[PATCH 54/67] afs: Add O_DIRECT read support

[David Howells <dhowells@redhat.com>]

Add synchronous O_DIRECT read support to AFS (no AIO yet).  It can
theoretically handle reads up to the maximum size describable by loff_t -
and given an iterator with sufficiently capacity to handle that and given
support on the server.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---

 fs/afs/file.c      |   59 +++++++++++++++++++++++++++++++++++++++++++
 fs/afs/fsclient.c  |   18 +++++++++----
 fs/afs/internal.h  |    2 +
 fs/afs/write.c     |   72 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/afs/yfsclient.c |   12 ++++++---
 5 files changed, 153 insertions(+), 10 deletions(-)

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 4af7ef607cf6..5db1e7d29ad5 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -28,6 +28,7 @@ static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 static void afs_vm_open(struct vm_area_struct *area);
 static void afs_vm_close(struct vm_area_struct *area);
 static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff);
+static ssize_t afs_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 
 const struct file_operations afs_file_operations = {
 	.open		= afs_open,
@@ -56,6 +57,7 @@ const struct address_space_operations afs_fs_aops = {
 	.launder_page	= afs_launder_page,
 	.releasepage	= afs_releasepage,
 	.invalidatepage	= afs_invalidatepage,
+	.direct_IO	= afs_direct_IO,
 	.write_begin	= afs_write_begin,
 	.write_end	= afs_write_end,
 	.writepage	= afs_writepage,
@@ -601,3 +603,60 @@ static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 
 	return generic_file_read_iter(iocb, iter);
 }
+
+/*
+ * Direct file read operation for an AFS file.
+ *
+ * TODO: To support AIO, the pages in the iterator have to be copied and
+ * refs taken on them.  Then -EIOCBQUEUED needs to be returned.
+ * iocb->ki_complete must then be called upon completion of the operation.
+ */
+static ssize_t afs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+	struct afs_read *req;
+	ssize_t ret, transferred;
+
+	_enter("%llx,%zx", iocb->ki_pos, iov_iter_count(iter));
+
+	req = afs_alloc_read(GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->vnode	= vnode;
+	req->key	= key_get(afs_file_key(file));
+	req->pos	= iocb->ki_pos;
+	req->len	= iov_iter_count(iter);
+	req->iter	= iter;
+
+	task_io_account_read(req->len);
+
+	// TODO nfs_start_io_direct(inode);
+	ret = afs_fetch_data(vnode, req);
+	if (ret == 0)
+		transferred = req->actual_len;
+	afs_put_read(req);
+
+	// TODO nfs_end_io_direct(inode);
+
+	if (ret == 0)
+		ret = transferred;
+
+	BUG_ON(ret == -EIOCBQUEUED); // TODO
+	//if (iocb->ki_complete)
+	//	iocb->ki_complete(iocb, ret, 0); // only if ret == -EIOCBQUEUED
+
+	_leave(" = %zu", ret);
+	return ret;
+}
+
+/*
+ * Do direct I/O.
+ */
+static ssize_t afs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+	if (iov_iter_rw(iter) == READ)
+		return afs_file_direct_read(iocb, iter);
+	return afs_file_direct_write(iocb, iter);
+}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4943413d9c5f..290d4d391a0e 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -439,7 +439,7 @@ static void afs_fs_fetch_data64(struct afs_operation *op)
 	bp[3] = htonl(vp->fid.unique);
 	bp[4] = htonl(upper_32_bits(req->pos));
 	bp[5] = htonl(lower_32_bits(req->pos));
-	bp[6] = 0;
+	bp[6] = htonl(upper_32_bits(req->len));
 	bp[7] = htonl(lower_32_bits(req->len));
 
 	trace_afs_make_fs_call(call, &vp->fid);
@@ -1057,6 +1057,7 @@ static void afs_fs_store_data64(struct afs_operation *op)
 	struct afs_vnode_param *vp = &op->file[0];
 	struct afs_call *call;
 	__be32 *bp;
+	u32 mask = 0;
 
