Virtualise tcp_always_keepalive, TCP and UDP log_in_vain. All three are
set in the netoptions startup script, which we would love to run for VNETs
as well [1].
While virtualising the log_in_vain sysctls seems pointles at first for as
long as the kernel message buffer is not virtualised, it at least allows
an administrator to debug the base system or an individual jail if needed
without turning the logging on for all jails running on a system.
PR: 243193 [1]
MFC after: 2 weeks
improvements, the ECN bits need to be exposed to the TCP SYNcache.
This change is a minimal modification to the function headers, without any
functional change intended.
Submitted by: Richard Scheffenegger
Reviewed by: rgrimes@, rrs@, tuexen@
Differential Revision: https://reviews.freebsd.org/D22436
This adds support for ifnet (NIC) KTLS using Chelsio T6 adapters.
Unlike the TOE-based KTLS in r353328, NIC TLS works with non-TOE
connections.
NIC KTLS on T6 is not able to use the normal TSO (LSO) path to segment
the encrypted TLS frames output by the crypto engine. Instead, the
TOE is placed into a special setup to permit "dummy" connections to be
associated with regular sockets using KTLS. This permits using the
TOE to segment the encrypted TLS records. However, this approach does
have some limitations:
1) Regular TOE sockets cannot be used when the TOE is in this special
mode. One can use either TOE and TOE-based KTLS or NIC KTLS, but
not both at the same time.
2) In NIC KTLS mode, the TOE is only able to accept a per-connection
timestamp offset that varies in the upper 4 bits. Put another way,
only connections whose timestamp offset has the 28 lower bits
cleared can use NIC KTLS and generate correct timestamps. The
driver will refuse to enable NIC KTLS on connections with a
timestamp offset with any of the lower 28 bits set. To use NIC
KTLS, users can either disable TCP timestamps by setting the
net.inet.tcp.rfc1323 sysctl to 0, or apply a local patch to the
tcp_new_ts_offset() function to clear the lower 28 bits of the
generated offset.
3) Because the TCP segmentation relies on fields mirrored in a TCB in
the TOE, not all fields in a TCP packet can be sent in the TCP
segments generated from a TLS record. Specifically, for packets
containing TCP options other than timestamps, the driver will
inject an "empty" TCP packet holding the requested options (e.g. a
SACK scoreboard) along with the segments from the TLS record.
These empty TCP packets are counted by the
dev.cc.N.txq.M.kern_tls_options sysctls.
Unlike TOE TLS which is able to buffer encrypted TLS records in
on-card memory to handle retransmits, NIC KTLS must re-encrypt TLS
records for retransmit requests as well as non-retransmit requests
that do not include the start of a TLS record but do include the
trailer. The T6 NIC KTLS code tries to optimize some of the cases for
requests to transmit partial TLS records. In particular it attempts
to minimize sending "waste" bytes that have to be given as input to
the crypto engine but are not needed on the wire to satisfy mbufs sent
from the TCP stack down to the driver.
TCP packets for TLS requests are broken down into the following
classes (with associated counters):
- Mbufs that send an entire TLS record in full do not have any waste
bytes (dev.cc.N.txq.M.kern_tls_full).
- Mbufs that send a short TLS record that ends before the end of the
trailer (dev.cc.N.txq.M.kern_tls_short). For sockets using AES-CBC,
the encryption must always start at the beginning, so if the mbuf
starts at an offset into the TLS record, the offset bytes will be
"waste" bytes. For sockets using AES-GCM, the encryption can start
at the 16 byte block before the starting offset capping the waste at
15 bytes.
- Mbufs that send a partial TLS record that has a non-zero starting
offset but ends at the end of the trailer
(dev.cc.N.txq.M.kern_tls_partial). In order to compute the
authentication hash stored in the trailer, the entire TLS record
must be sent as input to the crypto engine, so the bytes before the
offset are always "waste" bytes.
