Merge tag 'vfs-6.10.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull netfs updates from Christian Brauner:
 "This reworks the netfslib writeback implementation so that pages read
  from the cache are written to the cache through ->writepages(),
  thereby allowing the fscache page flag to be retired.

  The reworking also:

   - builds on top of the new writeback_iter() infrastructure

   - makes it possible to use vectored write RPCs as discontiguous
     streams of pages can be accommodated

   - makes it easier to do simultaneous content crypto and stream
     division

   - provides support for retrying writes and re-dividing a stream

   - replaces the ->launder_folio() op, so that ->writepages() is used
     instead

   - uses mempools to allocate the netfs_io_request and
     netfs_io_subrequest structs to avoid allocation failure in the
     writeback path

  Some code that uses the fscache page flag is retained for
  compatibility purposes with nfs and ceph. The code is switched to
  using the synonymous private_2 label instead and marked with
  deprecation comments.

  The merge commit contains additional details on the new algorithm that
  I've left out of here as it would probably be excessively detailed.

  On top of the netfslib infrastructure this contains the work to
  convert cifs over to netfslib"

* tag 'vfs-6.10.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (38 commits)
  cifs: Enable large folio support
  cifs: Remove some code that's no longer used, part 3
  cifs: Remove some code that's no longer used, part 2
  cifs: Remove some code that's no longer used, part 1
  cifs: Cut over to using netfslib
  cifs: Implement netfslib hooks
  cifs: Make add_credits_and_wake_if() clear deducted credits
  cifs: Add mempools for cifs_io_request and cifs_io_subrequest structs
  cifs: Set zero_point in the copy_file_range() and remap_file_range()
  cifs: Move cifs_loose_read_iter() and cifs_file_write_iter() to file.c
  cifs: Replace the writedata replay bool with a netfs sreq flag
  cifs: Make wait_mtu_credits take size_t args
  cifs: Use more fields from netfs_io_subrequest
  cifs: Replace cifs_writedata with a wrapper around netfs_io_subrequest
  cifs: Replace cifs_readdata with a wrapper around netfs_io_subrequest
  cifs: Use alternative invalidation to using launder_folio
  netfs, afs: Use writeback retry to deal with alternate keys
  netfs: Miscellaneous tidy ups
  netfs: Remove the old writeback code
  netfs: Cut over to using new writeback code
  ...

15 files changed, 783 insertions, 2840 deletions

diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig
index 2927bd174a88..2517dc242386 100644
--- a/fs/smb/client/Kconfig
+++ b/fs/smb/client/Kconfig
@@ -2,6 +2,7 @@
 config CIFS
 	tristate "SMB3 and CIFS support (advanced network filesystem)"
 	depends on INET
+	select NETFS_SUPPORT
 	select NLS
 	select NLS_UCS2_UTILS
 	select CRYPTO
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 39277c37185c..6e1698614745 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -371,9 +371,13 @@ static struct kmem_cache *cifs_inode_cachep;
 static struct kmem_cache *cifs_req_cachep;
 static struct kmem_cache *cifs_mid_cachep;
 static struct kmem_cache *cifs_sm_req_cachep;
+static struct kmem_cache *cifs_io_request_cachep;
+static struct kmem_cache *cifs_io_subrequest_cachep;
 mempool_t *cifs_sm_req_poolp;
 mempool_t *cifs_req_poolp;
 mempool_t *cifs_mid_poolp;
+mempool_t cifs_io_request_pool;
+mempool_t cifs_io_subrequest_pool;
 
 static struct inode *
 cifs_alloc_inode(struct super_block *sb)
@@ -986,61 +990,6 @@ out:
 	return root;
 }
 
-
-static ssize_t
-cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
-{
-	ssize_t rc;
-	struct inode *inode = file_inode(iocb->ki_filp);
-
-	if (iocb->ki_flags & IOCB_DIRECT)
-		return cifs_user_readv(iocb, iter);
-
-	rc = cifs_revalidate_mapping(inode);
-	if (rc)
-		return rc;
-
-	return generic_file_read_iter(iocb, iter);
-}
-
-static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct cifsInodeInfo *cinode = CIFS_I(inode);
-	ssize_t written;
-	int rc;
-
-	if (iocb->ki_filp->f_flags & O_DIRECT) {
-		written = cifs_user_writev(iocb, from);
-		if (written > 0 && CIFS_CACHE_READ(cinode)) {
-			cifs_zap_mapping(inode);
-			cifs_dbg(FYI,
-				 "Set no oplock for inode=%p after a write operation\n",
-				 inode);
-			cinode->oplock = 0;
-		}
-		return written;
-	}
-
-	written = cifs_get_writer(cinode);
-	if (written)
-		return written;
-
-	written = generic_file_write_iter(iocb, from);
-
-	if (CIFS_CACHE_WRITE(CIFS_I(inode)))
-		goto out;
-
-	rc = filemap_fdatawrite(inode->i_mapping);
-	if (rc)
-		cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n",
-			 rc, inode);
-
-out:
-	cifs_put_writer(cinode);
-	return written;
-}
-
 static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct cifsFileInfo *cfile = file->private_data;
@@ -1342,6 +1291,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
 	if (rc)
 		goto unlock;
+	if (fend > target_cifsi->netfs.zero_point)
+		target_cifsi->netfs.zero_point = fend + 1;
 
 	/* Discard all the folios that overlap the destination region. */
 	cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend);
@@ -1360,6 +1311,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
 		}
+		if (rc == 0 && new_size > target_cifsi->netfs.zero_point)
+			target_cifsi->netfs.zero_point = new_size;
 	}
 
 	/* force revalidate of size and timestamps of target file now
@@ -1451,6 +1404,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
 	if (rc)
 		goto unlock;
+	if (fend > target_cifsi->netfs.zero_point)
+		target_cifsi->netfs.zero_point = fend + 1;
 
 	/* Discard all the folios that overlap the destination region. */
 	truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
@@ -1567,8 +1522,8 @@ const struct file_operations cifs_file_strict_ops = {
 };
 
 const struct file_operations cifs_file_direct_ops = {
-	.read_iter = cifs_direct_readv,
-	.write_iter = cifs_direct_writev,
+	.read_iter = netfs_unbuffered_read_iter,
+	.write_iter = netfs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
 	.lock = cifs_lock,
@@ -1623,8 +1578,8 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 };
 
 const struct file_operations cifs_file_direct_nobrl_ops = {
-	.read_iter = cifs_direct_readv,
-	.write_iter = cifs_direct_writev,
+	.read_iter = netfs_unbuffered_read_iter,
+	.write_iter = netfs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
 	.fsync = cifs_fsync,
@@ -1799,6 +1754,48 @@ static void destroy_mids(void)
 	kmem_cache_destroy(cifs_mid_cachep);
 }
 
+static int cifs_init_netfs(void)
+{
+	cifs_io_request_cachep =
+		kmem_cache_create("cifs_io_request",
+				  sizeof(struct cifs_io_request), 0,
+				  SLAB_HWCACHE_ALIGN, NULL);
+	if (!cifs_io_request_cachep)
+		goto nomem_req;
+
+	if (mempool_init_slab_pool(&cifs_io_request_pool, 100, cifs_io_request_cachep) < 0)
+		goto nomem_reqpool;
+
+	cifs_io_subrequest_cachep =
+		kmem_cache_create("cifs_io_subrequest",
+				  sizeof(struct cifs_io_subrequest), 0,
+				  SLAB_HWCACHE_ALIGN, NULL);
+	if (!cifs_io_subrequest_cachep)
+		goto nomem_subreq;
+
+	if (mempool_init_slab_pool(&cifs_io_subrequest_pool, 100, cifs_io_subrequest_cachep) < 0)
+		goto nomem_subreqpool;
+
+	return 0;
+
+nomem_subreqpool:
+	kmem_cache_destroy(cifs_io_subrequest_cachep);
+nomem_subreq:
+	mempool_destroy(&cifs_io_request_pool);
+nomem_reqpool:
+	kmem_cache_destroy(cifs_io_request_cachep);
+nomem_req:
+	return -ENOMEM;
+}
+
+static void cifs_destroy_netfs(void)
+{
+	mempool_destroy(&cifs_io_subrequest_pool);
+	kmem_cache_destroy(cifs_io_subrequest_cachep);
+	mempool_destroy(&cifs_io_request_pool);
+	kmem_cache_destroy(cifs_io_request_cachep);
+}
+
 static int __init
 init_cifs(void)
 {
@@ -1903,10 +1900,14 @@ init_cifs(void)
 	if (rc)
 		goto out_destroy_deferredclose_wq;
 
-	rc = init_mids();
+	rc = cifs_init_netfs();
 	if (rc)
 		goto out_destroy_inodecache;
 
+	rc = init_mids();
+	if (rc)
+		goto out_destroy_netfs;
+
 	rc = cifs_init_request_bufs();
 	if (rc)
 		goto out_destroy_mids;
@@ -1961,6 +1962,8 @@ out_destroy_request_bufs:
 	cifs_destroy_request_bufs();
 out_destroy_mids:
 	destroy_mids();
+out_destroy_netfs:
+	cifs_destroy_netfs();
 out_destroy_inodecache:
 	cifs_destroy_inodecache();
 out_destroy_deferredclose_wq:
@@ -1999,6 +2002,7 @@ exit_cifs(void)
 #endif
 	cifs_destroy_request_bufs();
 	destroy_mids();
+	cifs_destroy_netfs();
 	cifs_destroy_inodecache();
 	destroy_workqueue(deferredclose_wq);
 	destroy_workqueue(cifsoplockd_wq);
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index ca55d01117c8..87310f05d397 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -69,7 +69,6 @@ extern int cifs_revalidate_file_attr(struct file *filp);
 extern int cifs_revalidate_dentry_attr(struct dentry *);
 extern int cifs_revalidate_file(struct file *filp);
 extern int cifs_revalidate_dentry(struct dentry *);
-extern int cifs_invalidate_mapping(struct inode *inode);
 extern int cifs_revalidate_mapping(struct inode *inode);
 extern int cifs_zap_mapping(struct inode *inode);
 extern int cifs_getattr(struct mnt_idmap *, const struct path *,
@@ -85,6 +84,7 @@ extern const struct inode_operations cifs_namespace_inode_operations;
 
 
 /* Functions related to files and directories */
+extern const struct netfs_request_ops cifs_req_ops;
 extern const struct file_operations cifs_file_ops;
 extern const struct file_operations cifs_file_direct_ops; /* if directio mnt */
 extern const struct file_operations cifs_file_strict_ops; /* if strictio mnt */
@@ -94,12 +94,10 @@ extern const struct file_operations cifs_file_strict_nobrl_ops;
 extern int cifs_open(struct inode *inode, struct file *file);
 extern int cifs_close(struct inode *inode, struct file *file);
 extern int cifs_closedir(struct inode *inode, struct file *file);
-extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to);
-extern ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to);
 extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
-extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
-extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from);
 extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
+ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 extern int cifs_flock(struct file *pfile, int cmd, struct file_lock *plock);
 extern int cifs_lock(struct file *, int, struct file_lock *);
 extern int cifs_fsync(struct file *, loff_t, loff_t, int);
@@ -110,9 +108,6 @@ extern int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma);
 extern const struct file_operations cifs_dir_ops;
 extern int cifs_dir_open(struct inode *inode, struct file *file);
 extern int cifs_readdir(struct file *file, struct dir_context *ctx);
-extern void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len);
-extern void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len);
-extern void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int len);
 
 /* Functions related to dir entries */
 extern const struct dentry_operations cifs_dentry_ops;
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 6ff35570db81..65574e69ba4f 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -268,8 +268,7 @@ struct dfs_info3_param;
 struct cifs_fattr;
 struct smb3_fs_context;
 struct cifs_fid;
-struct cifs_readdata;
-struct cifs_writedata;
+struct cifs_io_subrequest;
 struct cifs_io_parms;
 struct cifs_search_info;
 struct cifsInodeInfo;
@@ -450,10 +449,9 @@ struct smb_version_operations {
 	/* send a flush request to the server */
 	int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *);
 	/* async read from the server */
-	int (*async_readv)(struct cifs_readdata *);
+	int (*async_readv)(struct cifs_io_subrequest *);
 	/* async write to the server */
-	int (*async_writev)(struct cifs_writedata *,
-			    void (*release)(struct kref *));
+	void (*async_writev)(struct cifs_io_subrequest *);
 	/* sync read from the server */
 	int (*sync_read)(const unsigned int, struct cifs_fid *,
 			 struct cifs_io_parms *, unsigned int *, char **,
@@ -548,8 +546,8 @@ struct smb_version_operations {
 	/* writepages retry size */
 	unsigned int (*wp_retry_size)(struct inode *);
 	/* get mtu credits */
-	int (*wait_mtu_credits)(struct TCP_Server_Info *, unsigned int,
-				unsigned int *, struct cifs_credits *);
+	int (*wait_mtu_credits)(struct TCP_Server_Info *, size_t,
+				size_t *, struct cifs_credits *);
 	/* adjust previously taken mtu credits to request size */
 	int (*adjust_credits)(struct TCP_Server_Info *server,
 			      struct cifs_credits *credits,
@@ -883,11 +881,12 @@ add_credits(struct TCP_Server_Info *server, const struct cifs_credits *credits,
 
 static inline void
 add_credits_and_wake_if(struct TCP_Server_Info *server,
-			const struct cifs_credits *credits, const int optype)
+			struct cifs_credits *credits, const int optype)
 {
 	if (credits->value) {
 		server->ops->add_credits(server, credits, optype);
 		wake_up(&server->request_q);
+		credits->value = 0;
 	}
 }
 
@@ -1492,50 +1491,30 @@ struct cifs_aio_ctx {
 	bool			direct_io;
 };
 
-/* asynchronous read support */
-struct cifs_readdata {
-	struct kref			refcount;
-	struct list_head		list;
-	struct completion		done;
+struct cifs_io_request {
+	struct netfs_io_request		rreq;
 	struct cifsFileInfo		*cfile;
-	struct address_space		*mapping;
-	struct cifs_aio_ctx		*ctx;
-	__u64				offset;
-	ssize_t				got_bytes;
-	unsigned int			bytes;
-	pid_t				pid;
-	int				result;
-	struct work_struct		work;
-	struct iov_iter			iter;
-	struct kvec			iov[2];
-	struct TCP_Server_Info		*server;
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	struct smbd_mr			*mr;
-#endif
-	struct cifs_credits		credits;
 };
 
-/* asynchronous write support */
-struct cifs_writedata {
-	struct kref			refcount;
-	struct list_head		list;
-	struct completion		done;
-	enum writeback_sync_modes	sync_mode;
-	struct work_struct		work;
-	struct cifsFileInfo		*cfile;
-	struct cifs_aio_ctx		*ctx;
-	struct iov_iter			iter;
-	struct bio_vec			*bv;
-	__u64				offset;
+/* asynchronous read support */
+struct cifs_io_subrequest {
+	union {
+		struct netfs_io_subrequest subreq;
+		struct netfs_io_request *rreq;
+		struct cifs_io_request *req;
+	};
+	ssize_t				got_bytes;
 	pid_t				pid;
-	unsigned int			bytes;
+	unsigned int			xid;
 	int				result;
+	bool				have_xid;
+	bool				replay;
+	struct kvec			iov[2];
 	struct TCP_Server_Info		*server;
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	struct smbd_mr			*mr;
 #endif
 	struct cifs_credits		credits;
-	bool				replay;
 };
 
 /*
@@ -2115,6 +2094,8 @@ extern __u32 cifs_lock_secret;
 extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
+extern mempool_t cifs_io_request_pool;
+extern mempool_t cifs_io_subrequest_pool;
 
 /* Operations for different SMB versions */
 #define SMB1_VERSION_STRING	"1.0"
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index fbc358c09da3..c15bb5ee7eb7 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -121,7 +121,7 @@ extern struct mid_q_entry *cifs_setup_async_request(struct TCP_Server_Info *,
 extern int cifs_check_receive(struct mid_q_entry *mid,
 			struct TCP_Server_Info *server, bool log_error);
 extern int cifs_wait_mtu_credits(struct TCP_Server_Info *server,
-				 unsigned int size, unsigned int *num,
+				 size_t size, size_t *num,
 				 struct cifs_credits *credits);
 extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *,
 			struct kvec *, int /* nvec to send */,
@@ -148,6 +148,8 @@ extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof,
 				   bool from_readdir);
 extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 			    unsigned int bytes_written);
+void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result,
+				      bool was_async);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int);
 extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
 				  int flags,
@@ -599,15 +601,11 @@ void __cifs_put_smb_ses(struct cifs_ses *ses);
 extern struct cifs_ses *
 cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx);
 
-void cifs_readdata_release(struct kref *refcount);
-int cifs_async_readv(struct cifs_readdata *rdata);
+int cifs_async_readv(struct cifs_io_subrequest *rdata);
 int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid);
 
-int cifs_async_writev(struct cifs_writedata *wdata,
-		      void (*release)(struct kref *kref));
+void cifs_async_writev(struct cifs_io_subrequest *wdata);
 void cifs_writev_complete(struct work_struct *work);
-struct cifs_writedata *cifs_writedata_alloc(work_func_t complete);
-void cifs_writedata_release(struct kref *refcount);
 int cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 			  struct cifs_sb_info *cifs_sb,
 			  const unsigned char *path, char *pbuf,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 23b5709ddc31..25e9ab947c17 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -24,6 +24,8 @@
 #include <linux/swap.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/uaccess.h>
+#include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "cifspdu.h"
 #include "cifsfs.h"
 #include "cifsglob.h"
@@ -1262,18 +1264,17 @@ openRetry:
 static void
 cifs_readv_callback(struct mid_q_entry *mid)
 {
-	struct cifs_readdata *rdata = mid->callback_data;
-	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
+	struct cifs_io_subrequest *rdata = mid->callback_data;
+	struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct smb_rqst rqst = { .rq_iov = rdata->iov,
 				 .rq_nvec = 2,
-				 .rq_iter_size = iov_iter_count(&rdata->iter),
-				 .rq_iter = rdata->iter };
+				 .rq_iter = rdata->subreq.io_iter };
 	struct cifs_credits credits = { .value = 1, .instance = 0 };
 
-	cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n",
+	cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
 		 __func__, mid->mid, mid->mid_state, rdata->result,
-		 rdata->bytes);
+		 rdata->subreq.len);
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
@@ -1305,30 +1306,36 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		rdata->result = -EIO;
 	}
 
-	queue_work(cifsiod_wq, &rdata->work);
+	if (rdata->result == 0 || rdata->result == -EAGAIN)
+		iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes);
+	rdata->credits.value = 0;
+	netfs_subreq_terminated(&rdata->subreq,
+				(rdata->result == 0 || rdata->result == -EAGAIN) ?
+				rdata->got_bytes : rdata->result,
+				false);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }
 
 /* cifs_async_readv - send an async write, and set up mid to handle result */
 int
-cifs_async_readv(struct cifs_readdata *rdata)
+cifs_async_readv(struct cifs_io_subrequest *rdata)
 {
 	int rc;
 	READ_REQ *smb = NULL;
 	int wct;
-	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
 	struct smb_rqst rqst = { .rq_iov = rdata->iov,
 				 .rq_nvec = 2 };
 
