5 files changed, 68 insertions, 169 deletions

diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index a003d50edc..8f1f2aa5fb 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -375,7 +375,7 @@ void journal_commit_transaction(journal_t *journal)
                         struct buffer_head *bh = jh2bh(jh);
 
                         jbd_lock_bh_state(bh);
-                        jbd_slab_free(jh->b_committed_data, bh->b_size);
+                        jbd_free(jh->b_committed_data, bh->b_size);
                         jh->b_committed_data = NULL;
                         jbd_unlock_bh_state(bh);
                 }
@@ -466,7 +466,7 @@ void journal_commit_transaction(journal_t *journal)
         spin_unlock(&journal->j_list_lock);
 
         if (err)
-                __journal_abort_hard(journal);
+                journal_abort(journal, err);
 
         journal_write_revoke_records(journal, commit_transaction);
 
@@ -524,7 +524,7 @@ void journal_commit_transaction(journal_t *journal)
 
                         descriptor = journal_get_descriptor_buffer(journal);
                         if (!descriptor) {
-                                __journal_abort_hard(journal);
+                                journal_abort(journal, -EIO);
                                 continue;
                         }
 
@@ -557,7 +557,7 @@ void journal_commit_transaction(journal_t *journal)
                    and repeat this loop: we'll fall into the
                    refile-on-abort condition above. */
                 if (err) {
-                        __journal_abort_hard(journal);
+                        journal_abort(journal, err);
                         continue;
                 }
 
@@ -748,7 +748,7 @@ wait_for_iobuf:
                 err = -EIO;
 
         if (err)
-                __journal_abort_hard(journal);
+                journal_abort(journal, err);
 
         /* End of a transaction!  Finally, we can do checkpoint
            processing: any buffers committed as a result of this
@@ -792,14 +792,14 @@ restart_loop:
                  * Otherwise, we can just throw away the frozen data now.
                  */
                 if (jh->b_committed_data) {
-                        jbd_slab_free(jh->b_committed_data, bh->b_size);
+                        jbd_free(jh->b_committed_data, bh->b_size);
                         jh->b_committed_data = NULL;
                         if (jh->b_frozen_data) {
                                 jh->b_committed_data = jh->b_frozen_data;
                                 jh->b_frozen_data = NULL;
                         }
                 } else if (jh->b_frozen_data) {
-                        jbd_slab_free(jh->b_frozen_data, bh->b_size);
+                        jbd_free(jh->b_frozen_data, bh->b_size);
                         jh->b_frozen_data = NULL;
                 }
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 06ab3c10b1..5d14243499 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -35,6 +35,7 @@
 #include <linux/kthread.h>
 #include <linux/poison.h>
 #include <linux/proc_fs.h>
+#include <linux/debugfs.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -83,7 +84,6 @@ EXPORT_SYMBOL(journal_force_commit);
 
 static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
-static int journal_create_jbd_slab(size_t slab_size);
 
 /*
  * Helper function used to manage commit timeouts
@@ -218,7 +218,7 @@ static int journal_start_thread(journal_t *journal)
         if (IS_ERR(t))
                 return PTR_ERR(t);
 
-        wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+        wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
         return 0;
 }
 
@@ -230,7 +230,8 @@ static void journal_kill_thread(journal_t *journal)
         while (journal->j_task) {
                 wake_up(&journal->j_wait_commit);
                 spin_unlock(&journal->j_state_lock);
-                wait_event(journal->j_wait_done_commit, journal->j_task == 0);
+                wait_event(journal->j_wait_done_commit,
+                                journal->j_task == NULL);
                 spin_lock(&journal->j_state_lock);
         }
         spin_unlock(&journal->j_state_lock);
@@ -334,10 +335,10 @@ repeat:
                 char *tmp;
 
                 jbd_unlock_bh_state(bh_in);
-                tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS);
+                tmp = jbd_alloc(bh_in->b_size, GFP_NOFS);
                 jbd_lock_bh_state(bh_in);
                 if (jh_in->b_frozen_data) {
-                        jbd_slab_free(tmp, bh_in->b_size);
+                        jbd_free(tmp, bh_in->b_size);
                         goto repeat;
                 }
 
@@ -654,10 +655,9 @@ static journal_t * journal_init_common (void)
         journal_t *journal;
         int err;
 
-        journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
+        journal = kzalloc(sizeof(*journal), GFP_KERNEL);
         if (!journal)
                 goto fail;
-        memset(journal, 0, sizeof(*journal));
 
         init_waitqueue_head(&journal->j_wait_transaction_locked);
         init_waitqueue_head(&journal->j_wait_logspace);
@@ -1095,13 +1095,6 @@ int journal_load(journal_t *journal)
                 }
         }
 
-        /*
-         * Create a slab for this blocksize
-         */
-        err = journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize));
-        if (err)
-                return err;
-
         /* Let the recovery code check whether it needs to recover any
          * data from the journal. */
         if (journal_recover(journal))
@@ -1615,86 +1608,6 @@ int journal_blocks_per_page(struct inode *inode)
 }
 
 /*
- * Simple support for retrying memory allocations.  Introduced to help to
- * debug different VM deadlock avoidance strategies.
- */
-void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
-{
-        return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0));
-}
-
-/*
- * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
- * and allocate frozen and commit buffers from these slabs.
- *
- * Reason for doing this is to avoid, SLAB_DEBUG - since it could
- * cause bh to cross page boundary.
- */
-
-#define JBD_MAX_SLABS 5
-#define JBD_SLAB_INDEX(size)  (size >> 11)
-
-static struct kmem_cache *jbd_slab[JBD_MAX_SLABS];
-static const char *jbd_slab_names[JBD_MAX_SLABS] = {
-        "jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k"
-};
-
-static void journal_destroy_jbd_slabs(void)
-{
-        int i;
-
-        for (i = 0; i < JBD_MAX_SLABS; i++) {
-                if (jbd_slab[i])
-                        kmem_cache_destroy(jbd_slab[i]);
-                jbd_slab[i] = NULL;
-        }
-}
-
-static int journal_create_jbd_slab(size_t slab_size)
-{
-        int i = JBD_SLAB_INDEX(slab_size);
-
-        BUG_ON(i >= JBD_MAX_SLABS);
-
-        /*
-         * Check if we already have a slab created for this size
-         */
-        if (jbd_slab[i])
-                return 0;
-
-        /*
-         * Create a slab and force alignment to be same as slabsize -
-         * this will make sure that allocations won't cross the page
-         * boundary.
-         */
-        jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
-                                slab_size, slab_size, 0, NULL);
-        if (!jbd_slab[i]) {
-                printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
-                return -ENOMEM;
-        }
-        return 0;
-}
-
-void * jbd_slab_alloc(size_t size, gfp_t flags)
-{
-        int idx;
-
-        idx = JBD_SLAB_INDEX(size);
-        BUG_ON(jbd_slab[idx] == NULL);
-        return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
-}
-
-void jbd_slab_free(void *ptr,  size_t size)
-{
-        int idx;
-
-        idx = JBD_SLAB_INDEX(size);
-        BUG_ON(jbd_slab[idx] == NULL);
-        kmem_cache_free(jbd_slab[idx], ptr);
-}
-
-/*
  * Journal_head storage management
  */
 static struct kmem_cache *journal_head_cache;
@@ -1710,7 +1623,7 @@ static int journal_init_journal_head_cache(void)
         journal_head_cache = kmem_cache_create("journal_head",
                                 sizeof(struct journal_head),
                                 0,              /* offset */
-                                0,              /* flags */
+                                SLAB_TEMPORARY, /* flags */
                                 NULL);          /* ctor */
         retval = 0;
         if (journal_head_cache == 0) {
@@ -1739,14 +1652,14 @@ static struct journal_head *journal_alloc_journal_head(void)
         atomic_inc(&nr_journal_heads);
 #endif
         ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
-        if (ret == 0) {
+        if (ret == NULL) {
                 jbd_debug(1, "out of memory for journal_head\n");
                 if (time_after(jiffies, last_warning + 5*HZ)) {
                         printk(KERN_NOTICE "ENOMEM in %s, retrying.\n",
                                __FUNCTION__);
                         last_warning = jiffies;
                 }
-                while (ret == 0) {
+                while (ret == NULL) {
                         yield();
                         ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
                 }
@@ -1881,13 +1794,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
                                 printk(KERN_WARNING "%s: freeing "
                                                 "b_frozen_data\n",
                                                 __FUNCTION__);
-                                jbd_slab_free(jh->b_frozen_data, bh->b_size);
+                                jbd_free(jh->b_frozen_data, bh->b_size);
                         }
                         if (jh->b_committed_data) {
                                 printk(KERN_WARNING "%s: freeing "
                                                 "b_committed_data\n",
                                                 __FUNCTION__);
-                                jbd_slab_free(jh->b_committed_data, bh->b_size);
+                                jbd_free(jh->b_committed_data, bh->b_size);
                         }
                         bh->b_private = NULL;
                         jh->b_bh = NULL;        /* debug, really */
@@ -1939,64 +1852,41 @@ void journal_put_journal_head(struct journal_head *jh)
 }
 
