Merge: RHEL-9.8 early NFS Fixes/Stable updates

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7249

Let's update ~~RHEL-9.7~~ RHEL-9.8 with upstream work marked for stable and fixes here.

v4 incoming - added server-side TLS fix
v5 - dropped four spurious net/tls/ fixes

JIRA: https://issues.redhat.com/browse/RHEL-108616
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>

Approved-by: Scott Mayhew <smayhew@redhat.com>
Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: Olga Kornievskaia <okorniev@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Patrick Talbert <ptalbert@redhat.com>

Author: ptalbert

fs/Kconfig

@@ -359,6 +359,7 @@ config GRACE_PERIOD
 config LOCKD
 	tristate
 	depends on FILE_LOCKING
+	select CRC32
 	select GRACE_PERIOD
 
 config LOCKD_V4

fs/nfs/Kconfig

@@ -2,6 +2,7 @@
 config NFS_FS
 	tristate "NFS client support"
 	depends on INET && FILE_LOCKING && MULTIUSER
+	select CRC32
 	select LOCKD
 	select SUNRPC
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
@@ -194,7 +195,6 @@ config NFS_USE_KERNEL_DNS
 config NFS_DEBUG
 	bool
 	depends on NFS_FS && SUNRPC_DEBUG
-	select CRC32
 	default y
 
 config NFS_DISABLE_UDP_SUPPORT

fs/nfs/client.c

@@ -664,6 +664,44 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp,
 }
 EXPORT_SYMBOL_GPL(nfs_init_client);
 
+static void nfs4_server_set_init_caps(struct nfs_server *server)
+{
+#if IS_ENABLED(CONFIG_NFS_V4)
+	/* Set the basic capabilities */
+	server->caps = server->nfs_client->cl_mvops->init_caps;
+	if (server->flags & NFS_MOUNT_NORDIRPLUS)
+		server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping &&
+	    server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+#endif
+}
+
+void nfs_server_set_init_caps(struct nfs_server *server)
+{
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		break;
+	case 3:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		if (!(server->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+		break;
+	default:
+		nfs4_server_set_init_caps(server);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(nfs_server_set_init_caps);
+
 /*
  * Create a version 2 or 3 client
  */
@@ -705,7 +743,6 @@ static int nfs_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = ctx->flags;
 	server->options = ctx->options;
-	server->caps |= NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
 
 	switch (clp->rpc_ops->version) {
 	case 2:
@@ -741,6 +778,8 @@ static int nfs_init_server(struct nfs_server *server,
 	if (error < 0)
 		goto error;
 
+	nfs_server_set_init_caps(server);
+
 	/* Preserve the values of mount_server-related mount options */
 	if (ctx->mount_server.addrlen) {
 		memcpy(&server->mountd_address, &ctx->mount_server.address,
@@ -830,6 +869,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	if (fsinfo->xattr_support)
 		server->caps |= NFS_CAP_XATTR;
+	else
+		server->caps &= ~NFS_CAP_XATTR;
 #endif
 }
 
@@ -915,7 +956,6 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->acregmax = source->acregmax;
 	target->acdirmin = source->acdirmin;
 	target->acdirmax = source->acdirmax;
-	target->caps = source->caps;
 	target->options = source->options;
 	target->auth_info = source->auth_info;
 	target->port = source->port;
@@ -1149,6 +1189,8 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	if (error < 0)
 		goto out_free_server;
 
+	nfs_server_set_init_caps(server);
+
 	/* probe the filesystem info for this server filesystem */
 	error = nfs_probe_server(server, fh);
 	if (error < 0)

fs/nfs/delegation.c

@@ -79,6 +79,7 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
 				       struct nfs_delegation *delegation)
 {
 	set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
+	set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 }
 
