Thanks to Natalie Silvanovich from Google for finding and reporting the
issue found by her in the SCTP userland stack.
MFC after: 3 days
X-MFC with: https://svnweb.freebsd.org/changeset/base/360193
in all cases, by adjust snd_una right after the
connection initialization, to include the one byte
in sequence space occupied by the SYN bit.
This does not change the regular ACK processing,
while making the BYTES_THIS_ACK macro to work properly.
PR: 235256
Reviewed by: tuexen (mentor), rgrimes (mentor)
Approved by: tuexen (mentor), rgrimes (mentor)
MFC after: 2 weeks
Sponsored by: NetApp, Inc.
Differential Revision: https://reviews.freebsd.org/D19000
mb_reclaim() calls the protocol drain routines for each protocol in each
domain. Some protocols exist in more than one domain and share drain
routines. In the case of SCTP, it also uses the same drain routine for
its SOCK_SEQPACKET and SOCK_STREAM entries in the same domain.
On systems with INET, INET6, and SCTP all defined, mb_reclaim() calls
sctp_drain() four times. On systems with INET and INET6 defined,
mb_reclaim() calls tcp_drain() twice. mb_reclaim() is the only in-tree
caller of the pr_drain protocol entry.
Eliminate this duplication by ensuring that each pr_drain routine is only
specified for one protocol entry in one domain.
Reviewed by: tuexen
MFC after: 2 weeks
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D24418
One of the goals of the new routing KPI defined in r359823 is to
entirely hide`struct rtentry` from the consumers. It will allow to
improve routing subsystem internals and deliver more features much faster.
This change is one of the ongoing changes to eliminate direct
struct rtentry field accesses.
Additionally, with the followup multipath changes, single rtentry can point
to multiple nexthops.
With that in mind, convert rti_filter callback used when traversing the
routing table to accept pair (rt, nhop) instead of nexthop.
Reviewed by: ae
Differential Revision: https://reviews.freebsd.org/D24440
MSS in two steps and try each candidate two times. However, if two
candidates are the same (which is the case in TCP/IPv6), this candidate
was tested four times. This patch ensures that each candidate actually
reduced the MSS and is only tested 2 times. This reduces the time window
of missclassifying a temporary outage as an MTU issue.
Reviewed by: jtl
MFC after: 1 week
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D24308
While the original implementation of unmapped mbufs was a large
step forward in terms of reducing cache misses by enabling mbufs
to carry more than a single page for sendfile, they are rather
cache unfriendly when accessing the ext_pgs metadata and
data. This is because the ext_pgs part of the mbuf is allocated
separately, and almost guaranteed to be cold in cache.
This change takes advantage of the fact that unmapped mbufs
are never used at the same time as pkthdr mbufs. Given this
fact, we can overlap the ext_pgs metadata with the mbuf
pkthdr, and carry the ext_pgs meta directly in the mbuf itself.
Similarly, we can carry the ext_pgs data (TLS hdr/trailer/array
of pages) directly after the existing m_ext.
In order to be able to carry 5 pages (which is the minimum
required for a 16K TLS record which is not perfectly aligned) on
LP64, I've had to steal ext_arg2. The only user of this in the
xmit path is sendfile, and I've adjusted it to use arg1 when
using unmapped mbufs.
This change is almost entirely mechanical, except that we
change mb_alloc_ext_pgs() to no longer allow allocating
pkthdrs, the change to avoid ext_arg2 as mentioned above,
and the removal of the ext_pgs zone,
This change saves roughly 2% "raw" CPU (~59% -> 57%), or over
3% "scaled" CPU on a Netflix 100% software kTLS workload at
90+ Gb/s on Broadwell Xeons.
In a follow-on commit, I plan to remove some hacks to avoid
access ext_pgs fields of mbufs, since they will now be in
cache.
Many thanks to glebius for helping to make this better in
the Netflix tree.
Reviewed by: hselasky, jhb, rrs, glebius (early version)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D24213
Fix panics related to calling code which expects to be running inside
the NET_EPOCH from outside that epoch.
