This simplifies the asm and fixes irq-off tracing over sleep
instructions.

Also move powersave_nap check for POWER8 into C code, and move
PSSCR register value calculation for POWER9 into C.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

On Power9 DD1 due to a hardware bug the Power-Saving Level Status
field (PLS) of the PSSCR for a thread waking up from a deep state can
under-report if some other thread in the core is in a shallow stop
state. The scenario in which this can manifest is as follows:

   1) All the threads of the core are in deep stop.
   2) One of the threads is woken up. The PLS for this thread will
      correctly reflect that it is waking up from deep stop.
   3) The thread that has woken up now executes a shallow stop.
   4) When some other thread in the core is woken, its PLS will reflect
      the shallow stop state.

Thus, the subsequent thread for which the PLS is under-reporting the
wakeup state will not restore the hypervisor resources.

Hence, on DD1 systems, use the Requested Level (RL) field as a
workaround to restore the contents of the hypervisor resources on the
wakeup from the stop state.
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

On wakeup from a deep stop state which is supposed to lose the
hypervisor state, we don't restore the LPCR to the old value but set
it to a "sane" value via cur_cpu_spec->cpu_restore().

The problem is that the "sane" value doesn't include UPRT and the HR
bits which are required to run correctly in Radix mode.

Fix this on POWER9 onwards by restoring the LPCR value whatever it was
before executing the stop instruction.
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

On POWER8, in case of
   -  nap: both timebase and hypervisor state is retained.
   -  fast-sleep: timebase is lost. But the hypervisor state is retained.
   -  winkle: timebase and hypervisor state is lost.

Hence, the current code for handling exit from a idle state assumes
that if the timebase value is retained, then so is the hypervisor
state. Thus, the current code doesn't restore per-core hypervisor
state in such cases.

But that is no longer the case on POWER9 where we do have stop states
in which timebase value is retained, but the hypervisor state is
lost. So we have to ensure that the per-core hypervisor state gets
restored in such cases.

Fix this by ensuring that even in the case when timebase is retained,
we explicitly check if we are waking up from a deep stop that loses
per-core hypervisor state (indicated by cr4 being eq or gt), and if
this is the case, we restore the per-core hypervisor state.
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Commit 17ed4c8f ("powerpc/powernv: Recover correct PACA on wakeup
from a stop on P9 DD1") promises to set the NAPSTATELOST bit in paca
after recovering the correct paca for the thread waking up from stop1
on DD1, so that the GPRs can be correctly restored on the stop exit
path. However, it loads the value 1 into r3, but stores the value in
r0 into NAPSTATELOST(r13).

Fix this by correctly set the NAPSTATELOST bit in paca after
recovering the paca on POWER9 DD1.

Fixes: 17ed4c8f ("powerpc/powernv: Recover correct PACA on wakeup from a stop on P9 DD1")
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The idle workaround does not need to load PACATOC, and it does not
need to be called within a nested function that requires LR to be
saved.

Load the PACATOC at entry to the idle wakeup. It does not matter which
PACA this comes from, so it's okay to call before the workaround. Then
apply the workaround to get the right PACA.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

If not all threads were in winkle, full state loss recovery is not
necessary and can be avoided. A previous patch removed this optimisation
due to some complexity with the implementation. Re-implement it by
counting the number of threads in winkle with the per-core idle state.
Only restore full state loss if all threads were in winkle.

This has a small window of false positives right before threads execute
winkle and just after they wake up, when the winkle count does not
reflect the true number of threads in winkle. This is not a significant
problem in comparison with even the minimum winkle duration. For
correctness, a false positive is not a problem (only false negatives
would be).
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

When taking the core idle state lock, grab it immediately like a regular
lock, rather than adding more tests in there. Holding the lock keeps it
stable, so there is no need to do it whole holding the reservation.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

In preparation for adding more bits to the core idle state word, move
the lock bit up, and unlock by flipping the lock bit rather than masking
off all but the thread bits.

