summaryrefslogtreecommitdiffstats
path: root/fs/jbd2/commit.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/jbd2/commit.c')
-rw-r--r--fs/jbd2/commit.c184
1 files changed, 77 insertions, 107 deletions
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 0f53946f13c..559bec1a37b 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -30,15 +30,22 @@
#include <trace/events/jbd2.h>
/*
- * Default IO end handler for temporary BJ_IO buffer_heads.
+ * 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_clear_bit();
+ wake_up_bit(&orig_bh->b_state, BH_Shadow);
+ }
unlock_buffer(bh);
}
@@ -85,8 +92,7 @@ nope:
__brelse(bh);
}
-static void jbd2_commit_block_csum_set(journal_t *j,
- struct journal_head *descriptor)
+static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
{
struct commit_header *h;
__u32 csum;
@@ -94,12 +100,11 @@ static void jbd2_commit_block_csum_set(journal_t *j,
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return;
- h = (struct commit_header *)(jh2bh(descriptor)->b_data);
+ 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, jh2bh(descriptor)->b_data,
- j->j_blocksize);
+ csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
h->h_chksum[0] = cpu_to_be32(csum);
}
@@ -116,7 +121,6 @@ static int journal_submit_commit_record(journal_t *journal,
struct buffer_head **cbh,
__u32 crc32_sum)
{
- struct journal_head *descriptor;
struct commit_header *tmp;
struct buffer_head *bh;
int ret;
@@ -127,12 +131,10 @@ static int journal_submit_commit_record(journal_t *journal,
if (is_journal_aborted(journal))
return 0;
- descriptor = jbd2_journal_get_descriptor_buffer(journal);
- if (!descriptor)
+ bh = jbd2_journal_get_descriptor_buffer(journal);
+ if (!bh)
return 1;
- bh = jh2bh(descriptor);
-
tmp = (struct commit_header *)bh->b_data;
tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
@@ -146,9 +148,9 @@ static int journal_submit_commit_record(journal_t *journal,
tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE;
tmp->h_chksum[0] = cpu_to_be32(crc32_sum);
}
- jbd2_commit_block_csum_set(journal, descriptor);
+ jbd2_commit_block_csum_set(journal, bh);
- JBUFFER_TRACE(descriptor, "submit commit block");
+ BUFFER_TRACE(bh, "submit commit block");
lock_buffer(bh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
@@ -180,7 +182,6 @@ static int journal_wait_on_commit_record(journal_t *journal,
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
put_bh(bh); /* One for getblk() */
- jbd2_journal_put_journal_head(bh2jh(bh));
return ret;
}
@@ -321,7 +322,7 @@ static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
}
static void jbd2_descr_block_csum_set(journal_t *j,
- struct journal_head *descriptor)
+ struct buffer_head *bh)
{
struct jbd2_journal_block_tail *tail;
__u32 csum;
@@ -329,12 +330,10 @@ static void jbd2_descr_block_csum_set(journal_t *j,
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return;
- tail = (struct jbd2_journal_block_tail *)
- (jh2bh(descriptor)->b_data + j->j_blocksize -
+ 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, jh2bh(descriptor)->b_data,
- j->j_blocksize);
+ csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
tail->t_checksum = cpu_to_be32(csum);
}
@@ -343,20 +342,21 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
{
struct page *page = bh->b_page;
__u8 *addr;
- __u32 csum;
+ __u32 csum32;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return;
sequence = cpu_to_be32(sequence);
addr = kmap_atomic(page);
- csum = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
- sizeof(sequence));
- csum = jbd2_chksum(j, csum, addr + offset_in_page(bh->b_data),
- bh->b_size);
+ csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
+ sizeof(sequence));
+ csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data),
+ bh->b_size);
kunmap_atomic(addr);
- tag->t_checksum = cpu_to_be32(csum);
+ /* We only have space to store the lower 16 bits of the crc32c. */
+ tag->t_checksum = cpu_to_be16(csum32);
}
/*
* jbd2_journal_commit_transaction
@@ -368,7 +368,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
{
