diff options
Diffstat (limited to 'fs/jbd2')
| -rw-r--r-- | fs/jbd2/Kconfig | 36 | ||||
| -rw-r--r-- | fs/jbd2/Makefile | 8 | ||||
| -rw-r--r-- | fs/jbd2/checkpoint.c | 729 | ||||
| -rw-r--r-- | fs/jbd2/commit.c | 1201 | ||||
| -rw-r--r-- | fs/jbd2/journal.c | 3204 | ||||
| -rw-r--r-- | fs/jbd2/recovery.c | 938 | ||||
| -rw-r--r-- | fs/jbd2/revoke.c | 743 | ||||
| -rw-r--r-- | fs/jbd2/transaction.c | 2786 |
8 files changed, 9645 insertions, 0 deletions
diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig new file mode 100644 index 000000000..4ad2c67f9 --- /dev/null +++ b/fs/jbd2/Kconfig @@ -0,0 +1,36 @@ +# SPDX-License-Identifier: GPL-2.0-only +config JBD2 + tristate + select CRC32 + select CRYPTO + select CRYPTO_CRC32C + help + This is a generic journaling layer for block devices that support + both 32-bit and 64-bit block numbers. It is currently used by + the ext4 and OCFS2 filesystems, but it could also be used to add + journal support to other file systems or block devices such + as RAID or LVM. + + If you are using ext4 or OCFS2, you need to say Y here. + If you are not using ext4 or OCFS2 then you will + probably want to say N. + + To compile this device as a module, choose M here. The module will be + called jbd2. If you are compiling ext4 or OCFS2 into the kernel, + you cannot compile this code as a module. + +config JBD2_DEBUG + bool "JBD2 (ext4) debugging support" + depends on JBD2 + help + If you are using the ext4 journaled file system (or + potentially any other filesystem/device using JBD2), this option + allows you to enable debugging output while the system is running, + in order to help track down any problems you are having. + By default, the debugging output will be turned off. + + If you select Y here, then you will be able to turn on debugging + with "echo N > /sys/module/jbd2/parameters/jbd2_debug", where N is a + number between 1 and 5. The higher the number, the more debugging + output is generated. To turn debugging off again, do + "echo 0 > /sys/module/jbd2/parameters/jbd2_debug". diff --git a/fs/jbd2/Makefile b/fs/jbd2/Makefile new file mode 100644 index 000000000..126b4da6c --- /dev/null +++ b/fs/jbd2/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the linux journaling routines. +# + +obj-$(CONFIG_JBD2) += jbd2.o + +jbd2-objs := transaction.o commit.o recovery.o checkpoint.o revoke.o journal.o diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c new file mode 100644 index 000000000..f033ac807 --- /dev/null +++ b/fs/jbd2/checkpoint.c @@ -0,0 +1,729 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/checkpoint.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1999 Red Hat Software --- All Rights Reserved + * + * Checkpoint routines for the generic filesystem journaling code. + * Part of the ext2fs journaling system. + * + * Checkpointing is the process of ensuring that a section of the log is + * committed fully to disk, so that that portion of the log can be + * reused. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <trace/events/jbd2.h> + +/* + * Unlink a buffer from a transaction checkpoint list. + * + * Called with j_list_lock held. + */ +static inline void __buffer_unlink(struct journal_head *jh) +{ + transaction_t *transaction = jh->b_cp_transaction; + + jh->b_cpnext->b_cpprev = jh->b_cpprev; + jh->b_cpprev->b_cpnext = jh->b_cpnext; + if (transaction->t_checkpoint_list == jh) { + transaction->t_checkpoint_list = jh->b_cpnext; + if (transaction->t_checkpoint_list == jh) + transaction->t_checkpoint_list = NULL; + } +} + +/* + * Check a checkpoint buffer could be release or not. + * + * Requires j_list_lock + */ +static inline bool __cp_buffer_busy(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + return (jh->b_transaction || buffer_locked(bh) || buffer_dirty(bh)); +} + +/* + * __jbd2_log_wait_for_space: wait until there is space in the journal. + * + * Called under j-state_lock *only*. It will be unlocked if we have to wait + * for a checkpoint to free up some space in the log. + */ +void __jbd2_log_wait_for_space(journal_t *journal) +__acquires(&journal->j_state_lock) +__releases(&journal->j_state_lock) +{ + int nblocks, space_left; + /* assert_spin_locked(&journal->j_state_lock); */ + + nblocks = journal->j_max_transaction_buffers; + while (jbd2_log_space_left(journal) < nblocks) { + write_unlock(&journal->j_state_lock); + mutex_lock_io(&journal->j_checkpoint_mutex); + + /* + * Test again, another process may have checkpointed while we + * were waiting for the checkpoint lock. If there are no + * transactions ready to be checkpointed, try to recover + * journal space by calling cleanup_journal_tail(), and if + * that doesn't work, by waiting for the currently committing + * transaction to complete. If there is absolutely no way + * to make progress, this is either a BUG or corrupted + * filesystem, so abort the journal and leave a stack + * trace for forensic evidence. + */ + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) { + mutex_unlock(&journal->j_checkpoint_mutex); + return; + } + spin_lock(&journal->j_list_lock); + space_left = jbd2_log_space_left(journal); + if (space_left < nblocks) { + int chkpt = journal->j_checkpoint_transactions != NULL; + tid_t tid = 0; + + if (journal->j_committing_transaction) + tid = journal->j_committing_transaction->t_tid; + spin_unlock(&journal->j_list_lock); + write_unlock(&journal->j_state_lock); + if (chkpt) { + jbd2_log_do_checkpoint(journal); + } else if (jbd2_cleanup_journal_tail(journal) == 0) { + /* We were able to recover space; yay! */ + ; + } else if (tid) { + /* + * jbd2_journal_commit_transaction() may want + * to take the checkpoint_mutex if JBD2_FLUSHED + * is set. So we need to temporarily drop it. + */ + mutex_unlock(&journal->j_checkpoint_mutex); + jbd2_log_wait_commit(journal, tid); + write_lock(&journal->j_state_lock); + continue; + } else { + printk(KERN_ERR "%s: needed %d blocks and " + "only had %d space available\n", + __func__, nblocks, space_left); + printk(KERN_ERR "%s: no way to get more " + "journal space in %s\n", __func__, + journal->j_devname); + WARN_ON(1); + jbd2_journal_abort(journal, -EIO); + } + write_lock(&journal->j_state_lock); + } else { + spin_unlock(&journal->j_list_lock); + } + mutex_unlock(&journal->j_checkpoint_mutex); + } +} + +static void +__flush_batch(journal_t *journal, int *batch_count) +{ + int i; + struct blk_plug plug; + + blk_start_plug(&plug); + for (i = 0; i < *batch_count; i++) + write_dirty_buffer(journal->j_chkpt_bhs[i], REQ_SYNC); + blk_finish_plug(&plug); + + for (i = 0; i < *batch_count; i++) { + struct buffer_head *bh = journal->j_chkpt_bhs[i]; + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + journal->j_chkpt_bhs[i] = NULL; + } + *batch_count = 0; +} + +/* + * Perform an actual checkpoint. We take the first transaction on the + * list of transactions to be checkpointed and send all its buffers + * to disk. We submit larger chunks of data at once. + * + * The journal should be locked before calling this function. + * Called with j_checkpoint_mutex held. + */ +int jbd2_log_do_checkpoint(journal_t *journal) +{ + struct journal_head *jh; + struct buffer_head *bh; + transaction_t *transaction; + tid_t this_tid; + int result, batch_count = 0; + + jbd2_debug(1, "Start checkpoint\n"); + + /* + * First thing: if there are any transactions in the log which + * don't need checkpointing, just eliminate them from the + * journal straight away. + */ + result = jbd2_cleanup_journal_tail(journal); + trace_jbd2_checkpoint(journal, result); + jbd2_debug(1, "cleanup_journal_tail returned %d\n", result); + if (result <= 0) + return result; + + /* + * OK, we need to start writing disk blocks. Take one transaction + * and write it. + */ + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) + goto out; + transaction = journal->j_checkpoint_transactions; + if (transaction->t_chp_stats.cs_chp_time == 0) + transaction->t_chp_stats.cs_chp_time = jiffies; + this_tid = transaction->t_tid; +restart: + /* + * If someone cleaned up this transaction while we slept, we're + * done (maybe it's a new transaction, but it fell at the same + * address). + */ + if (journal->j_checkpoint_transactions != transaction || + transaction->t_tid != this_tid) + goto out; + + /* checkpoint all of the transaction's buffers */ + while (transaction->t_checkpoint_list) { + jh = transaction->t_checkpoint_list; + bh = jh2bh(jh); + + if (jh->b_transaction != NULL) { + transaction_t *t = jh->b_transaction; + tid_t tid = t->t_tid; + + transaction->t_chp_stats.cs_forced_to_close++; + spin_unlock(&journal->j_list_lock); + if (unlikely(journal->j_flags & JBD2_UNMOUNT)) + /* + * The journal thread is dead; so + * starting and waiting for a commit + * to finish will cause us to wait for + * a _very_ long time. + */ + printk(KERN_ERR + "JBD2: %s: Waiting for Godot: block %llu\n", + journal->j_devname, (unsigned long long) bh->b_blocknr); + + if (batch_count) + __flush_batch(journal, &batch_count); + jbd2_log_start_commit(journal, tid); + /* + * jbd2_journal_commit_transaction() may want + * to take the checkpoint_mutex if JBD2_FLUSHED + * is set, jbd2_update_log_tail() called by + * jbd2_journal_commit_transaction() may also take + * checkpoint_mutex. So we need to temporarily + * drop it. + */ + mutex_unlock(&journal->j_checkpoint_mutex); + jbd2_log_wait_commit(journal, tid); + mutex_lock_io(&journal->j_checkpoint_mutex); + spin_lock(&journal->j_list_lock); + goto restart; + } + if (!trylock_buffer(bh)) { + /* + * The buffer is locked, it may be writing back, or + * flushing out in the last couple of cycles, or + * re-adding into a new transaction, need to check + * it again until it's unlocked. + */ + get_bh(bh); + spin_unlock(&journal->j_list_lock); + wait_on_buffer(bh); + /* the journal_head may have gone by now */ + BUFFER_TRACE(bh, "brelse"); + __brelse(bh); + goto retry; + } else if (!buffer_dirty(bh)) { + unlock_buffer(bh); + BUFFER_TRACE(bh, "remove from checkpoint"); + /* + * If the transaction was released or the checkpoint + * list was empty, we're done. + */ + if (__jbd2_journal_remove_checkpoint(jh) || + !transaction->t_checkpoint_list) + goto out; + } else { + unlock_buffer(bh); + /* + * We are about to write the buffer, it could be + * raced by some other transaction shrink or buffer + * re-log logic once we release the j_list_lock, + * leave it on the checkpoint list and check status + * again to make sure it's clean. + */ + BUFFER_TRACE(bh, "queue"); + get_bh(bh); + J_ASSERT_BH(bh, !buffer_jwrite(bh)); + journal->j_chkpt_bhs[batch_count++] = bh; + transaction->t_chp_stats.cs_written++; + transaction->t_checkpoint_list = jh->b_cpnext; + } + + if ((batch_count == JBD2_NR_BATCH) || + need_resched() || spin_needbreak(&journal->j_list_lock) || + jh2bh(transaction->t_checkpoint_list) == journal->j_chkpt_bhs[0]) + goto unlock_and_flush; + } + + if (batch_count) { + unlock_and_flush: + spin_unlock(&journal->j_list_lock); + retry: + if (batch_count) + __flush_batch(journal, &batch_count); + spin_lock(&journal->j_list_lock); + goto restart; + } + +out: + spin_unlock(&journal->j_list_lock); + result = jbd2_cleanup_journal_tail(journal); + + return (result < 0) ? result : 0; +} + +/* + * Check the list of checkpoint transactions for the journal to see if + * we have already got rid of any since the last update of the log tail + * in the journal superblock. If so, we can instantly roll the + * superblock forward to remove those transactions from the log. + * + * Return <0 on error, 0 on success, 1 if there was nothing to clean up. + * + * Called with the journal lock held. + * + * This is the only part of the journaling code which really needs to be + * aware of transaction aborts. Checkpointing involves writing to the + * main filesystem area rather than to the journal, so it can proceed + * even in abort state, but we must not update the super block if + * checkpointing may have failed. Otherwise, we would lose some metadata + * buffers which should be written-back to the filesystem. + */ + +int jbd2_cleanup_journal_tail(journal_t *journal) +{ + tid_t first_tid; + unsigned long blocknr; + + if (is_journal_aborted(journal)) + return -EIO; + + if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr)) + return 1; + J_ASSERT(blocknr != 0); + + /* + * We need to make sure that any blocks that were recently written out + * --- perhaps by jbd2_log_do_checkpoint() --- are flushed out before + * we drop the transactions from the journal. It's unlikely this will + * be necessary, especially with an appropriately sized journal, but we + * need this to guarantee correctness. Fortunately + * jbd2_cleanup_journal_tail() doesn't get called all that often. + */ + if (journal->j_flags & JBD2_BARRIER) + blkdev_issue_flush(journal->j_fs_dev); + + return __jbd2_update_log_tail(journal, first_tid, blocknr); +} + + +/* Checkpoint list management */ + +enum shrink_type {SHRINK_DESTROY, SHRINK_BUSY_STOP, SHRINK_BUSY_SKIP}; + +/* + * journal_shrink_one_cp_list + * + * Find all the written-back checkpoint buffers in the given list + * and try to release them. If the whole transaction is released, set + * the 'released' parameter. Return the number of released checkpointed + * buffers. + * + * Called with j_list_lock held. + */ +static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, + enum shrink_type type, + bool *released) +{ + struct journal_head *last_jh; + struct journal_head *next_jh = jh; + unsigned long nr_freed = 0; + int ret; + + *released = false; + if (!jh) + return 0; + + last_jh = jh->b_cpprev; + do { + jh = next_jh; + next_jh = jh->b_cpnext; + + if (type == SHRINK_DESTROY) { + ret = __jbd2_journal_remove_checkpoint(jh); + } else { + ret = jbd2_journal_try_remove_checkpoint(jh); + if (ret < 0) { + if (type == SHRINK_BUSY_SKIP) + continue; + break; + } + } + + nr_freed++; + if (ret) { + *released = true; + break; + } + + if (need_resched()) + break; + } while (jh != last_jh); + + return nr_freed; +} + +/* + * jbd2_journal_shrink_checkpoint_list + * + * Find 'nr_to_scan' written-back checkpoint buffers in the journal + * and try to release them. Return the number of released checkpointed + * buffers. + * + * Called with j_list_lock held. + */ +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, + unsigned long *nr_to_scan) +{ + transaction_t *transaction, *last_transaction, *next_transaction; + bool __maybe_unused released; + tid_t first_tid = 0, last_tid = 0, next_tid = 0; + tid_t tid = 0; + unsigned long nr_freed = 0; + unsigned long freed; + +again: + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) { + spin_unlock(&journal->j_list_lock); + goto out; + } + + /* + * Get next shrink transaction, resume previous scan or start + * over again. If some others do checkpoint and drop transaction + * from the checkpoint list, we ignore saved j_shrink_transaction + * and start over unconditionally. + */ + if (journal->j_shrink_transaction) + transaction = journal->j_shrink_transaction; + else + transaction = journal->j_checkpoint_transactions; + + if (!first_tid) + first_tid = transaction->t_tid; + last_transaction = journal->j_checkpoint_transactions->t_cpprev; + next_transaction = transaction; + last_tid = last_transaction->t_tid; + do { + transaction = next_transaction; + next_transaction = transaction->t_cpnext; + tid = transaction->t_tid; + + freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, + SHRINK_BUSY_SKIP, &released); + nr_freed += freed; + (*nr_to_scan) -= min(*nr_to_scan, freed); + if (*nr_to_scan == 0) + break; + if (need_resched() || spin_needbreak(&journal->j_list_lock)) + break; + } while (transaction != last_transaction); + + if (transaction != last_transaction) { + journal->j_shrink_transaction = next_transaction; + next_tid = next_transaction->t_tid; + } else { + journal->j_shrink_transaction = NULL; + next_tid = 0; + } + + spin_unlock(&journal->j_list_lock); + cond_resched(); + + if (*nr_to_scan && next_tid) + goto again; +out: + trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid, + nr_freed, next_tid); + + return nr_freed; +} + +/* + * journal_clean_checkpoint_list + * + * Find all the written-back checkpoint buffers in the journal and release them. + * If 'destroy' is set, release all buffers unconditionally. + * + * Called with j_list_lock held. + */ +void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy) +{ + transaction_t *transaction, *last_transaction, *next_transaction; + enum shrink_type type; + bool released; + + transaction = journal->j_checkpoint_transactions; + if (!transaction) + return; + + type = destroy ? SHRINK_DESTROY : SHRINK_BUSY_STOP; + last_transaction = transaction->t_cpprev; + next_transaction = transaction; + do { + transaction = next_transaction; + next_transaction = transaction->t_cpnext; + journal_shrink_one_cp_list(transaction->t_checkpoint_list, + type, &released); + /* + * This function only frees up some memory if possible so we + * dont have an obligation to finish processing. Bail out if + * preemption requested: + */ + if (need_resched()) + return; + /* + * Stop scanning if we couldn't free the transaction. This + * avoids pointless scanning of transactions which still + * weren't checkpointed. + */ + if (!released) + return; + } while (transaction != last_transaction); +} + +/* + * Remove buffers from all checkpoint lists as journal is aborted and we just + * need to free memory + */ +void jbd2_journal_destroy_checkpoint(journal_t *journal) +{ + /* + * We loop because __jbd2_journal_clean_checkpoint_list() may abort + * early due to a need of rescheduling. + */ + while (1) { + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) { + spin_unlock(&journal->j_list_lock); + break; + } + __jbd2_journal_clean_checkpoint_list(journal, true); + spin_unlock(&journal->j_list_lock); + cond_resched(); + } +} + +/* + * journal_remove_checkpoint: called after a buffer has been committed + * to disk (either by being write-back flushed to disk, or being + * committed to the log). + * + * We cannot safely clean a transaction out of the log until all of the + * buffer updates committed in that transaction have safely been stored + * elsewhere on disk. To achieve this, all of the buffers in a + * transaction need to be maintained on the transaction's checkpoint + * lists until they have been rewritten, at which point this function is + * called to remove the buffer from the existing transaction's + * checkpoint lists. + * + * The function returns 1 if it frees the transaction, 0 otherwise. + * The function can free jh and bh. + * + * This function is called with j_list_lock held. + */ +int __jbd2_journal_remove_checkpoint(struct journal_head *jh) +{ + struct transaction_chp_stats_s *stats; + transaction_t *transaction; + journal_t *journal; + struct buffer_head *bh = jh2bh(jh); + + JBUFFER_TRACE(jh, "entry"); + + transaction = jh->b_cp_transaction; + if (!transaction) { + JBUFFER_TRACE(jh, "not on transaction"); + return 0; + } + journal = transaction->t_journal; + + JBUFFER_TRACE(jh, "removing from transaction"); + + /* + * If we have failed to write the buffer out to disk, the filesystem + * may become inconsistent. We cannot abort the journal here since + * we hold j_list_lock and we have to be careful about races with + * jbd2_journal_destroy(). So mark the writeback IO error in the + * journal here and we abort the journal later from a better context. + */ + if (buffer_write_io_error(bh)) + set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags); + + __buffer_unlink(jh); + jh->b_cp_transaction = NULL; + percpu_counter_dec(&journal->j_checkpoint_jh_count); + jbd2_journal_put_journal_head(jh); + + /* Is this transaction empty? */ + if (transaction->t_checkpoint_list) + return 0; + + /* + * There is one special case to worry about: if we have just pulled the + * buffer off a running or committing transaction's checkpoing list, + * then even if the checkpoint list is empty, the transaction obviously + * cannot be dropped! + * + * The locking here around t_state is a bit sleazy. + * See the comment at the end of jbd2_journal_commit_transaction(). + */ + if (transaction->t_state != T_FINISHED) + return 0; + + /* + * OK, that was the last buffer for the transaction, we can now + * safely remove this transaction from the log. + */ + stats = &transaction->t_chp_stats; + if (stats->cs_chp_time) + stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time, + jiffies); + trace_jbd2_checkpoint_stats(journal->j_fs_dev->bd_dev, + transaction->t_tid, stats); + + __jbd2_journal_drop_transaction(journal, transaction); + jbd2_journal_free_transaction(transaction); + return 1; +} + +/* + * Check the checkpoint buffer and try to remove it from the checkpoint + * list if it's clean. Returns -EBUSY if it is not clean, returns 1 if + * it frees the transaction, 0 otherwise. + * + * This function is called with j_list_lock held. + */ +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + if (jh->b_transaction) + return -EBUSY; + if (!trylock_buffer(bh)) + return -EBUSY; + if (buffer_dirty(bh)) { + unlock_buffer(bh); + return -EBUSY; + } + unlock_buffer(bh); + + /* + * Buffer is clean and the IO has finished (we held the buffer + * lock) so the checkpoint is done. We can safely remove the + * buffer from this transaction. + */ + JBUFFER_TRACE(jh, "remove from checkpoint list"); + return __jbd2_journal_remove_checkpoint(jh); +} + +/* + * journal_insert_checkpoint: put a committed buffer onto a checkpoint + * list so that we know when it is safe to clean the transaction out of + * the log. + * + * Called with the journal locked. + * Called with j_list_lock held. + */ +void __jbd2_journal_insert_checkpoint(struct journal_head *jh, + transaction_t *transaction) +{ + JBUFFER_TRACE(jh, "entry"); + J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh))); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + + /* Get reference for checkpointing transaction */ + jbd2_journal_grab_journal_head(jh2bh(jh)); + jh->b_cp_transaction = transaction; + + if (!transaction->t_checkpoint_list) { + jh->b_cpnext = jh->b_cpprev = jh; + } else { + jh->b_cpnext = transaction->t_checkpoint_list; + jh->b_cpprev = transaction->t_checkpoint_list->b_cpprev; + jh->b_cpprev->b_cpnext = jh; + jh->b_cpnext->b_cpprev = jh; + } + transaction->t_checkpoint_list = jh; + percpu_counter_inc(&transaction->t_journal->j_checkpoint_jh_count); +} + +/* + * We've finished with this transaction structure: adios... + * + * The transaction must have no links except for the checkpoint by this + * point. + * + * Called with the journal locked. + * Called with j_list_lock held. + */ + +void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transaction) +{ + assert_spin_locked(&journal->j_list_lock); + + journal->j_shrink_transaction = NULL; + if (transaction->t_cpnext) { + transaction->t_cpnext->t_cpprev = transaction->t_cpprev; + transaction->t_cpprev->t_cpnext = transaction->t_cpnext; + if (journal->j_checkpoint_transactions == transaction) + journal->j_checkpoint_transactions = + transaction->t_cpnext; + if (journal->j_checkpoint_transactions == transaction) + journal->j_checkpoint_transactions = NULL; + } + + J_ASSERT(transaction->t_state == T_FINISHED); + J_ASSERT(transaction->t_buffers == NULL); + J_ASSERT(transaction->t_forget == NULL); + J_ASSERT(transaction->t_shadow_list == NULL); + J_ASSERT(transaction->t_checkpoint_list == NULL); + J_ASSERT(atomic_read(&transaction->t_updates) == 0); + J_ASSERT(journal->j_committing_transaction != transaction); + J_ASSERT(journal->j_running_transaction != transaction); + + trace_jbd2_drop_transaction(journal, transaction); + + jbd2_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid); +} diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c new file mode 100644 index 000000000..556b259a0 --- /dev/null +++ b/fs/jbd2/commit.c @@ -0,0 +1,1201 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/commit.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * Journal commit routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/jiffies.h> +#include <linux/crc32.h> +#include <linux/writeback.h> +#include <linux/backing-dev.h> +#include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/bitops.h> +#include <trace/events/jbd2.h> + +/* + * IO end handler for temporary buffer_heads handling writes to the journal. + */ +static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) +{ + struct buffer_head *orig_bh = bh->b_private; + + BUFFER_TRACE(bh, ""); + if (uptodate) + set_buffer_uptodate(bh); + else + clear_buffer_uptodate(bh); + if (orig_bh) { + clear_bit_unlock(BH_Shadow, &orig_bh->b_state); + smp_mb__after_atomic(); + wake_up_bit(&orig_bh->b_state, BH_Shadow); + } + unlock_buffer(bh); +} + +/* + * When an ext4 file is truncated, it is possible that some pages are not + * successfully freed, because they are attached to a committing transaction. + * After the transaction commits, these pages are left on the LRU, with no + * ->mapping, and with attached buffers. These pages are trivially reclaimable + * by the VM, but their apparent absence upsets the VM accounting, and it makes + * the numbers in /proc/meminfo look odd. + * + * So here, we have a buffer which has just come off the forget list. Look to + * see if we can strip all buffers from the backing page. + * + * Called under lock_journal(), and possibly under journal_datalist_lock. The + * caller provided us with a ref against the buffer, and we drop that here. + */ +static void release_buffer_page(struct buffer_head *bh) +{ + struct folio *folio; + struct page *page; + + if (buffer_dirty(bh)) + goto nope; + if (atomic_read(&bh->b_count) != 1) + goto nope; + page = bh->b_page; + if (!page) + goto nope; + folio = page_folio(page); + if (folio->mapping) + goto nope; + + /* OK, it's a truncated page */ + if (!folio_trylock(folio)) + goto nope; + + folio_get(folio); + __brelse(bh); + try_to_free_buffers(folio); + folio_unlock(folio); + folio_put(folio); + return; + +nope: + __brelse(bh); +} + +static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh) +{ + struct commit_header *h; + __u32 csum; + + if (!jbd2_journal_has_csum_v2or3(j)) + return; + + h = (struct commit_header *)(bh->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, bh->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 + * mode we can now just skip the rest of the journal write + * entirely. + * + * Returns 1 if the journal needs to be aborted or 0 on success + */ +static int journal_submit_commit_record(journal_t *journal, + transaction_t *commit_transaction, + struct buffer_head **cbh, + __u32 crc32_sum) +{ + struct commit_header *tmp; + struct buffer_head *bh; + struct timespec64 now; + blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS; + + *cbh = NULL; + + if (is_journal_aborted(journal)) + return 0; + + bh = jbd2_journal_get_descriptor_buffer(commit_transaction, + JBD2_COMMIT_BLOCK); + if (!bh) + return 1; + + tmp = (struct commit_header *)bh->b_data; + ktime_get_coarse_real_ts64(&now); + tmp->h_commit_sec = cpu_to_be64(now.tv_sec); + tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec); + + if (jbd2_has_feature_checksum(journal)) { + tmp->h_chksum_type = JBD2_CRC32_CHKSUM; + tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; + tmp->h_chksum[0] = cpu_to_be32(crc32_sum); + } + jbd2_commit_block_csum_set(journal, bh); + + BUFFER_TRACE(bh, "submit commit block"); + lock_buffer(bh); + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + bh->b_end_io = journal_end_buffer_io_sync; + + if (journal->j_flags & JBD2_BARRIER && + !jbd2_has_feature_async_commit(journal)) + write_flags |= REQ_PREFLUSH | REQ_FUA; + + submit_bh(write_flags, bh); + *cbh = bh; + return 0; +} + +/* + * This function along with journal_submit_commit_record + * allows to write the commit record asynchronously. + */ +static int journal_wait_on_commit_record(journal_t *journal, + struct buffer_head *bh) +{ + int ret = 0; + + clear_buffer_dirty(bh); + wait_on_buffer(bh); + + if (unlikely(!buffer_uptodate(bh))) + ret = -EIO; + put_bh(bh); /* One for getblk() */ + + return ret; +} + +/* + * write the filemap data using writepage() address_space_operations. + * We don't do block allocation here even for delalloc. We don't + * use writepages() because with delayed allocation we may be doing + * block allocation in writepages(). + */ +int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode) +{ + struct address_space *mapping = jinode->i_vfs_inode->i_mapping; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = mapping->nrpages * 2, + .range_start = jinode->i_dirty_start, + .range_end = jinode->i_dirty_end, + }; + + /* + * submit the inode data buffers. We use writepage + * instead of writepages. Because writepages can do + * block allocation with delalloc. We need to write + * only allocated blocks here. + */ + return generic_writepages(mapping, &wbc); +} + +/* Send all the data buffers related to an inode */ +int jbd2_submit_inode_data(struct jbd2_inode *jinode) +{ + + if (!jinode || !(jinode->i_flags & JI_WRITE_DATA)) + return 0; + + trace_jbd2_submit_inode_data(jinode->i_vfs_inode); + return jbd2_journal_submit_inode_data_buffers(jinode); + +} +EXPORT_SYMBOL(jbd2_submit_inode_data); + +int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode) +{ + if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) || + !jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping) + return 0; + return filemap_fdatawait_range_keep_errors( + jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start, + jinode->i_dirty_end); +} +EXPORT_SYMBOL(jbd2_wait_inode_data); + +/* + * Submit all the data buffers of inode associated with the transaction to + * disk. + * + * We are in a committing transaction. Therefore no new inode can be added to + * our inode list. We use JI_COMMIT_RUNNING flag to protect inode we currently + * operate on from being released while we write out pages. + */ +static int journal_submit_data_buffers(journal_t *journal, + transaction_t *commit_transaction) +{ + struct jbd2_inode *jinode; + int err, ret = 0; + + spin_lock(&journal->j_list_lock); + list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + if (!(jinode->i_flags & JI_WRITE_DATA)) + continue; + jinode->i_flags |= JI_COMMIT_RUNNING; + spin_unlock(&journal->j_list_lock); + /* submit the inode data buffers. */ + trace_jbd2_submit_inode_data(jinode->i_vfs_inode); + if (journal->j_submit_inode_data_buffers) { + err = journal->j_submit_inode_data_buffers(jinode); + if (!ret) + ret = err; + } + spin_lock(&journal->j_list_lock); + J_ASSERT(jinode->i_transaction == commit_transaction); + jinode->i_flags &= ~JI_COMMIT_RUNNING; + smp_mb(); + wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); + } + spin_unlock(&journal->j_list_lock); + return ret; +} + +int jbd2_journal_finish_inode_data_buffers(struct jbd2_inode *jinode) +{ + struct address_space *mapping = jinode->i_vfs_inode->i_mapping; + + return filemap_fdatawait_range_keep_errors(mapping, + jinode->i_dirty_start, + jinode->i_dirty_end); +} + +/* + * Wait for data submitted for writeout, refile inodes to proper + * transaction if needed. + * + */ +static int journal_finish_inode_data_buffers(journal_t *journal, + transaction_t *commit_transaction) +{ + struct jbd2_inode *jinode, *next_i; + int err, ret = 0; + + /* For locking, see the comment in journal_submit_data_buffers() */ + spin_lock(&journal->j_list_lock); + list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + if (!