Merge v6.16.9linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

14 files changed, 287 insertions, 179 deletions

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 8c597fa60523..41e4b3d4f2b5 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
 
 int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_inode_item *inode_item;
 	struct inode *vfs_inode = &inode->vfs_inode;
@@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev)
 	i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item));
 	i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item));
 	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
-	btrfs_inode_set_file_extent_range(inode, 0,
-			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 	vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item);
 	set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item));
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e266a2294848..eb73025d4e4a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3881,10 +3881,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	bool filled = false;
 	int first_xattr_slot;
 
-	ret = btrfs_init_file_extent_tree(inode);
-	if (ret)
-		goto out;
-
 	ret = btrfs_fill_inode(inode, &rdev);
 	if (!ret)
 		filled = true;
@@ -3916,8 +3912,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item));
 	i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item));
 	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
-	btrfs_inode_set_file_extent_range(inode, 0,
-			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 
 	inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime),
 			btrfs_timespec_nsec(leaf, &inode_item->atime));
@@ -3948,6 +3942,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	btrfs_update_inode_mapping_flags(inode);
 
 cache_index:
+	ret = btrfs_init_file_extent_tree(inode);
+	if (ret)
+		goto out;
+	btrfs_inode_set_file_extent_range(inode, 0,
+			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 	/*
 	 * If we were modified in the current generation and evicted from memory
 	 * and then re-read we need to do a full sync since we don't have any
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8f4703b488b7..b59d01b976ff 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1756,10 +1756,10 @@ static int check_inode_ref(struct extent_buffer *leaf,
 	while (ptr < end) {
 		u16 namelen;
 
-		if (unlikely(ptr + sizeof(iref) > end)) {
+		if (unlikely(ptr + sizeof(*iref) > end)) {
 			inode_ref_err(leaf, slot,
 			"inode ref overflow, ptr %lu end %lu inode_ref_size %zu",
-				ptr, end, sizeof(iref));
+				ptr, end, sizeof(*iref));
 			return -EUCLEAN;
 		}
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 56d30ec0f52f..5466a93a28f5 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1933,7 +1933,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 
 	search_key.objectid = log_key.objectid;
 	search_key.type = BTRFS_INODE_EXTREF_KEY;
-	search_key.offset = key->objectid;
+	search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len);
 	ret = backref_in_log(root->log_root, &search_key, key->objectid, &name);
 	if (ret < 0) {
 		goto out;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index d7a1193332d9..60937127a0bc 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2577,9 +2577,9 @@ again:
 			spin_lock(&space_info->lock);
 			space_info->total_bytes -= bg->length;
 			space_info->disk_total -= bg->length * factor;
+			space_info->disk_total -= bg->zone_unusable;
 			/* There is no allocation ever happened. */
 			ASSERT(bg->used == 0);
-			ASSERT(bg->zone_unusable == 0);
 			/* No super block in a block group on the zoned setup. */
 			ASSERT(bg->bytes_super == 0);
 			spin_unlock(&space_info->lock);
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index 14868a3dd592..bc52afbfc5c7 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -1075,7 +1075,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs)
  ************************************************************************/
 
 static ssize_t nilfs_feature_revision_show(struct kobject *kobj,
-					    struct attribute *attr, char *buf)
+					    struct kobj_attribute *attr, char *buf)
 {
 	return sysfs_emit(buf, "%d.%d\n",
 			NILFS_CURRENT_REV, NILFS_MINOR_REV);
@@ -1087,7 +1087,7 @@ static const char features_readme_str[] =
 	"(1) revision\n\tshow current revision of NILFS file system driver.\n";
 
 static ssize_t nilfs_feature_README_show(struct kobject *kobj,
-					 struct attribute *attr,
+					 struct kobj_attribute *attr,
 					 char *buf)
 {
 	return sysfs_emit(buf, features_readme_str);
diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h
index 78a87a016928..d370cd5cce3f 100644
--- a/fs/nilfs2/sysfs.h
+++ b/fs/nilfs2/sysfs.h
@@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups {
 	struct completion sg_segments_kobj_unregister;
 };
 
-#define NILFS_COMMON_ATTR_STRUCT(name) \
+#define NILFS_KOBJ_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \
 	struct attribute attr; \
-	ssize_t (*show)(struct kobject *, struct attribute *, \
+	ssize_t (*show)(struct kobject *, struct kobj_attribute *, \
 			char *); \
-	ssize_t (*store)(struct kobject *, struct attribute *, \
+	ssize_t (*store)(struct kobject *, struct kobj_attribute *, \
 			 const char *, size_t); \
 }
 
