Btrfs: add a delalloc mutex to inodes for delalloc reservations

I was using i_mutex for this, but we're getting bogus lockdep warnings by doing
that and theres no real way to get rid of those, so just stop using i_mutex to
protect delalloc metadata reservations and use a delalloc mutex instead.  This
shouldn't be contended often at all, only if you are writing and mmap writing to
the file at the same time.  Thanks,

(cherry picked from commit f248679e86fead40cc78e724c7181d6bec1a2046)

Signed-off-by: Josef Bacik <josef@redhat.com>

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 634608d2a6d03b5d8741e573de0b142ff8cb6310..9b9b15fd5204347c5ef2931fb186af679cb0d369 100644 (file)
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -51,6 +51,9 @@ struct btrfs_inode {
        /* held while logging the inode in tree-log.c */
        struct mutex log_mutex;
 
+       /* held while doing delalloc reservations */
+       struct mutex delalloc_mutex;
+
        /* used to order data wrt metadata */
        struct btrfs_ordered_inode_tree ordered_tree;
 

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e2fff3e60a93d3523d07eb072e7a4f42f538a7d2..03503c50db5605bd0302333dbdf37989b8f00478 100644 (file)
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4203,12 +4203,11 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
        /* Need to be holding the i_mutex here if we aren't free space cache */
        if (btrfs_is_free_space_inode(root, inode))
                flush = 0;
-       else
-               WARN_ON(!mutex_is_locked(&inode->i_mutex));
 
        if (flush && btrfs_transaction_in_commit(root->fs_info))
                schedule_timeout(1);
 
+       mutex_lock(&BTRFS_I(inode)->delalloc_mutex);
        num_bytes = ALIGN(num_bytes, root->sectorsize);
 
        spin_lock(&BTRFS_I(inode)->lock);
@@ -4258,6 +4257,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
                if (to_free)
                        btrfs_block_rsv_release(root, block_rsv, to_free);
+               mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
                return ret;
        }
 
@@ -4268,6 +4268,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
        }
        BTRFS_I(inode)->reserved_extents += nr_extents;
        spin_unlock(&BTRFS_I(inode)->lock);
+       mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
 
        block_rsv_add_bytes(block_rsv, to_reserve, 1);
 

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f4485b392dfe84bb7c1c9e115f4c333023c7c480..a49b8c610280ba000610cb38c0cc5653ecf40da8 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2239,14 +2239,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                                continue;
                        }
                        nr_truncate++;
-                       /*
-                        * Need to hold the imutex for reservation purposes, not
-                        * a huge deal here but I have a WARN_ON in
-                        * btrfs_delalloc_reserve_space to catch offenders.
-                        */
-                       mutex_lock(&inode->i_mutex);
                        ret = btrfs_truncate(inode);
-                       mutex_unlock(&inode->i_mutex);
                } else {
                        nr_unlink++;
                }
@@ -6367,10 +6360,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
        u64 page_start;
        u64 page_end;
 
-       /* Need this to keep space reservations serialized */
-       mutex_lock(&inode->i_mutex);
        ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
-       mutex_unlock(&inode->i_mutex);
        if (!ret)
                ret = btrfs_update_time(vma->vm_file);
        if (ret) {
@@ -6714,6 +6704,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
        extent_io_tree_init(&ei->io_tree, &inode->i_data);
        extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
        mutex_init(&ei->log_mutex);
+       mutex_init(&ei->delalloc_mutex);
        btrfs_ordered_inode_tree_init(&ei->ordered_tree);
        INIT_LIST_HEAD(&ei->i_orphan);
        INIT_LIST_HEAD(&ei->delalloc_inodes);

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index efbffef01078c4c728bf9cdf32b70de0e902bb3d..d3bd1db41e67e8afa15a627f0d445aeb1b8c58ed 100644 (file)
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -876,10 +876,8 @@ static int cluster_pages_for_defrag(struct inode *inode,
                return 0;
        file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
 
-       mutex_lock(&inode->i_mutex);
        ret = btrfs_delalloc_reserve_space(inode,
                                           num_pages << PAGE_CACHE_SHIFT);
-       mutex_unlock(&inode->i_mutex);
        if (ret)
                return ret;
 again:

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index cfb55434a46981fa64416e68fa3fd29cf58238f5..dff29d5e151a3b80d516be44cc1ebdf0d00adad6 100644 (file)
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2947,9 +2947,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
        index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
        last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
        while (index <= last_index) {
-               mutex_lock(&inode->i_mutex);
                ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
-               mutex_unlock(&inode->i_mutex);
                if (ret)
                        goto out;