 /*
- * /proc tunables
+ * debugfs tunables
  */
-#if defined(CONFIG_JBD_DEBUG)
-int journal_enable_debug;
-EXPORT_SYMBOL(journal_enable_debug);
-#endif
+#ifdef CONFIG_JBD_DEBUG
 
-#if defined(CONFIG_JBD_DEBUG) && defined(CONFIG_PROC_FS)
+u8 journal_enable_debug __read_mostly;
+EXPORT_SYMBOL(journal_enable_debug);
 
-static struct proc_dir_entry *proc_jbd_debug;
+static struct dentry *jbd_debugfs_dir;
+static struct dentry *jbd_debug;
 
-static int read_jbd_debug(char *page, char **start, off_t off,
-                          int count, int *eof, void *data)
+static void __init jbd_create_debugfs_entry(void)
 {
-        int ret;
-
-        ret = sprintf(page + off, "%d\n", journal_enable_debug);
-        *eof = 1;
-        return ret;
+        jbd_debugfs_dir = debugfs_create_dir("jbd", NULL);
+        if (jbd_debugfs_dir)
+                jbd_debug = debugfs_create_u8("jbd-debug", S_IRUGO,
+                                               jbd_debugfs_dir,
+                                               &journal_enable_debug);
 }
 
-static int write_jbd_debug(struct file *file, const char __user *buffer,
-                           unsigned long count, void *data)
+static void __exit jbd_remove_debugfs_entry(void)
 {
-        char buf[32];
-
-        if (count > ARRAY_SIZE(buf) - 1)
-                count = ARRAY_SIZE(buf) - 1;
-        if (copy_from_user(buf, buffer, count))
-                return -EFAULT;
-        buf[ARRAY_SIZE(buf) - 1] = '\0';
-        journal_enable_debug = simple_strtoul(buf, NULL, 10);
-        return count;
+        debugfs_remove(jbd_debug);
+        debugfs_remove(jbd_debugfs_dir);
 }
 
-#define JBD_PROC_NAME "sys/fs/jbd-debug"
+#else
 
-static void __init create_jbd_proc_entry(void)
+static inline void jbd_create_debugfs_entry(void)
 {
-        proc_jbd_debug = create_proc_entry(JBD_PROC_NAME, 0644, NULL);
-        if (proc_jbd_debug) {
-                /* Why is this so hard? */
-                proc_jbd_debug->read_proc = read_jbd_debug;
-                proc_jbd_debug->write_proc = write_jbd_debug;
-        }
 }
 
-static void __exit remove_jbd_proc_entry(void)
+static inline void jbd_remove_debugfs_entry(void)
 {
-        if (proc_jbd_debug)
-                remove_proc_entry(JBD_PROC_NAME, NULL);
 }
 
