FAILED: patch "[PATCH] smb: client: resolve SWN tcon from live registrations" failed to apply to 5.15-stable tree

FAILED: patch "[PATCH] smb: client: resolve SWN tcon from live registrations" failed to apply to 5.15-stable tree

[gregkh]

The patch below does not apply to the 5.15-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x ec457f9afe5ae9538bdcd58fd4cb442b9787e183
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026071416-veal-lunchroom-f691@gregkh' --subject-prefix 'PATCH 5.15.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From ec457f9afe5ae9538bdcd58fd4cb442b9787e183 Mon Sep 17 00:00:00 2001
From: Michael Bommarito <michael.bommarito@gmail.com>
Date: Sun, 17 May 2026 20:11:49 -0400
Subject: [PATCH] smb: client: resolve SWN tcon from live registrations

cifs_swn_notify() looks up a witness registration by id under
cifs_swnreg_idr_mutex, drops the mutex, and then uses the registration's
cached tcon pointer.  That pointer is not a lifetime reference, and it is
not a stable representative once cifs_get_swn_reg() lets multiple tcons
for the same net/share name share one registration id.

A same-share second mount can keep the cifs_swn_reg alive after the first
tcon unregisters and is freed.  The registration then still points at the
freed first tcon, so taking tc_lock or incrementing tc_count through
swnreg->tcon only moves the use-after-free earlier.  Taking tc_lock while
holding cifs_swnreg_idr_mutex also violates the documented CIFS lock
order.

Fix this by making the registration store only the stable witness
identity: id, net name, share name, and notify flags.  When a notify
arrives, copy that identity under cifs_swnreg_idr_mutex, drop the mutex,
then find and pin a live witness tcon that currently matches the net/share
pair under the normal cifs_tcp_ses_lock -> tc_lock order.  The notification
path uses that pinned tcon directly and drops the reference when done.

Registration and unregister messages now use the live tcon passed by the
caller instead of a cached tcon in the registration.  The final unregister
send is folded into cifs_swn_unregister() while the registration is still
protected by cifs_swnreg_idr_mutex.  This removes the previous
find/drop/reacquire raw-pointer window.  The release path only removes the
idr entry and frees the stable identity strings.

This preserves the intended one-registration/many-tcon behavior: a
registration id represents a net/share pair, and notify handling acts on a
live representative selected at use time.  It also preserves CLIENT_MOVE
ordering for the representative tcon because the old-IP unregister is sent
before cifs_swn_register() sends the new-IP register.

Fixes: fed979a7e082 ("cifs: Set witness notification handler for messages from userspace daemon")
Cc: stable@vger.kernel.org
Signed-off-by: Michael Bommarito <michael.bommarito@gmail.com>
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Steve French <stfrench@microsoft.com>

diff --git a/fs/smb/client/cifs_swn.c b/fs/smb/client/cifs_swn.c
index 9753a432d099..9951817d0d7f 100644
--- a/fs/smb/client/cifs_swn.c
+++ b/fs/smb/client/cifs_swn.c
@@ -28,10 +28,54 @@ struct cifs_swn_reg {
 	bool net_name_notify;
 	bool share_name_notify;
 	bool ip_notify;
-
-	struct cifs_tcon *tcon;
 };
 
+struct cifs_swn_reg_info {
+	int id;
+	unsigned int ref_count;
+	const char *net_name;
+	const char *share_name;
+	bool net_name_notify;
+	bool share_name_notify;
+	bool ip_notify;
+};
+
+static void cifs_swn_snapshot_reg(struct cifs_swn_reg *swnreg,
+				  struct cifs_swn_reg_info *info)
+{
+	info->id = swnreg->id;
+	info->ref_count = kref_read(&swnreg->ref_count);
+	info->net_name = swnreg->net_name;
+	info->share_name = swnreg->share_name;
+	info->net_name_notify = swnreg->net_name_notify;
+	info->share_name_notify = swnreg->share_name_notify;
+	info->ip_notify = swnreg->ip_notify;
+}
+
+static int cifs_swn_dup_reg(struct cifs_swn_reg *swnreg,
+			    struct cifs_swn_reg_info *info)
+{
+	cifs_swn_snapshot_reg(swnreg, info);
+
+	info->net_name = kstrdup(swnreg->net_name, GFP_KERNEL);
+	if (!info->net_name)
+		return -ENOMEM;
+
+	info->share_name = kstrdup(swnreg->share_name, GFP_KERNEL);
+	if (!info->share_name) {
+		kfree(info->net_name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void cifs_swn_free_reg_info(struct cifs_swn_reg_info *info)
+{
+	kfree(info->net_name);
+	kfree(info->share_name);
+}
+
 static int cifs_swn_auth_info_krb(struct cifs_tcon *tcon, struct sk_buff *skb)
 {
 	int ret;
@@ -73,7 +117,8 @@ static int cifs_swn_auth_info_ntlm(struct cifs_tcon *tcon, struct sk_buff *skb)
  * The authentication information to connect to the witness service is bundled
  * into the message.
  */
-static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
+static int cifs_swn_send_register_message(struct cifs_swn_reg_info *swnreg,
+					  struct cifs_tcon *tcon)
 {
 	struct sk_buff *skb;
 	struct genlmsghdr *hdr;
@@ -109,10 +154,10 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 	 * told to switch to it (client move message). In these cases we unregister from the
 	 * server address and register to the new address when we receive the notification.
 	 */
-	if (swnreg->tcon->ses->server->use_swn_dstaddr)
-		addr = &swnreg->tcon->ses->server->swn_dstaddr;
+	if (tcon->ses->server->use_swn_dstaddr)
+		addr = &tcon->ses->server->swn_dstaddr;
 	else
-		addr = &swnreg->tcon->ses->server->dstaddr;
+		addr = &tcon->ses->server->dstaddr;
 
 	ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage), addr);
 	if (ret < 0)
@@ -136,10 +181,10 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 			goto nlmsg_fail;
 	}
 
-	authtype = cifs_select_sectype(swnreg->tcon->ses->server, swnreg->tcon->ses->sectype);
+	authtype = cifs_select_sectype(tcon->ses->server, tcon->ses->sectype);
 	switch (authtype) {
 	case Kerberos:
-		ret = cifs_swn_auth_info_krb(swnreg->tcon, skb);
+		ret = cifs_swn_auth_info_krb(tcon, skb);
 		if (ret < 0) {
 			cifs_dbg(VFS, "%s: Failed to get kerberos auth info: %d\n", __func__, ret);
 			goto nlmsg_fail;
@@ -147,7 +192,7 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 		break;
 	case NTLMv2:
 	case RawNTLMSSP:
-		ret = cifs_swn_auth_info_ntlm(swnreg->tcon, skb);
+		ret = cifs_swn_auth_info_ntlm(tcon, skb);
 		if (ret < 0) {
 			cifs_dbg(VFS, "%s: Failed to get NTLM auth info: %d\n", __func__, ret);
 			goto nlmsg_fail;
@@ -176,7 +221,8 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 /*
  * Sends an uregister message to the userspace daemon based on the registration
  */
-static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
+static int cifs_swn_send_unregister_message(struct cifs_swn_reg_info *swnreg,
+					    struct cifs_tcon *tcon)
 {
 	struct sk_buff *skb;
 	struct genlmsghdr *hdr;
@@ -205,7 +251,7 @@ static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
 		goto nlmsg_fail;
 
 	ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage),
-			&swnreg->tcon->ses->server->dstaddr);
+			&tcon->ses->server->dstaddr);
 	if (ret < 0)
 		goto nlmsg_fail;
 
@@ -241,6 +287,88 @@ static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
 	return ret;
 }
 