-	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
-		 __func__, rdata->offset, rdata->bytes);
+	cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n",
+		 __func__, rdata->subreq.start, rdata->subreq.len);
 
 	if (tcon->ses->capabilities & CAP_LARGE_FILES)
 		wct = 12;
 	else {
 		wct = 10; /* old style read */
-		if ((rdata->offset >> 32) > 0)  {
+		if ((rdata->subreq.start >> 32) > 0)  {
 			/* can not handle this big offset for old */
 			return -EIO;
 		}
@@ -1342,13 +1349,13 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->pid >> 16));
 
 	smb->AndXCommand = 0xFF;	/* none */
-	smb->Fid = rdata->cfile->fid.netfid;
-	smb->OffsetLow = cpu_to_le32(rdata->offset & 0xFFFFFFFF);
+	smb->Fid = rdata->req->cfile->fid.netfid;
+	smb->OffsetLow = cpu_to_le32(rdata->subreq.start & 0xFFFFFFFF);
 	if (wct == 12)
-		smb->OffsetHigh = cpu_to_le32(rdata->offset >> 32);
+		smb->OffsetHigh = cpu_to_le32(rdata->subreq.start >> 32);
 	smb->Remaining = 0;
-	smb->MaxCount = cpu_to_le16(rdata->bytes & 0xFFFF);
-	smb->MaxCountHigh = cpu_to_le32(rdata->bytes >> 16);
+	smb->MaxCount = cpu_to_le16(rdata->subreq.len & 0xFFFF);
+	smb->MaxCountHigh = cpu_to_le32(rdata->subreq.len >> 16);
 	if (wct == 12)
 		smb->ByteCount = 0;
 	else {
@@ -1364,15 +1371,11 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	rdata->iov[1].iov_base = (char *)smb + 4;
 	rdata->iov[1].iov_len = get_rfc1002_length(smb);
 
-	kref_get(&rdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive,
 			     cifs_readv_callback, NULL, rdata, 0, NULL);
 
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_reads);
-	else
-		kref_put(&rdata->refcount, cifs_readdata_release);
-
 	cifs_small_buf_release(smb);
 	return rc;
 }
@@ -1615,16 +1618,17 @@ CIFSSMBWrite(const unsigned int xid, struct cifs_io_parms *io_parms,
 static void
 cifs_writev_callback(struct mid_q_entry *mid)
 {
-	struct cifs_writedata *wdata = mid->callback_data;
-	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	unsigned int written;
+	struct cifs_io_subrequest *wdata = mid->callback_data;
+	struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
 	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
 	struct cifs_credits credits = { .value = 1, .instance = 0 };
+	ssize_t result;
+	size_t written;
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		wdata->result = cifs_check_receive(mid, tcon->ses->server, 0);
-		if (wdata->result != 0)
+		result = cifs_check_receive(mid, tcon->ses->server, 0);
+		if (result != 0)
 			break;
 
 		written = le16_to_cpu(smb->CountHigh);
@@ -1636,37 +1640,37 @@ cifs_writev_callback(struct mid_q_entry *mid)
 		 * client. OS/2 servers are known to set incorrect
 		 * CountHigh values.
 		 */
-		if (written > wdata->bytes)
+		if (written > wdata->subreq.len)
 			written &= 0xFFFF;
 
-		if (written < wdata->bytes)
-			wdata->result = -ENOSPC;
+		if (written < wdata->subreq.len)
+			result = -ENOSPC;
 		else
-			wdata->bytes = written;
+			result = written;
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
-		wdata->result = -EAGAIN;
+		result = -EAGAIN;
 		break;
 	default:
-		wdata->result = -EIO;
+		result = -EIO;
 		break;
 	}
 
-	queue_work(cifsiod_wq, &wdata->work);
+	wdata->credits.value = 0;
+	cifs_write_subrequest_terminated(wdata, result, true);
 	release_mid(mid);
 	add_credits(tcon->ses->server, &credits, 0);
 }
 
 /* cifs_async_writev - send an async write, and set up mid to handle result */
-int
-cifs_async_writev(struct cifs_writedata *wdata,
-		  void (*release)(struct kref *kref))
+void
+cifs_async_writev(struct cifs_io_subrequest *wdata)
 {
 	int rc = -EACCES;
 	WRITE_REQ *smb = NULL;
 	int wct;
-	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
 	struct kvec iov[2];
 	struct smb_rqst rqst = { };
 
@@ -1674,9 +1678,10 @@ cifs_async_writev(struct cifs_writedata *wdata,
 		wct = 14;
 	} else {
 		wct = 12;
-		if (wdata->offset >> 32 > 0) {
+		if (wdata->subreq.start >> 32 > 0) {
 			/* can not handle big offset for old srv */
-			return -EIO;
+			rc = -EIO;
+			goto out;
 		}
 	}
 
@@ -1688,10 +1693,10 @@ cifs_async_writev(struct cifs_writedata *wdata,
 	smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->pid >> 16));
 
 	smb->AndXCommand = 0xFF;	/* none */
-	smb->Fid = wdata->cfile->fid.netfid;
-	smb->OffsetLow = cpu_to_le32(wdata->offset & 0xFFFFFFFF);
+	smb->Fid = wdata->req->cfile->fid.netfid;
+	smb->OffsetLow = cpu_to_le32(wdata->subreq.start & 0xFFFFFFFF);
 	if (wct == 14)
-		smb->OffsetHigh = cpu_to_le32(wdata->offset >> 32);
+		smb->OffsetHigh = cpu_to_le32(wdata->subreq.start >> 32);
 	smb->Reserved = 0xFFFFFFFF;
 	smb->WriteMode = 0;
 	smb->Remaining = 0;
@@ -1707,39 +1712,40 @@ cifs_async_writev(struct cifs_writedata *wdata,
 
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 2;
-	rqst.rq_iter = wdata->iter;
-	rqst.rq_iter_size = iov_iter_count(&wdata->iter);
+	rqst.rq_iter = wdata->subreq.io_iter;
+	rqst.rq_iter_size = iov_iter_count(&wdata->subreq.io_iter);
 
-	cifs_dbg(FYI, "async write at %llu %u bytes\n",
-		 wdata->offset, wdata->bytes);
+	cifs_dbg(FYI, "async write at %llu %zu bytes\n",
+		 wdata->subreq.start, wdata->subreq.len);
 
-	smb->DataLengthLow = cpu_to_le16(wdata->bytes & 0xFFFF);
-	smb->DataLengthHigh = cpu_to_le16(wdata->bytes >> 16);
+	smb->DataLengthLow = cpu_to_le16(wdata->subreq.len & 0xFFFF);
+	smb->DataLengthHigh = cpu_to_le16(wdata->subreq.len >> 16);
 
 	if (wct == 14) {
-		inc_rfc1001_len(&smb->hdr, wdata->bytes + 1);
-		put_bcc(wdata->bytes + 1, &smb->hdr);
+		inc_rfc1001_len(&smb->hdr, wdata->subreq.len + 1);
+		put_bcc(wdata->subreq.len + 1, &smb->hdr);
 	} else {
 		/* wct == 12 */
 		struct smb_com_writex_req *smbw =
 				(struct smb_com_writex_req *)smb;
-		inc_rfc1001_len(&smbw->hdr, wdata->bytes + 5);
-		put_bcc(wdata->bytes + 5, &smbw->hdr);
+		inc_rfc1001_len(&smbw->hdr, wdata->subreq.len + 5);
+		put_bcc(wdata->subreq.len + 5, &smbw->hdr);
 		iov[1].iov_len += 4; /* pad bigger by four bytes */
 	}
 
-	kref_get(&wdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, NULL,
 			     cifs_writev_callback, NULL, wdata, 0, NULL);
-
+	/* Can't touch wdata if rc == 0 */
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
-	else
-		kref_put(&wdata->refcount, release);
 
 async_writev_out:
 	cifs_small_buf_release(smb);
-	return rc;
+out:
+	if (rc) {
+		add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
+		cifs_write_subrequest_terminated(wdata, rc, false);
+	}
 }
 
 int
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9be37d0fe724..4c981ce89f8a 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -36,133 +36,323 @@
 #include "fs_context.h"
 #include "cifs_ioctl.h"
 #include "cached_dir.h"
+#include <trace/events/netfs.h>
+
+static int cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush);
 
 /*
- * Remove the dirty flags from a span of pages.
+ * Prepare a subrequest to upload to the server.  We need to allocate credits
+ * so that we know the maximum amount of data that we can include in it.
  */
-static void cifs_undirty_folios(struct inode *inode, loff_t start, unsigned int len)
+static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
 {
-	struct address_space *mapping = inode->i_mapping;
-	struct folio *folio;
-	pgoff_t end;
+	struct cifs_io_subrequest *wdata =
+		container_of(subreq, struct cifs_io_subrequest, subreq);
+	struct cifs_io_request *req = wdata->req;
+	struct TCP_Server_Info *server;
+	struct cifsFileInfo *open_file = req->cfile;
+	size_t wsize = req->rreq.wsize;
+	int rc;
 
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
+	if (!wdata->have_xid) {
+		wdata->xid = get_xid();
+		wdata->have_xid = true;
+	}
 
-	rcu_read_lock();
+	server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
+	wdata->server = server;
 
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each_marked(&xas, folio, end, PAGECACHE_TAG_DIRTY) {
-		if (xas_retry(&xas, folio))
-			continue;
-		xas_pause(&xas);
-		rcu_read_unlock();
-		folio_lock(folio);
-		folio_clear_dirty_for_io(folio);
-		folio_unlock(folio);
-		rcu_read_lock();
+retry:
+	if (open_file->invalidHandle) {
+		rc = cifs_reopen_file(open_file, false);
+		if (rc < 0) {
+			if (rc == -EAGAIN)
+				goto retry;
+			subreq->error = rc;
+			return netfs_prepare_write_failed(subreq);
+		}
+	}
+
+	rc = server->ops->wait_mtu_credits(server, wsize, &wdata->subreq.max_len,
+					   &wdata->credits);
+	if (rc < 0) {
+		subreq->error = rc;
+		return netfs_prepare_write_failed(subreq);
 	}
 
-	rcu_read_unlock();
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	if (server->smbd_conn)
+		subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
+#endif
 }
 
 /*
- * Completion of write to server.
+ * Issue a subrequest to upload to the server.
  */
-void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len)
+static void cifs_issue_write(struct netfs_io_subrequest *subreq)
 {
-	struct address_space *mapping = inode->i_mapping;
-	struct folio *folio;
-	pgoff_t end;
+	struct cifs_io_subrequest *wdata =
+		container_of(subreq, struct cifs_io_subrequest, subreq);
+	struct cifs_sb_info *sbi = CIFS_SB(subreq->rreq->inode->i_sb);
+	int rc;
 
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
+	if (cifs_forced_shutdown(sbi)) {
+		rc = -EIO;
+		goto fail;
+	}
 
-	if (!len)
-		return;
+	rc = adjust_credits(wdata->server, &wdata->credits, wdata->subreq.len);
+	if (rc)
+		goto fail;
 
-	rcu_read_lock();
+	rc = -EAGAIN;
+	if (wdata->req->cfile->invalidHandle)
+		goto fail;
 
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (xas_retry(&xas, folio))
-			continue;
-		if (!folio_test_writeback(folio)) {
-			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio->index, end);
-			continue;
-		}
+	wdata->server->ops->async_writev(wdata);
+out:
+	return;
+
+fail:
+	if (rc == -EAGAIN)
+		trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
+	else
+		trace_netfs_sreq(subreq, netfs_sreq_trace_fail);
+	add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
+	cifs_write_subrequest_terminated(wdata, rc, false);
+	goto out;
+}
+
+/*
+ * Split the read up according to how many credits we can get for each piece.
+ * It's okay to sleep here if we need to wait for more credit to become
+ * available.
+ *
+ * We also choose the server and allocate an operation ID to be cleaned up
+ * later.
+ */
+static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct TCP_Server_Info *server;
+	struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
+	struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+	size_t rsize = 0;
+	int rc;
+
+	rdata->xid = get_xid();
+	rdata->have_xid = true;
+
+	server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
+	rdata->server = server;
+
+	if (cifs_sb->ctx->rsize == 0)
+		cifs_sb->ctx->rsize =
+			server->ops->negotiate_rsize(tlink_tcon(req->cfile->tlink),
+						     cifs_sb->ctx);
 
-		folio_detach_private(folio);
-		folio_end_writeback(folio);
+
+	rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize,
+					   &rdata->credits);
+	if (rc) {
+		subreq->error = rc;
+		return false;
 	}
 
-	rcu_read_unlock();
+	subreq->len = min_t(size_t, subreq->len, rsize);
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	if (server->smbd_conn)
+		subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
+#endif
+	return true;
 }
 
 /*
- * Failure of write to server.
+ * Issue a read operation on behalf of the netfs helper functions.  We're asked
+ * to make a read of a certain size at a point in the file.  We are permitted
+ * to only read a portion of that, but as long as we read something, the netfs
+ * helper will call us again so that we can issue another read.
  */
-void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len)
+static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
 {
-	struct address_space *mapping = inode->i_mapping;
-	struct folio *folio;
-	pgoff_t end;
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
+	struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+	pid_t pid;
+	int rc = 0;
 
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+		pid = req->cfile->pid;
+	else
+		pid = current->tgid; // Ummm...  This may be a workqueue
 
-	if (!len)
-		return;
+	cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n",
+		 __func__, rreq->debug_id, subreq->debug_index, rreq->mapping,
+		 subreq->transferred, subreq->len);
 
-	rcu_read_lock();
+	if (req->cfile->invalidHandle) {
+		do {
+			rc = cifs_reopen_file(req->cfile, true);
+		} while (rc == -EAGAIN);
+		if (rc)
+			goto out;
+	}
 
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (xas_retry(&xas, folio))
-			continue;
-		if (!folio_test_writeback(folio)) {
-			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio->index, end);
-			continue;
-		}
+	__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	rdata->pid = pid;
 
-		folio_set_error(folio);
-		folio_end_writeback(folio);
+	rc = adjust_credits(rdata->server, &rdata->credits, rdata->subreq.len);
+	if (!rc) {
+		if (rdata->req->cfile->invalidHandle)
+			rc = -EAGAIN;
+		else
+			rc = rdata->server->ops->async_readv(rdata);
 	}
 
-	rcu_read_unlock();
+out:
+	if (rc)
+		netfs_subreq_terminated(subreq, rc, false);
 }
 
 /*
- * Redirty pages after a temporary failure.
+ * Writeback calls this when it finds a folio that needs uploading.  This isn't
+ * called if writeback only has copy-to-cache to deal with.
  */
-void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int len)
+static void cifs_begin_writeback(struct netfs_io_request *wreq)
 {
-	struct address_space *mapping = inode->i_mapping;
-	struct folio *folio;
-	pgoff_t end;
-
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
+	struct cifs_io_request *req = container_of(wreq, struct cifs_io_request, rreq);
+	int ret;
 
-	if (!len)
+	ret = cifs_get_writable_file(CIFS_I(wreq->inode), FIND_WR_ANY, &req->cfile);
+	if (ret) {
+		cifs_dbg(VFS, "No writable handle in writepages ret=%d\n", ret);
 		return;
+	}
 
-	rcu_read_lock();
+	wreq->io_streams[0].avail = true;
+}
 
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (!folio_test_writeback(folio)) {
-			WARN_ONCE(1, "bad %x @%llx page %lx %lx\n",
-				  len, start, folio->index, end);
-			continue;
-		}
+/*
+ * Initialise a request.
+ */
+static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
+{
+	struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+	struct cifsFileInfo *open_file = NULL;
 
-		filemap_dirty_folio(folio->mapping, folio);
-		folio_end_writeback(folio);
+	rreq->rsize = cifs_sb->ctx->rsize;
+	rreq->wsize = cifs_sb->ctx->wsize;
+
+	if (file) {
+		open_file = file->private_data;
+		rreq->netfs_priv = file->private_data;
+		req->cfile = cifsFileInfo_get(open_file);
+	} else if (rreq->origin != NETFS_WRITEBACK) {
+		WARN_ON_ONCE(1);
+		return -EIO;
 	}
 
-	rcu_read_unlock();
+	return 0;
 }
 
 /*
+ * Expand the size of a readahead to the size of the rsize, if at least as
+ * large as a page, allowing for the possibility that rsize is not pow-2
+ * aligned.
+ */
+static void cifs_expand_readahead(struct netfs_io_request *rreq)
+{
+	unsigned int rsize = rreq->rsize;
+	loff_t misalignment, i_size = i_size_read(rreq->inode);
+
+	if (rsize < PAGE_SIZE)
+		return;
+
+	if (rsize < INT_MAX)
+		rsize = roundup_pow_of_two(rsize);
+	else
+		rsize = ((unsigned int)INT_MAX + 1) / 2;
+
+	misalignment = rreq->start & (rsize - 1);
+	if (misalignment) {
+		rreq->start -= misalignment;
+		rreq->len += misalignment;
+	}
+
+	rreq->len = round_up(rreq->len, rsize);
+	if (rreq->start < i_size && rreq->len > i_size - rreq->start)
+		rreq->len = i_size - rreq->start;
+}
+
+/*
+ * Completion of a request operation.
+ */
+static void cifs_rreq_done(struct netfs_io_request *rreq)
+{
+	struct timespec64 atime, mtime;
+	struct inode *inode = rreq->inode;
+
+	/* we do not want atime to be less than mtime, it broke some apps */
+	atime = inode_set_atime_to_ts(inode, current_time(inode));
+	mtime = inode_get_mtime(inode);
+	if (timespec64_compare(&atime, &mtime))
+		inode_set_atime_to_ts(inode, inode_get_mtime(inode));
+}
+
+static void cifs_post_modify(struct inode *inode)
+{
+	/* Indication to update ctime and mtime as close is deferred */
+	set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags);
+}
+
+static void cifs_free_request(struct netfs_io_request *rreq)
+{
+	struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq);
+
+	if (req->cfile)
+		cifsFileInfo_put(req->cfile);
+}
+
+static void cifs_free_subrequest(struct netfs_io_subrequest *subreq)
+{
+	struct cifs_io_subrequest *rdata =
+		container_of(subreq, struct cifs_io_subrequest, subreq);
+	int rc = subreq->error;
+
+	if (rdata->subreq.source == NETFS_DOWNLOAD_FROM_SERVER) {
+#ifdef CONFIG_CIFS_SMB_DIRECT
+		if (rdata->mr) {
+			smbd_deregister_mr(rdata->mr);
+			rdata->mr = NULL;
+		}
+#endif
+	}
+
+	add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
+	if (rdata->have_xid)
+		free_xid(rdata->xid);
+}
+
+const struct netfs_request_ops cifs_req_ops = {
+	.request_pool		= &cifs_io_request_pool,
+	.subrequest_pool	= &cifs_io_subrequest_pool,
+	.init_request		= cifs_init_request,
+	.free_request		= cifs_free_request,
+	.free_subrequest	= cifs_free_subrequest,
+	.expand_readahead	= cifs_expand_readahead,
+	.clamp_length		= cifs_clamp_length,
+	.issue_read		= cifs_req_issue_read,
+	.done			= cifs_rreq_done,
+	.post_modify		= cifs_post_modify,
+	.begin_writeback	= cifs_begin_writeback,
+	.prepare_write		= cifs_prepare_write,
+	.issue_write		= cifs_issue_write,
+};
+
+/*
  * Mark as invalid, all open files on tree connections since they
  * were closed when session to server was lost.
  */
@@ -2207,102 +2397,20 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 	return rc;
 }
 
