reside on their own cache line to prevent false sharing with other
nearby structures, especially for those in the .bss segment.
NB: Those mutexes and rwlocks with variables next to them that get
changed on every invocation do not benefit from their own cache line.
Actually it may be net negative because two cache misses would be
incurred in those cases.
of helper functions:
- carp_master() - boolean function which is true if an address
is in the MASTER state.
- ifa_preferred() - boolean function that compares two addresses,
and is aware of CARP.
Utilize ifa_preferred() in ifa_ifwithnet().
The previous version of patch also changed source address selection
logic in jails using carp_master(), but we failed to negotiate this part
with Bjoern. May be we will approach this problem again later.
Reported & tested by: Anton Yuzhaninov <citrin citrin.ru>
Sponsored by: Nginx, Inc
of the newer drivers. The basic problem was
that the driver was pulling the mbuf off the
drbr ring and then when sending with xmit(), encounting
a full transmit ring. Thus the lower layer
xmit() function would return an error, and the
drivers would then append the data back on to the ring.
For TCP this is a horrible scenario sure to bring
on a fast-retransmit.
The fix is to use drbr_peek() to pull the data pointer
but not remove it from the ring. If it fails then
we either call the new drbr_putback or drbr_advance
method. Advance moves it forward (we do this sometimes
when the xmit() function frees the mbuf). When
we succeed we always call advance. The
putback will always copy the mbuf back to the top
of the ring. Note that the putback *cannot* be used
with a drbr_dequeue() only with drbr_peek(). We most
of the time, in putback, would not need to copy it
back since most likey the mbuf is still the same, but
sometimes xmit() functions will change the mbuf via
a pullup or other call. So the optimial case for
the single consumer is to always copy it back. If
we ever do a multiple_consumer (for lagg?) we
will need a test and atomic in the put back possibly
a seperate putback_mc() in the ring buf.
Reviewed by: jhb@freebsd.org, jlv@freebsd.org
around the problem where high speed interfaces (such as ixgbe(4))
are not able to report real ifi_baudrate. bascially, take a spare
byte from struct if_data and use it to store ifi_baudrate power
factor. in other words,
real ifi_baudrate = ifi_baudrate * 10 ^ ifi_baudrate power factor
this should be backwards compatible with old binaries. use ixgbe(4)
as an example on how drivers would set ifi_baudrate power factor
Discussed with: kib, scottl, glebius
MFC after: 1 week
tree used it incorrectly, which lead to inaccurate overrated
if_obytes accounting. The drbr(9) used to update ifnet stats on
drbr_enqueue(), which is not accurate since enqueuing doesn't
imply successful processing by driver. Dequeuing neither mean
that. Most drivers also called drbr_stats_update() which did
accounting again, leading to doubled if_obytes statistics. And
in case of severe transmitting, when a packet could be several
times enqueued and dequeued it could have been accounted several
times.
o Thus, make drbr(9) API thinner. Now drbr(9) merely chooses between
ALTQ queueing or buf_ring(9) queueing.
- It doesn't touch the buf_ring stats any more.
- It doesn't touch ifnet stats anymore.
- drbr_stats_update() no longer exists.
o buf_ring(9) handles its stats itself:
- It handles br_drops itself.
- br_prod_bytes stats are dropped. Rationale: no one ever
reads them but update of a common counter on every packet
negatively affects performance due to excessive cache
invalidation.
- buf_ring_enqueue_bytes() reduced to buf_ring_enqueue(), since
we no longer account bytes.
o Drivers handle their stats theirselves: if_obytes, if_omcasts.
o mlx4(4), igb(4), em(4), vxge(4), oce(4) and ixv(4) no longer
use drbr_stats_update(), and update ifnet stats theirselves.
o bxe(4) was the most correct driver, it didn't call
drbr_stats_update(), thus it was the only driver accurate under
moderate load. Now it also maintains stats itself.
o ixgbe(4) had already taken stats from hardware, so just
- drop software stats updating.
- take multicast packet count from hardware as well.
o mxge(4) just no longer needs NO_SLOW_STATS define.
o cxgb(4), cxgbe(4) need no change, since they obtain stats
from hardware.
