Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits)
  ext4: Adding error check after calling ext4_mb_regular_allocator()
  ext4: Fix dirtying of journalled buffers in data=journal mode
  ext4: re-inline ext4_rec_len_(to|from)_disk functions
  jbd2: Remove t_handle_lock from start_this_handle()
  jbd2: Change j_state_lock to be a rwlock_t
  jbd2: Use atomic variables to avoid taking t_handle_lock in jbd2_journal_stop
  ext4: Add mount options in superblock
  ext4: force block allocation on quota_off
  ext4: fix freeze deadlock under IO
  ext4: drop inode from orphan list if ext4_delete_inode() fails
  ext4: check to make make sure bd_dev is set before dereferencing it
  jbd2: Make barrier messages less scary
  ext4: don't print scary messages for allocation failures post-abort
  ext4: fix EFBIG edge case when writing to large non-extent file
  ext4: fix ext4_get_blocks references
  ext4: Always journal quota file modifications
  ext4: Fix potential memory leak in ext4_fill_super
  ext4: Don't error out the fs if the user tries to make a file too big
  ext4: allocate stripe-multiple IOs on stripe boundaries
  ext4: move aio completion after unwritten extent conversion
  ...

Fix up conflicts in fs/ext4/inode.c as per Ted.

Fix up xfs conflicts as per earlier xfs merge.

1 files changed, 141 insertions, 92 deletions

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index b8e0806681b..d95cc9d0401 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -26,6 +26,8 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
+#include <linux/backing-dev.h>
+#include <linux/module.h>
 
 static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
 
@@ -53,6 +55,9 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
         transaction->t_tid = journal->j_transaction_sequence++;
         transaction->t_expires = jiffies + journal->j_commit_interval;
         spin_lock_init(&transaction->t_handle_lock);
+        atomic_set(&transaction->t_updates, 0);
+        atomic_set(&transaction->t_outstanding_credits, 0);
+        atomic_set(&transaction->t_handle_count, 0);
         INIT_LIST_HEAD(&transaction->t_inode_list);
         INIT_LIST_HEAD(&transaction->t_private_list);
 
@@ -83,65 +88,75 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
  * transaction's buffer credits.
  */
 
-static int start_this_handle(journal_t *journal, handle_t *handle)
+static int start_this_handle(journal_t *journal, handle_t *handle,
+                             int gfp_mask)
 {
         transaction_t *transaction;
         int needed;
         int nblocks = handle->h_buffer_credits;
         transaction_t *new_transaction = NULL;
-        int ret = 0;
         unsigned long ts = jiffies;
 
         if (nblocks > journal->j_max_transaction_buffers) {
                 printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
                        current->comm, nblocks,
                        journal->j_max_transaction_buffers);
-                ret = -ENOSPC;
-                goto out;
+                return -ENOSPC;
         }
 
 alloc_transaction:
         if (!journal->j_running_transaction) {
-                new_transaction = kzalloc(sizeof(*new_transaction),
-                                                GFP_NOFS|__GFP_NOFAIL);
+                new_transaction = kzalloc(sizeof(*new_transaction), gfp_mask);
                 if (!new_transaction) {
-                        ret = -ENOMEM;
-                        goto out;
+                        /*
+                         * If __GFP_FS is not present, then we may be
+                         * being called from inside the fs writeback
+                         * layer, so we MUST NOT fail.  Since
+                         * __GFP_NOFAIL is going away, we will arrange
+                         * to retry the allocation ourselves.
+                         */
+                        if ((gfp_mask & __GFP_FS) == 0) {
+                                congestion_wait(BLK_RW_ASYNC, HZ/50);
+                                goto alloc_transaction;
+                        }
+                        return -ENOMEM;
                 }
         }
 
         jbd_debug(3, "New handle %p going live.\n", handle);
 
-repeat:
-
         /*
          * We need to hold j_state_lock until t_updates has been incremented,
          * for proper journal barrier handling
          */
-        spin_lock(&journal->j_state_lock);
-repeat_locked:
+repeat:
+        read_lock(&journal->j_state_lock);
         if (is_journal_aborted(journal) ||
             (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
-                spin_unlock(&journal->j_state_lock);
-                ret = -EROFS;
-                goto out;
+                read_unlock(&journal->j_state_lock);
+                kfree(new_transaction);
+                return -EROFS;
         }
 