-/*
- * update the file size (if needed) after a write. Should be called with
- * the inode->i_lock held
- */
-void
-cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
-		      unsigned int bytes_written)
-{
-	loff_t end_of_write = offset + bytes_written;
-
-	if (end_of_write > cifsi->netfs.remote_i_size)
-		netfs_resize_file(&cifsi->netfs, end_of_write, true);
-}
-
-static ssize_t
-cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
-	   size_t write_size, loff_t *offset)
+void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result,
+				      bool was_async)
 {
-	int rc = 0;
-	unsigned int bytes_written = 0;
-	unsigned int total_written;
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
-	unsigned int xid;
-	struct dentry *dentry = open_file->dentry;
-	struct cifsInodeInfo *cifsi = CIFS_I(d_inode(dentry));
-	struct cifs_io_parms io_parms = {0};
+	struct netfs_io_request *wreq = wdata->rreq;
+	loff_t new_server_eof;
 
-	cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n",
-		 write_size, *offset, dentry);
+	if (result > 0) {
+		new_server_eof = wdata->subreq.start + wdata->subreq.transferred + result;
 
-	tcon = tlink_tcon(open_file->tlink);
-	server = tcon->ses->server;
-
-	if (!server->ops->sync_write)
-		return -ENOSYS;
-
-	xid = get_xid();
-
-	for (total_written = 0; write_size > total_written;
-	     total_written += bytes_written) {
-		rc = -EAGAIN;
-		while (rc == -EAGAIN) {
-			struct kvec iov[2];
-			unsigned int len;
-
-			if (open_file->invalidHandle) {
-				/* we could deadlock if we called
-				   filemap_fdatawait from here so tell
-				   reopen_file not to flush data to
-				   server now */
-				rc = cifs_reopen_file(open_file, false);
-				if (rc != 0)
-					break;
-			}
-
-			len = min(server->ops->wp_retry_size(d_inode(dentry)),
-				  (unsigned int)write_size - total_written);
-			/* iov[0] is reserved for smb header */
-			iov[1].iov_base = (char *)write_data + total_written;
-			iov[1].iov_len = len;
-			io_parms.pid = pid;
-			io_parms.tcon = tcon;
-			io_parms.offset = *offset;
-			io_parms.length = len;
-			rc = server->ops->sync_write(xid, &open_file->fid,
-					&io_parms, &bytes_written, iov, 1);
-		}
-		if (rc || (bytes_written == 0)) {
-			if (total_written)
-				break;
-			else {
-				free_xid(xid);
-				return rc;
-			}
-		} else {
-			spin_lock(&d_inode(dentry)->i_lock);
-			cifs_update_eof(cifsi, *offset, bytes_written);
-			spin_unlock(&d_inode(dentry)->i_lock);
-			*offset += bytes_written;
-		}
+		if (new_server_eof > netfs_inode(wreq->inode)->remote_i_size)
+			netfs_resize_file(netfs_inode(wreq->inode), new_server_eof, true);
 	}
 
-	cifs_stats_bytes_written(tcon, total_written);
-
-	if (total_written > 0) {
-		spin_lock(&d_inode(dentry)->i_lock);
-		if (*offset > d_inode(dentry)->i_size) {
-			i_size_write(d_inode(dentry), *offset);
-			d_inode(dentry)->i_blocks = (512 - 1 + *offset) >> 9;
-		}
-		spin_unlock(&d_inode(dentry)->i_lock);
-	}
-	mark_inode_dirty_sync(d_inode(dentry));
-	free_xid(xid);
-	return total_written;
+	netfs_write_subrequest_terminated(&wdata->subreq, result, was_async);
 }
 
 struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
@@ -2509,737 +2617,9 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 	return -ENOENT;
 }
 
-void
-cifs_writedata_release(struct kref *refcount)
-{
-	struct cifs_writedata *wdata = container_of(refcount,
-					struct cifs_writedata, refcount);
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (wdata->mr) {
-		smbd_deregister_mr(wdata->mr);
-		wdata->mr = NULL;
-	}
-#endif
-
-	if (wdata->cfile)
-		cifsFileInfo_put(wdata->cfile);
-
-	kfree(wdata);
-}
-
-/*
- * Write failed with a retryable error. Resend the write request. It's also
- * possible that the page was redirtied so re-clean the page.
- */
-static void
-cifs_writev_requeue(struct cifs_writedata *wdata)
-{
-	int rc = 0;
-	struct inode *inode = d_inode(wdata->cfile->dentry);
-	struct TCP_Server_Info *server;
-	unsigned int rest_len = wdata->bytes;
-	loff_t fpos = wdata->offset;
-
-	server = tlink_tcon(wdata->cfile->tlink)->ses->server;
-	do {
-		struct cifs_writedata *wdata2;
-		unsigned int wsize, cur_len;
-
-		wsize = server->ops->wp_retry_size(inode);
-		if (wsize < rest_len) {
-			if (wsize < PAGE_SIZE) {
-				rc = -EOPNOTSUPP;
-				break;
-			}
-			cur_len = min(round_down(wsize, PAGE_SIZE), rest_len);
-		} else {
-			cur_len = rest_len;
-		}
-
-		wdata2 = cifs_writedata_alloc(cifs_writev_complete);
-		if (!wdata2) {
-			rc = -ENOMEM;
-			break;
-		}
-
-		wdata2->sync_mode = wdata->sync_mode;
-		wdata2->offset	= fpos;
-		wdata2->bytes	= cur_len;
-		wdata2->iter	= wdata->iter;
-
-		iov_iter_advance(&wdata2->iter, fpos - wdata->offset);
-		iov_iter_truncate(&wdata2->iter, wdata2->bytes);
-
-		if (iov_iter_is_xarray(&wdata2->iter))
-			/* Check for pages having been redirtied and clean
-			 * them.  We can do this by walking the xarray.  If
-			 * it's not an xarray, then it's a DIO and we shouldn't
-			 * be mucking around with the page bits.
-			 */
-			cifs_undirty_folios(inode, fpos, cur_len);
-
-		rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY,
-					    &wdata2->cfile);
-		if (!wdata2->cfile) {
-			cifs_dbg(VFS, "No writable handle to retry writepages rc=%d\n",
-				 rc);
-			if (!is_retryable_error(rc))
-				rc = -EBADF;
-		} else {
-			wdata2->pid = wdata2->cfile->pid;
-			rc = server->ops->async_writev(wdata2,
-						       cifs_writedata_release);
-		}
-
-		kref_put(&wdata2->refcount, cifs_writedata_release);
-		if (rc) {
-			if (is_retryable_error(rc))
-				continue;
-			fpos += cur_len;
-			rest_len -= cur_len;
-			break;
-		}
-
-		fpos += cur_len;
-		rest_len -= cur_len;
-	} while (rest_len > 0);
-
-	/* Clean up remaining pages from the original wdata */
-	if (iov_iter_is_xarray(&wdata->iter))
-		cifs_pages_write_failed(inode, fpos, rest_len);
-
-	if (rc != 0 && !is_retryable_error(rc))
-		mapping_set_error(inode->i_mapping, rc);
-	kref_put(&wdata->refcount, cifs_writedata_release);
-}
-
-void
-cifs_writev_complete(struct work_struct *work)
-{
-	struct cifs_writedata *wdata = container_of(work,
-						struct cifs_writedata, work);
-	struct inode *inode = d_inode(wdata->cfile->dentry);
-
-	if (wdata->result == 0) {
-		spin_lock(&inode->i_lock);
-		cifs_update_eof(CIFS_I(inode), wdata->offset, wdata->bytes);
-		spin_unlock(&inode->i_lock);
-		cifs_stats_bytes_written(tlink_tcon(wdata->cfile->tlink),
-					 wdata->bytes);
-	} else if (wdata->sync_mode == WB_SYNC_ALL && wdata->result == -EAGAIN)
-		return cifs_writev_requeue(wdata);
-
-	if (wdata->result == -EAGAIN)
-		cifs_pages_write_redirty(inode, wdata->offset, wdata->bytes);
-	else if (wdata->result < 0)
-		cifs_pages_write_failed(inode, wdata->offset, wdata->bytes);
-	else
-		cifs_pages_written_back(inode, wdata->offset, wdata->bytes);
-
-	if (wdata->result != -EAGAIN)
-		mapping_set_error(inode->i_mapping, wdata->result);
-	kref_put(&wdata->refcount, cifs_writedata_release);
-}
-
-struct cifs_writedata *cifs_writedata_alloc(work_func_t complete)
-{
-	struct cifs_writedata *wdata;
-
-	wdata = kzalloc(sizeof(*wdata), GFP_NOFS);
-	if (wdata != NULL) {
-		kref_init(&wdata->refcount);
-		INIT_LIST_HEAD(&wdata->list);
-		init_completion(&wdata->done);
-		INIT_WORK(&wdata->work, complete);
-	}
-	return wdata;
-}
-
-static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
-{
-	struct address_space *mapping = page->mapping;
-	loff_t offset = (loff_t)page->index << PAGE_SHIFT;
-	char *write_data;
-	int rc = -EFAULT;
-	int bytes_written = 0;
-	struct inode *inode;
-	struct cifsFileInfo *open_file;
-
-	if (!mapping || !mapping->host)
-		return -EFAULT;
-
-	inode = page->mapping->host;
-
-	offset += (loff_t)from;
-	write_data = kmap(page);
-	write_data += from;
-
-	if ((to > PAGE_SIZE) || (from > to)) {
-		kunmap(page);
-		return -EIO;
-	}
-
-	/* racing with truncate? */
-	if (offset > mapping->host->i_size) {
-		kunmap(page);
-		return 0; /* don't care */
-	}
-
-	/* check to make sure that we are not extending the file */
-	if (mapping->host->i_size - offset < (loff_t)to)
-		to = (unsigned)(mapping->host->i_size - offset);
-
-	rc = cifs_get_writable_file(CIFS_I(mapping->host), FIND_WR_ANY,
-				    &open_file);
-	if (!rc) {
-		bytes_written = cifs_write(open_file, open_file->pid,
-					   write_data, to - from, &offset);
-		cifsFileInfo_put(open_file);
-		/* Does mm or vfs already set times? */
-		simple_inode_init_ts(inode);
-		if ((bytes_written > 0) && (offset))
-			rc = 0;
-		else if (bytes_written < 0)
-			rc = bytes_written;
-		else
-			rc = -EFAULT;
-	} else {
-		cifs_dbg(FYI, "No writable handle for write page rc=%d\n", rc);
-		if (!is_retryable_error(rc))
-			rc = -EIO;
-	}
-
-	kunmap(page);
-	return rc;
-}
-
 /*
- * Extend the region to be written back to include subsequent contiguously
- * dirty pages if possible, but don't sleep while doing so.
+ * Flush data on a strict file.
  */
-static void cifs_extend_writeback(struct address_space *mapping,
-				  struct xa_state *xas,
-				  long *_count,
-				  loff_t start,
-				  int max_pages,
-				  loff_t max_len,
-				  size_t *_len)
-{
-	struct folio_batch batch;
-	struct folio *folio;
-	unsigned int nr_pages;
-	pgoff_t index = (start + *_len) / PAGE_SIZE;
-	size_t len;
-	bool stop = true;
-	unsigned int i;
-
-	folio_batch_init(&batch);
-
-	do {
-		/* Firstly, we gather up a batch of contiguous dirty pages
-		 * under the RCU read lock - but we can't clear the dirty flags
-		 * there if any of those pages are mapped.
-		 */
-		rcu_read_lock();
-
-		xas_for_each(xas, folio, ULONG_MAX) {
-			stop = true;
-			if (xas_retry(xas, folio))
-				continue;
-			if (xa_is_value(folio))
-				break;
-			if (folio->index != index) {
-				xas_reset(xas);
-				break;
-			}
-
-			if (!folio_try_get_rcu(folio)) {
-				xas_reset(xas);
-				continue;
-			}
-			nr_pages = folio_nr_pages(folio);
-			if (nr_pages > max_pages) {
-				xas_reset(xas);
-				break;
-			}
-
-			/* Has the page moved or been split? */
-			if (unlikely(folio != xas_reload(xas))) {
-				folio_put(folio);
-				xas_reset(xas);
-				break;
-			}
-
-			if (!folio_trylock(folio)) {
-				folio_put(folio);
-				xas_reset(xas);
-				break;
-			}
-			if (!folio_test_dirty(folio) ||
-			    folio_test_writeback(folio)) {
-				folio_unlock(folio);
-				folio_put(folio);
-				xas_reset(xas);
-				break;
-			}
-
-			max_pages -= nr_pages;
-			len = folio_size(folio);
-			stop = false;
-
-			index += nr_pages;
-			*_count -= nr_pages;
-			*_len += len;
-			if (max_pages <= 0 || *_len >= max_len || *_count <= 0)
-				stop = true;
-
-			if (!folio_batch_add(&batch, folio))
-				break;
-			if (stop)
-				break;
-		}
-
-		xas_pause(xas);
-		rcu_read_unlock();
-
-		/* Now, if we obtained any pages, we can shift them to being
-		 * writable and mark them for caching.
-		 */
-		if (!folio_batch_count(&batch))
-			break;
-
-		for (i = 0; i < folio_batch_count(&batch); i++) {
-			folio = batch.folios[i];
-			/* The folio should be locked, dirty and not undergoing
-			 * writeback from the loop above.
-			 */
-			if (!folio_clear_dirty_for_io(folio))
-				WARN_ON(1);
-			folio_start_writeback(folio);
-			folio_unlock(folio);
-		}
-
-		folio_batch_release(&batch);
-		cond_resched();
-	} while (!stop);
-}
-
-/*
- * Write back the locked page and any subsequent non-locked dirty pages.
- */
-static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping,
-						 struct writeback_control *wbc,
-						 struct xa_state *xas,
-						 struct folio *folio,
-						 unsigned long long start,
-						 unsigned long long end)
-{
-	struct inode *inode = mapping->host;
-	struct TCP_Server_Info *server;
-	struct cifs_writedata *wdata;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	struct cifs_credits credits_on_stack;
-	struct cifs_credits *credits = &credits_on_stack;
-	struct cifsFileInfo *cfile = NULL;
-	unsigned long long i_size = i_size_read(inode), max_len;
-	unsigned int xid, wsize;
-	size_t len = folio_size(folio);
-	long count = wbc->nr_to_write;
-	int rc;
-
-	/* The folio should be locked, dirty and not undergoing writeback. */
-	if (!folio_clear_dirty_for_io(folio))
-		WARN_ON_ONCE(1);
-	folio_start_writeback(folio);
-
-	count -= folio_nr_pages(folio);
-
-	xid = get_xid();
-	server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses);
-
-	rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile);
-	if (rc) {
-		cifs_dbg(VFS, "No writable handle in writepages rc=%d\n", rc);
-		goto err_xid;
-	}
-
-	rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize,
-					   &wsize, credits);
-	if (rc != 0)
-		goto err_close;
-
-	wdata = cifs_writedata_alloc(cifs_writev_complete);
-	if (!wdata) {
-		rc = -ENOMEM;
-		goto err_uncredit;
-	}
-
-	wdata->sync_mode = wbc->sync_mode;
-	wdata->offset = folio_pos(folio);
-	wdata->pid = cfile->pid;
-	wdata->credits = credits_on_stack;
-	wdata->cfile = cfile;
-	wdata->server = server;
-	cfile = NULL;
-
-	/* Find all consecutive lockable dirty pages that have contiguous
-	 * written regions, stopping when we find a page that is not
-	 * immediately lockable, is not dirty or is missing, or we reach the
-	 * end of the range.
-	 */
-	if (start < i_size) {
-		/* Trim the write to the EOF; the extra data is ignored.  Also
-		 * put an upper limit on the size of a single storedata op.
-		 */
-		max_len = wsize;
-		max_len = min_t(unsigned long long, max_len, end - start + 1);
-		max_len = min_t(unsigned long long, max_len, i_size - start);
-
-		if (len < max_len) {
-			int max_pages = INT_MAX;
-
-#ifdef CONFIG_CIFS_SMB_DIRECT
-			if (server->smbd_conn)
-				max_pages = server->smbd_conn->max_frmr_depth;
-#endif
-			max_pages -= folio_nr_pages(folio);
-
-			if (max_pages > 0)
-				cifs_extend_writeback(mapping, xas, &count, start,
-						      max_pages, max_len, &len);
-		}
-	}
-	len = min_t(unsigned long long, len, i_size - start);
-
-	/* We now have a contiguous set of dirty pages, each with writeback
-	 * set; the first page is still locked at this point, but all the rest
-	 * have been unlocked.
-	 */
-	folio_unlock(folio);
-	wdata->bytes = len;
-
-	if (start < i_size) {
-		iov_iter_xarray(&wdata->iter, ITER_SOURCE, &mapping->i_pages,
-				start, len);
-
-		rc = adjust_credits(wdata->server, &wdata->credits, wdata->bytes);
-		if (rc)
-			goto err_wdata;
-
-		if (wdata->cfile->invalidHandle)
-			rc = -EAGAIN;
-		else
-			rc = wdata->server->ops->async_writev(wdata,
-							      cifs_writedata_release);
-		if (rc >= 0) {
-			kref_put(&wdata->refcount, cifs_writedata_release);
-			goto err_close;
-		}
-	} else {
-		/* The dirty region was entirely beyond the EOF. */
-		cifs_pages_written_back(inode, start, len);
-		rc = 0;
-	}
-
-err_wdata:
-	kref_put(&wdata->refcount, cifs_writedata_release);
-err_uncredit:
-	add_credits_and_wake_if(server, credits, 0);
-err_close:
-	if (cfile)
-		cifsFileInfo_put(cfile);
-err_xid:
-	free_xid(xid);
-	if (rc == 0) {
-		wbc->nr_to_write = count;
-		rc = len;
-	} else if (is_retryable_error(rc)) {
-		cifs_pages_write_redirty(inode, start, len);
-	} else {
-		cifs_pages_write_failed(inode, start, len);
-		mapping_set_error(mapping, rc);
-	}
-	/* Indication to update ctime and mtime as close is deferred */
-	set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags);
-	return rc;
-}
-
-/*
- * write a region of pages back to the server
- */
-static ssize_t cifs_writepages_begin(struct address_space *mapping,
-				     struct writeback_control *wbc,
-				     struct xa_state *xas,
-				     unsigned long long *_start,
-				     unsigned long long end)
-{
-	struct folio *folio;
-	unsigned long long start = *_start;
-	ssize_t ret;
-	int skips = 0;
-
-search_again:
-	/* Find the first dirty page. */
-	rcu_read_lock();
-
-	for (;;) {
-		folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY);
-		if (xas_retry(xas, folio) || xa_is_value(folio))
-			continue;
-		if (!folio)
-			break;
-
-		if (!folio_try_get_rcu(folio)) {
-			xas_reset(xas);
-			continue;
-		}
-
-		if (unlikely(folio != xas_reload(xas))) {
-			folio_put(folio);
-			xas_reset(xas);
-			continue;
-		}
-
-		xas_pause(xas);
-		break;
-	}
-	rcu_read_unlock();
-	if (!folio)
-		return 0;
-
-	start = folio_pos(folio); /* May regress with THPs */
-
-	/* At this point we hold neither the i_pages lock nor the page lock:
-	 * the page may be truncated or invalidated (changing page->mapping to
-	 * NULL), or even swizzled back from swapper_space to tmpfs file
-	 * mapping
-	 */
-lock_again:
-	if (wbc->sync_mode != WB_SYNC_NONE) {
-		ret = folio_lock_killable(folio);
-		if (ret < 0)
-			return ret;
-	} else {
-		if (!folio_trylock(folio))
-			goto search_again;
-	}
-
-	if (folio->mapping != mapping ||
-	    !folio_test_dirty(folio)) {
-		start += folio_size(folio);
-		folio_unlock(folio);
-		goto search_again;
-	}
-
-	if (folio_test_writeback(folio) ||
-	    folio_test_fscache(folio)) {
-		folio_unlock(folio);
-		if (wbc->sync_mode != WB_SYNC_NONE) {
-			folio_wait_writeback(folio);
-#ifdef CONFIG_CIFS_FSCACHE
-			folio_wait_fscache(folio);
-#endif
-			goto lock_again;
-		}
-
-		start += folio_size(folio);
-		if (wbc->sync_mode == WB_SYNC_NONE) {
-			if (skips >= 5 || need_resched()) {
-				ret = 0;
-				goto out;
-			}
-			skips++;
-		}
-		goto search_again;
-	}
-
-	ret = cifs_write_back_from_locked_folio(mapping, wbc, xas, folio, start, end);
-out:
-	if (ret > 0)
-		*_start = start + ret;
-	return ret;
-}
-
-/*
- * Write a region of pages back to the server
- */
-static int cifs_writepages_region(struct address_space *mapping,
-				  struct writeback_control *wbc,
-				  unsigned long long *_start,
-				  unsigned long long end)
-{
-	ssize_t ret;
-
-	XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE);
-
-	do {
-		ret = cifs_writepages_begin(mapping, wbc, &xas, _start, end);
-		if (ret > 0 && wbc->nr_to_write > 0)
-			cond_resched();
-	} while (ret > 0 && wbc->nr_to_write > 0);
-
-	return ret > 0 ? 0 : ret;
-}
-
-/*
- * Write some of the pending data back to the server
- */
-static int cifs_writepages(struct address_space *mapping,
-			   struct writeback_control *wbc)
-{
-	loff_t start, end;
-	int ret;
-
-	/* We have to be careful as we can end up racing with setattr()
-	 * truncating the pagecache since the caller doesn't take a lock here
-	 * to prevent it.
-	 */
-
-	if (wbc->range_cyclic && mapping->writeback_index) {
-		start = mapping->writeback_index * PAGE_SIZE;
-		ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX);
-		if (ret < 0)
-			goto out;
-
-		if (wbc->nr_to_write <= 0) {
-			mapping->writeback_index = start / PAGE_SIZE;
-			goto out;
-		}
-
-		start = 0;
-		end = mapping->writeback_index * PAGE_SIZE;
-		mapping->writeback_index = 0;
-		ret = cifs_writepages_region(mapping, wbc, &start, end);
-		if (ret == 0)
-			mapping->writeback_index = start / PAGE_SIZE;
-	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
-		start = 0;
-		ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX);
-		if (wbc->nr_to_write > 0 && ret == 0)
-			mapping->writeback_index = start / PAGE_SIZE;
-	} else {
-		start = wbc->range_start;
-		ret = cifs_writepages_region(mapping, wbc, &start, wbc->range_end);
-	}
-
-out:
-	return ret;
-}
-
-static int
-cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
-{
-	int rc;
-	unsigned int xid;
-
-	xid = get_xid();
-/* BB add check for wbc flags */
-	get_page(page);
-	if (!PageUptodate(page))
-		cifs_dbg(FYI, "ppw - page not up to date\n");
-
-	/*
-	 * Set the "writeback" flag, and clear "dirty" in the radix tree.
-	 *
-	 * A writepage() implementation always needs to do either this,
-	 * or re-dirty the page with "redirty_page_for_writepage()" in
-	 * the case of a failure.
-	 *
-	 * Just unlocking the page will cause the radix tree tag-bits
-	 * to fail to update with the state of the page correctly.
-	 */
-	set_page_writeback(page);
-retry_write:
-	rc = cifs_partialpagewrite(page, 0, PAGE_SIZE);
-	if (is_retryable_error(rc)) {
-		if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN)
-			goto retry_write;
-		redirty_page_for_writepage(wbc, page);
-	} else if (rc != 0) {
-		SetPageError(page);
-		mapping_set_error(page->mapping, rc);
-	} else {
-		SetPageUptodate(page);
-	}
-	end_page_writeback(page);
-	put_page(page);
-	free_xid(xid);
-	return rc;
-}
-
-static int cifs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
-{
-	int rc;
-	struct inode *inode = mapping->host;
-	struct cifsFileInfo *cfile = file->private_data;
-	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
-	struct folio *folio = page_folio(page);
-	__u32 pid;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		pid = cfile->pid;
-	else
-		pid = current->tgid;
-
-	cifs_dbg(FYI, "write_end for page %p from pos %lld with %d bytes\n",
-		 page, pos, copied);
-
-	if (folio_test_checked(folio)) {
-		if (copied == len)
-			folio_mark_uptodate(folio);
-		folio_clear_checked(folio);
-	} else if (!folio_test_uptodate(folio) && copied == PAGE_SIZE)
-		folio_mark_uptodate(folio);
-
-	if (!folio_test_uptodate(folio)) {
-		char *page_data;
-		unsigned offset = pos & (PAGE_SIZE - 1);
-		unsigned int xid;
-
-		xid = get_xid();
-		/* this is probably better than directly calling
-		   partialpage_write since in this function the file handle is
-		   known which we might as well	leverage */
-		/* BB check if anything else missing out of ppw
-		   such as updating last write time */
-		page_data = kmap(page);
-		rc = cifs_write(cfile, pid, page_data + offset, copied, &pos);
-		/* if (rc < 0) should we set writebehind rc? */
-		kunmap(page);
-
-		free_xid(xid);
-	} else {
-		rc = copied;
-		pos += copied;
-		set_page_dirty(page);
-	}
-
-	if (rc > 0) {
-		spin_lock(&inode->i_lock);
-		if (pos > inode->i_size) {
-			loff_t additional_blocks = (512 - 1 + copied) >> 9;
-
-			i_size_write(inode, pos);
-			/*
-			 * Estimate new allocation size based on the amount written.
-			 * This will be updated from server on close (and on queryinfo)
-			 */
-			inode->i_blocks = min_t(blkcnt_t, (512 - 1 + pos) >> 9,
-						inode->i_blocks + additional_blocks);
-		}
-		spin_unlock(&inode->i_lock);
-	}
-
-	unlock_page(page);
-	put_page(page);
-	/* Indication to update ctime and mtime as close is deferred */
-	set_bit(CIFS_INO_MODIFIED_ATTR, &CIFS_I(inode)->flags);
-
-	return rc;
-}
-
 int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync)
 {
@@ -3294,6 +2674,9 @@ strict_fsync_exit:
 	return rc;
 }
 