-#else
-
-#define create_jbd_proc_entry() do {} while (0)
-#define remove_jbd_proc_entry() do {} while (0)
-
 #endif
 
 struct kmem_cache *jbd_handle_cache;
@@ -2006,7 +1896,7 @@ static int __init journal_init_handle_cache(void)
         jbd_handle_cache = kmem_cache_create("journal_handle",
                                 sizeof(handle_t),
                                 0,              /* offset */
-                                0,              /* flags */
+                                SLAB_TEMPORARY, /* flags */
                                 NULL);          /* ctor */
         if (jbd_handle_cache == NULL) {
                 printk(KERN_EMERG "JBD: failed to create handle cache\n");
@@ -2042,7 +1932,6 @@ static void journal_destroy_caches(void)
         journal_destroy_revoke_caches();
         journal_destroy_journal_head_cache();
         journal_destroy_handle_cache();
-        journal_destroy_jbd_slabs();
 }
 
 static int __init journal_init(void)
@@ -2054,7 +1943,7 @@ static int __init journal_init(void)
         ret = journal_init_caches();
         if (ret != 0)
                 journal_destroy_caches();
-        create_jbd_proc_entry();
+        jbd_create_debugfs_entry();
         return ret;
 }
 
@@ -2065,7 +1954,7 @@ static void __exit journal_exit(void)
         if (n)
                 printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
 #endif
-        remove_jbd_proc_entry();
+        jbd_remove_debugfs_entry();
         journal_destroy_caches();
 }
 
diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c
index 2a5f4b833e..c5d9694b6a 100644
--- a/fs/jbd/recovery.c
+++ b/fs/jbd/recovery.c
@@ -250,10 +250,10 @@ int journal_recover(journal_t *journal)
         if (!err)
                 err = do_one_pass(journal, &info, PASS_REPLAY);
 
-        jbd_debug(0, "JBD: recovery, exit status %d, "
+        jbd_debug(1, "JBD: recovery, exit status %d, "
                   "recovered transactions %u to %u\n",
                   err, info.start_transaction, info.end_transaction);
-        jbd_debug(0, "JBD: Replayed %d and revoked %d/%d blocks\n",
+        jbd_debug(1, "JBD: Replayed %d and revoked %d/%d blocks\n",
                   info.nr_replays, info.nr_revoke_hits, info.nr_revokes);
 
         /* Restart the log at the next transaction ID, thus invalidating
@@ -297,7 +297,7 @@ int journal_skip_recovery(journal_t *journal)
 #ifdef CONFIG_JBD_DEBUG
                 int dropped = info.end_transaction - be32_to_cpu(sb->s_sequence);
 #endif
-                jbd_debug(0,
+                jbd_debug(1,
                           "JBD: ignoring %d transaction%s from the journal.\n",
                           dropped, (dropped == 1) ? "" : "s");
                 journal->j_transaction_sequence = ++info.end_transaction;
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index 62e13c8db1..ad2eacf570 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -170,13 +170,15 @@ int __init journal_init_revoke_caches(void)
 {
         revoke_record_cache = kmem_cache_create("revoke_record",
                                            sizeof(struct jbd_revoke_record_s),
-                                           0, SLAB_HWCACHE_ALIGN, NULL);
+                                           0,
+                                           SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
+                                           NULL);
         if (revoke_record_cache == 0)
                 return -ENOMEM;
 
         revoke_table_cache = kmem_cache_create("revoke_table",
                                            sizeof(struct jbd_revoke_table_s),
-                                           0, 0, NULL);
+                                           0, SLAB_TEMPORARY, NULL);
         if (revoke_table_cache == 0) {
                 kmem_cache_destroy(revoke_record_cache);
                 revoke_record_cache = NULL;
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 772b6531a2..08ff6c7028 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -96,13 +96,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle)
 
 alloc_transaction:
         if (!journal->j_running_transaction) {
-                new_transaction = jbd_kmalloc(sizeof(*new_transaction),
-                                                GFP_NOFS);
+                new_transaction = kzalloc(sizeof(*new_transaction),
+                                                GFP_NOFS|__GFP_NOFAIL);
                 if (!new_transaction) {
                         ret = -ENOMEM;
                         goto out;
                 }
-                memset(new_transaction, 0, sizeof(*new_transaction));
         }
 
         jbd_debug(3, "New handle %p going live.\n", handle);
@@ -233,6 +232,8 @@ out:
         return ret;
 }
 
+static struct lock_class_key jbd_handle_key;
+
 /* Allocate a new handle.  This should probably be in a slab... */
 static handle_t *new_handle(int nblocks)
 {
@@ -243,6 +244,8 @@ static handle_t *new_handle(int nblocks)
         handle->h_buffer_credits = nblocks;
         handle->h_ref = 1;
 
