Merge branch 'next' into for-linus

4 files changed, 129 insertions, 104 deletions

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 17159cacbd9e..5d70b3e6d49b 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -20,9 +20,9 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <trace/events/jbd2.h>
 
 /*
  * Unlink a buffer from a transaction checkpoint list.
@@ -358,8 +358,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
          * journal straight away.
          */
         result = jbd2_cleanup_journal_tail(journal);
-        trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d",
-                   journal->j_devname, result);
+        trace_jbd2_checkpoint(journal, result);
         jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
         if (result <= 0)
                 return result;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 0b7d3b8226fd..7b4088b2364d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -16,7 +16,6 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
-#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -26,6 +25,7 @@
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
+#include <trace/events/jbd2.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -253,6 +253,7 @@ static int journal_submit_data_buffers(journal_t *journal,
                  * block allocation  with delalloc. We need to write
                  * only allocated blocks here.
                  */
+                trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
                 err = journal_submit_inode_data_buffers(mapping);
                 if (!ret)
                         ret = err;
@@ -394,8 +395,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         commit_transaction = journal->j_running_transaction;
         J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
-        trace_mark(jbd2_start_commit, "dev %s transaction %d",
-                   journal->j_devname, commit_transaction->t_tid);
+        trace_jbd2_start_commit(journal, commit_transaction);
         jbd_debug(1, "JBD: starting commit of transaction %d\n",
                         commit_transaction->t_tid);
 
@@ -409,6 +409,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
          */
         if (commit_transaction->t_synchronous_commit)
                 write_op = WRITE_SYNC_PLUG;
+        trace_jbd2_commit_locking(journal, commit_transaction);
         stats.u.run.rs_wait = commit_transaction->t_max_wait;
         stats.u.run.rs_locked = jiffies;
         stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
@@ -484,6 +485,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
          */
         jbd2_journal_switch_revoke_table(journal);
 
+        trace_jbd2_commit_flushing(journal, commit_transaction);
         stats.u.run.rs_flushing = jiffies;
         stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
                                                stats.u.run.rs_flushing);
@@ -520,6 +522,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         commit_transaction->t_state = T_COMMIT;
         spin_unlock(&journal->j_state_lock);
 
+        trace_jbd2_commit_logging(journal, commit_transaction);
         stats.u.run.rs_logging = jiffies;
         stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
                                                  stats.u.run.rs_logging);
@@ -1054,9 +1057,7 @@ restart_loop:
         if (journal->j_commit_callback)
                 journal->j_commit_callback(journal, commit_transaction);
 
-        trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
-                   journal->j_devname, commit_transaction->t_tid,
-                   journal->j_tail_sequence);
+        trace_jbd2_end_commit(journal, commit_transaction);
         jbd_debug(1, "JBD: commit %d complete, head %d\n",
                   journal->j_commit_sequence, journal->j_tail_sequence);
         if (to_free)
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 58144102bf25..e378cb383979 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -38,6 +38,10 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/math64.h>
+#include <linux/hash.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/jbd2.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -293,6 +297,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
         unsigned int new_offset;
         struct buffer_head *bh_in = jh2bh(jh_in);
         struct jbd2_buffer_trigger_type *triggers;
+        journal_t *journal = transaction->t_journal;
 
         /*
          * The buffer really shouldn't be locked: only the current committing
@@ -306,6 +311,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
         J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
 
         new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+        /* keep subsequent assertions sane */
+        new_bh->b_state = 0;
+        init_buffer(new_bh, NULL, NULL);
+        atomic_set(&new_bh->b_count, 1);
+        new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
 
         /*
          * If a new transaction has already done a buffer copy-out, then
@@ -384,14 +394,6 @@ repeat:
                 kunmap_atomic(mapped_data, KM_USER0);
         }
 
-        /* keep subsequent assertions sane */
-        new_bh->b_state = 0;
-        init_buffer(new_bh, NULL, NULL);
-        atomic_set(&new_bh->b_count, 1);
-        jbd_unlock_bh_state(bh_in);
-
-        new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
-
         set_bh_page(new_bh, new_page, new_offset);
         new_jh->b_transaction = NULL;
         new_bh->b_size = jh2bh(jh_in)->b_size;
@@ -408,7 +410,11 @@ repeat:
          * copying is moved to the transaction's shadow queue.
          */
         JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
-        jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+        spin_lock(&journal->j_list_lock);
+        __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+        spin_unlock(&journal->j_list_lock);
+        jbd_unlock_bh_state(bh_in);
+
         JBUFFER_TRACE(new_jh, "file as BJ_IO");
         jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
 
@@ -1781,7 +1787,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
  *
- * Two internal function, which provide abort to te jbd layer
+ * Two internal functions, which provide abort to the jbd layer
  * itself are here.
  */
 