+/*
+ * Flush data on a non-strict data.
+ */
 int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	unsigned int xid;
@@ -3360,481 +2743,6 @@ int cifs_flush(struct file *file, fl_owner_t id)
 	return rc;
 }
 
-static void
-cifs_uncached_writedata_release(struct kref *refcount)
-{
-	struct cifs_writedata *wdata = container_of(refcount,
-					struct cifs_writedata, refcount);
-
-	kref_put(&wdata->ctx->refcount, cifs_aio_ctx_release);
-	cifs_writedata_release(refcount);
-}
-
-static void collect_uncached_write_data(struct cifs_aio_ctx *ctx);
-
-static void
-cifs_uncached_writev_complete(struct work_struct *work)
-{
-	struct cifs_writedata *wdata = container_of(work,
-					struct cifs_writedata, work);
-	struct inode *inode = d_inode(wdata->cfile->dentry);
-	struct cifsInodeInfo *cifsi = CIFS_I(inode);
-
-	spin_lock(&inode->i_lock);
-	cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
-	if (cifsi->netfs.remote_i_size > inode->i_size)
-		i_size_write(inode, cifsi->netfs.remote_i_size);
-	spin_unlock(&inode->i_lock);
-
-	complete(&wdata->done);
-	collect_uncached_write_data(wdata->ctx);
-	/* the below call can possibly free the last ref to aio ctx */
-	kref_put(&wdata->refcount, cifs_uncached_writedata_release);
-}
-
-static int
-cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list,
-	struct cifs_aio_ctx *ctx)
-{
-	unsigned int wsize;
-	struct cifs_credits credits;
-	int rc;
-	struct TCP_Server_Info *server = wdata->server;
-
-	do {
-		if (wdata->cfile->invalidHandle) {
-			rc = cifs_reopen_file(wdata->cfile, false);
-			if (rc == -EAGAIN)
-				continue;
-			else if (rc)
-				break;
-		}
-
-
-		/*
-		 * Wait for credits to resend this wdata.
-		 * Note: we are attempting to resend the whole wdata not in
-		 * segments
-		 */
-		do {
-			rc = server->ops->wait_mtu_credits(server, wdata->bytes,
-						&wsize, &credits);
-			if (rc)
-				goto fail;
-
-			if (wsize < wdata->bytes) {
-				add_credits_and_wake_if(server, &credits, 0);
-				msleep(1000);
-			}
-		} while (wsize < wdata->bytes);
-		wdata->credits = credits;
-
-		rc = adjust_credits(server, &wdata->credits, wdata->bytes);
-
-		if (!rc) {
-			if (wdata->cfile->invalidHandle)
-				rc = -EAGAIN;
-			else {
-				wdata->replay = true;
-#ifdef CONFIG_CIFS_SMB_DIRECT
-				if (wdata->mr) {
-					wdata->mr->need_invalidate = true;
-					smbd_deregister_mr(wdata->mr);
-					wdata->mr = NULL;
-				}
-#endif
-				rc = server->ops->async_writev(wdata,
-					cifs_uncached_writedata_release);
-			}
-		}
-
-		/* If the write was successfully sent, we are done */
-		if (!rc) {
-			list_add_tail(&wdata->list, wdata_list);
-			return 0;
-		}
-
-		/* Roll back credits and retry if needed */
-		add_credits_and_wake_if(server, &wdata->credits, 0);
-	} while (rc == -EAGAIN);
-
-fail:
-	kref_put(&wdata->refcount, cifs_uncached_writedata_release);
-	return rc;
-}
-
-/*
- * Select span of a bvec iterator we're going to use.  Limit it by both maximum
- * size and maximum number of segments.
- */
-static size_t cifs_limit_bvec_subset(const struct iov_iter *iter, size_t max_size,
-				     size_t max_segs, unsigned int *_nsegs)
-{
-	const struct bio_vec *bvecs = iter->bvec;
-	unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
-	size_t len, span = 0, n = iter->count;
-	size_t skip = iter->iov_offset;
-
-	if (WARN_ON(!iov_iter_is_bvec(iter)) || n == 0)
-		return 0;
-
-	while (n && ix < nbv && skip) {
-		len = bvecs[ix].bv_len;
-		if (skip < len)
-			break;
-		skip -= len;
-		n -= len;
-		ix++;
-	}
-
-	while (n && ix < nbv) {
-		len = min3(n, bvecs[ix].bv_len - skip, max_size);
-		span += len;
-		max_size -= len;
-		nsegs++;
-		ix++;
-		if (max_size == 0 || nsegs >= max_segs)
-			break;
-		skip = 0;
-		n -= len;
-	}
-
-	*_nsegs = nsegs;
-	return span;
-}
-
-static int
-cifs_write_from_iter(loff_t fpos, size_t len, struct iov_iter *from,
-		     struct cifsFileInfo *open_file,
-		     struct cifs_sb_info *cifs_sb, struct list_head *wdata_list,
-		     struct cifs_aio_ctx *ctx)
-{
-	int rc = 0;
-	size_t cur_len, max_len;
-	struct cifs_writedata *wdata;
-	pid_t pid;
-	struct TCP_Server_Info *server;
-	unsigned int xid, max_segs = INT_MAX;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		pid = open_file->pid;
-	else
-		pid = current->tgid;
-
-	server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
-	xid = get_xid();
-
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (server->smbd_conn)
-		max_segs = server->smbd_conn->max_frmr_depth;
-#endif
-
-	do {
-		struct cifs_credits credits_on_stack;
-		struct cifs_credits *credits = &credits_on_stack;
-		unsigned int wsize, nsegs = 0;
-
-		if (signal_pending(current)) {
-			rc = -EINTR;
-			break;
-		}
-
-		if (open_file->invalidHandle) {
-			rc = cifs_reopen_file(open_file, false);
-			if (rc == -EAGAIN)
-				continue;
-			else if (rc)
-				break;
-		}
-
-		rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize,
-						   &wsize, credits);
-		if (rc)
-			break;
-
-		max_len = min_t(const size_t, len, wsize);
-		if (!max_len) {
-			rc = -EAGAIN;
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		cur_len = cifs_limit_bvec_subset(from, max_len, max_segs, &nsegs);
-		cifs_dbg(FYI, "write_from_iter len=%zx/%zx nsegs=%u/%lu/%u\n",
-			 cur_len, max_len, nsegs, from->nr_segs, max_segs);
-		if (cur_len == 0) {
-			rc = -EIO;
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		wdata = cifs_writedata_alloc(cifs_uncached_writev_complete);
-		if (!wdata) {
-			rc = -ENOMEM;
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		wdata->sync_mode = WB_SYNC_ALL;
-		wdata->offset	= (__u64)fpos;
-		wdata->cfile	= cifsFileInfo_get(open_file);
-		wdata->server	= server;
-		wdata->pid	= pid;
-		wdata->bytes	= cur_len;
-		wdata->credits	= credits_on_stack;
-		wdata->iter	= *from;
-		wdata->ctx	= ctx;
-		kref_get(&ctx->refcount);
-
-		iov_iter_truncate(&wdata->iter, cur_len);
-
-		rc = adjust_credits(server, &wdata->credits, wdata->bytes);
-
-		if (!rc) {
-			if (wdata->cfile->invalidHandle)
-				rc = -EAGAIN;
-			else
-				rc = server->ops->async_writev(wdata,
-					cifs_uncached_writedata_release);
-		}
-
-		if (rc) {
-			add_credits_and_wake_if(server, &wdata->credits, 0);
-			kref_put(&wdata->refcount,
-				 cifs_uncached_writedata_release);
-			if (rc == -EAGAIN)
-				continue;
-			break;
-		}
-
-		list_add_tail(&wdata->list, wdata_list);
-		iov_iter_advance(from, cur_len);
-		fpos += cur_len;
-		len -= cur_len;
-	} while (len > 0);
-
-	free_xid(xid);
-	return rc;
-}
-
-static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
-{
-	struct cifs_writedata *wdata, *tmp;
-	struct cifs_tcon *tcon;
-	struct cifs_sb_info *cifs_sb;
-	struct dentry *dentry = ctx->cfile->dentry;
-	ssize_t rc;
-
-	tcon = tlink_tcon(ctx->cfile->tlink);
-	cifs_sb = CIFS_SB(dentry->d_sb);
-
-	mutex_lock(&ctx->aio_mutex);
-
-	if (list_empty(&ctx->list)) {
-		mutex_unlock(&ctx->aio_mutex);
-		return;
-	}
-
-	rc = ctx->rc;
-	/*
-	 * Wait for and collect replies for any successful sends in order of
-	 * increasing offset. Once an error is hit, then return without waiting
-	 * for any more replies.
-	 */
-restart_loop:
-	list_for_each_entry_safe(wdata, tmp, &ctx->list, list) {
-		if (!rc) {
-			if (!try_wait_for_completion(&wdata->done)) {
-				mutex_unlock(&ctx->aio_mutex);
-				return;
-			}
-
-			if (wdata->result)
-				rc = wdata->result;
-			else
-				ctx->total_len += wdata->bytes;
-
-			/* resend call if it's a retryable error */
-			if (rc == -EAGAIN) {
-				struct list_head tmp_list;
-				struct iov_iter tmp_from = ctx->iter;
-
-				INIT_LIST_HEAD(&tmp_list);
-				list_del_init(&wdata->list);
-
-				if (ctx->direct_io)
-					rc = cifs_resend_wdata(
-						wdata, &tmp_list, ctx);
-				else {
-					iov_iter_advance(&tmp_from,
-						 wdata->offset - ctx->pos);
-
-					rc = cifs_write_from_iter(wdata->offset,
-						wdata->bytes, &tmp_from,
-						ctx->cfile, cifs_sb, &tmp_list,
-						ctx);
-
-					kref_put(&wdata->refcount,
-						cifs_uncached_writedata_release);
-				}
-
-				list_splice(&tmp_list, &ctx->list);
-				goto restart_loop;
-			}
-		}
-		list_del_init(&wdata->list);
-		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
-	}
-
-	cifs_stats_bytes_written(tcon, ctx->total_len);
-	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
-
-	ctx->rc = (rc == 0) ? ctx->total_len : rc;
-
-	mutex_unlock(&ctx->aio_mutex);
-
-	if (ctx->iocb && ctx->iocb->ki_complete)
-		ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
-	else
-		complete(&ctx->done);
-}
-
-static ssize_t __cifs_writev(
-	struct kiocb *iocb, struct iov_iter *from, bool direct)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t total_written = 0;
-	struct cifsFileInfo *cfile;
-	struct cifs_tcon *tcon;
-	struct cifs_sb_info *cifs_sb;
-	struct cifs_aio_ctx *ctx;
-	int rc;
-
-	rc = generic_write_checks(iocb, from);
-	if (rc <= 0)
-		return rc;
-
-	cifs_sb = CIFS_FILE_SB(file);
-	cfile = file->private_data;
-	tcon = tlink_tcon(cfile->tlink);
-
-	if (!tcon->ses->server->ops->async_writev)
-		return -ENOSYS;
-
-	ctx = cifs_aio_ctx_alloc();
-	if (!ctx)
-		return -ENOMEM;
-
-	ctx->cfile = cifsFileInfo_get(cfile);
-
-	if (!is_sync_kiocb(iocb))
-		ctx->iocb = iocb;
-
-	ctx->pos = iocb->ki_pos;
-	ctx->direct_io = direct;
-	ctx->nr_pinned_pages = 0;
-
-	if (user_backed_iter(from)) {
-		/*
-		 * Extract IOVEC/UBUF-type iterators to a BVEC-type iterator as
-		 * they contain references to the calling process's virtual
-		 * memory layout which won't be available in an async worker
-		 * thread.  This also takes a pin on every folio involved.
-		 */
-		rc = netfs_extract_user_iter(from, iov_iter_count(from),
-					     &ctx->iter, 0);
-		if (rc < 0) {
-			kref_put(&ctx->refcount, cifs_aio_ctx_release);
-			return rc;
-		}
-
-		ctx->nr_pinned_pages = rc;
-		ctx->bv = (void *)ctx->iter.bvec;
-		ctx->bv_need_unpin = iov_iter_extract_will_pin(from);
-	} else if ((iov_iter_is_bvec(from) || iov_iter_is_kvec(from)) &&
-		   !is_sync_kiocb(iocb)) {
-		/*
-		 * If the op is asynchronous, we need to copy the list attached
-		 * to a BVEC/KVEC-type iterator, but we assume that the storage
-		 * will be pinned by the caller; in any case, we may or may not
-		 * be able to pin the pages, so we don't try.
-		 */
-		ctx->bv = (void *)dup_iter(&ctx->iter, from, GFP_KERNEL);
-		if (!ctx->bv) {
-			kref_put(&ctx->refcount, cifs_aio_ctx_release);
-			return -ENOMEM;
-		}
-	} else {
-		/*
-		 * Otherwise, we just pass the iterator down as-is and rely on
-		 * the caller to make sure the pages referred to by the
-		 * iterator don't evaporate.
-		 */
-		ctx->iter = *from;
-	}
-
-	ctx->len = iov_iter_count(&ctx->iter);
-
-	/* grab a lock here due to read response handlers can access ctx */
-	mutex_lock(&ctx->aio_mutex);
-
-	rc = cifs_write_from_iter(iocb->ki_pos, ctx->len, &ctx->iter,
-				  cfile, cifs_sb, &ctx->list, ctx);
-
-	/*
-	 * If at least one write was successfully sent, then discard any rc
-	 * value from the later writes. If the other write succeeds, then
-	 * we'll end up returning whatever was written. If it fails, then
-	 * we'll get a new rc value from that.
-	 */
-	if (!list_empty(&ctx->list))
-		rc = 0;
-
-	mutex_unlock(&ctx->aio_mutex);
-
-	if (rc) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return rc;
-	}
-
-	if (!is_sync_kiocb(iocb)) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return -EIOCBQUEUED;
-	}
-
-	rc = wait_for_completion_killable(&ctx->done);
-	if (rc) {
-		mutex_lock(&ctx->aio_mutex);
-		ctx->rc = rc = -EINTR;
-		total_written = ctx->total_len;
-		mutex_unlock(&ctx->aio_mutex);
-	} else {
-		rc = ctx->rc;
-		total_written = ctx->total_len;
-	}
-
-	kref_put(&ctx->refcount, cifs_aio_ctx_release);
-
-	if (unlikely(!total_written))
-		return rc;
-
-	iocb->ki_pos += total_written;
-	return total_written;
-}
-
-ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-
-	cifs_revalidate_mapping(file->f_inode);
-	return __cifs_writev(iocb, from, true);
-}
-
-ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
-{
-	return __cifs_writev(iocb, from, false);
-}
-
 static ssize_t
 cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -3845,7 +2753,10 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
 	ssize_t rc;
 