-NILFS_COMMON_ATTR_STRUCT(feature);
+NILFS_KOBJ_ATTR_STRUCT(feature);
 
 #define NILFS_DEV_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 045227ed4efc..0dcea9acca54 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -297,8 +297,8 @@ extern void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode);
 
 extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon);
 
-extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon,
-				const char *path);
+void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon,
+					   struct dentry *dentry);
 
 extern void cifs_mark_open_handles_for_deleted_file(struct inode *inode,
 				const char *path);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 11d442e8b3d6..0f0d2dae6283 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1984,7 +1984,7 @@ static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyren
 	}
 
 	netfs_wait_for_outstanding_io(inode);
-	cifs_close_deferred_file_under_dentry(tcon, full_path);
+	cifs_close_deferred_file_under_dentry(tcon, dentry);
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
@@ -2003,8 +2003,21 @@ retry_std_delete:
 		goto psx_del_no_retry;
 	}
 
-	if (sillyrename || (server->vals->protocol_id > SMB10_PROT_ID &&
-			    d_is_positive(dentry) && d_count(dentry) > 2))
+	/* For SMB2+, if the file is open, we always perform a silly rename.
+	 *
+	 * We check for d_count() right after calling
+	 * cifs_close_deferred_file_under_dentry() to make sure that the
+	 * dentry's refcount gets dropped in case the file had any deferred
+	 * close.
+	 */
+	if (!sillyrename && server->vals->protocol_id > SMB10_PROT_ID) {
+		spin_lock(&dentry->d_lock);
+		if (d_count(dentry) > 1)
+			sillyrename = true;
+		spin_unlock(&dentry->d_lock);
+	}
+
+	if (sillyrename)
 		rc = -EBUSY;
 	else
 		rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry);
@@ -2538,10 +2551,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
 		goto cifs_rename_exit;
 	}
 
-	cifs_close_deferred_file_under_dentry(tcon, from_name);
+	cifs_close_deferred_file_under_dentry(tcon, source_dentry);
 	if (d_inode(target_dentry) != NULL) {
 		netfs_wait_for_outstanding_io(d_inode(target_dentry));
-		cifs_close_deferred_file_under_dentry(tcon, to_name);
+		cifs_close_deferred_file_under_dentry(tcon, target_dentry);
 	}
 
 	rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry,
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index da23cc12a52c..dda6dece802a 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -832,33 +832,28 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon)
 		kfree(tmp_list);
 	}
 }
-void
-cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path)
+
+void cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon,
+					   struct dentry *dentry)
 {
-	struct cifsFileInfo *cfile;
 	struct file_list *tmp_list, *tmp_next_list;
-	void *page;
-	const char *full_path;
+	struct cifsFileInfo *cfile;
 	LIST_HEAD(file_head);
 
-	page = alloc_dentry_path();
 	spin_lock(&tcon->open_file_lock);
 	list_for_each_entry(cfile, &tcon->openFileList, tlist) {
-		full_path = build_path_from_dentry(cfile->dentry, page);
-		if (strstr(full_path, path)) {
-			if (delayed_work_pending(&cfile->deferred)) {
-				if (cancel_delayed_work(&cfile->deferred)) {
-					spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
-					cifs_del_deferred_close(cfile);
-					spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
-
-					tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
-					if (tmp_list == NULL)
-						break;
-					tmp_list->cfile = cfile;
-					list_add_tail(&tmp_list->list, &file_head);
-				}
-			}
+		if ((cfile->dentry == dentry) &&
+		    delayed_work_pending(&cfile->deferred) &&
+		    cancel_delayed_work(&cfile->deferred)) {
+			spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
+			cifs_del_deferred_close(cfile);
+			spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock);
+
+			tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC);
+			if (tmp_list == NULL)
+				break;
+			tmp_list->cfile = cfile;
+			list_add_tail(&tmp_list->list, &file_head);
 		}
 	}
 	spin_unlock(&tcon->open_file_lock);
@@ -868,7 +863,6 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path)
 		list_del(&tmp_list->list);
 		kfree(tmp_list);
 	}
-	free_dentry_path(page);
 }
 
 /*
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index b9bb531717a6..6dd2a1c66df3 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -13,23 +13,23 @@
 #include "cifsproto.h"
 #include "smb2proto.h"
 
