1 files changed, 299 insertions, 203 deletions

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 86c647a947cc..4e28632b5fd6 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"
@@ -30,7 +32,7 @@
 #include "cifs_unicode.h"
 #include "cifs_debug.h"
 #include "ntlmssp.h"
-#include "smb2status.h"
+#include "../common/smb2status.h"
 #include "smb2glob.h"
 #include "cifspdu.h"
 #include "cifs_spnego.h"
@@ -40,6 +42,8 @@
 #include "dfs_cache.h"
 #endif
 #include "cached_dir.h"
+#include "compress.h"
+#include "fs_context.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -80,6 +84,9 @@ int smb3_encryption_required(const struct cifs_tcon *tcon)
 	if (tcon->seal &&
 	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
 		return 1;
+	if (((global_secflags & CIFSSEC_MUST_SEAL) == CIFSSEC_MUST_SEAL) &&
+	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+		return 1;
 	return 0;
 }
 
@@ -210,10 +217,9 @@ static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	       struct TCP_Server_Info *server, bool from_reconnect)
 {
-	int rc = 0;
-	struct nls_table *nls_codepage = NULL;
 	struct cifs_ses *ses;
 	int xid;
+	int rc = 0;
 
 	/*
 	 * SMB2s NegProt, SessSetup, Logoff do not have tcon yet so
@@ -223,11 +229,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	if (tcon == NULL)
 		return 0;
 
-	/*
-	 * Need to also skip SMB2_IOCTL because it is used for checking nested dfs links in
-	 * cifs_tree_connect().
-	 */
-	if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
+	if (smb2_command == SMB2_TREE_CONNECT)
 		return 0;
 
 	spin_lock(&tcon->tc_lock);
@@ -299,37 +301,26 @@ again:
 
 	mutex_lock(&ses->session_mutex);
 	/*
-	 * if this is called by delayed work, and the channel has been disabled
-	 * in parallel, the delayed work can continue to execute in parallel
-	 * there's a chance that this channel may not exist anymore
+	 * Handle the case where a concurrent thread failed to negotiate or
+	 * killed a channel.
 	 */
 	spin_lock(&server->srv_lock);
-	if (server->tcpStatus == CifsExiting) {
+	switch (server->tcpStatus) {
+	case CifsExiting:
 		spin_unlock(&server->srv_lock);
 		mutex_unlock(&ses->session_mutex);
-		rc = -EHOSTDOWN;
-		goto out;
-	}
-
-	/*
-	 * Recheck after acquire mutex. If another thread is negotiating
-	 * and the server never sends an answer the socket will be closed
-	 * and tcpStatus set to reconnect.
-	 */
-	if (server->tcpStatus == CifsNeedReconnect) {
+		return -EHOSTDOWN;
+	case CifsNeedReconnect:
 		spin_unlock(&server->srv_lock);
 		mutex_unlock(&ses->session_mutex);
-
-		if (tcon->retry)
-			goto again;
-
-		rc = -EHOSTDOWN;
-		goto out;
+		if (!tcon->retry)
+			return -EHOSTDOWN;
+		goto again;
+	default:
+		break;
 	}
 	spin_unlock(&server->srv_lock);
 
-	nls_codepage = ses->local_nls;
-
 	/*
 	 * need to prevent multiple threads trying to simultaneously
 	 * reconnect the same SMB session
@@ -351,43 +342,41 @@ again:
 	spin_unlock(&ses->ses_lock);
 
