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
  ...

Author: torvalds

Documentation/admin-guide/filesystem-monitoring.rst

@@ -0,0 +1,78 @@
+.. 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);
 	}