+        lockdep_init_map(&handle->h_lockdep_map, "jbd_handle", &jbd_handle_key, 0);
+
         return handle;
 }
 
@@ -286,6 +289,9 @@ handle_t *journal_start(journal_t *journal, int nblocks)
                 current->journal_info = NULL;
                 handle = ERR_PTR(err);
         }
+
+        lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+
         return handle;
 }
 
@@ -668,7 +674,7 @@ repeat:
                                 JBUFFER_TRACE(jh, "allocate memory for buffer");
                                 jbd_unlock_bh_state(bh);
                                 frozen_buffer =
-                                        jbd_slab_alloc(jh2bh(jh)->b_size,
+                                        jbd_alloc(jh2bh(jh)->b_size,
                                                          GFP_NOFS);
                                 if (!frozen_buffer) {
                                         printk(KERN_EMERG
@@ -728,7 +734,7 @@ done:
 
 out:
         if (unlikely(frozen_buffer))    /* It's usually NULL */
-                jbd_slab_free(frozen_buffer, bh->b_size);
+                jbd_free(frozen_buffer, bh->b_size);
 
         JBUFFER_TRACE(jh, "exit");
         return error;
@@ -881,7 +887,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 
 repeat:
         if (!jh->b_committed_data) {
-                committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS);
+                committed_data = jbd_alloc(jh2bh(jh)->b_size, GFP_NOFS);
                 if (!committed_data) {
                         printk(KERN_EMERG "%s: No memory for committed data\n",
                                 __FUNCTION__);
@@ -908,7 +914,7 @@ repeat:
 out:
         journal_put_journal_head(jh);
         if (unlikely(committed_data))
-                jbd_slab_free(committed_data, bh->b_size);
+                jbd_free(committed_data, bh->b_size);
         return err;
 }
 
@@ -1165,7 +1171,7 @@ int journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
         }
 
         /* That test should have eliminated the following case: */
-        J_ASSERT_JH(jh, jh->b_frozen_data == 0);
+        J_ASSERT_JH(jh, jh->b_frozen_data == NULL);
 
         JBUFFER_TRACE(jh, "file as BJ_Metadata");
         spin_lock(&journal->j_list_lock);
@@ -1411,6 +1417,8 @@ int journal_stop(handle_t *handle)
                 spin_unlock(&journal->j_state_lock);
         }
 
+        lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+
         jbd_free_handle(handle);
         return err;
 }
@@ -1513,7 +1521,7 @@ static void __journal_temp_unlink_buffer(struct journal_head *jh)
 
         J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
         if (jh->b_jlist != BJ_None)
-                J_ASSERT_JH(jh, transaction != 0);
+                J_ASSERT_JH(jh, transaction != NULL);
 
         switch (jh->b_jlist) {
         case BJ_None:
@@ -1582,11 +1590,11 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
         if (buffer_locked(bh) || buffer_dirty(bh))
                 goto out;
 
-        if (jh->b_next_transaction != 0)
+        if (jh->b_next_transaction != NULL)
                 goto out;
 
         spin_lock(&journal->j_list_lock);
-        if (jh->b_transaction != 0 && jh->b_cp_transaction == 0) {
+        if (jh->b_transaction != NULL && jh->b_cp_transaction == NULL) {
                 if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) {
                         /* A written-back ordered data buffer */
                         JBUFFER_TRACE(jh, "release data");
@@ -1594,7 +1602,7 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
                         journal_remove_journal_head(bh);
                         __brelse(bh);
                 }
-        } else if (jh->b_cp_transaction != 0 && jh->b_transaction == 0) {
+        } else if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
                 /* written-back checkpointed metadata buffer */
                 if (jh->b_jlist == BJ_None) {
                         JBUFFER_TRACE(jh, "remove from checkpoint list");
@@ -1954,7 +1962,7 @@ void __journal_file_buffer(struct journal_head *jh,
 
         J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
         J_ASSERT_JH(jh, jh->b_transaction == transaction ||
-                                jh->b_transaction == 0);
+                                jh->b_transaction == NULL);
 
         if (jh->b_transaction && jh->b_jlist == jlist)
                 return;