Merge tag 'fsnotify_for_v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "Support for reporting filesystem errors through fanotify so that
  system health monitoring daemons can watch for these and act instead
  of scraping system logs"

* tag 'fsnotify_for_v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (34 commits)
  samples: remove duplicate include in fs-monitor.c
  samples: Fix warning in fsnotify sample
  docs: Fix formatting of literal sections in fanotify docs
  samples: Make fs-monitor depend on libc and headers
  docs: Document the FAN_FS_ERROR event
  samples: Add fs error monitoring example
  ext4: Send notifications on error
  fanotify: Allow users to request FAN_FS_ERROR events
  fanotify: Emit generic error info for error event
  fanotify: Report fid info for file related file system errors
  fanotify: WARN_ON against too large file handles
  fanotify: Add helpers to decide whether to report FID/DFID
  fanotify: Wrap object_fh inline space in a creator macro
  fanotify: Support merging of error events
  fanotify: Support enqueueing of error events
  fanotify: Pre-allocate pool of error events
  fanotify: Reserve UAPI bits for FAN_FS_ERROR
  fsnotify: Support FS_ERROR event type
  fanotify: Require fid_mode for any non-fd event
  fanotify: Encode empty file handle when no inode is provided
  ...

Documentation/admin-guide/filesystem-monitoring.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+====================================
+File system Monitoring with fanotify
+====================================
+
+File system Error Reporting
+===========================
+
+Fanotify supports the FAN_FS_ERROR event type for file system-wide error
+reporting.  It is meant to be used by file system health monitoring
+daemons, which listen for these events and take actions (notify
+sysadmin, start recovery) when a file system problem is detected.
+
+By design, a FAN_FS_ERROR notification exposes sufficient information
+for a monitoring tool to know a problem in the file system has happened.
+It doesn't necessarily provide a user space application with semantics
+to verify an IO operation was successfully executed.  That is out of
+scope for this feature.  Instead, it is only meant as a framework for
+early file system problem detection and reporting recovery tools.
+
+When a file system operation fails, it is common for dozens of kernel
+errors to cascade after the initial failure, hiding the original failure
+log, which is usually the most useful debug data to troubleshoot the
+problem.  For this reason, FAN_FS_ERROR tries to report only the first
+error that occurred for a file system since the last notification, and
+it simply counts additional errors.  This ensures that the most
+important pieces of information are never lost.
+
+FAN_FS_ERROR requires the fanotify group to be setup with the
+FAN_REPORT_FID flag.
+
+At the time of this writing, the only file system that emits FAN_FS_ERROR
+notifications is Ext4.
+
+A FAN_FS_ERROR Notification has the following format::
+
+  ::
+
+     [ Notification Metadata (Mandatory) ]
+     [ Generic Error Record  (Mandatory) ]
+     [ FID record            (Mandatory) ]
+
+The order of records is not guaranteed, and new records might be added
+in the future.  Therefore, applications must not rely on the order and
+must be prepared to skip over unknown records. Please refer to
+``samples/fanotify/fs-monitor.c`` for an example parser.
+
+Generic error record
+--------------------
+
+The generic error record provides enough information for a file system
+agnostic tool to learn about a problem in the file system, without
+providing any additional details about the problem.  This record is
+identified by ``struct fanotify_event_info_header.info_type`` being set
+to FAN_EVENT_INFO_TYPE_ERROR.
+
+  ::
+
+     struct fanotify_event_info_error {
+          struct fanotify_event_info_header hdr;
+         __s32 error;
+         __u32 error_count;
+     };
+
+The `error` field identifies the type of error using errno values.
+`error_count` tracks the number of errors that occurred and were
+suppressed to preserve the original error information, since the last
+notification.
+
+FID record
+----------
+
+The FID record can be used to uniquely identify the inode that triggered
+the error through the combination of fsid and file handle.  A file system
+specific application can use that information to attempt a recovery
+procedure.  Errors that are not related to an inode are reported with an
+empty file handle of type FILEID_INVALID.

Documentation/admin-guide/index.rst

@@ -82,6 +82,7 @@ configure specific aspects of kernel behavior to your liking.
    edid
    efi-stub
    ext4
+   filesystem-monitoring
    nfs/index
    gpio/index
    highuid

fs/ext4/super.c

@@ -46,6 +46,7 @@
 #include <linux/part_stat.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/fsnotify.h>
 
 #include "ext4.h"
 #include "ext4_extents.h"	/* Needed for trace points definition */
@@ -759,6 +760,8 @@ void __ext4_error(struct super_block *sb, const char *function,
 		       sb->s_id, function, line, current->comm, &vaf);
 		va_end(args);
 	}
+	fsnotify_sb_error(sb, NULL, error ? error : EFSCORRUPTED);
+
 	ext4_handle_error(sb, force_ro, error, 0, block, function, line);
 }
 
@@ -789,6 +792,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
 			       current->comm, &vaf);
 		va_end(args);
 	}
+	fsnotify_sb_error(inode->i_sb, inode, error ? error : EFSCORRUPTED);
+
 	ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
 			  function, line);
 }
@@ -827,6 +832,8 @@ void __ext4_error_file(struct file *file, const char *function,
 			       current->comm, path, &vaf);
 		va_end(args);
 	}
+	fsnotify_sb_error(inode->i_sb, inode, EFSCORRUPTED);
+
 	ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
 			  function, line);
 }
@@ -894,6 +901,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 		printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
 		       sb->s_id, function, line, errstr);
 	}
+	fsnotify_sb_error(sb, NULL, errno ? errno : EFSCORRUPTED);
 
 	ext4_handle_error(sb, false, -errno, 0, 0, function, line);
 }

fs/nfsd/filecache.c

@@ -602,6 +602,9 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
 				struct inode *inode, struct inode *dir,
 				const struct qstr *name, u32 cookie)
 {
+	if (WARN_ON_ONCE(!inode))
+		return 0;
+
 	trace_nfsd_file_fsnotify_handle_event(inode, mask);
 
 	/* Should be no marks on non-regular files */

fs/notify/fanotify/fanotify.c

@@ -111,6 +111,16 @@ static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
 	return fanotify_info_equal(info1, info2);
 }
 
+static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
+				       struct fanotify_error_event *fee2)
+{
+	/* Error events against the same file system are always merged. */
+	if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
+		return false;
+
+	return true;
+}
+
 static bool fanotify_should_merge(struct fanotify_event *old,
 				  struct fanotify_event *new)
 {
@@ -141,6 +151,9 @@ static bool fanotify_should_merge(struct fanotify_event *old,
 	case FANOTIFY_EVENT_TYPE_FID_NAME:
 		return fanotify_name_event_equal(FANOTIFY_NE(old),
 						 FANOTIFY_NE(new));
+	case FANOTIFY_EVENT_TYPE_FS_ERROR:
+		return fanotify_error_event_equal(FANOTIFY_EE(old),
+						  FANOTIFY_EE(new));
 	default:
 		WARN_ON_ONCE(1);
 	}
@@ -176,6 +189,10 @@ static int fanotify_merge(struct fsnotify_group *group,
 			break;
 		if (fanotify_should_merge(old, new)) {
 			old->mask |= new->mask;
+
+			if (fanotify_is_error_event(old->mask))
+				FANOTIFY_EE(old)->err_count++;
+
 			return 1;
 		}
 	}
@@ -343,13 +360,23 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 static int fanotify_encode_fh_len(struct inode *inode)
 {
 	int dwords = 0;
+	int fh_len;
 
 	if (!inode)
 		return 0;
 
 	exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
+	fh_len = dwords << 2;
+
+	/*
+	 * struct fanotify_error_event might be preallocated and is
+	 * limited to MAX_HANDLE_SZ.  This should never happen, but
+	 * safeguard by forcing an invalid file handle.
+	 */
+	if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
+		return 0;
 
-	return dwords << 2;
+	return fh_len;
 }
 
 /*
@@ -370,8 +397,14 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
 	fh->type = FILEID_ROOT;
 	fh->len = 0;
 	fh->flags = 0;
+
+	/*
+	 * Invalid FHs are used by FAN_FS_ERROR for errors not
+	 * linked to any inode. The f_handle won't be reported
+	 * back to userspace.
+	 */
 	if (!inode)
-		return 0;
+		goto out;
 
 	/*
 	 * !gpf means preallocated variable size fh, but fh_len could
@@ -403,8 +436,13 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
 	fh->type = type;
 	fh->len = fh_len;
 
-	/* Mix fh into event merge key */
-	*hash ^= fanotify_hash_fh(fh);
+out:
+	/*
+	 * Mix fh into event merge key.  Hash might be NULL in case of
+	 * unhashed FID events (i.e. FAN_FS_ERROR).
+	 */
+	if (hash)
+		*hash ^= fanotify_hash_fh(fh);
 
 	return FANOTIFY_FH_HDR_LEN + fh_len;
 
@@ -452,7 +490,7 @@ static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
 	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
 		return dir;
 
