sched: Introduce task_struct::user_cpus_ptr to track requested affinity

In preparation for saving and restoring the user-requested CPU affinity
mask of a task, add a new cpumask_t pointer to 'struct task_struct'.

If the pointer is non-NULL, then the mask is copied across fork() and
freed on task exit.

Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <Valentin.Schneider@arm.com>
Link: https://lore.kernel.org/r/20210730112443.23245-7-will@kernel.org

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50db949..2c5d638 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -748,6 +748,7 @@ struct task_struct {
        unsigned int                    policy;
        int                             nr_cpus_allowed;
        const cpumask_t                 *cpus_ptr;
+       cpumask_t                       *user_cpus_ptr;
        cpumask_t                       cpus_mask;
        void                            *migration_pending;
 #ifdef CONFIG_SMP
@@ -1706,6 +1707,8 @@ extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
+extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node);
+extern void release_user_cpus_ptr(struct task_struct *p);
 #else
 static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
@@ -1716,6 +1719,16 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma
                return -EINVAL;
        return 0;
 }
+static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
+{
+       if (src->user_cpus_ptr)
+               return -EINVAL;
+       return 0;
+}
+static inline void release_user_cpus_ptr(struct task_struct *p)
+{
+       WARN_ON(p->user_cpus_ptr);
+}
 #endif
 
 extern int yield_to(struct task_struct *p, bool preempt);

diff --git a/init/init_task.c b/init/init_task.c
index 562f2ef..2d02406 100644 (file)
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -80,6 +80,7 @@ struct task_struct init_task
        .normal_prio    = MAX_PRIO - 20,
        .policy         = SCHED_NORMAL,
        .cpus_ptr       = &init_task.cpus_mask,
+       .user_cpus_ptr  = NULL,
        .cpus_mask      = CPU_MASK_ALL,
        .nr_cpus_allowed= NR_CPUS,
        .mm             = NULL,

diff --git a/kernel/fork.c b/kernel/fork.c
index 1a9af73..5d7addf 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -446,6 +446,7 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+       release_user_cpus_ptr(tsk);
        scs_release(tsk);
 
 #ifndef CONFIG_THREAD_INFO_IN_TASK
@@ -919,6 +920,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #endif
        if (orig->cpus_ptr == &orig->cpus_mask)
                tsk->cpus_ptr = &tsk->cpus_mask;
+       dup_user_cpus_ptr(tsk, orig, node);
 
        /*
         * One for the user space visible state that goes away when reaped.

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8cec0d2..360a3ec 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2480,6 +2480,26 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
        __do_set_cpus_allowed(p, new_mask, 0);
 }
 
+int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
+                     int node)
+{
+       if (!src->user_cpus_ptr)
+               return 0;
+
+       dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+       if (!dst->user_cpus_ptr)
+               return -ENOMEM;
+
+       cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+       return 0;
+}
+
+void release_user_cpus_ptr(struct task_struct *p)
+{
+       kfree(p->user_cpus_ptr);
+       p->user_cpus_ptr = NULL;
+}
+
 /*
  * This function is wildly self concurrent; here be dragons.
  *