- Copy stable/10 (r259064) to releng/10.0 as part of the
10.0-RELEASE cycle.
- Update __FreeBSD_version [1]
- Set branch name to -RC1

[1] 10.0-CURRENT __FreeBSD_version value ended at '55', so
start releng/10.0 at '100' so the branch is started with
a value ending in zero.

Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation

Copy head (r256279) to stable/10 as part of the 10.0-RELEASE cycle.

Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation

Retire netisr.netisr_direct and netisr.netisr_direct_force sysctls.
These were used to control/export dispatch policy but they're not anymore.
This commit cannot be MFC'ed to 9 because old netstat(9) binary relies
on such sysctl to work. On the other hand, there's no real reason to
keep'em around in 10.

Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.

The SYSCTL_NODE macro defines a list that stores all child-elements of
that node. If there's no SYSCTL_DECL macro anywhere else, there's no
reason why it shouldn't be static.

On multi-core, multi-threaded PPC systems, it is important that the threads
be brought up in the order they are enumerated in the device tree (in
particular, that thread 0 on each core be brought up first). The SLIST
through which we loop to start the CPUs has all of its entries added with
SLIST_INSERT_HEAD(), which means it is in reverse order of enumeration
and so AP startup would always fail in such situations (causing a machine
check or RTAS failure). Fix this by changing the SLIST into an STAILQ,
and inserting new CPUs at the end.

Reviewed by: jhb

Rework netisr policy mechanism so that per-protocol dispatch policies can
be represented:

- A single policy namespace is defined, consisting of four possible
policies: "default" to use the global default, "deferred" to force
deferred dispatch, "direct" to employ direct dispatch where possible, and
"hybrid" which makes a dynamic decision based on CPU affinity, ordering,
etc. Routines are implemented to convert between strings and an integer
namespace.

- A new global variable, netisr_dispatch_policy, subsumes existing global
variables for direct dispatch, forced direct dispatch, etc, and is used
for explicit policy interpretation and composition. Old variables remain
so that they can be exported by legacy sysctls for use by old netstat(1)
binaries. A new sysctl and tunable, netisr.dispatch.policy, accepts the
above strings for specifying a global policy default.

- The protocol registration structure, netisr_handler, grows an nh_dispatch
field, which accepts a per-policy policy override. The default value is
'0', which corresponds to "default", meaning that protocols will accept
the global default policy unless otherwise specified.

- Policies are now interpreted and composed explicitly at various points in
packet dispatch; protocol policies override global policies.

- Protocols grow the ability to express a non-opinion about affinity even
when implenting m2cpuid by returning NETISR_CPUID_NONE. In that case, the
framework falls back on source ordering, rather than simply using the
current CPU.

These changes are in support of allowing link layer re-dispatch based on
RSS or similar hashes provided by NICs, especially in the case where the
number of hardware receive queues matches hardware core count, rather than
hardware thread count, requiring further software redistributeon. (i.e.,
on RMI XLR).

MFC after: 3 weeks
Reviewed by: bz
Sponsored by: Juniper Networks, Inc.

Mfp4 CH=177255:

Make VNET_ASSERT() available with either VNET_DEBUG or INVARIANTS.

Change the syntax to match KASSERT() to allow more flexible panic
messages rather than having a printf with hardcoded arguments
before panic.

Adjust the few assertions we have to the new format (and enhance
the output).

Sponsored by: The FreeBSD Foundation
Sponsored by: CK Software GmbH
Reviewed by: jhb

MFC after: 2 weeks

sysctl(9) cleanup checkpoint: amd64 GENERIC builds cleanly.

Commit the net* piece.

Update several places that iterate over CPUs to use CPU_FOREACH().

Changes to support crashdump analysis of netisr:

- Rename the netisr protocol registration array, 'np' to 'netisr_proto',
in order to reduce the chances of symbol name collisions. It remains
statically defined, but it will be looked up by netstat(1).

- Move certain internal structure definitions from netisr.c to
netisr_internal.h so that netstat(1) can find them. They remain
private, and should not be used for any other purpose (for example,
they should not be used by kernel modules, which must instead use the
public interfaces in netisr.h).

- Store a kernel-compiled version of NETISR_MAXPROT in the global variable
netisr_maxprot, and export via a sysctl, so that it is available for use
by netstat(1). This is especially important for crashdump
interpretation, where the size of the workstream structure is determined
by the maximum number of protocols compiled into the kernel.

