/*
- * linux/fs/journal.c
+ * linux/fs/jbd/journal.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 1998
*
#include <linux/jbd.h>
#include <linux/errno.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/mm.h>
-#include <linux/suspend.h>
+#include <linux/freezer.h>
#include <linux/pagemap.h>
#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>
EXPORT_SYMBOL(journal_create);
EXPORT_SYMBOL(journal_load);
EXPORT_SYMBOL(journal_destroy);
-EXPORT_SYMBOL(journal_update_superblock);
EXPORT_SYMBOL(journal_abort);
EXPORT_SYMBOL(journal_errno);
EXPORT_SYMBOL(journal_ack_err);
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
transaction->t_expires))
should_sleep = 0;
if (journal->j_flags & JFS_UNMOUNT)
- should_sleep = 0;
+ should_sleep = 0;
if (should_sleep) {
spin_unlock(&journal->j_state_lock);
schedule();
return 0;
}
-static void journal_start_thread(journal_t *journal)
+static int journal_start_thread(journal_t *journal)
{
- kthread_run(kjournald, journal, "kjournald");
- wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+ struct task_struct *t;
+
+ t = kthread_run(kjournald, journal, "kjournald");
+ if (IS_ERR(t))
+ return PTR_ERR(t);
+
+ wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
+ return 0;
}
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);
int journal_write_metadata_buffer(transaction_t *transaction,
struct journal_head *jh_in,
struct journal_head **jh_out,
- int blocknr)
+ unsigned long blocknr)
{
int need_copy_out = 0;
int done_copy_out = 0;
struct page *new_page;
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
+ journal_t *journal = transaction->t_journal;
/*
* The buffer really shouldn't be locked: only the current committing
J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+ /* keep subsequent assertions sane */
+ new_bh->b_state = 0;
+ init_buffer(new_bh, NULL, NULL);
+ atomic_set(&new_bh->b_count, 1);
+ new_jh = journal_add_journal_head(new_bh); /* This sleeps */
/*
* If a new transaction has already done a buffer copy-out, then
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;
}
kunmap_atomic(mapped_data, KM_USER0);
}
- /* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
- atomic_set(&new_bh->b_count, 1);
- jbd_unlock_bh_state(bh_in);
-
- new_jh = journal_add_journal_head(new_bh); /* This sleeps */
-
set_bh_page(new_bh, new_page, new_offset);
new_jh->b_transaction = NULL;
new_bh->b_size = jh2bh(jh_in)->b_size;
* copying is moved to the transaction's shadow queue.
*/
JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
- journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_lock(&journal->j_list_lock);
+ __journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh_in);
+
JBUFFER_TRACE(new_jh, "file as BJ_IO");
journal_file_buffer(new_jh, transaction, BJ_IO);
}
/*
- * Called under j_state_lock. Returns true if a transaction was started.
+ * Called under j_state_lock. Returns true if a transaction commit was started.
*/
int __log_start_commit(journal_t *journal, tid_t target)
{
/*
* Start a commit of the current running transaction (if any). Returns true
- * if a transaction was started, and fills its tid in at *ptid
+ * if a transaction is going to be committed (or is currently already
+ * committing), and fills its tid in at *ptid
*/
int journal_start_commit(journal_t *journal, tid_t *ptid)
{
if (journal->j_running_transaction) {
tid_t tid = journal->j_running_transaction->t_tid;
- ret = __log_start_commit(journal, tid);
- if (ret && ptid)
+ __log_start_commit(journal, tid);
+ /* There's a running transaction and we've just made sure
+ * it's commit has been scheduled. */
+ if (ptid)
*ptid = tid;
- } else if (journal->j_committing_transaction && ptid) {
+ ret = 1;
+ } else if (journal->j_committing_transaction) {
/*
* If ext3_write_super() recently started a commit, then we
* have to wait for completion of that transaction
*/
- *ptid = journal->j_committing_transaction->t_tid;
+ if (ptid)
+ *ptid = journal->j_committing_transaction->t_tid;
ret = 1;
}
spin_unlock(&journal->j_state_lock);
if (!tid_geq(journal->j_commit_request, tid)) {
printk(KERN_EMERG
"%s: error: j_commit_request=%d, tid=%d\n",
- __FUNCTION__, journal->j_commit_request, tid);
+ __func__, journal->j_commit_request, tid);
}
spin_unlock(&journal->j_state_lock);
#endif
printk(KERN_ALERT "%s: journal block not found "
"at offset %lu on %s\n",
- __FUNCTION__,
+ __func__,
blocknr,
bdevname(journal->j_dev, b));
err = -EIO;
return NULL;
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh)
+ return NULL;
lock_buffer(bh);
memset(bh->b_data, 0, journal->j_blocksize);
set_buffer_uptodate(bh);
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);
*/
/**
- * journal_t * journal_init_dev() - creates an initialises a journal structure
+ * journal_t * journal_init_dev() - creates and initialises a journal structure
* @bdev: Block device on which to create the journal
* @fs_dev: Device which hold journalled filesystem for this journal.
