diff options
Diffstat (limited to 'fs/jbd2/commit.c')
-rw-r--r-- | fs/jbd2/commit.c | 158 |
1 files changed, 135 insertions, 23 deletions
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index eef6979821a..af5280fb579 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -28,7 +28,6 @@ #include <linux/blkdev.h> #include <linux/bitops.h> #include <trace/events/jbd2.h> -#include <asm/system.h> /* * Default IO end handler for temporary BJ_IO buffer_heads. @@ -86,6 +85,24 @@ nope: __brelse(bh); } +static void jbd2_commit_block_csum_set(journal_t *j, + struct journal_head *descriptor) +{ + struct commit_header *h; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + h = (struct commit_header *)(jh2bh(descriptor)->b_data); + h->h_chksum_type = 0; + h->h_chksum_size = 0; + h->h_chksum[0] = 0; + csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, + j->j_blocksize); + h->h_chksum[0] = cpu_to_be32(csum); +} + /* * Done it all: now submit the commit record. We should have * cleaned up our previous buffers by now, so if we are in abort @@ -129,6 +146,7 @@ static int journal_submit_commit_record(journal_t *journal, tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); } + jbd2_commit_block_csum_set(journal, descriptor); JBUFFER_TRACE(descriptor, "submit commit block"); lock_buffer(bh); @@ -286,10 +304,10 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) char *addr; __u32 checksum; - addr = kmap_atomic(page, KM_USER0); + addr = kmap_atomic(page); checksum = crc32_be(crc32_sum, (void *)(addr + offset_in_page(bh->b_data)), bh->b_size); - kunmap_atomic(addr, KM_USER0); + kunmap_atomic(addr); return checksum; } @@ -302,6 +320,44 @@ static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } +static void jbd2_descr_block_csum_set(journal_t *j, + struct journal_head *descriptor) +{ + struct jbd2_journal_block_tail *tail; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + tail = (struct jbd2_journal_block_tail *) + (jh2bh(descriptor)->b_data + j->j_blocksize - + sizeof(struct jbd2_journal_block_tail)); + tail->t_checksum = 0; + csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, + j->j_blocksize); + tail->t_checksum = cpu_to_be32(csum); +} + +static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, + struct buffer_head *bh, __u32 sequence) +{ + struct page *page = bh->b_page; + __u8 *addr; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + sequence = cpu_to_be32(sequence); + addr = kmap_atomic(page); + csum = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, + sizeof(sequence)); + csum = jbd2_chksum(j, csum, addr + offset_in_page(bh->b_data), + bh->b_size); + kunmap_atomic(addr); + + tag->t_checksum = cpu_to_be32(csum); +} /* * jbd2_journal_commit_transaction * @@ -331,6 +387,14 @@ void jbd2_journal_commit_transaction(journal_t *journal) struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; struct blk_plug plug; + /* Tail of the journal */ + unsigned long first_block; + tid_t first_tid; + int update_tail; + int csum_size = 0; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + csum_size = sizeof(struct jbd2_journal_block_tail); /* * First job: lock down the current transaction and wait for @@ -340,7 +404,18 @@ void jbd2_journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { jbd_debug(3, "super block updated\n"); - jbd2_journal_update_superblock(journal, 1); + mutex_lock(&journal->j_checkpoint_mutex); + /* + * We hold j_checkpoint_mutex so tail cannot change under us. + * We don't need any special data guarantees for writing sb + * since journal is empty and it is ok for write to be + * flushed only with transaction commit. + */ + jbd2_journal_update_sb_log_tail(journal, + journal->j_tail_sequence, + journal->j_tail, + WRITE_SYNC); + mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd_debug(3, "superblock not updated\n"); } @@ -352,7 +427,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) J_ASSERT(commit_transaction->t_state == T_RUNNING); trace_jbd2_start_commit(journal, commit_transaction); - jbd_debug(1, "JBD: starting commit of transaction %d\n", + jbd_debug(1, "JBD2: starting commit of transaction %d\n", commit_transaction->t_tid); write_lock(&journal->j_state_lock); @@ -427,7 +502,13 @@ void jbd2_journal_commit_transaction(journal_t *journal) __jbd2_journal_clean_checkpoint_list(journal); spin_unlock(&journal->j_list_lock); - jbd_debug (3, "JBD: commit phase 1\n"); + jbd_debug(3, "JBD2: commit phase 1\n"); + + /* + * Clear revoked flag to reflect there is no revoked buffers + * in the next transaction which is going to be started. + */ + jbd2_clear_buffer_revoked_flags(journal); /* * Switch to a new revoke table. @@ -447,7 +528,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) wake_up(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock); - jbd_debug (3, "JBD: commit phase 2\n"); + jbd_debug(3, "JBD2: commit phase 2\n"); /* * Now start flushing things to disk, in the order they appear @@ -462,7 +543,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) WRITE_SYNC); blk_finish_plug(&plug); - jbd_debug(3, "JBD: commit phase 2\n"); + jbd_debug(3, "JBD2: commit phase 2\n"); /* * Way to go: we have now written out all of the data for a @@ -522,7 +603,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) J_ASSERT (bufs == 0); - jbd_debug(4, "JBD: get descriptor\n"); + jbd_debug(4, "JBD2: get descriptor\n"); descriptor = jbd2_journal_get_descriptor_buffer(journal); if (!descriptor) { @@ -531,7 +612,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) } bh = jh2bh(descriptor); - jbd_debug(4, "JBD: got buffer %llu (%p)\n", + jbd_debug(4, "JBD2: got buffer %llu (%p)\n", (unsigned long long)bh->b_blocknr, bh->b_data); header = (journal_header_t *)&bh->b_data[0]; header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); @@ -607,7 +688,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag = (journal_block_tag_t *) tagp; write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); - tag->t_flags = cpu_to_be32(tag_flag); + tag->t_flags = cpu_to_be16(tag_flag); + jbd2_block_tag_csum_set(journal, tag, jh2bh(new_jh), + commit_transaction->t_tid); tagp += tag_bytes; space_left -= tag_bytes; @@ -623,16 +706,17 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (bufs == journal->j_wbufsize || commit_transaction->t_buffers == NULL || - space_left < tag_bytes + 16) { + space_left < tag_bytes + 16 + csum_size) { - jbd_debug(4, "JBD: Submit %d IOs\n", bufs); + jbd_debug(4, "JBD2: Submit %d IOs\n", bufs); /* Write an end-of-descriptor marker before submitting the IOs. "tag" still points to the last tag we set up. */ - tag->t_flags |= cpu_to_be32(JBD2_FLAG_LAST_TAG); + tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG); + jbd2_descr_block_csum_set(journal, descriptor); start_journal_io: for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; @@ -671,10 +755,30 @@ start_journal_io: err = 0; } + /* + * Get current oldest transaction in the log before we issue flush + * to the filesystem device. After the flush we can be sure that + * blocks of all older transactions are checkpointed to persistent + * storage and we will be safe to update journal start in the + * superblock with the numbers we get here. + */ + update_tail = + jbd2_journal_get_log_tail(journal, &first_tid, &first_block); + write_lock(&journal->j_state_lock); + if (update_tail) { + long freed = first_block - journal->j_tail; + + if (first_block < journal->j_tail) + freed += journal->j_last - journal->j_first; + /* Update tail only if we free significant amount of space */ + if (freed < journal->j_maxlen / 4) + update_tail = 0; + } J_ASSERT(commit_transaction->t_state == T_COMMIT); commit_transaction->t_state = T_COMMIT_DFLUSH; write_unlock(&journal->j_state_lock); + /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue @@ -683,7 +787,7 @@ start_journal_io: if (commit_transaction->t_need_data_flush && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -707,7 +811,7 @@ start_journal_io: so we incur less scheduling load. */ - jbd_debug(3, "JBD: commit phase 3\n"); + jbd_debug(3, "JBD2: commit phase 3\n"); /* * akpm: these are BJ_IO, and j_list_lock is not needed. @@ -771,7 +875,7 @@ wait_for_iobuf: J_ASSERT (commit_transaction->t_shadow_list == NULL); - jbd_debug(3, "JBD: commit phase 4\n"); + jbd_debug(3, "JBD2: commit phase 4\n"); /* Here we wait for the revoke record and descriptor record buffers */ wait_for_ctlbuf: @@ -801,7 +905,7 @@ wait_for_iobuf: if (err) jbd2_journal_abort(journal, err); - jbd_debug(3, "JBD: commit phase 5\n"); + jbd_debug(3, "JBD2: commit phase 5\n"); write_lock(&journal->j_state_lock); J_ASSERT(commit_transaction->t_state == T_COMMIT_DFLUSH); commit_transaction->t_state = T_COMMIT_JFLUSH; @@ -819,18 +923,26 @@ wait_for_iobuf: if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && journal->j_flags & JBD2_BARRIER) { - blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); } if (err) jbd2_journal_abort(journal, err); + /* + * Now disk caches for filesystem device are flushed so we are safe to + * erase checkpointed transactions from the log by updating journal + * superblock. + */ + if (update_tail) + jbd2_update_log_tail(journal, first_tid, first_block); + /* End of a transaction! Finally, we can do checkpoint processing: any buffers committed as a result of this transaction can be removed from any checkpoint list it was on before. */ - jbd_debug(3, "JBD: commit phase 6\n"); + jbd_debug(3, "JBD2: commit phase 6\n"); J_ASSERT(list_empty(&commit_transaction->t_inode_list)); J_ASSERT(commit_transaction->t_buffers == NULL); @@ -964,7 +1076,7 @@ restart_loop: /* Done with this transaction! */ - jbd_debug(3, "JBD: commit phase 7\n"); + jbd_debug(3, "JBD2: commit phase 7\n"); J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH); @@ -1039,10 +1151,10 @@ restart_loop: journal->j_commit_callback(journal, commit_transaction); trace_jbd2_end_commit(journal, commit_transaction); - jbd_debug(1, "JBD: commit %d complete, head %d\n", + jbd_debug(1, "JBD2: commit %d complete, head %d\n", journal->j_commit_sequence, journal->j_tail_sequence); if (to_free) - kfree(commit_transaction); + jbd2_journal_free_transaction(commit_transaction); wake_up(&journal->j_wait_done_commit); } |