linux/kernel/smpboot.c

535 lines
13 KiB
C
Raw Normal View History

/*
* Common SMP CPU bringup/teardown functions
*/
#include <linux/cpu.h>
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
#include <linux/err.h>
#include <linux/smp.h>
smpboot: Add common code for notification from dying CPU RCU ignores offlined CPUs, so they cannot safely run RCU read-side code. (They -can- use SRCU, but not RCU.) This means that any use of RCU during or after the call to arch_cpu_idle_dead(). Unfortunately, commit 2ed53c0d6cc99 added a complete() call, which will contain RCU read-side critical sections if there is a task waiting to be awakened. Which, as it turns out, there almost never is. In my qemu/KVM testing, the to-be-awakened task is not yet asleep more than 99.5% of the time. In current mainline, failure is even harder to reproduce, requiring a virtualized environment that delays the outgoing CPU by at least three jiffies between the time it exits its stop_machine() task at CPU_DYING time and the time it calls arch_cpu_idle_dead() from the idle loop. However, this problem really can occur, especially in virtualized environments, and therefore really does need to be fixed This suggests moving back to the polling loop, but using a much shorter wait, with gentle exponential backoff instead of the old 100-millisecond wait. Most of the time, the loop will exit without waiting at all, and almost all of the remaining uses will wait only five microseconds. If the outgoing CPU is preempted, a loop will wait one jiffy, then increase the wait by a factor of 11/10ths, rounding up. As before, there is a five-second timeout. This commit therefore provides common-code infrastructure to do the dying-to-surviving CPU handoff in a safe manner. This code also provides an indication at CPU-online of whether the CPU to be onlined previously timed out on offline. The new cpu_check_up_prepare() function returns -EBUSY if this CPU previously took more than five seconds to go offline, or -EAGAIN if it has not yet managed to go offline. The rationale for -EAGAIN is that it might still be preempted, so an additional wait might well find it correctly offlined. Architecture-specific code can decide how to handle these conditions. Systems in which CPUs take themselves completely offline might respond to an -EBUSY return as if it was a zero (success) return. Systems in which the surviving CPU must take some action might take it at this time, or might simply mark the other CPU as unusable. Note that architectures that take the easy way out and simply pass the -EBUSY and -EAGAIN upwards will change the sysfs API. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> [ paulmck: Fixed state machine for architectures that don't check earlier CPU-hotplug results as suggested by James Hogan. ]
2015-02-26 02:34:39 +08:00
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/export.h>
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/smpboot.h>
#include "smpboot.h"
#ifdef CONFIG_SMP
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
/*
* For the hotplug case we keep the task structs around and reuse
* them.
*/
static DEFINE_PER_CPU(struct task_struct *, idle_threads);
struct task_struct *idle_thread_get(unsigned int cpu)
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
if (!tsk)
return ERR_PTR(-ENOMEM);
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
init_idle(tsk, cpu);
return tsk;
}
void __init idle_thread_set_boot_cpu(void)
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
{
per_cpu(idle_threads, smp_processor_id()) = current;
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
}
/**
* idle_init - Initialize the idle thread for a cpu
* @cpu: The cpu for which the idle thread should be initialized
*
* Creates the thread if it does not exist.
*/
static inline void idle_init(unsigned int cpu)
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
if (!tsk) {
tsk = fork_idle(cpu);
if (IS_ERR(tsk))
pr_err("SMP: fork_idle() failed for CPU %u\n", cpu);
else
per_cpu(idle_threads, cpu) = tsk;
}
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
}
/**
* idle_threads_init - Initialize idle threads for all cpus
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
*/
void __init idle_threads_init(void)
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
{
unsigned int cpu, boot_cpu;
boot_cpu = smp_processor_id();
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
for_each_possible_cpu(cpu) {
if (cpu != boot_cpu)
idle_init(cpu);
smp: Provide generic idle thread allocation All SMP architectures have magic to fork the idle task and to store it for reusage when cpu hotplug is enabled. Provide a generic infrastructure for it. Create/reinit the idle thread for the cpu which is brought up in the generic code and hand the thread pointer to the architecture code via __cpu_up(). Note, that fork_idle() is called via a workqueue, because this guarantees that the idle thread does not get a reference to a user space VM. This can happen when the boot process did not bring up all possible cpus and a later cpu_up() is initiated via the sysfs interface. In that case fork_idle() would be called in the context of the user space task and take a reference on the user space VM. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Tony Luck <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Howells <dhowells@redhat.com> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: David S. Miller <davem@davemloft.net> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Richard Weinberger <richard@nod.at> Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi <venki@google.com> Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de
2012-04-20 21:05:45 +08:00
}
}
#endif
#endif /* #ifdef CONFIG_SMP */
static LIST_HEAD(hotplug_threads);
static DEFINE_MUTEX(smpboot_threads_lock);
struct smpboot_thread_data {
unsigned int cpu;
unsigned int status;
struct smp_hotplug_thread *ht;
};
enum {
HP_THREAD_NONE = 0,
HP_THREAD_ACTIVE,
HP_THREAD_PARKED,
};
/**
* smpboot_thread_fn - percpu hotplug thread loop function
* @data: thread data pointer
*
* Checks for thread stop and park conditions. Calls the necessary
* setup, cleanup, park and unpark functions for the registered
* thread.
