From 2baab4e90495ebc9826c93f79d74d6e60a828d24 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 20 Mar 2012 15:57:01 +0100 Subject: [PATCH] sched: Fix select_fallback_rq() vs cpu_active/cpu_online Commit 5fbd036b55 ("sched: Cleanup cpu_active madness"), which was supposed to finally sort the cpu_active mess, instead uncovered more. Since CPU_STARTING is ran before setting the cpu online, there's a (small) window where the cpu has active,!online. If during this time there's a wakeup of a task that used to reside on that cpu select_task_rq() will use select_fallback_rq() to compute an alternative cpu to run on since we find !online. select_fallback_rq() however will compute the new cpu against cpu_active, this means that it can return the same cpu it started out with, the !online one, since that cpu is in fact marked active. This results in us trying to scheduling a task on an offline cpu and triggering a WARN in the IPI code. The solution proposed by Chuansheng Liu of setting cpu_active in set_cpu_online() is buggy, firstly not all archs actually use set_cpu_online(), secondly, not all archs call set_cpu_online() with IRQs disabled, this means we would introduce either the same race or the race from fd8a7de17 ("x86: cpu-hotplug: Prevent softirq wakeup on wrong CPU") -- albeit much narrower. [ By setting online first and active later we have a window of online,!active, fresh and bound kthreads have task_cpu() of 0 and since cpu0 isn't in tsk_cpus_allowed() we end up in select_fallback_rq() which excludes !active, resulting in a reset of ->cpus_allowed and the thread running all over the place. ] The solution is to re-work select_fallback_rq() to require active _and_ online. This makes the active,!online case work as expected, OTOH archs running CPU_STARTING after setting online are now vulnerable to the issue from fd8a7de17 -- these are alpha and blackfin. Reported-by: Chuansheng Liu Signed-off-by: Peter Zijlstra Cc: Mike Frysinger Cc: linux-alpha@vger.kernel.org Link: http://lkml.kernel.org/n/tip-hubqk1i10o4dpvlm06gq7v6j@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 6 ++-- kernel/cpuset.c | 20 +++----------- kernel/sched/core.c | 62 +++++++++++++++++++++++++++++++----------- 3 files changed, 52 insertions(+), 36 deletions(-) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index e9eaec522655..e0ffaf061ab7 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -22,7 +22,7 @@ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_update_active_cpus(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); -extern int cpuset_cpus_allowed_fallback(struct task_struct *p); +extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -144,10 +144,8 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, cpumask_copy(mask, cpu_possible_mask); } -static inline int cpuset_cpus_allowed_fallback(struct task_struct *p) +static inline void cpuset_cpus_allowed_fallback(struct task_struct *p) { - do_set_cpus_allowed(p, cpu_possible_mask); - return cpumask_any(cpu_active_mask); } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index a09ac2b9a661..c9837b74ab96 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2195,7 +2195,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) mutex_unlock(&callback_mutex); } -int cpuset_cpus_allowed_fallback(struct task_struct *tsk) +void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpuset *cs; int cpu; @@ -2219,22 +2219,10 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. + * + * select_fallback_rq() will fix things ups and set cpu_possible_mask + * if required. */ - - cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask); - if (cpu >= nr_cpu_ids) { - /* - * Either tsk->cpus_allowed is wrong (see above) or it - * is actually empty. The latter case is only possible - * if we are racing with remove_tasks_in_empty_cpuset(). - * Like above we can temporary set any mask and rely on - * set_cpus_allowed_ptr() as synchronization point. - */ - do_set_cpus_allowed(tsk, cpu_possible_mask); - cpu = cpumask_any(cpu_active_mask); - } - - return cpu; } void cpuset_init_current_mems_allowed(void) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e3ccc13c4caa..9c1629c90b2d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1263,29 +1263,59 @@ EXPORT_SYMBOL_GPL(kick_process); */ static int select_fallback_rq(int cpu, struct task_struct *p) { - int dest_cpu; const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); + enum { cpuset, possible, fail } state = cpuset; + int dest_cpu; /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) + for_each_cpu_mask(dest_cpu, *nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) return dest_cpu; + } - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask); - if (dest_cpu < nr_cpu_ids) - return dest_cpu; + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu_mask(dest_cpu, *tsk_cpus_allowed(p)) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + goto out; + } - /* No more Mr. Nice Guy. */ - dest_cpu = cpuset_cpus_allowed_fallback(p); - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", - task_pid_nr(p), p->comm, cpu); + switch (state) { + case cpuset: + /* No more Mr. Nice Guy. */ + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_sched("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } } return dest_cpu;