was committed in r295133, CSUM_TSO gets always disabled by em(4) on the
first invocation of em_init_locked() given that at that point no link is
established, yet. In turn, this causes CSUM_TSO also to be off when em(4)
is used as a parent device for vlan(4), i. e. besides IFCAP_TSO4, also
IFCAP_VLAN_HWTSO effectively doesn't work.
In head an attempt to fix this was made with r308345, but that revision
had several problems on its own. One of which was that r308345 caused
IFCAP_TSO4 to also be cleared from both the interface capability and
capability enable bits. Thus, once a link switched from gigabit to a
lower speed, TSO no longer could be enabled, even not via ifconfig(8).
So this change moves the aforementioned WAR to em_update_link_status()
like r308345 did, but only alters the hardware assist bits accordingly,
leaving IFCAP_TSO4 flags alone.
Still, this isn't the only problem r308345 had. Another one is that there
just is no way to atomically flush TSO-using descriptors already queued
at the point in time a link speed switch to below GbE occurs. Thus, such
in-flight descriptors still may hang the MAC. Moreover, at least currently
there also is no way of triggering a reconfiguration of vlan(4) when the
state of IFCAP_VLAN_HWTSO support changes at runtime, causing vlan(4) to
continue employing TSO. Last but not least, testing shows that - despite
all the WARs for TSO-related silicon bugs in em(4) - at least 82579 still
may hang at gigabit speed with IFCAP_TSO4 enabled. Therefore, this change
further removes IFCAP_TSO4 and IFCAP_VLAN_HWTSO from interface capability
enable bits as set by em(4). While at it, the use of CSUM_TCP is replaced
with CSUM_IP_TSO as em(4) only implements support for IFCAP_TSO4 but not
IFCAP_TSO6 (although in principle available with a subset of the supported
MACs).
At the bottom line, this change allows IFCAP_TSO4 and IFCAP_VLAN_HWTSO to
be used again with em(4), but these hardware offloading capabilities now
need to be explicitly enabled via ifconfig(8). Beware that it's only
considered safe to do so (and also only may work) in environments where
the link speed is not to be expected to change from GbE. Moreover, em(4)
appears to still be missing some more TSO workarounds for at least some
models, specifically the 82579 (I could not find an errata sheet and
"specification update" respectively for these latter, though, and the
generic ICH8 one doesn't list any TSO related bugs).
- Let igb_tso_setup() handle EtherType protocols that are unsupported or
for which support hasn't been compiled in gracefully instead of calling
panic(9).
- Make em_allocate_{legacy,msix}() and lem_allocate_irq() match their
prototypes WRT static.
This is a direct commit to stable/11 as corresponding code is no longer
present in head.
Don't set any WOL enabling hardware bits if WOL isn't requested
according to the enabled interface capability bits. Also remove
some dead code, which tried to preserve already set contents of
E1000_WUC while that register is completely overwritten shortly
after in all cases.
registers to the same values when processing interrupts. This reverts a
change made in r286831 that was not fully reverted in r311979
This resolves PR https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211219
PR: 211219
Submitted by: Franco Fitchner <[email protected]>
Approved by: re (marius)
issues when trying to passthrough a i340 (igb) to VMware.
While here, cleanup some bits of em(4) to DTRT as well.
PR: 218113
Submitted by: Kaho Toshikazu <[email protected]>
interface is used.
The legacy API (IGB_LEGACY_TX) is enabled when ALTQ is built into kernel.
As noted in altq(9), it is responsibility of the caller to protect this
queue against concurrent access and, in the igb case, the interface send
queue is protected by tx queue mutex. This obviously cannot protect the
driver managed queue against concurrent access from different tx queues
and leads to numerous and quite strange panic traces (usually shown as
packets disappearing into thin air).
Improving the locking to cope with this means serialize all access to this
(single) queue and produces no gain, it actually affects the performance
quite noticeabily.
The driver managed queue is already disabled when an ALTQ queue discipline
is set on interface (in altq_enable()), because the driver managed queue
can interfere with ALTQ timing (whence the reports that setting an ALTQ
queue discipline on interface also fixes the issue).
Disabling this additional queue keeps the ability to use if_start() to
send packets to individual NIC queues while it simply eliminate the race.
This is a direct commit to stable/11 as -head driver does not support ALTQ
anymore.
PR: 213257
PR: 212413
Discussed with: sbruno
Tested by: Konstantin Kormashev <[email protected]>
Obtained from: pfSense
Sponsored by: Rubicon Communications, LLC (Netgate)
free'd by the functions following its call, we can simply return instead
of crashing and burning in the event of igb_detach() failing.
PR: 197139
Submitted by: [email protected]
MFC after: 2 weeks
And factor out tcp_lro_rx_done, which deduplicates the same logic with
netinet/tcp_lro.c
Reviewed by: gallatin (1st version), hps, zbb, np, Dexuan Cui <decui microsoft com>
Sponsored by: Microsoft OSTC
Differential Revision: https://reviews.freebsd.org/D5725
- At Intel it is believed that most of their products support "only"
40 DMA segments so lower {EM,IGB}_MAX_SCATTER accordingly. Actually,
40 is more than plenty to handle full size TSO packets so it doesn't
make sense to further distinguish between MAC variants that really
can do 64 DMA segments. Moreover, capping at 40 DMA segments limits
the stack usage of {em,igb}_xmit() that - given the rare use of more
than these - previously hardly was justifiable, while still being
sufficient to avoid the problems seen with em(4) and EM_MAX_SCATTER
set to 32.
- In igb(4), pass the actually supported TSO parameters up the stack.
Previously, the defaults set in if_attach_internal() were applied,
i. e. a maximum of 35 TSO segments, which made supporting more than
these in the driver pointless. However, this might explain why no
problems were seen with IGB_MAX_SCATTER at 64.
- In em(4), take the 5 m_pullup(9) invocations performed by em_xmit()
in the TSO case into account when reporting TSO parameters upwards.
In the worst case, each of these calls will add another mbuf and,
thus, the requirement for an additional DMA segment. So for best
performance, it doesn't make sense to advertize a maximum of TSO
segments that typically will require defragmentation in em_xmit().
Again, this leaves enough room to handle full size TSO packets.
- Drop TSO macros from if_lem.h given that corresponding MACS don't
support TSO in the first place.
Reviewed by: erj, sbruno, jeffrey.e.pieper_intel.com
Approved by: erj
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D5238
Major changes:
- Add i219/i219(2) hardware support. (Found on Skylake generation and newer
chipsets.)
- Further to the last Skylake support diff, this one also includes support for
the Lewisburg chipset (i219(3)).
- Add a workaround to an igb hardware errata.
All 1G server products need to have IPv6 extension header parsing turned off.
This should be listed in the specification updates for current 1G server
products, e.g. for i350 it's errata #37 in this document:
http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/ethernet-controller-i350-spec-update.pdf
- Avoton (i354) PHY errata workaround added
And a bunch of minor fixes, as well as #defines for things that the current
em(4)/igb(4) drivers don't implement.
Differential Revision: https://reviews.freebsd.org/D3162
Reviewed by: sbruno, marius, gnn
Approved by: gnn
MFC after: 2 weeks
Sponsored by: Intel Corporation
causes watchdog timeouts when using TSO4 at link speeds below
Gigabit, at least with 82573E. So disable the assist automatically
when at lower speeds.
Submitted by: jfv
Approved by: erj
Obtained from: D3162
MFC after: 3 days
- Add optimizing LRO wrapper which pre-sorts all incoming packets
according to the hash type and flowid. This prevents exhaustion of
the LRO entries due to too many connections at the same time.
Testing using a larger number of higher bandwidth TCP connections
showed that the incoming ACK packet aggregation rate increased from
~1.3:1 to almost 3:1. Another test showed that for a number of TCP
connections greater than 16 per hardware receive ring, where 8 TCP
connections was the LRO active entry limit, there was a significant
improvement in throughput due to being able to fully aggregate more
than 8 TCP stream. For very few very high bandwidth TCP streams, the
optimizing LRO wrapper will add CPU usage instead of reducing CPU
usage. This is expected. Network drivers which want to use the
optimizing LRO wrapper needs to call "tcp_lro_queue_mbuf()" instead
of "tcp_lro_rx()" and "tcp_lro_flush_all()" instead of
"tcp_lro_flush()". Further the LRO control structure must be
initialized using "tcp_lro_init_args()" passing a non-zero number
into the "lro_mbufs" argument.
- Make LRO statistics 64-bit. Previously 32-bit integers were used for
statistics which can be prone to wrap-around. Fix this while at it
and update all SYSCTL's which expose LRO statistics.