-	inode_lock(inode);
+	rc = netfs_start_io_write(inode);
+	if (rc < 0)
+		return rc;
+
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents writing.
@@ -3859,13 +2770,12 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
 				     server->vals->exclusive_lock_type, 0,
 				     NULL, CIFS_WRITE_OP))
-		rc = __generic_file_write_iter(iocb, from);
+		rc = netfs_buffered_write_iter_locked(iocb, from, NULL);
 	else
 		rc = -EACCES;
 out:
 	up_read(&cinode->lock_sem);
-	inode_unlock(inode);
-
+	netfs_end_io_write(inode);
 	if (rc > 0)
 		rc = generic_write_sync(iocb, rc);
 	return rc;
@@ -3888,9 +2798,9 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 
 	if (CIFS_CACHE_WRITE(cinode)) {
 		if (cap_unix(tcon->ses) &&
-		(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
-		  && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
-			written = generic_file_write_iter(iocb, from);
+		    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
+		    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+			written = netfs_file_write_iter(iocb, from);
 			goto out;
 		}
 		written = cifs_writev(iocb, from);
@@ -3902,7 +2812,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 	 * affected pages because it may cause a error with mandatory locks on
 	 * these pages but not on the region from pos to ppos+len-1.
 	 */
-	written = cifs_user_writev(iocb, from);
+	written = netfs_file_write_iter(iocb, from);
 	if (CIFS_CACHE_READ(cinode)) {
 		/*
 		 * We have read level caching and we have just sent a write
@@ -3921,449 +2831,55 @@ out:
 	return written;
 }
 
-static struct cifs_readdata *cifs_readdata_alloc(work_func_t complete)
-{
-	struct cifs_readdata *rdata;
-
-	rdata = kzalloc(sizeof(*rdata), GFP_KERNEL);
-	if (rdata) {
-		kref_init(&rdata->refcount);
-		INIT_LIST_HEAD(&rdata->list);
-		init_completion(&rdata->done);
-		INIT_WORK(&rdata->work, complete);
-	}
-
-	return rdata;
-}
-
-void
-cifs_readdata_release(struct kref *refcount)
-{
-	struct cifs_readdata *rdata = container_of(refcount,
-					struct cifs_readdata, refcount);
-
-	if (rdata->ctx)
-		kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release);
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (rdata->mr) {
-		smbd_deregister_mr(rdata->mr);
-		rdata->mr = NULL;
-	}
-#endif
-	if (rdata->cfile)
-		cifsFileInfo_put(rdata->cfile);
-
-	kfree(rdata);
-}
-
-static void collect_uncached_read_data(struct cifs_aio_ctx *ctx);
-
-static void
-cifs_uncached_readv_complete(struct work_struct *work)
-{
-	struct cifs_readdata *rdata = container_of(work,
-						struct cifs_readdata, work);
-
-	complete(&rdata->done);
-	collect_uncached_read_data(rdata->ctx);
-	/* the below call can possibly free the last ref to aio ctx */
-	kref_put(&rdata->refcount, cifs_readdata_release);
-}
-
-static int cifs_resend_rdata(struct cifs_readdata *rdata,
-			struct list_head *rdata_list,
-			struct cifs_aio_ctx *ctx)
+ssize_t cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	unsigned int rsize;
-	struct cifs_credits credits;
-	int rc;
-	struct TCP_Server_Info *server;
-
-	/* XXX: should we pick a new channel here? */
-	server = rdata->server;
-
-	do {
-		if (rdata->cfile->invalidHandle) {
-			rc = cifs_reopen_file(rdata->cfile, true);
-			if (rc == -EAGAIN)
-				continue;
-			else if (rc)
-				break;
-		}
-
-		/*
-		 * Wait for credits to resend this rdata.
-		 * Note: we are attempting to resend the whole rdata not in
-		 * segments
-		 */
-		do {
-			rc = server->ops->wait_mtu_credits(server, rdata->bytes,
-						&rsize, &credits);
-
-			if (rc)
-				goto fail;
-
-			if (rsize < rdata->bytes) {
-				add_credits_and_wake_if(server, &credits, 0);
-				msleep(1000);
-			}
-		} while (rsize < rdata->bytes);
-		rdata->credits = credits;
-
-		rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-		if (!rc) {
-			if (rdata->cfile->invalidHandle)
-				rc = -EAGAIN;
-			else {
-#ifdef CONFIG_CIFS_SMB_DIRECT
-				if (rdata->mr) {
-					rdata->mr->need_invalidate = true;
-					smbd_deregister_mr(rdata->mr);
-					rdata->mr = NULL;
-				}
-#endif
-				rc = server->ops->async_readv(rdata);
-			}
-		}
-
-		/* If the read was successfully sent, we are done */
-		if (!rc) {
-			/* Add to aio pending list */
-			list_add_tail(&rdata->list, rdata_list);
-			return 0;
-		}
-
-		/* Roll back credits and retry if needed */
-		add_credits_and_wake_if(server, &rdata->credits, 0);
-	} while (rc == -EAGAIN);
-
-fail:
-	kref_put(&rdata->refcount, cifs_readdata_release);
-	return rc;
-}
-
-static int
-cifs_send_async_read(loff_t fpos, size_t len, struct cifsFileInfo *open_file,
-		     struct cifs_sb_info *cifs_sb, struct list_head *rdata_list,
-		     struct cifs_aio_ctx *ctx)
-{
-	struct cifs_readdata *rdata;
-	unsigned int rsize, nsegs, max_segs = INT_MAX;
-	struct cifs_credits credits_on_stack;
-	struct cifs_credits *credits = &credits_on_stack;
-	size_t cur_len, max_len;
-	int rc;
-	pid_t pid;
-	struct TCP_Server_Info *server;
-
-	server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
-
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (server->smbd_conn)
-		max_segs = server->smbd_conn->max_frmr_depth;
-#endif
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		pid = open_file->pid;
-	else
-		pid = current->tgid;
-
-	do {
-		if (open_file->invalidHandle) {
-			rc = cifs_reopen_file(open_file, true);
-			if (rc == -EAGAIN)
-				continue;
-			else if (rc)
-				break;
-		}
-
-		if (cifs_sb->ctx->rsize == 0)
-			cifs_sb->ctx->rsize =
-				server->ops->negotiate_rsize(tlink_tcon(open_file->tlink),
-							     cifs_sb->ctx);
-
-		rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
-						   &rsize, credits);
-		if (rc)
-			break;
-
-		max_len = min_t(size_t, len, rsize);
-
-		cur_len = cifs_limit_bvec_subset(&ctx->iter, max_len,
-						 max_segs, &nsegs);
-		cifs_dbg(FYI, "read-to-iter len=%zx/%zx nsegs=%u/%lu/%u\n",
-			 cur_len, max_len, nsegs, ctx->iter.nr_segs, max_segs);
-		if (cur_len == 0) {
-			rc = -EIO;
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		rdata = cifs_readdata_alloc(cifs_uncached_readv_complete);
-		if (!rdata) {
-			add_credits_and_wake_if(server, credits, 0);
-			rc = -ENOMEM;
-			break;
-		}
-
-		rdata->server	= server;
-		rdata->cfile	= cifsFileInfo_get(open_file);
-		rdata->offset	= fpos;
-		rdata->bytes	= cur_len;
-		rdata->pid	= pid;
-		rdata->credits	= credits_on_stack;
-		rdata->ctx	= ctx;
-		kref_get(&ctx->refcount);
-
-		rdata->iter	= ctx->iter;
-		iov_iter_truncate(&rdata->iter, cur_len);
-
-		rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-
-		if (!rc) {
-			if (rdata->cfile->invalidHandle)
-				rc = -EAGAIN;
-			else
-				rc = server->ops->async_readv(rdata);
-		}
+	ssize_t rc;
+	struct inode *inode = file_inode(iocb->ki_filp);
 
-		if (rc) {
-			add_credits_and_wake_if(server, &rdata->credits, 0);
-			kref_put(&rdata->refcount, cifs_readdata_release);
-			if (rc == -EAGAIN)
-				continue;
-			break;
-		}
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, iter);
 
-		list_add_tail(&rdata->list, rdata_list);
-		iov_iter_advance(&ctx->iter, cur_len);
-		fpos += cur_len;
-		len -= cur_len;
-	} while (len > 0);
+	rc = cifs_revalidate_mapping(inode);
+	if (rc)
+		return rc;
 
-	return rc;
+	return netfs_file_read_iter(iocb, iter);
 }
 
-static void
-collect_uncached_read_data(struct cifs_aio_ctx *ctx)
+ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct cifs_readdata *rdata, *tmp;
-	struct cifs_sb_info *cifs_sb;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct cifsInodeInfo *cinode = CIFS_I(inode);
+	ssize_t written;
 	int rc;
 
-	cifs_sb = CIFS_SB(ctx->cfile->dentry->d_sb);
-
-	mutex_lock(&ctx->aio_mutex);
-
-	if (list_empty(&ctx->list)) {
-		mutex_unlock(&ctx->aio_mutex);
-		return;
-	}
-
-	rc = ctx->rc;
-	/* the loop below should proceed in the order of increasing offsets */
-again:
-	list_for_each_entry_safe(rdata, tmp, &ctx->list, list) {
-		if (!rc) {
-			if (!try_wait_for_completion(&rdata->done)) {
-				mutex_unlock(&ctx->aio_mutex);
-				return;
-			}
-
-			if (rdata->result == -EAGAIN) {
-				/* resend call if it's a retryable error */
-				struct list_head tmp_list;
-				unsigned int got_bytes = rdata->got_bytes;
-
-				list_del_init(&rdata->list);
-				INIT_LIST_HEAD(&tmp_list);
-
-				if (ctx->direct_io) {
-					/*
-					 * Re-use rdata as this is a
-					 * direct I/O
-					 */
-					rc = cifs_resend_rdata(
-						rdata,
-						&tmp_list, ctx);
-				} else {
-					rc = cifs_send_async_read(
-						rdata->offset + got_bytes,
-						rdata->bytes - got_bytes,
-						rdata->cfile, cifs_sb,
-						&tmp_list, ctx);
-
-					kref_put(&rdata->refcount,
-						cifs_readdata_release);
-				}
-
-				list_splice(&tmp_list, &ctx->list);
-
-				goto again;
-			} else if (rdata->result)
-				rc = rdata->result;
-
-			/* if there was a short read -- discard anything left */
-			if (rdata->got_bytes && rdata->got_bytes < rdata->bytes)
-				rc = -ENODATA;
-
-			ctx->total_len += rdata->got_bytes;
-		}
-		list_del_init(&rdata->list);
-		kref_put(&rdata->refcount, cifs_readdata_release);
-	}
-
-	/* mask nodata case */
-	if (rc == -ENODATA)
-		rc = 0;
-
-	ctx->rc = (rc == 0) ? (ssize_t)ctx->total_len : rc;
-
-	mutex_unlock(&ctx->aio_mutex);
-
-	if (ctx->iocb && ctx->iocb->ki_complete)
-		ctx->iocb->ki_complete(ctx->iocb, ctx->rc);
-	else
-		complete(&ctx->done);
-}
-
-static ssize_t __cifs_readv(
-	struct kiocb *iocb, struct iov_iter *to, bool direct)
-{
-	size_t len;
-	struct file *file = iocb->ki_filp;
-	struct cifs_sb_info *cifs_sb;
-	struct cifsFileInfo *cfile;
-	struct cifs_tcon *tcon;
-	ssize_t rc, total_read = 0;
-	loff_t offset = iocb->ki_pos;
-	struct cifs_aio_ctx *ctx;
-
-	len = iov_iter_count(to);
-	if (!len)
-		return 0;
-
-	cifs_sb = CIFS_FILE_SB(file);
-	cfile = file->private_data;
-	tcon = tlink_tcon(cfile->tlink);
-
-	if (!tcon->ses->server->ops->async_readv)
-		return -ENOSYS;
-
-	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		cifs_dbg(FYI, "attempting read on write only file instance\n");
-
-	ctx = cifs_aio_ctx_alloc();
-	if (!ctx)
-		return -ENOMEM;
-
-	ctx->pos	= offset;
-	ctx->direct_io	= direct;
-	ctx->len	= len;
-	ctx->cfile	= cifsFileInfo_get(cfile);
-	ctx->nr_pinned_pages = 0;
-
-	if (!is_sync_kiocb(iocb))
-		ctx->iocb = iocb;
-
-	if (user_backed_iter(to)) {
-		/*
-		 * Extract IOVEC/UBUF-type iterators to a BVEC-type iterator as
-		 * they contain references to the calling process's virtual
-		 * memory layout which won't be available in an async worker
-		 * thread.  This also takes a pin on every folio involved.
-		 */
-		rc = netfs_extract_user_iter(to, iov_iter_count(to),
-					     &ctx->iter, 0);
-		if (rc < 0) {
-			kref_put(&ctx->refcount, cifs_aio_ctx_release);
-			return rc;
-		}
-
-		ctx->nr_pinned_pages = rc;
-		ctx->bv = (void *)ctx->iter.bvec;
-		ctx->bv_need_unpin = iov_iter_extract_will_pin(to);
-		ctx->should_dirty = true;
-	} else if ((iov_iter_is_bvec(to) || iov_iter_is_kvec(to)) &&
-		   !is_sync_kiocb(iocb)) {
-		/*
-		 * If the op is asynchronous, we need to copy the list attached
-		 * to a BVEC/KVEC-type iterator, but we assume that the storage
-		 * will be retained by the caller; in any case, we may or may
-		 * not be able to pin the pages, so we don't try.
-		 */
-		ctx->bv = (void *)dup_iter(&ctx->iter, to, GFP_KERNEL);
-		if (!ctx->bv) {
-			kref_put(&ctx->refcount, cifs_aio_ctx_release);
-			return -ENOMEM;
-		}
-	} else {
-		/*
-		 * Otherwise, we just pass the iterator down as-is and rely on
-		 * the caller to make sure the pages referred to by the
-		 * iterator don't evaporate.
-		 */
-		ctx->iter = *to;
-	}
-
-	if (direct) {
-		rc = filemap_write_and_wait_range(file->f_inode->i_mapping,
-						  offset, offset + len - 1);
-		if (rc) {
-			kref_put(&ctx->refcount, cifs_aio_ctx_release);
-			return -EAGAIN;
+	if (iocb->ki_filp->f_flags & O_DIRECT) {
+		written = netfs_unbuffered_write_iter(iocb, from);
+		if (written > 0 && CIFS_CACHE_READ(cinode)) {
+			cifs_zap_mapping(inode);
+			cifs_dbg(FYI,
+				 "Set no oplock for inode=%p after a write operation\n",
+				 inode);
+			cinode->oplock = 0;
 		}
+		return written;
 	}
 
-	/* grab a lock here due to read response handlers can access ctx */
-	mutex_lock(&ctx->aio_mutex);
-
-	rc = cifs_send_async_read(offset, len, cfile, cifs_sb, &ctx->list, ctx);
-
-	/* if at least one read request send succeeded, then reset rc */
-	if (!list_empty(&ctx->list))
-		rc = 0;
-
-	mutex_unlock(&ctx->aio_mutex);
-
-	if (rc) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return rc;
-	}
-
-	if (!is_sync_kiocb(iocb)) {
-		kref_put(&ctx->refcount, cifs_aio_ctx_release);
-		return -EIOCBQUEUED;
-	}
-
-	rc = wait_for_completion_killable(&ctx->done);
-	if (rc) {
-		mutex_lock(&ctx->aio_mutex);
-		ctx->rc = rc = -EINTR;
-		total_read = ctx->total_len;
-		mutex_unlock(&ctx->aio_mutex);
-	} else {
-		rc = ctx->rc;
-		total_read = ctx->total_len;
-	}
+	written = cifs_get_writer(cinode);
+	if (written)
+		return written;
 
-	kref_put(&ctx->refcount, cifs_aio_ctx_release);
+	written = netfs_file_write_iter(iocb, from);
 
-	if (total_read) {
-		iocb->ki_pos += total_read;
-		return total_read;
+	if (!CIFS_CACHE_WRITE(CIFS_I(inode))) {
+		rc = filemap_fdatawrite(inode->i_mapping);
+		if (rc)
+			cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n",
+				 rc, inode);
 	}
-	return rc;
-}
-
-ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to)
-{
-	return __cifs_readv(iocb, to, true);
-}
 
-ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
-{
-	return __cifs_readv(iocb, to, false);
+	cifs_put_writer(cinode);
+	return written;
 }
 
 ssize_t
@@ -4386,12 +2902,15 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 	 * pos+len-1.
 	 */
 	if (!CIFS_CACHE_READ(cinode))
-		return cifs_user_readv(iocb, to);
+		return netfs_unbuffered_read_iter(iocb, to);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
-	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
-		return generic_file_read_iter(iocb, to);
+	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
+		if (iocb->ki_flags & IOCB_DIRECT)
+			return netfs_unbuffered_read_iter(iocb, to);
+		return netfs_buffered_read_iter(iocb, to);
+	}
 
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
@@ -4400,126 +2919,19 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 	down_read(&cinode->lock_sem);
 	if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to),
 				     tcon->ses->server->vals->shared_lock_type,
-				     0, NULL, CIFS_READ_OP))
-		rc = generic_file_read_iter(iocb, to);
+				     0, NULL, CIFS_READ_OP)) {
+		if (iocb->ki_flags & IOCB_DIRECT)
+			rc = netfs_unbuffered_read_iter(iocb, to);
+		else
+			rc = netfs_buffered_read_iter(iocb, to);
+	}
 	up_read(&cinode->lock_sem);
 	return rc;
 }
 
-static ssize_t
-cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
-{
-	int rc = -EACCES;
-	unsigned int bytes_read = 0;
-	unsigned int total_read;
-	unsigned int current_read_size;
-	unsigned int rsize;
-	struct cifs_sb_info *cifs_sb;
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
-	unsigned int xid;
-	char *cur_offset;
-	struct cifsFileInfo *open_file;
-	struct cifs_io_parms io_parms = {0};
-	int buf_type = CIFS_NO_BUFFER;
-	__u32 pid;
-
-	xid = get_xid();
-	cifs_sb = CIFS_FILE_SB(file);
-
-	/* FIXME: set up handlers for larger reads and/or convert to async */
-	rsize = min_t(unsigned int, cifs_sb->ctx->rsize, CIFSMaxBufSize);
-
-	if (file->private_data == NULL) {
-		rc = -EBADF;
-		free_xid(xid);
-		return rc;
-	}
-	open_file = file->private_data;
-	tcon = tlink_tcon(open_file->tlink);
-	server = cifs_pick_channel(tcon->ses);
-
-	if (!server->ops->sync_read) {
-		free_xid(xid);
-		return -ENOSYS;
-	}
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		pid = open_file->pid;
-	else
-		pid = current->tgid;
-
-	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		cifs_dbg(FYI, "attempting read on write only file instance\n");
-
-	for (total_read = 0, cur_offset = read_data; read_size > total_read;
-	     total_read += bytes_read, cur_offset += bytes_read) {
-		do {
-			current_read_size = min_t(uint, read_size - total_read,
-						  rsize);
-			/*
-			 * For windows me and 9x we do not want to request more
-			 * than it negotiated since it will refuse the read
-			 * then.
-			 */
-			if (!(tcon->ses->capabilities &
-				tcon->ses->server->vals->cap_large_files)) {
-				current_read_size = min_t(uint,
-					current_read_size, CIFSMaxBufSize);
-			}
-			if (open_file->invalidHandle) {
-				rc = cifs_reopen_file(open_file, true);
-				if (rc != 0)
-					break;
-			}
-			io_parms.pid = pid;
-			io_parms.tcon = tcon;
-			io_parms.offset = *offset;
-			io_parms.length = current_read_size;
-			io_parms.server = server;
-			rc = server->ops->sync_read(xid, &open_file->fid, &io_parms,
-						    &bytes_read, &cur_offset,
-						    &buf_type);
-		} while (rc == -EAGAIN);
-
-		if (rc || (bytes_read == 0)) {
-			if (total_read) {
-				break;
-			} else {
-				free_xid(xid);
-				return rc;
-			}
-		} else {
-			cifs_stats_bytes_read(tcon, total_read);
-			*offset += bytes_read;
-		}
-	}
-	free_xid(xid);
-	return total_read;
-}
-
-/*
- * If the page is mmap'ed into a process' page tables, then we need to make
- * sure that it doesn't change while being written back.
- */
 static vm_fault_t cifs_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
-
-	/* Wait for the folio to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire folio will need writing back.
-	 */
-#ifdef CONFIG_CIFS_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		return VM_FAULT_RETRY;
-#endif
-
-	folio_wait_writeback(folio);
-
-	if (folio_lock_killable(folio) < 0)
-		return VM_FAULT_RETRY;
-	return VM_FAULT_LOCKED;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 static const struct vm_operations_struct cifs_file_vm_ops = {
@@ -4565,290 +2977,6 @@ int cifs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return rc;
 }
 
-/*
- * Unlock a bunch of folios in the pagecache.
- */
-static void cifs_unlock_folios(struct address_space *mapping, pgoff_t first, pgoff_t last)
-{
-	struct folio *folio;
-	XA_STATE(xas, &mapping->i_pages, first);
-
-	rcu_read_lock();
-	xas_for_each(&xas, folio, last) {
-		folio_unlock(folio);
-	}
-	rcu_read_unlock();
-}
-
-static void cifs_readahead_complete(struct work_struct *work)
-{
-	struct cifs_readdata *rdata = container_of(work,
-						   struct cifs_readdata, work);
-	struct folio *folio;
-	pgoff_t last;
-	bool good = rdata->result == 0 || (rdata->result == -EAGAIN && rdata->got_bytes);
-
-	XA_STATE(xas, &rdata->mapping->i_pages, rdata->offset / PAGE_SIZE);
-
-	if (good)
-		cifs_readahead_to_fscache(rdata->mapping->host,
-					  rdata->offset, rdata->bytes);
-
-	if (iov_iter_count(&rdata->iter) > 0)
-		iov_iter_zero(iov_iter_count(&rdata->iter), &rdata->iter);
-
-	last = (rdata->offset + rdata->bytes - 1) / PAGE_SIZE;
-
-	rcu_read_lock();
-	xas_for_each(&xas, folio, last) {
-		if (good) {
-			flush_dcache_folio(folio);
-			folio_mark_uptodate(folio);
-		}
-		folio_unlock(folio);
-	}
-	rcu_read_unlock();
-
-	kref_put(&rdata->refcount, cifs_readdata_release);
-}
-
-static void cifs_readahead(struct readahead_control *ractl)
-{
-	struct cifsFileInfo *open_file = ractl->file->private_data;
-	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file);
-	struct TCP_Server_Info *server;
-	unsigned int xid, nr_pages, cache_nr_pages = 0;
-	unsigned int ra_pages;
-	pgoff_t next_cached = ULONG_MAX, ra_index;
-	bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) &&
-		cifs_inode_cookie(ractl->mapping->host)->cache_priv;
-	bool check_cache = caching;
-	pid_t pid;
-	int rc = 0;
-
-	/* Note that readahead_count() lags behind our dequeuing of pages from
-	 * the ractl, wo we have to keep track for ourselves.
-	 */
-	ra_pages = readahead_count(ractl);
-	ra_index = readahead_index(ractl);
-
-	xid = get_xid();
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		pid = open_file->pid;
-	else
-		pid = current->tgid;
-
-	server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
-
-	cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n",
-		 __func__, ractl->file, ractl->mapping, ra_pages);
-
-	/*
-	 * Chop the readahead request up into rsize-sized read requests.
-	 */
-	while ((nr_pages = ra_pages)) {
-		unsigned int i, rsize;
-		struct cifs_readdata *rdata;
-		struct cifs_credits credits_on_stack;
-		struct cifs_credits *credits = &credits_on_stack;
-		struct folio *folio;
-		pgoff_t fsize;
-
-		/*
-		 * Find out if we have anything cached in the range of
-		 * interest, and if so, where the next chunk of cached data is.
-		 */
-		if (caching) {
-			if (check_cache) {
-				rc = cifs_fscache_query_occupancy(
-					ractl->mapping->host, ra_index, nr_pages,
-					&next_cached, &cache_nr_pages);
-				if (rc < 0)
-					caching = false;
-				check_cache = false;
-			}
-
-			if (ra_index == next_cached) {
-				/*
-				 * TODO: Send a whole batch of pages to be read
-				 * by the cache.
-				 */
-				folio = readahead_folio(ractl);
-				fsize = folio_nr_pages(folio);
-				ra_pages -= fsize;
-				ra_index += fsize;
-				if (cifs_readpage_from_fscache(ractl->mapping->host,
-							       &folio->page) < 0) {
-					/*
-					 * TODO: Deal with cache read failure
-					 * here, but for the moment, delegate
-					 * that to readpage.
-					 */
-					caching = false;
-				}
-				folio_unlock(folio);
-				next_cached += fsize;
-				cache_nr_pages -= fsize;
-				if (cache_nr_pages == 0)
-					check_cache = true;
-				continue;
-			}
-		}
-
-		if (open_file->invalidHandle) {
-			rc = cifs_reopen_file(open_file, true);
-			if (rc) {
-				if (rc == -EAGAIN)
-					continue;
-				break;
-			}
-		}
-
-		if (cifs_sb->ctx->rsize == 0)
-			cifs_sb->ctx->rsize =
-				server->ops->negotiate_rsize(tlink_tcon(open_file->tlink),
-							     cifs_sb->ctx);
-
-		rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
-						   &rsize, credits);
-		if (rc)
-			break;
-		nr_pages = min_t(size_t, rsize / PAGE_SIZE, ra_pages);
-		if (next_cached != ULONG_MAX)
-			nr_pages = min_t(size_t, nr_pages, next_cached - ra_index);
-
-		/*
-		 * Give up immediately if rsize is too small to read an entire
-		 * page. The VFS will fall back to readpage. We should never
-		 * reach this point however since we set ra_pages to 0 when the
-		 * rsize is smaller than a cache page.
-		 */
-		if (unlikely(!nr_pages)) {
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		rdata = cifs_readdata_alloc(cifs_readahead_complete);
-		if (!rdata) {
-			/* best to give up if we're out of mem */
-			add_credits_and_wake_if(server, credits, 0);
-			break;
-		}
-
-		rdata->offset	= ra_index * PAGE_SIZE;
-		rdata->bytes	= nr_pages * PAGE_SIZE;
-		rdata->cfile	= cifsFileInfo_get(open_file);
-		rdata->server	= server;
-		rdata->mapping	= ractl->mapping;
-		rdata->pid	= pid;
-		rdata->credits	= credits_on_stack;
-
-		for (i = 0; i < nr_pages; i++) {
-			if (!readahead_folio(ractl))
-				WARN_ON(1);
-		}
-		ra_pages -= nr_pages;
-		ra_index += nr_pages;
-
-		iov_iter_xarray(&rdata->iter, ITER_DEST, &rdata->mapping->i_pages,
-				rdata->offset, rdata->bytes);
-
-		rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-		if (!rc) {
-			if (rdata->cfile->invalidHandle)
-				rc = -EAGAIN;
-			else
-				rc = server->ops->async_readv(rdata);
-		}
-
-		if (rc) {
-			add_credits_and_wake_if(server, &rdata->credits, 0);
-			cifs_unlock_folios(rdata->mapping,
-					   rdata->offset / PAGE_SIZE,
-					   (rdata->offset + rdata->bytes - 1) / PAGE_SIZE);
-			/* Fallback to the readpage in error/reconnect cases */
-			kref_put(&rdata->refcount, cifs_readdata_release);
-			break;
-		}
-
-		kref_put(&rdata->refcount, cifs_readdata_release);
-	}
-
-	free_xid(xid);
-}
-
-/*
- * cifs_readpage_worker must be called with the page pinned
- */
-static int cifs_readpage_worker(struct file *file, struct page *page,
-	loff_t *poffset)
-{
-	struct inode *inode = file_inode(file);
-	struct timespec64 atime, mtime;
-	char *read_data;
-	int rc;
-
-	/* Is the page cached? */
-	rc = cifs_readpage_from_fscache(inode, page);
-	if (rc == 0)
-		goto read_complete;
-
-	read_data = kmap(page);
-	/* for reads over a certain size could initiate async read ahead */
-
-	rc = cifs_read(file, read_data, PAGE_SIZE, poffset);
-
-	if (rc < 0)
-		goto io_error;
-	else
-		cifs_dbg(FYI, "Bytes read %d\n", rc);
-
-	/* we do not want atime to be less than mtime, it broke some apps */
-	atime = inode_set_atime_to_ts(inode, current_time(inode));
-	mtime = inode_get_mtime(inode);
-	if (timespec64_compare(&atime, &mtime) < 0)
-		inode_set_atime_to_ts(inode, inode_get_mtime(inode));
-
-	if (PAGE_SIZE > rc)
-		memset(read_data + rc, 0, PAGE_SIZE - rc);
-
-	flush_dcache_page(page);
-	SetPageUptodate(page);
-	rc = 0;
-
-io_error:
-	kunmap(page);
-
-read_complete:
-	unlock_page(page);
-	return rc;
-}
-
-static int cifs_read_folio(struct file *file, struct folio *folio)
-{
-	struct page *page = &folio->page;
-	loff_t offset = page_file_offset(page);
-	int rc = -EACCES;
-	unsigned int xid;
-
-	xid = get_xid();
-
-	if (file->private_data == NULL) {
-		rc = -EBADF;
-		free_xid(xid);
-		return rc;
-	}
-
-	cifs_dbg(FYI, "read_folio %p at offset %d 0x%x\n",
-		 page, (int)offset, (int)offset);
-
-	rc = cifs_readpage_worker(file, page, &offset);
-
-	free_xid(xid);
-	return rc;
-}
-
 static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
 {
 	struct cifsFileInfo *open_file;
@@ -4896,123 +3024,6 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file,
 		return true;
 }
 
-static int cifs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
-{
-	int oncethru = 0;
-	pgoff_t index = pos >> PAGE_SHIFT;
-	loff_t offset = pos & (PAGE_SIZE - 1);
-	loff_t page_start = pos & PAGE_MASK;
-	loff_t i_size;
-	struct page *page;
-	int rc = 0;
-
-	cifs_dbg(FYI, "write_begin from %lld len %d\n", (long long)pos, len);
-
-start:
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
-	if (PageUptodate(page))
-		goto out;
-
-	/*
-	 * If we write a full page it will be up to date, no need to read from
-	 * the server. If the write is short, we'll end up doing a sync write
-	 * instead.
-	 */
-	if (len == PAGE_SIZE)
-		goto out;
-
-	/*
-	 * optimize away the read when we have an oplock, and we're not
-	 * expecting to use any of the data we'd be reading in. That
-	 * is, when the page lies beyond the EOF, or straddles the EOF
-	 * and the write will cover all of the existing data.
-	 */
-	if (CIFS_CACHE_READ(CIFS_I(mapping->host))) {
-		i_size = i_size_read(mapping->host);
-		if (page_start >= i_size ||
-		    (offset == 0 && (pos + len) >= i_size)) {
-			zero_user_segments(page, 0, offset,
-					   offset + len,
-					   PAGE_SIZE);
-			/*
-			 * PageChecked means that the parts of the page
-			 * to which we're not writing are considered up
-			 * to date. Once the data is copied to the
-			 * page, it can be set uptodate.
-			 */
-			SetPageChecked(page);
-			goto out;
-		}
-	}
-
-	if ((file->f_flags & O_ACCMODE) != O_WRONLY && !oncethru) {
-		/*
-		 * might as well read a page, it is fast enough. If we get
-		 * an error, we don't need to return it. cifs_write_end will
-		 * do a sync write instead since PG_uptodate isn't set.
-		 */
-		cifs_readpage_worker(file, page, &page_start);
-		put_page(page);
-		oncethru = 1;
-		goto start;
-	} else {
-		/* we could try using another file handle if there is one -
-		   but how would we lock it to prevent close of that handle
-		   racing with this read? In any case
-		   this will be written out by write_end so is fine */
-	}
-out:
-	*pagep = page;
-	return rc;
-}
-
-static bool cifs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	if (folio_test_private(folio))
-		return 0;
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(cifs_inode_cookie(folio->mapping->host));
-	return true;
-}
-
-static void cifs_invalidate_folio(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	folio_wait_fscache(folio);
-}
-
-static int cifs_launder_folio(struct folio *folio)
-{
-	int rc = 0;
-	loff_t range_start = folio_pos(folio);
-	loff_t range_end = range_start + folio_size(folio);
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0,
-		.range_start = range_start,
-		.range_end = range_end,
-	};
-
-	cifs_dbg(FYI, "Launder page: %lu\n", folio->index);
-
-	if (folio_clear_dirty_for_io(folio))
-		rc = cifs_writepage_locked(&folio->page, &wbc);
-
-	folio_wait_fscache(folio);
-	return rc;
-}
-
 void cifs_oplock_break(struct work_struct *work)
 {
 	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
@@ -5102,25 +3113,6 @@ out:
 	cifs_done_oplock_break(cinode);
 }
 
-/*
- * The presence of cifs_direct_io() in the address space ops vector
- * allowes open() O_DIRECT flags which would have failed otherwise.
- *
- * In the non-cached mode (mount with cache=none), we shunt off direct read and write requests
- * so this method should never be called.
- *
- * Direct IO is not yet supported in the cached mode.
- */
-static ssize_t
-cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
-{
-        /*
-         * FIXME
-         * Eventually need to support direct IO for non forcedirectio mounts
-         */
-        return -EINVAL;
-}
-
 static int cifs_swap_activate(struct swap_info_struct *sis,
 			      struct file *swap_file, sector_t *span)
 {
@@ -5182,22 +3174,19 @@ static void cifs_swap_deactivate(struct file *file)
 }
 
 const struct address_space_operations cifs_addr_ops = {
-	.read_folio = cifs_read_folio,
-	.readahead = cifs_readahead,
-	.writepages = cifs_writepages,
-	.write_begin = cifs_write_begin,
-	.write_end = cifs_write_end,
-	.dirty_folio = netfs_dirty_folio,
-	.release_folio = cifs_release_folio,
-	.direct_IO = cifs_direct_io,
-	.invalidate_folio = cifs_invalidate_folio,
-	.launder_folio = cifs_launder_folio,
-	.migrate_folio = filemap_migrate_folio,
+	.read_folio	= netfs_read_folio,
+	.readahead	= netfs_readahead,
+	.writepages	= netfs_writepages,
+	.dirty_folio	= netfs_dirty_folio,
+	.release_folio	= netfs_release_folio,
+	.direct_IO	= noop_direct_IO,
+	.invalidate_folio = netfs_invalidate_folio,
+	.migrate_folio	= filemap_migrate_folio,
 	/*
 	 * TODO: investigate and if useful we could add an is_dirty_writeback
 	 * helper if needed
 	 */
-	.swap_activate = cifs_swap_activate,
+	.swap_activate	= cifs_swap_activate,
 	.swap_deactivate = cifs_swap_deactivate,
 };
 
