diff options
Diffstat (limited to 'fs/jbd')
| -rw-r--r-- | fs/jbd/commit.c | 30 | ||||
| -rw-r--r-- | fs/jbd/journal.c | 34 | ||||
| -rw-r--r-- | fs/jbd/revoke.c | 44 | ||||
| -rw-r--r-- | fs/jbd/transaction.c | 2 |
4 files changed, 77 insertions, 33 deletions
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 3fbffb1ea714..06560c520f49 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/mm.h> #include <linux/pagemap.h> +#include <linux/bio.h> /* * Default IO end handler for temporary BJ_IO buffer_heads. @@ -171,14 +172,15 @@ static int journal_write_commit_record(journal_t *journal, return (ret == -EIO); } -static void journal_do_submit_data(struct buffer_head **wbuf, int bufs) +static void journal_do_submit_data(struct buffer_head **wbuf, int bufs, + int write_op) { int i; for (i = 0; i < bufs; i++) { wbuf[i]->b_end_io = end_buffer_write_sync; /* We use-up our safety reference in submit_bh() */ - submit_bh(WRITE, wbuf[i]); + submit_bh(write_op, wbuf[i]); } } @@ -186,7 +188,8 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs) * Submit all the data buffers to disk */ static int journal_submit_data_buffers(journal_t *journal, - transaction_t *commit_transaction) + transaction_t *commit_transaction, + int write_op) { struct journal_head *jh; struct buffer_head *bh; @@ -225,7 +228,7 @@ write_out_data: BUFFER_TRACE(bh, "needs blocking lock"); spin_unlock(&journal->j_list_lock); /* Write out all data to prevent deadlocks */ - journal_do_submit_data(wbuf, bufs); + journal_do_submit_data(wbuf, bufs, write_op); bufs = 0; lock_buffer(bh); spin_lock(&journal->j_list_lock); @@ -256,7 +259,7 @@ write_out_data: jbd_unlock_bh_state(bh); if (bufs == journal->j_wbufsize) { spin_unlock(&journal->j_list_lock); - journal_do_submit_data(wbuf, bufs); + journal_do_submit_data(wbuf, bufs, write_op); bufs = 0; goto write_out_data; } @@ -286,7 +289,7 @@ write_out_data: } } spin_unlock(&journal->j_list_lock); - journal_do_submit_data(wbuf, bufs); + journal_do_submit_data(wbuf, bufs, write_op); return err; } @@ -315,6 +318,7 @@ void journal_commit_transaction(journal_t *journal) int first_tag = 0; int tag_flag; int i; + int write_op = WRITE; /* * First job: lock down the current transaction and wait for @@ -347,6 +351,13 @@ void journal_commit_transaction(journal_t *journal) spin_lock(&journal->j_state_lock); commit_transaction->t_state = T_LOCKED; + /* + * Use plugged writes here, since we want to submit several before + * we unplug the device. We don't do explicit unplugging in here, + * instead we rely on sync_buffer() doing the unplug for us. + */ + if (commit_transaction->t_synchronous_commit) + write_op = WRITE_SYNC_PLUG; spin_lock(&commit_transaction->t_handle_lock); while (commit_transaction->t_updates) { DEFINE_WAIT(wait); @@ -431,7 +442,8 @@ void journal_commit_transaction(journal_t *journal) * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ - err = journal_submit_data_buffers(journal, commit_transaction); + err = journal_submit_data_buffers(journal, commit_transaction, + write_op); /* * Wait for all previously submitted IO to complete. @@ -490,7 +502,7 @@ void journal_commit_transaction(journal_t *journal) err = 0; } - journal_write_revoke_records(journal, commit_transaction); + journal_write_revoke_records(journal, commit_transaction, write_op); /* * If we found any dirty or locked buffers, then we should have @@ -660,7 +672,7 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(WRITE, bh); + submit_bh(write_op, bh); } cond_resched(); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index e79c07812afa..737f7246a4b5 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -637,6 +637,8 @@ struct journal_head *journal_get_descriptor_buffer(journal_t *journal) 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); @@ -733,9 +735,7 @@ journal_t * journal_init_dev(struct block_device *bdev, if (!journal->j_wbuf) { printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", __func__); - kfree(journal); - journal = NULL; - goto out; + goto out_err; } journal->j_dev = bdev; journal->j_fs_dev = fs_dev; @@ -743,11 +743,19 @@ journal_t * journal_init_dev(struct block_device *bdev, journal->j_maxlen = len; 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; -out: + return journal; +out_err: + kfree(journal); + return NULL; } /** @@ -787,8 +795,7 @@ journal_t * journal_init_inode (struct inode *inode) if (!journal->j_wbuf) { printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", __func__); - kfree(journal); - return NULL; + goto out_err; } err = journal_bmap(journal, 0, &blocknr); @@ -796,16 +803,23 @@ journal_t * journal_init_inode (struct inode *inode) if (err) { printk(KERN_ERR "%s: Cannnot locate journal superblock\n", __func__); - kfree(journal); - return NULL; + 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; } /* diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c index c7bd649bbbdc..da6cd9bdaabc 100644 --- a/fs/jbd/revoke.c +++ b/fs/jbd/revoke.c @@ -55,6 +55,25 @@ * need do nothing. * RevokeValid set, Revoked set: * buffer has been revoked. + * + * Locking rules: + * We keep two hash tables of revoke records. One hashtable belongs to the + * running transaction (is pointed to by journal->j_revoke), the other one + * belongs to the committing transaction. Accesses to the second hash table + * happen only from the kjournald and no other thread touches this table. Also + * journal_switch_revoke_table() which switches which hashtable belongs to the + * running and which to the committing transaction is called only from + * kjournald. Therefore we need no locks when accessing the hashtable belonging + * to the committing transaction. + * + * All users operating on the hash table belonging to the running transaction + * have a handle to the transaction. Therefore they are safe from kjournald + * switching hash tables under them. For operations on the lists of entries in + * the hash table j_revoke_lock is used. + * + * Finally, also replay code uses the hash tables but at this moment noone else + * can touch them (filesystem isn't mounted yet) and hence no locking is + * needed. */ #ifndef __KERNEL__ @@ -67,6 +86,7 @@ #include <linux/slab.h> #include <linux/list.h> #include <linux/init.h> +#include <linux/bio.h> #endif #include <linux/log2.h> @@ -99,8 +119,8 @@ struct jbd_revoke_table_s #ifdef __KERNEL__ static void write_one_revoke_record(journal_t *, transaction_t *, struct journal_head **, int *, - struct jbd_revoke_record_s *); -static void flush_descriptor(journal_t *, struct journal_head *, int); + struct jbd_revoke_record_s *, int); +static void flush_descriptor(journal_t *, struct journal_head *, int, int); #endif /* Utility functions to maintain the revoke table */ @@ -402,8 +422,6 @@ int journal_revoke(handle_t *handle, unsigned long blocknr, * the second time we would still have a pending revoke to cancel. So, * do not trust the Revoked bit on buffers unless RevokeValid is also * set. - * - * The caller must have the journal locked. */ int journal_cancel_revoke(handle_t *handle, struct journal_head *jh) { @@ -481,12 +499,9 @@ void journal_switch_revoke_table(journal_t *journal) /* * Write revoke records to the journal for all entries in the current * revoke hash, deleting the entries as we go. - * - * Called with the journal lock held. */ - void journal_write_revoke_records(journal_t *journal, - transaction_t *transaction) + transaction_t *transaction, int write_op) { struct journal_head *descriptor; struct jbd_revoke_record_s *record; @@ -510,14 +525,14 @@ void journal_write_revoke_records(journal_t *journal, hash_list->next; write_one_revoke_record(journal, transaction, &descriptor, &offset, - record); + record, write_op); count++; list_del(&record->hash); kmem_cache_free(revoke_record_cache, record); } } if (descriptor) - flush_descriptor(journal, descriptor, offset); + flush_descriptor(journal, descriptor, offset, write_op); jbd_debug(1, "Wrote %d revoke records\n", count); } @@ -530,7 +545,8 @@ static void write_one_revoke_record(journal_t *journal, transaction_t *transaction, struct journal_head **descriptorp, int *offsetp, - struct jbd_revoke_record_s *record) + struct jbd_revoke_record_s *record, + int write_op) { struct journal_head *descriptor; int offset; @@ -549,7 +565,7 @@ static void write_one_revoke_record(journal_t *journal, /* Make sure we have a descriptor with space left for the record */ if (descriptor) { if (offset == journal->j_blocksize) { - flush_descriptor(journal, descriptor, offset); + flush_descriptor(journal, descriptor, offset, write_op); descriptor = NULL; } } @@ -586,7 +602,7 @@ static void write_one_revoke_record(journal_t *journal, static void flush_descriptor(journal_t *journal, struct journal_head *descriptor, - int offset) + int offset, int write_op) { journal_revoke_header_t *header; struct buffer_head *bh = jh2bh(descriptor); @@ -601,7 +617,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(bh); BUFFER_TRACE(bh, "write"); set_buffer_dirty(bh); - ll_rw_block(SWRITE, 1, &bh); + ll_rw_block((write_op == WRITE) ? SWRITE : SWRITE_SYNC_PLUG, 1, &bh); } #endif diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index e6a117431277..ed886e6db399 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1440,6 +1440,8 @@ int journal_stop(handle_t *handle) } } + if (handle->h_sync) + transaction->t_synchronous_commit = 1; current->journal_info = NULL; spin_lock(&journal->j_state_lock); spin_lock(&transaction->t_handle_lock); |