Add branch hints for atomic operations while we're here.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The ISA specifies power save wakeup due to a machine check exception can
cause a machine check interrupt (rather than the usual system reset
interrupt).

The machine check handler copes with this by doing low level machine
check recovery without restoring full state from idle, then queues up a
machine check event for logging, then directly executes the same idle
instruction it woke from. This minimises the work done before recovery
is performed.

The problem is that it requires machine specific instructions and
knowledge of the book3s idle code. Currently it only has code to handle
POWER8 idle, so POWER9 crashes when trying to execute the P8 idle
instructions which don't exist in ISAv3.0B.

cpu 0x0: Vector: e40 (Emulation Assist) at [c0000000008f3810]
    pc: c000000000008380: machine_check_handle_early+0x130/0x2f0
    lr: c00000000053a098: stop_loop+0x68/0xd0
    sp: c0000000008f3a90
   msr: 9000000000081001
  current = 0xc0000000008a1080
  paca    = 0xc00000000ffd0000   softe: 0        irq_happened: 0x01
    pid   = 0, comm = swapper/0

Instead of going to sleep after recovery, do the usual idle wakeup and
state restoration by calling into the normal idle wakeup path. This
reuses the normal idle wakeup paths.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: NMahesh J Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This reduces the number of nops for POWER8.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The POWER8 idle code has a neat trick of programming the power on engine
to restore a low bit into HSPRG0, so idle wakeup code can test and see
if it has been programmed this way and therefore lost all state. Restore
time can be reduced if winkle has not been reached.

However this messes with our r13 PACA pointer, and requires HSPRG0 to be
written to. It also optimizes the slowest and most uncommon case at the
expense of another SPR write in the common nap state wakeup.

Remove this complexity and assume winkle sleeps always require a state
restore. This speedup could be made entirely contained within the winkle
idle code by counting per-core winkles and setting a thread bitmap when
all have gone to winkle.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

No functional change.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

POWER9 DD1.0 hardware has a bug where the SPRs of a thread waking up
from stop 0,1,2 with ESL=1 can endup being misplaced in the core. Thus
the HSPRG0 of a thread waking up from can contain the paca pointer of
its sibling.

This patch implements a context recovery framework within threads of a
core, by provisioning space in paca_struct for saving every sibling
threads's paca pointers. Basically, we should be able to arrive at the
right paca pointer from any of the thread's existing paca pointer.

At bootup, during powernv idle-init, we save the paca address of every
CPU in each one its siblings paca_struct in the slot corresponding to
this CPU's index in the core.

On wakeup from a stop, the thread will determine its index in the core
from the TIR register and recover its PACA pointer by indexing into
the correct slot in the provisioned space in the current PACA.

Furthermore, ensure that the NVGPRs are restored from the stack on the
way out by setting the NAPSTATELOST in paca.

[Changelog written with inputs from svaidy@linux.vnet.ibm.com]
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: NNicholas Piggin <npiggin@gmail.com>
[mpe: Call it a bug]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

We concluded there may be a window where the idle wakeup code could get
to pnv_wakeup_tb_loss() (which clobbers non-volatile GPRs), but the
hardware may set SRR1[46:47] to 01b (no state loss) which would result
in the wakeup code failing to restore non-volatile GPRs.

I was not able to trigger this condition with trivial tests on real
hardware or simulator, but the ISA (at least 2.07) seems to allow for
it, and Gautham says that it can happen if there is an exception pending
when the sleep/winkle instruction is executed.

Fixes: 17065671 ("powerpc/kvm: make hypervisor state restore a function")
Cc: stable@vger.kernel.org # v4.8+
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Acked-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Commit 09206b60 ("powernv: Pass PSSCR value and mask to
power9_idle_stop") added additional code in power_enter_stop() to
distinguish between stop requests whose PSSCR had ESL=EC=1 from those
which did not. When ESL=EC=1, we do a forward-jump to a location
labelled by "1", which had the code to handle the ESL=EC=1 case.