This leads to panics (with INVARIANTS) such as this one:
panic: Assertion in_epoch(net_epoch_preempt) failed at /usr/src/sys/netinet/if_ether.c:373
cpuid = 7
time = 1586095719
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe0090819700
vpanic() at vpanic+0x182/frame 0xfffffe0090819750
panic() at panic+0x43/frame 0xfffffe00908197b0
arprequest_internal() at arprequest_internal+0x59e/frame 0xfffffe00908198c0
arp_announce_ifaddr() at arp_announce_ifaddr+0x20/frame 0xfffffe00908198e0
carp_master_down_locked() at carp_master_down_locked+0x10d/frame 0xfffffe0090819910
carp_master_down() at carp_master_down+0x79/frame 0xfffffe0090819940
softclock_call_cc() at softclock_call_cc+0x13f/frame 0xfffffe00908199f0
softclock() at softclock+0x7c/frame 0xfffffe0090819a20
ithread_loop() at ithread_loop+0x279/frame 0xfffffe0090819ab0
fork_exit() at fork_exit+0x80/frame 0xfffffe0090819af0
fork_trampoline() at fork_trampoline+0xe/frame 0xfffffe0090819af0
--- trap 0, rip = 0, rsp = 0, rbp = 0 ---
Widen the NET_EPOCH to cover the relevant (callback / task) code.
Differential Revision: https://reviews.freebsd.org/D24302
This is the foundational change for the routing subsytem rearchitecture.
More details and goals are available in https://reviews.freebsd.org/D24141 .
This patch introduces concept of nexthop objects and new nexthop-based
routing KPI.
Nexthops are objects, containing all necessary information for performing
the packet output decision. Output interface, mtu, flags, gw address goes
there. For most of the cases, these objects will serve the same role as
the struct rtentry is currently serving.
Typically there will be low tens of such objects for the router even with
multiple BGP full-views, as these objects will be shared between routing
entries. This allows to store more information in the nexthop.
New KPI:
struct nhop_object *fib4_lookup(uint32_t fibnum, struct in_addr dst,
uint32_t scopeid, uint32_t flags, uint32_t flowid);
struct nhop_object *fib6_lookup(uint32_t fibnum, const struct in6_addr *dst6,
uint32_t scopeid, uint32_t flags, uint32_t flowid);
These 2 function are intended to replace all all flavours of
<in_|in6_>rtalloc[1]<_ign><_fib>, mpath functions and the previous
fib[46]-generation functions.
Upon successful lookup, they return nexthop object which is guaranteed to
exist within current NET_EPOCH. If longer lifetime is desired, one can
specify NHR_REF as a flag and get a referenced version of the nexthop.
Reference semantic closely resembles rtentry one, allowing sed-style conversion.
Additionally, another 2 functions are introduced to support uRPF functionality
inside variety of our firewalls. Their primary goal is to hide the multipath
implementation details inside the routing subsystem, greatly simplifying
firewalls implementation:
int fib4_lookup_urpf(uint32_t fibnum, struct in_addr dst, uint32_t scopeid,
uint32_t flags, const struct ifnet *src_if);
int fib6_lookup_urpf(uint32_t fibnum, const struct in6_addr *dst6, uint32_t scopeid,
uint32_t flags, const struct ifnet *src_if);
All functions have a separate scopeid argument, paving way to eliminating IPv6 scope
embedding and allowing to support IPv4 link-locals in the future.
Structure changes:
* rtentry gets new 'rt_nhop' pointer, slightly growing the overall size.
* rib_head gets new 'rnh_preadd' callback pointer, slightly growing overall sz.
Old KPI:
During the transition state old and new KPI will coexists. As there are another 4-5
decent-sized conversion patches, it will probably take a couple of weeks.
To support both KPIs, fields not required by the new KPI (most of rtentry) has to be
kept, resulting in the temporary size increase.
Once conversion is finished, rtentry will notably shrink.
More details:
* architectural overview: https://reviews.freebsd.org/D24141
* list of the next changes: https://reviews.freebsd.org/D24232
Reviewed by: ae,glebius(initial version)
Differential Revision: https://reviews.freebsd.org/D24232
The intended change was
sp->next.tqe_next = NULL;
sp->next.tqe_prev = NULL;
which doesn't fix the issue I'm seeing and the committed fix is
not the intended fix due to copy-and-paste.
Thanks a lot to Conrad Meyer for making me aware of the problem.
Reported by: cem
Split their functionality by moving random seed allocation
to SYSINIT and calling (new) generic multipath function from
standard IPv4/IPv5 RIB init handlers.
Differential Revision: https://reviews.freebsd.org/D24356
Before the change, proxyarp checks for src and dst addresses
were performed using default fib, breaking multi-fib scenario.
PR: 245181
Submitted by: Scott Aitken (original version)
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D24244
for IPv4, enabled only for IPv6, and enabled for IPv4 and IPv6.
The current blackhole detection might classify a temporary outage as
an MTU issue and reduces permanently the MSS. Since the consequences of
such a reduction due to a misclassification are much more drastically
for IPv4 than for IPv6, allow the administrator to enable it for IPv6 only.
Reviewed by: bcr@ (man page), Richard Scheffenegger
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D24219
parameters of the timer start and stop routines. Several inconsistencies
have been fixed in earlier commits. Now they will be catched when running
an INVARIANTS system.
MFC after: 1 week
For a Netflix 90Gb/s 100% TLS software kTLS workload, this reduces
the CPI of tcp_m_copym() from ~3.5 to ~2.5 as reported by vtune.
Reviewed by: jtl, rrs
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D23998
these are kernel modules. Also add a KMOD_TCPSTAT_ADD and use that
instead of TCPSTAT_ADD.
Reviewed by: jtl@, rrs@
MFC after: 1 week
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D23904
When I did the use_numa support, I missed the fact that there is
a separate hash function for send tag nic selection. So when
use_numa is enabled, ktls offload does not work properly, as it
does not reliably allocate a send tag on the proper egress nic
since different egress nics are selected for send-tag allocation
and packet transmit. To fix this, this change:
- refectors lacp_select_tx_port_by_hash() and
lacp_select_tx_port() to make lacp_select_tx_port_by_hash()
always called by lacp_select_tx_port()
- pre-shifts flowids to convert them to hashes when calling lacp_select_tx_port_by_hash()
- adds a numa_domain field to if_snd_tag_alloc_params
- plumbs the numa domain into places where we allocate send tags
In testing with NIC TLS setup on a NUMA machine, I see thousands
of output errors before the change when enabling
kern.ipc.tls.ifnet.permitted=1. After the change, I see no
errors, and I see the NIC sysctl counters showing active TLS
offload sessions.
Reviewed by: rrs, hselasky, jhb
Sponsored by: Netflix
cookies, use the same flow label for the segments sent during the
handshake and after the handshake.
This fixes a bug by making sure that sc_flowlabel is always stored in
network byte order.
Reviewed by: bz@
MFC after: 3 days
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D23957
Add four new counters for ND6 related Anti-DoS measures.
We split these out into a separate upfront commit so that we only
change the struct size one time. Implementations using them will
follow.
PR: 157410
Reviewed by: melifaro
MFC after: 2 weeks
X-MFC: cannot really MFC this without breaking netstat
Sponsored by: Netflix (initially)
Differential Revision: https://reviews.freebsd.org/D22711
sending a TCP segment from the TCP SYN cache (like a SYN-ACK).
This fix initialises it to zero. This is correct for the ECN bits,
but is does not honor the DSCP what an application might have set via
the IPPROTO_IPV6 level socket options IPV6_TCLASS. That will be
fixed separately.
Reviewed by: Richard Scheffenegger
MFC after: 3 days
Sponsored by: Netflix, Inc.
Differential Revision: https://reviews.freebsd.org/D23900