struct transaction_stats_s stats;
transaction_t *commit_transaction;
- struct journal_head *jh, *new_jh, *descriptor;
+ struct journal_head *jh;
+ struct buffer_head *descriptor;
struct buffer_head **wbuf = journal->j_wbuf;
int bufs;
int flags;
@@ -392,6 +393,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
tid_t first_tid;
int update_tail;
int csum_size = 0;
+ LIST_HEAD(io_bufs);
+ LIST_HEAD(log_bufs);
if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
csum_size = sizeof(struct jbd2_journal_block_tail);
@@ -424,13 +427,13 @@ void jbd2_journal_commit_transaction(journal_t *journal)
J_ASSERT(journal->j_committing_transaction == NULL);
commit_transaction = journal->j_running_transaction;
- J_ASSERT(commit_transaction->t_state == T_RUNNING);
trace_jbd2_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD2: starting commit of transaction %d\n",
commit_transaction->t_tid);
write_lock(&journal->j_state_lock);
+ J_ASSERT(commit_transaction->t_state == T_RUNNING);
commit_transaction->t_state = T_LOCKED;
trace_jbd2_commit_locking(journal, commit_transaction);
@@ -520,6 +523,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
*/
jbd2_journal_switch_revoke_table(journal);
+ /*
+ * 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,
@@ -533,7 +542,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
wake_up(&journal->j_wait_transaction_locked);
write_unlock(&journal->j_state_lock);
- jbd_debug(3, "JBD2: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2a\n");
/*
* Now start flushing things to disk, in the order they appear
@@ -545,10 +554,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
blk_start_plug(&plug);
jbd2_journal_write_revoke_records(journal, commit_transaction,
- WRITE_SYNC);
+ &log_bufs, WRITE_SYNC);
blk_finish_plug(&plug);
- jbd_debug(3, "JBD2: commit phase 2\n");
+ jbd_debug(3, "JBD2: commit phase 2b\n");
/*
* Way to go: we have now written out all of the data for a
@@ -571,8 +580,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
atomic_read(&commit_transaction->t_outstanding_credits));
err = 0;
- descriptor = NULL;
bufs = 0;
+ descriptor = NULL;
blk_start_plug(&plug);
while (commit_transaction->t_buffers) {
@@ -604,8 +613,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
record the metadata buffer. */
if (!descriptor) {
- struct buffer_head *bh;
-
J_ASSERT (bufs == 0);
jbd_debug(4, "JBD2: get descriptor\n");
@@ -616,26 +623,26 @@ void jbd2_journal_commit_transaction(journal_t *journal)
continue;
}
- bh = jh2bh(descriptor);
jbd_debug(4, "JBD2: got buffer %llu (%p)\n",
- (unsigned long long)bh->b_blocknr, bh->b_data);
- header = (journal_header_t *)&bh->b_data[0];
+ (unsigned long long)descriptor->b_blocknr,
+ descriptor->b_data);
+ header = (journal_header_t *)descriptor->b_data;
header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
- tagp = &bh->b_data[sizeof(journal_header_t)];
- space_left = bh->b_size - sizeof(journal_header_t);
+ tagp = &descriptor->b_data[sizeof(journal_header_t)];
+ space_left = descriptor->b_size -
+ sizeof(journal_header_t);
first_tag = 1;
- set_buffer_jwrite(bh);
- set_buffer_dirty(bh);
- wbuf[bufs++] = bh;
+ set_buffer_jwrite(descriptor);
+ set_buffer_dirty(descriptor);
+ wbuf[bufs++] = descriptor;
/* Record it so that we can wait for IO
completion later */
- BUFFER_TRACE(bh, "ph3: file as descriptor");
- jbd2_journal_file_buffer(descriptor, commit_transaction,
- BJ_LogCtl);
+ BUFFER_TRACE(descriptor, "ph3: file as descriptor");
+ jbd2_file_log_bh(&log_bufs, descriptor);
}
/* Where is the buffer to be written? */
@@ -658,29 +665,22 @@ void jbd2_journal_commit_transaction(journal_t *journal)
/* Bump b_count to prevent truncate from stumbling over
the shadowed buffer! @@@ This can go if we ever get
- rid of the BJ_IO/BJ_Shadow pairing of buffers. */
+ 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 both the metadata buffer and the
- temporary IO buffer). new_bh goes on BJ_IO*/
-
- set_bit(BH_JWrite, &jh2bh(jh)->b_state);
/*
- * akpm: jbd2_journal_write_metadata_buffer() sets
- * new_bh->b_transaction to commit_transaction.