- Ensure all data is freed when destroying a LRO control structures,
especially leftover LRO entries.
- Reduce number of memory allocations needed when setting up a LRO
control structure by precomputing the total amount of memory needed.
- Add own memory allocation counter for LRO.
- Bump the FreeBSD version to force recompilation of all KLDs due to
change of the LRO control structure size.
Sponsored by: Mellanox Technologies
Reviewed by: gallatin, sbruno, rrs, gnn, transport
Tested by: Netflix
Differential Revision: https://reviews.freebsd.org/D4914
alignment guarantees provided by m_defrag(9), use m_collapse(9)
instead for performance reasons.
While at it, sanitize the statistics softc members, i. e. retire
unused ones and add SYSCTL nodes missing for actually used ones.
Differential Revision: https://reviews.freebsd.org/D4717
e1000/e1000e split in linux.
Split rxbuffer and txbuffer apart to support the new RX descriptor format
structures. Move rxbuffer manipulation to em_setup_rxdesc() to unify the
new behavior changes.
Add a RSSKEYLEN macro for help in generating the RSSKEY data structures
in the card.
Change em_receive_checksum() to process the new rxdescriptor format
status bit.
MFC after: 2 weeks
Sponsored by: Limelight Networks
Differential Revision: https://reviews.freebsd.org/D3447
to attach with the last version of this commit. This commit fixes
attach failures on "ICH8" class devices via modifications to
e1000_init_nvm_params_ich8lan()
- Fix compiler warning in 80003es2lan.c
- Add return value handler for e1000_*_kmrn_reg_80003es2lan
- Fix usage of DEBUGOUT
- Remove unnecessary variable initializations.
- Removed unused variables (complaints from gcc).
- Edit defines in 82571.h.
- Add workaround for igb hw errata.
- Shared code changes for Skylake/I219 support.
- Remove unused OBFF and LTR functions.
Tested by some of the folks that reported breakage in previous incarnation.
Thanks to AllanJude, gjb, gnn, tijl for tempting fate with their machines.
Submitted by: [email protected]
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D3162
doesn't get overrun by things like NFS that can and do shove more than 32 segs when
being used with em(4) and TSO4.
Update tso handling code in em_xmit() with update from jhb@ in email thread:
https://lists.freebsd.org/pipermail/freebsd-net/2014-July/039306.html
set ifp->if_hw_tsomax, ifp->if_hw_tsomaxsegcount & ifp->if_hw_tsomaxsegsize
to appropriate values.
Define a TSO workaround "magic" number of 4 that is used to avoid an
alignment issue in hardware.
Change a couple of integer values that were used as booleans to actual
bool types.
Ensure that em_enable_intr() enables the appropriate mask of interrupts
and not just a hardcoded define of values.
PR: 200221 199174 195078
Differential Revision: https://reviews.freebsd.org/D3192
Reviewed by: erj jhb hiren
MFC after: 2 weeks
Sponsored by: Limelight Networks
This commit contains large contributions from Giuseppe Lettieri and
Stefano Garzarella, is partly supported by grants from Verisign and Cisco,
and brings in the following:
- fix zerocopy monitor ports and introduce copying monitor ports
(the latter are lower performance but give access to all traffic
in parallel with the application)
- exclusive open mode, useful to implement solutions that recover
from crashes of the main netmap client (suggested by Patrick Kelsey)
- revised memory allocator in preparation for the 'passthrough mode'
(ptnetmap) recently presented at bsdcan. ptnetmap is described in
S. Garzarella, G. Lettieri, L. Rizzo;
Virtual device passthrough for high speed VM networking,
ACM/IEEE ANCS 2015, Oakland (CA) May 2015
http://info.iet.unipi.it/~luigi/research.html
- fix rx CRC handing on ixl
- add module dependencies for netmap when building drivers as modules
- minor simplifications to device-specific routines (*txsync, *rxsync)
- general code cleanup (remove unused variables, introduce macros
to access rings and remove duplicate code,
Applications do not need to be recompiled, unless of course
they want to use the new features (monitors and exclusive open).
Those willing to try this code on stable/10 can just update the
sys/dev/netmap/*, sys/net/netmap* with the version in HEAD
and apply the small patches to individual device drivers.
MFC after: 1 month
Sponsored by: (partly) Verisign, Cisco
Marius Strobl