@@ -5207,13 +3196,10 @@ const struct address_space_operations cifs_addr_ops = {
  * to leave cifs_readahead out of the address space operations.
  */
 const struct address_space_operations cifs_addr_ops_smallbuf = {
-	.read_folio = cifs_read_folio,
-	.writepages = cifs_writepages,
-	.write_begin = cifs_write_begin,
-	.write_end = cifs_write_end,
-	.dirty_folio = netfs_dirty_folio,
-	.release_folio = cifs_release_folio,
-	.invalidate_folio = cifs_invalidate_folio,
-	.launder_folio = cifs_launder_folio,
-	.migrate_folio = filemap_migrate_folio,
+	.read_folio	= netfs_read_folio,
+	.writepages	= netfs_writepages,
+	.dirty_folio	= netfs_dirty_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
+	.migrate_folio	= filemap_migrate_folio,
 };
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index 1a895e6243ee..01424a5cdb99 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -170,112 +170,3 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 		cifsi->netfs.cache = NULL;
 	}
 }
-
-/*
- * Fallback page reading interface.
- */
-static int fscache_fallback_read_page(struct inode *inode, struct page *page)
-{
-	struct netfs_cache_resources cres;
-	struct fscache_cookie *cookie = cifs_inode_cookie(inode);
-	struct iov_iter iter;
-	struct bio_vec bvec;
-	int ret;
-
-	memset(&cres, 0, sizeof(cres));
-	bvec_set_page(&bvec, page, PAGE_SIZE, 0);
-	iov_iter_bvec(&iter, ITER_DEST, &bvec, 1, PAGE_SIZE);
-
-	ret = fscache_begin_read_operation(&cres, cookie);
-	if (ret < 0)
-		return ret;
-
-	ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
-			   NULL, NULL);
-	fscache_end_operation(&cres);
-	return ret;
-}
-
-/*
- * Fallback page writing interface.
- */
-static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_t len,
-					bool no_space_allocated_yet)
-{
-	struct netfs_cache_resources cres;
-	struct fscache_cookie *cookie = cifs_inode_cookie(inode);
-	struct iov_iter iter;
-	int ret;
-
-	memset(&cres, 0, sizeof(cres));
-	iov_iter_xarray(&iter, ITER_SOURCE, &inode->i_mapping->i_pages, start, len);
-
-	ret = fscache_begin_write_operation(&cres, cookie);
-	if (ret < 0)
-		return ret;
-
-	ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode),
-				      no_space_allocated_yet);
-	if (ret == 0)
-		ret = fscache_write(&cres, start, &iter, NULL, NULL);
-	fscache_end_operation(&cres);
-	return ret;
-}
-
-/*
- * Retrieve a page from FS-Cache
- */
-int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
-{
-	int ret;
-
-	cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n",
-		 __func__, cifs_inode_cookie(inode), page, inode);
-
-	ret = fscache_fallback_read_page(inode, page);
-	if (ret < 0)
-		return ret;
-
-	/* Read completed synchronously */
-	SetPageUptodate(page);
-	return 0;
-}
-
-void __cifs_readahead_to_fscache(struct inode *inode, loff_t pos, size_t len)
-{
-	cifs_dbg(FYI, "%s: (fsc: %p, p: %llx, l: %zx, i: %p)\n",
-		 __func__, cifs_inode_cookie(inode), pos, len, inode);
-
-	fscache_fallback_write_pages(inode, pos, len, true);
-}
-
-/*
- * Query the cache occupancy.
- */
-int __cifs_fscache_query_occupancy(struct inode *inode,
-				   pgoff_t first, unsigned int nr_pages,
-				   pgoff_t *_data_first,
-				   unsigned int *_data_nr_pages)
-{
-	struct netfs_cache_resources cres;
-	struct fscache_cookie *cookie = cifs_inode_cookie(inode);
-	loff_t start, data_start;
-	size_t len, data_len;
-	int ret;
-
-	ret = fscache_begin_read_operation(&cres, cookie);
-	if (ret < 0)
-		return ret;
-
-	start = first * PAGE_SIZE;
-	len = nr_pages * PAGE_SIZE;
-	ret = cres.ops->query_occupancy(&cres, start, len, PAGE_SIZE,
-					&data_start, &data_len);
-	if (ret == 0) {
-		*_data_first = data_start / PAGE_SIZE;
-		*_data_nr_pages = len / PAGE_SIZE;
-	}
-
-	fscache_end_operation(&cres);
-	return ret;
-}
diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h
index 1f2ea9f5cc9a..f06cb24f5f3c 100644
--- a/fs/smb/client/fscache.h
+++ b/fs/smb/client/fscache.h
@@ -74,41 +74,6 @@ static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags
 			   i_size_read(inode), flags);
 }
 
-extern int __cifs_fscache_query_occupancy(struct inode *inode,
-					  pgoff_t first, unsigned int nr_pages,
-					  pgoff_t *_data_first,
-					  unsigned int *_data_nr_pages);
-
-static inline int cifs_fscache_query_occupancy(struct inode *inode,
-					       pgoff_t first, unsigned int nr_pages,
-					       pgoff_t *_data_first,
-					       unsigned int *_data_nr_pages)
-{
-	if (!cifs_inode_cookie(inode))
-		return -ENOBUFS;
-	return __cifs_fscache_query_occupancy(inode, first, nr_pages,
-					      _data_first, _data_nr_pages);
-}
-
-extern int __cifs_readpage_from_fscache(struct inode *pinode, struct page *ppage);
-extern void __cifs_readahead_to_fscache(struct inode *pinode, loff_t pos, size_t len);
-
-
-static inline int cifs_readpage_from_fscache(struct inode *inode,
-					     struct page *page)
-{
-	if (cifs_inode_cookie(inode))
-		return __cifs_readpage_from_fscache(inode, page);
-	return -ENOBUFS;
-}
-
-static inline void cifs_readahead_to_fscache(struct inode *inode,
-					     loff_t pos, size_t len)
-{
-	if (cifs_inode_cookie(inode))
-		__cifs_readahead_to_fscache(inode, pos, len);
-}
-
 static inline bool cifs_fscache_enabled(struct inode *inode)
 {
 	return fscache_cookie_enabled(cifs_inode_cookie(inode));
@@ -131,25 +96,6 @@ static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { re
 static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {}
 static inline bool cifs_fscache_enabled(struct inode *inode) { return false; }
 
-static inline int cifs_fscache_query_occupancy(struct inode *inode,
-					       pgoff_t first, unsigned int nr_pages,
-					       pgoff_t *_data_first,
-					       unsigned int *_data_nr_pages)
-{
-	*_data_first = ULONG_MAX;
-	*_data_nr_pages = 0;
-	return -ENOBUFS;
-}
-
-static inline int
-cifs_readpage_from_fscache(struct inode *inode, struct page *page)
-{
-	return -ENOBUFS;
-}
-
-static inline
-void cifs_readahead_to_fscache(struct inode *inode, loff_t pos, size_t len) {}
-
 #endif /* CONFIG_CIFS_FSCACHE */
 
 #endif /* _CIFS_FSCACHE_H */
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 60afab5c83d4..e8bfeea23660 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -28,14 +28,29 @@
 #include "cached_dir.h"
 #include "reparse.h"
 
+/*
+ * Set parameters for the netfs library
+ */
+static void cifs_set_netfs_context(struct inode *inode)
+{
+	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+
+	netfs_inode_init(&cifs_i->netfs, &cifs_req_ops, true);
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
+		__set_bit(NETFS_ICTX_WRITETHROUGH, &cifs_i->netfs.flags);
+}
+
 static void cifs_set_ops(struct inode *inode)
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct netfs_inode *ictx = netfs_inode(inode);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &cifs_file_inode_ops;
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
+			set_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags);
 			if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
 				inode->i_fop = &cifs_file_direct_nobrl_ops;
 			else
@@ -57,6 +72,7 @@ static void cifs_set_ops(struct inode *inode)
 			inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
 		else
 			inode->i_data.a_ops = &cifs_addr_ops;
+		mapping_set_large_folios(inode->i_mapping);
 		break;
 	case S_IFDIR:
 		if (IS_AUTOMOUNT(inode)) {
@@ -221,8 +237,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
 
 	if (fattr->cf_flags & CIFS_FATTR_JUNCTION)
 		inode->i_flags |= S_AUTOMOUNT;
-	if (inode->i_state & I_NEW)
+	if (inode->i_state & I_NEW) {
+		cifs_set_netfs_context(inode);
 		cifs_set_ops(inode);
+	}
 	return 0;
 }
 
@@ -2431,24 +2449,6 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 	return false;
 }
 
-/*
- * Zap the cache. Called when invalid_mapping flag is set.
- */
-int
-cifs_invalidate_mapping(struct inode *inode)
-{
-	int rc = 0;
-
-	if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
-		rc = invalidate_inode_pages2(inode->i_mapping);
-		if (rc)
-			cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n",
-				 __func__, inode, rc);
-	}
-
-	return rc;
-}
-
 /**
  * cifs_wait_bit_killable - helper for functions that are sleeping on bit locks
  *
@@ -2485,9 +2485,12 @@ cifs_revalidate_mapping(struct inode *inode)
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
 			goto skip_invalidate;
 
-		rc = cifs_invalidate_mapping(inode);
-		if (rc)
+		rc = filemap_invalidate_inode(inode, true, 0, LLONG_MAX);
+		if (rc) {
+			cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n",
+				 __func__, inode, rc);
 			set_bit(CIFS_INO_INVALID_MAPPING, flags);
+		}
 	}
 
 skip_invalidate:
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 28f0b7d19d53..ef18cd30f66c 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -217,8 +217,8 @@ smb2_get_credits(struct mid_q_entry *mid)
 }
 
 static int
-smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size,
-		      unsigned int *num, struct cifs_credits *credits)
+smb2_wait_mtu_credits(struct TCP_Server_Info *server, size_t size,
+		      size_t *num, struct cifs_credits *credits)
 {
 	int rc = 0;
 	unsigned int scredits, in_flight;
@@ -4490,7 +4490,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 	unsigned int cur_off;
 	unsigned int cur_page_idx;
 	unsigned int pad_len;
-	struct cifs_readdata *rdata = mid->callback_data;
+	struct cifs_io_subrequest *rdata = mid->callback_data;
 	struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
 	int length;
 	bool use_rdma_mr = false;
@@ -4592,7 +4592,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 
 		/* Copy the data to the output I/O iterator. */
 		rdata->result = cifs_copy_pages_to_iter(pages, pages_len,
-							cur_off, &rdata->iter);
+							cur_off, &rdata->subreq.io_iter);
 		if (rdata->result != 0) {
 			if (is_offloaded)
 				mid->mid_state = MID_RESPONSE_MALFORMED;
@@ -4606,7 +4606,7 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 		/* read response payload is in buf */
 		WARN_ONCE(pages && !xa_empty(pages),
 			  "read data can be either in buf or in pages");
-		length = copy_to_iter(buf + data_offset, data_len, &rdata->iter);
+		length = copy_to_iter(buf + data_offset, data_len, &rdata->subreq.io_iter);
 		if (length < 0)
 			return length;
 		rdata->got_bytes = data_len;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a5efce03cb58..993ac36c3d58 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -23,6 +23,8 @@
 #include <linux/uuid.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
+#include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "cifsglob.h"
 #include "cifsacl.h"
 #include "cifsproto.h"
@@ -4391,7 +4393,7 @@ static inline bool smb3_use_rdma_offload(struct cifs_io_parms *io_parms)
  */
 static int
 smb2_new_read_req(void **buf, unsigned int *total_len,
-	struct cifs_io_parms *io_parms, struct cifs_readdata *rdata,
+	struct cifs_io_parms *io_parms, struct cifs_io_subrequest *rdata,
 	unsigned int remaining_bytes, int request_type)
 {
 	int rc = -EACCES;
@@ -4419,10 +4421,12 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
 	req->Length = cpu_to_le32(io_parms->length);
 	req->Offset = cpu_to_le64(io_parms->offset);
 
-	trace_smb3_read_enter(0 /* xid */,
-			io_parms->persistent_fid,
-			io_parms->tcon->tid, io_parms->tcon->ses->Suid,
-			io_parms->offset, io_parms->length);
+	trace_smb3_read_enter(rdata ? rdata->rreq->debug_id : 0,
+			      rdata ? rdata->subreq.debug_index : 0,
+			      rdata ? rdata->xid : 0,
+			      io_parms->persistent_fid,
+			      io_parms->tcon->tid, io_parms->tcon->ses->Suid,
+			      io_parms->offset, io_parms->length);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	/*
 	 * If we want to do a RDMA write, fill in and append
@@ -4432,7 +4436,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
 		struct smbd_buffer_descriptor_v1 *v1;
 		bool need_invalidate = server->dialect == SMB30_PROT_ID;
 
-		rdata->mr = smbd_register_mr(server->smbd_conn, &rdata->iter,
+		rdata->mr = smbd_register_mr(server->smbd_conn, &rdata->subreq.io_iter,
 					     true, need_invalidate);
 		if (!rdata->mr)
 			return -EAGAIN;
@@ -4483,8 +4487,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
 static void
 smb2_readv_callback(struct mid_q_entry *mid)
 {
-	struct cifs_readdata *rdata = mid->callback_data;
-	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
+	struct cifs_io_subrequest *rdata = mid->callback_data;
+	struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
 	struct TCP_Server_Info *server = rdata->server;
 	struct smb2_hdr *shdr =
 				(struct smb2_hdr *)rdata->iov[0].iov_base;
@@ -4492,17 +4496,17 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 };
 
 	if (rdata->got_bytes) {
-		rqst.rq_iter	  = rdata->iter;
-		rqst.rq_iter_size = iov_iter_count(&rdata->iter);
+		rqst.rq_iter	  = rdata->subreq.io_iter;
+		rqst.rq_iter_size = iov_iter_count(&rdata->subreq.io_iter);
 	}
 
 	WARN_ONCE(rdata->server != mid->server,
 		  "rdata server %p != mid server %p",
 		  rdata->server, mid->server);
 
-	cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n",
+	cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
 		 __func__, mid->mid, mid->mid_state, rdata->result,
-		 rdata->bytes);
+		 rdata->subreq.len);
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
@@ -4512,7 +4516,6 @@ smb2_readv_callback(struct mid_q_entry *mid)
 		if (server->sign && !mid->decrypted) {
 			int rc;
 
-			iov_iter_revert(&rqst.rq_iter, rdata->got_bytes);
 			iov_iter_truncate(&rqst.rq_iter, rdata->got_bytes);
 			rc = smb2_verify_signature(&rqst, server);
 			if (rc)
@@ -4553,24 +4556,40 @@ smb2_readv_callback(struct mid_q_entry *mid)
 #endif
 	if (rdata->result && rdata->result != -ENODATA) {
 		cifs_stats_fail_inc(tcon, SMB2_READ_HE);
-		trace_smb3_read_err(0 /* xid */,
-				    rdata->cfile->fid.persistent_fid,
-				    tcon->tid, tcon->ses->Suid, rdata->offset,
-				    rdata->bytes, rdata->result);
+		trace_smb3_read_err(rdata->rreq->debug_id,
+				    rdata->subreq.debug_index,
+				    rdata->xid,
+				    rdata->req->cfile->fid.persistent_fid,
+				    tcon->tid, tcon->ses->Suid, rdata->subreq.start,
+				    rdata->subreq.len, rdata->result);
 	} else
-		trace_smb3_read_done(0 /* xid */,
-				     rdata->cfile->fid.persistent_fid,
+		trace_smb3_read_done(rdata->rreq->debug_id,
+				     rdata->subreq.debug_index,
+				     rdata->xid,
+				     rdata->req->cfile->fid.persistent_fid,
 				     tcon->tid, tcon->ses->Suid,
-				     rdata->offset, rdata->got_bytes);
+				     rdata->subreq.start, rdata->got_bytes);
 
-	queue_work(cifsiod_wq, &rdata->work);
+	if (rdata->result == -ENODATA) {
+		/* We may have got an EOF error because fallocate
+		 * failed to enlarge the file.
+		 */
+		if (rdata->subreq.start < rdata->subreq.rreq->i_size)
+			rdata->result = 0;
+	}
+	if (rdata->result == 0 || rdata->result == -EAGAIN)
+		iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes);
+	rdata->credits.value = 0;
+	netfs_subreq_terminated(&rdata->subreq,
+				(rdata->result == 0 || rdata->result == -EAGAIN) ?
+				rdata->got_bytes : rdata->result, true);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }
 
 /* smb2_async_readv - send an async read, and set up mid to handle result */
 int
-smb2_async_readv(struct cifs_readdata *rdata)
+smb2_async_readv(struct cifs_io_subrequest *rdata)
 {
 	int rc, flags = 0;
 	char *buf;
@@ -4579,22 +4598,22 @@ smb2_async_readv(struct cifs_readdata *rdata)
 	struct smb_rqst rqst = { .rq_iov = rdata->iov,
 				 .rq_nvec = 1 };
 	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
 	unsigned int total_len;
 	int credit_request;
 
-	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
-		 __func__, rdata->offset, rdata->bytes);
+	cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n",
+		 __func__, rdata->subreq.start, rdata->subreq.len);
 
 	if (!rdata->server)
 		rdata->server = cifs_pick_channel(tcon->ses);
 
-	io_parms.tcon = tlink_tcon(rdata->cfile->tlink);
+	io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink);
 	io_parms.server = server = rdata->server;
-	io_parms.offset = rdata->offset;
-	io_parms.length = rdata->bytes;
-	io_parms.persistent_fid = rdata->cfile->fid.persistent_fid;
-	io_parms.volatile_fid = rdata->cfile->fid.volatile_fid;
+	io_parms.offset = rdata->subreq.start;
+	io_parms.length = rdata->subreq.len;
+	io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
+	io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
 	io_parms.pid = rdata->pid;
 
 	rc = smb2_new_read_req(
@@ -4611,7 +4630,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 	shdr = (struct smb2_hdr *)buf;
 
 	if (rdata->credits.value > 0) {
-		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->subreq.len,
 						SMB2_MAX_BUFFER_SIZE));
 		credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
 		if (server->credits >= server->max_credits)
@@ -4621,22 +4640,22 @@ smb2_async_readv(struct cifs_readdata *rdata)
 				min_t(int, server->max_credits -
 						server->credits, credit_request));
 
-		rc = adjust_credits(server, &rdata->credits, rdata->bytes);
+		rc = adjust_credits(server, &rdata->credits, rdata->subreq.len);
 		if (rc)
 			goto async_readv_out;
 
 		flags |= CIFS_HAS_CREDITS;
 	}
 
-	kref_get(&rdata->refcount);
 	rc = cifs_call_async(server, &rqst,
 			     cifs_readv_receive, smb2_readv_callback,
 			     smb3_handle_read_data, rdata, flags,
 			     &rdata->credits);
 	if (rc) {
-		kref_put(&rdata->refcount, cifs_readdata_release);
 		cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
-		trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid,
+		trace_smb3_read_err(rdata->rreq->debug_id,
+				    rdata->subreq.debug_index,
+				    rdata->xid, io_parms.persistent_fid,
 				    io_parms.tcon->tid,
 				    io_parms.tcon->ses->Suid,
 				    io_parms.offset, io_parms.length, rc);
@@ -4687,22 +4706,23 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 		if (rc != -ENODATA) {
 			cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
 			cifs_dbg(VFS, "Send error in read = %d\n", rc);
-			trace_smb3_read_err(xid,
+			trace_smb3_read_err(0, 0, xid,
 					    req->PersistentFileId,
 					    io_parms->tcon->tid, ses->Suid,
 					    io_parms->offset, io_parms->length,
 					    rc);
 		} else
-			trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid,
+			trace_smb3_read_done(0, 0, xid,
+					     req->PersistentFileId, io_parms->tcon->tid,
 					     ses->Suid, io_parms->offset, 0);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 		cifs_small_buf_release(req);
 		return rc == -ENODATA ? 0 : rc;
 	} else
-		trace_smb3_read_done(xid,
-				    req->PersistentFileId,
-				    io_parms->tcon->tid, ses->Suid,
-				    io_parms->offset, io_parms->length);
+		trace_smb3_read_done(0, 0, xid,
+				     req->PersistentFileId,
+				     io_parms->tcon->tid, ses->Suid,
+				     io_parms->offset, io_parms->length);
 
 	cifs_small_buf_release(req);
 
