1 files changed, 91 insertions, 75 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 95457576e434..02c7ad9d7a41 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -103,6 +103,24 @@ EXPORT_SYMBOL(jbd2_inode_cache);
 static void __journal_abort_soft (journal_t *journal, int errno);
 static int jbd2_journal_create_slab(size_t slab_size);
 
+#ifdef CONFIG_JBD2_DEBUG
+void __jbd2_debug(int level, const char *file, const char *func,
+                  unsigned int line, const char *fmt, ...)
+{
+        struct va_format vaf;
+        va_list args;
+
+        if (level > jbd2_journal_enable_debug)
+                return;
+        va_start(args, fmt);
+        vaf.fmt = fmt;
+        vaf.va = &args;
+        printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf);
+        va_end(args);
+}
+EXPORT_SYMBOL(__jbd2_debug);
+#endif
+
 /* Checksumming functions */
 int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
@@ -310,14 +328,12 @@ static void journal_kill_thread(journal_t *journal)
  *
  * If the source buffer has already been modified by a new transaction
  * since we took the last commit snapshot, we use the frozen copy of
- * that data for IO.  If we end up using the existing buffer_head's data
- * for the write, then we *have* to lock the buffer to prevent anyone
- * else from using and possibly modifying it while the IO is in
- * progress.
+ * that data for IO. If we end up using the existing buffer_head's data
+ * for the write, then we have to make sure nobody modifies it while the
+ * IO is in progress. do_get_write_access() handles this.
  *
- * The function returns a pointer to the buffer_heads to be used for IO.
- *
- * We assume that the journal has already been locked in this function.
+ * The function returns a pointer to the buffer_head to be used for IO.
+ * 
  *
  * Return value:
  *  <0: Error
@@ -330,15 +346,14 @@ static void journal_kill_thread(journal_t *journal)
 
 int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
                                   struct journal_head  *jh_in,
-                                  struct journal_head **jh_out,
-                                  unsigned long long blocknr)
+                                  struct buffer_head **bh_out,
+                                  sector_t blocknr)
 {
         int need_copy_out = 0;
         int done_copy_out = 0;
         int do_escape = 0;
         char *mapped_data;
         struct buffer_head *new_bh;
-        struct journal_head *new_jh;
         struct page *new_page;
         unsigned int new_offset;
         struct buffer_head *bh_in = jh2bh(jh_in);
@@ -368,14 +383,13 @@ retry_alloc:
 
         /* keep subsequent assertions sane */
         atomic_set(&new_bh->b_count, 1);
-        new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
 
+        jbd_lock_bh_state(bh_in);
+repeat:
         /*
          * If a new transaction has already done a buffer copy-out, then
          * we use that version of the data for the commit.
          */
-        jbd_lock_bh_state(bh_in);
-repeat:
         if (jh_in->b_frozen_data) {
                 done_copy_out = 1;
                 new_page = virt_to_page(jh_in->b_frozen_data);
@@ -415,7 +429,7 @@ repeat:
                 jbd_unlock_bh_state(bh_in);
                 tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
                 if (!tmp) {
-                        jbd2_journal_put_journal_head(new_jh);
+                        brelse(new_bh);
                         return -ENOMEM;
                 }
                 jbd_lock_bh_state(bh_in);
@@ -426,7 +440,7 @@ repeat:
 
                 jh_in->b_frozen_data = tmp;
                 mapped_data = kmap_atomic(new_page);
-                memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
+                memcpy(tmp, mapped_data + new_offset, bh_in->b_size);
                 kunmap_atomic(mapped_data);
 
                 new_page = virt_to_page(tmp);
@@ -452,14 +466,14 @@ repeat:
         }
 
         set_bh_page(new_bh, new_page, new_offset);
-        new_jh->b_transaction = NULL;
-        new_bh->b_size = jh2bh(jh_in)->b_size;
-        new_bh->b_bdev = transaction->t_journal->j_dev;
+        new_bh->b_size = bh_in->b_size;
+        new_bh->b_bdev = journal->j_dev;
         new_bh->b_blocknr = blocknr;
+        new_bh->b_private = bh_in;
         set_buffer_mapped(new_bh);
         set_buffer_dirty(new_bh);
 