In addition, other per-txq sysctls are provided:
- dev.cc.N.txq.M.kern_tls_cbc: Count of sockets sent via this txq
using AES-CBC.
- dev.cc.N.txq.M.kern_tls_gcm: Count of sockets sent via this txq
using AES-GCM.
- dev.cc.N.txq.M.kern_tls_fin: Count of empty FIN-only packets sent to
compensate for the TOE engine not being able to set FIN on the last
segment of a TLS record if the TLS record mbuf had FIN set.
- dev.cc.N.txq.M.kern_tls_records: Count of TLS records sent via this
txq including full, short, and partial records.
- dev.cc.N.txq.M.kern_tls_octets: Count of non-waste bytes (TLS header
and payload) sent for TLS record requests.
- dev.cc.N.txq.M.kern_tls_waste: Count of waste bytes sent for TLS
record requests.
To enable NIC KTLS with T6, set the following tunables prior to
loading the cxgbe(4) driver:
hw.cxgbe.config_file=kern_tls
hw.cxgbe.kern_tls=1
Reviewed by: np
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D21962
ccr(4) and TLS support in cxgbe(4) construct key contexts used by the
crypto engine in the T6. This consolidates some duplicated code for
helper functions used to build key contexts.
Reviewed by: np
MFC after: 1 month
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D22156
Previously the table was allocated on first use by TOE and the
ratelimit code. The forthcoming NIC KTLS code also uses this table.
Allocate it unconditionally during attach to simplify consumers.
Reviewed by: np
Differential Revision: https://reviews.freebsd.org/D22028
This adds a TOE hook to allocate a KTLS session. It also recognizes
TLS mbufs in the socket buffer and sends those to the NIC using a TLS
work request to encrypt the record before segmenting it.
TOE TLS support must be enabled via the dev.t6nex.<N>.tls sysctl in
addition to enabling KTLS.
Reviewed by: np, gallatin
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D21891
There are several mechanisms by which a vm_page reference is held,
preventing the page from being freed back to the page allocator. In
particular, holding the page's object lock is sufficient to prevent the
page from being freed; holding the busy lock or a wiring is sufficent as
well. These references are protected by the page lock, which must
therefore be acquired for many per-page operations. This results in
false sharing since the page locks are external to the vm_page
structures themselves and each lock protects multiple structures.
Transition to using an atomically updated per-page reference counter.
The object's reference is counted using a flag bit in the counter. A
second flag bit is used to atomically block new references via
pmap_extract_and_hold() while removing managed mappings of a page.
Thus, the reference count of a page is guaranteed not to increase if the
page is unbusied, unmapped, and the object's write lock is held. As
a consequence of this, the page lock no longer protects a page's
identity; operations which move pages between objects are now
synchronized solely by the objects' locks.
The vm_page_wire() and vm_page_unwire() KPIs are changed. The former
requires that either the object lock or the busy lock is held. The
latter no longer has a return value and may free the page if it releases
the last reference to that page. vm_page_unwire_noq() behaves the same
as before; the caller is responsible for checking its return value and
freeing or enqueuing the page as appropriate. vm_page_wire_mapped() is
introduced for use in pmap_extract_and_hold(). It fails if the page is
concurrently being unmapped, typically triggering a fallback to the
fault handler. vm_page_wire() no longer requires the page lock and
vm_page_unwire() now internally acquires the page lock when releasing
the last wiring of a page (since the page lock still protects a page's
queue state). In particular, synchronization details are no longer
leaked into the caller.
The change excises the page lock from several frequently executed code
paths. In particular, vm_object_terminate() no longer bounces between
page locks as it releases an object's pages, and direct I/O and
sendfile(SF_NOCACHE) completions no longer require the page lock. In
these latter cases we now get linear scalability in the common scenario
where different threads are operating on different files.
__FreeBSD_version is bumped. The DRM ports have been updated to
accomodate the KPI changes.
Reviewed by: jeff (earlier version)
Tested by: gallatin (earlier version), pho
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20486
Remove now-redundant items from toepcb and synq_entry and the code to
support them.
