ext2, ext4: fix issue with missing journal entry in ext4_dax_mkwrite()

As it is currently written ext4_dax_mkwrite() assumes that the call into
__dax_mkwrite() will not have to do a block allocation so it doesn't create
a journal entry.  For a read that creates a zero page to cover a hole
followed by a write that actually allocates storage this is incorrect.  The
ext4_dax_mkwrite() -> __dax_mkwrite() -> __dax_fault() path calls
get_blocks() to allocate storage.

Fix this by having the ->page_mkwrite fault handler call ext4_dax_fault()
as this function already has all the logic needed to allocate a journal
entry and call __dax_fault().

Also update the ext2 fault handlers in this same way to remove duplicate
code and keep the logic between ext2 and ext4 the same.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 2c88d683cd918d673c83390aea187e763b5aa78e..c1400b109805b8778d8ee947ecad3060539f5ebe 100644 (file)
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
        return ret;
 }
 
-static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-       struct inode *inode = file_inode(vma->vm_file);
-       struct ext2_inode_info *ei = EXT2_I(inode);
-       int ret;
-
-       sb_start_pagefault(inode->i_sb);
-       file_update_time(vma->vm_file);
-       down_read(&ei->dax_sem);
-
-       ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
-
-       up_read(&ei->dax_sem);
-       sb_end_pagefault(inode->i_sb);
-       return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
                struct vm_fault *vmf)
 {
@@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext2_dax_vm_ops = {
        .fault          = ext2_dax_fault,
        .pmd_fault      = ext2_dax_pmd_fault,
-       .page_mkwrite   = ext2_dax_mkwrite,
+       .page_mkwrite   = ext2_dax_fault,
        .pfn_mkwrite    = ext2_dax_pfn_mkwrite,
 };
 

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 474f1a4d2ca8f45be1c0c97ce8c13a90cf75d34d..4cd318f31cbeff21979d552cab7390c6df76a5c9 100644 (file)
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
        return result;
 }
 
-static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-       int err;
-       struct inode *inode = file_inode(vma->vm_file);
-
-       sb_start_pagefault(inode->i_sb);
-       file_update_time(vma->vm_file);
-       down_read(&EXT4_I(inode)->i_mmap_sem);
-       err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
-       up_read(&EXT4_I(inode)->i_mmap_sem);
-       sb_end_pagefault(inode->i_sb);
-
-       return err;
-}
-
 /*
- * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite()
+ * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
  * handler we check for races agaist truncate. Note that since we cycle through
  * i_mmap_sem, we are sure that also any hole punching that began before we
  * were called is finished by now and so if it included part of the file we
@@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext4_dax_vm_ops = {
        .fault          = ext4_dax_fault,
        .pmd_fault      = ext4_dax_pmd_fault,
-       .page_mkwrite   = ext4_dax_mkwrite,
+       .page_mkwrite   = ext4_dax_fault,
        .pfn_mkwrite    = ext4_dax_pfn_mkwrite,
 };
 #else