/*
- * linux/fs/revoke.c
+ * linux/fs/jbd2/revoke.c
*
* Written by Stephen C. Tweedie <sct@redhat.com>, 2000
*
* need do nothing.
* RevokeValid set, Revoked set:
* buffer has been revoked.
+ *
+ * Locking rules:
+ * We keep two hash tables of revoke records. One hashtable belongs to the
+ * running transaction (is pointed to by journal->j_revoke), the other one
+ * belongs to the committing transaction. Accesses to the second hash table
+ * happen only from the kjournald and no other thread touches this table. Also
+ * journal_switch_revoke_table() which switches which hashtable belongs to the
+ * running and which to the committing transaction is called only from
+ * kjournald. Therefore we need no locks when accessing the hashtable belonging
+ * to the committing transaction.
+ *
+ * All users operating on the hash table belonging to the running transaction
+ * have a handle to the transaction. Therefore they are safe from kjournald
+ * switching hash tables under them. For operations on the lists of entries in
+ * the hash table j_revoke_lock is used.
+ *
+ * Finally, also replay code uses the hash tables but at this moment noone else
+ * can touch them (filesystem isn't mounted yet) and hence no locking is
+ * needed.
*/
#ifndef __KERNEL__
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/list.h>
-#include <linux/smp_lock.h>
#include <linux/init.h>
+#include <linux/bio.h>
#endif
+#include <linux/log2.h>
static struct kmem_cache *jbd2_revoke_record_cache;
static struct kmem_cache *jbd2_revoke_table_cache;
#ifdef __KERNEL__
static void write_one_revoke_record(journal_t *, transaction_t *,
struct journal_head **, int *,
- struct jbd2_revoke_record_s *);
-static void flush_descriptor(journal_t *, struct journal_head *, int);
+ struct jbd2_revoke_record_s *, int);
+static void flush_descriptor(journal_t *, struct journal_head *, int, int);
#endif
/* Utility functions to maintain the revoke table */
oom:
if (!journal_oom_retry)
return -ENOMEM;
- jbd_debug(1, "ENOMEM in %s, retrying\n", __FUNCTION__);
+ jbd_debug(1, "ENOMEM in %s, retrying\n", __func__);
yield();
goto repeat;
}
return NULL;
}
+void jbd2_journal_destroy_revoke_caches(void)
+{
+ if (jbd2_revoke_record_cache) {
+ kmem_cache_destroy(jbd2_revoke_record_cache);
+ jbd2_revoke_record_cache = NULL;
+ }
+ if (jbd2_revoke_table_cache) {
+ kmem_cache_destroy(jbd2_revoke_table_cache);
+ jbd2_revoke_table_cache = NULL;
+ }
+}
+
int __init jbd2_journal_init_revoke_caches(void)
{
+ J_ASSERT(!jbd2_revoke_record_cache);
+ J_ASSERT(!jbd2_revoke_table_cache);
+
jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
sizeof(struct jbd2_revoke_record_s),
- 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (jbd2_revoke_record_cache == 0)
- return -ENOMEM;
+ 0,
+ SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
+ NULL);
+ if (!jbd2_revoke_record_cache)
+ goto record_cache_failure;
jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
sizeof(struct jbd2_revoke_table_s),
- 0, 0, NULL, NULL);
- if (jbd2_revoke_table_cache == 0) {
- kmem_cache_destroy(jbd2_revoke_record_cache);
- jbd2_revoke_record_cache = NULL;
- return -ENOMEM;
- }
+ 0, SLAB_TEMPORARY, NULL);
+ if (!jbd2_revoke_table_cache)
+ goto table_cache_failure;
return 0;
+table_cache_failure:
+ jbd2_journal_destroy_revoke_caches();
+record_cache_failure:
+ return -ENOMEM;
}
-void jbd2_journal_destroy_revoke_caches(void)
-{
- kmem_cache_destroy(jbd2_revoke_record_cache);
- jbd2_revoke_record_cache = NULL;
- kmem_cache_destroy(jbd2_revoke_table_cache);
- jbd2_revoke_table_cache = NULL;
-}
-
-/* Initialise the revoke table for a given journal to a given size. */
-
-int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
+static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size)
{
- int shift, tmp;
+ int shift = 0;
+ int tmp = hash_size;
+ struct jbd2_revoke_table_s *table;
- J_ASSERT (journal->j_revoke_table[0] == NULL);
+ table = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL);
+ if (!table)
+ goto out;
- shift = 0;
- tmp = hash_size;
while((tmp >>= 1UL) != 0UL)
shift++;
- journal->j_revoke_table[0] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL);
- if (!journal->j_revoke_table[0])
- return -ENOMEM;
- journal->j_revoke = journal->j_revoke_table[0];
-
- /* Check that the hash_size is a power of two */
- J_ASSERT ((hash_size & (hash_size-1)) == 0);
-
- journal->j_revoke->hash_size = hash_size;
-
- journal->j_revoke->hash_shift = shift;
-
- journal->j_revoke->hash_table =
+ table->hash_size = hash_size;
+ table->hash_shift = shift;
+ table->hash_table =
kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