MFC after: 1 week
Sponsored by: Juniper Networks

Fix edge cases in several KASSERTs: use <= rather than < when testing that
counters have not gone about MAXCPU or NETISR_MAXPROT. These problems
caused panics on UP kernels with INVARIANTS when using sysctl -a, but
would also have caused problems for 32-core boxes or if the netisr
protocol vector was fully populated.

Reported by: nwhitehorn, Neel Natu <neelnatu@gmail.com>
MFC after: 4 days

Export netisr configuration and statistics to userspace via sysctl(9).

MFC after: 1 week
Sponsored by: Juniper Networks

Mark various sysctls also as tunables.

Reviewed by: rwatson
MFC after: 1 week

When warning about possible netisr configuration problems during boot,
report using "netisr_init" rather than "netisr2", which was the development
name for the project.

MFC after: 3 days

Refine netisr.c comments a bit.

Merge the remainder of kern_vimage.c and vimage.h into vnet.c and
vnet.h, we now use jails (rather than vimages) as the abstraction
for virtualization management, and what remained was specific to
virtual network stacks. Minor cleanups are done in the process,
and comments updated to reflect these changes.

Reviewed by: bz
Approved by: re (vimage blanket)

In case we cannot queue a packet reaching the queue limit, retain the
semantics netisr_queue() always had and free the mbuf along with
returning the error.

Reviewed by: rwatson
Approved by: re (kensmith)

In light of DPCPU use by netisr, revise various for loops from using
MAXCPU to mp_maxid, and handling and reporting of requests to use more
threads than we have CPUs to run them on.

Reviewed by: bz
Approved by: re (kib)
MFC after: 6 weeks

Convert netisr to use dynamic per-CPU storage (DPCPU) instead of sizing
arrays to [MAXCPU], offering moderate memory savings. In some places,
this requires using CPU_ABSENT() to handle less common platforms with
sparse CPU IDs. In several places, assert that the selected CPUID for
work placement or statistics is not CPU_ABSENT() to be on the safe side.

Discussed with: bz, jeff

Add an optional callback function that will be invoked when a per-CPU
queue was drained. It will never fire for a directly dispatched packet.

You will most likely never want to use this for any ordinary netisr usage
and you will never blame netisr in case you try to use it and it does
not work as expected.

Reviewed by: rwatson

Revert a recent netisr2 change: when billing packets to the current
CPU, don't lock the workstream, as its mutexes may not have been
initialized if there are fewer workstreams than CPUs.

Run into by: hps, ps

Garbage collect NETISR_POLL and NETISR_POLLMORE, which are no longer
required for options DEVICE_POLLING.

De-fragment the NETISR_ constant space and lower NETISR_MAXPROT from
32 to 16 -- when sizing queue arrays using this compile-time constant,
significant amounts of memory are saved.

Warn on the console when tunable values for netisr are automatically
adjusted during boot due to exceeding limits, invalid values, or as a
result of DEVICE_POLLING.

Reimplement the netisr framework in order to support parallel netisr
threads:

- Support up to one netisr thread per CPU, each processings its own
workstream, or set of per-protocol queues. Threads may be bound
to specific CPUs, or allowed to migrate, based on a global policy.

In the future it would be desirable to support topology-centric
policies, such as "one netisr per package".

- Allow each protocol to advertise an ordering policy, which can
currently be one of:

NETISR_POLICY_SOURCE: packets must maintain ordering with respect to
an implicit or explicit source (such as an interface or socket).

NETISR_POLICY_FLOW: make use of mbuf flow identifiers to place work,
as well as allowing protocols to provide a flow generation function
for mbufs without flow identifers (m2flow). Falls back on
NETISR_POLICY_SOURCE if now flow ID is available.

NETISR_POLICY_CPU: allow protocols to inspect and assign a CPU for
each packet handled by netisr (m2cpuid).

- Provide utility functions for querying the number of workstreams
being used, as well as a mapping function from workstream to CPU ID,
which protocols may use in work placement decisions.

- Add explicit interfaces to get and set per-protocol queue limits, and
get and clear drop counters, which query data or apply changes across
all workstreams.

- Add a more extensible netisr registration interface, in which
protocols declare 'struct netisr_handler' structures for each
registered NETISR_ type. These include name, handler function,
optional mbuf to flow ID function, optional mbuf to CPU ID function,
queue limit, and ordering policy. Padding is present to allow these
to be expanded in the future. If no queue limit is declared, then
a default is used.