-	if (S_ISDIR(inode->i_mode))
+	if (inode && S_ISDIR(inode->i_mode))
 		return inode;
 
 	return dir;
@@ -563,6 +601,44 @@ static struct fanotify_event *fanotify_alloc_name_event(struct inode *id,
 	return &fne->fae;
 }
 
+static struct fanotify_event *fanotify_alloc_error_event(
+						struct fsnotify_group *group,
+						__kernel_fsid_t *fsid,
+						const void *data, int data_type,
+						unsigned int *hash)
+{
+	struct fs_error_report *report =
+			fsnotify_data_error_report(data, data_type);
+	struct inode *inode;
+	struct fanotify_error_event *fee;
+	int fh_len;
+
+	if (WARN_ON_ONCE(!report))
+		return NULL;
+
+	fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
+	if (!fee)
+		return NULL;
+
+	fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
+	fee->error = report->error;
+	fee->err_count = 1;
+	fee->fsid = *fsid;
+
+	inode = report->inode;
+	fh_len = fanotify_encode_fh_len(inode);
+
+	/* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
+	if (!fh_len && inode)
+		inode = NULL;
+
+	fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);
+
+	*hash ^= fanotify_hash_fsid(fsid);
+
+	return &fee->fae;
+}
+
 static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 						   u32 mask, const void *data,
 						   int data_type, struct inode *dir,
@@ -630,6 +706,9 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 
 	if (fanotify_is_perm_event(mask)) {
 		event = fanotify_alloc_perm_event(path, gfp);
+	} else if (fanotify_is_error_event(mask)) {
+		event = fanotify_alloc_error_event(group, fsid, data,
+						   data_type, &hash);
 	} else if (name_event && (file_name || child)) {
 		event = fanotify_alloc_name_event(id, fsid, file_name, child,
 						  &hash, gfp);
@@ -702,6 +781,9 @@ static void fanotify_insert_event(struct fsnotify_group *group,
 
 	assert_spin_locked(&group->notification_lock);
 
+	if (!fanotify_is_hashed_event(event->mask))
+		return;
+
 	pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
 		 group, event, bucket);
 
@@ -738,8 +820,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
 	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
+	BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20);
 
 	mask = fanotify_group_event_mask(group, iter_info, mask, data,
 					 data_type, dir);
@@ -778,9 +861,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	}
 
 	fsn_event = &event->fse;
-	ret = fsnotify_add_event(group, fsn_event, fanotify_merge,
-				 fanotify_is_hashed_event(mask) ?
-				 fanotify_insert_event : NULL);
+	ret = fsnotify_insert_event(group, fsn_event, fanotify_merge,
+				    fanotify_insert_event);
 	if (ret) {
 		/* Permission events shouldn't be merged */
 		BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
@@ -805,6 +887,9 @@ static void fanotify_free_group_priv(struct fsnotify_group *group)
 	if (group->fanotify_data.ucounts)
 		dec_ucount(group->fanotify_data.ucounts,
 			   UCOUNT_FANOTIFY_GROUPS);
+
+	if (mempool_initialized(&group->fanotify_data.error_events_pool))
+		mempool_exit(&group->fanotify_data.error_events_pool);
 }
 
 static void fanotify_free_path_event(struct fanotify_event *event)
@@ -833,7 +918,16 @@ static void fanotify_free_name_event(struct fanotify_event *event)
 	kfree(FANOTIFY_NE(event));
 }
 
-static void fanotify_free_event(struct fsnotify_event *fsn_event)
+static void fanotify_free_error_event(struct fsnotify_group *group,
+				      struct fanotify_event *event)
+{
+	struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+	mempool_free(fee, &group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_event(struct fsnotify_group *group,
+				struct fsnotify_event *fsn_event)
 {
 	struct fanotify_event *event;
 
@@ -855,6 +949,9 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
 	case FANOTIFY_EVENT_TYPE_OVERFLOW:
 		kfree(event);
 		break;
+	case FANOTIFY_EVENT_TYPE_FS_ERROR:
+		fanotify_free_error_event(group, event);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 	}

fs/notify/fanotify/fanotify.h

@@ -141,6 +141,7 @@ enum fanotify_event_type {
 	FANOTIFY_EVENT_TYPE_PATH,
 	FANOTIFY_EVENT_TYPE_PATH_PERM,
 	FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+	FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
 	__FANOTIFY_EVENT_TYPE_NUM
 };
 
@@ -170,12 +171,18 @@ static inline void fanotify_init_event(struct fanotify_event *event,
 	event->pid = NULL;
 }
 