- if (!journal->j_revoke->hash_table) {
- kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
- journal->j_revoke = NULL;
- return -ENOMEM;
+ 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(&journal->j_revoke->hash_table[tmp]);
+ INIT_LIST_HEAD(&table->hash_table[tmp]);
- journal->j_revoke_table[1] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL);
- if (!journal->j_revoke_table[1]) {
- kfree(journal->j_revoke_table[0]->hash_table);
- kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
- return -ENOMEM;
- }
+out:
+ return table;
+}
- journal->j_revoke = journal->j_revoke_table[1];
+static void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table)
+{
+ int i;
+ struct list_head *hash_list;
- /* Check that the hash_size is a power of two */
- J_ASSERT ((hash_size & (hash_size-1)) == 0);
+ for (i = 0; i < table->hash_size; i++) {
+ hash_list = &table->hash_table[i];
+ J_ASSERT(list_empty(hash_list));
+ }
- journal->j_revoke->hash_size = hash_size;
+ kfree(table->hash_table);
+ kmem_cache_free(jbd2_revoke_table_cache, table);
+}
- journal->j_revoke->hash_shift = shift;
+/* 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->hash_table =
- kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
- if (!journal->j_revoke->hash_table) {
- kfree(journal->j_revoke_table[0]->hash_table);
- kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
- kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[1]);
- journal->j_revoke = NULL;
- return -ENOMEM;
- }
+ journal->j_revoke_table[0] = jbd2_journal_init_revoke_table(hash_size);
+ if (!journal->j_revoke_table[0])
+ goto fail0;
- for (tmp = 0; tmp < hash_size; tmp++)
- INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+ 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;
-}
-/* Destoy a journal's revoke table. The table must already be empty! */
+fail1:
+ jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]);
+fail0:
+ return -ENOMEM;
+}
+/* Destroy a journal's revoke table. The table must already be empty! */
void jbd2_journal_destroy_revoke(journal_t *journal)
{
- struct jbd2_revoke_table_s *table;
- struct list_head *hash_list;
- int i;
-
- table = journal->j_revoke_table[0];
- if (!table)
- return;
-
- 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);
- journal->j_revoke = NULL;
-
- table = journal->j_revoke_table[1];
- if (!table)
- return;
-
- 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);
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]);
}
if (bh)
BUFFER_TRACE(bh, "found on hash");
}
-#ifdef JBD_EXPENSIVE_CHECKING
+#ifdef JBD2_EXPENSIVE_CHECKING
else {
struct buffer_head *bh2;
* the second time we would still have a pending revoke to cancel. So,
* do not trust the Revoked bit on buffers unless RevokeValid is also
* set.
- *
- * The caller must have the journal locked.
*/
int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
{
}
}
-#ifdef JBD_EXPENSIVE_CHECKING
+#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);
/*
* Write revoke records to the journal for all entries in the current
* revoke hash, deleting the entries as we go.
- *
- * Called with the journal lock held.
*/
-
void jbd2_journal_write_revoke_records(journal_t *journal,
- transaction_t *transaction)
+ transaction_t *transaction,
+ int write_op)
{
struct journal_head *descriptor;
struct jbd2_revoke_record_s *record;
hash_list->next;
write_one_revoke_record(journal, transaction,
&descriptor, &offset,
- record);
+ record, write_op);
count++;
list_del(&record->hash);
kmem_cache_free(jbd2_revoke_record_cache, record);
}
}
if (descriptor)
- flush_descriptor(journal, descriptor, offset);
+ flush_descriptor(journal, descriptor, offset, write_op);
jbd_debug(1, "Wrote %d revoke records\n", count);
}
transaction_t *transaction,
struct journal_head **descriptorp,
int *offsetp,
- struct jbd2_revoke_record_s *record)
+ struct jbd2_revoke_record_s *record,
+ int write_op)
{
struct journal_head *descriptor;
int offset;
/* Make sure we have a descriptor with space left for the record */
if (descriptor) {
if (offset == journal->j_blocksize) {
- flush_descriptor(journal, descriptor, offset);
+ flush_descriptor(journal, descriptor, offset, write_op);
descriptor = NULL;
}
}
static void flush_descriptor(journal_t *journal,
struct journal_head *descriptor,
- int offset)
+ int offset, int write_op)
{
jbd2_journal_revoke_header_t *header;
struct buffer_head *bh = jh2bh(descriptor);
set_buffer_jwrite(bh);
BUFFER_TRACE(bh, "write");
set_buffer_dirty(bh);
- ll_rw_block(SWRITE, 1, &bh);
+ ll_rw_block((write_op == WRITE) ? SWRITE : SWRITE_SYNC_PLUG, 1, &bh);
}
#endif