From 8ebc423238341b52912c7295b045a32477b33f09 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 7 Apr 2009 04:19:49 +0200 Subject: reiserfs: kill-the-BKL This patch is an attempt to remove the Bkl based locking scheme from reiserfs and is intended. It is a bit inspired from an old attempt by Peter Zijlstra: http://lkml.indiana.edu/hypermail/linux/kernel/0704.2/2174.html The bkl is heavily used in this filesystem to prevent from concurrent write accesses on the filesystem. Reiserfs makes a deep use of the specific properties of the Bkl: - It can be acqquired recursively by a same task - It is released on the schedule() calls and reacquired when schedule() returns The two properties above are a roadmap for the reiserfs write locking so it's very hard to simply replace it with a common mutex. - We need a recursive-able locking unless we want to restructure several blocks of the code. - We need to identify the sites where the bkl was implictly relaxed (schedule, wait, sync, etc...) so that we can in turn release and reacquire our new lock explicitly. Such implicit releases of the lock are often required to let other resources producer/consumer do their job or we can suffer unexpected starvations or deadlocks. So the new lock that replaces the bkl here is a per superblock mutex with a specific property: it can be acquired recursively by a same task, like the bkl. For such purpose, we integrate a lock owner and a lock depth field on the superblock information structure. The first axis on this patch is to turn reiserfs_write_(un)lock() function into a wrapper to manage this mutex. Also some explicit calls to lock_kernel() have been converted to reiserfs_write_lock() helpers. The second axis is to find the important blocking sites (schedule...(), wait_on_buffer(), sync_dirty_buffer(), etc...) and then apply an explicit release of the write lock on these locations before blocking. Then we can safely wait for those who can give us resources or those who need some. Typically this is a fight between the current writer, the reiserfs workqueue (aka the async commiter) and the pdflush threads. The third axis is a consequence of the second. The write lock is usually on top of a lock dependency chain which can include the journal lock, the flush lock or the commit lock. So it's dangerous to release and trying to reacquire the write lock while we still hold other locks. This is fine with the bkl: T1 T2 lock_kernel() mutex_lock(A) unlock_kernel() // do something lock_kernel() mutex_lock(A) -> already locked by T1 schedule() (and then unlock_kernel()) lock_kernel() mutex_unlock(A) .... This is not fine with a mutex: T1 T2 mutex_lock(write) mutex_lock(A) mutex_unlock(write) // do something mutex_lock(write) mutex_lock(A) -> already locked by T1 schedule() mutex_lock(write) -> already locked by T2 deadlock The solution in this patch is to provide a helper which releases the write lock and sleep a bit if we can't lock a mutex that depend on it. It's another simulation of the bkl behaviour. The last axis is to locate the fs callbacks that are called with the bkl held, according to Documentation/filesystem/Locking. Those are: - reiserfs_remount - reiserfs_fill_super - reiserfs_put_super Reiserfs didn't need to explicitly lock because of the context of these callbacks. But now we must take care of that with the new locking. After this patch, reiserfs suffers from a slight performance regression (for now). On UP, a high volume write with dd reports an average of 27 MB/s instead of 30 MB/s without the patch applied. Signed-off-by: Frederic Weisbecker Reviewed-by: Ingo Molnar Cc: Jeff Mahoney Cc: Peter Zijlstra Cc: Bron Gondwana Cc: Andrew Morton Cc: Linus Torvalds Cc: Alexander Viro LKML-Reference: <1239070789-13354-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/reiserfs_fs.h | 12 +++++++----- include/linux/reiserfs_fs_sb.h | 9 +++++++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index dd31e7bae35c..e47328f51801 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -52,11 +52,13 @@ #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); struct fid; diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index dab68bbed675..045c37213675 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -7,6 +7,8 @@ #ifdef __KERNEL__ #include #include +#include +#include #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 -- cgit v1.2.3 From