 	rc = cifs_negotiate_protocol(0, ses, server);
-	if (!rc) {
-		/*
-		 * if server stopped supporting multichannel
-		 * and the first channel reconnected, disable all the others.
-		 */
-		if (ses->chan_count > 1 &&
-		    !(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
-			rc = cifs_chan_skip_or_disable(ses, server,
-						       from_reconnect);
-			if (rc) {
-				mutex_unlock(&ses->session_mutex);
-				goto out;
-			}
-		}
-
-		rc = cifs_setup_session(0, ses, server, nls_codepage);
-		if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) {
-			/*
-			 * Try alternate password for next reconnect (key rotation
-			 * could be enabled on the server e.g.) if an alternate
-			 * password is available and the current password is expired,
-			 * but do not swap on non pwd related errors like host down
-			 */
-			if (ses->password2)
-				swap(ses->password2, ses->password);
-		}
-
-		if ((rc == -EACCES) && !tcon->retry) {
-			mutex_unlock(&ses->session_mutex);
-			rc = -EHOSTDOWN;
-			goto failed;
-		} else if (rc) {
+	if (rc) {
+		mutex_unlock(&ses->session_mutex);
+		if (!tcon->retry)
+			return -EHOSTDOWN;
+		goto again;
+	}
+	/*
+	 * if server stopped supporting multichannel
+	 * and the first channel reconnected, disable all the others.
+	 */
+	if (ses->chan_count > 1 &&
+	    !(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+		rc = cifs_chan_skip_or_disable(ses, server,
+					       from_reconnect);
+		if (rc) {
 			mutex_unlock(&ses->session_mutex);
 			goto out;
 		}
-	} else {
+	}
+
+	rc = cifs_setup_session(0, ses, server, ses->local_nls);
+	if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) {
+		/*
+		 * Try alternate password for next reconnect (key rotation
+		 * could be enabled on the server e.g.) if an alternate
+		 * password is available and the current password is expired,
+		 * but do not swap on non pwd related errors like host down
+		 */
+		if (ses->password2)
+			swap(ses->password2, ses->password);
+	}
+	if (rc) {
 		mutex_unlock(&ses->session_mutex);
+		if (rc == -EACCES && !tcon->retry)
+			return -EHOSTDOWN;
 		goto out;
 	}
 
@@ -400,7 +389,7 @@ skip_sess_setup:
 	if (tcon->use_persistent)
 		tcon->need_reopen_files = true;
 
-	rc = cifs_tree_connect(0, tcon, nls_codepage);
+	rc = cifs_tree_connect(0, tcon);
 
 	cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc);
 	if (rc) {
@@ -488,9 +477,9 @@ out:
 	case SMB2_CHANGE_NOTIFY:
 	case SMB2_QUERY_INFO:
 	case SMB2_SET_INFO:
+	case SMB2_IOCTL:
 		rc = -EAGAIN;
 	}
-failed:
 	return rc;
 }
 
@@ -1225,7 +1214,9 @@ SMB2_negotiate(const unsigned int xid,
 	 * SMB3.0 supports only 1 cipher and doesn't have a encryption neg context
 	 * Set the cipher type manually.
 	 */
-	if (server->dialect == SMB30_PROT_ID && (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+	if ((server->dialect == SMB30_PROT_ID ||
+	     server->dialect == SMB302_PROT_ID) &&
+	    (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
 		server->cipher_type = SMB2_ENCRYPTION_AES128_CCM;
 
 	security_blob = smb2_get_data_area_len(&blob_offset, &blob_length,
@@ -1260,6 +1251,9 @@ SMB2_negotiate(const unsigned int xid,
 		else
 			cifs_server_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
+
+	if (server->cipher_type && !rc)
+		rc = smb3_crypto_aead_allocate(server);
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1417,7 +1411,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		if (server->sec_ntlmssp &&
 			(global_secflags & CIFSSEC_MAY_NTLMSSP))
 			return RawNTLMSSP;
-		if ((server->sec_kerberos || server->sec_mskerberos) &&
+		if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) &&
 			(global_secflags & CIFSSEC_MAY_KRB5))
 			return Kerberos;
 		fallthrough;
@@ -1560,8 +1554,14 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 	cifs_small_buf_release(sess_data->iov[0].iov_base);
 	if (rc == 0)
 		sess_data->ses->expired_pwd = false;
-	else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED))
+	else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) {
+		if (sess_data->ses->expired_pwd == false)
+			trace_smb3_key_expired(sess_data->server->hostname,
+					       sess_data->ses->user_name,
+					       sess_data->server->conn_id,
+					       &sess_data->server->dstaddr, rc);
 		sess_data->ses->expired_pwd = true;
+	}
 
