linux-stable.git/arch/powerpc/kernel/idle.c, branch linux-3.3.y

powerpc: Fix broken cpu_idle_wait() implementation

2012-06-01T07:15:42+00:00

commit 9cd75e13de2dcf32ecc21c7f277cff3c0ced059e upstream.

commit 771dae818 (powerpc/cpuidle: Add cpu_idle_wait() to allow
switching of idle routines) implemented cpu_idle_wait() for powerpc.

The changelog says:
 "The equivalent routine for x86 is in arch/x86/kernel/process.c
  but the powerpc implementation is different.":

Unfortunately the changelog is completely useless as it does not tell
_WHY_ it is different.

Aside of being different the implementation is patently wrong.

The rescheduling IPI is async. That means that there is no guarantee,
that the other cores have executed the IPI when cpu_idle_wait()
returns. But that's the whole purpose of this function: to guarantee
that no CPU uses the old idle handler anymore.

Use the smp_functional_call() based implementation, which fulfils the
requirements.

[ This code is going to replaced by a core version to remove all the
  pointless copies in arch/*, but this one should go to stable ]

Signed-off-by: Thomas Gleixner 
Acked-by: Peter Zijlstra 
Cc: Deepthi Dharwar 
Cc: Trinabh Gupta 
Cc: Arun R Bharadwaj 
Acked-by: Benjamin Herrenschmidt 
Link: http://lkml.kernel.org/r/20120507175651.980164748@linutronix.de
Signed-off-by: Greg Kroah-Hartman

powerpc: Fix RCU idle and hcall tracing

2012-01-11T00:54:20+00:00

Tracepoints should not be called inside an rcu_idle_enter/rcu_idle_exit
region. Since pSeries calls H_CEDE in the idle loop, we were violating
this rule.

commit a7b152d5342c (powerpc: Tell RCU about idle after hcall tracing)
tried to work around it by delaying the rcu_idle_enter until after we
called the hcall tracepoint, but there are a number of issues with it.

The hcall tracepoint trampoline code is called conditionally when the
tracepoint is enabled. If the tracepoint is not enabled we never call
rcu_idle_enter. The idle_uses_rcu check was also done at compile time
which breaks multiplatform builds.

The simple fix is to avoid tracing H_CEDE and rely on other tracepoints
and the hypervisor dispatch trace log to work out if we called H_CEDE.

This fixes a hang during boot on pSeries.

Signed-off-by: Anton Blanchard 
Acked-by: Paul E. McKenney 
Signed-off-by: Benjamin Herrenschmidt

Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

2012-01-07T01:58:22+00:00

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (185 commits)
  powerpc: fix compile error with 85xx/p1010rdb.c
  powerpc: fix compile error with 85xx/p1023_rds.c
  powerpc/fsl: add MSI support for the Freescale hypervisor
  arch/powerpc/sysdev/fsl_rmu.c: introduce missing kfree
  powerpc/fsl: Add support for Integrated Flash Controller
  powerpc/fsl: update compatiable on fsl 16550 uart nodes
  powerpc/85xx: fix PCI and localbus properties in p1022ds.dts
  powerpc/85xx: re-enable ePAPR byte channel driver in corenet32_smp_defconfig
  powerpc/fsl: Update defconfigs to enable some standard FSL HW features
  powerpc: Add TBI PHY node to first MDIO bus
  sbc834x: put full compat string in board match check
  powerpc/fsl-pci: Allow 64-bit PCIe devices to DMA to any memory address
  powerpc: Fix unpaired probe_hcall_entry and probe_hcall_exit
  offb: Fix setting of the pseudo-palette for >8bpp
  offb: Add palette hack for qemu "standard vga" framebuffer
  offb: Fix bug in calculating requested vram size
  powerpc/boot: Change the WARN to INFO for boot wrapper overlap message
  powerpc/44x: Fix build error on currituck platform
  powerpc/boot: Change the load address for the wrapper to fit the kernel
  powerpc/44x: Enable CRASH_DUMP for 440x
  ...