daf88c898312a22b5385655bc6e0b064eaa2efba Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 14 Apr 2009 05:34:23 +0200 Subject: kill-the-BKL/reiserfs: provide a tool to lock only once the write lock Sometimes we don't want to recursively hold the per superblock write lock because we want to be sure it is actually released when we come to sleep. This patch introduces the necessary tools for that. reiserfs_write_lock_once() does the same job than reiserfs_write_lock() except that it won't try to acquire recursively the lock if the current task already owns it. Also the lock_depth before the call of this function is returned. reiserfs_write_unlock_once() unlock only if reiserfs_write_lock_once() returned a depth equal to -1, ie: only if it actually locked. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Jeff Mahoney Cc: Alexander Beregalov Cc: Chris Mason LKML-Reference: <1239680065-25013-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- fs/reiserfs/lock.c | 26 ++++++++++++++++++++++++++ include/linux/reiserfs_fs.h | 2 ++ 2 files changed, 28 insertions(+) (limited to 'include') diff --git a/fs/reiserfs/lock.c b/fs/reiserfs/lock.c index cdd8d9ef048e..cb1bba3802dd 100644 --- a/fs/reiserfs/lock.c +++ b/fs/reiserfs/lock.c @@ -49,6 +49,32 @@ void reiserfs_write_unlock(struct super_block *s) } } +/* + * If we already own the lock, just exit and don't increase the depth. + * Useful when we don't want to lock more than once. + * + * We always return the lock_depth we had before calling + * this function. + */ +int reiserfs_write_lock_once(struct super_block *s) +{ + struct reiserfs_sb_info *sb_i = REISERFS_SB(s); + + if (sb_i->lock_owner != current) { + mutex_lock(&sb_i->lock); + sb_i->lock_owner = current; + return sb_i->lock_depth++; + } + + return sb_i->lock_depth; +} + +void reiserfs_write_unlock_once(struct super_block *s, int lock_depth) +{ + if (lock_depth == -1) + reiserfs_write_unlock(s); +} + /* * Utility function to force a BUG if it is called without the superblock * write lock held. caller is the string printed just before calling BUG() diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index e47328f51801..4a2df57c8b1d 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -59,6 +59,8 @@ */ 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); struct fid; -- cgit v1.2.3 From f32049dc244f4d394c8faa161b4f13cb8c4f5c8c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 30 Apr 2009 22:05:25 +0200 Subject: kill-the-BKL/reiserfs: release write lock on fs_changed() fs_changed() is a macro used by reiserfs to check whether its tree has been rebalanced. It has been designed to check parallel changes on the tree after calling a sleeping function, which released the Bkl. fs_changed() also calls cond_resched(), so that if rescheduling is needed, we are in the best place to do that, since we check if the tree has changed just after (because of the bkl release on schedule()). Even if we are not anymore using the Bkl, we still want to release the lock while we reschedule, so that other waiters for the lock can acquire it safely, because of the following __fs_changed() check. [ Impact: release the reiserfs write lock when it is not needed ] Cc: Jeff Mahoney Cc: Chris Mason Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- include/linux/reiserfs_fs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 4a2df57c8b1d..fa5dbf307c40 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1333,7 +1333,13 @@ 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_write_unlock(s); \ + cond_resched(); \ + reiserfs_write_lock(s); \ + __fs_changed(gen, s); \ +}) /***************************************************************************/ /* FIXATE NODES */ -- cgit v1.2.3 From e43d3f21c502dec786f2885a75e25859f18d6ffa Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 7 May 2009 22:51:20 +0200 Subject: kill-the-BKL/reiserfs: add reiserfs_cond_resched() Usually, when we call cond_resched(), we want the write lock to be released and then reacquired once we return from scheduling. Not only does it follow the previous bkl based locking scheme, but it also let other waiters to get the lock. But if we aren't going to reschedule(), such as in !TIF_NEED_RESCHED case, it's useless to release the lock. Worse, if we release and reacquire the lock whereas it is not needed, we create useless contentions. Also if someone takes the lock while we are modifying or