(jinode->i_flags & JI_WAIT_DATA)) + continue; + jinode->i_flags |= JI_COMMIT_RUNNING; + spin_unlock(&journal->j_list_lock); + /* wait for the inode data buffers writeout. */ + if (journal->j_finish_inode_data_buffers) { + err = journal->j_finish_inode_data_buffers(jinode); + if (!ret) + ret = err; + } + cond_resched(); + spin_lock(&journal->j_list_lock); + jinode->i_flags &= ~JI_COMMIT_RUNNING; + smp_mb(); + wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); + } + + /* Now refile inode to proper lists */ + list_for_each_entry_safe(jinode, next_i, + &commit_transaction->t_inode_list, i_list) { + list_del(&jinode->i_list); + if (jinode->i_next_transaction) { + jinode->i_transaction = jinode->i_next_transaction; + jinode->i_next_transaction = NULL; + list_add(&jinode->i_list, + &jinode->i_transaction->t_inode_list); + } else { + jinode->i_transaction = NULL; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; + } + } + spin_unlock(&journal->j_list_lock); + + return ret; +} + +static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) +{ + struct page *page = bh->b_page; + char *addr; + __u32 checksum; + + addr = kmap_atomic(page); + checksum = crc32_be(crc32_sum, + (void *)(addr + offset_in_page(bh->b_data)), bh->b_size); + kunmap_atomic(addr); + + return checksum; +} + +static void write_tag_block(journal_t *j, journal_block_tag_t *tag, + unsigned long long block) +{ + tag->t_blocknr = cpu_to_be32(block & (u32)~0); + if (jbd2_has_feature_64bit(j)) + tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); +} + +static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, + struct buffer_head *bh, __u32 sequence) +{ + journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag; + struct page *page = bh->b_page; + __u8 *addr; + __u32 csum32; + __be32 seq; + + if (!jbd2_journal_has_csum_v2or3(j)) + return; + + seq = cpu_to_be32(sequence); + addr = kmap_atomic(page); + csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); + csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data), + bh->b_size); + kunmap_atomic(addr); + + if (jbd2_has_feature_csum3(j)) + tag3->t_checksum = cpu_to_be32(csum32); + else + tag->t_checksum = cpu_to_be16(csum32); +} +/* + * jbd2_journal_commit_transaction + * + * The primary function for committing a transaction to the log. This + * function is called by the journal thread to begin a complete commit. + */ +void jbd2_journal_commit_transaction(journal_t *journal) +{ + struct transaction_stats_s stats; + transaction_t *commit_transaction; + struct journal_head *jh; + struct buffer_head *descriptor; + struct buffer_head **wbuf = journal->j_wbuf; + int bufs; + int flags; + int err; + unsigned long long blocknr; + ktime_t start_time; + u64 commit_time; + char *tagp = NULL; + journal_block_tag_t *tag = NULL; + int space_left = 0; + int first_tag = 0; + int tag_flag; + int i; + int tag_bytes = journal_tag_bytes(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; + LIST_HEAD(io_bufs); + LIST_HEAD(log_bufs); + + if (jbd2_journal_has_csum_v2or3(journal)) + csum_size = sizeof(struct jbd2_journal_block_tail); + + /* + * First job: lock down the current transaction and wait for + * all outstanding updates to complete. + */ + + /* Do we need to erase the effects of a prior jbd2_journal_flush? */ + if (journal->j_flags & JBD2_FLUSHED) { + jbd2_debug(3, "super block updated\n"); + mutex_lock_io(&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, 0); + mutex_unlock(&journal->j_checkpoint_mutex); + } else { + jbd2_debug(3, "superblock not updated\n"); + } + + J_ASSERT(journal->j_running_transaction != NULL); + J_ASSERT(journal->j_committing_transaction == NULL); + + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_FULL_COMMIT_ONGOING; + while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_fc_wait, &wait, + TASK_UNINTERRUPTIBLE); + write_unlock(&journal->j_state_lock); + schedule(); + write_lock(&journal->j_state_lock); + finish_wait(&journal->j_fc_wait, &wait); + /* + * TODO: by blocking fast commits here, we are increasing + * fsync() latency slightly. Strictly speaking, we don't need + * to block fast commits until the transaction enters T_FLUSH + * state. So an optimization is possible where we block new fast + * commits here and wait for existing ones to complete + * just before we enter T_FLUSH. That way, the existing fast + * commits and this full commit can proceed parallely. + */ + } + write_unlock(&journal->j_state_lock); + + commit_transaction = journal->j_running_transaction; + + trace_jbd2_start_commit(journal, commit_transaction); + jbd2_debug(1, "JBD2: starting commit of transaction %d\n", + commit_transaction->t_tid); + + write_lock(&journal->j_state_lock); + journal->j_fc_off = 0; + J_ASSERT(commit_transaction->t_state == T_RUNNING); + commit_transaction->t_state = T_LOCKED; + + trace_jbd2_commit_locking(journal, commit_transaction); + stats.run.rs_wait = commit_transaction->t_max_wait; + stats.run.rs_request_delay = 0; + stats.run.rs_locked = jiffies; + if (commit_transaction->t_requested) + stats.run.rs_request_delay = + jbd2_time_diff(commit_transaction->t_requested, + stats.run.rs_locked); + stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, + stats.run.rs_locked); + + // waits for any t_updates to finish + jbd2_journal_wait_updates(journal); + + commit_transaction->t_state = T_SWITCH; + + J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= + journal->j_max_transaction_buffers); + + /* + * First thing we are allowed to do is to discard any remaining + * BJ_Reserved buffers. Note, it is _not_ permissible to assume + * that there are no such buffers: if a large filesystem + * operation like a truncate needs to split itself over multiple + * transactions, then it may try to do a jbd2_journal_restart() while + * there are still BJ_Reserved buffers outstanding. These must + * be released cleanly from the current transaction. + * + * In this case, the filesystem must still reserve write access + * again before modifying the buffer in the new transaction, but + * we do not require it to remember exactly which old buffers it + * has reserved. This is consistent with the existing behaviour + * that multiple jbd2_journal_get_write_access() calls to the same + * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). + */ + while (commit_transaction->t_reserved_list) { + jh = commit_transaction->t_reserved_list; + JBUFFER_TRACE(jh, "reserved, unused: refile"); + /* + * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may + * leave undo-committed data. + */ + if (jh->b_committed_data) { + struct buffer_head *bh = jh2bh(jh); + + spin_lock(&jh->b_state_lock); + jbd2_free(jh->b_committed_data, bh->b_size); + jh->b_committed_data = NULL; + spin_unlock(&jh->b_state_lock); + } + jbd2_journal_refile_buffer(journal, jh); + } + + write_unlock(&journal->j_state_lock); + /* + * Now try to drop any written-back buffers from the journal's + * checkpoint lists. We do this *before* commit because it potentially + * frees some memory + */ + spin_lock(&journal->j_list_lock); + __jbd2_journal_clean_checkpoint_list(journal, false); + spin_unlock(&journal->j_list_lock); + + jbd2_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. + */ + jbd2_journal_switch_revoke_table(journal); + + write_lock(&journal->j_state_lock); + /* + * Reserved credits cannot be claimed anymore, free them + */ + atomic_sub(atomic_read(&journal->j_reserved_credits), + &commit_transaction->t_outstanding_credits); + + trace_jbd2_commit_flushing(journal, commit_transaction); + stats.run.rs_flushing = jiffies; + stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, + stats.run.rs_flushing); + + commit_transaction->t_state = T_FLUSH; + journal->j_committing_transaction = commit_transaction; + journal->j_running_transaction = NULL; + start_time = ktime_get(); + commit_transaction->t_log_start = journal->j_head; + wake_up_all(&journal->j_wait_transaction_locked); + write_unlock(&journal->j_state_lock); + + jbd2_debug(3, "JBD2: commit phase 2a\n"); + + /* + * 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); + if (err) + jbd2_journal_abort(journal, err); + + blk_start_plug(&plug); + jbd2_journal_write_revoke_records(commit_transaction, &log_bufs); + + jbd2_debug(3, "JBD2: commit phase 2b\n"); + + /* + * Way to go: we have now written out all of the data for a + * transaction! Now comes the tricky part: we need to write out + * metadata. Loop over the transaction's entire buffer list: + */ + write_lock(&journal->j_state_lock); + commit_transaction->t_state = T_COMMIT; + write_unlock(&journal->j_state_lock); + + trace_jbd2_commit_logging(journal, commit_transaction); + stats.run.rs_logging = jiffies; + stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, + stats.run.rs_logging); + stats.run.rs_blocks = commit_transaction->t_nr_buffers; + stats.run.rs_blocks_logged = 0; + + J_ASSERT(commit_transaction->t_nr_buffers <= + atomic_read(&commit_transaction->t_outstanding_credits)); + + err = 0; + bufs = 0; + descriptor = NULL; + while (commit_transaction->t_buffers) { + + /* Find the next buffer to be journaled... */ + + jh = commit_transaction->t_buffers; + + /* If we're in abort mode, we just un-journal the buffer and + release it. */ + + if (is_journal_aborted(journal)) { + clear_buffer_jbddirty(jh2bh(jh)); + JBUFFER_TRACE(jh, "journal is aborting: refile"); + jbd2_buffer_abort_trigger(jh, + jh->b_frozen_data ? + jh->b_frozen_triggers : + jh->b_triggers); + jbd2_journal_refile_buffer(journal, jh); + /* If that was the last one, we need to clean up + * any descriptor buffers which may have been + * already allocated, even if we are now + * aborting. */ + if (!commit_transaction->t_buffers) + goto start_journal_io; + continue; + } + + /* Make sure we have a descriptor block in which to + record the metadata buffer. */ + + if (!descriptor) { + J_ASSERT (bufs == 0); + + jbd2_debug(4, "JBD2: get descriptor\n"); + + descriptor = jbd2_journal_get_descriptor_buffer( + commit_transaction, + JBD2_DESCRIPTOR_BLOCK); + if (!descriptor) { + jbd2_journal_abort(journal, -EIO); + continue; + } + + jbd2_debug(4, "JBD2: got buffer %llu (%p)\n", + (unsigned long long)descriptor->b_blocknr, + descriptor->b_data); + tagp = &descriptor->b_data[sizeof(journal_header_t)]; + space_left = descriptor->b_size - + sizeof(journal_header_t); + first_tag = 1; + set_buffer_jwrite(descriptor); + set_buffer_dirty(descriptor); + wbuf[bufs++] = descriptor; + + /* Record it so that we can wait for IO + completion later */ + BUFFER_TRACE(descriptor, "ph3: file as descriptor"); + jbd2_file_log_bh(&log_bufs, descriptor); + } + + /* Where is the buffer to be written? */ + + err = jbd2_journal_next_log_block(journal, &blocknr); + /* If the block mapping failed, just abandon the buffer + and repeat this loop: we'll fall into the + refile-on-abort condition above. */ + if (err) { + jbd2_journal_abort(journal, err); + continue; + } + + /* + * start_this_handle() uses t_outstanding_credits to determine + * the free space in the log. + */ + atomic_dec(&commit_transaction->t_outstanding_credits); + + /* Bump b_count to prevent truncate from stumbling over + the shadowed buffer! @@@ This can go if we ever get + rid of the shadow pairing of buffers. */ + atomic_inc(&jh2bh(jh)->b_count); + + /* + * Make a temporary IO buffer with which to write it out + * (this will requeue the metadata buffer to BJ_Shadow). + */ + set_bit(BH_JWrite, &jh2bh(jh)->b_state); + JBUFFER_TRACE(jh, "ph3: write metadata"); + flags = jbd2_journal_write_metadata_buffer(commit_transaction, + jh, &wbuf[bufs], blocknr); + if (flags < 0) { + jbd2_journal_abort(journal, flags); + continue; + } + jbd2_file_log_bh(&io_bufs, wbuf[bufs]); + + /* Record the new block's tag in the current descriptor + buffer */ + + tag_flag = 0; + if (flags & 1) + tag_flag |= JBD2_FLAG_ESCAPE; + if (!first_tag) + tag_flag |= JBD2_FLAG_SAME_UUID; + + tag = (journal_block_tag_t *) tagp; + write_tag_block(journal, tag, jh2bh(jh)->b_blocknr); + tag->t_flags = cpu_to_be16(tag_flag); + jbd2_block_tag_csum_set(journal, tag, wbuf[bufs], + commit_transaction->t_tid); + tagp += tag_bytes; + space_left -= tag_bytes; + bufs++; + + if (first_tag) { + memcpy (tagp, journal->j_uuid, 16); + tagp += 16; + space_left -= 16; + first_tag = 0; + } + + /* If there's no more to do, or if the descriptor is full, + let the IO rip! */ + + if (bufs == journal->j_wbufsize || + commit_transaction->t_buffers == NULL || + space_left < tag_bytes + 16 + csum_size) { + + jbd2_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_be16(JBD2_FLAG_LAST_TAG); +start_journal_io: + if (descriptor) + jbd2_descriptor_block_csum_set(journal, + descriptor); + + for (i = 0; i < bufs; i++) { + struct buffer_head *bh = wbuf[i]; + + /* + * Compute checksum. + */ + if (jbd2_has_feature_checksum(journal)) { + crc32_sum = + jbd2_checksum_data(crc32_sum, bh); + } + + lock_buffer(bh); + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + bh->b_end_io = journal_end_buffer_io_sync; + submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS, + bh); + } + cond_resched(); + + /* Force a new descriptor to be generated next + time round the loop. */ + descriptor = NULL; + bufs = 0; + } + } + + err = journal_finish_inode_data_buffers(journal, commit_transaction); + if (err) { + printk(KERN_WARNING + "JBD2: Detected IO errors while flushing file data " + "on %s\n", journal->j_devname); + if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR) + jbd2_journal_abort(journal, err); + 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 < jbd2_journal_get_max_txn_bufs(journal)) + 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 + * the commit record + */ + 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); + + /* Done it all: now write the commit record asynchronously. */ + if (jbd2_has_feature_async_commit(journal)) { + err = journal_submit_commit_record(journal, commit_transaction, + &cbh, crc32_sum); + if (err) + jbd2_journal_abort(journal, err); + } + + blk_finish_plug(&plug); + + /* Lo and behold: we have just managed to send a transaction to + the log. Before we can commit it, wait for the IO so far to + complete. Control buffers being written are on the + transaction's t_log_list queue, and metadata buffers are on + the io_bufs list. + + Wait for the buffers in reverse order. That way we are + less likely to be woken up until all IOs have completed, and + so we incur less scheduling load. + */ + + jbd2_debug(3, "JBD2: commit phase 3\n"); + + while (!list_empty(&io_bufs)) { + struct buffer_head *bh = list_entry(io_bufs.prev, + struct buffer_head, + b_assoc_buffers); + + wait_on_buffer(bh); + cond_resched(); + + if (unlikely(!buffer_uptodate(bh))) + err = -EIO; + jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; + + /* + * The list contains temporary buffer heads created by + * jbd2_journal_write_metadata_buffer(). + */ + BUFFER_TRACE(bh, "dumping temporary bh"); + __brelse(bh); + J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0); + free_buffer_head(bh); + + /* We also have to refile the corresponding shadowed buffer */ + jh = commit_transaction->t_shadow_list->b_tprev; + bh = jh2bh(jh); + clear_buffer_jwrite(bh); + J_ASSERT_BH(bh, buffer_jbddirty(bh)); + J_ASSERT_BH(bh, !buffer_shadow(bh)); + + /* The metadata is now released for reuse, but we need + to remember it against this transaction so that when + we finally commit, we can do any checkpointing + required. */ + JBUFFER_TRACE(jh, "file as BJ_Forget"); + jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget); + JBUFFER_TRACE(jh, "brelse shadowed buffer"); + __brelse(bh); + } + + J_ASSERT (commit_transaction->t_shadow_list == NULL); + + jbd2_debug(3, "JBD2: commit phase 4\n"); + + /* Here we wait for the revoke record and descriptor record buffers */ + while (!list_empty(&log_bufs)) { + struct buffer_head *bh; + + bh = list_entry(log_bufs.prev, struct buffer_head, b_assoc_buffers); + wait_on_buffer(bh); + cond_resched(); + + if (unlikely(!buffer_uptodate(bh))) + err = -EIO; + + BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile"); + clear_buffer_jwrite(bh); + jbd2_unfile_log_bh(bh); + stats.run.rs_blocks_logged++; + __brelse(bh); /* One for getblk */ + /* AKPM: bforget here */ + } + + if (err) + jbd2_journal_abort(journal, err); + + jbd2_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; + write_unlock(&journal->j_state_lock); + + if (!jbd2_has_feature_async_commit(journal)) { + err = journal_submit_commit_record(journal, commit_transaction, + &cbh, crc32_sum); + if (err) + jbd2_journal_abort(journal, err); + } + if (cbh) + err = journal_wait_on_commit_record(journal, cbh); + stats.run.rs_blocks_logged++; + if (jbd2_has_feature_async_commit(journal) && + journal->j_flags & JBD2_BARRIER) { + blkdev_issue_flush(journal->j_dev); + } + + if (err) + jbd2_journal_abort(journal, err); + + WARN_ON_ONCE( + atomic_read(&commit_transaction->t_outstanding_credits) < 0); + + /* + * 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. */ + + jbd2_debug(3, "JBD2: commit phase 6\n"); + + J_ASSERT(list_empty(&commit_transaction->t_inode_list)); + J_ASSERT(commit_transaction->t_buffers == NULL); + J_ASSERT(commit_transaction->t_checkpoint_list == NULL); + J_ASSERT(commit_transaction->t_shadow_list == NULL); + +restart_loop: + /* + * As there are other places (journal_unmap_buffer()) adding buffers + * to this list we have to be careful and hold the j_list_lock. + */ + spin_lock(&journal->j_list_lock); + while (commit_transaction->t_forget) { + transaction_t *cp_transaction; + struct buffer_head *bh; + int try_to_free = 0; + bool drop_ref; + + jh = commit_transaction->t_forget; + spin_unlock(&journal->j_list_lock); + bh = jh2bh(jh); + /* + * Get a reference so that bh cannot be freed before we are + * done with it. + */ + get_bh(bh); + spin_lock(&jh->b_state_lock); + J_ASSERT_JH(jh, jh->b_transaction == commit_transaction); + + /* + * If there is undo-protected committed data against + * this buffer, then we can remove it now. If it is a + * buffer needing such protection, the old frozen_data + * field now points to a committed version of the + * buffer, so rotate that field to the new committed + * data. + * + * Otherwise, we can just throw away the frozen data now. + * + * We also know that the frozen data has already fired + * its triggers if they exist, so we can clear that too. + */ + if (jh->b_committed_data) { + jbd2_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; + jh->b_frozen_triggers = NULL; + } + } else if (jh->b_frozen_data) { + jbd2_free(jh->b_frozen_data, bh->b_size); + jh->b_frozen_data = NULL; + jh->b_frozen_triggers = NULL; + } + + spin_lock(&journal->j_list_lock); + cp_transaction = jh->b_cp_transaction; + if (cp_transaction) { + JBUFFER_TRACE(jh, "remove from old cp transaction"); + cp_transaction->t_chp_stats.cs_dropped++; + __jbd2_journal_remove_checkpoint(jh); + } + + /* Only re-checkpoint the buffer_head if it is marked + * dirty. If the buffer was added to the BJ_Forget list + * by jbd2_journal_forget, it may no longer be dirty and + * there's no point in keeping a checkpoint record for + * it. */ + + /* + * A buffer which has been freed while still being journaled + * by a previous transaction, refile the buffer to BJ_Forget of + * the running transaction. If the just committed transaction + * contains "add to orphan" operation, we can completely + * invalidate the buffer now. We are rather through in that + * since the buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial page. + */ + if (buffer_freed(bh) && !jh->b_next_transaction) { + struct address_space *mapping; + + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + + /* + * Block device buffers need to stay mapped all the + * time, so it is enough to clear buffer_jbddirty and + * buffer_freed bits. For the file mapping buffers (i.e. + * journalled data) we need to unmap buffer and clear + * more bits. We also need to be careful about the check + * because the data page mapping can get cleared under + * our hands. Note that if mapping == NULL, we don't + * need to make buffer unmapped because the page is + * already detached from the mapping and buffers cannot + * get reused. + */ + mapping = READ_ONCE(bh->b_page->mapping); + if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) { + clear_buffer_mapped(bh); + clear_buffer_new(bh); + clear_buffer_req(bh); + bh->b_bdev = NULL; + } + } + + if (buffer_jbddirty(bh)) { + JBUFFER_TRACE(jh, "add to new checkpointing trans"); + __jbd2_journal_insert_checkpoint(jh, commit_transaction); + if (is_journal_aborted(journal)) + clear_buffer_jbddirty(bh); + } else { + J_ASSERT_BH(bh, !buffer_dirty(bh)); + /* + * The buffer on BJ_Forget list and not jbddirty means + * it has been freed by this transaction and hence it + * could not have been reallocated until this + * transaction has committed. *BUT* it could be + * reallocated once we have written all the data to + * disk and before we process the buffer on BJ_Forget + * list. + */ + if (!jh->b_next_transaction) + try_to_free = 1; + } + JBUFFER_TRACE(jh, "refile or unfile buffer"); + drop_ref = __jbd2_journal_refile_buffer(jh); + spin_unlock(&jh->b_state_lock); + if (drop_ref) + jbd2_journal_put_journal_head(jh); + if (try_to_free) + release_buffer_page(bh); /* Drops bh reference */ + else + __brelse(bh); + cond_resched_lock(&journal->j_list_lock); + } + spin_unlock(&journal->j_list_lock); + /* + * This is a bit sleazy. We use j_list_lock to protect transition + * of a transaction into T_FINISHED state and calling + * __jbd2_journal_drop_transaction(). Otherwise we could race with + * other checkpointing code processing the transaction... + */ + write_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + /* + * Now recheck if some buffers did not get attached to the transaction + * while the lock was dropped... + */ + if (commit_transaction->t_forget) { + spin_unlock(&journal->j_list_lock); + write_unlock(&journal->j_state_lock); + goto restart_loop; + } + + /* Add the transaction to the checkpoint list + * __journal_remove_checkpoint() can not destroy transaction + * under us because it is not marked as T_FINISHED yet */ + if (journal->j_checkpoint_transactions == NULL) { + journal->j_checkpoint_transactions = commit_transaction; + commit_transaction->t_cpnext = commit_transaction; + commit_transaction->t_cpprev = commit_transaction; + } else { + commit_transaction->t_cpnext = + journal->j_checkpoint_transactions; + commit_transaction->t_cpprev = + commit_transaction->t_cpnext->t_cpprev; + commit_transaction->t_cpnext->t_cpprev = + commit_transaction; + commit_transaction->t_cpprev->t_cpnext = + commit_transaction; + } + spin_unlock(&journal->j_list_lock); + + /* Done with this transaction! */ + + jbd2_debug(3, "JBD2: commit phase 7\n"); + + J_ASSERT(commit_transaction->t_state == T_COMMIT_JFLUSH); + + commit_transaction->t_start = jiffies; + stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging, + commit_transaction->t_start); + + /* + * File the transaction statistics + */ + stats.ts_tid = commit_transaction->t_tid; + stats.run.rs_handle_count = + atomic_read(&commit_transaction->t_handle_count); + trace_jbd2_run_stats(journal->j_fs_dev->bd_dev, + commit_transaction->t_tid, &stats.run); + stats.ts_requested = (commit_transaction->t_requested) ? 1 : 0; + + commit_transaction->t_state = T_COMMIT_CALLBACK; + J_ASSERT(commit_transaction == journal->j_committing_transaction); + journal->j_commit_sequence = commit_transaction->t_tid; + journal->j_committing_transaction = NULL; + commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); + + /* + * weight the commit time higher than the average time so we don't + * react too strongly to vast changes in the commit time + */ + if (likely(journal->j_average_commit_time)) + journal->j_average_commit_time = (commit_time + + journal->j_average_commit_time*3) / 4; + else + journal->j_average_commit_time = commit_time; + + write_unlock(&journal->j_state_lock); + + if (journal->j_commit_callback) + journal->j_commit_callback(journal, commit_transaction); + if (journal->j_fc_cleanup_callback) + journal->j_fc_cleanup_callback(journal, 1, commit_transaction->t_tid); + + trace_jbd2_end_commit(journal, commit_transaction); + jbd2_debug(1, "JBD2: commit %d complete, head %d\n", + journal->j_commit_sequence, journal->j_tail_sequence); + + write_lock(&journal->j_state_lock); + journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING; + journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; + spin_lock(&journal->j_list_lock); + commit_transaction->t_state = T_FINISHED; + /* Check if the transaction can be dropped now that we are finished */ + if (commit_transaction->t_checkpoint_list == NULL) { + __jbd2_journal_drop_transaction(journal, commit_transaction); + jbd2_journal_free_transaction(commit_transaction); + } + spin_unlock(&journal->j_list_lock); + write_unlock(&journal->j_state_lock); + wake_up(&journal->j_wait_done_commit); + wake_up(&journal->j_fc_wait); + + /* + * Calculate overall stats + */ + spin_lock(&journal->j_history_lock); + journal->j_stats.ts_tid++; + journal->j_stats.ts_requested += stats.ts_requested; + journal->j_stats.run.rs_wait += stats.run.rs_wait; + journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay; + journal->j_stats.run.rs_running += stats.run.rs_running; + journal->j_stats.run.rs_locked += stats.run.rs_locked; + journal->j_stats.run.rs_flushing += stats.run.rs_flushing; + journal->j_stats.run.rs_logging += stats.run.rs_logging; + journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count; + journal->j_stats.run.rs_blocks += stats.run.rs_blocks; + journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged; + spin_unlock(&journal->j_history_lock); +} diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c new file mode 100644 index 000000000..3df45e469 --- /dev/null +++ b/fs/jbd2/journal.c @@ -0,0 +1,3204 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/journal.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * Generic filesystem journal-writing code; part of the ext2fs + * journaling system. + * + * This file manages journals: areas of disk reserved for logging + * transactional updates. This includes the kernel journaling thread + * which is responsible for scheduling updates to the log. + * + * We do not actually manage the physical storage of the journal in this + * file: that is left to a per-journal policy function, which allows us + * to store the journal within a filesystem-specified area for ext2 + * journaling (ext2 can use a reserved inode for storing the log). + */ + +#include <linux/module.h> +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/freezer.h> +#include <linux/pagemap.h> +#include <linux/kthread.h> +#include <linux/poison.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/math64.h> +#include <linux/hash.h> +#include <linux/log2.h> +#include <linux/vmalloc.h> +#include <linux/backing-dev.h> +#include <linux/bitops.h> +#include <linux/ratelimit.h> +#include <linux/sched/mm.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/jbd2.h> + +#include <linux/uaccess.h> +#include <asm/page.h> + +#ifdef CONFIG_JBD2_DEBUG +static ushort jbd2_journal_enable_debug __read_mostly; + +module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); +MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); +#endif + +EXPORT_SYMBOL(jbd2_journal_extend); +EXPORT_SYMBOL(jbd2_journal_stop); +EXPORT_SYMBOL(jbd2_journal_lock_updates); +EXPORT_SYMBOL(jbd2_journal_unlock_updates); +EXPORT_SYMBOL(jbd2_journal_get_write_access); +EXPORT_SYMBOL(jbd2_journal_get_create_access); +EXPORT_SYMBOL(jbd2_journal_get_undo_access); +EXPORT_SYMBOL(jbd2_journal_set_triggers); +EXPORT_SYMBOL(jbd2_journal_dirty_metadata); +EXPORT_SYMBOL(jbd2_journal_forget); +EXPORT_SYMBOL(jbd2_journal_flush); +EXPORT_SYMBOL(jbd2_journal_revoke); + +EXPORT_SYMBOL(jbd2_journal_init_dev); +EXPORT_SYMBOL(jbd2_journal_init_inode); +EXPORT_SYMBOL(jbd2_journal_check_used_features); +EXPORT_SYMBOL(jbd2_journal_check_available_features); +EXPORT_SYMBOL(jbd2_journal_set_features); +EXPORT_SYMBOL(jbd2_journal_load); +EXPORT_SYMBOL(jbd2_journal_destroy); +EXPORT_SYMBOL(jbd2_journal_abort); +EXPORT_SYMBOL(jbd2_journal_errno); +EXPORT_SYMBOL(jbd2_journal_ack_err); +EXPORT_SYMBOL(jbd2_journal_clear_err); +EXPORT_SYMBOL(jbd2_log_wait_commit); +EXPORT_SYMBOL(jbd2_journal_start_commit); +EXPORT_SYMBOL(jbd2_journal_force_commit_nested); +EXPORT_SYMBOL(jbd2_journal_wipe); +EXPORT_SYMBOL(jbd2_journal_blocks_per_page); +EXPORT_SYMBOL(jbd2_journal_invalidate_folio); +EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); +EXPORT_SYMBOL(jbd2_journal_force_commit); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); +EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers); +EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); +EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); +EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); +EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); +EXPORT_SYMBOL(jbd2_inode_cache); + +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", file, func, line, &vaf); + va_end(args); +} +#endif + +/* Checksumming functions */ +static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) +{ + if (!jbd2_journal_has_csum_v2or3_feature(j)) + return 1; + + return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; +} + +static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) +{ + __u32 csum; + __be32 old_csum; + + old_csum = sb->s_checksum; + sb->s_checksum = 0; + csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t)); + sb->s_checksum = old_csum; + + return cpu_to_be32(csum); +} + +/* + * Helper function used to manage commit timeouts + */ + +static void commit_timeout(struct timer_list *t) +{ + journal_t *journal = from_timer(journal, t, j_commit_timer); + + wake_up_process(journal->j_task); +} + +/* + * kjournald2: The main thread function used to manage a logging device + * journal. + * + * This kernel thread is responsible for two things: + * + * 1) COMMIT: Every so often we need to commit the current state of the + * filesystem to disk. The journal thread is responsible for writing + * all of the metadata buffers to disk. If a fast commit is ongoing + * journal thread waits until it's done and then continues from + * there on. + * + * 2) CHECKPOINT: We cannot reuse a used section of the log file until all + * of the data in that part of the log has been rewritten elsewhere on + * the disk. Flushing these old buffers to reclaim space in the log is + * known as checkpointing, and this thread is responsible for that job. + */ + +static int kjournald2(void *arg) +{ + journal_t *journal = arg; + transaction_t *transaction; + + /* + * Set up an interval timer which can be used to trigger a commit wakeup + * after the commit interval expires + */ + timer_setup(&journal->j_commit_timer, commit_timeout, 0); + + set_freezable(); + + /* Record that the journal thread is running */ + journal->j_task = current; + wake_up(&journal->j_wait_done_commit); + + /* + * Make sure that no allocations from this kernel thread will ever + * recurse to the fs layer because we are responsible for the + * transaction commit and any fs involvement might get stuck waiting for + * the trasn. commit. + */ + memalloc_nofs_save(); + + /* + * And now, wait forever for commit wakeup events. + */ + write_lock(&journal->j_state_lock); + +loop: + if (journal->j_flags & JBD2_UNMOUNT) + goto end_loop; + + jbd2_debug(1, "commit_sequence=%u, commit_request=%u\n", + journal->j_commit_sequence, journal->j_commit_request); + + if (journal->j_commit_sequence != journal->j_commit_request) { + jbd2_debug(1, "OK, requests differ\n"); + write_unlock(&journal->j_state_lock); + del_timer_sync(&journal->j_commit_timer); + jbd2_journal_commit_transaction(journal); + write_lock(&journal->j_state_lock); + goto loop; + } + + wake_up(&journal->j_wait_done_commit); + if (freezing(current)) { + /* + * The simpler the better. Flushing journal isn't a + * good idea, because that depends on threads that may + * be already stopped. + */ + jbd2_debug(1, "Now suspending kjournald2\n"); + write_unlock(&journal->j_state_lock); + try_to_freeze(); + write_lock(&journal->j_state_lock); + } else { + /* + * We assume on resume that commits are already there, + * so we don't sleep + */ + DEFINE_WAIT(wait); + int should_sleep = 1; + + prepare_to_wait(&journal->j_wait_commit, &wait, + TASK_INTERRUPTIBLE); + if (journal->j_commit_sequence != journal->j_commit_request) + should_sleep = 0; + transaction = journal->j_running_transaction; + if (transaction && time_after_eq(jiffies, + transaction->t_expires)) + should_sleep = 0; + if (journal->j_flags & JBD2_UNMOUNT) + should_sleep = 0; + if (should_sleep) { + write_unlock(&journal->j_state_lock); + schedule(); + write_lock(&journal->j_state_lock); + } + finish_wait(&journal->j_wait_commit, &wait); + } + + jbd2_debug(1, "kjournald2 wakes\n"); + + /* + * Were we woken up by a commit wakeup event? + */ + transaction = journal->j_running_transaction; + if (transaction && time_after_eq(jiffies, transaction->t_expires)) { + journal->j_commit_request = transaction->t_tid; + jbd2_debug(1, "woke because of timeout\n"); + } + goto loop; + +end_loop: + del_timer_sync(&journal->j_commit_timer); + journal->j_task = NULL; + wake_up(&journal->j_wait_done_commit); + jbd2_debug(1, "Journal thread exiting.