+/*
+ * Allocation-free mirror of extract_hostname() + extract_sharename() from
+ * fs/smb/client/unc.c.  Those helpers kmalloc(GFP_KERNEL); this runs under
+ * cifs_tcp_ses_lock and tcon->tc_lock, both spinlocks, so we mirror their
+ * parsing in place against the caller's stable net_name/share_name strings.
+ * Keep in sync with unc.c.
+ */
+static bool cifs_swn_tcon_matches(struct cifs_tcon *tcon,
+				  const char *net_name,
+				  const char *share_name)
+{
+	const char *unc = tcon->tree_name;
+	const char *host, *share, *delim;
+	size_t host_len, share_len;
+
+	if (!tcon->use_witness)
+		return false;
+
+	/* extract_hostname: require strlen(unc) >= 3 */
+	if (strnlen(unc, 3) < 3)
+		return false;
+	/* extract_hostname: skip all leading '\' characters */
+	for (host = unc; *host == '\\'; host++)
+		;
+	if (!*host)
+		return false;
+	delim = strchr(host, '\\');
+	if (!delim)
+		return false;
+	host_len = delim - host;
+	if (strlen(net_name) != host_len ||
+	    strncasecmp(host, net_name, host_len))
+		return false;
+
+	/* extract_sharename: start at unc + 2, then first '\' onward */
+	share = unc + 2;
+	delim = strchr(share, '\\');
+	if (!delim)
+		return false;
+	share = delim + 1;
+	share_len = strlen(share);
+
+	return strlen(share_name) == share_len &&
+	       !strncasecmp(share, share_name, share_len);
+}
+
+/*
+ * One SWN registration id represents one net/share name pair.  Multiple
+ * mounted tcons can therefore share the id.  Pick a live representative at
+ * use time instead of caching the first tcon pointer in the registration.
+ */
+static struct cifs_tcon *cifs_swn_get_tcon(struct cifs_swn_reg_info *swnreg)
+{
+	struct TCP_Server_Info *server;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+		list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+			list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+				spin_lock(&tcon->tc_lock);
+				if (tcon->status == TID_EXITING ||
+				    !cifs_swn_tcon_matches(tcon, swnreg->net_name,
+							   swnreg->share_name)) {
+					spin_unlock(&tcon->tc_lock);
+					continue;
+				}
+				++tcon->tc_count;
+				trace_smb3_tcon_ref(tcon->debug_id,
+						    tcon->tc_count,
+						    netfs_trace_tcon_ref_get_swn_notify);
+				spin_unlock(&tcon->tc_lock);
+				spin_unlock(&cifs_tcp_ses_lock);
+				return tcon;
+			}
+		}
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+	return NULL;
+}
+
 /*
  * Try to find a matching registration for the tcon's server name and share name.
  * Calls to this function must be protected by cifs_swnreg_idr_mutex.
@@ -347,8 +475,6 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg->net_name_notify = true;
 	reg->share_name_notify = true;
 	reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT);
-
-	reg->tcon = tcon;
 unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
@@ -368,11 +494,6 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 static void cifs_swn_reg_release(struct kref *ref)
 {
 	struct cifs_swn_reg *swnreg = container_of(ref, struct cifs_swn_reg, ref_count);
-	int ret;
-
-	ret = cifs_swn_send_unregister_message(swnreg);
-	if (ret < 0)
-		cifs_dbg(VFS, "%s: Failed to send unregister message: %d\n", __func__, ret);
 
 	idr_remove(&cifs_swnreg_idr, swnreg->id);
 	kfree(swnreg->net_name);
@@ -380,23 +501,33 @@ static void cifs_swn_reg_release(struct kref *ref)
 	kfree(swnreg);
 }
 
-static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg)
+static void cifs_put_swn_reg_locked(struct cifs_swn_reg *swnreg,
+				    struct cifs_tcon *tcon)
 {
-	mutex_lock(&cifs_swnreg_idr_mutex);
+	if (kref_read(&swnreg->ref_count) == 1) {
+		struct cifs_swn_reg_info swnreg_info;
+		int ret;
+
+		cifs_swn_snapshot_reg(swnreg, &swnreg_info);
+		ret = cifs_swn_send_unregister_message(&swnreg_info, tcon);
+		if (ret < 0)
+			cifs_dbg(VFS, "%s: Failed to send unregister message: %d\n",
+				 __func__, ret);
+	}
+
 	kref_put(&swnreg->ref_count, cifs_swn_reg_release);
-	mutex_unlock(&cifs_swnreg_idr_mutex);
 }
 
-static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state)
+static int cifs_swn_resource_state_changed(struct cifs_tcon *tcon, const char *name, int state)
 {
 	switch (state) {
 	case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name);
-		cifs_signal_cifsd_for_reconnect(swnreg->tcon->ses->server, true);
+		cifs_signal_cifsd_for_reconnect(tcon->ses->server, true);
 		break;
 	case CIFS_SWN_RESOURCE_STATE_AVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name);
-		cifs_signal_cifsd_for_reconnect(swnreg->tcon->ses->server, true);
+		cifs_signal_cifsd_for_reconnect(tcon->ses->server, true);
 		break;
 	case CIFS_SWN_RESOURCE_STATE_UNKNOWN:
 		cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name);
@@ -502,7 +633,7 @@ static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *a
 	return ret;
 }
 
-static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_storage *addr)
+static int cifs_swn_client_move(struct cifs_tcon *tcon, struct sockaddr_storage *addr)
 {
 	struct sockaddr_in *ipv4 = (struct sockaddr_in *)addr;
 	struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)addr;
@@ -512,14 +643,17 @@ static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_sto
 	else if (addr->ss_family == AF_INET6)
 		cifs_dbg(FYI, "%s: move to %pI6\n", __func__, &ipv6->sin6_addr);
 
-	return cifs_swn_reconnect(swnreg->tcon, addr);
+	return cifs_swn_reconnect(tcon, addr);
 }
 
 int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cifs_swn_reg *swnreg;
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
 	char name[256];
 	int type;
+	int ret = 0;
 
 	if (info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]) {
 		int swnreg_id;
@@ -527,21 +661,34 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 		swnreg_id = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]);
 		mutex_lock(&cifs_swnreg_idr_mutex);
 		swnreg = idr_find(&cifs_swnreg_idr, swnreg_id);
-		mutex_unlock(&cifs_swnreg_idr_mutex);
 		if (swnreg == NULL) {
+			mutex_unlock(&cifs_swnreg_idr_mutex);
 			cifs_dbg(FYI, "%s: registration id %d not found\n", __func__, swnreg_id);
 			return -EINVAL;
 		}
+		ret = cifs_swn_dup_reg(swnreg, &swnreg_info);
+		mutex_unlock(&cifs_swnreg_idr_mutex);
+		if (ret)
+			return ret;
 	} else {
 		cifs_dbg(FYI, "%s: missing registration id attribute\n", __func__);
 		return -EINVAL;
 	}
 
+	tcon = cifs_swn_get_tcon(&swnreg_info);
+	if (!tcon) {
+		cifs_dbg(FYI, "%s: registration id %d has no live tcon\n",
+			 __func__, swnreg_info.id);
+		ret = -ENODEV;
+		goto free_info;
+	}
+
 	if (info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]) {
 		type = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]);
 	} else {
 		cifs_dbg(FYI, "%s: missing notification type attribute\n", __func__);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	switch (type) {
@@ -553,15 +700,18 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 					sizeof(name));
 		} else {
 			cifs_dbg(FYI, "%s: missing resource name attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 		if (info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]) {
 			state = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]);
 		} else {
 			cifs_dbg(FYI, "%s: missing resource state attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
-		return cifs_swn_resource_state_changed(swnreg, name, state);
+		ret = cifs_swn_resource_state_changed(tcon, name, state);
+		break;
 	}
 	case CIFS_SWN_NOTIFICATION_CLIENT_MOVE: {
 		struct sockaddr_storage addr;
@@ -570,28 +720,36 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 			nla_memcpy(&addr, info->attrs[CIFS_GENL_ATTR_SWN_IP], sizeof(addr));
 		} else {
 			cifs_dbg(FYI, "%s: missing IP address attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
-		return cifs_swn_client_move(swnreg, &addr);
+		ret = cifs_swn_client_move(tcon, &addr);
+		break;
 	}
 	default:
 		cifs_dbg(FYI, "%s: unknown notification type %d\n", __func__, type);
 		break;
 	}
 
-	return 0;
+out:
+	cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+free_info:
+	cifs_swn_free_reg_info(&swnreg_info);
+	return ret;
 }
 
 int cifs_swn_register(struct cifs_tcon *tcon)
 {
 	struct cifs_swn_reg *swnreg;
+	struct cifs_swn_reg_info swnreg_info;
 	int ret;
 
 	swnreg = cifs_get_swn_reg(tcon);
 	if (IS_ERR(swnreg))
 		return PTR_ERR(swnreg);
 