         /* Wait on the journal's transaction barrier if necessary */
         if (journal->j_barrier_count) {
-                spin_unlock(&journal->j_state_lock);
+                read_unlock(&journal->j_state_lock);
                 wait_event(journal->j_wait_transaction_locked,
                                 journal->j_barrier_count == 0);
                 goto repeat;
         }
 
         if (!journal->j_running_transaction) {
-                if (!new_transaction) {
-                        spin_unlock(&journal->j_state_lock);
+                read_unlock(&journal->j_state_lock);
+                if (!new_transaction)
                         goto alloc_transaction;
+                write_lock(&journal->j_state_lock);
+                if (!journal->j_running_transaction) {
+                        jbd2_get_transaction(journal, new_transaction);
+                        new_transaction = NULL;
                 }
-                jbd2_get_transaction(journal, new_transaction);
-                new_transaction = NULL;
+                write_unlock(&journal->j_state_lock);
+                goto repeat;
         }
 
         transaction = journal->j_running_transaction;
@@ -155,7 +170,7 @@ repeat_locked:
 
                 prepare_to_wait(&journal->j_wait_transaction_locked,
                                         &wait, TASK_UNINTERRUPTIBLE);
-                spin_unlock(&journal->j_state_lock);
+                read_unlock(&journal->j_state_lock);
                 schedule();
                 finish_wait(&journal->j_wait_transaction_locked, &wait);
                 goto repeat;
@@ -166,8 +181,8 @@ repeat_locked:
          * buffers requested by this operation, we need to stall pending a log
          * checkpoint to free some more log space.
          */
-        spin_lock(&transaction->t_handle_lock);
-        needed = transaction->t_outstanding_credits + nblocks;
+        needed = atomic_add_return(nblocks,
+                                   &transaction->t_outstanding_credits);
 
         if (needed > journal->j_max_transaction_buffers) {
                 /*
@@ -178,11 +193,11 @@ repeat_locked:
                 DEFINE_WAIT(wait);
 
                 jbd_debug(2, "Handle %p starting new commit...\n", handle);
-                spin_unlock(&transaction->t_handle_lock);
+                atomic_sub(nblocks, &transaction->t_outstanding_credits);
                 prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
                                 TASK_UNINTERRUPTIBLE);
                 __jbd2_log_start_commit(journal, transaction->t_tid);
-                spin_unlock(&journal->j_state_lock);
+                read_unlock(&journal->j_state_lock);
                 schedule();
                 finish_wait(&journal->j_wait_transaction_locked, &wait);
                 goto repeat;
@@ -215,35 +230,48 @@ repeat_locked:
          */
         if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
                 jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
-                spin_unlock(&transaction->t_handle_lock);
-                __jbd2_log_wait_for_space(journal);
-                goto repeat_locked;
+                atomic_sub(nblocks, &transaction->t_outstanding_credits);
+                read_unlock(&journal->j_state_lock);
+                write_lock(&journal->j_state_lock);
+                if (__jbd2_log_space_left(journal) < jbd_space_needed(journal))
+                        __jbd2_log_wait_for_space(journal);
+                write_unlock(&journal->j_state_lock);
+                goto repeat;
         }
 
         /* OK, account for the buffers that this operation expects to
-         * use and add the handle to the running transaction. */
-
-        if (time_after(transaction->t_start, ts)) {
+         * use and add the handle to the running transaction. 
+         *
+         * In order for t_max_wait to be reliable, it must be
+         * protected by a lock.  But doing so will mean that
+         * start_this_handle() can not be run in parallel on SMP
+         * systems, which limits our scalability.  So we only enable
+         * it when debugging is enabled.  We may want to use a
+         * separate flag, eventually, so we can enable this
+         * independently of debugging.
+         */
+#ifdef CONFIG_JBD2_DEBUG
+        if (jbd2_journal_enable_debug &&
+            time_after(transaction->t_start, ts)) {
                 ts = jbd2_time_diff(ts, transaction->t_start);
+                spin_lock(&transaction->t_handle_lock);
                 if (ts > transaction->t_max_wait)
                         transaction->t_max_wait = ts;
+                spin_unlock(&transaction->t_handle_lock);
         }
-
+#endif
         handle->h_transaction = transaction;
-        transaction->t_outstanding_credits += nblocks;
-        transaction->t_updates++;
-        transaction->t_handle_count++;
+        atomic_inc(&transaction->t_updates);
+        atomic_inc(&transaction->t_handle_count);
         jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
-                  handle, nblocks, transaction->t_outstanding_credits,
+                  handle, nblocks,
+                  atomic_read(&transaction->t_outstanding_credits),
                   __jbd2_log_space_left(journal));
-        spin_unlock(&transaction->t_handle_lock);
-        spin_unlock(&journal->j_state_lock);
+        read_unlock(&journal->j_state_lock);
 