*
* Returns 1 when the thread should exit, 0 otherwise.
*/
static int smpboot_thread_fn(void *data)
{
struct smpboot_thread_data *td = data;
struct smp_hotplug_thread *ht = td->ht;
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
preempt_disable();
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
preempt_enable();
smpboot: make cleanup to mirror setup The per-cpu kthread cleanup() callback is the mirror of the setup() callback. When the per-cpu kthread is started, it first calls setup() to initialize the resources which are then released by cleanup() when the kthread exits. Now since the introduction of a per-cpu kthread cpumask, the kthreads excluded by the cpumask on boot may happen to be parked immediately after their creation without taking the setup() stage, waiting to be asked to unpark to do so. Then when smpboot_unregister_percpu_thread() is later called, the kthread is stopped without having ever called setup(). But this triggers a bug as the kthread unconditionally calls cleanup() on exit but this doesn't mirror any setup(). Thus the kernel crashes because we try to free resources that haven't been initialized, as in the watchdog case: WATCHDOG disable 0 WATCHDOG disable 1 WATCHDOG disable 2 BUG: unable to handle kernel NULL pointer dereference at (null) IP: hrtimer_active+0x26/0x60 [...] Call Trace: hrtimer_try_to_cancel+0x1c/0x280 hrtimer_cancel+0x1d/0x30 watchdog_disable+0x56/0x70 watchdog_cleanup+0xe/0x10 smpboot_thread_fn+0x23c/0x2c0 kthread+0xf8/0x110 ret_from_fork+0x3f/0x70 This bug is currently masked with explicit kthread unparking before kthread_stop() on smpboot_destroy_threads(). This forces a call to setup() and then unpark(). We could fix this by unconditionally calling setup() on kthread entry. But setup() isn't always cheap. In the case of watchdog it launches hrtimer, perf events, etc... So we may as well like to skip it if there are chances the kthread will never be used, as in a reduced cpumask value. So let's simply do a state machine check before calling cleanup() that makes sure setup() has been called before mirroring it. And remove the nasty hack workaround. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Reviewed-by: Chris Metcalf <cmetcalf@ezchip.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-05 06:45:03 +08:00
/* cleanup must mirror setup */
if (ht->cleanup && td->status != HP_THREAD_NONE)
ht->cleanup(td->cpu, cpu_online(td->cpu));
kfree(td);
return 0;
}
if (kthread_should_park()) {
__set_current_state(TASK_RUNNING);
preempt_enable();
if (ht->park && td->status == HP_THREAD_ACTIVE) {
BUG_ON(td->cpu != smp_processor_id());
ht->park(td->cpu);
td->status = HP_THREAD_PARKED;
}
kthread_parkme();
/* We might have been woken for stop */
continue;
}
BUG_ON(td->cpu != smp_processor_id());
/* Check for state change setup */
switch (td->status) {
case HP_THREAD_NONE:
__set_current_state(TASK_RUNNING);
preempt_enable();
if (ht->setup)
ht->setup(td->cpu);
td->status = HP_THREAD_ACTIVE;
continue;
case HP_THREAD_PARKED:
__set_current_state(TASK_RUNNING);
preempt_enable();
if (ht->unpark)
ht->unpark(td->cpu);
td->status = HP_THREAD_ACTIVE;
continue;
}
if (!ht->thread_should_run(td->cpu)) {
preempt_enable_no_resched();
schedule();
} else {
__set_current_state(TASK_RUNNING);
preempt_enable();
ht->thread_fn(td->cpu);
}
}
}
static int
__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
{
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
struct smpboot_thread_data *td;
if (tsk)
return 0;
td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu));
if (!td)
return -ENOMEM;
td->cpu = cpu;
td->ht = ht;
tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu,
ht->thread_comm);
if (IS_ERR(tsk)) {
kfree(td);
return PTR_ERR(tsk);
}
kthread/smpboot: do not park in kthread_create_on_cpu() kthread_create_on_cpu() was added by the commit 2a1d446019f9a5983e ("kthread: Implement park/unpark facility"). It is currently used only when enabling new CPU. For this purpose, the newly created kthread has to be parked. The CPU binding is a bit tricky. The kthread is parked when the CPU has not been allowed yet. And the CPU is bound when the kthread is unparked. The function would be useful for more per-CPU kthreads, e.g. bnx2fc_thread, fcoethread. For this purpose, the newly created kthread should stay in the uninterruptible state. This patch moves the parking into smpboot. It binds the thread already when created. Then the function might be used universally. Also the behavior is consistent with kthread_create() and kthread_create_on_node(). Link: http://lkml.kernel.org/r/1470754545-17632-4-git-send-email-pmladek@suse.com Signed-off-by: Petr Mladek <pmladek@suse.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Tejun Heo <tj@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Josh Triplett <josh@joshtriplett.org> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Borislav Petkov <bp@suse.de> Cc: Michal Hocko <mhocko@suse.cz> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:55:23 +08:00
/*
* Park the thread so that it could start right on the CPU
* when it is available.
*/
kthread_park(tsk);
get_task_struct(tsk);
*per_cpu_ptr(ht->store, cpu) = tsk;
kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones <davej@redhat.com> Reported-and-tested-by: Dave Hansen <dave@sr71.net> Reported-and-tested-by: Borislav Petkov <bp@alien8.de> Acked-by: Peter Ziljstra <peterz@infradead.org> Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com> Cc: dhillf@gmail.com Cc: Ingo Molnar <mingo@kernel.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2013-04-09 15:33:34 +08:00
if (ht->create) {
/*
* Make sure that the task has actually scheduled out
* into park position, before calling the create
* callback. At least the migration thread callback
* requires that the task is off the runqueue.
*/
if (!wait_task_inactive(tsk, TASK_PARKED))
WARN_ON(1);
else
ht->create(cpu);
}
return 0;
}
int smpboot_create_threads(unsigned int cpu)
{
struct smp_hotplug_thread *cur;
int ret = 0;
mutex_lock(&smpboot_threads_lock);
list_for_each_entry(cur, &hotplug_threads, list) {
ret = __smpboot_create_thread(cur, cpu);
if (ret)
break;
}
mutex_unlock(&smpboot_threads_lock);
return ret;
}
static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
{
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
if (!ht->selfparking)
kthread_unpark(tsk);
}
int smpboot_unpark_threads(unsigned int cpu)
{
struct smp_hotplug_thread *cur;
mutex_lock(&smpboot_threads_lock);
list_for_each_entry(cur, &hotplug_threads, list)
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
if (cpumask_test_cpu(cpu, cur->cpumask))
smpboot_unpark_thread(cur, cpu);
mutex_unlock(&smpboot_threads_lock);
return 0;
}
static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
{
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
if (tsk && !ht->selfparking)
kthread_park(tsk);
}
int smpboot_park_threads(unsigned int cpu)
{
struct smp_hotplug_thread *cur;
mutex_lock(&smpboot_threads_lock);
list_for_each_entry_reverse(cur, &hotplug_threads, list)
smpboot_park_thread(cur, cpu);
mutex_unlock(&smpboot_threads_lock);
return 0;
}
static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
{
unsigned int cpu;
/* We need to destroy also the parked threads of offline cpus */
for_each_possible_cpu(cpu) {
struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
if (tsk) {
kthread_stop(tsk);
put_task_struct(tsk);
*per_cpu_ptr(ht->store, cpu) = NULL;
}
}
}
/**
* smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
* to hotplug
* @plug_thread: Hotplug thread descriptor
* @cpumask: The cpumask where threads run
*
* Creates and starts the threads on all online cpus.