-	ret = cifs_swn_send_register_message(swnreg);
+	cifs_swn_snapshot_reg(swnreg, &swnreg_info);
+	ret = cifs_swn_send_register_message(&swnreg_info, tcon);
 	if (ret < 0) {
 		cifs_dbg(VFS, "%s: Failed to send swn register message: %d\n", __func__, ret);
 		/* Do not put the swnreg or return error, the echo task will retry */
@@ -612,35 +770,68 @@ int cifs_swn_unregister(struct cifs_tcon *tcon)
 		return PTR_ERR(swnreg);
 	}
 
+	cifs_put_swn_reg_locked(swnreg, tcon);
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
-	cifs_put_swn_reg(swnreg);
-
 	return 0;
 }
 
-void cifs_swn_dump(struct seq_file *m)
+/*
+ * Snapshot one registration under cifs_swnreg_idr_mutex and return.  Callers
+ * intentionally do the per-registration network/genlmsg work without the
+ * mutex held, both to keep the critical section short and to avoid nesting
+ * cifs_swnreg_idr_mutex inside the higher tc_lock when a live tcon is then
+ * pinned for the send.
+ */
+static int cifs_swn_get_next_reg_info(int *id, struct cifs_swn_reg_info *info)
 {
 	struct cifs_swn_reg *swnreg;
+	int ret = 0;
+
+	mutex_lock(&cifs_swnreg_idr_mutex);
+	swnreg = idr_get_next(&cifs_swnreg_idr, id);
+	if (swnreg) {
+		ret = cifs_swn_dup_reg(swnreg, info);
+		if (!ret) {
+			*id = swnreg->id + 1;
+			ret = 1;
+		}
+	}
+	mutex_unlock(&cifs_swnreg_idr_mutex);
+
+	return ret;
+}
+
+void cifs_swn_dump(struct seq_file *m)
+{
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
 	struct sockaddr_in *sa;
 	struct sockaddr_in6 *sa6;
-	int id;
+	int id = 0;
+	int ret;
 
 	seq_puts(m, "Witness registrations:");
 
-	mutex_lock(&cifs_swnreg_idr_mutex);
-	idr_for_each_entry(&cifs_swnreg_idr, swnreg, id) {
+	while ((ret = cifs_swn_get_next_reg_info(&id, &swnreg_info)) > 0) {
 		seq_printf(m, "\nId: %u Refs: %u Network name: '%s'%s Share name: '%s'%s Ip address: ",
-				id, kref_read(&swnreg->ref_count),
-				swnreg->net_name, swnreg->net_name_notify ? "(y)" : "(n)",
-				swnreg->share_name, swnreg->share_name_notify ? "(y)" : "(n)");
-		switch (swnreg->tcon->ses->server->dstaddr.ss_family) {
+			   swnreg_info.id, swnreg_info.ref_count,
+			   swnreg_info.net_name, swnreg_info.net_name_notify ? "(y)" : "(n)",
+			   swnreg_info.share_name, swnreg_info.share_name_notify ? "(y)" : "(n)");
+
+		tcon = cifs_swn_get_tcon(&swnreg_info);
+		if (!tcon) {
+			seq_puts(m, "(no live tcon)");
+			goto next;
+		}
+
+		switch (tcon->ses->server->dstaddr.ss_family) {
 		case AF_INET:
-			sa = (struct sockaddr_in *) &swnreg->tcon->ses->server->dstaddr;
+			sa = (struct sockaddr_in *)&tcon->ses->server->dstaddr;
 			seq_printf(m, "%pI4", &sa->sin_addr.s_addr);
 			break;
 		case AF_INET6:
-			sa6 = (struct sockaddr_in6 *) &swnreg->tcon->ses->server->dstaddr;
+			sa6 = (struct sockaddr_in6 *)&tcon->ses->server->dstaddr;
 			seq_printf(m, "%pI6", &sa6->sin6_addr.s6_addr);
 			if (sa6->sin6_scope_id)
 				seq_printf(m, "%%%u", sa6->sin6_scope_id);
@@ -648,23 +839,38 @@ void cifs_swn_dump(struct seq_file *m)
 		default:
 			seq_puts(m, "(unknown)");
 		}
-		seq_printf(m, "%s", swnreg->ip_notify ? "(y)" : "(n)");
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+next:
+		seq_printf(m, "%s", swnreg_info.ip_notify ? "(y)" : "(n)");
+		cifs_swn_free_reg_info(&swnreg_info);
 	}
-	mutex_unlock(&cifs_swnreg_idr_mutex);
+	if (ret < 0)
+		seq_printf(m, "\nFailed to snapshot witness registration: %d", ret);
 	seq_puts(m, "\n");
 }
 
 void cifs_swn_check(void)
 {
-	struct cifs_swn_reg *swnreg;
-	int id;
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
+	int id = 0;
 	int ret;
 
-	mutex_lock(&cifs_swnreg_idr_mutex);
-	idr_for_each_entry(&cifs_swnreg_idr, swnreg, id) {
-		ret = cifs_swn_send_register_message(swnreg);
+	while ((ret = cifs_swn_get_next_reg_info(&id, &swnreg_info)) > 0) {
+		tcon = cifs_swn_get_tcon(&swnreg_info);
+		if (!tcon) {
+			cifs_dbg(FYI, "%s: registration id %d has no live tcon\n",
+				 __func__, swnreg_info.id);
+			goto free_info;
+		}
+
+		ret = cifs_swn_send_register_message(&swnreg_info, tcon);
 		if (ret < 0)
 			cifs_dbg(FYI, "%s: Failed to send register message: %d\n", __func__, ret);
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+free_info:
+		cifs_swn_free_reg_info(&swnreg_info);
 	}
-	mutex_unlock(&cifs_swnreg_idr_mutex);
+	if (ret < 0)
+		cifs_dbg(FYI, "%s: Failed to snapshot registration: %d\n", __func__, ret);
 }
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index b99ec5a417fa..5b21ad3c15fb 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -181,6 +181,7 @@
 	EM(netfs_trace_tcon_ref_get_find,		"GET Find  ") \
 	EM(netfs_trace_tcon_ref_get_find_sess_tcon,	"GET FndSes") \
 	EM(netfs_trace_tcon_ref_get_reconnect_server,	"GET Reconn") \
+	EM(netfs_trace_tcon_ref_get_swn_notify,		"GET SwnNot") \
 	EM(netfs_trace_tcon_ref_new,			"NEW       ") \
 	EM(netfs_trace_tcon_ref_new_ipc,		"NEW Ipc   ") \
 	EM(netfs_trace_tcon_ref_new_reconnect_server,	"NEW Reconn") \
@@ -192,6 +193,7 @@
 	EM(netfs_trace_tcon_ref_put_mnt_ctx,		"PUT MntCtx") \
 	EM(netfs_trace_tcon_ref_put_dfs_refer,		"PUT DfsRfr") \
 	EM(netfs_trace_tcon_ref_put_reconnect_server,	"PUT Reconn") \
+	EM(netfs_trace_tcon_ref_put_swn_notify,		"PUT SwnNot") \
 	EM(netfs_trace_tcon_ref_put_tlink,		"PUT Tlink ") \
 	EM(netfs_trace_tcon_ref_see_cancelled_close,	"SEE Cn-Cls") \
 	EM(netfs_trace_tcon_ref_see_fscache_collision,	"SEE FV-CO!") \

[PATCH 5.15.y 1/2] cifs: Add tracing for the cifs_tcon struct refcounting

[Sasha Levin]

From: David Howells <dhowells@redhat.com>

[ Upstream commit afc23febd51c7e24361e3a9c09f3e892eb0a41ea ]

