cls_can: Handle generator now uses full 32 bits for its values.

[lisovros/linux_canprio.git] / mm / memcontrol.c

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3eed583895a6f31eb434a252697371c7daa6bbd4..e6aadd65a71a1bd9c30e0921364aacb37c2c3372 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -269,13 +269,14 @@ enum move_type {
 
 /* "mc" and its members are protected by cgroup_mutex */
 static struct move_charge_struct {
-       spinlock_t        lock; /* for from, to, moving_task */
+       spinlock_t        lock; /* for from, to */
        struct mem_cgroup *from;
        struct mem_cgroup *to;
        unsigned long precharge;
        unsigned long moved_charge;
        unsigned long moved_swap;
        struct task_struct *moving_task;        /* a task moving charges */
+       struct mm_struct *mm;
        wait_queue_head_t waitq;                /* a waitq for other context */
 } mc = {
        .lock = __SPIN_LOCK_UNLOCKED(mc.lock),
@@ -3587,9 +3588,13 @@ unlock:
 
 static void mem_cgroup_threshold(struct mem_cgroup *memcg)
 {
-       __mem_cgroup_threshold(memcg, false);
-       if (do_swap_account)
-               __mem_cgroup_threshold(memcg, true);
+       while (memcg) {
+               __mem_cgroup_threshold(memcg, false);
+               if (do_swap_account)
+                       __mem_cgroup_threshold(memcg, true);
+
+               memcg = parent_mem_cgroup(memcg);
+       }
 }
 
 static int compare_thresholds(const void *a, const void *b)
@@ -4441,7 +4446,7 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
        unsigned long precharge;
        struct vm_area_struct *vma;
 
-       down_read(&mm->mmap_sem);
+       /* We've already held the mmap_sem */
        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                struct mm_walk mem_cgroup_count_precharge_walk = {
                        .pmd_entry = mem_cgroup_count_precharge_pte_range,
@@ -4453,7 +4458,6 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
                walk_page_range(vma->vm_start, vma->vm_end,
                                        &mem_cgroup_count_precharge_walk);
        }
-       up_read(&mm->mmap_sem);
 
        precharge = mc.precharge;
        mc.precharge = 0;
@@ -4504,11 +4508,16 @@ static void mem_cgroup_clear_mc(void)
 
                mc.moved_swap = 0;
        }
+       if (mc.mm) {
+               up_read(&mc.mm->mmap_sem);
+               mmput(mc.mm);
+       }
        spin_lock(&mc.lock);
        mc.from = NULL;
        mc.to = NULL;
-       mc.moving_task = NULL;
        spin_unlock(&mc.lock);
+       mc.moving_task = NULL;
+       mc.mm = NULL;
        memcg_oom_recover(from);
        memcg_oom_recover(to);
        wake_up_all(&mc.waitq);
@@ -4533,26 +4542,37 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
                        return 0;
                /* We move charges only when we move a owner of the mm */
                if (mm->owner == p) {
+                       /*
+                        * We do all the move charge works under one mmap_sem to
+                        * avoid deadlock with down_write(&mmap_sem)
+                        * -> try_charge() -> if (mc.moving_task) -> sleep.
+                        */
+                       down_read(&mm->mmap_sem);
+
                        VM_BUG_ON(mc.from);
                        VM_BUG_ON(mc.to);
                        VM_BUG_ON(mc.precharge);
                        VM_BUG_ON(mc.moved_charge);
                        VM_BUG_ON(mc.moved_swap);
                        VM_BUG_ON(mc.moving_task);
+                       VM_BUG_ON(mc.mm);
+
                        spin_lock(&mc.lock);
                        mc.from = from;
                        mc.to = mem;
                        mc.precharge = 0;
                        mc.moved_charge = 0;
                        mc.moved_swap = 0;
-                       mc.moving_task = current;
                        spin_unlock(&mc.lock);
+                       mc.moving_task = current;
+                       mc.mm = mm;
 
                        ret = mem_cgroup_precharge_mc(mm);
                        if (ret)
                                mem_cgroup_clear_mc();
-               }
-               mmput(mm);
+                       /* We call up_read() and mmput() in clear_mc(). */
+               } else
+                       mmput(mm);
        }
        return ret;
 }
@@ -4640,7 +4660,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
        struct vm_area_struct *vma;
 
        lru_add_drain_all();
-       down_read(&mm->mmap_sem);
+       /* We've already held the mmap_sem */
        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                int ret;
                struct mm_walk mem_cgroup_move_charge_walk = {
@@ -4659,7 +4679,6 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
                         */
                        break;
        }
-       up_read(&mm->mmap_sem);
 }
 
 static void mem_cgroup_move_task(struct cgroup_subsys *ss,
@@ -4668,17 +4687,11 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
                                struct task_struct *p,
                                bool threadgroup)
 {
-       struct mm_struct *mm;
-
-       if (!mc.to)
+       if (!mc.mm)
                /* no need to move charge */
                return;
 
-       mm = get_task_mm(p);
-       if (mm) {
-               mem_cgroup_move_charge(mm);
-               mmput(mm);
-       }
+       mem_cgroup_move_charge(mc.mm);
        mem_cgroup_clear_mc();
 }
 #else  /* !CONFIG_MMU */