1 files changed, 63 insertions, 8 deletions

diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index dd31e7bae35c..a05b4a20768d 100644
--- a/include/linux/reiserfs_fs.h
+++ b/include/linux/reiserfs_fs.h
@@ -52,11 +52,63 @@
 #define REISERFS_IOC32_GETVERSION       FS_IOC32_GETVERSION
 #define REISERFS_IOC32_SETVERSION       FS_IOC32_SETVERSION
 
-/* Locking primitives */
-/* Right now we are still falling back to (un)lock_kernel, but eventually that
-   would evolve into real per-fs locks */
-#define reiserfs_write_lock( sb ) lock_kernel()
-#define reiserfs_write_unlock( sb ) unlock_kernel()
+/*
+ * Locking primitives. The write lock is a per superblock
+ * special mutex that has properties close to the Big Kernel Lock
+ * which was used in the previous locking scheme.
+ */
+void reiserfs_write_lock(struct super_block *s);
+void reiserfs_write_unlock(struct super_block *s);
+int reiserfs_write_lock_once(struct super_block *s);
+void reiserfs_write_unlock_once(struct super_block *s, int lock_depth);
+
+/*
+ * Several mutexes depend on the write lock.
+ * However sometimes we want to relax the write lock while we hold
+ * these mutexes, according to the release/reacquire on schedule()
+ * properties of the Bkl that were used.
+ * Reiserfs performances and locking were based on this scheme.
+ * Now that the write lock is a mutex and not the bkl anymore, doing so
+ * may result in a deadlock:
+ *
+ * A acquire write_lock
+ * A acquire j_commit_mutex
+ * A release write_lock and wait for something
+ * B acquire write_lock
+ * B can't acquire j_commit_mutex and sleep
+ * A can't acquire write lock anymore
+ * deadlock
+ *
+ * What we do here is avoiding such deadlock by playing the same game
+ * than the Bkl: if we can't acquire a mutex that depends on the write lock,
+ * we release the write lock, wait a bit and then retry.
+ *
+ * The mutexes concerned by this hack are:
+ * - The commit mutex of a journal list
+ * - The flush mutex
+ * - The journal lock
+ * - The inode mutex
+ */
+static inline void reiserfs_mutex_lock_safe(struct mutex *m,
+                               struct super_block *s)
+{
+        reiserfs_write_unlock(s);
+        mutex_lock(m);
+        reiserfs_write_lock(s);
+}
+
+/*
+ * When we schedule, we usually want to also release the write lock,
+ * according to the previous bkl based locking scheme of reiserfs.
+ */
+static inline void reiserfs_cond_resched(struct super_block *s)
+{
+        if (need_resched()) {
+                reiserfs_write_unlock(s);
+                schedule();
+                reiserfs_write_lock(s);
+        }
+}
 
 struct fid;
 
@@ -1329,7 +1381,11 @@ static inline loff_t max_reiserfs_offset(struct inode *inode)
 #define get_generation(s) atomic_read (&fs_generation(s))
 #define FILESYSTEM_CHANGED_TB(tb)  (get_generation((tb)->tb_sb) != (tb)->fs_gen)
 #define __fs_changed(gen,s) (gen != get_generation (s))
-#define fs_changed(gen,s) ({cond_resched(); __fs_changed(gen, s);})
+#define fs_changed(gen,s)               \
+({                                      \
+        reiserfs_cond_resched(s);       \
+        __fs_changed(gen, s);           \
+})
 
 /***************************************************************************/
 /*                  FIXATE NODES                                           */
@@ -2258,8 +2314,7 @@ __u32 r5_hash(const signed char *msg, int len);
 #define SPARE_SPACE 500
 
 /* prototypes from ioctl.c */
-int reiserfs_ioctl(struct inode *inode, struct file *filp,
-                   unsigned int cmd, unsigned long arg);
+long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long reiserfs_compat_ioctl(struct file *filp,
                    unsigned int cmd, unsigned long arg);
 int reiserfs_unpack(struct inode *inode, struct file *filp);