Add tracing for the refcounting/lifecycle of the cifs_tcon struct, marking
different events with different labels and giving each tcon its own debug
ID so that the tracelines corresponding to individual tcons can be
distinguished.  This can be enabled with:

	echo 1 >/sys/kernel/debug/tracing/events/cifs/smb3_tcon_ref/enable

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
Stable-dep-of: ec457f9afe5a ("smb: client: resolve SWN tcon from live registrations")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/cifs/cifs_swn.c      | 13 +++---
 fs/cifs/cifsfs.c        |  2 +
 fs/cifs/cifsglob.h      |  1 +
 fs/cifs/cifsproto.h     |  9 ++--
 fs/cifs/connect.c       | 21 ++++++----
 fs/cifs/dfs_cache.c     |  2 +-
 fs/cifs/misc.c          | 10 +++--
 fs/cifs/smb2misc.c      | 10 +++--
 fs/cifs/smb2ops.c       |  7 +++-
 fs/cifs/smb2pdu.c       |  4 +-
 fs/cifs/smb2transport.c |  2 +
 fs/cifs/trace.h         | 93 ++++++++++++++++++++++++++++++++++++++++-
 12 files changed, 141 insertions(+), 33 deletions(-)

diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index 12bde7bfda86be..b5b7611ab15d20 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -313,17 +313,15 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg = cifs_find_swn_reg(tcon);
 	if (!IS_ERR(reg)) {
 		kref_get(&reg->ref_count);
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return reg;
+		goto unlock;
 	} else if (PTR_ERR(reg) != -EEXIST) {
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return reg;
+		goto unlock;
 	}
 
 	reg = kmalloc(sizeof(struct cifs_swn_reg), GFP_ATOMIC);
 	if (reg == NULL) {
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto fail_unlock;
 	}
 
 	kref_init(&reg->ref_count);
@@ -354,7 +352,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT);
 
 	reg->tcon = tcon;
-
+unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
 	return reg;
@@ -365,6 +363,7 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	idr_remove(&cifs_swnreg_idr, reg->id);
 fail:
 	kfree(reg);
+fail_unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 	return ERR_PTR(ret);
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c254e714f7ceb9..d31e4a6dad605f 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -706,6 +706,8 @@ static void cifs_umount_begin(struct super_block *sb)
 	tcon = cifs_sb_master_tcon(cifs_sb);
 
 	spin_lock(&cifs_tcp_ses_lock);
+	trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+			    netfs_trace_tcon_ref_see_umount);
 	if ((tcon->tc_count > 1) || (tcon->tidStatus == CifsExiting)) {
 		/* we have other mounts to same share or we have
 		   already tried to force umount this and woken up
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 68b9b382d44bf2..91f5f35fe296ba 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1024,6 +1024,7 @@ struct cached_fid {
  */
 struct cifs_tcon {
 	struct list_head tcon_list;
+	int debug_id;		/* Debugging for tracing */
 	int tc_count;
 	struct list_head rlist; /* reconnect list */
 	atomic_t num_local_opens;  /* num of all opens including disconnected */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 7d00802f972239..21fb1dcbc23c89 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -273,7 +273,7 @@ extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon,
 extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx);
 extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
 				 int from_reconnect);
-extern void cifs_put_tcon(struct cifs_tcon *tcon);
+extern void cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace);
 
 #if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL)
 extern void cifs_dfs_release_automount_timer(void);
@@ -489,8 +489,8 @@ extern int CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses);
 
 extern struct cifs_ses *sesInfoAlloc(void);
 extern void sesInfoFree(struct cifs_ses *);
-extern struct cifs_tcon *tconInfoAlloc(void);
-extern void tconInfoFree(struct cifs_tcon *);
+extern struct cifs_tcon *tconInfoAlloc(enum smb3_tcon_ref_trace trace);
+extern void tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace);
 
 extern int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server,
 		   __u32 *pexpected_response_sequence_number);
@@ -634,9 +634,6 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options)
 		return options;
 }
 
-struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon);
-void cifs_put_tcon_super(struct super_block *sb);
-
 static inline void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
 {
 	kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5fd9098250906a..03db7ae121d8e4 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1664,7 +1664,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 		}
 	}
 
-	tcon = tconInfoAlloc();
+	tcon = tconInfoAlloc(netfs_trace_tcon_ref_new_ipc);
 	if (tcon == NULL)
 		return -ENOMEM;
 
@@ -1679,7 +1679,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 
 	if (rc) {
 		cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc);
-		tconInfoFree(tcon);
+		tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail);
 		goto out;
 	}
 
@@ -1710,7 +1710,7 @@ cifs_free_ipc(struct cifs_ses *ses)
 	if (tcon == NULL)
 		return 0;
 
-	tconInfoFree(tcon);
+	tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc);
 	ses->tcon_ipc = NULL;
 	return 0;
 }
@@ -2115,6 +2115,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 		if (!match_tcon(tcon, ctx))
 			continue;
 		++tcon->tc_count;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_get_find);
 		spin_unlock(&cifs_tcp_ses_lock);
 		return tcon;
 	}
@@ -2123,7 +2125,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 }
 
 void
-cifs_put_tcon(struct cifs_tcon *tcon)
+cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace)
 {
 	unsigned int xid;
 	struct cifs_ses *ses;
@@ -2138,6 +2140,7 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	ses = tcon->ses;
 	cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
 	spin_lock(&cifs_tcp_ses_lock);
+	trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count - 1, trace);
 	if (--tcon->tc_count > 0) {
 		spin_unlock(&cifs_tcp_ses_lock);
 		return;
@@ -2165,7 +2168,7 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	_free_xid(xid);
 
 	cifs_fscache_release_super_cookie(tcon);
-	tconInfoFree(tcon);
+	tconInfoFree(tcon, netfs_trace_tcon_ref_free);
 	cifs_put_smb_ses(ses);
 }
 
@@ -2213,7 +2216,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 		goto out_fail;
 	}
 
-	tcon = tconInfoAlloc();
+	tcon = tconInfoAlloc(netfs_trace_tcon_ref_new);
 	if (tcon == NULL) {
 		rc = -ENOMEM;
 		goto out_fail;
@@ -2389,7 +2392,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 	return tcon;
 
 out_fail:
-	tconInfoFree(tcon);
+	tconInfoFree(tcon, netfs_trace_tcon_ref_free_fail);
 	return ERR_PTR(rc);
 }
 
@@ -2406,7 +2409,7 @@ cifs_put_tlink(struct tcon_link *tlink)
 	}
 
 	if (!IS_ERR(tlink_tcon(tlink)))
-		cifs_put_tcon(tlink_tcon(tlink));
+		cifs_put_tcon(tlink_tcon(tlink), netfs_trace_tcon_ref_put_tlink);
 	kfree(tlink);
 	return;
 }
@@ -2960,7 +2963,7 @@ static inline void mount_put_conns(struct mount_ctx *mnt_ctx)
 	int rc = 0;
 
 	if (mnt_ctx->tcon)
-		cifs_put_tcon(mnt_ctx->tcon);
+		cifs_put_tcon(mnt_ctx->tcon, netfs_trace_tcon_ref_put_mnt_ctx);
 	else if (mnt_ctx->ses)
 		cifs_put_smb_ses(mnt_ctx->ses);
 	else if (mnt_ctx->server)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 1864bdadf3ddd0..c78accc623ec9b 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1544,7 +1544,7 @@ static void refresh_mounts(struct cifs_ses **sessions)
 		mutex_unlock(&server->refpath_lock);
 
 		__refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false);
-		cifs_put_tcon(tcon);
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_dfs_refer);
 	}
 }
 
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index a3d37e7769e61f..5c15b602ba3dc2 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -101,9 +101,10 @@ sesInfoFree(struct cifs_ses *buf_to_free)
 }
 
 struct cifs_tcon *
-tconInfoAlloc(void)
+tconInfoAlloc(enum smb3_tcon_ref_trace trace)
 {
 	struct cifs_tcon *ret_buf;
+	static atomic_t tcon_debug_id;
 
 	ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL);
 	if (!ret_buf)
@@ -116,7 +117,8 @@ tconInfoAlloc(void)
 
 	atomic_inc(&tconInfoAllocCount);
 	ret_buf->tidStatus = CifsNew;
-	++ret_buf->tc_count;
+	ret_buf->debug_id = atomic_inc_return(&tcon_debug_id);
+	ret_buf->tc_count = 1;
 	INIT_LIST_HEAD(&ret_buf->openFileList);
 	INIT_LIST_HEAD(&ret_buf->tcon_list);
 	spin_lock_init(&ret_buf->open_file_lock);
@@ -124,17 +126,19 @@ tconInfoAlloc(void)
 	spin_lock_init(&ret_buf->stat_lock);
 	atomic_set(&ret_buf->num_local_opens, 0);
 	atomic_set(&ret_buf->num_remote_opens, 0);
+	trace_smb3_tcon_ref(ret_buf->debug_id, ret_buf->tc_count, trace);
 
 	return ret_buf;
 }
 
 void
-tconInfoFree(struct cifs_tcon *buf_to_free)
+tconInfoFree(struct cifs_tcon *buf_to_free, enum smb3_tcon_ref_trace trace)
 {
 	if (buf_to_free == NULL) {
 		cifs_dbg(FYI, "Null buffer passed to tconInfoFree\n");
 		return;
 	}
+	trace_smb3_tcon_ref(buf_to_free->debug_id, buf_to_free->tc_count, trace);
 	atomic_dec(&tconInfoAllocCount);
 	kfree(buf_to_free->nativeFileSystem);
 	kfree_sensitive(buf_to_free->password);
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index da32b3f6686bd9..8896e682ab96ac 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -743,7 +743,7 @@ smb2_cancelled_close_fid(struct work_struct *work)
 	if (rc)
 		cifs_tcon_dbg(VFS, "Close cancelled mid failed rc:%d\n", rc);
 
