Copy stable/10@r272459 to releng/10.1 as part of
the 10.1-RELEASE process.

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

MFcalloutng:
Switch eventtimers(9) from using struct bintime to sbintime_t.
Even before this not a single driver really supported full dynamic range of
struct bintime even in theory, not speaking about practical inexpediency.
This change legitimates the status quo and cleans up the code.

Revert the part of r239864 which removed obtaining the SMP mutex around
reading registers from other CPUs. As it turns out, the hardware doesn't
really like concurrent IPI'ing causing adverse effects. Also the thought
deadlock when using this spin lock here and the targeted CPU(s) are also
holding or in case of nested locks can't actually happen. This is due to
the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't
disable interrupts completely. Thus direct cross calls as used for the
register reading (and all other MD IPI needs) still will be executed by
the targeted CPU(s) in that case.

MFC after: 3 days

Let SCHED_ULE give affinity to the CPU the tick interrupt triggered on
when running tick_process(), similarly to what the x86 equivalents of
this function do, however employing the less racy sequence also used in
intr_event_handle().

MFC after: 3 days

- Unlike cache invalidation and TLB demapping IPIs, reading registers from
other CPUs doesn't require locking so get rid of it. As the latter is used
for the timecounter on certain machine models, using a spin lock in this
case can lead to a deadlock with the upcoming callout(9) rework.
- Merge r134227/r167250 from x86:
Avoid cross-IPI SMP deadlock by using the smp_ipi_mtx spin lock not only
for smp_rendezvous_cpus() but also for the MD cache invalidation and TLB
demapping IPIs.
- Mark some unused function arguments as such.

MFC after: 1 week

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.

Remove NULL assignments which are redundant for static timecounters.

Submitted by: jkim

On Serengeti-class machines the OFW root isn't the parent of the CPU
nodes.

Extend the hack of r182730 to trick GAS/GCC into compiling access to
STICK/STICK_COMPARE independently of the selected instruction set by
TICK_COMPARE so tick.c as of r214358 once again can be compiled with
gcc -mcpu=v9 for reference purposes.

- Given that in one-shot mode tick_et_start() also is called frequently
introduce function pointers once set up to the respective implementation
for reading the (S)TICK and writing the (S)STICK_COMPARE registers as a
compromise between duplicating code and selecting between different
implementations during execution over and over again, similar to what is
done elsewhere in the MD in order to support different CPU models that
won't ever change at runtime.
- In the remaining tick interrupt handler further push down disabling of
interrupts to the periodic case as it isn't necessary here in one-shot
mode at all.

- Wrap exchanging td_intr_frame and calling the event timer callback in
a critical section as apparently required by both. I don't think either
belongs in the event timer front-ends but the callback should handle
this as necessary instead just like for example intr_event_handle()
does but this is how the other architectures currently handle it, either
explicitly or implicitly.
- Further rename and reword references to hardclock as this front-end no
longer has a notion of actually calling it.

- In oneshot-mode it doesn't make sense to try to compensate the clock
drift in order to achieve a more stable clock as the tick intervals may
vary in the first place. In fact I haven't seen this code kick in when
in oneshot-mode so just skip it in that case.
- There's no need to explicitly stop the (S)TICK counter in oneshot-mode
with every tick as it just won't trigger again with the (S)TICK compare
register set to a value in the past (with a wrap-around once every ~195
years of uptime at 1.5 GHz this isn't something we have to worry about
in practice).
- Given that we'll disable interrupts completely anyway there's no
need to enter critical sections.

- As it is not possible for sched_bind(9) to context switch with
td_critnest > 1 when not already running on the desired CPU read the
TICK counter of the BSP via a direct cross trap request in that case
instead.
- Treat the STICK based timecounter the same way as the TICK based one
regarding its quality and obtaining the counter value from the BSP.
Like the TICK timers the STICK ones also are only synchronized during
their startup (which might not result in good synchronicity in the
first place) but not afterwards and might drift over time, causing
problems when the time is read from different CPUs (see r135972).

Adapt sparc64 and sun4v timer code for the new event timers infrastructure.

Reviewed by: marius@

Add support for SPARC64 V (and where it already makes sense for other
HAL/Fujitsu) CPUs. For the most part this consists of fleshing out the
MMU and cache handling, it doesn't add pmap optimizations possible with
these CPU, yet, though.
With these changes FreeBSD runs stable on Fujitsu Siemens PRIMEPOWER 250
and likely also other models based on SPARC64 V like 450, 650 and 850.
Thanks go to Michael Moll for providing access to a PRIMEPOWER 250.