         lock_map_acquire(&handle->h_lockdep_map);
-out:
-        if (unlikely(new_transaction))          /* It's usually NULL */
-                kfree(new_transaction);
-        return ret;
+        kfree(new_transaction);
+        return 0;
 }
 
 static struct lock_class_key jbd2_handle_key;
@@ -278,7 +306,7 @@ static handle_t *new_handle(int nblocks)
  *
  * Return a pointer to a newly allocated handle, or NULL on failure
  */
-handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
+handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int gfp_mask)
 {
         handle_t *handle = journal_current_handle();
         int err;
@@ -298,7 +326,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
 
         current->journal_info = handle;
 
-        err = start_this_handle(journal, handle);
+        err = start_this_handle(journal, handle, gfp_mask);
         if (err < 0) {
                 jbd2_free_handle(handle);
                 current->journal_info = NULL;
@@ -308,6 +336,15 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
 out:
         return handle;
 }
+EXPORT_SYMBOL(jbd2__journal_start);
+
+
+handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
+{
+        return jbd2__journal_start(journal, nblocks, GFP_NOFS);
+}
+EXPORT_SYMBOL(jbd2_journal_start);
+
 
 /**
  * int jbd2_journal_extend() - extend buffer credits.
@@ -342,7 +379,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
 
         result = 1;
 
-        spin_lock(&journal->j_state_lock);
+        read_lock(&journal->j_state_lock);
 
         /* Don't extend a locked-down transaction! */
         if (handle->h_transaction->t_state != T_RUNNING) {
@@ -352,7 +389,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
         }
 
         spin_lock(&transaction->t_handle_lock);
-        wanted = transaction->t_outstanding_credits + nblocks;
+        wanted = atomic_read(&transaction->t_outstanding_credits) + nblocks;
 
         if (wanted > journal->j_max_transaction_buffers) {
                 jbd_debug(3, "denied handle %p %d blocks: "
@@ -367,14 +404,14 @@ int jbd2_journal_extend(handle_t *handle, int nblocks)
         }
 
         handle->h_buffer_credits += nblocks;
-        transaction->t_outstanding_credits += nblocks;
+        atomic_add(nblocks, &transaction->t_outstanding_credits);
         result = 0;
 
         jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
 unlock:
         spin_unlock(&transaction->t_handle_lock);
 error_out:
-        spin_unlock(&journal->j_state_lock);
+        read_unlock(&journal->j_state_lock);
 out:
         return result;
 }
@@ -394,8 +431,7 @@ out:
  * transaction capabable of guaranteeing the requested number of
  * credits.
  */
-
-int jbd2_journal_restart(handle_t *handle, int nblocks)
+int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
 {
         transaction_t *transaction = handle->h_transaction;
         journal_t *journal = transaction->t_journal;
@@ -410,29 +446,35 @@ int jbd2_journal_restart(handle_t *handle, int nblocks)
          * First unlink the handle from its current transaction, and start the
          * commit on that.
          */
-        J_ASSERT(transaction->t_updates > 0);
+        J_ASSERT(atomic_read(&transaction->t_updates) > 0);
         J_ASSERT(journal_current_handle() == handle);
 
-        spin_lock(&journal->j_state_lock);
+        read_lock(&journal->j_state_lock);
         spin_lock(&transaction->t_handle_lock);
-        transaction->t_outstanding_credits -= handle->h_buffer_credits;
-        transaction->t_updates--;
-
-        if (!transaction->t_updates)
+        atomic_sub(handle->h_buffer_credits,
+                   &transaction->t_outstanding_credits);
+        if (atomic_dec_and_test(&transaction->t_updates))
                 wake_up(&journal->j_wait_updates);
         spin_unlock(&transaction->t_handle_lock);
 
         jbd_debug(2, "restarting handle %p\n", handle);
         __jbd2_log_start_commit(journal, transaction->t_tid);
-        spin_unlock(&journal->j_state_lock);
+        read_unlock(&journal->j_state_lock);
 
         lock_map_release(&handle->h_lockdep_map);
         handle->h_buffer_credits = nblocks;
-        ret = start_this_handle(journal, handle);
+        ret = start_this_handle(journal, handle, gfp_mask);
         return ret;
 }
+EXPORT_SYMBOL(jbd2__journal_restart);
 
