ext2: Add locking for DAX faults

Add locking to ensure that DAX faults are isolated from ext2 operations
that modify the data blocks allocation for an inode.  This is intended to
be analogous to the work being done in XFS by Dave Chinner:

http://www.spinics.net/lists/linux-fsdevel/msg90260.html

Compared with XFS the ext2 case is greatly simplified by the fact that ext2
already allocates and zeros new blocks before they are returned as part of
ext2_get_block(), so DAX doesn't need to worry about getting unmapped or
unwritten buffer heads.

This means that the only work we need to do in ext2 is to isolate the DAX
faults from inode block allocation changes.  I believe this just means that
we need to isolate the DAX faults from truncate operations.

The newly introduced dax_sem is intended to replicate the protection
offered by i_mmaplock in XFS.  In addition to truncate the i_mmaplock also
protects XFS operations like hole punching, fallocate down, extent
manipulation IOCTLS like xfs_ioc_space() and extent swapping.  Truncate is
the only one of these operations supported by ext2.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.com>

1 files changed, 80 insertions, 4 deletions

diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 1982c3f11aec..11a42c5a09ae 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -27,27 +27,103 @@
 #include "acl.h"
 
 #ifdef CONFIG_FS_DAX
+/*
+ * The lock ordering for ext2 DAX fault paths is:
+ *
+ * mmap_sem (MM)
+ *   sb_start_pagefault (vfs, freeze)
+ *     ext2_inode_info->dax_sem
+ *       address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
+ *         ext2_inode_info->truncate_mutex
+ *
+ * The default page_lock and i_size verification done by non-DAX fault paths
+ * is sufficient because ext2 doesn't support hole punching.
+ */
 static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-        return dax_fault(vma, vmf, ext2_get_block, NULL);
+        struct inode *inode = file_inode(vma->vm_file);
+        struct ext2_inode_info *ei = EXT2_I(inode);
+        int ret;
+
+        if (vmf->flags & FAULT_FLAG_WRITE) {
+                sb_start_pagefault(inode->i_sb);
+                file_update_time(vma->vm_file);
+        }
+        down_read(&ei->dax_sem);
+
+        ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+
+        up_read(&ei->dax_sem);
+        if (vmf->flags & FAULT_FLAG_WRITE)
+                sb_end_pagefault(inode->i_sb);
+        return ret;
 }
 
 static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
                                                 pmd_t *pmd, unsigned int flags)
 {
-        return dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+        struct inode *inode = file_inode(vma->vm_file);
+        struct ext2_inode_info *ei = EXT2_I(inode);
+        int ret;
+
+        if (flags & FAULT_FLAG_WRITE) {
+                sb_start_pagefault(inode->i_sb);
+                file_update_time(vma->vm_file);
+        }
+        down_read(&ei->dax_sem);
+
+        ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+
+        up_read(&ei->dax_sem);
+        if (flags & FAULT_FLAG_WRITE)
+                sb_end_pagefault(inode->i_sb);
+        return ret;
 }
 
 static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-        return dax_mkwrite(vma, vmf, ext2_get_block, NULL);
+        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)
+{
+        struct inode *inode = file_inode(vma->vm_file);
+        struct ext2_inode_info *ei = EXT2_I(inode);
+        int ret = VM_FAULT_NOPAGE;
+        loff_t size;
+
+        sb_start_pagefault(inode->i_sb);
+        file_update_time(vma->vm_file);
+        down_read(&ei->dax_sem);
+
+        /* check that the faulting page hasn't raced with truncate */
+        size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        if (vmf->pgoff >= size)
+                ret = VM_FAULT_SIGBUS;
+
+        up_read(&ei->dax_sem);
+        sb_end_pagefault(inode->i_sb);
+        return ret;
 }
 
 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,
-        .pfn_mkwrite    = dax_pfn_mkwrite,
+        .pfn_mkwrite    = ext2_dax_pfn_mkwrite,
 };
 
 static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)