- Queue limits are now per-workstream, and raised from the previous
IFQ_MAXLEN default of 50 to 256.

- All protocols are updated to use the new registration interface, and
with the exception of netnatm, default queue limits. Most protocols
register as NETISR_POLICY_SOURCE, except IPv4 and IPv6, which use
NETISR_POLICY_FLOW, and will therefore take advantage of driver-
generated flow IDs if present.

- Formalize a non-packet based interface between interface polling and
the netisr, rather than having polling pretend to be two protocols.
Provide two explicit hooks in the netisr worker for start and end
events for runs: netisr_poll() and netisr_pollmore(), as well as a
function, netisr_sched_poll(), to allow the polling code to schedule
netisr execution. DEVICE_POLLING still embeds single-netisr
assumptions in its implementation, so for now if it is compiled into
the kernel, a single and un-bound netisr thread is enforced
regardless of tunable configuration.

In the default configuration, the new netisr implementation maintains
the same basic assumptions as the previous implementation: a single,
un-bound worker thread processes all deferred work, and direct dispatch
is enabled by default wherever possible.

Performance measurement shows a marginal performance improvement over
the old implementation due to the use of batched dequeue.

An rmlock is used to synchronize use and registration/unregistration
using the framework; currently, synchronized use is disabled
(replicating current netisr policy) due to a measurable 3%-6% hit in
ping-pong micro-benchmarking. It will be enabled once further rmlock
optimization has taken place. However, in practice, netisrs are
rarely registered or unregistered at runtime.

A new man page for netisr will follow, but since one doesn't currently
exist, it hasn't been updated.

This change is not appropriate for MFC, although the polling shutdown
handler should be merged to 7-STABLE.

Bump __FreeBSD_version.

Reviewed by: bz

Garbage collect now-unused NETISR_FORCEQUEUE, which overrode the global
direct dispatch policy for specific protocols (NETISR_USB). We leave
the additional 'flags' argument to netisr_register() for the time being,
even though it is no longer required.

Change the curvnet variable from a global const struct vnet *,
previously always pointing to the default vnet context, to a
dynamically changing thread-local one. The currvnet context
should be set on entry to networking code via CURVNET_SET() macros,
and reverted to previous state via CURVNET_RESTORE(). Recursions
on curvnet are permitted, though strongly discuouraged.

This change should have no functional impact on nooptions VIMAGE
kernel builds, where CURVNET_* macros expand to whitespace.

The curthread->td_vnet (aka curvnet) variable's purpose is to be an
indicator of the vnet context in which the current network-related
operation takes place, in case we cannot deduce the current vnet
context from any other source, such as by looking at mbuf's
m->m_pkthdr.rcvif->if_vnet, sockets's so->so_vnet etc. Moreover, so
far curvnet has turned out to be an invaluable consistency checking
aid: it helps to catch cases when sockets, ifnets or any other
vnet-aware structures may have leaked from one vnet to another.

The exact placement of the CURVNET_SET() / CURVNET_RESTORE() macros
was a result of an empirical iterative process, whith an aim to
reduce recursions on CURVNET_SET() to a minimum, while still reducing
the scope of CURVNET_SET() to networking only operations - the
alternative would be calling CURVNET_SET() on each system call entry.
In general, curvnet has to be set in three typicall cases: when
processing socket-related requests from userspace or from within the
kernel; when processing inbound traffic flowing from device drivers
to upper layers of the networking stack, and when executing
timer-driven networking functions.

This change also introduces a DDB subcommand to show the list of all
vnet instances.

Approved by: julian (mentor)

Remove NETISR_MPSAFE, which allows specific netisr handlers to be directly
dispatched without Giant, and add NETISR_FORCEQUEUE, which allows specific
netisr handlers to always be dispatched via a queue (deferred). Mark the
usb and if_ppp netisr handlers as NETISR_FORCEQUEUE, and explicitly
acquire Giant in those handlers.

Previously, any netisr handler not marked NETISR_MPSAFE would necessarily
run deferred and with Giant acquired. This change removes Giant
scaffolding from the netisr infrastructure, but NETISR_FORCEQUEUE allows
non-MPSAFE handlers to continue to force deferred dispatch so as to avoid
lock order reversals between their acqusition of Giant and any calling
context.

It is likely we will be able to remove NETISR_FORCEQUEUE once
IFF_NEEDSGIANT is removed, as non-MPSAFE usb and if_ppp drivers will no
longer be supported.

