Merge: RHEL-9.5: NFS fixes and stable

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/4941

Fixes and stable updates for NFS RHEL-9.5

JIRA: https://issues.redhat.com/browse/RHEL-53004  
BREW: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=63139189  
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>

Approved-by: Steve Dickson <steved@redhat.com>
Approved-by: Scott Mayhew <smayhew@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Lucas Zampieri <lzampier@redhat.com>

Author: zampierilucas

fs/nfs/dir.c

@@ -1804,9 +1804,10 @@ __nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,
 		if (parent != READ_ONCE(dentry->d_parent))
 			return -ECHILD;
 	} else {
-		/* Wait for unlink to complete */
+		/* Wait for unlink to complete - see unblock_revalidate() */
 		wait_var_event(&dentry->d_fsdata,
-			       dentry->d_fsdata != NFS_FSDATA_BLOCKED);
+			       smp_load_acquire(&dentry->d_fsdata)
+			       != NFS_FSDATA_BLOCKED);
 		parent = dget_parent(dentry);
 		ret = reval(d_inode(parent), dentry, flags);
 		dput(parent);
@@ -1819,6 +1820,29 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate);
 }
 
+static void block_revalidate(struct dentry *dentry)
+{
+	/* old devname - just in case */
+	kfree(dentry->d_fsdata);
+
+	/* Any new reference that could lead to an open
+	 * will take ->d_lock in lookup_open() -> d_lookup().
+	 * Holding this lock ensures we cannot race with
+	 * __nfs_lookup_revalidate() and removes and need
+	 * for further barriers.
+	 */
+	lockdep_assert_held(&dentry->d_lock);
+
+	dentry->d_fsdata = NFS_FSDATA_BLOCKED;
+}
+
+static void unblock_revalidate(struct dentry *dentry)
+{
+	/* store_release ensures wait_var_event() sees the update */
+	smp_store_release(&dentry->d_fsdata, NULL);
+	wake_up_var(&dentry->d_fsdata);
+}
+
 /*
  * A weaker form of d_revalidate for revalidating just the d_inode(dentry)
  * when we don't really care about the dentry name. This is called when a
@@ -2503,15 +2527,12 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		spin_unlock(&dentry->d_lock);
 		goto out;
 	}
-	/* old devname */
-	kfree(dentry->d_fsdata);
-	dentry->d_fsdata = NFS_FSDATA_BLOCKED;
+	block_revalidate(dentry);
 
 	spin_unlock(&dentry->d_lock);
 	error = nfs_safe_remove(dentry);
 	nfs_dentry_remove_handle_error(dir, dentry, error);
-	dentry->d_fsdata = NULL;
-	wake_up_var(&dentry->d_fsdata);
+	unblock_revalidate(dentry);
 out:
 	trace_nfs_unlink_exit(dir, dentry, error);
 	return error;
@@ -2618,8 +2639,7 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
 {
 	struct dentry *new_dentry = data->new_dentry;
 
-	new_dentry->d_fsdata = NULL;
-	wake_up_var(&new_dentry->d_fsdata);
+	unblock_revalidate(new_dentry);
 }
 
 /*
@@ -2681,11 +2701,6 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 		if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) ||
 		    WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED))
 			goto out;
-		if (new_dentry->d_fsdata) {
-			/* old devname */
-			kfree(new_dentry->d_fsdata);
-			new_dentry->d_fsdata = NULL;
-		}
 
 		spin_lock(&new_dentry->d_lock);
 		if (d_count(new_dentry) > 2) {
@@ -2707,7 +2722,7 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 			new_dentry = dentry;
 			new_inode = NULL;
 		} else {
-			new_dentry->d_fsdata = NFS_FSDATA_BLOCKED;
+			block_revalidate(new_dentry);
 			must_unblock = true;
 			spin_unlock(&new_dentry->d_lock);
 		}
@@ -2719,6 +2734,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
 				must_unblock ? nfs_unblock_rename : NULL);
 	if (IS_ERR(task)) {
+		if (must_unblock)
+			unblock_revalidate(new_dentry);
 		error = PTR_ERR(task);
 		goto out;
 	}

fs/nfs/direct.c

@@ -141,8 +141,6 @@ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
 {
 	ssize_t ret;
 
-	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
-
 	if (iov_iter_rw(iter) == READ)
 		ret = nfs_file_direct_read(iocb, iter, true);
 	else

fs/nfs/file.c

@@ -412,7 +412,7 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_folio_cancel(inode, folio);
 	folio_wait_fscache(folio);
-	trace_nfs_invalidate_folio(inode, folio);
+	trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
 }
 
 /*
@@ -480,7 +480,8 @@ static int nfs_launder_folio(struct folio *folio)
 
 	folio_wait_fscache(folio);
 	ret = nfs_wb_folio(inode, folio);
-	trace_nfs_launder_folio_done(inode, folio, ret);
+	trace_nfs_launder_folio_done(inode, folio_pos(folio),
+			folio_size(folio), ret);
 	return ret;
 }
 

fs/nfs/filelayout/filelayout.c

@@ -883,7 +883,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 						      NFS4_MAX_UINT64,
 						      IOMODE_READ,
 						      false,
-						      GFP_KERNEL);
+						      nfs_io_gfp_mask());
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
@@ -907,7 +907,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 						      NFS4_MAX_UINT64,
 						      IOMODE_RW,
 						      false,
-						      GFP_NOFS);
+						      nfs_io_gfp_mask());
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;

fs/nfs/fs_context.c

@@ -1111,9 +1111,12 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		ctx->acdirmax	= data->acdirmax;
 		ctx->need_mount	= false;
 
-		memcpy(sap, &data->addr, sizeof(data->addr));
-		ctx->nfs_server.addrlen = sizeof(data->addr);
-		ctx->nfs_server.port = ntohs(data->addr.sin_port);
+		if (!is_remount_fc(fc)) {
+			memcpy(sap, &data->addr, sizeof(data->addr));
+			ctx->nfs_server.addrlen = sizeof(data->addr);
+			ctx->nfs_server.port = ntohs(data->addr.sin_port);
+		}
+
 		if (sap->ss_family != AF_INET ||
 		    !nfs_verify_server_address(sap))
 			goto out_no_address;

fs/nfs/internal.h

@@ -710,9 +710,9 @@ unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
 	if ((bsize & (bsize - 1)) || nrbitsp) {
 		unsigned char	nrbits;
 
-		for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
+		for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--)
 			;
-		bsize = 1 << nrbits;
+		bsize = 1UL << nrbits;
 		if (nrbitsp)
 			*nrbitsp = nrbits;
 	}

fs/nfs/nfs4client.c

@@ -231,9 +231,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
 		__set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
 	__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
-
-	if (test_bit(NFS_CS_DS, &cl_init->init_flags))
-		__set_bit(NFS_CS_DS, &clp->cl_flags);
+	if (test_bit(NFS_CS_PNFS, &cl_init->init_flags))
+		__set_bit(NFS_CS_PNFS, &clp->cl_flags);
 	/*
 	 * Set up the connection to the server before we add add to the
 	 * global list.
@@ -1011,7 +1010,6 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
-	__set_bit(NFS_CS_DS, &cl_init.init_flags);
 	__set_bit(NFS_CS_PNFS, &cl_init.init_flags);
 	cl_init.max_connect = NFS_MAX_TRANSPORTS;
 	/*

fs/nfs/nfs4proc.c

@@ -4028,6 +4028,23 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location,
 	}
 }
 
+static bool _is_same_nfs4_pathname(struct nfs4_pathname *path1,
+				   struct nfs4_pathname *path2)
+{
+	int i;
+
+	if (path1->ncomponents != path2->ncomponents)
+		return false;
+	for (i = 0; i < path1->ncomponents; i++) {
+		if (path1->components[i].len != path2->components[i].len)
+			return false;
+		if (memcmp(path1->components[i].data, path2->components[i].data,
+				path1->components[i].len))
+			return false;
+	}
+	return true;
+}
+
 static int _nfs4_discover_trunking(struct nfs_server *server,
 				   struct nfs_fh *fhandle)
 {
@@ -4061,9 +4078,13 @@ static int _nfs4_discover_trunking(struct nfs_server *server,
 	if (status)
 		goto out_free_3;
 
-	for (i = 0; i < locations->nlocations; i++)
+	for (i = 0; i < locations->nlocations; i++) {
+		if (!_is_same_nfs4_pathname(&locations->fs_path,
+					&locations->locations[i].rootpath))
+			continue;
 		test_fs_location_for_trunking(&locations->locations[i], clp,
 					      server);
+	}
 out_free_3:
 	kfree(locations->fattr);
 out_free_2:
@@ -5461,7 +5482,7 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
 	struct rpc_message *msg = &task->tk_msg;
 