\n"); + write_unlock(&journal->j_state_lock); + return 0; +} + +static int jbd2_journal_start_thread(journal_t *journal) +{ + struct task_struct *t; + + t = kthread_run(kjournald2, journal, "jbd2/%s", + journal->j_devname); + 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) +{ + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_UNMOUNT; + + while (journal->j_task) { + write_unlock(&journal->j_state_lock); + wake_up(&journal->j_wait_commit); + wait_event(journal->j_wait_done_commit, journal->j_task == NULL); + write_lock(&journal->j_state_lock); + } + write_unlock(&journal->j_state_lock); +} + +/* + * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. + * + * Writes a metadata buffer to a given disk block. The actual IO is not + * performed but a new buffer_head is constructed which labels the data + * to be written with the correct destination disk block. + * + * Any magic-number escaping which needs to be done will cause a + * copy-out here. If the buffer happens to start with the + * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the + * magic number is only written to the log for descripter blocks. In + * this case, we copy the data and replace the first word with 0, and we + * return a result code which indicates that this buffer needs to be + * marked as an escaped buffer in the corresponding log descriptor + * block. The missing word can then be restored when the block is read + * during recovery. + * + * 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 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_head to be used for IO. + * + * + * Return value: + * <0: Error + * >=0: Finished OK + * + * On success: + * Bit 0 set == escape performed on the data + * Bit 1 set == buffer copy-out performed (kfree the data after IO) + */ + +int jbd2_journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + 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 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 + * transaction is allowed to write it, so nobody else is allowed + * to do any IO. + * + * akpm: except if we're journalling data, and write() output is + * also part of a shared mapping, and another thread has + * decided to launch a writepage() against this buffer. + */ + J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in)); + + new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); + + /* keep subsequent assertions sane */ + atomic_set(&new_bh->b_count, 1); + + spin_lock(&jh_in->b_state_lock); +repeat: + /* + * If a new transaction has already done a buffer copy-out, then + * we use that version of the data for the commit. + */ + if (jh_in->b_frozen_data) { + done_copy_out = 1; + new_page = virt_to_page(jh_in->b_frozen_data); + new_offset = offset_in_page(jh_in->b_frozen_data); + } else { + new_page = jh2bh(jh_in)->b_page; + new_offset = offset_in_page(jh2bh(jh_in)->b_data); + } + + mapped_data = kmap_atomic(new_page); + /* + * Fire data frozen trigger if data already wasn't frozen. Do this + * before checking for escaping, as the trigger may modify the magic + * offset. If a copy-out happens afterwards, it will have the correct + * data in the buffer. + */ + if (!done_copy_out) + jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset, + jh_in->b_triggers); + + /* + * Check for escaping + */ + if (*((__be32 *)(mapped_data + new_offset)) == + cpu_to_be32(JBD2_MAGIC_NUMBER)) { + need_copy_out = 1; + do_escape = 1; + } + kunmap_atomic(mapped_data); + + /* + * Do we need to do a data copy? + */ + if (need_copy_out && !done_copy_out) { + char *tmp; + + spin_unlock(&jh_in->b_state_lock); + tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); + if (!tmp) { + brelse(new_bh); + return -ENOMEM; + } + spin_lock(&jh_in->b_state_lock); + if (jh_in->b_frozen_data) { + jbd2_free(tmp, bh_in->b_size); + goto repeat; + } + + jh_in->b_frozen_data = tmp; + mapped_data = kmap_atomic(new_page); + memcpy(tmp, mapped_data + new_offset, bh_in->b_size); + kunmap_atomic(mapped_data); + + new_page = virt_to_page(tmp); + new_offset = offset_in_page(tmp); + done_copy_out = 1; + + /* + * This isn't strictly necessary, as we're using frozen + * data for the escaping, but it keeps consistency with + * b_frozen_data usage. + */ + jh_in->b_frozen_triggers = jh_in->b_triggers; + } + + /* + * Did we need to do an escaping? Now we've done all the + * copying, we can finally do so. + */ + if (do_escape) { + mapped_data = kmap_atomic(new_page); + *((unsigned int *)(mapped_data + new_offset)) = 0; + kunmap_atomic(mapped_data); + } + + set_bh_page(new_bh, new_page, new_offset); + 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); + + *bh_out = new_bh; + + /* + * The to-be-written buffer needs to get moved to the io queue, + * and the original buffer whose contents we are shadowing or + * copying is moved to the transaction's shadow queue. + */ + JBUFFER_TRACE(jh_in, "file as BJ_Shadow"); + 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); + spin_unlock(&jh_in->b_state_lock); + + return do_escape | (done_copy_out << 1); +} + +/* + * Allocation code for the journal file. Manage the space left in the + * journal, so that we can begin checkpointing when appropriate. + */ + +/* + * Called with j_state_lock locked for writing. + * Returns true if a transaction commit was started. + */ +static int __jbd2_log_start_commit(journal_t *journal, tid_t target) +{ + /* Return if the txn has already requested to be committed */ + if (journal->j_commit_request == target) + return 0; + + /* + * The only transaction we can possibly wait upon is the + * currently running transaction (if it exists). Otherwise, + * the target tid must be an old one. + */ + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == target) { + /* + * We want a new commit: OK, mark the request and wakeup the + * commit thread. We do _not_ do the commit ourselves. + */ + + journal->j_commit_request = target; + jbd2_debug(1, "JBD2: requesting commit %u/%u\n", + journal->j_commit_request, + journal->j_commit_sequence); + journal->j_running_transaction->t_requested = jiffies; + wake_up(&journal->j_wait_commit); + return 1; + } else if (!tid_geq(journal->j_commit_request, target)) + /* This should never happen, but if it does, preserve + the evidence before kjournald goes into a loop and + increments j_commit_sequence beyond all recognition. */ + WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", + journal->j_commit_request, + journal->j_commit_sequence, + target, journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0); + return 0; +} + +int jbd2_log_start_commit(journal_t *journal, tid_t tid) +{ + int ret; + + write_lock(&journal->j_state_lock); + ret = __jbd2_log_start_commit(journal, tid); + write_unlock(&journal->j_state_lock); + return ret; +} + +/* + * 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. + */ +static int __jbd2_journal_force_commit(journal_t *journal) +{ + transaction_t *transaction = NULL; + tid_t tid; + int need_to_start = 0, ret = 0; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && !current->journal_info) { + transaction = journal->j_running_transaction; + if (!tid_geq(journal->j_commit_request, transaction->t_tid)) + need_to_start = 1; + } else if (journal->j_committing_transaction) + transaction = journal->j_committing_transaction; + + if (!transaction) { + /* Nothing to commit */ + read_unlock(&journal->j_state_lock); + return 0; + } + tid = transaction->t_tid; + read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); + ret = jbd2_log_wait_commit(journal, tid); + if (!ret) + ret = 1; + + return ret; +} + +/** + * jbd2_journal_force_commit_nested - Force and wait upon a commit if the + * calling process is not within transaction. + * + * @journal: journal to force + * Returns true if progress was made. + * + * This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. + */ +int jbd2_journal_force_commit_nested(journal_t *journal) +{ + int ret; + + ret = __jbd2_journal_force_commit(journal); + return ret > 0; +} + +/** + * jbd2_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; +} + +/* + * Start a commit of the current running transaction (if any). Returns true + * if a transaction is going to be committed (or is currently already + * committing), and fills its tid in at *ptid + */ +int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) +{ + int ret = 0; + + write_lock(&journal->j_state_lock); + if (journal->j_running_transaction) { + tid_t tid = journal->j_running_transaction->t_tid; + + __jbd2_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; + ret = 1; + } else if (journal->j_committing_transaction) { + /* + * If commit has been started, then we have to wait for + * completion of that transaction. + */ + if (ptid) + *ptid = journal->j_committing_transaction->t_tid; + ret = 1; + } + write_unlock(&journal->j_state_lock); + return ret; +} + +/* + * Return 1 if a given transaction has not yet sent barrier request + * connected with a transaction commit. If 0 is returned, transaction + * may or may not have sent the barrier. Used to avoid sending barrier + * twice in common cases. + */ +int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) +{ + int ret = 0; + transaction_t *commit_trans; + + if (!(journal->j_flags & JBD2_BARRIER)) + return 0; + read_lock(&journal->j_state_lock); + /* Transaction already committed? */ + if (tid_geq(journal->j_commit_sequence, tid)) + goto out; + commit_trans = journal->j_committing_transaction; + if (!commit_trans || commit_trans->t_tid != tid) { + ret = 1; + goto out; + } + /* + * Transaction is being committed and we already proceeded to + * submitting a flush to fs partition? + */ + if (journal->j_fs_dev != journal->j_dev) { + if (!commit_trans->t_need_data_flush || + commit_trans->t_state >= T_COMMIT_DFLUSH) + goto out; + } else { + if (commit_trans->t_state >= T_COMMIT_JFLUSH) + goto out; + } + ret = 1; +out: + read_unlock(&journal->j_state_lock); + return ret; +} +EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier); + +/* + * Wait for a specified commit to complete. + * The caller may not hold the journal lock. + */ +int jbd2_log_wait_commit(journal_t *journal, tid_t tid) +{ + int err = 0; + + read_lock(&journal->j_state_lock); +#ifdef CONFIG_PROVE_LOCKING + /* + * Some callers make sure transaction is already committing and in that + * case we cannot block on open handles anymore. So don't warn in that + * case. + */ + if (tid_gt(tid, journal->j_commit_sequence) && + (!journal->j_committing_transaction || + journal->j_committing_transaction->t_tid != tid)) { + read_unlock(&journal->j_state_lock); + jbd2_might_wait_for_commit(journal); + read_lock(&journal->j_state_lock); + } +#endif +#ifdef CONFIG_JBD2_DEBUG + if (!tid_geq(journal->j_commit_request, tid)) { + printk(KERN_ERR + "%s: error: j_commit_request=%u, tid=%u\n", + __func__, journal->j_commit_request, tid); + } +#endif + while (tid_gt(tid, journal->j_commit_sequence)) { + jbd2_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", + tid, journal->j_commit_sequence); + read_unlock(&journal->j_state_lock); + wake_up(&journal->j_wait_commit); + wait_event(journal->j_wait_done_commit, + !tid_gt(tid, journal->j_commit_sequence)); + read_lock(&journal->j_state_lock); + } + read_unlock(&journal->j_state_lock); + + if (unlikely(is_journal_aborted(journal))) + err = -EIO; + return err; +} + +/* + * Start a fast commit. If there's an ongoing fast or full commit wait for + * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY + * if a fast commit is not needed, either because there's an already a commit + * going on or this tid has already been committed. Returns -EINVAL if no jbd2 + * commit has yet been performed. + */ +int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) +{ + if (unlikely(is_journal_aborted(journal))) + return -EIO; + /* + * Fast commits only allowed if at least one full commit has + * been processed. + */ + if (!journal->j_stats.ts_tid) + return -EINVAL; + + write_lock(&journal->j_state_lock); + if (tid <= journal->j_commit_sequence) { + write_unlock(&journal->j_state_lock); + return -EALREADY; + } + + if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_fc_wait, &wait, + TASK_UNINTERRUPTIBLE); + write_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_fc_wait, &wait); + return -EALREADY; + } + journal->j_flags |= JBD2_FAST_COMMIT_ONGOING; + write_unlock(&journal->j_state_lock); + jbd2_journal_lock_updates(journal); + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_begin_commit); + +/* + * Stop a fast commit. If fallback is set, this function starts commit of + * TID tid before any other fast commit can start. + */ +static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) +{ + jbd2_journal_unlock_updates(journal); + if (journal->j_fc_cleanup_callback) + journal->j_fc_cleanup_callback(journal, 0, tid); + write_lock(&journal->j_state_lock); + journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; + if (fallback) + journal->j_flags |= JBD2_FULL_COMMIT_ONGOING; + write_unlock(&journal->j_state_lock); + wake_up(&journal->j_fc_wait); + if (fallback) + return jbd2_complete_transaction(journal, tid); + return 0; +} + +int jbd2_fc_end_commit(journal_t *journal) +{ + return __jbd2_fc_end_commit(journal, 0, false); +} +EXPORT_SYMBOL(jbd2_fc_end_commit); + +int jbd2_fc_end_commit_fallback(journal_t *journal) +{ + tid_t tid; + + read_lock(&journal->j_state_lock); + tid = journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0; + read_unlock(&journal->j_state_lock); + return __jbd2_fc_end_commit(journal, tid, true); +} +EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); + +/* Return 1 when transaction with given tid has already committed. */ +int jbd2_transaction_committed(journal_t *journal, tid_t tid) +{ + int ret = 1; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == tid) + ret = 0; + if (journal->j_committing_transaction && + journal->j_committing_transaction->t_tid == tid) + ret = 0; + read_unlock(&journal->j_state_lock); + return ret; +} +EXPORT_SYMBOL(jbd2_transaction_committed); + +/* + * When this function returns the transaction corresponding to tid + * will be completed. If the transaction has currently running, start + * committing that transaction before waiting for it to complete. If + * the transaction id is stale, it is by definition already completed, + * so just return SUCCESS. + */ +int jbd2_complete_transaction(journal_t *journal, tid_t tid) +{ + int need_to_wait = 1; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == tid) { + if (journal->j_commit_request != tid) { + /* transaction not yet started, so request it */ + read_unlock(&journal->j_state_lock); + jbd2_log_start_commit(journal, tid); + goto wait_commit; + } + } else if (!(journal->j_committing_transaction && + journal->j_committing_transaction->t_tid == tid)) + need_to_wait = 0; + read_unlock(&journal->j_state_lock); + if (!need_to_wait) + return 0; +wait_commit: + return jbd2_log_wait_commit(journal, tid); +} +EXPORT_SYMBOL(jbd2_complete_transaction); + +/* + * Log buffer allocation routines: + */ + +int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) +{ + unsigned long blocknr; + + write_lock(&journal->j_state_lock); + J_ASSERT(journal->j_free > 1); + + blocknr = journal->j_head; + journal->j_head++; + journal->j_free--; + if (journal->j_head == journal->j_last) + journal->j_head = journal->j_first; + write_unlock(&journal->j_state_lock); + return jbd2_journal_bmap(journal, blocknr, retp); +} + +/* Map one fast commit buffer for use by the file system */ +int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) +{ + unsigned long long pblock; + unsigned long blocknr; + int ret = 0; + struct buffer_head *bh; + int fc_off; + + *bh_out = NULL; + + if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { + fc_off = journal->j_fc_off; + blocknr = journal->j_fc_first + fc_off; + journal->j_fc_off++; + } else { + ret = -EINVAL; + } + + if (ret) + return ret; + + ret = jbd2_journal_bmap(journal, blocknr, &pblock); + if (ret) + return ret; + + bh = __getblk(journal->j_dev, pblock, journal->j_blocksize); + if (!bh) + return -ENOMEM; + + + journal->j_fc_wbuf[fc_off] = bh; + + *bh_out = bh; + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_get_buf); + +/* + * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf + * for completion. + */ +int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) +{ + struct buffer_head *bh; + int i, j_fc_off; + + j_fc_off = journal->j_fc_off; + + /* + * Wait in reverse order to minimize chances of us being woken up before + * all IOs have completed + */ + for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { + bh = journal->j_fc_wbuf[i]; + wait_on_buffer(bh); + /* + * Update j_fc_off so jbd2_fc_release_bufs can release remain + * buffer head. + */ + if (unlikely(!buffer_uptodate(bh))) { + journal->j_fc_off = i + 1; + return -EIO; + } + put_bh(bh); + journal->j_fc_wbuf[i] = NULL; + } + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_wait_bufs); + +int jbd2_fc_release_bufs(journal_t *journal) +{ + struct buffer_head *bh; + int i, j_fc_off; + + j_fc_off = journal->j_fc_off; + + for (i = j_fc_off - 1; i >= 0; i--) { + bh = journal->j_fc_wbuf[i]; + if (!bh) + break; + put_bh(bh); + journal->j_fc_wbuf[i] = NULL; + } + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_release_bufs); + +/* + * Conversion of logical to physical block numbers for the journal + * + * On external journals the journal blocks are identity-mapped, so + * this is a no-op. If needed, we can use j_blk_offset - everything is + * ready. + */ +int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, + unsigned long long *retp) +{ + int err = 0; + unsigned long long ret; + sector_t block = 0; + + if (journal->j_inode) { + block = blocknr; + ret = bmap(journal->j_inode, &block); + + if (ret || !block) { + printk(KERN_ALERT "%s: journal block not found " + "at offset %lu on %s\n", + __func__, blocknr, journal->j_devname); + err = -EIO; + jbd2_journal_abort(journal, err); + } else { + *retp = block; + } + + } else { + *retp = blocknr; /* +journal->j_blk_offset */ + } + return err; +} + +/* + * We play buffer_head aliasing tricks to write data/metadata blocks to + * the journal without copying their contents, but for journal + * descriptor blocks we do need to generate bona fide buffers. + * + * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying + * the buffer's contents they really should run flush_dcache_page(bh->b_page). + * But we don't bother doing that, so there will be coherency problems with + * mmaps of blockdevs which hold live JBD-controlled filesystems. + */ +struct buffer_head * +jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) +{ + journal_t *journal = transaction->t_journal; + struct buffer_head *bh; + unsigned long long blocknr; + journal_header_t *header; + int err; + + err = jbd2_journal_next_log_block(journal, &blocknr); + + if (err) + return NULL; + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) + return NULL; + atomic_dec(&transaction->t_outstanding_credits); + lock_buffer(bh); + memset(bh->b_data, 0, journal->j_blocksize); + header = (journal_header_t *)bh->b_data; + header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); + header->h_blocktype = cpu_to_be32(type); + header->h_sequence = cpu_to_be32(transaction->t_tid); + set_buffer_uptodate(bh); + unlock_buffer(bh); + BUFFER_TRACE(bh, "return this buffer"); + return bh; +} + +void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh) +{ + struct jbd2_journal_block_tail *tail; + __u32 csum; + + if (!jbd2_journal_has_csum_v2or3(j)) + return; + + tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - + sizeof(struct jbd2_journal_block_tail)); + tail->t_checksum = 0; + csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); + tail->t_checksum = cpu_to_be32(csum); +} + +/* + * Return tid of the oldest transaction in the journal and block in the journal + * where the transaction starts. + * + * If the journal is now empty, return which will be the next transaction ID + * we will write and where will that transaction start. + * + * The return value is 0 if journal tail cannot be pushed any further, 1 if + * it can. + */ +int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, + unsigned long *block) +{ + transaction_t *transaction; + int ret; + + read_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + transaction = journal->j_checkpoint_transactions; + if (transaction) { + *tid = transaction->t_tid; + *block = transaction->t_log_start; + } else if ((transaction = journal->j_committing_transaction) != NULL) { + *tid = transaction->t_tid; + *block = transaction->t_log_start; + } else if ((transaction = journal->j_running_transaction) != NULL) { + *tid = transaction->t_tid; + *block = journal->j_head; + } else { + *tid = journal->j_transaction_sequence; + *block = journal->j_head; + } + ret = tid_gt(*tid, journal->j_tail_sequence); + spin_unlock(&journal->j_list_lock); + read_unlock(&journal->j_state_lock); + + return ret; +} + +/* + * Update information in journal structure and in on disk journal superblock + * about log tail. This function does not check whether information passed in + * really pushes log tail further. It's responsibility of the caller to make + * sure provided log tail information is valid (e.g. by holding + * j_checkpoint_mutex all the time between computing log tail and calling this + * function as is the case with jbd2_cleanup_journal_tail()). + * + * Requires j_checkpoint_mutex + */ +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) +{ + unsigned long freed; + int ret; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + + /* + * We cannot afford for write to remain in drive's caches since as + * soon as we update j_tail, next transaction can start reusing journal + * space and if we lose sb update during power failure we'd replay + * old transaction with possibly newly overwritten data. + */ + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA); + if (ret) + goto out; + + write_lock(&journal->j_state_lock); + freed = block - journal->j_tail; + if (block < journal->j_tail) + freed += journal->j_last - journal->j_first; + + trace_jbd2_update_log_tail(journal, tid, block, freed); + jbd2_debug(1, + "Cleaning journal tail from %u to %u (offset %lu), " + "freeing %lu\n", + journal->j_tail_sequence, tid, block, freed); + + journal->j_free += freed; + journal->j_tail_sequence = tid; + journal->j_tail = block; + write_unlock(&journal->j_state_lock); + +out: + return ret; +} + +/* + * This is a variation of __jbd2_update_log_tail which checks for validity of + * provided log tail and locks j_checkpoint_mutex. So it is safe against races + * with other threads updating log tail. + */ +void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) +{ + mutex_lock_io(&journal->j_checkpoint_mutex); + if (tid_gt(tid, journal->j_tail_sequence)) + __jbd2_update_log_tail(journal, tid, block); + mutex_unlock(&journal->j_checkpoint_mutex); +} + +struct jbd2_stats_proc_session { + journal_t *journal; + struct transaction_stats_s *stats; + int start; + int max; +}; + +static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) +{ + return *pos ? NULL : SEQ_START_TOKEN; +} + +static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos) +{ + (*pos)++; + return NULL; +} + +static int jbd2_seq_info_show(struct seq_file *seq, void *v) +{ + struct jbd2_stats_proc_session *s = seq->private; + + if (v != SEQ_START_TOKEN) + return 0; + seq_printf(seq, "%lu transactions (%lu requested), " + "each up to %u blocks\n", + s->stats->ts_tid, s->stats->ts_requested, + s->journal->j_max_transaction_buffers); + if (s->stats->ts_tid == 0) + return 0; + seq_printf(seq, "average: \n %ums waiting for transaction\n", + jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); + seq_printf(seq, " %ums request delay\n", + (s->stats->ts_requested == 0) ? 0 : + jiffies_to_msecs(s->stats->run.rs_request_delay / + s->stats->ts_requested)); + seq_printf(seq, " %ums running transaction\n", + jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); + seq_printf(seq, " %ums transaction was being locked\n", + jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); + seq_printf(seq, " %ums flushing data (in ordered mode)\n", + jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); + seq_printf(seq, " %ums logging transaction\n", + jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); + seq_printf(seq, " %lluus average transaction commit time\n", + div_u64(s->journal->j_average_commit_time, 1000)); + seq_printf(seq, " %lu handles per transaction\n", + s->stats->run.rs_handle_count / s->stats->ts_tid); + seq_printf(seq, " %lu blocks per transaction\n", + s->stats->run.rs_blocks / s->stats->ts_tid); + seq_printf(seq, " %lu logged blocks per transaction\n", + s->stats->run.rs_blocks_logged / s->stats->ts_tid); + return 0; +} + +static void jbd2_seq_info_stop(struct seq_file *seq, void *v) +{ +} + +static const struct seq_operations jbd2_seq_info_ops = { + .start = jbd2_seq_info_start, + .next = jbd2_seq_info_next, + .stop = jbd2_seq_info_stop, + .show = jbd2_seq_info_show, +}; + +static int jbd2_seq_info_open(struct inode *inode, struct file *file) +{ + journal_t *journal = pde_data(inode); + struct jbd2_stats_proc_session *s; + int rc, size; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return -ENOMEM; + size = sizeof(struct transaction_stats_s); + s->stats = kmalloc(size, GFP_KERNEL); + if (s->stats == NULL) { + kfree(s); + return -ENOMEM; + } + spin_lock(&journal->j_history_lock); + memcpy(s->stats, &journal->j_stats, size); + s->journal = journal; + spin_unlock(&journal->j_history_lock); + + rc = seq_open(file, &jbd2_seq_info_ops); + if (rc == 0) { + struct seq_file *m = file->private_data; + m->private = s; + } else { + kfree(s->stats); + kfree(s); + } + return rc; + +} + +static int jbd2_seq_info_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct jbd2_stats_proc_session *s = seq->private; + kfree(s->stats); + kfree(s); + return seq_release(inode, file); +} + +static const struct proc_ops jbd2_info_proc_ops = { + .proc_open = jbd2_seq_info_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = jbd2_seq_info_release, +}; + +static struct proc_dir_entry *proc_jbd2_stats; + +static void jbd2_stats_proc_init(journal_t *journal) +{ + journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); + if (journal->j_proc_entry) { + proc_create_data("info", S_IRUGO, journal->j_proc_entry, + &jbd2_info_proc_ops, journal); + } +} + +static void jbd2_stats_proc_exit(journal_t *journal) +{ + remove_proc_entry("info", journal->j_proc_entry); + remove_proc_entry(journal->j_devname, proc_jbd2_stats); +} + +/* Minimum size of descriptor tag */ +static int jbd2_min_tag_size(void) +{ + /* + * Tag with 32-bit block numbers does not use last four bytes of the + * structure + */ + return sizeof(journal_block_tag_t) - 4; +} + +/** + * jbd2_journal_shrink_scan() + * @shrink: shrinker to work on + * @sc: reclaim request to process + * + * Scan the checkpointed buffer on the checkpoint list and release the + * journal_head. + */ +static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long nr_to_scan = sc->nr_to_scan; + unsigned long nr_shrunk; + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count); + + nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan); + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count); + + return nr_shrunk; +} + +/** + * jbd2_journal_shrink_count() + * @shrink: shrinker to work on + * @sc: reclaim request to process + * + * Count the number of checkpoint buffers on the checkpoint list. + */ +static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_count(journal, sc->nr_to_scan, count); + + return count; +} + +/* + * Management for journal control blocks: functions to create and + * destroy journal_t structures, and to initialise and read existing + * journal blocks from disk. */ + +/* First: create and setup a journal_t object in memory. We initialise + * very few fields yet: that has to wait until we have created the + * journal structures from from scratch, or loaded them from disk. */ + +static journal_t *journal_init_common(struct block_device *bdev, + struct block_device *fs_dev, + unsigned long long start, int len, int blocksize) +{ + static struct lock_class_key jbd2_trans_commit_key; + journal_t *journal; + int err; + struct buffer_head *bh; + int n; + + journal = kzalloc(sizeof(*journal), GFP_KERNEL); + if (!journal) + return NULL; + + init_waitqueue_head(&journal->j_wait_transaction_locked); + init_waitqueue_head(&journal->j_wait_done_commit); + init_waitqueue_head(&journal->j_wait_commit); + init_waitqueue_head(&journal->j_wait_updates); + init_waitqueue_head(&journal->j_wait_reserved); + init_waitqueue_head(&journal->j_fc_wait); + mutex_init(&journal->j_abort_mutex); + mutex_init(&journal->j_barrier); + mutex_init(&journal->j_checkpoint_mutex); + spin_lock_init(&journal->j_revoke_lock); + spin_lock_init(&journal->j_list_lock); + rwlock_init(&journal->j_state_lock); + + 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; + + /* Set up a default-sized revoke table for the new mount. */ + err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); + if (err) + goto err_cleanup; + + spin_lock_init(&journal->j_history_lock); + + lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", + &jbd2_trans_commit_key, 0); + + /* journal descriptor can store up to n blocks -bzzz */ + journal->j_blocksize = blocksize; + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_total_len = len; + /* We need enough buffers to write out full descriptor block. */ + n = journal->j_blocksize / jbd2_min_tag_size(); + journal->j_wbufsize = n; + journal->j_fc_wbuf = NULL; + journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), + GFP_KERNEL); + if (!journal->j_wbuf) + goto err_cleanup; + + bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); + if (!bh) { + pr_err("%s: Cannot get buffer for journal superblock\n", + __func__); + goto err_cleanup; + } + journal->j_sb_buffer = bh; + journal->j_superblock = (journal_superblock_t *)bh->b_data; + + journal->j_shrink_transaction = NULL; + journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; + journal->j_shrinker.count_objects = jbd2_journal_shrink_count; + journal->j_shrinker.seeks = DEFAULT_SEEKS; + journal->j_shrinker.batch = journal->j_max_transaction_buffers; + + if (percpu_counter_init(&journal->j_checkpoint_jh_count, 0, GFP_KERNEL)) + goto err_cleanup; + + if (register_shrinker(&journal->j_shrinker, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev))) { + percpu_counter_destroy(&journal->j_checkpoint_jh_count); + goto err_cleanup; + } + return journal; + +err_cleanup: + brelse(journal->j_sb_buffer); + kfree(journal->j_wbuf); + jbd2_journal_destroy_revoke(journal); + kfree(journal); + return NULL; +} + +/* jbd2_journal_init_dev and jbd2_journal_init_inode: + * + * Create a journal structure assigned some fixed set of disk blocks to + * the journal. We don't actually touch those disk blocks yet, but we + * need to set up all of the mapping information to tell the journaling + * system where the journal blocks are. + * + */ + +/** + * journal_t * jbd2_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: Length of the journal in blocks. + * @blocksize: blocksize of journalling device + * + * Returns: a newly created journal_t * + * + * jbd2_journal_init_dev creates a journal which maps a fixed contiguous + * range of blocks on an arbitrary block device. + * + */ +journal_t *jbd2_journal_init_dev(struct block_device *bdev, + struct block_device *fs_dev, + unsigned long long start, int len, int blocksize) +{ + journal_t *journal; + + journal = journal_init_common(bdev, fs_dev, start, len, blocksize); + if (!journal) + return NULL; + + snprintf(journal->j_devname, sizeof(journal->j_devname), + "%pg", journal->j_dev); + strreplace(journal->j_devname, '/', '!'); + jbd2_stats_proc_init(journal); + + return journal; +} + +/** + * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode. + * @inode: An inode to create the journal in + * + * jbd2_journal_init_inode creates a journal which maps an on-disk inode as + * the journal. The inode must exist already, must support bmap() and + * must have all data blocks preallocated. + */ +journal_t *jbd2_journal_init_inode(struct inode *inode) +{ + journal_t *journal; + sector_t blocknr; + char *p; + int err = 0; + + blocknr = 0; + err = bmap(inode, &blocknr); + + if (err || !blocknr) { + pr_err("%s: Cannot locate journal superblock\n", + __func__); + return NULL; + } + + jbd2_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", + inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, + inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); + + journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev, + blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits, + inode->i_sb->s_blocksize); + if (!journal) + return NULL; + + journal->j_inode = inode; + snprintf(journal->j_devname, sizeof(journal->j_devname), + "%pg", journal->j_dev); + p = strreplace(journal->j_devname, '/', '!'); + sprintf(p, "-%lu", journal->j_inode->i_ino); + jbd2_stats_proc_init(journal); + + return journal; +} + +/* + * If the journal init or create aborts, we need to mark the journal + * superblock as being NULL to prevent the journal destroy from writing + * back a bogus superblock. + */ +static void journal_fail_superblock(journal_t *journal) +{ + struct buffer_head *bh = journal->j_sb_buffer; + brelse(bh); + journal->j_sb_buffer = NULL; +} + +/* + * Given a journal_t structure, initialise the various fields for + * startup of a new journaling session. We use this both when creating + * a journal, and after recovering an old journal to reset it for + * subsequent use. + */ + +static int journal_reset(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long first, last; + + first = be32_to_cpu(sb->s_first); + last = be32_to_cpu(sb->s_maxlen); + if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) { + printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n", + first, last); + journal_fail_superblock(journal); + return -EINVAL; + } + + journal->j_first = first; + journal->j_last = last; + + journal->j_head = journal->j_first; + journal->j_tail = journal->j_first; + journal->j_free = journal->j_last - journal->j_first; + + journal->j_tail_sequence = journal->j_transaction_sequence; + journal->j_commit_sequence = journal->j_transaction_sequence - 1; + journal->j_commit_request = journal->j_commit_sequence; + + journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); + + /* + * Now that journal recovery is done, turn fast commits off here. This + * way, if fast commit was enabled before the crash but if now FS has + * disabled it, we don't enable fast commits. + */ + jbd2_clear_feature_fast_commit(journal); + + /* + * As a special case, if the on-disk copy is already marked as needing + * no recovery (s_start == 0), then we can safely defer the superblock + * update until the next commit by setting JBD2_FLUSHED. This avoids + * attempting a write to a potential-readonly device. + */ + if (sb->s_start == 0) { + jbd2_debug(1, "JBD2: Skipping superblock update on recovered sb " + "(start %ld, seq %u, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, + journal->j_errno); + journal->j_flags |= JBD2_FLUSHED; + } else { + /* Lock here to make assertions happy... */ + mutex_lock_io(&journal->j_checkpoint_mutex); + /* + * Update log tail information. We use REQ_FUA since new + * transaction will start reusing journal space and so we + * must make sure information about current log tail is on + * disk before that. + */ + jbd2_journal_update_sb_log_tail(journal, + journal->j_tail_sequence, + journal->j_tail, REQ_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } + return jbd2_journal_start_thread(journal); +} + +/* + * This function expects that the caller will have locked the journal + * buffer head, and will return with it unlocked + */ +static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags) +{ + struct buffer_head *bh = journal->j_sb_buffer; + journal_superblock_t *sb = journal->j_superblock; + int ret = 0; + + /* Buffer got discarded which means block device got invalidated */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + + /* + * Always set high priority flags to exempt from block layer's + * QOS policies, e.g. writeback throttle. + */ + write_flags |= JBD2_JOURNAL_REQ_FLAGS; + if (!(journal->j_flags & JBD2_BARRIER)) + write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + + if (buffer_write_io_error(bh)) { + /* + * Oh, dear. A previous attempt to write the journal + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. + */ + printk(KERN_ERR "JBD2: previous I/O error detected " + "for journal superblock update for %s.\n", + journal->j_devname); + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + } + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(journal, sb); + get_bh(bh); + bh->b_end_io = end_buffer_write_sync; + submit_bh(REQ_OP_WRITE | write_flags, bh); + wait_on_buffer(bh); + if (buffer_write_io_error(bh)) { + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + ret = -EIO; + } + if (ret) { + printk(KERN_ERR "JBD2: I/O error when updating journal superblock for %s.