 	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
@@ -2151,7 +2151,7 @@ tcon_exit:
 
 tcon_error_exit:
 	if (rsp && rsp->hdr.Status == STATUS_BAD_NETWORK_NAME)
-		cifs_tcon_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
+		cifs_dbg(VFS | ONCE, "BAD_NETWORK_NAME: %s\n", tree);
 	goto tcon_exit;
 }
 
@@ -2311,7 +2311,7 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info,
 
 int smb2_parse_contexts(struct TCP_Server_Info *server,
 			struct kvec *rsp_iov,
-			unsigned int *epoch,
+			__u16 *epoch,
 			char *lease_key, __u8 *oplock,
 			struct smb2_file_all_info *buf,
 			struct create_posix_rsp *posix)
@@ -2612,7 +2612,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 	unsigned int group_offset = 0;
 	struct smb3_acl acl = {};
 
-	*len = round_up(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8);
+	*len = round_up(sizeof(struct crt_sd_ctxt) + (sizeof(struct smb_ace) * 4), 8);
 
 	if (set_owner) {
 		/* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */
@@ -2661,21 +2661,21 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 	ptr += sizeof(struct smb3_acl);
 
 	/* create one ACE to hold the mode embedded in reserved special SID */
-	acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode);
+	acelen = setup_special_mode_ACE((struct smb_ace *)ptr, false, (__u64)mode);
 	ptr += acelen;
 	acl_size = acelen + sizeof(struct smb3_acl);
 	ace_count = 1;
 
 	if (set_owner) {
 		/* we do not need to reallocate buffer to add the two more ACEs. plenty of space */
-		acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr);
+		acelen = setup_special_user_owner_ACE((struct smb_ace *)ptr);
 		ptr += acelen;
 		acl_size += acelen;
 		ace_count += 1;
 	}
 
 	/* and one more ACE to allow access for authenticated users */
-	acelen = setup_authusers_ACE((struct cifs_ace *)ptr);
+	acelen = setup_authusers_ACE((struct smb_ace *)ptr);
 	ptr += acelen;
 	acl_size += acelen;
 	ace_count += 1;
@@ -2921,6 +2921,7 @@ replay_again:
 		req->CreateContextsOffset = cpu_to_le32(
 			sizeof(struct smb2_create_req) +
 			iov[1].iov_len);
+		le32_add_cpu(&req->CreateContextsLength, iov[n_iov-1].iov_len);
 		pc_buf = iov[n_iov-1].iov_base;
 	}
 
@@ -2964,10 +2965,10 @@ replay_again:
 
 	SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
 
-	/* Eventually save off posix specific response info and timestaps */
+	/* Eventually save off posix specific response info and timestamps */
 
 err_free_rsp_buf:
-	free_rsp_buf(resp_buftype, rsp);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	kfree(pc_buf);
 err_free_req:
 	cifs_small_buf_release(req);
@@ -3895,7 +3896,7 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 		u64 persistent_fid, u64 volatile_fid, struct smb311_posix_qinfo *data, u32 *plen)
 {
 	size_t output_len = sizeof(struct smb311_posix_qinfo *) +
-			(sizeof(struct cifs_sid) * 2) + (PATH_MAX * 2);
+			(sizeof(struct smb_sid) * 2) + (PATH_MAX * 2);
 	*plen = 0;
 
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
@@ -3910,12 +3911,10 @@ SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 	       u64 persistent_fid, u64 volatile_fid,
 	       void **data, u32 *plen, u32 extra_info)
 {
-	__u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO |
-				extra_info;
 	*plen = 0;
 
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
-			  0, SMB2_O_INFO_SECURITY, additional_info,
+			  0, SMB2_O_INFO_SECURITY, extra_info,
 			  SMB2_MAX_BUFFER_SIZE, MIN_SEC_DESC_LEN, data, plen);
 }
 