@@ -330,14 +331,16 @@ nfs_start_delegation_return(struct nfs_inode *nfsi)
 }
 
 static void nfs_abort_delegation_return(struct nfs_delegation *delegation,
-					struct nfs_client *clp, int err)
+					struct nfs_server *server, int err)
 {
-
 	spin_lock(&delegation->lock);
 	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	if (err == -EAGAIN) {
 		set_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags);
-		set_bit(NFS4CLNT_DELEGRETURN_DELAYED, &clp->cl_state);
+		set_bit(NFS4SERV_DELEGRETURN_DELAYED,
+			&server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGRETURN_DELAYED,
+			&server->nfs_client->cl_state);
 	}
 	spin_unlock(&delegation->lock);
 }
@@ -547,7 +550,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
  */
 static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
 {
-	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct nfs_server *server = NFS_SERVER(inode);
 	unsigned int mode = O_WRONLY | O_RDWR;
 	int err = 0;
 
@@ -569,11 +572,11 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 		/*
 		 * Guard against state recovery
 		 */
-		err = nfs4_wait_clnt_recover(clp);
+		err = nfs4_wait_clnt_recover(server->nfs_client);
 	}
 
 	if (err) {
-		nfs_abort_delegation_return(delegation, clp, err);
+		nfs_abort_delegation_return(delegation, server, err);
 		goto out;
 	}
 
@@ -590,17 +593,6 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
-	else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) {
-		struct inode *inode;
-
-		spin_lock(&delegation->lock);
-		inode = delegation->inode;
-		if (inode && list_empty(&NFS_I(inode)->open_files))
-			ret = true;
-		spin_unlock(&delegation->lock);
-	}
-	if (ret)
-		clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
 	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
@@ -619,6 +611,9 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
 	struct nfs_delegation *place_holder_deleg = NULL;
 	int err = 0;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN,
+				&server->delegation_flags))
+		return 0;
 restart:
 	/*
 	 * To avoid quadratic looping we hold a reference
@@ -670,6 +665,7 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
 		cond_resched();
 		if (!err)
 			goto restart;
+		set_bit(NFS4SERV_DELEGRETURN, &server->delegation_flags);
 		set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
 		goto out;
 	}
@@ -684,13 +680,17 @@ static bool nfs_server_clear_delayed_delegations(struct nfs_server *server)
 	struct nfs_delegation *d;
 	bool ret = false;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGRETURN_DELAYED,
+				&server->delegation_flags))
+		goto out;
 	list_for_each_entry_rcu (d, &server->delegations, super_list) {
 		if (!test_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags))
 			continue;
 		nfs_mark_return_delegation(server, d);
 		clear_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags);
 		ret = true;
 	}
+out:
 	return ret;
 }
 
@@ -780,6 +780,43 @@ int nfs4_inode_return_delegation(struct inode *inode)
 	return 0;
 }
 
+/**
+ * nfs4_inode_set_return_delegation_on_close - asynchronously return a delegation
+ * @inode: inode to process
+ *
+ * This routine is called to request that the delegation be returned as soon
+ * as the file is closed. If the file is already closed, the delegation is
+ * immediately returned.
+ */
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	struct nfs_delegation *ret = NULL;
+
+	if (!inode)
+		return;
+	rcu_read_lock();
+	delegation = nfs4_get_valid_delegation(inode);
+	if (!delegation)
+		goto out;
+	spin_lock(&delegation->lock);
+	if (!delegation->inode)
+		goto out_unlock;
+	if (list_empty(&NFS_I(inode)->open_files) &&
+	    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+		/* Refcount matched in nfs_end_delegation_return() */
+		ret = nfs_get_delegation(delegation);
+	} else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out_unlock:
+	spin_unlock(&delegation->lock);
+	if (ret)
+		nfs_clear_verifier_delegated(inode);
+out:
+	rcu_read_unlock();
+	nfs_end_delegation_return(inode, ret, 0);
+}
+
 /**
  * nfs4_inode_return_delegation_on_close - asynchronously return a delegation
  * @inode: inode to process
@@ -841,11 +878,25 @@ int nfs4_inode_make_writeable(struct inode *inode)
 	return nfs4_inode_return_delegation(inode);
 }
 
