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_insert_pfn_mkwrite() to insert page table entry. 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 | 6 +++++-
fs/ext4/inode.c | 15 +++++++++++++++
fs/jbd2/journal.c | 17 +++++++++++++++++
include/linux/jbd2.h | 1 +
4 files changed, 38 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 208adfc3e673..61a8788168f3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -295,6 +295,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
*/
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
+ pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
@@ -310,9 +311,12 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
} else {
down_read(&EXT4_I(inode)->i_mmap_sem);
}
- result = dax_iomap_fault(vmf, pe_size, NULL, &ext4_iomap_ops);
+ result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
if (write) {
ext4_journal_stop(handle);
+ /* Handling synchronous page fault? */
+ if (result & VM_FAULT_NEEDDSYNC)
+ result = dax_finish_sync_fault(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 31db875bc7a1..13a198924a0f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3394,6 +3394,19 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
}
#ifdef CONFIG_FS_DAX
+static bool ext4_inode_datasync_dirty(struct inode *inode)
+{
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+ if (journal)
+ return !jbd2_transaction_committed(journal,
+ EXT4_I(inode)->i_datasync_tid);
+ /* Any metadata buffers to write? */
+ if (!list_empty(&inode->i_mapping->private_list))
+ return true;
+ return inode->i_state & I_DIRTY_DATASYNC;
+}
+
static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
{
@@ -3466,6 +3479,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
}
iomap->flags = 0;
+ if ((flags & IOMAP_WRITE) && ext4_inode_datasync_dirty(inode))
+ iomap->flags |= IOMAP_F_DIRTY;
iomap->bdev = inode->i_sb->s_bdev;
iomap->dax_dev = sbi->s_daxdev;
iomap->offset = first_block << blkbits;
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
