aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/fs/jbd2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd2')
-rw-r--r--fs/jbd2/commit.c14
-rw-r--r--fs/jbd2/journal.c123
-rw-r--r--fs/jbd2/recovery.c33
-rw-r--r--fs/jbd2/transaction.c45
4 files changed, 121 insertions, 94 deletions
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 75ea4e9a5cab..4305a1ac808a 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -353,7 +353,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
struct buffer_head *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
- int flags;
+ int escape;
int err;
unsigned long long blocknr;
ktime_t start_time;
@@ -660,10 +660,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
*/
set_bit(BH_JWrite, &jh2bh(jh)->b_state);
JBUFFER_TRACE(jh, "ph3: write metadata");
- flags = jbd2_journal_write_metadata_buffer(commit_transaction,
+ escape = jbd2_journal_write_metadata_buffer(commit_transaction,
jh, &wbuf[bufs], blocknr);
- if (flags < 0) {
- jbd2_journal_abort(journal, flags);
+ if (escape < 0) {
+ jbd2_journal_abort(journal, escape);
continue;
}
jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
@@ -672,7 +672,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
buffer */
tag_flag = 0;
- if (flags & 1)
+ if (escape)
tag_flag |= JBD2_FLAG_ESCAPE;
if (!first_tag)
tag_flag |= JBD2_FLAG_SAME_UUID;
@@ -766,7 +766,7 @@ start_journal_io:
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))
+ if (freed < journal->j_max_transaction_buffers)
update_tail = 0;
}
J_ASSERT(commit_transaction->t_state == T_COMMIT);
@@ -1107,7 +1107,7 @@ restart_loop:
commit_transaction->t_state = T_COMMIT_CALLBACK;
J_ASSERT(commit_transaction == journal->j_committing_transaction);
- journal->j_commit_sequence = commit_transaction->t_tid;
+ WRITE_ONCE(journal->j_commit_sequence, commit_transaction->t_tid);
journal->j_committing_transaction = NULL;
commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0d2825c131cc..1ebf2393bfb7 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -220,19 +220,12 @@ loop:
* 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) {
+ if (transaction == NULL ||
+ time_before(jiffies, transaction->t_expires)) {
write_unlock(&journal->j_state_lock);
schedule();
write_lock(&journal->j_state_lock);
@@ -316,11 +309,8 @@ static void journal_kill_thread(journal_t *journal)
*
* 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)
+ * =0: Finished OK without escape
+ * =1: Finished OK with escape
*/
int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
@@ -328,7 +318,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
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;
@@ -355,7 +344,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
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.
@@ -365,8 +353,8 @@ repeat:
new_folio = virt_to_folio(jh_in->b_frozen_data);
new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
} else {
- new_folio = jh2bh(jh_in)->b_folio;
- new_offset = offset_in_folio(new_folio, jh2bh(jh_in)->b_data);
+ new_folio = bh_in->b_folio;
+ new_offset = offset_in_folio(new_folio, bh_in->b_data);
}
mapped_data = kmap_local_folio(new_folio, new_offset);
@@ -383,54 +371,52 @@ repeat:
/*
* Check for escaping
*/
- if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER)) {
- need_copy_out = 1;
+ if (*((__be32 *)mapped_data) == cpu_to_be32(JBD2_MAGIC_NUMBER))
do_escape = 1;
- }
kunmap_local(mapped_data);
/*
* Do we need to do a data copy?
*/
- if (need_copy_out && !done_copy_out) {
+ if (do_escape && !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);
+ free_buffer_head(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;
+ goto copy_done;
}
jh_in->b_frozen_data = tmp;
memcpy_from_folio(tmp, new_folio, new_offset, bh_in->b_size);
-
- new_folio = virt_to_folio(tmp);
- new_offset = offset_in_folio(new_folio, 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;
+
+copy_done:
+ new_folio = virt_to_folio(jh_in->b_frozen_data);
+ new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data);
+ done_copy_out = 1;
}
/*
* Did we need to do an escaping? Now we've done all the
* copying, we can finally do so.
+ * b_frozen_data is from jbd2_alloc() which always provides an
+ * address from the direct kernels mapping.
*/
- if (do_escape) {
- mapped_data = kmap_local_folio(new_folio, new_offset);
- *((unsigned int *)mapped_data) = 0;
- kunmap_local(mapped_data);
- }
+ if (do_escape)
+ *((unsigned int *)jh_in->b_frozen_data) = 0;
folio_set_bh(new_bh, new_folio, new_offset);
new_bh->b_size = bh_in->b_size;
@@ -454,7 +440,7 @@ repeat:
set_buffer_shadow(bh_in);
spin_unlock(&jh_in->b_state_lock);
- return do_escape | (done_copy_out << 1);
+ return do_escape;
}
/*
@@ -789,17 +775,7 @@ 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;
+ return tid_geq(READ_ONCE(journal->j_commit_sequence), tid);
}
EXPORT_SYMBOL(jbd2_transaction_committed);
@@ -1451,6 +1427,48 @@ static int journal_revoke_records_per_block(journal_t *journal)
return space / record_size;
}
+static int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+ return (journal->j_total_len - journal->j_fc_wbufsize) / 3;
+}
+
+/*
+ * 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(jbd2_journal_get_max_txn_bufs(journal),
+ tags_per_block);
+}
+
+/*
+ * Initialize number of blocks each transaction reserves for its bookkeeping
+ * and maximum number of blocks a transaction can use. This needs to be called
+ * after the journal size and the fastcommit area size are initialized.