Reviewed by: bz
MFC after: 1 month
X-MFC note: We can't remove NETISR_MPSAFE from stable/7 for KPI reasons,
but the rest can go back.

In keeping with style(9)'s recommendations on macros, use a ';'
after each SYSINIT() macro invocation. This makes a number of
lightweight C parsers much happier with the FreeBSD kernel
source, including cflow's prcc and lxr.

MFC after: 1 month
Discussed with: imp, rink

Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, which
previously conditionally acquired Giant based on debug.mpsafenet. As that
has now been removed, they are no longer required. Removing them
significantly simplifies error-handling in the socket layer, eliminated
quite a bit of unwinding of locking in error cases.

While here clean up the now unneeded opt_net.h, which previously was used
for the NET_WITH_GIANT kernel option. Clean up some related gotos for
consistency.

Reviewed by: bz, csjp
Tested by: kris
Approved by: re (kensmith)

First in a series of changes to remove the now-unused Giant compatibility
framework for non-MPSAFE network protocols:

- Remove debug_mpsafenet variable, sysctl, and tunable.
- Remove NET_NEEDS_GIANT() and associate SYSINITSs used by it to force
debug.mpsafenet=0 if non-MPSAFE protocols are compiled into the kernel.
- Remove logic to automatically flag interrupt handlers as non-MPSAFE if
debug.mpsafenet is set for an INTR_TYPE_NET handler.
- Remove logic to automatically flag netisr handlers as non-MPSAFE if
debug.mpsafenet is set.
- Remove references in a few subsystems, including NFS and Cronyx drivers,
which keyed off debug_mpsafenet to determine various aspects of their own
locking behavior.
- Convert NET_LOCK_GIANT(), NET_UNLOCK_GIANT(), and NET_ASSERT_GIANT into
no-op's, as their entire behavior was determined by the value in
debug_mpsafenet.
- Alias NET_CALLOUT_MPSAFE to CALLOUT_MPSAFE.

Many remaining references to NET_.*_GIANT() and NET_CALLOUT_MPSAFE are still
present in subsystems, and will be removed in followup commits.

Reviewed by: bz, jhb
Approved by: re (kensmith)

Change net.isr.direct from defaulting to 0 to 1 in 7-CURRENT. This
enables direct dispatch of the network stack from the device driver
ithread, enabling input path parallelism by default when multiple
interfaces are present.

The strategy for network stack parallelism is something being actively
discussed, and this is just one of several possible (and perfectly
reasonable) strategies, but has the distinct advantage of reducing the
number of context switches and preemptions significantly, resulting in
higher efficiency in many cases. In some caes, this may reduce
network stack parallelism due to work not being deferred from the
ithread to the netisr. Therefore, the strategy may change in the
future, but this offers a reasonable first pass and enabling
parallelism while maintaining strong ordering.

Hopefully this will trigger lots of nice new bugs.

This change is not intended for MFC.

- Don't pollute opt_global.h with DEVICE_POLLING and introduce
opt_device_polling.h
- Include opt_device_polling.h into appropriate files.
- Embrace with HAVE_KERNEL_OPTION_HEADERS the include in the files that
can be compiled as loadable modules.

Reviewed by: bde

Rename net.isr.enable to net.isr.dispatch.

No compatibility code is provided, as this will be the production name
as of 6.0.

MFC after: 3 days
Requested by: scottl

Correctly unregister a netisr by clearing the ni->ni_queue field to NULL as
well. This field is actually used by various netisr functions to determine
the availablility of the specified netisr. This uncomplete unregister leads
directly to a crash when the KLD unregistering the netisr is unloaded.

Submitted by: Sam <sah@softcardsystems.com>
MFC after: 3 days

Correct a comment typo: s/Note/Not/.

Pointed out by: kensmith

Correct typo in printf() warning.

Submitted by: Pawel Worach <pawel.worach at telia.com>

Change the default disposition of debug.mpsafenet from 0 to 1, which
will cause the network stack to operate without the Giant lock by
default. This change has the potential to improve performance by
increasing parallelism and decreasing latency in network processing.

Due to the potential exposure of existing or new bugs, the following
compatibility functionality is maintained:

- It is still possible to disable Giant-free operation by setting
debug.mpsafenet to 0 in loader.conf.

- Add "options NET_WITH_GIANT", which will restore the default value of
debug.mpsafenet to 0, and is intended for use on systems compiled with
known unsafe components, or where a more conservative configuration is
desired.

