The mark value for MATCH_ACTION_MARK has a maximum value.
Requesting a value larger than the maximum will cause the
filter insertion to fail with EINVAL. This patch allows the
driver to check the value at the filter validation.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18240
This patch adds support for DPDK rte_flow "MARK" and "FLAG" filter
actions to filters on EF10 family NICs.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18239
Filter actions MARK and FLAG are supported on Medford2 by DPDK
firmware variant.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18238
Equal stride super-buffer Rx mode is supported by DPDK firmware
variant. One Rx descriptor provides many Rx buffers to firmware.
Rx buffers follow each other with specified stride.
Also it supports head of line blocking with timeout to address
drops when no Rx descriptors are available. So it gives extra time
to the driver to provide Rx descriptors before drop.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18236
The type is an internal interface. Single integer is insufficient
to carry RxQ type-specific information in the case of equal stride
super-buffer Rx mode (packet buffers per bucket, maximum DMA length,
packet stride, head of line block timeout).
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18234
Equal stride super-buffer is a new name instead of deprecated equal
stride packed stream to avoid confusion with previous packed stream.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18233
Packed stream firmware variant on EF10 adapters has a
number of properties which must be taken into account:
- Only one exclusive RSS context is available per port.
- Only IP addresses can contribute to the hash value.
Huntington and Medford have one more limitation which
is important for the drivers capable of packed stream:
- Hash algorithm is non-standard (i.e. non-Toeplitz).
This implies XORing together source + destination
IP addresses (or last four bytes in the case of IPv6)
and using the result as the input to a Toeplitz hash.
This patch provides a number of improvements in order
to treat the mentioned limitations in the common code.
If the firmware variant is packed stream, the list of
supported hash tuples will include less variants, and
the maximum number of RSS contexts will be set to one.
Submitted by: Ivan Malov <ivan.malov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18232
Modern firmwares on EF10 adapters have support for
more traffic classes eligible for hash computation.
Also, it has become possible to adjust hashing per
individual class and select distinct packet fields
which will be able to contribute to the hash value.
This patch adds support for the mentioned features.
Submitted by: Ivan Malov <ivan.malov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18231
Currently, libefx has no support for additional RSS modes
available with later controllers. In order to support this,
libefx should be able to list available hash configurations.
This patch provides basic infrastructure for the new interface.
The client drivers will be able to query the list of supported
hash configurations for a particular hash algorithm. Also, it
will be possible to configure hashing by means of new definitions.
Submitted by: Ivan Malov <ivan.malov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18230
clang 4.0.1-6 on Ubuntu generates false positive warning that shift
is negative. It is done regardless of the fact that the branch is
not taken because of previous check.
The warning is generate in EFX_INSERT_NATIVE32 used by
EFX_INSERT_FIELD_NATIVE32. All similar cases are fixed as well.
It is undesirable to suppress the warning completely.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18229
Loopback type used as bit index has efx_loopback_type_t type
which is enum. clang complains that it is always true when it
is compared with qword (64 bit) bits number boundary.
Sponsored by: Solarflare Communications, Inc.
MFC after: 1 week
Differential Revision: https://reviews.freebsd.org/D18228
If DPDK application or OS does not need checksumming on transmit,
it may be disabled in firmware to achieve higher packet rates.
Choice must be done before VIS allocation and is allowed if
no other non-preboot and firmware subvariant-unaware drivers are
attached.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18227
FW subvariants allow to tweak NIC global features. For example,
if no drivers require checksumming on transmit, it may be disabled
in FW to increase packet rate.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18225
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18223
Add support for filters which drop packets when forming MCDI request
for a filter.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18221
Add filter match flag to distinguish filters applied only to
encapsulated packets.
Match flags set should allow to determine whether a filter
is supported or not. The problem is that if specification
has supported set outer match flags and specified
encapsulation without any inner flags, check says that it
is supported, and filter insertion is performed. However,
there is no filtering of the encapsulated traffic. A new
flag is added to solve this problem and separate the
filters for the encapsulated packets.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18220
This supports VNI/VSID and inner frame local MAC fields to
match in VXLAN, GENEVE, or NVGRE packets.
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18218
This adds filters for encapsulated packets to the list
returned by ef10_filter_supported_filters().