\n", + journal->j_devname); + if (!is_journal_aborted(journal)) + jbd2_journal_abort(journal, ret); + } + + return ret; +} + +/** + * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk. + * @journal: The journal to update. + * @tail_tid: TID of the new transaction at the tail of the log + * @tail_block: The first block of the transaction at the tail of the log + * @write_flags: Flags for the journal sb write operation + * + * Update a journal's superblock information about log tail and write it to + * disk, waiting for the IO to complete. + */ +int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, + unsigned long tail_block, + blk_opf_t write_flags) +{ + journal_superblock_t *sb = journal->j_superblock; + int ret; + + if (is_journal_aborted(journal)) + return -EIO; + if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) { + jbd2_journal_abort(journal, -EIO); + return -EIO; + } + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + jbd2_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", + tail_block, tail_tid); + + lock_buffer(journal->j_sb_buffer); + sb->s_sequence = cpu_to_be32(tail_tid); + sb->s_start = cpu_to_be32(tail_block); + + ret = jbd2_write_superblock(journal, write_flags); + if (ret) + goto out; + + /* Log is no longer empty */ + write_lock(&journal->j_state_lock); + WARN_ON(!sb->s_sequence); + journal->j_flags &= ~JBD2_FLUSHED; + write_unlock(&journal->j_state_lock); + +out: + return ret; +} + +/** + * jbd2_mark_journal_empty() - Mark on disk journal as empty. + * @journal: The journal to update. + * @write_flags: Flags for the journal sb write operation + * + * Update a journal's dynamic superblock fields to show that journal is empty. + * Write updated superblock to disk waiting for IO to complete. + */ +static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags) +{ + journal_superblock_t *sb = journal->j_superblock; + bool had_fast_commit = false; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + lock_buffer(journal->j_sb_buffer); + if (sb->s_start == 0) { /* Is it already empty? */ + unlock_buffer(journal->j_sb_buffer); + return; + } + + jbd2_debug(1, "JBD2: Marking journal as empty (seq %u)\n", + journal->j_tail_sequence); + + sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); + sb->s_start = cpu_to_be32(0); + if (jbd2_has_feature_fast_commit(journal)) { + /* + * When journal is clean, no need to commit fast commit flag and + * make file system incompatible with older kernels. + */ + jbd2_clear_feature_fast_commit(journal); + had_fast_commit = true; + } + + jbd2_write_superblock(journal, write_flags); + + if (had_fast_commit) + jbd2_set_feature_fast_commit(journal); + + /* Log is no longer empty */ + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_FLUSHED; + write_unlock(&journal->j_state_lock); +} + +/** + * __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock) + * @journal: The journal to erase. + * @flags: A discard/zeroout request is sent for each physically contigous + * region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or + * JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation + * to perform. + * + * Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes + * will be explicitly written if no hardware offload is available, see + * blkdev_issue_zeroout for more details. + */ +static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) +{ + int err = 0; + unsigned long block, log_offset; /* logical */ + unsigned long long phys_block, block_start, block_stop; /* physical */ + loff_t byte_start, byte_stop, byte_count; + + /* flags must be set to either discard or zeroout */ + if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags || + ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) + return -EINVAL; + + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(journal->j_dev)) + return -EOPNOTSUPP; + + /* + * lookup block mapping and issue discard/zeroout for each + * contiguous region + */ + log_offset = be32_to_cpu(journal->j_superblock->s_first); + block_start = ~0ULL; + for (block = log_offset; block < journal->j_total_len; block++) { + err = jbd2_journal_bmap(journal, block, &phys_block); + if (err) { + pr_err("JBD2: bad block at offset %lu", block); + return err; + } + + if (block_start == ~0ULL) { + block_start = phys_block; + block_stop = block_start - 1; + } + + /* + * last block not contiguous with current block, + * process last contiguous region and return to this block on + * next loop + */ + if (phys_block != block_stop + 1) { + block--; + } else { + block_stop++; + /* + * if this isn't the last block of journal, + * no need to process now because next block may also + * be part of this contiguous region + */ + if (block != journal->j_total_len - 1) + continue; + } + + /* + * end of contiguous region or this is last block of journal, + * take care of the region + */ + byte_start = block_start * journal->j_blocksize; + byte_stop = block_stop * journal->j_blocksize; + byte_count = (block_stop - block_start + 1) * + journal->j_blocksize; + + truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping, + byte_start, byte_stop); + + if (flags & JBD2_JOURNAL_FLUSH_DISCARD) { + err = blkdev_issue_discard(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS); + } else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) { + err = blkdev_issue_zeroout(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS, 0); + } + + if (unlikely(err != 0)) { + pr_err("JBD2: (error %d) unable to wipe journal at physical blocks %llu - %llu", + err, block_start, block_stop); + return err; + } + + /* reset start and stop after processing a region */ + block_start = ~0ULL; + } + + return blkdev_issue_flush(journal->j_dev); +} + +/** + * jbd2_journal_update_sb_errno() - Update error in the journal. + * @journal: The journal to update. + * + * Update a journal's errno. Write updated superblock to disk waiting for IO + * to complete. + */ +void jbd2_journal_update_sb_errno(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + int errcode; + + lock_buffer(journal->j_sb_buffer); + errcode = journal->j_errno; + if (errcode == -ESHUTDOWN) + errcode = 0; + jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); + sb->s_errno = cpu_to_be32(errcode); + + jbd2_write_superblock(journal, REQ_FUA); +} +EXPORT_SYMBOL(jbd2_journal_update_sb_errno); + +static int journal_revoke_records_per_block(journal_t *journal) +{ + int record_size; + int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); + + if (jbd2_has_feature_64bit(journal)) + record_size = 8; + else + record_size = 4; + + if (jbd2_journal_has_csum_v2or3(journal)) + space -= sizeof(struct jbd2_journal_block_tail); + return space / record_size; +} + +/* + * Read the superblock for a given journal, performing initial + * validation of the format. + */ +static int journal_get_superblock(journal_t *journal) +{ + struct buffer_head *bh; + journal_superblock_t *sb; + int err; + + bh = journal->j_sb_buffer; + + J_ASSERT(bh != NULL); + err = bh_read(bh, 0); + if (err < 0) { + printk(KERN_ERR + "JBD2: IO error reading journal superblock\n"); + goto out; + } + + if (buffer_verified(bh)) + return 0; + + sb = journal->j_superblock; + + err = -EINVAL; + + if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || + sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { + printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); + goto out; + } + + switch(be32_to_cpu(sb->s_header.h_blocktype)) { + case JBD2_SUPERBLOCK_V1: + journal->j_format_version = 1; + break; + case JBD2_SUPERBLOCK_V2: + journal->j_format_version = 2; + break; + default: + printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); + goto out; + } + + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { + printk(KERN_WARNING "JBD2: journal file too short\n"); + goto out; + } + + if (be32_to_cpu(sb->s_first) == 0 || + be32_to_cpu(sb->s_first) >= journal->j_total_len) { + printk(KERN_WARNING + "JBD2: Invalid start block of journal: %u\n", + be32_to_cpu(sb->s_first)); + goto out; + } + + if (jbd2_has_feature_csum2(journal) && + jbd2_has_feature_csum3(journal)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + goto out; + } + + if (jbd2_journal_has_csum_v2or3_feature(journal) && + jbd2_has_feature_checksum(journal)) { + /* Can't have checksum v1 and v2 on at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " + "at the same time!\n"); + goto out; + } + + if (!jbd2_verify_csum_type(journal, sb)) { + printk(KERN_ERR "JBD2: Unknown checksum type\n"); + goto out; + } + + /* Load the checksum driver */ + if (jbd2_journal_has_csum_v2or3_feature(journal)) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); + err = PTR_ERR(journal->j_chksum_driver); + journal->j_chksum_driver = NULL; + goto out; + } + } + + if (jbd2_journal_has_csum_v2or3(journal)) { + /* Check superblock checksum */ + if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { + printk(KERN_ERR "JBD2: journal checksum error\n"); + err = -EFSBADCRC; + goto out; + } + + /* Precompute checksum seed for all metadata */ + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + } + + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); + set_buffer_verified(bh); + + return 0; + +out: + journal_fail_superblock(journal); + return err; +} + +/* + * Load the on-disk journal superblock and read the key fields into the + * journal_t. + */ + +static int load_superblock(journal_t *journal) +{ + int err; + journal_superblock_t *sb; + int num_fc_blocks; + + err = journal_get_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + + journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); + journal->j_tail = be32_to_cpu(sb->s_start); + journal->j_first = be32_to_cpu(sb->s_first); + journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); + + if (jbd2_has_feature_fast_commit(journal)) { + journal->j_fc_last = be32_to_cpu(sb->s_maxlen); + num_fc_blocks = jbd2_journal_get_num_fc_blks(sb); + if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) + journal->j_last = journal->j_fc_last - num_fc_blocks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + } + + return 0; +} + + +/** + * jbd2_journal_load() - Read journal from disk. + * @journal: Journal to act on. + * + * Given a journal_t structure which tells us which disk blocks contain + * a journal, read the journal from disk to initialise the in-memory + * structures. + */ +int jbd2_journal_load(journal_t *journal) +{ + int err; + journal_superblock_t *sb; + + err = load_superblock(journal); + if (err) + return err; + + sb = journal->j_superblock; + /* If this is a V2 superblock, then we have to check the + * features flags on it. */ + + if (journal->j_format_version >= 2) { + if ((sb->s_feature_ro_compat & + ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || + (sb->s_feature_incompat & + ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { + printk(KERN_WARNING + "JBD2: Unrecognised features on journal\n"); + return -EINVAL; + } + } + + /* + * Create a slab for this blocksize + */ + err = jbd2_journal_create_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 (jbd2_journal_recover(journal)) + goto recovery_error; + + if (journal->j_failed_commit) { + printk(KERN_ERR "JBD2: journal transaction %u on %s " + "is corrupt.\n", journal->j_failed_commit, + journal->j_devname); + return -EFSCORRUPTED; + } + /* + * clear JBD2_ABORT flag initialized in journal_init_common + * here to update log tail information with the newest seq. + */ + journal->j_flags &= ~JBD2_ABORT; + + /* OK, we've finished with the dynamic journal bits: + * reinitialise the dynamic contents of the superblock in memory + * and reset them on disk. */ + if (journal_reset(journal)) + goto recovery_error; + + journal->j_flags |= JBD2_LOADED; + return 0; + +recovery_error: + printk(KERN_WARNING "JBD2: recovery failed\n"); + return -EIO; +} + +/** + * jbd2_journal_destroy() - Release a journal_t structure. + * @journal: Journal to act on. + * + * 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. + */ +int jbd2_journal_destroy(journal_t *journal) +{ + int err = 0; + + /* Wait for the commit thread to wake up and die. */ + journal_kill_thread(journal); + + /* Force a final log commit */ + if (journal->j_running_transaction) + jbd2_journal_commit_transaction(journal); + + /* Force any old transactions to disk */ + + /* Totally anal locking here... */ + spin_lock(&journal->j_list_lock); + while (journal->j_checkpoint_transactions != NULL) { + spin_unlock(&journal->j_list_lock); + mutex_lock_io(&journal->j_checkpoint_mutex); + err = jbd2_log_do_checkpoint(journal); + mutex_unlock(&journal->j_checkpoint_mutex); + /* + * If checkpointing failed, just free the buffers to avoid + * looping forever + */ + if (err) { + jbd2_journal_destroy_checkpoint(journal); + spin_lock(&journal->j_list_lock); + break; + } + spin_lock(&journal->j_list_lock); + } + + J_ASSERT(journal->j_running_transaction == NULL); + J_ASSERT(journal->j_committing_transaction == NULL); + J_ASSERT(journal->j_checkpoint_transactions == NULL); + spin_unlock(&journal->j_list_lock); + + /* + * OK, all checkpoint transactions have been checked, now check the + * write out io error flag and abort the journal if some buffer failed + * to write back to the original location, otherwise the filesystem + * may become inconsistent. + */ + if (!is_journal_aborted(journal) && + test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) + jbd2_journal_abort(journal, -EIO); + + if (journal->j_sb_buffer) { + if (!is_journal_aborted(journal)) { + mutex_lock_io(&journal->j_checkpoint_mutex); + + write_lock(&journal->j_state_lock); + journal->j_tail_sequence = + ++journal->j_transaction_sequence; + write_unlock(&journal->j_state_lock); + + jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } else + err = -EIO; + brelse(journal->j_sb_buffer); + } + + if (journal->j_shrinker.flags & SHRINKER_REGISTERED) { + percpu_counter_destroy(&journal->j_checkpoint_jh_count); + unregister_shrinker(&journal->j_shrinker); + } + if (journal->j_proc_entry) + jbd2_stats_proc_exit(journal); + iput(journal->j_inode); + if (journal->j_revoke) + jbd2_journal_destroy_revoke(journal); + if (journal->j_chksum_driver) + crypto_free_shash(journal->j_chksum_driver); + kfree(journal->j_fc_wbuf); + kfree(journal->j_wbuf); + kfree(journal); + + return err; +} + + +/** + * jbd2_journal_check_used_features() - Check if features specified are used. + * @journal: Journal to check. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Check whether the journal uses all of a given set of + * features. Return true (non-zero) if it does. + **/ + +int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + journal_superblock_t *sb; + + if (!compat && !ro && !incompat) + return 1; + /* Load journal superblock if it is not loaded yet. */ + if (journal->j_format_version == 0 && + journal_get_superblock(journal) != 0) + return 0; + if (journal->j_format_version == 1) + return 0; + + sb = journal->j_superblock; + + if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) && + ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) && + ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat)) + return 1; + + return 0; +} + +/** + * jbd2_journal_check_available_features() - Check feature set in journalling layer + * @journal: Journal to check. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Check whether the journaling code supports the use of + * all of a given set of features on this journal. Return true + * (non-zero) if it can. */ + +int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + if (!compat && !ro && !incompat) + return 1; + + /* We can support any known requested features iff the + * superblock is in version 2. Otherwise we fail to support any + * extended sb features. */ + + if (journal->j_format_version != 2) + return 0; + + if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat && + (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro && + (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat) + return 1; + + return 0; +} + +static int +jbd2_journal_initialize_fast_commit(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long num_fc_blks; + + num_fc_blks = jbd2_journal_get_num_fc_blks(sb); + if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) + return -ENOSPC; + + /* Are we called twice? */ + WARN_ON(journal->j_fc_wbuf != NULL); + journal->j_fc_wbuf = kmalloc_array(num_fc_blks, + sizeof(struct buffer_head *), GFP_KERNEL); + if (!journal->j_fc_wbuf) + return -ENOMEM; + + journal->j_fc_wbufsize = num_fc_blks; + journal->j_fc_last = journal->j_last; + journal->j_last = journal->j_fc_last - num_fc_blks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + journal->j_free = journal->j_last - journal->j_first; + journal->j_max_transaction_buffers = + jbd2_journal_get_max_txn_bufs(journal); + + return 0; +} + +/** + * jbd2_journal_set_features() - Mark a given journal feature in the superblock + * @journal: Journal to act on. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Mark a given journal feature as present on the + * superblock. Returns true if the requested features could be set. + * + */ + +int jbd2_journal_set_features(journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ +#define INCOMPAT_FEATURE_ON(f) \ + ((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f))) +#define COMPAT_FEATURE_ON(f) \ + ((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f))) + journal_superblock_t *sb; + + if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) + return 1; + + if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) + return 0; + + /* If enabling v2 checksums, turn on v3 instead */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { + incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; + incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; + } + + /* Asking for checksumming v3 and v1? Only give them v3. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && + compat & JBD2_FEATURE_COMPAT_CHECKSUM) + compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; + + jbd2_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", + compat, ro, incompat); + + sb = journal->j_superblock; + + if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { + if (jbd2_journal_initialize_fast_commit(journal)) { + pr_err("JBD2: Cannot enable fast commits.\n"); + return 0; + } + } + + /* Load the checksum driver if necessary */ + if ((journal->j_chksum_driver == NULL) && + INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); + journal->j_chksum_driver = NULL; + return 0; + } + /* Precompute checksum seed for all metadata */ + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + } + + lock_buffer(journal->j_sb_buffer); + + /* If enabling v3 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { + sb->s_checksum_type = JBD2_CRC32C_CHKSUM; + sb->s_feature_compat &= + ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); + } + + /* If enabling v1 checksums, downgrade superblock */ + if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) + sb->s_feature_incompat &= + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | + JBD2_FEATURE_INCOMPAT_CSUM_V3); + + sb->s_feature_compat |= cpu_to_be32(compat); + sb->s_feature_ro_compat |= cpu_to_be32(ro); + sb->s_feature_incompat |= cpu_to_be32(incompat); + unlock_buffer(journal->j_sb_buffer); + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); + + return 1; +#undef COMPAT_FEATURE_ON +#undef INCOMPAT_FEATURE_ON +} + +/* + * jbd2_journal_clear_features() - Clear a given journal feature in the + * superblock + * @journal: Journal to act on. + * @compat: bitmask of compatible features + * @ro: bitmask of features that force read-only mount + * @incompat: bitmask of incompatible features + * + * Clear a given journal feature as present on the + * superblock. + */ +void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, + unsigned long ro, unsigned long incompat) +{ + journal_superblock_t *sb; + + jbd2_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", + compat, ro, incompat); + + sb = journal->j_superblock; + + sb->s_feature_compat &= ~cpu_to_be32(compat); + sb->s_feature_ro_compat &= ~cpu_to_be32(ro); + sb->s_feature_incompat &= ~cpu_to_be32(incompat); + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); +} +EXPORT_SYMBOL(jbd2_journal_clear_features); + +/** + * jbd2_journal_flush() - Flush journal + * @journal: Journal to act on. + * @flags: optional operation on the journal blocks after the flush (see below) + * + * Flush all data for a given journal to disk and empty the journal. + * Filesystems can use this when remounting readonly to ensure that + * recovery does not need to happen on remount. Optionally, a discard or zeroout + * can be issued on the journal blocks after flushing. + * + * flags: + * JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks + * JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks + */ +int jbd2_journal_flush(journal_t *journal, unsigned int flags) +{ + int err = 0; + transaction_t *transaction = NULL; + + write_lock(&journal->j_state_lock); + + /* Force everything buffered to the log... */ + if (journal->j_running_transaction) { + transaction = journal->j_running_transaction; + __jbd2_log_start_commit(journal, transaction->t_tid); + } else if (journal->j_committing_transaction) + transaction = journal->j_committing_transaction; + + /* Wait for the log commit to complete... */ + if (transaction) { + tid_t tid = transaction->t_tid; + + write_unlock(&journal->j_state_lock); + jbd2_log_wait_commit(journal, tid); + } else { + write_unlock(&journal->j_state_lock); + } + + /* ...and flush everything in the log out to disk. */ + spin_lock(&journal->j_list_lock); + while (!err && journal->j_checkpoint_transactions != NULL) { + spin_unlock(&journal->j_list_lock); + mutex_lock_io(&journal->j_checkpoint_mutex); + err = jbd2_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; + + mutex_lock_io(&journal->j_checkpoint_mutex); + if (!err) { + err = jbd2_cleanup_journal_tail(journal); + if (err < 0) { + mutex_unlock(&journal->j_checkpoint_mutex); + goto out; + } + err = 0; + } + + /* Finally, mark the journal as really needing no recovery. + * This sets s_start==0 in the underlying superblock, which is + * the magic code for a fully-recovered superblock. Any future + * commits of data to the journal will restore the current + * s_start value. */ + jbd2_mark_journal_empty(journal, REQ_FUA); + + if (flags) + err = __jbd2_journal_erase(journal, flags); + + mutex_unlock(&journal->j_checkpoint_mutex); + write_lock(&journal->j_state_lock); + J_ASSERT(!journal->j_running_transaction); + J_ASSERT(!journal->j_committing_transaction); + J_ASSERT(!journal->j_checkpoint_transactions); + J_ASSERT(journal->j_head == journal->j_tail); + J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); + write_unlock(&journal->j_state_lock); +out: + return err; +} + +/** + * jbd2_journal_wipe() - Wipe journal contents + * @journal: Journal to act on. + * @write: flag (see below) + * + * Wipe out all of the contents of a journal, safely. This will produce + * a warning if the journal contains any valid recovery information. + * Must be called between journal_init_*() and jbd2_journal_load(). + * + * If 'write' is non-zero, then we wipe out the journal on disk; otherwise + * we merely suppress recovery. + */ + +int jbd2_journal_wipe(journal_t *journal, int write) +{ + int err = 0; + + J_ASSERT (!(journal->j_flags & JBD2_LOADED)); + + err = load_superblock(journal); + if (err) + return err; + + if (!journal->j_tail) + goto no_recovery; + + printk(KERN_WARNING "JBD2: %s recovery information on journal\n", + write ? "Clearing" : "Ignoring"); + + err = jbd2_journal_skip_recovery(journal); + if (write) { + /* Lock to make assertions happy... */ + mutex_lock_io(&journal->j_checkpoint_mutex); + jbd2_mark_journal_empty(journal, REQ_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } + + no_recovery: + return err; +} + +/** + * jbd2_journal_abort () - Shutdown the journal immediately. + * @journal: the journal to shutdown. + * @errno: an error number to record in the journal indicating + * the reason for the shutdown. + * + * Perform a complete, immediate shutdown of the ENTIRE + * journal (not of a single transaction). This operation cannot be + * undone without closing and reopening the journal. + * + * The jbd2_journal_abort function is intended to support higher level error + * recovery mechanisms such as the ext2/ext3 remount-readonly error + * mode. + * + * Journal abort has very specific semantics. Any existing dirty, + * unjournaled buffers in the main filesystem will still be written to + * disk by bdflush, but the journaling mechanism will be suspended + * immediately and no further transaction commits will be honoured. + * + * Any dirty, journaled buffers will be written back to disk without + * hitting the journal. Atomicity cannot be guaranteed on an aborted + * filesystem, but we _do_ attempt to leave as much data as possible + * behind for fsck to use for cleanup. + * + * Any attempt to get a new transaction handle on a journal which is in + * ABORT state will just result in an -EROFS error return. A + * jbd2_journal_stop on an existing handle will return -EIO if we have + * entered abort state during the update. + * + * Recursive transactions are not disturbed by journal abort until the + * final jbd2_journal_stop, which will receive the -EIO error. + * + * Finally, the jbd2_journal_abort call allows the caller to supply an errno + * which will be recorded (if possible) in the journal superblock. This + * allows a client to record failure conditions in the middle of a + * transaction without having to complete the transaction to record the + * failure to disk. ext3_error, for example, now uses this + * functionality. + * + */ + +void jbd2_journal_abort(journal_t *journal, int errno) +{ + transaction_t *transaction; + + /* + * Lock the aborting procedure until everything is done, this avoid + * races between filesystem's error handling flow (e.g. ext4_abort()), + * ensure panic after the error info is written into journal's + * superblock. + */ + mutex_lock(&journal->j_abort_mutex); + /* + * ESHUTDOWN always takes precedence because a file system check + * caused by any other journal abort error is not required after + * a shutdown triggered. + */ + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) { + int old_errno = journal->j_errno; + + write_unlock(&journal->j_state_lock); + if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { + journal->j_errno = errno; + jbd2_journal_update_sb_errno(journal); + } + mutex_unlock(&journal->j_abort_mutex); + return; + } + + /* + * Mark the abort as occurred and start current running transaction + * to release all journaled buffer. + */ + pr_err("Aborting journal on device %s.\n", journal->j_devname); + + journal->j_flags |= JBD2_ABORT; + journal->j_errno = errno; + transaction = journal->j_running_transaction; + if (transaction) + __jbd2_log_start_commit(journal, transaction->t_tid); + write_unlock(&journal->j_state_lock); + + /* + * Record errno to the journal super block, so that fsck and jbd2 + * layer could realise that a filesystem check is needed. + */ + jbd2_journal_update_sb_errno(journal); + mutex_unlock(&journal->j_abort_mutex); +} + +/** + * jbd2_journal_errno() - returns the journal's error state. + * @journal: journal to examine. + * + * This is the errno number set with jbd2_journal_abort(), the last + * time the journal was mounted - if the journal was stopped + * without calling abort this will be 0. + * + * If the journal has been aborted on this mount time -EROFS will + * be returned. + */ +int jbd2_journal_errno(journal_t *journal) +{ + int err; + + read_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) + err = -EROFS; + else + err = journal->j_errno; + read_unlock(&journal->j_state_lock); + return err; +} + +/** + * jbd2_journal_clear_err() - clears the journal's error state + * @journal: journal to act on. + * + * An error must be cleared or acked to take a FS out of readonly + * mode. + */ +int jbd2_journal_clear_err(journal_t *journal) +{ + int err = 0; + + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) + err = -EROFS; + else + journal->j_errno = 0; + write_unlock(&journal->j_state_lock); + return err; +} + +/** + * jbd2_journal_ack_err() - Ack journal err. + * @journal: journal to act on. + * + * An error must be cleared or acked to take a FS out of readonly + * mode. + */ +void jbd2_journal_ack_err(journal_t *journal) +{ + write_lock(&journal->j_state_lock); + if (journal->j_errno) + journal->j_flags |= JBD2_ACK_ERR; + write_unlock(&journal->j_state_lock); +} + +int jbd2_journal_blocks_per_page(struct inode *inode) +{ + return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); +} + +/* + * helper functions to deal with 32 or 64bit block numbers. + */ +size_t journal_tag_bytes(journal_t *journal) +{ + size_t sz; + + if (jbd2_has_feature_csum3(journal)) + return sizeof(journal_block_tag3_t); + + sz = sizeof(journal_block_tag_t); + + if (jbd2_has_feature_csum2(journal)) + sz += sizeof(__u16); + + if (jbd2_has_feature_64bit(journal)) + return sz; + else + return sz - sizeof(__u32); +} + +/* + * JBD memory management + * + * These functions are used to allocate block-sized chunks of memory + * used for making copies of buffer_head data. Very often it will be + * page-sized chunks of data, but sometimes it will be in + * sub-page-size chunks. (For example, 16k pages on Power systems + * with a 4k block file system.) For blocks smaller than a page, we + * use a SLAB allocator. There are slab caches for each block size, + * which are allocated at mount time, if necessary, and we only free + * (all of) the slab caches when/if the jbd2 module is unloaded. For + * this reason we don't need to a mutex to protect access to + * jbd2_slab[] allocating or releasing memory; only in + * jbd2_journal_create_slab(). + */ +#define JBD2_MAX_SLABS 8 +static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; + +static const char *jbd2_slab_names[JBD2_MAX_SLABS] = { + "jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k", + "jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k" +}; + + +static void jbd2_journal_destroy_slabs(void) +{ + int i; + + for (i = 0; i < JBD2_MAX_SLABS; i++) { + kmem_cache_destroy(jbd2_slab[i]); + jbd2_slab[i] = NULL; + } +} + +static int jbd2_journal_create_slab(size_t size) +{ + static DEFINE_MUTEX(jbd2_slab_create_mutex); + int i = order_base_2(size) - 10; + size_t slab_size; + + if (size == PAGE_SIZE) + return 0; + + if (i >= JBD2_MAX_SLABS) + return -EINVAL; + + if (unlikely(i < 0)) + i = 0; + mutex_lock(&jbd2_slab_create_mutex); + if (jbd2_slab[i]) { + mutex_unlock(&jbd2_slab_create_mutex); + return 0; /* Already created */ + } + + slab_size = 1 << (i+10); + jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size, + slab_size, 0, NULL); + mutex_unlock(&jbd2_slab_create_mutex); + if (!jbd2_slab[i]) { + printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n"); + return -ENOMEM; + } + return 0; +} + +static struct kmem_cache *get_slab(size_t size) +{ + int i = order_base_2(size) - 10; + + BUG_ON(i >= JBD2_MAX_SLABS); + if (unlikely(i < 0)) + i = 0; + BUG_ON(jbd2_slab[i] == NULL); + return jbd2_slab[i]; +} + +void *jbd2_alloc(size_t size, gfp_t flags) +{ + void *ptr; + + BUG_ON(size & (size-1)); /* Must be a power of 2 */ + + if (size < PAGE_SIZE) + ptr = kmem_cache_alloc(get_slab(size), flags); + else + ptr = (void *)__get_free_pages(flags, get_order(size)); + + /* Check alignment; SLUB has gotten this wrong in the past, + * and this can lead to user data corruption! */ + BUG_ON(((unsigned long) ptr) & (size-1)); + + return ptr; +} + +void jbd2_free(void *ptr, size_t size) +{ + if (size < PAGE_SIZE) + kmem_cache_free(get_slab(size), ptr); + else + free_pages((unsigned long)ptr, get_order(size)); +}; + +/* + * Journal_head storage management + */ +static struct kmem_cache *jbd2_journal_head_cache; +#ifdef CONFIG_JBD2_DEBUG +static atomic_t nr_journal_heads = ATOMIC_INIT(0); +#endif + +static int __init jbd2_journal_init_journal_head_cache(void) +{ + J_ASSERT(!jbd2_journal_head_cache); + jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", + sizeof(struct journal_head), + 0, /* offset */ + SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, + NULL); /* ctor */ + if (!jbd2_journal_head_cache) { + printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); + return -ENOMEM; + } + return 0; +} + +static void jbd2_journal_destroy_journal_head_cache(void) +{ + kmem_cache_destroy(jbd2_journal_head_cache); + jbd2_journal_head_cache = NULL; +} + +/* + * journal_head splicing and dicing + */ +static struct journal_head *journal_alloc_journal_head(void) +{ + struct journal_head *ret; + +#ifdef CONFIG_JBD2_DEBUG + atomic_inc(&nr_journal_heads); +#endif + ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); + if (!ret) { + jbd2_debug(1, "out of memory for journal_head\n"); + pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); + ret = kmem_cache_zalloc(jbd2_journal_head_cache, + GFP_NOFS | __GFP_NOFAIL); + } + if (ret) + spin_lock_init(&ret->b_state_lock); + return ret; +} + +static void journal_free_journal_head(struct journal_head *jh) +{ +#ifdef CONFIG_JBD2_DEBUG + atomic_dec(&nr_journal_heads); + memset(jh, JBD2_POISON_FREE, sizeof(*jh)); +#endif + kmem_cache_free(jbd2_journal_head_cache, jh); +} + +/* + * A journal_head is attached to a buffer_head whenever JBD has an + * interest in the buffer. + * + * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit + * is set. This bit is tested in core kernel code where we need to take + * JBD-specific actions. Testing the zeroness of ->b_private is not reliable + * there. + * + * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one. + * + * When a buffer has its BH_JBD bit set it is immune from being released by + * core kernel code, mainly via ->b_count. + * + * A journal_head is detached from its buffer_head when the journal_head's + * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint + * transaction (b_cp_transaction) hold their references to b_jcount. + * + * Various places in the kernel want to attach a journal_head to a buffer_head + * _before_ attaching the journal_head to a transaction. To protect the + * journal_head in this situation, jbd2_journal_add_journal_head elevates the + * journal_head's b_jcount refcount by one. The caller must call + * jbd2_journal_put_journal_head() to undo this. + * + * So the typical usage would be: + * + * (Attach a journal_head if needed. Increments b_jcount) + * struct journal_head *jh = jbd2_journal_add_journal_head(bh); + * ... + * (Get another reference for transaction) + * jbd2_journal_grab_journal_head(bh); + * jh->b_transaction = xxx; + * (Put original reference) + * jbd2_journal_put_journal_head(jh); + */ + +/* + * Give a buffer_head a journal_head. + * + * May sleep. + */ +struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh; + struct journal_head *new_jh = NULL; + +repeat: + if (!buffer_jbd(bh)) + new_jh = journal_alloc_journal_head(); + + jbd_lock_bh_journal_head(bh); + if (buffer_jbd(bh)) { + jh = bh2jh(bh); + } else { + J_ASSERT_BH(bh, + (atomic_read(&bh->b_count) > 0) || + (bh->b_page && bh->b_page->mapping)); + + if (!new_jh) { + jbd_unlock_bh_journal_head(bh); + goto repeat; + } + + jh = new_jh; + new_jh = NULL; /* We consumed it */ + set_buffer_jbd(bh); + bh->b_private = jh; + jh->b_bh = bh; + get_bh(bh); + BUFFER_TRACE(bh, "added journal_head"); + } + jh->b_jcount++; + jbd_unlock_bh_journal_head(bh); + if (new_jh) + journal_free_journal_head(new_jh); + return bh->b_private; +} + +/* + * Grab a ref against this buffer_head's journal_head. If it ended up not + * having a journal_head, return NULL + */ +struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh = NULL; + + jbd_lock_bh_journal_head(bh); + if (buffer_jbd(bh)) { + jh = bh2jh(bh); + jh->b_jcount++; + } + jbd_unlock_bh_journal_head(bh); + return jh; +} +EXPORT_SYMBOL(jbd2_journal_grab_journal_head); + +static void __journal_remove_journal_head(struct buffer_head *bh) +{ + struct journal_head *jh = bh2jh(bh); + + J_ASSERT_JH(jh, jh->b_transaction == NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + J_ASSERT_JH(jh, jh->b_jlist == BJ_None); + J_ASSERT_BH(bh, buffer_jbd(bh)); + J_ASSERT_BH(bh, jh2bh(jh) == bh); + BUFFER_TRACE(bh, "remove journal_head"); + + /* Unlink before dropping the lock */ + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); +} + +static void journal_release_journal_head(struct journal_head *jh, size_t b_size) +{ + if (jh->b_frozen_data) { + printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); + jbd2_free(jh->b_frozen_data, b_size); + } + if (jh->b_committed_data) { + printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); + jbd2_free(jh->b_committed_data, b_size); + } + journal_free_journal_head(jh); +} + +/* + * Drop a reference on the passed journal_head. If it fell to zero then + * release the journal_head from the buffer_head. + */ +void jbd2_journal_put_journal_head(struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + jbd_lock_bh_journal_head(bh); + J_ASSERT_JH(jh, jh->b_jcount > 0); + --jh->b_jcount; + if (!jh->b_jcount) { + __journal_remove_journal_head(bh); + jbd_unlock_bh_journal_head(bh); + journal_release_journal_head(jh, bh->b_size); + __brelse(bh); + } else { + jbd_unlock_bh_journal_head(bh); + } +} +EXPORT_SYMBOL(jbd2_journal_put_journal_head); + +/* + * Initialize jbd inode head + */ +void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) +{ + jinode->i_transaction = NULL; + jinode->i_next_transaction = NULL; + jinode->i_vfs_inode = inode; + jinode->i_flags = 0; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; + INIT_LIST_HEAD(&jinode->i_list); +} + +/* + * Function to be called before we start removing inode from memory (i.e., + * clear_inode() is a fine place to be called from). It removes inode from + * transaction's lists. + */ +void jbd2_journal_release_jbd_inode(journal_t *journal, + struct jbd2_inode *jinode) +{ + if (!journal) + return; +restart: + spin_lock(&journal->j_list_lock); + /* Is commit writing out inode - we have to wait */ + if (jinode->i_flags & JI_COMMIT_RUNNING) { + wait_queue_head_t *wq; + DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); + wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + spin_unlock(&journal->j_list_lock); + schedule(); + finish_wait(wq, &wait.wq_entry); + goto restart; + } + + if (jinode->i_transaction) { + list_del(&jinode->i_list); + jinode->i_transaction = NULL; + } + spin_unlock(&journal->j_list_lock); +} + + +#ifdef CONFIG_PROC_FS + +#define JBD2_STATS_PROC_NAME "fs/jbd2" + +static void __init jbd2_create_jbd_stats_proc_entry(void) +{ + proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL); +} + +static void __exit jbd2_remove_jbd_stats_proc_entry(void) +{ + if (proc_jbd2_stats) + remove_proc_entry(JBD2_STATS_PROC_NAME, NULL); +} + +#else + +#define jbd2_create_jbd_stats_proc_entry() do {} while (0) +#define jbd2_remove_jbd_stats_proc_entry() do {} while (0) + +#endif + +struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; + +static int __init jbd2_journal_init_inode_cache(void) +{ + J_ASSERT(!jbd2_inode_cache); + jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); + if (!jbd2_inode_cache) { + pr_emerg("JBD2: failed to create inode cache\n"); + return -ENOMEM; + } + return 0; +} + +static int __init jbd2_journal_init_handle_cache(void) +{ + J_ASSERT(!jbd2_handle_cache); + jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); + if (!jbd2_handle_cache) { + printk(KERN_EMERG "JBD2: failed to create handle cache\n"); + return -ENOMEM; + } + return 0; +} + +static void jbd2_journal_destroy_inode_cache(void) +{ + kmem_cache_destroy(jbd2_inode_cache); + jbd2_inode_cache = NULL; +} + +static void jbd2_journal_destroy_handle_cache(void) +{ + kmem_cache_destroy(jbd2_handle_cache); + jbd2_handle_cache = NULL; +} + +/* + * Module startup and shutdown + */ + +static int __init journal_init_caches(void) +{ + int ret; + + ret = jbd2_journal_init_revoke_record_cache(); + if (ret == 0) + ret = jbd2_journal_init_revoke_table_cache(); + if (ret == 0) + ret = jbd2_journal_init_journal_head_cache(); + if (ret == 0) + ret = jbd2_journal_init_handle_cache(); + if (ret == 0) + ret = jbd2_journal_init_inode_cache(); + if (ret == 0) + ret = jbd2_journal_init_transaction_cache(); + return ret; +} + +static void jbd2_journal_destroy_caches(void) +{ + jbd2_journal_destroy_revoke_record_cache(); + jbd2_journal_destroy_revoke_table_cache(); + jbd2_journal_destroy_journal_head_cache(); + jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_inode_cache(); + jbd2_journal_destroy_transaction_cache(); + jbd2_journal_destroy_slabs(); +} + +static int __init journal_init(void) +{ + int ret; + + BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); + + ret = journal_init_caches(); + if (ret == 0) { + jbd2_create_jbd_stats_proc_entry(); + } else { + jbd2_journal_destroy_caches(); + } + return ret; +} + +static void __exit journal_exit(void) +{ +#ifdef CONFIG_JBD2_DEBUG + int n = atomic_read(&nr_journal_heads); + if (n) + printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); +#endif + jbd2_remove_jbd_stats_proc_entry(); + jbd2_journal_destroy_caches(); +} + +MODULE_LICENSE("GPL"); +module_init(journal_init); +module_exit(journal_exit); + diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c new file mode 100644 index 000000000..2426b89f1 --- /dev/null +++ b/fs/jbd2/recovery.c @@ -0,0 +1,938 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/recovery.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1999-2000 Red Hat Software --- All Rights Reserved + * + * Journal recovery routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + */ + +#ifndef __KERNEL__ +#include "jfs_user.h" +#else +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/crc32.h> +#include <linux/blkdev.h> +#endif + +/* + * Maintain information about the progress of the recovery job, so that + * the different passes can carry information between them. + */ +struct recovery_info +{ + tid_t start_transaction; + tid_t end_transaction; + + int nr_replays; + int nr_revokes; + int nr_revoke_hits; +}; + +static int do_one_pass(journal_t *journal, + struct recovery_info *info, enum passtype pass); +static int scan_revoke_records(journal_t *, struct buffer_head *, + tid_t, struct recovery_info *); + +#ifdef __KERNEL__ + +/* Release readahead buffers after use */ +static void journal_brelse_array(struct buffer_head *b[], int n) +{ + while (--n >= 0) + brelse (b[n]); +} + + +/* + * When reading from the journal, we are going through the block device + * layer directly and so there is no readahead being done for us. We + * need to implement any readahead ourselves if we want it to happen at + * all. Recovery is basically one long sequential read, so make sure we + * do the IO in reasonably large chunks. + * + * This is not so critical that we need to be enormously clever about + * the readahead size, though. 128K is a purely arbitrary, good-enough + * fixed value. + */ + +#define MAXBUF 8 +static int do_readahead(journal_t *journal, unsigned int start) +{ + int err; + unsigned int max, nbufs, next; + unsigned long long blocknr; + struct buffer_head *bh; + + struct buffer_head * bufs[MAXBUF]; + + /* Do up to 128K of readahead */ + max = start + (128 * 1024 / journal->j_blocksize); + if (max > journal->j_total_len) + max = journal->j_total_len; + + /* Do the readahead itself. We'll submit MAXBUF buffer_heads at + * a time to the block device IO layer. */ + + nbufs = 0; + + for (next = start; next < max; next++) { + err = jbd2_journal_bmap(journal, next, &blocknr); + + if (err) { + printk(KERN_ERR "JBD2: bad block at offset %u\n", + next); + goto failed; + } + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) { + err = -ENOMEM; + goto failed; + } + + if (!buffer_uptodate(bh) && !buffer_locked(bh)) { + bufs[nbufs++] = bh; + if (nbufs == MAXBUF) { + bh_readahead_batch(nbufs, bufs, 0); + journal_brelse_array(bufs, nbufs); + nbufs = 0; + } + } else + brelse(bh); + } + + if (nbufs) + bh_readahead_batch(nbufs, bufs, 0); + err = 0; + +failed: + if (nbufs) + journal_brelse_array(bufs, nbufs); + return err; +} + +#endif /* __KERNEL__ */ + + +/* + * Read a block from the journal + */ + +static int jread(struct buffer_head **bhp, journal_t *journal, + unsigned int offset) +{ + int err; + unsigned long long blocknr; + struct buffer_head *bh; + + *bhp = NULL; + + if (offset >= journal->j_total_len) { + printk(KERN_ERR "JBD2: corrupted journal superblock\n"); + return -EFSCORRUPTED; + } + + err = jbd2_journal_bmap(journal, offset, &blocknr); + + if (err) { + printk(KERN_ERR "JBD2: bad block at offset %u\n", + offset); + return err; + } + + bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) + return -ENOMEM; + + if (!buffer_uptodate(bh)) { + /* + * If this is a brand new buffer, start readahead. + * Otherwise, we assume we are already reading it. + */ + bool need_readahead = !buffer_req(bh); + + bh_read_nowait(bh, 0); + if (need_readahead) + do_readahead(journal, offset); + wait_on_buffer(bh); + } + + if (!buffer_uptodate(bh)) { + printk(KERN_ERR "JBD2: Failed to read block at offset %u\n", + offset); + brelse(bh); + return -EIO; + } + + *bhp = bh; + return 0; +} + +static int jbd2_descriptor_block_csum_verify(journal_t *j, void *buf) +{ + struct jbd2_journal_block_tail *tail; + __be32 provided; + __u32 calculated; + + if (!jbd2_journal_has_csum_v2or3(j)) + return 1; + + tail = (struct jbd2_journal_block_tail *)((char *)buf + + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); + provided = tail->t_checksum; + tail->t_checksum = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); + tail->t_checksum = provided; + + return provided == cpu_to_be32(calculated); +} + +/* + * Count the number of in-use tags in a journal descriptor block. + */ + +static int count_tags(journal_t *journal, struct buffer_head *bh) +{ + char * tagp; + journal_block_tag_t tag; + int nr = 0, size = journal->j_blocksize; + int tag_bytes = journal_tag_bytes(journal); + + if (jbd2_journal_has_csum_v2or3(journal)) + size -= sizeof(struct jbd2_journal_block_tail); + + tagp = &bh->b_data[sizeof(journal_header_t)]; + + while ((tagp - bh->b_data + tag_bytes) <= size) { + memcpy(&tag, tagp, sizeof(tag)); + + nr++; + tagp += tag_bytes; + if (!(tag.t_flags & cpu_to_be16(JBD2_FLAG_SAME_UUID))) + tagp += 16; + + if (tag.t_flags & cpu_to_be16(JBD2_FLAG_LAST_TAG)) + break; + } + + return nr; +} + + +/* Make sure we wrap around the log correctly! */ +#define wrap(journal, var) \ +do { \ + if (var >= (journal)->j_last) \ + var -= ((journal)->j_last - (journal)->j_first); \ +} while (0) + +static int fc_do_one_pass(journal_t *journal, + struct recovery_info *info, enum passtype pass) +{ + unsigned int expected_commit_id = info->end_transaction; + unsigned long next_fc_block; + struct buffer_head *bh; + int err = 0; + + next_fc_block = journal->j_fc_first; + if (!journal->j_fc_replay_callback) + return 0; + + while (next_fc_block <= journal->j_fc_last) { + jbd2_debug(3, "Fast commit replay: next block %ld\n", + next_fc_block); + err = jread(&bh, journal, next_fc_block); + if (err) { + jbd2_debug(3, "Fast commit replay: read error\n"); + break; + } + + err = journal->j_fc_replay_callback(journal, bh, pass, + next_fc_block - journal->j_fc_first, + expected_commit_id); + brelse(bh); + next_fc_block++; + if (err < 0 || err == JBD2_FC_REPLAY_STOP) + break; + err = 0; + } + + if (err) + jbd2_debug(3, "Fast commit replay failed, err = %d\n", err); + + return err; +} + +/** + * jbd2_journal_recover - recovers a on-disk journal + * @journal: the journal to recover + * + * The primary function for recovering the log contents when mounting a + * journaled device. + * + * Recovery is done in three passes. In the first pass, we look for the + * end of the log. In the second, we assemble the list of revoke + * blocks. In the third and final pass, we replay any un-revoked blocks + * in the log. + */ +int jbd2_journal_recover(journal_t *journal) +{ + int err, err2; + journal_superblock_t * sb; + + struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; + + memset(&info, 0, sizeof(info)); + sb = journal->j_superblock; + + /* + * The journal superblock's s_start field (the current log head) + * is always zero if, and only if, the journal was cleanly + * unmounted. + */ + + if (!sb->s_start) { + jbd2_debug(1, "No recovery required, last transaction %d\n", + be32_to_cpu(sb->s_sequence)); + journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1; + return 0; + } + + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); + err = do_one_pass(journal, &info, PASS_SCAN); + if (!err) + err = do_one_pass(journal, &info, PASS_REVOKE); + if (!err) + err = do_one_pass(journal, &info, PASS_REPLAY); + + jbd2_debug(1, "JBD2: recovery, exit status %d, " + "recovered transactions %u to %u\n", + err, info.start_transaction, info.end_transaction); + jbd2_debug(1, "JBD2: 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 + * any existing commit records in the log. */ + journal->j_transaction_sequence = ++info.end_transaction; + + jbd2_journal_clear_revoke(journal); + err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); + if (!err) + err = err2; + /* Make sure all replayed data is on permanent storage */ + if (journal->j_flags & JBD2_BARRIER) { + err2 = blkdev_issue_flush(journal->j_fs_dev); + if (!err) + err = err2; + } + return err; +} + +/** + * jbd2_journal_skip_recovery - Start journal and wipe exiting records + * @journal: journal to startup + * + * Locate any valid recovery information from the journal and set up the + * journal structures in memory to ignore it (presumably because the + * caller has evidence that it is out of date). + * This function doesn't appear to be exported.. + * + * We perform one pass over the journal to allow us to tell the user how + * much recovery information is being erased, and to let us initialise + * the journal transaction sequence numbers to the next unused ID. + */ +int jbd2_journal_skip_recovery(journal_t *journal) +{ + int err; + + struct recovery_info info; + + memset (&info, 0, sizeof(info)); + + err = do_one_pass(journal, &info, PASS_SCAN); + + if (err) { + printk(KERN_ERR "JBD2: error %d scanning journal\n", err); + ++journal->j_transaction_sequence; + } else { +#ifdef CONFIG_JBD2_DEBUG + int dropped = info.end_transaction - + be32_to_cpu(journal->j_superblock->s_sequence); + jbd2_debug(1, + "JBD2: ignoring %d transaction%s from the journal.\n", + dropped, (dropped == 1) ? "" : "s"); +#endif + journal->j_transaction_sequence = ++info.end_transaction; + } + + journal->j_tail = 0; + return err; +} + +static inline unsigned long long read_tag_block(journal_t *journal, + journal_block_tag_t *tag) +{ + unsigned long long block = be32_to_cpu(tag->t_blocknr); + if (jbd2_has_feature_64bit(journal)) + block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32; + return block; +} + +/* + * calc_chksums calculates the checksums for the blocks described in the + * descriptor block. + */ +static int calc_chksums(journal_t *journal, struct buffer_head *bh, + unsigned long *next_log_block, __u32 *crc32_sum) +{ + int i, num_blks, err; + unsigned long io_block; + struct buffer_head *obh; + + num_blks = count_tags(journal, bh); + /* Calculate checksum of the descriptor block. */ + *crc32_sum = crc32_be(*crc32_sum, (void *)bh->b_data, bh->b_size); + + for (i = 0; i < num_blks; i++) { + io_block = (*next_log_block)++; + wrap(journal, *next_log_block); + err = jread(&obh, journal, io_block); + if (err) { + printk(KERN_ERR "JBD2: IO error %d recovering block " + "%lu in log\n", err, io_block); + return 1; + } else { + *crc32_sum = crc32_be(*crc32_sum, (void *)obh->b_data, + obh->b_size); + } + put_bh(obh); + } + return 0; +} + +static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) +{ + struct commit_header *h; + __be32 provided; + __u32 calculated; + + if (!jbd2_journal_has_csum_v2or3(j)) + return 1; + + h = buf; + provided = h->h_chksum[0]; + h->h_chksum[0] = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); + h->h_chksum[0] = provided; + + return provided == cpu_to_be32(calculated); +} + +static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, + journal_block_tag3_t *tag3, + void *buf, __u32 sequence) +{ + __u32 csum32; + __be32 seq; + + if (!jbd2_journal_has_csum_v2or3(j)) + return 1; + + seq = cpu_to_be32(sequence); + csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq)); + csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize); + + if (jbd2_has_feature_csum3(j)) + return tag3->t_checksum == cpu_to_be32(csum32); + else + return tag->t_checksum == cpu_to_be16(csum32); +} + +static int do_one_pass(journal_t *journal, + struct recovery_info *info, enum passtype pass) +{ + unsigned int first_commit_ID, next_commit_ID; + unsigned long next_log_block; + int err, success = 0; + journal_superblock_t * sb; + journal_header_t * tmp; + struct buffer_head * bh; + unsigned int sequence; + int blocktype; + int tag_bytes = journal_tag_bytes(journal); + __u32 crc32_sum = ~0; /* Transactional Checksums */ + int descr_csum_size = 0; + int block_error = 0; + bool need_check_commit_time = false; + __u64 last_trans_commit_time = 0, commit_time; + + /* + * First thing is to establish what we expect to find in the log + * (in terms of transaction IDs), and where (in terms of log + * block offsets): query the superblock. + */ + + sb = journal->j_superblock; + next_commit_ID = be32_to_cpu(sb->s_sequence); + next_log_block = be32_to_cpu(sb->s_start); + + first_commit_ID = next_commit_ID; + if (pass == PASS_SCAN) + info->start_transaction = first_commit_ID; + + jbd2_debug(1, "Starting recovery pass %d\n", pass); + + /* + * Now we walk through the log, transaction by transaction, + * making sure that each transaction has a commit block in the + * expected place. Each complete transaction gets replayed back + * into the main filesystem. + */ + + while (1) { + int flags; + char * tagp; + journal_block_tag_t tag; + struct buffer_head * obh; + struct buffer_head * nbh; + + cond_resched(); + + /* If we already know where to stop the log traversal, + * check right now that we haven't gone past the end of + * the log. */ + + if (pass != PASS_SCAN) + if (tid_geq(next_commit_ID, info->end_transaction)) + break; + + jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n", + next_commit_ID, next_log_block, journal->j_last); + + /* Skip over each chunk of the transaction looking + * either the next descriptor block or the final commit + * record. */ + + jbd2_debug(3, "JBD2: checking block %ld\n", next_log_block); + err = jread(&bh, journal, next_log_block); + if (err) + goto failed; + + next_log_block++; + wrap(journal, next_log_block); + + /* What kind of buffer is it? + * + * If it is a descriptor block, check that it has the + * expected sequence number. Otherwise, we're all done + * here. */ + + tmp = (journal_header_t *)bh->b_data; + + if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) { + brelse(bh); + break; + } + + blocktype = be32_to_cpu(tmp->h_blocktype); + sequence = be32_to_cpu(tmp->h_sequence); + jbd2_debug(3, "Found magic %d, sequence %d\n", + blocktype, sequence); + + if (sequence != next_commit_ID) { + brelse(bh); + break; + } + + /* OK, we have a valid descriptor block which matches + * all of the sequence number checks. What are we going + * to do with it? That depends on the pass... */ + + switch(blocktype) { + case JBD2_DESCRIPTOR_BLOCK: + /* Verify checksum first */ + if (jbd2_journal_has_csum_v2or3(journal)) + descr_csum_size = + sizeof(struct jbd2_journal_block_tail); + if (descr_csum_size > 0 && + !jbd2_descriptor_block_csum_verify(journal, + bh->b_data)) { + /* + * PASS_SCAN can see stale blocks due to lazy + * journal init. Don't error out on those yet. + */ + if (pass != PASS_SCAN) { + pr_err("JBD2: Invalid checksum recovering block %lu in log\n", + next_log_block); + err = -EFSBADCRC; + brelse(bh); + goto failed; + } + need_check_commit_time = true; + jbd2_debug(1, + "invalid descriptor block found in %lu\n", + next_log_block); + } + + /* If it is a valid descriptor block, replay it + * in pass REPLAY; if journal_checksums enabled, then + * calculate checksums in PASS_SCAN, otherwise, + * just skip over the blocks it describes. */ + if (pass != PASS_REPLAY) { + if (pass == PASS_SCAN && + jbd2_has_feature_checksum(journal) && + !need_check_commit_time && + !info->end_transaction) { + if (calc_chksums(journal, bh, + &next_log_block, + &crc32_sum)) { + put_bh(bh); + break; + } + put_bh(bh); + continue; + } + next_log_block += count_tags(journal, bh); + wrap(journal, next_log_block); + put_bh(bh); + continue; + } + + /* A descriptor block: we can now write all of + * the data blocks. Yay, useful work is finally + * getting done here! */ + + tagp = &bh->b_data[sizeof(journal_header_t)]; + while ((tagp - bh->b_data + tag_bytes) + <= journal->j_blocksize - descr_csum_size) { + unsigned long io_block; + + memcpy(&tag, tagp, sizeof(tag)); + flags = be16_to_cpu(tag.t_flags); + + io_block = next_log_block++; + wrap(journal, next_log_block); + err = jread(&obh, journal, io_block); + if (err) { + /* Recover what we can, but + * report failure at the end. */ + success = err; + printk(KERN_ERR + "JBD2: IO error %d recovering " + "block %ld in log\n", + err, io_block); + } else { + unsigned long long blocknr; + + J_ASSERT(obh != NULL); + blocknr = read_tag_block(journal, + &tag); + + /* If the block has been + * revoked, then we're all done + * here. */ + if (jbd2_journal_test_revoke + (journal, blocknr, + next_commit_ID)) { + brelse(obh); + ++info->nr_revoke_hits; + goto skip_write; + } + + /* Look for block corruption */ + if (!jbd2_block_tag_csum_verify( + journal, &tag, (journal_block_tag3_t *)tagp, + obh->b_data, be32_to_cpu(tmp->h_sequence))) { + brelse(obh); + success = -EFSBADCRC; + printk(KERN_ERR "JBD2: Invalid " + "checksum recovering " + "data block %llu in " + "log\n", blocknr); + block_error = 1; + goto skip_write; + } + + /* Find a buffer for the new + * data being restored */ + nbh = __getblk(journal->j_fs_dev, + blocknr, + journal->j_blocksize); + if (nbh == NULL) { + printk(KERN_ERR + "JBD2: Out of memory " + "during recovery.\n"); + err = -ENOMEM; + brelse(bh); + brelse(obh); + goto failed; + } + + lock_buffer(nbh); + memcpy(nbh->b_data, obh->b_data, + journal->j_blocksize); + if (flags & JBD2_FLAG_ESCAPE) { + *((__be32 *)nbh->b_data) = + cpu_to_be32(JBD2_MAGIC_NUMBER); + } + + BUFFER_TRACE(nbh, "marking dirty"); + set_buffer_uptodate(nbh); + mark_buffer_dirty(nbh); + BUFFER_TRACE(nbh, "marking uptodate"); + ++info->nr_replays; + unlock_buffer(nbh); + brelse(obh); + brelse(nbh); + } + + skip_write: + tagp += tag_bytes; + if (!(flags & JBD2_FLAG_SAME_UUID)) + tagp += 16; + + if (flags & JBD2_FLAG_LAST_TAG) + break; + } + + brelse(bh); + continue; + + case JBD2_COMMIT_BLOCK: + /* How to differentiate between interrupted commit + * and journal corruption ? + * + * {nth transaction} + * Checksum Verification Failed + * | + * ____________________ + * | | + * async_commit sync_commit + * | | + * | GO TO NEXT "Journal Corruption" + * | TRANSACTION + * | + * {(n+1)th transanction} + * | + * _______|______________ + * | | + * Commit block found Commit block not found + * | | + * "Journal Corruption" | + * _____________|_________ + * | | + * nth trans corrupt OR nth trans + * and (n+1)th interrupted interrupted + * before commit block + * could reach the disk. + * (Cannot find the difference in above + * mentioned conditions. Hence assume + * "Interrupted Commit".) + */ + commit_time = be64_to_cpu( + ((struct commit_header *)bh->b_data)->h_commit_sec); + /* + * If need_check_commit_time is set, it means we are in + * PASS_SCAN and csum verify failed before. If + * commit_time is increasing, it's the same journal, + * otherwise it is stale journal block, just end this + * recovery. + */ + if (need_check_commit_time) { + if (commit_time >= last_trans_commit_time) { + pr_err("JBD2: Invalid checksum found in transaction %u\n", + next_commit_ID); + err = -EFSBADCRC; + brelse(bh); + goto failed; + } + ignore_crc_mismatch: + /* + * It likely does not belong to same journal, + * just end this recovery with success. + */ + jbd2_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n", + next_commit_ID); + brelse(bh); + goto done; + } + + /* + * Found an expected commit block: if checksums + * are present, verify them in PASS_SCAN; else not + * much to do other than move on to the next sequence + * number. + */ + if (pass == PASS_SCAN && + jbd2_has_feature_checksum(journal)) { + struct commit_header *cbh = + (struct commit_header *)bh->b_data; + unsigned found_chksum = + be32_to_cpu(cbh->h_chksum[0]); + + if (info->end_transaction) { + journal->j_failed_commit = + info->end_transaction; + brelse(bh); + break; + } + + /* Neither checksum match nor unused? */ + if (!((crc32_sum == found_chksum && + cbh->h_chksum_type == + JBD2_CRC32_CHKSUM && + cbh->h_chksum_size == + JBD2_CRC32_CHKSUM_SIZE) || + (cbh->h_chksum_type == 0 && + cbh->h_chksum_size == 0 && + found_chksum == 0))) + goto chksum_error; + + crc32_sum = ~0; + } + if (pass == PASS_SCAN && + !jbd2_commit_block_csum_verify(journal, + bh->b_data)) { + chksum_error: + if (commit_time < last_trans_commit_time) + goto ignore_crc_mismatch; + info->end_transaction = next_commit_ID; + + if (!jbd2_has_feature_async_commit(journal)) { + journal->j_failed_commit = + next_commit_ID; + brelse(bh); + break; + } + } + if (pass == PASS_SCAN) + last_trans_commit_time = commit_time; + brelse(bh); + next_commit_ID++; + continue; + + case JBD2_REVOKE_BLOCK: + /* + * Check revoke block crc in pass_scan, if csum verify + * failed, check commit block time later. + */ + if (pass == PASS_SCAN && + !jbd2_descriptor_block_csum_verify(journal, + bh->b_data)) { + jbd2_debug(1, "JBD2: invalid revoke block found in %lu\n", + next_log_block); + need_check_commit_time = true; + } + /* If we aren't in the REVOKE pass, then we can + * just skip over this block. */ + if (pass != PASS_REVOKE) { + brelse(bh); + continue; + } + + err = scan_revoke_records(journal, bh, + next_commit_ID, info); + brelse(bh); + if (err) + goto failed; + continue; + + default: + jbd2_debug(3, "Unrecognised magic %d, end of scan.\n", + blocktype); + brelse(bh); + goto done; + } + } + + done: + /* + * We broke out of the log scan loop: either we came to the + * known end of the log or we found an unexpected block in the + * log. If the latter happened, then we know that the "current" + * transaction marks the end of the valid log. + */ + + if (pass == PASS_SCAN) { + if (!info->end_transaction) + info->end_transaction = next_commit_ID; + } else { + /* It's really bad news if different passes end up at + * different places (but possible due to IO errors). */ + if (info->end_transaction != next_commit_ID) { + printk(KERN_ERR "JBD2: recovery pass %d ended at " + "transaction %u, expected %u\n", + pass, next_commit_ID, info->end_transaction); + if (!success) + success = -EIO; + } + } + + if (jbd2_has_feature_fast_commit(journal) && pass != PASS_REVOKE) { + err = fc_do_one_pass(journal, info, pass); + if (err) + success = err; + } + + if (block_error && success == 0) + success = -EIO; + return success; + + failed: + return err; +} + +/* Scan a revoke record, marking all blocks mentioned as revoked. */ + +static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, + tid_t sequence, struct recovery_info *info) +{ + jbd2_journal_revoke_header_t *header; + int offset, max; + unsigned csum_size = 0; + __u32 rcount; + int record_len = 4; + + header = (jbd2_journal_revoke_header_t *) bh->b_data; + offset = sizeof(jbd2_journal_revoke_header_t); + rcount = be32_to_cpu(header->r_count); + + if (jbd2_journal_has_csum_v2or3(journal)) + csum_size = sizeof(struct jbd2_journal_block_tail); + if (rcount > journal->j_blocksize - csum_size) + return -EINVAL; + max = rcount; + + if (jbd2_has_feature_64bit(journal)) + record_len = 8; + + while (offset + record_len <= max) { + unsigned long long blocknr; + int err; + + if (record_len == 4) + blocknr = be32_to_cpu(* ((__be32 *) (bh->b_data+offset))); + else + blocknr = be64_to_cpu(* ((__be64 *) (bh->b_data+offset))); + offset += record_len; + err = jbd2_journal_set_revoke(journal, blocknr, sequence); + if (err) + return err; + ++info->nr_revokes; + } + return 0; +} diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c new file mode 100644 index 000000000..4556e4689 --- /dev/null +++ b/fs/jbd2/revoke.c @@ -0,0 +1,743 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/revoke.