 
+int jbd2_journal_restart(handle_t *handle, int nblocks)
+{
+        return jbd2__journal_restart(handle, nblocks, GFP_NOFS);
+}
+EXPORT_SYMBOL(jbd2_journal_restart);
+
 /**
  * void jbd2_journal_lock_updates () - establish a transaction barrier.
  * @journal:  Journal to establish a barrier on.
@@ -447,7 +489,7 @@ void jbd2_journal_lock_updates(journal_t *journal)
 {
         DEFINE_WAIT(wait);
 
-        spin_lock(&journal->j_state_lock);
+        write_lock(&journal->j_state_lock);
         ++journal->j_barrier_count;
 
         /* Wait until there are no running updates */
@@ -458,19 +500,19 @@ void jbd2_journal_lock_updates(journal_t *journal)
                         break;
 
                 spin_lock(&transaction->t_handle_lock);
-                if (!transaction->t_updates) {
+                if (!atomic_read(&transaction->t_updates)) {
                         spin_unlock(&transaction->t_handle_lock);
                         break;
                 }
                 prepare_to_wait(&journal->j_wait_updates, &wait,
                                 TASK_UNINTERRUPTIBLE);
                 spin_unlock(&transaction->t_handle_lock);
-                spin_unlock(&journal->j_state_lock);
+                write_unlock(&journal->j_state_lock);
                 schedule();
                 finish_wait(&journal->j_wait_updates, &wait);
-                spin_lock(&journal->j_state_lock);
+                write_lock(&journal->j_state_lock);
         }
-        spin_unlock(&journal->j_state_lock);
+        write_unlock(&journal->j_state_lock);
 
         /*
          * We have now established a barrier against other normal updates, but
@@ -494,9 +536,9 @@ void jbd2_journal_unlock_updates (journal_t *journal)
         J_ASSERT(journal->j_barrier_count != 0);
 
         mutex_unlock(&journal->j_barrier);
-        spin_lock(&journal->j_state_lock);
+        write_lock(&journal->j_state_lock);
         --journal->j_barrier_count;
-        spin_unlock(&journal->j_state_lock);
+        write_unlock(&journal->j_state_lock);
         wake_up(&journal->j_wait_transaction_locked);
 }
 
@@ -1238,7 +1280,8 @@ int jbd2_journal_stop(handle_t *handle)
 {
         transaction_t *transaction = handle->h_transaction;
         journal_t *journal = transaction->t_journal;
-        int err;
+        int err, wait_for_commit = 0;
+        tid_t tid;
         pid_t pid;
 
         J_ASSERT(journal_current_handle() == handle);
@@ -1246,7 +1289,7 @@ int jbd2_journal_stop(handle_t *handle)
         if (is_handle_aborted(handle))
                 err = -EIO;
         else {
-                J_ASSERT(transaction->t_updates > 0);
+                J_ASSERT(atomic_read(&transaction->t_updates) > 0);
                 err = 0;
         }
 
@@ -1291,9 +1334,9 @@ int jbd2_journal_stop(handle_t *handle)
 
                 journal->j_last_sync_writer = pid;
 
-                spin_lock(&journal->j_state_lock);
+                read_lock(&journal->j_state_lock);
                 commit_time = journal->j_average_commit_time;
-                spin_unlock(&journal->j_state_lock);
+                read_unlock(&journal->j_state_lock);
 
                 trans_time = ktime_to_ns(ktime_sub(ktime_get(),
                                                    transaction->t_start_time));
@@ -1314,14 +1357,8 @@ int jbd2_journal_stop(handle_t *handle)
         if (handle->h_sync)
                 transaction->t_synchronous_commit = 1;
         current->journal_info = NULL;
-        spin_lock(&transaction->t_handle_lock);
-        transaction->t_outstanding_credits -= handle->h_buffer_credits;
-        transaction->t_updates--;
-        if (!transaction->t_updates) {
-                wake_up(&journal->j_wait_updates);
-                if (journal->j_barrier_count)
-                        wake_up(&journal->j_wait_transaction_locked);
-        }
+        atomic_sub(handle->h_buffer_credits,
+                   &transaction->t_outstanding_credits);
 