@@ -1879,7 +1885,7 @@ void jbd2_journal_abort(journal_t *journal, int errno)
  * int jbd2_journal_errno () - returns the journal's error state.
  * @journal: journal to examine.
  *
- * This is the errno numbet set with jbd2_journal_abort(), the last
+ * This is the errno number set with jbd2_journal_abort(), the last
  * time the journal was mounted - if the journal was stopped
  * without calling abort this will be 0.
  *
@@ -1903,7 +1909,7 @@ int jbd2_journal_errno(journal_t *journal)
  * int jbd2_journal_clear_err () - clears the journal's error state
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 int jbd2_journal_clear_err(journal_t *journal)
@@ -1923,7 +1929,7 @@ int jbd2_journal_clear_err(journal_t *journal)
  * void jbd2_journal_ack_err() - Ack journal err.
  * @journal: journal to act on.
  *
- * An error must be cleared or Acked to take a FS out of readonly
+ * An error must be cleared or acked to take a FS out of readonly
  * mode.
  */
 void jbd2_journal_ack_err(journal_t *journal)
@@ -2377,6 +2383,72 @@ static void __exit journal_exit(void)
         jbd2_journal_destroy_caches();
 }
 
+/* 
+ * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 
+ * tracing infrastructure to map a dev_t to a device name.
+ *
+ * The caller should use rcu_read_lock() in order to make sure the
+ * device name stays valid until its done with it.  We use
+ * rcu_read_lock() as well to make sure we're safe in case the caller
+ * gets sloppy, and because rcu_read_lock() is cheap and can be safely
+ * nested.
+ */
+struct devname_cache {
+        struct rcu_head rcu;
+        dev_t           device;
+        char            devname[BDEVNAME_SIZE];
+};
+#define CACHE_SIZE_BITS 6
+static struct devname_cache *devcache[1 << CACHE_SIZE_BITS];
+static DEFINE_SPINLOCK(devname_cache_lock);
+
+static void free_devcache(struct rcu_head *rcu)
+{
+        kfree(rcu);
+}
+
+const char *jbd2_dev_to_name(dev_t device)
+{
+        int     i = hash_32(device, CACHE_SIZE_BITS);
+        char    *ret;
+        struct block_device *bd;
+        static struct devname_cache *new_dev;
+
+        rcu_read_lock();
+        if (devcache[i] && devcache[i]->device == device) {
+                ret = devcache[i]->devname;
+                rcu_read_unlock();
+                return ret;
+        }
+        rcu_read_unlock();
+
+        new_dev = kmalloc(sizeof(struct devname_cache), GFP_KERNEL);
+        if (!new_dev)
+                return "NODEV-ALLOCFAILURE"; /* Something non-NULL */
+        spin_lock(&devname_cache_lock);
+        if (devcache[i]) {
+                if (devcache[i]->device == device) {
+                        kfree(new_dev);
+                        ret = devcache[i]->devname;
+                        spin_unlock(&devname_cache_lock);
+                        return ret;
+                }
+                call_rcu(&devcache[i]->rcu, free_devcache);
+        }
+        devcache[i] = new_dev;
+        devcache[i]->device = device;
+        bd = bdget(device);
+        if (bd) {
+                bdevname(bd, devcache[i]->devname);
+                bdput(bd);
+        } else
+                __bdevname(device, devcache[i]->devname);
+        ret = devcache[i]->devname;
+        spin_unlock(&devname_cache_lock);
+        return ret;
+}
+EXPORT_SYMBOL(jbd2_dev_to_name);
+
 MODULE_LICENSE("GPL");
 module_init(journal_init);
 module_exit(journal_exit);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 996ffda06bf3..6213ac728f30 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -499,34 +499,15 @@ void jbd2_journal_unlock_updates (journal_t *journal)
         wake_up(&journal->j_wait_transaction_locked);
 }
 
-/*
- * Report any unexpected dirty buffers which turn up.  Normally those
- * indicate an error, but they can occur if the user is running (say)
- * tune2fs to modify the live filesystem, so we need the option of
- * continuing as gracefully as possible.  #
- *
- * The caller should already hold the journal lock and
- * j_list_lock spinlock: most callers will need those anyway
- * in order to probe the buffer's journaling state safely.
- */
-static void jbd_unexpected_dirty_buffer(struct journal_head *jh)
+static void warn_dirty_buffer(struct buffer_head *bh)
 {
-        int jlist;
-
-        /* If this buffer is one which might reasonably be dirty
-         * --- ie. data, or not part of this journal --- then
-         * we're OK to leave it alone, but otherwise we need to
-         * move the dirty bit to the journal's own internal
-         * JBDDirty bit. */
-        jlist = jh->b_jlist;
-
-        if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
-            jlist == BJ_Shadow || jlist == BJ_Forget) {
-                struct buffer_head *bh = jh2bh(jh);
+        char b[BDEVNAME_SIZE];
 
-                if (test_clear_buffer_dirty(bh))
-                        set_buffer_jbddirty(bh);
-        }
+        printk(KERN_WARNING
+               "JBD: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
+               "There's a risk of filesystem corruption in case of system "
+               "crash.\n",
+               bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
 }
 