@@ -4735,12 +4755,13 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 static void
 smb2_writev_callback(struct mid_q_entry *mid)
 {
-	struct cifs_writedata *wdata = mid->callback_data;
-	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
+	struct cifs_io_subrequest *wdata = mid->callback_data;
+	struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
 	struct TCP_Server_Info *server = wdata->server;
-	unsigned int written;
 	struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
 	struct cifs_credits credits = { .value = 0, .instance = 0 };
+	ssize_t result = 0;
+	size_t written;
 
 	WARN_ONCE(wdata->server != mid->server,
 		  "wdata server %p != mid server %p",
@@ -4750,8 +4771,8 @@ smb2_writev_callback(struct mid_q_entry *mid)
 	case MID_RESPONSE_RECEIVED:
 		credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
 		credits.instance = server->reconnect_instance;
-		wdata->result = smb2_check_receive(mid, server, 0);
-		if (wdata->result != 0)
+		result = smb2_check_receive(mid, server, 0);
+		if (result != 0)
 			break;
 
 		written = le32_to_cpu(rsp->DataLength);
@@ -4761,24 +4782,25 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		 * client. OS/2 servers are known to set incorrect
 		 * CountHigh values.
 		 */
-		if (written > wdata->bytes)
+		if (written > wdata->subreq.len)
 			written &= 0xFFFF;
 
-		if (written < wdata->bytes)
+		if (written < wdata->subreq.len)
 			wdata->result = -ENOSPC;
 		else
-			wdata->bytes = written;
+			wdata->subreq.len = written;
+		iov_iter_advance(&wdata->subreq.io_iter, written);
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
-		wdata->result = -EAGAIN;
+		result = -EAGAIN;
 		break;
 	case MID_RESPONSE_MALFORMED:
 		credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
 		credits.instance = server->reconnect_instance;
 		fallthrough;
 	default:
-		wdata->result = -EIO;
+		result = -EIO;
 		break;
 	}
 #ifdef CONFIG_CIFS_SMB_DIRECT
@@ -4794,44 +4816,44 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		wdata->mr = NULL;
 	}
 #endif
-	if (wdata->result) {
+	if (result) {
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
-		trace_smb3_write_err(0 /* no xid */,
-				     wdata->cfile->fid.persistent_fid,
-				     tcon->tid, tcon->ses->Suid, wdata->offset,
-				     wdata->bytes, wdata->result);
+		trace_smb3_write_err(wdata->xid,
+				     wdata->req->cfile->fid.persistent_fid,
+				     tcon->tid, tcon->ses->Suid, wdata->subreq.start,
+				     wdata->subreq.len, wdata->result);
 		if (wdata->result == -ENOSPC)
 			pr_warn_once("Out of space writing to %s\n",
 				     tcon->tree_name);
 	} else
 		trace_smb3_write_done(0 /* no xid */,
-				      wdata->cfile->fid.persistent_fid,
+				      wdata->req->cfile->fid.persistent_fid,
 				      tcon->tid, tcon->ses->Suid,
-				      wdata->offset, wdata->bytes);
+				      wdata->subreq.start, wdata->subreq.len);
 
-	queue_work(cifsiod_wq, &wdata->work);
+	wdata->credits.value = 0;
+	cifs_write_subrequest_terminated(wdata, result ?: written, true);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }
 
 /* smb2_async_writev - send an async write, and set up mid to handle result */
-int
-smb2_async_writev(struct cifs_writedata *wdata,
-		  void (*release)(struct kref *kref))
+void
+smb2_async_writev(struct cifs_io_subrequest *wdata)
 {
 	int rc = -EACCES, flags = 0;
 	struct smb2_write_req *req = NULL;
 	struct smb2_hdr *shdr;
-	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
+	struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
 	struct TCP_Server_Info *server = wdata->server;
 	struct kvec iov[1];
 	struct smb_rqst rqst = { };
-	unsigned int total_len;
+	unsigned int total_len, xid = wdata->xid;
 	struct cifs_io_parms _io_parms;
 	struct cifs_io_parms *io_parms = NULL;
 	int credit_request;
 
-	if (!wdata->server || wdata->replay)
+	if (!wdata->server || test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags))
 		server = wdata->server = cifs_pick_channel(tcon->ses);
 
 	/*
@@ -4841,10 +4863,10 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	_io_parms = (struct cifs_io_parms) {
 		.tcon = tcon,
 		.server = server,
-		.offset = wdata->offset,
-		.length = wdata->bytes,
-		.persistent_fid = wdata->cfile->fid.persistent_fid,
-		.volatile_fid = wdata->cfile->fid.volatile_fid,
+		.offset = wdata->subreq.start,
+		.length = wdata->subreq.len,
+		.persistent_fid = wdata->req->cfile->fid.persistent_fid,
+		.volatile_fid = wdata->req->cfile->fid.volatile_fid,
 		.pid = wdata->pid,
 	};
 	io_parms = &_io_parms;
@@ -4852,7 +4874,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	rc = smb2_plain_req_init(SMB2_WRITE, tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
-		return rc;
+		goto out;
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -4870,7 +4892,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 				offsetof(struct smb2_write_req, Buffer));
 	req->RemainingBytes = 0;
 
-	trace_smb3_write_enter(0 /* xid */,
+	trace_smb3_write_enter(wdata->xid,
 			       io_parms->persistent_fid,
 			       io_parms->tcon->tid,
 			       io_parms->tcon->ses->Suid,
@@ -4884,10 +4906,10 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	 */
 	if (smb3_use_rdma_offload(io_parms)) {
 		struct smbd_buffer_descriptor_v1 *v1;
-		size_t data_size = iov_iter_count(&wdata->iter);
+		size_t data_size = iov_iter_count(&wdata->subreq.io_iter);
 		bool need_invalidate = server->dialect == SMB30_PROT_ID;
 
-		wdata->mr = smbd_register_mr(server->smbd_conn, &wdata->iter,
+		wdata->mr = smbd_register_mr(server->smbd_conn, &wdata->subreq.io_iter,
 					     false, need_invalidate);
 		if (!wdata->mr) {
 			rc = -EAGAIN;
@@ -4914,9 +4936,9 @@ smb2_async_writev(struct cifs_writedata *wdata,
 
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
-	rqst.rq_iter = wdata->iter;
+	rqst.rq_iter = wdata->subreq.io_iter;
 	rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
-	if (wdata->replay)
+	if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags))
 		smb2_set_replay(server, &rqst);
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	if (wdata->mr)
@@ -4934,7 +4956,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
 #endif
 
 	if (wdata->credits.value > 0) {
-		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->subreq.len,
 						    SMB2_MAX_BUFFER_SIZE));
 		credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
 		if (server->credits >= server->max_credits)
@@ -4951,25 +4973,27 @@ smb2_async_writev(struct cifs_writedata *wdata,
 		flags |= CIFS_HAS_CREDITS;
 	}
 
-	kref_get(&wdata->refcount);
 	rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, NULL,
 			     wdata, flags, &wdata->credits);
-
+	/* Can't touch wdata if rc == 0 */
 	if (rc) {
-		trace_smb3_write_err(0 /* no xid */,
+		trace_smb3_write_err(xid,
 				     io_parms->persistent_fid,
 				     io_parms->tcon->tid,
 				     io_parms->tcon->ses->Suid,
 				     io_parms->offset,
 				     io_parms->length,
 				     rc);
-		kref_put(&wdata->refcount, release);
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
 	}
 
 async_writev_out:
 	cifs_small_buf_release(req);
-	return rc;
+out:
+	if (rc) {
+		add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
+		cifs_write_subrequest_terminated(wdata, rc, true);
+	}
 }
 
 /*
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 732169d8a67a..b208232b12a2 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -210,11 +210,10 @@ extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid,
 			    __le64 *uniqueid);
-extern int smb2_async_readv(struct cifs_readdata *rdata);
+extern int smb2_async_readv(struct cifs_io_subrequest *rdata);
 extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 		     unsigned int *nbytes, char **buf, int *buf_type);
-extern int smb2_async_writev(struct cifs_writedata *wdata,
-			     void (*release)(struct kref *kref));
+extern void smb2_async_writev(struct cifs_io_subrequest *wdata);
 extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 		      unsigned int *nbytes, struct kvec *iov, int n_vec);
 extern int SMB2_echo(struct TCP_Server_Info *server);
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 604e52876cd2..af97389e983e 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -85,6 +85,62 @@ smb3_tcon_ref_traces;
 
 /* For logging errors in read or write */
 DECLARE_EVENT_CLASS(smb3_rw_err_class,
+	TP_PROTO(unsigned int rreq_debug_id,
+		 unsigned int rreq_debug_index,
+		 unsigned int xid,
+		 __u64	fid,
+		 __u32	tid,
+		 __u64	sesid,
+		 __u64	offset,
+		 __u32	len,
+		 int	rc),
+	TP_ARGS(rreq_debug_id, rreq_debug_index,
+		xid, fid, tid, sesid, offset, len, rc),
+	TP_STRUCT__entry(
+		__field(unsigned int, rreq_debug_id)
+		__field(unsigned int, rreq_debug_index)
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, offset)
+		__field(__u32, len)
+		__field(int, rc)
+	),
+	TP_fast_assign(
+		__entry->rreq_debug_id = rreq_debug_id;
+		__entry->rreq_debug_index = rreq_debug_index;
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->offset = offset;
+		__entry->len = len;
+		__entry->rc = rc;
+	),
+	TP_printk("\tR=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
+		  __entry->rreq_debug_id, __entry->rreq_debug_index,
+		  __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		  __entry->offset, __entry->len, __entry->rc)
+)
+
+#define DEFINE_SMB3_RW_ERR_EVENT(name)          \
+DEFINE_EVENT(smb3_rw_err_class, smb3_##name,    \
+	TP_PROTO(unsigned int rreq_debug_id,	\
+		 unsigned int rreq_debug_index,		\
+		 unsigned int xid,			\
+		 __u64	fid,				\
+		 __u32	tid,				\
+		 __u64	sesid,				\
+		 __u64	offset,				\
+		 __u32	len,				\
+		 int	rc),				\
+	TP_ARGS(rreq_debug_id, rreq_debug_index, xid, fid, tid, sesid, offset, len, rc))
+
+DEFINE_SMB3_RW_ERR_EVENT(read_err);
+
+/* For logging errors in other file I/O ops */
+DECLARE_EVENT_CLASS(smb3_other_err_class,
 	TP_PROTO(unsigned int xid,
 		__u64	fid,
 		__u32	tid,
@@ -116,8 +172,8 @@ DECLARE_EVENT_CLASS(smb3_rw_err_class,
 		__entry->offset, __entry->len, __entry->rc)
 )
 
-#define DEFINE_SMB3_RW_ERR_EVENT(name)          \
-DEFINE_EVENT(smb3_rw_err_class, smb3_##name,    \
+#define DEFINE_SMB3_OTHER_ERR_EVENT(name)	\
+DEFINE_EVENT(smb3_other_err_class, smb3_##name, \
 	TP_PROTO(unsigned int xid,		\
 		__u64	fid,			\
 		__u32	tid,			\
@@ -127,15 +183,67 @@ DEFINE_EVENT(smb3_rw_err_class, smb3_##name,    \
 		int	rc),			\
 	TP_ARGS(xid, fid, tid, sesid, offset, len, rc))
 
-DEFINE_SMB3_RW_ERR_EVENT(write_err);
-DEFINE_SMB3_RW_ERR_EVENT(read_err);
-DEFINE_SMB3_RW_ERR_EVENT(query_dir_err);
-DEFINE_SMB3_RW_ERR_EVENT(zero_err);
-DEFINE_SMB3_RW_ERR_EVENT(falloc_err);
+DEFINE_SMB3_OTHER_ERR_EVENT(write_err);
+DEFINE_SMB3_OTHER_ERR_EVENT(query_dir_err);
+DEFINE_SMB3_OTHER_ERR_EVENT(zero_err);
+DEFINE_SMB3_OTHER_ERR_EVENT(falloc_err);
 
 
 /* For logging successful read or write */
 DECLARE_EVENT_CLASS(smb3_rw_done_class,
+	TP_PROTO(unsigned int rreq_debug_id,
+		 unsigned int rreq_debug_index,
+		 unsigned int xid,
+		 __u64	fid,
+		 __u32	tid,
+		 __u64	sesid,
+		 __u64	offset,
+		 __u32	len),
+	TP_ARGS(rreq_debug_id, rreq_debug_index,
+		xid, fid, tid, sesid, offset, len),
+	TP_STRUCT__entry(
+		__field(unsigned int, rreq_debug_id)
+		__field(unsigned int, rreq_debug_index)
+		__field(unsigned int, xid)
+		__field(__u64, fid)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, offset)
+		__field(__u32, len)
+	),
+	TP_fast_assign(
+		__entry->rreq_debug_id = rreq_debug_id;
+		__entry->rreq_debug_index = rreq_debug_index;
+		__entry->xid = xid;
+		__entry->fid = fid;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->offset = offset;
+		__entry->len = len;
+	),
+	TP_printk("R=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x",
+		  __entry->rreq_debug_id, __entry->rreq_debug_index,
+		  __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
+		  __entry->offset, __entry->len)
+)
+
+#define DEFINE_SMB3_RW_DONE_EVENT(name)         \
+DEFINE_EVENT(smb3_rw_done_class, smb3_##name,   \
+	TP_PROTO(unsigned int rreq_debug_id,	\
+		 unsigned int rreq_debug_index,	\
+		 unsigned int xid,		\
+		__u64	fid,			\
+		__u32	tid,			\
+		__u64	sesid,			\
+		__u64	offset,			\
+		__u32	len),			\
+	TP_ARGS(rreq_debug_id, rreq_debug_index, xid, fid, tid, sesid, offset, len))
+
+DEFINE_SMB3_RW_DONE_EVENT(read_enter);
+DEFINE_SMB3_RW_DONE_EVENT(read_done);
+
+/* For logging successful other op */
+DECLARE_EVENT_CLASS(smb3_other_done_class,
 	TP_PROTO(unsigned int xid,
 		__u64	fid,
 		__u32	tid,
@@ -164,8 +272,8 @@ DECLARE_EVENT_CLASS(smb3_rw_done_class,
 		__entry->offset, __entry->len)
 )
 
-#define DEFINE_SMB3_RW_DONE_EVENT(name)         \
-DEFINE_EVENT(smb3_rw_done_class, smb3_##name,   \
+#define DEFINE_SMB3_OTHER_DONE_EVENT(name)         \
+DEFINE_EVENT(smb3_other_done_class, smb3_##name,   \
 	TP_PROTO(unsigned int xid,		\
 		__u64	fid,			\
 		__u32	tid,			\
@@ -174,16 +282,14 @@ DEFINE_EVENT(smb3_rw_done_class, smb3_##name,   \
 		__u32	len),			\
 	TP_ARGS(xid, fid, tid, sesid, offset, len))
 
-DEFINE_SMB3_RW_DONE_EVENT(write_enter);
-DEFINE_SMB3_RW_DONE_EVENT(read_enter);
-DEFINE_SMB3_RW_DONE_EVENT(query_dir_enter);
-DEFINE_SMB3_RW_DONE_EVENT(zero_enter);
-DEFINE_SMB3_RW_DONE_EVENT(falloc_enter);
-DEFINE_SMB3_RW_DONE_EVENT(write_done);
-DEFINE_SMB3_RW_DONE_EVENT(read_done);
-DEFINE_SMB3_RW_DONE_EVENT(query_dir_done);
-DEFINE_SMB3_RW_DONE_EVENT(zero_done);
-DEFINE_SMB3_RW_DONE_EVENT(falloc_done);
+DEFINE_SMB3_OTHER_DONE_EVENT(write_enter);
+DEFINE_SMB3_OTHER_DONE_EVENT(query_dir_enter);
+DEFINE_SMB3_OTHER_DONE_EVENT(zero_enter);
+DEFINE_SMB3_OTHER_DONE_EVENT(falloc_enter);
+DEFINE_SMB3_OTHER_DONE_EVENT(write_done);
+DEFINE_SMB3_OTHER_DONE_EVENT(query_dir_done);
+DEFINE_SMB3_OTHER_DONE_EVENT(zero_done);
+DEFINE_SMB3_OTHER_DONE_EVENT(falloc_done);
 
 /* For logging successful set EOF (truncate) */
 DECLARE_EVENT_CLASS(smb3_eof_class,
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index ddf1a3aafee5..012b9bd06995 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -691,8 +691,8 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num,
 }
 
 int
-cifs_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size,
-		      unsigned int *num, struct cifs_credits *credits)
+cifs_wait_mtu_credits(struct TCP_Server_Info *server, size_t size,
+		      size_t *num, struct cifs_credits *credits)
 {
 	*num = size;
 	credits->value = 0;
@@ -1692,7 +1692,7 @@ __cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid,
 static int
 cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
-	struct cifs_readdata *rdata = mid->callback_data;
+	struct cifs_io_subrequest *rdata = mid->callback_data;
 
 	return  __cifs_readv_discard(server, mid, rdata->result);
 }
@@ -1702,13 +1702,13 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 {
 	int length, len;
 	unsigned int data_offset, data_len;
-	struct cifs_readdata *rdata = mid->callback_data;
+	struct cifs_io_subrequest *rdata = mid->callback_data;
 	char *buf = server->smallbuf;
 	unsigned int buflen = server->pdu_size + HEADER_PREAMBLE_SIZE(server);
 	bool use_rdma_mr = false;
 
-	cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%u\n",
-		 __func__, mid->mid, rdata->offset, rdata->bytes);
+	cifs_dbg(FYI, "%s: mid=%llu offset=%llu bytes=%zu\n",
+		 __func__, mid->mid, rdata->subreq.start, rdata->subreq.len);
 
 	/*
 	 * read the rest of READ_RSP header (sans Data array), or whatever we
@@ -1813,8 +1813,11 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		length = data_len; /* An RDMA read is already done. */
 	else
 #endif
-		length = cifs_read_iter_from_socket(server, &rdata->iter,
+	{
+		length = cifs_read_iter_from_socket(server, &rdata->subreq.io_iter,
 						    data_len);
+		iov_iter_revert(&rdata->subreq.io_iter, data_len);
+	}
 	if (length > 0)
 		rdata->got_bytes += length;
 	server->total_read += length;