-static struct smbd_response *get_receive_buffer(
+static struct smbdirect_recv_io *get_receive_buffer(
 		struct smbd_connection *info);
 static void put_receive_buffer(
 		struct smbd_connection *info,
-		struct smbd_response *response);
+		struct smbdirect_recv_io *response);
 static int allocate_receive_buffers(struct smbd_connection *info, int num_buf);
 static void destroy_receive_buffers(struct smbd_connection *info);
 
 static void enqueue_reassembly(
 		struct smbd_connection *info,
-		struct smbd_response *response, int data_length);
-static struct smbd_response *_get_first_reassembly(
+		struct smbdirect_recv_io *response, int data_length);
+static struct smbdirect_recv_io *_get_first_reassembly(
 		struct smbd_connection *info);
 
 static int smbd_post_recv(
 		struct smbd_connection *info,
-		struct smbd_response *response);
+		struct smbdirect_recv_io *response);
 
 static int smbd_post_send_empty(struct smbd_connection *info);
 
@@ -260,7 +260,7 @@ static inline void *smbd_request_payload(struct smbd_request *request)
 	return (void *)request->packet;
 }
 
-static inline void *smbd_response_payload(struct smbd_response *response)
+static inline void *smbdirect_recv_io_payload(struct smbdirect_recv_io *response)
 {
 	return (void *)response->packet;
 }
@@ -315,12 +315,13 @@ static void dump_smbdirect_negotiate_resp(struct smbdirect_negotiate_resp *resp)
  * return value: true if negotiation is a success, false if failed
  */
 static bool process_negotiation_response(
-		struct smbd_response *response, int packet_length)
+		struct smbdirect_recv_io *response, int packet_length)
 {
-	struct smbd_connection *info = response->info;
-	struct smbdirect_socket *sc = &info->socket;
+	struct smbdirect_socket *sc = response->socket;
+	struct smbd_connection *info =
+		container_of(sc, struct smbd_connection, socket);
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
-	struct smbdirect_negotiate_resp *packet = smbd_response_payload(response);
+	struct smbdirect_negotiate_resp *packet = smbdirect_recv_io_payload(response);
 
 	if (packet_length < sizeof(struct smbdirect_negotiate_resp)) {
 		log_rdma_event(ERR,
@@ -383,6 +384,7 @@ static bool process_negotiation_response(
 			info->max_frmr_depth * PAGE_SIZE);
 	info->max_frmr_depth = sp->max_read_write_size / PAGE_SIZE;
 
+	sc->recv_io.expected = SMBDIRECT_EXPECT_DATA_TRANSFER;
 	return true;
 }
 
@@ -390,7 +392,7 @@ static void smbd_post_send_credits(struct work_struct *work)
 {
 	int ret = 0;
 	int rc;
-	struct smbd_response *response;
+	struct smbdirect_recv_io *response;
 	struct smbd_connection *info =
 		container_of(work, struct smbd_connection,
 			post_send_credits_work);
@@ -408,7 +410,6 @@ static void smbd_post_send_credits(struct work_struct *work)
 			if (!response)
 				break;
 
-			response->type = SMBD_TRANSFER_DATA;
 			response->first_segment = false;
 			rc = smbd_post_recv(info, response);
 			if (rc) {
@@ -442,13 +443,18 @@ static void smbd_post_send_credits(struct work_struct *work)
 static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct smbdirect_data_transfer *data_transfer;
-	struct smbd_response *response =
-		container_of(wc->wr_cqe, struct smbd_response, cqe);
-	struct smbd_connection *info = response->info;
-	int data_length = 0;
+	struct smbdirect_recv_io *response =
+		container_of(wc->wr_cqe, struct smbdirect_recv_io, cqe);
+	struct smbdirect_socket *sc = response->socket;
+	struct smbdirect_socket_parameters *sp = &sc->parameters;
+	struct smbd_connection *info =
+		container_of(sc, struct smbd_connection, socket);
+	u32 data_offset = 0;
+	u32 data_length = 0;
+	u32 remaining_data_length = 0;
 
 	log_rdma_recv(INFO, "response=0x%p type=%d wc status=%d wc opcode %d byte_len=%d pkey_index=%u\n",
-		      response, response->type, wc->status, wc->opcode,
+		      response, sc->recv_io.expected, wc->status, wc->opcode,
 		      wc->byte_len, wc->pkey_index);
 
 	if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) {
@@ -463,10 +469,10 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		response->sge.length,
 		DMA_FROM_DEVICE);
 