-	cifs_put_tcon(tcon);
+	cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close_fid);
 	kfree(cancelled);
 }
 
@@ -787,6 +787,8 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
 	if (tcon->tc_count <= 0) {
 		struct TCP_Server_Info *server = NULL;
 
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_see_cancelled_close);
 		WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative");
 		spin_unlock(&cifs_tcp_ses_lock);
 
@@ -800,12 +802,14 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid,
 		return 0;
 	}
 	tcon->tc_count++;
+	trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+			    netfs_trace_tcon_ref_get_cancelled_close);
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	rc = __smb2_handle_cancelled_cmd(tcon, SMB2_CLOSE_HE, 0,
 					 persistent_fid, volatile_fid);
 	if (rc)
-		cifs_put_tcon(tcon);
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close);
 
 	return rc;
 }
@@ -833,7 +837,7 @@ smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *serve
 					 rsp->PersistentFileId,
 					 rsp->VolatileFileId);
 	if (rc)
-		cifs_put_tcon(tcon);
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_mid);
 
 	return rc;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c372ab70396513..898f3d12ac440b 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2893,8 +2893,11 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		tcon = list_first_entry_or_null(&ses->tcon_list,
 						struct cifs_tcon,
 						tcon_list);
-		if (tcon)
+		if (tcon) {
 			tcon->tc_count++;
+			trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+					    netfs_trace_tcon_ref_get_dfs_refer);
+		}
 		spin_unlock(&cifs_tcp_ses_lock);
 	}
 
@@ -2958,6 +2961,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		/* ipc tcons are not refcounted */
 		spin_lock(&cifs_tcp_ses_lock);
 		tcon->tc_count--;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_dec_dfs_refer);
 		/* tc_count can never go negative */
 		WARN_ON(tcon->tc_count < 0);
 		spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 302c08dfb686dc..04a43cc2ee7ab9 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3771,6 +3771,8 @@ 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_exist = true;
 			}
@@ -3804,7 +3806,7 @@ void smb2_reconnect_server(struct work_struct *work)
 		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);
 	}
 
 	cifs_dbg(FYI, "Reconnecting tcons finished\n");
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index f1e981328bc874..5b88288f6978b9 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -169,6 +169,8 @@ smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32  tid)
 		if (tcon->tid != tid)
 			continue;
 		++tcon->tc_count;
+		trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+				    netfs_trace_tcon_ref_get_find_sess_tcon);
 		return tcon;
 	}
 
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index dafcb6ab050dd9..4e66ca4c16517f 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -3,6 +3,9 @@
  *   Copyright (C) 2018, Microsoft Corporation.
  *
  *   Author(s): Steve French <stfrench@microsoft.com>
+ *
+ * Please use this 3-part article as a reference for writing new tracepoints:
+ * https://lwn.net/Articles/379903/
  */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM cifs
@@ -13,9 +16,71 @@
 #include <linux/tracepoint.h>
 
 /*
- * Please use this 3-part article as a reference for writing new tracepoints:
- * https://lwn.net/Articles/379903/
+ * Specify enums for tracing information.
+ */
+#define smb3_tcon_ref_traces					      \
+	EM(netfs_trace_tcon_ref_dec_dfs_refer,		"DEC DfsRef") \
+	EM(netfs_trace_tcon_ref_free,			"FRE       ") \
+	EM(netfs_trace_tcon_ref_free_fail,		"FRE Fail  ") \
+	EM(netfs_trace_tcon_ref_free_ipc,		"FRE Ipc   ") \
+	EM(netfs_trace_tcon_ref_free_ipc_fail,		"FRE Ipc-F ") \
+	EM(netfs_trace_tcon_ref_free_reconnect_server,	"FRE Reconn") \
+	EM(netfs_trace_tcon_ref_get_cancelled_close,	"GET Cn-Cls") \
+	EM(netfs_trace_tcon_ref_get_dfs_refer,		"GET DfsRef") \
+	EM(netfs_trace_tcon_ref_get_find,		"GET Find  ") \
+	EM(netfs_trace_tcon_ref_get_find_sess_tcon,	"GET FndSes") \
+	EM(netfs_trace_tcon_ref_get_reconnect_server,	"GET Reconn") \
+	EM(netfs_trace_tcon_ref_new,			"NEW       ") \
+	EM(netfs_trace_tcon_ref_new_ipc,		"NEW Ipc   ") \
+	EM(netfs_trace_tcon_ref_new_reconnect_server,	"NEW Reconn") \
+	EM(netfs_trace_tcon_ref_put_cancelled_close,	"PUT Cn-Cls") \
+	EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \
+	EM(netfs_trace_tcon_ref_put_cancelled_mid,	"PUT Cn-Mid") \
+	EM(netfs_trace_tcon_ref_put_mnt_ctx,		"PUT MntCtx") \
+	EM(netfs_trace_tcon_ref_put_dfs_refer,		"PUT DfsRfr") \
+	EM(netfs_trace_tcon_ref_put_reconnect_server,	"PUT Reconn") \
+	EM(netfs_trace_tcon_ref_put_tlink,		"PUT Tlink ") \
+	EM(netfs_trace_tcon_ref_see_cancelled_close,	"SEE Cn-Cls") \
+	EM(netfs_trace_tcon_ref_see_fscache_collision,	"SEE FV-CO!") \
+	EM(netfs_trace_tcon_ref_see_fscache_okay,	"SEE FV-Ok ") \
+	EM(netfs_trace_tcon_ref_see_fscache_relinq,	"SEE FV-Rlq") \
+	E_(netfs_trace_tcon_ref_see_umount,		"SEE Umount")
+
+#undef EM
+#undef E_
+
+/*
+ * Define those tracing enums.
+ */
+#ifndef __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY
+#define __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY
+
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
+
+#undef EM
+#undef E_
+#endif
+
+/*
+ * Export enum symbols via userspace.
+ */
+#define EM(a, b) TRACE_DEFINE_ENUM(a);
+#define E_(a, b) TRACE_DEFINE_ENUM(a);
+
+smb3_tcon_ref_traces;
+
+#undef EM
+#undef E_
+
+/*
+ * Now redefine the EM() and E_() macros to map the enums to the strings that
+ * will be printed in the output.
  */
+#define EM(a, b)	{ a, b },
+#define E_(a, b)	{ a, b }
 
 /* For logging errors in read or write */
 DECLARE_EVENT_CLASS(smb3_rw_err_class,
@@ -937,6 +1002,30 @@ DEFINE_SMB3_CREDIT_EVENT(too_many_credits);
 DEFINE_SMB3_CREDIT_EVENT(add_credits);
 DEFINE_SMB3_CREDIT_EVENT(set_credits);
 
+
+TRACE_EVENT(smb3_tcon_ref,
+	    TP_PROTO(unsigned int tcon_debug_id, int ref,
+		     enum smb3_tcon_ref_trace trace),
+	    TP_ARGS(tcon_debug_id, ref, trace),
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		tcon)
+		    __field(int,			ref)
+		    __field(enum smb3_tcon_ref_trace,	trace)
+			     ),
+	    TP_fast_assign(
+		    __entry->tcon	= tcon_debug_id;
+		    __entry->ref	= ref;
+		    __entry->trace	= trace;
+			   ),
+	    TP_printk("TC=%08x %s r=%u",
+		      __entry->tcon,
+		      __print_symbolic(__entry->trace, smb3_tcon_ref_traces),
+		      __entry->ref)
+	    );
+
+
+#undef EM
+#undef E_
 #endif /* _CIFS_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
-- 
2.53.0

[PATCH 5.15.y 2/2] smb: client: resolve SWN tcon from live registrations

[Sasha Levin]

From: Michael Bommarito <michael.bommarito@gmail.com>

cifs_swn_notify() looks up a witness registration by id under
cifs_swnreg_idr_mutex, drops the mutex, and then uses the registration's
cached tcon pointer.  That pointer is not a lifetime reference, and it is
not a stable representative once cifs_get_swn_reg() lets multiple tcons
for the same net/share name share one registration id.

