We return IOMAP_F_NEEDDSYNC flag from ext4_iomap_begin() for a
synchronous write fault when inode has some uncommitted metadata
changes. In the fault handler ext4_dax_fault() we then detect this case,
call vfs_fsync_range() to make sure all metadata is committed, and call
dax_pfn_mkwrite() to mark PTE as writeable. Note that this will also
dirty corresponding radix tree entry which is what we want - fsync(2)
will still provide data integrity guarantees for applications not using
userspace flushing. And applications using userspace flushing can avoid
calling fsync(2) and thus avoid the performance overhead.
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
fs/ext4/file.c | 36 ++++++++++++++++++++++++++++++------
fs/ext4/inode.c | 4 ++++
fs/jbd2/journal.c | 17 +++++++++++++++++
include/linux/jbd2.h | 1 +
4 files changed, 52 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 850037e140d7..3765c4ed1368 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -280,6 +280,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = vmf->flags & FAULT_FLAG_WRITE;
+ pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
@@ -287,16 +288,39 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
+ if (IS_ERR(handle)) {
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+ sb_end_pagefault(sb);
+ return VM_FAULT_SIGBUS;
+ }
} else {
down_read(&EXT4_I(inode)->i_mmap_sem);
}
- if (!IS_ERR(handle))
- result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops, NULL);
- else
- result = VM_FAULT_SIGBUS;
+ result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops, &pfn);
if (write) {
- if (!IS_ERR(handle))
- ext4_journal_stop(handle);
+ ext4_journal_stop(handle);
+ /* Write fault but PFN mapped only RO? */
+ if (result & VM_FAULT_NEEDDSYNC) {
+ int err;
+ loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
+ size_t len = 0;
+
+ if (pe_size == PE_SIZE_PTE)
+ len = PAGE_SIZE;
+#ifdef CONFIG_FS_DAX_PMD
+ else if (pe_size == PE_SIZE_PMD)
+ len = HPAGE_PMD_SIZE;
+#endif
+ else
+ WARN_ON_ONCE(1);
+ err = vfs_fsync_range(vmf->vma->vm_file, start,
+ start + len - 1, 1);
+ if (err)
+ result = VM_FAULT_SIGBUS;
+ else
+ result = dax_insert_pfn_mkwrite(vmf, pe_size,
+ pfn);
+ }
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
} else {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3c600f02673f..7a7529c3f0c8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3429,6 +3429,10 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
}
iomap->flags = 0;
+ if ((flags & IOMAP_WRITE) &&
+ !jbd2_transaction_committed(EXT4_SB(inode->i_sb)->s_journal,
+ EXT4_I(inode)->i_datasync_tid))
+ iomap->flags |= IOMAP_F_NEEDDSYNC;
bdev = inode->i_sb->s_bdev;
iomap->bdev = bdev;
if (blk_queue_dax(bdev->bd_queue))
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 7d5ef3bf3f3e..fa8cde498b4b 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -738,6 +738,23 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
return err;
}
+/* Return 1 when transaction with given tid has already committed. */
+int jbd2_transaction_committed(journal_t *journal, tid_t tid)
+{
+ int ret = 1;
+
+ read_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction &&
+ journal->j_running_transaction->t_tid == tid)
+ ret = 0;
+ if (journal->j_committing_transaction &&
+ journal->j_committing_transaction->t_tid == tid)
+ ret = 0;
+ read_unlock(&journal->j_state_lock);
+ return ret;
+}
+EXPORT_SYMBOL(jbd2_transaction_committed);
+
/*
* When this function returns the transaction corresponding to tid
* will be completed. If the transaction has currently running, start
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 606b6bce3a5b..296d1e0ea87b 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1367,6 +1367,7 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid);
int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_transaction_committed(journal_t *journal, tid_t tid);
int jbd2_complete_transaction(journal_t *journal, tid_t tid);
int jbd2_log_do_checkpoint(journal_t *journal);
int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);
--
2.12.3