Reviewed by: jfv, gnn
Merge ether_ipfw_chk() and part of bridge_pfil() into
unified ipfw_check_frame() function called by PFIL.
This change was suggested by rwatson? @ DevSummit.
Remove ipfw headers from ether/bridge code since they are unneeded now.
Note this thange introduce some (temporary) performance penalty since
PFIL read lock has to be acquired for every link-level packet.
MFC after: 3 weeks
llentry_free() and arptimer():
o Use callout_init_rw() for lle timeout, this allows us safely
disestablish them.
- This allows us to simplify the arptimer() and make it
race safe.
o Consistently use ifp->if_afdata_lock to lock access to
linked lists in the lle hashes.
o Introduce new lle flag LLE_LINKED, which marks an entry that
is attached to the hash.
- Use LLE_LINKED to avoid double unlinking via consequent
calls to llentry_free().
- Mark lle with LLE_DELETED via |= operation istead of =,
so that other flags won't be lost.
o Make LLE_ADDREF(), LLE_REMREF() and LLE_FREE_LOCKED() more
consistent and provide more informative KASSERTs.
The patch is a collaborative work of all submitters and myself.
PR: kern/165863
Submitted by: Andrey Zonov <andrey zonov.org>
Submitted by: Ryan Stone <rysto32 gmail.com>
Submitted by: Eric van Gyzen <eric_van_gyzen dell.com>
- Stateful TCP offload drivers for Terminator 3 and 4 (T3 and T4) ASICs.
These are available as t3_tom and t4_tom modules that augment cxgb(4)
and cxgbe(4) respectively. The cxgb/cxgbe drivers continue to work as
usual with or without these extra features.
- iWARP driver for Terminator 3 ASIC (kernel verbs). T4 iWARP in the
works and will follow soon.
Build-tested with make universe.
30s overview
============
What interfaces support TCP offload? Look for TOE4 and/or TOE6 in the
capabilities of an interface:
# ifconfig -m | grep TOE
Enable/disable TCP offload on an interface (just like any other ifnet
capability):
# ifconfig cxgbe0 toe
# ifconfig cxgbe0 -toe
Which connections are offloaded? Look for toe4 and/or toe6 in the
output of netstat and sockstat:
# netstat -np tcp | grep toe
# sockstat -46c | grep toe
Reviewed by: bz, gnn
Sponsored by: Chelsio communications.
MFC after: ~3 months (after 9.1, and after ensuring MFC is feasible)
interface address lists that distinguish read locks from write locks.
To preserve the KPI, the previous operations are mapped to the write
lock macros. The lock is still kept as a mutex for now.
Reviewed by: bz
MFC after: 2 weeks
from scratch, copying needed functionality from the old implemenation
on demand, with a thorough review of all code. The main change is that
interface layer has been removed from the CARP. Now redundant addresses
are configured exactly on the interfaces, they run on.
The CARP configuration itself is, as before, configured and read via
SIOCSVH/SIOCGVH ioctls. A new prefix created with SIOCAIFADDR or
SIOCAIFADDR_IN6 may now be configured to a particular virtual host id,
which makes the prefix redundant.
ifconfig(8) semantics has been changed too: now one doesn't need
to clone carpXX interface, he/she should directly configure a vhid
on a Ethernet interface.
To supply vhid data from the kernel to an application the getifaddrs(8)
function had been changed to pass ifam_data with each address. [1]
The new implementation definitely closes all PRs related to carp(4)
being an interface, and may close several others. It also allows
to run a single redundant IP per interface.
Big thanks to Bjoern Zeeb for his help with inet6 part of patch, for
idea on using ifam_data and for several rounds of reviewing!
PR: kern/117000, kern/126945, kern/126714, kern/120130, kern/117448
Reviewed by: bz
Submitted by: bz [1]
- TCP keep* timers
- TCP UTO (adjust from what was there already)
- netmap
- route caching
- user cookie (temporary to allow for the real fix)
Slightly re-shuffle struct ifnet moving fields out of the middle
of spares and to better align.
Discussed with: rwatson (slightly earlier version)
to be assigned to a non-default FIB instance.
You may need to recompile world or ports due to the change of struct ifnet.