A same-share second mount can keep the cifs_swn_reg alive after the first
tcon unregisters and is freed.  The registration then still points at the
freed first tcon, so taking tc_lock or incrementing tc_count through
swnreg->tcon only moves the use-after-free earlier.  Taking tc_lock while
holding cifs_swnreg_idr_mutex also violates the documented CIFS lock
order.

Fix this by making the registration store only the stable witness
identity: id, net name, share name, and notify flags.  When a notify
arrives, copy that identity under cifs_swnreg_idr_mutex, drop the mutex,
then find and pin a live witness tcon that currently matches the net/share
pair under the normal cifs_tcp_ses_lock -> tc_lock order.  The notification
path uses that pinned tcon directly and drops the reference when done.

Registration and unregister messages now use the live tcon passed by the
caller instead of a cached tcon in the registration.  The final unregister
send is folded into cifs_swn_unregister() while the registration is still
protected by cifs_swnreg_idr_mutex.  This removes the previous
find/drop/reacquire raw-pointer window.  The release path only removes the
idr entry and frees the stable identity strings.

This preserves the intended one-registration/many-tcon behavior: a
registration id represents a net/share pair, and notify handling acts on a
live representative selected at use time.  It also preserves CLIENT_MOVE
ordering for the representative tcon because the old-IP unregister is sent
before cifs_swn_register() sends the new-IP register.

Fixes: fed979a7e082 ("cifs: Set witness notification handler for messages from userspace daemon")
Cc: stable@vger.kernel.org
Signed-off-by: Michael Bommarito <michael.bommarito@gmail.com>
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Steve French <stfrench@microsoft.com>
(cherry picked from commit ec457f9afe5ae9538bdcd58fd4cb442b9787e183)

[ sashal: 5.15 adaptations: cifs_swn_resource_state_changed() keeps the
  per-channel GlobalMid_Lock tcpStatus reconnect loop (5.15 lacks
  cifs_signal_cifsd_for_reconnect(), v5.17), switched from swnreg->tcon
  to the tcon argument; cifs_swn_get_tcon() drops the tc_lock pair and
  checks tcon->tidStatus == CifsExiting instead of
  tcon->status == TID_EXITING -- 5.15 has no tc_lock, tc_count and
  tidStatus are protected by the already-held cifs_tcp_ses_lock;
  tcon->tree_name is tcon->treeName in 5.15; trace.h hunks applied to
  fs/cifs/trace.h (pre fs/smb/client move) ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/cifs/cifs_swn.c | 318 ++++++++++++++++++++++++++++++++++++---------
 fs/cifs/trace.h    |   2 +
 2 files changed, 262 insertions(+), 58 deletions(-)

diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index b5b7611ab15d20..bfd17ca309df3d 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -28,10 +28,54 @@ struct cifs_swn_reg {
 	bool net_name_notify;
 	bool share_name_notify;
 	bool ip_notify;
+};
 
-	struct cifs_tcon *tcon;
+struct cifs_swn_reg_info {
+	int id;
+	unsigned int ref_count;
+	const char *net_name;
+	const char *share_name;
+	bool net_name_notify;
+	bool share_name_notify;
+	bool ip_notify;
 };
 
+static void cifs_swn_snapshot_reg(struct cifs_swn_reg *swnreg,
+				  struct cifs_swn_reg_info *info)
+{
+	info->id = swnreg->id;
+	info->ref_count = kref_read(&swnreg->ref_count);
+	info->net_name = swnreg->net_name;
+	info->share_name = swnreg->share_name;
+	info->net_name_notify = swnreg->net_name_notify;
+	info->share_name_notify = swnreg->share_name_notify;
+	info->ip_notify = swnreg->ip_notify;
+}
+
+static int cifs_swn_dup_reg(struct cifs_swn_reg *swnreg,
+			    struct cifs_swn_reg_info *info)
+{
+	cifs_swn_snapshot_reg(swnreg, info);
+
+	info->net_name = kstrdup(swnreg->net_name, GFP_KERNEL);
+	if (!info->net_name)
+		return -ENOMEM;
+
+	info->share_name = kstrdup(swnreg->share_name, GFP_KERNEL);
+	if (!info->share_name) {
+		kfree(info->net_name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void cifs_swn_free_reg_info(struct cifs_swn_reg_info *info)
+{
+	kfree(info->net_name);
+	kfree(info->share_name);
+}
+
 static int cifs_swn_auth_info_krb(struct cifs_tcon *tcon, struct sk_buff *skb)
 {
 	int ret;
@@ -73,7 +117,8 @@ static int cifs_swn_auth_info_ntlm(struct cifs_tcon *tcon, struct sk_buff *skb)
  * The authentication information to connect to the witness service is bundled
  * into the message.
  */
-static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
+static int cifs_swn_send_register_message(struct cifs_swn_reg_info *swnreg,
+					  struct cifs_tcon *tcon)
 {
 	struct sk_buff *skb;
 	struct genlmsghdr *hdr;
@@ -111,10 +156,10 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 	 * told to switch to it (client move message). In these cases we unregister from the
 	 * server address and register to the new address when we receive the notification.
 	 */
-	if (swnreg->tcon->ses->server->use_swn_dstaddr)
-		addr = &swnreg->tcon->ses->server->swn_dstaddr;
+	if (tcon->ses->server->use_swn_dstaddr)
+		addr = &tcon->ses->server->swn_dstaddr;
 	else
-		addr = &swnreg->tcon->ses->server->dstaddr;
+		addr = &tcon->ses->server->dstaddr;
 
 	ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage), addr);
 	if (ret < 0)
@@ -138,10 +183,10 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 			goto nlmsg_fail;
 	}
 
-	authtype = cifs_select_sectype(swnreg->tcon->ses->server, swnreg->tcon->ses->sectype);
+	authtype = cifs_select_sectype(tcon->ses->server, tcon->ses->sectype);
 	switch (authtype) {
 	case Kerberos:
-		ret = cifs_swn_auth_info_krb(swnreg->tcon, skb);
+		ret = cifs_swn_auth_info_krb(tcon, skb);
 		if (ret < 0) {
 			cifs_dbg(VFS, "%s: Failed to get kerberos auth info: %d\n", __func__, ret);
 			goto nlmsg_fail;
@@ -149,7 +194,7 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 		break;
 	case NTLMv2:
 	case RawNTLMSSP:
-		ret = cifs_swn_auth_info_ntlm(swnreg->tcon, skb);
+		ret = cifs_swn_auth_info_ntlm(tcon, skb);
 		if (ret < 0) {
 			cifs_dbg(VFS, "%s: Failed to get NTLM auth info: %d\n", __func__, ret);
 			goto nlmsg_fail;
@@ -179,7 +224,8 @@ static int cifs_swn_send_register_message(struct cifs_swn_reg *swnreg)
 /*
  * Sends an uregister message to the userspace daemon based on the registration
  */
-static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
+static int cifs_swn_send_unregister_message(struct cifs_swn_reg_info *swnreg,
+					    struct cifs_tcon *tcon)
 {
 	struct sk_buff *skb;
 	struct genlmsghdr *hdr;
@@ -208,7 +254,7 @@ static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
 		goto nlmsg_fail;
 
 	ret = nla_put(skb, CIFS_GENL_ATTR_SWN_IP, sizeof(struct sockaddr_storage),
-			&swnreg->tcon->ses->server->dstaddr);
+			&tcon->ses->server->dstaddr);
 	if (ret < 0)
 		goto nlmsg_fail;
 
@@ -244,6 +290,84 @@ static int cifs_swn_send_unregister_message(struct cifs_swn_reg *swnreg)
 	return ret;
 }
 
