1 files changed, 80 insertions, 20 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 70f2a0fd6aec..701985e4ccda 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>
@@ -34,7 +36,6 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DECLARE_LGLOCK(files_lglock);
 DEFINE_LGLOCK(files_lglock);
 
 /* SLAB cache for file structures */
@@ -42,7 +43,7 @@ static struct kmem_cache *filp_cachep __read_mostly;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
-static inline void file_free_rcu(struct rcu_head *head)
+static void file_free_rcu(struct rcu_head *head)
 {
 	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
 
@@ -216,7 +217,7 @@ static void drop_file_write_access(struct file *file)
 		return;
 	if (file_check_writeable(file) != 0)
 		return;
-	mnt_drop_write(mnt);
+	__mnt_drop_write(mnt);
 	file_release_write(file);
 }
 
@@ -252,7 +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)
@@ -264,10 +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);
@@ -421,9 +488,9 @@ static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
  */
 void file_sb_list_add(struct file *file, struct super_block *sb)
 {
-	lg_local_lock(files_lglock);
+	lg_local_lock(&files_lglock);
 	__file_sb_list_add(file, sb);
-	lg_local_unlock(files_lglock);
+	lg_local_unlock(&files_lglock);
 }
 
 /**
@@ -436,9 +503,9 @@ void file_sb_list_add(struct file *file, struct super_block *sb)
 void file_sb_list_del(struct file *file)
 {
 	if (!list_empty(&file->f_u.fu_list)) {
-		lg_local_lock_cpu(files_lglock, file_list_cpu(file));
+		lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
 		list_del_init(&file->f_u.fu_list);
-		lg_local_unlock_cpu(files_lglock, file_list_cpu(file));
+		lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
 	}
 }
 
@@ -484,10 +551,8 @@ void mark_files_ro(struct super_block *sb)
 {
 	struct file *f;
 
-retry:
-	lg_global_lock(files_lglock);
+	lg_global_lock(&files_lglock);
 	do_file_list_for_each_entry(sb, f) {
-		struct vfsmount *mnt;
 		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
 		       continue;
 		if (!file_count(f))
@@ -500,14 +565,9 @@ retry:
 		if (file_check_writeable(f) != 0)
 			continue;
 		file_release_write(f);
-		mnt = mntget(f->f_path.mnt);
-		/* This can sleep, so we can't hold the spinlock. */
-		lg_global_unlock(files_lglock);
-		mnt_drop_write(mnt);
-		mntput(mnt);
-		goto retry;
+		mnt_drop_write_file(f);
 	} while_file_list_for_each_entry;
-	lg_global_unlock(files_lglock);
+	lg_global_unlock(&files_lglock);
 }
 
 void __init files_init(unsigned long mempages)
@@ -525,6 +585,6 @@ void __init files_init(unsigned long mempages)
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	files_defer_init();
-	lg_lock_init(files_lglock);
+	lg_lock_init(&files_lglock, "files_lglock");
 	percpu_counter_init(&nr_files, 0);
 }