Submitted by: cjsp
Submitted by: Alexander V. Chernikov (melifaro ipfw.ru)
(original versions)
Reviewed by: julian
Reviewed by: Alexander V. Chernikov (melifaro ipfw.ru)
MFC after: 2 weeks
X-MFC: use spare in struct ifnet
- introduce drbr_needs_enqueue that returns whether the interface/br needs
an enqueue operation: returns true if altq is enabled or there are
already packets in the ring (as we need to maintain packet order)
- update all drbr consumers
- fix drbr_flush
- avoid using the driver queue (IFQ_DRV_*) in the altq case as the
multiqueue consumer does not provide enough protection, serialize altq
interaction with the main queue lock
- make drbr_dequeue_cond work with altq
Discussed with: kmacy, yongari, jfv
MFC after: 4 weeks
ifmultiaddr structures' reference to the parent interface, unless the parent
interface is really detaching. While here, program only link layer multicast
filters to a wlan's hardware parent interface.
PR: kern/142391, kern/142392
Reviewed by: sam, rpaolo, bms
MFC after: 1 week
address on an interface has changed. This lets stacked interfaces such as
vlan(4) detect that their lower interface has changed and adjust things in
order to keep working. Previously this situation broke at least vlan(4) and
lagg(4) configurations.
The EVENTHANDLER_INVOKE call was not placed within if_setlladdr() due to the
risk of a loop.
PR: kern/142927
Submitted by: Nikolay Denev
IFF_POINTOPOINT link types. The reason was due to the routing
entry returned from the kernel covering the remote end is of an
interface type that does not support ARP. This patch fixes this
problem by providing a hint to the kernel routing code, which
indicates the prefix route instead of the PPP host route should
be returned to the caller. Since a host route to the local end
point is also added into the routing table, and there could be
multiple such instantiations due to multiple PPP links can be
created with the same local end IP address, this patch also fixes
the loopback route installation failure problem observed prior to
this patch. The reference count of loopback route to local end would
be either incremented or decremented. The first instantiation would
create the entry and the last removal would delete the route entry.
MFC after: 5 days
and address aliases. After an interface is brought down and brought
back up again, those self pointing routes disappeared. This patch
ensures after an interface is brought back up, the loopback routes
are reinstalled properly.
Reviewed by: bz
MFC after: immediately
several critical bugs, including race conditions and lock order issues:
Replace the single rwlock, ifnet_lock, with two locks, an rwlock and an
sxlock. Either can be held to stablize the lists and indexes, but both
are required to write. This allows the list to be held stable in both
network interrupt contexts and sleepable user threads across sleeping
memory allocations or device driver interactions. As before, writes to
the interface list must occur from sleepable contexts.
Reviewed by: bz, julian
MFC after: 3 days
- Allow loopback route to be installed for address assigned to
interface of IFF_POINTOPOINT type.
- Install loopback route for an IPv4 interface addreess when the
"useloopback" sysctl variable is enabled. Similarly, install
loopback route for an IPv6 interface address when the sysctl variable
"nd6_useloopback" is enabled. Deleting loopback routes for interface
addresses is unconditional in case these sysctl variables were
disabled after an interface address has been assigned.
Reviewed by: bz
Approved by: re
(DPCPU), as suggested by Peter Wemm, and implement a new per-virtual
network stack memory allocator. Modify vnet to use the allocator
instead of monolithic global container structures (vinet, ...). This
change solves many binary compatibility problems associated with
VIMAGE, and restores ELF symbols for virtualized global variables.
Each virtualized global variable exists as a "reference copy", and also
once per virtual network stack. Virtualized global variables are
tagged at compile-time, placing the in a special linker set, which is
loaded into a contiguous region of kernel memory. Virtualized global
variables in the base kernel are linked as normal, but those in modules
are copied and relocated to a reserved portion of the kernel's vnet
region with the help of a the kernel linker.
Virtualized global variables exist in per-vnet memory set up when the
network stack instance is created, and are initialized statically from
the reference copy. Run-time access occurs via an accessor macro, which
converts from the current vnet and requested symbol to a per-vnet
address. When "options VIMAGE" is not compiled into the kernel, normal
global ELF symbols will be used instead and indirection is avoided.