+/*
+ * Allocation-free mirror of extract_hostname() + extract_sharename() from
+ * fs/cifs/unc.c.  Those helpers kmalloc(GFP_KERNEL); this runs under the
+ * cifs_tcp_ses_lock spinlock, so we mirror their parsing in place against
+ * the caller's stable net_name/share_name strings.
+ * Keep in sync with unc.c.
+ */
+static bool cifs_swn_tcon_matches(struct cifs_tcon *tcon,
+				  const char *net_name,
+				  const char *share_name)
+{
+	const char *unc = tcon->treeName;
+	const char *host, *share, *delim;
+	size_t host_len, share_len;
+
+	if (!tcon->use_witness)
+		return false;
+
+	/* extract_hostname: require strlen(unc) >= 3 */
+	if (strnlen(unc, 3) < 3)
+		return false;
+	/* extract_hostname: skip all leading '\' characters */
+	for (host = unc; *host == '\\'; host++)
+		;
+	if (!*host)
+		return false;
+	delim = strchr(host, '\\');
+	if (!delim)
+		return false;
+	host_len = delim - host;
+	if (strlen(net_name) != host_len ||
+	    strncasecmp(host, net_name, host_len))
+		return false;
+
+	/* extract_sharename: start at unc + 2, then first '\' onward */
+	share = unc + 2;
+	delim = strchr(share, '\\');
+	if (!delim)
+		return false;
+	share = delim + 1;
+	share_len = strlen(share);
+
+	return strlen(share_name) == share_len &&
+	       !strncasecmp(share, share_name, share_len);
+}
+
+/*
+ * One SWN registration id represents one net/share name pair.  Multiple
+ * mounted tcons can therefore share the id.  Pick a live representative at
+ * use time instead of caching the first tcon pointer in the registration.
+ */
+static struct cifs_tcon *cifs_swn_get_tcon(struct cifs_swn_reg_info *swnreg)
+{
+	struct TCP_Server_Info *server;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+		list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+			list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+				if (tcon->tidStatus == CifsExiting ||
+				    !cifs_swn_tcon_matches(tcon, swnreg->net_name,
+							   swnreg->share_name))
+					continue;
+				++tcon->tc_count;
+				trace_smb3_tcon_ref(tcon->debug_id,
+						    tcon->tc_count,
+						    netfs_trace_tcon_ref_get_swn_notify);
+				spin_unlock(&cifs_tcp_ses_lock);
+				return tcon;
+			}
+		}
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+	return NULL;
+}
+
 /*
  * Try to find a matching registration for the tcon's server name and share name.
  * Calls to this function must be protected by cifs_swnreg_idr_mutex.
@@ -350,8 +474,6 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 	reg->net_name_notify = true;
 	reg->share_name_notify = true;
 	reg->ip_notify = (tcon->capabilities & SMB2_SHARE_CAP_SCALEOUT);
-
-	reg->tcon = tcon;
 unlock:
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
@@ -371,11 +493,6 @@ static struct cifs_swn_reg *cifs_get_swn_reg(struct cifs_tcon *tcon)
 static void cifs_swn_reg_release(struct kref *ref)
 {
 	struct cifs_swn_reg *swnreg = container_of(ref, struct cifs_swn_reg, ref_count);
-	int ret;
-
-	ret = cifs_swn_send_unregister_message(swnreg);
-	if (ret < 0)
-		cifs_dbg(VFS, "%s: Failed to send unregister message: %d\n", __func__, ret);
 
 	idr_remove(&cifs_swnreg_idr, swnreg->id);
 	kfree(swnreg->net_name);
@@ -383,33 +500,43 @@ static void cifs_swn_reg_release(struct kref *ref)
 	kfree(swnreg);
 }
 
-static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg)
+static void cifs_put_swn_reg_locked(struct cifs_swn_reg *swnreg,
+				    struct cifs_tcon *tcon)
 {
-	mutex_lock(&cifs_swnreg_idr_mutex);
+	if (kref_read(&swnreg->ref_count) == 1) {
+		struct cifs_swn_reg_info swnreg_info;
+		int ret;
+
+		cifs_swn_snapshot_reg(swnreg, &swnreg_info);
+		ret = cifs_swn_send_unregister_message(&swnreg_info, tcon);
+		if (ret < 0)
+			cifs_dbg(VFS, "%s: Failed to send unregister message: %d\n",
+				 __func__, ret);
+	}
+
 	kref_put(&swnreg->ref_count, cifs_swn_reg_release);
-	mutex_unlock(&cifs_swnreg_idr_mutex);
 }
 
-static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state)
+static int cifs_swn_resource_state_changed(struct cifs_tcon *tcon, const char *name, int state)
 {
 	int i;
 
 	switch (state) {
 	case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name);
-		for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
+		for (i = 0; i < tcon->ses->chan_count; i++) {
 			spin_lock(&GlobalMid_Lock);
-			if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
-				swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+			if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
+				tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
 			spin_unlock(&GlobalMid_Lock);
 		}
 		break;
 	case CIFS_SWN_RESOURCE_STATE_AVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name);
-		for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
+		for (i = 0; i < tcon->ses->chan_count; i++) {
 			spin_lock(&GlobalMid_Lock);
-			if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
-				swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+			if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
+				tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
 			spin_unlock(&GlobalMid_Lock);
 		}
 		break;
@@ -520,7 +647,7 @@ static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *a
 	return ret;
 }
 
-static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_storage *addr)
+static int cifs_swn_client_move(struct cifs_tcon *tcon, struct sockaddr_storage *addr)
 {
 	struct sockaddr_in *ipv4 = (struct sockaddr_in *)addr;
 	struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)addr;
@@ -530,14 +657,17 @@ static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_sto
 	else if (addr->ss_family == AF_INET6)
 		cifs_dbg(FYI, "%s: move to %pI6\n", __func__, &ipv6->sin6_addr);
 
-	return cifs_swn_reconnect(swnreg->tcon, addr);
+	return cifs_swn_reconnect(tcon, addr);
 }
 
 int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cifs_swn_reg *swnreg;
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
 	char name[256];
 	int type;
+	int ret = 0;
 
 	if (info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]) {
 		int swnreg_id;
@@ -545,21 +675,34 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 		swnreg_id = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_REGISTRATION_ID]);
 		mutex_lock(&cifs_swnreg_idr_mutex);
 		swnreg = idr_find(&cifs_swnreg_idr, swnreg_id);
-		mutex_unlock(&cifs_swnreg_idr_mutex);
 		if (swnreg == NULL) {
+			mutex_unlock(&cifs_swnreg_idr_mutex);
 			cifs_dbg(FYI, "%s: registration id %d not found\n", __func__, swnreg_id);
 			return -EINVAL;
 		}
+		ret = cifs_swn_dup_reg(swnreg, &swnreg_info);
+		mutex_unlock(&cifs_swnreg_idr_mutex);
+		if (ret)
+			return ret;
 	} else {
 		cifs_dbg(FYI, "%s: missing registration id attribute\n", __func__);
 		return -EINVAL;
 	}
 
+	tcon = cifs_swn_get_tcon(&swnreg_info);
+	if (!tcon) {
+		cifs_dbg(FYI, "%s: registration id %d has no live tcon\n",
+			 __func__, swnreg_info.id);
+		ret = -ENODEV;
+		goto free_info;
+	}
+
 	if (info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]) {
 		type = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_NOTIFICATION_TYPE]);
 	} else {
 		cifs_dbg(FYI, "%s: missing notification type attribute\n", __func__);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	switch (type) {
@@ -571,15 +714,18 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 					sizeof(name));
 		} else {
 			cifs_dbg(FYI, "%s: missing resource name attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 		if (info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]) {
 			state = nla_get_u32(info->attrs[CIFS_GENL_ATTR_SWN_RESOURCE_STATE]);
 		} else {
 			cifs_dbg(FYI, "%s: missing resource state attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
-		return cifs_swn_resource_state_changed(swnreg, name, state);
+		ret = cifs_swn_resource_state_changed(tcon, name, state);
+		break;
 	}
 	case CIFS_SWN_NOTIFICATION_CLIENT_MOVE: {
 		struct sockaddr_storage addr;
@@ -588,28 +734,36 @@ int cifs_swn_notify(struct sk_buff *skb, struct genl_info *info)
 			nla_memcpy(&addr, info->attrs[CIFS_GENL_ATTR_SWN_IP], sizeof(addr));
 		} else {
 			cifs_dbg(FYI, "%s: missing IP address attribute\n", __func__);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
-		return cifs_swn_client_move(swnreg, &addr);
+		ret = cifs_swn_client_move(tcon, &addr);
+		break;
 	}
 	default:
 		cifs_dbg(FYI, "%s: unknown notification type %d\n", __func__, type);
 		break;
 	}
 