+#define FANOTIFY_INLINE_FH(name, size)					\
+struct {								\
+	struct fanotify_fh (name);					\
+	/* Space for object_fh.buf[] - access with fanotify_fh_buf() */	\
+	unsigned char _inline_fh_buf[(size)];				\
+}
+
 struct fanotify_fid_event {
 	struct fanotify_event fae;
 	__kernel_fsid_t fsid;
-	struct fanotify_fh object_fh;
-	/* Reserve space in object_fh.buf[] - access with fanotify_fh_buf() */
-	unsigned char _inline_fh_buf[FANOTIFY_INLINE_FH_LEN];
+
+	FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN);
 };
 
 static inline struct fanotify_fid_event *
@@ -196,12 +203,30 @@ FANOTIFY_NE(struct fanotify_event *event)
 	return container_of(event, struct fanotify_name_event, fae);
 }
 
+struct fanotify_error_event {
+	struct fanotify_event fae;
+	s32 error; /* Error reported by the Filesystem. */
+	u32 err_count; /* Suppressed errors count */
+
+	__kernel_fsid_t fsid; /* FSID this error refers to. */
+
+	FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ);
+};
+
+static inline struct fanotify_error_event *
+FANOTIFY_EE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_error_event, fae);
+}
+
 static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
 {
 	if (event->type == FANOTIFY_EVENT_TYPE_FID)
 		return &FANOTIFY_FE(event)->fsid;
 	else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
 		return &FANOTIFY_NE(event)->fsid;
+	else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return &FANOTIFY_EE(event)->fsid;
 	else
 		return NULL;
 }
@@ -213,6 +238,8 @@ static inline struct fanotify_fh *fanotify_event_object_fh(
 		return &FANOTIFY_FE(event)->object_fh;
 	else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
 		return fanotify_info_file_fh(&FANOTIFY_NE(event)->info);
+	else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return &FANOTIFY_EE(event)->object_fh;
 	else
 		return NULL;
 }
@@ -244,6 +271,19 @@ static inline int fanotify_event_dir_fh_len(struct fanotify_event *event)
 	return info ? fanotify_info_dir_fh_len(info) : 0;
 }
 
+static inline bool fanotify_event_has_object_fh(struct fanotify_event *event)
+{
+	/* For error events, even zeroed fh are reported. */
+	if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+		return true;
+	return fanotify_event_object_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event)
+{
+	return fanotify_event_dir_fh_len(event) > 0;
+}
+
 struct fanotify_path_event {
 	struct fanotify_event fae;
 	struct path path;
@@ -287,6 +327,11 @@ static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
 	return container_of(fse, struct fanotify_event, fse);
 }
 
+static inline bool fanotify_is_error_event(u32 mask)
+{
+	return mask & FAN_FS_ERROR;
+}
+
 static inline bool fanotify_event_has_path(struct fanotify_event *event)
 {
 	return event->type == FANOTIFY_EVENT_TYPE_PATH ||
@@ -315,7 +360,8 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event)
  */
 static inline bool fanotify_is_hashed_event(u32 mask)
 {
-	return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW);
+	return !(fanotify_is_perm_event(mask) ||
+		 fsnotify_is_overflow_event(mask));
 }
 
 static inline unsigned int fanotify_event_hash_bucket(

fs/notify/fsnotify.c

@@ -252,6 +252,9 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group,
 	if (WARN_ON_ONCE(!ops->handle_inode_event))
 		return 0;
 
+	if (WARN_ON_ONCE(!inode && !dir))
+		return 0;
+
 	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
 	    path && d_unlinked(path->dentry))
 		return 0;
@@ -455,16 +458,16 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
  *		@file_name is relative to
  * @file_name:	optional file name associated with event
  * @inode:	optional inode associated with event -
- *		either @dir or @inode must be non-NULL.
- *		if both are non-NULL event may be reported to both.
+ *		If @dir and @inode are both non-NULL, event may be
+ *		reported to both.
  * @cookie:	inotify rename cookie
  */
 int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	     const struct qstr *file_name, struct inode *inode, u32 cookie)
 {
 	const struct path *path = fsnotify_data_path(data, data_type);
+	struct super_block *sb = fsnotify_data_sb(data, data_type);
 	struct fsnotify_iter_info iter_info = {};
-	struct super_block *sb;
 	struct mount *mnt = NULL;
 	struct inode *parent = NULL;
 	int ret = 0;
@@ -483,7 +486,6 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		 */
 		parent = dir;
 	}
-	sb = inode->i_sb;
 
 	/*
 	 * Optimization: srcu_read_lock() has a memory barrier which can

fs/notify/group.c

@@ -88,7 +88,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
 	 * that deliberately ignores overflow events.
 	 */
 	if (group->overflow_event)
-		group->ops->free_event(group->overflow_event);
+		group->ops->free_event(group, group->overflow_event);
 
 	fsnotify_put_group(group);
 }

fs/notify/inotify/inotify_fsnotify.c

@@ -116,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 	if (len)
 		strcpy(event->name, name->name);
 
-	ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL);
+	ret = fsnotify_add_event(group, fsn_event, inotify_merge);
 	if (ret) {
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);
@@ -177,7 +177,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
 		dec_inotify_instances(group->inotify_data.ucounts);
 }
 
-static void inotify_free_event(struct fsnotify_event *fsn_event)
+static void inotify_free_event(struct fsnotify_group *group,
+			       struct fsnotify_event *fsn_event)
 {
 	kfree(INOTIFY_E(fsn_event));
 }

fs/notify/inotify/inotify_user.c

@@ -94,10 +94,10 @@ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg)
 	__u32 mask;
 
 	/*
-	 * Everything should accept their own ignored and should receive events
-	 * when the inode is unmounted.  All directories care about children.
+	 * Everything should receive events when the inode is unmounted.
+	 * All directories care about children.
 	 */
-	mask = (FS_IN_IGNORED | FS_UNMOUNT);
+	mask = (FS_UNMOUNT);
 	if (S_ISDIR(inode->i_mode))
 		mask |= FS_EVENT_ON_CHILD;
 

fs/notify/notification.c

@@ -64,7 +64,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
 		WARN_ON(!list_empty(&event->list));
 		spin_unlock(&group->notification_lock);
 	}
-	group->ops->free_event(event);
+	group->ops->free_event(group, event);
 }
 
 /*
@@ -78,12 +78,12 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
  * 2 if the event was not queued - either the queue of events has overflown
  *   or the group is shutting down.
  */
-int fsnotify_add_event(struct fsnotify_group *group,
-		       struct fsnotify_event *event,
-		       int (*merge)(struct fsnotify_group *,
-				    struct fsnotify_event *),
-		       void (*insert)(struct fsnotify_group *,
-				      struct fsnotify_event *))
+int fsnotify_insert_event(struct fsnotify_group *group,
+			  struct fsnotify_event *event,
+			  int (*merge)(struct fsnotify_group *,
+				       struct fsnotify_event *),
+			  void (*insert)(struct fsnotify_group *,
+					 struct fsnotify_event *))
 {
 	int ret = 0;
 	struct list_head *list = &group->notification_list;

include/linux/fanotify.h

@@ -84,13 +84,20 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
  */
 #define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
 
+/* Events that can be reported with event->fd */
+#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS)
+
 /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
 #define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \
 				 FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF)
 
+/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */
+#define FANOTIFY_ERROR_EVENTS	(FAN_FS_ERROR)
+
 /* Events that user can request to be notified on */
 #define FANOTIFY_EVENTS		(FANOTIFY_PATH_EVENTS | \
-				 FANOTIFY_INODE_EVENTS)
+				 FANOTIFY_INODE_EVENTS | \
+				 FANOTIFY_ERROR_EVENTS)
 
 /* Events that require a permission response from user */
 #define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM | \

include/linux/fsnotify.h

@@ -26,20 +26,20 @@
  * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only
  * the child is interested and not the parent.
  */
-static inline void fsnotify_name(struct inode *dir, __u32 mask,
-				 struct inode *child,
-				 const struct qstr *name, u32 cookie)
+static inline int fsnotify_name(__u32 mask, const void *data, int data_type,
+				struct inode *dir, const struct qstr *name,
+				u32 cookie)
 {
 	if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0)
-		return;
+		return 0;
 
-	fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie);
+	return fsnotify(mask, data, data_type, dir, name, NULL, cookie);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 				   __u32 mask)
 {
-	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
+	fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0);
 }
 
 static inline void fsnotify_inode(struct inode *inode, __u32 mask)
@@ -86,7 +86,7 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
  */
 static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 {
-	fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE);
+	fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
 }
 
 static inline int fsnotify_file(struct file *file, __u32 mask)
@@ -154,8 +154,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		new_dir_mask |= FS_ISDIR;
 	}
 
-	fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie);
-	fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie);
+	fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      old_dir, old_name, fs_cookie);
+	fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      new_dir, new_name, fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
@@ -190,16 +192,22 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 
 /*
  * fsnotify_create - 'name' was linked in
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_create(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE);
+	fsnotify_dirent(dir, dentry, FS_CREATE);
 }
 
 /*
  * fsnotify_link - new hardlink in 'inode' directory
+ *
+ * Caller must make sure that new_dentry->d_name is stable.
  * Note: We have to pass also the linked inode ptr as some filesystems leave
  *   new_dentry->d_inode NULL and instantiate inode pointer later
  */
@@ -209,7 +217,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode,
 	fsnotify_link_count(inode);
 	audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0);
+	fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE,
+		      dir, &new_dentry->d_name, 0);
 }
 
 /*
@@ -227,12 +236,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry)
 
 /*
  * fsnotify_mkdir - directory 'name' was created
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR);
+	fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR);
 }
 
 /*
@@ -326,4 +339,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
+static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
+				    int error)
+{
+	struct fs_error_report report = {
+		.error = error,
+		.inode = inode,
+		.sb = sb,
+	};
+
+	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
+			NULL, NULL, NULL, 0);
+}
+
 #endif	/* _LINUX_FS_NOTIFY_H */

include/linux/fsnotify_backend.h

@@ -19,6 +19,7 @@
 #include <linux/atomic.h>
 #include <linux/user_namespace.h>
 #include <linux/refcount.h>
+#include <linux/mempool.h>
 
 /*
  * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
@@ -42,6 +43,12 @@
 
 #define FS_UNMOUNT		0x00002000	/* inode on umount fs */
 #define FS_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define FS_ERROR		0x00008000	/* Filesystem Error (fanotify) */
+
+/*
+ * FS_IN_IGNORED overloads FS_ERROR.  It is only used internally by inotify
+ * which does not support FS_ERROR.
+ */
 #define FS_IN_IGNORED		0x00008000	/* last inotify event here */
 
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
@@ -95,7 +102,8 @@
 #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
 			     FS_EVENTS_POSS_ON_CHILD | \
 			     FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \
-			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED)
+			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
+			     FS_ERROR)
 
 /* Extra flags that may be reported with event or control handling of events */
 #define ALL_FSNOTIFY_FLAGS  (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \
@@ -136,6 +144,7 @@ struct mem_cgroup;
  * @dir:	optional directory associated with event -
  *		if @file_name is not NULL, this is the directory that
  *		@file_name is relative to.
+ *		Either @inode or @dir must be non-NULL.
  * @file_name:	optional file name associated with event
  * @cookie:	inotify rename cookie
  *
@@ -155,7 +164,7 @@ struct fsnotify_ops {
 			    const struct qstr *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
-	void (*free_event)(struct fsnotify_event *event);
+	void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event);
 	/* called on final put+free to free memory */
 	void (*free_mark)(struct fsnotify_mark *mark);
 };
@@ -238,6 +247,7 @@ struct fsnotify_group {
 			int flags;           /* flags from fanotify_init() */
 			int f_flags; /* event_f_flags from fanotify_init() */
 			struct ucounts *ucounts;
+			mempool_t error_events_pool;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
@@ -248,6 +258,14 @@ enum fsnotify_data_type {
 	FSNOTIFY_EVENT_NONE,
 	FSNOTIFY_EVENT_PATH,
 	FSNOTIFY_EVENT_INODE,
+	FSNOTIFY_EVENT_DENTRY,
+	FSNOTIFY_EVENT_ERROR,
+};
+
+struct fs_error_report {
+	int error;
+	struct inode *inode;
+	struct super_block *sb;
 };
 
 static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
@@ -255,8 +273,25 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 	switch (data_type) {
 	case FSNOTIFY_EVENT_INODE:
 		return (struct inode *)data;
+	case FSNOTIFY_EVENT_DENTRY:
+		return d_inode(data);
 	case FSNOTIFY_EVENT_PATH:
 		return d_inode(((const struct path *)data)->dentry);
+	case FSNOTIFY_EVENT_ERROR:
+		return ((struct fs_error_report *)data)->inode;
+	default:
+		return NULL;
+	}
+}
+
+static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_DENTRY:
+		/* Non const is needed for dget() */
+		return (struct dentry *)data;
+	case FSNOTIFY_EVENT_PATH:
+		return ((const struct path *)data)->dentry;
 	default:
 		return NULL;
 	}
@@ -273,6 +308,35 @@ static inline const struct path *fsnotify_data_path(const void *data,
 	}
 }
 