@@ -4085,6 +4084,20 @@ smb2_echo_callback(struct mid_q_entry *mid)
 	add_credits(server, &credits, CIFS_ECHO_OP);
 }
 
+static void cifs_renegotiate_iosize(struct TCP_Server_Info *server,
+				    struct cifs_tcon *tcon)
+{
+	struct cifs_sb_info *cifs_sb;
+
+	if (server == NULL || tcon == NULL)
+		return;
+
+	spin_lock(&tcon->sb_list_lock);
+	list_for_each_entry(cifs_sb, &tcon->cifs_sb_list, tcon_sb_link)
+		cifs_negotiate_iosize(server, cifs_sb->ctx, tcon);
+	spin_unlock(&tcon->sb_list_lock);
+}
+
 void smb2_reconnect_server(struct work_struct *work)
 {
 	struct TCP_Server_Info *server = container_of(work,
@@ -4138,6 +4151,8 @@ void smb2_reconnect_server(struct work_struct *work)
 		list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
 			if (tcon->need_reconnect || tcon->need_reopen_files) {
 				tcon->tc_count++;
+				trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+						    netfs_trace_tcon_ref_get_reconnect_server);
 				list_add_tail(&tcon->rlist, &tmp_list);
 				tcon_selected = true;
 			}
@@ -4168,22 +4183,23 @@ void smb2_reconnect_server(struct work_struct *work)
 
 	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
 		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon, server, true);
-		if (!rc)
+		if (!rc) {
+			cifs_renegotiate_iosize(server, tcon);
 			cifs_reopen_persistent_handles(tcon);
-		else
+		} else
 			resched = true;
 		list_del_init(&tcon->rlist);
 		if (tcon->ipc)
 			cifs_put_smb_ses(tcon->ses);
 		else
-			cifs_put_tcon(tcon);
+			cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_reconnect_server);
 	}
 
 	if (!ses_exist)
 		goto done;
 
 	/* allocate a dummy tcon struct used for reconnect */
-	tcon = tcon_info_alloc(false);
+	tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_reconnect_server);
 	if (!tcon) {
 		resched = true;
 		list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) {
@@ -4206,7 +4222,7 @@ void smb2_reconnect_server(struct work_struct *work)
 		list_del_init(&ses->rlist);
 		cifs_put_smb_ses(ses);
 	}
-	tconInfoFree(tcon);
+	tconInfoFree(tcon, netfs_trace_tcon_ref_free_reconnect_server);
 
 done:
 	cifs_dbg(FYI, "Reconnecting tcons and channels finished\n");
@@ -4389,7 +4405,7 @@ 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;
@@ -4417,20 +4433,22 @@ 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
 	 * smbd_buffer_descriptor_v1 to the end of read request
 	 */
-	if (smb3_use_rdma_offload(io_parms)) {
+	if (rdata && smb3_use_rdma_offload(io_parms)) {
 		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;
@@ -4481,26 +4499,33 @@ 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 netfs_inode *ictx = netfs_inode(rdata->rreq->inode);
+	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;
-	struct cifs_credits credits = { .value = 0, .instance = 0 };
+	struct cifs_credits credits = {
+		.value = 0,
+		.instance = 0,
+		.rreq_debug_id = rdata->rreq->debug_id,
+		.rreq_debug_index = rdata->subreq.debug_index,
+	};
 	struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 };
+	unsigned int rreq_debug_id = rdata->rreq->debug_id;
+	unsigned int subreq_debug_index = rdata->subreq.debug_index;
 