Unfortunately just a couple of instructions before this label, is the
macro IDLE_STATE_ENTER_SEQ() which also has a label "1" in its
expansion.

As a result, the current code can result in directly executing stop
instruction for deep stop requests with PSSCR ESL=EC=1, without saving
the hypervisor state.

Fix this BUG by labeling the location that handles ESL=EC=1 case with
a more descriptive label ".Lhandle_esl_ec_set" (local label suggestion
a la .Lxx from Anton Blanchard).

While at it, rename the label "2" labelling the location of the code
handling entry into deep stop states with ".Lhandle_deep_stop".

For a good measure, change the label in IDLE_STATE_ENTER_SEQ() macro
to an not-so commonly used value in order to avoid similar mishaps in
the future.

Fixes: 09206b60 ("powernv: Pass PSSCR value and mask to power9_idle_stop")
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

All entry points already read the MSR so they can easily do
the right thing.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The power9_idle_stop method currently takes only the requested stop
level as a parameter and picks up the rest of the PSSCR bits from a
hand-coded macro. This is not a very flexible design, especially when
the firmware has the capability to communicate the psscr value and the
mask associated with a particular stop state via device tree.

This patch modifies the power9_idle_stop API to take as parameters the
PSSCR value and the PSSCR mask corresponding to the stop state that
needs to be set. These PSSCR value and mask are respectively obtained
by parsing the "ibm,cpu-idle-state-psscr" and
"ibm,cpu-idle-state-psscr-mask" fields from the device tree.

In addition to this, the patch adds support for handling stop states
for which ESL and EC bits in the PSSCR are zero. As per the
architecture, a wakeup from these stop states resumes execution from
the subsequent instruction as opposed to waking up at the System
Vector.

The older firmware sets only the Requested Level (RL) field in the
psscr and psscr-mask exposed in the device tree. For older firmware
where psscr-mask=0xf, this patch will set the default sane values that
the set for for remaining PSSCR fields (i.e PSLL, MTL, ESL, EC, and
TR). For the new firmware, the patch will validate that the invariants
required by the ISA for the psscr values are maintained by the
firmware.

This skiboot patch that exports fully populated PSSCR values and the
mask for all the stop states can be found here:
https://lists.ozlabs.org/pipermail/skiboot/2016-September/004869.html

[Optimize the number of instructions before entering STOP with
ESL=EC=0, validate the PSSCR values provided by the firimware
maintains the invariants required as per the ISA suggested by Balbir
Singh]
Acked-by: NBalbir Singh <bsingharora@gmail.com>
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Currently all the low-power idle states are expected to wake up
at reset vector 0x100. Which is why the macro IDLE_STATE_ENTER_SEQ
that puts the CPU to an idle state and never returns.

On ISA v3.0, when the ESL and EC bits in the PSSCR are zero, the CPU
is expected to wake up at the next instruction of the idle
instruction.

This patch adds a new macro named IDLE_STATE_ENTER_SEQ_NORET for the
no-return variant and reuses the name IDLE_STATE_ENTER_SEQ
for a variant that allows resuming operation at the instruction next
to the idle-instruction.
Acked-by: NBalbir Singh <bsingharora@gmail.com>
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

This fixes a race condition where one thread that is entering or
leaving a power-saving state can inadvertently ignore the lock bit
that was set by another thread, and potentially also clear it.
The core_idle_lock_held function is called when the lock bit is
seen to be set.  It polls the lock bit until it is clear, then
does a lwarx to load the word containing the lock bit and thread
idle bits so it can be updated.  However, it is possible that the
value loaded with the lwarx has the lock bit set, even though an
immediately preceding lwz loaded a value with the lock bit clear.
If this happens then we go ahead and update the word despite the
lock bit being set, and when called from pnv_enter_arch207_idle_mode,
we will subsequently clear the lock bit.