-	switch (response->type) {
+	switch (sc->recv_io.expected) {
 	/* SMBD negotiation response */
-	case SMBD_NEGOTIATE_RESP:
-		dump_smbdirect_negotiate_resp(smbd_response_payload(response));
+	case SMBDIRECT_EXPECT_NEGOTIATE_REP:
+		dump_smbdirect_negotiate_resp(smbdirect_recv_io_payload(response));
 		info->full_packet_received = true;
 		info->negotiate_done =
 			process_negotiation_response(response, wc->byte_len);
@@ -475,9 +481,24 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 
 	/* SMBD data transfer packet */
-	case SMBD_TRANSFER_DATA:
-		data_transfer = smbd_response_payload(response);
+	case SMBDIRECT_EXPECT_DATA_TRANSFER:
+		data_transfer = smbdirect_recv_io_payload(response);
+
+		if (wc->byte_len <
+		    offsetof(struct smbdirect_data_transfer, padding))
+			goto error;
+
+		remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length);
+		data_offset = le32_to_cpu(data_transfer->data_offset);
 		data_length = le32_to_cpu(data_transfer->data_length);
+		if (wc->byte_len < data_offset ||
+		    (u64)wc->byte_len < (u64)data_offset + data_length)
+			goto error;
+
+		if (remaining_data_length > sp->max_fragmented_recv_size ||
+		    data_length > sp->max_fragmented_recv_size ||
+		    (u64)remaining_data_length + (u64)data_length > (u64)sp->max_fragmented_recv_size)
+			goto error;
 
 		if (data_length) {
 			if (info->full_packet_received)
@@ -526,13 +547,17 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			put_receive_buffer(info, response);
 
 		return;
+
+	case SMBDIRECT_EXPECT_NEGOTIATE_REQ:
+		/* Only server... */
+		break;
 	}
 
 	/*
 	 * This is an internal error!
 	 */
-	log_rdma_recv(ERR, "unexpected response type=%d\n", response->type);
-	WARN_ON_ONCE(response->type != SMBD_TRANSFER_DATA);
+	log_rdma_recv(ERR, "unexpected response type=%d\n", sc->recv_io.expected);
+	WARN_ON_ONCE(sc->recv_io.expected != SMBDIRECT_EXPECT_DATA_TRANSFER);
 error:
 	put_receive_buffer(info, response);
 	smbd_disconnect_rdma_connection(info);
@@ -1029,7 +1054,7 @@ static int smbd_post_send_full_iter(struct smbd_connection *info,
  * The interaction is controlled by send/receive credit system
  */
 static int smbd_post_recv(
-		struct smbd_connection *info, struct smbd_response *response)
+		struct smbd_connection *info, struct smbdirect_recv_io *response)
 {
 	struct smbdirect_socket *sc = &info->socket;
 	struct smbdirect_socket_parameters *sp = &sc->parameters;
@@ -1067,16 +1092,19 @@ static int smbd_post_recv(
 /* Perform SMBD negotiate according to [MS-SMBD] 3.1.5.2 */
 static int smbd_negotiate(struct smbd_connection *info)
 {
+	struct smbdirect_socket *sc = &info->socket;
 	int rc;
-	struct smbd_response *response = get_receive_buffer(info);
+	struct smbdirect_recv_io *response = get_receive_buffer(info);
 
-	response->type = SMBD_NEGOTIATE_RESP;
+	sc->recv_io.expected = SMBDIRECT_EXPECT_NEGOTIATE_REP;
 	rc = smbd_post_recv(info, response);
 	log_rdma_event(INFO, "smbd_post_recv rc=%d iov.addr=0x%llx iov.length=%u iov.lkey=0x%x\n",
 		       rc, response->sge.addr,
 		       response->sge.length, response->sge.lkey);
-	if (rc)
+	if (rc) {
+		put_receive_buffer(info, response);
 		return rc;
+	}
 
 	init_completion(&info->negotiate_completion);
 	info->negotiate_done = false;
@@ -1113,7 +1141,7 @@ static int smbd_negotiate(struct smbd_connection *info)
  */
 static void enqueue_reassembly(
 	struct smbd_connection *info,
-	struct smbd_response *response,
+	struct smbdirect_recv_io *response,
 	int data_length)
 {
 	spin_lock(&info->reassembly_queue_lock);
@@ -1137,14 +1165,14 @@ static void enqueue_reassembly(
  * Caller is responsible for locking
  * return value: the first entry if any, NULL if queue is empty
  */
-static struct smbd_response *_get_first_reassembly(struct smbd_connection *info)
+static struct smbdirect_recv_io *_get_first_reassembly(struct smbd_connection *info)
 {
-	struct smbd_response *ret = NULL;
+	struct smbdirect_recv_io *ret = NULL;
 