         /*
          * If the handle is marked SYNC, we need to set another commit
@@ -1330,15 +1367,13 @@ int jbd2_journal_stop(handle_t *handle)
          * transaction is too old now.
          */
         if (handle->h_sync ||
-                        transaction->t_outstanding_credits >
-                                journal->j_max_transaction_buffers ||
-                        time_after_eq(jiffies, transaction->t_expires)) {
+            (atomic_read(&transaction->t_outstanding_credits) >
+             journal->j_max_transaction_buffers) ||
+            time_after_eq(jiffies, transaction->t_expires)) {
                 /* Do this even for aborted journals: an abort still
                  * completes the commit thread, it just doesn't write
                  * anything to disk. */
-                tid_t tid = transaction->t_tid;
 
-                spin_unlock(&transaction->t_handle_lock);
                 jbd_debug(2, "transaction too old, requesting commit for "
                                         "handle %p\n", handle);
                 /* This is non-blocking */
@@ -1349,11 +1384,25 @@ int jbd2_journal_stop(handle_t *handle)
                  * to wait for the commit to complete.
                  */
                 if (handle->h_sync && !(current->flags & PF_MEMALLOC))
-                        err = jbd2_log_wait_commit(journal, tid);
-        } else {
-                spin_unlock(&transaction->t_handle_lock);
+                        wait_for_commit = 1;
         }
 
+        /*
+         * Once we drop t_updates, if it goes to zero the transaction
+         * could start commiting on us and eventually disappear.  So
+         * once we do this, we must not dereference transaction
+         * pointer again.
+         */
+        tid = transaction->t_tid;
+        if (atomic_dec_and_test(&transaction->t_updates)) {
+                wake_up(&journal->j_wait_updates);
+                if (journal->j_barrier_count)
+                        wake_up(&journal->j_wait_transaction_locked);
+        }
+
+        if (wait_for_commit)
+                err = jbd2_log_wait_commit(journal, tid);
+
         lock_map_release(&handle->h_lockdep_map);
 
         jbd2_free_handle(handle);
@@ -1719,7 +1768,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
                 goto zap_buffer_unlocked;
 
         /* OK, we have data buffer in journaled mode */
-        spin_lock(&journal->j_state_lock);
+        write_lock(&journal->j_state_lock);
         jbd_lock_bh_state(bh);
         spin_lock(&journal->j_list_lock);
 
@@ -1772,7 +1821,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
                         jbd2_journal_put_journal_head(jh);
                         spin_unlock(&journal->j_list_lock);
                         jbd_unlock_bh_state(bh);
-                        spin_unlock(&journal->j_state_lock);
+                        write_unlock(&journal->j_state_lock);
                         return ret;
                 } else {
                         /* There is no currently-running transaction. So the
@@ -1786,7 +1835,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
                                 jbd2_journal_put_journal_head(jh);
                                 spin_unlock(&journal->j_list_lock);
                                 jbd_unlock_bh_state(bh);
-                                spin_unlock(&journal->j_state_lock);
+                                write_unlock(&journal->j_state_lock);
                                 return ret;
                         } else {
                                 /* The orphan record's transaction has
@@ -1810,7 +1859,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
                 jbd2_journal_put_journal_head(jh);
                 spin_unlock(&journal->j_list_lock);
                 jbd_unlock_bh_state(bh);
-                spin_unlock(&journal->j_state_lock);
+                write_unlock(&journal->j_state_lock);
                 return 0;
         } else {
                 /* Good, the buffer belongs to the running transaction.
@@ -1829,7 +1878,7 @@ zap_buffer:
 zap_buffer_no_jh:
         spin_unlock(&journal->j_list_lock);
         jbd_unlock_bh_state(bh);
-        spin_unlock(&journal->j_state_lock);
+        write_unlock(&journal->j_state_lock);
 zap_buffer_unlocked:
         clear_buffer_dirty(bh);
         J_ASSERT_BH(bh, !buffer_jbddirty(bh));
@@ -2136,9 +2185,9 @@ int jbd2_journal_begin_ordered_truncate(journal_t *journal,
         /* Locks are here just to force reading of recent values, it is
          * enough that the transaction was not committing before we started
          * a transaction adding the inode to orphan list */
-        spin_lock(&journal->j_state_lock);
+        read_lock(&journal->j_state_lock);
         commit_trans = journal->j_committing_transaction;
-        spin_unlock(&journal->j_state_lock);
+        read_unlock(&journal->j_state_lock);
         spin_lock(&journal->j_list_lock);
         inode_trans = jinode->i_transaction;
         spin_unlock(&journal->j_list_lock);