Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs update from Chris Mason:
 "The biggest feature in the pull is the new (and still experimental)
  raid56 code that David Woodhouse started long ago.  I'm still working
  on the parity logging setup that will avoid inconsistent parity after
  a crash, so this is only for testing right now.  But, I'd really like
  to get it out to a broader audience to hammer out any performance
  issues or other problems.

  scrub does not yet correct errors on raid5/6 either.

  Josef has another pass at fsync performance.  The big change here is
  to combine waiting for metadata with waiting for data, which is a big
  latency win.  It is also step one toward using atomics from the
  hardware during a commit.

  Mark Fasheh has a new way to use btrfs send/receive to send only the
  metadata changes.  SUSE is using this to make snapper more efficient
  at finding changes between snapshosts.

  Snapshot-aware defrag is also included.

  Otherwise we have a large number of fixes and cleanups.  Eric Sandeen
  wins the award for removing the most lines, and I'm hoping we steal
  this idea from XFS over and over again."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (118 commits)
  btrfs: fixup/remove module.h usage as required
  Btrfs: delete inline extents when we find them during logging
  btrfs: try harder to allocate raid56 stripe cache
  Btrfs: cleanup to make the function btrfs_delalloc_reserve_metadata more logic
  Btrfs: don't call btrfs_qgroup_free if just btrfs_qgroup_reserve fails
  Btrfs: remove reduplicate check about root in the function btrfs_clean_quota_tree
  Btrfs: return ENOMEM rather than use BUG_ON when btrfs_alloc_path fails
  Btrfs: fix missing deleted items in btrfs_clean_quota_tree
  btrfs: use only inline_pages from extent buffer
  Btrfs: fix wrong reserved space when deleting a snapshot/subvolume
  Btrfs: fix wrong reserved space in qgroup during snap/subv creation
  Btrfs: remove unnecessary dget_parent/dput when creating the pending snapshot
  btrfs: remove a printk from scan_one_device
  Btrfs: fix NULL pointer after aborting a transaction
  Btrfs: fix memory leak of log roots
  Btrfs: copy everything if we've created an inline extent
  btrfs: cleanup for open-coded alignment
  Btrfs: do not change inode flags in rename
  Btrfs: use reserved space for creating a snapshot
  clear chunk_alloc flag on retryable failure
  ...

1 files changed, 80 insertions, 18 deletions

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e5ed56729607..dc08d77b717e 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -196,6 +196,9 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
         entry->file_offset = file_offset;
         entry->start = start;
         entry->len = len;
+        if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) &&
+            !(type == BTRFS_ORDERED_NOCOW))
+                entry->csum_bytes_left = disk_len;
         entry->disk_len = disk_len;
         entry->bytes_left = len;
         entry->inode = igrab(inode);
@@ -213,6 +216,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
         INIT_LIST_HEAD(&entry->root_extent_list);
         INIT_LIST_HEAD(&entry->work_list);
         init_completion(&entry->completion);
+        INIT_LIST_HEAD(&entry->log_list);
 
         trace_btrfs_ordered_extent_add(inode, entry);
 
@@ -270,6 +274,10 @@ void btrfs_add_ordered_sum(struct inode *inode,
         tree = &BTRFS_I(inode)->ordered_tree;
         spin_lock_irq(&tree->lock);
         list_add_tail(&sum->list, &entry->list);
+        WARN_ON(entry->csum_bytes_left < sum->len);
+        entry->csum_bytes_left -= sum->len;
+        if (entry->csum_bytes_left == 0)
+                wake_up(&entry->wait);
         spin_unlock_irq(&tree->lock);
 }
 