*/
int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
const struct cpumask *cpumask)
{
unsigned int cpu;
int ret = 0;
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
return -ENOMEM;
cpumask_copy(plug_thread->cpumask, cpumask);
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
get_online_cpus();
mutex_lock(&smpboot_threads_lock);
for_each_online_cpu(cpu) {
ret = __smpboot_create_thread(plug_thread, cpu);
if (ret) {
smpboot_destroy_threads(plug_thread);
free_cpumask_var(plug_thread->cpumask);
goto out;
}
if (cpumask_test_cpu(cpu, cpumask))
smpboot_unpark_thread(plug_thread, cpu);
}
list_add(&plug_thread->list, &hotplug_threads);
out:
mutex_unlock(&smpboot_threads_lock);
put_online_cpus();
return ret;
}
EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
/**
* smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
* @plug_thread: Hotplug thread descriptor
*
* Stops all threads on all possible cpus.
*/
void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
{
get_online_cpus();
mutex_lock(&smpboot_threads_lock);
list_del(&plug_thread->list);
smpboot_destroy_threads(plug_thread);
mutex_unlock(&smpboot_threads_lock);
put_online_cpus();
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
free_cpumask_var(plug_thread->cpumask);
}
EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
smpboot: Add common code for notification from dying CPU RCU ignores offlined CPUs, so they cannot safely run RCU read-side code. (They -can- use SRCU, but not RCU.) This means that any use of RCU during or after the call to arch_cpu_idle_dead(). Unfortunately, commit 2ed53c0d6cc99 added a complete() call, which will contain RCU read-side critical sections if there is a task waiting to be awakened. Which, as it turns out, there almost never is. In my qemu/KVM testing, the to-be-awakened task is not yet asleep more than 99.5% of the time. In current mainline, failure is even harder to reproduce, requiring a virtualized environment that delays the outgoing CPU by at least three jiffies between the time it exits its stop_machine() task at CPU_DYING time and the time it calls arch_cpu_idle_dead() from the idle loop. However, this problem really can occur, especially in virtualized environments, and therefore really does need to be fixed This suggests moving back to the polling loop, but using a much shorter wait, with gentle exponential backoff instead of the old 100-millisecond wait. Most of the time, the loop will exit without waiting at all, and almost all of the remaining uses will wait only five microseconds. If the outgoing CPU is preempted, a loop will wait one jiffy, then increase the wait by a factor of 11/10ths, rounding up. As before, there is a five-second timeout. This commit therefore provides common-code infrastructure to do the dying-to-surviving CPU handoff in a safe manner. This code also provides an indication at CPU-online of whether the CPU to be onlined previously timed out on offline. The new cpu_check_up_prepare() function returns -EBUSY if this CPU previously took more than five seconds to go offline, or -EAGAIN if it has not yet managed to go offline. The rationale for -EAGAIN is that it might still be preempted, so an additional wait might well find it correctly offlined. Architecture-specific code can decide how to handle these conditions. Systems in which CPUs take themselves completely offline might respond to an -EBUSY return as if it was a zero (success) return. Systems in which the surviving CPU must take some action might take it at this time, or might simply mark the other CPU as unusable. Note that architectures that take the easy way out and simply pass the -EBUSY and -EAGAIN upwards will change the sysfs API. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> [ paulmck: Fixed state machine for architectures that don't check earlier CPU-hotplug results as suggested by James Hogan. ]
2015-02-26 02:34:39 +08:00
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
/**
* smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
* @plug_thread: Hotplug thread descriptor
* @new: Revised mask to use
*
* The cpumask field in the smp_hotplug_thread must not be updated directly
* by the client, but only by calling this function.
watchdog: add watchdog_cpumask sysctl to assist nohz Change the default behavior of watchdog so it only runs on the housekeeping cores when nohz_full is enabled at build and boot time. Allow modifying the set of cores the watchdog is currently running on with a new kernel.watchdog_cpumask sysctl. In the current system, the watchdog subsystem runs a periodic timer that schedules the watchdog kthread to run. However, nohz_full cores are designed to allow userspace application code running on those cores to have 100% access to the CPU. So the watchdog system prevents the nohz_full application code from being able to run the way it wants to, thus the motivation to suppress the watchdog on nohz_full cores, which this patchset provides by default. However, if we disable the watchdog globally, then the housekeeping cores can't benefit from the watchdog functionality. So we allow disabling it only on some cores. See Documentation/lockup-watchdogs.txt for more information. [jhubbard@nvidia.com: fix a watchdog crash in some configurations] Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Acked-by: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:45 +08:00
* This function can only be called on a registered smp_hotplug_thread.