No identifiable misbehaviour has been attributed to this race.

This fixes it by checking the lock bit in the value loaded by the
lwarx.  If it is set then we just go back and keep on polling.

Fixes: b32aadc1 ("powerpc/powernv: Fix race in updating core_idle_state")
Cc: stable@vger.kernel.org # v4.2+
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Commit 8117ac6a ("powerpc/powernv: Switch off MMU before entering
nap/sleep/rvwinkle mode", 2014-12-10) fixed a race condition where one
thread entering a KVM guest could switch the MMU context to the guest
while another thread was still in host kernel context with the MMU on.
That commit moved the point where a thread entering a power-saving
mode set its kvm_hstate.hwthread_state field in its PACA to
KVM_HWTHREAD_IN_IDLE from a point where the MMU was on to after the
MMU had been switched off.  That commit also added a comment
explaining that we have to switch to real mode before setting
hwthread_state to avoid this race.

Nevertheless, commit 4eae2c9a ("powerpc/powernv: Make
pnv_powersave_common more generic", 2016-07-08) subsequently moved
the setting of hwthread_state back to a point where the MMU is on,
thus reintroducing the race, despite the comment saying that this
should not be done being included in full in the context lines of
the patch that did it.

This fixes the race again and adds a bigger and shoutier comment
explaining the potential race condition.

Fixes: 4eae2c9a ("powerpc/powernv: Make pnv_powersave_common more generic")
Cc: stable@vger.kernel.org # v4.8+
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>
Reviewed-by: NShreyas B. Prabhu <shreyasbp@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

pnv_wakeup_tb_loss() currently expects cr4 to be "eq" if the CPU is
waking up from a complete hypervisor state loss. Hence, it currently
restores the SPR contents only if cr4 is "eq".

However, after commit bcef83a0 ("powerpc/powernv: Add platform
support for stop instruction"), on ISA v3.0 CPUs, the function
pnv_restore_hyp_resource() sets cr4 to contain the result of the
comparison between the state the CPU has woken up from and the first
deep stop state before calling pnv_wakeup_tb_loss().

Thus if the CPU woke up from a state that is deeper than the first
deep stop state, cr4 will have "gt" set and hence, pnv_wakeup_tb_loss()
will fail to restore the SPRs on waking up from such a state.

Fix the code in pnv_wakeup_tb_loss() to restore the SPR states when cr4
is "eq" or "gt".

Fixes: bcef83a0 ("powerpc/powernv: Add platform support for stop instruction")
Signed-off-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: NShreyas B. Prabhu <shreyasbp@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Move IDLE_STATE_ENTER_SEQ macro to cpuidle.h so that MCE handler changes
in subsequent patch can use it.

No functionality change.
Signed-off-by: NMahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The function pnv_restore_hyp_resource() loads the TOC into r2 from
the invalid PACA pointer before fixing r13 value. This do not affect
POWER ISA 3.0 but it does have an impact on POWER ISA 2.07 or less
leading CPU to get stuck forever.

	login: [  471.830433] Processor 120 is stuck.

This can be easily reproducible using following steps:
- Turn off SMT
	$ ppc64_cpu --smt=off
- offline/online any online cpu (Thread 0 of any core which is online)
	$ echo 0 > /sys/devices/system/cpu/cpu<num>/online
	$ echo 1 > /sys/devices/system/cpu/cpu<num>/online

For POWER ISA 2.07 or less, the last bit of HSPRG0 is set indicating
that thread is waking up from winkle. Hence, the last bit of HSPRG0(r13)
needs to be clear before accessing it as PACA to avoid loading invalid
values from invalid PACA pointer.

Fix this by loading TOC after r13 register is corrected.

