Revert "sched/autogroup: Fix crash on reboot when autogroup is disabled"

This reverts commit 5258f386ea4e8454bc801fb443e8a4217da1947c,
because the underlying autogroups bug got fixed upstream in
a better way, via:

  fd8ef11730f1 Revert "sched, autogroup: Stop going ahead if autogroup is disabled"

Cc: Mike Galbraith <efault@gmx.de>
Cc: Yong Zhang <yong.zhang0@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 587631e1cd0631f4ba55892425f83f077091150f..9e28356a959a2f4f0aecddd6170ebacfa799a5b3 100644 (file)
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1272,6 +1272,81 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+/*
+ * Print out autogroup related information:
+ */
+static int sched_autogroup_show(struct seq_file *m, void *v)
+{
+       struct inode *inode = m->private;
+       struct task_struct *p;
+
+       p = get_proc_task(inode);
+       if (!p)
+               return -ESRCH;
+       proc_sched_autogroup_show_task(p, m);
+
+       put_task_struct(p);
+
+       return 0;
+}
+
+static ssize_t
+sched_autogroup_write(struct file *file, const char __user *buf,
+           size_t count, loff_t *offset)
+{
+       struct inode *inode = file->f_path.dentry->d_inode;
+       struct task_struct *p;
+       char buffer[PROC_NUMBUF];
+       int nice;
+       int err;
+
+       memset(buffer, 0, sizeof(buffer));
+       if (count > sizeof(buffer) - 1)
+               count = sizeof(buffer) - 1;
+       if (copy_from_user(buffer, buf, count))
+               return -EFAULT;
+
+       err = kstrtoint(strstrip(buffer), 0, &nice);
+       if (err < 0)
+               return err;
+
+       p = get_proc_task(inode);
+       if (!p)
+               return -ESRCH;
+
+       err = proc_sched_autogroup_set_nice(p, nice);
+       if (err)
+               count = err;
+
+       put_task_struct(p);
+
+       return count;
+}
+
+static int sched_autogroup_open(struct inode *inode, struct file *filp)
+{
+       int ret;
+
+       ret = single_open(filp, sched_autogroup_show, NULL);
+       if (!ret) {
+               struct seq_file *m = filp->private_data;
+
+               m->private = inode;
+       }
+       return ret;
+}
+
+static const struct file_operations proc_pid_sched_autogroup_operations = {
+       .open           = sched_autogroup_open,
+       .read           = seq_read,
+       .write          = sched_autogroup_write,
+       .llseek         = seq_lseek,
+       .release        = single_release,
+};
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
+
 static ssize_t comm_write(struct file *file, const char __user *buf,
                                size_t count, loff_t *offset)
 {
@@ -2582,6 +2657,9 @@ static const struct pid_entry tgid_base_stuff[] = {
        INF("limits",     S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
        REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+#ifdef CONFIG_SCHED_AUTOGROUP
+       REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
 #endif
        REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK

diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 0f1bacb005a4f5f2761b032dfec8a32e913fab54..0984a21076a3ed8a37e56d5381bff6320d8fa5f2 100644 (file)
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -110,9 +110,6 @@ out_fail:
 
 bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
-       if (!sysctl_sched_autogroup_enabled)
-               return false;
-
        if (tg != &root_task_group)
                return false;
 
@@ -146,11 +143,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
        p->signal->autogroup = autogroup_kref_get(ag);
 
+       if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+               goto out;
+
        t = p;
        do {
                sched_move_task(t);
        } while_each_thread(p, t);
 
+out:
        unlock_task_sighand(p, &flags);
        autogroup_kref_put(prev);
 }
@@ -158,11 +159,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 /* Allocates GFP_KERNEL, cannot be called under any spinlock */
 void sched_autogroup_create_attach(struct task_struct *p)
 {
-       struct autogroup *ag;
+       struct autogroup *ag = autogroup_create();
 
-       if (!sysctl_sched_autogroup_enabled)
-               return;
-       ag = autogroup_create();
        autogroup_move_group(p, ag);
        /* drop extra reference added by autogroup_create() */
        autogroup_kref_put(ag);
@@ -178,15 +176,11 @@ EXPORT_SYMBOL(sched_autogroup_detach);
 
 void sched_autogroup_fork(struct signal_struct *sig)
 {
-       if (!sysctl_sched_autogroup_enabled)
-               return;
        sig->autogroup = autogroup_task_get(current);
 }
 
 void sched_autogroup_exit(struct signal_struct *sig)
 {
-       if (!sysctl_sched_autogroup_enabled)
-               return;
        autogroup_kref_put(sig->autogroup);
 }
 
@@ -199,6 +193,58 @@ static int __init setup_autogroup(char *str)
 
 __setup("noautogroup", setup_autogroup);
 
+#ifdef CONFIG_PROC_FS
+
+int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
+{
+       static unsigned long next = INITIAL_JIFFIES;
+       struct autogroup *ag;
+       int err;
+
+       if (nice < -20 || nice > 19)
+               return -EINVAL;
+
+       err = security_task_setnice(current, nice);
+       if (err)
+               return err;
+
+       if (nice < 0 && !can_nice(current, nice))
+               return -EPERM;
+
+       /* this is a heavy operation taking global locks.. */
+       if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
+               return -EAGAIN;
+
+       next = HZ / 10 + jiffies;
+       ag = autogroup_task_get(p);
+
+       down_write(&ag->lock);
+       err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
+       if (!err)
+               ag->nice = nice;
+       up_write(&ag->lock);
+
+       autogroup_kref_put(ag);
+
+       return err;
+}
+
+void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
+{
+       struct autogroup *ag = autogroup_task_get(p);
+
+       if (!task_group_is_autogroup(ag->tg))
+               goto out;
+
+       down_read(&ag->lock);
+       seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
+       up_read(&ag->lock);
+
+out:
+       autogroup_kref_put(ag);
+}
+#endif /* CONFIG_PROC_FS */
+
 #ifdef CONFIG_SCHED_DEBUG
 int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {

diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h
index 4552c6bf79d2e1720054d2f5abe417ea22a9f49a..8bd047142816dea81894bb27ccc3c78a38ac3d61 100644 (file)
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/auto_group.h
@@ -4,6 +4,11 @@
 #include <linux/rwsem.h>
 
 struct autogroup {
+       /*
+        * reference doesn't mean how many thread attach to this
+        * autogroup now. It just stands for the number of task
+        * could use this autogroup.
+        */
        struct kref             kref;
        struct task_group       *tg;
        struct rw_semaphore     lock;
@@ -24,7 +29,9 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)
 {
-       if (task_wants_autogroup(p, tg))
+       int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+       if (enabled && task_wants_autogroup(p, tg))
                return p->signal->autogroup->tg;
 
        return tg;

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b0fa5ad09873f874775cc72ffd534bfec825f639..26f65eaa01f9c94366aa5156f9c304bbc589808f 100644 (file)
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -367,8 +367,10 @@ static struct ctl_table kern_table[] = {
                .procname       = "sched_autogroup_enabled",
                .data           = &sysctl_sched_autogroup_enabled,
                .maxlen         = sizeof(unsigned int),
-               .mode           = 0444,
-               .proc_handler   = proc_dointvec,
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec_minmax,
+               .extra1         = &zero,
+               .extra2         = &one,
        },
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH