The problem is:
1. write cached data to a file
2. read directly from the same file (via another fd)
The 2nd operation may read stale data, i.e. the one that was in a file
before the 1st op. Problem is in how fuse manages writeback.
When direct op occurs the core kernel code calls filemap_write_and_wait
to flush all the cached ops in flight. But fuse acks the writeback right
after the ->writepages callback exits w/o waiting for the real write to
happen. Thus the subsequent direct op proceeds while the real writeback
is still in flight. This is a problem for backends that reorder operation.
Fix this by making the fuse direct IO callback explicitly wait on the
in-flight writeback to finish.
Changed in v2:
- do not wait on writeback if fuse_direct_io() call came from
CUSE (because it doesn't use fuse inodes)
Original patch by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Signed-off-by: Maxim Patlasov <MPatlasov@xxxxxxxxxxxxx>
---
fs/fuse/cuse.c | 5 +++--
fs/fuse/file.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++--
fs/fuse/fuse_i.h | 13 ++++++++++++-
3 files changed, 62 insertions(+), 5 deletions(-)
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 6f96a8d..fb63185 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -93,7 +93,7 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
loff_t pos = 0;
struct iovec iov = { .iov_base = buf, .iov_len = count };
- return fuse_direct_io(file, &iov, 1, count, &pos, 0);
+ return fuse_direct_io(file, &iov, 1, count, &pos, FUSE_DIO_CUSE);
}
static ssize_t cuse_write(struct file *file, const char __user *buf,
@@ -106,7 +106,8 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
* No locking or generic_write_checks(), the server is
* responsible for locking and sanity checks.
*/
- return fuse_direct_io(file, &iov, 1, count, &pos, 1);
+ return fuse_direct_io(file, &iov, 1, count, &pos,
+ FUSE_DIO_WRITE | FUSE_DIO_CUSE);
}
static int cuse_open(struct inode *inode, struct file *file)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3767824..e6e064c 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -349,6 +349,31 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
return (u64) v0 + ((u64) v1 << 32);
}
+static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
+ pgoff_t idx_to)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ struct fuse_req *req;
+ bool found = false;
+
+ spin_lock(&fc->lock);
+ list_for_each_entry(req, &fi->writepages, writepages_entry) {
+ pgoff_t curr_index;
+
+ BUG_ON(req->inode != inode);
+ curr_index = req->misc.write.in.offset >> PAGE_CACHE_SHIFT;
+ if (!(idx_from >= curr_index + req->num_pages ||
+ idx_to < curr_index)) {
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&fc->lock);
+
+ return found;
+}
+
/*
* Check if page is under writeback
*
@@ -393,6 +418,19 @@ static int fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
return 0;
}
+static void fuse_wait_on_writeback(struct inode *inode, pgoff_t start,
+ size_t bytes)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ pgoff_t idx_from, idx_to;
+
+ idx_from = start >> PAGE_CACHE_SHIFT;
+ idx_to = (start + bytes - 1) >> PAGE_CACHE_SHIFT;
+
+ wait_event(fi->page_waitq,
+ !fuse_range_is_writeback(inode, idx_from, idx_to));
+}
+
static int fuse_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file->f_path.dentry->d_inode;
@@ -1245,8 +1283,10 @@ static inline int fuse_iter_npages(const struct iov_iter *ii_p)
ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
unsigned long nr_segs, size_t count, loff_t *ppos,
- int write)
+ int flags)
{
+ int write = flags & FUSE_DIO_WRITE;
+ int cuse = flags & FUSE_DIO_CUSE;
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fc;
size_t nmax = write ? fc->max_write : fc->max_read;
@@ -1271,6 +1311,10 @@ ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
break;
}
+ if (!cuse)
+ fuse_wait_on_writeback(file->f_mapping->host, pos,
+ nbytes);
+
if (write)
nres = fuse_send_write(req, file, pos, nbytes, owner);
else
@@ -1339,7 +1383,8 @@ static ssize_t __fuse_direct_write(struct file *file, const struct iovec *iov,
res = generic_write_checks(file, ppos, &count, 0);
if (!res) {
- res = fuse_direct_io(file, iov, nr_segs, count, ppos, 1);
+ res = fuse_direct_io(file, iov, nr_segs, count, ppos,
+ FUSE_DIO_WRITE);
if (res > 0) {
struct fuse_inode *fi = get_fuse_inode(inode);
fuse_write_update_size(inode, *ppos);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fdeccc5..86caa8c 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -823,9 +823,20 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
bool isdir);
+
+/**
+ * fuse_direct_io() flags
+ */
+
+/** If set, it is WRITE; otherwise - READ */
+#define FUSE_DIO_WRITE (1 << 0)
+
+/** CUSE pass fuse_direct_io() a file which f_mapping->host is not from FUSE */
+#define FUSE_DIO_CUSE (1 << 1)
+
ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
unsigned long nr_segs, size_t count, loff_t *ppos,
- int write);
+ int flags);
long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
unsigned int flags);
long fuse_ioctl_common(struct file *file, unsigned int cmd,
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