-static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
-		struct nfs_delegation *delegation)
+static void
+nfs_mark_return_if_closed_delegation(struct nfs_server *server,
+				     struct nfs_delegation *delegation)
 {
-	set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
+	struct inode *inode;
+
+	if (test_bit(NFS_DELEGATION_RETURN, &delegation->flags) ||
+	    test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags))
+		return;
+	spin_lock(&delegation->lock);
+	inode = delegation->inode;
+	if (!inode)
+		goto out;
+	if (list_empty(&NFS_I(inode)->open_files))
+		nfs_mark_return_delegation(server, delegation);
+	else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out:
+	spin_unlock(&delegation->lock);
 }
 
 static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)
@@ -1245,6 +1296,7 @@ static void nfs_mark_test_expired_delegation(struct nfs_server *server,
 		return;
 	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
 	set_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
+	set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
 	set_bit(NFS4CLNT_DELEGATION_EXPIRED, &server->nfs_client->cl_state);
 }
 
@@ -1323,6 +1375,9 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 	nfs4_stateid stateid;
 	unsigned long gen = ++server->delegation_gen;
 
+	if (!test_and_clear_bit(NFS4SERV_DELEGATION_EXPIRED,
+				&server->delegation_flags))
+		return 0;
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
@@ -1352,6 +1407,9 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
 			goto restart;
 		}
 		nfs_inode_mark_test_expired_delegation(server,inode);
+		set_bit(NFS4SERV_DELEGATION_EXPIRED, &server->delegation_flags);
+		set_bit(NFS4CLNT_DELEGATION_EXPIRED,
+			&server->nfs_client->cl_state);
 		iput(inode);
 		return -EAGAIN;
 	}

fs/nfs/delegation.h

@@ -49,6 +49,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 				  unsigned long pagemod_limit, u32 deleg_type);
 int nfs4_inode_return_delegation(struct inode *inode);
 void nfs4_inode_return_delegation_on_close(struct inode *inode);
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_evict_delegation(struct inode *inode);
 

fs/nfs/direct.c

@@ -56,6 +56,7 @@
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 
+#include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
 #include "pnfs.h"
@@ -286,6 +287,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	nfs_direct_count_bytes(dreq, hdr);
 	spin_unlock(&dreq->lock);
 
+	nfs_update_delegated_atime(dreq->inode);
+
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
@@ -770,6 +773,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 
 	spin_lock(&inode->i_lock);
 	nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count);
+	nfs_update_delegated_mtime_locked(dreq->inode);
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {

fs/nfs/export.c

@@ -66,14 +66,21 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 {
 	struct nfs_fattr *fattr = NULL;
 	struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
-	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	size_t fh_size = offsetof(struct nfs_fh, data);
 	const struct nfs_rpc_ops *rpc_ops;
 	struct dentry *dentry;
 	struct inode *inode;
-	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+	int len = EMBED_FH_OFF;
 	u32 *p = fid->raw;
 	int ret;
 
+	/* Initial check of bounds */
+	if (fh_len < len + XDR_QUADLEN(fh_size) ||
+	    fh_len > XDR_QUADLEN(NFS_MAXFHSIZE))
+		return NULL;
+	/* Calculate embedded filehandle size */
+	fh_size += server_fh->size;
+	len += XDR_QUADLEN(fh_size);
 	/* NULL translates to ESTALE */
 	if (fh_len < len || fh_type != len)
 		return NULL;

fs/nfs/file.c

@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 #include <linux/uaccess.h>
 #include <linux/filelock.h>
@@ -429,7 +430,7 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
 	/* If the private flag is set, then the folio is not freeable */
 	if (folio_test_private(folio)) {
 		if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
-		    current_is_kswapd())
+		    current_is_kswapd() || current_is_kcompactd())
 			return false;
 		if (nfs_wb_folio(folio->mapping->host, folio) < 0)
 			return false;