 	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;
 	}
 
 	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/%zu\n",
 		 __func__, mid->mid, mid->mid_state, rdata->result,
-		 rdata->bytes);
+		 rdata->got_bytes, rdata->subreq.len - rdata->subreq.transferred);
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
@@ -4510,7 +4535,6 @@ 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)
@@ -4523,6 +4547,7 @@ smb2_readv_callback(struct mid_q_entry *mid)
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
+		__set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags);
 		rdata->result = -EAGAIN;
 		if (server->sign && rdata->got_bytes)
 			/* reset bytes number since we can not check a sign */
@@ -4540,7 +4565,7 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	}
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	/*
-	 * If this rdata has a memmory registered, the MR can be freed
+	 * If this rdata has a memory registered, the MR can be freed
 	 * MR needs to be freed as soon as I/O finishes to prevent deadlock
 	 * because they have limited number and are used for future I/Os
 	 */
@@ -4551,49 +4576,80 @@ 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.transferred,
+				    rdata->subreq.len   - rdata->subreq.transferred,
+				    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->subreq.transferred,
+				     rdata->got_bytes);
 
-	queue_work(cifsiod_wq, &rdata->work);
+	if (rdata->result == -ENODATA) {
+		__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+		rdata->result = 0;
+	} else {
+		size_t trans = rdata->subreq.transferred + rdata->got_bytes;
+		if (trans < rdata->subreq.len &&
+		    rdata->subreq.start + trans == ictx->remote_i_size) {
+			__set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+			rdata->result = 0;
+		}
+		if (rdata->got_bytes)
+			__set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags);
+	}
+	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
+			      server->credits, server->in_flight,
+			      0, cifs_trace_rw_credits_read_response_clear);
+	rdata->credits.value = 0;
+	rdata->subreq.error = rdata->result;
+	rdata->subreq.transferred += rdata->got_bytes;
+	trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(&rdata->subreq);
 	release_mid(mid);
+	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
+			      server->credits, server->in_flight,
+			      credits.value, cifs_trace_rw_credits_read_response_add);
 	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;
+	struct netfs_io_subrequest *subreq = &rdata->subreq;
 	struct smb2_hdr *shdr;
 	struct cifs_io_parms io_parms;
 	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__, subreq->start, 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.pid = rdata->pid;
+	io_parms.offset = subreq->start + subreq->transferred;
+	io_parms.length = subreq->len   - subreq->transferred;
+	io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
+	io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
+	io_parms.pid = rdata->req->pid;
 
 	rc = smb2_new_read_req(
 		(void **) &buf, &total_len, &io_parms, rdata, 0, 0);
@@ -4605,11 +4661,13 @@ smb2_async_readv(struct cifs_readdata *rdata)
 
 	rdata->iov[0].iov_base = buf;
 	rdata->iov[0].iov_len = total_len;
+	rdata->got_bytes = 0;
+	rdata->result = 0;
 
 	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(io_parms.length,
 						SMB2_MAX_BUFFER_SIZE));
 		credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
 		if (server->credits >= server->max_credits)
@@ -4619,25 +4677,26 @@ 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, cifs_trace_rw_credits_call_readv_adjust);
 		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,
+				    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);
+				    io_parms.offset,
+				    subreq->len - subreq->transferred, rc);
 	}
 
 async_readv_out:
@@ -4685,22 +4744,23 @@ 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);
 
@@ -4733,12 +4793,20 @@ 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 };
+	struct cifs_credits credits = {
+		.value = 0,
+		.instance = 0,
+		.rreq_debug_id = wdata->rreq->debug_id,
+		.rreq_debug_index = wdata->subreq.debug_index,
+	};
+	unsigned int rreq_debug_id = wdata->rreq->debug_id;
+	unsigned int subreq_debug_index = wdata->subreq.debug_index;
+	ssize_t result = 0;
+	size_t written;
 
 	WARN_ONCE(wdata->server != mid->server,
 		  "wdata server %p != mid server %p",
@@ -4748,8 +4816,8 @@ 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);
@@ -4759,24 +4827,28 @@ 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)
+		cifs_stats_bytes_written(tcon, written);
+
+		if (written < wdata->subreq.len) {
 			wdata->result = -ENOSPC;
-		else
-			wdata->bytes = written;
+		} else if (written > 0) {
+			wdata->subreq.len = written;
+			__set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags);
+		}
 		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
@@ -4792,46 +4864,54 @@ 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->rreq->debug_id,
+				     wdata->subreq.debug_index,
+				     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,
+		trace_smb3_write_done(wdata->rreq->debug_id,
+				      wdata->subreq.debug_index,
+				      wdata->xid,
+				      wdata->req->cfile->fid.persistent_fid,
 				      tcon->tid, tcon->ses->Suid,
-				      wdata->offset, wdata->bytes);
-
-	queue_work(cifsiod_wq, &wdata->work);
+				      wdata->subreq.start, wdata->subreq.len);
+
+	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, wdata->credits.value,
+			      server->credits, server->in_flight,
+			      0, cifs_trace_rw_credits_write_response_clear);
+	wdata->credits.value = 0;
+	trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress);
+	cifs_write_subrequest_terminated(wdata, result ?: written, true);
 	release_mid(mid);
+	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
+			      server->credits, server->in_flight,
+			      credits.value, cifs_trace_rw_credits_write_response_add);
 	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)
-		server = wdata->server = cifs_pick_channel(tcon->ses);
-
 	/*
 	 * in future we may get cifs_io_parms passed in from the caller,
 	 * but for now we construct it here...
@@ -4839,18 +4919,25 @@ 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,
-		.pid = wdata->pid,
+		.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->req->pid,
 	};
 	io_parms = &_io_parms;
 
 	rc = smb2_plain_req_init(SMB2_WRITE, tcon, server,
 				 (void **) &req, &total_len);
 	if (rc)
-		return rc;
+		goto out;
+
+	rqst.rq_iov = iov;
+	rqst.rq_iter = wdata->subreq.io_iter;
+
+	rqst.rq_iov[0].iov_len = total_len - 1;
+	rqst.rq_iov[0].iov_base = (char *)req;
+	rqst.rq_nvec += 1;
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
@@ -4863,12 +4950,15 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	req->WriteChannelInfoOffset = 0;
 	req->WriteChannelInfoLength = 0;
 	req->Channel = SMB2_CHANNEL_NONE;
+	req->Length = cpu_to_le32(io_parms->length);
 	req->Offset = cpu_to_le64(io_parms->offset);
 	req->DataOffset = cpu_to_le16(
 				offsetof(struct smb2_write_req, Buffer));
 	req->RemainingBytes = 0;
 
-	trace_smb3_write_enter(0 /* xid */,
+	trace_smb3_write_enter(wdata->rreq->debug_id,
+			       wdata->subreq.debug_index,
+			       wdata->xid,
 			       io_parms->persistent_fid,
 			       io_parms->tcon->tid,
 			       io_parms->tcon->ses->Suid,
@@ -4882,18 +4972,18 @@ 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);
 		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;
 			goto async_writev_out;
 		}
+		/* For RDMA read, I/O size is in RemainingBytes not in Length */
+		req->RemainingBytes = req->Length;
 		req->Length = 0;
 		req->DataOffset = 0;
-		req->RemainingBytes = cpu_to_le32(data_size);
 		req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE;
 		if (need_invalidate)
 			req->Channel = SMB2_CHANNEL_RDMA_V1;
@@ -4905,34 +4995,25 @@ smb2_async_writev(struct cifs_writedata *wdata,
 		v1->offset = cpu_to_le64(wdata->mr->mr->iova);
 		v1->token = cpu_to_le32(wdata->mr->mr->rkey);
 		v1->length = cpu_to_le32(wdata->mr->mr->length);
+
+		rqst.rq_iov[0].iov_len += sizeof(*v1);
+
+		/*
+		 * We keep wdata->subreq.io_iter,
+		 * but we have to truncate rqst.rq_iter
+		 */
+		iov_iter_truncate(&rqst.rq_iter, 0);
 	}
 #endif
-	iov[0].iov_len = total_len - 1;
-	iov[0].iov_base = (char *)req;
 
-	rqst.rq_iov = iov;
-	rqst.rq_nvec = 1;
-	rqst.rq_iter = wdata->iter;
-	rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
-	if (wdata->replay)
+	if (wdata->subreq.retry_count > 0)
 		smb2_set_replay(server, &rqst);
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	if (wdata->mr)
-		iov[0].iov_len += sizeof(struct smbd_buffer_descriptor_v1);
-#endif
-	cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n",
-		 io_parms->offset, io_parms->length, iov_iter_count(&rqst.rq_iter));
 