Submitted by: Roman Zhukov <roman.zhukov at oktetlabs.ru>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18217
Regenerate MCDI and TLV layout headers from firmwaresrc to
pick up DPDK firmware variant and related Rx queue and filtering
extensions.
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18216
Submitted by: Andy Moreton <amoreton at solarflare.com>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18215
Submitted by: Andy Moreton <amoreton at solarflare.com>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18214
racct is not enabled by default and even when it is enabled processes are
typically not throttled. The order of checks is left unchanged since
racct_enable will be annotated as __read_frequently, while checking for the
flag in the processes would probably require an extra fetch.
Sponsored by: The FreeBSD Foundation
Summary:
Currently, truss doesn't work on ELFv2 processes due to not recognizing the ABI.
Since there's no special handling needed here, just adding a PROCABI struct for
it is sufficient to get it working.
Submitted by: git_bdragon.rtk0.net
Differential Revision: https://reviews.freebsd.org/D18352
Summary:
Currently, the upcall used to create threads assumes ELFv1.
Instead, we should check which sysentvec is in use on the process and act
accordingly.
This makes ELFv2 threaded processes work.
Submitted by: git_bdragon.rtk0.net
Differential Revision: https://reviews.freebsd.org/D18330
waitpid always takes proctree to evaluate the list, but only takes allproc
if it can reap. With this patch allproc is no longer taken, which helps during
poudriere -j 128.
Discussed with: kib
Sponsored by: The FreeBSD Foundation
- Store the clip table in 'struct adapter' instead of in the TOM softc.
- Init the clip table during attach and teardown during detach.
- While here, add a dev.<nexus>.<unit>.misc.clip sysctl to dump the
CLIP table.
This does mean that we update the clip table even if TOE is not enabled,
but non-TOE things need the CLIP table anyway.
Reviewed by: np, Krishnamraju Eraparaju @ Chelsio
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D18010
If word in ${param?word} is missing, the shell shall write a default error
message. So expanding ${param?} when param is not set should write an error
message like
sh: param: parameter not set
This was broken by r316417.
PR: 233585
several pages, but leaves no space for struct uma_slab at the end we
miscalculate number of pages by one. Totally mimic keg_large_init() math
here to cover that problem.
Reported by: gallatin
is calculated to guarantee that struct uma_slab is placed at pointer size
alignment. Calculation of real struct uma_slab size is done in keg_ctor()
and yet again in keg_large_init(), to check if we need an extra page. This
calculation can actually be performed at compile time.
- Add SIZEOF_UMA_SLAB macro to calculate size of struct uma_slab placed at
an end of a page with alignment requirement.
- Use SIZEOF_UMA_SLAB in keg_ctor() and in keg_large_init(). This is a not
a functional change.
- Use SIZEOF_UMA_SLAB in UMA_SLAB_SPACE definition and in keg_small_init().
This is a potential bugfix, but in reality I don't think there are any
systems affected, since compiler aligns struct uma_slab anyway.
The first packet after the ring is initialized was never
completed as isc_txd_credits_update() would not include it in the
count of completed packets. This caused netmap to never complete
a batch. See PR 233022 for more details.
This is the same fix as the r340310 for e1000
PR: 233607
Reported by: lev
Reviewed by: lev
MFC after: 3 days
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D18368
A related future change, which changes KERNBASE for Book-E for some reason
causes a "KERNBASE redefined" error with assym.inc, even though it only changed
the value of KERNBASE and nothing else. Since machine/vmparam.h is already
included in booke/locore.S, and the requisite guards are already in place for
properly handling KERNBASE in vmparam.h, just remove it from genassym, and
include vmparam.h in the AIM locore files.
After the fix contained in r341144, cxgbe does not need anymore
to set the IFCAP_NETMAP flag manually.
Reviewed by: np
Approved by: gnn (mentor)
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D17987
Revision r307394 removed (by mistake) the code that sets IFCAP_NETMAP
in if_capabilities on netmap_attach. This patch reverts this change.
Reviewed by: np
Approved by: gnn (mentor)
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D17987
Set outer_ip_id in the TX option descriptor for encapsulated packets.
Submitted by: Vijay Srivastava <vijays at solarflare.com>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18213
Submitted by: Andy Moreton <amoreton at solarflare.com>
Sponsored by: Solarflare Communications, Inc.
Differential Revision: https://reviews.freebsd.org/D18211