+ */
+static void jbd2_journal_init_transaction_limits(journal_t *journal)
+{
+ journal->j_revoke_records_per_block =
+ journal_revoke_records_per_block(journal);
+ journal->j_transaction_overhead_buffers =
+ jbd2_descriptor_blocks_per_trans(journal);
+ journal->j_max_transaction_buffers =
+ jbd2_journal_get_max_txn_bufs(journal);
+}
+
/*
* Load the on-disk journal superblock and read the key fields into the
* journal_t.
@@ -1492,8 +1510,8 @@ static int journal_load_superblock(journal_t *journal)
if (jbd2_journal_has_csum_v2or3(journal))
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);
+ /* After journal features are set, we can compute transaction limits */
+ jbd2_journal_init_transaction_limits(journal);
if (jbd2_has_feature_fast_commit(journal)) {
journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
@@ -1599,7 +1617,6 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan;
journal->j_shrinker->count_objects = jbd2_journal_shrink_count;
- journal->j_shrinker->batch = journal->j_max_transaction_buffers;
journal->j_shrinker->private_data = journal;
shrinker_register(journal->j_shrinker);
@@ -1743,8 +1760,6 @@ static int journal_reset(journal_t *journal)
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
@@ -2285,8 +2300,6 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
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;
}
@@ -2374,8 +2387,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long 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);
+ jbd2_journal_init_transaction_limits(journal);
return 1;
#undef COMPAT_FEATURE_ON
@@ -2406,8 +2418,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
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);
+ jbd2_journal_init_transaction_limits(journal);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 1f7664984d6e..667f67342c52 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -19,6 +19,7 @@
#include <linux/errno.h>
#include <linux/crc32.h>
#include <linux/blkdev.h>
+#include <linux/string_choices.h>
#endif
/*
@@ -374,7 +375,7 @@ int jbd2_journal_skip_recovery(journal_t *journal)
be32_to_cpu(journal->j_superblock->s_sequence);
jbd2_debug(1,
"JBD2: ignoring %d transaction%s from the journal.\n",
- dropped, (dropped == 1) ? "" : "s");
+ dropped, str_plural(dropped));
#endif
journal->j_transaction_sequence = ++info.end_transaction;
journal->j_head = info.head_block;
@@ -443,6 +444,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
return provided == cpu_to_be32(calculated);
}
+static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf)
+{
+ struct commit_header *h;
+ __be32 provided;
+ __u32 calculated;
+ void *tmpbuf;
+
+ tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL);
+ if (!tmpbuf)
+ return false;
+
+ memcpy(tmpbuf, buf, sizeof(struct commit_header));
+ h = tmpbuf;
+ provided = h->h_chksum[0];
+ h->h_chksum[0] = 0;
+ calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize);
+ kfree(tmpbuf);
+
+ 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)
@@ -810,6 +832,13 @@ static int do_one_pass(journal_t *journal,
if (pass == PASS_SCAN &&
!jbd2_commit_block_csum_verify(journal,
bh->b_data)) {
+ if (jbd2_commit_block_csum_verify_partial(
+ journal,
+ bh->b_data)) {
+ pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+ next_commit_ID, next_log_block);
+ goto chksum_ok;
+ }
chksum_error:
if (commit_time < last_trans_commit_time)
goto ignore_crc_mismatch;
@@ -824,6 +853,7 @@ static int do_one_pass(journal_t *journal,
}
}
if (pass == PASS_SCAN) {
+ chksum_ok:
last_trans_commit_time = commit_time;
head_block = next_log_block;
}
@@ -843,6 +873,7 @@ static int do_one_pass(journal_t *journal,
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) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index cb0b8d6fc0c6..66513c18ca29 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -63,28 +63,6 @@ void jbd2_journal_free_transaction(transaction_t *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
@@ -109,7 +87,7 @@ static void jbd2_get_transaction(journal_t *journal,
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) +
+ journal->j_transaction_overhead_buffers +
atomic_read(&journal->j_reserved_credits));
atomic_set(&transaction->t_outstanding_revokes, 0);
atomic_set(&transaction->t_handle_count, 0);
@@ -213,6 +191,13 @@ static void sub_reserved_credits(journal_t *journal, int blocks)
wake_up(&journal->j_wait_reserved);
}
+/* Maximum number of blocks for user transaction payload */
+static int jbd2_max_user_trans_buffers(journal_t *journal)
+{
+ return journal->j_max_transaction_buffers -
+ journal->j_transaction_overhead_buffers;
+}
+
/*
* 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
@@ -262,12 +247,12 @@ __must_hold(&journal->j_state_lock)
* big to fit this handle? Wait until reserved credits are freed.
*/
if (atomic_read(&journal->j_reserved_credits) + total >
- journal->j_max_transaction_buffers) {
+ jbd2_max_user_trans_buffers(journal)) {
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);
+ jbd2_max_user_trans_buffers(journal));
__acquire(&journal->j_state_lock); /* fake out sparse */
return 1;
}
@@ -307,14 +292,14 @@ __must_hold(&journal->j_state_lock)
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) {
+ if (needed > jbd2_max_user_trans_buffers(journal) / 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);
+ <= jbd2_max_user_trans_buffers(journal) / 2);
__acquire(&journal->j_state_lock); /* fake out sparse */
return 1;
}
@@ -344,12 +329,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
* 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)) {
+ if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 ||
+ rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) {
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);
+ jbd2_max_user_trans_buffers(journal));
WARN_ON(1);
return -ENOSPC;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.