mlx4 currently uses a too high tx coalescing setting, deferring
TX completion interrupts by up to 128 us.
With the recent skb_orphan() removal in commit 8112ec3b87,
performance of a single TCP flow is capped to ~4 Gbps, unless
we increase tcp_limit_output_bytes.
I suggest using 16 us instead of 128 us, allowing a finer control.
Performance of a single TCP flow is restored to previous levels,
while keeping TCP small queues fully enabled with default sysctl.
This patch is also a BQL prereq.
Reported-by: Vimalkumar <j.vimal@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yevgeny Petrilin <yevgenyp@mellanox.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Acked-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RFS filter id can't have the special value RPS_NO_FILTER,
need to skip it when allocating id's.
CC: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use RFS infrastructure and flow steering in HW to keep CPU
affinity of rx interrupts and application per TCP stream.
A flow steering filter is added to the HW whenever the RFS
ndo callback is invoked by core networking code.
Because the invocation takes place in interrupt context, the
actual setup of HW is done using workqueue. Whenever new filter
is added, the driver checks for expiry of existing filters.
Since there's window in time between the point where the core
RFS code invoked the ndo callback, to the point where the HW
is configured from the workqueue context, the 2nd, 3rd etc
packets from that stream will cause the net core to invoke
the callback again and again.
To prevent inefficient/double configuration of the HW, the filters
are kept in a database which is indexed using hash function to enable
fast access.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We dereferenced "mclist" after the kfree().
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The drop action is implemented by allocating a QP and keeping it in a reset state
such that the HW drops any packets which are steered to that QP. When a drop action
is requested, we attach the relevant flow to that QP.
Sign-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The device managed flow steering API has three promiscuous modes:
1. Uplink - captures all the packets that arrive to the port.
2. Allmulti - captures all multicast packets arriving to the port.
3. Function port - for future use, this mode is not implemented yet.
Use these modes with the flow_attach and flow_detach firmware commands
according to the promiscuous state of the netdevice.
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The driver is modified to support three operation modes.
If supported by firmware use the device managed flow steering
API, that which we call device managed steering mode. Else, if
the firmware supports the B0 steering mode use it, and finally,
if none of the above, use the A0 steering mode.
When the steering mode is device managed, the code is modified
such that L2 based rules set by the mlx4_en driver for Ethernet
unicast and multicast, and the IB stack multicast attach calls
done through the mlx4_ib driver are all routed to use the device
managed API.
When attaching rule using device managed flow steering API,
the firmware returns a 64 bit registration id, which is to be
provided during detach.
Currently the firmware is always programmed during HCA initialization
to use standard L2 hashing. Future work should be done to allow
configuring the flow-steering hash function with common, non
proprietary means.
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of checking the firmware supported steering mode in various
places in the code, add a dedicated field in the mlx4 device capabilities
structure which is written once during the initialization flow and read
across the code.
This also set the grounds for add new steering modes. Currently two modes
are supported, and are named after the ConnectX HW versions A0 and B0.
A0 steering uses mac_index, vlan_index and priority to steer traffic
into pre-defined range of QPs.
B0 steering uses Ethernet L2 hashing rules and is enabled only
if the firmware supports both unicast and multicast B0 steering,
The current steering modes are relevant for Ethernet traffic only,
such that Infiniband steering remains untouched.
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, for every change in the net device multicast list, the driver
detaches all the addresses from the HW device, and then attaches the
updated list. This behavior is wrong from two aspects: first, it causes
a load of firmware commands and second, there is period of time where
the correct addresses are not attached, which turned into packet loss.
To improve - a copy of the multicast list is saved by the driver. For
every change in the multicast list, the multicast list copy is used
to find the delta between those two lists and add or remove multicast
addresses as needed.
Reported-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a missing resource release in ring cleanup.
Not doing this leaves a range of QPs that are being reserved,
and no one can use them.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set valid port parameters: MTU and flow control configuration when
configuring the port during HW device initialization,
prior to the net device open() being called.
Using invalid parameters (such as all zeros)
could lead to bad firmware behavior.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change the TX ring scheme such that the number of rings for untagged packets
and for tagged packets (per each of the vlan priorities) is the same, unlike
the current situation where for tagged traffic there's one ring per priority
and for untagged rings as the number of core.
Queue selection is done as follows:
If the mqprio qdisc is operates on the interface, such that the core networking
code invoked the device setup_tc ndo callback, a mapping of skb->priority =>
queue set is forced - for both, tagged and untagged traffic.
Else, the egress map skb->priority => User priority is used for tagged traffic, and
all untagged traffic is sent through tx rings of UP 0.
