[PATCH] md / procfs: avoid Oops if md-mod removed while /proc/mdstat is being polled.

[NeilBrown]

If poll or select is waiting on /proc/mdstat when md-mod is unloaded
an oops will ensure when the poll/select completes.

This is because the wait_queue_head which is registered with poll_wait()
is local to the module and no longer exists when the poll completes and
detaches that wait_queue_head (in poll_free_wait -> remove_wait_queue).

To fix this we need the wait_queue_head to have (at least) the same life
time as the proc_dir_entry.  So this patch places it in that structure.

We:
  - add pde_poll_wait to struct proc_dir_entry
  - call poll_wait() passing this when poll() is called on the proc file
  - export a function proc_wake_up which will call wake_up() on pde_poll_wait

and make use of all that in md.c

Reported-by: "majianpeng" <majianp...@gmail.com>
Signed-off-by: NeilBrown <ne...@suse.de>

--

Do we have a maintainer for fs/proc ??
If I could get a couple of Acks, or constructive comments, on this,
I would  appreciate it.
Thanks,
NeilBrown


diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ad5cc4e63e8..1bf70d9c55d3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -193,12 +193,12 @@ EXPORT_SYMBOL_GPL(bio_clone_mddev);
  *  start array, stop array, error, add device, remove device,
  *  start build, activate spare
  */
-static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
+static struct proc_dir_entry *mdstat_pde;
 static atomic_t md_event_count;
 void md_new_event(struct mddev *mddev)
 {
        atomic_inc(&md_event_count);
-       wake_up(&md_event_waiters);
+       proc_wake_up(mdstat_pde);
 }
 EXPORT_SYMBOL_GPL(md_new_event);
 
@@ -208,7 +208,7 @@ EXPORT_SYMBOL_GPL(md_new_event);
 static void md_new_event_inintr(struct mddev *mddev)
 {
        atomic_inc(&md_event_count);
-       wake_up(&md_event_waiters);
+       proc_wake_up(mdstat_pde);
 }
 
 /*
@@ -7187,8 +7187,6 @@ static unsigned int mdstat_poll(struct file *filp, 
poll_table *wait)
        struct seq_file *seq = filp->private_data;
        int mask;
 
-       poll_wait(filp, &md_event_waiters, wait);
-
        /* always allow read */
        mask = POLLIN | POLLRDNORM;
 
@@ -8557,7 +8555,7 @@ static void md_geninit(void)
 {
        pr_debug("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t));
 
-       proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops);
+       mdstat_pde = proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops);
 }
 
 static int __init md_init(void)
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index b7f268eb5f45..c579da4cd765 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -357,6 +357,7 @@ static struct proc_dir_entry *__proc_create(struct 
proc_dir_entry **parent,
        atomic_set(&ent->count, 1);
        spin_lock_init(&ent->pde_unload_lock);
        INIT_LIST_HEAD(&ent->pde_openers);
+       init_waitqueue_head(&ent->pde_poll_wait);
 out:
        return ent;
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 124fc43c7090..353fc199e8b5 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -234,13 +234,21 @@ static unsigned int proc_reg_poll(struct file *file, 
struct poll_table_struct *p
        unsigned int (*poll)(struct file *, struct poll_table_struct *);
        if (use_pde(pde)) {
                poll = pde->proc_fops->poll;
-               if (poll)
+               if (poll) {
+                       poll_wait(file, &pde->pde_poll_wait, pts);
                        rv = poll(file, pts);
+               }
                unuse_pde(pde);
        }
        return rv;
 }
 
+void proc_wake_up(struct proc_dir_entry *pde)
+{
+       wake_up(&pde->pde_poll_wait);
+}
+EXPORT_SYMBOL_GPL(proc_wake_up);
+
 static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, 
unsigned long arg)
 {
        struct proc_dir_entry *pde = PDE(file_inode(file));
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 651d09a11dde..6f9f84eecded 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -46,6 +46,7 @@ struct proc_dir_entry {
        struct completion *pde_unload_completion;
        struct list_head pde_openers;   /* who did ->open, but not ->release */
        spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
+       wait_queue_head_t pde_poll_wait; /* For proc_reg_poll */
        u8 namelen;
        char name[];
 };
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 608e60a74c3c..a4a3d5f001ef 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -34,6 +34,7 @@ static inline struct proc_dir_entry *proc_create(
        return proc_create_data(name, mode, parent, proc_fops, NULL);
 }
 
+extern void proc_wake_up(struct proc_dir_entry *pde);
 extern void proc_set_size(struct proc_dir_entry *, loff_t);
 extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t);
 extern void *PDE_DATA(const struct inode *);

signature.asc
Description: PGP signature