[PATCH 38/64] vfs, cachefiles: Mark a backing file in use with an inode flag

[David Howells <dhowells@redhat.com>]

Use an inode flag, S_KERNEL_FILE, to mark that a backing file is in use by
the kernel to prevent cachefiles or other kernel services from interfering
with that file.

Alter rmdir to reject attempts to remove a directory marked with this flag.
This is used by cachefiles to prevent cachefilesd from removing them.

Using S_SWAPFILE instead isn't really viable as that has other effects in
the I/O paths.

Signed-off-by: David Howells <dhowells@redhat.com>
---

 fs/cachefiles/Makefile            |    1 +
 fs/cachefiles/namei.c             |   44 +++++++++++++++++++++++++++++++++++++
 fs/namei.c                        |    3 ++-
 include/linux/fs.h                |    1 +
 include/trace/events/cachefiles.h |   42 +++++++++++++++++++++++++++++++++++
 5 files changed, 90 insertions(+), 1 deletion(-)
 create mode 100644 fs/cachefiles/namei.c

diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
index 463e3d608b75..e0b092ca077f 100644
--- a/fs/cachefiles/Makefile
+++ b/fs/cachefiles/Makefile
@@ -7,6 +7,7 @@ cachefiles-y := \
 	cache.o \
 	daemon.o \
 	main.o \
+	namei.o \
 	security.o
 
 cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
new file mode 100644
index 000000000000..fef06d2a88ec
--- /dev/null
+++ b/fs/cachefiles/namei.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* CacheFiles path walking and related routines
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include "internal.h"
+
+/*
+ * Mark the backing file as being a cache file if it's not already in use.  The
+ * mark tells the culling request command that it's not allowed to cull the
+ * file or directory.  The caller must hold the inode lock.
+ */
+static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object,
+					   struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	bool can_use = false;
+
+	if (!(inode->i_flags & S_KERNEL_FILE)) {
+		inode->i_flags |= S_KERNEL_FILE;
+		if (object)
+			trace_cachefiles_mark_active(object, inode);
+		can_use = true;
+	} else {
+		pr_notice("cachefiles: Inode already in use: %pd\n", dentry);
+	}
+
+	return can_use;
+}
+
+/*
+ * Unmark a backing inode.  The caller must hold the inode lock.
+ */
+static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object,
+					     struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+
+	inode->i_flags &= ~S_KERNEL_FILE;
+	trace_cachefiles_mark_inactive(object, inode);
+}
diff --git a/fs/namei.c b/fs/namei.c
index 1f9d2187c765..d81f04f8d818 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3958,7 +3958,8 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir,
 	inode_lock(dentry->d_inode);
 
 	error = -EBUSY;
-	if (is_local_mountpoint(dentry))
+	if (is_local_mountpoint(dentry) ||
+	    (dentry->d_inode->i_flags & S_KERNEL_FILE))
 		goto out;
 
 	error = security_inode_rmdir(dir, dentry);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 473ea3ff0ad4..d4ec20f51129 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2249,6 +2249,7 @@ struct super_operations {
 #define S_ENCRYPTED	(1 << 14) /* Encrypted file (using fs/crypto/) */
 #define S_CASEFOLD	(1 << 15) /* Casefolded file */
 #define S_VERITY	(1 << 16) /* Verity file (using fs/verity/) */
+#define S_KERNEL_FILE	(1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h
index 9bd5a8a60801..29fdcfddbbc2 100644
--- a/include/trace/events/cachefiles.h
+++ b/include/trace/events/cachefiles.h
@@ -83,6 +83,48 @@ cachefiles_error_traces;
 #define E_(a, b)	{ a, b }
 
 
+TRACE_EVENT(cachefiles_mark_active,
+	    TP_PROTO(struct cachefiles_object *obj,
+		     struct inode *inode),
+
+	    TP_ARGS(obj, inode),
+
+	    /* Note that obj may be NULL */
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		obj		)
+		    __field(ino_t,			inode		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->obj	= obj->debug_id;
+		    __entry->inode	= inode->i_ino;
+			   ),
+
+	    TP_printk("o=%08x i=%lx",
+		      __entry->obj, __entry->inode)
+	    );
+
+TRACE_EVENT(cachefiles_mark_inactive,
+	    TP_PROTO(struct cachefiles_object *obj,
+		     struct inode *inode),
+
+	    TP_ARGS(obj, inode),
+
+	    /* Note that obj may be NULL */
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		obj		)
+		    __field(ino_t,			inode		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->obj	= obj->debug_id;
+		    __entry->inode	= inode->i_ino;
+			   ),
+
+	    TP_printk("o=%08x i=%lx",
+		      __entry->obj, __entry->inode)
+	    );
+
 TRACE_EVENT(cachefiles_vfs_error,
 	    TP_PROTO(struct cachefiles_object *obj, struct inode *backer,
 		     int error, enum cachefiles_error_trace where),