+static inline struct super_block *fsnotify_data_sb(const void *data,
+						   int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_INODE:
+		return ((struct inode *)data)->i_sb;
+	case FSNOTIFY_EVENT_DENTRY:
+		return ((struct dentry *)data)->d_sb;
+	case FSNOTIFY_EVENT_PATH:
+		return ((const struct path *)data)->dentry->d_sb;
+	case FSNOTIFY_EVENT_ERROR:
+		return ((struct fs_error_report *) data)->sb;
+	default:
+		return NULL;
+	}
+}
+
+static inline struct fs_error_report *fsnotify_data_error_report(
+							const void *data,
+							int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_ERROR:
+		return (struct fs_error_report *) data;
+	default:
+		return NULL;
+	}
+}
+
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
 	FSNOTIFY_OBJ_TYPE_PARENT,
@@ -482,16 +546,30 @@ extern int fsnotify_fasync(int fd, struct file *file, int on);
 extern void fsnotify_destroy_event(struct fsnotify_group *group,
 				   struct fsnotify_event *event);
 /* attach the event to the group notification queue */
-extern int fsnotify_add_event(struct fsnotify_group *group,
-			      struct fsnotify_event *event,
-			      int (*merge)(struct fsnotify_group *,
-					   struct fsnotify_event *),
-			      void (*insert)(struct fsnotify_group *,
-					     struct fsnotify_event *));
+extern int fsnotify_insert_event(struct fsnotify_group *group,
+				 struct fsnotify_event *event,
+				 int (*merge)(struct fsnotify_group *,
+					      struct fsnotify_event *),
+				 void (*insert)(struct fsnotify_group *,
+						struct fsnotify_event *));
+
+static inline int fsnotify_add_event(struct fsnotify_group *group,
+				     struct fsnotify_event *event,
+				     int (*merge)(struct fsnotify_group *,
+						  struct fsnotify_event *))
+{
+	return fsnotify_insert_event(group, event, merge, NULL);
+}
+
 /* Queue overflow event to a notification group */
 static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
 {
-	fsnotify_add_event(group, group->overflow_event, NULL, NULL);
+	fsnotify_add_event(group, group->overflow_event, NULL);
+}
+
+static inline bool fsnotify_is_overflow_event(u32 mask)
+{
+	return mask & FS_Q_OVERFLOW;
 }
 
 static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)

include/uapi/linux/fanotify.h

@@ -20,6 +20,7 @@
 #define FAN_OPEN_EXEC		0x00001000	/* File was opened for exec */
 
 #define FAN_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define FAN_FS_ERROR		0x00008000	/* Filesystem error */
 
 #define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
 #define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
@@ -125,6 +126,7 @@ struct fanotify_event_metadata {
 #define FAN_EVENT_INFO_TYPE_DFID_NAME	2
 #define FAN_EVENT_INFO_TYPE_DFID	3
 #define FAN_EVENT_INFO_TYPE_PIDFD	4
+#define FAN_EVENT_INFO_TYPE_ERROR	5
 
 /* Variable length info record following event metadata */
 struct fanotify_event_info_header {
@@ -159,6 +161,12 @@ struct fanotify_event_info_pidfd {
 	__s32 pidfd;
 };
 
+struct fanotify_event_info_error {
+	struct fanotify_event_info_header hdr;
+	__s32 error;
+	__u32 error_count;
+};
+
 struct fanotify_response {
 	__s32 fd;
 	__u32 response;

kernel/audit_fsnotify.c

@@ -160,8 +160,7 @@ static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
 
 	audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
 
-	if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) ||
-	    WARN_ON_ONCE(!inode))
+	if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group))
 		return 0;
 
 	if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {

kernel/audit_watch.c

@@ -473,8 +473,7 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
 
 	parent = container_of(inode_mark, struct audit_parent, mark);
 
-	if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) ||
-	    WARN_ON_ONCE(!inode))
+	if (WARN_ON_ONCE(inode_mark->group != audit_watch_group))
 		return 0;
 
 	if (mask & (FS_CREATE|FS_MOVED_TO) && inode)

samples/Kconfig

@@ -120,6 +120,15 @@ config SAMPLE_CONNECTOR
 	  with it.
 	  See also Documentation/driver-api/connector.rst
 
+config SAMPLE_FANOTIFY_ERROR
+	bool "Build fanotify error monitoring sample"
+	depends on FANOTIFY && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  When enabled, this builds an example code that uses the
+	  FAN_FS_ERROR fanotify mechanism to monitor filesystem
+	  errors.
+	  See also Documentation/admin-guide/filesystem-monitoring.rst.
+
 config SAMPLE_HIDRAW
 	bool "hidraw sample"
 	depends on CC_CAN_LINK && HEADERS_INSTALL