-#ifdef CONFIG_CIFS_SMB_DIRECT
-	/* For RDMA read, I/O size is in RemainingBytes not in Length */
-	if (!wdata->mr)
-		req->Length = cpu_to_le32(io_parms->length);
-#else
-	req->Length = cpu_to_le32(io_parms->length);
-#endif
+	cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n",
+		 io_parms->offset, io_parms->length, iov_iter_count(&wdata->subreq.io_iter));
 
 	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)
@@ -4942,32 +5023,46 @@ smb2_async_writev(struct cifs_writedata *wdata,
 				min_t(int, server->max_credits -
 						server->credits, credit_request));
 
-		rc = adjust_credits(server, &wdata->credits, io_parms->length);
+		rc = adjust_credits(server, wdata, cifs_trace_rw_credits_call_writev_adjust);
 		if (rc)
 			goto async_writev_out;
 
 		flags |= CIFS_HAS_CREDITS;
 	}
 
-	kref_get(&wdata->refcount);
+	/* XXX: compression + encryption is unsupported for now */
+	if (((flags & CIFS_TRANSFORM_REQ) != CIFS_TRANSFORM_REQ) && should_compress(tcon, &rqst))
+		flags |= CIFS_COMPRESS_REQ;
+
 	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(wdata->rreq->debug_id,
+				     wdata->subreq.debug_index,
+				     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) {
+		trace_smb3_rw_credits(wdata->rreq->debug_id,
+				      wdata->subreq.debug_index,
+				      wdata->credits.value,
+				      server->credits, server->in_flight,
+				      -(int)wdata->credits.value,
+				      cifs_trace_rw_credits_write_response_clear);
+		add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
+		cifs_write_subrequest_terminated(wdata, rc, true);
+	}
 }
 
 /*
@@ -5025,7 +5120,7 @@ replay_again:
 				offsetof(struct smb2_write_req, Buffer));
 	req->RemainingBytes = 0;
 
-	trace_smb3_write_enter(xid, io_parms->persistent_fid,
+	trace_smb3_write_enter(0, 0, xid, io_parms->persistent_fid,
 		io_parms->tcon->tid, io_parms->tcon->ses->Suid,
 		io_parms->offset, io_parms->length);
 
@@ -5046,7 +5141,7 @@ replay_again:
 	rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
-		trace_smb3_write_err(xid,
+		trace_smb3_write_err(0, 0, xid,
 				     req->PersistentFileId,
 				     io_parms->tcon->tid,
 				     io_parms->tcon->ses->Suid,
@@ -5055,7 +5150,8 @@ replay_again:
 		cifs_dbg(VFS, "Send error in write = %d\n", rc);
 	} else {
 		*nbytes = le32_to_cpu(rsp->DataLength);
-		trace_smb3_write_done(xid,
+		cifs_stats_bytes_written(io_parms->tcon, *nbytes);
+		trace_smb3_write_done(0, 0, xid,
 				      req->PersistentFileId,
 				      io_parms->tcon->tid,
 				      io_parms->tcon->ses->Suid,
@@ -5604,7 +5700,7 @@ SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 int
 SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon,
 		u64 persistent_fid, u64 volatile_fid,
-		struct cifs_ntsd *pnntsd, int pacllen, int aclflag)
+		struct smb_ntsd *pnntsd, int pacllen, int aclflag)
 {
 	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
 			current->tgid, 0, SMB2_O_INFO_SECURITY, aclflag,
@@ -6103,7 +6199,7 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 	req->StructureSize = cpu_to_le16(36);
 	total_len += 12;
 
-	memcpy(req->LeaseKey, lease_key, 16);
+	memcpy(req->LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	req->LeaseState = lease_state;
 
 	flags |= CIFS_NO_RSP_BUF;