 	_enter(",%x,{%llx:%llu},,",
 	       key_serial(op->key), vp->fid.vid, vp->fid.vnode);
@@ -1069,6 +1070,9 @@ static void afs_fs_store_data64(struct afs_operation *op)
 
 	call->write_iter = op->store.write_iter;
 
+	if (op->flags & AFS_OPERATION_SET_MTIME)
+		mask |= AFS_SET_MTIME;
+
 	/* marshall the parameters */
 	bp = call->request;
 	*bp++ = htonl(FSSTOREDATA64);
@@ -1076,8 +1080,8 @@ static void afs_fs_store_data64(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
-	*bp++ = htonl(AFS_SET_MTIME); /* mask */
-	*bp++ = htonl(op->mtime.tv_sec); /* mtime */
+	*bp++ = htonl(mask);
+	*bp++ = htonl(op->mtime.tv_sec);
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
@@ -1102,6 +1106,7 @@ void afs_fs_store_data(struct afs_operation *op)
 	struct afs_vnode_param *vp = &op->file[0];
 	struct afs_call *call;
 	__be32 *bp;
+	u32 mask = 0;
 
 	_enter(",%x,{%llx:%llu},,",
 	       key_serial(op->key), vp->fid.vid, vp->fid.vnode);
@@ -1122,6 +1127,9 @@ void afs_fs_store_data(struct afs_operation *op)
 
 	call->write_iter = op->store.write_iter;
 
+	if (op->flags & AFS_OPERATION_SET_MTIME)
+		mask |= AFS_SET_MTIME;
+
 	/* marshall the parameters */
 	bp = call->request;
 	*bp++ = htonl(FSSTOREDATA);
@@ -1129,8 +1137,8 @@ void afs_fs_store_data(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
-	*bp++ = htonl(AFS_SET_MTIME); /* mask */
-	*bp++ = htonl(op->mtime.tv_sec); /* mtime */
+	*bp++ = htonl(mask);
+	*bp++ = htonl(op->mtime.tv_sec);
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 07d34291bf4f..d3fb9b3845bc 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -863,6 +863,7 @@ struct afs_operation {
 #define AFS_OPERATION_TRIED_ALL		0x0400	/* Set if we've tried all the fileservers */
 #define AFS_OPERATION_RETRY_SERVER	0x0800	/* Set if we should retry the current server */
 #define AFS_OPERATION_DIR_CONFLICT	0x1000	/* Set if we detected a 3rd-party dir change */
+#define AFS_OPERATION_SET_MTIME		0x2000	/* Set if we should try to store the mtime */
 };
 
 /*
@@ -1538,6 +1539,7 @@ extern int afs_fsync(struct file *, loff_t, loff_t, int);
 extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf);
 extern void afs_prune_wb_keys(struct afs_vnode *);
 extern int afs_launder_page(struct page *);
+extern ssize_t afs_file_direct_write(struct kiocb *, struct iov_iter *);
 
 /*
  * xattr.c
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a540da6ad423..281f0e93e2c6 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -406,7 +406,7 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t
 	op->store.i_size = max(pos + size, i_size);
 	op->store.laundering = laundering;
 	op->mtime = vnode->vfs_inode.i_mtime;
-	op->flags |= AFS_OPERATION_UNINTR;
+	op->flags |= AFS_OPERATION_SET_MTIME | AFS_OPERATION_UNINTR;
 	op->ops = &afs_store_data_operation;
 