smpboot: allow excluding cpus from the smpboot threads This patch series allows the watchdog to run by default only on the housekeeping cores when nohz_full is in effect; this seems to be a good compromise short of turning it off completely (since the nohz_full cores can't tolerate a watchdog). To provide customizability, we add /proc/sys/kernel/watchdog_cpumask so that the set of cores running the watchdog can be tuned to different values after bootup. To implement this customizability, we add a new smpboot_update_cpumask_percpu_thread() API to the smpboot_thread subsystem that lets us park or unpark "unwanted" threads. And now that threads can be parked for long periods of time, we tweak the /proc/<pid>/stat and /proc/<pid>/status code so parked threads aren't reported as running, which is otherwise confusing. This patch (of 3): This change allows some cores to be excluded from running the smp_hotplug_thread tasks. The following commit to update kernel/watchdog.c to use this functionality is the motivating example, and more information on the motivation is provided there. A new smp_hotplug_thread field is introduced, "cpumask", which is cpumask field managed by the smpboot subsystem that indicates whether or not the given smp_hotplug_thread should run on that core; the cpumask is checked when deciding whether to unpark the thread. To limit the cpumask to less than cpu_possible, you must call smpboot_update_cpumask_percpu_thread() after registering. Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ulrich Obergfell <uobergfe@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-25 07:55:42 +08:00
*/
int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
const struct cpumask *new)
{
struct cpumask *old = plug_thread->cpumask;
cpumask_var_t tmp;
unsigned int cpu;
if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
return -ENOMEM;
get_online_cpus();
mutex_lock(&smpboot_threads_lock);
/* Park threads that were exclusively enabled on the old mask. */
cpumask_andnot(tmp, old, new);
for_each_cpu_and(cpu, tmp, cpu_online_mask)
smpboot_park_thread(plug_thread, cpu);
/* Unpark threads that are exclusively enabled on the new mask. */
cpumask_andnot(tmp, new, old);
for_each_cpu_and(cpu, tmp, cpu_online_mask)
smpboot_unpark_thread(plug_thread, cpu);
cpumask_copy(old, new);
mutex_unlock(&smpboot_threads_lock);
put_online_cpus();
free_cpumask_var(tmp);
return 0;
}
EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread);
smpboot: Add common code for notification from dying CPU RCU ignores offlined CPUs, so they cannot safely run RCU read-side code. (They -can- use SRCU, but not RCU.) This means that any use of RCU during or after the call to arch_cpu_idle_dead(). Unfortunately, commit 2ed53c0d6cc99 added a complete() call, which will contain RCU read-side critical sections if there is a task waiting to be awakened. Which, as it turns out, there almost never is. In my qemu/KVM testing, the to-be-awakened task is not yet asleep more than 99.5% of the time. In current mainline, failure is even harder to reproduce, requiring a virtualized environment that delays the outgoing CPU by at least three jiffies between the time it exits its stop_machine() task at CPU_DYING time and the time it calls arch_cpu_idle_dead() from the idle loop. However, this problem really can occur, especially in virtualized environments, and therefore really does need to be fixed This suggests moving back to the polling loop, but using a much shorter wait, with gentle exponential backoff instead of the old 100-millisecond wait. Most of the time, the loop will exit without waiting at all, and almost all of the remaining uses will wait only five microseconds. If the outgoing CPU is preempted, a loop will wait one jiffy, then increase the wait by a factor of 11/10ths, rounding up. As before, there is a five-second timeout. This commit therefore provides common-code infrastructure to do the dying-to-surviving CPU handoff in a safe manner. This code also provides an indication at CPU-online of whether the CPU to be onlined previously timed out on offline. The new cpu_check_up_prepare() function returns -EBUSY if this CPU previously took more than five seconds to go offline, or -EAGAIN if it has not yet managed to go offline. The rationale for -EAGAIN is that it might still be preempted, so an additional wait might well find it correctly offlined. Architecture-specific code can decide how to handle these conditions. Systems in which CPUs take themselves completely offline might respond to an -EBUSY return as if it was a zero (success) return. Systems in which the surviving CPU must take some action might take it at this time, or might simply mark the other CPU as unusable. Note that architectures that take the easy way out and simply pass the -EBUSY and -EAGAIN upwards will change the sysfs API. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> [ paulmck: Fixed state machine for architectures that don't check earlier CPU-hotplug results as suggested by James Hogan. ]
2015-02-26 02:34:39 +08:00
static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
/*
* Called to poll specified CPU's state, for example, when waiting for
* a CPU to come online.