-	return 0;
+out:
+	cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+free_info:
+	cifs_swn_free_reg_info(&swnreg_info);
+	return ret;
 }
 
 int cifs_swn_register(struct cifs_tcon *tcon)
 {
 	struct cifs_swn_reg *swnreg;
+	struct cifs_swn_reg_info swnreg_info;
 	int ret;
 
 	swnreg = cifs_get_swn_reg(tcon);
 	if (IS_ERR(swnreg))
 		return PTR_ERR(swnreg);
 
-	ret = cifs_swn_send_register_message(swnreg);
+	cifs_swn_snapshot_reg(swnreg, &swnreg_info);
+	ret = cifs_swn_send_register_message(&swnreg_info, tcon);
 	if (ret < 0) {
 		cifs_dbg(VFS, "%s: Failed to send swn register message: %d\n", __func__, ret);
 		/* Do not put the swnreg or return error, the echo task will retry */
@@ -630,35 +784,68 @@ int cifs_swn_unregister(struct cifs_tcon *tcon)
 		return PTR_ERR(swnreg);
 	}
 
+	cifs_put_swn_reg_locked(swnreg, tcon);
 	mutex_unlock(&cifs_swnreg_idr_mutex);
 
-	cifs_put_swn_reg(swnreg);
-
 	return 0;
 }
 
-void cifs_swn_dump(struct seq_file *m)
+/*
+ * Snapshot one registration under cifs_swnreg_idr_mutex and return.  Callers
+ * intentionally do the per-registration network/genlmsg work without the
+ * mutex held, both to keep the critical section short and to avoid nesting
+ * cifs_swnreg_idr_mutex inside the higher cifs_tcp_ses_lock when a live
+ * tcon is then pinned for the send.
+ */
+static int cifs_swn_get_next_reg_info(int *id, struct cifs_swn_reg_info *info)
 {
 	struct cifs_swn_reg *swnreg;
+	int ret = 0;
+
+	mutex_lock(&cifs_swnreg_idr_mutex);
+	swnreg = idr_get_next(&cifs_swnreg_idr, id);
+	if (swnreg) {
+		ret = cifs_swn_dup_reg(swnreg, info);
+		if (!ret) {
+			*id = swnreg->id + 1;
+			ret = 1;
+		}
+	}
+	mutex_unlock(&cifs_swnreg_idr_mutex);
+
+	return ret;
+}
+
+void cifs_swn_dump(struct seq_file *m)
+{
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
 	struct sockaddr_in *sa;
 	struct sockaddr_in6 *sa6;
-	int id;
+	int id = 0;
+	int ret;
 
 	seq_puts(m, "Witness registrations:");
 
-	mutex_lock(&cifs_swnreg_idr_mutex);
-	idr_for_each_entry(&cifs_swnreg_idr, swnreg, id) {
+	while ((ret = cifs_swn_get_next_reg_info(&id, &swnreg_info)) > 0) {
 		seq_printf(m, "\nId: %u Refs: %u Network name: '%s'%s Share name: '%s'%s Ip address: ",
-				id, kref_read(&swnreg->ref_count),
-				swnreg->net_name, swnreg->net_name_notify ? "(y)" : "(n)",
-				swnreg->share_name, swnreg->share_name_notify ? "(y)" : "(n)");
-		switch (swnreg->tcon->ses->server->dstaddr.ss_family) {
+			   swnreg_info.id, swnreg_info.ref_count,
+			   swnreg_info.net_name, swnreg_info.net_name_notify ? "(y)" : "(n)",
+			   swnreg_info.share_name, swnreg_info.share_name_notify ? "(y)" : "(n)");
+
+		tcon = cifs_swn_get_tcon(&swnreg_info);
+		if (!tcon) {
+			seq_puts(m, "(no live tcon)");
+			goto next;
+		}
+
+		switch (tcon->ses->server->dstaddr.ss_family) {
 		case AF_INET:
-			sa = (struct sockaddr_in *) &swnreg->tcon->ses->server->dstaddr;
+			sa = (struct sockaddr_in *)&tcon->ses->server->dstaddr;
 			seq_printf(m, "%pI4", &sa->sin_addr.s_addr);
 			break;
 		case AF_INET6:
-			sa6 = (struct sockaddr_in6 *) &swnreg->tcon->ses->server->dstaddr;
+			sa6 = (struct sockaddr_in6 *)&tcon->ses->server->dstaddr;
 			seq_printf(m, "%pI6", &sa6->sin6_addr.s6_addr);
 			if (sa6->sin6_scope_id)
 				seq_printf(m, "%%%u", sa6->sin6_scope_id);
@@ -666,23 +853,38 @@ void cifs_swn_dump(struct seq_file *m)
 		default:
 			seq_puts(m, "(unknown)");
 		}
-		seq_printf(m, "%s", swnreg->ip_notify ? "(y)" : "(n)");
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+next:
+		seq_printf(m, "%s", swnreg_info.ip_notify ? "(y)" : "(n)");
+		cifs_swn_free_reg_info(&swnreg_info);
 	}
-	mutex_unlock(&cifs_swnreg_idr_mutex);
+	if (ret < 0)
+		seq_printf(m, "\nFailed to snapshot witness registration: %d", ret);
 	seq_puts(m, "\n");
 }
 
 void cifs_swn_check(void)
 {
-	struct cifs_swn_reg *swnreg;
-	int id;
+	struct cifs_swn_reg_info swnreg_info;
+	struct cifs_tcon *tcon;
+	int id = 0;
 	int ret;
 
-	mutex_lock(&cifs_swnreg_idr_mutex);
-	idr_for_each_entry(&cifs_swnreg_idr, swnreg, id) {
-		ret = cifs_swn_send_register_message(swnreg);
+	while ((ret = cifs_swn_get_next_reg_info(&id, &swnreg_info)) > 0) {
+		tcon = cifs_swn_get_tcon(&swnreg_info);
+		if (!tcon) {
+			cifs_dbg(FYI, "%s: registration id %d has no live tcon\n",
+				 __func__, swnreg_info.id);
+			goto free_info;
+		}
+
+		ret = cifs_swn_send_register_message(&swnreg_info, tcon);
 		if (ret < 0)
 			cifs_dbg(FYI, "%s: Failed to send register message: %d\n", __func__, ret);
+		cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_swn_notify);
+free_info:
+		cifs_swn_free_reg_info(&swnreg_info);
 	}
-	mutex_unlock(&cifs_swnreg_idr_mutex);
+	if (ret < 0)
+		cifs_dbg(FYI, "%s: Failed to snapshot registration: %d\n", __func__, ret);
 }
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 4e66ca4c16517f..787b5b3c57f34a 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -30,6 +30,7 @@
 	EM(netfs_trace_tcon_ref_get_find,		"GET Find  ") \
 	EM(netfs_trace_tcon_ref_get_find_sess_tcon,	"GET FndSes") \
 	EM(netfs_trace_tcon_ref_get_reconnect_server,	"GET Reconn") \
+	EM(netfs_trace_tcon_ref_get_swn_notify,		"GET SwnNot") \
 	EM(netfs_trace_tcon_ref_new,			"NEW       ") \
 	EM(netfs_trace_tcon_ref_new_ipc,		"NEW Ipc   ") \
 	EM(netfs_trace_tcon_ref_new_reconnect_server,	"NEW Reconn") \
@@ -39,6 +40,7 @@
 	EM(netfs_trace_tcon_ref_put_mnt_ctx,		"PUT MntCtx") \
 	EM(netfs_trace_tcon_ref_put_dfs_refer,		"PUT DfsRfr") \
 	EM(netfs_trace_tcon_ref_put_reconnect_server,	"PUT Reconn") \
+	EM(netfs_trace_tcon_ref_put_swn_notify,		"PUT SwnNot") \
 	EM(netfs_trace_tcon_ref_put_tlink,		"PUT Tlink ") \
 	EM(netfs_trace_tcon_ref_see_cancelled_close,	"SEE Cn-Cls") \
 	EM(netfs_trace_tcon_ref_see_fscache_collision,	"SEE FV-CO!") \
-- 
2.53.0