 	if (!list_empty(&info->reassembly_queue)) {
 		ret = list_first_entry(
 			&info->reassembly_queue,
-			struct smbd_response, list);
+			struct smbdirect_recv_io, list);
 	}
 	return ret;
 }
@@ -1155,16 +1183,16 @@ static struct smbd_response *_get_first_reassembly(struct smbd_connection *info)
  * pre-allocated in advance.
  * return value: the receive buffer, NULL if none is available
  */
-static struct smbd_response *get_receive_buffer(struct smbd_connection *info)
+static struct smbdirect_recv_io *get_receive_buffer(struct smbd_connection *info)
 {
-	struct smbd_response *ret = NULL;
+	struct smbdirect_recv_io *ret = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&info->receive_queue_lock, flags);
 	if (!list_empty(&info->receive_queue)) {
 		ret = list_first_entry(
 			&info->receive_queue,
-			struct smbd_response, list);
+			struct smbdirect_recv_io, list);
 		list_del(&ret->list);
 		info->count_receive_queue--;
 		info->count_get_receive_buffer++;
@@ -1181,7 +1209,7 @@ static struct smbd_response *get_receive_buffer(struct smbd_connection *info)
  * receive buffer is returned.
  */
 static void put_receive_buffer(
-	struct smbd_connection *info, struct smbd_response *response)
+	struct smbd_connection *info, struct smbdirect_recv_io *response)
 {
 	struct smbdirect_socket *sc = &info->socket;
 	unsigned long flags;
@@ -1206,8 +1234,9 @@ static void put_receive_buffer(
 /* Preallocate all receive buffer on transport establishment */
 static int allocate_receive_buffers(struct smbd_connection *info, int num_buf)
 {
+	struct smbdirect_socket *sc = &info->socket;
+	struct smbdirect_recv_io *response;
 	int i;
-	struct smbd_response *response;
 
 	INIT_LIST_HEAD(&info->reassembly_queue);
 	spin_lock_init(&info->reassembly_queue_lock);
@@ -1225,7 +1254,7 @@ static int allocate_receive_buffers(struct smbd_connection *info, int num_buf)
 		if (!response)
 			goto allocate_failed;
 
-		response->info = info;
+		response->socket = sc;
 		response->sge.length = 0;
 		list_add_tail(&response->list, &info->receive_queue);
 		info->count_receive_queue++;
@@ -1237,7 +1266,7 @@ allocate_failed:
 	while (!list_empty(&info->receive_queue)) {
 		response = list_first_entry(
 				&info->receive_queue,
-				struct smbd_response, list);
+				struct smbdirect_recv_io, list);
 		list_del(&response->list);
 		info->count_receive_queue--;
 
@@ -1248,7 +1277,7 @@ allocate_failed:
 
 static void destroy_receive_buffers(struct smbd_connection *info)
 {
-	struct smbd_response *response;
+	struct smbdirect_recv_io *response;
 
 	while ((response = get_receive_buffer(info)))
 		mempool_free(response, info->response_mempool);
@@ -1289,7 +1318,7 @@ void smbd_destroy(struct TCP_Server_Info *server)
 	struct smbd_connection *info = server->smbd_conn;
 	struct smbdirect_socket *sc;
 	struct smbdirect_socket_parameters *sp;
-	struct smbd_response *response;
+	struct smbdirect_recv_io *response;
 	unsigned long flags;
 
 	if (!info) {
@@ -1308,13 +1337,16 @@ void smbd_destroy(struct TCP_Server_Info *server)
 			sc->status == SMBDIRECT_SOCKET_DISCONNECTED);
 	}
 
+	log_rdma_event(INFO, "cancelling post_send_credits_work\n");
+	disable_work_sync(&info->post_send_credits_work);
+
 	log_rdma_event(INFO, "destroying qp\n");
 	ib_drain_qp(sc->ib.qp);
 	rdma_destroy_qp(sc->rdma.cm_id);
 	sc->ib.qp = NULL;
 
 	log_rdma_event(INFO, "cancelling idle timer\n");
-	cancel_delayed_work_sync(&info->idle_timer_work);
+	disable_delayed_work_sync(&info->idle_timer_work);
 
 	/* It's not possible for upper layer to get to reassembly */
 	log_rdma_event(INFO, "drain the reassembly queue\n");
@@ -1446,17 +1478,17 @@ static int allocate_caches_and_workqueue(struct smbd_connection *info)
 	if (!info->request_mempool)
 		goto out1;
 