 try_next_key:
@@ -1039,3 +1039,73 @@ static void afs_write_to_cache(struct afs_vnode *vnode,
 			       vnode->vfs_inode.i_mapping, start, len, i_size,
 			       afs_write_to_cache_done, vnode);
 }
+
+static void afs_dio_store_data_success(struct afs_operation *op)
+{
+	struct afs_vnode *vnode = op->file[0].vnode;
+
+	op->ctime = op->file[0].scb.status.mtime_client;
+	afs_vnode_commit_status(op, &op->file[0]);
+	if (op->error == 0) {
+		afs_stat_v(vnode, n_stores);
+		atomic_long_add(op->store.size, &afs_v2net(vnode)->n_store_bytes);
+	}
+}
+
+static const struct afs_operation_ops afs_dio_store_data_operation = {
+	.issue_afs_rpc	= afs_fs_store_data,
+	.issue_yfs_rpc	= yfs_fs_store_data,
+	.success	= afs_dio_store_data_success,
+};
+
+/*
+ * Direct file write operation for an AFS file.
+ *
+ * TODO: To support AIO, the pages in the iterator have to be copied and
+ * refs taken on them.  Then -EIOCBQUEUED needs to be returned.
+ * iocb->ki_complete must then be called upon completion of the operation.
+ */
+ssize_t afs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+	struct afs_operation *op;
+	loff_t size = iov_iter_count(iter), i_size;
+	ssize_t ret;
+
+	_enter("%s{%llx:%llu.%u},%llx,%llx",
+	       vnode->volume->name,
+	       vnode->fid.vid,
+	       vnode->fid.vnode,
+	       vnode->fid.unique,
+	       size, iocb->ki_pos);
+
+	op = afs_alloc_operation(afs_file_key(file), vnode->volume);
+	if (IS_ERR(op))
+		return -ENOMEM;
+
+	i_size = i_size_read(&vnode->vfs_inode);
+
+	afs_op_set_vnode(op, 0, vnode);
+	op->file[0].dv_delta	= 1;
+	op->file[0].set_size	= true;
+	op->store.write_iter	= iter;
+	op->store.pos		= iocb->ki_pos;
+	op->store.size		= size;
+	op->store.i_size	= max(iocb->ki_pos + size, i_size);
+	op->ops			= &afs_dio_store_data_operation;
+
+	//if (!is_sync_kiocb(iocb)) {
+
+	ret = afs_do_sync_operation(op);
+	if (ret == 0)
+		ret = size;
+
+	afs_invalidate_cache(vnode, FSCACHE_INVAL_DIO_WRITE);
+
+	//if (iocb->ki_complete)
+	//	iocb->ki_complete(iocb, ret, 0); // only if ret == -EIOCBQUEUED
+
+	_leave(" = %zd", ret);
+	return ret;
+}
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2b35cba8ad62..a8c4e230002d 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -95,12 +95,16 @@ static __be32 *xdr_encode_YFSStoreStatus_mode(__be32 *bp, mode_t mode)
 	return bp + xdr_size(x);
 }
 
-static __be32 *xdr_encode_YFSStoreStatus_mtime(__be32 *bp, const struct timespec64 *t)
+static __be32 *xdr_encode_YFSStoreStatus_mtime(__be32 *bp, struct afs_operation *op)
 {
 	struct yfs_xdr_YFSStoreStatus *x = (void *)bp;
-	s64 mtime = linux_to_yfs_time(t);
+	s64 mtime = linux_to_yfs_time(&op->mtime);
+	u32 mask = 0;
 
-	x->mask		= htonl(AFS_SET_MTIME);
+	if (op->flags & AFS_OPERATION_SET_MTIME)
+		mask |= AFS_SET_MTIME;
+
+	x->mask		= htonl(mask);
 	x->mode		= htonl(0);
 	x->mtime_client	= u64_to_xdr(mtime);
 	x->owner	= u64_to_xdr(0);
@@ -1103,7 +1107,7 @@ void yfs_fs_store_data(struct afs_operation *op)
 	bp = xdr_encode_u32(bp, YFSSTOREDATA64);
 	bp = xdr_encode_u32(bp, 0); /* RPC flags */
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
-	bp = xdr_encode_YFSStoreStatus_mtime(bp, &op->mtime);
+	bp = xdr_encode_YFSStoreStatus_mtime(bp, op);
 	bp = xdr_encode_u64(bp, op->store.pos);
 	bp = xdr_encode_u64(bp, op->store.size);
 	bp = xdr_encode_u64(bp, op->store.i_size);