@@ -405,6 +413,66 @@ out:
         return ret == 0;
 }
 
+/* Needs to either be called under a log transaction or the log_mutex */
+void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode)
+{
+        struct btrfs_ordered_inode_tree *tree;
+        struct btrfs_ordered_extent *ordered;
+        struct rb_node *n;
+        int index = log->log_transid % 2;
+
+        tree = &BTRFS_I(inode)->ordered_tree;
+        spin_lock_irq(&tree->lock);
+        for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
+                ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
+                spin_lock(&log->log_extents_lock[index]);
+                if (list_empty(&ordered->log_list)) {
+                        list_add_tail(&ordered->log_list, &log->logged_list[index]);
+                        atomic_inc(&ordered->refs);
+                }
+                spin_unlock(&log->log_extents_lock[index]);
+        }
+        spin_unlock_irq(&tree->lock);
+}
+
+void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
+{
+        struct btrfs_ordered_extent *ordered;
+        int index = transid % 2;
+
+        spin_lock_irq(&log->log_extents_lock[index]);
+        while (!list_empty(&log->logged_list[index])) {
+                ordered = list_first_entry(&log->logged_list[index],
+                                           struct btrfs_ordered_extent,
+                                           log_list);
+                list_del_init(&ordered->log_list);
+                spin_unlock_irq(&log->log_extents_lock[index]);
+                wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
+                                                   &ordered->flags));
+                btrfs_put_ordered_extent(ordered);
+                spin_lock_irq(&log->log_extents_lock[index]);
+        }
+        spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
+void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid)
+{
+        struct btrfs_ordered_extent *ordered;
+        int index = transid % 2;
+
+        spin_lock_irq(&log->log_extents_lock[index]);
+        while (!list_empty(&log->logged_list[index])) {
+                ordered = list_first_entry(&log->logged_list[index],
+                                           struct btrfs_ordered_extent,
+                                           log_list);
+                list_del_init(&ordered->log_list);
+                spin_unlock_irq(&log->log_extents_lock[index]);
+                btrfs_put_ordered_extent(ordered);
+                spin_lock_irq(&log->log_extents_lock[index]);
+        }
+        spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
 /*
  * used to drop a reference on an ordered extent.  This will free
  * the extent if the last reference is dropped
@@ -544,10 +612,12 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
  * extra check to make sure the ordered operation list really is empty
  * before we return
  */
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
+int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
+                                 struct btrfs_root *root, int wait)
 {
         struct btrfs_inode *btrfs_inode;
         struct inode *inode;
+        struct btrfs_transaction *cur_trans = trans->transaction;
         struct list_head splice;
         struct list_head works;
         struct btrfs_delalloc_work *work, *next;
@@ -558,14 +628,10 @@ int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
 
         mutex_lock(&root->fs_info->ordered_operations_mutex);
         spin_lock(&root->fs_info->ordered_extent_lock);
-again:
-        list_splice_init(&root->fs_info->ordered_operations, &splice);
-
+        list_splice_init(&cur_trans->ordered_operations, &splice);
         while (!list_empty(&splice)) {
-
                 btrfs_inode = list_entry(splice.next, struct btrfs_inode,
                                    ordered_operations);
-
                 inode = &btrfs_inode->vfs_inode;
 
                 list_del_init(&btrfs_inode->ordered_operations);
@@ -574,24 +640,22 @@ again:
                  * the inode may be getting freed (in sys_unlink path).
                  */
                 inode = igrab(inode);
-
-                if (!wait && inode) {
-                        list_add_tail(&BTRFS_I(inode)->ordered_operations,
-                              &root->fs_info->ordered_operations);
-                }
-
                 if (!inode)
                         continue;
+
+                if (!wait)
+                        list_add_tail(&BTRFS_I(inode)->ordered_operations,
+                                      &cur_trans->ordered_operations);
                 spin_unlock(&root->fs_info->ordered_extent_lock);
 
                 work = btrfs_alloc_delalloc_work(inode, wait, 1);
                 if (!work) {
+                        spin_lock(&root->fs_info->ordered_extent_lock);
                         if (list_empty(&BTRFS_I(inode)->ordered_operations))
                                 list_add_tail(&btrfs_inode->ordered_operations,
                                               &splice);
-                        spin_lock(&root->fs_info->ordered_extent_lock);
                         list_splice_tail(&splice,
-                                         &root->fs_info->ordered_operations);
+                                         &cur_trans->ordered_operations);
                         spin_unlock(&root->fs_info->ordered_extent_lock);
                         ret = -ENOMEM;
                         goto out;
@@ -603,9 +667,6 @@ again:
                 cond_resched();
                 spin_lock(&root->fs_info->ordered_extent_lock);
         }
-        if (wait && !list_empty(&root->fs_info->ordered_operations))
-                goto again;
-
         spin_unlock(&root->fs_info->ordered_extent_lock);
 out:
         list_for_each_entry_safe(work, next, &works, list) {
@@ -974,6 +1035,7 @@ out:
 void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root, struct inode *inode)
 {
+        struct btrfs_transaction *cur_trans = trans->transaction;
         u64 last_mod;
 
         last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans);
@@ -988,7 +1050,7 @@ void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
         spin_lock(&root->fs_info->ordered_extent_lock);
         if (list_empty(&BTRFS_I(inode)->ordered_operations)) {
                 list_add_tail(&BTRFS_I(inode)->ordered_operations,
-                              &root->fs_info->ordered_operations);
+                              &cur_trans->ordered_operations);
         }
         spin_unlock(&root->fs_info->ordered_extent_lock);
 }