-	scnprintf(name, MAX_NAME_LEN, "smbd_response_%p", info);
+	scnprintf(name, MAX_NAME_LEN, "smbdirect_recv_io_%p", info);
 
 	struct kmem_cache_args response_args = {
-		.align		= __alignof__(struct smbd_response),
-		.useroffset	= (offsetof(struct smbd_response, packet) +
+		.align		= __alignof__(struct smbdirect_recv_io),
+		.useroffset	= (offsetof(struct smbdirect_recv_io, packet) +
 				   sizeof(struct smbdirect_data_transfer)),
 		.usersize	= sp->max_recv_size - sizeof(struct smbdirect_data_transfer),
 	};
 	info->response_cache =
 		kmem_cache_create(name,
-				  sizeof(struct smbd_response) + sp->max_recv_size,
+				  sizeof(struct smbdirect_recv_io) + sp->max_recv_size,
 				  &response_args, SLAB_HWCACHE_ALIGN);
 	if (!info->response_cache)
 		goto out2;
@@ -1686,7 +1718,7 @@ allocate_mr_failed:
 	return NULL;
 
 negotiation_failed:
-	cancel_delayed_work_sync(&info->idle_timer_work);
+	disable_delayed_work_sync(&info->idle_timer_work);
 	destroy_caches_and_workqueue(info);
 	sc->status = SMBDIRECT_SOCKET_NEGOTIATE_FAILED;
 	rdma_disconnect(sc->rdma.cm_id);
@@ -1747,7 +1779,7 @@ try_again:
 int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
 {
 	struct smbdirect_socket *sc = &info->socket;
-	struct smbd_response *response;
+	struct smbdirect_recv_io *response;
 	struct smbdirect_data_transfer *data_transfer;
 	size_t size = iov_iter_count(&msg->msg_iter);
 	int to_copy, to_read, data_read, offset;
@@ -1783,7 +1815,7 @@ again:
 		offset = info->first_entry_offset;
 		while (data_read < size) {
 			response = _get_first_reassembly(info);
-			data_transfer = smbd_response_payload(response);
+			data_transfer = smbdirect_recv_io_payload(response);
 			data_length = le32_to_cpu(data_transfer->data_length);
 			remaining_data_length =
 				le32_to_cpu(
@@ -2045,7 +2077,7 @@ static void destroy_mr_list(struct smbd_connection *info)
 	struct smbdirect_socket *sc = &info->socket;
 	struct smbd_mr *mr, *tmp;
 
-	cancel_work_sync(&info->mr_recovery_work);
+	disable_work_sync(&info->mr_recovery_work);
 	list_for_each_entry_safe(mr, tmp, &info->mr_list, list) {
 		if (mr->state == MR_INVALIDATED)
 			ib_dma_unmap_sg(sc->ib.dev, mr->sgt.sgl,
diff --git a/fs/smb/client/smbdirect.h b/fs/smb/client/smbdirect.h
index ea04ce8a9763..d60e445da225 100644
--- a/fs/smb/client/smbdirect.h
+++ b/fs/smb/client/smbdirect.h
@@ -157,11 +157,6 @@ struct smbd_connection {
 	unsigned int count_send_empty;
 };
 
-enum smbd_message_type {
-	SMBD_NEGOTIATE_RESP,
-	SMBD_TRANSFER_DATA,
-};
-
 /* Maximum number of SGEs used by smbdirect.c in any send work request */
 #define SMBDIRECT_MAX_SEND_SGE	6
 
@@ -181,24 +176,6 @@ struct smbd_request {
 /* Maximum number of SGEs used by smbdirect.c in any receive work request */
 #define SMBDIRECT_MAX_RECV_SGE	1
 
-/* The context for a SMBD response */
-struct smbd_response {
-	struct smbd_connection *info;
-	struct ib_cqe cqe;
-	struct ib_sge sge;
-
-	enum smbd_message_type type;
-
-	/* Link to receive queue or reassembly queue */
-	struct list_head list;
-
-	/* Indicate if this is the 1st packet of a payload */
-	bool first_segment;
-
-	/* SMBD packet header and payload follows this structure */
-	u8 packet[];
-};
-
 /* Create a SMBDirect session */
 struct smbd_connection *smbd_get_connection(
 	struct TCP_Server_Info *server, struct sockaddr *dstaddr);
diff --git a/fs/smb/common/smbdirect/smbdirect_socket.h b/fs/smb/common/smbdirect/smbdirect_socket.h
index e5b15cc44a7b..a7ad31c471a7 100644
--- a/fs/smb/common/smbdirect/smbdirect_socket.h
+++ b/fs/smb/common/smbdirect/smbdirect_socket.h
@@ -38,6 +38,35 @@ struct smbdirect_socket {
 	} ib;
 