*/
int cpu_report_state(int cpu)
{
return atomic_read(&per_cpu(cpu_hotplug_state, cpu));
}
/*
* If CPU has died properly, set its state to CPU_UP_PREPARE and
* return success. Otherwise, return -EBUSY if the CPU died after
* cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN
* if cpu_wait_death() timed out and the CPU still hasn't gotten around
* to dying. In the latter two cases, the CPU might not be set up
* properly, but it is up to the arch-specific code to decide.
* Finally, -EIO indicates an unanticipated problem.
*
* Note that it is permissible to omit this call entirely, as is
* done in architectures that do no CPU-hotplug error checking.
*/
int cpu_check_up_prepare(int cpu)
{
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
return 0;
}
switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) {
case CPU_POST_DEAD:
/* The CPU died properly, so just start it up again. */
atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE);
return 0;
case CPU_DEAD_FROZEN:
/*
* Timeout during CPU death, so let caller know.
* The outgoing CPU completed its processing, but after
* cpu_wait_death() timed out and reported the error. The
* caller is free to proceed, in which case the state
* will be reset properly by cpu_set_state_online().
* Proceeding despite this -EBUSY return makes sense
* for systems where the outgoing CPUs take themselves
* offline, with no post-death manipulation required from
* a surviving CPU.
*/
return -EBUSY;
case CPU_BROKEN:
/*
* The most likely reason we got here is that there was
* a timeout during CPU death, and the outgoing CPU never
* did complete its processing. This could happen on
* a virtualized system if the outgoing VCPU gets preempted
* for more than five seconds, and the user attempts to
* immediately online that same CPU. Trying again later
* might return -EBUSY above, hence -EAGAIN.
*/
return -EAGAIN;
default:
/* Should not happen. Famous last words. */
return -EIO;
}
}
/*
* Mark the specified CPU online.
*
* Note that it is permissible to omit this call entirely, as is
* done in architectures that do no CPU-hotplug error checking.
*/
void cpu_set_state_online(int cpu)
{
(void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE);
}
#ifdef CONFIG_HOTPLUG_CPU
/*
* Wait for the specified CPU to exit the idle loop and die.
*/
bool cpu_wait_death(unsigned int cpu, int seconds)
{
int jf_left = seconds * HZ;
int oldstate;
bool ret = true;
int sleep_jf = 1;
might_sleep();
/* The outgoing CPU will normally get done quite quickly. */
if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD)
goto update_state;
udelay(5);
/* But if the outgoing CPU dawdles, wait increasingly long times. */
while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) {
schedule_timeout_uninterruptible(sleep_jf);
jf_left -= sleep_jf;
if (jf_left <= 0)
break;
sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10);
}
update_state:
oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
if (oldstate == CPU_DEAD) {
/* Outgoing CPU died normally, update state. */
smp_mb(); /* atomic_read() before update. */
atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD);
} else {
/* Outgoing CPU still hasn't died, set state accordingly. */
if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
oldstate, CPU_BROKEN) != oldstate)
goto update_state;
ret = false;
}
return ret;
}
/*
* Called by the outgoing CPU to report its successful death. Return
* false if this report follows the surviving CPU's timing out.
*
* A separate "CPU_DEAD_FROZEN" is used when the surviving CPU
* timed out. This approach allows architectures to omit calls to
* cpu_check_up_prepare() and cpu_set_state_online() without defeating
* the next cpu_wait_death()'s polling loop.
*/
bool cpu_report_death(void)
{
int oldstate;
int newstate;
int cpu = smp_processor_id();
do {
oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu));
if (oldstate != CPU_BROKEN)
newstate = CPU_DEAD;
else
newstate = CPU_DEAD_FROZEN;
} while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu),
oldstate, newstate) != oldstate);
return newstate == CPU_DEAD;
}
#endif /* #ifdef CONFIG_HOTPLUG_CPU */