Let the driver calculate tx_align, rx_coalesce, and sndbuf by default.
Reviewed by: jhb@
MFC after: 1 week
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D21387
descriptor. The per-tid tx credits are in demand during active Tx and
it's best not to use too many just for payload.
Sponsored by: Chelsio Communications
The hold_count and wire_count fields of struct vm_page are separate
reference counters with similar semantics. The remaining essential
differences are that holds are not counted as a reference with respect
to LRU, and holds have an implicit free-on-last unhold semantic whereas
vm_page_unwire() callers must explicitly determine whether to free the
page once the last reference to the page is released.
This change removes the KPIs which directly manipulate hold_count.
Functions such as vm_fault_quick_hold_pages() now return wired pages
instead. Since r328977 the overhead of maintaining LRU for wired pages
is lower, and in many cases vm_fault_quick_hold_pages() callers would
swap holds for wirings on the returned pages anyway, so with this change
we remove a number of page lock acquisitions.
No functional change is intended. __FreeBSD_version is bumped.
Reviewed by: alc, kib
Discussed with: jeff
Discussed with: jhb, np (cxgbe)
Tested by: pho (previous version)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D19247
Previously the TOE code used its own custom unmapped mbufs via
EXT_FLAG_VENDOR1. The old version always wired the entire AIO request
buffer first for the duration of the AIO operation and constructed
multiple mbufs which used the wired buffer as an external buffer.
The new version determines how much room is available in the socket
buffer and only wires the pages needed for the available room building
chains of M_NOMAP mbufs. This means that a large AIO write will now
limit the amount of wired memory it uses to the size of the socket
buffer.
Reviewed by: gallatin, np
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D20839
Since cxgbe(4) uses sglist instead of bus_dma, this required updates
to the code that generates scatter/gather lists for packets. Also,
unmapped mbufs are always sent via DMA and never as immediate data in
the payload of a work request.
Submitted by: gallatin (earlier version)
Reviewed by: gallatin, hselasky, rrs
Discussed with: np
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20616
handle_ddp_close.
This eliminates a bad race where an aio_ddp_requeue that happened to run
after handle_ddp_close could bump up the active count.
Discussed with: jhb@
MFC after: 3 days
Sponsored by: Chelsio Communications
t_maxseg was changed in r293284 to not have any adjustment for TCP
timestamps. t4_tom inadvertently went back to pre-r293284 semantics
in r332506.
Sponsored by: Chelsio Communications
Previously, the aiotx task relied on the aio jobs in the queue to hold
a reference on the socket. However, when the last job is completed,
there is nothing left to hold a reference to the socket buffer lock
used to check if the queue is empty. In addition, if the last job on
the queue is cancelled, the task can run with no queued jobs holding a
reference to the socket buffer lock the task uses to notice the queue
is empty.
Fix these races by holding an explicit reference on the socket when
the task is queued and dropping that reference when the task
completes.
Reviewed by: np
MFC after: 1 week
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D20539
receive sockbuf's high water mark.
Calculate rx credits on the spot instead of tracking sbused/sb_cc and
rx_credits in the toepcb. The previous method worked when the high
water mark changed due to SB_AUTOSIZE but not when it was adjusted
directly (for example, by the soreserve in nfsrvd_addsock).
This fixes a connection hang while running iozone over an NFS mounted
share where nfsd's TCP sockets are being handled by t4_tom.
MFC after: 3 days
Sponsored by: Chelsio Communications
it hasn't been initialized.
This fixes a bug in r346570 that could cause a panic when servicing
TCP_INFO for offloaded connections.
MFC after: 3 days
Sponsored by: Chelsio Communications
This allows replacing "sys/eventfilter.h" includes with "sys/_eventfilter.h"
in other header files (e.g., sys/{bus,conf,cpu}.h) and reduces header
pollution substantially.