Fix up a trivial conflict in arch/powerpc/include/asm/cputime.h due to
the additional sparse-checking code for cputime_t.

nohz: Remove tick_nohz_idle_enter_norcu() / tick_nohz_idle_exit_norcu()

2011-12-11T18:31:57+00:00

Those two APIs were provided to optimize the calls of
tick_nohz_idle_enter() and rcu_idle_enter() into a single
irq disabled section. This way no interrupt happening in-between would
needlessly process any RCU job.

Now we are talking about an optimization for which benefits
have yet to be measured. Let's start simple and completely decouple
idle rcu and dyntick idle logics to simplify.

Signed-off-by: Frederic Weisbecker 
Cc: Ingo Molnar 
Cc: Thomas Gleixner 
Cc: Peter Zijlstra 
Reviewed-by: Josh Triplett 
Signed-off-by: Paul E. McKenney

powerpc: Tell RCU about idle after hcall tracing

2011-12-11T18:31:39+00:00

The PowerPC pSeries platform (CONFIG_PPC_PSERIES=y) enables
hypervisor-call tracing for CONFIG_TRACEPOINTS=y kernels.  One of the
hypervisor calls that is traced is the H_CEDE call in the idle loop
that tells the hypervisor that this OS instance no longer needs the
current CPU.  However, tracing uses RCU, so this combination of kernel
configuration variables needs to avoid telling RCU about the current CPU's
idleness until after the H_CEDE-entry tracing completes on the one hand,
and must tell RCU that the the current CPU is no longer idle before the
H_CEDE-exit tracing starts.

In all other cases, it suffices to inform RCU of CPU idleness upon
idle-loop entry and exit.

This commit makes the required adjustments.

Signed-off-by: Paul E. McKenney 
Signed-off-by: Paul E. McKenney 
Reviewed-by: Josh Triplett

nohz: Allow rcu extended quiescent state handling seperately from tick stop

2011-12-11T18:31:36+00:00

It is assumed that rcu won't be used once we switch to tickless
mode and until we restart the tick. However this is not always
true, as in x86-64 where we dereference the idle notifiers after
the tick is stopped.

To prepare for fixing this, add two new APIs:
tick_nohz_idle_enter_norcu() and tick_nohz_idle_exit_norcu().

If no use of RCU is made in the idle loop between
tick_nohz_enter_idle() and tick_nohz_exit_idle() calls, the arch
must instead call the new *_norcu() version such that the arch doesn't
need to call rcu_idle_enter() and rcu_idle_exit().

Otherwise the arch must call tick_nohz_enter_idle() and
tick_nohz_exit_idle() and also call explicitly:

- rcu_idle_enter() after its last use of RCU before the CPU is put
to sleep.
- rcu_idle_exit() before the first use of RCU after the CPU is woken
up.

Signed-off-by: Frederic Weisbecker 
Cc: Mike Frysinger 
Cc: Guan Xuetao 
Cc: David Miller 
Cc: Chris Metcalf 
Cc: Hans-Christian Egtvedt 
Cc: Ralf Baechle 
Cc: Paul E. McKenney 
Cc: Ingo Molnar 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: H. Peter Anvin 
Cc: Russell King 
Cc: Paul Mackerras 
Cc: Heiko Carstens 
Cc: Paul Mundt 
Signed-off-by: Paul E. McKenney

nohz: Separate out irq exit and idle loop dyntick logic

2011-12-11T18:31:35+00:00

The tick_nohz_stop_sched_tick() function, which tries to delay
the next timer tick as long as possible, can be called from two
places:

- From the idle loop to start the dytick idle mode
- From interrupt exit if we have interrupted the dyntick
idle mode, so that we reprogram the next tick event in
case the irq changed some internal state that requires this
action.

There are only few minor differences between both that
are handled by that function, driven by the ts->inidle
cpu variable and the inidle parameter. The whole guarantees
that we only update the dyntick mode on irq exit if we actually
interrupted the dyntick idle mode, and that we enter in RCU extended
quiescent state from idle loop entry only.

