Merge branch 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing

* 'reiserfs/kill-bkl' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing: (31 commits)
  kill-the-bkl/reiserfs: turn GFP_ATOMIC flag to GFP_NOFS in reiserfs_get_block()
  kill-the-bkl/reiserfs: drop the fs race watchdog from _get_block_create_0()
  kill-the-bkl/reiserfs: definitely drop the bkl from reiserfs_ioctl()
  kill-the-bkl/reiserfs: always lock the ioctl path
  kill-the-bkl/reiserfs: fix reiserfs lock to cpu_add_remove_lock dependency
  kill-the-bkl/reiserfs: Fix induced mm->mmap_sem to sysfs_mutex dependency
  kill-the-bkl/reiserfs: panic in case of lock imbalance
  kill-the-bkl/reiserfs: fix recursive reiserfs write lock in reiserfs_commit_write()
  kill-the-bkl/reiserfs: fix recursive reiserfs lock in reiserfs_mkdir()
  kill-the-bkl/reiserfs: fix "reiserfs lock" / "inode mutex" lock inversion dependency
  kill-the-bkl/reiserfs: move the concurrent tree accesses checks per superblock
  kill-the-bkl/reiserfs: acquire the inode mutex safely
  kill-the-bkl/reiserfs: unlock only when needed in search_by_key
  kill-the-bkl/reiserfs: use mutex_lock in reiserfs_mutex_lock_safe
  kill-the-bkl/reiserfs: factorize the locking in reiserfs_write_end()
  kill-the-bkl/reiserfs: reduce number of contentions in search_by_key()
  kill-the-bkl/reiserfs: don't hold the write recursively in reiserfs_lookup()
  kill-the-bkl/reiserfs: lock only once on reiserfs_get_block()
  kill-the-bkl/reiserfs: conditionaly release the write lock on fs_changed()
  kill-the-BKL/reiserfs: add reiserfs_cond_resched()
  ...

2 files changed, 83 insertions, 8 deletions

diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h
index dd31e7bae35..a05b4a20768 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);
diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h
index dab68bbed67..52c83b6a758 100644
--- a/include/linux/reiserfs_fs_sb.h
+++ b/include/linux/reiserfs_fs_sb.h
@@ -7,6 +7,8 @@
 #ifdef __KERNEL__
 #include <linux/workqueue.h>
 #include <linux/rwsem.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
 #endif
 
 typedef enum {
@@ -355,6 +357,13 @@ struct reiserfs_sb_info {
 	struct reiserfs_journal *s_journal;	/* pointer to journal information */
 	unsigned short s_mount_state;	/* reiserfs state (valid, invalid) */
 
+	/* Serialize writers access, replace the old bkl */
+	struct mutex lock;
+	/* Owner of the lock (can be recursive) */
+	struct task_struct *lock_owner;
+	/* Depth of the lock, start from -1 like the bkl */
+	int lock_depth;
+
 	/* Comment? -Hans */
 	void (*end_io_handler) (struct buffer_head *, int);
 	hashf_t s_hash_function;	/* pointer to function which is used
@@ -408,6 +417,17 @@ struct reiserfs_sb_info {
 	char *s_qf_names[MAXQUOTAS];
 	int s_jquota_fmt;
 #endif
+#ifdef CONFIG_REISERFS_CHECK
+
+	struct tree_balance *cur_tb;	/*
+					 * Detects whether more than one
+					 * copy of tb exists per superblock
+					 * as a means of checking whether
+					 * do_balance is executing concurrently
+					 * against another tree reader/writer
+					 * on a same mount point.
+					 */
+#endif
 };
 
 /* Definitions of reiserfs on-disk properties: */