 	struct smbdirect_socket_parameters parameters;
+
+	/*
+	 * The state for posted receive buffers
+	 */
+	struct {
+		/*
+		 * The type of PDU we are expecting
+		 */
+		enum {
+			SMBDIRECT_EXPECT_NEGOTIATE_REQ = 1,
+			SMBDIRECT_EXPECT_NEGOTIATE_REP = 2,
+			SMBDIRECT_EXPECT_DATA_TRANSFER = 3,
+		} expected;
+	} recv_io;
+};
+
+struct smbdirect_recv_io {
+	struct smbdirect_socket *socket;
+	struct ib_cqe cqe;
+	struct ib_sge sge;
+
+	/* Link to free or reassembly list */
+	struct list_head list;
+
+	/* Indicate if this is the 1st packet of a payload */
+	bool first_segment;
+
+	/* SMBD packet header and payload follows this structure */
+	u8 packet[];
 };
 
 #endif /* __FS_SMB_COMMON_SMBDIRECT_SMBDIRECT_SOCKET_H__ */
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 5466aa8c39b1..6550bd9f002c 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	case SMB_DIRECT_MSG_DATA_TRANSFER: {
 		struct smb_direct_data_transfer *data_transfer =
 			(struct smb_direct_data_transfer *)recvmsg->packet;
-		unsigned int data_length;
+		u32 remaining_data_length, data_offset, data_length;
 		int avail_recvmsg_count, receive_credits;
 
 		if (wc->byte_len <
@@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			return;
 		}
 
+		remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length);
 		data_length = le32_to_cpu(data_transfer->data_length);
-		if (data_length) {
-			if (wc->byte_len < sizeof(struct smb_direct_data_transfer) +
-			    (u64)data_length) {
-				put_recvmsg(t, recvmsg);
-				smb_direct_disconnect_rdma_connection(t);
-				return;
-			}
+		data_offset = le32_to_cpu(data_transfer->data_offset);
+		if (wc->byte_len < data_offset ||
+		    wc->byte_len < (u64)data_offset + data_length) {
+			put_recvmsg(t, recvmsg);
+			smb_direct_disconnect_rdma_connection(t);
+			return;
+		}
+		if (remaining_data_length > t->max_fragmented_recv_size ||
+		    data_length > t->max_fragmented_recv_size ||
+		    (u64)remaining_data_length + (u64)data_length >
+		    (u64)t->max_fragmented_recv_size) {
+			put_recvmsg(t, recvmsg);
+			smb_direct_disconnect_rdma_connection(t);
+			return;
+		}
 
+		if (data_length) {
 			if (t->full_packet_received)
 				recvmsg->first_segment = true;
 
@@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t,
 			     bool need_invalidate, unsigned int remote_key)
 {
 	struct smb_direct_transport *st = smb_trans_direct_transfort(t);
-	int remaining_data_length;
-	int start, i, j;
-	int max_iov_size = st->max_send_size -
+	size_t remaining_data_length;
+	size_t iov_idx;
+	size_t iov_ofs;
+	size_t max_iov_size = st->max_send_size -
 			sizeof(struct smb_direct_data_transfer);
 	int ret;
-	struct kvec vec;
 	struct smb_direct_send_ctx send_ctx;
+	int error = 0;
 
 	if (st->status != SMB_DIRECT_CS_CONNECTED)
 		return -ENOTCONN;
 
 	//FIXME: skip RFC1002 header..
+	if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4))
+		return -EINVAL;
 	buflen -= 4;
+	iov_idx = 1;
+	iov_ofs = 0;
 
 	remaining_data_length = buflen;
 	ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen);
 