Some machines can not only consist of CPUs running at different speeds
but also of different types, f.e. Sun Fire V890 can be equipped with a
mix of UltraSPARC IV and IV+ CPUs, requiring different MMU initialization
and different workarounds for model specific errata. Therefore move the
CPU implementation number from a global variable to the per-CPU data.
Functions which are called before the latter is available are passed the
implementation number as a parameter now.

Use the STICK timers only when absolutely necessary, i.e. if a machine
consists of CPUs running at different speeds, for driving hardclock as
these timers in turn are driven at frequencies as low as 5MHz, resulting
in bad granularity compared to the TICK timers. However, don't employ
the workaround for the BlackBird erratum #1 when using the TICK timer
on machines with cheetah-class CPUs for performance reasons.

Reported by: Florian Smeets

- USIII-based machines can consist of CPUs running at different
frequencies (and having different cache sizes) so use the STICK
(System TICK) timer, which was introduced due to this and is
driven by the same frequency across all CPUs, instead of the
TICK timer, whose frequency varies with the CPU clock, to drive
hardclock. We try to use the STICK counter with all CPUs that are
USIII or beyond, even when not necessary due to identical CPUs,
as we can can also avoid the workaround for the BlackBird erratum
#1 there. Unfortunately, using the STICK counter currently causes
a hang with USIIIi MP machines for reasons unknown, so we still
use the TICK timer there (which is okay as they can only consist
of identical CPUs).
- Given that we only (try to) synchronize the (S)TICK timers of APs
with the BSP during startup, we could end up spinning forever in
DELAY(9) if that function is migrated to another CPU while we're
spinning due to clock drift afterwards, so pin to the CPU in order
to avoid migration. Unfortunately, pinning doesn't work at the
point DELAY(9) is required by the low-level console drivers, yet,
so switch to a function pointer, which is updated accordingly, for
implementing DELAY(9). For USIII and beyond, this would also allow
to easily use the STICK counter instead of the TICK one here,
there's no benefit in doing so however.
While at it, use cpu_spinwait(9) for spinning in the delay-
functions. This currently is a NOP though.
- Don't set the TICK timer of the BSP to 0 during at startup as
there's no need to do so.
- Implement cpu_est_clockrate().
- Unfortunately, USIIIi-based machines don't provide a timecounter
device besides the STICK and TICK counters (well, in theory the
Tomatillo bridges have a performance counter that can be (ab)used
as timecounter by configuring it to count bus cycles, though unlike
the performance counter of Schizo bridges, the Tomatillo one is
broken and counts Sun knows what in this mode). This means that
we've to use a (S)TICK counter for timecounting, which has the old
problem of not being in sync across CPUs, so provide an additional
timecounter function which binds itself to the BSP but has an
adequate low priority.

cosmetic changes and style fixes

o Revamp the sparc64 interrupt code in order to be able to interface
with the INTR_FILTER-enabled MI code. Basically this consists of
registering an interrupt controller (of which there can be multiple
and optionally different ones either per host-to-foo bridge or shared
amongst host-to-foo bridges in any one machine) along with an interrupt
vector as specific argument for all the interrupt vectors used by a
given host-to-foo bridge (roughly similar to registering interrupt
sources on amd64 and i386), providing functions to enable, clear and
disable the interrupts of the children beneath the bridge.
This also includes:
- No longer entering a critical section in tl0_intr() and tl1_intr()
for executing interrupt handlers but rather let the handlers enter
it themselves so in the case of intr_event_handle() we don't enter
a nested critical section.
- Adding infrastructure for binding delivery of interrupt vectors to
specific CPUs which later on can be interfaced with the code from
amd64/i386 for binding interrupts to specific CPUs.
- Getting rid of the wrapper hack introduced along the lines of the
API changes for INTR_FILTER which as a side-effect caused interrupts
associated with ithread handlers only to get the elevated priority
of those associated with filters ("fast handlers") (this removes the
hack also in the non-INTR_FILTER case).
- Disabling (by not clearing) an interrupt in the interrupt controller
until all associated handlers have been executed, which is crucial
for the typical locking strategy of NIC drivers in order to work
correctly in case of shared interrupts. This was a more or less
theoretical problem on sparc64 though, as shared interrupts are
rather uncommon there except for the on-board SCCs and UARTs.
Note that due to the behavior of at least of some of the interrupt
controllers used on sparc64 an enable+EOI instead of a disable+EOI
approach (as implied by the INTR_FILTER MI code and implemented on
other architectures) is used as the latter can cause lost interrupts
or in the worst case interrupt starvation.
o Correct a typo in sbus_alloc_resource() which caused (pass-through)
allocations to only work down to the grandchildren of the bus, which
wasn't a real problem so far as we don't support any devices which are
great-grandchildren or greater of a U2S bridge, yet.
o In fhc(4) use bus_{read,write}_4() instead of bus_space_{read,write}_4()
in order to get rid of sc_bh and sc_bt in the fhc_softc. Also get rid
of some other unneeded members in fhc_softc.

