This allows the "irdma" driver to communicate with the ice(4)
driver to allow it access to the underlying device's hardware
resources as well as synchronize access to shared resources.
This interface already existed in the standalone out-of-tree
1.34.2 driver; this commit adds and enables it in the in-kernel
driver.
Note:
Adds hack to module Makefile to compile interface/.m files
These are required for the RDMA client interface, but they don't
build as-is like the normal .c files. The source directory doesn't
seem to be included by default, so add lines that specifically
add them as libraries so that ice_rdma.h can be found and the
interface files will compile.
Signed-off-by: Eric Joyner <erj@FreeBSD.org>
MFC after: 1 week
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D30889
The previous commit (56429daea2) that updated the driver included a
bug where a variable was undefined when ALTQ was enabled; this fixes
that issue to declare the missing variable. This wasn't caught before
because we don't use ALTQ, and so it fell on the Jenkins CI's LINT
builds to catch it.
Signed-off-by: Eric Joyner <erj@FreeBSD.org>
Reported by: Jenkins CI
MFC after: 3 days
MFC with: 56429daea2
Sponsored by: Intel Corporation
- Adds FW logging support
- Once enabled, this lets the firmware print event and error messages
to the log, increasing the visibility into what the hardware is
doing; this is useful for debugging
- General bug fixes
- Adds inital DCB support to the driver
- Notably, this adds support for DCBX to the driver; now with the
fw_lldp sysctl set to 1, the driver and adapter will adopt a DCBX
configuration sent from a link partner
- Adds statistcs sysctls for priority flow control frames
- Adds new configuration sysctls for DCB-related features: (VLAN) user
priority to TC mapping; ETS bandwidth allocation; priority flow
control
- Remove unused SR-IOV files (until support gets added)
Signed-off-by: Eric Joyner <erj@FreeBSD.org>
Tested by: jeffrey.e.pieper@intel.com
MFC after: 3 days
MFC with: 213e91399b, e438f0a975
Relnotes: yes
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D34024
The logic that sets iri_vtag and M_VLANTAG does not handle the
case where the 802.11q VLAN tag is 0. Fix this issue across
the iflib drivers. While there, also improve and align the
VLAN tag check extraction, by moving it outside the RX descriptor
loop, eliminating a local variable and additional checks.
PR: 260068
Reviewed by: kbowling, gallatin
Reported by: erj
MFC after: 1 month
Differential Revision: https://reviews.freebsd.org/D33156
Since isc_capenable (private copy of ifp->if_capenable) is
now synchronized to if_capenable, use it in the drivers
when checking the IFCAP_* bits.
This results in better cache usage and avoids indirection
through the ifp pointer.
PR: 260068
Reviewed by: kbowling, gallatin
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D33156
Includes various feature improvements and bug fixes.
Notable changes include:
- Firmware logging support
- Link management flow changes
- New sysctl to report aggregated error counts
- Health Status Event reporting from firmware (Use the new read-only
tunables hw.ice.enable_health_events / dev.ice.#.enable_health_events
to turn this off)
Signed-off-by: Eric Joyner <erj@FreeBSD.org>
Sponsored by: Intel Corporation
This updates the driver to align with the version included in
the "Intel Ethernet Adapter Complete Driver Pack", version 25.6.
There are no major functional changes; this mostly contains
bug fixes and changes to prepare for new features. This version
of the driver uses the previously committed ice_ddp package
1.3.19.0.
Signed-off-by: Eric Joyner <erj@FreeBSD.org>
Tested by: jeffrey.e.pieper@intel.com
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D28640
Doing a 'dd' over iscsi will reliably cause stalls. Tx
cleaning _should_ reliably happen as data is sent.
However, currently if the transmit queue fills it will
wait until the iflib timer (hz/2) runs.
This change causes the the tx taskq thread to be run
if there are completed descriptors.
While here:
- make timer interrupt delay a sysctl
- simplify txd_db_check handling
- comment on INTR types
Background on the change:
Initially doorbell updates were minimized by only writing to the register
on every fourth packet. If txq_drain would return without writing to the
doorbell it scheduled a callout on the next tick to do the doorbell write
to ensure that the write otherwise happened "soon". At that time a sysctl
was added for users to avoid the potential added latency by simply writing
to the doorbell register on every packet. This worked perfectly well for
e1000 and ixgbe ... and appeared to work well on ixl. However, as it
turned out there was a race to this approach that would lockup the ixl MAC.
It was possible for a lower producer index to be written after a higher one.
On e1000 and ixgbe this was harmless - on ixl it was fatal. My initial
response was to add a lock around doorbell writes - fixing the problem but
adding an unacceptable amount of lock contention.
The next iteration was to use transmit interrupts to drive delayed doorbell
writes. If there were no packets in the queue all doorbell writes would be
immediate as the queue started to fill up we could delay doorbell writes
further and further. At the start of drain if we've cleaned any packets we
know we've moved the state machine along and we write the doorbell (an
obvious missing optimization was to skip that doorbell write if db_pending
is zero). This change required that tx interrupts be scheduled periodically
as opposed to just when the hardware txq was full. However, that just leads
to our next problem.
Initially dedicated msix vectors were used for both tx and rx. However, it
was often possible to use up all available vectors before we set up all the
queues we wanted. By having rx and tx share a vector for a given queue we
could halve the number of vectors used by a given configuration. The problem
here is that with this change only e1000 passed the necessary value to have
the fast interrupt drive tx when appropriate.
Reported by: mav@
Tested by: mav@
Reviewed by: gallatin@
MFC after: 1 month
Sponsored by: iXsystems
Differential Revision: https://reviews.freebsd.org/D27683
Summary of changes:
- Assorted bug fixes
- Support for newer versions of the device firmware
- Suspend/resume support
- Support for Lenient Link Mode for E82X devices (e.g. can try to link with
SFP/QSFP modules with bad EEPROMs)
- Adds port-level rx_discards sysctl, similar to ixl(4)'s
This version of the driver is intended to be used with DDP package 1.3.16.0,
which has already been updated in a previous commit.
Tested by: Jeffrey Pieper <jeffrey.e.pieper@intel.com>
MFC after: 3 days
MFC with: r365332, r365550
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D26322
The ice(4) driver is the driver for the Intel E8xx series Ethernet
controllers; currently with codenames Columbiaville and
Columbia Park.
These new controllers support 100G speeds, as well as introducing
more queues, better virtualization support, and more offload
capabilities. Future work will enable virtual functions (like
in ixl(4)) and the other functionality outlined above.
For full functionality, the kernel should be compiled with
"device ice_ddp" like in the amd64 NOTES file, and/or
ice_ddp_load="YES" should be added to /boot/loader.conf so that
the DDP package file included in this commit can be downloaded
to the adapter. Otherwise, the adapter will fall back to a single
queue mode with limited functionality.
A man page for this driver will be forthcoming.
MFC after: 1 month
Relnotes: yes
Sponsored by: Intel Corporation
Differential Revision: https://reviews.freebsd.org/D21959