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 2000 + * + * Copyright 2000 Red Hat corp --- All Rights Reserved + * + * Journal revoke routines for the generic filesystem journaling code; + * part of the ext2fs journaling system. + * + * Revoke is the mechanism used to prevent old log records for deleted + * metadata from being replayed on top of newer data using the same + * blocks. The revoke mechanism is used in two separate places: + * + * + Commit: during commit we write the entire list of the current + * transaction's revoked blocks to the journal + * + * + Recovery: during recovery we record the transaction ID of all + * revoked blocks. If there are multiple revoke records in the log + * for a single block, only the last one counts, and if there is a log + * entry for a block beyond the last revoke, then that log entry still + * gets replayed. + * + * We can get interactions between revokes and new log data within a + * single transaction: + * + * Block is revoked and then journaled: + * The desired end result is the journaling of the new block, so we + * cancel the revoke before the transaction commits. + * + * Block is journaled and then revoked: + * The revoke must take precedence over the write of the block, so we + * need either to cancel the journal entry or to write the revoke + * later in the log than the log block. In this case, we choose the + * latter: journaling a block cancels any revoke record for that block + * in the current transaction, so any revoke for that block in the + * transaction must have happened after the block was journaled and so + * the revoke must take precedence. + * + * Block is revoked and then written as data: + * The data write is allowed to succeed, but the revoke is _not_ + * cancelled. We still need to prevent old log records from + * overwriting the new data. We don't even need to clear the revoke + * bit here. + * + * We cache revoke status of a buffer in the current transaction in b_states + * bits. As the name says, revokevalid flag indicates that the cached revoke + * status of a buffer is valid and we can rely on the cached status. + * + * Revoke information on buffers is a tri-state value: + * + * RevokeValid clear: no cached revoke status, need to look it up + * RevokeValid set, Revoked clear: + * buffer has not been revoked, and cancel_revoke + * 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 no one else + * can touch them (filesystem isn't mounted yet) and hence no locking is + * needed. + */ + +#ifndef __KERNEL__ +#include "jfs_user.h" +#else +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/init.h> +#include <linux/bio.h> +#include <linux/log2.h> +#include <linux/hash.h> +#endif + +static struct kmem_cache *jbd2_revoke_record_cache; +static struct kmem_cache *jbd2_revoke_table_cache; + +/* Each revoke record represents one single revoked block. During + journal replay, this involves recording the transaction ID of the + last transaction to revoke this block. */ + +struct jbd2_revoke_record_s +{ + struct list_head hash; + tid_t sequence; /* Used for recovery only */ + unsigned long long blocknr; +}; + + +/* The revoke table is just a simple hash table of revoke records. */ +struct jbd2_revoke_table_s +{ + /* It is conceivable that we might want a larger hash table + * for recovery. Must be a power of two. */ + int hash_size; + int hash_shift; + struct list_head *hash_table; +}; + + +#ifdef __KERNEL__ +static void write_one_revoke_record(transaction_t *, + struct list_head *, + struct buffer_head **, int *, + struct jbd2_revoke_record_s *); +static void flush_descriptor(journal_t *, struct buffer_head *, int); +#endif + +/* Utility functions to maintain the revoke table */ + +static inline int hash(journal_t *journal, unsigned long long block) +{ + return hash_64(block, journal->j_revoke->hash_shift); +} + +static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr, + tid_t seq) +{ + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + gfp_t gfp_mask = GFP_NOFS; + + if (journal_oom_retry) + gfp_mask |= __GFP_NOFAIL; + record = kmem_cache_alloc(jbd2_revoke_record_cache, gfp_mask); + if (!record) + return -ENOMEM; + + record->sequence = seq; + record->blocknr = blocknr; + hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; + spin_lock(&journal->j_revoke_lock); + list_add(&record->hash, hash_list); + spin_unlock(&journal->j_revoke_lock); + return 0; +} + +/* Find a revoke record in the journal's hash table. */ + +static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, + unsigned long long blocknr) +{ + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + + hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)]; + + spin_lock(&journal->j_revoke_lock); + record = (struct jbd2_revoke_record_s *) hash_list->next; + while (&(record->hash) != hash_list) { + if (record->blocknr == blocknr) { + spin_unlock(&journal->j_revoke_lock); + return record; + } + record = (struct jbd2_revoke_record_s *) record->hash.next; + } + spin_unlock(&journal->j_revoke_lock); + return NULL; +} + +void jbd2_journal_destroy_revoke_record_cache(void) +{ + kmem_cache_destroy(jbd2_revoke_record_cache); + jbd2_revoke_record_cache = NULL; +} + +void jbd2_journal_destroy_revoke_table_cache(void) +{ + kmem_cache_destroy(jbd2_revoke_table_cache); + jbd2_revoke_table_cache = NULL; +} + +int __init jbd2_journal_init_revoke_record_cache(void) +{ + J_ASSERT(!jbd2_revoke_record_cache); + jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s, + SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY); + + if (!jbd2_revoke_record_cache) { + pr_emerg("JBD2: failed to create revoke_record cache\n"); + return -ENOMEM; + } + return 0; +} + +int __init jbd2_journal_init_revoke_table_cache(void) +{ + J_ASSERT(!jbd2_revoke_table_cache); + jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s, + SLAB_TEMPORARY); + if (!jbd2_revoke_table_cache) { + pr_emerg("JBD2: failed to create revoke_table cache\n"); + return -ENOMEM; + } + return 0; +} + +static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size) +{ + int shift = 0; + int tmp = hash_size; + struct jbd2_revoke_table_s *table; + + table = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL); + if (!table) + goto out; + + while((tmp >>= 1UL) != 0UL) + shift++; + + table->hash_size = hash_size; + table->hash_shift = shift; + table->hash_table = + kmalloc_array(hash_size, sizeof(struct list_head), GFP_KERNEL); + if (!table->hash_table) { + kmem_cache_free(jbd2_revoke_table_cache, table); + table = NULL; + goto out; + } + + for (tmp = 0; tmp < hash_size; tmp++) + INIT_LIST_HEAD(&table->hash_table[tmp]); + +out: + return table; +} + +static void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table) +{ + int i; + struct list_head *hash_list; + + for (i = 0; i < table->hash_size; i++) { + hash_list = &table->hash_table[i]; + J_ASSERT(list_empty(hash_list)); + } + + kfree(table->hash_table); + kmem_cache_free(jbd2_revoke_table_cache, table); +} + +/* Initialise the revoke table for a given journal to a given size. */ +int jbd2_journal_init_revoke(journal_t *journal, int hash_size) +{ + J_ASSERT(journal->j_revoke_table[0] == NULL); + J_ASSERT(is_power_of_2(hash_size)); + + journal->j_revoke_table[0] = jbd2_journal_init_revoke_table(hash_size); + if (!journal->j_revoke_table[0]) + goto fail0; + + journal->j_revoke_table[1] = jbd2_journal_init_revoke_table(hash_size); + if (!journal->j_revoke_table[1]) + goto fail1; + + journal->j_revoke = journal->j_revoke_table[1]; + + spin_lock_init(&journal->j_revoke_lock); + + return 0; + +fail1: + jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]); + journal->j_revoke_table[0] = NULL; +fail0: + return -ENOMEM; +} + +/* Destroy a journal's revoke table. The table must already be empty! */ +void jbd2_journal_destroy_revoke(journal_t *journal) +{ + journal->j_revoke = NULL; + if (journal->j_revoke_table[0]) + jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]); + if (journal->j_revoke_table[1]) + jbd2_journal_destroy_revoke_table(journal->j_revoke_table[1]); +} + + +#ifdef __KERNEL__ + +/* + * jbd2_journal_revoke: revoke a given buffer_head from the journal. This + * prevents the block from being replayed during recovery if we take a + * crash after this current transaction commits. Any subsequent + * metadata writes of the buffer in this transaction cancel the + * revoke. + * + * Note that this call may block --- it is up to the caller to make + * sure that there are no further calls to journal_write_metadata + * before the revoke is complete. In ext3, this implies calling the + * revoke before clearing the block bitmap when we are deleting + * metadata. + * + * Revoke performs a jbd2_journal_forget on any buffer_head passed in as a + * parameter, but does _not_ forget the buffer_head if the bh was only + * found implicitly. + * + * bh_in may not be a journalled buffer - it may have come off + * the hash tables without an attached journal_head. + * + * If bh_in is non-zero, jbd2_journal_revoke() will decrement its b_count + * by one. + */ + +int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, + struct buffer_head *bh_in) +{ + struct buffer_head *bh = NULL; + journal_t *journal; + struct block_device *bdev; + int err; + + might_sleep(); + if (bh_in) + BUFFER_TRACE(bh_in, "enter"); + + journal = handle->h_transaction->t_journal; + if (!jbd2_journal_set_features(journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)){ + J_ASSERT (!"Cannot set revoke feature!"); + return -EINVAL; + } + + bdev = journal->j_fs_dev; + bh = bh_in; + + if (!bh) { + bh = __find_get_block(bdev, blocknr, journal->j_blocksize); + if (bh) + BUFFER_TRACE(bh, "found on hash"); + } +#ifdef JBD2_EXPENSIVE_CHECKING + else { + struct buffer_head *bh2; + + /* If there is a different buffer_head lying around in + * memory anywhere... */ + bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize); + if (bh2) { + /* ... and it has RevokeValid status... */ + if (bh2 != bh && buffer_revokevalid(bh2)) + /* ...then it better be revoked too, + * since it's illegal to create a revoke + * record against a buffer_head which is + * not marked revoked --- that would + * risk missing a subsequent revoke + * cancel. */ + J_ASSERT_BH(bh2, buffer_revoked(bh2)); + put_bh(bh2); + } + } +#endif + + if (WARN_ON_ONCE(handle->h_revoke_credits <= 0)) { + if (!bh_in) + brelse(bh); + return -EIO; + } + /* We really ought not ever to revoke twice in a row without + first having the revoke cancelled: it's illegal to free a + block twice without allocating it in between! */ + if (bh) { + if (!J_EXPECT_BH(bh, !buffer_revoked(bh), + "inconsistent data on disk")) { + if (!bh_in) + brelse(bh); + return -EIO; + } + set_buffer_revoked(bh); + set_buffer_revokevalid(bh); + if (bh_in) { + BUFFER_TRACE(bh_in, "call jbd2_journal_forget"); + jbd2_journal_forget(handle, bh_in); + } else { + BUFFER_TRACE(bh, "call brelse"); + __brelse(bh); + } + } + handle->h_revoke_credits--; + + jbd2_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); + err = insert_revoke_hash(journal, blocknr, + handle->h_transaction->t_tid); + BUFFER_TRACE(bh_in, "exit"); + return err; +} + +/* + * Cancel an outstanding revoke. For use only internally by the + * journaling code (called from jbd2_journal_get_write_access). + * + * We trust buffer_revoked() on the buffer if the buffer is already + * being journaled: if there is no revoke pending on the buffer, then we + * don't do anything here. + * + * This would break if it were possible for a buffer to be revoked and + * discarded, and then reallocated within the same transaction. In such + * a case we would have lost the revoked bit, but when we arrived here + * 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. + */ +int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh) +{ + struct jbd2_revoke_record_s *record; + journal_t *journal = handle->h_transaction->t_journal; + int need_cancel; + int did_revoke = 0; /* akpm: debug */ + struct buffer_head *bh = jh2bh(jh); + + jbd2_debug(4, "journal_head %p, cancelling revoke\n", jh); + + /* Is the existing Revoke bit valid? If so, we trust it, and + * only perform the full cancel if the revoke bit is set. If + * not, we can't trust the revoke bit, and we need to do the + * full search for a revoke record. */ + if (test_set_buffer_revokevalid(bh)) { + need_cancel = test_clear_buffer_revoked(bh); + } else { + need_cancel = 1; + clear_buffer_revoked(bh); + } + + if (need_cancel) { + record = find_revoke_record(journal, bh->b_blocknr); + if (record) { + jbd2_debug(4, "cancelled existing revoke on " + "blocknr %llu\n", (unsigned long long)bh->b_blocknr); + spin_lock(&journal->j_revoke_lock); + list_del(&record->hash); + spin_unlock(&journal->j_revoke_lock); + kmem_cache_free(jbd2_revoke_record_cache, record); + did_revoke = 1; + } + } + +#ifdef JBD2_EXPENSIVE_CHECKING + /* There better not be one left behind by now! */ + record = find_revoke_record(journal, bh->b_blocknr); + J_ASSERT_JH(jh, record == NULL); +#endif + + /* Finally, have we just cleared revoke on an unhashed + * buffer_head? If so, we'd better make sure we clear the + * revoked status on any hashed alias too, otherwise the revoke + * state machine will get very upset later on. */ + if (need_cancel) { + struct buffer_head *bh2; + bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size); + if (bh2) { + if (bh2 != bh) + clear_buffer_revoked(bh2); + __brelse(bh2); + } + } + return did_revoke; +} + +/* + * journal_clear_revoked_flag clears revoked flag of buffers in + * revoke table to reflect there is no revoked buffers in the next + * transaction which is going to be started. + */ +void jbd2_clear_buffer_revoked_flags(journal_t *journal) +{ + struct jbd2_revoke_table_s *revoke = journal->j_revoke; + int i = 0; + + for (i = 0; i < revoke->hash_size; i++) { + struct list_head *hash_list; + struct list_head *list_entry; + hash_list = &revoke->hash_table[i]; + + list_for_each(list_entry, hash_list) { + struct jbd2_revoke_record_s *record; + struct buffer_head *bh; + record = (struct jbd2_revoke_record_s *)list_entry; + bh = __find_get_block(journal->j_fs_dev, + record->blocknr, + journal->j_blocksize); + if (bh) { + clear_buffer_revoked(bh); + __brelse(bh); + } + } + } +} + +/* journal_switch_revoke table select j_revoke for next transaction + * we do not want to suspend any processing until all revokes are + * written -bzzz + */ +void jbd2_journal_switch_revoke_table(journal_t *journal) +{ + int i; + + if (journal->j_revoke == journal->j_revoke_table[0]) + journal->j_revoke = journal->j_revoke_table[1]; + else + journal->j_revoke = journal->j_revoke_table[0]; + + for (i = 0; i < journal->j_revoke->hash_size; i++) + INIT_LIST_HEAD(&journal->j_revoke->hash_table[i]); +} + +/* + * Write revoke records to the journal for all entries in the current + * revoke hash, deleting the entries as we go. + */ +void jbd2_journal_write_revoke_records(transaction_t *transaction, + struct list_head *log_bufs) +{ + journal_t *journal = transaction->t_journal; + struct buffer_head *descriptor; + struct jbd2_revoke_record_s *record; + struct jbd2_revoke_table_s *revoke; + struct list_head *hash_list; + int i, offset, count; + + descriptor = NULL; + offset = 0; + count = 0; + + /* select revoke table for committing transaction */ + revoke = journal->j_revoke == journal->j_revoke_table[0] ? + journal->j_revoke_table[1] : journal->j_revoke_table[0]; + + for (i = 0; i < revoke->hash_size; i++) { + hash_list = &revoke->hash_table[i]; + + while (!list_empty(hash_list)) { + record = (struct jbd2_revoke_record_s *) + hash_list->next; + write_one_revoke_record(transaction, log_bufs, + &descriptor, &offset, record); + count++; + list_del(&record->hash); + kmem_cache_free(jbd2_revoke_record_cache, record); + } + } + if (descriptor) + flush_descriptor(journal, descriptor, offset); + jbd2_debug(1, "Wrote %d revoke records\n", count); +} + +/* + * Write out one revoke record. We need to create a new descriptor + * block if the old one is full or if we have not already created one. + */ + +static void write_one_revoke_record(transaction_t *transaction, + struct list_head *log_bufs, + struct buffer_head **descriptorp, + int *offsetp, + struct jbd2_revoke_record_s *record) +{ + journal_t *journal = transaction->t_journal; + int csum_size = 0; + struct buffer_head *descriptor; + int sz, offset; + + /* If we are already aborting, this all becomes a noop. We + still need to go round the loop in + jbd2_journal_write_revoke_records in order to free all of the + revoke records: only the IO to the journal is omitted. */ + if (is_journal_aborted(journal)) + return; + + descriptor = *descriptorp; + offset = *offsetp; + + /* Do we need to leave space at the end for a checksum? */ + if (jbd2_journal_has_csum_v2or3(journal)) + csum_size = sizeof(struct jbd2_journal_block_tail); + + if (jbd2_has_feature_64bit(journal)) + sz = 8; + else + sz = 4; + + /* Make sure we have a descriptor with space left for the record */ + if (descriptor) { + if (offset + sz > journal->j_blocksize - csum_size) { + flush_descriptor(journal, descriptor, offset); + descriptor = NULL; + } + } + + if (!descriptor) { + descriptor = jbd2_journal_get_descriptor_buffer(transaction, + JBD2_REVOKE_BLOCK); + if (!descriptor) + return; + + /* Record it so that we can wait for IO completion later */ + BUFFER_TRACE(descriptor, "file in log_bufs"); + jbd2_file_log_bh(log_bufs, descriptor); + + offset = sizeof(jbd2_journal_revoke_header_t); + *descriptorp = descriptor; + } + + if (jbd2_has_feature_64bit(journal)) + * ((__be64 *)(&descriptor->b_data[offset])) = + cpu_to_be64(record->blocknr); + else + * ((__be32 *)(&descriptor->b_data[offset])) = + cpu_to_be32(record->blocknr); + offset += sz; + + *offsetp = offset; +} + +/* + * Flush a revoke descriptor out to the journal. If we are aborting, + * this is a noop; otherwise we are generating a buffer which needs to + * be waited for during commit, so it has to go onto the appropriate + * journal buffer list. + */ + +static void flush_descriptor(journal_t *journal, + struct buffer_head *descriptor, + int offset) +{ + jbd2_journal_revoke_header_t *header; + + if (is_journal_aborted(journal)) + return; + + header = (jbd2_journal_revoke_header_t *)descriptor->b_data; + header->r_count = cpu_to_be32(offset); + jbd2_descriptor_block_csum_set(journal, descriptor); + + set_buffer_jwrite(descriptor); + BUFFER_TRACE(descriptor, "write"); + set_buffer_dirty(descriptor); + write_dirty_buffer(descriptor, REQ_SYNC); +} +#endif + +/* + * Revoke support for recovery. + * + * Recovery needs to be able to: + * + * record all revoke records, including the tid of the latest instance + * of each revoke in the journal + * + * check whether a given block in a given transaction should be replayed + * (ie. has not been revoked by a revoke record in that or a subsequent + * transaction) + * + * empty the revoke table after recovery. + */ + +/* + * First, setting revoke records. We create a new revoke record for + * every block ever revoked in the log as we scan it for recovery, and + * we update the existing records if we find multiple revokes for a + * single block. + */ + +int jbd2_journal_set_revoke(journal_t *journal, + unsigned long long blocknr, + tid_t sequence) +{ + struct jbd2_revoke_record_s *record; + + record = find_revoke_record(journal, blocknr); + if (record) { + /* If we have multiple occurrences, only record the + * latest sequence number in the hashed record */ + if (tid_gt(sequence, record->sequence)) + record->sequence = sequence; + return 0; + } + return insert_revoke_hash(journal, blocknr, sequence); +} + +/* + * Test revoke records. For a given block referenced in the log, has + * that block been revoked? A revoke record with a given transaction + * sequence number revokes all blocks in that transaction and earlier + * ones, but later transactions still need replayed. + */ + +int jbd2_journal_test_revoke(journal_t *journal, + unsigned long long blocknr, + tid_t sequence) +{ + struct jbd2_revoke_record_s *record; + + record = find_revoke_record(journal, blocknr); + if (!record) + return 0; + if (tid_gt(sequence, record->sequence)) + return 0; + return 1; +} + +/* + * Finally, once recovery is over, we need to clear the revoke table so + * that it can be reused by the running filesystem. + */ + +void jbd2_journal_clear_revoke(journal_t *journal) +{ + int i; + struct list_head *hash_list; + struct jbd2_revoke_record_s *record; + struct jbd2_revoke_table_s *revoke; + + revoke = journal->j_revoke; + + for (i = 0; i < revoke->hash_size; i++) { + hash_list = &revoke->hash_table[i]; + while (!list_empty(hash_list)) { + record = (struct jbd2_revoke_record_s*) hash_list->next; + list_del(&record->hash); + kmem_cache_free(jbd2_revoke_record_cache, record); + } + } +} diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c new file mode 100644 index 000000000..6ef502294 --- /dev/null +++ b/fs/jbd2/transaction.c @@ -0,0 +1,2786 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * linux/fs/jbd2/transaction.c + * + * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 + * + * Copyright 1998 Red Hat corp --- All Rights Reserved + * + * Generic filesystem transaction handling code; part of the ext2fs + * journaling system. + * + * This file manages transactions (compound commits managed by the + * journaling code) and handles (individual atomic operations by the + * filesystem). + */ + +#include <linux/time.h> +#include <linux/fs.h> +#include <linux/jbd2.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/highmem.h> +#include <linux/hrtimer.h> +#include <linux/backing-dev.h> +#include <linux/bug.h> +#include <linux/module.h> +#include <linux/sched/mm.h> + +#include <trace/events/jbd2.h> + +static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +static void __jbd2_journal_unfile_buffer(struct journal_head *jh); + +static struct kmem_cache *transaction_cache; +int __init jbd2_journal_init_transaction_cache(void) +{ + J_ASSERT(!transaction_cache); + transaction_cache = kmem_cache_create("jbd2_transaction_s", + sizeof(transaction_t), + 0, + SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, + NULL); + if (!transaction_cache) { + pr_emerg("JBD2: failed to create transaction cache\n"); + return -ENOMEM; + } + return 0; +} + +void jbd2_journal_destroy_transaction_cache(void) +{ + kmem_cache_destroy(transaction_cache); + transaction_cache = NULL; +} + +void jbd2_journal_free_transaction(transaction_t *transaction) +{ + if (unlikely(ZERO_OR_NULL_PTR(transaction))) + return; + kmem_cache_free(transaction_cache, transaction); +} + +/* + * Base amount of descriptor blocks we reserve for each transaction. + */ +static int jbd2_descriptor_blocks_per_trans(journal_t *journal) +{ + int tag_space = journal->j_blocksize - sizeof(journal_header_t); + int tags_per_block; + + /* Subtract UUID */ + tag_space -= 16; + if (jbd2_journal_has_csum_v2or3(journal)) + tag_space -= sizeof(struct jbd2_journal_block_tail); + /* Commit code leaves a slack space of 16 bytes at the end of block */ + tags_per_block = (tag_space - 16) / journal_tag_bytes(journal); + /* + * Revoke descriptors are accounted separately so we need to reserve + * space for commit block and normal transaction descriptor blocks. + */ + return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers, + tags_per_block); +} + +/* + * jbd2_get_transaction: obtain a new transaction_t object. + * + * Simply initialise a new transaction. Initialize it in + * RUNNING state and add it to the current journal (which should not + * have an existing running transaction: we only make a new transaction + * once we have started to commit the old one). + * + * Preconditions: + * The journal MUST be locked. We don't perform atomic mallocs on the + * new transaction and we can't block without protecting against other + * processes trying to touch the journal while it is in transition. + * + */ + +static void jbd2_get_transaction(journal_t *journal, + transaction_t *transaction) +{ + transaction->t_journal = journal; + transaction->t_state = T_RUNNING; + transaction->t_start_time = ktime_get(); + transaction->t_tid = journal->j_transaction_sequence++; + transaction->t_expires = jiffies + journal->j_commit_interval; + atomic_set(&transaction->t_updates, 0); + atomic_set(&transaction->t_outstanding_credits, + jbd2_descriptor_blocks_per_trans(journal) + + atomic_read(&journal->j_reserved_credits)); + atomic_set(&transaction->t_outstanding_revokes, 0); + atomic_set(&transaction->t_handle_count, 0); + INIT_LIST_HEAD(&transaction->t_inode_list); + INIT_LIST_HEAD(&transaction->t_private_list); + + /* Set up the commit timer for the new transaction. */ + journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires); + add_timer(&journal->j_commit_timer); + + J_ASSERT(journal->j_running_transaction == NULL); + journal->j_running_transaction = transaction; + transaction->t_max_wait = 0; + transaction->t_start = jiffies; + transaction->t_requested = 0; +} + +/* + * Handle management. + * + * A handle_t is an object which represents a single atomic update to a + * filesystem, and which tracks all of the modifications which form part + * of that one update. + */ + +/* + * Update transaction's maximum wait time, if debugging is enabled. + * + * t_max_wait is carefully updated here with use of atomic compare exchange. + * Note that there could be multiplre threads trying to do this simultaneously + * hence using cmpxchg to avoid any use of locks in this case. + * With this t_max_wait can be updated w/o enabling jbd2_journal_enable_debug. + */ +static inline void update_t_max_wait(transaction_t *transaction, + unsigned long ts) +{ + unsigned long oldts, newts; + + if (time_after(transaction->t_start, ts)) { + newts = jbd2_time_diff(ts, transaction->t_start); + oldts = READ_ONCE(transaction->t_max_wait); + while (oldts < newts) + oldts = cmpxchg(&transaction->t_max_wait, oldts, newts); + } +} + +/* + * Wait until running transaction passes to T_FLUSH state and new transaction + * can thus be started. Also starts the commit if needed. The function expects + * running transaction to exist and releases j_state_lock. + */ +static void wait_transaction_locked(journal_t *journal) + __releases(journal->j_state_lock) +{ + DEFINE_WAIT(wait); + int need_to_start; + tid_t tid = journal->j_running_transaction->t_tid; + + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, + TASK_UNINTERRUPTIBLE); + need_to_start = !tid_geq(journal->j_commit_request, tid); + read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); + jbd2_might_wait_for_commit(journal); + schedule(); + finish_wait(&journal->j_wait_transaction_locked, &wait); +} + +/* + * Wait until running transaction transitions from T_SWITCH to T_FLUSH + * state and new transaction can thus be started. The function releases + * j_state_lock. + */ +static void wait_transaction_switching(journal_t *journal) + __releases(journal->j_state_lock) +{ + DEFINE_WAIT(wait); + + if (WARN_ON(!journal->j_running_transaction || + journal->j_running_transaction->t_state != T_SWITCH)) { + read_unlock(&journal->j_state_lock); + return; + } + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, + TASK_UNINTERRUPTIBLE); + read_unlock(&journal->j_state_lock); + /* + * We don't call jbd2_might_wait_for_commit() here as there's no + * waiting for outstanding handles happening anymore in T_SWITCH state + * and handling of reserved handles actually relies on that for + * correctness. + */ + schedule(); + finish_wait(&journal->j_wait_transaction_locked, &wait); +} + +static void sub_reserved_credits(journal_t *journal, int blocks) +{ + atomic_sub(blocks, &journal->j_reserved_credits); + wake_up(&journal->j_wait_reserved); +} + +/* + * Wait until we can add credits for handle to the running transaction. Called + * with j_state_lock held for reading. Returns 0 if handle joined the running + * transaction. Returns 1 if we had to wait, j_state_lock is dropped, and + * caller must retry. + * + * Note: because j_state_lock may be dropped depending on the return + * value, we need to fake out sparse so ti doesn't complain about a + * locking imbalance. Callers of add_transaction_credits will need to + * make a similar accomodation. + */ +static int add_transaction_credits(journal_t *journal, int blocks, + int rsv_blocks) +__must_hold(&journal->j_state_lock) +{ + transaction_t *t = journal->j_running_transaction; + int needed; + int total = blocks + rsv_blocks; + + /* + * If the current transaction is locked down for commit, wait + * for the lock to be released. + */ + if (t->t_state != T_RUNNING) { + WARN_ON_ONCE(t->t_state >= T_FLUSH); + wait_transaction_locked(journal); + __acquire(&journal->j_state_lock); /* fake out sparse */ + return 1; + } + + /* + * If there is not enough space left in the log to write all + * potential buffers requested by this operation, we need to + * stall pending a log checkpoint to free some more log space. + */ + needed = atomic_add_return(total, &t->t_outstanding_credits); + if (needed > journal->j_max_transaction_buffers) { + /* + * If the current transaction is already too large, + * then start to commit it: we can then go back and + * attach this handle to a new transaction. + */ + atomic_sub(total, &t->t_outstanding_credits); + + /* + * Is the number of reserved credits in the current transaction too + * big to fit this handle? Wait until reserved credits are freed. + */ + if (atomic_read(&journal->j_reserved_credits) + total > + journal->j_max_transaction_buffers) { + read_unlock(&journal->j_state_lock); + jbd2_might_wait_for_commit(journal); + wait_event(journal->j_wait_reserved, + atomic_read(&journal->j_reserved_credits) + total <= + journal->j_max_transaction_buffers); + __acquire(&journal->j_state_lock); /* fake out sparse */ + return 1; + } + + wait_transaction_locked(journal); + __acquire(&journal->j_state_lock); /* fake out sparse */ + return 1; + } + + /* + * The commit code assumes that it can get enough log space + * without forcing a checkpoint. This is *critical* for + * correctness: a checkpoint of a buffer which is also + * associated with a committing transaction creates a deadlock, + * so commit simply cannot force through checkpoints. + * + * We must therefore ensure the necessary space in the journal + * *before* starting to dirty potentially checkpointed buffers + * in the new transaction. + */ + if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) { + atomic_sub(total, &t->t_outstanding_credits); + read_unlock(&journal->j_state_lock); + jbd2_might_wait_for_commit(journal); + write_lock(&journal->j_state_lock); + if (jbd2_log_space_left(journal) < + journal->j_max_transaction_buffers) + __jbd2_log_wait_for_space(journal); + write_unlock(&journal->j_state_lock); + __acquire(&journal->j_state_lock); /* fake out sparse */ + return 1; + } + + /* No reservation? We are done... */ + if (!rsv_blocks) + return 0; + + needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits); + /* We allow at most half of a transaction to be reserved */ + if (needed > journal->j_max_transaction_buffers / 2) { + sub_reserved_credits(journal, rsv_blocks); + atomic_sub(total, &t->t_outstanding_credits); + read_unlock(&journal->j_state_lock); + jbd2_might_wait_for_commit(journal); + wait_event(journal->j_wait_reserved, + atomic_read(&journal->j_reserved_credits) + rsv_blocks + <= journal->j_max_transaction_buffers / 2); + __acquire(&journal->j_state_lock); /* fake out sparse */ + return 1; + } + return 0; +} + +/* + * start_this_handle: Given a handle, deal with any locking or stalling + * needed to make sure that there is enough journal space for the handle + * to begin. Attach the handle to a transaction and set up the + * transaction's buffer credits. + */ + +static int start_this_handle(journal_t *journal, handle_t *handle, + gfp_t gfp_mask) +{ + transaction_t *transaction, *new_transaction = NULL; + int blocks = handle->h_total_credits; + int rsv_blocks = 0; + unsigned long ts = jiffies; + + if (handle->h_rsv_handle) + rsv_blocks = handle->h_rsv_handle->h_total_credits; + + /* + * Limit the number of reserved credits to 1/2 of maximum transaction + * size and limit the number of total credits to not exceed maximum + * transaction size per operation. + */ + if ((rsv_blocks > journal->j_max_transaction_buffers / 2) || + (rsv_blocks + blocks > journal->j_max_transaction_buffers)) { + printk(KERN_ERR "JBD2: %s wants too many credits " + "credits:%d rsv_credits:%d max:%d\n", + current->comm, blocks, rsv_blocks, + journal->j_max_transaction_buffers); + WARN_ON(1); + return -ENOSPC; + } + +alloc_transaction: + /* + * This check is racy but it is just an optimization of allocating new + * transaction early if there are high chances we'll need it. If we + * guess wrong, we'll retry or free unused transaction. + */ + if (!data_race(journal->j_running_transaction)) { + /* + * If __GFP_FS is not present, then we may be being called from + * inside the fs writeback layer, so we MUST NOT fail. + */ + if ((gfp_mask & __GFP_FS) == 0) + gfp_mask |= __GFP_NOFAIL; + new_transaction = kmem_cache_zalloc(transaction_cache, + gfp_mask); + if (!new_transaction) + return -ENOMEM; + } + + jbd2_debug(3, "New handle %p going live.\n", handle); + + /* + * We need to hold j_state_lock until t_updates has been incremented, + * for proper journal barrier handling + */ +repeat: + read_lock(&journal->j_state_lock); + BUG_ON(journal->j_flags & JBD2_UNMOUNT); + if (is_journal_aborted(journal) || + (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { + read_unlock(&journal->j_state_lock); + jbd2_journal_free_transaction(new_transaction); + return -EROFS; + } + + /* + * Wait on the journal's transaction barrier if necessary. Specifically + * we allow reserved handles to proceed because otherwise commit could + * deadlock on page writeback not being able to complete. + */ + if (!handle->h_reserved && journal->j_barrier_count) { + read_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_transaction_locked, + journal->j_barrier_count == 0); + goto repeat; + } + + if (!journal->j_running_transaction) { + read_unlock(&journal->j_state_lock); + if (!new_transaction) + goto alloc_transaction; + write_lock(&journal->j_state_lock); + if (!journal->j_running_transaction && + (handle->h_reserved || !journal->j_barrier_count)) { + jbd2_get_transaction(journal, new_transaction); + new_transaction = NULL; + } + write_unlock(&journal->j_state_lock); + goto repeat; + } + + transaction = journal->j_running_transaction; + + if (!handle->h_reserved) { + /* We may have dropped j_state_lock - restart in that case */ + if (add_transaction_credits(journal, blocks, rsv_blocks)) { + /* + * add_transaction_credits releases + * j_state_lock on a non-zero return + */ + __release(&journal->j_state_lock); + goto repeat; + } + } else { + /* + * We have handle reserved so we are allowed to join T_LOCKED + * transaction and we don't have to check for transaction size + * and journal space. But we still have to wait while running + * transaction is being switched to a committing one as it + * won't wait for any handles anymore. + */ + if (transaction->t_state == T_SWITCH) { + wait_transaction_switching(journal); + goto repeat; + } + sub_reserved_credits(journal, blocks); + handle->h_reserved = 0; + } + + /* OK, account for the buffers that this operation expects to + * use and add the handle to the running transaction. + */ + update_t_max_wait(transaction, ts); + handle->h_transaction = transaction; + handle->h_requested_credits = blocks; + handle->h_revoke_credits_requested = handle->h_revoke_credits; + handle->h_start_jiffies = jiffies; + atomic_inc(&transaction->t_updates); + atomic_inc(&transaction->t_handle_count); + jbd2_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", + handle, blocks, + atomic_read(&transaction->t_outstanding_credits), + jbd2_log_space_left(journal)); + read_unlock(&journal->j_state_lock); + current->journal_info = handle; + + rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_); + jbd2_journal_free_transaction(new_transaction); + /* + * Ensure that no allocations done while the transaction is open are + * going to recurse back to the fs layer. + */ + handle->saved_alloc_context = memalloc_nofs_save(); + return 0; +} + +/* Allocate a new handle. This should probably be in a slab... */ +static handle_t *new_handle(int nblocks) +{ + handle_t *handle = jbd2_alloc_handle(GFP_NOFS); + if (!handle) + return NULL; + handle->h_total_credits = nblocks; + handle->h_ref = 1; + + return handle; +} + +handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, + int revoke_records, gfp_t gfp_mask, + unsigned int type, unsigned int line_no) +{ + handle_t *handle = journal_current_handle(); + int err; + + if (!journal) + return ERR_PTR(-EROFS); + + if (handle) { + J_ASSERT(handle->h_transaction->t_journal == journal); + handle->h_ref++; + return handle; + } + + nblocks += DIV_ROUND_UP(revoke_records, + journal->j_revoke_records_per_block); + handle = new_handle(nblocks); + if (!handle) + return ERR_PTR(-ENOMEM); + if (rsv_blocks) { + handle_t *rsv_handle; + + rsv_handle = new_handle(rsv_blocks); + if (!rsv_handle) { + jbd2_free_handle(handle); + return ERR_PTR(-ENOMEM); + } + rsv_handle->h_reserved = 1; + rsv_handle->h_journal = journal; + handle->h_rsv_handle = rsv_handle; + } + handle->h_revoke_credits = revoke_records; + + err = start_this_handle(journal, handle, gfp_mask); + if (err < 0) { + if (handle->h_rsv_handle) + jbd2_free_handle(handle->h_rsv_handle); + jbd2_free_handle(handle); + return ERR_PTR(err); + } + handle->h_type = type; + handle->h_line_no = line_no; + trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, + handle->h_transaction->t_tid, type, + line_no, nblocks); + + return handle; +} +EXPORT_SYMBOL(jbd2__journal_start); + + +/** + * jbd2_journal_start() - Obtain a new handle. + * @journal: Journal to start transaction on. + * @nblocks: number of block buffer we might modify + * + * We make sure that the transaction can guarantee at least nblocks of + * modified buffers in the log. We block until the log can guarantee + * that much space. Additionally, if rsv_blocks > 0, we also create another + * handle with rsv_blocks reserved blocks in the journal. This handle is + * stored in h_rsv_handle. It is not attached to any particular transaction + * and thus doesn't block transaction commit. If the caller uses this reserved + * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() + * on the parent handle will dispose the reserved one. Reserved handle has to + * be converted to a normal handle using jbd2_journal_start_reserved() before + * it can be used. + * + * Return a pointer to a newly allocated handle, or an ERR_PTR() value + * on failure. + */ +handle_t *jbd2_journal_start(journal_t *journal, int nblocks) +{ + return jbd2__journal_start(journal, nblocks, 0, 0, GFP_NOFS, 0, 0); +} +EXPORT_SYMBOL(jbd2_journal_start); + +static void __jbd2_journal_unreserve_handle(handle_t *handle, transaction_t *t) +{ + journal_t *journal = handle->h_journal; + + WARN_ON(!handle->h_reserved); + sub_reserved_credits(journal, handle->h_total_credits); + if (t) + atomic_sub(handle->h_total_credits, &t->t_outstanding_credits); +} + +void jbd2_journal_free_reserved(handle_t *handle) +{ + journal_t *journal = handle->h_journal; + + /* Get j_state_lock to pin running transaction if it exists */ + read_lock(&journal->j_state_lock); + __jbd2_journal_unreserve_handle(handle, journal->j_running_transaction); + read_unlock(&journal->j_state_lock); + jbd2_free_handle(handle); +} +EXPORT_SYMBOL(jbd2_journal_free_reserved); + +/** + * jbd2_journal_start_reserved() - start reserved handle + * @handle: handle to start + * @type: for handle statistics + * @line_no: for handle statistics + * + * Start handle that has been previously reserved with jbd2_journal_reserve(). + * This attaches @handle to the running transaction (or creates one if there's + * not transaction running). Unlike jbd2_journal_start() this function cannot + * block on journal commit, checkpointing, or similar stuff. It can block on + * memory allocation or frozen journal though. + * + * Return 0 on success, non-zero on error - handle is freed in that case. + */ +int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, + unsigned int line_no) +{ + journal_t *journal = handle->h_journal; + int ret = -EIO; + + if (WARN_ON(!handle->h_reserved)) { + /* Someone passed in normal handle? Just stop it. */ + jbd2_journal_stop(handle); + return ret; + } + /* + * Usefulness of mixing of reserved and unreserved handles is + * questionable. So far nobody seems to need it so just error out. + */ + if (WARN_ON(current->journal_info)) { + jbd2_journal_free_reserved(handle); + return ret; + } + + handle->h_journal = NULL; + /* + * GFP_NOFS is here because callers are likely from writeback or + * similarly constrained call sites + */ + ret = start_this_handle(journal, handle, GFP_NOFS); + if (ret < 0) { + handle->h_journal = journal; + jbd2_journal_free_reserved(handle); + return ret; + } + handle->h_type = type; + handle->h_line_no = line_no; + trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, + handle->h_transaction->t_tid, type, + line_no, handle->h_total_credits); + return 0; +} +EXPORT_SYMBOL(jbd2_journal_start_reserved); + +/** + * jbd2_journal_extend() - extend buffer credits. + * @handle: handle to 'extend' + * @nblocks: nr blocks to try to extend by. + * @revoke_records: number of revoke records to try to extend by. + * + * Some transactions, such as large extends and truncates, can be done + * atomically all at once or in several stages. The operation requests + * a credit for a number of buffer modifications in advance, but can + * extend its credit if it needs more. + * + * jbd2_journal_extend tries to give the running handle more buffer credits. + * It does not guarantee that allocation - this is a best-effort only. + * The calling process MUST be able to deal cleanly with a failure to + * extend here. + * + * Return 0 on success, non-zero on failure. + * + * return code < 0 implies an error + * return code > 0 implies normal transaction-full status. + */ +int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + int result; + int wanted; + + if (is_handle_aborted(handle)) + return -EROFS; + journal = transaction->t_journal; + + result = 1; + + read_lock(&journal->j_state_lock); + + /* Don't extend a locked-down transaction! */ + if (transaction->t_state != T_RUNNING) { + jbd2_debug(3, "denied handle %p %d blocks: " + "transaction not running\n", handle, nblocks); + goto error_out; + } + + nblocks += DIV_ROUND_UP( + handle->h_revoke_credits_requested + revoke_records, + journal->j_revoke_records_per_block) - + DIV_ROUND_UP( + handle->h_revoke_credits_requested, + journal->j_revoke_records_per_block); + wanted = atomic_add_return(nblocks, + &transaction->t_outstanding_credits); + + if (wanted > journal->j_max_transaction_buffers) { + jbd2_debug(3, "denied handle %p %d blocks: " + "transaction too large\n", handle, nblocks); + atomic_sub(nblocks, &transaction->t_outstanding_credits); + goto error_out; + } + + trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, + transaction->t_tid, + handle->h_type, handle->h_line_no, + handle->h_total_credits, + nblocks); + + handle->h_total_credits += nblocks; + handle->h_requested_credits += nblocks; + handle->h_revoke_credits += revoke_records; + handle->h_revoke_credits_requested += revoke_records; + result = 0; + + jbd2_debug(3, "extended handle %p by %d\n", handle, nblocks); +error_out: + read_unlock(&journal->j_state_lock); + return result; +} + +static void stop_this_handle(handle_t *handle) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal = transaction->t_journal; + int revokes; + + J_ASSERT(journal_current_handle() == handle); + J_ASSERT(atomic_read(&transaction->t_updates) > 0); + current->journal_info = NULL; + /* + * Subtract necessary revoke descriptor blocks from handle credits. We + * take care to account only for revoke descriptor blocks the + * transaction will really need as large sequences of transactions with + * small numbers of revokes are relatively common. + */ + revokes = handle->h_revoke_credits_requested - handle->h_revoke_credits; + if (revokes) { + int t_revokes, revoke_descriptors; + int rr_per_blk = journal->j_revoke_records_per_block; + + WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk) + > handle->h_total_credits); + t_revokes = atomic_add_return(revokes, + &transaction->t_outstanding_revokes); + revoke_descriptors = + DIV_ROUND_UP(t_revokes, rr_per_blk) - + DIV_ROUND_UP(t_revokes - revokes, rr_per_blk); + handle->h_total_credits -= revoke_descriptors; + } + atomic_sub(handle->h_total_credits, + &transaction->t_outstanding_credits); + if (handle->h_rsv_handle) + __jbd2_journal_unreserve_handle(handle->h_rsv_handle, + transaction); + if (atomic_dec_and_test(&transaction->t_updates)) + wake_up(&journal->j_wait_updates); + + rwsem_release(&journal->j_trans_commit_map, _THIS_IP_); + /* + * Scope of the GFP_NOFS context is over here and so we can restore the + * original alloc context. + */ + memalloc_nofs_restore(handle->saved_alloc_context); +} + +/** + * jbd2__journal_restart() - restart a handle . + * @handle: handle to restart + * @nblocks: nr credits requested + * @revoke_records: number of revoke record credits requested + * @gfp_mask: memory allocation flags (for start_this_handle) + * + * Restart a handle for a multi-transaction filesystem + * operation. + * + * If the jbd2_journal_extend() call above fails to grant new buffer credits + * to a running handle, a call to jbd2_journal_restart will commit the + * handle's transaction so far and reattach the handle to a new + * transaction capable of guaranteeing the requested number of + * credits. We preserve reserved handle if there's any attached to the + * passed in handle. + */ +int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, + gfp_t gfp_mask) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + tid_t tid; + int need_to_start; + int ret; + + /* If we've had an abort of any type, don't even think about + * actually doing the restart! */ + if (is_handle_aborted(handle)) + return 0; + journal = transaction->t_journal; + tid = transaction->t_tid; + + /* + * First unlink the handle from its current transaction, and start the + * commit on that. + */ + jbd2_debug(2, "restarting handle %p\n", handle); + stop_this_handle(handle); + handle->h_transaction = NULL; + + /* + * TODO: If we use READ_ONCE / WRITE_ONCE for j_commit_request we can + * get rid of pointless j_state_lock traffic like this. + */ + read_lock(&journal->j_state_lock); + need_to_start = !tid_geq(journal->j_commit_request, tid); + read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); + handle->h_total_credits = nblocks + + DIV_ROUND_UP(revoke_records, + journal->j_revoke_records_per_block); + handle->h_revoke_credits = revoke_records; + ret = start_this_handle(journal, handle, gfp_mask); + trace_jbd2_handle_restart(journal->j_fs_dev->bd_dev, + ret ? 0 : handle->h_transaction->t_tid, + handle->h_type, handle->h_line_no, + handle->h_total_credits); + return ret; +} +EXPORT_SYMBOL(jbd2__journal_restart); + + +int jbd2_journal_restart(handle_t *handle, int nblocks) +{ + return jbd2__journal_restart(handle, nblocks, 0, GFP_NOFS); +} +EXPORT_SYMBOL(jbd2_journal_restart); + +/* + * Waits for any outstanding t_updates to finish. + * This is called with write j_state_lock held. + */ +void jbd2_journal_wait_updates(journal_t *journal) +{ + DEFINE_WAIT(wait); + + while (1) { + /* + * Note that the running transaction can get freed under us if + * this transaction is getting committed in + * jbd2_journal_commit_transaction() -> + * jbd2_journal_free_transaction(). This can only happen when we + * release j_state_lock -> schedule() -> acquire j_state_lock. + * Hence we should everytime retrieve new j_running_transaction + * value (after j_state_lock release acquire cycle), else it may + * lead to use-after-free of old freed transaction. + */ + transaction_t *transaction = journal->j_running_transaction; + + if (!transaction) + break; + + prepare_to_wait(&journal->j_wait_updates, &wait, + TASK_UNINTERRUPTIBLE); + if (!atomic_read(&transaction->t_updates)) { + finish_wait(&journal->j_wait_updates, &wait); + break; + } + write_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_wait_updates, &wait); + write_lock(&journal->j_state_lock); + } +} + +/** + * jbd2_journal_lock_updates () - establish a transaction barrier. + * @journal: Journal to establish a barrier on. + * + * This locks out any further updates from being started, and blocks + * until all existing updates have completed, returning only once the + * journal is in a quiescent state with no updates running. + * + * The journal lock should not be held on entry. + */ +void jbd2_journal_lock_updates(journal_t *journal) +{ + jbd2_might_wait_for_commit(journal); + + write_lock(&journal->j_state_lock); + ++journal->j_barrier_count; + + /* Wait until there are no reserved handles */ + if (atomic_read(&journal->j_reserved_credits)) { + write_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_reserved, + atomic_read(&journal->j_reserved_credits) == 0); + write_lock(&journal->j_state_lock); + } + + /* Wait until there are no running t_updates */ + jbd2_journal_wait_updates(journal); + + write_unlock(&journal->j_state_lock); + + /* + * We have now established a barrier against other normal updates, but + * we also need to barrier against other jbd2_journal_lock_updates() calls + * to make sure that we serialise special journal-locked operations + * too. + */ + mutex_lock(&journal->j_barrier); +} + +/** + * jbd2_journal_unlock_updates () - release barrier + * @journal: Journal to release the barrier on. + * + * Release a transaction barrier obtained with jbd2_journal_lock_updates(). + * + * Should be called without the journal lock held. + */ +void jbd2_journal_unlock_updates (journal_t *journal) +{ + J_ASSERT(journal->j_barrier_count != 0); + + mutex_unlock(&journal->j_barrier); + write_lock(&journal->j_state_lock); + --journal->j_barrier_count; + write_unlock(&journal->j_state_lock); + wake_up_all(&journal->j_wait_transaction_locked); +} + +static void warn_dirty_buffer(struct buffer_head *bh) +{ + printk(KERN_WARNING + "JBD2: Spotted dirty metadata buffer (dev = %pg, blocknr = %llu). " + "There's a risk of filesystem corruption in case of system " + "crash.\n", + bh->b_bdev, (unsigned long long)bh->b_blocknr); +} + +/* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */ +static void jbd2_freeze_jh_data(struct journal_head *jh) +{ + struct page *page; + int offset; + char *source; + struct buffer_head *bh = jh2bh(jh); + + J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n"); + page = bh->b_page; + offset = offset_in_page(bh->b_data); + source = kmap_atomic(page); + /* Fire data frozen trigger just before we copy the data */ + jbd2_buffer_frozen_trigger(jh, source + offset, jh->b_triggers); + memcpy(jh->b_frozen_data, source + offset, bh->b_size); + kunmap_atomic(source); + + /* + * Now that the frozen data is saved off, we need to store any matching + * triggers. + */ + jh->b_frozen_triggers = jh->b_triggers; +} + +/* + * If the buffer is already part of the current transaction, then there + * is nothing we need to do. If it is already part of a prior + * transaction which we are still committing to disk, then we need to + * make sure that we do not overwrite the old copy: we do copy-out to + * preserve the copy going to disk. We also account the buffer against + * the handle's metadata buffer credits (unless the buffer is already + * part of the transaction, that is). + * + */ +static int +do_get_write_access(handle_t *handle, struct journal_head *jh, + int force_copy) +{ + struct buffer_head *bh; + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + int error; + char *frozen_buffer = NULL; + unsigned long start_lock, time_lock; + + journal = transaction->t_journal; + + jbd2_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); + + JBUFFER_TRACE(jh, "entry"); +repeat: + bh = jh2bh(jh); + + /* @@@ Need to check for errors here at some point. */ + + start_lock = jiffies; + lock_buffer(bh); + spin_lock(&jh->b_state_lock); + + /* If it takes too long to lock the buffer, trace it */ + time_lock = jbd2_time_diff(start_lock, jiffies); + if (time_lock > HZ/10) + trace_jbd2_lock_buffer_stall(bh->b_bdev->bd_dev, + jiffies_to_msecs(time_lock)); + + /* We now hold the buffer lock so it is safe to query the buffer + * state. Is the buffer dirty? + * + * If so, there are two possibilities. The buffer may be + * non-journaled, and undergoing a quite legitimate writeback. + * Otherwise, it is journaled, and we don't expect dirty buffers + * in that state (the buffers should be marked JBD_Dirty + * instead.) So either the IO is being done under our own + * control and this is a bug, or it's a third party IO such as + * dump(8) (which may leave the buffer scheduled for read --- + * ie. locked but not dirty) or tune2fs (which may actually have + * the buffer dirtied, ugh.) */ + + if (buffer_dirty(bh) && jh->b_transaction) { + warn_dirty_buffer(bh); + /* + * We need to clean the dirty flag and we must do it under the + * buffer lock to be sure we don't race with running write-out. + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + clear_buffer_dirty(bh); + /* + * The buffer is going to be added to BJ_Reserved list now and + * nothing guarantees jbd2_journal_dirty_metadata() will be + * ever called for it. So we need to set jbddirty bit here to + * make sure the buffer is dirtied and written out when the + * journaling machinery is done with it. + */ + set_buffer_jbddirty(bh); + } + + error = -EROFS; + if (is_handle_aborted(handle)) { + spin_unlock(&jh->b_state_lock); + unlock_buffer(bh); + goto out; + } + error = 0; + + /* + * The buffer is already part of this transaction if b_transaction or + * b_next_transaction points to it + */ + if (jh->b_transaction == transaction || + jh->b_next_transaction == transaction) { + unlock_buffer(bh); + goto done; + } + + /* + * this is the first time this transaction is touching this buffer, + * reset the modified flag + */ + jh->b_modified = 0; + + /* + * If the buffer is not journaled right now, we need to make sure it + * doesn't get written to disk before the caller actually commits the + * new data + */ + if (!jh->b_transaction) { + JBUFFER_TRACE(jh, "no transaction"); + J_ASSERT_JH(jh, !jh->b_next_transaction); + JBUFFER_TRACE(jh, "file as BJ_Reserved"); + /* + * Make sure all stores to jh (b_modified, b_frozen_data) are + * visible before attaching it to the running transaction. + * Paired with barrier in jbd2_write_access_granted() + */ + smp_wmb(); + spin_lock(&journal->j_list_lock); + if (test_clear_buffer_dirty(bh)) { + /* + * Execute buffer dirty clearing and jh->b_transaction + * assignment under journal->j_list_lock locked to + * prevent bh being removed from checkpoint list if + * the buffer is in an intermediate state (not dirty + * and jh->b_transaction is NULL). + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + set_buffer_jbddirty(bh); + } + __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); + unlock_buffer(bh); + goto done; + } + unlock_buffer(bh); + + /* + * If there is already a copy-out version of this buffer, then we don't + * need to make another one + */ + if (jh->b_frozen_data) { + JBUFFER_TRACE(jh, "has frozen data"); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + goto attach_next; + } + + JBUFFER_TRACE(jh, "owned by older transaction"); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_transaction == journal->j_committing_transaction); + + /* + * There is one case we have to be very careful about. If the + * committing transaction is currently writing this buffer out to disk + * and has NOT made a copy-out, then we cannot modify the buffer + * contents at all right now. The essence of copy-out is that it is + * the extra copy, not the primary copy, which gets journaled. If the + * primary copy is already going to disk then we cannot do copy-out + * here. + */ + if (buffer_shadow(bh)) { + JBUFFER_TRACE(jh, "on shadow: sleep"); + spin_unlock(&jh->b_state_lock); + wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE); + goto repeat; + } + + /* + * Only do the copy if the currently-owning transaction still needs it. + * If buffer isn't on BJ_Metadata list, the committing transaction is + * past that stage (here we use the fact that BH_Shadow is set under + * bh_state lock together with refiling to BJ_Shadow list and at this + * point we know the buffer doesn't have BH_Shadow set). + * + * Subtle point, though: if this is a get_undo_access, then we will be + * relying on the frozen_data to contain the new value of the + * committed_data record after the transaction, so we HAVE to force the + * frozen_data copy in that case. + */ + if (jh->b_jlist == BJ_Metadata || force_copy) { + JBUFFER_TRACE(jh, "generate frozen data"); + if (!frozen_buffer) { + JBUFFER_TRACE(jh, "allocate memory for buffer"); + spin_unlock(&jh->b_state_lock); + frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, + GFP_NOFS | __GFP_NOFAIL); + goto repeat; + } + jh->b_frozen_data = frozen_buffer; + frozen_buffer = NULL; + jbd2_freeze_jh_data(jh); + } +attach_next: + /* + * Make sure all stores to jh (b_modified, b_frozen_data) are visible + * before attaching it to the running transaction. Paired with barrier + * in jbd2_write_access_granted() + */ + smp_wmb(); + jh->b_next_transaction = transaction; + +done: + spin_unlock(&jh->b_state_lock); + + /* + * If we are about to journal a buffer, then any revoke pending on it is + * no longer valid + */ + jbd2_journal_cancel_revoke(handle, jh); + +out: + if (unlikely(frozen_buffer)) /* It's usually NULL */ + jbd2_free(frozen_buffer, bh->b_size); + + JBUFFER_TRACE(jh, "exit"); + return error; +} + +/* Fast check whether buffer is already attached to the required transaction */ +static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, + bool undo) +{ + struct journal_head *jh; + bool ret = false; + + /* Dirty buffers require special handling... */ + if (buffer_dirty(bh)) + return false; + + /* + * RCU protects us from dereferencing freed pages. So the checks we do + * are guaranteed not to oops. However the jh slab object can get freed + * & reallocated while we work with it. So we have to be careful. When + * we see jh attached to the running transaction, we know it must stay + * so until the transaction is committed. Thus jh won't be freed and + * will be attached to the same bh while we run. However it can + * happen jh gets freed, reallocated, and attached to the transaction + * just after we get pointer to it from bh. So we have to be careful + * and recheck jh still belongs to our bh before we return success. + */ + rcu_read_lock(); + if (!buffer_jbd(bh)) + goto out; + /* This should be bh2jh() but that doesn't work with inline functions */ + jh = READ_ONCE(bh->b_private); + if (!jh) + goto out; + /* For undo access buffer must have data copied */ + if (undo && !jh->b_committed_data) + goto out; + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) + goto out; + /* + * There are two reasons for the barrier here: + * 1) Make sure to fetch b_bh after we did previous checks so that we + * detect when jh went through free, realloc, attach to transaction + * while we were checking. Paired with implicit barrier in that path. + * 2) So that access to bh done after jbd2_write_access_granted() + * doesn't get reordered and see inconsistent state of concurrent + * do_get_write_access(). + */ + smp_mb(); + if (unlikely(jh->b_bh != bh)) + goto out; + ret = true; +out: + rcu_read_unlock(); + return ret; +} + +/** + * jbd2_journal_get_write_access() - notify intent to modify a buffer + * for metadata (not data) update. + * @handle: transaction to add buffer modifications to + * @bh: bh to be used for metadata writes + * + * Returns: error code or 0 on success. + * + * In full data journalling mode the buffer may be of type BJ_AsyncData, + * because we're ``write()ing`` a buffer which is also part of a shared mapping. + */ + +int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) +{ + struct journal_head *jh; + int rc; + + if (is_handle_aborted(handle)) + return -EROFS; + + if (jbd2_write_access_granted(handle, bh, false)) + return 0; + + jh = jbd2_journal_add_journal_head(bh); + /* We do not want to get caught playing with fields which the + * log thread also manipulates. Make sure that the buffer + * completes any outstanding IO before proceeding. */ + rc = do_get_write_access(handle, jh, 0); + jbd2_journal_put_journal_head(jh); + return rc; +} + + +/* + * When the user wants to journal a newly created buffer_head + * (ie. getblk() returned a new buffer and we are going to populate it + * manually rather than reading off disk), then we need to keep the + * buffer_head locked until it has been completely filled with new + * data. In this case, we should be able to make the assertion that + * the bh is not already part of an existing transaction. + * + * The buffer should already be locked by the caller by this point. + * There is no lock ranking violation: it was a newly created, + * unlocked buffer beforehand. */ + +/** + * jbd2_journal_get_create_access () - notify intent to use newly created bh + * @handle: transaction to new buffer to + * @bh: new buffer. + * + * Call this if you create a new bh. + */ +int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + struct journal_head *jh = jbd2_journal_add_journal_head(bh); + int err; + + jbd2_debug(5, "journal_head %p\n", jh); + err = -EROFS; + if (is_handle_aborted(handle)) + goto out; + journal = transaction->t_journal; + err = 0; + + JBUFFER_TRACE(jh, "entry"); + /* + * The buffer may already belong to this transaction due to pre-zeroing + * in the filesystem's new_block code. It may also be on the previous, + * committing transaction's lists, but it HAS to be in Forget state in + * that case: the transaction must have deleted the buffer for it to be + * reused here. + */ + spin_lock(&jh->b_state_lock); + J_ASSERT_JH(jh, (jh->b_transaction == transaction || + jh->b_transaction == NULL || + (jh->b_transaction == journal->j_committing_transaction && + jh->b_jlist == BJ_Forget))); + + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, buffer_locked(jh2bh(jh))); + + if (jh->b_transaction == NULL) { + /* + * Previous jbd2_journal_forget() could have left the buffer + * with jbddirty bit set because it was being committed. When + * the commit finished, we've filed the buffer for + * checkpointing and marked it dirty. Now we are reallocating + * the buffer so the transaction freeing it must have + * committed and so it's safe to clear the dirty bit. + */ + clear_buffer_dirty(jh2bh(jh)); + /* first access by this transaction */ + jh->b_modified = 0; + + JBUFFER_TRACE(jh, "file as BJ_Reserved"); + spin_lock(&journal->j_list_lock); + __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); + } else if (jh->b_transaction == journal->j_committing_transaction) { + /* first access by this transaction */ + jh->b_modified = 0; + + JBUFFER_TRACE(jh, "set next transaction"); + spin_lock(&journal->j_list_lock); + jh->b_next_transaction = transaction; + spin_unlock(&journal->j_list_lock); + } + spin_unlock(&jh->b_state_lock); + + /* + * akpm: I added this. ext3_alloc_branch can pick up new indirect + * blocks which contain freed but then revoked metadata. We need + * to cancel the revoke in case we end up freeing it yet again + * and the reallocating as data - this would cause a second revoke, + * which hits an assertion error. + */ + JBUFFER_TRACE(jh, "cancelling revoke"); + jbd2_journal_cancel_revoke(handle, jh); +out: + jbd2_journal_put_journal_head(jh); + return err; +} + +/** + * jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * non-rewindable consequences + * @handle: transaction + * @bh: buffer to undo + * + * Sometimes there is a need to distinguish between metadata which has + * been committed to disk and that which has not. The ext3fs code uses + * this for freeing and allocating space, we have to make sure that we + * do not reuse freed space until the deallocation has been committed, + * since if we overwrote that space we would make the delete + * un-rewindable in case of a crash. + * + * To deal with that, jbd2_journal_get_undo_access requests write access to a + * buffer for parts of non-rewindable operations such as delete + * operations on the bitmaps. The journaling code must keep a copy of + * the buffer's contents prior to the undo_access call until such time + * as we know that the buffer has definitely been committed to disk. + * + * We never need to know which transaction the committed data is part + * of, buffers touched here are guaranteed to be dirtied later and so + * will be committed to a new transaction in due course, at which point + * we can discard the old committed data pointer. + * + * Returns error number or 0 on success. + */ +int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) +{ + int err; + struct journal_head *jh; + char *committed_data = NULL; + + if (is_handle_aborted(handle)) + return -EROFS; + + if (jbd2_write_access_granted(handle, bh, true)) + return 0; + + jh = jbd2_journal_add_journal_head(bh); + JBUFFER_TRACE(jh, "entry"); + + /* + * Do this first --- it can drop the journal lock, so we want to + * make sure that obtaining the committed_data is done + * atomically wrt. completion of any outstanding commits. + */ + err = do_get_write_access(handle, jh, 1); + if (err) + goto out; + +repeat: + if (!jh->b_committed_data) + committed_data = jbd2_alloc(jh2bh(jh)->b_size, + GFP_NOFS|__GFP_NOFAIL); + + spin_lock(&jh->b_state_lock); + if (!jh->b_committed_data) { + /* Copy out the current buffer contents into the + * preserved, committed copy. */ + JBUFFER_TRACE(jh, "generate b_committed data"); + if (!committed_data) { + spin_unlock(&jh->b_state_lock); + goto repeat; + } + + jh->b_committed_data = committed_data; + committed_data = NULL; + memcpy(jh->b_committed_data, bh->b_data, bh->b_size); + } + spin_unlock(&jh->b_state_lock); +out: + jbd2_journal_put_journal_head(jh); + if (unlikely(committed_data)) + jbd2_free(committed_data, bh->b_size); + return err; +} + +/** + * jbd2_journal_set_triggers() - Add triggers for commit writeout + * @bh: buffer to trigger on + * @type: struct jbd2_buffer_trigger_type containing the trigger(s). + * + * Set any triggers on this journal_head. This is always safe, because + * triggers for a committing buffer will be saved off, and triggers for + * a running transaction will match the buffer in that transaction. + * + * Call with NULL to clear the triggers. + */ +void jbd2_journal_set_triggers(struct buffer_head *bh, + struct jbd2_buffer_trigger_type *type) +{ + struct journal_head *jh = jbd2_journal_grab_journal_head(bh); + + if (WARN_ON_ONCE(!jh)) + return; + jh->b_triggers = type; + jbd2_journal_put_journal_head(jh); +} + +void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, + struct jbd2_buffer_trigger_type *triggers) +{ + struct buffer_head *bh = jh2bh(jh); + + if (!triggers || !triggers->t_frozen) + return; + + triggers->t_frozen(triggers, bh, mapped_data, bh->b_size); +} + +void jbd2_buffer_abort_trigger(struct journal_head *jh, + struct jbd2_buffer_trigger_type *triggers) +{ + if (!triggers || !triggers->t_abort) + return; + + triggers->t_abort(triggers, jh2bh(jh)); +} + +/** + * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * @handle: transaction to add buffer to. + * @bh: buffer to mark + * + * mark dirty metadata which needs to be journaled as part of the current + * transaction. + * + * The buffer must have previously had jbd2_journal_get_write_access() + * called so that it has a valid journal_head attached to the buffer + * head. + * + * The buffer is placed on the transaction's metadata list and is marked + * as belonging to the transaction. + * + * Returns error number or 0 on success. + * + * Special care needs to be taken if the buffer already belongs to the + * current committing transaction (in which case we should have frozen + * data present for that commit). In that case, we don't relink the + * buffer: that only gets done when the old transaction finally + * completes its commit. + */ +int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + struct journal_head *jh; + int ret = 0; + + if (!buffer_jbd(bh)) + return -EUCLEAN; + + /* + * We don't grab jh reference here since the buffer must be part + * of the running transaction. + */ + jh = bh2jh(bh); + jbd2_debug(5, "journal_head %p\n", jh); + JBUFFER_TRACE(jh, "entry"); + + /* + * This and the following assertions are unreliable since we may see jh + * in inconsistent state unless we grab bh_state lock. But this is + * crucial to catch bugs so let's do a reliable check until the + * lockless handling is fully proven. + */ + if (data_race(jh->b_transaction != transaction && + jh->b_next_transaction != transaction)) { + spin_lock(&jh->b_state_lock); + J_ASSERT_JH(jh, jh->b_transaction == transaction || + jh->b_next_transaction == transaction); + spin_unlock(&jh->b_state_lock); + } + if (jh->b_modified == 1) { + /* If it's in our transaction it must be in BJ_Metadata list. */ + if (data_race(jh->b_transaction == transaction && + jh->b_jlist != BJ_Metadata)) { + spin_lock(&jh->b_state_lock); + if (jh->b_transaction == transaction && + jh->b_jlist != BJ_Metadata) + pr_err("JBD2: assertion failure: h_type=%u " + "h_line_no=%u block_no=%llu jlist=%u\n", + handle->h_type, handle->h_line_no, + (unsigned long long) bh->b_blocknr, + jh->b_jlist); + J_ASSERT_JH(jh, jh->b_transaction != transaction || + jh->b_jlist == BJ_Metadata); + spin_unlock(&jh->b_state_lock); + } + goto out; + } + + journal = transaction->t_journal; + spin_lock(&jh->b_state_lock); + + if (is_handle_aborted(handle)) { + /* + * Check journal aborting with @jh->b_state_lock locked, + * since 'jh->b_transaction' could be replaced with + * 'jh->b_next_transaction' during old transaction + * committing if journal aborted, which may fail + * assertion on 'jh->b_frozen_data == NULL'. + */ + ret = -EROFS; + goto out_unlock_bh; + } + + if (jh->b_modified == 0) { + /* + * This buffer's got modified and becoming part + * of the transaction. This needs to be done + * once a transaction -bzzz + */ + if (WARN_ON_ONCE(jbd2_handle_buffer_credits(handle) <= 0)) { + ret = -ENOSPC; + goto out_unlock_bh; + } + jh->b_modified = 1; + handle->h_total_credits--; + } + + /* + * fastpath, to avoid expensive locking. If this buffer is already + * on the running transaction's metadata list there is nothing to do. + * Nobody can take it off again because there is a handle open. + * I _think_ we're OK here with SMP barriers - a mistaken decision will + * result in this test being false, so we go in and take the locks. + */ + if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) { + JBUFFER_TRACE(jh, "fastpath"); + if (unlikely(jh->b_transaction != + journal->j_running_transaction)) { + printk(KERN_ERR "JBD2: %s: " + "jh->b_transaction (%llu, %p, %u) != " + "journal->j_running_transaction (%p, %u)\n", + journal->j_devname, + (unsigned long long) bh->b_blocknr, + jh->b_transaction, + jh->b_transaction ? jh->b_transaction->t_tid : 0, + journal->j_running_transaction, + journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0); + ret = -EINVAL; + } + goto out_unlock_bh; + } + + set_buffer_jbddirty(bh); + + /* + * Metadata already on the current transaction list doesn't + * need to be filed. Metadata on another transaction's list must + * be committing, and will be refiled once the commit completes: + * leave it alone for now. + */ + if (jh->b_transaction != transaction) { + JBUFFER_TRACE(jh, "already on other transaction"); + if (unlikely(((jh->b_transaction != + journal->j_committing_transaction)) || + (jh->b_next_transaction != transaction))) { + printk(KERN_ERR "jbd2_journal_dirty_metadata: %s: " + "bad jh for block %llu: " + "transaction (%p, %u), " + "jh->b_transaction (%p, %u), " + "jh->b_next_transaction (%p, %u), jlist %u\n", + journal->j_devname, + (unsigned long long) bh->b_blocknr, + transaction, transaction->t_tid, + jh->b_transaction, + jh->b_transaction ? + jh->b_transaction->t_tid : 0, + jh->b_next_transaction, + jh->b_next_transaction ? + jh->b_next_transaction->t_tid : 0, + jh->b_jlist); + WARN_ON(1); + ret = -EINVAL; + } + /* And this case is illegal: we can't reuse another + * transaction's data buffer, ever. */ + goto out_unlock_bh; + } + + /* That test should have eliminated the following case: */ + J_ASSERT_JH(jh, jh->b_frozen_data == NULL); + + JBUFFER_TRACE(jh, "file as BJ_Metadata"); + spin_lock(&journal->j_list_lock); + __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata); + spin_unlock(&journal->j_list_lock); +out_unlock_bh: + spin_unlock(&jh->b_state_lock); +out: + JBUFFER_TRACE(jh, "exit"); + return ret; +} + +/** + * jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * @handle: transaction handle + * @bh: bh to 'forget' + * + * We can only do the bforget if there are no commits pending against the + * buffer. If the buffer is dirty in the current running transaction we + * can safely unlink it. + * + * bh may not be a journalled buffer at all - it may be a non-JBD + * buffer which came off the hashtable. Check for this. + * + * Decrements bh->b_count by one. + * + * Allow this call even if the handle has aborted --- it may be part of + * the caller's cleanup after an abort. + */ +int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + struct journal_head *jh; + int drop_reserve = 0; + int err = 0; + int was_modified = 0; + + if (is_handle_aborted(handle)) + return -EROFS; + journal = transaction->t_journal; + + BUFFER_TRACE(bh, "entry"); + + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) { + __bforget(bh); + return 0; + } + + spin_lock(&jh->b_state_lock); + + /* Critical error: attempting to delete a bitmap buffer, maybe? + * Don't do any jbd operations, and return an error. */ + if (!J_EXPECT_JH(jh, !jh->b_committed_data, + "inconsistent data on disk")) { + err = -EIO; + goto drop; + } + + /* keep track of whether or not this transaction modified us */ + was_modified = jh->b_modified; + + /* + * The buffer's going from the transaction, we must drop + * all references -bzzz + */ + jh->b_modified = 0; + + if (jh->b_transaction == transaction) { + J_ASSERT_JH(jh, !jh->b_frozen_data); + + /* If we are forgetting a buffer which is already part + * of this transaction, then we can just drop it from + * the transaction immediately. */ + clear_buffer_dirty(bh); + clear_buffer_jbddirty(bh); + + JBUFFER_TRACE(jh, "belongs to current transaction: unfile"); + + /* + * we only want to drop a reference if this transaction + * modified the buffer + */ + if (was_modified) + drop_reserve = 1; + + /* + * We are no longer going to journal this buffer. + * However, the commit of this transaction is still + * important to the buffer: the delete that we are now + * processing might obsolete an old log entry, so by + * committing, we can satisfy the buffer's checkpoint. + * + * So, if we have a checkpoint on the buffer, we should + * now refile the buffer on our BJ_Forget list so that + * we know to remove the checkpoint after we commit. + */ + + spin_lock(&journal->j_list_lock); + if (jh->b_cp_transaction) { + __jbd2_journal_temp_unlink_buffer(jh); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + } else { + __jbd2_journal_unfile_buffer(jh); + jbd2_journal_put_journal_head(jh); + } + spin_unlock(&journal->j_list_lock); + } else if (jh->b_transaction) { + J_ASSERT_JH(jh, (jh->b_transaction == + journal->j_committing_transaction)); + /* However, if the buffer is still owned by a prior + * (committing) transaction, we can't drop it yet... */ + JBUFFER_TRACE(jh, "belongs to older transaction"); + /* ... but we CAN drop it from the new transaction through + * marking the buffer as freed and set j_next_transaction to + * the new transaction, so that not only the commit code + * knows it should clear dirty bits when it is done with the + * buffer, but also the buffer can be checkpointed only + * after the new transaction commits. */ + + set_buffer_freed(bh); + + if (!jh->b_next_transaction) { + spin_lock(&journal->j_list_lock); + jh->b_next_transaction = transaction; + spin_unlock(&journal->j_list_lock); + } else { + J_ASSERT(jh->b_next_transaction == transaction); + + /* + * only drop a reference if this transaction modified + * the buffer + */ + if (was_modified) + drop_reserve = 1; + } + } else { + /* + * Finally, if the buffer is not belongs to any + * transaction, we can just drop it now if it has no + * checkpoint. + */ + spin_lock(&journal->j_list_lock); + if (!jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "belongs to none transaction"); + spin_unlock(&journal->j_list_lock); + goto drop; + } + + /* + * Otherwise, if the buffer has been written to disk, + * it is safe to remove the checkpoint and drop it. + */ + if (jbd2_journal_try_remove_checkpoint(jh) >= 0) { + spin_unlock(&journal->j_list_lock); + goto drop; + } + + /* + * The buffer is still not written to disk, we should + * attach this buffer to current transaction so that the + * buffer can be checkpointed only after the current + * transaction commits. + */ + clear_buffer_dirty(bh); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + spin_unlock(&journal->j_list_lock); + } +drop: + __brelse(bh); + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh); + if (drop_reserve) { + /* no need to reserve log space for this block -bzzz */ + handle->h_total_credits++; + } + return err; +} + +/** + * jbd2_journal_stop() - complete a transaction + * @handle: transaction to complete. + * + * All done for a particular handle. + * + * There is not much action needed here. We just return any remaining + * buffer credits to the transaction and remove the handle. The only + * complication is that we need to start a commit operation if the + * filesystem is marked for synchronous update. + * + * jbd2_journal_stop itself will not usually return an error, but it may + * do so in unusual circumstances. In particular, expect it to + * return -EIO if a jbd2_journal_abort has been executed since the + * transaction began. + */ +int jbd2_journal_stop(handle_t *handle) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + int err = 0, wait_for_commit = 0; + tid_t tid; + pid_t pid; + + if (--handle->h_ref > 0) { + jbd2_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, + handle->h_ref); + if (is_handle_aborted(handle)) + return -EIO; + return 0; + } + if (!transaction) { + /* + * Handle is already detached from the transaction so there is + * nothing to do other than free the handle. + */ + memalloc_nofs_restore(handle->saved_alloc_context); + goto free_and_exit; + } + journal = transaction->t_journal; + tid = transaction->t_tid; + + if (is_handle_aborted(handle)) + err = -EIO; + + jbd2_debug(4, "Handle %p going down\n", handle); + trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev, + tid, handle->h_type, handle->h_line_no, + jiffies - handle->h_start_jiffies, + handle->h_sync, handle->h_requested_credits, + (handle->h_requested_credits - + handle->h_total_credits)); + + /* + * Implement synchronous transaction batching. If the handle + * was synchronous, don't force a commit immediately. Let's + * yield and let another thread piggyback onto this + * transaction. Keep doing that while new threads continue to + * arrive. It doesn't cost much - we're about to run a commit + * and sleep on IO anyway. Speeds up many-threaded, many-dir + * operations by 30x or more... + * + * We try and optimize the sleep time against what the + * underlying disk can do, instead of having a static sleep + * time. This is useful for the case where our storage is so + * fast that it is more optimal to go ahead and force a flush + * and wait for the transaction to be committed than it is to + * wait for an arbitrary amount of time for new writers to + * join the transaction. We achieve this by measuring how + * long it takes to commit a transaction, and compare it with + * how long this transaction has been running, and if run time + * < commit time then we sleep for the delta and commit. This + * greatly helps super fast disks that would see slowdowns as + * more threads started doing fsyncs. + * + * But don't do this if this process was the most recent one + * to perform a synchronous write. We do this to detect the + * case where a single process is doing a stream of sync + * writes. No point in waiting for joiners in that case. + * + * Setting max_batch_time to 0 disables this completely. + */ + pid = current->pid; + if (handle->h_sync && journal->j_last_sync_writer != pid && + journal->j_max_batch_time) { + u64 commit_time, trans_time; + + journal->j_last_sync_writer = pid; + + read_lock(&journal->j_state_lock); + commit_time = journal->j_average_commit_time; + read_unlock(&journal->j_state_lock); + + trans_time = ktime_to_ns(ktime_sub(ktime_get(), + transaction->t_start_time)); + + commit_time = max_t(u64, commit_time, + 1000*journal->j_min_batch_time); + commit_time = min_t(u64, commit_time, + 1000*journal->j_max_batch_time); + + if (trans_time < commit_time) { + ktime_t expires = ktime_add_ns(ktime_get(), + commit_time); + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); + } + } + + if (handle->h_sync) + transaction->t_synchronous_commit = 1; + + /* + * If the handle is marked SYNC, we need to set another commit + * going! We also want to force a commit if the transaction is too + * old now. + */ + if (handle->h_sync || + time_after_eq(jiffies, transaction->t_expires)) { + /* Do this even for aborted journals: an abort still + * completes the commit thread, it just doesn't write + * anything to disk. */ + + jbd2_debug(2, "transaction too old, requesting commit for " + "handle %p\n", handle); + /* This is non-blocking */ + jbd2_log_start_commit(journal, tid); + + /* + * Special case: JBD2_SYNC synchronous updates require us + * to wait for the commit to complete. + */ + if (handle->h_sync && !(current->flags & PF_MEMALLOC)) + wait_for_commit = 1; + } + + /* + * Once stop_this_handle() drops t_updates, the transaction could start + * committing on us and eventually disappear. So we must not + * dereference transaction pointer again after calling + * stop_this_handle(). + */ + stop_this_handle(handle); + + if (wait_for_commit) + err = jbd2_log_wait_commit(journal, tid); + +free_and_exit: + if (handle->h_rsv_handle) + jbd2_free_handle(handle->h_rsv_handle); + jbd2_free_handle(handle); + return err; +} + +/* + * + * List management code snippets: various functions for manipulating the + * transaction buffer lists. + * + */ + +/* + * Append a buffer to a transaction list, given the transaction's list head + * pointer. + * + * j_list_lock is held. + * + * jh->b_state_lock is held. + */ + +static inline void +__blist_add_buffer(struct journal_head **list, struct journal_head *jh) +{ + if (!*list) { + jh->b_tnext = jh->b_tprev = jh; + *list = jh; + } else { + /* Insert at the tail of the list to preserve order */ + struct journal_head *first = *list, *last = first->b_tprev; + jh->b_tprev = last; + jh->b_tnext = first; + last->b_tnext = first->b_tprev = jh; + } +} + +/* + * Remove a buffer from a transaction list, given the transaction's list + * head pointer. + * + * Called with j_list_lock held, and the journal may not be locked. + * + * jh->b_state_lock is held. + */ + +static inline void +__blist_del_buffer(struct journal_head **list, struct journal_head *jh) +{ + if (*list == jh) { + *list = jh->b_tnext; + if (*list == jh) + *list = NULL; + } + jh->b_tprev->b_tnext = jh->b_tnext; + jh->b_tnext->b_tprev = jh->b_tprev; +} + +/* + * Remove a buffer from the appropriate transaction list. + * + * Note that this function can *change* the value of + * bh->b_transaction->t_buffers, t_forget, t_shadow_list, t_log_list or + * t_reserved_list. If the caller is holding onto a copy of one of these + * pointers, it could go bad. Generally the caller needs to re-read the + * pointer from the transaction_t. + * + * Called under j_list_lock. + */ +static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) +{ + struct journal_head **list = NULL; + transaction_t *transaction; + struct buffer_head *bh = jh2bh(jh); + + lockdep_assert_held(&jh->b_state_lock); + transaction = jh->b_transaction; + if (transaction) + assert_spin_locked(&transaction->t_journal->j_list_lock); + + J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); + if (jh->b_jlist != BJ_None) + J_ASSERT_JH(jh, transaction != NULL); + + switch (jh->b_jlist) { + case BJ_None: + return; + case BJ_Metadata: + transaction->t_nr_buffers--; + J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0); + list = &transaction->t_buffers; + break; + case BJ_Forget: + list = &transaction->t_forget; + break; + case BJ_Shadow: + list = &transaction->t_shadow_list; + break; + case BJ_Reserved: + list = &transaction->t_reserved_list; + break; + } + + __blist_del_buffer(list, jh); + jh->b_jlist = BJ_None; + if (transaction && is_journal_aborted(transaction->t_journal)) + clear_buffer_jbddirty(bh); + else if (test_clear_buffer_jbddirty(bh)) + mark_buffer_dirty(bh); /* Expose it to the VM */ +} + +/* + * Remove buffer from all transactions. The caller is responsible for dropping + * the jh reference that belonged to the transaction. + * + * Called with bh_state lock and j_list_lock + */ +static void __jbd2_journal_unfile_buffer(struct journal_head *jh) +{ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + + __jbd2_journal_temp_unlink_buffer(jh); + jh->b_transaction = NULL; +} + +void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) +{ + struct buffer_head *bh = jh2bh(jh); + + /* Get reference so that buffer cannot be freed before we unlock it */ + get_bh(bh); + spin_lock(&jh->b_state_lock); + spin_lock(&journal->j_list_lock); + __jbd2_journal_unfile_buffer(jh); + spin_unlock(&journal->j_list_lock); + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh); + __brelse(bh); +} + +/* + * Called from jbd2_journal_try_to_free_buffers(). + * + * Called under jh->b_state_lock + */ +static void +__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) +{ + struct journal_head *jh; + + jh = bh2jh(bh); + + if (jh->b_next_transaction != NULL || jh->b_transaction != NULL) + return; + + spin_lock(&journal->j_list_lock); + /* Remove written-back checkpointed metadata buffer */ + if (jh->b_cp_transaction != NULL) + jbd2_journal_try_remove_checkpoint(jh); + spin_unlock(&journal->j_list_lock); + return; +} + +/** + * jbd2_journal_try_to_free_buffers() - try to free page buffers. + * @journal: journal for operation + * @folio: Folio to detach data from. + * + * For all the buffers on this page, + * if they are fully written out ordered data, move them onto BUF_CLEAN + * so try_to_free_buffers() can reap them. + * + * This function returns non-zero if we wish try_to_free_buffers() + * to be called. We do this if the page is releasable by try_to_free_buffers(). + * We also do it if the page has locked or dirty buffers and the caller wants + * us to perform sync or async writeout. + * + * This complicates JBD locking somewhat. We aren't protected by the + * BKL here. We wish to remove the buffer from its committing or + * running transaction's ->t_datalist via __jbd2_journal_unfile_buffer. + * + * This may *change* the value of transaction_t->t_datalist, so anyone + * who looks at t_datalist needs to lock against this function. + * + * Even worse, someone may be doing a jbd2_journal_dirty_data on this + * buffer. So we need to lock against that. jbd2_journal_dirty_data() + * will come out of the lock with the buffer dirty, which makes it + * ineligible for release here. + * + * Who else is affected by this? hmm... Really the only contender + * is do_get_write_access() - it could be looking at the buffer while + * journal_try_to_free_buffer() is changing its state. But that + * cannot happen because we never reallocate freed data as metadata + * while the data is part of a transaction. Yes? + * + * Return false on failure, true on success + */ +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio) +{ + struct buffer_head *head; + struct buffer_head *bh; + bool ret = false; + + J_ASSERT(folio_test_locked(folio)); + + head = folio_buffers(folio); + bh = head; + do { + struct journal_head *jh; + + /* + * We take our own ref against the journal_head here to avoid + * having to add tons of locking around each instance of + * jbd2_journal_put_journal_head(). + */ + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) + continue; + + spin_lock(&jh->b_state_lock); + __journal_try_to_free_buffer(journal, bh); + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh); + if (buffer_jbd(bh)) + goto busy; + } while ((bh = bh->b_this_page) != head); + + ret = try_to_free_buffers(folio); +busy: + return ret; +} + +/* + * This buffer is no longer needed. If it is on an older transaction's + * checkpoint list we need to record it on this transaction's forget list + * to pin this buffer (and hence its checkpointing transaction) down until + * this transaction commits. If the buffer isn't on a checkpoint list, we + * release it. + * Returns non-zero if JBD no longer has an interest in the buffer. + * + * Called under j_list_lock. + * + * Called under jh->b_state_lock. + */ +static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) +{ + int may_free = 1; + struct buffer_head *bh = jh2bh(jh); + + if (jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "on running+cp transaction"); + __jbd2_journal_temp_unlink_buffer(jh); + /* + * We don't want to write the buffer anymore, clear the + * bit so that we don't confuse checks in + * __journal_file_buffer + */ + clear_buffer_dirty(bh); + __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); + may_free = 0; + } else { + JBUFFER_TRACE(jh, "on running transaction"); + __jbd2_journal_unfile_buffer(jh); + jbd2_journal_put_journal_head(jh); + } + return may_free; +} + +/* + * jbd2_journal_invalidate_folio + * + * This code is tricky. It has a number of cases to deal with. + * + * There are two invariants which this code relies on: + * + * i_size must be updated on disk before we start calling invalidate_folio + * on the data. + * + * This is done in ext3 by defining an ext3_setattr method which + * updates i_size before truncate gets going. By maintaining this + * invariant, we can be sure that it is safe to throw away any buffers + * attached to the current transaction: once the transaction commits, + * we know that the data will not be needed. + * + * Note however that we can *not* throw away data belonging to the + * previous, committing transaction! + * + * Any disk blocks which *are* part of the previous, committing + * transaction (and which therefore cannot be discarded immediately) are + * not going to be reused in the new running transaction + * + * The bitmap committed_data images guarantee this: any block which is + * allocated in one transaction and removed in the next will be marked + * as in-use in the committed_data bitmap, so cannot be reused until + * the next transaction to delete the block commits. This means that + * leaving committing buffers dirty is quite safe: the disk blocks + * cannot be reallocated to a different file and so buffer aliasing is + * not possible. + * + * + * The above applies mainly to ordered data mode. In writeback mode we + * don't make guarantees about the order in which data hits disk --- in + * particular we don't guarantee that new dirty data is flushed before + * transaction commit --- so it is always safe just to discard data + * immediately in that mode. --sct + */ + +/* + * The journal_unmap_buffer helper function returns zero if the buffer + * concerned remains pinned as an anonymous buffer belonging to an older + * transaction. + * + * We're outside-transaction here. Either or both of j_running_transaction + * and j_committing_transaction may be NULL. + */ +static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, + int partial_page) +{ + transaction_t *transaction; + struct journal_head *jh; + int may_free = 1; + + BUFFER_TRACE(bh, "entry"); + + /* + * It is safe to proceed here without the j_list_lock because the + * buffers cannot be stolen by try_to_free_buffers as long as we are + * holding the page lock. --sct + */ + + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) + goto zap_buffer_unlocked; + + /* OK, we have data buffer in journaled mode */ + write_lock(&journal->j_state_lock); + spin_lock(&jh->b_state_lock); + spin_lock(&journal->j_list_lock); + + /* + * We cannot remove the buffer from checkpoint lists until the + * transaction adding inode to orphan list (let's call it T) + * is committed. Otherwise if the transaction changing the + * buffer would be cleaned from the journal before T is + * committed, a crash will cause that the correct contents of + * the buffer will be lost. On the other hand we have to + * clear the buffer dirty bit at latest at the moment when the + * transaction marking the buffer as freed in the filesystem + * structures is committed because from that moment on the + * block can be reallocated and used by a different page. + * Since the block hasn't been freed yet but the inode has + * already been added to orphan list, it is safe for us to add + * the buffer to BJ_Forget list of the newest transaction. + * + * Also we have to clear buffer_mapped flag of a truncated buffer + * because the buffer_head may be attached to the page straddling + * i_size (can happen only when blocksize < pagesize) and thus the + * buffer_head can be reused when the file is extended again. So we end + * up keeping around invalidated buffers attached to transactions' + * BJ_Forget list just to stop checkpointing code from cleaning up + * the transaction this buffer was modified in. + */ + transaction = jh->b_transaction; + if (transaction == NULL) { + /* First case: not on any transaction. If it + * has no checkpoint link, then we can zap it: + * it's a writeback-mode buffer so we don't care + * if it hits disk safely. */ + if (!jh->b_cp_transaction) { + JBUFFER_TRACE(jh, "not on any transaction: zap"); + goto zap_buffer; + } + + if (!buffer_dirty(bh)) { + /* bdflush has written it. We can drop it now */ + __jbd2_journal_remove_checkpoint(jh); + goto zap_buffer; + } + + /* OK, it must be in the journal but still not + * written fully to disk: it's metadata or + * journaled data... */ + + if (journal->j_running_transaction) { + /* ... and once the current transaction has + * committed, the buffer won't be needed any + * longer. */ + JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget"); + may_free = __dispose_buffer(jh, + journal->j_running_transaction); + goto zap_buffer; + } else { + /* There is no currently-running transaction. So the + * orphan record which we wrote for this file must have + * passed into commit. We must attach this buffer to + * the committing transaction, if it exists. */ + if (journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "give to committing trans"); + may_free = __dispose_buffer(jh, + journal->j_committing_transaction); + goto zap_buffer; + } else { + /* The orphan record's transaction has + * committed. We can cleanse this buffer */ + clear_buffer_jbddirty(bh); + __jbd2_journal_remove_checkpoint(jh); + goto zap_buffer; + } + } + } else if (transaction == journal->j_committing_transaction) { + JBUFFER_TRACE(jh, "on committing transaction"); + /* + * The buffer is committing, we simply cannot touch + * it. If the page is straddling i_size we have to wait + * for commit and try again. + */ + if (partial_page) { + spin_unlock(&journal->j_list_lock); + spin_unlock(&jh->b_state_lock); + write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); + /* Already zapped buffer? Nothing to do... */ + if (!bh->b_bdev) + return 0; + return -EBUSY; + } + /* + * OK, buffer won't be reachable after truncate. We just clear + * b_modified to not confuse transaction credit accounting, and + * set j_next_transaction to the running transaction (if there + * is one) and mark buffer as freed so that commit code knows + * it should clear dirty bits when it is done with the buffer. + */ + set_buffer_freed(bh); + if (journal->j_running_transaction && buffer_jbddirty(bh)) + jh->b_next_transaction = journal->j_running_transaction; + jh->b_modified = 0; + spin_unlock(&journal->j_list_lock); + spin_unlock(&jh->b_state_lock); + write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); + return 0; + } else { + /* Good, the buffer belongs to the running transaction. + * We are writing our own transaction's data, not any + * previous one's, so it is safe to throw it away + * (remember that we expect the filesystem to have set + * i_size already for this truncate so recovery will not + * expose the disk blocks we are discarding here.) */ + J_ASSERT_JH(jh, transaction == journal->j_running_transaction); + JBUFFER_TRACE(jh, "on running transaction"); + may_free = __dispose_buffer(jh, transaction); + } + +zap_buffer: + /* + * This is tricky. Although the buffer is truncated, it may be reused + * if blocksize < pagesize and it is attached to the page straddling + * EOF. Since the buffer might have been added to BJ_Forget list of the + * running transaction, journal_get_write_access() won't clear + * b_modified and credit accounting gets confused. So clear b_modified + * here. + */ + jh->b_modified = 0; + spin_unlock(&journal->j_list_lock); + spin_unlock(&jh->b_state_lock); + write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); +zap_buffer_unlocked: + clear_buffer_dirty(bh); + J_ASSERT_BH(bh, !buffer_jbddirty(bh)); + clear_buffer_mapped(bh); + clear_buffer_req(bh); + clear_buffer_new(bh); + clear_buffer_delay(bh); + clear_buffer_unwritten(bh); + bh->b_bdev = NULL; + return may_free; +} + +/** + * jbd2_journal_invalidate_folio() + * @journal: journal to use for flush... + * @folio: folio to flush + * @offset: start of the range to invalidate + * @length: length of the range to invalidate + * + * Reap page buffers containing data after in the specified range in page. + * Can return -EBUSY if buffers are part of the committing transaction and + * the page is straddling i_size. Caller then has to wait for current commit + * and try again. + */ +int jbd2_journal_invalidate_folio(journal_t *journal, struct folio *folio, + size_t offset, size_t length) +{ + struct buffer_head *head, *bh, *next; + unsigned int stop = offset + length; + unsigned int curr_off = 0; + int partial_page = (offset || length < folio_size(folio)); + int may_free = 1; + int ret = 0; + + if (!folio_test_locked(folio)) + BUG(); + head = folio_buffers(folio); + if (!head) + return 0; + + BUG_ON(stop > folio_size(folio) || stop < length); + + /* We will potentially be playing with lists other than just the + * data lists (especially for journaled data mode), so be + * cautious in our locking. */ + + bh = head; + do { + unsigned int next_off = curr_off + bh->b_size; + next = bh->b_this_page; + + if (next_off > stop) + return 0; + + if (offset <= curr_off) { + /* This block is wholly outside the truncation point */ + lock_buffer(bh); + ret = journal_unmap_buffer(journal, bh, partial_page); + unlock_buffer(bh); + if (ret < 0) + return ret; + may_free &= ret; + } + curr_off = next_off; + bh = next; + + } while (bh != head); + + if (!partial_page) { + if (may_free && try_to_free_buffers(folio)) + J_ASSERT(!folio_buffers(folio)); + } + return 0; +} + +/* + * File a buffer on the given transaction list. + */ +void __jbd2_journal_file_buffer(struct journal_head *jh, + transaction_t *transaction, int jlist) +{ + struct journal_head **list = NULL; + int was_dirty = 0; + struct buffer_head *bh = jh2bh(jh); + + lockdep_assert_held(&jh->b_state_lock); + assert_spin_locked(&transaction->t_journal->j_list_lock); + + J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); + J_ASSERT_JH(jh, jh->b_transaction == transaction || + jh->b_transaction == NULL); + + if (jh->b_transaction && jh->b_jlist == jlist) + return; + + if (jlist == BJ_Metadata || jlist == BJ_Reserved || + jlist == BJ_Shadow || jlist == BJ_Forget) { + /* + * For metadata buffers, we track dirty bit in buffer_jbddirty + * instead of buffer_dirty. We should not see a dirty bit set + * here because we clear it in do_get_write_access but e.g. + * tune2fs can modify the sb and set the dirty bit at any time + * so we try to gracefully handle that. + */ + if (buffer_dirty(bh)) + warn_dirty_buffer(bh); + if (test_clear_buffer_dirty(bh) || + test_clear_buffer_jbddirty(bh)) + was_dirty = 1; + } + + if (jh->b_transaction) + __jbd2_journal_temp_unlink_buffer(jh); + else + jbd2_journal_grab_journal_head(bh); + jh->b_transaction = transaction; + + switch (jlist) { + case BJ_None: + J_ASSERT_JH(jh, !jh->b_committed_data); + J_ASSERT_JH(jh, !jh->b_frozen_data); + return; + case BJ_Metadata: + transaction->t_nr_buffers++; + list = &transaction->t_buffers; + break; + case BJ_Forget: + list = &transaction->t_forget; + break; + case BJ_Shadow: + list = &transaction->t_shadow_list; + break; + case BJ_Reserved: + list = &transaction->t_reserved_list; + break; + } + + __blist_add_buffer(list, jh); + jh->b_jlist = jlist; + + if (was_dirty) + set_buffer_jbddirty(bh); +} + +void jbd2_journal_file_buffer(struct journal_head *jh, + transaction_t *transaction, int jlist) +{ + spin_lock(&jh->b_state_lock); + spin_lock(&transaction->t_journal->j_list_lock); + __jbd2_journal_file_buffer(jh, transaction, jlist); + spin_unlock(&transaction->t_journal->j_list_lock); + spin_unlock(&jh->b_state_lock); +} + +/* + * Remove a buffer from its current buffer list in preparation for + * dropping it from its current transaction entirely. If the buffer has + * already started to be used by a subsequent transaction, refile the + * buffer on that transaction's metadata list. + * + * Called under j_list_lock + * Called under jh->b_state_lock + * + * When this function returns true, there's no next transaction to refile to + * and the caller has to drop jh reference through + * jbd2_journal_put_journal_head(). + */ +bool __jbd2_journal_refile_buffer(struct journal_head *jh) +{ + int was_dirty, jlist; + struct buffer_head *bh = jh2bh(jh); + + lockdep_assert_held(&jh->b_state_lock); + if (jh->b_transaction) + assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock); + + /* If the buffer is now unused, just drop it. */ + if (jh->b_next_transaction == NULL) { + __jbd2_journal_unfile_buffer(jh); + return true; + } + + /* + * It has been modified by a later transaction: add it to the new + * transaction's metadata list. + */ + + was_dirty = test_clear_buffer_jbddirty(bh); + __jbd2_journal_temp_unlink_buffer(jh); + + /* + * b_transaction must be set, otherwise the new b_transaction won't + * be holding jh reference + */ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + + /* + * We set b_transaction here because b_next_transaction will inherit + * our jh reference and thus __jbd2_journal_file_buffer() must not + * take a new one. + */ + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); + if (buffer_freed(bh)) + jlist = BJ_Forget; + else if (jh->b_modified) + jlist = BJ_Metadata; + else + jlist = BJ_Reserved; + __jbd2_journal_file_buffer(jh, jh->b_transaction, jlist); + J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING); + + if (was_dirty) + set_buffer_jbddirty(bh); + return false; +} + +/* + * __jbd2_journal_refile_buffer() with necessary locking added. We take our + * bh reference so that we can safely unlock bh. + * + * The jh and bh may be freed by this call. + */ +void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) +{ + bool drop; + + spin_lock(&jh->b_state_lock); + spin_lock(&journal->j_list_lock); + drop = __jbd2_journal_refile_buffer(jh); + spin_unlock(&jh->b_state_lock); + spin_unlock(&journal->j_list_lock); + if (drop) + jbd2_journal_put_journal_head(jh); +} + +/* + * File inode in the inode list of the handle's transaction + */ +static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, + unsigned long flags, loff_t start_byte, loff_t end_byte) +{ + transaction_t *transaction = handle->h_transaction; + journal_t *journal; + + if (is_handle_aborted(handle)) + return -EROFS; + journal = transaction->t_journal; + + jbd2_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, + transaction->t_tid); + + spin_lock(&journal->j_list_lock); + jinode->i_flags |= flags; + + if (jinode->i_dirty_end) { + jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); + jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); + } else { + jinode->i_dirty_start = start_byte; + jinode->i_dirty_end = end_byte; + } + + /* Is inode already attached where we need it? */ + if (jinode->i_transaction == transaction || + jinode->i_next_transaction == transaction) + goto done; + + /* + * We only ever set this variable to 1 so the test is safe. Since + * t_need_data_flush is likely to be set, we do the test to save some + * cacheline bouncing + */ + if (!transaction->t_need_data_flush) + transaction->t_need_data_flush = 1; + /* On some different transaction's list - should be + * the committing one */ + if (jinode->i_transaction) { + J_ASSERT(jinode->i_next_transaction == NULL); + J_ASSERT(jinode->i_transaction == + journal->j_committing_transaction); + jinode->i_next_transaction = transaction; + goto done; + } + /* Not on any transaction list... */ + J_ASSERT(!jinode->i_next_transaction); + jinode->i_transaction = transaction; + list_add(&jinode->i_list, &transaction->t_inode_list); +done: + spin_unlock(&journal->j_list_lock); + + return 0; +} + +int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *jinode, loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, + JI_WRITE_DATA | JI_WAIT_DATA, start_byte, + start_byte + length - 1); +} + +int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, + loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, + start_byte, start_byte + length - 1); +} + +/* + * File truncate and transaction commit interact with each other in a + * non-trivial way. If a transaction writing data block A is + * committing, we cannot discard the data by truncate until we have + * written them. Otherwise if we crashed after the transaction with + * write has committed but before the transaction with truncate has + * committed, we could see stale data in block A. This function is a + * helper to solve this problem. It starts writeout of the truncated + * part in case it is in the committing transaction. + * + * Filesystem code must call this function when inode is journaled in + * ordered mode before truncation happens and after the inode has been + * placed on orphan list with the new inode size. The second condition + * avoids the race that someone writes new data and we start + * committing the transaction after this function has been called but + * before a transaction for truncate is started (and furthermore it + * allows us to optimize the case where the addition to orphan list + * happens in the same transaction as write --- we don't have to write + * any data in such case). + */ +int jbd2_journal_begin_ordered_truncate(journal_t *journal, + struct jbd2_inode *jinode, + loff_t new_size) +{ + transaction_t *inode_trans, *commit_trans; + int ret = 0; + + /* This is a quick check to avoid locking if not necessary */ + if (!jinode->i_transaction) + goto out; + /* Locks are here just to force reading of recent values, it is + * enough that the transaction was not committing before we started + * a transaction adding the inode to orphan list */ + read_lock(&journal->j_state_lock); + commit_trans = journal->j_committing_transaction; + read_unlock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + inode_trans = jinode->i_transaction; + spin_unlock(&journal->j_list_lock); + if (inode_trans == commit_trans) { + ret = filemap_fdatawrite_range(jinode->i_vfs_inode->i_mapping, + new_size, LLONG_MAX); + if (ret) + jbd2_journal_abort(journal, ret); + } +out: + return ret; +} |