EVENTHANDLER_DECLARE and EVENTHANDLER_LIST_DECLAREs were moved out of .c
files into appropriate headers (e.g., sys/proc.h, powernv/opal.h).
As a side effect of reduced header pollution, many .c files and headers no
longer contain needed definitions. The remainder of the patch addresses
adding appropriate includes to fix those files.
LOCK_DEBUG and LOCK_FILE_LINE_ARG are moved to sys/_lock.h, as required by
sys/mutex.h since r326106 (but silently protected by header pollution prior
to this change).
No functional change (intended). Of course, any out of tree modules that
relied on header pollution for sys/eventhandler.h, sys/lock.h, or
sys/mutex.h inclusion need to be fixed. __FreeBSD_version has been bumped.
The declaration in tcp_var.h is still around so t4_tom continued to
compile but wouldn't load. A separate commit will fix tcp_var.h
Reported By: Dustin Marquess (dmarquess at gmail)
Sponsored by: Chelsio Communications
Recent firmwares prefer to use a different format for viid internally
and this change allows them to do so.
MFC after: 1 week
Sponsored by: Chelsio Communications
- Fix PR 227760 by getting the TOE to respond to the SYN after the call
to toe_syncache_add, not during it. The kernel syncache code calls
syncache_respond just before syncache_insert. If the ACK to the
syncache_respond is processed in another thread it may run before the
syncache_insert and won't find the entry. Note that this affects only
t4_tom because it's the only driver trying to insert and expand
syncache entries from different threads.
- Do not leak resources if an embryonic connection terminates at
SYN_RCVD because of L2 lookup failures.
- Retire lctx->synq and associated code because there is never a need to
walk the list of embryonic connections associated with a listener.
The per-tid state is still called a synq entry in the driver even
though the synq itself is now gone.
PR: 227760
MFC after: 2 weeks
Sponsored by: Chelsio Communications
- 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
vmem's are not just used for TLS memory in TOM and the #include actually
predates the TLS code so should not have been removed when the TLS vmem
moved in r340466.
Pointy hat to: jhb
Sponsored by: Chelsio Communications
The key context is always placed immediately after the work request
header. The total work request length has to be rounded up by 16
however.
MFC after: 1 month
Sponsored by: Chelsio Communications
For TOE TLS, we just want to advance the send pointer to skip over the
record just sent to the TOE. The recently added sbsndptr_adv() is
sufficient for that and is cheaper.
MFC after: 1 month
Sponsored by: Chelsio Communications
r254889 added tcp_state_change() as a centralized place to log state
changes in TCP connections for DTrace. r294869 and r296881 took
advantage of this central location to manage per-state counters.
However, TOE sockets were still performing some (but not all) state
change updates via direct assignments to t_state. This resulted in
state counters underflowing when TOE was in use. Fix by using
tcp_state_change() when changing a TOE connection's state.
Reviewed by: np, markj
MFC after: 1 month
Sponsored by: Chelsio Communications
Differential Revision: https://reviews.freebsd.org/D17915
- Switch to using 32b port/link capabilities in the driver. The 32b
format is used internally by firmwares > 1.16.45.0 and the driver will
now interact with the firmware in its native format, whether it's 16b
or 32b. Note that the 16b format doesn't have room for 50G, 200G, or
400G speeds.
- Add a bit in the pause_settings knobs to allow negotiated PAUSE
settings to override manual settings.
- Ensure that manual link settings persist across an administrative
down/up as well as transceiver unplug/replug.
- Remove unused is_*G_port() functions.
Approved by: re@ (gjb@)
MFC after: 1 month
Sponsored by: Chelsio Communications
own region in the TCAM starting with T6, unlike previous chips where
they were in the same region as normal filters.
These filters "hit" before anything else in the LE's lookup. The exact
order is:
a) High priority filters
b) TOE's active region (TCAM and/or hash)
c) Servers (TOE hw listeners)
d) Normal filters
MFC after: 1 week
Sponsored by: Chelsio Communications