- * We need to clean this up before we release new_bh
- * (which is of type BJ_IO)
+ * 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, &new_jh, blocknr);
+ jh, &wbuf[bufs], blocknr);
if (flags < 0) {
jbd2_journal_abort(journal, flags);
continue;
}
- set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
- wbuf[bufs++] = jh2bh(new_jh);
+ jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
/* Record the new block's tag in the current descriptor
buffer */
@@ -694,10 +694,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
tag = (journal_block_tag_t *) tagp;
write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
tag->t_flags = cpu_to_be16(tag_flag);
- jbd2_block_tag_csum_set(journal, tag, jh2bh(new_jh),
+ 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);
@@ -809,7 +810,7 @@ start_journal_io:
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 t_iobuf_list queue.
+ 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
@@ -818,47 +819,33 @@ start_journal_io:
jbd_debug(3, "JBD2: commit phase 3\n");
- /*
- * akpm: these are BJ_IO, and j_list_lock is not needed.
- * See __journal_try_to_free_buffer.
- */
-wait_for_iobuf:
- while (commit_transaction->t_iobuf_list != NULL) {
- struct buffer_head *bh;
+ while (!list_empty(&io_bufs)) {
+ struct buffer_head *bh = list_entry(io_bufs.prev,
+ struct buffer_head,
+ b_assoc_buffers);
- jh = commit_transaction->t_iobuf_list->b_tprev;
- bh = jh2bh(jh);
- if (buffer_locked(bh)) {
- wait_on_buffer(bh);
- goto wait_for_iobuf;
- }
- if (cond_resched())
- goto wait_for_iobuf;
+ wait_on_buffer(bh);
+ cond_resched();
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
-
- clear_buffer_jwrite(bh);
-
- JBUFFER_TRACE(jh, "ph4: unfile after journal write");
- jbd2_journal_unfile_buffer(journal, jh);
+ jbd2_unfile_log_bh(bh);
/*
- * ->t_iobuf_list should contain only dummy buffer_heads
- * which were created by jbd2_journal_write_metadata_buffer().
+ * The list contains temporary buffer heads created by
+ * jbd2_journal_write_metadata_buffer().
*/
BUFFER_TRACE(bh, "dumping temporary bh");
- jbd2_journal_put_journal_head(jh);
__brelse(bh);
J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
free_buffer_head(bh);
- /* We also have to unlock and free the corresponding
- shadowed buffer */
+ /* We also have to refile the corresponding shadowed buffer */
jh = commit_transaction->t_shadow_list->b_tprev;
bh = jh2bh(jh);
- clear_bit(BH_JWrite, &bh->b_state);
+ 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
@@ -866,14 +853,6 @@ wait_for_iobuf:
required. */
JBUFFER_TRACE(jh, "file as BJ_Forget");
jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
- /*
- * Wake up any transactions which were waiting for this IO to
- * complete. The barrier must be here so that changes by
- * jbd2_journal_file_buffer() take effect before wake_up_bit()
- * does the waitqueue check.
- */
- smp_mb();
- wake_up_bit(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "brelse shadowed buffer");
__brelse(bh);
}
@@ -883,26 +862,19 @@ wait_for_iobuf:
jbd_debug(3, "JBD2: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
- wait_for_ctlbuf:
- while (commit_transaction->t_log_list != NULL) {
+ while (!list_empty(&log_bufs)) {
struct buffer_head *bh;
- jh = commit_transaction->t_log_list->b_tprev;
- bh = jh2bh(jh);
- if (buffer_locked(bh)) {
- wait_on_buffer(bh);
- goto wait_for_ctlbuf;
- }
- if (cond_resched())
- goto wait_for_ctlbuf;
+ 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_journal_unfile_buffer(journal, jh);
- jbd2_journal_put_journal_head(jh);
+ jbd2_unfile_log_bh(bh);
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
@@ -952,9 +924,7 @@ wait_for_iobuf:
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_iobuf_list == NULL);
J_ASSERT(commit_transaction->t_shadow_list == NULL);
- J_ASSERT(commit_transaction->t_log_list == NULL);
restart_loop:
/*
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-08 16:35:01 +0000