-        *jh_out = new_jh;
+        *bh_out = new_bh;
 
         /*
          * The to-be-written buffer needs to get moved to the io queue,
@@ -470,11 +484,9 @@ repeat:
         spin_lock(&journal->j_list_lock);
         __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
         spin_unlock(&journal->j_list_lock);
+        set_buffer_shadow(bh_in);
         jbd_unlock_bh_state(bh_in);
 
-        JBUFFER_TRACE(new_jh, "file as BJ_IO");
-        jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
-
         return do_escape | (done_copy_out << 1);
 }
 
@@ -484,35 +496,6 @@ repeat:
  */
 
 /*
- * __jbd2_log_space_left: Return the number of free blocks left in the journal.
- *
- * Called with the journal already locked.
- *
- * Called under j_state_lock
- */
-
-int __jbd2_log_space_left(journal_t *journal)
-{
-        int left = journal->j_free;
-
-        /* assert_spin_locked(&journal->j_state_lock); */
-
-        /*
-         * Be pessimistic here about the number of those free blocks which
-         * might be required for log descriptor control blocks.
-         */
-
-#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */
-
-        left -= MIN_LOG_RESERVED_BLOCKS;
-
-        if (left <= 0)
-                return 0;
-        left -= (left >> 3);
-        return left;
-}
-
-/*
  * Called with j_state_lock locked for writing.
  * Returns true if a transaction commit was started.
  */
@@ -564,20 +547,17 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid)
 }
 
 /*
- * Force and wait upon a commit if the calling process is not within
- * transaction.  This is used for forcing out undo-protected data which contains
- * bitmaps, when the fs is running out of space.
- *
- * We can only force the running transaction if we don't have an active handle;
- * otherwise, we will deadlock.
- *
- * Returns true if a transaction was started.
+ * Force and wait any uncommitted transactions.  We can only force the running
+ * transaction if we don't have an active handle, otherwise, we will deadlock.
+ * Returns: <0 in case of error,
+ *           0 if nothing to commit,
+ *           1 if transaction was successfully committed.
  */
-int jbd2_journal_force_commit_nested(journal_t *journal)
+static int __jbd2_journal_force_commit(journal_t *journal)
 {
         transaction_t *transaction = NULL;
         tid_t tid;
-        int need_to_start = 0;
+        int need_to_start = 0, ret = 0;
 
         read_lock(&journal->j_state_lock);
         if (journal->j_running_transaction && !current->journal_info) {
@@ -588,16 +568,53 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
                 transaction = journal->j_committing_transaction;
 
         if (!transaction) {
+                /* Nothing to commit */
                 read_unlock(&journal->j_state_lock);
-                return 0;       /* Nothing to retry */
+                return 0;
         }
-
         tid = transaction->t_tid;
         read_unlock(&journal->j_state_lock);
         if (need_to_start)
                 jbd2_log_start_commit(journal, tid);
-        jbd2_log_wait_commit(journal, tid);
-        return 1;
+        ret = jbd2_log_wait_commit(journal, tid);
+        if (!ret)
+                ret = 1;
+
+        return ret;
+}
+
+/**
+ * Force and wait upon a commit if the calling process is not within
+ * transaction.  This is used for forcing out undo-protected data which contains
+ * bitmaps, when the fs is running out of space.
+ *
+ * @journal: journal to force
+ * Returns true if progress was made.
+ */
+int jbd2_journal_force_commit_nested(journal_t *journal)
+{
+        int ret;
+
+        ret = __jbd2_journal_force_commit(journal);
+        return ret > 0;
+}
+
+/**
+ * int journal_force_commit() - force any uncommitted transactions
+ * @journal: journal to force
+ *
+ * Caller want unconditional commit. We can only force the running transaction
+ * if we don't have an active handle, otherwise, we will deadlock.
+ */
+int jbd2_journal_force_commit(journal_t *journal)
+{
+        int ret;
+
+        J_ASSERT(!current->journal_info);
+        ret = __jbd2_journal_force_commit(journal);
+        if (ret > 0)
+                ret = 0;
+        return ret;
 }
 
 /*
@@ -798,7 +815,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
  * But we don't bother doing that, so there will be coherency problems with
  * mmaps of blockdevs which hold live JBD-controlled filesystems.
  */
-struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
+struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
 {
         struct buffer_head *bh;
         unsigned long long blocknr;
@@ -817,7 +834,7 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
         set_buffer_uptodate(bh);
         unlock_buffer(bh);
         BUFFER_TRACE(bh, "return this buffer");
-        return jbd2_journal_add_journal_head(bh);
+        return bh;
 }
 
 /*
@@ -1062,11 +1079,10 @@ static journal_t * journal_init_common (void)
                 return NULL;
 
         init_waitqueue_head(&journal->j_wait_transaction_locked);
-        init_waitqueue_head(&journal->j_wait_logspace);
         init_waitqueue_head(&journal->j_wait_done_commit);
-        init_waitqueue_head(&journal->j_wait_checkpoint);
         init_waitqueue_head(&journal->j_wait_commit);
         init_waitqueue_head(&journal->j_wait_updates);
+        init_waitqueue_head(&journal->j_wait_reserved);
         mutex_init(&journal->j_barrier);
         mutex_init(&journal->j_checkpoint_mutex);
         spin_lock_init(&journal->j_revoke_lock);
@@ -1076,6 +1092,7 @@ static journal_t * journal_init_common (void)
         journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
         journal->j_min_batch_time = 0;
         journal->j_max_batch_time = 15000; /* 15ms */
+        atomic_set(&journal->j_reserved_credits, 0);
 
         /* The journal is marked for error until we succeed with recovery! */
         journal->j_flags = JBD2_ABORT;
@@ -1318,6 +1335,7 @@ static int journal_reset(journal_t *journal)
 static void jbd2_write_superblock(journal_t *journal, int write_op)
 {
         struct buffer_head *bh = journal->j_sb_buffer;
+        journal_superblock_t *sb = journal->j_superblock;
         int ret;
 
         trace_jbd2_write_superblock(journal, write_op);
@@ -1339,6 +1357,7 @@ static void jbd2_write_superblock(journal_t *journal, int write_op)
                 clear_buffer_write_io_error(bh);
                 set_buffer_uptodate(bh);
         }
+        jbd2_superblock_csum_set(journal, sb);
         get_bh(bh);
         bh->b_end_io = end_buffer_write_sync;
         ret = submit_bh(write_op, bh);
@@ -1435,7 +1454,6 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
         jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
                   journal->j_errno);
         sb->s_errno    = cpu_to_be32(journal->j_errno);
-        jbd2_superblock_csum_set(journal, sb);
         read_unlock(&journal->j_state_lock);
 
         jbd2_write_superblock(journal, WRITE_SYNC);
@@ -2325,13 +2343,13 @@ static struct journal_head *journal_alloc_journal_head(void)
 #ifdef CONFIG_JBD2_DEBUG
         atomic_inc(&nr_journal_heads);
 #endif
-        ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+        ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS);
         if (!ret) {
                 jbd_debug(1, "out of memory for journal_head\n");
                 pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__);
                 while (!ret) {
                         yield();
-                        ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+                        ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS);
                 }
         }
         return ret;
@@ -2393,10 +2411,8 @@ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
         struct journal_head *new_jh = NULL;
 
 repeat:
-        if (!buffer_jbd(bh)) {
+        if (!buffer_jbd(bh))
                 new_jh = journal_alloc_journal_head();
-                memset(new_jh, 0, sizeof(*new_jh));
-        }
 
         jbd_lock_bh_journal_head(bh);
         if (buffer_jbd(bh)) {