Reviewed by: marcel (earlier version)
Approved by: re (kensmith)

- Move the check for too high HZ values from tick_init() to tick_start()
as we have to call tick_init() before cninit() in order to provide the
low-level console drivers with a working DELAY() which in turn means we
cannot use panic() in tick_init().
- s,to high, too high, in the panic string

Inspired by: kmacy's sun4v changes
MFC after: 3 days

CPU time accounting speedup (step 2)

Keep accounting time (in per-cpu) cputicks and the statistics counts
in the thread and summarize into struct proc when at context switch.

Don't reach across CPUs in calcru().

Add code to calibrate the top speed of cpu_tickrate() for variable
cpu_tick hardware (like TSC on power managed machines).

Don't enforce monotonicity (at least for now) in calcru. While the
calibrated cpu_tickrate ramps up it may not be true.

Use 27MHz counter on i386/Geode.

Use TSC on amd64 & i386 if present.

Use tick counter on sparc64

Modify the way we account for CPU time spent (step 1)

Keep track of time spent by the cpu in various contexts in units of
"cputicks" and scale to real-world microsec^H^H^H^H^H^H^H^Hclock_t
only when somebody wants to inspect the numbers.

For now "cputicks" are still derived from the current timecounter
and therefore things should by definition remain sensible also on
SMP machines. (The main reason for this first milestone commit is
to verify that hypothesis.)

On slower machines, the avoided multiplications to normalize timestams
at every context switch, comes out as a 5-7% better score on the
unixbench/context1 microbenchmark. On more modern hardware no change
in performance is seen.

Tweak how the MD code calls the fooclock() methods some. Instead of
passing a pointer to an opaque clockframe structure and requiring the
MD code to supply CLKF_FOO() macros to extract needed values out of the
opaque structure, just pass the needed values directly. In practice this
means passing the pair (usermode, pc) to hardclock() and profclock() and
passing the boolean (usermode) to hardclock_cpu() and hardclock_process().
Other details:
- Axe clockframe and CLKF_FOO() macros on all architectures. Basically,
all the archs were taking a trapframe and converting it into a clockframe
one way or another. Now they can just extract the PC and usermode values
directly out of the trapframe and pass it to fooclock().
- Renamed hardclock_process() to hardclock_cpu() as the latter is more
accurate.
- On Alpha, we now run profclock() at hz (profhz == hz) rather than at
the slower stathz.
- On Alpha, for the TurboLaser machines that don't have an 8254
timecounter, call hardclock() directly. This removes an extra
conditional check from every clock interrupt on Alpha on the BSP.
There is probably room for even further pruning here by changing Alpha
to use the simplified timecounter we use on x86 with the lapic timer
since we don't get interrupts from the 8254 on Alpha anyway.
- On x86, clkintr() shouldn't ever be called now unless using_lapic_timer
is false, so add a KASSERT() to that affect and remove a condition
to slightly optimize the non-lapic case.
- Change prototypeof arm_handler_execute() so that it's first arg is a
trapframe pointer rather than a void pointer for clarity.
- Use KCOUNT macro in profclock() to lookup the kernel profiling bucket.

Tested on: alpha, amd64, arm, i386, ia64, sparc64
Reviewed by: bde (mostly)

The system tick _compare_ register of USIII CPUs and up is ASR25, not
ASR24 (which is the system tick register).

- Add a workaround for a bug in BlackBird CPUs (said to be part of the
SpitFire erratum #54) which can cause writes to the TICK_CMPR register
to fail. This seems to fix the dying clocks problem reported by jhb@
and kris@. [1]
- In tick_start() don't reset the tick counter of the boot processor to
zero. It's initially reset in _start() and afterwards but _before_
tick_start() is called on the BSP the APs synchronise with the tick
counter of the BSP in mp_startup(). Resetting the tick counter of the
BSP in tick_start() probably also was the cause of problems seen when
using the CPU tick counter as timecounter on SMP machines.
Not resetting the tick counter of the BSP in mp_startup() makes the
tick counters and tick interrupts between the BSP and APs be pretty
much in sync as it's supposed to be. This also means there's no longer
a real reason to have separate tick_start() and tick_start_ap() so
merge them and zap tick_start_ap(). This is also a first step in
simplifying the interface to the tick counters in preparation to use
alternate clock hardware where available.
- Switch to the algorithm used on FreeBSD/ia64 for updating the tick
interrupt register and which compensates the clock drift caused by
varying delays between when the tick interrupts actually trigger and
when they are serviced. Not compensating the clock drift mainly hurts
interactive performance especially when using WITNESS. [2]
For further information about the algorithm also see the commit log
of sys/ia64/ia64/interrupt.c rev. 1.38.
On sparc64 the sysctls for monitoring the behaviour of the tick
interrupts are machdep.tick.adjust_edges, machdep.tick.adjust_excess,
machdep.tick.adjust_missed and machdep.tick.adjust_ticks.
- In tick_init() just use tick_stop() for stopping the tick interrupts
until a proper handler is set up later. This also stops the system
tick interrupt on USIII systems earlier.
- In tick_start() check for a rough upper limit of HZ.
- Some minor changes, e.g. use FBSDID, remove unused headers, etc.