The patch follows the convergence of discussing that issue with John Fastabend
over this thread http://comments.gmane.org/gmane.linux.network/229877
Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Liran Liss <liranl@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moving to interrupts instead of polling fpr TX completions
Avoiding situations where skb can be held in by the driver for
a long time (till timer expires).
The change is also necessary for supporting BQL.
Removing comp_lock that was required because we could handle TX
completions from several contexts: Interrupts, timer, polling.
Now there is only interrupts
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since vlan egress map is only good for tagged traffic, need to have other
mapping to be used by untagged traffic.
For that, the driver uses sch_mqprio mapping. This mapping could be set by
using tc tool from iproute2 package.
Mapped UP will be used by the HW for QoS purposes, but won't go out on the
wire.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set TSA, promised BW and PFC using IEEE 802.1qaz netlink commands.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of relying on HW to change schedule queue by UP, schedule
queue is fixed for a tx_ring, and UP in WQE is ignored in this aspect. This
resolves two issues with untagged traffic:
1. untagged traffic has no UP in packet which is needed for QoS. The change
above allows setting the schedule queue (and by that the UP) of such a stream.
2. BlueFlame uses the same field used by vlan tag. So forcing UP from QPC
allows using BF for untagged but prioritized traffic.
In old firmware that force UP is not supported, untagged traffic will not subject to
QoS.
Because UP is set by QP, need to always have a tx ring per UP, even if pfcrx
module paramter is false.
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Localized the pdev->dev, and using dma_map instead of pci_map
There are multiple map/unmap operations on data path,
optimizing those by saving redundant pointer access.
Those places were identified as hot-spots when running kernel profiling
during some benchmarks.
The fixes had most impact when testing packet rate with small packets,
reducing several % from CPU load, and in some case being the difference
between reaching wire speed or being CPU bound.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
After opening the network interface, Mellanox ConnectX device cannot be
removed by hotplug because it has not properly unmapped all DMA memory.
It happens that mlx4_en_activate_rx_rings overrides the variable that
keeps the size of the memory mapped.
This is fixed by passing to mlx4_en_destroy_rx_ring the same size that is
given to mlx4_en_create_rx_ring.
After applying this patch, hot unplugging the device works after opening
the interface.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
alloc_etherdev has a generic OOM/unable to alloc message.
Remove the duplicative messages after alloc_etherdev calls.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In native mode display all available staticstics.
In SRIOV mode on VF display only SW counters statistics,
in SRIOV mode on hypervisor display SW counters and errors (got from FW)
statistics.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Bug fix: Not all stats fields were cleared.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Reviewed-by: Yevgeny Petriln <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Solves an issue where we tried to free the same page twice after
the port has been opened and closed.
Signed-off-by: Alexander Guller <alexg@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The physical port is now common to the PF and VFs.
The port resources and configuration is managed by the PF, VFs can
only influence the MTU of the port, it is set as max among all functions,
Each function allocates RX buffers of required size to meet it's MTU enforcement.
Port management code was moved to mlx4_core, as the mlx4_en module is
virtualization unaware
Move handling qp functionality to mlx4_get_eth_qp/mlx4_put_eth_qp
including reserve/release range and add/release unicast steering.
Let mlx4_register/unregister_mac deal only with MAC (un)registration.
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Let caller know the result of adding/removing vlan id to/from vlan
filter.
In some drivers I make those functions to just return 0. But in those
where there is able to see if hw setup went correctly, return value is
set appropriately.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Device must be in promiscuous mode or DMAC must be same as the host MAC, or
else packet will be dropped by the HW rx filtering.
Signed-off-by: Amir Vadai <amirv@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moving to Toeplitz function in RSS calculation.
Reporting rxhash in skb.
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Netdevice was being freed without being unregistered first if
mlx4_SET_PORT_general or mlx4_INIT_PORT failed.
Signed-off-by: Alexander Guller <alexg@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moderation is now done per ring and coalescing is enabled
by set_ring_param in ethtool.
Signed-off-by: Alexander Guller <alexg@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixed a bug where ring size change caused insufficient memory
upon driver restart due to unreleased EQs.
Signed-off-by: Alexander Guller <alexg@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Until now only RX rings used irq per ring
and TX used only one per port.
>From now on, both of them will use the
irq per ring while RX & TX ring[i] will
use the same irq.
Signed-off-by: Alexander Guller <alexg@mellanox.co.il>
Signed-off-by: Sharon Cohen <sharonc@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Moves the Mellanox driver into drivers/net/ethernet/mellanox/ and
make the necessary Kconfig and Makefile changes.
CC: Roland Dreier <roland@kernel.org>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2011-08-11 02:41:35 -07:00
Renamed from drivers/net/mlx4/en_netdev.c (Browse further)