Fixes: bcef83a0 ("powerpc/powernv: Add platform support for stop instruction")
Signed-off-by: NMahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: NVaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

MMU feature bits are defined such that we use the lower half to
present MMU family features. Remove the strict split of half and
also move Radix to a mmu family feature. Radix introduce a new MMU
model and strictly speaking it is a new MMU family. This also free
up bits which can be used for individual features later.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Replace the old generic opal_call_realmode() with proper per-call
wrappers similar to the normal ones and convert callers.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

POWER ISA v3 defines a new idle processor core mechanism. In summary,
 a) new instruction named stop is added. This instruction replaces
	instructions like nap, sleep, rvwinkle.
 b) new per thread SPR named Processor Stop Status and Control Register
	(PSSCR) is added which controls the behavior of stop instruction.

PSSCR layout:
----------------------------------------------------------
| PLS | /// | SD | ESL | EC | PSLL | /// | TR | MTL | RL |
----------------------------------------------------------
0      4     41   42    43   44     48    54   56    60

PSSCR key fields:
	Bits 0:3  - Power-Saving Level Status. This field indicates the lowest
	power-saving state the thread entered since stop instruction was last
	executed.

	Bit 42 - Enable State Loss
	0 - No state is lost irrespective of other fields
	1 - Allows state loss

	Bits 44:47 - Power-Saving Level Limit
	This limits the power-saving level that can be entered into.

	Bits 60:63 - Requested Level
	Used to specify which power-saving level must be entered on executing
	stop instruction

This patch adds support for stop instruction and PSSCR handling.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Create a function for saving SPRs before entering deep idle states.
This function can be reused for POWER9 deep idle states.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

pnv_powersave_common does common steps needed before entering idle
state and eventually changes MSR to MSR_IDLE and does rfid to
pnv_enter_arch207_idle_mode.

Move the updation of HSTATE_HWTHREAD_STATE to pnv_powersave_common
from pnv_enter_arch207_idle_mode and make it more generic by passing the
rfid address as a function parameter.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Functions like power7_wakeup_loss, power7_wakeup_noloss,
power7_wakeup_tb_loss are used by POWER7 and POWER8 hardware. They can
also be used by POWER9. Hence rename these functions hardware agnostic
names.
Suggested-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

idle_power7.S handles idle entry/exit for POWER7, POWER8 and in next
patch for POWER9. Rename the file to a non-hardware specific
name.
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

In the current code, when the thread wakes up in reset vector, some
of the state restore code and check for whether a thread needs to
branch to kvm is duplicated. Reorder the code such that this
duplication is avoided.

At a higher level this is what the change looks like-

Before this patch -
power7_wakeup_tb_loss:
	restore hypervisor state
	if (thread needed by kvm)
		goto kvm_start_guest
	restore nvgprs, cr, pc
	rfid to process context

power7_wakeup_loss:
	restore nvgprs, cr, pc
	rfid to process context

reset vector:
	if (waking from deep idle states)
		goto power7_wakeup_tb_loss
	else
		if (thread needed by kvm)
			goto kvm_start_guest
		goto power7_wakeup_loss

After this patch -
power7_wakeup_tb_loss:
	restore hypervisor state
	return

power7_restore_hyp_resource():
	if (waking from deep idle states)
		goto power7_wakeup_tb_loss
	return

power7_wakeup_loss:
	restore nvgprs, cr, pc
	rfid to process context

reset vector:
	power7_restore_hyp_resource()
	if (thread needed by kvm)
                goto kvm_start_guest
	goto power7_wakeup_loss
Reviewed-by: NPaul Mackerras <paulus@samba.org>
Reviewed-by: NGautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

When a guest is assigned to a core it converts the host Timebase (TB)
into guest TB by adding guest timebase offset before entering into
guest. During guest exit it restores the guest TB to host TB. This means
under certain conditions (Guest migration) host TB and guest TB can differ.

When we get an HMI for TB related issues the opal HMI handler would
try fixing errors and restore the correct host TB value. With no guest
running, we don't have any issues. But with guest running on the core
we run into TB corruption issues.