 /*
@@ -593,14 +574,16 @@ repeat:
                         if (jh->b_next_transaction)
                                 J_ASSERT_JH(jh, jh->b_next_transaction ==
                                                         transaction);
+                        warn_dirty_buffer(bh);
                 }
                 /*
                  * In any case we need to clean the dirty flag and we must
                  * do it under the buffer lock to be sure we don't race
                  * with running write-out.
                  */
-                JBUFFER_TRACE(jh, "Unexpected dirty buffer");
-                jbd_unexpected_dirty_buffer(jh);
+                JBUFFER_TRACE(jh, "Journalling dirty buffer");
+                clear_buffer_dirty(bh);
+                set_buffer_jbddirty(bh);
         }
 
         unlock_buffer(bh);
@@ -843,6 +826,15 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
         J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
 
         if (jh->b_transaction == NULL) {
+                /*
+                 * Previous jbd2_journal_forget() could have left the buffer
+                 * with jbddirty bit set because it was being committed. When
+                 * the commit finished, we've filed the buffer for
+                 * checkpointing and marked it dirty. Now we are reallocating
+                 * the buffer so the transaction freeing it must have
+                 * committed and so it's safe to clear the dirty bit.
+                 */
+                clear_buffer_dirty(jh2bh(jh));
                 jh->b_transaction = transaction;
 
                 /* first access by this transaction */
@@ -1547,36 +1539,6 @@ out:
         return;
 }
 
-/*
- * jbd2_journal_try_to_free_buffers() could race with
- * jbd2_journal_commit_transaction(). The later might still hold the
- * reference count to the buffers when inspecting them on
- * t_syncdata_list or t_locked_list.
- *
- * jbd2_journal_try_to_free_buffers() will call this function to
- * wait for the current transaction to finish syncing data buffers, before
- * try to free that buffer.
- *
- * Called with journal->j_state_lock hold.
- */
-static void jbd2_journal_wait_for_transaction_sync_data(journal_t *journal)
-{
-        transaction_t *transaction;
-        tid_t tid;
-
-        spin_lock(&journal->j_state_lock);
-        transaction = journal->j_committing_transaction;
-
-        if (!transaction) {
-                spin_unlock(&journal->j_state_lock);
-                return;
-        }
-
-        tid = transaction->t_tid;
-        spin_unlock(&journal->j_state_lock);
-        jbd2_log_wait_commit(journal, tid);
-}
-
 /**
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
@@ -1649,25 +1611,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 
         ret = try_to_free_buffers(page);
 
-        /*
-         * There are a number of places where jbd2_journal_try_to_free_buffers()
-         * could race with jbd2_journal_commit_transaction(), the later still
-         * holds the reference to the buffers to free while processing them.
-         * try_to_free_buffers() failed to free those buffers. Some of the
-         * caller of releasepage() request page buffers to be dropped, otherwise
-         * treat the fail-to-free as errors (such as generic_file_direct_IO())
-         *
-         * So, if the caller of try_to_release_page() wants the synchronous
-         * behaviour(i.e make sure buffers are dropped upon return),
-         * let's wait for the current transaction to finish flush of
-         * dirty data buffers, then try to free those buffers again,
-         * with the journal locked.
-         */
-        if (ret == 0 && (gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)) {
-                jbd2_journal_wait_for_transaction_sync_data(journal);
-                ret = try_to_free_buffers(page);
-        }
-
 busy:
         return ret;
 }
@@ -1693,8 +1636,13 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 
         if (jh->b_cp_transaction) {
                 JBUFFER_TRACE(jh, "on running+cp transaction");
+                /*
+                 * We don't want to write the buffer anymore, clear the
+                 * bit so that we don't confuse checks in
+                 * __journal_file_buffer
+                 */
+                clear_buffer_dirty(bh);
                 __jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
-                clear_buffer_jbddirty(bh);
                 may_free = 0;
         } else {
                 JBUFFER_TRACE(jh, "on running transaction");
@@ -1945,12 +1893,17 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
         if (jh->b_transaction && jh->b_jlist == jlist)
                 return;
 
-        /* The following list of buffer states needs to be consistent
-         * with __jbd_unexpected_dirty_buffer()'s handling of dirty
-         * state. */
-
         if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
             jlist == BJ_Shadow || jlist == BJ_Forget) {
+                /*
+                 * For metadata buffers, we track dirty bit in buffer_jbddirty
+                 * instead of buffer_dirty. We should not see a dirty bit set
+                 * here because we clear it in do_get_write_access but e.g.
+                 * tune2fs can modify the sb and set the dirty bit at any time
+                 * so we try to gracefully handle that.
+                 */
+                if (buffer_dirty(bh))
+                        warn_dirty_buffer(bh);
                 if (test_clear_buffer_dirty(bh) ||
                     test_clear_buffer_jbddirty(bh))
                         was_dirty = 1;