Commit 24be85a23d ("powerpc/powernv: Clear PECE1 in LPCR via
stop-api only on Hotplug") clears the PECE1 bit of the LPCR via
stop-api during CPU-Hotplug to prevent wakeup due to a decrementer on
an offlined CPU which is in a deep stop state.
In the case where the stop-api support is found to be lacking, the
commit 785a12afdb ("powerpc/powernv/idle: Disable LOSE_FULL_CONTEXT
states when stop-api fails") disables deep states that lose hypervisor
context. Thus in this case, the offlined CPU will be put to some
shallow idle state.
However, we currently unconditionally clear the PECE1 in LPCR via
stop-api during CPU-Hotplug even when deep states are disabled due to
stop-api failure.
Fix this by clearing PECE1 of LPCR via stop-api during CPU-Hotplug
*only* when the offlined CPU will be put to a deep state that loses
hypervisor context.
Fixes: 24be85a23d ("powerpc/powernv: Clear PECE1 in LPCR via stop-api only on Hotplug")
Reported-by: Pavithra Prakash <pavirampu@linux.vnet.ibm.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Pavithra Prakash <pavrampu@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
There's a non-trivial dependency between some commits we want to put in
next and the KVM prefetch work around that went into fixes. So merge
fixes into next.
Currently, we use the opal call opal_slw_set_reg() to inform the
Sleep-Winkle Engine (SLW) to restore the contents of some of the
Hypervisor state on wakeup from deep idle states that lose full
hypervisor context (characterized by the flag
OPAL_PM_LOSE_FULL_CONTEXT).
However, the current code has a bug in that if opal_slw_set_reg()
fails, we don't disable the use of these deep states (winkle on
POWER8, stop4 onwards on POWER9).
This patch fixes this bug by ensuring that if programing the
sleep-winkle engine to restore the hypervisor states in
pnv_save_sprs_for_deep_states() fails, then we exclude such states by
clearing the OPAL_PM_LOSE_FULL_CONTEXT flag from
supported_cpuidle_states. As a result POWER8 will be prevented from
using winkle for CPU-Hotplug, and POWER9 will put the offlined CPUs to
the default stop state when available.
Further, we ensure in the initialization of the cpuidle-powernv driver
to only include those states whose flags are present in
supported_cpuidle_states, thereby skipping OPAL_PM_LOSE_FULL_CONTEXT
states when they have been disabled due to stop-api failure.
Fixes: 1e1601b38e ("powerpc/powernv/idle: Restore SPRs for deep idle
states via stop API.")
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently we use the stop-api provided by the firmware to program the
SLW engine to restore the values of hypervisor resources that get lost
on deeper idle states (such as winkle). Since the deep states were
only used for CPU-Hotplug on POWER8 systems, we would program the LPCR
to have the PECE1 bit since Hotplugged CPUs shouldn't be spuriously
woken up by decrementer.
On POWER9, some of the deep platform idle states such as stop4 can be
used in cpuidle as well. In this case, we want the CPU in stop4 to be
woken up by the decrementer when some timer on the CPU expires.
In this patch, we program the stop-api for LPCR with PECE1
bit cleared only when we are offlining the CPU and set it
back once the CPU is online.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In the idle sleep/wake code we know that MSR[EE] is clear, so we can
avoid 2 x mfmsr and 2 x mtmsr by calling the double-underscore
versions of the run latch routines which assume interrupts are already
disabled.
Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
When the CPU wakes from low power state, it begins at the system reset
interrupt with the exception that caused the wakeup encoded in SRR1.
Today, powernv idle wakeup ignores the wakeup reason (except a special
case for HMI), and the regular interrupt corresponding to the
exception will fire after the idle wakeup exits.
Change this to replay the interrupt from the idle wakeup before
interrupts are hard-enabled.
Test on POWER8 of context_switch selftests benchmark with polling idle
disabled (e.g., always nap, giving cross-CPU IPIs) gives the following
results:
original wakeup direct
Different threads, same core: 315k/s 264k/s
Different cores: 235k/s 242k/s
There is a slowdown for doorbell IPI (same core) case because system
reset wakeup does not clear the message and the doorbell interrupt
fires again needlessly.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Rather than concern ourselves with any soft-mask logic in the CPU
hotplug handler, just hard disable interrupts. This ensures there
are no lazy-irqs pending, which means we can call directly to idle
instruction in order to sleep.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
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: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Some of the SPR values (HID0, MSR, SPRG0) don't change during the run
time of a booted kernel, once they have been initialized.
The contents of these SPRs are lost when the CPUs enter deep stop
states. So instead saving and restoring SPRs from the kernel, use the
stop-api provided by the firmware by which the firmware can restore
the contents of these SPRs to their initialized values after wakeup
from a deep stop state.
Apart from these, program the PSSCR value to that of the deepest stop
state via the stop-api. This will be used to indicate to the
underlying firmware as to what stop state to put the threads that have
been woken up by a special-wakeup.
And while we are at programming SPRs via stop-api, ensure that HID1,
HID4 and HID5 registers which are only available on POWER8 are not
requested to be restored by the firware on POWER9.
Signed-off-by: Akshay Adiga <akshay.adiga@linux.vnet.ibm.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The lower 8 bits of core_idle_state_ptr tracks the number of non-idle
threads in the core. This is supposed to be initialized to bit-map
corresponding to the threads_per_core. However, currently it is
initialized to PNV_CORE_IDLE_THREAD_BITS (0xFF). This is correct for
POWER8 which has 8 threads per core, but not for POWER9 which has 4
threads per core.