Split this function into:

- tick_nohz_idle_enter(), which sets ts->inidle to 1, enters
dynticks idle mode unconditionally if it can, and enters into RCU
extended quiescent state.

- tick_nohz_irq_exit() which only updates the dynticks idle mode
when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called).

To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed
into tick_nohz_idle_exit().

This simplifies the code and micro-optimize the irq exit path (no need
for local_irq_save there). This also prepares for the split between
dynticks and rcu extended quiescent state logics. We'll need this split to
further fix illegal uses of RCU in extended quiescent states in the idle
loop.

Signed-off-by: Frederic Weisbecker 
Cc: Mike Frysinger 
Cc: Guan Xuetao 
Cc: David Miller 
Cc: Chris Metcalf 
Cc: Hans-Christian Egtvedt 
Cc: Ralf Baechle 
Cc: Paul E. McKenney 
Cc: Ingo Molnar 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: H. Peter Anvin 
Cc: Russell King 
Cc: Paul Mackerras 
Cc: Heiko Carstens 
Cc: Paul Mundt 
Signed-off-by: Paul E. McKenney 
Reviewed-by: Josh Triplett

powerpc/cpuidle: Add cpu_idle_wait() to allow switching of idle routines

2011-12-08T02:54:58+00:00

This patch provides cpu_idle_wait() routine for the powerpc
platform which is required by the cpuidle subsystem. This
routine is required to change the idle handler on SMP systems.
The equivalent routine for x86 is in arch/x86/kernel/process.c
but the powerpc implementation is different.

cpuidle_disable variable is to enable/disable cpuidle
framework if power_save option is set during the boot
time.

Signed-off-by: Deepthi Dharwar 
Signed-off-by: Trinabh Gupta 
Signed-off-by: Arun R Bharadwaj 
Signed-off-by: Benjamin Herrenschmidt

powerpc: Re-enable preemption before cpu_die()

2010-08-24T05:26:29+00:00

start_secondary() is called shortly after _start and also via

cpu_idle()->cpu_die()->pseries_mach_cpu_die()

start_secondary() expects a preempt_count() of 0. pseries_mach_cpu_die() is
called via the cpu_idle() routine with preemption disabled, resulting in the
following repeating message during rapid cpu offline/online tests
with CONFIG_PREEMPT=y:

BUG: scheduling while atomic: swapper/0/0x00000002
Modules linked in: autofs4 binfmt_misc dm_mirror dm_region_hash dm_log [last unloaded: scsi_wait_scan]
Call Trace:
[c00000010e7079c0] [c0000000000133ec] .show_stack+0xd8/0x218 (unreliable)
[c00000010e707aa0] [c0000000006a47f0] .dump_stack+0x28/0x3c
[c00000010e707b20] [c00000000006e7a4] .__schedule_bug+0x7c/0x9c
[c00000010e707bb0] [c000000000699d9c] .schedule+0x104/0x800
[c00000010e707cd0] [c000000000015b24] .cpu_idle+0x1c4/0x1d8
[c00000010e707d70] [c0000000006aa1b4] .start_secondary+0x398/0x3d4
[c00000010e707e30] [c000000000008278] .start_secondary_resume+0x10/0x14

Move the cpu_die() call inside the existing preemption enabled block of
cpu_idle(). This is safe as the idle task is affined to a single CPU so the
debug_smp_processor_id() tests (from cpu_should_die()) won't trigger as we are
in a "migration disabled" region.

Signed-off-by: Darren Hart 
Acked-by: Will Schmidt 
Cc: Thomas Gleixner 
Cc: Nathan Fontenot 
Cc: Robert Jennings 
Cc: Brian King 
Signed-off-by: Benjamin Herrenschmidt

sysctl: Drop & in front of every proc_handler.

2009-11-18T16:37:40+00:00

For consistency drop & in front of every proc_handler.  Explicity
taking the address is unnecessary and it prevents optimizations
like stubbing the proc_handlers to NULL.

Cc: Alexey Dobriyan 
Cc: Ingo Molnar 
Cc: Joe Perches 
Signed-off-by: Eric W. Biederman