If we get an HMI while in the guest, the current HMI handler invokes opal
hmi handler before forcing guest to exit. The guest exit path subtracts
the guest TB offset from the current TB value which may have already
been restored with host value by opal hmi handler. This leads to incorrect
host and guest TB values.

With split-core, things become more complex. With split-core, TB also gets
split and each subcore gets its own TB register. When a hmi handler fixes
a TB error and restores the TB value, it affects all the TB values of
sibling subcores on the same core. On TB errors all the thread in the core
gets HMI. With existing code, the individual threads call opal hmi handle
independently which can easily throw TB out of sync if we have guest
running on subcores. Hence we will need to co-ordinate with all the
threads before making opal hmi handler call followed by TB resync.

This patch introduces a sibling subcore state structure (shared by all
threads in the core) in paca which holds information about whether sibling
subcores are in Guest mode or host mode. An array in_guest[] of size
MAX_SUBCORE_PER_CORE=4 is used to maintain the state of each subcore.
The subcore id is used as index into in_guest[] array. Only primary
thread entering/exiting the guest is responsible to set/unset its
designated array element.

On TB error, we get HMI interrupt on every thread on the core. Upon HMI,
this patch will now force guest to vacate the core/subcore. Primary
thread from each subcore will then turn off its respective bit
from the above bitmap during the guest exit path just after the
guest->host partition switch is complete.

All other threads that have just exited the guest OR were already in host
will wait until all other subcores clears their respective bit.
Once all the subcores turn off their respective bit, all threads will
will make call to opal hmi handler.

It is not necessary that opal hmi handler would resync the TB value for
every HMI interrupts. It would do so only for the HMI caused due to
TB errors. For rest, it would not touch TB value. Hence to make things
simpler, primary thread would call TB resync explicitly once for each
core immediately after opal hmi handler instead of subtracting guest
offset from TB. TB resync call will restore the TB with host value.
Thus we can be sure about the TB state.

One of the primary threads exiting the guest will take up the
responsibility of calling TB resync. It will use one of the top bits
(bit 63) from subcore state flags bitmap to make the decision. The first
primary thread (among the subcores) that is able to set the bit will
have to call the TB resync. Rest all other threads will wait until TB
resync is complete.  Once TB resync is complete all threads will then
proceed.
Signed-off-by: NMahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@ozlabs.org>

No code changes.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The UP only lazy floating point and vector optimisations were written
back when SMP was not common, and neither glibc nor gcc used vector
instructions. Now SMP is very common, glibc aggressively uses vector
instructions and gcc autovectorises.

We want to add new optimisations that apply to both UP and SMP, but
in preparation for that remove these UP only optimisations.
Signed-off-by: NAnton Blanchard <anton@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

core_idle_state is maintained for each core. It uses 0-7 bits to track
whether a thread in the core has entered fastsleep or winkle. 8th bit is
used as a lock bit.
The lock bit is set in these 2 scenarios-
 - The thread is first in subcore to wakeup from sleep/winkle.
 - If its the last thread in the core about to enter sleep/winkle

While the lock bit is set, if any other thread in the core wakes up, it
loops until the lock bit is cleared before proceeding in the wakeup
path. This helps prevent race conditions w.r.t fastsleep workaround and
prevents threads from switching to process context before core/subcore
resources are restored.

But, in the path to sleep/winkle entry, we currently don't check for
lock-bit. This exposes us to following race when running with subcore
on-

First thread in the subcorea		Another thread in the same
waking up		   		core entering sleep/winkle

lwarx   r15,0,r14
ori     r15,r15,PNV_CORE_IDLE_LOCK_BIT
stwcx.  r15,0,r14
[Code to restore subcore state]

						lwarx   r15,0,r14
						[clear thread bit]
						stwcx.  r15,0,r14

andi.   r15,r15,PNV_CORE_IDLE_THREAD_BITS
stw     r15,0(r14)

Here, after the thread entering sleep clears its thread bit in
core_idle_state, the value is overwritten by the thread waking up.
In such cases when the core enters fastsleep, code mistakes an idle
thread as running. Because of this, the first thread waking up from
fastsleep which is supposed to resync timebase skips it. So we can
end up having a core with stale timebase value.