- Add a new declaration, NET_NEEDS_GIANT("componentname"), which permits
kernel components to declare dependence on Giant over the network
stack. If the declaration is made by a preloaded module or a compiled
in component, the disposition of debug.mpsafenet will be set to 0 and
a warning concerning performance degraded operation printed to the
console. If it is declared by a loadable kernel module after boot, a
warning is displayed but the disposition cannot be changed. This is
implemented by defining a new SYSINIT() value, SI_SUB_SETTINGS, which
is intended for the processing of configuration choices after tunables
are read in and the console is available to generate errors, but
before much else gets going.

This compatibility behavior will go away when we've finished the last
of the locking work and are confident that operation is correct.

Apply error and success logic consistently to the function netisr_queue() and
its users.

netisr_queue() now returns (0) on success and ERRNO on failure. At the
moment ENXIO (netisr queue not functional) and ENOBUFS (netisr queue full)
are supported.

Previously it would return (1) on success but the return value of IF_HANDOFF()
was interpreted wrongly and (0) was actually returned on success. Due to this
schednetisr() was never called to kick the scheduling of the isr. However this
was masked by other normal packets coming through netisr_dispatch() causing the
dequeueing of waiting packets.

PR: kern/70988
Found by: MOROHOSHI Akihiko <moro@remus.dti.ne.jp>
MFC after: 3 days

Comment clarifying debug_mpsafenet.

o add a flags parameter to netisr_register that is used to specify
whether or not the isr needs to hold Giant when running; Giant-less
operation is also controlled by the setting of debug_mpsafenet
o mark all netisr's except NETISR_IP as needing Giant
o add a GIANT_REQUIRED assertion to the top of netisr's that need Giant
o pickup Giant (when debug_mpsafenet is 1) inside ip_input before
calling up with a packet
o change netisr handling so swi_net runs w/o Giant; instead we grab
Giant before invoking handlers based on whether the handler needs Giant
o change netisr handling so that netisr's that are marked MPSAFE may
have multiple instances active at a time
o add netisr statistics for packets dropped because the isr is inactive

Supported by: FreeBSD Foundation

o make debug_mpsafenet globally visible
o move it from subr_bus.c to netisr.c where it more properly belongs
o add NET_PICKUP_GIANT and NET_DROP_GIANT macros that will be used to
grab Giant as needed when MPSAFE operation is enabled

Supported by: FreeBSD Foundation

When direct dispatching an netisr (net.isr.enable=1), if there are already
any queued packets for the isr, process those packets before the newly
submitted packet, maintaining ordering of all packets being delivered
to the netisr. Remove the bypass counter since we don't bypass anymore.
Leave the comment about possible problems and options since later
performance optimization may change the strategy for addressing ordering
problems here.

Specifically, this maintains the strong isr ordering guarantee; additional
parallelism and lower latency may be possible by moving to weaker
guarantees (per-interface, for example). We will probably at some point
also want to remove the one instance netisr dispatch limit currently
enforced by a mutex, but it's not clear that's 100% safe yet, even in
the netperf branch.

Reviewed by: sam, others

Create a tunable for net.isr.enable so that it may be set from
inception, rather than having to wait for the boot to finish.

Temporarily turn net.isr.enable back off again until patches to
correct potential nits in packet ordering are resolved.

Enable net.isr.enable by default, causing "delivery to completion"
(direct dispatch) in interrupt threads when the netisr in question
isn't already active. If a netisr is already active, or direct
dispatch is already in progress, we queue the packet for later
delivery. Previously, this option was disabled by default. I have
measured 20%+ performance improvements in IP packet forwarding with
this enabled.

Please report any problems ASAP, especially relating to stack depth or
out-of-order packet processing.

Discussed with: jlemon, peter
Sponsored by: DARPA, Network Associates Laboratories

Discard the packet if the netisr queue is null instead of panicing, for
the benefit of modules which are compiled differently than the kernel.

Update netisr handling; Each SWI now registers its queue, and all queue
drain routines are done by swi_net, which allows for better queue control
at some future point. Packets may also be directly dispatched to a netisr
instead of queued, this may be of interest at some installations, but
currently defaults to off.

Reviewed by: hsu, silby, jayanth, sam
Sponsored by: DARPA, NAI Labs

Moved netisr code from kern/kern_intr.c to net/netisr.c as threatened in a
comment.