reading the tree, there are good chances we'll have to retry our operation, eg if the block we were seeeking has moved. So this patch introduces a helper which only unlock the write lock if we are going to schedule. [ Impact: prepare to inject less lock contention and less tree operation attempts ] Reported-by: Andi Kleen Cc: Jeff Mahoney Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- include/linux/reiserfs_fs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index fa5dbf307c40..27f4ecc28180 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -62,6 +62,19 @@ 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); +/* + * 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; /* in reading the #defines, it may help to understand that they employ -- cgit v1.2.3 From d663af807d8bb226394cb7e02f4665f6141a8140 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 7 May 2009 23:25:29 +0200 Subject: kill-the-bkl/reiserfs: conditionaly release the write lock on fs_changed() The goal of fs_changed() is to check whether the tree changed during a schedule(). This is a BKL legacy. A recent patch added an explicit unconditional release/reacquire of the write lock around the cond_resched() called inside fs_changed. But it's wasteful to unconditionally do that, we are creating superfluous lock contention in !TIF_NEED_RESCHED case. This patch manage that by calling reiserfs_cond_resched() from fs_changed() which only releases the lock if we are going to reschedule. [ Impact: inject less lock contention and tree job retries ] Cc: Jeff Mahoney Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- include/linux/reiserfs_fs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 27f4ecc28180..508fb523863e 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -1348,9 +1348,7 @@ static inline loff_t max_reiserfs_offset(struct inode *inode) #define __fs_changed(gen,s) (gen != get_generation (s)) #define fs_changed(gen,s) \ ({ \ - reiserfs_write_unlock(s); \ - cond_resched(); \ - reiserfs_write_lock(s); \ + reiserfs_cond_resched(s); \ __fs_changed(gen, s); \ }) -- cgit v1.2.3 From c72e05756b900b3be24cd73a16de52bab80984c0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 16 May 2009 18:12:08 +0200 Subject: kill-the-bkl/reiserfs: acquire the inode mutex safely While searching a pathname, an inode mutex can be acquired in do_lookup() which calls reiserfs_lookup() which in turn acquires the write lock. On the other side reiserfs_fill_super() can acquire the write_lock and then call reiserfs_lookup_privroot() which can acquire an inode mutex (the root of the mount point). So we theoretically risk an AB - BA lock inversion that could lead to a deadlock. As for other lock dependencies found since the bkl to mutex conversion, the fix is to use reiserfs_mutex_lock_safe() which drops the lock dependency to the write lock. [ Impact: fix a possible deadlock with reiserfs ] Cc: Jeff Mahoney Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- fs/reiserfs/journal.c | 34 ---------------------------------- fs/reiserfs/xattr.c | 4 ++-- include/linux/reiserfs_fs.h | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 37 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index e9a972bd0323..d23d6d7a45a6 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -537,40 +537,6 @@ static inline void insert_journal_hash(struct reiserfs_journal_cnode **table, journal_hash(table, cn->sb, cn->blocknr) = cn; } -/* - * 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 - */ -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); -} - /* lock the current transaction */ static inline void lock_journal(struct super_block *sb) { diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 6925b835a43b..59870a4751cc 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -975,7 +975,7 @@ int reiserfs_lookup_privroot(struct super_block *s) int err = 0; /* If we don't have the privroot located yet - go find it */ - mutex_lock(&s->s_root->d_inode->i_mutex); + reiserfs_mutex_lock_safe(&s->s_root->d_inode->i_mutex, s); dentry = lookup_one_len(PRIVROOT_NAME, s->s_root, strlen(PRIVROOT_NAME)); if (!IS_ERR(dentry)) { @@ -1011,7 +1011,7 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags) if (privroot->d_inode) { s->s_xattr = reiserfs_xattr_handlers; - mutex_lock(&privroot->d_inode->i_mutex); + reiserfs_mutex_lock_safe(&privroot->d_inode->i_mutex, s); if (!REISERFS_SB(s)->xattr_root) { struct