Info obtained from: Linux [1]
Ok'ed by: marcel [2]
Additional testing by: kris (earlier version of the workaround), jhb
X-MFC after: 3 days [1]

UltraSparc II[e,i] based systems come up with the tick compare register
loaded, the tick interrupt enabled and a handler that resets the tick
counter on every tick interrupt. While this isn't documented this can
cause DELAY() to wait for a value the tick counter will not reach when
used in early boot, i.e. before cpu_initclocks() is called, depending
on when in the cycle DELAY() is called, the delay value and the value
the tick compare register is set to. The excessive use of DELAY() in
uart(4) when probing Sun keyboards seems to always manage to trigger
this, resulting in a hang during boot.
Disable the tick interrupt in tick_init(), which is called early in
sparc64_init(), until the interrupt is enabled again in tick_start(),
called by cpu_initclocks(), with our own handler. This fixes the hang
during probing Sun keyboards on AXi boards and Ultra 10, with other
machines like Ultra 5 probably being affected but not tested.

Additional testing by: Matthias Muthmann
MFC after: 1 week

Prefer new location of pci include files (which have only been in the
tree for two or more years now), except in a few places where there's
code to be compatible with older versions of FreeBSD.

Completely disable interrupts (not just raise %pil) when calculating the
value to be written into tick_compare in tick_hardclock(). While
we were taking care that the value to be written was at least TICK_GRACE
ticks in the future, a vector interrupt could happen between calculating
the value and writing it. If it took longer than TICK_GRACE to complete
(which is doubtful for a single device-triggered vector interrupt, but
quite likely for some IPIs), the value written would be in the past
and tick interrupts (which drive hardclock and statclock) would stop
until %tick wraps around, which takes a long time.
Also, increase TICK_GRACE from 1000 to 10000 for good measure.

Reported by: kris
Reviewed by: jake
Approved by: re (scottl)

- Set cpu_impl early in sparc64_init so that we can use it to detect
UltraSPARC III and higher cpus and do needed setup.
- Disable the "system tick" interrupt for UltraSPARC III. This avoids
an interrupt storm on startup since we're not prepared for these at
all. This feature has questionable use anyway.
- Clear tick on startup and then leave it alone.

Split statclock into statclock and profclock, and made the method for driving
statclock based on profhz when profiling is enabled MD, since most platforms
don't use this anyway. This removes the need for statclock_process, whose
only purpose was to subdivide profhz, and gets the profiling clock running
outside of sched_lock on platforms that implement suswintr.
Also changed the interface for starting and stopping the profiling clock to
do just that, instead of changing the rate of statclock, since they can now
be separate.

Reviewed by: jhb, tmm
Tested on: i386, sparc64

Reversion of commit by Davidxu plus fixes since applied.

I'm not convinced there is anything major wrong with the patch but
them's the rules..

I am using my "David's mentor" hat to revert this as he's
offline for a while.

Fix standard kse breakage of non-x86 platforms.

Pointy hat to: davidxu

Initialize tick_MHz and related variables much earlier. After the last
revision of tick.c, this was done at SI_SUB_CLOCKS, which is too late
because tick_MHz is required for DELAY() to work.

Reviewed by: jake

We always need sys/pcpu.h now, not just for the SMP case.

Approved by: jake

Start tick at the correct time (cpu_init_clocks), instead of cpu_startup.

Add support for driving the clocks on secondary cpus.

Submitted by: tmm

- Add a file for machine dependant loader metdata types. Include this in
machdep.c.
- Adapt to critical_* changes.

Avoid missing ticks and hardclock stopping.

Submitted by: tmm

Implement DELAY() using the %tick register.

Add code to program the tick register and to setup its interrupt handler.