This change restores static initialization for network stack global
variables, restores support for non-global symbols and types, eliminates
the need for many subsystem constructors, eliminates large per-subsystem
structures that caused many binary compatibility issues both for
monitoring applications (netstat) and kernel modules, removes the
per-function INIT_VNET_*() macros throughout the stack, eliminates the
need for vnet_symmap ksym(2) munging, and eliminates duplicate
definitions of virtualized globals under VIMAGE_GLOBALS.
Bump __FreeBSD_version and update UPDATING.
Portions submitted by: bz
Reviewed by: bz, zec
Discussed with: gnn, jamie, jeff, jhb, julian, sam
Suggested by: peter
Approved by: re (kensmith)
little purpose and are unused in the base system.
The IOCTL functionality is entirely duplicated and routing sockets
provide a richer interface than the kqueue functionality.
Further, it is not practical for these devices to be made sensible in
the face of VIMAGE.
Bump __FreeBSD_version on the off chance that there is any code out
there that actually uses this stuff.
Reviewed by: rwatson
Discussed with: bz, zec
Approved by: re@ (kensmith)
if_addr_rlock() and if_addr_runlock() for regular address lists, and
if_maddr_rlock() and if_maddr_runlock() for multicast address lists.
We will use these in various kernel modules to avoid encoding specific
type and locking strategy information into modules that currently use
IF_ADDR_LOCK() and IF_ADDR_UNLOCK() directly.
MFC after: 6 weeks
a pointer to an ifaddr matching the passed socket address, returns a
boolean indicating whether one was present. In the (near) future,
ifa_ifwithaddr() will return a referenced ifaddr rather than a raw
ifaddr pointer, and the new wrapper will allow callers that care only
about the boolean condition to avoid having to free that reference.
MFC after: 3 weeks
- Unify reference count and lock initialization in a single function,
ifa_init().
- Move tear-down from a macro (IFAFREE) to a function ifa_free().
- Move reference count bump from a macro (IFAREF) to a function ifa_ref().
- Instead of using a u_int protected by a mutex to refcount(9) for
reference count management.
The ifa_mtx is now used for exactly one ioctl, and possibly should be
removed.
MFC after: 3 weeks
by if_free (w/o doing if_attach); move ifq_attach to if_alloc and
rename ifq_attach/detach to ifq_init/ifq_delete to better identify
their purpose
Reviewed by: jhb, kmacy
Vnet modules and protocol domains may now register destructor
functions to clean up and release per-module state. The destructor
mechanisms can be triggered by invoking "vimage -d", or a future
equivalent command which will be provided via the new jail framework.
While this patch introduces numerous placeholder destructor functions,
many of those are currently incomplete, thus leaking memory or (even
worse) failing to stop all running timers. Many of such issues are
already known and will be incrementaly fixed over the next weeks in
smaller incremental commits.
Apart from introducing new fields in structs ifnet, domain, protosw
and vnet_net, which requires the kernel and modules to be rebuilt, this
change should have no impact on nooptions VIMAGE builds, since vnet
destructors can only be called in VIMAGE kernels. Moreover,
destructor functions should be in general compiled in only in
options VIMAGE builds, except for kernel modules which can be safely
kldunloaded at run time.
Bump __FreeBSD_version to 800097.
Reviewed by: bz, julian
Approved by: rwatson, kib (re), julian (mentor)
CPU for too long period than necessary. Additively, interfaces are kept
polled (in the tick) even if no more packets are available.
In order to avoid such situations a new generic mechanism can be
implemented in proactive way, keeping track of the time spent on any
packet and fragmenting the time for any tick, stopping the processing
as soon as possible.
In order to implement such mechanism, the polling handler needs to
change, returning the number of packets processed.
While the intended logic is not part of this patch, the polling KPI is
broken by this commit, adding an int return value and the new flag
IFCAP_POLLING_NOCOUNT (which will signal that the return value is
meaningless for the installed handler and checking should be skipped).
Bump __FreeBSD_version in order to signal such situation.
Reviewed by: emaste
Sponsored by: Sandvine Incorporated
