Btrfs: fix ioctl-initiated transactions vs wait_current_trans()

Commit 597:466b27332893 (btrfs_start_transaction: wait for commits in
progress) breaks the transaction start/stop ioctls by making
btrfs_start_transaction conditionally wait for the next transaction to
start.  If an application artificially is holding a transaction open,
things deadlock.

This workaround maintains a count of open ioctl-initiated transactions in
fs_info, and avoids wait_current_trans() if any are currently open (in
start_transaction() and btrfs_throttle()).  The start transaction ioctl
uses a new btrfs_start_ioctl_transaction() that _does_ call
wait_current_trans(), effectively pushing the join/wait decision to the
outer ioctl-initiated transaction.

This more or less neuters btrfs_throttle() when ioctl-initiated
transactions are in use, but that seems like a pretty fundamental
consequence of wrapping lots of write()'s in a transaction.  Btrfs has no
way to tell if the application considers a given operation as part of it's
transaction.

Obviously, if the transaction start/stop ioctls aren't being used, there
is no effect on current behavior.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 ctree.h       |    1 +
 ioctl.c       |   12 +++++++++++-
 transaction.c |   18 +++++++++++++-----
 transaction.h |    2 ++
 4 files changed, 27 insertions(+), 6 deletions(-)

Signed-off-by: Chris Mason <chris.mason@oracle.com>

4 files changed, 27 insertions, 6 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9b025960bbde..62499dd761b7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -518,6 +518,7 @@ struct btrfs_fs_info {
 
         u64 generation;
         u64 last_trans_committed;
+        u64 open_ioctl_trans;
         unsigned long mount_opt;
         u64 max_extent;
         u64 max_inline;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 224da287b3ed..0b63c3c77cfd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -715,7 +715,12 @@ long btrfs_ioctl_trans_start(struct file *file)
                 ret = -EINPROGRESS;
                 goto out;
         }
-        trans = btrfs_start_transaction(root, 0);
+
+        mutex_lock(&root->fs_info->trans_mutex);
+        root->fs_info->open_ioctl_trans++;
+        mutex_unlock(&root->fs_info->trans_mutex);
+
+        trans = btrfs_start_ioctl_transaction(root, 0);
         if (trans)
                 file->private_data = trans;
         else
@@ -745,6 +750,11 @@ long btrfs_ioctl_trans_end(struct file *file)
         }
         btrfs_end_transaction(trans, root);
         file->private_data = 0;
+
+        mutex_lock(&root->fs_info->trans_mutex);
+        root->fs_info->open_ioctl_trans--;
+        mutex_unlock(&root->fs_info->trans_mutex);
+
 out:
         return ret;
 }
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index cf73342e8215..a2c821e3c3a7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -152,14 +152,14 @@ static void wait_current_trans(struct btrfs_root *root)
 }
 
 struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
-                                             int num_blocks, int join)
+                                             int num_blocks, int wait)
 {
         struct btrfs_trans_handle *h =
                 kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
         int ret;
 
         mutex_lock(&root->fs_info->trans_mutex);
-        if (!join)
+        if ((wait == 1 && !root->fs_info->open_ioctl_trans) || wait == 2)
                 wait_current_trans(root);
         ret = join_transaction(root);
         BUG_ON(ret);
@@ -180,14 +180,21 @@ struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    int num_blocks)
 {
-        return start_transaction(root, num_blocks, 0);
+        return start_transaction(root, num_blocks, 1);
 }
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
                                                    int num_blocks)
 {
-        return start_transaction(root, num_blocks, 1);
+        return start_transaction(root, num_blocks, 0);
 }
 
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
+                                                         int num_blocks)
+{
+        return start_transaction(r, num_blocks, 2);
+}
+
+
 static noinline int wait_for_commit(struct btrfs_root *root,
                                     struct btrfs_transaction *commit)
 {
@@ -247,7 +254,8 @@ harder:
 void btrfs_throttle(struct btrfs_root *root)
 {
         mutex_lock(&root->fs_info->trans_mutex);
-        wait_current_trans(root);
+        if (!root->fs_info->open_ioctl_trans)
+                wait_current_trans(root);
         mutex_unlock(&root->fs_info->trans_mutex);
 
         throttle_on_drops(root);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index f5adb23151fb..2c73caeebb2c 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -83,6 +83,8 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    int num_blocks);
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
                                                    int num_blocks);
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
+                                                   int num_blocks);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root);
 int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans,