos sysctl directory entry for mlx5en(4).
For Routable RoCE QPs, the DSCP should be set in the QP's address path.
The DSCP's value is derived from the traffic class.
Linux commit:
ed88451e1f2d400fd6a743d0a481631cf9f97550
MFC after: 1 week
Sponsored by: Mellanox Technologies
The hardware rate limiting feature is enabled by the RATELIMIT kernel
option. Please refer to ifconfig(8) and the txrtlmt option and the
SO_MAX_PACING_RATE set socket option for more information. This
feature is compatible with hardware transmit send offload, TSO.
A set of sysctl(8) knobs under dev.mce.<N>.rate_limit are provided to
setup the ratelimit table and also to fine tune various rate limit
related parameters.
Sponsored by: Mellanox Technologies
According to the 802.1Q-2014 9.6 VLAN Tag Control Information, VID value 0
means that there is no VLAN tag assigned to the packet, and only PCP and
DEI values from the tag are meaningful. Current flow table programming
filter out such packets.
When programming VLAN filter for flow table, unconditionally add rule which
accept packets with VLAN id 0. The packets are already handled correctly
by the network stack.
Reviewed by: hselasky, slavash
Sponsored by: Mellanox Technologies
MFC after: 1 week
This fixes 32-bit compat (no ioctl command defintions are required
as struct ifreq is the same size). This is believed to be sufficent to
fully support ifconfig on 32-bit systems.
Reviewed by: kib
Obtained from: CheriBSD
MFC after: 1 week
Relnotes: yes
Sponsored by: DARPA, AFRL
Differential Revision: https://reviews.freebsd.org/D14900
error state.
If the device is in internal error state the hardware will not
generate completions. Just move on to destroy the resources.
Submitted by: slavash@
MFC after: 1 week
Sponsored by: Mellanox Technologies
The mlx5e_destroy_ifp() function may be called from the system workqueue and
in this case trying to flush all works will cause a dead lock.
Instead of using the system workqueue, create a designated workqueue
for each mlx5en(4) device instance.
Submitted by: slavash@
MFC after: 1 week
Sponsored by: Mellanox Technologies
When the mlx5en(4) driver was converted to using BUSDMA(9) the call to
m_defrag() was moved after the part of the TX routine that strips the
header from the mbuf chain. Before it called m_defrag it first trimmed
off the now-empty mbufs from the start of the chain. This has the side
effect of also removing the head of the chain that has M_PKTHDR set.
m_defrag() will not defrag a chain that does not have M_PKTHDR set,
thus it was effectively never defragging the mbuf chains.
As it turns out, trimming the mbufs in this fashion is unnecessary since
the call to bus_dmamap_load_mbuf_sg doesn't map empty mbufs anyway, so
remove it.
Differential Revision: https://reviews.freebsd.org/D12050
Submitted by: mjoras@
MFC after: 1 week
Sponsored by: Mellanox Technologies
Set and report vport MTU rather than physical MTU,
The driver will set both vport and physical port mtu
and will rely on the query of vport mtu.
SRIOV VFs have to report their MTU to their vport manager (PF),
and this will allow them to work with any MTU they need
without failing the request.
Also for some cases where the PF is not a port owner, PF can
work with MTU less than the physical port mtu if set physical
port mtu didn't take effect.
Based on Linux upstream commit:
cd255efff9baadd654d6160e52d17ae7c568c9d3
Submitted by: Meny Yossefi <menyy@mellanox.com>
MFC after: 1 week
Sponsored by: Mellanox Technologies
Currently the ifnet interface is named mceX, where X is a monotonically
incremented value. If the device is reset due to a fatal error, then the
interface name will change. Using the device unit number will keep the
naming consistent across the reset logic.
Submitted by: Matthew Finlay <matt@mellanox.com>
MFC after: 1 week
Sponsored by: Mellanox Technologies
Add support for PFC and implement reading the per priority statistics
using the sysctl(8) interface. PFC is used together with VLAN priority
and can be enabled and disabled on a per priority basis.
Global pause frames and PFC are incompatible features and surrounding
logic has been added to warn the user about misconfiguration.
Update relevant mlx5core APIs for PFC configuration.
MFC after: 1 week
Sponsored by: Mellanox Technologies
Add support for mapping priority to traffic class via sysctl
Submitted by: Slava Shwartsman <slavash@mellanox.com>
MFC after: 1 week
Sponsored by: Mellanox Technologies