* @start: Block nr Start of journal.
- * @len: Lenght of the journal in blocks.
+ * @len: Length of the journal in blocks.
* @blocksize: blocksize of journalling device
- * @returns: a newly created journal_t *
+ *
+ * Returns: a newly created journal_t *
*
* journal_init_dev creates a journal which maps a fixed contiguous
* range of blocks on an arbitrary block device.
if (!journal)
return NULL;
+ /* journal descriptor can store up to n blocks -bzzz */
+ journal->j_blocksize = blocksize;
+ n = journal->j_blocksize / sizeof(journal_block_tag_t);
+ journal->j_wbufsize = n;
+ journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
+ if (!journal->j_wbuf) {
+ printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+ __func__);
+ goto out_err;
+ }
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
journal->j_maxlen = len;
- journal->j_blocksize = blocksize;
bh = __getblk(journal->j_dev, start, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
- /* journal descriptor can store up to n blocks -bzzz */
- n = journal->j_blocksize / sizeof(journal_block_tag_t);
- journal->j_wbufsize = n;
- journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
- if (!journal->j_wbuf) {
- printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
- __FUNCTION__);
- kfree(journal);
- journal = NULL;
- }
-
return journal;
+out_err:
+ kfree(journal);
+ return NULL;
}
/**
journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
if (!journal->j_wbuf) {
printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
- __FUNCTION__);
- kfree(journal);
- return NULL;
+ __func__);
+ goto out_err;
}
err = journal_bmap(journal, 0, &blocknr);
/* If that failed, give up */
if (err) {
printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
- __FUNCTION__);
- kfree(journal);
- return NULL;
+ __func__);
+ goto out_err;
}
bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
- J_ASSERT(bh != NULL);
+ if (!bh) {
+ printk(KERN_ERR
+ "%s: Cannot get buffer for journal superblock\n",
+ __func__);
+ goto out_err;
+ }
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
return journal;
+out_err:
+ kfree(journal);
+ return NULL;
}
/*
static int journal_reset(journal_t *journal)
{
journal_superblock_t *sb = journal->j_superblock;
- unsigned int first, last;
+ unsigned long first, last;
first = be32_to_cpu(sb->s_first);
last = be32_to_cpu(sb->s_maxlen);
+ if (first + JFS_MIN_JOURNAL_BLOCKS > last + 1) {
+ printk(KERN_ERR "JBD: Journal too short (blocks %lu-%lu).\n",
+ first, last);
+ journal_fail_superblock(journal);
+ return -EINVAL;
+ }
journal->j_first = first;
journal->j_last = last;
/* Add the dynamic fields and write it to disk. */
journal_update_superblock(journal, 1);
- journal_start_thread(journal);
- return 0;
+ return journal_start_thread(journal);
}
/**
*/
printk(KERN_EMERG
"%s: creation of journal on external device!\n",
- __FUNCTION__);
+ __func__);
BUG();
}
}
}
- /*
- * Create a slab for this blocksize
- */
- err = journal_create_jbd_slab(cpu_to_be32(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))
*
* Release a journal_t structure once it is no longer in use by the
* journaled object.
+ * Return <0 if we couldn't clean up the journal.
