1 files changed, 35 insertions, 19 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 0647d80accf6..0b3da4a77704 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -25,6 +25,7 @@
 #include <linux/async.h>
 #include <linux/posix_acl.h>
 #include <linux/ima.h>
+#include <linux/cred.h>
 
 /*
  * This is needed for the following functions:
@@ -84,16 +85,13 @@ static struct hlist_head *inode_hashtable __read_mostly;
 DEFINE_SPINLOCK(inode_lock);
 
 /*
- * iprune_sem provides exclusion between the kswapd or try_to_free_pages
- * icache shrinking path, and the umount path.  Without this exclusion,
- * by the time prune_icache calls iput for the inode whose pages it has
- * been invalidating, or by the time it calls clear_inode & destroy_inode
- * from its final dispose_list, the struct super_block they refer to
- * (for inode->i_sb->s_op) may already have been freed and reused.
+ * iprune_sem provides exclusion between the icache shrinking and the
+ * umount path.
  *
- * We make this an rwsem because the fastpath is icache shrinking. In
- * some cases a filesystem may be doing a significant amount of work in
- * its inode reclaim code, so this should improve parallelism.
+ * We don't actually need it to protect anything in the umount path,
+ * but only need to cycle through it to make sure any inode that
+ * prune_icache took off the LRU list has been fully torn down by the
+ * time we are past evict_inodes.
  */
 static DECLARE_RWSEM(iprune_sem);
 
@@ -516,17 +514,12 @@ void evict_inodes(struct super_block *sb)
         struct inode *inode, *next;
         LIST_HEAD(dispose);
 
-        down_write(&iprune_sem);
-
         spin_lock(&inode_lock);
         list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
                 if (atomic_read(&inode->i_count))
                         continue;
-
-                if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
-                        WARN_ON(1);
+                if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
                         continue;
-                }
 
                 inode->i_state |= I_FREEING;
 
@@ -542,6 +535,13 @@ void evict_inodes(struct super_block *sb)
         spin_unlock(&inode_lock);
 
         dispose_list(&dispose);
+
+        /*
+         * Cycle through iprune_sem to make sure any inode that prune_icache
+         * moved off the list before we took the lock has been fully torn
+         * down.
+         */
+        down_write(&iprune_sem);
         up_write(&iprune_sem);
 }
 
@@ -561,8 +561,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
         struct inode *inode, *next;
         LIST_HEAD(dispose);
 
-        down_write(&iprune_sem);
-
         spin_lock(&inode_lock);
         list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
                 if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
@@ -590,7 +588,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
         spin_unlock(&inode_lock);
 
         dispose_list(&dispose);
-        up_write(&iprune_sem);
 
         return busy;
 }
@@ -1719,7 +1716,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 EXPORT_SYMBOL(init_special_inode);
 
 /**
- * Init uid,gid,mode for new inode according to posix standards
+ * inode_init_owner - Init uid,gid,mode for new inode according to posix standards
  * @inode: New inode
  * @dir: Directory inode
  * @mode: mode of the new inode
@@ -1737,3 +1734,22 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
         inode->i_mode = mode;
 }
 EXPORT_SYMBOL(inode_init_owner);
+
+/**
+ * inode_owner_or_capable - check current task permissions to inode
+ * @inode: inode being checked
+ *
+ * Return true if current either has CAP_FOWNER to the inode, or
+ * owns the file.
+ */
+bool inode_owner_or_capable(const struct inode *inode)
+{
+        struct user_namespace *ns = inode_userns(inode);
+
+        if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
+                return true;
+        if (ns_capable(ns, CAP_FOWNER))
+                return true;
+        return false;
+}
+EXPORT_SYMBOL(inode_owner_or_capable);