1 files changed, 183 insertions, 129 deletions

diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 2e1453a5e99..198c9c10276 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -47,6 +47,10 @@
  *   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
@@ -55,6 +59,25 @@
  *			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  *			buffer has been revoked.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__
@@ -67,6 +90,7 @@
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/init.h>
+#include <linux/bio.h>
 #endif
 #include <linux/log2.h>
 
@@ -98,9 +122,10 @@ struct jbd2_revoke_table_s
 
 #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 list_head *,
+				    struct buffer_head **, int *,
+				    struct jbd2_revoke_record_s *, int);
+static void flush_descriptor(journal_t *, struct buffer_head *, int, int);
 #endif
 
 /* Utility functions to maintain the revoke table */
@@ -139,7 +164,7 @@ repeat:
 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;
 }
@@ -167,138 +192,117 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal,
 	return NULL;
 }
 
-int __init jbd2_journal_init_revoke_caches(void)
+void jbd2_journal_destroy_revoke_caches(void)
 {
-	jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
-					   sizeof(struct jbd2_revoke_record_s),
-					   0,
-					   SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
-					   NULL);
-	if (!jbd2_revoke_record_cache)
-		return -ENOMEM;
-
-	jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
-					   sizeof(struct jbd2_revoke_table_s),
-					   0, SLAB_TEMPORARY, NULL);
-	if (!jbd2_revoke_table_cache) {
+	if (jbd2_revoke_record_cache) {
 		kmem_cache_destroy(jbd2_revoke_record_cache);
 		jbd2_revoke_record_cache = NULL;
-		return -ENOMEM;
 	}
-	return 0;
+	if (jbd2_revoke_table_cache) {
+		kmem_cache_destroy(jbd2_revoke_table_cache);
+		jbd2_revoke_table_cache = NULL;
+	}
 }
 
-void jbd2_journal_destroy_revoke_caches(void)
+int __init jbd2_journal_init_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;
-}
+	J_ASSERT(!jbd2_revoke_record_cache);
+	J_ASSERT(!jbd2_revoke_table_cache);
 
-/* Initialise the revoke table for a given journal to a given size. */
+	jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s,
+					SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY);
+	if (!jbd2_revoke_record_cache)
+		goto record_cache_failure;
 
-int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
+	jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s,
+					     SLAB_TEMPORARY);
+	if (!jbd2_revoke_table_cache)
+		goto table_cache_failure;
+	return 0;
+table_cache_failure:
+	jbd2_journal_destroy_revoke_caches();
+record_cache_failure:
+		return -ENOMEM;
+}
+
+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(is_power_of_2(hash_size));
-
-	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;
+}
+
+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));
 	}
 
-	journal->j_revoke = journal->j_revoke_table[1];
+	kfree(table->hash_table);
+	kmem_cache_free(jbd2_revoke_table_cache, table);
+}
 
-	/* Check that the hash_size is a power of two */
+/* 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_size = hash_size;
-
-	journal->j_revoke->hash_shift = shift;
+	journal->j_revoke_table[0] = jbd2_journal_init_revoke_table(hash_size);
+	if (!journal->j_revoke_table[0])
+		goto fail0;
 
-	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[1] = jbd2_journal_init_revoke_table(hash_size);
+	if (!journal->j_revoke_table[1])
+		goto fail1;
 
-	for (tmp = 0; tmp < hash_size; tmp++)
-		INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+	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]);
 }
 
 
@@ -418,8 +422,6 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
  * 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)
 {
@@ -477,6 +479,36 @@ int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 	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
@@ -497,14 +529,13 @@ void jbd2_journal_switch_revoke_table(journal_t *journal)
 /*
  * 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,
+				       struct list_head *log_bufs,
+				       int write_op)
 {
-	struct journal_head *descriptor;
+	struct buffer_head *descriptor;
 	struct jbd2_revoke_record_s *record;
 	struct jbd2_revoke_table_s *revoke;
 	struct list_head *hash_list;
@@ -524,16 +555,16 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
 		while (!list_empty(hash_list)) {
 			record = (struct jbd2_revoke_record_s *)
 				hash_list->next;
-			write_one_revoke_record(journal, transaction,
+			write_one_revoke_record(journal, transaction, log_bufs,
 						&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);
 }
 
