4 files changed, 173 insertions, 7 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 144a96732dd..3c231adf845 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = {
         .release        = mem_release,
 };
 
+static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
+                            loff_t *ppos)
+{
+        struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+        char buffer[PROC_NUMBUF];
+        int oom_adj = OOM_ADJUST_MIN;
+        size_t len;
+        unsigned long flags;
+
+        if (!task)
+                return -ESRCH;
+        if (lock_task_sighand(task, &flags)) {
+                if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+                        oom_adj = OOM_ADJUST_MAX;
+                else
+                        oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+                                  OOM_SCORE_ADJ_MAX;
+                unlock_task_sighand(task, &flags);
+        }
+        put_task_struct(task);
+        len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
+        return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_adj_write(struct file *file, const char __user *buf,
+                             size_t count, loff_t *ppos)
+{
+        struct task_struct *task;
+        char buffer[PROC_NUMBUF];
+        int oom_adj;
+        unsigned long flags;
+        int err;
+
+        memset(buffer, 0, sizeof(buffer));
+        if (count > sizeof(buffer) - 1)
+                count = sizeof(buffer) - 1;
+        if (copy_from_user(buffer, buf, count)) {
+                err = -EFAULT;
+                goto out;
+        }
+
+        err = kstrtoint(strstrip(buffer), 0, &oom_adj);
+        if (err)
+                goto out;
+        if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
+             oom_adj != OOM_DISABLE) {
+                err = -EINVAL;
+                goto out;
+        }
+
+        task = get_proc_task(file->f_path.dentry->d_inode);
+        if (!task) {
+                err = -ESRCH;
+                goto out;
+        }
+
+        task_lock(task);
+        if (!task->mm) {
+                err = -EINVAL;
+                goto err_task_lock;
+        }
+
+        if (!lock_task_sighand(task, &flags)) {
+                err = -ESRCH;
+                goto err_task_lock;
+        }
+
+        /*
+         * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+         * value is always attainable.
+         */
+        if (oom_adj == OOM_ADJUST_MAX)
+                oom_adj = OOM_SCORE_ADJ_MAX;
+        else
+                oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+
+        if (oom_adj < task->signal->oom_score_adj &&
+            !capable(CAP_SYS_RESOURCE)) {
+                err = -EACCES;
+                goto err_sighand;
+        }
+
+        /*
+         * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+         * /proc/pid/oom_score_adj instead.
+         */
+        printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+                  current->comm, task_pid_nr(current), task_pid_nr(task),
+                  task_pid_nr(task));
+
+        task->signal->oom_score_adj = oom_adj;
+        trace_oom_score_adj_update(task);
+err_sighand:
+        unlock_task_sighand(task, &flags);
+err_task_lock:
+        task_unlock(task);
+        put_task_struct(task);
+out:
+        return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_adj_operations = {
+        .read           = oom_adj_read,
+        .write          = oom_adj_write,
+        .llseek         = generic_file_llseek,
+};
+
 static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
                                         size_t count, loff_t *ppos)
 {
@@ -2598,6 +2705,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
         INF("oom_score",  S_IRUGO, proc_oom_score),
+        REG("oom_adj",    S_IRUGO|S_IWUSR, proc_oom_adj_operations),
         REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",   S_IWUSR|S_IRUGO, proc_loginuid_operations),
@@ -2964,6 +3072,7 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("cgroup",  S_IRUGO, proc_cgroup_operations),
 #endif
         INF("oom_score", S_IRUGO, proc_oom_score),
+        REG("oom_adj",   S_IRUGO|S_IWUSR, proc_oom_adj_operations),
         REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index cceaab07ad5..43973b084ab 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/proc_fs.h>
 struct  ctl_table_header;
+struct  mempolicy;
 
 extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
@@ -74,6 +75,9 @@ struct proc_maps_private {
 #ifdef CONFIG_MMU
         struct vm_area_struct *tail_vma;
 #endif
+#ifdef CONFIG_NUMA
+        struct mempolicy *task_mempolicy;
+#endif
 };
 
 void proc_init_inodecache(void);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 64c3b317236..e296572c73e 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -45,10 +45,13 @@ static cputime64_t get_iowait_time(int cpu)
 
