From 8239c25f47d2b318156993b15f33900a86ea5e17 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 20 Apr 2012 13:05:42 +0000 Subject: smp: Add task_struct argument to __cpu_up() Preparatory patch to make the idle thread allocation for secondary cpus generic. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Rusty Russell Cc: Paul E. McKenney Cc: Srivatsa S. Bhat Cc: Matt Turner Cc: Russell King Cc: Mike Frysinger Cc: Jesper Nilsson Cc: Richard Kuo Cc: Tony Luck Cc: Hirokazu Takata Cc: Ralf Baechle Cc: David Howells Cc: James E.J. Bottomley Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Paul Mundt Cc: David S. Miller Cc: Chris Metcalf Cc: Richard Weinberger Cc: x86@kernel.org Link: http://lkml.kernel.org/r/20120420124556.964170564@linutronix.de --- kernel/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 2060c6e57027..e711aef0fb3c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -309,7 +309,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) } /* Arch-specific enabling code. */ - ret = __cpu_up(cpu); + ret = __cpu_up(cpu, NULL); if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); -- cgit v1.2.3 From 38498a67aa2cf8c80754b8d304bfacc10bc582b5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 20 Apr 2012 13:05:44 +0000 Subject: smp: Add generic smpboot facility Start a new file, which will hold SMP and CPU hotplug related generic infrastructure. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Rusty Russell Cc: Paul E. McKenney Cc: Srivatsa S. Bhat Cc: Matt Turner Cc: Russell King Cc: Mike Frysinger Cc: Jesper Nilsson Cc: Richard Kuo Cc: Tony Luck Cc: Hirokazu Takata Cc: Ralf Baechle Cc: David Howells Cc: James E.J. Bottomley Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Paul Mundt Cc: David S. Miller Cc: Chris Metcalf Cc: Richard Weinberger Cc: x86@kernel.org Link: http://lkml.kernel.org/r/20120420124557.035417523@linutronix.de --- kernel/cpu.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index e711aef0fb3c..e58b99ada3d8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -17,6 +17,8 @@ #include #include +#include "smpboot.h" + #ifdef CONFIG_SMP /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); @@ -300,6 +302,11 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) return -EINVAL; cpu_hotplug_begin(); + + ret = smpboot_prepare(cpu); + if (ret) + goto out; + ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); if (ret) { nr_calls--; @@ -320,6 +327,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) out_notify: if (ret != 0) __cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL); +out: cpu_hotplug_done(); return ret; -- cgit v1.2.3 From 29d5e0476e1c4a513859e7858845ad172f560389 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 20 Apr 2012 13:05:45 +0000 Subject: 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 Cc: Peter Zijlstra Cc: Rusty Russell Cc: Paul E. McKenney Cc: Srivatsa S. Bhat Cc: Matt Turner Cc: Russell King Cc: Mike Frysinger Cc: Jesper Nilsson Cc: Richard Kuo Cc: Tony Luck Cc: Hirokazu Takata Cc: Ralf Baechle Cc: David Howells Cc: James E.J. Bottomley Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Paul Mundt Cc: David S. Miller Cc: Chris Metcalf Cc: Richard Weinberger Cc: x86@kernel.org Acked-by: Venkatesh Pallipadi Link: http://lkml.kernel.org/r/20120420124557.102478630@linutronix.de --- kernel/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index e58b99ada3d8..05c46bae5e55 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -316,7 +316,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) } /* Arch-specific enabling code. */ - ret = __cpu_up(cpu, NULL); + ret = __cpu_up(cpu, idle_thread_get(cpu)); if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); -- cgit v1.2.3 From 3bb5d2ee396aabaa4e318f17e94d13e2ee0e5a88 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 20 Apr 2012 17:08:50 -0700 Subject: smp, idle: Allocate idle thread for each possible cpu during boot percpu areas are already allocated during boot for each possible cpu. percpu idle threads can be considered as an extension of the percpu areas, and allocate them for each possible cpu during boot. This will eliminate the need for workqueue based idle thread allocation. In future we can move the idle thread area into the percpu area too. [ tglx: Moved the loop into smpboot.c and added an error check when the init code failed to allocate an idle thread for a cpu which should be onlined ] Signed-off-by: Suresh Siddha Cc: Peter Zijlstra Cc: Rusty Russell Cc: Paul E. McKenney Cc: Srivatsa S. Bhat Cc: Tejun Heo Cc: David Rientjes Cc: venki@google.com Link: http://lkml.kernel.org/r/1334966930.28674.245.camel@sbsiddha-desk.sc.intel.com Signed-off-by: Thomas Gleixner --- kernel/cpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 05c46bae5e55..0e6353cf147a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -297,15 +297,18 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) int