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