 static u64 get_idle_time(int cpu)
 {
-        u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL);
+        u64 idle, idle_time = -1ULL;
+
+        if (cpu_online(cpu))
+                idle_time = get_cpu_idle_time_us(cpu, NULL);
 
         if (idle_time == -1ULL)
-                /* !NO_HZ so we can rely on cpustat.idle */
+                /* !NO_HZ or cpu offline so we can rely on cpustat.idle */
                 idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
         else
                 idle = usecs_to_cputime64(idle_time);
@@ -58,10 +61,13 @@ static u64 get_idle_time(int cpu)
 
 static u64 get_iowait_time(int cpu)
 {
-        u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+        u64 iowait, iowait_time = -1ULL;
+
+        if (cpu_online(cpu))
+                iowait_time = get_cpu_iowait_time_us(cpu, NULL);
 
         if (iowait_time == -1ULL)
-                /* !NO_HZ so we can rely on cpustat.iowait */
+                /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
                 iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
         else
                 iowait = usecs_to_cputime64(iowait_time);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 79827ce03e3..90c63f9392a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -90,10 +90,55 @@ static void pad_len_spaces(struct seq_file *m, int len)
         seq_printf(m, "%*c", len, ' ');
 }
 
+#ifdef CONFIG_NUMA
+/*
+ * These functions are for numa_maps but called in generic **maps seq_file
+ * ->start(), ->stop() ops.
+ *
+ * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
+ * Each mempolicy object is controlled by reference counting. The problem here
+ * is how to avoid accessing dead mempolicy object.
+ *
+ * Because we're holding mmap_sem while reading seq_file, it's safe to access
+ * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
+ *
+ * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
+ * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
+ * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
+ * gurantee the task never exits under us. But taking task_lock() around
+ * get_vma_plicy() causes lock order problem.
+ *
+ * To access task->mempolicy without lock, we hold a reference count of an
+ * object pointed by task->mempolicy and remember it. This will guarantee
+ * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ */
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+        struct task_struct *task = priv->task;
+
+        task_lock(task);
+        priv->task_mempolicy = task->mempolicy;
+        mpol_get(priv->task_mempolicy);
+        task_unlock(task);
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+        mpol_put(priv->task_mempolicy);
+}
+#else
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+#endif
+
 static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
 {
         if (vma && vma != priv->tail_vma) {
                 struct mm_struct *mm = vma->vm_mm;
+                release_task_mempolicy(priv);
                 up_read(&mm->mmap_sem);
                 mmput(mm);
         }
@@ -132,7 +177,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
         tail_vma = get_gate_vma(priv->task->mm);
         priv->tail_vma = tail_vma;
-
+        hold_task_mempolicy(priv);
         /* Start with last addr hint */
         vma = find_vma(mm, last_addr);
         if (last_addr && vma) {
@@ -159,6 +204,7 @@ out:
         if (vma)
                 return vma;
 
+        release_task_mempolicy(priv);
         /* End of vmas has been reached */
         m->version = (tail_vma != NULL)? 0: -1UL;
         up_read(&mm->mmap_sem);
@@ -1158,6 +1204,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
         struct vm_area_struct *vma = v;
         struct numa_maps *md = &numa_priv->md;
         struct file *file = vma->vm_file;
+        struct task_struct *task = proc_priv->task;
         struct mm_struct *mm = vma->vm_mm;
         struct mm_walk walk = {};
         struct mempolicy *pol;
@@ -1177,7 +1224,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
         walk.private = md;
         walk.mm = mm;
 
-        pol = get_vma_policy(proc_priv->task, vma, vma->vm_start);
+        pol = get_vma_policy(task, vma, vma->vm_start);
         mpol_to_str(buffer, sizeof(buffer), pol, 0);
         mpol_cond_put(pol);
 
@@ -1189,7 +1236,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
         } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
                 seq_printf(m, " heap");
         } else {
-                pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+                pid_t tid = vm_is_stack(task, vma, is_pid);
                 if (tid != 0) {
                         /*
                          * Thread stack in /proc/PID/task/TID/maps or