ext4: convert DAX faults to iomap infrastructure

Convert DAX faults to use iomap infrastructure. We would not have to start
transaction in ext4_dax_fault() anymore since ext4_iomap_begin takes
care of that but so far we do that to avoid lock inversion of
transaction start with DAX entry lock which gets acquired in
dax_iomap_fault() before calling ->iomap_begin handler.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1953fe3..b5f1844 100644 (file)
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -275,7 +275,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        if (IS_ERR(handle))
                result = VM_FAULT_SIGBUS;
        else
-               result = dax_fault(vma, vmf, ext4_dax_get_block);
+               result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
 
        if (write) {
                if (!IS_ERR(handle))
@@ -309,9 +309,10 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 
        if (IS_ERR(handle))
                result = VM_FAULT_SIGBUS;
-       else
-               result = dax_pmd_fault(vma, addr, pmd, flags,
-                                        ext4_dax_get_block);
+       else {
+               result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+                                            &ext4_iomap_ops);
+       }
 
        if (write) {
                if (!IS_ERR(handle))

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 29237f2..9de9a5a 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3369,12 +3369,16 @@ retry:
                }
 
                /*
-                * If we added blocks beyond i_size we need to make sure they
+                * If we added blocks beyond i_size, we need to make sure they
                 * will get truncated if we crash before updating i_size in
-                * ext4_iomap_end().
+                * ext4_iomap_end(). For faults we don't need to do that (and
+                * even cannot because for orphan list operations inode_lock is
+                * required) - if we happen to instantiate block beyond i_size,
+                * it is because we race with truncate which has already added
+                * the inode to the orphan list.
                 */
-               if (first_block + map.m_len >
-                   (inode->i_size + (1 << blkbits) - 1) >> blkbits) {
+               if (!(flags & IOMAP_FAULT) && first_block + map.m_len >
+                   (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) {
                        int err;
 
                        err = ext4_orphan_add(handle, inode);
@@ -3420,7 +3424,7 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
        int blkbits = inode->i_blkbits;
        bool truncate = false;
 
-       if (!(flags & IOMAP_WRITE))
+       if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
                return 0;
 
        handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);