dentry *dentry; dentry = lookup_one_len(XAROOT_NAME, privroot, diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index 508fb523863e..a498d9266d8c 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -62,6 +62,41 @@ 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. -- cgit v1.2.3 From 08f14fc8963e585e65b71212ce8050607b9b6c36 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 16 May 2009 19:10:38 +0200 Subject: kill-the-bkl/reiserfs: move the concurrent tree accesses checks per superblock When do_balance() balances the tree, a trick is performed to provide the ability for other tree writers/readers to check whether do_balance() is executing concurrently (requires CONFIG_REISERFS_CHECK). This is done to protect concurrent accesses to the tree. The trick is the following: When do_balance is called, a unique global variable called cur_tb takes a pointer to the current tree to be rebalanced. Once do_balance finishes its work, cur_tb takes the NULL value. Then, concurrent tree readers/writers just have to check the value of cur_tb to ensure do_balance isn't executing concurrently. If it is, then it proves that schedule() occured on do_balance(), which then relaxed the bkl that protected the tree. Now that the bkl has be turned into a mutex, this check is still fine even though do_balance() becomes preemptible: the write lock will not be automatically released on schedule(), so the tree is still protected. But this is only fine if we have a single reiserfs mountpoint. Indeed, because the bkl is a global lock, it didn't allowed concurrent executions between a tree reader/writer in a mount point and a do_balance() on another tree from another mountpoint. So assuming all these readers/writers weren't supposed to be reentrant, the current check now sometimes detect false positives with the current per-superblock mutex which allows this reentrancy. This patch keeps the concurrent tree accesses check but moves it per superblock, so that only trees from a same mount point are checked to be not accessed concurrently. [ Impact: fix spurious panic while running several reiserfs mount-points ] Cc: Jeff Mahoney Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Signed-off-by: Frederic Weisbecker --- fs/reiserfs/do_balan.c | 17 +++++------------ fs/reiserfs/fix_node.c | 5 +---- fs/reiserfs/prints.c | 4 ---- fs/reiserfs/stree.c | 5 +---- include/linux/reiserfs_fs_sb.h | 11 +++++++++++ 5 files changed, 18 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c index 128d3f7c8aa5..60c080440661 100644 --- a/fs/reiserfs/do_balan.c +++ b/fs/reiserfs/do_balan.c @@ -21,14 +21,6 @@ #include #include -#ifdef CONFIG_REISERFS_CHECK - -struct tree_balance *cur_tb = NULL; /* detects whether more than one - copy of tb exists as a means - of checking whether schedule - is interrupting do_balance */ -#endif - static inline void buffer_info_init_left(struct tree_balance *tb, struct buffer_info *bi) { @@ -1840,11 +1832,12 @@ static int check_before_balancing(struct tree_balance *tb) { int retval = 0; - if (cur_tb) { + if (REISERFS_SB(tb->tb_sb)->cur_tb) { reiserfs_panic(tb->tb_sb, "vs-12335", "suspect that schedule " "occurred based on cur_tb not being null at " "this point in code. do_balance cannot properly " - "handle schedule occurring while it runs."); + "handle concurrent tree accesses on a same " + "mount point."); } /* double check that buffers that we will modify are unlocked. (fix_nodes should already have @@ -1986,7 +1979,7 @@ static inline void do_balance_starts(struct tree_balance *tb) "check");*/ RFALSE(check_before_balancing(tb), "PAP-12340: locked buffers in TB"); #ifdef CONFIG_REISERFS_CHECK - cur_tb = tb; + REISERFS_SB(tb->tb_sb)->cur_tb = tb; #endif } @@ -1996,7 +1989,7 @@ static inline void do_balance_completed(struct tree_balance *tb) #ifdef CONFIG_REISERFS_CHECK check_leaf_level(tb); check_internal_levels(tb); - cur_tb = NULL; + REISERFS_SB(tb->tb_sb)->cur_tb = NULL; #endif /* reiserfs_free_block is no longer schedule safe. So, we need to diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c index 3a685e3f754f..d2f31330dcae 100644 --- a/fs/reiserfs/fix_node.c +++ b/fs/reiserfs/fix_node.c @@ -563,9 +563,6 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h, return needed_nodes; } -#ifdef CONFIG_REISERFS_CHECK -extern struct tree_balance *cur_tb; -#endif /* Set parameters for balancing. * Performs write of results of analysis of balancing into structure tb, @@ -2368,7 +2365,7 @@ int fix_nodes(int op_mode, struct tree_balance *tb, return REPEAT_SEARCH; } #ifdef CONFIG_REISERFS_CHECK - if (cur_tb) { + if (REISERFS_SB(tb->tb_sb)->cur_tb) { print_cur_tb("fix_nodes"); reiserfs_panic(tb->tb_sb, "PAP-8305", "there is pending do_balance"); diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 536eacaeb710..adbc6f538515 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -349,10 +349,6 @@ void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...) . */ -#ifdef CONFIG_REISERFS_CHECK -extern struct tree_balance *cur_tb; -#endif - void __reiserfs_panic(struct super_block *sb, const char *id, const char *function, const char *fmt, ...) { diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index 6b025a42d510..5fa7118f04e1 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -222,9 +222,6 @@ static inline int bin_search(const void *key, /* Key to search for. */ return ITEM_NOT_FOUND; } -#ifdef CONFIG_REISERFS_CHECK -extern struct tree_balance *cur_tb; -#endif /* Minimal possible key. It is never in the tree. */ const struct reiserfs_key MIN_KEY = { 0, 0, {{0, 0},} }; @@ -711,7 +708,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key, /* Key to s !key_in_buffer(search_path, key, sb), "PAP-5130: key is not in the buffer"); #ifdef CONFIG_REISERFS_CHECK - if (cur_tb) { + if (REISERFS_SB(sb)->cur_tb) { print_cur_tb("5140"); reiserfs_panic(sb, "PAP-5140", "schedule occurred in do_balance!"); diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h index 045c37213675..52c83b6a758a 100644 --- a/include/linux/reiserfs_fs_sb.h +++ b/include/linux/reiserfs_fs_sb.h @@ -417,6 +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: */ -- cgit v1.2.3 From 205cb37b89ab37db553907e5ac17962eec561804 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 14 Oct 2009 23:22:17 +0200 Subject: kill-the-bkl/reiserfs: definitely drop the bkl from reiserfs_ioctl() The reiserfs ioctl path doesn't need the big kernel lock anymore , now that the filesystem synchronizes through its own lock. We can then turn reiserfs_ioctl() into an unlocked_ioctl callback. Signed-off-by: Frederic Weisbecker Cc: Jeff Mahoney Cc: Chris Mason Cc: Ingo Molnar Cc: Alexander Beregalov Cc: Laurent Riffard Cc: Thomas Gleixner --- fs/reiserfs/dir.c | 2 +- fs/reiserfs/file.c | 2 +- fs/reiserfs/ioctl.c | 11 +++-------- include/linux/reiserfs_fs.h | 3 +-- 4 files changed, 6 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 17f31ad379c8..c094f58c7448 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -20,7 +20,7 @@ const struct file_operations reiserfs_dir_operations = { .read = generic_read_dir, .readdir = reiserfs_readdir, .fsync = reiserfs_dir_fsync, - .ioctl = reiserfs_ioctl, + .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, #endif diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 9f436668b7f8..da2dba082e2d 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -284,7 +284,7 @@ static ssize_t reiserfs_file_write(struct file *file, /* the file we are going t const struct file_operations reiserfs_file_operations = { .read = do_sync_read, .write = reiserfs_file_write, - .ioctl = reiserfs_ioctl, + .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, #endif diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index e30e8be09179..ace77451ceb1 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -20,9 +20,9 @@ * 2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION * 3) That's all for a while ... */ -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) { + struct inode *inode = filp->f_path.dentry->d_inode; unsigned int flags; int err = 0; @@ -132,9 +132,6 @@ setversion_out: long reiserfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct inode *inode = file->f_path.dentry->d_inode; - int ret; - /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case REISERFS_IOC32_UNPACK: @@ -156,9 +153,7 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd, return -ENOIOCTLCMD; } - ret = reiserfs_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg)); - - return ret; + return reiserfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif diff --git a/include/linux/reiserfs_fs.h b/include/linux/reiserfs_fs.h index a498d9266d8c..a05b4a20768d 100644 --- a/include/linux/reiserfs_fs.h +++ b/include/linux/reiserfs_fs.h @@ -2314,8 +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); -- cgit v1.2.3