switch fput to task_work_add

... and schedule_work() for interrupt/kernel_thread callers
(and yes, now it *is* OK to call from interrupt).

We are guaranteed that __fput() will be done before we return
to userland (or exit).  Note that for fput() from a kernel
thread we get an async behaviour; it's almost always OK, but
sometimes you might need to have __fput() completed before
you do anything else.  There are two mechanisms for that -
a general barrier (flush_delayed_fput()) and explicit
__fput_sync().  Both should be used with care (as was the
case for fput() from kernel threads all along).  See comments
in fs/file_table.c for details.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 75 insertions, 3 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 9ace2781931e..b3fc4d67a26b 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -23,6 +23,8 @@
 #include <linux/lglock.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/task_work.h>
 #include <linux/ima.h>
 
 #include <linux/atomic.h>
@@ -251,7 +253,6 @@ static void __fput(struct file *file)
         }
         fops_put(file->f_op);
         put_pid(file->f_owner.pid);
-        file_sb_list_del(file);
         if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
                 i_readcount_dec(inode);
         if (file->f_mode & FMODE_WRITE)
@@ -263,10 +264,77 @@ static void __fput(struct file *file)
         mntput(mnt);
 }
 
+static DEFINE_SPINLOCK(delayed_fput_lock);
+static LIST_HEAD(delayed_fput_list);
+static void delayed_fput(struct work_struct *unused)
+{
+        LIST_HEAD(head);
+        spin_lock_irq(&delayed_fput_lock);
+        list_splice_init(&delayed_fput_list, &head);
+        spin_unlock_irq(&delayed_fput_lock);
+        while (!list_empty(&head)) {
+                struct file *f = list_first_entry(&head, struct file, f_u.fu_list);
+                list_del_init(&f->f_u.fu_list);
+                __fput(f);
+        }
+}
+
+static void ____fput(struct callback_head *work)
+{
+        __fput(container_of(work, struct file, f_u.fu_rcuhead));
+}
+
+/*
+ * If kernel thread really needs to have the final fput() it has done
+ * to complete, call this.  The only user right now is the boot - we
+ * *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve()
+ * won't work without that.  Please, don't add more callers without
+ * very good reasons; in particular, never call that with locks
+ * held and never call that from a thread that might need to do
+ * some work on any kind of umount.
+ */
+void flush_delayed_fput(void)
+{
+        delayed_fput(NULL);
+}
+
+static DECLARE_WORK(delayed_fput_work, delayed_fput);
+
 void fput(struct file *file)
 {
-        if (atomic_long_dec_and_test(&file->f_count))
+        if (atomic_long_dec_and_test(&file->f_count)) {
+                struct task_struct *task = current;
+                file_sb_list_del(file);
+                if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) {
+                        unsigned long flags;
+                        spin_lock_irqsave(&delayed_fput_lock, flags);
+                        list_add(&file->f_u.fu_list, &delayed_fput_list);
+                        schedule_work(&delayed_fput_work);
+                        spin_unlock_irqrestore(&delayed_fput_lock, flags);
+                        return;
+                }
+                init_task_work(&file->f_u.fu_rcuhead, ____fput);
+                task_work_add(task, &file->f_u.fu_rcuhead, true);
+        }
+}
+
+/*
+ * synchronous analog of fput(); for kernel threads that might be needed
+ * in some umount() (and thus can't use flush_delayed_fput() without
+ * risking deadlocks), need to wait for completion of __fput() and know
+ * for this specific struct file it won't involve anything that would
+ * need them.  Use only if you really need it - at the very least,
+ * don't blindly convert fput() by kernel thread to that.
+ */
+void __fput_sync(struct file *file)
+{
+        if (atomic_long_dec_and_test(&file->f_count)) {
+                struct task_struct *task = current;
+                file_sb_list_del(file);
+                BUG_ON(!(task->flags & PF_KTHREAD));
                 __fput(file);
+        }
 }
 
 EXPORT_SYMBOL(fput);
diff --git a/include/linux/file.h b/include/linux/file.h
index 58bf158c53d9..a22408bac0d0 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -39,4 +39,7 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
+extern void flush_delayed_fput(void);
+extern void __fput_sync(struct file *);
+
 #endif /* __LINUX_FILE_H */
diff --git a/init/main.c b/init/main.c
index b5cc0a7c4708..3f151f6c6da7 100644
--- a/init/main.c
+++ b/init/main.c
@@ -68,6 +68,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/perf_event.h>
+#include <linux/file.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -804,8 +805,8 @@ static noinline int init_post(void)
         system_state = SYSTEM_RUNNING;
         numa_default_policy();
 
-
         current->signal->flags |= SIGNAL_UNKILLABLE;
+        flush_delayed_fput();
 
         if (ramdisk_execute_command) {
                 run_init_process(ramdisk_execute_command);