 	smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key);
-	start = i = 1;
-	buflen = 0;
-	while (true) {
-		buflen += iov[i].iov_len;
-		if (buflen > max_iov_size) {
-			if (i > start) {
-				remaining_data_length -=
-					(buflen - iov[i].iov_len);
-				ret = smb_direct_post_send_data(st, &send_ctx,
-								&iov[start], i - start,
-								remaining_data_length);
-				if (ret)
+	while (remaining_data_length) {
+		struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */
+		size_t possible_bytes = max_iov_size;
+		size_t possible_vecs;
+		size_t bytes = 0;
+		size_t nvecs = 0;
+
+		/*
+		 * For the last message remaining_data_length should be
+		 * have been 0 already!
+		 */
+		if (WARN_ON_ONCE(iov_idx >= niovs)) {
+			error = -EINVAL;
+			goto done;
+		}
+
+		/*
+		 * We have 2 factors which limit the arguments we pass
+		 * to smb_direct_post_send_data():
+		 *
+		 * 1. The number of supported sges for the send,
+		 *    while one is reserved for the smbdirect header.
+		 *    And we currently need one SGE per page.
+		 * 2. The number of negotiated payload bytes per send.
+		 */
+		possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx);
+
+		while (iov_idx < niovs && possible_vecs && possible_bytes) {
+			struct kvec *v = &vecs[nvecs];
+			int page_count;
+
+			v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs;
+			v->iov_len = min_t(size_t,
+					   iov[iov_idx].iov_len - iov_ofs,
+					   possible_bytes);
+			page_count = get_buf_page_count(v->iov_base, v->iov_len);
+			if (page_count > possible_vecs) {
+				/*
+				 * If the number of pages in the buffer
+				 * is to much (because we currently require
+				 * one SGE per page), we need to limit the
+				 * length.
+				 *
+				 * We know possible_vecs is at least 1,
+				 * so we always keep the first page.
+				 *
+				 * We need to calculate the number extra
+				 * pages (epages) we can also keep.
+				 *
+				 * We calculate the number of bytes in the
+				 * first page (fplen), this should never be
+				 * larger than v->iov_len because page_count is
+				 * at least 2, but adding a limitation feels
+				 * better.
+				 *
+				 * Then we calculate the number of bytes (elen)
+				 * we can keep for the extra pages.
+				 */
+				size_t epages = possible_vecs - 1;
+				size_t fpofs = offset_in_page(v->iov_base);
+				size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len);
+				size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE);
+
+				v->iov_len = fplen + elen;
+				page_count = get_buf_page_count(v->iov_base, v->iov_len);
+				if (WARN_ON_ONCE(page_count > possible_vecs)) {
+					/*
+					 * Something went wrong in the above
+					 * logic...
+					 */
+					error = -EINVAL;
 					goto done;
-			} else {
-				/* iov[start] is too big, break it */
-				int nvec  = (buflen + max_iov_size - 1) /
-						max_iov_size;
-
-				for (j = 0; j < nvec; j++) {
-					vec.iov_base =
-						(char *)iov[start].iov_base +
-						j * max_iov_size;
-					vec.iov_len =
-						min_t(int, max_iov_size,
-						      buflen - max_iov_size * j);
-					remaining_data_length -= vec.iov_len;
-					ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1,
-									remaining_data_length);
-					if (ret)
-						goto done;
 				}
-				i++;
-				if (i == niovs)
-					break;
 			}
-			start = i;
-			buflen = 0;
-		} else {
-			i++;
-			if (i == niovs) {
-				/* send out all remaining vecs */
-				remaining_data_length -= buflen;
-				ret = smb_direct_post_send_data(st, &send_ctx,
-								&iov[start], i - start,
-								remaining_data_length);
-				if (ret)
-					goto done;
-				break;
+			possible_vecs -= page_count;
+			nvecs += 1;
+			possible_bytes -= v->iov_len;
+			bytes += v->iov_len;
+
+			iov_ofs += v->iov_len;
+			if (iov_ofs >= iov[iov_idx].iov_len) {
+				iov_idx += 1;
+				iov_ofs = 0;
 			}
 		}
+
+		remaining_data_length -= bytes;
+
+		ret = smb_direct_post_send_data(st, &send_ctx,
+						vecs, nvecs,
+						remaining_data_length);
+		if (unlikely(ret)) {
+			error = ret;
+			goto done;
+		}
 	}
 
 done:
 	ret = smb_direct_flush_send_list(st, &send_ctx, true);
+	if (unlikely(!ret && error))
+		ret = error;
 
 	/*
 	 * As an optimization, we don't wait for individual I/O to finish
@@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t,
 		return -EINVAL;
 	}
 
+	if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) {
+		pr_err("warning: device max_send_sge = %d too small\n",
+		       device->attrs.max_send_sge);
+		return -EINVAL;
+	}
 	if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) {
 		pr_err("warning: device max_recv_sge = %d too small\n",
 		       device->attrs.max_recv_sge);
@@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t,
 
 	cap->max_send_wr = max_send_wrs;
 	cap->max_recv_wr = t->recv_credit_max;
-	cap->max_send_sge = max_sge_per_wr;
+	cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES;
 	cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES;
 	cap->max_inline_data = 0;
 	cap->max_rdma_ctxs = t->max_rw_credits;