This patch fixes the above race by looping on the lock bit even while
entering the idle states.
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Fixes: 7b54e9f213f76 'powernv/powerpc: Add winkle support for offline cpus'
Cc: stable@vger.kernel.org # 3.19+
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Patches 7cba160a "powernv/cpuidle: Redesign idle states management"
and 77b54e9f "powernv/powerpc: Add winkle support for offline cpus"
use non-volatile condition registers (cr2, cr3 and cr4) early in the system
reset interrupt handler (system_reset_pSeries()) before it has been determined
if state loss has occurred. If state loss has not occurred, control returns via
the power7_wakeup_noloss() path which does not restore those condition
registers, leaving them corrupted.

Fix this by restoring the condition registers in the power7_wakeup_noloss()
case.

This is apparent when running a KVM guest on hardware that does not
support winkle or sleep and the guest makes use of secondary threads. In
practice this means Power7 machines, though some early unreleased Power8
machines may also be susceptible.

The secondary CPUs are taken off line before the guest is started and
they call pnv_smp_cpu_kill_self(). This checks support for sleep
states (in this case there is no support) and power7_nap() is called.

When the CPU is woken, power7_nap() returns and because the CPU is
still off line, the main while loop executes again. The sleep states
support test is executed again, but because the tested values cannot
have changed, the compiler has optimized the test away and instead we
rely on the result of the first test, which has been left in cr3
and/or cr4. With the result overwritten, the wrong branch is taken and
power7_winkle() is called on a CPU that does not support it, leading
to it stalling.

Fixes: 7cba160a ("powernv/cpuidle: Redesign idle states management")
Fixes: 77b54e9f ("powernv/powerpc: Add winkle support for offline cpus")
[mpe: Massage change log a bit more]
Signed-off-by: NSam Bobroff <sam.bobroff@au1.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

The power7_nap(), power7_sleep() and power7_winkle() functions are
called from pnv_smp_cpu_kill_self(), which expects them to return the
SRR1 value set by the hardware on wakeup, or 0 if no nap/sleep/winkle
occurred.  However, in the case where an interrupt needs to be
replayed, the logic in power7_powersave_common (the common code for
power7_nap et al.) doesn't set r3 to 0 in this case.  Instead what we
get as the return value is the selector for the type of power-saving
mode requested (1, 2 or 3).  In fact this should not affect the
operation of pnv_smp_cpu_kill_self(), but it is better to get this
correct, so this adds an instruction to set r3 to 0 in this case.
Signed-off-by: NPaul Mackerras <paulus@samba.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

Winkle is a deep idle state supported in power8 chips. A core enters
winkle when all the threads of the core enter winkle. In this state
power supply to the entire chiplet i.e core, private L2 and private L3
is turned off. As a result it gives higher powersavings compared to
sleep.

But entering winkle results in a total hypervisor state loss. Hence the
hypervisor context has to be preserved before entering winkle and
restored upon wake up.

Power-on Reset Engine (PORE) is a dedicated engine which is responsible
for powering on the chiplet during wake up. It can be programmed to
restore the register contests of a few specific registers. This patch
uses PORE to restore register state wherever possible and uses stack to
save and restore rest of the necessary registers.

With hypervisor state restore things fall under three categories-
per-core state, per-subcore state and per-thread state. To manage this,
extend the infrastructure introduced for sleep. Mainly we add a paca
variable subcore_sibling_mask. Using this and the core_idle_state we can
distingush first thread in core and subcore.
Signed-off-by: NShreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>