 	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
-	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+	    task->tk_status == -ENOTSUPP) {
 		server->caps &= ~NFS_CAP_READ_PLUS;
 		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 		rpc_restart_call_prepare(task);
@@ -8820,7 +8841,7 @@ nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred,
 #ifdef CONFIG_NFS_V4_1_MIGRATION
 	calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR;
 #endif
-	if (test_bit(NFS_CS_DS, &clp->cl_flags))
+	if (test_bit(NFS_CS_PNFS, &clp->cl_flags))
 		calldata->args.flags |= EXCHGID4_FLAG_USE_PNFS_DS;
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;

fs/nfs/nfstrace.h

@@ -939,18 +939,19 @@ TRACE_EVENT(nfs_sillyrename_unlink,
 DECLARE_EVENT_CLASS(nfs_folio_event,
 		TP_PROTO(
 			const struct inode *inode,
-			struct folio *folio
+			loff_t offset,
+			size_t count
 		),
 
-		TP_ARGS(inode, folio),
+		TP_ARGS(inode, offset, count),
 
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
 			__field(u64, version)
 			__field(loff_t, offset)
-			__field(u32, count)
+			__field(size_t, count)
 		),
 
 		TP_fast_assign(
@@ -960,13 +961,13 @@ DECLARE_EVENT_CLASS(nfs_folio_event,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->version = inode_peek_iversion_raw(inode);
-			__entry->offset = folio_file_pos(folio);
-			__entry->count = nfs_folio_length(folio);
+			__entry->offset = offset,
+			__entry->count = count;
 		),
 
 		TP_printk(
 			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
-			"offset=%lld count=%u",
+			"offset=%lld count=%zu",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle, __entry->version,
@@ -978,18 +979,20 @@ DECLARE_EVENT_CLASS(nfs_folio_event,
 	DEFINE_EVENT(nfs_folio_event, name, \
 			TP_PROTO( \
 				const struct inode *inode, \
-				struct folio *folio \
+				loff_t offset, \
+				size_t count \
 			), \
-			TP_ARGS(inode, folio))
+			TP_ARGS(inode, offset, count))
 
 DECLARE_EVENT_CLASS(nfs_folio_event_done,
 		TP_PROTO(
 			const struct inode *inode,
-			struct folio *folio,
+			loff_t offset,
+			size_t count,
 			int ret
 		),
 
-		TP_ARGS(inode, folio, ret),
+		TP_ARGS(inode, offset, count, ret),
 
 		TP_STRUCT__entry(
 			__field(dev_t, dev)
@@ -998,7 +1001,7 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
 			__field(u64, fileid)
 			__field(u64, version)
 			__field(loff_t, offset)
-			__field(u32, count)
+			__field(size_t, count)
 		),
 
 		TP_fast_assign(
@@ -1008,14 +1011,14 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->version = inode_peek_iversion_raw(inode);
-			__entry->offset = folio_file_pos(folio);
-			__entry->count = nfs_folio_length(folio);
+			__entry->offset = offset,
+			__entry->count = count,
 			__entry->ret = ret;
 		),
 
 		TP_printk(
 			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
-			"offset=%lld count=%u ret=%d",
+			"offset=%lld count=%zu ret=%d",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle, __entry->version,
@@ -1027,10 +1030,11 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
 	DEFINE_EVENT(nfs_folio_event_done, name, \
 			TP_PROTO( \
 				const struct inode *inode, \
-				struct folio *folio, \
+				loff_t offset, \
+				size_t count, \
 				int ret \
 			), \
-			TP_ARGS(inode, folio, ret))
+			TP_ARGS(inode, offset, count, ret))
 
 DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage);
 DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done);

fs/nfs/read.c

@@ -332,13 +332,15 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
 int nfs_read_folio(struct file *file, struct folio *folio)
 {
 	struct inode *inode = file_inode(file);
+	loff_t pos = folio_pos(folio);
+	size_t len = folio_size(folio);
 	struct nfs_pageio_descriptor pgio;
 	struct nfs_open_context *ctx;
 	int ret;
 
-	trace_nfs_aop_readpage(inode, folio);
+	trace_nfs_aop_readpage(inode, pos, len);
 	nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
-	task_io_account_read(folio_size(folio));
+	task_io_account_read(len);
 
 	/*
 	 * Try to flush any pending writes to the file..
@@ -381,7 +383,7 @@ int nfs_read_folio(struct file *file, struct folio *folio)
 out_put:
 	put_nfs_open_context(ctx);
 out:
-	trace_nfs_aop_readpage_done(inode, folio, ret);
+	trace_nfs_aop_readpage_done(inode, pos, len, ret);
 	return ret;
 out_unlock:
 	folio_unlock(folio);