samples/Makefile

@@ -5,6 +5,7 @@ subdir-$(CONFIG_SAMPLE_AUXDISPLAY)	+= auxdisplay
 subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs
 obj-$(CONFIG_SAMPLE_CONFIGFS)		+= configfs/
 obj-$(CONFIG_SAMPLE_CONNECTOR)		+= connector/
+obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR)	+= fanotify/
 subdir-$(CONFIG_SAMPLE_HIDRAW)		+= hidraw
 obj-$(CONFIG_SAMPLE_HW_BREAKPOINT)	+= hw_breakpoint/
 obj-$(CONFIG_SAMPLE_KDB)		+= kdb/

samples/fanotify/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+userprogs-always-y += fs-monitor
+
+userccflags += -I usr/include -Wall
+

samples/fanotify/fs-monitor.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2021, Collabora Ltd.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <err.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <sys/fanotify.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef FAN_FS_ERROR
+#define FAN_FS_ERROR		0x00008000
+#define FAN_EVENT_INFO_TYPE_ERROR	5
+
+struct fanotify_event_info_error {
+	struct fanotify_event_info_header hdr;
+	__s32 error;
+	__u32 error_count;
+};
+#endif
+
+#ifndef FILEID_INO32_GEN
+#define FILEID_INO32_GEN	1
+#endif
+
+#ifndef FILEID_INVALID
+#define	FILEID_INVALID		0xff
+#endif
+
+static void print_fh(struct file_handle *fh)
+{
+	int i;
+	uint32_t *h = (uint32_t *) fh->f_handle;
+
+	printf("\tfh: ");
+	for (i = 0; i < fh->handle_bytes; i++)
+		printf("%hhx", fh->f_handle[i]);
+	printf("\n");
+
+	printf("\tdecoded fh: ");
+	if (fh->handle_type == FILEID_INO32_GEN)
+		printf("inode=%u gen=%u\n", h[0], h[1]);
+	else if (fh->handle_type == FILEID_INVALID && !fh->handle_bytes)
+		printf("Type %d (Superblock error)\n", fh->handle_type);
+	else
+		printf("Type %d (Unknown)\n", fh->handle_type);
+
+}
+
+static void handle_notifications(char *buffer, int len)
+{
+	struct fanotify_event_metadata *event =
+		(struct fanotify_event_metadata *) buffer;
+	struct fanotify_event_info_header *info;
+	struct fanotify_event_info_error *err;
+	struct fanotify_event_info_fid *fid;
+	int off;
+
+	for (; FAN_EVENT_OK(event, len); event = FAN_EVENT_NEXT(event, len)) {
+
+		if (event->mask != FAN_FS_ERROR) {
+			printf("unexpected FAN MARK: %llx\n",
+							(unsigned long long)event->mask);
+			goto next_event;
+		}
+
+		if (event->fd != FAN_NOFD) {
+			printf("Unexpected fd (!= FAN_NOFD)\n");
+			goto next_event;
+		}
+
+		printf("FAN_FS_ERROR (len=%d)\n", event->event_len);
+
+		for (off = sizeof(*event) ; off < event->event_len;
+		     off += info->len) {
+			info = (struct fanotify_event_info_header *)
+				((char *) event + off);
+
+			switch (info->info_type) {
+			case FAN_EVENT_INFO_TYPE_ERROR:
+				err = (struct fanotify_event_info_error *) info;
+
+				printf("\tGeneric Error Record: len=%d\n",
+				       err->hdr.len);
+				printf("\terror: %d\n", err->error);
+				printf("\terror_count: %d\n", err->error_count);
+				break;
+
+			case FAN_EVENT_INFO_TYPE_FID:
+				fid = (struct fanotify_event_info_fid *) info;
+
+				printf("\tfsid: %x%x\n",
+				       fid->fsid.val[0], fid->fsid.val[1]);
+				print_fh((struct file_handle *) &fid->handle);
+				break;
+
+			default:
+				printf("\tUnknown info type=%d len=%d:\n",
+				       info->info_type, info->len);
+			}
+		}
+next_event:
+		printf("---\n\n");
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int fd;
+
+	char buffer[BUFSIZ];
+
+	if (argc < 2) {
+		printf("Missing path argument\n");
+		return 1;
+	}
+
+	fd = fanotify_init(FAN_CLASS_NOTIF|FAN_REPORT_FID, O_RDONLY);
+	if (fd < 0)
+		errx(1, "fanotify_init");
+
+	if (fanotify_mark(fd, FAN_MARK_ADD|FAN_MARK_FILESYSTEM,
+			  FAN_FS_ERROR, AT_FDCWD, argv[1])) {
+		errx(1, "fanotify_mark");
+	}
+
+	while (1) {
+		int n = read(fd, buffer, BUFSIZ);
+
+		if (n < 0)
+			errx(1, "read");
+
+		handle_notifications(buffer, n);
+	}
+
+	return 0;
+}