As a result, on POWER9, core_idle_state_ptr gets initialized to
0xFF. In case when all the threads of the core are idle, the bits
corresponding tracking the idle-threads are non-zero. As a result, the
idle entry/exit code fails to save/restore per-core hypervisor state
since it assumes that there are threads in the cores which are still
active.
Fix this by correctly initializing the lower bits of the
core_idle_state_ptr on the basis of threads_per_core.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Fixes: a7cd88da97 ("powerpc/powernv: Move CPU-Offline idle state invocation from smp.c to idle.c")
Cc: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael 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: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael 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: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Call it a bug]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently during idle-init on power9, if we don't find suitable stop
states in the device tree that can be used as the
default_stop/deepest_stop, we set stop0 (ESL=1,EC=1) as the default
stop state psscr to be used by power9_idle and deepest stop state
which is used by CPU-Hotplug.
However, if the platform firmware has not configured or enabled a stop
state, the kernel should not make any assumptions and fallback to a
default choice.
If the kernel uses a stop state that is not configured by the platform
firmware, it may lead to further failures which should be avoided.
In this patch, we modify the init code to ensure that the kernel uses
only the stop states exposed by the firmware through the device
tree. When a suitable default stop state isn't found, we disable
ppc_md.power_save for power9. Similarly, when a suitable
deepest_stop_state is not found in the device tree exported by the
firmware, fall back to the default busy-wait loop in the CPU-Hotplug
code.
[Changelog written with inputs from svaidy@linux.vnet.ibm.com]
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently, the powernv cpu-offline function assumes that platform idle
states such as stop on POWER9, winkle/sleep/nap on POWER8 are always
available. On POWER8, it picks nap as the default state if other deep
idle states like sleep/winkle are not available and enabled in the
platform.
On POWER9, nap is not available and all idle states are managed by
STOP instruction. The parameters to the idle state are passed through
processor stop status control register (PSSCR). Hence as such
executing STOP would take parameters from current PSSCR. We do not
want to make any assumptions in kernel on what STOP states and PSSCR
features are configured by the platform.
Ideally platform will configure a good set of stop states that can be
used in the kernel. We would like to start with a clean slate, if the
platform choose to not configure any state or there is an error in
platform firmware that lead to no stop states being configured or
allowed to be requested.
This patch adds a fallback method for CPU-Hotplug that is similar to
snooze loop at idle where the threads are left to spin at low priority
and hence reduce the cycles consumed.
This is a safe fallback mechanism in the case when no stop state would
be requested if the platform firmware did not configure them most
likely due to an error condition.
Requesting a stop state when the platform has not configured them or
enabled them would lead to further error conditions which could be
difficult to debug.
[Changelog written with inputs from svaidy@linux.vnet.ibm.com]
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Move the piece of code in powernv/smp.c::pnv_smp_cpu_kill_self() which
transitions the CPU to the deepest available platform idle state to a
new function named pnv_cpu_offline() in powernv/idle.c. The rationale
behind this code movement is that the data required to determine the
deepest available platform state resides in powernv/idle.c.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael 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: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Balbir pointed out that the name of the function pnv_arch300_idle_init
was inconsistent with the names of the variables and functions
pertaining to POWER9 features in book3s_idle.S.
This patch renames pnv_arch300_idle_init to pnv_power9_idle_init.
This patch does not change any behaviour.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
If hardware supports stop state, use the deepest stop state when
the cpu is offlined.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: Michael 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: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
pnv_init_idle_states() discovers supported idle states from the
device tree and does the required initialization. Set power_save
function pointer only after this initialization is done
Otherwise on machines which don't support nap, eg. Power9, the kernel
will crash when it tries to nap.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This is just a smattering of things picked up by sparse that should
be made static.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Long ago, only in the lab, there was OPALv1 and OPALv2. Now there is
just OPALv3, with nobody ever expecting anything on pre-OPALv3 to
be cared about or supported by mainline kernels.
So, let's remove FW_FEATURE_OPALv3 and instead use FW_FEATURE_OPAL
exclusively.
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Although this init call checks for device tree properties before doing
anything, it should still only run on powernv machines.
Reviewed-by: Shreyas B Prabhu <shreyas@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Fastsleep is one of the idle state which cpuidle subsystem currently
uses on power8 machines. In this state L2 cache is brought down to a
threshold voltage. Therefore when the core is in fastsleep, the
communication between L2 and L3 needs to be fenced. But there is a bug
in the current power8 chips surrounding this fencing.
OPAL provides a workaround which precludes the possibility of hitting
this bug. But running with this workaround applied causes checkstop
if any correctable error in L2 cache directory is detected. Hence OPAL
also provides a way to undo the workaround.
In the existing implementation, workaround is applied by the last thread
of the core entering fastsleep and undone by the first thread waking up.
But this has a performance cost. These OPAL calls account for roughly
4000 cycles everytime the core has to enter or wakeup from fastsleep.
This patch introduces a sysfs attribute (fastsleep_workaround_applyonce)
to choose the behavior of this workaround.
By default, fastsleep_workaround_applyonce = 0. In this case, workaround
is applied/undone everytime the core enters/exits fastsleep.
fastsleep_workaround_applyonce = 1. In this case the workaround is
applied once on all the cores and never undone. This can be triggered by
echo 1 > /sys/devices/system/cpu/fastsleep_workaround_applyonce
For simplicity this attribute can be modified only once. Implying, once
fastsleep_workaround_applyonce is changed to 1, it cannot be reverted
to the default state.
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This is a cleanup patch; doesn't change any functionality. Moves
all cpuidle related code from setup.c to a new file.
Signed-off-by: Shreyas B. Prabhu <shreyas@linux.vnet.ibm.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
[mpe: Fix the SMP=n build by including asm/smp.h in idle.c]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Gautham R. Shenoy