1 files changed, 30 insertions, 14 deletions

diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index c7bd649bbbdc..da6cd9bdaabc 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -55,6 +55,25 @@
  *                      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  *                      buffer has been revoked.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 noone else
+ * can touch them (filesystem isn't mounted yet) and hence no locking is
+ * needed.
  */
 
 #ifndef __KERNEL__
@@ -67,6 +86,7 @@
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/init.h>
+#include <linux/bio.h>
 #endif
 #include <linux/log2.h>
 
@@ -99,8 +119,8 @@ struct jbd_revoke_table_s
 #ifdef __KERNEL__
 static void write_one_revoke_record(journal_t *, transaction_t *,
                                     struct journal_head **, int *,
-                                    struct jbd_revoke_record_s *);
-static void flush_descriptor(journal_t *, struct journal_head *, int);
+                                    struct jbd_revoke_record_s *, int);
+static void flush_descriptor(journal_t *, struct journal_head *, int, int);
 #endif
 
 /* Utility functions to maintain the revoke table */
@@ -402,8 +422,6 @@ int journal_revoke(handle_t *handle, unsigned 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 journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
 {
@@ -481,12 +499,9 @@ void 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 journal_write_revoke_records(journal_t *journal,
-                                  transaction_t *transaction)
+                                  transaction_t *transaction, int write_op)
 {
         struct journal_head *descriptor;
         struct jbd_revoke_record_s *record;
@@ -510,14 +525,14 @@ void journal_write_revoke_records(journal_t *journal,
                                 hash_list->next;
                         write_one_revoke_record(journal, transaction,
                                                 &descriptor, &offset,
-                                                record);
+                                                record, write_op);
                         count++;
                         list_del(&record->hash);
                         kmem_cache_free(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);
 }
 
@@ -530,7 +545,8 @@ static void write_one_revoke_record(journal_t *journal,
                                     transaction_t *transaction,
                                     struct journal_head **descriptorp,
                                     int *offsetp,
-                                    struct jbd_revoke_record_s *record)
+                                    struct jbd_revoke_record_s *record,
+                                    int write_op)
 {
         struct journal_head *descriptor;
         int offset;
@@ -549,7 +565,7 @@ static void write_one_revoke_record(journal_t *journal,
         /* 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;
                 }
         }
@@ -586,7 +602,7 @@ static void write_one_revoke_record(journal_t *journal,
 
 static void flush_descriptor(journal_t *journal,
                              struct journal_head *descriptor,
-                             int offset)
+                             int offset, int write_op)
 {
         journal_revoke_header_t *header;
         struct buffer_head *bh = jh2bh(descriptor);
@@ -601,7 +617,7 @@ static void flush_descriptor(journal_t *journal,
         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