@@ -544,11 +575,14 @@ void jbd2_journal_write_revoke_records(journal_t *journal,
 
 static void write_one_revoke_record(journal_t *journal,
 				    transaction_t *transaction,
-				    struct journal_head **descriptorp,
+				    struct list_head *log_bufs,
+				    struct buffer_head **descriptorp,
 				    int *offsetp,
-				    struct jbd2_revoke_record_s *record)
+				    struct jbd2_revoke_record_s *record,
+				    int write_op)
 {
-	struct journal_head *descriptor;
+	int csum_size = 0;
+	struct buffer_head *descriptor;
 	int offset;
 	journal_header_t *header;
 
@@ -562,10 +596,14 @@ static void write_one_revoke_record(journal_t *journal,
 	descriptor = *descriptorp;
 	offset = *offsetp;
 
+	/* Do we need to leave space at the end for a checksum? */
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		csum_size = sizeof(struct jbd2_journal_revoke_tail);
+
 	/* Make sure we have a descriptor with space left for the record */
 	if (descriptor) {
-		if (offset == journal->j_blocksize) {
-			flush_descriptor(journal, descriptor, offset);
+		if (offset >= journal->j_blocksize - csum_size) {
+			flush_descriptor(journal, descriptor, offset, write_op);
 			descriptor = NULL;
 		}
 	}
@@ -574,26 +612,26 @@ static void write_one_revoke_record(journal_t *journal,
 		descriptor = jbd2_journal_get_descriptor_buffer(journal);
 		if (!descriptor)
 			return;
-		header = (journal_header_t *) &jh2bh(descriptor)->b_data[0];
+		header = (journal_header_t *)descriptor->b_data;
 		header->h_magic     = cpu_to_be32(JBD2_MAGIC_NUMBER);
 		header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK);
 		header->h_sequence  = cpu_to_be32(transaction->t_tid);
 
 		/* Record it so that we can wait for IO completion later */
-		JBUFFER_TRACE(descriptor, "file as BJ_LogCtl");
-		jbd2_journal_file_buffer(descriptor, transaction, BJ_LogCtl);
+		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_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) {
-		* ((__be64 *)(&jh2bh(descriptor)->b_data[offset])) =
+		* ((__be64 *)(&descriptor->b_data[offset])) =
 			cpu_to_be64(record->blocknr);
 		offset += 8;
 
 	} else {
-		* ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) =
+		* ((__be32 *)(&descriptor->b_data[offset])) =
 			cpu_to_be32(record->blocknr);
 		offset += 4;
 	}
@@ -601,6 +639,21 @@ static void write_one_revoke_record(journal_t *journal,
 	*offsetp = offset;
 }
 
+static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
+{
+	struct jbd2_journal_revoke_tail *tail;
+	__u32 csum;
+
+	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		return;
+
+	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
+			sizeof(struct jbd2_journal_revoke_tail));
+	tail->r_checksum = 0;
+	csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize);
+	tail->r_checksum = cpu_to_be32(csum);
+}
+
 /*
  * 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
@@ -609,23 +662,24 @@ static void write_one_revoke_record(journal_t *journal,
  */
 
 static void flush_descriptor(journal_t *journal,
-			     struct journal_head *descriptor,
-			     int offset)
+			     struct buffer_head *descriptor,
+			     int offset, int write_op)
 {
 	jbd2_journal_revoke_header_t *header;
-	struct buffer_head *bh = jh2bh(descriptor);
 
 	if (is_journal_aborted(journal)) {
-		put_bh(bh);
+		put_bh(descriptor);
 		return;
 	}
 
-	header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data;
+	header = (jbd2_journal_revoke_header_t *)descriptor->b_data;
 	header->r_count = cpu_to_be32(offset);
-	set_buffer_jwrite(bh);
-	BUFFER_TRACE(bh, "write");
-	set_buffer_dirty(bh);
-	ll_rw_block(SWRITE, 1, &bh);
+	jbd2_revoke_csum_set(journal, descriptor);
+
+	set_buffer_jwrite(descriptor);
+	BUFFER_TRACE(descriptor, "write");
+	set_buffer_dirty(descriptor);
+	write_dirty_buffer(descriptor, write_op);
 }
 #endif