ret, nr_calls = 0; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct task_struct *idle; if (cpu_online(cpu) || !cpu_present(cpu)) return -EINVAL; cpu_hotplug_begin(); - ret = smpboot_prepare(cpu); - if (ret) + idle = idle_thread_get(cpu); + if (IS_ERR(idle)) { + ret = PTR_ERR(idle); goto out; + } ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); if (ret) { @@ -316,7 +319,7 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) } /* Arch-specific enabling code. */ - ret = __cpu_up(cpu, idle_thread_get(cpu)); + ret = __cpu_up(cpu, idle); if (ret != 0) goto out_notify; BUG_ON(!cpu_online(cpu)); -- cgit v1.2.3 From cb79295e20a8088a2fd6a9b3cb5f2d889ec36b4d Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 31 May 2012 16:26:22 -0700 Subject: cpu: introduce clear_tasks_mm_cpumask() helper Many architectures clear tasks' mm_cpumask like this: read_lock(&tasklist_lock); for_each_process(p) { if (p->mm) cpumask_clear_cpu(cpu, mm_cpumask(p->mm)); } read_unlock(&tasklist_lock); Depending on the context, the code above may have several problems, such as: 1. Working with task->mm w/o getting mm or grabing the task lock is dangerous as ->mm might disappear (exit_mm() assigns NULL under task_lock(), so tasklist lock is not enough). 2. Checking for process->mm is not enough because process' main thread may exit or detach its mm via use_mm(), but other threads may still have a valid mm. This patch implements a small helper function that does things correctly, i.e.: 1. We take the task's lock while whe handle its mm (we can't use get_task_mm()/mmput() pair as mmput() might sleep); 2. To catch exited main thread case, we use find_lock_task_mm(), which walks up all threads and returns an appropriate task (with task lock held). Also, Per Peter Zijlstra's idea, now we don't grab tasklist_lock in the new helper, instead we take the rcu read lock. We can do this because the function is called after the cpu is taken down and marked offline, so no new tasks will get this cpu set in their mm mask. Signed-off-by: Anton Vorontsov Cc: Richard Weinberger Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Russell King Cc: Benjamin Herrenschmidt Cc: Mike Frysinger Cc: Paul Mundt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpu.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 0e6353cf147a..0575197deb4a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -10,6 +10,8 @@ #include #include #include +#include +#include #include #include #include @@ -173,6 +175,30 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_cpu_notifier); +void clear_tasks_mm_cpumask(int cpu) +{ + struct task_struct *p; + + /* + * This function is called after the cpu is taken down and marked + * offline, so its not like new tasks will ever get this cpu set in + * their mm mask. -- Peter Zijlstra + * Thus, we may use rcu_read_lock() here, instead of grabbing + * full-fledged tasklist_lock. + */ + rcu_read_lock(); + for_each_process(p) { + struct task_struct *t; + + t = find_lock_task_mm(p); + if (!t) + continue; + cpumask_clear_cpu(cpu, mm_cpumask(t->mm)); + task_unlock(t); + } + rcu_read_unlock(); +} + static inline void check_for_tasks(int cpu) { struct task_struct *p; -- cgit v1.2.3 From e4cc2f873ad0833aa5c4aca56bebe15b9603a1e7 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Thu, 31 May 2012 16:26:26 -0700 Subject: kernel/cpu.c: document clear_tasks_mm_cpumask() Add more comments on clear_tasks_mm_cpumask, plus adds a runtime check: the function is only suitable for offlined CPUs, and if called inappropriately, the kernel should scream aloud. [akpm@linux-foundation.org: tweak comment: s/walks up/walks/, use 80 cols] Suggested-by: Andrew Morton Suggested-by: Peter Zijlstra Signed-off-by: Anton Vorontsov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpu.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index 0575197deb4a..a4eb5227a19e 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -175,6 +176,18 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_cpu_notifier); +/** + * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU + * @cpu: a CPU id + * + * This function walks all processes, finds a valid mm struct for each one and + * then clears a corresponding bit in mm's cpumask. While this all sounds + * trivial, there are various non-obvious corner cases, which this function + * tries to solve in a safe manner. + * + * Also note that the function uses a somewhat relaxed locking scheme, so it may + * be called only for an already offlined CPU. + */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; @@ -186,10 +199,15 @@ void clear_tasks_mm_cpumask(int cpu) * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ + WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; + /* + * Main thread might exit, but other threads may still have + * a valid mm. Find one. + */ t = find_lock_task_mm(p); if (!t) continue; -- cgit v1.2.3