*/
-void journal_destroy(journal_t *journal)
+int journal_destroy(journal_t *journal)
{
+ int err = 0;
+
/* Wait for the commit thread to wake up and die. */
journal_kill_thread(journal);
J_ASSERT(journal->j_checkpoint_transactions == NULL);
spin_unlock(&journal->j_list_lock);
- /* We can now mark the journal as empty. */
- journal->j_tail = 0;
- journal->j_tail_sequence = ++journal->j_transaction_sequence;
if (journal->j_sb_buffer) {
- journal_update_superblock(journal, 1);
+ if (!is_journal_aborted(journal)) {
+ /* We can now mark the journal as empty. */
+ journal->j_tail = 0;
+ journal->j_tail_sequence =
+ ++journal->j_transaction_sequence;
+ journal_update_superblock(journal, 1);
+ } else {
+ err = -EIO;
+ }
brelse(journal->j_sb_buffer);
}
journal_destroy_revoke(journal);
kfree(journal->j_wbuf);
kfree(journal);
+
+ return err;
}
spin_lock(&journal->j_list_lock);
while (!err && journal->j_checkpoint_transactions != NULL) {
spin_unlock(&journal->j_list_lock);
+ mutex_lock(&journal->j_checkpoint_mutex);
err = log_do_checkpoint(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
+
+ if (is_journal_aborted(journal))
+ return -EIO;
+
cleanup_journal_tail(journal);
/* Finally, mark the journal as really needing no recovery.
J_ASSERT(journal->j_head == journal->j_tail);
J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
spin_unlock(&journal->j_state_lock);
- return err;
+ return 0;
}
/**
* Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
* and don't attempt to make any other journal updates.
*/
-void __journal_abort_hard(journal_t *journal)
+static void __journal_abort_hard(journal_t *journal)
{
transaction_t *transaction;
char b[BDEVNAME_SIZE];
}
/*
- * 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 kmem_cache_t *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, 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 kmem_cache_t *journal_head_cache;
+static struct kmem_cache *journal_head_cache;
#ifdef CONFIG_JBD_DEBUG
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif
{
int retval;
- J_ASSERT(journal_head_cache == 0);
+ J_ASSERT(journal_head_cache == NULL);
journal_head_cache = kmem_cache_create("journal_head",
sizeof(struct journal_head),
0, /* offset */
- 0, /* flags */
- NULL, /* ctor */
- NULL); /* dtor */
+ SLAB_TEMPORARY, /* flags */
+ NULL); /* ctor */
retval = 0;
- if (journal_head_cache == 0) {
+ if (!journal_head_cache) {
retval = -ENOMEM;
printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
}
static void journal_destroy_journal_head_cache(void)
{
- J_ASSERT(journal_head_cache != NULL);
- kmem_cache_destroy(journal_head_cache);
- journal_head_cache = NULL;
+ if (journal_head_cache) {
+ kmem_cache_destroy(journal_head_cache);
+ journal_head_cache = NULL;
+ }
}
/*
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__);
+ __func__);
last_warning = jiffies;
}
- while (ret == 0) {
+ while (ret == NULL) {
yield();
ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS);
}
if (jh->b_frozen_data) {
printk(KERN_WARNING "%s: freeing "
"b_frozen_data\n",
- __FUNCTION__);
- jbd_slab_free(jh->b_frozen_data, bh->b_size);
+ __func__);
+ 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);
+ __func__);
+ jbd_free(jh->b_committed_data, bh->b_size);
}
bh->b_private = NULL;
jh->b_bh = NULL; /* debug, really */
}
/*
- * /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
-kmem_cache_t *jbd_handle_cache;
+struct kmem_cache *jbd_handle_cache;
static int __init journal_init_handle_cache(void)
{
jbd_handle_cache = kmem_cache_create("journal_handle",
sizeof(handle_t),
0, /* offset */
- 0, /* flags */
- NULL, /* ctor */
- NULL); /* dtor */
+ SLAB_TEMPORARY, /* flags */
+ NULL); /* ctor */
if (jbd_handle_cache == NULL) {
printk(KERN_EMERG "JBD: failed to create handle cache\n");
return -ENOMEM;
journal_destroy_revoke_caches();
journal_destroy_journal_head_cache();
journal_destroy_handle_cache();
- journal_destroy_jbd_slabs();
}
static int __init journal_init(void)
{
int ret;
-/* Static check for data structure consistency. There's no code
- * invoked --- we'll just get a linker failure if things aren't right.
- */
- extern void journal_bad_superblock_size(void);
- if (sizeof(struct journal_superblock_s) != 1024)
- journal_bad_superblock_size();
-
+ BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);
ret = journal_init_caches();
if (ret != 0)
journal_destroy_caches();
- create_jbd_proc_entry();
+ jbd_create_debugfs_entry();
return ret;
}
if (n)
printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
#endif
- remove_jbd_proc_entry();
+ jbd_remove_debugfs_entry();
journal_destroy_caches();
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff